diff --git a/Documentation/devicetree/bindings/arm/gic-v3.txt b/Documentation/devicetree/bindings/arm/gic-v3.txt
index ddfade4..7803e77 100644
--- a/Documentation/devicetree/bindings/arm/gic-v3.txt
+++ b/Documentation/devicetree/bindings/arm/gic-v3.txt
@@ -57,6 +57,8 @@
 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 @@
 		gic-its@2c200000 {
 			compatible = "arm,gic-v3-its";
 			msi-controller;
+			#msi-cells = <1>;
 			reg = <0x0 0x2c200000 0 0x200000>;
 		};
 	};
@@ -107,12 +110,14 @@
 		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 a8274ea..b8e41c1 100644
--- a/Documentation/devicetree/bindings/arm/idle-states.txt
+++ b/Documentation/devicetree/bindings/arm/idle-states.txt
@@ -497,7 +497,7 @@
 	};
 
 	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 5788d5c..82d40e2 100644
--- a/Documentation/devicetree/bindings/gpio/gpio.txt
+++ b/Documentation/devicetree/bindings/gpio/gpio.txt
@@ -16,7 +16,9 @@
 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 c593357..4a3679d 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 @@
 
   - 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 d8ef5bf..7fab84b 100644
--- a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
+++ b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
@@ -7,7 +7,8 @@
 
 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 32aa26f..acbcb45 100644
--- a/Documentation/devicetree/bindings/regulator/pbias-regulator.txt
+++ b/Documentation/devicetree/bindings/regulator/pbias-regulator.txt
@@ -2,7 +2,12 @@
 
 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 dcefc43..6160ffb 100644
--- a/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
+++ b/Documentation/devicetree/bindings/spi/spi-mt65xx.txt
@@ -15,17 +15,18 @@
 - 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 @@
 	#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 8a49362..41b817f 100644
--- a/Documentation/devicetree/bindings/thermal/thermal.txt
+++ b/Documentation/devicetree/bindings/thermal/thermal.txt
@@ -55,19 +55,11 @@
 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 @@
 			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 @@
 			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 @@
 	 */
 	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 d71ef07..a057b75 100644
--- a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
+++ b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
@@ -6,6 +6,7 @@
 	"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 ac5f0c3..82d2ac9 100644
--- a/Documentation/devicetree/bindings/vendor-prefixes.txt
+++ b/Documentation/devicetree/bindings/vendor-prefixes.txt
@@ -203,6 +203,7 @@
 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/gpio/board.txt b/Documentation/gpio/board.txt
index b80606d..f59c43b 100644
--- a/Documentation/gpio/board.txt
+++ b/Documentation/gpio/board.txt
@@ -21,8 +21,8 @@
 device tree bindings for your controller.
 
 GPIOs mappings are defined in the consumer device's node, in a property named
-<function>-gpios, where <function> is the function the driver will request
-through gpiod_get(). For example:
+either <function>-gpios or <function>-gpio, where <function> is the function
+the driver will request through gpiod_get(). For example:
 
 	foo_device {
 		compatible = "acme,foo";
@@ -31,7 +31,7 @@
 			    <&gpio 16 GPIO_ACTIVE_HIGH>, /* green */
 			    <&gpio 17 GPIO_ACTIVE_HIGH>; /* blue */
 
-		power-gpios = <&gpio 1 GPIO_ACTIVE_LOW>;
+		power-gpio = <&gpio 1 GPIO_ACTIVE_LOW>;
 	};
 
 This property will make GPIOs 15, 16 and 17 available to the driver under the
@@ -39,15 +39,24 @@
 
 	struct gpio_desc *red, *green, *blue, *power;
 
-	red = gpiod_get_index(dev, "led", 0);
-	green = gpiod_get_index(dev, "led", 1);
-	blue = gpiod_get_index(dev, "led", 2);
+	red = gpiod_get_index(dev, "led", 0, GPIOD_OUT_HIGH);
+	green = gpiod_get_index(dev, "led", 1, GPIOD_OUT_HIGH);
+	blue = gpiod_get_index(dev, "led", 2, GPIOD_OUT_HIGH);
 
-	power = gpiod_get(dev, "power");
+	power = gpiod_get(dev, "power", GPIOD_OUT_HIGH);
 
 The led GPIOs will be active-high, while the power GPIO will be active-low (i.e.
 gpiod_is_active_low(power) will be true).
 
+The second parameter of the gpiod_get() functions, the con_id string, has to be
+the <function>-prefix of the GPIO suffixes ("gpios" or "gpio", automatically
+looked up by the gpiod functions internally) used in the device tree. With above
+"led-gpios" example, use the prefix without the "-" as con_id parameter: "led".
+
+Internally, the GPIO subsystem prefixes the GPIO suffix ("gpios" or "gpio")
+with the string passed in con_id to get the resulting string
+(snprintf(... "%s-%s", con_id, gpio_suffixes[]).
+
 ACPI
 ----
 ACPI also supports function names for GPIOs in a similar fashion to DT.
@@ -142,13 +151,14 @@
 
 	struct gpio_desc *red, *green, *blue, *power;
 
-	red = gpiod_get_index(dev, "led", 0);
-	green = gpiod_get_index(dev, "led", 1);
-	blue = gpiod_get_index(dev, "led", 2);
+	red = gpiod_get_index(dev, "led", 0, GPIOD_OUT_HIGH);
+	green = gpiod_get_index(dev, "led", 1, GPIOD_OUT_HIGH);
+	blue = gpiod_get_index(dev, "led", 2, GPIOD_OUT_HIGH);
 
-	power = gpiod_get(dev, "power");
-	gpiod_direction_output(power, 1);
+	power = gpiod_get(dev, "power", GPIOD_OUT_HIGH);
 
-Since the "power" GPIO is mapped as active-low, its actual signal will be 0
-after this code. Contrary to the legacy integer GPIO interface, the active-low
-property is handled during mapping and is thus transparent to GPIO consumers.
+Since the "led" GPIOs are mapped as active-high, this example will switch their
+signals to 1, i.e. enabling the LEDs. And for the "power" GPIO, which is mapped
+as active-low, its actual signal will be 0 after this code. Contrary to the legacy
+integer GPIO interface, the active-low property is handled during mapping and is
+thus transparent to GPIO consumers.
diff --git a/Documentation/gpio/consumer.txt b/Documentation/gpio/consumer.txt
index a206639..e000502 100644
--- a/Documentation/gpio/consumer.txt
+++ b/Documentation/gpio/consumer.txt
@@ -39,6 +39,9 @@
 					  const char *con_id, unsigned int idx,
 					  enum gpiod_flags flags)
 
+For a more detailed description of the con_id parameter in the DeviceTree case
+see Documentation/gpio/board.txt
+
 The flags parameter is used to optionally specify a direction and initial value
 for the GPIO. Values can be:
 
diff --git a/Documentation/hwmon/nct6775 b/Documentation/hwmon/nct6775
index f0dd3d2..76add4c 100644
--- a/Documentation/hwmon/nct6775
+++ b/Documentation/hwmon/nct6775
@@ -32,6 +32,10 @@
     Prefix: 'nct6792'
     Addresses scanned: ISA address retrieved from Super I/O registers
     Datasheet: Available from Nuvoton upon request
+  * Nuvoton NCT6793D
+    Prefix: 'nct6793'
+    Addresses scanned: ISA address retrieved from Super I/O registers
+    Datasheet: Available from Nuvoton upon request
 
 Authors:
         Guenter Roeck <linux@roeck-us.net>
diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt
new file mode 100644
index 0000000..031ef4a
--- /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/static-keys.txt b/Documentation/static-keys.txt
index f4cb0b2..477927b 100644
--- a/Documentation/static-keys.txt
+++ b/Documentation/static-keys.txt
@@ -15,8 +15,8 @@
 
 DEFINE_STATIC_KEY_TRUE(key);
 DEFINE_STATIC_KEY_FALSE(key);
-static_key_likely()
-statick_key_unlikely()
+static_branch_likely()
+static_branch_unlikely()
 
 0) Abstract
 
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
index 6294b51..809ab6e 100644
--- a/Documentation/sysctl/net.txt
+++ b/Documentation/sysctl/net.txt
@@ -54,13 +54,15 @@
 --------------
 
 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 c3797b5..a1ce223 100644
--- a/Documentation/thermal/power_allocator.txt
+++ b/Documentation/thermal/power_allocator.txt
@@ -4,7 +4,7 @@
 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 7ba7ab7..9f6685f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -615,9 +615,8 @@
 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 @@
 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 @@
 
 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
@@ -6452,11 +6457,11 @@
 LTP (Linux Test Project)
 M:	Mike Frysinger <vapier@gentoo.org>
 M:	Cyril Hrubis <chrubis@suse.cz>
-M:	Wanlong Gao <gaowanlong@cn.fujitsu.com>
+M:	Wanlong Gao <wanlong.gao@gmail.com>
 M:	Jan Stancek <jstancek@redhat.com>
 M:	Stanislav Kholmanskikh <stanislav.kholmanskikh@oracle.com>
 M:	Alexey Kodanev <alexey.kodanev@oracle.com>
-L:	ltp-list@lists.sourceforge.net (subscribers-only)
+L:	ltp@lists.linux.it (subscribers-only)
 W:	http://linux-test-project.github.io/
 T:	git git://github.com/linux-test-project/ltp.git
 S:	Maintained
@@ -8500,7 +8505,6 @@
 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 @@
 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/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:	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 @@
 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 @@
 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 @@
 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 1a132ea..84f4b31 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 3
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
diff --git a/arch/alpha/include/asm/io.h b/arch/alpha/include/asm/io.h
index f05bdb4..ff40491 100644
--- a/arch/alpha/include/asm/io.h
+++ b/arch/alpha/include/asm/io.h
@@ -297,7 +297,9 @@
 					     unsigned long size)
 {
 	return ioremap(offset, size);
-} 
+}
+
+#define ioremap_uc ioremap_nocache
 
 static inline void iounmap(volatile void __iomem *addr)
 {
diff --git a/arch/alpha/kernel/irq.c b/arch/alpha/kernel/irq.c
index 2804648..2d6efcf 100644
--- a/arch/alpha/kernel/irq.c
+++ b/arch/alpha/kernel/irq.c
@@ -117,6 +117,6 @@
 	}
 
 	irq_enter();
-	generic_handle_irq_desc(irq, desc);
+	generic_handle_irq_desc(desc);
 	irq_exit();
 }
diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c
index cded02c..5f387ee 100644
--- a/arch/alpha/kernel/pci.c
+++ b/arch/alpha/kernel/pci.c
@@ -242,7 +242,12 @@
 
 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/alpha/lib/udelay.c b/arch/alpha/lib/udelay.c
index 69d52aa..f2d81ff 100644
--- a/arch/alpha/lib/udelay.c
+++ b/arch/alpha/lib/udelay.c
@@ -30,6 +30,7 @@
 		"	bgt %0,1b"
 		: "=&r" (tmp), "=r" (loops) : "1"(loops));
 }
+EXPORT_SYMBOL(__delay);
 
 #ifdef CONFIG_SMP
 #define LPJ	 cpu_data[smp_processor_id()].loops_per_jiffy
diff --git a/arch/arc/kernel/mcip.c b/arch/arc/kernel/mcip.c
index d9e44b6..4ffd185 100644
--- a/arch/arc/kernel/mcip.c
+++ b/arch/arc/kernel/mcip.c
@@ -252,7 +252,7 @@
 
 static int idu_first_irq;
 
-static void idu_cascade_isr(unsigned int __core_irq, struct irq_desc *desc)
+static void idu_cascade_isr(struct irq_desc *desc)
 {
 	struct irq_domain *domain = irq_desc_get_handler_data(desc);
 	unsigned int core_irq = irq_desc_get_irq(desc);
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 7451b44..2c2b28e 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -54,6 +54,14 @@
 LD		+= -EL
 endif
 
+#
+# The Scalar Replacement of Aggregates (SRA) optimization pass in GCC 4.9 and
+# later may result in code being generated that handles signed short and signed
+# char struct members incorrectly. So disable it.
+# (https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65932)
+#
+KBUILD_CFLAGS	+= $(call cc-option,-fno-ipa-sra)
+
 # This selects which instruction set is used.
 # Note that GCC does not numerically define an architecture version
 # macro, but instead defines a whole series of macros which makes
diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c
index 96dabcb..996aed3 100644
--- a/arch/arm/common/it8152.c
+++ b/arch/arm/common/it8152.c
@@ -95,7 +95,7 @@
 	}
 }
 
-void it8152_irq_demux(unsigned int irq, struct irq_desc *desc)
+void it8152_irq_demux(struct irq_desc *desc)
 {
        int bits_pd, bits_lp, bits_ld;
        int i;
diff --git a/arch/arm/common/locomo.c b/arch/arm/common/locomo.c
index 304adea..0e97b4b 100644
--- a/arch/arm/common/locomo.c
+++ b/arch/arm/common/locomo.c
@@ -138,7 +138,7 @@
 	},
 };
 
-static void locomo_handler(unsigned int __irq, struct irq_desc *desc)
+static void locomo_handler(struct irq_desc *desc)
 {
 	struct locomo *lchip = irq_desc_get_chip_data(desc);
 	int req, i;
diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index 4f29025..3d22494 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -196,10 +196,8 @@
  * active IRQs causes the interrupt output to pulse, the upper levels
  * will call us again if there are more interrupts to process.
  */
-static void
-sa1111_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void sa1111_irq_handler(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
 	unsigned int stat0, stat1, i;
 	struct sa1111 *sachip = irq_desc_get_handler_data(desc);
 	void __iomem *mapbase = sachip->base + SA1111_INTC;
@@ -214,7 +212,7 @@
 	sa1111_writel(stat1, mapbase + SA1111_INTSTATCLR1);
 
 	if (stat0 == 0 && stat1 == 0) {
-		do_bad_IRQ(irq, desc);
+		do_bad_IRQ(desc);
 		return;
 	}
 
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 7bbf325..b2bc8e1 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -491,11 +491,6 @@
 #endif
 	.endm
 
-	.macro	uaccess_save_and_disable, tmp
-	uaccess_save \tmp
-	uaccess_disable \tmp
-	.endm
-
 	.irp	c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
 	.macro	ret\c, reg
 #if __LINUX_ARM_ARCH__ < 6
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index b274bde..e7335a9 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -40,6 +40,7 @@
 		"2:\t.asciz " #__file "\n" 			\
 		".popsection\n" 				\
 		".pushsection __bug_table,\"a\"\n"		\
+		".align 2\n"					\
 		"3:\t.word 1b, 2b\n"				\
 		"\t.hword " #__line ", 0\n"			\
 		".popsection");					\
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index e878129..fc8ba16 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -12,6 +12,7 @@
 
 #ifndef __ASSEMBLY__
 #include <asm/barrier.h>
+#include <asm/thread_info.h>
 #endif
 
 /*
@@ -89,7 +90,8 @@
 
 	asm(
 	"mrc	p15, 0, %0, c3, c0	@ get domain"
-	 : "=r" (domain));
+	 : "=r" (domain)
+	 : "m" (current_thread_info()->cpu_domain));
 
 	return domain;
 }
@@ -98,7 +100,7 @@
 {
 	asm volatile(
 	"mcr	p15, 0, %0, c3, c0	@ set domain"
-	  : : "r" (val));
+	  : : "r" (val) : "memory");
 	isb();
 }
 
diff --git a/arch/arm/include/asm/hardware/it8152.h b/arch/arm/include/asm/hardware/it8152.h
index d36a73d7..076777f 100644
--- a/arch/arm/include/asm/hardware/it8152.h
+++ b/arch/arm/include/asm/hardware/it8152.h
@@ -106,7 +106,7 @@
 struct pci_dev;
 struct pci_sys_data;
 
-extern void it8152_irq_demux(unsigned int irq, struct irq_desc *desc);
+extern void it8152_irq_demux(struct irq_desc *desc);
 extern void it8152_init_irq(void);
 extern int it8152_pci_map_irq(const struct pci_dev *dev, u8 slot, u8 pin);
 extern int it8152_pci_setup(int nr, struct pci_sys_data *sys);
diff --git a/arch/arm/include/asm/hw_irq.h b/arch/arm/include/asm/hw_irq.h
index af79da4..9beb929 100644
--- a/arch/arm/include/asm/hw_irq.h
+++ b/arch/arm/include/asm/hw_irq.h
@@ -11,12 +11,6 @@
 	pr_crit("unexpected IRQ trap at vector %02x\n", irq);
 }
 
-void set_irq_flags(unsigned int irq, unsigned int flags);
-
-#define IRQF_VALID	(1 << 0)
-#define IRQF_PROBE	(1 << 1)
-#define IRQF_NOAUTOEN	(1 << 2)
-
 #define ARCH_IRQ_INIT_FLAGS	(IRQ_NOREQUEST | IRQ_NOPROBE)
 
 #endif
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index dcba0fa..c4072d9 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -29,21 +29,18 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#if defined(CONFIG_KVM_ARM_MAX_VCPUS)
-#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
-#else
-#define KVM_MAX_VCPUS 0
-#endif
-
 #define KVM_USER_MEM_SLOTS 32
 #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
 
 #include <kvm/arm_vgic.h>
 
+#define KVM_MAX_VCPUS VGIC_V2_MAX_CPUS
+
 u32 *kvm_vcpu_reg(struct kvm_vcpu *vcpu, u8 reg_num, u32 mode);
 int __attribute_const__ kvm_target_cpu(void);
 int kvm_reset_vcpu(struct kvm_vcpu *vcpu);
@@ -148,6 +145,7 @@
 
 struct kvm_vcpu_stat {
 	u32 halt_successful_poll;
+	u32 halt_attempted_poll;
 	u32 halt_wakeup;
 };
 
diff --git a/arch/arm/include/asm/mach/irq.h b/arch/arm/include/asm/mach/irq.h
index 2092ee1..de4634b 100644
--- a/arch/arm/include/asm/mach/irq.h
+++ b/arch/arm/include/asm/mach/irq.h
@@ -23,10 +23,10 @@
 /*
  * This is for easy migration, but should be changed in the source
  */
-#define do_bad_IRQ(irq,desc)				\
+#define do_bad_IRQ(desc)				\
 do {							\
 	raw_spin_lock(&desc->lock);			\
-	handle_bad_irq(irq, desc);			\
+	handle_bad_irq(desc);				\
 	raw_spin_unlock(&desc->lock);			\
 } while(0)
 
diff --git a/arch/arm/include/asm/thread_info.h b/arch/arm/include/asm/thread_info.h
index d0a1119..776757d 100644
--- a/arch/arm/include/asm/thread_info.h
+++ b/arch/arm/include/asm/thread_info.h
@@ -25,7 +25,6 @@
 struct task_struct;
 
 #include <asm/types.h>
-#include <asm/domain.h>
 
 typedef unsigned long mm_segment_t;
 
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index 5ff4826..2766183 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -79,26 +79,6 @@
 	handle_IRQ(irq, regs);
 }
 
-void set_irq_flags(unsigned int irq, unsigned int iflags)
-{
-	unsigned long clr = 0, set = IRQ_NOREQUEST | IRQ_NOPROBE | IRQ_NOAUTOEN;
-
-	if (irq >= nr_irqs) {
-		pr_err("Trying to set irq flags for IRQ%d\n", irq);
-		return;
-	}
-
-	if (iflags & IRQF_VALID)
-		clr |= IRQ_NOREQUEST;
-	if (iflags & IRQF_PROBE)
-		clr |= IRQ_NOPROBE;
-	if (!(iflags & IRQF_NOAUTOEN))
-		clr |= IRQ_NOAUTOEN;
-	/* Order is clear bits in "clr" then set bits in "set" */
-	irq_modify_status(irq, clr, set & ~clr);
-}
-EXPORT_SYMBOL_GPL(set_irq_flags);
-
 void __init init_IRQ(void)
 {
 	int ret;
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index a6ad93c..fd9eefc 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -259,15 +259,17 @@
 	if (err)
 		return err;
 
-	patch_text((void *)bpt->bpt_addr,
-		   *(unsigned int *)arch_kgdb_ops.gdb_bpt_instr);
+	/* Machine is already stopped, so we can use __patch_text() directly */
+	__patch_text((void *)bpt->bpt_addr,
+		     *(unsigned int *)arch_kgdb_ops.gdb_bpt_instr);
 
 	return err;
 }
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-	patch_text((void *)bpt->bpt_addr, *(unsigned int *)bpt->saved_instr);
+	/* Machine is already stopped, so we can use __patch_text() directly */
+	__patch_text((void *)bpt->bpt_addr, *(unsigned int *)bpt->saved_instr);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index a3089ba..7a7c4ce 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -226,6 +226,7 @@
 
 	memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
 
+#ifdef CONFIG_CPU_USE_DOMAINS
 	/*
 	 * Copy the initial value of the domain access control register
 	 * from the current thread: thread->addr_limit will have been
@@ -233,6 +234,7 @@
 	 * kernel/fork.c
 	 */
 	thread->cpu_domain = get_domain();
+#endif
 
 	if (likely(!(p->flags & PF_KTHREAD))) {
 		*childregs = *current_pt_regs();
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index b6cda06..7b8f214 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -343,15 +343,18 @@
 		 */
 		thumb = handler & 1;
 
-#if __LINUX_ARM_ARCH__ >= 7
 		/*
-		 * Clear the If-Then Thumb-2 execution state
-		 * ARM spec requires this to be all 000s in ARM mode
-		 * Snapdragon S4/Krait misbehaves on a Thumb=>ARM
-		 * signal transition without this.
+		 * Clear the If-Then Thumb-2 execution state.  ARM spec
+		 * requires this to be all 000s in ARM mode.  Snapdragon
+		 * S4/Krait misbehaves on a Thumb=>ARM signal transition
+		 * without this.
+		 *
+		 * We must do this whenever we are running on a Thumb-2
+		 * capable CPU, which includes ARMv6T2.  However, we elect
+		 * to always do this to simplify the code; this field is
+		 * marked UNK/SBZP for older architectures.
 		 */
 		cpsr &= ~PSR_IT_MASK;
-#endif
 
 		if (thumb) {
 			cpsr |= PSR_T_BIT;
diff --git a/arch/arm/kvm/Kconfig b/arch/arm/kvm/Kconfig
index bfb915d..210ecca 100644
--- a/arch/arm/kvm/Kconfig
+++ b/arch/arm/kvm/Kconfig
@@ -45,15 +45,4 @@
 	---help---
 	  Provides host support for ARM processors.
 
-config KVM_ARM_MAX_VCPUS
-	int "Number maximum supported virtual CPUs per VM"
-	depends on KVM_ARM_HOST
-	default 4
-	help
-	  Static number of max supported virtual CPUs per VM.
-
-	  If you choose a high number, the vcpu structures will be quite
-	  large, so only choose a reasonable number that you expect to
-	  actually use.
-
 endif # VIRTUALIZATION
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index ce404a5..dc017ad 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -446,7 +446,7 @@
 	 * Map the VGIC hardware resources before running a vcpu the first
 	 * time on this VM.
 	 */
-	if (unlikely(!vgic_ready(kvm))) {
+	if (unlikely(irqchip_in_kernel(kvm) && !vgic_ready(kvm))) {
 		ret = kvm_vgic_map_resources(kvm);
 		if (ret)
 			return ret;
diff --git a/arch/arm/kvm/interrupts_head.S b/arch/arm/kvm/interrupts_head.S
index 702740d..51a5950 100644
--- a/arch/arm/kvm/interrupts_head.S
+++ b/arch/arm/kvm/interrupts_head.S
@@ -515,8 +515,7 @@
 
 	mrc	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
 	str	r2, [vcpu, #VCPU_TIMER_CNTV_CTL]
-	bic	r2, #1			@ Clear ENABLE
-	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
+
 	isb
 
 	mrrc	p15, 3, rr_lo_hi(r2, r3), c14	@ CNTV_CVAL
@@ -529,6 +528,9 @@
 	mcrr	p15, 4, r2, r2, c14	@ CNTVOFF
 
 1:
+	mov	r2, #0			@ Clear ENABLE
+	mcr	p15, 0, r2, c14, c3, 1	@ CNTV_CTL
+
 	@ Allow physical timer/counter access for the host
 	mrc	p15, 4, r2, c14, c1, 0	@ CNTHCTL
 	orr	r2, r2, #(CNTHCTL_PL1PCEN | CNTHCTL_PL1PCTEN)
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index 7b42012..6984342 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -1792,8 +1792,10 @@
 		if (vma->vm_flags & VM_PFNMAP) {
 			gpa_t gpa = mem->guest_phys_addr +
 				    (vm_start - mem->userspace_addr);
-			phys_addr_t pa = (vma->vm_pgoff << PAGE_SHIFT) +
-					 vm_start - vma->vm_start;
+			phys_addr_t pa;
+
+			pa = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
+			pa += vm_start - vma->vm_start;
 
 			/* IO region dirty page logging not allowed */
 			if (memslot->flags & KVM_MEM_LOG_DIRTY_PAGES)
diff --git a/arch/arm/kvm/psci.c b/arch/arm/kvm/psci.c
index 4b94b51..ad6f642 100644
--- a/arch/arm/kvm/psci.c
+++ b/arch/arm/kvm/psci.c
@@ -126,7 +126,7 @@
 
 static unsigned long kvm_psci_vcpu_affinity_info(struct kvm_vcpu *vcpu)
 {
-	int i;
+	int i, matching_cpus = 0;
 	unsigned long mpidr;
 	unsigned long target_affinity;
 	unsigned long target_affinity_mask;
@@ -151,12 +151,16 @@
 	 */
 	kvm_for_each_vcpu(i, tmp, kvm) {
 		mpidr = kvm_vcpu_get_mpidr_aff(tmp);
-		if (((mpidr & target_affinity_mask) == target_affinity) &&
-		    !tmp->arch.pause) {
-			return PSCI_0_2_AFFINITY_LEVEL_ON;
+		if ((mpidr & target_affinity_mask) == target_affinity) {
+			matching_cpus++;
+			if (!tmp->arch.pause)
+				return PSCI_0_2_AFFINITY_LEVEL_ON;
 		}
 	}
 
+	if (!matching_cpus)
+		return PSCI_RET_INVALID_PARAMS;
+
 	return PSCI_0_2_AFFINITY_LEVEL_OFF;
 }
 
diff --git a/arch/arm/mach-dove/irq.c b/arch/arm/mach-dove/irq.c
index 305d7c6..bfb3703 100644
--- a/arch/arm/mach-dove/irq.c
+++ b/arch/arm/mach-dove/irq.c
@@ -69,14 +69,14 @@
 	.irq_ack	= pmu_irq_ack,
 };
 
-static void pmu_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void pmu_irq_handler(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
 	unsigned long cause = readl(PMU_INTERRUPT_CAUSE);
+	unsigned int irq;
 
 	cause &= readl(PMU_INTERRUPT_MASK);
 	if (cause == 0) {
-		do_bad_IRQ(irq, desc);
+		do_bad_IRQ(desc);
 		return;
 	}
 
diff --git a/arch/arm/mach-footbridge/isa-irq.c b/arch/arm/mach-footbridge/isa-irq.c
index fcd79bc..c01fca1 100644
--- a/arch/arm/mach-footbridge/isa-irq.c
+++ b/arch/arm/mach-footbridge/isa-irq.c
@@ -87,13 +87,12 @@
 	.irq_unmask	= isa_unmask_pic_hi_irq,
 };
 
-static void
-isa_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void isa_irq_handler(struct irq_desc *desc)
 {
 	unsigned int isa_irq = *(unsigned char *)PCIIACK_BASE;
 
 	if (isa_irq < _ISA_IRQ(0) || isa_irq >= _ISA_IRQ(16)) {
-		do_bad_IRQ(isa_irq, desc);
+		do_bad_IRQ(desc);
 		return;
 	}
 
diff --git a/arch/arm/mach-gemini/gpio.c b/arch/arm/mach-gemini/gpio.c
index 220333e..2478d9f 100644
--- a/arch/arm/mach-gemini/gpio.c
+++ b/arch/arm/mach-gemini/gpio.c
@@ -126,7 +126,7 @@
 	return 0;
 }
 
-static void gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void gpio_irq_handler(struct irq_desc *desc)
 {
 	unsigned int port = (unsigned int)irq_desc_get_handler_data(desc);
 	unsigned int gpio_irq_no, irq_stat;
diff --git a/arch/arm/mach-imx/3ds_debugboard.c b/arch/arm/mach-imx/3ds_debugboard.c
index 45903be..16496a0 100644
--- a/arch/arm/mach-imx/3ds_debugboard.c
+++ b/arch/arm/mach-imx/3ds_debugboard.c
@@ -85,7 +85,7 @@
 	.resource = smsc911x_resources,
 };
 
-static void mxc_expio_irq_handler(u32 irq, struct irq_desc *desc)
+static void mxc_expio_irq_handler(struct irq_desc *desc)
 {
 	u32 imr_val;
 	u32 int_valid;
diff --git a/arch/arm/mach-imx/mach-mx31ads.c b/arch/arm/mach-imx/mach-mx31ads.c
index 2c08535..2b147e4 100644
--- a/arch/arm/mach-imx/mach-mx31ads.c
+++ b/arch/arm/mach-imx/mach-mx31ads.c
@@ -154,7 +154,7 @@
 	imx31_add_imx_uart0(&uart_pdata);
 }
 
-static void mx31ads_expio_irq_handler(u32 irq, struct irq_desc *desc)
+static void mx31ads_expio_irq_handler(struct irq_desc *desc)
 {
 	u32 imr_val;
 	u32 int_valid;
diff --git a/arch/arm/mach-iop13xx/msi.c b/arch/arm/mach-iop13xx/msi.c
index 9f89e76..f6235b2 100644
--- a/arch/arm/mach-iop13xx/msi.c
+++ b/arch/arm/mach-iop13xx/msi.c
@@ -91,7 +91,7 @@
 	write_imipr_3,
 };
 
-static void iop13xx_msi_handler(unsigned int irq, struct irq_desc *desc)
+static void iop13xx_msi_handler(struct irq_desc *desc)
 {
 	int i, j;
 	unsigned long status;
diff --git a/arch/arm/mach-lpc32xx/irq.c b/arch/arm/mach-lpc32xx/irq.c
index cce4cef..2ae431e 100644
--- a/arch/arm/mach-lpc32xx/irq.c
+++ b/arch/arm/mach-lpc32xx/irq.c
@@ -370,7 +370,7 @@
 	.irq_set_wake = lpc32xx_irq_wake
 };
 
-static void lpc32xx_sic1_handler(unsigned int irq, struct irq_desc *desc)
+static void lpc32xx_sic1_handler(struct irq_desc *desc)
 {
 	unsigned long ints = __raw_readl(LPC32XX_INTC_STAT(LPC32XX_SIC1_BASE));
 
@@ -383,7 +383,7 @@
 	}
 }
 
-static void lpc32xx_sic2_handler(unsigned int irq, struct irq_desc *desc)
+static void lpc32xx_sic2_handler(struct irq_desc *desc)
 {
 	unsigned long ints = __raw_readl(LPC32XX_INTC_STAT(LPC32XX_SIC2_BASE));
 
diff --git a/arch/arm/mach-netx/generic.c b/arch/arm/mach-netx/generic.c
index 6373e2b..842302d 100644
--- a/arch/arm/mach-netx/generic.c
+++ b/arch/arm/mach-netx/generic.c
@@ -69,8 +69,7 @@
 #define DEBUG_IRQ(fmt...)	while (0) {}
 #endif
 
-static void
-netx_hif_demux_handler(unsigned int irq_unused, struct irq_desc *desc)
+static void netx_hif_demux_handler(struct irq_desc *desc)
 {
 	unsigned int irq = NETX_IRQ_HIF_CHAINED(0);
 	unsigned int stat;
diff --git a/arch/arm/mach-omap1/fpga.c b/arch/arm/mach-omap1/fpga.c
index dfec671..39e20d0 100644
--- a/arch/arm/mach-omap1/fpga.c
+++ b/arch/arm/mach-omap1/fpga.c
@@ -87,7 +87,7 @@
 	fpga_ack_irq(d);
 }
 
-static void innovator_fpga_IRQ_demux(unsigned int irq, struct irq_desc *desc)
+static void innovator_fpga_IRQ_demux(struct irq_desc *desc)
 {
 	u32 stat;
 	int fpga_irq;
diff --git a/arch/arm/mach-omap2/prm_common.c b/arch/arm/mach-omap2/prm_common.c
index 257e98c..3fc2cbe 100644
--- a/arch/arm/mach-omap2/prm_common.c
+++ b/arch/arm/mach-omap2/prm_common.c
@@ -102,7 +102,7 @@
  * dispatched accordingly. Clearing of the wakeup events should be
  * done by the SoC specific individual handlers.
  */
-static void omap_prcm_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void omap_prcm_irq_handler(struct irq_desc *desc)
 {
 	unsigned long pending[OMAP_PRCM_MAX_NR_PENDING_REG];
 	unsigned long priority_pending[OMAP_PRCM_MAX_NR_PENDING_REG];
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index 70366b3..a3ebb51 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -496,7 +496,7 @@
 	.irq_unmask	= balloon3_unmask_irq,
 };
 
-static void balloon3_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void balloon3_irq_handler(struct irq_desc *desc)
 {
 	unsigned long pending = __raw_readl(BALLOON3_INT_CONTROL_REG) &
 					balloon3_irq_enabled;
diff --git a/arch/arm/mach-pxa/cm-x2xx-pci.c b/arch/arm/mach-pxa/cm-x2xx-pci.c
index 1fa79f1..3221ae1 100644
--- a/arch/arm/mach-pxa/cm-x2xx-pci.c
+++ b/arch/arm/mach-pxa/cm-x2xx-pci.c
@@ -29,13 +29,12 @@
 void __iomem *it8152_base_address;
 static int cmx2xx_it8152_irq_gpio;
 
-static void cmx2xx_it8152_irq_demux(unsigned int __irq, struct irq_desc *desc)
+static void cmx2xx_it8152_irq_demux(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
 	/* clear our parent irq */
 	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
-	it8152_irq_demux(irq, desc);
+	it8152_irq_demux(desc);
 }
 
 void __cmx2xx_pci_init_irq(int irq_gpio)
diff --git a/arch/arm/mach-pxa/lpd270.c b/arch/arm/mach-pxa/lpd270.c
index b070167..4823d97 100644
--- a/arch/arm/mach-pxa/lpd270.c
+++ b/arch/arm/mach-pxa/lpd270.c
@@ -120,7 +120,7 @@
 	.irq_unmask	= lpd270_unmask_irq,
 };
 
-static void lpd270_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void lpd270_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq;
 	unsigned long pending;
diff --git a/arch/arm/mach-pxa/pcm990-baseboard.c b/arch/arm/mach-pxa/pcm990-baseboard.c
index 9a0c8af..d8319b5 100644
--- a/arch/arm/mach-pxa/pcm990-baseboard.c
+++ b/arch/arm/mach-pxa/pcm990-baseboard.c
@@ -284,7 +284,7 @@
 	.irq_unmask	= pcm990_unmask_irq,
 };
 
-static void pcm990_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void pcm990_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq;
 	unsigned long pending;
diff --git a/arch/arm/mach-pxa/viper.c b/arch/arm/mach-pxa/viper.c
index 4841d6c..8ab2637 100644
--- a/arch/arm/mach-pxa/viper.c
+++ b/arch/arm/mach-pxa/viper.c
@@ -276,7 +276,7 @@
 			viper_irq_enabled_mask;
 }
 
-static void viper_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void viper_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq;
 	unsigned long pending;
diff --git a/arch/arm/mach-pxa/zeus.c b/arch/arm/mach-pxa/zeus.c
index 6f94dd7..30e62a3 100644
--- a/arch/arm/mach-pxa/zeus.c
+++ b/arch/arm/mach-pxa/zeus.c
@@ -105,7 +105,7 @@
 	return __raw_readw(ZEUS_CPLD_ISA_IRQ) & zeus_irq_enabled_mask;
 }
 
-static void zeus_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void zeus_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq;
 	unsigned long pending;
diff --git a/arch/arm/mach-rpc/ecard.c b/arch/arm/mach-rpc/ecard.c
index f726d4c..dc67a7f 100644
--- a/arch/arm/mach-rpc/ecard.c
+++ b/arch/arm/mach-rpc/ecard.c
@@ -551,8 +551,7 @@
 	}
 }
 
-static void
-ecard_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ecard_irq_handler(struct irq_desc *desc)
 {
 	ecard_t *ec;
 	int called = 0;
diff --git a/arch/arm/mach-s3c24xx/bast-irq.c b/arch/arm/mach-s3c24xx/bast-irq.c
index ced1ab86..2bb0896 100644
--- a/arch/arm/mach-s3c24xx/bast-irq.c
+++ b/arch/arm/mach-s3c24xx/bast-irq.c
@@ -100,9 +100,7 @@
 	.irq_ack	= bast_pc104_maskack
 };
 
-static void
-bast_irq_pc104_demux(unsigned int irq,
-		     struct irq_desc *desc)
+static void bast_irq_pc104_demux(struct irq_desc *desc)
 {
 	unsigned int stat;
 	unsigned int irqno;
diff --git a/arch/arm/mach-s3c64xx/common.c b/arch/arm/mach-s3c64xx/common.c
index fd63ecf..ddb30b8 100644
--- a/arch/arm/mach-s3c64xx/common.c
+++ b/arch/arm/mach-s3c64xx/common.c
@@ -388,22 +388,22 @@
 	}
 }
 
-static void s3c_irq_demux_eint0_3(unsigned int irq, struct irq_desc *desc)
+static void s3c_irq_demux_eint0_3(struct irq_desc *desc)
 {
 	s3c_irq_demux_eint(0, 3);
 }
 
-static void s3c_irq_demux_eint4_11(unsigned int irq, struct irq_desc *desc)
+static void s3c_irq_demux_eint4_11(struct irq_desc *desc)
 {
 	s3c_irq_demux_eint(4, 11);
 }
 
-static void s3c_irq_demux_eint12_19(unsigned int irq, struct irq_desc *desc)
+static void s3c_irq_demux_eint12_19(struct irq_desc *desc)
 {
 	s3c_irq_demux_eint(12, 19);
 }
 
-static void s3c_irq_demux_eint20_27(unsigned int irq, struct irq_desc *desc)
+static void s3c_irq_demux_eint20_27(struct irq_desc *desc)
 {
 	s3c_irq_demux_eint(20, 27);
 }
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index 6d237b4..8411985 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -166,7 +166,7 @@
  * ensure that the IRQ signal is deasserted before returning.  This
  * is rather unfortunate.
  */
-static void neponset_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void neponset_irq_handler(struct irq_desc *desc)
 {
 	struct neponset_drvdata *d = irq_desc_get_handler_data(desc);
 	unsigned int irr;
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index e626043..1a7815e 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1249,7 +1249,7 @@
 	struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev);
 	unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	dma_addr_t dma_addr, iova;
-	int i, ret = DMA_ERROR_CODE;
+	int i;
 
 	dma_addr = __alloc_iova(mapping, size);
 	if (dma_addr == DMA_ERROR_CODE)
@@ -1257,6 +1257,8 @@
 
 	iova = dma_addr;
 	for (i = 0; i < count; ) {
+		int ret;
+
 		unsigned int next_pfn = page_to_pfn(pages[i]) + 1;
 		phys_addr_t phys = page_to_phys(pages[i]);
 		unsigned int len, j;
diff --git a/arch/arm/nwfpe/entry.S b/arch/arm/nwfpe/entry.S
index 71df435..39c20af 100644
--- a/arch/arm/nwfpe/entry.S
+++ b/arch/arm/nwfpe/entry.S
@@ -95,9 +95,10 @@
 	reteq	r4			@ no, return failure
 
 next:
+	uaccess_enable r3
 .Lx1:	ldrt	r6, [r5], #4		@ get the next instruction and
 					@ increment PC
-
+	uaccess_disable r3
 	and	r2, r6, #0x0F000000	@ test for FP insns
 	teq	r2, #0x0C000000
 	teqne	r2, #0x0D000000
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index 79c33ec..7bd22d8 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -407,7 +407,7 @@
 	return 0;
 }
 
-static void gpio_irq_handler(unsigned __irq, struct irq_desc *desc)
+static void gpio_irq_handler(struct irq_desc *desc)
 {
 	struct orion_gpio_chip *ochip = irq_desc_get_handler_data(desc);
 	u32 cause, type;
diff --git a/arch/arm/xen/hypercall.S b/arch/arm/xen/hypercall.S
index f00e080..10fd99c 100644
--- a/arch/arm/xen/hypercall.S
+++ b/arch/arm/xen/hypercall.S
@@ -98,8 +98,23 @@
 	mov r1, r2
 	mov r2, r3
 	ldr r3, [sp, #8]
+	/*
+	 * Privcmd calls are issued by the userspace. We need to allow the
+	 * kernel to access the userspace memory before issuing the hypercall.
+	 */
+	uaccess_enable r4
+
+	/* r4 is loaded now as we use it as scratch register before */
 	ldr r4, [sp, #4]
 	__HVC(XEN_IMM)
+
+	/*
+	 * Disable userspace access from kernel. This is fine to do it
+	 * unconditionally as no set_fs(KERNEL_DS)/set_fs(get_ds()) is
+	 * called before.
+	 */
+	uaccess_disable r4
+
 	ldm sp!, {r4}
 	ret lr
 ENDPROC(privcmd_call);
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 7d95663..07d1811 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -32,6 +32,7 @@
 	select GENERIC_CLOCKEVENTS_BROADCAST
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
+	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
@@ -331,6 +332,22 @@
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_843419
+	bool "Cortex-A53: 843419: A load or store might access an incorrect address"
+	depends on MODULES
+	default y
+	help
+	  This option builds kernel modules using the large memory model in
+	  order to avoid the use of the ADRP instruction, which can cause
+	  a subsequent memory access to use an incorrect address on Cortex-A53
+	  parts up to r0p4.
+
+	  Note that the kernel itself must be linked with a version of ld
+	  which fixes potentially affected ADRP instructions through the
+	  use of veneers.
+
+	  If unsure, say Y.
+
 endmenu
 
 
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 15ff5b4..f9914d7 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -41,6 +41,10 @@
 
 CHECKFLAGS	+= -D__aarch64__
 
+ifeq ($(CONFIG_ARM64_ERRATUM_843419), y)
+CFLAGS_MODULE	+= -mcmodel=large
+endif
+
 # Default value
 head-y		:= arch/arm64/kernel/head.o
 
diff --git a/arch/arm64/boot/dts/mediatek/mt8173.dtsi b/arch/arm64/boot/dts/mediatek/mt8173.dtsi
index d18ee42..06a1564 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 a712bea..cc093a4 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/hardirq.h b/arch/arm64/include/asm/hardirq.h
index 2bb7009..a57601f 100644
--- a/arch/arm64/include/asm/hardirq.h
+++ b/arch/arm64/include/asm/hardirq.h
@@ -43,9 +43,4 @@
 	irq_err_count++;
 }
 
-/*
- * No arch-specific IRQ flags.
- */
-#define set_irq_flags(irq, flags)
-
 #endif /* __ASM_HARDIRQ_H */
diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h
index 7605e09..9694f26 100644
--- a/arch/arm64/include/asm/kvm_arm.h
+++ b/arch/arm64/include/asm/kvm_arm.h
@@ -95,6 +95,7 @@
 			 SCTLR_EL2_SA | SCTLR_EL2_I)
 
 /* TCR_EL2 Registers bits */
+#define TCR_EL2_RES1	((1 << 31) | (1 << 23))
 #define TCR_EL2_TBI	(1 << 20)
 #define TCR_EL2_PS	(7 << 16)
 #define TCR_EL2_PS_40B	(2 << 16)
@@ -106,9 +107,10 @@
 #define TCR_EL2_MASK	(TCR_EL2_TG0 | TCR_EL2_SH0 | \
 			 TCR_EL2_ORGN0 | TCR_EL2_IRGN0 | TCR_EL2_T0SZ)
 
-#define TCR_EL2_FLAGS	(TCR_EL2_PS_40B)
+#define TCR_EL2_FLAGS	(TCR_EL2_RES1 | TCR_EL2_PS_40B)
 
 /* VTCR_EL2 Registers bits */
+#define VTCR_EL2_RES1		(1 << 31)
 #define VTCR_EL2_PS_MASK	(7 << 16)
 #define VTCR_EL2_TG0_MASK	(1 << 14)
 #define VTCR_EL2_TG0_4K		(0 << 14)
@@ -147,7 +149,8 @@
  */
 #define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_64K | VTCR_EL2_SH0_INNER | \
 				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \
+				 VTCR_EL2_RES1)
 #define VTTBR_X		(38 - VTCR_EL2_T0SZ_40B)
 #else
 /*
@@ -158,7 +161,8 @@
  */
 #define VTCR_EL2_FLAGS		(VTCR_EL2_TG0_4K | VTCR_EL2_SH0_INNER | \
 				 VTCR_EL2_ORGN0_WBWA | VTCR_EL2_IRGN0_WBWA | \
-				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B)
+				 VTCR_EL2_SL0_LVL1 | VTCR_EL2_T0SZ_40B | \
+				 VTCR_EL2_RES1)
 #define VTTBR_X		(37 - VTCR_EL2_T0SZ_40B)
 #endif
 
@@ -168,7 +172,6 @@
 #define VTTBR_VMID_MASK	  (UL(0xFF) << VTTBR_VMID_SHIFT)
 
 /* Hyp System Trap Register */
-#define HSTR_EL2_TTEE	(1 << 16)
 #define HSTR_EL2_T(x)	(1 << x)
 
 /* Hyp Coproccessor Trap Register Shifts */
diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h
index 67fa0de..5e37710 100644
--- a/arch/arm64/include/asm/kvm_asm.h
+++ b/arch/arm64/include/asm/kvm_asm.h
@@ -53,9 +53,7 @@
 #define	IFSR32_EL2	25	/* Instruction Fault Status Register */
 #define	FPEXC32_EL2	26	/* Floating-Point Exception Control Register */
 #define	DBGVCR32_EL2	27	/* Debug Vector Catch Register */
-#define	TEECR32_EL1	28	/* ThumbEE Configuration Register */
-#define	TEEHBR32_EL1	29	/* ThumbEE Handler Base Register */
-#define	NR_SYS_REGS	30
+#define	NR_SYS_REGS	28
 
 /* 32bit mapping */
 #define c0_MPIDR	(MPIDR_EL1 * 2)	/* MultiProcessor ID Register */
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 415938d..ed03968 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -30,19 +30,16 @@
 
 #define __KVM_HAVE_ARCH_INTC_INITIALIZED
 
-#if defined(CONFIG_KVM_ARM_MAX_VCPUS)
-#define KVM_MAX_VCPUS CONFIG_KVM_ARM_MAX_VCPUS
-#else
-#define KVM_MAX_VCPUS 0
-#endif
-
 #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>
 
+#define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS
+
 #define KVM_VCPU_MAX_FEATURES 3
 
 int __attribute_const__ kvm_target_cpu(void);
@@ -195,6 +192,7 @@
 
 struct kvm_vcpu_stat {
 	u32 halt_successful_poll;
+	u32 halt_attempted_poll;
 	u32 halt_wakeup;
 };
 
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 6900b2d9..b0329be 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -26,13 +26,9 @@
  * Software defined PTE bits definition.
  */
 #define PTE_VALID		(_AT(pteval_t, 1) << 0)
+#define PTE_WRITE		(PTE_DBM)		 /* same as DBM (51) */
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
-#ifdef CONFIG_ARM64_HW_AFDBM
-#define PTE_WRITE		(PTE_DBM)		 /* same as DBM */
-#else
-#define PTE_WRITE		(_AT(pteval_t, 1) << 57)
-#endif
 #define PTE_PROT_NONE		(_AT(pteval_t, 1) << 58) /* only when !PTE_VALID */
 
 /*
@@ -146,7 +142,7 @@
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
-#define pte_hw_dirty(pte)	(!(pte_val(pte) & PTE_RDONLY))
+#define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
 #else
 #define pte_hw_dirty(pte)	(0)
 #endif
@@ -238,7 +234,7 @@
  * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via
  * the page fault mechanism. Checking the dirty status of a pte becomes:
  *
- *   PTE_DIRTY || !PTE_RDONLY
+ *   PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY)
  */
 static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep, pte_t pte)
@@ -503,7 +499,7 @@
 			      PTE_PROT_NONE | PTE_WRITE | PTE_TYPE_MASK;
 	/* preserve the hardware dirty information */
 	if (pte_hw_dirty(pte))
-		newprot |= PTE_DIRTY;
+		pte = pte_mkdirty(pte);
 	pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask);
 	return pte;
 }
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index 9b3b62a..cebf786 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -134,7 +134,7 @@
 				    unsigned long action, void *data)
 {
 	int cpu = (unsigned long)data;
-	if (action == CPU_ONLINE)
+	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
 		smp_call_function_single(cpu, clear_os_lock, NULL, 1);
 	return NOTIFY_OK;
 }
diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S
index a055be6..90d09ed 100644
--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -523,6 +523,11 @@
 	msr	hstr_el2, xzr			// Disable CP15 traps to EL2
 #endif
 
+	/* EL2 debug */
+	mrs	x0, pmcr_el0			// Disable debug access traps
+	ubfx	x0, x0, #11, #5			// to EL2 and allow access to
+	msr	mdcr_el2, x0			// all PMU counters from EL1
+
 	/* Stage-2 translation */
 	msr	vttbr_el2, xzr
 
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index c97040e..bba85c8 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -872,7 +872,7 @@
 						void *hcpu)
 {
 	int cpu = (long)hcpu;
-	if (action == CPU_ONLINE)
+	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
 		smp_call_function_single(cpu, hw_breakpoint_reset, NULL, 1);
 	return NOTIFY_OK;
 }
diff --git a/arch/arm64/kernel/module.c b/arch/arm64/kernel/module.c
index 67bf410..876eb8d 100644
--- a/arch/arm64/kernel/module.c
+++ b/arch/arm64/kernel/module.c
@@ -332,12 +332,14 @@
 			ovf = reloc_insn_imm(RELOC_OP_PREL, loc, val, 0, 21,
 					     AARCH64_INSN_IMM_ADR);
 			break;
+#ifndef CONFIG_ARM64_ERRATUM_843419
 		case R_AARCH64_ADR_PREL_PG_HI21_NC:
 			overflow_check = false;
 		case R_AARCH64_ADR_PREL_PG_HI21:
 			ovf = reloc_insn_imm(RELOC_OP_PAGE, loc, val, 12, 21,
 					     AARCH64_INSN_IMM_ADR);
 			break;
+#endif
 		case R_AARCH64_ADD_ABS_LO12_NC:
 		case R_AARCH64_LDST8_ABS_LO12_NC:
 			overflow_check = false;
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 948f0ad..71ef6dc 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -212,14 +212,32 @@
 
 /*
  * VFP save/restore code.
+ *
+ * We have to be careful with endianness, since the fpsimd context-switch
+ * code operates on 128-bit (Q) register values whereas the compat ABI
+ * uses an array of 64-bit (D) registers. Consequently, we need to swap
+ * the two halves of each Q register when running on a big-endian CPU.
  */
+union __fpsimd_vreg {
+	__uint128_t	raw;
+	struct {
+#ifdef __AARCH64EB__
+		u64	hi;
+		u64	lo;
+#else
+		u64	lo;
+		u64	hi;
+#endif
+	};
+};
+
 static int compat_preserve_vfp_context(struct compat_vfp_sigframe __user *frame)
 {
 	struct fpsimd_state *fpsimd = &current->thread.fpsimd_state;
 	compat_ulong_t magic = VFP_MAGIC;
 	compat_ulong_t size = VFP_STORAGE_SIZE;
 	compat_ulong_t fpscr, fpexc;
-	int err = 0;
+	int i, err = 0;
 
 	/*
 	 * Save the hardware registers to the fpsimd_state structure.
@@ -235,10 +253,15 @@
 	/*
 	 * Now copy the FP registers. Since the registers are packed,
 	 * we can copy the prefix we want (V0-V15) as it is.
-	 * FIXME: Won't work if big endian.
 	 */
-	err |= __copy_to_user(&frame->ufp.fpregs, fpsimd->vregs,
-			      sizeof(frame->ufp.fpregs));
+	for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) {
+		union __fpsimd_vreg vreg = {
+			.raw = fpsimd->vregs[i >> 1],
+		};
+
+		__put_user_error(vreg.lo, &frame->ufp.fpregs[i], err);
+		__put_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err);
+	}
 
 	/* Create an AArch32 fpscr from the fpsr and the fpcr. */
 	fpscr = (fpsimd->fpsr & VFP_FPSCR_STAT_MASK) |
@@ -263,7 +286,7 @@
 	compat_ulong_t magic = VFP_MAGIC;
 	compat_ulong_t size = VFP_STORAGE_SIZE;
 	compat_ulong_t fpscr;
-	int err = 0;
+	int i, err = 0;
 
 	__get_user_error(magic, &frame->magic, err);
 	__get_user_error(size, &frame->size, err);
@@ -273,12 +296,14 @@
 	if (magic != VFP_MAGIC || size != VFP_STORAGE_SIZE)
 		return -EINVAL;
 
-	/*
-	 * Copy the FP registers into the start of the fpsimd_state.
-	 * FIXME: Won't work if big endian.
-	 */
-	err |= __copy_from_user(fpsimd.vregs, frame->ufp.fpregs,
-				sizeof(frame->ufp.fpregs));
+	/* Copy the FP registers into the start of the fpsimd_state. */
+	for (i = 0; i < ARRAY_SIZE(frame->ufp.fpregs); i += 2) {
+		union __fpsimd_vreg vreg;
+
+		__get_user_error(vreg.lo, &frame->ufp.fpregs[i], err);
+		__get_user_error(vreg.hi, &frame->ufp.fpregs[i + 1], err);
+		fpsimd.vregs[i >> 1] = vreg.raw;
+	}
 
 	/* Extract the fpsr and the fpcr from the fpscr */
 	__get_user_error(fpscr, &frame->ufp.fpscr, err);
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index bfffe8f..5c7e920e 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -41,15 +41,4 @@
 	---help---
 	  Provides host support for ARM processors.
 
-config KVM_ARM_MAX_VCPUS
-	int "Number maximum supported virtual CPUs per VM"
-	depends on KVM_ARM_HOST
-	default 4
-	help
-	  Static number of max supported virtual CPUs per VM.
-
-	  If you choose a high number, the vcpu structures will be quite
-	  large, so only choose a reasonable number that you expect to
-	  actually use.
-
 endif # VIRTUALIZATION
diff --git a/arch/arm64/kvm/hyp.S b/arch/arm64/kvm/hyp.S
index 37c89ea..e583613 100644
--- a/arch/arm64/kvm/hyp.S
+++ b/arch/arm64/kvm/hyp.S
@@ -433,20 +433,13 @@
 	mrs	x5, ifsr32_el2
 	stp	x4, x5, [x3]
 
-	skip_fpsimd_state x8, 3f
+	skip_fpsimd_state x8, 2f
 	mrs	x6, fpexc32_el2
 	str	x6, [x3, #16]
-3:
-	skip_debug_state x8, 2f
+2:
+	skip_debug_state x8, 1f
 	mrs	x7, dbgvcr32_el2
 	str	x7, [x3, #24]
-2:
-	skip_tee_state x8, 1f
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
-	mrs	x4, teecr32_el1
-	mrs	x5, teehbr32_el1
-	stp	x4, x5, [x3]
 1:
 .endm
 
@@ -466,16 +459,9 @@
 	msr	dacr32_el2, x4
 	msr	ifsr32_el2, x5
 
-	skip_debug_state x8, 2f
+	skip_debug_state x8, 1f
 	ldr	x7, [x3, #24]
 	msr	dbgvcr32_el2, x7
-2:
-	skip_tee_state x8, 1f
-
-	add	x3, x2, #CPU_SYSREG_OFFSET(TEECR32_EL1)
-	ldp	x4, x5, [x3]
-	msr	teecr32_el1, x4
-	msr	teehbr32_el1, x5
 1:
 .endm
 
@@ -570,8 +556,6 @@
 	mrs	x3, cntv_ctl_el0
 	and	x3, x3, #3
 	str	w3, [x0, #VCPU_TIMER_CNTV_CTL]
-	bic	x3, x3, #1		// Clear Enable
-	msr	cntv_ctl_el0, x3
 
 	isb
 
@@ -579,6 +563,9 @@
 	str	x3, [x0, #VCPU_TIMER_CNTV_CVAL]
 
 1:
+	// Disable the virtual timer
+	msr	cntv_ctl_el0, xzr
+
 	// Allow physical timer/counter access for the host
 	mrs	x2, cnthctl_el2
 	orr	x2, x2, #3
@@ -753,6 +740,9 @@
 	// Guest context
 	add	x2, x0, #VCPU_CONTEXT
 
+	// We must restore the 32-bit state before the sysregs, thanks
+	// to Cortex-A57 erratum #852523.
+	restore_guest_32bit_state
 	bl __restore_sysregs
 
 	skip_debug_state x3, 1f
@@ -760,7 +750,6 @@
 	kern_hyp_va x3
 	bl	__restore_debug
 1:
-	restore_guest_32bit_state
 	restore_guest_regs
 
 	// That's it, no more messing around.
diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
index b41607d..d03d3af 100644
--- a/arch/arm64/kvm/sys_regs.c
+++ b/arch/arm64/kvm/sys_regs.c
@@ -272,7 +272,7 @@
 {
 	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg];
 
-	if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
+	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
 	return 0;
 }
@@ -314,7 +314,7 @@
 {
 	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg];
 
-	if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
+	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
 
 	return 0;
@@ -358,7 +358,7 @@
 {
 	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg];
 
-	if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
+	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
 	return 0;
 }
@@ -400,7 +400,7 @@
 {
 	__u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg];
 
-	if (copy_from_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0)
+	if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0)
 		return -EFAULT;
 	return 0;
 }
@@ -539,13 +539,6 @@
 	{ Op0(0b10), Op1(0b000), CRn(0b0111), CRm(0b1110), Op2(0b110),
 	  trap_dbgauthstatus_el1 },
 
-	/* TEECR32_EL1 */
-	{ Op0(0b10), Op1(0b010), CRn(0b0000), CRm(0b0000), Op2(0b000),
-	  NULL, reset_val, TEECR32_EL1, 0 },
-	/* TEEHBR32_EL1 */
-	{ Op0(0b10), Op1(0b010), CRn(0b0001), CRm(0b0000), Op2(0b000),
-	  NULL, reset_val, TEEHBR32_EL1, 0 },
-
 	/* MDCCSR_EL1 */
 	{ Op0(0b10), Op1(0b011), CRn(0b0000), CRm(0b0001), Op2(0b000),
 	  trap_raz_wi },
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 0bcc4bc..99224dc 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -100,7 +100,7 @@
 	if (IS_ENABLED(CONFIG_ZONE_DMA) &&
 	    dev->coherent_dma_mask <= DMA_BIT_MASK(32))
 		flags |= GFP_DMA;
-	if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) {
+	if (dev_get_cma_area(dev) && (flags & __GFP_WAIT)) {
 		struct page *page;
 		void *addr;
 
diff --git a/arch/avr32/mach-at32ap/extint.c b/arch/avr32/mach-at32ap/extint.c
index d51ff8f..96cabad 100644
--- a/arch/avr32/mach-at32ap/extint.c
+++ b/arch/avr32/mach-at32ap/extint.c
@@ -144,7 +144,7 @@
 	.irq_set_type	= eic_set_irq_type,
 };
 
-static void demux_eic_irq(unsigned int irq, struct irq_desc *desc)
+static void demux_eic_irq(struct irq_desc *desc)
 {
 	struct eic *eic = irq_desc_get_handler_data(desc);
 	unsigned long status, pending;
diff --git a/arch/avr32/mach-at32ap/pio.c b/arch/avr32/mach-at32ap/pio.c
index 157a5e0..4f61378 100644
--- a/arch/avr32/mach-at32ap/pio.c
+++ b/arch/avr32/mach-at32ap/pio.c
@@ -281,7 +281,7 @@
 	.irq_set_type	= gpio_irq_type,
 };
 
-static void gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void gpio_irq_handler(struct irq_desc *desc)
 {
 	struct pio_device	*pio = irq_desc_get_chip_data(desc);
 	unsigned		gpio_irq;
diff --git a/arch/blackfin/include/asm/irq_handler.h b/arch/blackfin/include/asm/irq_handler.h
index 4b2a992..d2f90c7 100644
--- a/arch/blackfin/include/asm/irq_handler.h
+++ b/arch/blackfin/include/asm/irq_handler.h
@@ -60,7 +60,7 @@
 extern void bfin_internal_unmask_irq(unsigned int irq);
 
 struct irq_desc;
-extern void bfin_demux_mac_status_irq(unsigned int, struct irq_desc *);
-extern void bfin_demux_gpio_irq(unsigned int, struct irq_desc *);
+extern void bfin_demux_mac_status_irq(struct irq_desc *);
+extern void bfin_demux_gpio_irq(struct irq_desc *);
 
 #endif
diff --git a/arch/blackfin/kernel/irqchip.c b/arch/blackfin/kernel/irqchip.c
index 0ba2576..052cde5 100644
--- a/arch/blackfin/kernel/irqchip.c
+++ b/arch/blackfin/kernel/irqchip.c
@@ -107,7 +107,7 @@
 	 * than crashing, do something sensible.
 	 */
 	if (irq >= NR_IRQS)
-		handle_bad_irq(irq, &bad_irq_desc);
+		handle_bad_irq(&bad_irq_desc);
 	else
 		generic_handle_irq(irq);
 
diff --git a/arch/blackfin/mach-bf537/ints-priority.c b/arch/blackfin/mach-bf537/ints-priority.c
index 14b2f74..a48baae 100644
--- a/arch/blackfin/mach-bf537/ints-priority.c
+++ b/arch/blackfin/mach-bf537/ints-priority.c
@@ -89,8 +89,7 @@
 	.irq_unmask = bf537_generic_error_unmask_irq,
 };
 
-static void bf537_demux_error_irq(unsigned int int_err_irq,
-				  struct irq_desc *inta_desc)
+static void bf537_demux_error_irq(struct irq_desc *inta_desc)
 {
 	int irq = 0;
 
@@ -182,15 +181,12 @@
 	.irq_unmask = bf537_mac_rx_unmask_irq,
 };
 
-static void bf537_demux_mac_rx_irq(unsigned int __int_irq,
-				   struct irq_desc *desc)
+static void bf537_demux_mac_rx_irq(struct irq_desc *desc)
 {
-	unsigned int int_irq = irq_desc_get_irq(desc);
-
 	if (bfin_read_DMA1_IRQ_STATUS() & (DMA_DONE | DMA_ERR))
 		bfin_handle_irq(IRQ_MAC_RX);
 	else
-		bfin_demux_gpio_irq(int_irq, desc);
+		bfin_demux_gpio_irq(desc);
 }
 #endif
 
diff --git a/arch/blackfin/mach-common/ints-priority.c b/arch/blackfin/mach-common/ints-priority.c
index a6d1b03..e8d4d74 100644
--- a/arch/blackfin/mach-common/ints-priority.c
+++ b/arch/blackfin/mach-common/ints-priority.c
@@ -656,8 +656,7 @@
 	.irq_set_wake = bfin_mac_status_set_wake,
 };
 
-void bfin_demux_mac_status_irq(unsigned int int_err_irq,
-			       struct irq_desc *inta_desc)
+void bfin_demux_mac_status_irq(struct irq_desc *inta_desc)
 {
 	int i, irq = 0;
 	u32 status = bfin_read_EMAC_SYSTAT();
@@ -825,7 +824,7 @@
 	}
 }
 
-void bfin_demux_gpio_irq(unsigned int __inta_irq, struct irq_desc *desc)
+void bfin_demux_gpio_irq(struct irq_desc *desc)
 {
 	unsigned int inta_irq = irq_desc_get_irq(desc);
 	unsigned int irq;
diff --git a/arch/c6x/platforms/megamod-pic.c b/arch/c6x/platforms/megamod-pic.c
index d487698..ddcb45d 100644
--- a/arch/c6x/platforms/megamod-pic.c
+++ b/arch/c6x/platforms/megamod-pic.c
@@ -93,7 +93,7 @@
 	.irq_unmask	= unmask_megamod,
 };
 
-static void megamod_irq_cascade(unsigned int __irq, struct irq_desc *desc)
+static void megamod_irq_cascade(struct irq_desc *desc)
 {
 	struct megamod_cascade_data *cascade;
 	struct megamod_pic *pic;
diff --git a/arch/frv/mb93090-mb00/pci-vdk.c b/arch/frv/mb93090-mb00/pci-vdk.c
index f9c86c4..f211839 100644
--- a/arch/frv/mb93090-mb00/pci-vdk.c
+++ b/arch/frv/mb93090-mb00/pci-vdk.c
@@ -294,6 +294,8 @@
 	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/include/asm/unistd.h b/arch/ia64/include/asm/unistd.h
index 95c39b9..99c96a5 100644
--- a/arch/ia64/include/asm/unistd.h
+++ b/arch/ia64/include/asm/unistd.h
@@ -11,7 +11,7 @@
 
 
 
-#define NR_syscalls			319 /* length of syscall table */
+#define NR_syscalls			321 /* length of syscall table */
 
 /*
  * The following defines stop scripts/checksyscalls.sh from complaining about
diff --git a/arch/ia64/include/uapi/asm/unistd.h b/arch/ia64/include/uapi/asm/unistd.h
index 4610795..98e94e1 100644
--- a/arch/ia64/include/uapi/asm/unistd.h
+++ b/arch/ia64/include/uapi/asm/unistd.h
@@ -332,5 +332,7 @@
 #define __NR_memfd_create		1340
 #define __NR_bpf			1341
 #define __NR_execveat			1342
+#define __NR_userfaultfd		1343
+#define __NR_membarrier			1344
 
 #endif /* _UAPI_ASM_IA64_UNISTD_H */
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index ae0de7b..37cc7a6 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -1768,5 +1768,7 @@
 	data8 sys_memfd_create			// 1340
 	data8 sys_bpf
 	data8 sys_execveat
+	data8 sys_userfaultfd
+	data8 sys_membarrier
 
 	.org sys_call_table + 8*NR_syscalls	// guard against failures to increase NR_syscalls
diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c
index d89b601..7cc3be9 100644
--- a/arch/ia64/pci/pci.c
+++ b/arch/ia64/pci/pci.c
@@ -533,9 +533,10 @@
 {
 	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/m68k/amiga/amiints.c b/arch/m68k/amiga/amiints.c
index 47b5f90..7ff739e 100644
--- a/arch/m68k/amiga/amiints.c
+++ b/arch/m68k/amiga/amiints.c
@@ -46,7 +46,7 @@
  * The builtin Amiga hardware interrupt handlers.
  */
 
-static void ami_int1(unsigned int irq, struct irq_desc *desc)
+static void ami_int1(struct irq_desc *desc)
 {
 	unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
 
@@ -69,7 +69,7 @@
 	}
 }
 
-static void ami_int3(unsigned int irq, struct irq_desc *desc)
+static void ami_int3(struct irq_desc *desc)
 {
 	unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
 
@@ -92,7 +92,7 @@
 	}
 }
 
-static void ami_int4(unsigned int irq, struct irq_desc *desc)
+static void ami_int4(struct irq_desc *desc)
 {
 	unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
 
@@ -121,7 +121,7 @@
 	}
 }
 
-static void ami_int5(unsigned int irq, struct irq_desc *desc)
+static void ami_int5(struct irq_desc *desc)
 {
 	unsigned short ints = amiga_custom.intreqr & amiga_custom.intenar;
 
diff --git a/arch/m68k/coldfire/intc-5272.c b/arch/m68k/coldfire/intc-5272.c
index 47371de..b0a19e2 100644
--- a/arch/m68k/coldfire/intc-5272.c
+++ b/arch/m68k/coldfire/intc-5272.c
@@ -143,12 +143,10 @@
  * We need to be careful with the masking/acking due to the side effects
  * of masking an interrupt.
  */
-static void intc_external_irq(unsigned int __irq, struct irq_desc *desc)
+static void intc_external_irq(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
-
 	irq_desc_get_chip(desc)->irq_ack(&desc->irq_data);
-	handle_simple_irq(irq, desc);
+	handle_simple_irq(desc);
 }
 
 static struct irq_chip intc_irq_chip = {
diff --git a/arch/m68k/include/asm/irq.h b/arch/m68k/include/asm/irq.h
index 81ca118..a644f4a 100644
--- a/arch/m68k/include/asm/irq.h
+++ b/arch/m68k/include/asm/irq.h
@@ -64,8 +64,7 @@
 						      struct pt_regs *));
 extern void m68k_setup_user_interrupt(unsigned int vec, unsigned int cnt);
 extern void m68k_setup_irq_controller(struct irq_chip *,
-				      void (*handle)(unsigned int irq,
-						     struct irq_desc *desc),
+				      void (*handle)(struct irq_desc *desc),
 				      unsigned int irq, unsigned int cnt);
 
 extern unsigned int irq_canonicalize(unsigned int irq);
diff --git a/arch/m68k/include/asm/mac_via.h b/arch/m68k/include/asm/mac_via.h
index fe3fc9a..53c632c 100644
--- a/arch/m68k/include/asm/mac_via.h
+++ b/arch/m68k/include/asm/mac_via.h
@@ -261,7 +261,7 @@
 extern void via_irq_disable(int);
 extern void via_nubus_irq_startup(int irq);
 extern void via_nubus_irq_shutdown(int irq);
-extern void via1_irq(unsigned int irq, struct irq_desc *desc);
+extern void via1_irq(struct irq_desc *desc);
 extern void via1_set_head(int);
 extern int via2_scsi_drq_pending(void);
 
diff --git a/arch/m68k/mac/baboon.c b/arch/m68k/mac/baboon.c
index 3fe0e43..f6f7d42 100644
--- a/arch/m68k/mac/baboon.c
+++ b/arch/m68k/mac/baboon.c
@@ -45,7 +45,7 @@
  * Baboon interrupt handler. This works a lot like a VIA.
  */
 
-static void baboon_irq(unsigned int irq, struct irq_desc *desc)
+static void baboon_irq(struct irq_desc *desc)
 {
 	int irq_bit, irq_num;
 	unsigned char events;
diff --git a/arch/m68k/mac/oss.c b/arch/m68k/mac/oss.c
index 191610d..55d65927 100644
--- a/arch/m68k/mac/oss.c
+++ b/arch/m68k/mac/oss.c
@@ -63,7 +63,7 @@
  * Handle miscellaneous OSS interrupts.
  */
 
-static void oss_irq(unsigned int __irq, struct irq_desc *desc)
+static void oss_irq(struct irq_desc *desc)
 {
 	int events = oss->irq_pending &
 		(OSS_IP_IOPSCC | OSS_IP_SCSI | OSS_IP_IOPISM);
@@ -99,7 +99,7 @@
  * Unlike the VIA/RBV this is on its own autovector interrupt level.
  */
 
-static void oss_nubus_irq(unsigned int irq, struct irq_desc *desc)
+static void oss_nubus_irq(struct irq_desc *desc)
 {
 	int events, irq_bit, i;
 
diff --git a/arch/m68k/mac/psc.c b/arch/m68k/mac/psc.c
index 3b9e302..cd38f29 100644
--- a/arch/m68k/mac/psc.c
+++ b/arch/m68k/mac/psc.c
@@ -113,7 +113,7 @@
  * PSC interrupt handler. It's a lot like the VIA interrupt handler.
  */
 
-static void psc_irq(unsigned int __irq, struct irq_desc *desc)
+static void psc_irq(struct irq_desc *desc)
 {
 	unsigned int offset = (unsigned int)irq_desc_get_handler_data(desc);
 	unsigned int irq = irq_desc_get_irq(desc);
diff --git a/arch/m68k/mac/via.c b/arch/m68k/mac/via.c
index e198dec..ce56e04 100644
--- a/arch/m68k/mac/via.c
+++ b/arch/m68k/mac/via.c
@@ -446,7 +446,7 @@
  * via6522.c :-), disable/pending masks added.
  */
 
-void via1_irq(unsigned int irq, struct irq_desc *desc)
+void via1_irq(struct irq_desc *desc)
 {
 	int irq_num;
 	unsigned char irq_bit, events;
@@ -467,7 +467,7 @@
 	} while (events >= irq_bit);
 }
 
-static void via2_irq(unsigned int irq, struct irq_desc *desc)
+static void via2_irq(struct irq_desc *desc)
 {
 	int irq_num;
 	unsigned char irq_bit, events;
@@ -493,7 +493,7 @@
  * VIA2 dispatcher as a fast interrupt handler.
  */
 
-void via_nubus_irq(unsigned int irq, struct irq_desc *desc)
+static void via_nubus_irq(struct irq_desc *desc)
 {
 	int slot_irq;
 	unsigned char slot_bit, events;
diff --git a/arch/metag/kernel/irq.c b/arch/metag/kernel/irq.c
index a336094..3074b64 100644
--- a/arch/metag/kernel/irq.c
+++ b/arch/metag/kernel/irq.c
@@ -94,13 +94,11 @@
 			"MOV   D0.5,%0\n"
 			"MOV   D1Ar1,%1\n"
 			"MOV   D1RtP,%2\n"
-			"MOV   D0Ar2,%3\n"
 			"SWAP  A0StP,D0.5\n"
 			"SWAP  PC,D1RtP\n"
 			"MOV   A0StP,D0.5\n"
 			:
-			: "r" (isp), "r" (irq), "r" (desc->handle_irq),
-			  "r" (desc)
+			: "r" (isp), "r" (desc), "r" (desc->handle_irq)
 			: "memory", "cc", "D1Ar1", "D0Ar2", "D1Ar3", "D0Ar4",
 			  "D1Ar5", "D0Ar6", "D0Re0", "D1Re0", "D0.4", "D1RtP",
 			  "D0.5"
diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c
index 6b8b752..ae838ed 100644
--- a/arch/microblaze/pci/pci-common.c
+++ b/arch/microblaze/pci/pci-common.c
@@ -863,7 +863,14 @@
 
 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/alchemy/common/irq.c b/arch/mips/alchemy/common/irq.c
index 4c496c5..da9f922 100644
--- a/arch/mips/alchemy/common/irq.c
+++ b/arch/mips/alchemy/common/irq.c
@@ -851,7 +851,7 @@
 
 /* create chained handlers for the 4 IC requests to the MIPS IRQ ctrl */
 #define DISP(name, base, addr)						      \
-static void au1000_##name##_dispatch(unsigned int irq, struct irq_desc *d)    \
+static void au1000_##name##_dispatch(struct irq_desc *d)		      \
 {									      \
 	unsigned long r = __raw_readl((void __iomem *)KSEG1ADDR(addr));	      \
 	if (likely(r))							      \
@@ -865,7 +865,7 @@
 DISP(ic1r0, AU1000_INTC1_INT_BASE, AU1000_IC1_PHYS_ADDR + IC_REQ0INT)
 DISP(ic1r1, AU1000_INTC1_INT_BASE, AU1000_IC1_PHYS_ADDR + IC_REQ1INT)
 
-static void alchemy_gpic_dispatch(unsigned int irq, struct irq_desc *d)
+static void alchemy_gpic_dispatch(struct irq_desc *d)
 {
 	int i = __raw_readl(AU1300_GPIC_ADDR + AU1300_GPIC_PRIENC);
 	generic_handle_irq(ALCHEMY_GPIC_INT_BASE + i);
diff --git a/arch/mips/alchemy/devboards/bcsr.c b/arch/mips/alchemy/devboards/bcsr.c
index 324ad72..faeddf1 100644
--- a/arch/mips/alchemy/devboards/bcsr.c
+++ b/arch/mips/alchemy/devboards/bcsr.c
@@ -86,7 +86,7 @@
 /*
  * DB1200/PB1200 CPLD IRQ muxer
  */
-static void bcsr_csc_handler(unsigned int irq, struct irq_desc *d)
+static void bcsr_csc_handler(struct irq_desc *d)
 {
 	unsigned short bisr = __raw_readw(bcsr_virt + BCSR_REG_INTSTAT);
 	struct irq_chip *chip = irq_desc_get_chip(d);
diff --git a/arch/mips/ath25/ar2315.c b/arch/mips/ath25/ar2315.c
index ec9a371..8da9961 100644
--- a/arch/mips/ath25/ar2315.c
+++ b/arch/mips/ath25/ar2315.c
@@ -69,7 +69,7 @@
 	.name		= "ar2315-ahb-error",
 };
 
-static void ar2315_misc_irq_handler(unsigned irq, struct irq_desc *desc)
+static void ar2315_misc_irq_handler(struct irq_desc *desc)
 {
 	u32 pending = ar2315_rst_reg_read(AR2315_ISR) &
 		      ar2315_rst_reg_read(AR2315_IMR);
diff --git a/arch/mips/ath25/ar5312.c b/arch/mips/ath25/ar5312.c
index e63e38f..acd55a9 100644
--- a/arch/mips/ath25/ar5312.c
+++ b/arch/mips/ath25/ar5312.c
@@ -73,7 +73,7 @@
 	.name    = "ar5312-ahb-error",
 };
 
-static void ar5312_misc_irq_handler(unsigned irq, struct irq_desc *desc)
+static void ar5312_misc_irq_handler(struct irq_desc *desc)
 {
 	u32 pending = ar5312_rst_reg_read(AR5312_ISR) &
 		      ar5312_rst_reg_read(AR5312_IMR);
diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c
index 807132b..15ecb48 100644
--- a/arch/mips/ath79/irq.c
+++ b/arch/mips/ath79/irq.c
@@ -26,7 +26,7 @@
 #include "common.h"
 #include "machtypes.h"
 
-static void ath79_misc_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ath79_misc_irq_handler(struct irq_desc *desc)
 {
 	void __iomem *base = ath79_reset_base;
 	u32 pending;
@@ -119,7 +119,7 @@
 	irq_set_chained_handler(ATH79_CPU_IRQ(6), ath79_misc_irq_handler);
 }
 
-static void ar934x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc)
+static void ar934x_ip2_irq_dispatch(struct irq_desc *desc)
 {
 	u32 status;
 
@@ -148,7 +148,7 @@
 	irq_set_chained_handler(ATH79_CPU_IRQ(2), ar934x_ip2_irq_dispatch);
 }
 
-static void qca955x_ip2_irq_dispatch(unsigned int irq, struct irq_desc *desc)
+static void qca955x_ip2_irq_dispatch(struct irq_desc *desc)
 {
 	u32 status;
 
@@ -171,7 +171,7 @@
 	}
 }
 
-static void qca955x_ip3_irq_dispatch(unsigned int irq, struct irq_desc *desc)
+static void qca955x_ip3_irq_dispatch(struct irq_desc *desc)
 {
 	u32 status;
 
diff --git a/arch/mips/cavium-octeon/octeon-irq.c b/arch/mips/cavium-octeon/octeon-irq.c
index f26c3c6..0352bc8 100644
--- a/arch/mips/cavium-octeon/octeon-irq.c
+++ b/arch/mips/cavium-octeon/octeon-irq.c
@@ -2221,7 +2221,7 @@
 			if (irqd_get_trigger_type(irq_data) &
 				IRQ_TYPE_EDGE_BOTH)
 				cvmx_write_csr(host_data->raw_reg, 1ull << i);
-			generic_handle_irq_desc(irq, desc);
+			generic_handle_irq_desc(desc);
 		}
 	}
 
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index e8c8d9d..5a1a882 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
 
 
 
@@ -128,6 +129,7 @@
 	u32 msa_disabled_exits;
 	u32 flush_dcache_exits;
 	u32 halt_successful_poll;
+	u32 halt_attempted_poll;
 	u32 halt_wakeup;
 };
 
diff --git a/arch/mips/include/asm/netlogic/common.h b/arch/mips/include/asm/netlogic/common.h
index 2a4c128..be52c21 100644
--- a/arch/mips/include/asm/netlogic/common.h
+++ b/arch/mips/include/asm/netlogic/common.h
@@ -57,8 +57,8 @@
 #include <asm/mach-netlogic/multi-node.h>
 
 struct irq_desc;
-void nlm_smp_function_ipi_handler(unsigned int irq, struct irq_desc *desc);
-void nlm_smp_resched_ipi_handler(unsigned int irq, struct irq_desc *desc);
+void nlm_smp_function_ipi_handler(struct irq_desc *desc);
+void nlm_smp_resched_ipi_handler(struct irq_desc *desc);
 void nlm_smp_irq_init(int hwcpuid);
 void nlm_boot_secondary_cpus(void);
 int nlm_wakeup_secondary_cpus(void);
diff --git a/arch/mips/jz4740/gpio.c b/arch/mips/jz4740/gpio.c
index 6cd69fd..a74e181 100644
--- a/arch/mips/jz4740/gpio.c
+++ b/arch/mips/jz4740/gpio.c
@@ -291,7 +291,7 @@
 	writel(mask, reg);
 }
 
-static void jz_gpio_irq_demux_handler(unsigned int irq, struct irq_desc *desc)
+static void jz_gpio_irq_demux_handler(struct irq_desc *desc)
 {
 	uint32_t flag;
 	unsigned int gpio_irq;
diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c
index cd4c129..49ff3bf 100644
--- a/arch/mips/kvm/mips.c
+++ b/arch/mips/kvm/mips.c
@@ -55,6 +55,7 @@
 	{ "msa_disabled", VCPU_STAT(msa_disabled_exits), KVM_STAT_VCPU },
 	{ "flush_dcache", VCPU_STAT(flush_dcache_exits), KVM_STAT_VCPU },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), KVM_STAT_VCPU },
+	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), KVM_STAT_VCPU },
 	{ "halt_wakeup",  VCPU_STAT(halt_wakeup),	 KVM_STAT_VCPU },
 	{NULL}
 };
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 0136b4f..10d86d5 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -82,7 +82,7 @@
 }
 
 /* IRQ_IPI_SMP_FUNCTION Handler */
-void nlm_smp_function_ipi_handler(unsigned int __irq, struct irq_desc *desc)
+void nlm_smp_function_ipi_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	clear_c0_eimr(irq);
@@ -92,7 +92,7 @@
 }
 
 /* IRQ_IPI_SMP_RESCHEDULE  handler */
-void nlm_smp_resched_ipi_handler(unsigned int __irq, struct irq_desc *desc)
+void nlm_smp_resched_ipi_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	clear_c0_eimr(irq);
diff --git a/arch/mips/pci/pci-ar2315.c b/arch/mips/pci/pci-ar2315.c
index f8d0acb..b4fa641 100644
--- a/arch/mips/pci/pci-ar2315.c
+++ b/arch/mips/pci/pci-ar2315.c
@@ -318,7 +318,7 @@
 	return 0;
 }
 
-static void ar2315_pci_irq_handler(unsigned irq, struct irq_desc *desc)
+static void ar2315_pci_irq_handler(struct irq_desc *desc)
 {
 	struct ar2315_pci_ctrl *apc = irq_desc_get_handler_data(desc);
 	u32 pending = ar2315_pci_reg_read(apc, AR2315_PCI_ISR) &
diff --git a/arch/mips/pci/pci-ar71xx.c b/arch/mips/pci/pci-ar71xx.c
index ad35a5e..7db963d 100644
--- a/arch/mips/pci/pci-ar71xx.c
+++ b/arch/mips/pci/pci-ar71xx.c
@@ -226,7 +226,7 @@
 	.write	= ar71xx_pci_write_config,
 };
 
-static void ar71xx_pci_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ar71xx_pci_irq_handler(struct irq_desc *desc)
 {
 	struct ar71xx_pci_controller *apc;
 	void __iomem *base = ath79_reset_base;
diff --git a/arch/mips/pci/pci-ar724x.c b/arch/mips/pci/pci-ar724x.c
index 907d11d..2013dad 100644
--- a/arch/mips/pci/pci-ar724x.c
+++ b/arch/mips/pci/pci-ar724x.c
@@ -225,7 +225,7 @@
 	.write	= ar724x_pci_write,
 };
 
-static void ar724x_pci_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ar724x_pci_irq_handler(struct irq_desc *desc)
 {
 	struct ar724x_pci_controller *apc;
 	void __iomem *base;
diff --git a/arch/mips/pci/pci-rt3883.c b/arch/mips/pci/pci-rt3883.c
index 53c8efa..ed6732f9 100644
--- a/arch/mips/pci/pci-rt3883.c
+++ b/arch/mips/pci/pci-rt3883.c
@@ -129,7 +129,7 @@
 	rt3883_pci_w32(rpc, val, RT3883_PCI_REG_CFGDATA);
 }
 
-static void rt3883_pci_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void rt3883_pci_irq_handler(struct irq_desc *desc)
 {
 	struct rt3883_pci_controller *rpc;
 	u32 pending;
diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c
index c6996cf..b8a0bf5 100644
--- a/arch/mips/pci/pci.c
+++ b/arch/mips/pci/pci.c
@@ -311,6 +311,12 @@
 
 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/mips/ralink/irq.c b/arch/mips/ralink/irq.c
index 8c624a8..4cf77f3 100644
--- a/arch/mips/ralink/irq.c
+++ b/arch/mips/ralink/irq.c
@@ -96,7 +96,7 @@
 	return CP0_LEGACY_COMPARE_IRQ;
 }
 
-static void ralink_intc_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ralink_intc_irq_handler(struct irq_desc *desc)
 {
 	u32 pending = rt_intc_r32(INTC_REG_STATUS0);
 
diff --git a/arch/mn10300/unit-asb2305/pci.c b/arch/mn10300/unit-asb2305/pci.c
index deaa893..3dfe2d3 100644
--- a/arch/mn10300/unit-asb2305/pci.c
+++ b/arch/mn10300/unit-asb2305/pci.c
@@ -324,6 +324,7 @@
 	struct pci_dev *dev;
 
 	if (bus->self) {
+		pci_read_bridge_bases(bus);
 		pcibios_fixup_bridge_resources(bus->self);
 	}
 
diff --git a/arch/powerpc/boot/Makefile b/arch/powerpc/boot/Makefile
index 73eddda..4eec430 100644
--- a/arch/powerpc/boot/Makefile
+++ b/arch/powerpc/boot/Makefile
@@ -28,6 +28,9 @@
 endif
 ifdef CONFIG_CPU_BIG_ENDIAN
 BOOTCFLAGS	+= -mbig-endian
+else
+BOOTCFLAGS	+= -mlittle-endian
+BOOTCFLAGS	+= $(call cc-option,-mabi=elfv2)
 endif
 
 BOOTAFLAGS	:= -D__ASSEMBLY__ $(BOOTCFLAGS) -traditional -nostdinc
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index 98eebbf..827a38d 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
@@ -108,6 +109,7 @@
 	u32 dec_exits;
 	u32 ext_intr_exits;
 	u32 halt_successful_poll;
+	u32 halt_attempted_poll;
 	u32 halt_wakeup;
 	u32 dbell_exits;
 	u32 gdbell_exits;
diff --git a/arch/powerpc/include/asm/qe_ic.h b/arch/powerpc/include/asm/qe_ic.h
index 25784cc..1e155ca 100644
--- a/arch/powerpc/include/asm/qe_ic.h
+++ b/arch/powerpc/include/asm/qe_ic.h
@@ -59,14 +59,14 @@
 
 #ifdef CONFIG_QUICC_ENGINE
 void qe_ic_init(struct device_node *node, unsigned int flags,
-		void (*low_handler)(unsigned int irq, struct irq_desc *desc),
-		void (*high_handler)(unsigned int irq, struct irq_desc *desc));
+		void (*low_handler)(struct irq_desc *desc),
+		void (*high_handler)(struct irq_desc *desc));
 unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic);
 unsigned int qe_ic_get_high_irq(struct qe_ic *qe_ic);
 #else
 static inline void qe_ic_init(struct device_node *node, unsigned int flags,
-		void (*low_handler)(unsigned int irq, struct irq_desc *desc),
-		void (*high_handler)(unsigned int irq, struct irq_desc *desc))
+		void (*low_handler)(struct irq_desc *desc),
+		void (*high_handler)(struct irq_desc *desc))
 {}
 static inline unsigned int qe_ic_get_low_irq(struct qe_ic *qe_ic)
 { return 0; }
@@ -78,8 +78,7 @@
 int qe_ic_set_priority(unsigned int virq, unsigned int priority);
 int qe_ic_set_high_priority(unsigned int virq, unsigned int priority, int high);
 
-static inline void qe_ic_cascade_low_ipic(unsigned int irq,
-					  struct irq_desc *desc)
+static inline void qe_ic_cascade_low_ipic(struct irq_desc *desc)
 {
 	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
 	unsigned int cascade_irq = qe_ic_get_low_irq(qe_ic);
@@ -88,8 +87,7 @@
 		generic_handle_irq(cascade_irq);
 }
 
-static inline void qe_ic_cascade_high_ipic(unsigned int irq,
-					   struct irq_desc *desc)
+static inline void qe_ic_cascade_high_ipic(struct irq_desc *desc)
 {
 	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
 	unsigned int cascade_irq = qe_ic_get_high_irq(qe_ic);
@@ -98,8 +96,7 @@
 		generic_handle_irq(cascade_irq);
 }
 
-static inline void qe_ic_cascade_low_mpic(unsigned int irq,
-					  struct irq_desc *desc)
+static inline void qe_ic_cascade_low_mpic(struct irq_desc *desc)
 {
 	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
 	unsigned int cascade_irq = qe_ic_get_low_irq(qe_ic);
@@ -111,8 +108,7 @@
 	chip->irq_eoi(&desc->irq_data);
 }
 
-static inline void qe_ic_cascade_high_mpic(unsigned int irq,
-					   struct irq_desc *desc)
+static inline void qe_ic_cascade_high_mpic(struct irq_desc *desc)
 {
 	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
 	unsigned int cascade_irq = qe_ic_get_high_irq(qe_ic);
@@ -124,8 +120,7 @@
 	chip->irq_eoi(&desc->irq_data);
 }
 
-static inline void qe_ic_cascade_muxed_mpic(unsigned int irq,
-					    struct irq_desc *desc)
+static inline void qe_ic_cascade_muxed_mpic(struct irq_desc *desc)
 {
 	struct qe_ic *qe_ic = irq_desc_get_handler_data(desc);
 	unsigned int cascade_irq;
diff --git a/arch/powerpc/include/asm/systbl.h b/arch/powerpc/include/asm/systbl.h
index 71f2b3f..126d0c4 100644
--- a/arch/powerpc/include/asm/systbl.h
+++ b/arch/powerpc/include/asm/systbl.h
@@ -368,3 +368,5 @@
 SYSCALL_SPU(bpf)
 COMPAT_SYS(execveat)
 PPC64ONLY(switch_endian)
+SYSCALL_SPU(userfaultfd)
+SYSCALL_SPU(membarrier)
diff --git a/arch/powerpc/include/asm/tsi108_pci.h b/arch/powerpc/include/asm/tsi108_pci.h
index 5653d7c..ae59d5b 100644
--- a/arch/powerpc/include/asm/tsi108_pci.h
+++ b/arch/powerpc/include/asm/tsi108_pci.h
@@ -39,7 +39,7 @@
 
 extern int tsi108_setup_pci(struct device_node *dev, u32 cfg_phys, int primary);
 extern void tsi108_pci_int_init(struct device_node *node);
-extern void tsi108_irq_cascade(unsigned int irq, struct irq_desc *desc);
+extern void tsi108_irq_cascade(struct irq_desc *desc);
 extern void tsi108_clear_pci_cfg_error(void);
 
 #endif				/*  _ASM_POWERPC_TSI108_PCI_H */
diff --git a/arch/powerpc/include/asm/unistd.h b/arch/powerpc/include/asm/unistd.h
index f4f8b66..13411be 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		364
+#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 e4aa173..6337738 100644
--- a/arch/powerpc/include/uapi/asm/unistd.h
+++ b/arch/powerpc/include/uapi/asm/unistd.h
@@ -386,5 +386,7 @@
 #define __NR_bpf		361
 #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/irq.c b/arch/powerpc/kernel/irq.c
index 4509603..290559d 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -441,7 +441,7 @@
 
 		chip = irq_data_get_irq_chip(data);
 
-		cpumask_and(mask, data->affinity, map);
+		cpumask_and(mask, irq_data_get_affinity_mask(data), map);
 		if (cpumask_any(mask) >= nr_cpu_ids) {
 			pr_warn("Breaking affinity for irq %i\n", irq);
 			cpumask_copy(mask, map);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index a1d0632..7587b2a 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1032,7 +1032,13 @@
 
 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/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index bb02e9f..ad8c9db 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -38,6 +38,7 @@
 #include <asm/udbg.h>
 #include <asm/mmu_context.h>
 #include <asm/epapr_hcalls.h>
+#include <asm/code-patching.h>
 
 #define DBG(fmt...)
 
@@ -109,6 +110,8 @@
  * This is called very early on the boot process, after a minimal
  * MMU environment has been set up but before MMU_init is called.
  */
+extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
+
 notrace void __init machine_init(u64 dt_ptr)
 {
 	lockdep_init();
@@ -116,6 +119,9 @@
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
+	patch_instruction((unsigned int *)&memcpy, PPC_INST_NOP);
+	patch_instruction(&memset_nocache_branch, PPC_INST_NOP);
+
 	/* Do some early initialization based on the flat device tree */
 	early_init_devtree(__va(dt_ptr));
 
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index d75bf32..099c79d 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -53,6 +53,7 @@
 	{ "ext_intr",    VCPU_STAT(ext_intr_exits) },
 	{ "queue_intr",  VCPU_STAT(queue_intr) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll), },
+	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll), },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "pf_storage",  VCPU_STAT(pf_storage) },
 	{ "sp_storage",  VCPU_STAT(sp_storage) },
@@ -828,12 +829,15 @@
 	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;
 
@@ -868,6 +872,7 @@
 	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) {
@@ -891,7 +896,9 @@
 		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 9754e68..2280497 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2692,9 +2692,13 @@
 
 	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 2273dca..b98889e 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -1257,6 +1257,7 @@
 	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/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index ae458f0..fd58751 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -63,6 +63,7 @@
 	{ "dec",        VCPU_STAT(dec_exits) },
 	{ "ext_intr",   VCPU_STAT(ext_intr_exits) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
+	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "doorbell", VCPU_STAT(dbell_exits) },
 	{ "guest doorbell", VCPU_STAT(gdbell_exits) },
diff --git a/arch/powerpc/lib/copy_32.S b/arch/powerpc/lib/copy_32.S
index 2ef50c6..c44df2d 100644
--- a/arch/powerpc/lib/copy_32.S
+++ b/arch/powerpc/lib/copy_32.S
@@ -73,6 +73,10 @@
  * Use dcbz on the complete cache lines in the destination
  * to set them to zero.  This requires that the destination
  * area is cacheable.  -- paulus
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore skip the optimised bloc that uses dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
  */
 _GLOBAL(memset)
 	rlwimi	r4,r4,8,16,23
@@ -88,6 +92,8 @@
 	subf	r6,r0,r6
 	cmplwi	0,r4,0
 	bne	2f	/* Use normal procedure if r4 is not zero */
+_GLOBAL(memset_nocache_branch)
+	b	2f	/* Skip optimised bloc until cache is enabled */
 
 	clrlwi	r7,r6,32-LG_CACHELINE_BYTES
 	add	r8,r7,r5
@@ -128,6 +134,10 @@
  * the destination area is cacheable.
  * We only use this version if the source and dest don't overlap.
  * -- paulus.
+ *
+ * During early init, cache might not be active yet, so dcbz cannot be used.
+ * We therefore jump to generic_memcpy which doesn't use dcbz. This jump is
+ * replaced by a nop once cache is active. This is done in machine_init()
  */
 _GLOBAL(memmove)
 	cmplw	0,r3,r4
@@ -135,6 +145,7 @@
 	/* fall through */
 
 _GLOBAL(memcpy)
+	b	generic_memcpy
 	add	r7,r3,r5		/* test if the src & dst overlap */
 	add	r8,r4,r5
 	cmplw	0,r4,r7
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 43dafb9..4d87122 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -85,7 +85,6 @@
 	BUG_ON(index >= 4096);
 
 	vpn = hpt_vpn(ea, vsid, ssize);
-	hash = hpt_hash(vpn, shift, ssize);
 	hpte_slot_array = get_hpte_slot_array(pmdp);
 	if (psize == MMU_PAGE_4K) {
 		/*
@@ -101,6 +100,7 @@
 	valid = hpte_valid(hpte_slot_array, index);
 	if (valid) {
 		/* update the hpte bits */
+		hash = hpt_hash(vpn, shift, ssize);
 		hidx =  hpte_hash_index(hpte_slot_array, index);
 		if (hidx & _PTEIDX_SECONDARY)
 			hash = ~hash;
@@ -126,6 +126,7 @@
 	if (!valid) {
 		unsigned long hpte_group;
 
+		hash = hpt_hash(vpn, shift, ssize);
 		/* insert new entry */
 		pa = pmd_pfn(__pmd(old_pmd)) << PAGE_SHIFT;
 		new_pmd |= _PAGE_HASHPTE;
diff --git a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
index 11090ab..0035d14 100644
--- a/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
+++ b/arch/powerpc/platforms/512x/mpc5121_ads_cpld.c
@@ -104,9 +104,10 @@
 	return irq_linear_revmap(cpld_pic_host, cpld_irq);
 }
 
-static void
-cpld_pic_cascade(unsigned int irq, struct irq_desc *desc)
+static void cpld_pic_cascade(struct irq_desc *desc)
 {
+	unsigned int irq;
+
 	irq = cpld_pic_get_irq(0, PCI_IGNORE, &cpld_regs->pci_status,
 		&cpld_regs->pci_mask);
 	if (irq != NO_IRQ) {
diff --git a/arch/powerpc/platforms/52xx/media5200.c b/arch/powerpc/platforms/52xx/media5200.c
index 32cae33..8fb9548 100644
--- a/arch/powerpc/platforms/52xx/media5200.c
+++ b/arch/powerpc/platforms/52xx/media5200.c
@@ -80,7 +80,7 @@
 	.irq_mask_ack = media5200_irq_mask,
 };
 
-void media5200_irq_cascade(unsigned int virq, struct irq_desc *desc)
+static void media5200_irq_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	int sub_virq, val;
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index 6301662..78ac19a 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -191,7 +191,7 @@
 	.irq_set_type = mpc52xx_gpt_irq_set_type,
 };
 
-void mpc52xx_gpt_irq_cascade(unsigned int virq, struct irq_desc *desc)
+static void mpc52xx_gpt_irq_cascade(struct irq_desc *desc)
 {
 	struct mpc52xx_gpt_priv *gpt = irq_desc_get_handler_data(desc);
 	int sub_virq;
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_pic.c b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
index 2944bc8..4fe2074 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_pic.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_pic.c
@@ -196,7 +196,7 @@
 	ctrl_reg |= (type << (22 - (l2irq * 2)));
 	out_be32(&intr->ctrl, ctrl_reg);
 
-	__irq_set_handler_locked(d->irq, handler);
+	irq_set_handler_locked(d, handler);
 
 	return 0;
 }
diff --git a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
index 74861a7..60e89fc 100644
--- a/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
+++ b/arch/powerpc/platforms/82xx/pq2ads-pci-pic.c
@@ -78,7 +78,7 @@
 	.irq_disable = pq2ads_pci_mask_irq
 };
 
-static void pq2ads_pci_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void pq2ads_pci_irq_demux(struct irq_desc *desc)
 {
 	struct pq2ads_pci_pic *priv = irq_desc_get_handler_data(desc);
 	u32 stat, mask, pend;
diff --git a/arch/powerpc/platforms/85xx/common.c b/arch/powerpc/platforms/85xx/common.c
index 7bfb9b1..23791de 100644
--- a/arch/powerpc/platforms/85xx/common.c
+++ b/arch/powerpc/platforms/85xx/common.c
@@ -49,7 +49,7 @@
 	return of_platform_bus_probe(NULL, mpc85xx_common_ids, NULL);
 }
 #ifdef CONFIG_CPM2
-static void cpm2_cascade(unsigned int irq, struct irq_desc *desc)
+static void cpm2_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	int cascade_irq;
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_cds.c b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
index b0753e2..5ac70de 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_cds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_cds.c
@@ -192,8 +192,7 @@
 }
 
 #ifdef CONFIG_PPC_I8259
-static void mpc85xx_8259_cascade_handler(unsigned int irq,
-					 struct irq_desc *desc)
+static void mpc85xx_8259_cascade_handler(struct irq_desc *desc)
 {
 	unsigned int cascade_irq = i8259_irq();
 
@@ -202,7 +201,7 @@
 		generic_handle_irq(cascade_irq);
 
 	/* check for any interrupts from the shared IRQ line */
-	handle_fasteoi_irq(irq, desc);
+	handle_fasteoi_irq(desc);
 }
 
 static irqreturn_t mpc85xx_8259_cascade_action(int irq, void *dev_id)
diff --git a/arch/powerpc/platforms/85xx/mpc85xx_ds.c b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
index ffdf021..f858306 100644
--- a/arch/powerpc/platforms/85xx/mpc85xx_ds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_ds.c
@@ -46,7 +46,7 @@
 #endif
 
 #ifdef CONFIG_PPC_I8259
-static void mpc85xx_8259_cascade(unsigned int irq, struct irq_desc *desc)
+static void mpc85xx_8259_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq = i8259_irq();
diff --git a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
index 55a9682..b02d6a5 100644
--- a/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
+++ b/arch/powerpc/platforms/85xx/socrates_fpga_pic.c
@@ -91,9 +91,10 @@
 			(irq_hw_number_t)i);
 }
 
-void socrates_fpga_pic_cascade(unsigned int irq, struct irq_desc *desc)
+static void socrates_fpga_pic_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int irq = irq_desc_get_irq(desc);
 	unsigned int cascade_irq;
 
 	/*
diff --git a/arch/powerpc/platforms/86xx/pic.c b/arch/powerpc/platforms/86xx/pic.c
index d5b98c0..845defa 100644
--- a/arch/powerpc/platforms/86xx/pic.c
+++ b/arch/powerpc/platforms/86xx/pic.c
@@ -17,7 +17,7 @@
 #include <asm/i8259.h>
 
 #ifdef CONFIG_PPC_I8259
-static void mpc86xx_8259_cascade(unsigned int irq, struct irq_desc *desc)
+static void mpc86xx_8259_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq = i8259_irq();
diff --git a/arch/powerpc/platforms/8xx/m8xx_setup.c b/arch/powerpc/platforms/8xx/m8xx_setup.c
index d303774..c289fc7 100644
--- a/arch/powerpc/platforms/8xx/m8xx_setup.c
+++ b/arch/powerpc/platforms/8xx/m8xx_setup.c
@@ -214,7 +214,7 @@
 	panic("Restart failed\n");
 }
 
-static void cpm_cascade(unsigned int irq, struct irq_desc *desc)
+static void cpm_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	int cascade_irq = cpm_get_irq();
diff --git a/arch/powerpc/platforms/cell/axon_msi.c b/arch/powerpc/platforms/cell/axon_msi.c
index 306888a..e0e68a1 100644
--- a/arch/powerpc/platforms/cell/axon_msi.c
+++ b/arch/powerpc/platforms/cell/axon_msi.c
@@ -93,7 +93,7 @@
 	dcr_write(msic->dcr_host, dcr_n, val);
 }
 
-static void axon_msi_cascade(unsigned int irq, struct irq_desc *desc)
+static void axon_msi_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct axon_msic *msic = irq_desc_get_handler_data(desc);
diff --git a/arch/powerpc/platforms/cell/interrupt.c b/arch/powerpc/platforms/cell/interrupt.c
index a15f1ef..9f609fc 100644
--- a/arch/powerpc/platforms/cell/interrupt.c
+++ b/arch/powerpc/platforms/cell/interrupt.c
@@ -99,11 +99,12 @@
 {
 }
 
-static void iic_ioexc_cascade(unsigned int irq, struct irq_desc *desc)
+static void iic_ioexc_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct cbe_iic_regs __iomem *node_iic =
 		(void __iomem *)irq_desc_get_handler_data(desc);
+	unsigned int irq = irq_desc_get_irq(desc);
 	unsigned int base = (irq & 0xffffff00) | IIC_IRQ_TYPE_IOEXC;
 	unsigned long bits, ack;
 	int cascade;
diff --git a/arch/powerpc/platforms/cell/spider-pic.c b/arch/powerpc/platforms/cell/spider-pic.c
index 1f72f4a..9d27de6 100644
--- a/arch/powerpc/platforms/cell/spider-pic.c
+++ b/arch/powerpc/platforms/cell/spider-pic.c
@@ -199,7 +199,7 @@
 	.xlate = spider_host_xlate,
 };
 
-static void spider_irq_cascade(unsigned int irq, struct irq_desc *desc)
+static void spider_irq_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct spider_pic *pic = irq_desc_get_handler_data(desc);
diff --git a/arch/powerpc/platforms/chrp/setup.c b/arch/powerpc/platforms/chrp/setup.c
index 15ebc4e..987d1b8 100644
--- a/arch/powerpc/platforms/chrp/setup.c
+++ b/arch/powerpc/platforms/chrp/setup.c
@@ -363,7 +363,7 @@
 	if (ppc_md.progress) ppc_md.progress("Linux/PPC "UTS_RELEASE"\n", 0x0);
 }
 
-static void chrp_8259_cascade(unsigned int irq, struct irq_desc *desc)
+static void chrp_8259_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq = i8259_irq();
diff --git a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
index 9dd154d..9b79757 100644
--- a/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
+++ b/arch/powerpc/platforms/embedded6xx/hlwd-pic.c
@@ -120,8 +120,7 @@
 	return irq_linear_revmap(h, irq);
 }
 
-static void hlwd_pic_irq_cascade(unsigned int cascade_virq,
-				      struct irq_desc *desc)
+static void hlwd_pic_irq_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct irq_domain *irq_domain = irq_desc_get_handler_data(desc);
diff --git a/arch/powerpc/platforms/embedded6xx/mvme5100.c b/arch/powerpc/platforms/embedded6xx/mvme5100.c
index 1613303..8f65aa3 100644
--- a/arch/powerpc/platforms/embedded6xx/mvme5100.c
+++ b/arch/powerpc/platforms/embedded6xx/mvme5100.c
@@ -42,7 +42,7 @@
 static phys_addr_t pci_membase;
 static u_char *restart;
 
-static void mvme5100_8259_cascade(unsigned int irq, struct irq_desc *desc)
+static void mvme5100_8259_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq = i8259_irq();
diff --git a/arch/powerpc/platforms/pasemi/msi.c b/arch/powerpc/platforms/pasemi/msi.c
index e66ef19..b304a9f 100644
--- a/arch/powerpc/platforms/pasemi/msi.c
+++ b/arch/powerpc/platforms/pasemi/msi.c
@@ -63,6 +63,7 @@
 static void pasemi_msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
 
 	pr_debug("pasemi_msi_teardown_msi_irqs, pdev %p\n", pdev);
 
@@ -70,10 +71,10 @@
 		if (entry->irq == NO_IRQ)
 			continue;
 
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap,
-				       virq_to_hw(entry->irq), ALLOC_CHUNK);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, ALLOC_CHUNK);
 	}
 
 	return;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 2927cd5..414fd1a 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2049,9 +2049,23 @@
 	struct iommu_table *tbl = NULL;
 	long rc;
 
+	/*
+	 * crashkernel= specifies the kdump kernel's maximum memory at
+	 * some offset and there is no guaranteed the result is a power
+	 * of 2, which will cause errors later.
+	 */
+	const u64 max_memory = __rounddown_pow_of_two(memory_hotplug_max());
+
+	/*
+	 * In memory constrained environments, e.g. kdump kernel, the
+	 * DMA window can be larger than available memory, which will
+	 * cause errors later.
+	 */
+	const u64 window_size = min((u64)pe->table_group.tce32_size, max_memory);
+
 	rc = pnv_pci_ioda2_create_table(&pe->table_group, 0,
 			IOMMU_PAGE_SHIFT_4K,
-			pe->table_group.tce32_size,
+			window_size,
 			POWERNV_IOMMU_DEFAULT_LEVELS, &tbl);
 	if (rc) {
 		pe_err(pe, "Failed to create 32-bit TCE table, err %ld",
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index 9b2480b..f2dd772 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -99,6 +99,7 @@
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
 	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
 
 	if (WARN_ON(!phb))
 		return;
@@ -106,10 +107,10 @@
 	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&phb->msi_bmp,
-			virq_to_hw(entry->irq) - phb->msi_base, 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, 1);
 	}
 }
 #endif /* CONFIG_PCI_MSI */
diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index 47d9cebe..db17827 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -422,8 +422,10 @@
 
 	dn = dlpar_configure_connector(cpu_to_be32(drc_index), parent);
 	of_node_put(parent);
-	if (!dn)
+	if (!dn) {
+		dlpar_release_drc(drc_index);
 		return -EINVAL;
+	}
 
 	rc = dlpar_attach_node(dn);
 	if (rc) {
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 39a74fa..9a83eb7 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -111,7 +111,7 @@
 		fwnmi_active = 1;
 }
 
-static void pseries_8259_cascade(unsigned int irq, struct irq_desc *desc)
+static void pseries_8259_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq = i8259_irq();
diff --git a/arch/powerpc/sysdev/cpm2_pic.c b/arch/powerpc/sysdev/cpm2_pic.c
index a11bd1d..9e86074 100644
--- a/arch/powerpc/sysdev/cpm2_pic.c
+++ b/arch/powerpc/sysdev/cpm2_pic.c
@@ -155,9 +155,9 @@
 
 	irqd_set_trigger_type(d, flow_type);
 	if (flow_type & IRQ_TYPE_LEVEL_LOW)
-		__irq_set_handler_locked(d->irq, handle_level_irq);
+		irq_set_handler_locked(d, handle_level_irq);
 	else
-		__irq_set_handler_locked(d->irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 
 	/* internal IRQ senses are LEVEL_LOW
 	 * EXT IRQ and Port C IRQ senses are programmable
diff --git a/arch/powerpc/sysdev/fsl_msi.c b/arch/powerpc/sysdev/fsl_msi.c
index 5916da1..48a576a 100644
--- a/arch/powerpc/sysdev/fsl_msi.c
+++ b/arch/powerpc/sysdev/fsl_msi.c
@@ -128,15 +128,16 @@
 {
 	struct msi_desc *entry;
 	struct fsl_msi *msi_data;
+	irq_hw_number_t hwirq;
 
 	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
+		hwirq = virq_to_hw(entry->irq);
 		msi_data = irq_get_chip_data(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_data->bitmap,
-				       virq_to_hw(entry->irq), 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
 	}
 
 	return;
diff --git a/arch/powerpc/sysdev/ge/ge_pic.c b/arch/powerpc/sysdev/ge/ge_pic.c
index 2bcb78b..d57b775 100644
--- a/arch/powerpc/sysdev/ge/ge_pic.c
+++ b/arch/powerpc/sysdev/ge/ge_pic.c
@@ -91,7 +91,7 @@
  * should be masked out.
  */
 
-void gef_pic_cascade(unsigned int irq, struct irq_desc *desc)
+static void gef_pic_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq;
diff --git a/arch/powerpc/sysdev/ge/ge_pic.h b/arch/powerpc/sysdev/ge/ge_pic.h
index 908dbd9..5bf7e4b 100644
--- a/arch/powerpc/sysdev/ge/ge_pic.h
+++ b/arch/powerpc/sysdev/ge/ge_pic.h
@@ -1,8 +1,6 @@
 #ifndef __GEF_PIC_H__
 #define __GEF_PIC_H__
 
-
-void gef_pic_cascade(unsigned int, struct irq_desc *);
 unsigned int gef_pic_get_irq(void);
 void gef_pic_init(struct device_node *);
 
diff --git a/arch/powerpc/sysdev/ipic.c b/arch/powerpc/sysdev/ipic.c
index 6b2b689..b1297ab 100644
--- a/arch/powerpc/sysdev/ipic.c
+++ b/arch/powerpc/sysdev/ipic.c
@@ -624,10 +624,10 @@
 
 	irqd_set_trigger_type(d, flow_type);
 	if (flow_type & IRQ_TYPE_LEVEL_LOW)  {
-		__irq_set_handler_locked(d->irq, handle_level_irq);
+		irq_set_handler_locked(d, handle_level_irq);
 		d->chip = &ipic_level_irq_chip;
 	} else {
-		__irq_set_handler_locked(d->irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 		d->chip = &ipic_edge_irq_chip;
 	}
 
diff --git a/arch/powerpc/sysdev/mpc8xx_pic.c b/arch/powerpc/sysdev/mpc8xx_pic.c
index d93a78be..9a42397 100644
--- a/arch/powerpc/sysdev/mpc8xx_pic.c
+++ b/arch/powerpc/sysdev/mpc8xx_pic.c
@@ -55,7 +55,7 @@
 		unsigned int siel = in_be32(&siu_reg->sc_siel);
 		siel |= mpc8xx_irqd_to_bit(d);
 		out_be32(&siu_reg->sc_siel, siel);
-		__irq_set_handler_locked(d->irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 	}
 	return 0;
 }
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 97a8ae8..537e5db 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -1181,7 +1181,7 @@
 }
 
 /* IRQ handler for a secondary MPIC cascaded from another IRQ controller */
-static void mpic_cascade(unsigned int irq, struct irq_desc *desc)
+static void mpic_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct mpic *mpic = irq_desc_get_handler_data(desc);
diff --git a/arch/powerpc/sysdev/mpic_u3msi.c b/arch/powerpc/sysdev/mpic_u3msi.c
index 70fbd56..2cbc7e2 100644
--- a/arch/powerpc/sysdev/mpic_u3msi.c
+++ b/arch/powerpc/sysdev/mpic_u3msi.c
@@ -107,15 +107,16 @@
 static void u3msi_teardown_msi_irqs(struct pci_dev *pdev)
 {
 	struct msi_desc *entry;
+	irq_hw_number_t hwirq;
 
 	for_each_pci_msi_entry(entry, pdev) {
 		if (entry->irq == NO_IRQ)
 			continue;
 
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap,
-				       virq_to_hw(entry->irq), 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, 1);
 	}
 
 	return;
diff --git a/arch/powerpc/sysdev/ppc4xx_msi.c b/arch/powerpc/sysdev/ppc4xx_msi.c
index 24d0470..8fb8061 100644
--- a/arch/powerpc/sysdev/ppc4xx_msi.c
+++ b/arch/powerpc/sysdev/ppc4xx_msi.c
@@ -124,16 +124,17 @@
 {
 	struct msi_desc *entry;
 	struct ppc4xx_msi *msi_data = &ppc4xx_msi;
+	irq_hw_number_t hwirq;
 
 	dev_dbg(&dev->dev, "PCIE-MSI: tearing down msi irqs\n");
 
 	for_each_pci_msi_entry(entry, dev) {
 		if (entry->irq == NO_IRQ)
 			continue;
+		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
-		msi_bitmap_free_hwirqs(&msi_data->bitmap,
-				virq_to_hw(entry->irq), 1);
 		irq_dispose_mapping(entry->irq);
+		msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
 	}
 }
 
diff --git a/arch/powerpc/sysdev/qe_lib/qe_ic.c b/arch/powerpc/sysdev/qe_lib/qe_ic.c
index 47b352e..fbcc1f8 100644
--- a/arch/powerpc/sysdev/qe_lib/qe_ic.c
+++ b/arch/powerpc/sysdev/qe_lib/qe_ic.c
@@ -311,8 +311,8 @@
 }
 
 void __init qe_ic_init(struct device_node *node, unsigned int flags,
-		void (*low_handler)(unsigned int irq, struct irq_desc *desc),
-		void (*high_handler)(unsigned int irq, struct irq_desc *desc))
+		       void (*low_handler)(struct irq_desc *desc),
+		       void (*high_handler)(struct irq_desc *desc))
 {
 	struct qe_ic *qe_ic;
 	struct resource res;
diff --git a/arch/powerpc/sysdev/tsi108_pci.c b/arch/powerpc/sysdev/tsi108_pci.c
index 57b5447..379de95 100644
--- a/arch/powerpc/sysdev/tsi108_pci.c
+++ b/arch/powerpc/sysdev/tsi108_pci.c
@@ -428,7 +428,7 @@
 	init_pci_source();
 }
 
-void tsi108_irq_cascade(unsigned int irq, struct irq_desc *desc)
+void tsi108_irq_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq = get_pci_source();
diff --git a/arch/powerpc/sysdev/uic.c b/arch/powerpc/sysdev/uic.c
index d773453..6893d8f 100644
--- a/arch/powerpc/sysdev/uic.c
+++ b/arch/powerpc/sysdev/uic.c
@@ -194,7 +194,7 @@
 	.xlate	= irq_domain_xlate_twocell,
 };
 
-void uic_irq_cascade(unsigned int virq, struct irq_desc *desc)
+static void uic_irq_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct irq_data *idata = irq_desc_get_irq_data(desc);
diff --git a/arch/powerpc/sysdev/xics/ics-opal.c b/arch/powerpc/sysdev/xics/ics-opal.c
index 11ac964..27c936c 100644
--- a/arch/powerpc/sysdev/xics/ics-opal.c
+++ b/arch/powerpc/sysdev/xics/ics-opal.c
@@ -54,7 +54,7 @@
 	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
 		return;
 
-	server = xics_get_irq_server(d->irq, d->affinity, 0);
+	server = xics_get_irq_server(d->irq, irq_data_get_affinity_mask(d), 0);
 	server = ics_opal_mangle_server(server);
 
 	rc = opal_set_xive(hw_irq, server, DEFAULT_PRIORITY);
diff --git a/arch/powerpc/sysdev/xics/ics-rtas.c b/arch/powerpc/sysdev/xics/ics-rtas.c
index d1c625c..3854dd4 100644
--- a/arch/powerpc/sysdev/xics/ics-rtas.c
+++ b/arch/powerpc/sysdev/xics/ics-rtas.c
@@ -47,7 +47,7 @@
 	if (hw_irq == XICS_IPI || hw_irq == XICS_IRQ_SPURIOUS)
 		return;
 
-	server = xics_get_irq_server(d->irq, d->affinity, 0);
+	server = xics_get_irq_server(d->irq, irq_data_get_affinity_mask(d), 0);
 
 	call_status = rtas_call(ibm_set_xive, 3, 1, NULL, hw_irq, server,
 				DEFAULT_PRIORITY);
diff --git a/arch/powerpc/sysdev/xilinx_intc.c b/arch/powerpc/sysdev/xilinx_intc.c
index 43b8b27..0f52d79 100644
--- a/arch/powerpc/sysdev/xilinx_intc.c
+++ b/arch/powerpc/sysdev/xilinx_intc.c
@@ -222,7 +222,7 @@
 /*
  * Support code for cascading to 8259 interrupt controllers
  */
-static void xilinx_i8259_cascade(unsigned int irq, struct irq_desc *desc)
+static void xilinx_i8259_cascade(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned int cascade_irq = i8259_irq();
diff --git a/arch/s390/configs/zfcpdump_defconfig b/arch/s390/configs/zfcpdump_defconfig
index 1b0184a..92805d6 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_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 3d012e0..8ced426 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
@@ -210,6 +211,7 @@
 	u32 exit_validity;
 	u32 exit_instruction;
 	u32 halt_successful_poll;
+	u32 halt_attempted_poll;
 	u32 halt_wakeup;
 	u32 instruction_lctl;
 	u32 instruction_lctlg;
diff --git a/arch/s390/include/asm/unistd.h b/arch/s390/include/asm/unistd.h
index 525cef7..02613ba 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 59d2bb4..a848adb 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 eb46642..e0f9d27 100644
--- a/arch/s390/kernel/compat_signal.c
+++ b/arch/s390/kernel/compat_signal.c
@@ -48,6 +48,19 @@
 	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 @@
 {
 	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 @@
 {
 	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 @@
 		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_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 @@
 	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 f8498dd..09f1940 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_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_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(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_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_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_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 247b7aa..09b039d 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -1191,6 +1191,7 @@
 	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 @@
 	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 56fdad4..a956340 100644
--- a/arch/s390/kernel/perf_cpum_cf.c
+++ b/arch/s390/kernel/perf_cpum_cf.c
@@ -157,10 +157,14 @@
 
 	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 @@
 	 */
 	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 @@
 	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 ca62946..2d6b6e8 100644
--- a/arch/s390/kernel/swsusp.S
+++ b/arch/s390/kernel/swsusp.S
@@ -30,6 +30,9 @@
 	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 @@
 
 	/* 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 @@
 	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 f3f4a13..8c56929 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_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 @@
 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_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_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_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_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_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_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_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_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_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 b9ce650..c865343 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -89,17 +89,21 @@
 	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/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index c91eb94..0a67c40 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -63,6 +63,7 @@
 	{ "exit_program_interruption", VCPU_STAT(exit_program_interruption) },
 	{ "exit_instr_and_program_int", VCPU_STAT(exit_instr_and_program) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
+	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "instruction_lctlg", VCPU_STAT(instruction_lctlg) },
 	{ "instruction_lctl", VCPU_STAT(instruction_lctl) },
@@ -1574,7 +1575,7 @@
 
 static void kvm_s390_vcpu_request_handled(struct kvm_vcpu *vcpu)
 {
-	atomic_or(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
+	atomic_andnot(PROG_REQUEST, &vcpu->arch.sie_block->prog20);
 }
 
 /*
diff --git a/arch/sh/boards/mach-se/7343/irq.c b/arch/sh/boards/mach-se/7343/irq.c
index 6f97a8f..6129aef 100644
--- a/arch/sh/boards/mach-se/7343/irq.c
+++ b/arch/sh/boards/mach-se/7343/irq.c
@@ -29,7 +29,7 @@
 static void __iomem *se7343_irq_regs;
 struct irq_domain *se7343_irq_domain;
 
-static void se7343_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void se7343_irq_demux(struct irq_desc *desc)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
diff --git a/arch/sh/boards/mach-se/7722/irq.c b/arch/sh/boards/mach-se/7722/irq.c
index 60aebd1..24c74a8 100644
--- a/arch/sh/boards/mach-se/7722/irq.c
+++ b/arch/sh/boards/mach-se/7722/irq.c
@@ -28,7 +28,7 @@
 static void __iomem *se7722_irq_regs;
 struct irq_domain *se7722_irq_domain;
 
-static void se7722_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void se7722_irq_demux(struct irq_desc *desc)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
diff --git a/arch/sh/boards/mach-se/7724/irq.c b/arch/sh/boards/mach-se/7724/irq.c
index 9f20338..64e681e 100644
--- a/arch/sh/boards/mach-se/7724/irq.c
+++ b/arch/sh/boards/mach-se/7724/irq.c
@@ -92,7 +92,7 @@
 	.irq_unmask	= enable_se7724_irq,
 };
 
-static void se7724_irq_demux(unsigned int __irq, struct irq_desc *desc)
+static void se7724_irq_demux(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct fpga_irq set = get_fpga_irq(irq);
diff --git a/arch/sh/boards/mach-x3proto/gpio.c b/arch/sh/boards/mach-x3proto/gpio.c
index 24555c3..1fb2cbe 100644
--- a/arch/sh/boards/mach-x3proto/gpio.c
+++ b/arch/sh/boards/mach-x3proto/gpio.c
@@ -60,7 +60,7 @@
 	return virq;
 }
 
-static void x3proto_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void x3proto_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct irq_chip *chip = irq_data_get_irq_chip(data);
diff --git a/arch/sh/cchips/hd6446x/hd64461.c b/arch/sh/cchips/hd6446x/hd64461.c
index e973561..8180092 100644
--- a/arch/sh/cchips/hd6446x/hd64461.c
+++ b/arch/sh/cchips/hd6446x/hd64461.c
@@ -56,7 +56,7 @@
 	.irq_unmask	= hd64461_unmask_irq,
 };
 
-static void hd64461_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void hd64461_irq_demux(struct irq_desc *desc)
 {
 	unsigned short intv = __raw_readw(HD64461_NIRR);
 	unsigned int ext_irq = HD64461_IRQBASE;
diff --git a/arch/sparc/kernel/leon_kernel.c b/arch/sparc/kernel/leon_kernel.c
index 0299f05..42efcf8 100644
--- a/arch/sparc/kernel/leon_kernel.c
+++ b/arch/sparc/kernel/leon_kernel.c
@@ -53,7 +53,7 @@
 }
 
 /* Handle one or multiple IRQs from the extended interrupt controller */
-static void leon_handle_ext_irq(unsigned int irq, struct irq_desc *desc)
+static void leon_handle_ext_irq(struct irq_desc *desc)
 {
 	unsigned int eirq;
 	struct irq_bucket *p;
diff --git a/arch/sparc/kernel/leon_pci_grpci1.c b/arch/sparc/kernel/leon_pci_grpci1.c
index 3382f7b..1e77128 100644
--- a/arch/sparc/kernel/leon_pci_grpci1.c
+++ b/arch/sparc/kernel/leon_pci_grpci1.c
@@ -357,7 +357,7 @@
 };
 
 /* Handle one or multiple IRQs from the PCI core */
-static void grpci1_pci_flow_irq(unsigned int irq, struct irq_desc *desc)
+static void grpci1_pci_flow_irq(struct irq_desc *desc)
 {
 	struct grpci1_priv *priv = grpci1priv;
 	int i, ack = 0;
diff --git a/arch/sparc/kernel/leon_pci_grpci2.c b/arch/sparc/kernel/leon_pci_grpci2.c
index 814fb17..f727c4d 100644
--- a/arch/sparc/kernel/leon_pci_grpci2.c
+++ b/arch/sparc/kernel/leon_pci_grpci2.c
@@ -498,7 +498,7 @@
 };
 
 /* Handle one or multiple IRQs from the PCI core */
-static void grpci2_pci_flow_irq(unsigned int irq, struct irq_desc *desc)
+static void grpci2_pci_flow_irq(struct irq_desc *desc)
 {
 	struct grpci2_priv *priv = grpci2priv;
 	int i, ack = 0;
diff --git a/arch/tile/kernel/pci_gx.c b/arch/tile/kernel/pci_gx.c
index b3f73fd..4c017d0 100644
--- a/arch/tile/kernel/pci_gx.c
+++ b/arch/tile/kernel/pci_gx.c
@@ -304,17 +304,16 @@
  * to Linux which just calls handle_level_irq() after clearing the
  * MAC INTx Assert status bit associated with this interrupt.
  */
-static void trio_handle_level_irq(unsigned int __irq, struct irq_desc *desc)
+static void trio_handle_level_irq(struct irq_desc *desc)
 {
 	struct pci_controller *controller = irq_desc_get_handler_data(desc);
 	gxio_trio_context_t *trio_context = controller->trio;
 	uint64_t intx = (uint64_t)irq_desc_get_chip_data(desc);
-	unsigned int irq = irq_desc_get_irq(desc);
 	int mac = controller->mac;
 	unsigned int reg_offset;
 	uint64_t level_mask;
 
-	handle_level_irq(irq, desc);
+	handle_level_irq(desc);
 
 	/*
 	 * Clear the INTx Level status, otherwise future interrupts are
diff --git a/arch/unicore32/kernel/irq.c b/arch/unicore32/kernel/irq.c
index c53729d..eb1fd00 100644
--- a/arch/unicore32/kernel/irq.c
+++ b/arch/unicore32/kernel/irq.c
@@ -112,7 +112,7 @@
  * irq_controller_lock held, and IRQs disabled.  Decode the IRQ
  * and call the handler.
  */
-static void puv3_gpio_handler(unsigned int __irq, struct irq_desc *desc)
+static void puv3_gpio_handler(struct irq_desc *desc)
 {
 	unsigned int mask, irq;
 
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 7aef2d5..328c835 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1006,7 +1006,7 @@
 	depends on X86_MCE_INTEL
 
 config X86_LEGACY_VM86
-	bool "Legacy VM86 support (obsolete)"
+	bool "Legacy VM86 support"
 	default n
 	depends on X86_32
 	---help---
@@ -1018,19 +1018,20 @@
 	  available to accelerate real mode DOS programs.  However, any
 	  recent version of DOSEMU, X, or vbetool should be fully
 	  functional even without kernel VM86 support, as they will all
-	  fall back to (pretty well performing) software emulation.
+	  fall back to software emulation. Nevertheless, if you are using
+	  a 16-bit DOS program where 16-bit performance matters, vm86
+	  mode might be faster than emulation and you might want to
+	  enable this option.
 
-	  Anything that works on a 64-bit kernel is unlikely to need
-	  this option, as 64-bit kernels don't, and can't, support V8086
-	  mode.  This option is also unrelated to 16-bit protected mode
-	  and is not needed to run most 16-bit programs under Wine.
+	  Note that any app that works on a 64-bit kernel is unlikely to
+	  need this option, as 64-bit kernels don't, and can't, support
+	  V8086 mode. This option is also unrelated to 16-bit protected
+	  mode and is not needed to run most 16-bit programs under Wine.
 
-	  Enabling this option adds considerable attack surface to the
-	  kernel and slows down system calls and exception handling.
+	  Enabling this option increases the complexity of the kernel
+	  and slows down exception handling a tiny bit.
 
-	  Unless you use very old userspace or need the last drop of
-	  performance in your real mode DOS games and can't use KVM,
-	  say N here.
+	  If unsure, say N here.
 
 config VM86
        bool
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 477fc28..e6cf2ad 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -241,6 +241,7 @@
 #define X86_FEATURE_AVX512PF	( 9*32+26) /* AVX-512 Prefetch */
 #define X86_FEATURE_AVX512ER	( 9*32+27) /* AVX-512 Exponential and Reciprocal */
 #define X86_FEATURE_AVX512CD	( 9*32+28) /* AVX-512 Conflict Detection */
+#define X86_FEATURE_SHA_NI	( 9*32+29) /* SHA1/SHA256 Instruction Extensions */
 
 /* Extended state features, CPUID level 0x0000000d:1 (eax), word 10 */
 #define X86_FEATURE_XSAVEOPT	(10*32+ 0) /* XSAVEOPT */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 155162e..ab5f1d4 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -86,6 +86,16 @@
 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 c12e845..2beee03 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
 
@@ -711,6 +712,7 @@
 	u32 nmi_window_exits;
 	u32 halt_exits;
 	u32 halt_successful_poll;
+	u32 halt_attempted_poll;
 	u32 halt_wakeup;
 	u32 request_irq_exits;
 	u32 irq_exits;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index c1c0a1c..b98b471 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/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index ce029e4..31247b5 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -97,7 +97,6 @@
 struct pv_time_ops {
 	unsigned long long (*sched_clock)(void);
 	unsigned long long (*steal_clock)(int cpu);
-	unsigned long (*get_tsc_khz)(void);
 };
 
 struct pv_cpu_ops {
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 9d51fae..eaba080 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -39,18 +39,27 @@
 }
 #endif
 
-#define virt_queued_spin_lock virt_queued_spin_lock
-
-static inline bool virt_queued_spin_lock(struct qspinlock *lock)
+#ifdef CONFIG_PARAVIRT
+#define virt_spin_lock virt_spin_lock
+static inline bool virt_spin_lock(struct qspinlock *lock)
 {
 	if (!static_cpu_has(X86_FEATURE_HYPERVISOR))
 		return false;
 
-	while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0)
-		cpu_relax();
+	/*
+	 * On hypervisors without PARAVIRT_SPINLOCKS support we fall
+	 * back to a Test-and-Set spinlock, because fair locks have
+	 * horrible lock 'holder' preemption issues.
+	 */
+
+	do {
+		while (atomic_read(&lock->val) != 0)
+			cpu_relax();
+	} while (atomic_cmpxchg(&lock->val, 0, _Q_LOCKED_VAL) != 0);
 
 	return true;
 }
+#endif /* CONFIG_PARAVIRT */
 
 #include <asm-generic/qspinlock.h>
 
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index c42827e..25f9093 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -338,10 +338,15 @@
 
 static void __init_or_module optimize_nops(struct alt_instr *a, u8 *instr)
 {
+	unsigned long flags;
+
 	if (instr[0] != 0x90)
 		return;
 
+	local_irq_save(flags);
 	add_nops(instr + (a->instrlen - a->padlen), a->padlen);
+	sync_core();
+	local_irq_restore(flags);
 
 	DUMP_BYTES(instr, a->instrlen, "%p: [%d:%d) optimized NOPs: ",
 		   instr, a->instrlen - a->padlen, a->padlen);
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3ca3e46..24e94ce 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -336,6 +336,13 @@
 	apic_write(APIC_LVTT, lvtt_value);
 
 	if (lvtt_value & APIC_LVT_TIMER_TSCDEADLINE) {
+		/*
+		 * See Intel SDM: TSC-Deadline Mode chapter. In xAPIC mode,
+		 * writing to the APIC LVTT and TSC_DEADLINE MSR isn't serialized.
+		 * According to Intel, MFENCE can do the serialization here.
+		 */
+		asm volatile("mfence" : : : "memory");
+
 		printk_once(KERN_DEBUG "TSC deadline timer enabled\n");
 		return;
 	}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 38a76f8..5c60bb1 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2522,6 +2522,7 @@
 	int pin, ioapic, irq, irq_entry;
 	const struct cpumask *mask;
 	struct irq_data *idata;
+	struct irq_chip *chip;
 
 	if (skip_ioapic_setup == 1)
 		return;
@@ -2545,9 +2546,9 @@
 		else
 			mask = apic->target_cpus();
 
-		irq_set_affinity(irq, mask);
+		chip = irq_data_get_irq_chip(idata);
+		chip->irq_set_affinity(idata, mask, false);
 	}
-
 }
 #endif
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 1bbd0fe..836d11b 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -489,10 +489,8 @@
 
 	err = assign_irq_vector(irq, data, dest);
 	if (err) {
-		struct irq_data *top = irq_get_irq_data(irq);
-
 		if (assign_irq_vector(irq, data,
-				      irq_data_get_affinity_mask(top)))
+				      irq_data_get_affinity_mask(irq_data)))
 			pr_err("Failed to recover vector for irq %d\n", irq);
 		return err;
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 07ce52c..de22ea7 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1110,10 +1110,10 @@
 	else
 		printk(KERN_CONT "%d86", c->x86);
 
-	printk(KERN_CONT " (fam: %02x, model: %02x", c->x86, c->x86_model);
+	printk(KERN_CONT " (family: 0x%x, model: 0x%x", c->x86, c->x86_model);
 
 	if (c->x86_mask || c->cpuid_level >= 0)
-		printk(KERN_CONT ", stepping: %02x)\n", c->x86_mask);
+		printk(KERN_CONT ", stepping: 0x%x)\n", c->x86_mask);
 	else
 		printk(KERN_CONT ")\n");
 
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index cd9b6d0..3fefebf 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -2316,9 +2316,12 @@
 intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
 			    struct perf_event *event)
 {
-	struct event_constraint *c1 = cpuc->event_constraint[idx];
+	struct event_constraint *c1 = NULL;
 	struct event_constraint *c2;
 
+	if (idx >= 0) /* fake does < 0 */
+		c1 = cpuc->event_constraint[idx];
+
 	/*
 	 * first time only
 	 * - static constraint: no change across incremental scheduling calls
diff --git a/arch/x86/kernel/cpu/perf_event_intel_bts.c b/arch/x86/kernel/cpu/perf_event_intel_bts.c
index 54690e8..d1c0f25 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_bts.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_bts.c
@@ -222,6 +222,7 @@
 	if (!buf || bts_buffer_is_full(buf, bts))
 		return;
 
+	event->hw.itrace_started = 1;
 	event->hw.state = 0;
 
 	if (!buf->snapshot)
diff --git a/arch/x86/kernel/irq_32.c b/arch/x86/kernel/irq_32.c
index c80cf66..38da8f2 100644
--- a/arch/x86/kernel/irq_32.c
+++ b/arch/x86/kernel/irq_32.c
@@ -68,11 +68,10 @@
 	return (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
 }
 
-static inline int
-execute_on_irq_stack(int overflow, struct irq_desc *desc, int irq)
+static inline int execute_on_irq_stack(int overflow, struct irq_desc *desc)
 {
 	struct irq_stack *curstk, *irqstk;
-	u32 *isp, *prev_esp, arg1, arg2;
+	u32 *isp, *prev_esp, arg1;
 
 	curstk = (struct irq_stack *) current_stack();
 	irqstk = __this_cpu_read(hardirq_stack);
@@ -98,8 +97,8 @@
 	asm volatile("xchgl	%%ebx,%%esp	\n"
 		     "call	*%%edi		\n"
 		     "movl	%%ebx,%%esp	\n"
-		     : "=a" (arg1), "=d" (arg2), "=b" (isp)
-		     :  "0" (irq),   "1" (desc),  "2" (isp),
+		     : "=a" (arg1), "=b" (isp)
+		     :  "0" (desc),   "1" (isp),
 			"D" (desc->handle_irq)
 		     : "memory", "cc", "ecx");
 	return 1;
@@ -150,19 +149,15 @@
 
 bool handle_irq(struct irq_desc *desc, struct pt_regs *regs)
 {
-	unsigned int irq;
-	int overflow;
-
-	overflow = check_stack_overflow();
+	int overflow = check_stack_overflow();
 
 	if (IS_ERR_OR_NULL(desc))
 		return false;
 
-	irq = irq_desc_get_irq(desc);
-	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc, irq)) {
+	if (user_mode(regs) || !execute_on_irq_stack(overflow, desc)) {
 		if (unlikely(overflow))
 			print_stack_overflow();
-		generic_handle_irq_desc(irq, desc);
+		generic_handle_irq_desc(desc);
 	}
 
 	return true;
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ff16ccb..c767cf2 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -75,6 +75,6 @@
 	if (unlikely(IS_ERR_OR_NULL(desc)))
 		return false;
 
-	generic_handle_irq_desc(irq_desc_get_irq(desc), desc);
+	generic_handle_irq_desc(desc);
 	return true;
 }
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index 2bcc052..6acc9dd 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -58,7 +58,7 @@
 	if (alloc_size > PAGE_SIZE)
 		new_ldt->entries = vzalloc(alloc_size);
 	else
-		new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
+		new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL);
 
 	if (!new_ldt->entries) {
 		kfree(new_ldt);
@@ -95,7 +95,7 @@
 	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
 		vfree(ldt->entries);
 	else
-		kfree(ldt->entries);
+		free_page((unsigned long)ldt->entries);
 	kfree(ldt);
 }
 
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 84b8ef8..1b55de1 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -131,8 +131,8 @@
 
 bool arch_dma_alloc_attrs(struct device **dev, gfp_t *gfp)
 {
-	*gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
 	*gfp &= ~(__GFP_DMA | __GFP_HIGHMEM | __GFP_DMA32);
+	*gfp = dma_alloc_coherent_gfp_flags(*dev, *gfp);
 
 	if (!*dev)
 		*dev = &x86_dma_fallback_dev;
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index c8d52cb..c3f7602 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -21,6 +21,7 @@
 #include <asm/hypervisor.h>
 #include <asm/nmi.h>
 #include <asm/x86_init.h>
+#include <asm/geode.h>
 
 unsigned int __read_mostly cpu_khz;	/* TSC clocks / usec, not used here */
 EXPORT_SYMBOL(cpu_khz);
@@ -1013,15 +1014,17 @@
 
 static void __init check_system_tsc_reliable(void)
 {
-#ifdef CONFIG_MGEODE_LX
-	/* RTSC counts during suspend */
+#if defined(CONFIG_MGEODEGX1) || defined(CONFIG_MGEODE_LX) || defined(CONFIG_X86_GENERIC)
+	if (is_geode_lx()) {
+		/* RTSC counts during suspend */
 #define RTSC_SUSP 0x100
-	unsigned long res_low, res_high;
+		unsigned long res_low, res_high;
 
-	rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
-	/* Geode_LX - the OLPC CPU has a very reliable TSC */
-	if (res_low & RTSC_SUSP)
-		tsc_clocksource_reliable = 1;
+		rdmsr_safe(MSR_GEODE_BUSCONT_CONF0, &res_low, &res_high);
+		/* Geode_LX - the OLPC CPU has a very reliable TSC */
+		if (res_low & RTSC_SUSP)
+			tsc_clocksource_reliable = 1;
+	}
 #endif
 	if (boot_cpu_has(X86_FEATURE_TSC_RELIABLE))
 		tsc_clocksource_reliable = 1;
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index abd8b856..5246193 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -45,6 +45,7 @@
 #include <linux/audit.h>
 #include <linux/stddef.h>
 #include <linux/slab.h>
+#include <linux/security.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -232,6 +233,32 @@
 	struct pt_regs *regs = current_pt_regs();
 	unsigned long err = 0;
 
+	err = security_mmap_addr(0);
+	if (err) {
+		/*
+		 * vm86 cannot virtualize the address space, so vm86 users
+		 * need to manage the low 1MB themselves using mmap.  Given
+		 * that BIOS places important data in the first page, vm86
+		 * is essentially useless if mmap_min_addr != 0.  DOSEMU,
+		 * for example, won't even bother trying to use vm86 if it
+		 * can't map a page at virtual address 0.
+		 *
+		 * To reduce the available kernel attack surface, simply
+		 * disallow vm86(old) for users who cannot mmap at va 0.
+		 *
+		 * The implementation of security_mmap_addr will allow
+		 * suitably privileged users to map va 0 even if
+		 * vm.mmap_min_addr is set above 0, and we want this
+		 * behavior for vm86 as well, as it ensures that legacy
+		 * tools like vbetool will not fail just because of
+		 * vm.mmap_min_addr.
+		 */
+		pr_info_once("Denied a call to vm86(old) from %s[%d] (uid: %d).  Set the vm.mmap_min_addr sysctl to 0 and/or adjust LSM mmap_min_addr policy to enable vm86 if you are using a vm86-based DOS emulator.\n",
+			     current->comm, task_pid_nr(current),
+			     from_kuid_munged(&init_user_ns, current_uid()));
+		return -EPERM;
+	}
+
 	if (!vm86) {
 		if (!(vm86 = kzalloc(sizeof(*vm86), GFP_KERNEL)))
 			return -ENOMEM;
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index 69088a1..ff606f5 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3322,7 +3322,7 @@
 			break;
 
 		reserved |= is_shadow_zero_bits_set(&vcpu->arch.mmu, spte,
-						    leaf);
+						    iterator.level);
 	}
 
 	walk_shadow_page_lockless_end(vcpu);
@@ -3614,7 +3614,7 @@
 __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 @@
 	 * 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 @@
 	__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 @@
 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 @@
 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 fdb8cb6..94b7d15 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -202,6 +202,7 @@
 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 @@
 	 * 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/vmx.c b/arch/x86/kvm/vmx.c
index d019868..6407674 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -6064,6 +6064,8 @@
 	memcpy(vmx_msr_bitmap_longmode_x2apic,
 			vmx_msr_bitmap_longmode, PAGE_SIZE);
 
+	set_bit(0, vmx_vpid_bitmap); /* 0 is reserved for host */
+
 	if (enable_apicv) {
 		for (msr = 0x800; msr <= 0x8ff; msr++)
 			vmx_disable_intercept_msr_read_x2apic(msr);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index a60bdbc..991466b 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -149,6 +149,7 @@
 	{ "nmi_window", VCPU_STAT(nmi_window_exits) },
 	{ "halt_exits", VCPU_STAT(halt_exits) },
 	{ "halt_successful_poll", VCPU_STAT(halt_successful_poll) },
+	{ "halt_attempted_poll", VCPU_STAT(halt_attempted_poll) },
 	{ "halt_wakeup", VCPU_STAT(halt_wakeup) },
 	{ "hypercalls", VCPU_STAT(hypercalls) },
 	{ "request_irq", VCPU_STAT(request_irq_exits) },
@@ -2189,6 +2190,8 @@
 	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/lguest/boot.c b/arch/x86/lguest/boot.c
index 161804d..a0d09f6 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1015,7 +1015,7 @@
  * This is the Guest timer interrupt handler (hardware interrupt 0).  We just
  * call the clockevent infrastructure and it does whatever needs doing.
  */
-static void lguest_time_irq(unsigned int irq, struct irq_desc *desc)
+static void lguest_time_irq(struct irq_desc *desc)
 {
 	unsigned long flags;
 
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 66338a6..c2aea63 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -192,10 +192,11 @@
 
 	node_set(node, numa_nodes_parsed);
 
-	pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s\n",
+	pr_info("SRAT: Node %u PXM %u [mem %#010Lx-%#010Lx]%s%s\n",
 		node, pxm,
 		(unsigned long long) start, (unsigned long long) end - 1,
-		hotpluggable ? " hotplug" : "");
+		hotpluggable ? " hotplug" : "",
+		ma->flags & ACPI_SRAT_MEM_NON_VOLATILE ? " non-volatile" : "");
 
 	/* Mark hotplug range in memblock. */
 	if (hotpluggable && memblock_mark_hotplug(start, ma->length))
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 09d3afc..dc78a4a 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -166,6 +166,7 @@
 {
 	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 d27b4dc..b848cc3 100644
--- a/arch/xtensa/kernel/pci.c
+++ b/arch/xtensa/kernel/pci.c
@@ -210,6 +210,10 @@
 
 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/block/bio-integrity.c b/block/bio-integrity.c
index 4aecca7..14b8faf 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -140,6 +140,11 @@
 
 	iv = bip->bip_vec + bip->bip_vcnt;
 
+	if (bip->bip_vcnt &&
+	    bvec_gap_to_prev(bdev_get_queue(bio->bi_bdev),
+			     &bip->bip_vec[bip->bip_vcnt - 1], offset))
+		return 0;
+
 	iv->bv_page = page;
 	iv->bv_len = len;
 	iv->bv_offset = offset;
diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index ac8370c..55512dd 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -370,6 +370,9 @@
 		blkg_destroy(blkg);
 		spin_unlock(&blkcg->lock);
 	}
+
+	q->root_blkg = NULL;
+	q->root_rl.blkg = NULL;
 }
 
 /*
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index f548b64..75f29cf 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -204,6 +204,9 @@
 	    q->limits.max_integrity_segments)
 		return false;
 
+	if (integrity_req_gap_back_merge(req, next->bio))
+		return false;
+
 	return true;
 }
 EXPORT_SYMBOL(blk_integrity_merge_rq);
diff --git a/block/blk-map.c b/block/blk-map.c
index 2338416..f565e11 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -9,6 +9,24 @@
 
 #include "blk.h"
 
+static bool iovec_gap_to_prv(struct request_queue *q,
+			     struct iovec *prv, struct iovec *cur)
+{
+	unsigned long prev_end;
+
+	if (!queue_virt_boundary(q))
+		return false;
+
+	if (prv->iov_base == NULL && prv->iov_len == 0)
+		/* prv is not set - don't check */
+		return false;
+
+	prev_end = (unsigned long)(prv->iov_base + prv->iov_len);
+
+	return (((unsigned long)cur->iov_base & queue_virt_boundary(q)) ||
+		prev_end & queue_virt_boundary(q));
+}
+
 int blk_rq_append_bio(struct request_queue *q, struct request *rq,
 		      struct bio *bio)
 {
@@ -67,7 +85,7 @@
 	struct bio *bio;
 	int unaligned = 0;
 	struct iov_iter i;
-	struct iovec iov;
+	struct iovec iov, prv = {.iov_base = NULL, .iov_len = 0};
 
 	if (!iter || !iter->count)
 		return -EINVAL;
@@ -81,8 +99,12 @@
 		/*
 		 * Keep going so we check length of all segments
 		 */
-		if (uaddr & queue_dma_alignment(q))
+		if ((uaddr & queue_dma_alignment(q)) ||
+		    iovec_gap_to_prv(q, &prv, &iov))
 			unaligned = 1;
+
+		prv.iov_base = iov.iov_base;
+		prv.iov_len = iov.iov_len;
 	}
 
 	if (unaligned || (q->dma_pad_mask & iter->count) || map_data)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index d088cff..c4e9c37 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -66,36 +66,33 @@
 					 struct bio *bio,
 					 struct bio_set *bs)
 {
-	struct bio *split;
-	struct bio_vec bv, bvprv;
+	struct bio_vec bv, bvprv, *bvprvp = NULL;
 	struct bvec_iter iter;
 	unsigned seg_size = 0, nsegs = 0, sectors = 0;
-	int prev = 0;
 
 	bio_for_each_segment(bv, bio, iter) {
-		sectors += bv.bv_len >> 9;
-
-		if (sectors > queue_max_sectors(q))
+		if (sectors + (bv.bv_len >> 9) > queue_max_sectors(q))
 			goto split;
 
 		/*
 		 * If the queue doesn't support SG gaps and adding this
 		 * offset would create a gap, disallow it.
 		 */
-		if (prev && bvec_gap_to_prev(q, &bvprv, bv.bv_offset))
+		if (bvprvp && bvec_gap_to_prev(q, bvprvp, bv.bv_offset))
 			goto split;
 
-		if (prev && blk_queue_cluster(q)) {
+		if (bvprvp && blk_queue_cluster(q)) {
 			if (seg_size + bv.bv_len > queue_max_segment_size(q))
 				goto new_segment;
-			if (!BIOVEC_PHYS_MERGEABLE(&bvprv, &bv))
+			if (!BIOVEC_PHYS_MERGEABLE(bvprvp, &bv))
 				goto new_segment;
-			if (!BIOVEC_SEG_BOUNDARY(q, &bvprv, &bv))
+			if (!BIOVEC_SEG_BOUNDARY(q, bvprvp, &bv))
 				goto new_segment;
 
 			seg_size += bv.bv_len;
 			bvprv = bv;
-			prev = 1;
+			bvprvp = &bv;
+			sectors += bv.bv_len >> 9;
 			continue;
 		}
 new_segment:
@@ -104,23 +101,14 @@
 
 		nsegs++;
 		bvprv = bv;
-		prev = 1;
+		bvprvp = &bv;
 		seg_size = bv.bv_len;
+		sectors += bv.bv_len >> 9;
 	}
 
 	return NULL;
 split:
-	split = bio_clone_bioset(bio, GFP_NOIO, bs);
-
-	split->bi_iter.bi_size -= iter.bi_size;
-	bio->bi_iter = iter;
-
-	if (bio_integrity(bio)) {
-		bio_integrity_advance(bio, split->bi_iter.bi_size);
-		bio_integrity_trim(split, 0, bio_sectors(split));
-	}
-
-	return split;
+	return bio_split(bio, sectors, GFP_NOIO, bs);
 }
 
 void blk_queue_split(struct request_queue *q, struct bio **bio,
@@ -439,6 +427,11 @@
 int ll_back_merge_fn(struct request_queue *q, struct request *req,
 		     struct bio *bio)
 {
+	if (req_gap_back_merge(req, bio))
+		return 0;
+	if (blk_integrity_rq(req) &&
+	    integrity_req_gap_back_merge(req, bio))
+		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req)) {
 		req->cmd_flags |= REQ_NOMERGE;
@@ -457,6 +450,12 @@
 int ll_front_merge_fn(struct request_queue *q, struct request *req,
 		      struct bio *bio)
 {
+
+	if (req_gap_front_merge(req, bio))
+		return 0;
+	if (blk_integrity_rq(req) &&
+	    integrity_req_gap_front_merge(req, bio))
+		return 0;
 	if (blk_rq_sectors(req) + bio_sectors(bio) >
 	    blk_rq_get_max_sectors(req)) {
 		req->cmd_flags |= REQ_NOMERGE;
@@ -483,14 +482,6 @@
 	return !q->mq_ops && req->special;
 }
 
-static int req_gap_to_prev(struct request *req, struct bio *next)
-{
-	struct bio *prev = req->biotail;
-
-	return bvec_gap_to_prev(req->q, &prev->bi_io_vec[prev->bi_vcnt - 1],
-			next->bi_io_vec[0].bv_offset);
-}
-
 static int ll_merge_requests_fn(struct request_queue *q, struct request *req,
 				struct request *next)
 {
@@ -505,7 +496,7 @@
 	if (req_no_special_merge(req) || req_no_special_merge(next))
 		return 0;
 
-	if (req_gap_to_prev(req, next->bio))
+	if (req_gap_back_merge(req, next->bio))
 		return 0;
 
 	/*
@@ -713,10 +704,6 @@
 	    !blk_write_same_mergeable(rq->bio, bio))
 		return false;
 
-	/* Only check gaps if the bio carries data */
-	if (bio_has_data(bio) && req_gap_to_prev(rq, bio))
-		return false;
-
 	return true;
 }
 
diff --git a/block/bounce.c b/block/bounce.c
index 0611aea..1cb5dd3 100644
--- a/block/bounce.c
+++ b/block/bounce.c
@@ -128,12 +128,14 @@
 	struct bio *bio_orig = bio->bi_private;
 	struct bio_vec *bvec, *org_vec;
 	int i;
+	int start = bio_orig->bi_iter.bi_idx;
 
 	/*
 	 * free up bounce indirect pages used
 	 */
 	bio_for_each_segment_all(bvec, bio, i) {
-		org_vec = bio_orig->bi_io_vec + i;
+		org_vec = bio_orig->bi_io_vec + i + start;
+
 		if (bvec->bv_page == org_vec->bv_page)
 			continue;
 
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index 35c2de1..fa18753 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -940,6 +940,7 @@
 	char *xbuf[XBUFSIZE];
 	char *xoutbuf[XBUFSIZE];
 	int ret = -ENOMEM;
+	unsigned int ivsize = crypto_skcipher_ivsize(tfm);
 
 	if (testmgr_alloc_buf(xbuf))
 		goto out_nobuf;
@@ -975,7 +976,7 @@
 			continue;
 
 		if (template[i].iv)
-			memcpy(iv, template[i].iv, MAX_IVLEN);
+			memcpy(iv, template[i].iv, ivsize);
 		else
 			memset(iv, 0, MAX_IVLEN);
 
@@ -1051,7 +1052,7 @@
 			continue;
 
 		if (template[i].iv)
-			memcpy(iv, template[i].iv, MAX_IVLEN);
+			memcpy(iv, template[i].iv, ivsize);
 		else
 			memset(iv, 0, MAX_IVLEN);
 
diff --git a/drivers/acpi/bus.c b/drivers/acpi/bus.c
index 46506e7..a212cef 100644
--- a/drivers/acpi/bus.c
+++ b/drivers/acpi/bus.c
@@ -315,14 +315,10 @@
 
 	capbuf[OSC_QUERY_DWORD] = OSC_QUERY_ENABLE;
 	capbuf[OSC_SUPPORT_DWORD] = OSC_SB_PR3_SUPPORT; /* _PR3 is in use */
-#if defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) ||\
-			defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
-	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PAD_SUPPORT;
-#endif
-
-#if defined(CONFIG_ACPI_PROCESSOR) || defined(CONFIG_ACPI_PROCESSOR_MODULE)
-	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT;
-#endif
+	if (IS_ENABLED(CONFIG_ACPI_PROCESSOR_AGGREGATOR))
+		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PAD_SUPPORT;
+	if (IS_ENABLED(CONFIG_ACPI_PROCESSOR))
+		capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_PPC_OST_SUPPORT;
 
 	capbuf[OSC_SUPPORT_DWORD] |= OSC_SB_HOTPLUG_OST_SUPPORT;
 
diff --git a/drivers/acpi/int340x_thermal.c b/drivers/acpi/int340x_thermal.c
index 9dcf836..33505c6 100644
--- a/drivers/acpi/int340x_thermal.c
+++ b/drivers/acpi/int340x_thermal.c
@@ -33,13 +33,12 @@
 static int int340x_thermal_handler_attach(struct acpi_device *adev,
 					const struct acpi_device_id *id)
 {
-#if defined(CONFIG_INT340X_THERMAL) || defined(CONFIG_INT340X_THERMAL_MODULE)
-	acpi_create_platform_device(adev);
-#elif defined(INTEL_SOC_DTS_THERMAL) || defined(INTEL_SOC_DTS_THERMAL_MODULE)
-	/* Intel SoC DTS thermal driver needs INT3401 to set IRQ descriptor */
-	if (id->driver_data == INT3401_DEVICE)
+	if (IS_ENABLED(CONFIG_INT340X_THERMAL))
 		acpi_create_platform_device(adev);
-#endif
+	/* Intel SoC DTS thermal driver needs INT3401 to set IRQ descriptor */
+	else if (IS_ENABLED(CONFIG_INTEL_SOC_DTS_THERMAL) &&
+		 id->driver_data == INT3401_DEVICE)
+		acpi_create_platform_device(adev);
 	return 1;
 }
 
diff --git a/drivers/atm/he.c b/drivers/atm/he.c
index a8da3a5..0f5cb37 100644
--- a/drivers/atm/he.c
+++ b/drivers/atm/he.c
@@ -1578,9 +1578,7 @@
 
 	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 @@
 		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 74e18b0..3d7fb65 100644
--- a/drivers/atm/solos-pci.c
+++ b/drivers/atm/solos-pci.c
@@ -805,7 +805,12 @@
 					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 @@
 		/* 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 764280a..e9fd32e 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -148,7 +148,11 @@
 
 			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 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 @@
 		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/base/platform-msi.c b/drivers/base/platform-msi.c
index 1857a5d..134483d 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -63,20 +63,8 @@
 			     unsigned int virq, irq_hw_number_t hwirq,
 			     msi_alloc_info_t *arg)
 {
-	struct irq_data *data;
-
-	irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
-				      info->chip, info->chip_data);
-
-	/*
-	 * Save the MSI descriptor in handler_data so that the
-	 * irq_write_msi_msg callback can retrieve it (and the
-	 * associated device).
-	 */
-	data = irq_domain_get_irq_data(domain, virq);
-	data->handler_data = arg->desc;
-
-	return 0;
+	return irq_domain_set_hwirq_and_chip(domain, virq, hwirq,
+					     info->chip, info->chip_data);
 }
 #else
 #define platform_msi_set_desc		NULL
@@ -97,7 +85,7 @@
 
 static void platform_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct msi_desc *desc = irq_data_get_irq_handler_data(data);
+	struct msi_desc *desc = irq_data_get_msi_desc(data);
 	struct platform_msi_priv_data *priv_data;
 
 	priv_data = desc->platform.msi_priv_data;
diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c
index 17269a3..a295b98 100644
--- a/drivers/block/null_blk.c
+++ b/drivers/block/null_blk.c
@@ -406,6 +406,22 @@
 	.complete	= null_softirq_done_fn,
 };
 
+static void cleanup_queue(struct nullb_queue *nq)
+{
+	kfree(nq->tag_map);
+	kfree(nq->cmds);
+}
+
+static void cleanup_queues(struct nullb *nullb)
+{
+	int i;
+
+	for (i = 0; i < nullb->nr_queues; i++)
+		cleanup_queue(&nullb->queues[i]);
+
+	kfree(nullb->queues);
+}
+
 static void null_del_dev(struct nullb *nullb)
 {
 	list_del_init(&nullb->list);
@@ -415,6 +431,7 @@
 	if (queue_mode == NULL_Q_MQ)
 		blk_mq_free_tag_set(&nullb->tag_set);
 	put_disk(nullb->disk);
+	cleanup_queues(nullb);
 	kfree(nullb);
 }
 
@@ -459,22 +476,6 @@
 	return 0;
 }
 
-static void cleanup_queue(struct nullb_queue *nq)
-{
-	kfree(nq->tag_map);
-	kfree(nq->cmds);
-}
-
-static void cleanup_queues(struct nullb *nullb)
-{
-	int i;
-
-	for (i = 0; i < nullb->nr_queues; i++)
-		cleanup_queue(&nullb->queues[i]);
-
-	kfree(nullb->queues);
-}
-
 static int setup_queues(struct nullb *nullb)
 {
 	nullb->queues = kzalloc(submit_queues * sizeof(struct nullb_queue),
@@ -588,8 +589,7 @@
 	blk_queue_physical_block_size(nullb->q, bs);
 
 	size = gb * 1024 * 1024 * 1024ULL;
-	sector_div(size, bs);
-	set_capacity(disk, size);
+	set_capacity(disk, size >> 9);
 
 	disk->flags |= GENHD_FL_EXT_DEVT | GENHD_FL_SUPPRESS_PARTITION_INFO;
 	disk->major		= null_major;
diff --git a/drivers/block/zram/zcomp.c b/drivers/block/zram/zcomp.c
index 965d1af..5cb13ca 100644
--- a/drivers/block/zram/zcomp.c
+++ b/drivers/block/zram/zcomp.c
@@ -330,12 +330,14 @@
  * allocate new zcomp and initialize it. return compressing
  * backend pointer or ERR_PTR if things went bad. ERR_PTR(-EINVAL)
  * if requested algorithm is not supported, ERR_PTR(-ENOMEM) in
- * case of allocation error.
+ * case of allocation error, or any other error potentially
+ * returned by functions zcomp_strm_{multi,single}_create.
  */
 struct zcomp *zcomp_create(const char *compress, int max_strm)
 {
 	struct zcomp *comp;
 	struct zcomp_backend *backend;
+	int error;
 
 	backend = find_backend(compress);
 	if (!backend)
@@ -347,12 +349,12 @@
 
 	comp->backend = backend;
 	if (max_strm > 1)
-		zcomp_strm_multi_create(comp, max_strm);
+		error = zcomp_strm_multi_create(comp, max_strm);
 	else
-		zcomp_strm_single_create(comp);
-	if (!comp->stream) {
+		error = zcomp_strm_single_create(comp);
+	if (error) {
 		kfree(comp);
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(error);
 	}
 	return comp;
 }
diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 43e2c3a..0ebcf44 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -2437,7 +2437,8 @@
 	hlist_for_each_entry_safe(orphan, tmp2, &clk_orphan_list, child_node) {
 		if (orphan->num_parents && orphan->ops->get_parent) {
 			i = orphan->ops->get_parent(orphan->hw);
-			if (!strcmp(core->name, orphan->parent_names[i]))
+			if (i >= 0 && i < orphan->num_parents &&
+			    !strcmp(core->name, orphan->parent_names[i]))
 				clk_core_reparent(orphan, core);
 			continue;
 		}
diff --git a/drivers/clk/h8300/clk-h8s2678.c b/drivers/clk/h8300/clk-h8s2678.c
index 2a38eb4..6cf38dc 100644
--- a/drivers/clk/h8300/clk-h8s2678.c
+++ b/drivers/clk/h8300/clk-h8s2678.c
@@ -8,6 +8,7 @@
 #include <linux/err.h>
 #include <linux/device.h>
 #include <linux/of_address.h>
+#include <linux/slab.h>
 
 static DEFINE_SPINLOCK(clklock);
 
diff --git a/drivers/clk/hisilicon/Kconfig b/drivers/clk/hisilicon/Kconfig
index 2c16807..e434854 100644
--- a/drivers/clk/hisilicon/Kconfig
+++ b/drivers/clk/hisilicon/Kconfig
@@ -1,6 +1,12 @@
 config COMMON_CLK_HI6220
 	bool "Hi6220 Clock Driver"
-	depends on (ARCH_HISI || COMPILE_TEST) && MAILBOX
+	depends on ARCH_HISI || COMPILE_TEST
 	default ARCH_HISI
 	help
 	  Build the Hisilicon Hi6220 clock driver based on the common clock framework.
+
+config STUB_CLK_HI6220
+	bool "Hi6220 Stub Clock Driver"
+	depends on COMMON_CLK_HI6220 && MAILBOX
+	help
+	  Build the Hisilicon Hi6220 stub clock driver.
diff --git a/drivers/clk/hisilicon/Makefile b/drivers/clk/hisilicon/Makefile
index 4a1001a..74dba31 100644
--- a/drivers/clk/hisilicon/Makefile
+++ b/drivers/clk/hisilicon/Makefile
@@ -7,4 +7,5 @@
 obj-$(CONFIG_ARCH_HI3xxx)	+= clk-hi3620.o
 obj-$(CONFIG_ARCH_HIP04)	+= clk-hip04.o
 obj-$(CONFIG_ARCH_HIX5HD2)	+= clk-hix5hd2.o
-obj-$(CONFIG_COMMON_CLK_HI6220)	+= clk-hi6220.o clk-hi6220-stub.o
+obj-$(CONFIG_COMMON_CLK_HI6220)	+= clk-hi6220.o
+obj-$(CONFIG_STUB_CLK_HI6220)	+= clk-hi6220-stub.o
diff --git a/drivers/clk/rockchip/clk-rk3188.c b/drivers/clk/rockchip/clk-rk3188.c
index ed02bbc..abb4760 100644
--- a/drivers/clk/rockchip/clk-rk3188.c
+++ b/drivers/clk/rockchip/clk-rk3188.c
@@ -716,6 +716,8 @@
 	"aclk_cpu",
 	"aclk_peri",
 	"hclk_peri",
+	"pclk_cpu",
+	"pclk_peri",
 };
 
 static void __init rk3188_common_clk_init(struct device_node *np)
@@ -744,8 +746,6 @@
 
 	rockchip_clk_register_branches(common_clk_branches,
 				  ARRAY_SIZE(common_clk_branches));
-	rockchip_clk_protect_critical(rk3188_critical_clocks,
-				      ARRAY_SIZE(rk3188_critical_clocks));
 
 	rockchip_register_softrst(np, 9, reg_base + RK2928_SOFTRST_CON(0),
 				  ROCKCHIP_SOFTRST_HIWORD_MASK);
@@ -765,6 +765,8 @@
 			mux_armclk_p, ARRAY_SIZE(mux_armclk_p),
 			&rk3066_cpuclk_data, rk3066_cpuclk_rates,
 			ARRAY_SIZE(rk3066_cpuclk_rates));
+	rockchip_clk_protect_critical(rk3188_critical_clocks,
+				      ARRAY_SIZE(rk3188_critical_clocks));
 }
 CLK_OF_DECLARE(rk3066a_cru, "rockchip,rk3066a-cru", rk3066a_clk_init);
 
@@ -801,6 +803,9 @@
 		pr_warn("%s: missing clocks to reparent aclk_cpu_pre to gpll\n",
 			__func__);
 	}
+
+	rockchip_clk_protect_critical(rk3188_critical_clocks,
+				      ARRAY_SIZE(rk3188_critical_clocks));
 }
 CLK_OF_DECLARE(rk3188a_cru, "rockchip,rk3188a-cru", rk3188a_clk_init);
 
diff --git a/drivers/clk/rockchip/clk-rk3368.c b/drivers/clk/rockchip/clk-rk3368.c
index 9c5d61e..7e6b783 100644
--- a/drivers/clk/rockchip/clk-rk3368.c
+++ b/drivers/clk/rockchip/clk-rk3368.c
@@ -818,6 +818,10 @@
 	GATE(0, "sclk_timer00", "xin24m", CLK_IGNORE_UNUSED, RK3368_CLKGATE_CON(24), 0, GFLAGS),
 };
 
+static const char *const rk3368_critical_clocks[] __initconst = {
+	"pclk_pd_pmu",
+};
+
 static void __init rk3368_clk_init(struct device_node *np)
 {
 	void __iomem *reg_base;
@@ -862,6 +866,8 @@
 				   RK3368_GRF_SOC_STATUS0);
 	rockchip_clk_register_branches(rk3368_clk_branches,
 				  ARRAY_SIZE(rk3368_clk_branches));
+	rockchip_clk_protect_critical(rk3368_critical_clocks,
+				      ARRAY_SIZE(rk3368_critical_clocks));
 
 	rockchip_clk_register_armclk(ARMCLKB, "armclkb",
 			mux_armclkb_p, ARRAY_SIZE(mux_armclkb_p),
diff --git a/drivers/clk/st/clkgen-fsyn.c b/drivers/clk/st/clkgen-fsyn.c
index 83ccf14..576cd03 100644
--- a/drivers/clk/st/clkgen-fsyn.c
+++ b/drivers/clk/st/clkgen-fsyn.c
@@ -307,7 +307,7 @@
 	.get_rate	= clk_fs660c32_dig_get_rate,
 };
 
-static const struct clkgen_quadfs_data st_fs660c32_C_407 = {
+static const struct clkgen_quadfs_data st_fs660c32_C = {
 	.nrst_present = true,
 	.nrst	= { CLKGEN_FIELD(0x2f0, 0x1, 0),
 		    CLKGEN_FIELD(0x2f0, 0x1, 1),
@@ -350,7 +350,7 @@
 	.get_rate	= clk_fs660c32_dig_get_rate,
 };
 
-static const struct clkgen_quadfs_data st_fs660c32_D_407 = {
+static const struct clkgen_quadfs_data st_fs660c32_D = {
 	.nrst_present = true,
 	.nrst	= { CLKGEN_FIELD(0x2a0, 0x1, 0),
 		    CLKGEN_FIELD(0x2a0, 0x1, 1),
@@ -1077,11 +1077,11 @@
 	},
 	{
 		.compatible = "st,stih407-quadfs660-C",
-		.data = &st_fs660c32_C_407
+		.data = &st_fs660c32_C
 	},
 	{
 		.compatible = "st,stih407-quadfs660-D",
-		.data = &st_fs660c32_D_407
+		.data = &st_fs660c32_D
 	},
 	{}
 };
diff --git a/drivers/clk/st/clkgen-pll.c b/drivers/clk/st/clkgen-pll.c
index 47a38a9..b2a332c 100644
--- a/drivers/clk/st/clkgen-pll.c
+++ b/drivers/clk/st/clkgen-pll.c
@@ -193,7 +193,7 @@
 	.ops		= &stm_pll3200c32_ops,
 };
 
-static const struct clkgen_pll_data st_pll3200c32_407_c0_0 = {
+static const struct clkgen_pll_data st_pll3200c32_cx_0 = {
 	/* 407 C0 PLL0 */
 	.pdn_status	= CLKGEN_FIELD(0x2a0,	0x1,			8),
 	.locked_status	= CLKGEN_FIELD(0x2a0,	0x1,			24),
@@ -205,7 +205,7 @@
 	.ops		= &stm_pll3200c32_ops,
 };
 
-static const struct clkgen_pll_data st_pll3200c32_407_c0_1 = {
+static const struct clkgen_pll_data st_pll3200c32_cx_1 = {
 	/* 407 C0 PLL1 */
 	.pdn_status	= CLKGEN_FIELD(0x2c8,	0x1,			8),
 	.locked_status	= CLKGEN_FIELD(0x2c8,	0x1,			24),
@@ -624,12 +624,12 @@
 		.data = &st_pll3200c32_407_a0,
 	},
 	{
-		.compatible = "st,stih407-plls-c32-c0_0",
-		.data = &st_pll3200c32_407_c0_0,
+		.compatible = "st,plls-c32-cx_0",
+		.data = &st_pll3200c32_cx_0,
 	},
 	{
-		.compatible = "st,stih407-plls-c32-c0_1",
-		.data = &st_pll3200c32_407_c0_1,
+		.compatible = "st,plls-c32-cx_1",
+		.data = &st_pll3200c32_cx_1,
 	},
 	{
 		.compatible = "st,stih407-plls-c32-a9",
diff --git a/drivers/clk/tegra/clk-dfll.c b/drivers/clk/tegra/clk-dfll.c
index c2ff859..c4e3a52 100644
--- a/drivers/clk/tegra/clk-dfll.c
+++ b/drivers/clk/tegra/clk-dfll.c
@@ -682,11 +682,17 @@
 	struct dev_pm_opp *opp;
 	int i, uv;
 
+	rcu_read_lock();
+
 	opp = dev_pm_opp_find_freq_ceil(td->soc->dev, &rate);
-	if (IS_ERR(opp))
+	if (IS_ERR(opp)) {
+		rcu_read_unlock();
 		return PTR_ERR(opp);
+	}
 	uv = dev_pm_opp_get_voltage(opp);
 
+	rcu_read_unlock();
+
 	for (i = 0; i < td->i2c_lut_size; i++) {
 		if (regulator_list_voltage(td->vdd_reg, td->i2c_lut[i]) == uv)
 			return i;
diff --git a/drivers/cpufreq/acpi-cpufreq.c b/drivers/cpufreq/acpi-cpufreq.c
index 15b921a..7982772 100644
--- a/drivers/cpufreq/acpi-cpufreq.c
+++ b/drivers/cpufreq/acpi-cpufreq.c
@@ -375,12 +375,11 @@
 
 	pr_debug("get_cur_freq_on_cpu (%d)\n", cpu);
 
-	policy = cpufreq_cpu_get(cpu);
+	policy = cpufreq_cpu_get_raw(cpu);
 	if (unlikely(!policy))
 		return 0;
 
 	data = policy->driver_data;
-	cpufreq_cpu_put(policy);
 	if (unlikely(!data || !data->freq_table))
 		return 0;
 
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 6633b3f..ef5ed94 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -238,13 +238,13 @@
 }
 EXPORT_SYMBOL_GPL(cpufreq_generic_init);
 
-/* Only for cpufreq core internal use */
-static struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
 {
 	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
 	return policy && cpumask_test_cpu(cpu, policy->cpus) ? policy : NULL;
 }
+EXPORT_SYMBOL_GPL(cpufreq_cpu_get_raw);
 
 unsigned int cpufreq_generic_get(unsigned int cpu)
 {
diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index 07bc7aa..d234719 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -461,7 +461,7 @@
 
 config CRYPTO_DEV_VMX
 	bool "Support for VMX cryptographic acceleration instructions"
-	depends on PPC64
+	depends on PPC64 && VSX
 	help
 	  Support for VMX cryptographic acceleration instructions.
 
diff --git a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
index e070c31..a19ee12 100644
--- a/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
+++ b/drivers/crypto/sunxi-ss/sun4i-ss-cipher.c
@@ -104,7 +104,7 @@
 			sg_miter_next(&mo);
 			oo = 0;
 		}
-	} while (mo.length > 0);
+	} while (oleft > 0);
 
 	if (areq->info) {
 		for (i = 0; i < 4 && i < ivsize / 4; i++) {
diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index ca1b362..3927ed9 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -53,7 +53,7 @@
 {
 	struct devfreq *tmp_devfreq;
 
-	if (unlikely(IS_ERR_OR_NULL(dev))) {
+	if (IS_ERR_OR_NULL(dev)) {
 		pr_err("DEVFREQ: %s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
@@ -133,7 +133,7 @@
 {
 	struct devfreq_governor *tmp_governor;
 
-	if (unlikely(IS_ERR_OR_NULL(name))) {
+	if (IS_ERR_OR_NULL(name)) {
 		pr_err("DEVFREQ: %s: Invalid parameters\n", __func__);
 		return ERR_PTR(-EINVAL);
 	}
@@ -177,10 +177,10 @@
 		return err;
 
 	/*
-	 * Adjust the freuqency with user freq and QoS.
+	 * Adjust the frequency with user freq and QoS.
 	 *
-	 * List from the highest proiority
-	 * max_freq (probably called by thermal when it's too hot)
+	 * List from the highest priority
+	 * max_freq
 	 * min_freq
 	 */
 
@@ -482,7 +482,7 @@
 						devfreq->profile->max_state *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
-	devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned int) *
+	devfreq->time_in_state = devm_kzalloc(dev, sizeof(unsigned long) *
 						devfreq->profile->max_state,
 						GFP_KERNEL);
 	devfreq->last_stat_updated = jiffies;
diff --git a/drivers/devfreq/event/exynos-ppmu.c b/drivers/devfreq/event/exynos-ppmu.c
index f9901f5..f312485 100644
--- a/drivers/devfreq/event/exynos-ppmu.c
+++ b/drivers/devfreq/event/exynos-ppmu.c
@@ -319,7 +319,8 @@
 	case PPMU_PMNCNT3:
 		pmcnt_high = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_HIGH);
 		pmcnt_low = __raw_readl(info->ppmu.base + PPMU_V2_PMCNT3_LOW);
-		load_count = (u64)((pmcnt_high & 0xff) << 32) + (u64)pmcnt_low;
+		load_count = ((u64)((pmcnt_high & 0xff)) << 32)
+			   + (u64)pmcnt_low;
 		break;
 	}
 	edata->load_count = load_count;
diff --git a/drivers/devfreq/governor_simpleondemand.c b/drivers/devfreq/governor_simpleondemand.c
index 0720ba8..ae72ba5 100644
--- a/drivers/devfreq/governor_simpleondemand.c
+++ b/drivers/devfreq/governor_simpleondemand.c
@@ -21,17 +21,20 @@
 static int devfreq_simple_ondemand_func(struct devfreq *df,
 					unsigned long *freq)
 {
-	struct devfreq_dev_status stat;
-	int err = df->profile->get_dev_status(df->dev.parent, &stat);
+	int err;
+	struct devfreq_dev_status *stat;
 	unsigned long long a, b;
 	unsigned int dfso_upthreshold = DFSO_UPTHRESHOLD;
 	unsigned int dfso_downdifferential = DFSO_DOWNDIFFERENCTIAL;
 	struct devfreq_simple_ondemand_data *data = df->data;
 	unsigned long max = (df->max_freq) ? df->max_freq : UINT_MAX;
 
+	err = devfreq_update_stats(df);
 	if (err)
 		return err;
 
+	stat = &df->last_status;
+
 	if (data) {
 		if (data->upthreshold)
 			dfso_upthreshold = data->upthreshold;
@@ -43,41 +46,41 @@
 		return -EINVAL;
 
 	/* Assume MAX if it is going to be divided by zero */
-	if (stat.total_time == 0) {
+	if (stat->total_time == 0) {
 		*freq = max;
 		return 0;
 	}
 
 	/* Prevent overflow */
-	if (stat.busy_time >= (1 << 24) || stat.total_time >= (1 << 24)) {
-		stat.busy_time >>= 7;
-		stat.total_time >>= 7;
+	if (stat->busy_time >= (1 << 24) || stat->total_time >= (1 << 24)) {
+		stat->busy_time >>= 7;
+		stat->total_time >>= 7;
 	}
 
 	/* Set MAX if it's busy enough */
-	if (stat.busy_time * 100 >
-	    stat.total_time * dfso_upthreshold) {
+	if (stat->busy_time * 100 >
+	    stat->total_time * dfso_upthreshold) {
 		*freq = max;
 		return 0;
 	}
 
 	/* Set MAX if we do not know the initial frequency */
-	if (stat.current_frequency == 0) {
+	if (stat->current_frequency == 0) {
 		*freq = max;
 		return 0;
 	}
 
 	/* Keep the current frequency */
-	if (stat.busy_time * 100 >
-	    stat.total_time * (dfso_upthreshold - dfso_downdifferential)) {
-		*freq = stat.current_frequency;
+	if (stat->busy_time * 100 >
+	    stat->total_time * (dfso_upthreshold - dfso_downdifferential)) {
+		*freq = stat->current_frequency;
 		return 0;
 	}
 
 	/* Set the desired frequency based on the load */
-	a = stat.busy_time;
-	a *= stat.current_frequency;
-	b = div_u64(a, stat.total_time);
+	a = stat->busy_time;
+	a *= stat->current_frequency;
+	b = div_u64(a, stat->total_time);
 	b *= 100;
 	b = div_u64(b, (dfso_upthreshold - dfso_downdifferential / 2));
 	*freq = (unsigned long) b;
diff --git a/drivers/devfreq/tegra-devfreq.c b/drivers/devfreq/tegra-devfreq.c
index 13a1a6e..848b93e 100644
--- a/drivers/devfreq/tegra-devfreq.c
+++ b/drivers/devfreq/tegra-devfreq.c
@@ -541,18 +541,20 @@
 static int tegra_governor_get_target(struct devfreq *devfreq,
 				     unsigned long *freq)
 {
-	struct devfreq_dev_status stat;
+	struct devfreq_dev_status *stat;
 	struct tegra_devfreq *tegra;
 	struct tegra_devfreq_device *dev;
 	unsigned long target_freq = 0;
 	unsigned int i;
 	int err;
 
-	err = devfreq->profile->get_dev_status(devfreq->dev.parent, &stat);
+	err = devfreq_update_stats(devfreq);
 	if (err)
 		return err;
 
-	tegra = stat.private_data;
+	stat = &devfreq->last_status;
+
+	tegra = stat->private_data;
 
 	for (i = 0; i < ARRAY_SIZE(tegra->devices); i++) {
 		dev = &tegra->devices[i];
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index 4768a82..2bf37e6 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -266,7 +266,7 @@
 }
 
 /* Chained IRQ handler for IPU function and error interrupt */
-static void ipu_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void ipu_irq_handler(struct irq_desc *desc)
 {
 	struct ipu *ipu = irq_desc_get_handler_data(desc);
 	u32 status;
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index a07addd..8dd0af1 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -159,7 +159,7 @@
 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/efi/libstub/efistub.h b/drivers/firmware/efi/libstub/efistub.h
index e334a01..6b6548f 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/gpio/Kconfig b/drivers/gpio/Kconfig
index b4fc9e4..8949b3f 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -356,7 +356,7 @@
 
 config GPIO_RCAR
 	tristate "Renesas R-Car GPIO"
-	depends on ARM && (ARCH_SHMOBILE || COMPILE_TEST)
+	depends on ARCH_SHMOBILE || COMPILE_TEST
 	select GPIOLIB_IRQCHIP
 	help
 	  Say yes here to support GPIO on Renesas R-Car SoCs.
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 9b7e0b3..1b44941 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -201,8 +201,7 @@
 	return 0;
 }
 
-static void altera_gpio_irq_edge_handler(unsigned int irq,
-					struct irq_desc *desc)
+static void altera_gpio_irq_edge_handler(struct irq_desc *desc)
 {
 	struct altera_gpio_chip *altera_gc;
 	struct irq_chip *chip;
@@ -231,8 +230,7 @@
 }
 
 
-static void altera_gpio_irq_leveL_high_handler(unsigned int irq,
-					      struct irq_desc *desc)
+static void altera_gpio_irq_leveL_high_handler(struct irq_desc *desc)
 {
 	struct altera_gpio_chip *altera_gc;
 	struct irq_chip *chip;
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 31b90ac..33a1f97 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -433,7 +433,7 @@
 	return 0;
 }
 
-static void bcm_kona_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void bcm_kona_gpio_irq_handler(struct irq_desc *desc)
 {
 	void __iomem *reg_base;
 	int bit, bank_id;
diff --git a/drivers/gpio/gpio-brcmstb.c b/drivers/gpio/gpio-brcmstb.c
index 9ea86d2..4c64627 100644
--- a/drivers/gpio/gpio-brcmstb.c
+++ b/drivers/gpio/gpio-brcmstb.c
@@ -236,7 +236,7 @@
 }
 
 /* Each UPG GIO block has one IRQ for all banks */
-static void brcmstb_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void brcmstb_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct brcmstb_gpio_priv *priv = brcmstb_gpio_gc_to_priv(gc);
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index 94b0ab7..5e71538 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -326,8 +326,7 @@
 	.flags		= IRQCHIP_SET_TYPE_MASKED,
 };
 
-static void
-gpio_irq_handler(unsigned __irq, struct irq_desc *desc)
+static void gpio_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct davinci_gpio_regs __iomem *g;
diff --git a/drivers/gpio/gpio-dwapb.c b/drivers/gpio/gpio-dwapb.c
index c5be4b9..fcd5b0a 100644
--- a/drivers/gpio/gpio-dwapb.c
+++ b/drivers/gpio/gpio-dwapb.c
@@ -147,7 +147,7 @@
 	return ret;
 }
 
-static void dwapb_irq_handler(u32 irq, struct irq_desc *desc)
+static void dwapb_irq_handler(struct irq_desc *desc)
 {
 	struct dwapb_gpio *gpio = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/gpio/gpio-ep93xx.c b/drivers/gpio/gpio-ep93xx.c
index 9d90366..3e3947b 100644
--- a/drivers/gpio/gpio-ep93xx.c
+++ b/drivers/gpio/gpio-ep93xx.c
@@ -78,7 +78,7 @@
 		EP93XX_GPIO_REG(int_debounce_register_offset[port]));
 }
 
-static void ep93xx_gpio_ab_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ep93xx_gpio_ab_irq_handler(struct irq_desc *desc)
 {
 	unsigned char status;
 	int i;
@@ -100,8 +100,7 @@
 	}
 }
 
-static void ep93xx_gpio_f_irq_handler(unsigned int __irq,
-				      struct irq_desc *desc)
+static void ep93xx_gpio_f_irq_handler(struct irq_desc *desc)
 {
 	/*
 	 * map discontiguous hw irq range to continuous sw irq range:
diff --git a/drivers/gpio/gpio-intel-mid.c b/drivers/gpio/gpio-intel-mid.c
index aa28c65..7009747 100644
--- a/drivers/gpio/gpio-intel-mid.c
+++ b/drivers/gpio/gpio-intel-mid.c
@@ -301,7 +301,7 @@
 };
 MODULE_DEVICE_TABLE(pci, intel_gpio_ids);
 
-static void intel_mid_irq_handler(unsigned irq, struct irq_desc *desc)
+static void intel_mid_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct intel_mid_gpio *priv = to_intel_gpio_priv(gc);
diff --git a/drivers/gpio/gpio-lynxpoint.c b/drivers/gpio/gpio-lynxpoint.c
index 153af46..127c37b 100644
--- a/drivers/gpio/gpio-lynxpoint.c
+++ b/drivers/gpio/gpio-lynxpoint.c
@@ -234,7 +234,7 @@
 	return 0;
 }
 
-static void lp_gpio_irq_handler(unsigned hwirq, struct irq_desc *desc)
+static void lp_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
diff --git a/drivers/gpio/gpio-mpc8xxx.c b/drivers/gpio/gpio-mpc8xxx.c
index 8ef7a12..48ef368 100644
--- a/drivers/gpio/gpio-mpc8xxx.c
+++ b/drivers/gpio/gpio-mpc8xxx.c
@@ -194,7 +194,7 @@
 		return -ENXIO;
 }
 
-static void mpc8xxx_gpio_irq_cascade(unsigned int irq, struct irq_desc *desc)
+static void mpc8xxx_gpio_irq_cascade(struct irq_desc *desc)
 {
 	struct mpc8xxx_gpio_chip *mpc8xxx_gc = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/gpio/gpio-msic.c b/drivers/gpio/gpio-msic.c
index 7bcfb87..22523aa 100644
--- a/drivers/gpio/gpio-msic.c
+++ b/drivers/gpio/gpio-msic.c
@@ -232,7 +232,7 @@
 	.irq_bus_sync_unlock	= msic_bus_sync_unlock,
 };
 
-static void msic_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void msic_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct msic_gpio *mg = irq_data_get_irq_handler_data(data);
diff --git a/drivers/gpio/gpio-msm-v2.c b/drivers/gpio/gpio-msm-v2.c
index d2012cf..4b42221 100644
--- a/drivers/gpio/gpio-msm-v2.c
+++ b/drivers/gpio/gpio-msm-v2.c
@@ -305,7 +305,7 @@
  * which have been set as summary IRQ lines and which are triggered,
  * and to call their interrupt handlers.
  */
-static void msm_summary_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void msm_summary_irq_handler(struct irq_desc *desc)
 {
 	unsigned long i;
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index b396bf3..df418b8 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -458,7 +458,7 @@
 	return 0;
 }
 
-static void mvebu_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void mvebu_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct mvebu_gpio_chip *mvchip = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/gpio/gpio-mxc.c b/drivers/gpio/gpio-mxc.c
index b752b56..b8dd847 100644
--- a/drivers/gpio/gpio-mxc.c
+++ b/drivers/gpio/gpio-mxc.c
@@ -272,7 +272,7 @@
 }
 
 /* MX1 and MX3 has one interrupt *per* gpio port */
-static void mx3_gpio_irq_handler(u32 irq, struct irq_desc *desc)
+static void mx3_gpio_irq_handler(struct irq_desc *desc)
 {
 	u32 irq_stat;
 	struct mxc_gpio_port *port = irq_desc_get_handler_data(desc);
@@ -288,7 +288,7 @@
 }
 
 /* MX2 has one interrupt *for all* gpio ports */
-static void mx2_gpio_irq_handler(u32 irq, struct irq_desc *desc)
+static void mx2_gpio_irq_handler(struct irq_desc *desc)
 {
 	u32 irq_msk, irq_stat;
 	struct mxc_gpio_port *port;
@@ -339,13 +339,15 @@
 	return 0;
 }
 
-static void mxc_gpio_init_gc(struct mxc_gpio_port *port, int irq_base)
+static int mxc_gpio_init_gc(struct mxc_gpio_port *port, int irq_base)
 {
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
 
 	gc = irq_alloc_generic_chip("gpio-mxc", 1, irq_base,
 				    port->base, handle_level_irq);
+	if (!gc)
+		return -ENOMEM;
 	gc->private = port;
 
 	ct = gc->chip_types;
@@ -360,6 +362,8 @@
 
 	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
 			       IRQ_NOREQUEST, 0);
+
+	return 0;
 }
 
 static void mxc_gpio_get_hw(struct platform_device *pdev)
@@ -477,12 +481,16 @@
 	}
 
 	/* gpio-mxc can be a generic irq chip */
-	mxc_gpio_init_gc(port, irq_base);
+	err = mxc_gpio_init_gc(port, irq_base);
+	if (err < 0)
+		goto out_irqdomain_remove;
 
 	list_add_tail(&port->node, &mxc_gpio_ports);
 
 	return 0;
 
+out_irqdomain_remove:
+	irq_domain_remove(port->domain);
 out_irqdesc_free:
 	irq_free_descs(irq_base, 32);
 out_gpiochip_remove:
diff --git a/drivers/gpio/gpio-mxs.c b/drivers/gpio/gpio-mxs.c
index b7f383e..a4288f4 100644
--- a/drivers/gpio/gpio-mxs.c
+++ b/drivers/gpio/gpio-mxs.c
@@ -154,7 +154,7 @@
 }
 
 /* MXS has one interrupt *per* gpio port */
-static void mxs_gpio_irq_handler(u32 irq, struct irq_desc *desc)
+static void mxs_gpio_irq_handler(struct irq_desc *desc)
 {
 	u32 irq_stat;
 	struct mxs_gpio_port *port = irq_desc_get_handler_data(desc);
@@ -196,13 +196,16 @@
 	return 0;
 }
 
-static void __init mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base)
+static int __init mxs_gpio_init_gc(struct mxs_gpio_port *port, int irq_base)
 {
 	struct irq_chip_generic *gc;
 	struct irq_chip_type *ct;
 
 	gc = irq_alloc_generic_chip("gpio-mxs", 1, irq_base,
 				    port->base, handle_level_irq);
+	if (!gc)
+		return -ENOMEM;
+
 	gc->private = port;
 
 	ct = gc->chip_types;
@@ -216,6 +219,8 @@
 
 	irq_setup_generic_chip(gc, IRQ_MSK(32), IRQ_GC_INIT_NESTED_LOCK,
 			       IRQ_NOREQUEST, 0);
+
+	return 0;
 }
 
 static int mxs_gpio_to_irq(struct gpio_chip *gc, unsigned offset)
@@ -317,7 +322,9 @@
 	}
 
 	/* gpio-mxs can be a generic irq chip */
-	mxs_gpio_init_gc(port, irq_base);
+	err = mxs_gpio_init_gc(port, irq_base);
+	if (err < 0)
+		goto out_irqdomain_remove;
 
 	/* setup one handler for each entry */
 	irq_set_chained_handler_and_data(port->irq, mxs_gpio_irq_handler,
@@ -343,6 +350,8 @@
 
 out_bgpio_remove:
 	bgpio_remove(&port->bgc);
+out_irqdomain_remove:
+	irq_domain_remove(port->domain);
 out_irqdesc_free:
 	irq_free_descs(irq_base, 32);
 	return err;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 2ae0d47..5236db1 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -709,7 +709,7 @@
  * line's interrupt handler has been run, we may miss some nested
  * interrupts.
  */
-static void omap_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void omap_gpio_irq_handler(struct irq_desc *desc)
 {
 	void __iomem *isr_reg = NULL;
 	u32 isr;
@@ -1098,7 +1098,6 @@
 	} else {
 		bank->chip.label = "gpio";
 		bank->chip.base = gpio;
-		gpio += bank->width;
 	}
 	bank->chip.ngpio = bank->width;
 
@@ -1108,6 +1107,9 @@
 		return ret;
 	}
 
+	if (!bank->is_mpuio)
+		gpio += bank->width;
+
 #ifdef CONFIG_ARCH_OMAP1
 	/*
 	 * REVISIT: Once we have OMAP1 supporting SPARSE_IRQ, we can drop
@@ -1253,8 +1255,11 @@
 	omap_gpio_mod_init(bank);
 
 	ret = omap_gpio_chip_init(bank, irqc);
-	if (ret)
+	if (ret) {
+		pm_runtime_put_sync(bank->dev);
+		pm_runtime_disable(bank->dev);
 		return ret;
+	}
 
 	omap_gpio_show_rev(bank);
 
diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c
index 0475613..229ef65 100644
--- a/drivers/gpio/gpio-pl061.c
+++ b/drivers/gpio/gpio-pl061.c
@@ -187,7 +187,7 @@
 	return 0;
 }
 
-static void pl061_irq_handler(unsigned irq, struct irq_desc *desc)
+static void pl061_irq_handler(struct irq_desc *desc)
 {
 	unsigned long pending;
 	int offset;
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index 55a11de..df2ce55 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -401,7 +401,7 @@
 	return 0;
 }
 
-static void pxa_gpio_demux_handler(unsigned int irq, struct irq_desc *desc)
+static void pxa_gpio_demux_handler(struct irq_desc *desc)
 {
 	struct pxa_gpio_chip *c;
 	int loop, gpio, gpio_base, n;
diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index 67bd2f5..990fa90 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -172,8 +172,7 @@
  * irq_controller_lock held, and IRQs disabled.  Decode the IRQ
  * and call the handler.
  */
-static void
-sa1100_gpio_handler(unsigned int __irq, struct irq_desc *desc)
+static void sa1100_gpio_handler(struct irq_desc *desc)
 {
 	unsigned int irq, mask;
 
diff --git a/drivers/gpio/gpio-sx150x.c b/drivers/gpio/gpio-sx150x.c
index 458d9d7..9c6b967 100644
--- a/drivers/gpio/gpio-sx150x.c
+++ b/drivers/gpio/gpio-sx150x.c
@@ -706,4 +706,3 @@
 MODULE_AUTHOR("Gregory Bean <gbean@codeaurora.org>");
 MODULE_DESCRIPTION("Driver for Semtech SX150X I2C GPIO Expanders");
 MODULE_LICENSE("GPL v2");
-MODULE_ALIAS("i2c:sx150x");
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 9b14aaf..027e5f4 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -266,7 +266,7 @@
 	gpiochip_unlock_as_irq(&tegra_gpio_chip, gpio);
 }
 
-static void tegra_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void tegra_gpio_irq_handler(struct irq_desc *desc)
 {
 	int port;
 	int pin;
diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index 5a49205..30653e6 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -192,7 +192,7 @@
 	return ret;
 }
 
-static void timbgpio_irq(unsigned int irq, struct irq_desc *desc)
+static void timbgpio_irq(struct irq_desc *desc)
 {
 	struct timbgpio *tgpio = irq_desc_get_handler_data(desc);
 	struct irq_data *data = irq_desc_get_irq_data(desc);
diff --git a/drivers/gpio/gpio-tz1090.c b/drivers/gpio/gpio-tz1090.c
index bbac92a..87bb1b1 100644
--- a/drivers/gpio/gpio-tz1090.c
+++ b/drivers/gpio/gpio-tz1090.c
@@ -375,7 +375,7 @@
 #define gpio_set_irq_wake NULL
 #endif
 
-static void tz1090_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void tz1090_gpio_irq_handler(struct irq_desc *desc)
 {
 	irq_hw_number_t hw;
 	unsigned int irq_stat, irq_no;
@@ -400,7 +400,7 @@
 				== IRQ_TYPE_EDGE_BOTH)
 			tz1090_gpio_irq_next_edge(bank, hw);
 
-		generic_handle_irq_desc(irq_no, child_desc);
+		generic_handle_irq_desc(child_desc);
 	}
 }
 
diff --git a/drivers/gpio/gpio-vf610.c b/drivers/gpio/gpio-vf610.c
index 3d5714d..069f9e4 100644
--- a/drivers/gpio/gpio-vf610.c
+++ b/drivers/gpio/gpio-vf610.c
@@ -120,7 +120,7 @@
 	return pinctrl_gpio_direction_output(chip->base + gpio);
 }
 
-static void vf610_gpio_irq_handler(u32 irq, struct irq_desc *desc)
+static void vf610_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct vf610_gpio_port *port = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
@@ -176,9 +176,9 @@
 	port->irqc[d->hwirq] = irqc;
 
 	if (type & IRQ_TYPE_LEVEL_MASK)
-		__irq_set_handler_locked(d->irq, handle_level_irq);
+		irq_set_handler_locked(d, handle_level_irq);
 	else
-		__irq_set_handler_locked(d->irq, handle_edge_irq);
+		irq_set_handler_locked(d, handle_edge_irq);
 
 	return 0;
 }
diff --git a/drivers/gpio/gpio-zx.c b/drivers/gpio/gpio-zx.c
index 12ee196..4b8a269 100644
--- a/drivers/gpio/gpio-zx.c
+++ b/drivers/gpio/gpio-zx.c
@@ -177,7 +177,7 @@
 	return 0;
 }
 
-static void zx_irq_handler(unsigned irq, struct irq_desc *desc)
+static void zx_irq_handler(struct irq_desc *desc)
 {
 	unsigned long pending;
 	int offset;
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index 27348e7..1d1a586 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -514,7 +514,7 @@
  * application for that pin.
  * Note: A bug is reported if no handler is set for the gpio pin.
  */
-static void zynq_gpio_irqhandler(unsigned int irq, struct irq_desc *desc)
+static void zynq_gpio_irqhandler(struct irq_desc *desc)
 {
 	u32 int_sts, int_enb;
 	unsigned int bank_num;
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 980c1f8..5db3445 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1174,15 +1174,16 @@
  * that the GPIO was actually requested.
  */
 
-static bool _gpiod_get_raw_value(const struct gpio_desc *desc)
+static int _gpiod_get_raw_value(const struct gpio_desc *desc)
 {
 	struct gpio_chip	*chip;
-	bool value;
 	int offset;
+	int value;
 
 	chip = desc->chip;
 	offset = gpio_chip_hwgpio(desc);
-	value = chip->get ? chip->get(chip, offset) : false;
+	value = chip->get ? chip->get(chip, offset) : -EIO;
+	value = value < 0 ? value : !!value;
 	trace_gpio_value(desc_to_gpio(desc), 1, value);
 	return value;
 }
@@ -1192,7 +1193,7 @@
  * @desc: gpio whose value will be returned
  *
  * Return the GPIO's raw value, i.e. the value of the physical line disregarding
- * its ACTIVE_LOW status.
+ * its ACTIVE_LOW status, or negative errno on failure.
  *
  * This function should be called from contexts where we cannot sleep, and will
  * complain if the GPIO chip functions potentially sleep.
@@ -1212,7 +1213,7 @@
  * @desc: gpio whose value will be returned
  *
  * Return the GPIO's logical value, i.e. taking the ACTIVE_LOW status into
- * account.
+ * account, or negative errno on failure.
  *
  * This function should be called from contexts where we cannot sleep, and will
  * complain if the GPIO chip functions potentially sleep.
@@ -1226,6 +1227,9 @@
 	WARN_ON(desc->chip->can_sleep);
 
 	value = _gpiod_get_raw_value(desc);
+	if (value < 0)
+		return value;
+
 	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
 		value = !value;
 
@@ -1548,7 +1552,7 @@
  * @desc: gpio whose value will be returned
  *
  * Return the GPIO's raw value, i.e. the value of the physical line disregarding
- * its ACTIVE_LOW status.
+ * its ACTIVE_LOW status, or negative errno on failure.
  *
  * This function is to be called from contexts that can sleep.
  */
@@ -1566,7 +1570,7 @@
  * @desc: gpio whose value will be returned
  *
  * Return the GPIO's logical value, i.e. taking the ACTIVE_LOW status into
- * account.
+ * account, or negative errno on failure.
  *
  * This function is to be called from contexts that can sleep.
  */
@@ -1579,6 +1583,9 @@
 		return 0;
 
 	value = _gpiod_get_raw_value(desc);
+	if (value < 0)
+		return value;
+
 	if (test_bit(FLAG_ACTIVE_LOW, &desc->flags))
 		value = !value;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index 668939a..6647fb2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -82,6 +82,7 @@
 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 @@
 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_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_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 @@
 	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 496ed21..84d68d6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd.c
@@ -183,7 +183,7 @@
 		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 98d59ee..cd639c3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_benchmark.c
@@ -79,7 +79,8 @@
 	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 @@
 	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 6b1243f..1c3fc99 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
@@ -86,7 +86,7 @@
 
 	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 @@
 
 	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 3b355ae..749420f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
@@ -154,42 +154,41 @@
 {
 	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 @@
 		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 @@
 
 		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 @@
 				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 @@
 			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 @@
 	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 @@
 					domain = lobj->allowed_domains;
 					goto retry;
 				}
-				ttm_eu_backoff_reservation(&p->ticket, &p->validated);
 				return r;
 			}
 		}
@@ -386,6 +394,7 @@
 {
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 		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 @@
 
 		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 20cbc4e..e0b80cc 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
@@ -43,10 +43,10 @@
 		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 @@
 
 		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 @@
 
 	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 6ff6ae9..6068d82 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -246,7 +246,7 @@
 		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 @@
 
 	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 @@
 	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 @@
 	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 0fcc0bd..adb4835 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_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_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 1be2bd6..b3fc26c 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -609,9 +609,9 @@
  * 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 @@
 			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 @@
 		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 cbd3a48..7312d72 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
@@ -127,7 +127,7 @@
 		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 5839fab..7297ca3 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -69,7 +69,8 @@
 		}
 	}
 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 @@
 					   &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 @@
 						   args->data.flags);
 	}
 
+unreserve:
 	amdgpu_bo_unreserve(robj);
 out:
 	drm_gem_object_unreference_unlocked(gobj);
@@ -454,11 +460,12 @@
 	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 @@
 	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 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 5c8a803..534fc04 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ih.c
@@ -43,7 +43,7 @@
 		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 0aba8e9..7c42ff6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_irq.c
@@ -140,7 +140,7 @@
  */
 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 2236793..8c735f54 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -390,7 +390,7 @@
 				    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 @@
 		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 08b09d5..1a7708f 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.c
@@ -215,6 +215,7 @@
 				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 @@
 	/* 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(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 @@
 	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 @@
 	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 6ea18dc..3c2ff45 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_object.h
@@ -129,12 +129,14 @@
 			    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 d9652fe..59f735a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_prime.c
@@ -61,12 +61,15 @@
 							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 9bec914..30dce23 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
@@ -357,11 +357,11 @@
 		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 @@
 	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 74dad27..e907124 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sa.c
@@ -64,8 +64,8 @@
 		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 @@
 	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 @@
 }
 
 #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 @@
 		}
 		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 de98fbd..2e946b2 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 @@
 			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 @@
 		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 068aeaf..4921de1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
@@ -65,8 +65,14 @@
 
 	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 @@
 		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 @@
 			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 f80b1a4..4865615 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_test.c
@@ -59,8 +59,9 @@
 		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 @@
 		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 b5abd5c..364cbe9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
@@ -861,7 +861,7 @@
 	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 482e667..5cc95f1 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ucode.c
@@ -247,7 +247,7 @@
 	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 2cf6c6b..d0312364 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_uvd.c
@@ -156,7 +156,7 @@
 	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 @@
 		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 */
+	default:
+		DRM_ERROR("Illegal UVD message type (%d)!\n", msg_type);
+		return -EINVAL;
 	}
-
-	/* 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;
-		}
-	}
-
-	DRM_ERROR("No more free UVD handles!\n");
+	BUG();
 	return -EINVAL;
 }
 
@@ -805,10 +819,10 @@
 }
 
 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 @@
 	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 @@
 	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 3cab96c..74f2038a 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vce.c
@@ -143,7 +143,7 @@
 	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 @@
 }
 
 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 f68b7cd..1e14531 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -316,12 +316,12 @@
 	}
 }
 
-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 @@
 }
 
 /**
- * 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 @@
 	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 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 @@
 
 	/* 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 @@
 		/* 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 @@
 	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 a72ffc7..e33180d 100644
--- a/drivers/gpu/drm/amd/amdgpu/cz_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/cz_smc.c
@@ -814,7 +814,8 @@
 	* 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 @@
 	}
 
 	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 322edea..bda1249 100644
--- a/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/fiji_smc.c
@@ -764,7 +764,7 @@
 	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 @@
 	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 4bd1e5c..e992bf2 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 @@
 		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 @@
 			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 @@
 	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 @@
 					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 @@
 		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 @@
 			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 @@
 			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 @@
 			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 @@
 		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 @@
 	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 @@
 	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 53f0743..cb4f68f 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 @@
 		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 @@
 		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 @@
 	/* 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 @@
 	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 @@
 					     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 @@
 			  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 @@
 	return true;
 }
 
-static void gfx_v8_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);
-}
-
 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);
+	uint32_t seq = ring->fence_drv.sync_seq[ring->idx];
+	uint64_t addr = ring->fence_drv.gpu_addr;
+
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WAIT_REG_MEM, 5));
+	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 */
+
+	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 @@
 		/* 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 c900aa9..966d4b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/iceland_smc.c
@@ -625,7 +625,7 @@
 	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 1f5ac94..5421309 100644
--- a/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
+++ b/drivers/gpu/drm/amd/amdgpu/tonga_smc.c
@@ -763,7 +763,7 @@
 	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 @@
 	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 5fac5da..ed50dd7 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 @@
 	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 2d5c59c..9ad8b99 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 @@
 	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 d9f553f..7e9934f 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 @@
 	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 @@
 	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 552d9e7..b55ceb1 100644
--- a/drivers/gpu/drm/amd/amdgpu/vi.c
+++ b/drivers/gpu/drm/amd/amdgpu/vi.c
@@ -1400,7 +1400,8 @@
 	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 0000000..144f50a
--- /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 9259f1b..3697eee 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 @@
 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 @@
 			  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 @@
 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 @@
 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 @@
 		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 @@
 			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 @@
 /**
  * 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 @@
 	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 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 @@
 
 	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 2af0e4d..80b64dc 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_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_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 @@
  * 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 e62c379..d802638 100644
--- a/drivers/gpu/drm/amd/scheduler/sched_fence.c
+++ b/drivers/gpu/drm/amd/scheduler/sched_fence.c
@@ -36,7 +36,7 @@
 	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_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 9a860ca..d93e737 100644
--- a/drivers/gpu/drm/drm_ioctl.c
+++ b/drivers/gpu/drm/drm_ioctl.c
@@ -520,7 +520,8 @@
 
 /** 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 82be6b8..d1e300d 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 @@
 					     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 5a244ab..39d73db 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -640,6 +640,32 @@
 		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 89c1a8ce..2a5c76f 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -430,7 +430,7 @@
 
 /**
  * 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 b3e437b..c19e669 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -42,7 +42,7 @@
 	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 @@
 		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 @@
 		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 8cc9264..cf418be 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -15087,9 +15087,12 @@
 
 		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 87de15e..b35b5b2 100644
--- a/drivers/gpu/drm/mgag200/mgag200_fb.c
+++ b/drivers/gpu/drm/mgag200/mgag200_fb.c
@@ -186,17 +186,19 @@
 
 	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 @@
 
 	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 @@
 	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 de06388..b1a0f56 100644
--- a/drivers/gpu/drm/mgag200/mgag200_main.c
+++ b/drivers/gpu/drm/mgag200/mgag200_main.c
@@ -220,7 +220,7 @@
 	}
 	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 @@
 	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 @@
 					  &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:
+	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;
+	}
 
-out:
-	if (r)
-		mgag200_driver_unload(dev);
+	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/msm/mdp/mdp5/mdp5_irq.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
index b1f73be..b0d4b53 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_irq.c
@@ -178,7 +178,6 @@
 
 	irq_set_chip_and_handler(irq, &mdp5_hw_irq_chip, handle_level_irq);
 	irq_set_chip_data(irq, mdp5_kms);
-	set_irq_flags(irq, IRQF_VALID);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
index 7c6225c..dd845f8 100644
--- a/drivers/gpu/drm/qxl/qxl_display.c
+++ b/drivers/gpu/drm/qxl/qxl_display.c
@@ -886,13 +886,15 @@
 		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 d8319da..f3f562f 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -1573,10 +1573,12 @@
 
 	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 @@
 	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 787cd8f..e9115d3 100644
--- a/drivers/gpu/drm/radeon/si_dpm.c
+++ b/drivers/gpu/drm/radeon/si_dpm.c
@@ -2927,6 +2927,7 @@
 	{ 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 8d9b7de..745e996 100644
--- a/drivers/gpu/drm/ttm/ttm_bo.c
+++ b/drivers/gpu/drm/ttm/ttm_bo.c
@@ -882,6 +882,8 @@
 		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 @@
 		if (!type_ok)
 			continue;
 
+		type_found = true;
 		cur_flags = ttm_bo_select_caching(man, bo->mem.placement,
 						  cur_flags);
 		/*
@@ -901,12 +904,10 @@
 		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 @@
 		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 @@
 		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 @@
 		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 67720f7..b49445d 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 ce659a1..092ea81 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_cotable.c
@@ -311,7 +311,6 @@
 	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 @@
 	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 e13b20b..2c7a25c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c
@@ -752,12 +752,8 @@
 	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_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 @@
 
 	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 6d02de6..f19fd39 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
@@ -376,7 +376,6 @@
 	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 @@
 				 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 @@
 					 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 b565654..5da5de0 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c
@@ -1236,7 +1236,8 @@
 	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 @@
 	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 61fb7f3..15a6c01 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
@@ -1685,7 +1685,6 @@
 	struct drm_crtc *crtc;
 	u32 num_units = 0;
 	u32 i, k;
-	int ret;
 
 	dirty->dev_priv = dev_priv;
 
@@ -1711,7 +1710,7 @@
 			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 76069f0..222c9c2 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
@@ -484,7 +484,7 @@
 		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 c1912f8..e57667c 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
@@ -354,7 +354,7 @@
 	}
 
 	*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 @@
 			  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 @@
 	}
 
 	*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 @@
 	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 @@
 
 	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 @@
 				       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 @@
 		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_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 @@
 	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 @@
 
 	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 @@
 	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 bba1ee3..fd47547 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_shader.c
@@ -855,7 +855,7 @@
 
 	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 3361769..64b5040 100644
--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
@@ -46,6 +46,7 @@
 	struct vmw_surface srf;
 	uint32_t size;
 	struct drm_master *master;
+	struct ttm_base_object *backup_base;
 };
 
 /**
@@ -656,6 +657,7 @@
 	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 @@
 					    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 @@
 
 	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 @@
 					    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/gpu/ipu-v3/ipu-common.c b/drivers/gpu/ipu-v3/ipu-common.c
index 243f99a..e5a38d2 100644
--- a/drivers/gpu/ipu-v3/ipu-common.c
+++ b/drivers/gpu/ipu-v3/ipu-common.c
@@ -912,7 +912,7 @@
 	}
 }
 
-static void ipu_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ipu_irq_handler(struct irq_desc *desc)
 {
 	struct ipu_soc *ipu = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
@@ -925,7 +925,7 @@
 	chained_irq_exit(chip, desc);
 }
 
-static void ipu_err_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void ipu_err_irq_handler(struct irq_desc *desc)
 {
 	struct ipu_soc *ipu = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
@@ -1099,8 +1099,7 @@
 	}
 
 	ret = irq_alloc_domain_generic_chips(ipu->domain, 32, 1, "IPU",
-					     handle_level_irq, 0,
-					     IRQF_VALID, 0);
+					     handle_level_irq, 0, 0, 0);
 	if (ret < 0) {
 		dev_err(ipu->dev, "failed to alloc generic irq chips\n");
 		irq_domain_remove(ipu->domain);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 2f9aead..652afd1 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -204,6 +204,8 @@
 		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 @@
 		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 @@
 			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/hwmon/Kconfig b/drivers/hwmon/Kconfig
index 500b262..e13c902 100644
--- a/drivers/hwmon/Kconfig
+++ b/drivers/hwmon/Kconfig
@@ -1140,8 +1140,8 @@
 	help
 	  If you say yes here you get support for the hardware monitoring
 	  functionality of the Nuvoton NCT6106D, NCT6775F, NCT6776F, NCT6779D,
-	  NCT6791D, NCT6792D and compatible Super-I/O chips. This driver
-	  replaces the w83627ehf driver for NCT6775F and NCT6776F.
+	  NCT6791D, NCT6792D, NCT6793D, and compatible Super-I/O chips. This
+	  driver replaces the w83627ehf driver for NCT6775F and NCT6776F.
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called nct6775.
diff --git a/drivers/hwmon/nct6775.c b/drivers/hwmon/nct6775.c
index bd1c99d..8b4fa55 100644
--- a/drivers/hwmon/nct6775.c
+++ b/drivers/hwmon/nct6775.c
@@ -39,6 +39,7 @@
  * nct6779d    15      5       5       2+6    0xc560 0xc1    0x5ca3
  * nct6791d    15      6       6       2+6    0xc800 0xc1    0x5ca3
  * nct6792d    15      6       6       2+6    0xc910 0xc1    0x5ca3
+ * nct6793d    15      6       6       2+6    0xd120 0xc1    0x5ca3
  *
  * #temp lists the number of monitored temperature sources (first value) plus
  * the number of directly connectable temperature sensors (second value).
@@ -63,7 +64,7 @@
 
 #define USE_ALTERNATE
 
-enum kinds { nct6106, nct6775, nct6776, nct6779, nct6791, nct6792 };
+enum kinds { nct6106, nct6775, nct6776, nct6779, nct6791, nct6792, nct6793 };
 
 /* used to set data->name = nct6775_device_names[data->sio_kind] */
 static const char * const nct6775_device_names[] = {
@@ -73,6 +74,17 @@
 	"nct6779",
 	"nct6791",
 	"nct6792",
+	"nct6793",
+};
+
+static const char * const nct6775_sio_names[] __initconst = {
+	"NCT6106D",
+	"NCT6775F",
+	"NCT6776D/F",
+	"NCT6779D",
+	"NCT6791D",
+	"NCT6792D",
+	"NCT6793D",
 };
 
 static unsigned short force_id;
@@ -104,6 +116,7 @@
 #define SIO_NCT6779_ID		0xc560
 #define SIO_NCT6791_ID		0xc800
 #define SIO_NCT6792_ID		0xc910
+#define SIO_NCT6793_ID		0xd120
 #define SIO_ID_MASK		0xFFF0
 
 enum pwm_enable { off, manual, thermal_cruise, speed_cruise, sf3, sf4 };
@@ -354,6 +367,10 @@
 
 /* NCT6776 specific data */
 
+/* STEP_UP_TIME and STEP_DOWN_TIME regs are swapped for all chips but NCT6775 */
+#define NCT6776_REG_FAN_STEP_UP_TIME NCT6775_REG_FAN_STEP_DOWN_TIME
+#define NCT6776_REG_FAN_STEP_DOWN_TIME NCT6775_REG_FAN_STEP_UP_TIME
+
 static const s8 NCT6776_ALARM_BITS[] = {
 	0, 1, 2, 3, 8, 21, 20, 16,	/* in0.. in7 */
 	17, -1, -1, -1, -1, -1, -1,	/* in8..in14 */
@@ -533,7 +550,7 @@
 	4, 5, 13, -1, -1, -1,		/* temp1..temp6 */
 	12, 9 };			/* intrusion0, intrusion1 */
 
-/* NCT6792 specific data */
+/* NCT6792/NCT6793 specific data */
 
 static const u16 NCT6792_REG_TEMP_MON[] = {
 	0x73, 0x75, 0x77, 0x79, 0x7b, 0x7d };
@@ -1056,6 +1073,7 @@
 	case nct6779:
 	case nct6791:
 	case nct6792:
+	case nct6793:
 		return reg == 0x150 || reg == 0x153 || reg == 0x155 ||
 		  ((reg & 0xfff0) == 0x4b0 && (reg & 0x000f) < 0x0b) ||
 		  reg == 0x402 ||
@@ -1407,6 +1425,7 @@
 		case nct6779:
 		case nct6791:
 		case nct6792:
+		case nct6793:
 			reg = nct6775_read_value(data,
 					data->REG_CRITICAL_PWM_ENABLE[i]);
 			if (reg & data->CRITICAL_PWM_ENABLE_MASK)
@@ -2822,6 +2841,7 @@
 		case nct6779:
 		case nct6791:
 		case nct6792:
+		case nct6793:
 			nct6775_write_value(data, data->REG_CRITICAL_PWM[nr],
 					    val);
 			reg = nct6775_read_value(data,
@@ -3256,7 +3276,7 @@
 		pwm4pin = false;
 		pwm5pin = false;
 		pwm6pin = false;
-	} else {	/* NCT6779D, NCT6791D, or NCT6792D */
+	} else {	/* NCT6779D, NCT6791D, NCT6792D, or NCT6793D */
 		regval = superio_inb(sioreg, 0x1c);
 
 		fan3pin = !(regval & (1 << 5));
@@ -3269,7 +3289,8 @@
 
 		fan4min = fan4pin;
 
-		if (data->kind == nct6791 || data->kind == nct6792) {
+		if (data->kind == nct6791 || data->kind == nct6792 ||
+		    data->kind == nct6793) {
 			regval = superio_inb(sioreg, 0x2d);
 			fan6pin = (regval & (1 << 1));
 			pwm6pin = (regval & (1 << 0));
@@ -3528,8 +3549,8 @@
 		data->REG_FAN_PULSES = NCT6776_REG_FAN_PULSES;
 		data->FAN_PULSE_SHIFT = NCT6775_FAN_PULSE_SHIFT;
 		data->REG_FAN_TIME[0] = NCT6775_REG_FAN_STOP_TIME;
-		data->REG_FAN_TIME[1] = NCT6775_REG_FAN_STEP_UP_TIME;
-		data->REG_FAN_TIME[2] = NCT6775_REG_FAN_STEP_DOWN_TIME;
+		data->REG_FAN_TIME[1] = NCT6776_REG_FAN_STEP_UP_TIME;
+		data->REG_FAN_TIME[2] = NCT6776_REG_FAN_STEP_DOWN_TIME;
 		data->REG_TOLERANCE_H = NCT6776_REG_TOLERANCE_H;
 		data->REG_PWM[0] = NCT6775_REG_PWM;
 		data->REG_PWM[1] = NCT6775_REG_FAN_START_OUTPUT;
@@ -3600,8 +3621,8 @@
 		data->REG_FAN_PULSES = NCT6779_REG_FAN_PULSES;
 		data->FAN_PULSE_SHIFT = NCT6775_FAN_PULSE_SHIFT;
 		data->REG_FAN_TIME[0] = NCT6775_REG_FAN_STOP_TIME;
-		data->REG_FAN_TIME[1] = NCT6775_REG_FAN_STEP_UP_TIME;
-		data->REG_FAN_TIME[2] = NCT6775_REG_FAN_STEP_DOWN_TIME;
+		data->REG_FAN_TIME[1] = NCT6776_REG_FAN_STEP_UP_TIME;
+		data->REG_FAN_TIME[2] = NCT6776_REG_FAN_STEP_DOWN_TIME;
 		data->REG_TOLERANCE_H = NCT6776_REG_TOLERANCE_H;
 		data->REG_PWM[0] = NCT6775_REG_PWM;
 		data->REG_PWM[1] = NCT6775_REG_FAN_START_OUTPUT;
@@ -3643,6 +3664,7 @@
 		break;
 	case nct6791:
 	case nct6792:
+	case nct6793:
 		data->in_num = 15;
 		data->pwm_num = 6;
 		data->auto_pwm_num = 4;
@@ -3677,8 +3699,8 @@
 		data->REG_FAN_PULSES = NCT6779_REG_FAN_PULSES;
 		data->FAN_PULSE_SHIFT = NCT6775_FAN_PULSE_SHIFT;
 		data->REG_FAN_TIME[0] = NCT6775_REG_FAN_STOP_TIME;
-		data->REG_FAN_TIME[1] = NCT6775_REG_FAN_STEP_UP_TIME;
-		data->REG_FAN_TIME[2] = NCT6775_REG_FAN_STEP_DOWN_TIME;
+		data->REG_FAN_TIME[1] = NCT6776_REG_FAN_STEP_UP_TIME;
+		data->REG_FAN_TIME[2] = NCT6776_REG_FAN_STEP_DOWN_TIME;
 		data->REG_TOLERANCE_H = NCT6776_REG_TOLERANCE_H;
 		data->REG_PWM[0] = NCT6775_REG_PWM;
 		data->REG_PWM[1] = NCT6775_REG_FAN_START_OUTPUT;
@@ -3918,6 +3940,7 @@
 	case nct6779:
 	case nct6791:
 	case nct6792:
+	case nct6793:
 		break;
 	}
 
@@ -3950,6 +3973,7 @@
 			break;
 		case nct6791:
 		case nct6792:
+		case nct6793:
 			tmp |= 0x7e;
 			break;
 		}
@@ -4047,7 +4071,8 @@
 	if (reg != data->sio_reg_enable)
 		superio_outb(sioreg, SIO_REG_ENABLE, data->sio_reg_enable);
 
-	if (data->kind == nct6791 || data->kind == nct6792)
+	if (data->kind == nct6791 || data->kind == nct6792 ||
+	    data->kind == nct6793)
 		nct6791_enable_io_mapping(sioreg);
 
 	superio_exit(sioreg);
@@ -4106,15 +4131,6 @@
 	.probe		= nct6775_probe,
 };
 
-static const char * const nct6775_sio_names[] __initconst = {
-	"NCT6106D",
-	"NCT6775F",
-	"NCT6776D/F",
-	"NCT6779D",
-	"NCT6791D",
-	"NCT6792D",
-};
-
 /* nct6775_find() looks for a '627 in the Super-I/O config space */
 static int __init nct6775_find(int sioaddr, struct nct6775_sio_data *sio_data)
 {
@@ -4150,6 +4166,9 @@
 	case SIO_NCT6792_ID:
 		sio_data->kind = nct6792;
 		break;
+	case SIO_NCT6793_ID:
+		sio_data->kind = nct6793;
+		break;
 	default:
 		if (val != 0xffff)
 			pr_debug("unsupported chip ID: 0x%04x\n", val);
@@ -4175,7 +4194,8 @@
 		superio_outb(sioaddr, SIO_REG_ENABLE, val | 0x01);
 	}
 
-	if (sio_data->kind == nct6791 || sio_data->kind == nct6792)
+	if (sio_data->kind == nct6791 || sio_data->kind == nct6792 ||
+	    sio_data->kind == nct6793)
 		nct6791_enable_io_mapping(sioaddr);
 
 	superio_exit(sioaddr);
@@ -4285,7 +4305,7 @@
 }
 
 MODULE_AUTHOR("Guenter Roeck <linux@roeck-us.net>");
-MODULE_DESCRIPTION("NCT6106D/NCT6775F/NCT6776F/NCT6779D/NCT6791D/NCT6792D driver");
+MODULE_DESCRIPTION("Driver for NCT6775F and compatible chips");
 MODULE_LICENSE("GPL");
 
 module_init(sensors_nct6775_init);
diff --git a/drivers/infiniband/Kconfig b/drivers/infiniband/Kconfig
index da4c697..aa26f3c 100644
--- a/drivers/infiniband/Kconfig
+++ b/drivers/infiniband/Kconfig
@@ -56,7 +56,6 @@
 
 source "drivers/infiniband/hw/mthca/Kconfig"
 source "drivers/infiniband/hw/qib/Kconfig"
-source "drivers/infiniband/hw/ehca/Kconfig"
 source "drivers/infiniband/hw/cxgb3/Kconfig"
 source "drivers/infiniband/hw/cxgb4/Kconfig"
 source "drivers/infiniband/hw/mlx4/Kconfig"
diff --git a/drivers/infiniband/hw/Makefile b/drivers/infiniband/hw/Makefile
index 1bdb999..aded2a5 100644
--- a/drivers/infiniband/hw/Makefile
+++ b/drivers/infiniband/hw/Makefile
@@ -1,6 +1,5 @@
 obj-$(CONFIG_INFINIBAND_MTHCA)		+= mthca/
 obj-$(CONFIG_INFINIBAND_QIB)		+= qib/
-obj-$(CONFIG_INFINIBAND_EHCA)		+= ehca/
 obj-$(CONFIG_INFINIBAND_CXGB3)		+= cxgb3/
 obj-$(CONFIG_INFINIBAND_CXGB4)		+= cxgb4/
 obj-$(CONFIG_MLX4_INFINIBAND)		+= mlx4/
diff --git a/drivers/irqchip/exynos-combiner.c b/drivers/irqchip/exynos-combiner.c
index e9c6f2a..cd7d3bc 100644
--- a/drivers/irqchip/exynos-combiner.c
+++ b/drivers/irqchip/exynos-combiner.c
@@ -65,12 +65,10 @@
 	__raw_writel(mask, combiner_base(data) + COMBINER_ENABLE_SET);
 }
 
-static void combiner_handle_cascade_irq(unsigned int __irq,
-					struct irq_desc *desc)
+static void combiner_handle_cascade_irq(struct irq_desc *desc)
 {
 	struct combiner_chip_data *chip_data = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	unsigned int irq = irq_desc_get_irq(desc);
 	unsigned int cascade_irq, combiner_irq;
 	unsigned long status;
 
@@ -88,7 +86,7 @@
 	cascade_irq = irq_find_mapping(combiner_irq_domain, combiner_irq);
 
 	if (unlikely(!cascade_irq))
-		handle_bad_irq(irq, desc);
+		handle_bad_irq(desc);
 	else
 		generic_handle_irq(cascade_irq);
 
@@ -165,7 +163,7 @@
 
 	irq_set_chip_and_handler(irq, &combiner_chip, handle_level_irq);
 	irq_set_chip_data(irq, &combiner_data[hw >> 3]);
-	set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	irq_set_probe(irq);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
index 39b72da..655cb96 100644
--- a/drivers/irqchip/irq-armada-370-xp.c
+++ b/drivers/irqchip/irq-armada-370-xp.c
@@ -200,7 +200,6 @@
 {
 	irq_set_chip_and_handler(virq, &armada_370_xp_msi_irq_chip,
 				 handle_simple_irq);
-	set_irq_flags(virq, IRQF_VALID);
 
 	return 0;
 }
@@ -317,7 +316,7 @@
 		irq_set_chip_and_handler(virq, &armada_370_xp_irq_chip,
 					handle_level_irq);
 	}
-	set_irq_flags(virq, IRQF_VALID | IRQF_PROBE);
+	irq_set_probe(virq);
 
 	return 0;
 }
@@ -447,8 +446,7 @@
 static void armada_370_xp_handle_msi_irq(struct pt_regs *r, bool b) {}
 #endif
 
-static void armada_370_xp_mpic_handle_cascade_irq(unsigned int irq,
-						  struct irq_desc *desc)
+static void armada_370_xp_mpic_handle_cascade_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned long irqmap, irqn, irqsrc, cpuid;
diff --git a/drivers/irqchip/irq-bcm2835.c b/drivers/irqchip/irq-bcm2835.c
index ed4ca9d..bf9cc5f 100644
--- a/drivers/irqchip/irq-bcm2835.c
+++ b/drivers/irqchip/irq-bcm2835.c
@@ -96,7 +96,7 @@
 static struct armctrl_ic intc __read_mostly;
 static void __exception_irq_entry bcm2835_handle_irq(
 	struct pt_regs *regs);
-static void bcm2836_chained_handle_irq(unsigned int irq, struct irq_desc *desc);
+static void bcm2836_chained_handle_irq(struct irq_desc *desc);
 
 static void armctrl_mask_irq(struct irq_data *d)
 {
@@ -166,7 +166,7 @@
 			BUG_ON(irq <= 0);
 			irq_set_chip_and_handler(irq, &armctrl_chip,
 				handle_level_irq);
-			set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+			irq_set_probe(irq);
 		}
 	}
 
@@ -245,7 +245,7 @@
 		handle_IRQ(irq_linear_revmap(intc.domain, hwirq), regs);
 }
 
-static void bcm2836_chained_handle_irq(unsigned int irq, struct irq_desc *desc)
+static void bcm2836_chained_handle_irq(struct irq_desc *desc)
 {
 	u32 hwirq;
 
diff --git a/drivers/irqchip/irq-bcm7038-l1.c b/drivers/irqchip/irq-bcm7038-l1.c
index 409bdc6..0fea985 100644
--- a/drivers/irqchip/irq-bcm7038-l1.c
+++ b/drivers/irqchip/irq-bcm7038-l1.c
@@ -115,7 +115,7 @@
 		writel(val, reg);
 }
 
-static void bcm7038_l1_irq_handle(unsigned int irq, struct irq_desc *desc)
+static void bcm7038_l1_irq_handle(struct irq_desc *desc)
 {
 	struct bcm7038_l1_chip *intc = irq_desc_get_handler_data(desc);
 	struct bcm7038_l1_cpu *cpu;
diff --git a/drivers/irqchip/irq-bcm7120-l2.c b/drivers/irqchip/irq-bcm7120-l2.c
index d3f9769..61b18ab 100644
--- a/drivers/irqchip/irq-bcm7120-l2.c
+++ b/drivers/irqchip/irq-bcm7120-l2.c
@@ -56,7 +56,7 @@
 	const __be32 *map_mask_prop;
 };
 
-static void bcm7120_l2_intc_irq_handle(unsigned int irq, struct irq_desc *desc)
+static void bcm7120_l2_intc_irq_handle(struct irq_desc *desc)
 {
 	struct bcm7120_l1_intc_data *data = irq_desc_get_handler_data(desc);
 	struct bcm7120_l2_intc_data *b = data->b;
diff --git a/drivers/irqchip/irq-brcmstb-l2.c b/drivers/irqchip/irq-brcmstb-l2.c
index aedda06..65cd341 100644
--- a/drivers/irqchip/irq-brcmstb-l2.c
+++ b/drivers/irqchip/irq-brcmstb-l2.c
@@ -49,13 +49,12 @@
 	u32 saved_mask; /* for suspend/resume */
 };
 
-static void brcmstb_l2_intc_irq_handle(unsigned int __irq,
-				       struct irq_desc *desc)
+static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc)
 {
 	struct brcmstb_l2_intc_data *b = irq_desc_get_handler_data(desc);
 	struct irq_chip_generic *gc = irq_get_domain_generic_chip(b->domain, 0);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	unsigned int irq = irq_desc_get_irq(desc);
+	unsigned int irq;
 	u32 status;
 
 	chained_irq_enter(chip, desc);
@@ -65,7 +64,7 @@
 
 	if (status == 0) {
 		raw_spin_lock(&desc->lock);
-		handle_bad_irq(irq, desc);
+		handle_bad_irq(desc);
 		raw_spin_unlock(&desc->lock);
 		goto out;
 	}
diff --git a/drivers/irqchip/irq-clps711x.c b/drivers/irqchip/irq-clps711x.c
index 2dd929e..eb5eb0c 100644
--- a/drivers/irqchip/irq-clps711x.c
+++ b/drivers/irqchip/irq-clps711x.c
@@ -132,14 +132,14 @@
 					irq_hw_number_t hw)
 {
 	irq_flow_handler_t handler = handle_level_irq;
-	unsigned int flags = IRQF_VALID | IRQF_PROBE;
+	unsigned int flags = 0;
 
 	if (!clps711x_irqs[hw].flags)
 		return 0;
 
 	if (clps711x_irqs[hw].flags & CLPS711X_FLAG_FIQ) {
 		handler = handle_bad_irq;
-		flags |= IRQF_NOAUTOEN;
+		flags |= IRQ_NOAUTOEN;
 	} else if (clps711x_irqs[hw].eoi) {
 		handler = handle_fasteoi_irq;
 	}
@@ -149,7 +149,7 @@
 		writel_relaxed(0, clps711x_intc->base + clps711x_irqs[hw].eoi);
 
 	irq_set_chip_and_handler(virq, &clps711x_intc_chip, handler);
-	set_irq_flags(virq, flags);
+	irq_modify_status(virq, IRQ_NOPROBE, flags);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-dw-apb-ictl.c b/drivers/irqchip/irq-dw-apb-ictl.c
index efd95d9..052f266 100644
--- a/drivers/irqchip/irq-dw-apb-ictl.c
+++ b/drivers/irqchip/irq-dw-apb-ictl.c
@@ -26,7 +26,7 @@
 #define APB_INT_FINALSTATUS_H	0x34
 #define APB_INT_BASE_OFFSET	0x04
 
-static void dw_apb_ictl_handler(unsigned int irq, struct irq_desc *desc)
+static void dw_apb_ictl_handler(struct irq_desc *desc)
 {
 	struct irq_domain *d = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
index db04fc1..12985da 100644
--- a/drivers/irqchip/irq-gic-v2m.c
+++ b/drivers/irqchip/irq-gic-v2m.c
@@ -95,8 +95,8 @@
 	struct v2m_data *v2m = irq_data_get_irq_chip_data(data);
 	phys_addr_t addr = v2m->res.start + V2M_MSI_SETSPI_NS;
 
-	msg->address_hi = (u32) (addr >> 32);
-	msg->address_lo = (u32) (addr);
+	msg->address_hi = upper_32_bits(addr);
+	msg->address_lo = lower_32_bits(addr);
 	msg->data = data->hwirq;
 }
 
diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c
index 26b55c5..ac7ae2b 100644
--- a/drivers/irqchip/irq-gic-v3-its.c
+++ b/drivers/irqchip/irq-gic-v3-its.c
@@ -898,8 +898,10 @@
 			 * non-cacheable as well.
 			 */
 			shr = tmp & GITS_BASER_SHAREABILITY_MASK;
-			if (!shr)
+			if (!shr) {
 				cache = GITS_BASER_nC;
+				__flush_dcache_area(base, alloc_size);
+			}
 			goto retry_baser;
 		}
 
@@ -1140,6 +1142,8 @@
 		return NULL;
 	}
 
+	__flush_dcache_area(itt, sz);
+
 	dev->its = its;
 	dev->itt = itt;
 	dev->nr_ites = nr_ites;
diff --git a/drivers/irqchip/irq-gic-v3.c b/drivers/irqchip/irq-gic-v3.c
index 7deed6e..36ecfc8 100644
--- a/drivers/irqchip/irq-gic-v3.c
+++ b/drivers/irqchip/irq-gic-v3.c
@@ -70,11 +70,6 @@
 	return gic_irq(d) < 32;
 }
 
-static inline bool forwarded_irq(struct irq_data *d)
-{
-	return d->handler_data != NULL;
-}
-
 static inline void __iomem *gic_dist_base(struct irq_data *d)
 {
 	if (gic_irq_in_rdist(d))	/* SGI+PPI -> SGI_base for this CPU */
@@ -249,7 +244,7 @@
 	 * disabled/masked will not get "stuck", because there is
 	 * noone to deactivate it (guest is being terminated).
 	 */
-	if (forwarded_irq(d))
+	if (irqd_is_forwarded_to_vcpu(d))
 		gic_poke_irq(d, GICD_ICACTIVER);
 }
 
@@ -324,7 +319,7 @@
 	 * No need to deactivate an LPI, or an interrupt that
 	 * is is getting forwarded to a vcpu.
 	 */
-	if (gic_irq(d) >= 8192 || forwarded_irq(d))
+	if (gic_irq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d))
 		return;
 	gic_write_dir(gic_irq(d));
 }
@@ -357,7 +352,10 @@
 
 static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu)
 {
-	d->handler_data = vcpu;
+	if (vcpu)
+		irqd_set_forwarded_to_vcpu(d);
+	else
+		irqd_clr_forwarded_to_vcpu(d);
 	return 0;
 }
 
@@ -754,13 +752,13 @@
 		irq_set_percpu_devid(irq);
 		irq_domain_set_info(d, irq, hw, chip, d->host_data,
 				    handle_percpu_devid_irq, NULL, NULL);
-		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	}
 	/* SPIs */
 	if (hw >= 32 && hw < gic_data.irq_nr) {
 		irq_domain_set_info(d, irq, hw, chip, d->host_data,
 				    handle_fasteoi_irq, NULL, NULL);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_set_probe(irq);
 	}
 	/* LPIs */
 	if (hw >= 8192 && hw < GIC_ID_NR) {
@@ -768,7 +766,6 @@
 			return -EPERM;
 		irq_domain_set_info(d, irq, hw, chip, d->host_data,
 				    handle_fasteoi_irq, NULL, NULL);
-		set_irq_flags(irq, IRQF_VALID);
 	}
 
 	return 0;
diff --git a/drivers/irqchip/irq-gic.c b/drivers/irqchip/irq-gic.c
index e6b7ed5..982c09c 100644
--- a/drivers/irqchip/irq-gic.c
+++ b/drivers/irqchip/irq-gic.c
@@ -145,29 +145,10 @@
 	void *data = irq_data_get_irq_handler_data(d);
 
 	/*
-	 * If handler_data pointing to one of the secondary GICs, then
-	 * this is a cascading interrupt, and it cannot possibly be
-	 * forwarded.
+	 * If handler_data is set, this is a cascading interrupt, and
+	 * it cannot possibly be forwarded.
 	 */
-	if (data >= (void *)(gic_data + 1) &&
-	    data <  (void *)(gic_data + MAX_GIC_NR))
-		return true;
-
-	return false;
-}
-
-static inline bool forwarded_irq(struct irq_data *d)
-{
-	/*
-	 * A forwarded interrupt:
-	 * - is on the primary GIC
-	 * - has its handler_data set to a value
-	 * - that isn't a secondary GIC
-	 */
-	if (d->handler_data && !cascading_gic_irq(d))
-		return true;
-
-	return false;
+	return data != NULL;
 }
 
 /*
@@ -201,7 +182,7 @@
 	 * disabled/masked will not get "stuck", because there is
 	 * noone to deactivate it (guest is being terminated).
 	 */
-	if (forwarded_irq(d))
+	if (irqd_is_forwarded_to_vcpu(d))
 		gic_poke_irq(d, GIC_DIST_ACTIVE_CLEAR);
 }
 
@@ -218,7 +199,7 @@
 static void gic_eoimode1_eoi_irq(struct irq_data *d)
 {
 	/* Do not deactivate an IRQ forwarded to a vcpu. */
-	if (forwarded_irq(d))
+	if (irqd_is_forwarded_to_vcpu(d))
 		return;
 
 	writel_relaxed(gic_irq(d), gic_cpu_base(d) + GIC_CPU_DEACTIVATE);
@@ -296,7 +277,10 @@
 	if (cascading_gic_irq(d))
 		return -EINVAL;
 
-	d->handler_data = vcpu;
+	if (vcpu)
+		irqd_set_forwarded_to_vcpu(d);
+	else
+		irqd_clr_forwarded_to_vcpu(d);
 	return 0;
 }
 
@@ -357,7 +341,7 @@
 	} while (1);
 }
 
-static void gic_handle_cascade_irq(unsigned int irq, struct irq_desc *desc)
+static void gic_handle_cascade_irq(struct irq_desc *desc)
 {
 	struct gic_chip_data *chip_data = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
@@ -376,7 +360,7 @@
 
 	cascade_irq = irq_find_mapping(chip_data->domain, gic_irq);
 	if (unlikely(gic_irq < 32 || gic_irq > 1020))
-		handle_bad_irq(cascade_irq, desc);
+		handle_bad_irq(desc);
 	else
 		generic_handle_irq(cascade_irq);
 
@@ -906,11 +890,11 @@
 		irq_set_percpu_devid(irq);
 		irq_domain_set_info(d, irq, hw, chip, d->host_data,
 				    handle_percpu_devid_irq, NULL, NULL);
-		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	} else {
 		irq_domain_set_info(d, irq, hw, chip, d->host_data,
 				    handle_fasteoi_irq, NULL, NULL);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_set_probe(irq);
 	}
 	return 0;
 }
@@ -1119,12 +1103,49 @@
 #ifdef CONFIG_OF
 static int gic_cnt __initdata;
 
+static bool gic_check_eoimode(struct device_node *node, void __iomem **base)
+{
+	struct resource cpuif_res;
+
+	of_address_to_resource(node, 1, &cpuif_res);
+
+	if (!is_hyp_mode_available())
+		return false;
+	if (resource_size(&cpuif_res) < SZ_8K)
+		return false;
+	if (resource_size(&cpuif_res) == SZ_128K) {
+		u32 val_low, val_high;
+
+		/*
+		 * Verify that we have the first 4kB of a GIC400
+		 * aliased over the first 64kB by checking the
+		 * GICC_IIDR register on both ends.
+		 */
+		val_low = readl_relaxed(*base + GIC_CPU_IDENT);
+		val_high = readl_relaxed(*base + GIC_CPU_IDENT + 0xf000);
+		if ((val_low & 0xffff0fff) != 0x0202043B ||
+		    val_low != val_high)
+			return false;
+
+		/*
+		 * Move the base up by 60kB, so that we have a 8kB
+		 * contiguous region, which allows us to use GICC_DIR
+		 * at its normal offset. Please pass me that bucket.
+		 */
+		*base += 0xf000;
+		cpuif_res.start += 0xf000;
+		pr_warn("GIC: Adjusting CPU interface base to %pa",
+			&cpuif_res.start);
+	}
+
+	return true;
+}
+
 static int __init
 gic_of_init(struct device_node *node, struct device_node *parent)
 {
 	void __iomem *cpu_base;
 	void __iomem *dist_base;
-	struct resource cpu_res;
 	u32 percpu_offset;
 	int irq;
 
@@ -1137,14 +1158,11 @@
 	cpu_base = of_iomap(node, 1);
 	WARN(!cpu_base, "unable to map gic cpu registers\n");
 
-	of_address_to_resource(node, 1, &cpu_res);
-
 	/*
 	 * Disable split EOI/Deactivate if either HYP is not available
 	 * or the CPU interface is too small.
 	 */
-	if (gic_cnt == 0 && (!is_hyp_mode_available() ||
-			     resource_size(&cpu_res) < SZ_8K))
+	if (gic_cnt == 0 && !gic_check_eoimode(node, &cpu_base))
 		static_key_slow_dec(&supports_deactivate);
 
 	if (of_property_read_u32(node, "cpu-offset", &percpu_offset))
diff --git a/drivers/irqchip/irq-hip04.c b/drivers/irqchip/irq-hip04.c
index a0128c7..8f3ca8f 100644
--- a/drivers/irqchip/irq-hip04.c
+++ b/drivers/irqchip/irq-hip04.c
@@ -307,11 +307,11 @@
 		irq_set_percpu_devid(irq);
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_percpu_devid_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_NOAUTOEN);
+		irq_set_status_flags(irq, IRQ_NOAUTOEN);
 	} else {
 		irq_set_chip_and_handler(irq, &hip04_irq_chip,
 					 handle_fasteoi_irq);
-		set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+		irq_set_probe(irq);
 	}
 	irq_set_chip_data(irq, d->host_data);
 	return 0;
diff --git a/drivers/irqchip/irq-i8259.c b/drivers/irqchip/irq-i8259.c
index 4836102..e484fd2 100644
--- a/drivers/irqchip/irq-i8259.c
+++ b/drivers/irqchip/irq-i8259.c
@@ -352,7 +352,7 @@
 	__init_i8259_irqs(NULL);
 }
 
-static void i8259_irq_dispatch(unsigned int __irq, struct irq_desc *desc)
+static void i8259_irq_dispatch(struct irq_desc *desc)
 {
 	struct irq_domain *domain = irq_desc_get_handler_data(desc);
 	int hwirq = i8259_irq();
diff --git a/drivers/irqchip/irq-imgpdc.c b/drivers/irqchip/irq-imgpdc.c
index 841604b..c02d29c 100644
--- a/drivers/irqchip/irq-imgpdc.c
+++ b/drivers/irqchip/irq-imgpdc.c
@@ -218,7 +218,7 @@
 	return 0;
 }
 
-static void pdc_intc_perip_isr(unsigned int __irq, struct irq_desc *desc)
+static void pdc_intc_perip_isr(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct pdc_intc_priv *priv;
@@ -240,7 +240,7 @@
 	generic_handle_irq(irq_no);
 }
 
-static void pdc_intc_syswake_isr(unsigned int irq, struct irq_desc *desc)
+static void pdc_intc_syswake_isr(struct irq_desc *desc)
 {
 	struct pdc_intc_priv *priv;
 	unsigned int syswake, irq_no;
diff --git a/drivers/irqchip/irq-keystone.c b/drivers/irqchip/irq-keystone.c
index c151726..deb89d6 100644
--- a/drivers/irqchip/irq-keystone.c
+++ b/drivers/irqchip/irq-keystone.c
@@ -83,7 +83,7 @@
 	/* nothing to do here */
 }
 
-static void keystone_irq_handler(unsigned __irq, struct irq_desc *desc)
+static void keystone_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct keystone_irq_device *kirq = irq_desc_get_handler_data(desc);
@@ -127,7 +127,7 @@
 
 	irq_set_chip_data(virq, kirq);
 	irq_set_chip_and_handler(virq, &kirq->chip, handle_level_irq);
-	set_irq_flags(virq, IRQF_VALID | IRQF_PROBE);
+	irq_set_probe(virq);
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-metag-ext.c b/drivers/irqchip/irq-metag-ext.c
index 5f4c529..8c38b3d 100644
--- a/drivers/irqchip/irq-metag-ext.c
+++ b/drivers/irqchip/irq-metag-ext.c
@@ -446,7 +446,7 @@
  * Whilst using TR2 to detect external interrupts is a software convention it is
  * (hopefully) unlikely to change.
  */
-static void meta_intc_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void meta_intc_irq_demux(struct irq_desc *desc)
 {
 	struct meta_intc_priv *priv = &meta_intc_priv;
 	irq_hw_number_t hw;
diff --git a/drivers/irqchip/irq-metag.c b/drivers/irqchip/irq-metag.c
index 3d23ce3..a5f053b 100644
--- a/drivers/irqchip/irq-metag.c
+++ b/drivers/irqchip/irq-metag.c
@@ -220,7 +220,7 @@
  *	occurred. It is this function's job to demux this irq and
  *	figure out exactly which trigger needs servicing.
  */
-static void metag_internal_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void metag_internal_irq_demux(struct irq_desc *desc)
 {
 	struct metag_internal_irq_priv *priv = irq_desc_get_handler_data(desc);
 	irq_hw_number_t hw;
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 1764bcf..af2f16b 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -546,7 +546,7 @@
 	gic_handle_shared_int(false);
 }
 
-static void gic_irq_dispatch(unsigned int irq, struct irq_desc *desc)
+static void gic_irq_dispatch(struct irq_desc *desc)
 {
 	gic_handle_local_int(true);
 	gic_handle_shared_int(true);
diff --git a/drivers/irqchip/irq-mmp.c b/drivers/irqchip/irq-mmp.c
index 781ed6e..013fc96 100644
--- a/drivers/irqchip/irq-mmp.c
+++ b/drivers/irqchip/irq-mmp.c
@@ -129,7 +129,7 @@
 	.irq_unmask	= icu_unmask_irq,
 };
 
-static void icu_mux_irq_demux(unsigned int __irq, struct irq_desc *desc)
+static void icu_mux_irq_demux(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct irq_domain *domain;
@@ -164,7 +164,6 @@
 			      irq_hw_number_t hw)
 {
 	irq_set_chip_and_handler(irq, &icu_irq_chip, handle_level_irq);
-	set_irq_flags(irq, IRQF_VALID);
 	return 0;
 }
 
@@ -234,7 +233,6 @@
 	for (irq = 0; irq < 64; irq++) {
 		icu_mask_irq(irq_get_irq_data(irq));
 		irq_set_chip_and_handler(irq, &icu_irq_chip, handle_level_irq);
-		set_irq_flags(irq, IRQF_VALID);
 	}
 	irq_set_default_host(icu_data[0].domain);
 	set_handle_irq(mmp_handle_irq);
@@ -337,7 +335,6 @@
 			irq_set_chip_and_handler(irq, &icu_irq_chip,
 						 handle_level_irq);
 		}
-		set_irq_flags(irq, IRQF_VALID);
 	}
 	irq_set_default_host(icu_data[0].domain);
 	set_handle_irq(mmp2_handle_irq);
diff --git a/drivers/irqchip/irq-mxs.c b/drivers/irqchip/irq-mxs.c
index 1faf812..604df63 100644
--- a/drivers/irqchip/irq-mxs.c
+++ b/drivers/irqchip/irq-mxs.c
@@ -84,7 +84,6 @@
 				irq_hw_number_t hw)
 {
 	irq_set_chip_and_handler(virq, &mxs_icoll_chip, handle_level_irq);
-	set_irq_flags(virq, IRQF_VALID);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-orion.c b/drivers/irqchip/irq-orion.c
index 5ea999a..be4c5a8 100644
--- a/drivers/irqchip/irq-orion.c
+++ b/drivers/irqchip/irq-orion.c
@@ -106,7 +106,7 @@
 #define ORION_BRIDGE_IRQ_CAUSE	0x00
 #define ORION_BRIDGE_IRQ_MASK	0x04
 
-static void orion_bridge_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void orion_bridge_irq_handler(struct irq_desc *desc)
 {
 	struct irq_domain *d = irq_desc_get_handler_data(desc);
 
diff --git a/drivers/irqchip/irq-renesas-intc-irqpin.c b/drivers/irqchip/irq-renesas-intc-irqpin.c
index 0670ab4..9525335 100644
--- a/drivers/irqchip/irq-renesas-intc-irqpin.c
+++ b/drivers/irqchip/irq-renesas-intc-irqpin.c
@@ -283,6 +283,9 @@
 static int intc_irqpin_irq_set_wake(struct irq_data *d, unsigned int on)
 {
 	struct intc_irqpin_priv *p = irq_data_get_irq_chip_data(d);
+	int hw_irq = irqd_to_hwirq(d);
+
+	irq_set_irq_wake(p->irq[hw_irq].requested_irq, on);
 
 	if (!p->clk)
 		return 0;
@@ -332,6 +335,12 @@
 	return status;
 }
 
+/*
+ * This lock class tells lockdep that INTC External IRQ Pin irqs are in a
+ * different category than their parents, so it won't report false recursion.
+ */
+static struct lock_class_key intc_irqpin_irq_lock_class;
+
 static int intc_irqpin_irq_domain_map(struct irq_domain *h, unsigned int virq,
 				      irq_hw_number_t hw)
 {
@@ -342,8 +351,8 @@
 
 	intc_irqpin_dbg(&p->irq[hw], "map");
 	irq_set_chip_data(virq, h->host_data);
+	irq_set_lockdep_class(virq, &intc_irqpin_irq_lock_class);
 	irq_set_chip_and_handler(virq, &p->irq_chip, handle_level_irq);
-	set_irq_flags(virq, IRQF_VALID); /* kill me now */
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-renesas-irqc.c b/drivers/irqchip/irq-renesas-irqc.c
index 2aa3add7..35bf97b 100644
--- a/drivers/irqchip/irq-renesas-irqc.c
+++ b/drivers/irqchip/irq-renesas-irqc.c
@@ -121,6 +121,9 @@
 static int irqc_irq_set_wake(struct irq_data *d, unsigned int on)
 {
 	struct irqc_priv *p = irq_data_get_irq_chip_data(d);
+	int hw_irq = irqd_to_hwirq(d);
+
+	irq_set_irq_wake(p->irq[hw_irq].requested_irq, on);
 
 	if (!p->clk)
 		return 0;
@@ -150,6 +153,12 @@
 	return IRQ_NONE;
 }
 
+/*
+ * This lock class tells lockdep that IRQC irqs are in a different
+ * category than their parents, so it won't report false recursion.
+ */
+static struct lock_class_key irqc_irq_lock_class;
+
 static int irqc_irq_domain_map(struct irq_domain *h, unsigned int virq,
 			       irq_hw_number_t hw)
 {
@@ -157,6 +166,7 @@
 
 	irqc_dbg(&p->irq[hw], "map");
 	irq_set_chip_data(virq, h->host_data);
+	irq_set_lockdep_class(virq, &irqc_irq_lock_class);
 	irq_set_chip_and_handler(virq, &p->irq_chip, handle_level_irq);
 	return 0;
 }
diff --git a/drivers/irqchip/irq-s3c24xx.c b/drivers/irqchip/irq-s3c24xx.c
index 506d9f2..7154b01 100644
--- a/drivers/irqchip/irq-s3c24xx.c
+++ b/drivers/irqchip/irq-s3c24xx.c
@@ -298,7 +298,7 @@
 	.irq_set_type	= s3c_irqext0_type,
 };
 
-static void s3c_irq_demux(unsigned int __irq, struct irq_desc *desc)
+static void s3c_irq_demux(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct s3c_irq_data *irq_data = irq_desc_get_chip_data(desc);
@@ -466,13 +466,11 @@
 
 	irq_set_chip_data(virq, irq_data);
 
-	set_irq_flags(virq, IRQF_VALID);
-
 	if (parent_intc && irq_data->type != S3C_IRQTYPE_NONE) {
 		if (irq_data->parent_irq > 31) {
 			pr_err("irq-s3c24xx: parent irq %lu is out of range\n",
 			       irq_data->parent_irq);
-			goto err;
+			return -EINVAL;
 		}
 
 		parent_irq_data = &parent_intc->irqs[irq_data->parent_irq];
@@ -485,18 +483,12 @@
 		if (!irqno) {
 			pr_err("irq-s3c24xx: could not find mapping for parent irq %lu\n",
 			       irq_data->parent_irq);
-			goto err;
+			return -EINVAL;
 		}
 		irq_set_chained_handler(irqno, s3c_irq_demux);
 	}
 
 	return 0;
-
-err:
-	set_irq_flags(virq, 0);
-
-	/* the only error can result from bad mapping data*/
-	return -EINVAL;
 }
 
 static const struct irq_domain_ops s3c24xx_irq_ops = {
@@ -1174,8 +1166,6 @@
 
 	irq_set_chip_data(virq, irq_data);
 
-	set_irq_flags(virq, IRQF_VALID);
-
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-sun4i.c b/drivers/irqchip/irq-sun4i.c
index 4ad3e7c..0704362 100644
--- a/drivers/irqchip/irq-sun4i.c
+++ b/drivers/irqchip/irq-sun4i.c
@@ -83,7 +83,7 @@
 			 irq_hw_number_t hw)
 {
 	irq_set_chip_and_handler(virq, &sun4i_irq_chip, handle_fasteoi_irq);
-	set_irq_flags(virq, IRQF_VALID | IRQF_PROBE);
+	irq_set_probe(virq);
 
 	return 0;
 }
diff --git a/drivers/irqchip/irq-sunxi-nmi.c b/drivers/irqchip/irq-sunxi-nmi.c
index 772a82c..c143dd5 100644
--- a/drivers/irqchip/irq-sunxi-nmi.c
+++ b/drivers/irqchip/irq-sunxi-nmi.c
@@ -58,7 +58,7 @@
 	return irq_reg_readl(gc, off);
 }
 
-static void sunxi_sc_nmi_handle_irq(unsigned int irq, struct irq_desc *desc)
+static void sunxi_sc_nmi_handle_irq(struct irq_desc *desc)
 {
 	struct irq_domain *domain = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/irqchip/irq-tb10x.c b/drivers/irqchip/irq-tb10x.c
index 3318296..848d782 100644
--- a/drivers/irqchip/irq-tb10x.c
+++ b/drivers/irqchip/irq-tb10x.c
@@ -97,7 +97,7 @@
 	return IRQ_SET_MASK_OK;
 }
 
-static void tb10x_irq_cascade(unsigned int __irq, struct irq_desc *desc)
+static void tb10x_irq_cascade(struct irq_desc *desc)
 {
 	struct irq_domain *domain = irq_desc_get_handler_data(desc);
 	unsigned int irq = irq_desc_get_irq(desc);
diff --git a/drivers/irqchip/irq-versatile-fpga.c b/drivers/irqchip/irq-versatile-fpga.c
index 16123f6..598ab3f 100644
--- a/drivers/irqchip/irq-versatile-fpga.c
+++ b/drivers/irqchip/irq-versatile-fpga.c
@@ -65,19 +65,19 @@
 	writel(mask, f->base + IRQ_ENABLE_SET);
 }
 
-static void fpga_irq_handle(unsigned int __irq, struct irq_desc *desc)
+static void fpga_irq_handle(struct irq_desc *desc)
 {
 	struct fpga_irq_data *f = irq_desc_get_handler_data(desc);
-	unsigned int irq = irq_desc_get_irq(desc);
 	u32 status = readl(f->base + IRQ_STATUS);
 
 	if (status == 0) {
-		do_bad_IRQ(irq, desc);
+		do_bad_IRQ(desc);
 		return;
 	}
 
 	do {
-		irq = ffs(status) - 1;
+		unsigned int irq = ffs(status) - 1;
+
 		status &= ~(1 << irq);
 		generic_handle_irq(irq_find_mapping(f->domain, irq));
 	} while (status);
@@ -128,7 +128,7 @@
 	irq_set_chip_data(irq, f);
 	irq_set_chip_and_handler(irq, &f->chip,
 				handle_level_irq);
-	set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	irq_set_probe(irq);
 	return 0;
 }
 
diff --git a/drivers/irqchip/irq-vic.c b/drivers/irqchip/irq-vic.c
index 03846df..b956dff 100644
--- a/drivers/irqchip/irq-vic.c
+++ b/drivers/irqchip/irq-vic.c
@@ -201,7 +201,7 @@
 		return -EPERM;
 	irq_set_chip_and_handler(irq, &vic_chip, handle_level_irq);
 	irq_set_chip_data(irq, v->base);
-	set_irq_flags(irq, IRQF_VALID | IRQF_PROBE);
+	irq_set_probe(irq);
 	return 0;
 }
 
@@ -225,7 +225,7 @@
 	return handled;
 }
 
-static void vic_handle_irq_cascaded(unsigned int irq, struct irq_desc *desc)
+static void vic_handle_irq_cascaded(struct irq_desc *desc)
 {
 	u32 stat, hwirq;
 	struct irq_chip *host_chip = irq_desc_get_chip(desc);
diff --git a/drivers/irqchip/irq-vt8500.c b/drivers/irqchip/irq-vt8500.c
index 8371d99..f9af0af 100644
--- a/drivers/irqchip/irq-vt8500.c
+++ b/drivers/irqchip/irq-vt8500.c
@@ -167,7 +167,6 @@
 							irq_hw_number_t hw)
 {
 	irq_set_chip_and_handler(virq, &vt8500_irq_chip, handle_level_irq);
-	set_irq_flags(virq, IRQF_VALID);
 
 	return 0;
 }
diff --git a/drivers/irqchip/spear-shirq.c b/drivers/irqchip/spear-shirq.c
index 4cbd9c5..1ccd2ab 100644
--- a/drivers/irqchip/spear-shirq.c
+++ b/drivers/irqchip/spear-shirq.c
@@ -182,7 +182,7 @@
 	&spear320_shirq_intrcomm_ras,
 };
 
-static void shirq_handler(unsigned __irq, struct irq_desc *desc)
+static void shirq_handler(struct irq_desc *desc)
 {
 	struct spear_shirq *shirq = irq_desc_get_handler_data(desc);
 	u32 pend;
@@ -211,7 +211,6 @@
 	for (i = 0; i < shirq->nr_irqs; i++) {
 		irq_set_chip_and_handler(shirq->virq_base + i,
 					 shirq->irq_chip, handle_simple_irq);
-		set_irq_flags(shirq->virq_base + i, IRQF_VALID);
 		irq_set_chip_data(shirq->virq_base + i, shirq);
 	}
 }
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 70f4255..42990f2 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -170,6 +170,7 @@
 
 config LEDS_IPAQ_MICRO
 	tristate "LED Support for the Compaq iPAQ h3xxx"
+	depends on LEDS_CLASS
 	depends on MFD_IPAQ_MICRO
 	help
 	  Choose this option if you want to use the notification LED on
@@ -229,7 +230,7 @@
 	tristate "Common Driver for TI/National LP5521/5523/55231/5562/8501"
 	depends on LEDS_LP5521 || LEDS_LP5523 || LEDS_LP5562 || LEDS_LP8501
 	select FW_LOADER
-	select FW_LOADER_USER_HELPER_FALLBACK
+	select FW_LOADER_USER_HELPER
 	help
 	  This option supports common operations for LP5521/5523/55231/5562/8501
 	  devices.
diff --git a/drivers/leds/leds-aat1290.c b/drivers/leds/leds-aat1290.c
index fd7c25f..ac77d36 100644
--- a/drivers/leds/leds-aat1290.c
+++ b/drivers/leds/leds-aat1290.c
@@ -331,7 +331,7 @@
 	cfg->max_brightness = b + 1;
 }
 
-int init_mm_current_scale(struct aat1290_led *led,
+static int init_mm_current_scale(struct aat1290_led *led,
 			struct aat1290_led_config_data *cfg)
 {
 	int max_mm_current_percent[] = { 20, 22, 25, 28, 32, 36, 40, 45, 50, 56,
@@ -559,6 +559,7 @@
 	{ .compatible = "skyworks,aat1290" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, aat1290_led_dt_match);
 
 static struct platform_driver aat1290_led_driver = {
 	.probe		= aat1290_led_probe,
diff --git a/drivers/leds/leds-bcm6328.c b/drivers/leds/leds-bcm6328.c
index 986fe1e..1793727 100644
--- a/drivers/leds/leds-bcm6328.c
+++ b/drivers/leds/leds-bcm6328.c
@@ -395,6 +395,7 @@
 	{ .compatible = "brcm,bcm6328-leds", },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, bcm6328_leds_of_match);
 
 static struct platform_driver bcm6328_leds_driver = {
 	.probe = bcm6328_leds_probe,
diff --git a/drivers/leds/leds-bcm6358.c b/drivers/leds/leds-bcm6358.c
index 21f9693..7ea3526 100644
--- a/drivers/leds/leds-bcm6358.c
+++ b/drivers/leds/leds-bcm6358.c
@@ -226,6 +226,7 @@
 	{ .compatible = "brcm,bcm6358-leds", },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, bcm6358_leds_of_match);
 
 static struct platform_driver bcm6358_leds_driver = {
 	.probe = bcm6358_leds_probe,
diff --git a/drivers/leds/leds-ktd2692.c b/drivers/leds/leds-ktd2692.c
index 2ae8c4d..feca07b 100644
--- a/drivers/leds/leds-ktd2692.c
+++ b/drivers/leds/leds-ktd2692.c
@@ -426,6 +426,7 @@
 	{ .compatible = "kinetic,ktd2692", },
 	{ /* sentinel */ },
 };
+MODULE_DEVICE_TABLE(of, ktd2692_match);
 
 static struct platform_driver ktd2692_driver = {
 	.driver = {
diff --git a/drivers/leds/leds-max77693.c b/drivers/leds/leds-max77693.c
index df348a0..afbb140 100644
--- a/drivers/leds/leds-max77693.c
+++ b/drivers/leds/leds-max77693.c
@@ -1080,6 +1080,7 @@
 	{ .compatible = "maxim,max77693-led" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, max77693_led_dt_match);
 
 static struct platform_driver max77693_led_driver = {
 	.probe		= max77693_led_probe,
diff --git a/drivers/leds/leds-ns2.c b/drivers/leds/leds-ns2.c
index b33514d..a95a612 100644
--- a/drivers/leds/leds-ns2.c
+++ b/drivers/leds/leds-ns2.c
@@ -337,6 +337,7 @@
 	{ .compatible = "lacie,ns2-leds", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, of_ns2_leds_match);
 #endif /* CONFIG_OF_GPIO */
 
 struct ns2_led_priv {
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index d60c88d..4b3b6f8 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -968,7 +968,8 @@
 
 /*
  * 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 @@
 	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 @@
 	.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 6578b7b..6fcbfb0 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -4249,6 +4249,10 @@
 {
 	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/mfd/asic3.c b/drivers/mfd/asic3.c
index 4b54128..a726f01 100644
--- a/drivers/mfd/asic3.c
+++ b/drivers/mfd/asic3.c
@@ -138,7 +138,7 @@
 	spin_unlock_irqrestore(&asic->lock, flags);
 }
 
-static void asic3_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void asic3_irq_demux(struct irq_desc *desc)
 {
 	struct asic3 *asic = irq_desc_get_handler_data(desc);
 	struct irq_data *data = irq_desc_get_irq_data(desc);
diff --git a/drivers/mfd/ezx-pcap.c b/drivers/mfd/ezx-pcap.c
index a76eb6e..b279205 100644
--- a/drivers/mfd/ezx-pcap.c
+++ b/drivers/mfd/ezx-pcap.c
@@ -205,7 +205,7 @@
 	} while (gpio_get_value(pdata->gpio));
 }
 
-static void pcap_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void pcap_irq_handler(struct irq_desc *desc)
 {
 	struct pcap_chip *pcap = irq_desc_get_handler_data(desc);
 
diff --git a/drivers/mfd/htc-egpio.c b/drivers/mfd/htc-egpio.c
index 9131cdc..6ccaf90 100644
--- a/drivers/mfd/htc-egpio.c
+++ b/drivers/mfd/htc-egpio.c
@@ -98,7 +98,7 @@
 	.irq_unmask	= egpio_unmask,
 };
 
-static void egpio_handler(unsigned int irq, struct irq_desc *desc)
+static void egpio_handler(struct irq_desc *desc)
 {
 	struct egpio_info *ei = irq_desc_get_handler_data(desc);
 	int irqpin;
diff --git a/drivers/mfd/jz4740-adc.c b/drivers/mfd/jz4740-adc.c
index 5bb49f0..798e443 100644
--- a/drivers/mfd/jz4740-adc.c
+++ b/drivers/mfd/jz4740-adc.c
@@ -65,7 +65,7 @@
 	spinlock_t lock;
 };
 
-static void jz4740_adc_irq_demux(unsigned int irq, struct irq_desc *desc)
+static void jz4740_adc_irq_demux(struct irq_desc *desc)
 {
 	struct irq_chip_generic *gc = irq_desc_get_handler_data(desc);
 	uint8_t status;
diff --git a/drivers/mfd/pm8921-core.c b/drivers/mfd/pm8921-core.c
index 59502d0..1b7ec08 100644
--- a/drivers/mfd/pm8921-core.c
+++ b/drivers/mfd/pm8921-core.c
@@ -156,7 +156,7 @@
 	return ret;
 }
 
-static void pm8xxx_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void pm8xxx_irq_handler(struct irq_desc *desc)
 {
 	struct pm_irq_chip *chip = irq_desc_get_handler_data(desc);
 	struct irq_chip *irq_chip = irq_desc_get_chip(desc);
diff --git a/drivers/mfd/t7l66xb.c b/drivers/mfd/t7l66xb.c
index 16fc1ad..94bd89c 100644
--- a/drivers/mfd/t7l66xb.c
+++ b/drivers/mfd/t7l66xb.c
@@ -185,7 +185,7 @@
 /*--------------------------------------------------------------------------*/
 
 /* Handle the T7L66XB interrupt mux */
-static void t7l66xb_irq(unsigned int irq, struct irq_desc *desc)
+static void t7l66xb_irq(struct irq_desc *desc)
 {
 	struct t7l66xb *t7l66xb = irq_desc_get_handler_data(desc);
 	unsigned int isr;
diff --git a/drivers/mfd/tc6393xb.c b/drivers/mfd/tc6393xb.c
index 775b9ac..8c84a51 100644
--- a/drivers/mfd/tc6393xb.c
+++ b/drivers/mfd/tc6393xb.c
@@ -522,8 +522,7 @@
 
 /*--------------------------------------------------------------------------*/
 
-static void
-tc6393xb_irq(unsigned int irq, struct irq_desc *desc)
+static void tc6393xb_irq(struct irq_desc *desc)
 {
 	struct tc6393xb *tc6393xb = irq_desc_get_handler_data(desc);
 	unsigned int isr;
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index 9a23021..f691d7e 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -282,7 +282,7 @@
  * SIBCLK to talk to the chip.  We leave the clock running until
  * we have finished processing all interrupts from the chip.
  */
-static void ucb1x00_irq(unsigned int __irq, struct irq_desc *desc)
+static void ucb1x00_irq(struct irq_desc *desc)
 {
 	struct ucb1x00 *ucb = irq_desc_get_handler_data(desc);
 	unsigned int isr, i;
diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile
index 6f484df..6982f60 100644
--- a/drivers/misc/cxl/Makefile
+++ b/drivers/misc/cxl/Makefile
@@ -1,4 +1,4 @@
-ccflags-y := -Werror
+ccflags-y := -Werror -Wno-unused-const-variable
 
 cxl-y				+= main.o file.o irq.o fault.o native.o
 cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 02c8516..a5e9771 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -1249,8 +1249,6 @@
 	int slice;
 	int rc;
 
-	pci_dev_get(dev);
-
 	if (cxl_verbose)
 		dump_cxl_config_space(dev);
 
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 25868c2..02006f71 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/drivers/misc/cxl/sysfs.c
@@ -592,6 +592,8 @@
 
 	/* 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/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index 6dd16a6..94b5208 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -48,6 +48,12 @@
 
 	phb = pci_bus_to_host(dev->bus);
 	afu = (struct cxl_afu *)phb->private_data;
+
+	if (!cxl_adapter_link_ok(afu->adapter)) {
+		dev_warn(&dev->dev, "%s: Device link is down, refusing to enable AFU\n", __func__);
+		return false;
+	}
+
 	set_dma_ops(&dev->dev, &dma_direct_ops);
 	set_dma_offset(&dev->dev, PAGE_OFFSET);
 
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index 4b469cf..8504dbe 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -204,6 +204,8 @@
 	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 @@
 		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 10f71c73..816d0e9 100644
--- a/drivers/net/arcnet/arcnet.c
+++ b/drivers/net/arcnet/arcnet.c
@@ -326,7 +326,7 @@
 	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 6f13f72..f8baa89 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -2000,6 +2000,7 @@
 		 */
 		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 cfa3704..c4bb802 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 @@
 			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;
+		}
 
-	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_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;
+		}
 	}
 
 	pdata->phy_speed = SPEED_UNKNOWN;
diff --git a/drivers/net/ethernet/arc/emac_arc.c b/drivers/net/ethernet/arc/emac_arc.c
index f9cb99b..ffd1805 100644
--- a/drivers/net/ethernet/arc/emac_arc.c
+++ b/drivers/net/ethernet/arc/emac_arc.c
@@ -78,6 +78,7 @@
 	{ .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 b9a5a97..f1b5364 100644
--- a/drivers/net/ethernet/broadcom/bcmsysport.c
+++ b/drivers/net/ethernet/broadcom/bcmsysport.c
@@ -2079,6 +2079,7 @@
 	{ .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 ba93663..b5e64b0 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h
@@ -1946,6 +1946,7 @@
 	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 e3da2bd..f1d62d5 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -3705,16 +3705,14 @@
 
 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 @@
 	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_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 c9bd7f1..ff702a7 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sp.c
@@ -4319,8 +4319,16 @@
 
 	/* 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 fadbd00..3bc701e 100644
--- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c
+++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c
@@ -3155,6 +3155,7 @@
 	{ .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 5d0753c..04b0d16 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 @@
 		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 @@
 					: 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 e0e797f..c438d03 100644
--- a/drivers/net/ethernet/brocade/bna/bna_types.h
+++ b/drivers/net/ethernet/brocade/bna/bna_types.h
@@ -587,6 +587,7 @@
 	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 506047c..21a0cfc 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.c
+++ b/drivers/net/ethernet/brocade/bna/bnad.c
@@ -399,7 +399,13 @@
 		}
 
 		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 @@
 			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 @@
 	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 @@
 
 		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 faedbf2..f4ed816 100644
--- a/drivers/net/ethernet/brocade/bna/bnad.h
+++ b/drivers/net/ethernet/brocade/bna/bnad.h
@@ -175,6 +175,7 @@
 	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 @@
 	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 2bdfc5d..0e4fdc3 100644
--- a/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
+++ b/drivers/net/ethernet/brocade/bna/bnad_ethtool.c
@@ -90,6 +90,7 @@
 	"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 @@
 	"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 @@
 							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 @@
 							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 8353a6c..03ed00c 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_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 0a27805..8215409 100644
--- a/drivers/net/ethernet/emulex/benet/be.h
+++ b/drivers/net/ethernet/emulex/benet/be.h
@@ -582,6 +582,7 @@
 	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 12687bf..7bf51a1 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -5176,6 +5176,11 @@
 	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 @@
 	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 4b69d061..710715f 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -1710,8 +1710,10 @@
 	 * 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 @@
 	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 @@
 		/* 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 @@
 
 			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 @@
 			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 8e3cd77..664d0c2 100644
--- a/drivers/net/ethernet/freescale/gianfar_ptp.c
+++ b/drivers/net/ethernet/freescale/gianfar_ptp.c
@@ -557,6 +557,7 @@
 	{ .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 4dd40e0..650f788 100644
--- a/drivers/net/ethernet/freescale/ucc_geth.c
+++ b/drivers/net/ethernet/freescale/ucc_geth.c
@@ -1384,6 +1384,8 @@
 		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 @@
 	 * 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 @@
 	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 fe2299a..514df76 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/drivers/net/ethernet/marvell/mvneta.c
@@ -1479,6 +1479,7 @@
 		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 @@
 		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 @@
 		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 @@
 		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 4402a1e..e7a5000 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -1047,13 +1047,15 @@
 
 	/* If we used up all the quota - we're probably not done yet... */
 	if (done == budget) {
-		int cpu_curr;
 		const struct cpumask *aff;
+		struct irq_data *idata;
+		int cpu_curr;
 
 		INC_PERF_COUNTER(priv->pstats.napi_quota);
 
 		cpu_curr = smp_processor_id();
-		aff = irq_desc_get_irq_data(cq->irq_desc)->affinity;
+		idata = irq_desc_get_irq_data(cq->irq_desc);
+		aff = irq_data_get_affinity_mask(idata);
 
 		if (likely(cpumask_test_cpu(cpu_curr, aff)))
 			return budget;
@@ -1268,8 +1270,6 @@
 		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 66d4ab7..60f43ec 100644
--- a/drivers/net/ethernet/micrel/ks8851.c
+++ b/drivers/net/ethernet/micrel/ks8851.c
@@ -1601,6 +1601,7 @@
 	{ .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 becbb5f..a10c928 100644
--- a/drivers/net/ethernet/moxa/moxart_ether.c
+++ b/drivers/net/ethernet/moxa/moxart_ether.c
@@ -552,6 +552,7 @@
 	{ .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 06bcc73..d6696cf 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h
@@ -536,6 +536,7 @@
 	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 8b08b20..d448145 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c
@@ -483,11 +483,17 @@
 	/* 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 @@
 	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 d79e33b..686334f 100644
--- a/drivers/net/ethernet/realtek/8139cp.c
+++ b/drivers/net/ethernet/realtek/8139cp.c
@@ -157,6 +157,7 @@
 	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 @@
 	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 @@
 		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 @@
 {
 	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 @@
 	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 @@
 		txd->addr = cpu_to_le64(mapping);
 		wmb();
 
-		flags = eor | len | DescOwn | FirstFrag | LastFrag;
+		opts1 |= eor | len | 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() */
-		}
-
-		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 @@
 			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 @@
 
 			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 @@
 			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 @@
 		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 @@
 {
 	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 @@
 			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 @@
 					 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 @@
 
 	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 @@
 {
 	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 @@
 
 	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 b735fa2..ebf6abc 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c
@@ -161,11 +161,16 @@
 
 		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 53fe200..cc106d8 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1756,7 +1756,8 @@
 #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 @@
 			   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 @@
 	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 @@
 		}
 	}
 	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 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 @@
 	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 @@
 
 	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 1a5aca5..9f9832f 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -291,13 +291,6 @@
 			    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 @@
 		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 @@
 			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 @@
 		if (ret < 0)
 			goto fail;
 	}
-
 	mutex_unlock(&netcp_modules_lock);
 	return 0;
 
@@ -796,7 +805,7 @@
 	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 @@
 	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 @@
 	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 @@
 
 	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 @@
 			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 @@
 						 naddr);
 			WARN_ON(error);
 		}
-		mutex_unlock(&netcp_modules_lock);
 		netcp_addr_del(netcp, naddr);
 	}
 }
@@ -1410,7 +1418,7 @@
 			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 @@
 			error = module->add_addr(priv->module_priv, naddr);
 			WARN_ON(error);
 		}
-		mutex_unlock(&netcp_modules_lock);
 	}
 }
 
@@ -1432,6 +1439,7 @@
 		   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 @@
 	/* 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 @@
 		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 @@
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
 
 	napi_enable(&netcp->rx_napi);
 	napi_enable(&netcp->tx_napi);
@@ -1642,7 +1649,6 @@
 		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 @@
 	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 @@
 				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 @@
 	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 @@
 	}
 
 out:
-	mutex_unlock(&netcp_modules_lock);
 	return (ret == 0) ? 0 : err;
 }
 
@@ -1754,11 +1756,12 @@
 	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 @@
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
+	spin_unlock_irqrestore(&netcp->lock, flags);
+
 	return err;
 }
 
@@ -1779,11 +1783,12 @@
 	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 @@
 			}
 		}
 	}
-	mutex_unlock(&netcp_modules_lock);
+	spin_unlock_irqrestore(&netcp->lock, flags);
 	return err;
 }
 
@@ -2040,7 +2045,6 @@
 	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 @@
 	/* 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 6f16d6a..6bff8d8 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 @@
 		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_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_sgmii_config(struct gbe_priv *priv, struct gbe_slave *slave)
 {
-	void __iomem *sgmii_port_regs;
+	if (SLAVE_LINK_IS_XGMII(slave))
+		return;
 
-	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)) {
-		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 @@
 	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 2f1264b..d3d0947 100644
--- a/drivers/net/ethernet/via/Kconfig
+++ b/drivers/net/ethernet/via/Kconfig
@@ -17,7 +17,7 @@
 
 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 6008eee..cf468c8 100644
--- a/drivers/net/ethernet/xilinx/xilinx_emaclite.c
+++ b/drivers/net/ethernet/xilinx/xilinx_emaclite.c
@@ -828,6 +828,8 @@
 		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 b5f4a78..2d3848c 100644
--- a/drivers/net/fjes/fjes_hw.c
+++ b/drivers/net/fjes/fjes_hw.c
@@ -1011,11 +1011,11 @@
 					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 da3259c..8f5c02e 100644
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -126,6 +126,8 @@
 	__be32 addr;
 	int err;
 
+	iph = ip_hdr(skb); /* outer IP header... */
+
 	if (gs->collect_md) {
 		static u8 zero_vni[3];
 
@@ -133,7 +135,6 @@
 		addr = 0;
 	} else {
 		vni = gnvh->vni;
-		iph = ip_hdr(skb); /* Still outer IP header... */
 		addr = iph->saddr;
 	}
 
@@ -178,7 +179,6 @@
 
 	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 @@
 	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 @@
 	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 @@
 		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 @@
 	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 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 @@
 
 	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_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 @@
 		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 @@
 		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 @@
 	    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 @@
 	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 58ae11a..64bb44d 100644
--- a/drivers/net/irda/ali-ircc.c
+++ b/drivers/net/irda/ali-ircc.c
@@ -1031,7 +1031,6 @@
 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 @@
 	/* 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 @@
 	/* 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 edd7734..248478c 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -1111,10 +1111,10 @@
 		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 fb1299c..e23bf5b 100644
--- a/drivers/net/phy/fixed_phy.c
+++ b/drivers/net/phy/fixed_phy.c
@@ -220,7 +220,7 @@
 	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 e6897b6..5de8d58 100644
--- a/drivers/net/phy/marvell.c
+++ b/drivers/net/phy/marvell.c
@@ -785,6 +785,7 @@
 	int adv;
 	int err;
 	int lpa;
+	int lpagb;
 	int status = 0;
 
 	/* Update the link, but return if there
@@ -802,10 +803,17 @@
 		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 @@
 			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 6a52a7f..4bde5e7 100644
--- a/drivers/net/phy/mdio-bcm-unimac.c
+++ b/drivers/net/phy/mdio-bcm-unimac.c
@@ -244,6 +244,7 @@
 	{ .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 7dc21e5..3bc9f03 100644
--- a/drivers/net/phy/mdio-gpio.c
+++ b/drivers/net/phy/mdio-gpio.c
@@ -261,6 +261,7 @@
 	{ .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 4d4d25e..280c7c3 100644
--- a/drivers/net/phy/mdio-mux.c
+++ b/drivers/net/phy/mdio-mux.c
@@ -113,18 +113,18 @@
 	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 @@
 		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 @@
 		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 02a4615..12f44c5 100644
--- a/drivers/net/phy/mdio_bus.c
+++ b/drivers/net/phy/mdio_bus.c
@@ -167,7 +167,9 @@
  * 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 @@
 #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 @@
 	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 @@
 
 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 @@
 	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 c0f2111..f761288 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -384,6 +384,24 @@
 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 @@
  *     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 @@
 			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 @@
 		phy_resume(phydev);
 
 	return err;
+
+error:
+	put_device(d);
+	module_put(bus->owner);
+	return err;
 }
 EXPORT_SYMBOL(phy_attach_direct);
 
@@ -677,14 +701,15 @@
 /**
  * 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 @@
 			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 17cad18..76cad71 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 @@
 	.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 @@
 	{ 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 0481daf..ed00446 100644
--- a/drivers/net/ppp/ppp_generic.c
+++ b/drivers/net/ppp/ppp_generic.c
@@ -2755,6 +2755,7 @@
 	 */
 	dev_net_set(dev, net);
 
+	rtnl_lock();
 	mutex_lock(&pn->all_ppp_mutex);
 
 	if (unit < 0) {
@@ -2785,7 +2786,7 @@
 	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 @@
 
 	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 1610b79..fbb9325 100644
--- a/drivers/net/usb/Kconfig
+++ b/drivers/net/usb/Kconfig
@@ -583,4 +583,15 @@
 
 	  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 cf6a0e6..b5f0406 100644
--- a/drivers/net/usb/Makefile
+++ b/drivers/net/usb/Makefile
@@ -38,4 +38,4 @@
 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 0000000..5e151e6
--- /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 e7094fb..488c6f5 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -193,7 +193,8 @@
 		.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 cf8b7f0..bbac1d3 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2392,10 +2392,6 @@
 
 	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 @@
 		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 @@
 
 		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/nvdimm/btt_devs.c b/drivers/nvdimm/btt_devs.c
index 59ad54a6..cb47751 100644
--- a/drivers/nvdimm/btt_devs.c
+++ b/drivers/nvdimm/btt_devs.c
@@ -128,13 +128,13 @@
 	struct nd_btt *nd_btt = to_nd_btt(dev);
 	ssize_t rc;
 
-	nvdimm_bus_lock(dev);
 	device_lock(dev);
+	nvdimm_bus_lock(dev);
 	rc = nd_namespace_store(dev, &nd_btt->ndns, buf, len);
 	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
 			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
-	device_unlock(dev);
 	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
 
 	return rc;
 }
diff --git a/drivers/nvdimm/pfn_devs.c b/drivers/nvdimm/pfn_devs.c
index 3fd7d0d..71805a1 100644
--- a/drivers/nvdimm/pfn_devs.c
+++ b/drivers/nvdimm/pfn_devs.c
@@ -148,13 +148,13 @@
 	struct nd_pfn *nd_pfn = to_nd_pfn(dev);
 	ssize_t rc;
 
-	nvdimm_bus_lock(dev);
 	device_lock(dev);
+	nvdimm_bus_lock(dev);
 	rc = nd_namespace_store(dev, &nd_pfn->ndns, buf, len);
 	dev_dbg(dev, "%s: result: %zd wrote: %s%s", __func__,
 			rc, buf, buf[len - 1] == '\n' ? "" : "\n");
-	device_unlock(dev);
 	nvdimm_bus_unlock(dev);
+	device_unlock(dev);
 
 	return rc;
 }
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index b952538..0ba6a97 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -92,6 +92,8 @@
 	struct pmem_device *pmem = bdev->bd_disk->private_data;
 
 	pmem_do_bvec(pmem, page, PAGE_CACHE_SIZE, 0, rw, sector);
+	if (rw & WRITE)
+		wmb_pmem();
 	page_endio(page, rw & WRITE, 0);
 
 	return 0;
diff --git a/drivers/of/of_mdio.c b/drivers/of/of_mdio.c
index 1350fa2..a87a868 100644
--- a/drivers/of/of_mdio.c
+++ b/drivers/of/of_mdio.c
@@ -197,7 +197,8 @@
  * 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 @@
  * @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 @@
 				  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 @@
  * @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 1710d9d..2306313 100644
--- a/drivers/of/of_pci_irq.c
+++ b/drivers/of/of_pci_irq.c
@@ -38,8 +38,8 @@
 	 */
 	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 @@
 			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 @@
 	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 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 baec33c..a0580af 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -560,6 +560,9 @@
 	} 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 7b9e89b..a32c1f6 100644
--- a/drivers/parisc/lba_pci.c
+++ b/drivers/parisc/lba_pci.c
@@ -693,6 +693,7 @@
 	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 769f7e3..59ac36f 100644
--- a/drivers/pci/access.c
+++ b/drivers/pci/access.c
@@ -442,7 +442,8 @@
 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_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 @@
 	.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 @@
 	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 6fbd3f2..d3346d2 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -256,6 +256,8 @@
 
 		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-keystone.c b/drivers/pci/host/pci-keystone.c
index 81253e7..0aa81bd 100644
--- a/drivers/pci/host/pci-keystone.c
+++ b/drivers/pci/host/pci-keystone.c
@@ -110,7 +110,7 @@
 	return -EINVAL;
 }
 
-static void ks_pcie_msi_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void ks_pcie_msi_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
@@ -138,8 +138,7 @@
  * Traverse through pending legacy interrupts and invoke handler for each. Also
  * takes care of interrupt controller level mask/ack operation.
  */
-static void ks_pcie_legacy_irq_handler(unsigned int __irq,
-				       struct irq_desc *desc)
+static void ks_pcie_legacy_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
diff --git a/drivers/pci/host/pci-rcar-gen2.c b/drivers/pci/host/pci-rcar-gen2.c
index 367e28f..c4f64bf 100644
--- a/drivers/pci/host/pci-rcar-gen2.c
+++ b/drivers/pci/host/pci-rcar-gen2.c
@@ -362,6 +362,7 @@
 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/host/pci-xgene-msi.c b/drivers/pci/host/pci-xgene-msi.c
index 996327c..e491681 100644
--- a/drivers/pci/host/pci-xgene-msi.c
+++ b/drivers/pci/host/pci-xgene-msi.c
@@ -295,7 +295,7 @@
 	return 0;
 }
 
-static void xgene_msi_isr(unsigned int irq, struct irq_desc *desc)
+static void xgene_msi_isr(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct xgene_msi_group *msi_groups;
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 0b2be17..8361d27 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -676,15 +676,20 @@
 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 @@
 			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 @@
 
 		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 6a30252..b03373f 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -1907,11 +1907,27 @@
 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/pinctrl/bcm/pinctrl-cygnus-gpio.c b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
index 7d9482b..1ca7830 100644
--- a/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-cygnus-gpio.c
@@ -143,7 +143,7 @@
 	return !!(readl(chip->base + offset) & BIT(shift));
 }
 
-static void cygnus_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void cygnus_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct cygnus_gpio *chip = to_cygnus_gpio(gc);
diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 69723e0..9638a00 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -349,6 +349,9 @@
 	struct pinctrl_gpio_range *range = NULL;
 	struct gpio_chip *chip = gpio_to_chip(gpio);
 
+	if (WARN(!chip, "no gpio_chip for gpio%i?", gpio))
+		return false;
+
 	mutex_lock(&pinctrldev_list_mutex);
 
 	/* Loop over the pin controllers */
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index dac4865..f79ea43 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -425,7 +425,7 @@
 	}
 }
 
-static void byt_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void byt_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct byt_gpio *vg = to_byt_gpio(irq_desc_get_handler_data(desc));
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 2d5d3dd..270c127 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1414,7 +1414,7 @@
 	.flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
-static void chv_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void chv_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct chv_pinctrl *pctrl = gpiochip_to_pinctrl(gc);
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index bb377c1..54848b8 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -836,7 +836,7 @@
 	}
 }
 
-static void intel_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void intel_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct intel_pinctrl *pctrl = gpiochip_to_pinctrl(gc);
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index 7726c6c..1b22f96 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -1190,7 +1190,7 @@
 	}
 }
 
-static void mtk_eint_irq_handler(unsigned irq, struct irq_desc *desc)
+static void mtk_eint_irq_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct mtk_pinctrl *pctl = irq_desc_get_handler_data(desc);
diff --git a/drivers/pinctrl/nomadik/pinctrl-nomadik.c b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
index 352ede1..96cf039 100644
--- a/drivers/pinctrl/nomadik/pinctrl-nomadik.c
+++ b/drivers/pinctrl/nomadik/pinctrl-nomadik.c
@@ -860,7 +860,7 @@
 	chained_irq_exit(host_chip, desc);
 }
 
-static void nmk_gpio_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void nmk_gpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *chip = irq_desc_get_handler_data(desc);
 	struct nmk_gpio_chip *nmk_chip = container_of(chip, struct nmk_gpio_chip, chip);
@@ -873,7 +873,7 @@
 	__nmk_gpio_irq_handler(desc, status);
 }
 
-static void nmk_gpio_latent_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void nmk_gpio_latent_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *chip = irq_desc_get_handler_data(desc);
 	struct nmk_gpio_chip *nmk_chip = container_of(chip, struct nmk_gpio_chip, chip);
diff --git a/drivers/pinctrl/pinctrl-adi2.c b/drivers/pinctrl/pinctrl-adi2.c
index a5976eb..f6be685 100644
--- a/drivers/pinctrl/pinctrl-adi2.c
+++ b/drivers/pinctrl/pinctrl-adi2.c
@@ -530,8 +530,7 @@
 static inline void preflow_handler(struct irq_desc *desc) { }
 #endif
 
-static void adi_gpio_handle_pint_irq(unsigned int inta_irq,
-			struct irq_desc *desc)
+static void adi_gpio_handle_pint_irq(struct irq_desc *desc)
 {
 	u32 request;
 	u32 level_mask, hwirq;
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index 5e86bb8..3318f1d 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -492,15 +492,15 @@
 	.irq_set_type = amd_gpio_irq_set_type,
 };
 
-static void amd_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void amd_gpio_irq_handler(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
 	u32 i;
 	u32 off;
 	u32 reg;
 	u32 pin_reg;
 	u64 reg64;
 	int handled = 0;
+	unsigned int irq;
 	unsigned long flags;
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
@@ -541,7 +541,7 @@
 	}
 
 	if (handled == 0)
-		handle_bad_irq(irq, desc);
+		handle_bad_irq(desc);
 
 	spin_lock_irqsave(&gpio_dev->lock, flags);
 	reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG);
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index bae0012..b0fde0f 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1585,7 +1585,7 @@
 	.irq_set_wake	= gpio_irq_set_wake,
 };
 
-static void gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void gpio_irq_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct gpio_chip *gpio_chip = irq_desc_get_handler_data(desc);
diff --git a/drivers/pinctrl/pinctrl-coh901.c b/drivers/pinctrl/pinctrl-coh901.c
index 3731cc6..9c9b889 100644
--- a/drivers/pinctrl/pinctrl-coh901.c
+++ b/drivers/pinctrl/pinctrl-coh901.c
@@ -519,7 +519,7 @@
 	.irq_set_type		= u300_gpio_irq_type,
 };
 
-static void u300_gpio_irq_handler(unsigned __irq, struct irq_desc *desc)
+static void u300_gpio_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct irq_chip *parent_chip = irq_desc_get_chip(desc);
diff --git a/drivers/pinctrl/pinctrl-digicolor.c b/drivers/pinctrl/pinctrl-digicolor.c
index 461fffc..11f8b83 100644
--- a/drivers/pinctrl/pinctrl-digicolor.c
+++ b/drivers/pinctrl/pinctrl-digicolor.c
@@ -337,9 +337,9 @@
 	pmap->dev = &pdev->dev;
 
 	pmap->pctl = pinctrl_register(pctl_desc, &pdev->dev, pmap);
-	if (!pmap->pctl) {
+	if (IS_ERR(pmap->pctl)) {
 		dev_err(&pdev->dev, "pinctrl driver registration failed\n");
-		return -EINVAL;
+		return PTR_ERR(pmap->pctl);
 	}
 
 	ret = dc_gpiochip_add(pmap, pdev->dev.of_node);
diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c
index 3dc2ae1..952b1c6 100644
--- a/drivers/pinctrl/pinctrl-pistachio.c
+++ b/drivers/pinctrl/pinctrl-pistachio.c
@@ -1303,20 +1303,18 @@
 	}
 
 	if (type & IRQ_TYPE_LEVEL_MASK)
-		__irq_set_handler_locked(data->irq, handle_level_irq);
+		irq_set_handler_locked(data, handle_level_irq);
 	else
-		__irq_set_handler_locked(data->irq, handle_edge_irq);
+		irq_set_handler_locked(data, handle_edge_irq);
 
 	return 0;
 }
 
-static void pistachio_gpio_irq_handler(unsigned int __irq,
-				       struct irq_desc *desc)
+static void pistachio_gpio_irq_handler(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct pistachio_gpio_bank *bank = gc_to_bank(gc);
-	struct irq_chip *chip = irq_get_chip(irq);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	unsigned long pending;
 	unsigned int pin;
 
diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
index c5246c0..88bb707 100644
--- a/drivers/pinctrl/pinctrl-rockchip.c
+++ b/drivers/pinctrl/pinctrl-rockchip.c
@@ -1475,7 +1475,7 @@
  * Interrupt handling
  */
 
-static void rockchip_irq_demux(unsigned int __irq, struct irq_desc *desc)
+static void rockchip_irq_demux(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct rockchip_pin_bank *bank = irq_desc_get_handler_data(desc);
diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
index bf548c2..ef04b96 100644
--- a/drivers/pinctrl/pinctrl-single.c
+++ b/drivers/pinctrl/pinctrl-single.c
@@ -1679,7 +1679,7 @@
  * Use this if you have a separate interrupt for each
  * pinctrl-single instance.
  */
-static void pcs_irq_chain_handler(unsigned int irq, struct irq_desc *desc)
+static void pcs_irq_chain_handler(struct irq_desc *desc)
 {
 	struct pcs_soc_data *pcs_soc = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip;
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index f8338d2..389526e 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1460,7 +1460,7 @@
 	}
 }
 
-static void st_gpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void st_gpio_irq_handler(struct irq_desc *desc)
 {
 	/* interrupt dedicated per bank */
 	struct irq_chip *chip = irq_desc_get_chip(desc);
@@ -1472,7 +1472,7 @@
 	chained_irq_exit(chip, desc);
 }
 
-static void st_gpio_irqmux_handler(unsigned irq, struct irq_desc *desc)
+static void st_gpio_irqmux_handler(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct st_pinctrl *info = irq_desc_get_handler_data(desc);
diff --git a/drivers/pinctrl/pinmux.c b/drivers/pinctrl/pinmux.c
index 67e08cb..29984b3 100644
--- a/drivers/pinctrl/pinmux.c
+++ b/drivers/pinctrl/pinmux.c
@@ -313,8 +313,7 @@
 
 	/* See if this pctldev has this function */
 	while (selector < nfuncs) {
-		const char *fname = ops->get_function_name(pctldev,
-							   selector);
+		const char *fname = ops->get_function_name(pctldev, selector);
 
 		if (!strcmp(function, fname))
 			return selector;
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index 492cdd5..a0c7407 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -765,9 +765,8 @@
 	.irq_set_wake   = msm_gpio_irq_set_wake,
 };
 
-static void msm_gpio_irq_handler(unsigned int __irq, struct irq_desc *desc)
+static void msm_gpio_irq_handler(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	const struct msm_pingroup *g;
 	struct msm_pinctrl *pctrl = to_msm_pinctrl(gc);
@@ -795,7 +794,7 @@
 
 	/* No interrupts were flagged */
 	if (handled == 0)
-		handle_bad_irq(irq, desc);
+		handle_bad_irq(desc);
 
 	chained_irq_exit(chip, desc);
 }
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
index c978b31..e1a3721 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
@@ -723,9 +723,9 @@
 #endif
 
 	pctrl->pctrl = pinctrl_register(&pctrl->desc, &pdev->dev, pctrl);
-	if (!pctrl->pctrl) {
+	if (IS_ERR(pctrl->pctrl)) {
 		dev_err(&pdev->dev, "couldn't register pm8xxx gpio driver\n");
-		return -ENODEV;
+		return PTR_ERR(pctrl->pctrl);
 	}
 
 	pctrl->chip = pm8xxx_gpio_template;
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
index 2d1b69f..6652b8d 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
@@ -814,9 +814,9 @@
 #endif
 
 	pctrl->pctrl = pinctrl_register(&pctrl->desc, &pdev->dev, pctrl);
-	if (!pctrl->pctrl) {
+	if (IS_ERR(pctrl->pctrl)) {
 		dev_err(&pdev->dev, "couldn't register pm8xxx mpp driver\n");
-		return -ENODEV;
+		return PTR_ERR(pctrl->pctrl);
 	}
 
 	pctrl->chip = pm8xxx_mpp_template;
diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index 5f45caa..71ccf6a 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -419,7 +419,7 @@
 };
 
 /* interrupt handler for wakeup interrupts 0..15 */
-static void exynos_irq_eint0_15(unsigned int irq, struct irq_desc *desc)
+static void exynos_irq_eint0_15(struct irq_desc *desc)
 {
 	struct exynos_weint_data *eintd = irq_desc_get_handler_data(desc);
 	struct samsung_pin_bank *bank = eintd->bank;
@@ -451,7 +451,7 @@
 }
 
 /* interrupt handler for wakeup interrupt 16 */
-static void exynos_irq_demux_eint16_31(unsigned int irq, struct irq_desc *desc)
+static void exynos_irq_demux_eint16_31(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct exynos_muxed_weint_data *eintd = irq_desc_get_handler_data(desc);
diff --git a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c
index 019844d..3d92f82 100644
--- a/drivers/pinctrl/samsung/pinctrl-s3c24xx.c
+++ b/drivers/pinctrl/samsung/pinctrl-s3c24xx.c
@@ -240,7 +240,7 @@
 	.irq_set_type	= s3c24xx_eint_type,
 };
 
-static void s3c2410_demux_eint0_3(unsigned int irq, struct irq_desc *desc)
+static void s3c2410_demux_eint0_3(struct irq_desc *desc)
 {
 	struct irq_data *data = irq_desc_get_irq_data(desc);
 	struct s3c24xx_eint_data *eint_data = irq_desc_get_handler_data(desc);
@@ -295,7 +295,7 @@
 	.irq_set_type	= s3c24xx_eint_type,
 };
 
-static void s3c2412_demux_eint0_3(unsigned int irq, struct irq_desc *desc)
+static void s3c2412_demux_eint0_3(struct irq_desc *desc)
 {
 	struct s3c24xx_eint_data *eint_data = irq_desc_get_handler_data(desc);
 	struct irq_data *data = irq_desc_get_irq_data(desc);
@@ -361,7 +361,7 @@
 				      u32 offset, u32 range)
 {
 	struct s3c24xx_eint_data *data = irq_desc_get_handler_data(desc);
-	struct irq_chip *chip = irq_desc_get_irq_chip(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct samsung_pinctrl_drv_data *d = data->drvdata;
 	unsigned int pend, mask;
 
@@ -388,12 +388,12 @@
 	chained_irq_exit(chip, desc);
 }
 
-static void s3c24xx_demux_eint4_7(unsigned int irq, struct irq_desc *desc)
+static void s3c24xx_demux_eint4_7(struct irq_desc *desc)
 {
 	s3c24xx_demux_eint(desc, 0, 0xf0);
 }
 
-static void s3c24xx_demux_eint8_23(unsigned int irq, struct irq_desc *desc)
+static void s3c24xx_demux_eint8_23(struct irq_desc *desc)
 {
 	s3c24xx_demux_eint(desc, 8, 0xffff00);
 }
diff --git a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c
index f5ea40a..43407ab 100644
--- a/drivers/pinctrl/samsung/pinctrl-s3c64xx.c
+++ b/drivers/pinctrl/samsung/pinctrl-s3c64xx.c
@@ -407,7 +407,7 @@
 	.xlate	= irq_domain_xlate_twocell,
 };
 
-static void s3c64xx_eint_gpio_irq(unsigned int irq, struct irq_desc *desc)
+static void s3c64xx_eint_gpio_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct s3c64xx_eint_gpio_data *data = irq_desc_get_handler_data(desc);
@@ -631,22 +631,22 @@
 	chained_irq_exit(chip, desc);
 }
 
-static void s3c64xx_demux_eint0_3(unsigned int irq, struct irq_desc *desc)
+static void s3c64xx_demux_eint0_3(struct irq_desc *desc)
 {
 	s3c64xx_irq_demux_eint(desc, 0xf);
 }
 
-static void s3c64xx_demux_eint4_11(unsigned int irq, struct irq_desc *desc)
+static void s3c64xx_demux_eint4_11(struct irq_desc *desc)
 {
 	s3c64xx_irq_demux_eint(desc, 0xff0);
 }
 
-static void s3c64xx_demux_eint12_19(unsigned int irq, struct irq_desc *desc)
+static void s3c64xx_demux_eint12_19(struct irq_desc *desc)
 {
 	s3c64xx_irq_demux_eint(desc, 0xff000);
 }
 
-static void s3c64xx_demux_eint20_27(unsigned int irq, struct irq_desc *desc)
+static void s3c64xx_demux_eint20_27(struct irq_desc *desc)
 {
 	s3c64xx_irq_demux_eint(desc, 0xff00000);
 }
diff --git a/drivers/pinctrl/sirf/pinctrl-atlas7.c b/drivers/pinctrl/sirf/pinctrl-atlas7.c
index 9df0c5f..0d24d9e 100644
--- a/drivers/pinctrl/sirf/pinctrl-atlas7.c
+++ b/drivers/pinctrl/sirf/pinctrl-atlas7.c
@@ -4489,7 +4489,7 @@
 	.irq_set_type = atlas7_gpio_irq_type,
 };
 
-static void atlas7_gpio_handle_irq(unsigned int __irq, struct irq_desc *desc)
+static void atlas7_gpio_handle_irq(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct atlas7_gpio_chip *a7gc = to_atlas7_gpio(gc);
@@ -4512,7 +4512,7 @@
 	if (!status) {
 		pr_warn("%s: gpio [%s] status %#x no interrupt is flaged\n",
 			__func__, gc->label, status);
-		handle_bad_irq(irq, desc);
+		handle_bad_irq(desc);
 		return;
 	}
 
diff --git a/drivers/pinctrl/sirf/pinctrl-sirf.c b/drivers/pinctrl/sirf/pinctrl-sirf.c
index f8bd9fb..2a8d697 100644
--- a/drivers/pinctrl/sirf/pinctrl-sirf.c
+++ b/drivers/pinctrl/sirf/pinctrl-sirf.c
@@ -545,7 +545,7 @@
 	.irq_set_type = sirfsoc_gpio_irq_type,
 };
 
-static void sirfsoc_gpio_handle_irq(unsigned int __irq, struct irq_desc *desc)
+static void sirfsoc_gpio_handle_irq(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
@@ -570,7 +570,7 @@
 		printk(KERN_WARNING
 			"%s: gpio id %d status %#x no interrupt is flagged\n",
 			__func__, bank->id, status);
-		handle_bad_irq(irq, desc);
+		handle_bad_irq(desc);
 		return;
 	}
 
diff --git a/drivers/pinctrl/spear/pinctrl-plgpio.c b/drivers/pinctrl/spear/pinctrl-plgpio.c
index ae8f29f..1f0af25 100644
--- a/drivers/pinctrl/spear/pinctrl-plgpio.c
+++ b/drivers/pinctrl/spear/pinctrl-plgpio.c
@@ -356,7 +356,7 @@
 	.irq_set_type	= plgpio_irq_set_type,
 };
 
-static void plgpio_irq_handler(unsigned irq, struct irq_desc *desc)
+static void plgpio_irq_handler(struct irq_desc *desc)
 {
 	struct gpio_chip *gc = irq_desc_get_handler_data(desc);
 	struct plgpio *plgpio = container_of(gc, struct plgpio, chip);
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index fb4669c0..38e0c7b 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -617,13 +617,11 @@
 	spin_lock_irqsave(&pctl->lock, flags);
 
 	if (type & IRQ_TYPE_LEVEL_MASK)
-		__irq_set_chip_handler_name_locked(d->irq,
-						   &sunxi_pinctrl_level_irq_chip,
-						   handle_fasteoi_irq, NULL);
+		irq_set_chip_handler_name_locked(d, &sunxi_pinctrl_level_irq_chip,
+						 handle_fasteoi_irq, NULL);
 	else
-		__irq_set_chip_handler_name_locked(d->irq,
-						   &sunxi_pinctrl_edge_irq_chip,
-						   handle_edge_irq, NULL);
+		irq_set_chip_handler_name_locked(d, &sunxi_pinctrl_edge_irq_chip,
+						 handle_edge_irq, NULL);
 
 	regval = readl(pctl->membase + reg);
 	regval &= ~(IRQ_CFG_IRQ_MASK << index);
@@ -742,7 +740,7 @@
 	.xlate		= sunxi_pinctrl_irq_of_xlate,
 };
 
-static void sunxi_pinctrl_irq_handler(unsigned __irq, struct irq_desc *desc)
+static void sunxi_pinctrl_irq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
index abdaed3..131fee2 100644
--- a/drivers/platform/x86/asus-nb-wmi.c
+++ b/drivers/platform/x86/asus-nb-wmi.c
@@ -128,6 +128,24 @@
 	},
 	{
 		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. X456UA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X456UA"),
+		},
+		.driver_data = &quirk_asus_wapf4,
+	},
+	{
+		.callback = dmi_matched,
+		.ident = "ASUSTeK COMPUTER INC. X456UF",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X456UF"),
+		},
+		.driver_data = &quirk_asus_wapf4,
+	},
+	{
+		.callback = dmi_matched,
 		.ident = "ASUSTeK COMPUTER INC. X501U",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
diff --git a/drivers/platform/x86/hp-wmi.c b/drivers/platform/x86/hp-wmi.c
index 0669731..fb4dd7b 100644
--- a/drivers/platform/x86/hp-wmi.c
+++ b/drivers/platform/x86/hp-wmi.c
@@ -54,8 +54,9 @@
 #define HPWMI_HARDWARE_QUERY 0x4
 #define HPWMI_WIRELESS_QUERY 0x5
 #define HPWMI_BIOS_QUERY 0x9
+#define HPWMI_FEATURE_QUERY 0xb
 #define HPWMI_HOTKEY_QUERY 0xc
-#define HPWMI_FEATURE_QUERY 0xd
+#define HPWMI_FEATURE2_QUERY 0xd
 #define HPWMI_WIRELESS2_QUERY 0x1b
 #define HPWMI_POSTCODEERROR_QUERY 0x2a
 
@@ -295,25 +296,33 @@
 	return (state & 0x4) ? 1 : 0;
 }
 
-static int __init hp_wmi_bios_2009_later(void)
+static int __init hp_wmi_bios_2008_later(void)
 {
 	int state = 0;
 	int ret = hp_wmi_perform_query(HPWMI_FEATURE_QUERY, 0, &state,
 				       sizeof(state), sizeof(state));
-	if (ret)
-		return ret;
+	if (!ret)
+		return 1;
 
-	return (state & 0x10) ? 1 : 0;
+	return (ret == HPWMI_RET_UNKNOWN_CMDTYPE) ? 0 : -ENXIO;
 }
 
-static int hp_wmi_enable_hotkeys(void)
+static int __init hp_wmi_bios_2009_later(void)
 {
-	int ret;
-	int query = 0x6e;
+	int state = 0;
+	int ret = hp_wmi_perform_query(HPWMI_FEATURE2_QUERY, 0, &state,
+				       sizeof(state), sizeof(state));
+	if (!ret)
+		return 1;
 
-	ret = hp_wmi_perform_query(HPWMI_BIOS_QUERY, 1, &query, sizeof(query),
-				   0);
+	return (ret == HPWMI_RET_UNKNOWN_CMDTYPE) ? 0 : -ENXIO;
+}
 
+static int __init hp_wmi_enable_hotkeys(void)
+{
+	int value = 0x6e;
+	int ret = hp_wmi_perform_query(HPWMI_BIOS_QUERY, 1, &value,
+				       sizeof(value), 0);
 	if (ret)
 		return -EINVAL;
 	return 0;
@@ -663,7 +672,7 @@
 			    hp_wmi_tablet_state());
 	input_sync(hp_wmi_input_dev);
 
-	if (hp_wmi_bios_2009_later() == 4)
+	if (!hp_wmi_bios_2009_later() && hp_wmi_bios_2008_later())
 		hp_wmi_enable_hotkeys();
 
 	status = wmi_install_notify_handler(HPWMI_EVENT_GUID, hp_wmi_notify, NULL);
diff --git a/drivers/platform/x86/toshiba_acpi.c b/drivers/platform/x86/toshiba_acpi.c
index 6740c51..f2372f4 100644
--- a/drivers/platform/x86/toshiba_acpi.c
+++ b/drivers/platform/x86/toshiba_acpi.c
@@ -938,7 +938,7 @@
 	else if (result == TOS_NOT_SUPPORTED)
 		return -ENODEV;
 
-	return result = TOS_SUCCESS ? 0 : -EIO;
+	return result == TOS_SUCCESS ? 0 : -EIO;
 }
 
 static int toshiba_usb_sleep_music_set(struct toshiba_acpi_dev *dev, u32 state)
@@ -2398,11 +2398,9 @@
 	if (error)
 		return error;
 
-	error = toshiba_hotkey_event_type_get(dev, &events_type);
-	if (error) {
-		pr_err("Unable to query Hotkey Event Type\n");
-		return error;
-	}
+	if (toshiba_hotkey_event_type_get(dev, &events_type))
+		pr_notice("Unable to query Hotkey Event Type\n");
+
 	dev->hotkey_event_type = events_type;
 
 	dev->hotkey_dev = input_allocate_device();
diff --git a/drivers/platform/x86/wmi.c b/drivers/platform/x86/wmi.c
index aac4757..eb391a2 100644
--- a/drivers/platform/x86/wmi.c
+++ b/drivers/platform/x86/wmi.c
@@ -194,34 +194,6 @@
 	return true;
 }
 
-/*
- * Convert a raw GUID to the ACII string representation
- */
-static int wmi_gtoa(const char *in, char *out)
-{
-	int i;
-
-	for (i = 3; i >= 0; i--)
-		out += sprintf(out, "%02X", in[i] & 0xFF);
-
-	out += sprintf(out, "-");
-	out += sprintf(out, "%02X", in[5] & 0xFF);
-	out += sprintf(out, "%02X", in[4] & 0xFF);
-	out += sprintf(out, "-");
-	out += sprintf(out, "%02X", in[7] & 0xFF);
-	out += sprintf(out, "%02X", in[6] & 0xFF);
-	out += sprintf(out, "-");
-	out += sprintf(out, "%02X", in[8] & 0xFF);
-	out += sprintf(out, "%02X", in[9] & 0xFF);
-	out += sprintf(out, "-");
-
-	for (i = 10; i <= 15; i++)
-		out += sprintf(out, "%02X", in[i] & 0xFF);
-
-	*out = '\0';
-	return 0;
-}
-
 static bool find_guid(const char *guid_string, struct wmi_block **out)
 {
 	char tmp[16], guid_input[16];
@@ -457,11 +429,7 @@
 
 static void wmi_dump_wdg(const struct guid_block *g)
 {
-	char guid_string[37];
-
-	wmi_gtoa(g->guid, guid_string);
-
-	pr_info("%s:\n", guid_string);
+	pr_info("%pUL:\n", g->guid);
 	pr_info("\tobject_id: %c%c\n", g->object_id[0], g->object_id[1]);
 	pr_info("\tnotify_id: %02X\n", g->notify_id);
 	pr_info("\treserved: %02X\n", g->reserved);
@@ -661,7 +629,6 @@
 static ssize_t modalias_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
-	char guid_string[37];
 	struct wmi_block *wblock;
 
 	wblock = dev_get_drvdata(dev);
@@ -670,9 +637,7 @@
 		return strlen(buf);
 	}
 
-	wmi_gtoa(wblock->gblock.guid, guid_string);
-
-	return sprintf(buf, "wmi:%s\n", guid_string);
+	return sprintf(buf, "wmi:%pUL\n", wblock->gblock.guid);
 }
 static DEVICE_ATTR_RO(modalias);
 
@@ -695,7 +660,7 @@
 	if (!wblock)
 		return -ENOMEM;
 
-	wmi_gtoa(wblock->gblock.guid, guid_string);
+	sprintf(guid_string, "%pUL", wblock->gblock.guid);
 
 	strcpy(&env->buf[env->buflen - 1], "wmi:");
 	memcpy(&env->buf[env->buflen - 1 + 4], guid_string, 36);
@@ -721,12 +686,9 @@
 static int wmi_create_device(const struct guid_block *gblock,
 			     struct wmi_block *wblock, acpi_handle handle)
 {
-	char guid_string[37];
-
 	wblock->dev.class = &wmi_class;
 
-	wmi_gtoa(gblock->guid, guid_string);
-	dev_set_name(&wblock->dev, "%s", guid_string);
+	dev_set_name(&wblock->dev, "%pUL", gblock->guid);
 
 	dev_set_drvdata(&wblock->dev, wblock);
 
@@ -877,7 +839,6 @@
 	struct guid_block *block;
 	struct wmi_block *wblock;
 	struct list_head *p;
-	char guid_string[37];
 
 	list_for_each(p, &wmi_block_list) {
 		wblock = list_entry(p, struct wmi_block, list);
@@ -888,8 +849,8 @@
 			if (wblock->handler)
 				wblock->handler(event, wblock->handler_data);
 			if (debug_event) {
-				wmi_gtoa(wblock->gblock.guid, guid_string);
-				pr_info("DEBUG Event GUID: %s\n", guid_string);
+				pr_info("DEBUG Event GUID: %pUL\n",
+					wblock->gblock.guid);
 			}
 
 			acpi_bus_generate_netlink_event(
diff --git a/drivers/power/twl4030_charger.c b/drivers/power/twl4030_charger.c
index f4f2c1f..74f2d3f 100644
--- a/drivers/power/twl4030_charger.c
+++ b/drivers/power/twl4030_charger.c
@@ -91,7 +91,7 @@
 #define TWL4030_MSTATEC_COMPLETE1	0x0b
 #define TWL4030_MSTATEC_COMPLETE4	0x0e
 
-#if IS_ENABLED(CONFIG_TWL4030_MADC)
+#if IS_REACHABLE(CONFIG_TWL4030_MADC)
 /*
  * If AC (Accessory Charger) voltage exceeds 4.5V (MADC 11)
  * then AC is available.
@@ -1057,13 +1057,9 @@
 
 		phynode = of_find_compatible_node(bci->dev->of_node->parent,
 						  NULL, "ti,twl4030-usb");
-		if (phynode) {
+		if (phynode)
 			bci->transceiver = devm_usb_get_phy_by_node(
 				bci->dev, phynode, &bci->usb_nb);
-			if (IS_ERR(bci->transceiver) &&
-			    PTR_ERR(bci->transceiver) == -EPROBE_DEFER)
-				return -EPROBE_DEFER;
-		}
 	}
 
 	/* Enable interrupts now. */
diff --git a/drivers/regulator/anatop-regulator.c b/drivers/regulator/anatop-regulator.c
index 738adfa..52ea605 100644
--- a/drivers/regulator/anatop-regulator.c
+++ b/drivers/regulator/anatop-regulator.c
@@ -318,6 +318,7 @@
 	{ .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 7a85ac9..7849187 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -1394,15 +1394,15 @@
 		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 @@
 		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 464018d..7bba8b7 100644
--- a/drivers/regulator/gpio-regulator.c
+++ b/drivers/regulator/gpio-regulator.c
@@ -394,6 +394,7 @@
 	{ .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 4fa7bca..f9d74d6 100644
--- a/drivers/regulator/pbias-regulator.c
+++ b/drivers/regulator/pbias-regulator.c
@@ -45,6 +45,10 @@
 	int voltage;
 };
 
+struct pbias_of_data {
+	unsigned int offset;
+};
+
 static const unsigned int pbias_volt_table[] = {
 	1800000,
 	3000000
@@ -102,8 +106,35 @@
 };
 #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 @@
 	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 @@
 	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 @@
 		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 @@
 		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 7f97223..a02c1b9 100644
--- a/drivers/regulator/tps65218-regulator.c
+++ b/drivers/regulator/tps65218-regulator.c
@@ -73,7 +73,7 @@
 };
 
 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 bed9d3e..c810cbb 100644
--- a/drivers/regulator/vexpress.c
+++ b/drivers/regulator/vexpress.c
@@ -103,6 +103,7 @@
 	{ .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/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c
index f8d8fdb..e9fae30 100644
--- a/drivers/s390/virtio/virtio_ccw.c
+++ b/drivers/s390/virtio/virtio_ccw.c
@@ -400,12 +400,16 @@
 static int virtio_ccw_read_vq_conf(struct virtio_ccw_device *vcdev,
 				   struct ccw1 *ccw, int index)
 {
+	int ret;
+
 	vcdev->config_block->index = index;
 	ccw->cmd_code = CCW_CMD_READ_VQ_CONF;
 	ccw->flags = 0;
 	ccw->count = sizeof(struct vq_config_block);
 	ccw->cda = (__u32)(unsigned long)(vcdev->config_block);
-	ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF);
+	ret = ccw_io_helper(vcdev, ccw, VIRTIO_CCW_DOING_READ_VQ_CONF);
+	if (ret)
+		return ret;
 	return vcdev->config_block->num;
 }
 
@@ -503,6 +507,10 @@
 		goto out_err;
 	}
 	info->num = virtio_ccw_read_vq_conf(vcdev, ccw, i);
+	if (info->num < 0) {
+		err = info->num;
+		goto out_err;
+	}
 	size = PAGE_ALIGN(vring_size(info->num, KVM_VIRTIO_CCW_RING_ALIGN));
 	info->queue = alloc_pages_exact(size, GFP_KERNEL | __GFP_ZERO);
 	if (info->queue == NULL) {
diff --git a/drivers/sh/intc/core.c b/drivers/sh/intc/core.c
index 043419d..8e72bcb 100644
--- a/drivers/sh/intc/core.c
+++ b/drivers/sh/intc/core.c
@@ -65,7 +65,7 @@
 	raw_spin_unlock_irqrestore(&intc_big_lock, flags);
 }
 
-static void intc_redirect_irq(unsigned int irq, struct irq_desc *desc)
+static void intc_redirect_irq(struct irq_desc *desc)
 {
 	generic_handle_irq((unsigned int)irq_desc_get_handler_data(desc));
 }
diff --git a/drivers/sh/intc/internals.h b/drivers/sh/intc/internals.h
index 7dff08e..6ce7f0d 100644
--- a/drivers/sh/intc/internals.h
+++ b/drivers/sh/intc/internals.h
@@ -99,15 +99,7 @@
  */
 static inline void activate_irq(int irq)
 {
-#ifdef CONFIG_ARM
-	/* ARM requires an extra step to clear IRQ_NOREQUEST, which it
-	 * sets on behalf of every irq_chip.  Also sets IRQ_NOPROBE.
-	 */
-	set_irq_flags(irq, IRQF_VALID);
-#else
-	/* same effect on other architectures */
-	irq_set_noprobe(irq);
-#endif
+	irq_modify_status(irq, IRQ_NOREQUEST, IRQ_NOPROBE);
 }
 
 static inline int intc_handle_int_cmp(const void *a, const void *b)
diff --git a/drivers/sh/intc/virq.c b/drivers/sh/intc/virq.c
index bafc51c..e789962 100644
--- a/drivers/sh/intc/virq.c
+++ b/drivers/sh/intc/virq.c
@@ -109,7 +109,7 @@
 	return 0;
 }
 
-static void intc_virq_handler(unsigned int __irq, struct irq_desc *desc)
+static void intc_virq_handler(struct irq_desc *desc)
 {
 	unsigned int irq = irq_desc_get_irq(desc);
 	struct irq_data *data = irq_desc_get_irq_data(desc);
@@ -127,7 +127,7 @@
 			handle = (unsigned long)irq_desc_get_handler_data(vdesc);
 			addr = INTC_REG(d, _INTC_ADDR_E(handle), 0);
 			if (intc_reg_fns[_INTC_FN(handle)](addr, handle, 0))
-				generic_handle_irq_desc(entry->irq, vdesc);
+				generic_handle_irq_desc(vdesc);
 		}
 	}
 
diff --git a/drivers/sh/pm_runtime.c b/drivers/sh/pm_runtime.c
index d3d1891..25abd4e 100644
--- a/drivers/sh/pm_runtime.c
+++ b/drivers/sh/pm_runtime.c
@@ -35,20 +35,11 @@
 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/soc/dove/pmu.c b/drivers/soc/dove/pmu.c
index 6792aae..052aecf 100644
--- a/drivers/soc/dove/pmu.c
+++ b/drivers/soc/dove/pmu.c
@@ -222,9 +222,9 @@
 }
 
 /* PMU IRQ controller */
-static void pmu_irq_handler(unsigned int irq, struct irq_desc *desc)
+static void pmu_irq_handler(struct irq_desc *desc)
 {
-	struct pmu_data *pmu = irq_get_handler_data(irq);
+	struct pmu_data *pmu = irq_desc_get_handler_data(desc);
 	struct irq_chip_generic *gc = pmu->irq_gc;
 	struct irq_domain *domain = pmu->irq_domain;
 	void __iomem *base = gc->reg_base;
@@ -232,7 +232,7 @@
 	u32 done = ~0;
 
 	if (stat == 0) {
-		handle_bad_irq(irq, desc);
+		handle_bad_irq(desc);
 		return;
 	}
 
diff --git a/drivers/spi/spi-atmel.c b/drivers/spi/spi-atmel.c
index bf9ed38..63318e2 100644
--- a/drivers/spi/spi-atmel.c
+++ b/drivers/spi/spi-atmel.c
@@ -1720,6 +1720,7 @@
 	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 @@
 
 	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 e7874a6..3e8eeb2 100644
--- a/drivers/spi/spi-bcm2835.c
+++ b/drivers/spi/spi-bcm2835.c
@@ -386,14 +386,14 @@
 	/* 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 5468fc7..2465259 100644
--- a/drivers/spi/spi-meson-spifc.c
+++ b/drivers/spi/spi-meson-spifc.c
@@ -444,6 +444,7 @@
 	{ .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 5f6315c..ecb6c58 100644
--- a/drivers/spi/spi-mt65xx.c
+++ b/drivers/spi/spi-mt65xx.c
@@ -85,7 +85,7 @@
 	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 @@
 		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 @@
 	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 @@
 	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 @@
 		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 @@
 		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 @@
 	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 fdd79197..a8ef38e 100644
--- a/drivers/spi/spi-pxa2xx.c
+++ b/drivers/spi/spi-pxa2xx.c
@@ -654,6 +654,10 @@
 	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 2e32ea2..be6155c 100644
--- a/drivers/spi/spi-xtensa-xtfpga.c
+++ b/drivers/spi/spi-xtensa-xtfpga.c
@@ -34,13 +34,13 @@
 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 3abb390..a5f53de 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -1610,8 +1610,7 @@
  *
  * 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 fba92a5..ef008e5 100644
--- a/drivers/spi/spidev.c
+++ b/drivers/spi/spidev.c
@@ -651,7 +651,8 @@
 		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/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c
index bdfb3c8..4a3cf9b 100644
--- a/drivers/spmi/spmi-pmic-arb.c
+++ b/drivers/spmi/spmi-pmic-arb.c
@@ -451,7 +451,7 @@
 	}
 }
 
-static void pmic_arb_chained_irq(unsigned int irq, struct irq_desc *desc)
+static void pmic_arb_chained_irq(struct irq_desc *desc)
 {
 	struct spmi_pmic_arb_dev *pa = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO
index 20288fc..8f3ac37 100644
--- a/drivers/staging/android/TODO
+++ b/drivers/staging/android/TODO
@@ -5,5 +5,25 @@
 	- 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 217aa53..6e8d839 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1179,13 +1179,13 @@
 		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 32f3a9d..5cafa50 100644
--- a/drivers/staging/fbtft/fb_uc1611.c
+++ b/drivers/staging/fbtft/fb_uc1611.c
@@ -76,7 +76,7 @@
 
 	/* 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 88fb2c0..8eae6ef 100644
--- a/drivers/staging/fbtft/fb_watterott.c
+++ b/drivers/staging/fbtft/fb_watterott.c
@@ -169,7 +169,7 @@
 	/* 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 @@
 	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 23392eb..7f5fa3d 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -1436,15 +1436,11 @@
 
 	/* 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 c763efc..3f380a0 100644
--- a/drivers/staging/fbtft/flexfb.c
+++ b/drivers/staging/fbtft/flexfb.c
@@ -463,15 +463,12 @@
 			}
 			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 cf0ca50..0676243 100644
--- a/drivers/staging/lustre/README.txt
+++ b/drivers/staging/lustre/README.txt
@@ -14,10 +14,8 @@
 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 @@
 
 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 d50de03..0b9b9b5 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 1d4ad1d..fc54876 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 a482c3f..ec15463 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 38abf1b..4717254 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/rdma/Kconfig b/drivers/staging/rdma/Kconfig
index cf5fe9b..d7f6235 100644
--- a/drivers/staging/rdma/Kconfig
+++ b/drivers/staging/rdma/Kconfig
@@ -24,6 +24,8 @@
 
 source "drivers/staging/rdma/amso1100/Kconfig"
 
+source "drivers/staging/rdma/ehca/Kconfig"
+
 source "drivers/staging/rdma/hfi1/Kconfig"
 
 source "drivers/staging/rdma/ipath/Kconfig"
diff --git a/drivers/staging/rdma/Makefile b/drivers/staging/rdma/Makefile
index cbd915a..139d78e 100644
--- a/drivers/staging/rdma/Makefile
+++ b/drivers/staging/rdma/Makefile
@@ -1,4 +1,5 @@
 # Entries for RDMA_STAGING tree
 obj-$(CONFIG_INFINIBAND_AMSO1100)	+= amso1100/
+obj-$(CONFIG_INFINIBAND_EHCA)	+= ehca/
 obj-$(CONFIG_INFINIBAND_HFI1)	+= hfi1/
 obj-$(CONFIG_INFINIBAND_IPATH)	+= ipath/
diff --git a/drivers/infiniband/hw/ehca/Kconfig b/drivers/staging/rdma/ehca/Kconfig
similarity index 69%
rename from drivers/infiniband/hw/ehca/Kconfig
rename to drivers/staging/rdma/ehca/Kconfig
index 59f807d..3fadd2a 100644
--- a/drivers/infiniband/hw/ehca/Kconfig
+++ b/drivers/staging/rdma/ehca/Kconfig
@@ -2,7 +2,8 @@
 	tristate "eHCA support"
 	depends on IBMEBUS
 	---help---
-	This driver supports the IBM pSeries eHCA InfiniBand adapter.
+	This driver supports the deprecated IBM pSeries eHCA InfiniBand
+	adapter.
 
 	To compile the driver as a module, choose M here. The module
 	will be called ib_ehca.
diff --git a/drivers/infiniband/hw/ehca/Makefile b/drivers/staging/rdma/ehca/Makefile
similarity index 100%
rename from drivers/infiniband/hw/ehca/Makefile
rename to drivers/staging/rdma/ehca/Makefile
diff --git a/drivers/staging/rdma/ehca/TODO b/drivers/staging/rdma/ehca/TODO
new file mode 100644
index 0000000..199a4a6
--- /dev/null
+++ b/drivers/staging/rdma/ehca/TODO
@@ -0,0 +1,4 @@
+9/2015
+
+The ehca driver has been deprecated and moved to drivers/staging/rdma.
+It will be removed in the 4.6 merge window.
diff --git a/drivers/infiniband/hw/ehca/ehca_av.c b/drivers/staging/rdma/ehca/ehca_av.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_av.c
rename to drivers/staging/rdma/ehca/ehca_av.c
diff --git a/drivers/infiniband/hw/ehca/ehca_classes.h b/drivers/staging/rdma/ehca/ehca_classes.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_classes.h
rename to drivers/staging/rdma/ehca/ehca_classes.h
diff --git a/drivers/infiniband/hw/ehca/ehca_classes_pSeries.h b/drivers/staging/rdma/ehca/ehca_classes_pSeries.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_classes_pSeries.h
rename to drivers/staging/rdma/ehca/ehca_classes_pSeries.h
diff --git a/drivers/infiniband/hw/ehca/ehca_cq.c b/drivers/staging/rdma/ehca/ehca_cq.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_cq.c
rename to drivers/staging/rdma/ehca/ehca_cq.c
diff --git a/drivers/infiniband/hw/ehca/ehca_eq.c b/drivers/staging/rdma/ehca/ehca_eq.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_eq.c
rename to drivers/staging/rdma/ehca/ehca_eq.c
diff --git a/drivers/infiniband/hw/ehca/ehca_hca.c b/drivers/staging/rdma/ehca/ehca_hca.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_hca.c
rename to drivers/staging/rdma/ehca/ehca_hca.c
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.c b/drivers/staging/rdma/ehca/ehca_irq.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_irq.c
rename to drivers/staging/rdma/ehca/ehca_irq.c
diff --git a/drivers/infiniband/hw/ehca/ehca_irq.h b/drivers/staging/rdma/ehca/ehca_irq.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_irq.h
rename to drivers/staging/rdma/ehca/ehca_irq.h
diff --git a/drivers/infiniband/hw/ehca/ehca_iverbs.h b/drivers/staging/rdma/ehca/ehca_iverbs.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_iverbs.h
rename to drivers/staging/rdma/ehca/ehca_iverbs.h
diff --git a/drivers/infiniband/hw/ehca/ehca_main.c b/drivers/staging/rdma/ehca/ehca_main.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_main.c
rename to drivers/staging/rdma/ehca/ehca_main.c
diff --git a/drivers/infiniband/hw/ehca/ehca_mcast.c b/drivers/staging/rdma/ehca/ehca_mcast.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_mcast.c
rename to drivers/staging/rdma/ehca/ehca_mcast.c
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.c b/drivers/staging/rdma/ehca/ehca_mrmw.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_mrmw.c
rename to drivers/staging/rdma/ehca/ehca_mrmw.c
diff --git a/drivers/infiniband/hw/ehca/ehca_mrmw.h b/drivers/staging/rdma/ehca/ehca_mrmw.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_mrmw.h
rename to drivers/staging/rdma/ehca/ehca_mrmw.h
diff --git a/drivers/infiniband/hw/ehca/ehca_pd.c b/drivers/staging/rdma/ehca/ehca_pd.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_pd.c
rename to drivers/staging/rdma/ehca/ehca_pd.c
diff --git a/drivers/infiniband/hw/ehca/ehca_qes.h b/drivers/staging/rdma/ehca/ehca_qes.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_qes.h
rename to drivers/staging/rdma/ehca/ehca_qes.h
diff --git a/drivers/infiniband/hw/ehca/ehca_qp.c b/drivers/staging/rdma/ehca/ehca_qp.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_qp.c
rename to drivers/staging/rdma/ehca/ehca_qp.c
diff --git a/drivers/infiniband/hw/ehca/ehca_reqs.c b/drivers/staging/rdma/ehca/ehca_reqs.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_reqs.c
rename to drivers/staging/rdma/ehca/ehca_reqs.c
diff --git a/drivers/infiniband/hw/ehca/ehca_sqp.c b/drivers/staging/rdma/ehca/ehca_sqp.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_sqp.c
rename to drivers/staging/rdma/ehca/ehca_sqp.c
diff --git a/drivers/infiniband/hw/ehca/ehca_tools.h b/drivers/staging/rdma/ehca/ehca_tools.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_tools.h
rename to drivers/staging/rdma/ehca/ehca_tools.h
diff --git a/drivers/infiniband/hw/ehca/ehca_uverbs.c b/drivers/staging/rdma/ehca/ehca_uverbs.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ehca_uverbs.c
rename to drivers/staging/rdma/ehca/ehca_uverbs.c
diff --git a/drivers/infiniband/hw/ehca/hcp_if.c b/drivers/staging/rdma/ehca/hcp_if.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/hcp_if.c
rename to drivers/staging/rdma/ehca/hcp_if.c
diff --git a/drivers/infiniband/hw/ehca/hcp_if.h b/drivers/staging/rdma/ehca/hcp_if.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/hcp_if.h
rename to drivers/staging/rdma/ehca/hcp_if.h
diff --git a/drivers/infiniband/hw/ehca/hcp_phyp.c b/drivers/staging/rdma/ehca/hcp_phyp.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/hcp_phyp.c
rename to drivers/staging/rdma/ehca/hcp_phyp.c
diff --git a/drivers/infiniband/hw/ehca/hcp_phyp.h b/drivers/staging/rdma/ehca/hcp_phyp.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/hcp_phyp.h
rename to drivers/staging/rdma/ehca/hcp_phyp.h
diff --git a/drivers/infiniband/hw/ehca/hipz_fns.h b/drivers/staging/rdma/ehca/hipz_fns.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/hipz_fns.h
rename to drivers/staging/rdma/ehca/hipz_fns.h
diff --git a/drivers/infiniband/hw/ehca/hipz_fns_core.h b/drivers/staging/rdma/ehca/hipz_fns_core.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/hipz_fns_core.h
rename to drivers/staging/rdma/ehca/hipz_fns_core.h
diff --git a/drivers/infiniband/hw/ehca/hipz_hw.h b/drivers/staging/rdma/ehca/hipz_hw.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/hipz_hw.h
rename to drivers/staging/rdma/ehca/hipz_hw.h
diff --git a/drivers/infiniband/hw/ehca/ipz_pt_fn.c b/drivers/staging/rdma/ehca/ipz_pt_fn.c
similarity index 100%
rename from drivers/infiniband/hw/ehca/ipz_pt_fn.c
rename to drivers/staging/rdma/ehca/ipz_pt_fn.c
diff --git a/drivers/infiniband/hw/ehca/ipz_pt_fn.h b/drivers/staging/rdma/ehca/ipz_pt_fn.h
similarity index 100%
rename from drivers/infiniband/hw/ehca/ipz_pt_fn.h
rename to drivers/staging/rdma/ehca/ipz_pt_fn.h
diff --git a/drivers/staging/rdma/hfi1/chip.c b/drivers/staging/rdma/hfi1/chip.c
index 654eafe..aa58e59 100644
--- a/drivers/staging/rdma/hfi1/chip.c
+++ b/drivers/staging/rdma/hfi1/chip.c
@@ -2710,7 +2710,7 @@
 	if (sleep_ok) {
 		mutex_lock(&ppd->hls_lock);
 	} else {
-		while (mutex_trylock(&ppd->hls_lock) == EBUSY)
+		while (!mutex_trylock(&ppd->hls_lock))
 			udelay(1);
 	}
 
@@ -2758,7 +2758,7 @@
 	if (sleep_ok) {
 		mutex_lock(&dd->pport->hls_lock);
 	} else {
-		while (mutex_trylock(&dd->pport->hls_lock) == EBUSY)
+		while (!mutex_trylock(&dd->pport->hls_lock))
 			udelay(1);
 	}
 
diff --git a/drivers/staging/rdma/hfi1/device.c b/drivers/staging/rdma/hfi1/device.c
index 07c87a87..bc26a53 100644
--- a/drivers/staging/rdma/hfi1/device.c
+++ b/drivers/staging/rdma/hfi1/device.c
@@ -57,11 +57,13 @@
 #include "device.h"
 
 static struct class *class;
+static struct class *user_class;
 static dev_t hfi1_dev;
 
 int hfi1_cdev_init(int minor, const char *name,
 		   const struct file_operations *fops,
-		   struct cdev *cdev, struct device **devp)
+		   struct cdev *cdev, struct device **devp,
+		   bool user_accessible)
 {
 	const dev_t dev = MKDEV(MAJOR(hfi1_dev), minor);
 	struct device *device = NULL;
@@ -78,7 +80,11 @@
 		goto done;
 	}
 
-	device = device_create(class, NULL, dev, NULL, "%s", name);
+	if (user_accessible)
+		device = device_create(user_class, NULL, dev, NULL, "%s", name);
+	else
+		device = device_create(class, NULL, dev, NULL, "%s", name);
+
 	if (!IS_ERR(device))
 		goto done;
 	ret = PTR_ERR(device);
@@ -110,6 +116,26 @@
 	return hfi1_class_name;
 }
 
+static char *hfi1_devnode(struct device *dev, umode_t *mode)
+{
+	if (mode)
+		*mode = 0600;
+	return kasprintf(GFP_KERNEL, "%s", dev_name(dev));
+}
+
+static const char *hfi1_class_name_user = "hfi1_user";
+const char *class_name_user(void)
+{
+	return hfi1_class_name_user;
+}
+
+static char *hfi1_user_devnode(struct device *dev, umode_t *mode)
+{
+	if (mode)
+		*mode = 0666;
+	return kasprintf(GFP_KERNEL, "%s", dev_name(dev));
+}
+
 int __init dev_init(void)
 {
 	int ret;
@@ -125,7 +151,22 @@
 		ret = PTR_ERR(class);
 		pr_err("Could not create device class (err %d)\n", -ret);
 		unregister_chrdev_region(hfi1_dev, HFI1_NMINORS);
+		goto done;
 	}
+	class->devnode = hfi1_devnode;
+
+	user_class = class_create(THIS_MODULE, class_name_user());
+	if (IS_ERR(user_class)) {
+		ret = PTR_ERR(user_class);
+		pr_err("Could not create device class for user accessible files (err %d)\n",
+		       -ret);
+		class_destroy(class);
+		class = NULL;
+		user_class = NULL;
+		unregister_chrdev_region(hfi1_dev, HFI1_NMINORS);
+		goto done;
+	}
+	user_class->devnode = hfi1_user_devnode;
 
 done:
 	return ret;
@@ -133,10 +174,11 @@
 
 void dev_cleanup(void)
 {
-	if (class) {
-		class_destroy(class);
-		class = NULL;
-	}
+	class_destroy(class);
+	class = NULL;
+
+	class_destroy(user_class);
+	user_class = NULL;
 
 	unregister_chrdev_region(hfi1_dev, HFI1_NMINORS);
 }
diff --git a/drivers/staging/rdma/hfi1/device.h b/drivers/staging/rdma/hfi1/device.h
index 98caecd..2850ff7 100644
--- a/drivers/staging/rdma/hfi1/device.h
+++ b/drivers/staging/rdma/hfi1/device.h
@@ -52,7 +52,8 @@
 
 int hfi1_cdev_init(int minor, const char *name,
 		   const struct file_operations *fops,
-		   struct cdev *cdev, struct device **devp);
+		   struct cdev *cdev, struct device **devp,
+		   bool user_accessible);
 void hfi1_cdev_cleanup(struct cdev *cdev, struct device **devp);
 const char *class_name(void);
 int __init dev_init(void);
diff --git a/drivers/staging/rdma/hfi1/diag.c b/drivers/staging/rdma/hfi1/diag.c
index 6777d6b..3e8d5ac 100644
--- a/drivers/staging/rdma/hfi1/diag.c
+++ b/drivers/staging/rdma/hfi1/diag.c
@@ -292,7 +292,7 @@
 	if (atomic_inc_return(&diagpkt_count) == 1) {
 		ret = hfi1_cdev_init(HFI1_DIAGPKT_MINOR, name,
 				     &diagpkt_file_ops, &diagpkt_cdev,
-				     &diagpkt_device);
+				     &diagpkt_device, false);
 	}
 
 	return ret;
@@ -592,7 +592,8 @@
 
 	ret = hfi1_cdev_init(HFI1_SNOOP_CAPTURE_BASE + dd->unit, name,
 			     &snoop_file_ops,
-			     &dd->hfi1_snoop.cdev, &dd->hfi1_snoop.class_dev);
+			     &dd->hfi1_snoop.cdev, &dd->hfi1_snoop.class_dev,
+			     false);
 
 	if (ret) {
 		dd_dev_err(dd, "Couldn't create %s device: %d", name, ret);
@@ -1012,11 +1013,10 @@
 		case HFI1_SNOOP_IOCSETLINKSTATE_EXTRA:
 			memset(&link_info, 0, sizeof(link_info));
 
-			ret = copy_from_user(&link_info,
+			if (copy_from_user(&link_info,
 				(struct hfi1_link_info __user *)arg,
-				sizeof(link_info));
-			if (ret)
-				break;
+				sizeof(link_info)))
+				ret = -EFAULT;
 
 			value = link_info.port_state;
 			index = link_info.port_number;
@@ -1080,9 +1080,10 @@
 		case HFI1_SNOOP_IOCGETLINKSTATE_EXTRA:
 			if (cmd == HFI1_SNOOP_IOCGETLINKSTATE_EXTRA) {
 				memset(&link_info, 0, sizeof(link_info));
-				ret = copy_from_user(&link_info,
+				if (copy_from_user(&link_info,
 					(struct hfi1_link_info __user *)arg,
-					sizeof(link_info));
+					sizeof(link_info)))
+					ret = -EFAULT;
 				index = link_info.port_number;
 			} else {
 				ret = __get_user(index, (int __user *) arg);
@@ -1114,9 +1115,10 @@
 							ppd->link_speed_active;
 				link_info.link_width_active =
 							ppd->link_width_active;
-				ret = copy_to_user(
+				if (copy_to_user(
 					(struct hfi1_link_info __user *)arg,
-					&link_info, sizeof(link_info));
+					&link_info, sizeof(link_info)))
+					ret = -EFAULT;
 			} else {
 				ret = __put_user(value, (int __user *)arg);
 			}
@@ -1142,10 +1144,9 @@
 			snoop_dbg("Setting filter");
 			/* just copy command structure */
 			argp = (unsigned long *)arg;
-			ret = copy_from_user(&filter_cmd, (void __user *)argp,
-					     sizeof(filter_cmd));
-			if (ret < 0) {
-				pr_alert("Error copying filter command\n");
+			if (copy_from_user(&filter_cmd, (void __user *)argp,
+					     sizeof(filter_cmd))) {
+				ret = -EFAULT;
 				break;
 			}
 			if (filter_cmd.opcode >= HFI1_MAX_FILTERS) {
@@ -1167,12 +1168,11 @@
 				break;
 			}
 			/* copy remaining data from userspace */
-			ret = copy_from_user((u8 *)filter_value,
+			if (copy_from_user((u8 *)filter_value,
 					(void __user *)filter_cmd.value_ptr,
-					filter_cmd.length);
-			if (ret < 0) {
+					filter_cmd.length)) {
 				kfree(filter_value);
-				pr_alert("Error copying filter data\n");
+				ret = -EFAULT;
 				break;
 			}
 			/* Drain packets first */
diff --git a/drivers/staging/rdma/hfi1/file_ops.c b/drivers/staging/rdma/hfi1/file_ops.c
index 4698617..72d3850 100644
--- a/drivers/staging/rdma/hfi1/file_ops.c
+++ b/drivers/staging/rdma/hfi1/file_ops.c
@@ -1181,6 +1181,7 @@
 	struct hfi1_filedata *fd = fp->private_data;
 	int ret = 0;
 
+	memset(&cinfo, 0, sizeof(cinfo));
 	ret = hfi1_get_base_kinfo(uctxt, &cinfo);
 	if (ret < 0)
 		goto done;
@@ -2089,14 +2090,16 @@
 
 	if (atomic_inc_return(&user_count) == 1) {
 		ret = hfi1_cdev_init(0, class_name(), &hfi1_file_ops,
-				     &wildcard_cdev, &wildcard_device);
+				     &wildcard_cdev, &wildcard_device,
+				     true);
 		if (ret)
 			goto done;
 	}
 
 	snprintf(name, sizeof(name), "%s_%d", class_name(), dd->unit);
 	ret = hfi1_cdev_init(dd->unit + 1, name, &hfi1_file_ops,
-			     &dd->user_cdev, &dd->user_device);
+			     &dd->user_cdev, &dd->user_device,
+			     true);
 	if (ret)
 		goto done;
 
@@ -2104,7 +2107,8 @@
 		snprintf(name, sizeof(name),
 			 "%s_ui%d", class_name(), dd->unit);
 		ret = hfi1_cdev_init(dd->unit + UI_OFFSET, name, &ui_file_ops,
-				     &dd->ui_cdev, &dd->ui_device);
+				     &dd->ui_cdev, &dd->ui_device,
+				     false);
 		if (ret)
 			goto done;
 	}
diff --git a/drivers/staging/rdma/hfi1/mad.c b/drivers/staging/rdma/hfi1/mad.c
index 37269eb..b2c1b72 100644
--- a/drivers/staging/rdma/hfi1/mad.c
+++ b/drivers/staging/rdma/hfi1/mad.c
@@ -1717,9 +1717,9 @@
 	psi->port_states.portphysstate_portstate =
 		(hfi1_ibphys_portstate(ppd) << 4) | (lstate & 0xf);
 	psi->link_width_downgrade_tx_active =
-	  ppd->link_width_downgrade_tx_active;
+		cpu_to_be16(ppd->link_width_downgrade_tx_active);
 	psi->link_width_downgrade_rx_active =
-	  ppd->link_width_downgrade_rx_active;
+		cpu_to_be16(ppd->link_width_downgrade_rx_active);
 	if (resp_len)
 		*resp_len += sizeof(struct opa_port_state_info);
 
diff --git a/drivers/staging/rdma/hfi1/sdma.c b/drivers/staging/rdma/hfi1/sdma.c
index a8c903c..aecd1a7 100644
--- a/drivers/staging/rdma/hfi1/sdma.c
+++ b/drivers/staging/rdma/hfi1/sdma.c
@@ -737,7 +737,7 @@
 	 */
 	if (!is_power_of_2(count))
 		return SDMA_DESCQ_CNT;
-	if (count < 64 && count > 32768)
+	if (count < 64 || count > 32768)
 		return SDMA_DESCQ_CNT;
 	return count;
 }
@@ -1848,7 +1848,7 @@
 			dd_dev_err(sde->dd,
 				"\taidx: %u amode: %u alen: %u\n",
 				(u8)((desc[1] & SDMA_DESC1_HEADER_INDEX_SMASK)
-					>> SDMA_DESC1_HEADER_INDEX_MASK),
+					>> SDMA_DESC1_HEADER_INDEX_SHIFT),
 				(u8)((desc[1] & SDMA_DESC1_HEADER_MODE_SMASK)
 					>> SDMA_DESC1_HEADER_MODE_SHIFT),
 				(u8)((desc[1] & SDMA_DESC1_HEADER_DWS_SMASK)
@@ -1926,7 +1926,7 @@
 		if (desc[0] & SDMA_DESC0_FIRST_DESC_FLAG)
 			seq_printf(s, "\t\tahgidx: %u ahgmode: %u\n",
 				(u8)((desc[1] & SDMA_DESC1_HEADER_INDEX_SMASK)
-					>> SDMA_DESC1_HEADER_INDEX_MASK),
+					>> SDMA_DESC1_HEADER_INDEX_SHIFT),
 				(u8)((desc[1] & SDMA_DESC1_HEADER_MODE_SMASK)
 					>> SDMA_DESC1_HEADER_MODE_SHIFT));
 		head = (head + 1) & sde->sdma_mask;
diff --git a/drivers/staging/rdma/hfi1/sdma.h b/drivers/staging/rdma/hfi1/sdma.h
index 1e613fc..4960869 100644
--- a/drivers/staging/rdma/hfi1/sdma.h
+++ b/drivers/staging/rdma/hfi1/sdma.h
@@ -109,53 +109,53 @@
 /*
  * Bits defined in the send DMA descriptor.
  */
-#define SDMA_DESC0_FIRST_DESC_FLAG      (1ULL<<63)
-#define SDMA_DESC0_LAST_DESC_FLAG       (1ULL<<62)
+#define SDMA_DESC0_FIRST_DESC_FLAG      (1ULL << 63)
+#define SDMA_DESC0_LAST_DESC_FLAG       (1ULL << 62)
 #define SDMA_DESC0_BYTE_COUNT_SHIFT     48
 #define SDMA_DESC0_BYTE_COUNT_WIDTH     14
 #define SDMA_DESC0_BYTE_COUNT_MASK \
-	((1ULL<<SDMA_DESC0_BYTE_COUNT_WIDTH)-1ULL)
+	((1ULL << SDMA_DESC0_BYTE_COUNT_WIDTH) - 1)
 #define SDMA_DESC0_BYTE_COUNT_SMASK \
-	(SDMA_DESC0_BYTE_COUNT_MASK<<SDMA_DESC0_BYTE_COUNT_SHIFT)
+	(SDMA_DESC0_BYTE_COUNT_MASK << SDMA_DESC0_BYTE_COUNT_SHIFT)
 #define SDMA_DESC0_PHY_ADDR_SHIFT       0
 #define SDMA_DESC0_PHY_ADDR_WIDTH       48
 #define SDMA_DESC0_PHY_ADDR_MASK \
-	((1ULL<<SDMA_DESC0_PHY_ADDR_WIDTH)-1ULL)
+	((1ULL << SDMA_DESC0_PHY_ADDR_WIDTH) - 1)
 #define SDMA_DESC0_PHY_ADDR_SMASK \
-	(SDMA_DESC0_PHY_ADDR_MASK<<SDMA_DESC0_PHY_ADDR_SHIFT)
+	(SDMA_DESC0_PHY_ADDR_MASK << SDMA_DESC0_PHY_ADDR_SHIFT)
 
 #define SDMA_DESC1_HEADER_UPDATE1_SHIFT 32
 #define SDMA_DESC1_HEADER_UPDATE1_WIDTH 32
 #define SDMA_DESC1_HEADER_UPDATE1_MASK \
-	((1ULL<<SDMA_DESC1_HEADER_UPDATE1_WIDTH)-1ULL)
+	((1ULL << SDMA_DESC1_HEADER_UPDATE1_WIDTH) - 1)
 #define SDMA_DESC1_HEADER_UPDATE1_SMASK \
-	(SDMA_DESC1_HEADER_UPDATE1_MASK<<SDMA_DESC1_HEADER_UPDATE1_SHIFT)
+	(SDMA_DESC1_HEADER_UPDATE1_MASK << SDMA_DESC1_HEADER_UPDATE1_SHIFT)
 #define SDMA_DESC1_HEADER_MODE_SHIFT    13
 #define SDMA_DESC1_HEADER_MODE_WIDTH    3
 #define SDMA_DESC1_HEADER_MODE_MASK \
-	((1ULL<<SDMA_DESC1_HEADER_MODE_WIDTH)-1ULL)
+	((1ULL << SDMA_DESC1_HEADER_MODE_WIDTH) - 1)
 #define SDMA_DESC1_HEADER_MODE_SMASK \
-	(SDMA_DESC1_HEADER_MODE_MASK<<SDMA_DESC1_HEADER_MODE_SHIFT)
+	(SDMA_DESC1_HEADER_MODE_MASK << SDMA_DESC1_HEADER_MODE_SHIFT)
 #define SDMA_DESC1_HEADER_INDEX_SHIFT   8
 #define SDMA_DESC1_HEADER_INDEX_WIDTH   5
 #define SDMA_DESC1_HEADER_INDEX_MASK \
-	((1ULL<<SDMA_DESC1_HEADER_INDEX_WIDTH)-1ULL)
+	((1ULL << SDMA_DESC1_HEADER_INDEX_WIDTH) - 1)
 #define SDMA_DESC1_HEADER_INDEX_SMASK \
-	(SDMA_DESC1_HEADER_INDEX_MASK<<SDMA_DESC1_HEADER_INDEX_SHIFT)
+	(SDMA_DESC1_HEADER_INDEX_MASK << SDMA_DESC1_HEADER_INDEX_SHIFT)
 #define SDMA_DESC1_HEADER_DWS_SHIFT     4
 #define SDMA_DESC1_HEADER_DWS_WIDTH     4
 #define SDMA_DESC1_HEADER_DWS_MASK \
-	((1ULL<<SDMA_DESC1_HEADER_DWS_WIDTH)-1ULL)
+	((1ULL << SDMA_DESC1_HEADER_DWS_WIDTH) - 1)
 #define SDMA_DESC1_HEADER_DWS_SMASK \
-	(SDMA_DESC1_HEADER_DWS_MASK<<SDMA_DESC1_HEADER_DWS_SHIFT)
+	(SDMA_DESC1_HEADER_DWS_MASK << SDMA_DESC1_HEADER_DWS_SHIFT)
 #define SDMA_DESC1_GENERATION_SHIFT     2
 #define SDMA_DESC1_GENERATION_WIDTH     2
 #define SDMA_DESC1_GENERATION_MASK \
-	((1ULL<<SDMA_DESC1_GENERATION_WIDTH)-1ULL)
+	((1ULL << SDMA_DESC1_GENERATION_WIDTH) - 1)
 #define SDMA_DESC1_GENERATION_SMASK \
-	(SDMA_DESC1_GENERATION_MASK<<SDMA_DESC1_GENERATION_SHIFT)
-#define SDMA_DESC1_INT_REQ_FLAG         (1ULL<<1)
-#define SDMA_DESC1_HEAD_TO_HOST_FLAG    (1ULL<<0)
+	(SDMA_DESC1_GENERATION_MASK << SDMA_DESC1_GENERATION_SHIFT)
+#define SDMA_DESC1_INT_REQ_FLAG         (1ULL << 1)
+#define SDMA_DESC1_HEAD_TO_HOST_FLAG    (1ULL << 0)
 
 enum sdma_states {
 	sdma_state_s00_hw_down,
diff --git a/drivers/staging/rdma/hfi1/verbs.c b/drivers/staging/rdma/hfi1/verbs.c
index 53ac214..41bb59e 100644
--- a/drivers/staging/rdma/hfi1/verbs.c
+++ b/drivers/staging/rdma/hfi1/verbs.c
@@ -749,11 +749,13 @@
 	struct verbs_txreq *tx;
 
 	tx = kmem_cache_alloc(dev->verbs_txreq_cache, GFP_ATOMIC);
-	if (!tx)
+	if (!tx) {
 		/* call slow path to get the lock */
 		tx =  __get_txreq(dev, qp);
-	if (tx)
-		tx->qp = qp;
+		if (IS_ERR(tx))
+			return tx;
+	}
+	tx->qp = qp;
 	return tx;
 }
 
diff --git a/drivers/staging/unisys/visorbus/Makefile b/drivers/staging/unisys/visorbus/Makefile
index fa27ee5..fc790e7 100644
--- a/drivers/staging/unisys/visorbus/Makefile
+++ b/drivers/staging/unisys/visorbus/Makefile
@@ -10,4 +10,3 @@
 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 2309f5f..a272b48 100644
--- a/drivers/staging/unisys/visorbus/visorbus_main.c
+++ b/drivers/staging/unisys/visorbus/visorbus_main.c
@@ -37,6 +37,8 @@
 #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 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 @@
 	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 @@
 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 8c9da7e..9d3c1e2 100644
--- a/drivers/staging/unisys/visornic/visornic_main.c
+++ b/drivers/staging/unisys/visornic/visornic_main.c
@@ -1189,16 +1189,16 @@
 	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 @@
 			"%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 @@
 	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/thermal/Kconfig b/drivers/thermal/Kconfig
index 0390044..5aabc4b 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -163,7 +163,7 @@
 
 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 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 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 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 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 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 @@
 	  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 @@
 
 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 620dcd4..42c6f71 100644
--- a/drivers/thermal/cpu_cooling.c
+++ b/drivers/thermal/cpu_cooling.c
@@ -262,7 +262,9 @@
  * 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 @@
 	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 @@
 		}
 
 		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 @@
 		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 @@
 		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 @@
 	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 @@
 
 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 @@
 
 	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 607b62c..e58bd0b 100644
--- a/drivers/thermal/db8500_cpufreq_cooling.c
+++ b/drivers/thermal/db8500_cpufreq_cooling.c
@@ -72,6 +72,7 @@
 	{ .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 9c8a7aa..7ff9627 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 @@
 
 /**
  * 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 @@
 };
 
 /**
+ * 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 @@
 {
 	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 @@
 	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 @@
 		}
 	}
 
+	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 @@
 	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 @@
  * 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;
+		}
+
+		params->allocated_tzp = true;
 	}
 
-	ret = tz->ops->get_trip_temp(tz, params->trip_switch_on,
-				     &switch_on_temp);
-	if (ret)
-		goto free;
+	if (!tz->tzp->sustainable_power)
+		dev_warn(&tz->device, "power_allocator: sustainable_power will be estimated\n");
 
-	ret = tz->ops->get_trip_temp(tz, params->trip_max_desired_temperature,
-				     &control_temp);
-	if (ret)
-		goto free;
+	get_governor_trips(tz, params);
 
-	temperature_threshold = control_temp - switch_on_temp;
-
-	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 @@
 
 	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 @@
 
 	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 5e5fc70..d9e525c 100644
--- a/drivers/thermal/thermal_core.c
+++ b/drivers/thermal/thermal_core.c
@@ -1013,6 +1013,34 @@
 }
 
 /**
+ * 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 bd4c7be..cb6686f 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 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 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 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 c68fe12..20a41f7 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -643,7 +643,7 @@
 	{
 		.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 54e6c8d..b1e0ba3 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2910,3 +2910,5 @@
 }
 
 #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 867e9f3..dcc50c87 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -61,7 +61,7 @@
 	{ .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 9eae1a1..4456d2c 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 @@
 	.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 @@
 	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 a637da2..8223fe7 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -656,6 +656,44 @@
 	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 @@
 				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 @@
 
 	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 @@
 					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_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 b2a540b..b9ddf0c 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -112,7 +112,7 @@
 				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 @@
 	}
 
 	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 a5a1b7c..22e9606 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -514,8 +514,6 @@
 		goto err1;
 	}
 
-	dwc3_omap_enable_irqs(omap);
-
 	ret = dwc3_omap_extcon_register(omap);
 	if (ret < 0)
 		goto err2;
@@ -526,6 +524,8 @@
 		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 0c25704..1e8bdf8 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2665,8 +2665,6 @@
 	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 @@
 			ret = status;
 	}
 
-	spin_unlock(&dwc->lock);
-
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/epautoconf.c b/drivers/usb/gadget/epautoconf.c
index 978435a..6399c10 100644
--- a/drivers/usb/gadget/epautoconf.c
+++ b/drivers/usb/gadget/epautoconf.c
@@ -186,6 +186,7 @@
 
 	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 fdacddb..175ca93 100644
--- a/drivers/usb/gadget/udc/amd5536udc.c
+++ b/drivers/usb/gadget/udc/amd5536udc.c
@@ -3138,8 +3138,8 @@
 	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 @@
 
 	/* 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 @@
 
 	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 @@
 
 	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 @@
 		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 3dfada8..f0f2b06 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -2002,6 +2002,17 @@
 		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 5c8f4ef..ccb9c21 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_core.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_core.c
@@ -324,8 +324,7 @@
 				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 1379ad4..27af0f0 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1348,6 +1348,7 @@
 {
 	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 @@
 			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 @@
 				req->req.status = len;
 			} else {
 				limit -= len;
+				sent += len;
 				urb->actual_length += len;
 				req->req.actual += len;
 			}
@@ -1421,7 +1426,7 @@
 					*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 @@
 					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 @@
 		if (rescan)
 			goto top;
 	}
-	return limit;
+	return sent;
 }
 
 static int periodic_bytes(struct dummy *dum, struct dummy_ep *ep)
@@ -1890,7 +1904,7 @@
 		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 8aa2593..b9429bc 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -2117,8 +2117,7 @@
 		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 4c48969..dafe74e 100644
--- a/drivers/usb/gadget/udc/mv_u3d_core.c
+++ b/drivers/usb/gadget/udc/mv_u3d_core.c
@@ -1767,8 +1767,7 @@
 	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 339af51..81b6229 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -2100,8 +2100,7 @@
 	}
 
 	/* 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 9a8c936..41f841f 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1498,10 +1498,10 @@
 	 * 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 @@
 	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 @@
 
 	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 @@
 			"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 5590eac..c79d336 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -180,51 +180,6 @@
 				"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 @@
 }
 
 #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 a47a1e8..43291f9 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -302,6 +302,15 @@
 	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 @@
 	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 6b0f4a4..9957bd9 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -146,7 +146,8 @@
 				"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 @@
 }
 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 @@
 	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 @@
 	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 @@
 
 	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 514a6cd..4a518ff 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1051,6 +1051,7 @@
 	 * (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 @@
 	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 @@
 	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 d07cafb..e499b86 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -551,6 +551,9 @@
 	} 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 a0cfead..84512d1 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -225,8 +225,11 @@
 
 	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 39168fe..b2685e7 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -379,6 +379,8 @@
         {}
 };
 
+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 7d3beee..1731324 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -155,7 +155,7 @@
 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 ec6ecd0..5320cb8 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -232,7 +232,8 @@
 		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 8a55b37..db68156 100644
--- a/drivers/usb/phy/phy-isp1301.c
+++ b/drivers/usb/phy/phy-isp1301.c
@@ -31,6 +31,7 @@
 	{ "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 6d1941a..6956c4f 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -278,6 +278,10 @@
 #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 @@
 	.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 @@
 	 .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 6c3734d..d3ea90b 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -80,6 +80,8 @@
 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 @@
 	.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 @@
 /*****************************************************************************
  * 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/drivers/vhost/net.c b/drivers/vhost/net.c
index 7d137a4..9eda69e 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -61,8 +61,7 @@
 enum {
 	VHOST_NET_FEATURES = VHOST_FEATURES |
 			 (1ULL << VHOST_NET_F_VIRTIO_NET_HDR) |
-			 (1ULL << VIRTIO_NET_F_MRG_RXBUF) |
-			 (1ULL << VIRTIO_F_VERSION_1),
+			 (1ULL << VIRTIO_NET_F_MRG_RXBUF)
 };
 
 enum {
diff --git a/drivers/vhost/scsi.c b/drivers/vhost/scsi.c
index f114a9d..e25a236 100644
--- a/drivers/vhost/scsi.c
+++ b/drivers/vhost/scsi.c
@@ -166,9 +166,7 @@
 /* Note: can't set VIRTIO_F_VERSION_1 yet, since that implies ANY_LAYOUT. */
 enum {
 	VHOST_SCSI_FEATURES = VHOST_FEATURES | (1ULL << VIRTIO_SCSI_F_HOTPLUG) |
-					       (1ULL << VIRTIO_SCSI_F_T10_PI) |
-					       (1ULL << VIRTIO_F_ANY_LAYOUT) |
-					       (1ULL << VIRTIO_F_VERSION_1)
+					       (1ULL << VIRTIO_SCSI_F_T10_PI)
 };
 
 #define VHOST_SCSI_MAX_TARGET	256
diff --git a/drivers/vhost/test.c b/drivers/vhost/test.c
index d9c501e..f2882ac 100644
--- a/drivers/vhost/test.c
+++ b/drivers/vhost/test.c
@@ -277,10 +277,13 @@
 			return -EFAULT;
 		return 0;
 	case VHOST_SET_FEATURES:
+		printk(KERN_ERR "1\n");
 		if (copy_from_user(&features, featurep, sizeof features))
 			return -EFAULT;
+		printk(KERN_ERR "2\n");
 		if (features & ~VHOST_FEATURES)
 			return -EOPNOTSUPP;
+		printk(KERN_ERR "3\n");
 		return vhost_test_set_features(n, features);
 	case VHOST_RESET_OWNER:
 		return vhost_test_reset_owner(n);
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
index ce6f6da..4772862 100644
--- a/drivers/vhost/vhost.h
+++ b/drivers/vhost/vhost.h
@@ -173,7 +173,9 @@
 	VHOST_FEATURES = (1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
 			 (1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
 			 (1ULL << VIRTIO_RING_F_EVENT_IDX) |
-			 (1ULL << VHOST_F_LOG_ALL),
+			 (1ULL << VHOST_F_LOG_ALL) |
+			 (1ULL << VIRTIO_F_ANY_LAYOUT) |
+			 (1ULL << VIRTIO_F_VERSION_1)
 };
 
 static inline bool vhost_has_feature(struct vhost_virtqueue *vq, int bit)
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 22ea424..073bb57 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1242,6 +1242,13 @@
 				goto out_clear;
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
+			/*
+			 * If the partition is not aligned on a page
+			 * boundary, we can't do dax I/O to it.
+			 */
+			if ((bdev->bd_part->start_sect % (PAGE_SIZE / 512)) ||
+			    (bdev->bd_part->nr_sects % (PAGE_SIZE / 512)))
+				bdev->bd_inode->i_flags &= ~S_DAX;
 		}
 	} else {
 		if (bdev->bd_contains == bdev) {
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 81220b2..0ef5cc1 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 0d98aee..295795a 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -3765,9 +3765,7 @@
 		 * 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 5411f0a..9f96042 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -3742,10 +3742,7 @@
 	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 @@
 	}
 
 	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 f1018cf..e2357e3 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2798,7 +2798,8 @@
 			      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 @@
 			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 @@
 			 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 @@
 	}
 	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 @@
 		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 @@
 					 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 @@
 	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 @@
 
 	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 @@
 	}
 
 	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 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 @@
 						 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 @@
 		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 a0fa725..611b66d 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -5084,7 +5084,8 @@
 		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 @@
 	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 @@
 	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 @@
 		 * 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 @@
 		 * 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_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 @@
 {
 	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 @@
 		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 @@
 		 * 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 @@
 	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 2b07b35..11d1eab 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -1658,9 +1658,7 @@
 		 * 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 8f259b3..74bc333 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -117,6 +117,18 @@
 			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 @@
 	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 @@
 }
 
 
+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 edc2fbc..87964bf 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -65,6 +65,7 @@
 	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 @@
 	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_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/cifsfs.c b/fs/cifs/cifsfs.c
index 6a1119e..e739950 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -325,8 +325,11 @@
 static void
 cifs_show_security(struct seq_file *s, struct cifs_ses *ses)
 {
-	if (ses->sectype == Unspecified)
+	if (ses->sectype == Unspecified) {
+		if (ses->user_name == NULL)
+			seq_puts(s, ",sec=none");
 		return;
+	}
 
 	seq_puts(s, ",sec=");
 
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index c63f522..28a77bf 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -67,6 +67,12 @@
 		goto out_drop_write;
 	}
 
+	if (src_file.file->f_op->unlocked_ioctl != cifs_ioctl) {
+		rc = -EBADF;
+		cifs_dbg(VFS, "src file seems to be from a different filesystem type\n");
+		goto out_fput;
+	}
+
 	if ((!src_file.file->private_data) || (!dst_file->private_data)) {
 		rc = -EBADF;
 		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
diff --git a/fs/dax.c b/fs/dax.c
index 93bf2f9..7ae6df7 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -119,7 +119,8 @@
 		size_t len;
 		if (pos == max) {
 			unsigned blkbits = inode->i_blkbits;
-			sector_t block = pos >> blkbits;
+			long page = pos >> PAGE_SHIFT;
+			sector_t block = page << (PAGE_SHIFT - blkbits);
 			unsigned first = pos - (block << blkbits);
 			long size;
 
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index 587ac08..091a364 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -1481,6 +1481,21 @@
 		wbc_detach_inode(&wbc);
 		work->nr_pages -= write_chunk - wbc.nr_to_write;
 		wrote += write_chunk - wbc.nr_to_write;
+
+		if (need_resched()) {
+			/*
+			 * We're trying to balance between building up a nice
+			 * long list of IOs to improve our merge rate, and
+			 * getting those IOs out quickly for anyone throttling
+			 * in balance_dirty_pages().  cond_resched() doesn't
+			 * unplug, so get our IOs out the door before we
+			 * give up the CPU.
+			 */
+			blk_flush_plug(current);
+			cond_resched();
+		}
+
+
 		spin_lock(&wb->list_lock);
 		spin_lock(&inode->i_lock);
 		if (!(inode->i_state & I_DIRTY_ALL))
@@ -1488,7 +1503,7 @@
 		requeue_inode(inode, wb, &wbc);
 		inode_sync_complete(inode);
 		spin_unlock(&inode->i_lock);
-		cond_resched_lock(&wb->list_lock);
+
 		/*
 		 * bail out to wb_writeback() often enough to check
 		 * background threshold and other termination conditions.
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 2714ef8..be806ea 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -113,7 +113,8 @@
 	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 @@
 		/* 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 @@
 	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 a448291..333063e 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -54,7 +54,7 @@
 
 /* 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 38678d9..4b1d08f 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -166,8 +166,11 @@
 	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 b34f2e2..02ec079 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -629,23 +629,18 @@
 	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 @@
 		/* 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 @@
 	__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 d731bbf..0f020e4 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -175,10 +175,12 @@
 {
 	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 693b903..f93b9cd 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1127,6 +1127,21 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 		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 @@
 
 	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 @@
 			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 da73bc4..5db3246 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -1481,7 +1481,7 @@
 					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 7c5718b..fe3ddd2 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -508,7 +508,7 @@
 	 * 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 ba12464..8abe271 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -1104,20 +1104,15 @@
 			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 @@
 	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 78c9351..d1990e9 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -270,6 +270,7 @@
 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 @@
 {
 }
 
+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 ae0ff7a..01b8cc8 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -72,6 +72,9 @@
 {
 	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 388f480..72624dc 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1351,6 +1351,9 @@
 {
 	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 46b8b2b..ee5aa4d 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -1439,6 +1439,7 @@
 	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 @@
 			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 @@
 
 
 	/* 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 ce12e0b..3d90ad7 100644
--- a/fs/ocfs2/dlm/dlmrecovery.c
+++ b/fs/ocfs2/dlm/dlmrecovery.c
@@ -1694,6 +1694,7 @@
 	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 @@
 				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 @@
 	}
 	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 634e676..5031170 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -467,8 +467,8 @@
 	 * 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 @@
 	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);
 }
 
@@ -1287,8 +1287,10 @@
 
 	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
 				  O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
-	if (IS_ERR(file))
+	if (IS_ERR(file)) {
+		mmput(ctx->mm);
 		kmem_cache_free(userfaultfd_ctx_cachep, ctx);
+	}
 out:
 	return file;
 }
diff --git a/include/acpi/button.h b/include/acpi/button.h
index 97eea0e..1cad8b2 100644
--- a/include/acpi/button.h
+++ b/include/acpi/button.h
@@ -3,7 +3,7 @@
 
 #include <linux/notifier.h>
 
-#if defined(CONFIG_ACPI_BUTTON) || defined(CONFIG_ACPI_BUTTON_MODULE)
+#if IS_ENABLED(CONFIG_ACPI_BUTTON)
 extern int acpi_lid_notifier_register(struct notifier_block *nb);
 extern int acpi_lid_notifier_unregister(struct notifier_block *nb);
 extern int acpi_lid_open(void);
@@ -20,6 +20,6 @@
 {
 	return 1;
 }
-#endif /* defined(CONFIG_ACPI_BUTTON) || defined(CONFIG_ACPI_BUTTON_MODULE) */
+#endif /* IS_ENABLED(CONFIG_ACPI_BUTTON) */
 
 #endif /* ACPI_BUTTON_H */
diff --git a/include/acpi/video.h b/include/acpi/video.h
index e840b29..c62392d 100644
--- a/include/acpi/video.h
+++ b/include/acpi/video.h
@@ -24,7 +24,7 @@
 	acpi_backlight_native,
 };
 
-#if (defined CONFIG_ACPI_VIDEO || defined CONFIG_ACPI_VIDEO_MODULE)
+#if IS_ENABLED(CONFIG_ACPI_VIDEO)
 extern int acpi_video_register(void);
 extern void acpi_video_unregister(void);
 extern int acpi_video_get_edid(struct acpi_device *device, int type,
diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h
index f20f407..4b4b056 100644
--- a/include/asm-generic/memory_model.h
+++ b/include/asm-generic/memory_model.h
@@ -73,7 +73,7 @@
  * Convert a physical address to a Page Frame Number and back
  */
 #define	__phys_to_pfn(paddr)	((unsigned long)((paddr) >> PAGE_SHIFT))
-#define	__pfn_to_phys(pfn)	((pfn) << PAGE_SHIFT)
+#define	__pfn_to_phys(pfn)	PFN_PHYS(pfn)
 
 #define page_to_pfn __page_to_pfn
 #define pfn_to_page __pfn_to_page
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 83bfb87..e2aadbc 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -111,8 +111,8 @@
 		cpu_relax();
 }
 
-#ifndef virt_queued_spin_lock
-static __always_inline bool virt_queued_spin_lock(struct qspinlock *lock)
+#ifndef virt_spin_lock
+static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {
 	return false;
 }
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index d901f1a..4e14dac 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -35,11 +35,7 @@
 #define VGIC_V3_MAX_LRS		16
 #define VGIC_MAX_IRQS		1024
 #define VGIC_V2_MAX_CPUS	8
-
-/* Sanity checks... */
-#if (KVM_MAX_VCPUS > 255)
-#error Too many KVM VCPUs, the VGIC only supports up to 255 VCPUs for now
-#endif
+#define VGIC_V3_MAX_CPUS	255
 
 #if (VGIC_NR_IRQS_LEGACY & 31)
 #error "VGIC_NR_IRQS must be a multiple of 32"
diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
index 5a5d79e..d5eb4ad1 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 @@
  * @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/blkdev.h b/include/linux/blkdev.h
index 38a5ff7..99da9eb 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1368,6 +1368,26 @@
 		((bprv->bv_offset + bprv->bv_len) & queue_virt_boundary(q));
 }
 
+static inline bool bio_will_gap(struct request_queue *q, struct bio *prev,
+			 struct bio *next)
+{
+	if (!bio_has_data(prev))
+		return false;
+
+	return bvec_gap_to_prev(q, &prev->bi_io_vec[prev->bi_vcnt - 1],
+				next->bi_io_vec[0].bv_offset);
+}
+
+static inline bool req_gap_back_merge(struct request *req, struct bio *bio)
+{
+	return bio_will_gap(req->q, req->biotail, bio);
+}
+
+static inline bool req_gap_front_merge(struct request *req, struct bio *bio)
+{
+	return bio_will_gap(req->q, bio, req->bio);
+}
+
 struct work_struct;
 int kblockd_schedule_work(struct work_struct *work);
 int kblockd_schedule_delayed_work(struct delayed_work *dwork, unsigned long delay);
@@ -1494,6 +1514,26 @@
 	return q->limits.max_integrity_segments;
 }
 
+static inline bool integrity_req_gap_back_merge(struct request *req,
+						struct bio *next)
+{
+	struct bio_integrity_payload *bip = bio_integrity(req->bio);
+	struct bio_integrity_payload *bip_next = bio_integrity(next);
+
+	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
+				bip_next->bip_vec[0].bv_offset);
+}
+
+static inline bool integrity_req_gap_front_merge(struct request *req,
+						 struct bio *bio)
+{
+	struct bio_integrity_payload *bip = bio_integrity(bio);
+	struct bio_integrity_payload *bip_next = bio_integrity(req->bio);
+
+	return bvec_gap_to_prev(req->q, &bip->bip_vec[bip->bip_vcnt - 1],
+				bip_next->bip_vec[0].bv_offset);
+}
+
 #else /* CONFIG_BLK_DEV_INTEGRITY */
 
 struct bio;
@@ -1560,6 +1600,16 @@
 {
 	return 0;
 }
+static inline bool integrity_req_gap_back_merge(struct request *req,
+						struct bio *next)
+{
+	return false;
+}
+static inline bool integrity_req_gap_front_merge(struct request *req,
+						 struct bio *bio)
+{
+	return false;
+}
 
 #endif /* CONFIG_BLK_DEV_INTEGRITY */
 
diff --git a/include/linux/ceph/ceph_features.h b/include/linux/ceph/ceph_features.h
index 4763ad6..f89b31d 100644
--- a/include/linux/ceph/ceph_features.h
+++ b/include/linux/ceph/ceph_features.h
@@ -107,6 +107,7 @@
 	 CEPH_FEATURE_OSDMAP_ENC |		\
 	 CEPH_FEATURE_CRUSH_TUNABLES3 |		\
 	 CEPH_FEATURE_OSD_PRIMARY_AFFINITY |	\
+	 CEPH_FEATURE_MSGR_KEEPALIVE2 |		\
 	 CEPH_FEATURE_CRUSH_V4)
 
 #define CEPH_FEATURES_REQUIRED_DEFAULT   \
diff --git a/include/linux/ceph/messenger.h b/include/linux/ceph/messenger.h
index 7e1252e..b2371d9 100644
--- a/include/linux/ceph/messenger.h
+++ b/include/linux/ceph/messenger.h
@@ -238,6 +238,8 @@
 	bool out_kvec_is_msg; /* kvec refers to out_msg */
 	int out_more;        /* there is more data after the kvecs */
 	__le64 out_temp_ack; /* for writing an ack */
+	struct ceph_timespec out_temp_keepalive2; /* for writing keepalive2
+						     stamp */
 
 	/* message in temps */
 	struct ceph_msg_header in_hdr;
@@ -248,7 +250,7 @@
 	int in_base_pos;     /* bytes read */
 	__le64 in_temp_ack;  /* for reading an ack */
 
-	struct timespec last_keepalive_ack;
+	struct timespec last_keepalive_ack; /* keepalive2 ack stamp */
 
 	struct delayed_work work;	    /* send|recv work */
 	unsigned long       delay;          /* current delay interval */
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 4d8fcf2..8492721 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -473,31 +473,8 @@
 	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/clockchips.h b/include/linux/clockchips.h
index 31ce435..bdcf358 100644
--- a/include/linux/clockchips.h
+++ b/include/linux/clockchips.h
@@ -18,15 +18,6 @@
 struct clock_event_device;
 struct module;
 
-/* Clock event mode commands for legacy ->set_mode(): OBSOLETE */
-enum clock_event_mode {
-	CLOCK_EVT_MODE_UNUSED,
-	CLOCK_EVT_MODE_SHUTDOWN,
-	CLOCK_EVT_MODE_PERIODIC,
-	CLOCK_EVT_MODE_ONESHOT,
-	CLOCK_EVT_MODE_RESUME,
-};
-
 /*
  * Possible states of a clock event device.
  *
@@ -86,16 +77,14 @@
  * @min_delta_ns:	minimum delta value in ns
  * @mult:		nanosecond to cycles multiplier
  * @shift:		nanoseconds to cycles divisor (power of two)
- * @mode:		operating mode, relevant only to ->set_mode(), OBSOLETE
  * @state_use_accessors:current state of the device, assigned by the core code
  * @features:		features
  * @retries:		number of forced programming retries
- * @set_mode:		legacy set mode function, only for modes <= CLOCK_EVT_MODE_RESUME.
- * @set_state_periodic:	switch state to periodic, if !set_mode
- * @set_state_oneshot:	switch state to oneshot, if !set_mode
- * @set_state_oneshot_stopped: switch state to oneshot_stopped, if !set_mode
- * @set_state_shutdown:	switch state to shutdown, if !set_mode
- * @tick_resume:	resume clkevt device, if !set_mode
+ * @set_state_periodic:	switch state to periodic
+ * @set_state_oneshot:	switch state to oneshot
+ * @set_state_oneshot_stopped: switch state to oneshot_stopped
+ * @set_state_shutdown:	switch state to shutdown
+ * @tick_resume:	resume clkevt device
  * @broadcast:		function to broadcast events
  * @min_delta_ticks:	minimum delta value in ticks stored for reconfiguration
  * @max_delta_ticks:	maximum delta value in ticks stored for reconfiguration
@@ -116,18 +105,10 @@
 	u64			min_delta_ns;
 	u32			mult;
 	u32			shift;
-	enum clock_event_mode	mode;
 	enum clock_event_state	state_use_accessors;
 	unsigned int		features;
 	unsigned long		retries;
 
-	/*
-	 * State transition callback(s): Only one of the two groups should be
-	 * defined:
-	 * - set_mode(), only for modes <= CLOCK_EVT_MODE_RESUME.
-	 * - set_state_{shutdown|periodic|oneshot|oneshot_stopped}(), tick_resume().
-	 */
-	void			(*set_mode)(enum clock_event_mode mode, struct clock_event_device *);
 	int			(*set_state_periodic)(struct clock_event_device *);
 	int			(*set_state_oneshot)(struct clock_event_device *);
 	int			(*set_state_oneshot_stopped)(struct clock_event_device *);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 430efcb..dca22de 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -127,9 +127,14 @@
 #define CPUFREQ_SHARED_TYPE_ANY	 (3) /* Freq can be set from any dependent CPU*/
 
 #ifdef CONFIG_CPU_FREQ
+struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu);
 struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu);
 void cpufreq_cpu_put(struct cpufreq_policy *policy);
 #else
+static inline struct cpufreq_policy *cpufreq_cpu_get_raw(unsigned int cpu)
+{
+	return NULL;
+}
 static inline struct cpufreq_policy *cpufreq_cpu_get(unsigned int cpu)
 {
 	return NULL;
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index ce447f0..68030e2 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -65,7 +65,10 @@
  *			The "flags" parameter's possible values are
  *			explained above with "DEVFREQ_FLAG_*" macros.
  * @get_dev_status:	The device should provide the current performance
- *			status to devfreq, which is used by governors.
+ *			status to devfreq. Governors are recommended not to
+ *			use this directly. Instead, governors are recommended
+ *			to use devfreq_update_stats() along with
+ *			devfreq.last_status.
  * @get_cur_freq:	The device should provide the current frequency
  *			at which it is operating.
  * @exit:		An optional callback that is called when devfreq
@@ -161,6 +164,7 @@
 	struct delayed_work work;
 
 	unsigned long previous_freq;
+	struct devfreq_dev_status last_status;
 
 	void *data; /* private data for governors */
 
@@ -204,6 +208,19 @@
 extern void devm_devfreq_unregister_opp_notifier(struct device *dev,
 						struct devfreq *devfreq);
 
+/**
+ * devfreq_update_stats() - update the last_status pointer in struct devfreq
+ * @df:		the devfreq instance whose status needs updating
+ *
+ *  Governors are recommended to use this function along with last_status,
+ * which allows other entities to reuse the last_status without affecting
+ * the values fetched later by governors.
+ */
+static inline int devfreq_update_stats(struct devfreq *df)
+{
+	return df->profile->get_dev_status(df->dev.parent, &df->last_status);
+}
+
 #if IS_ENABLED(CONFIG_DEVFREQ_GOV_SIMPLE_ONDEMAND)
 /**
  * struct devfreq_simple_ondemand_data - void *data fed to struct devfreq
@@ -289,6 +306,11 @@
 							struct devfreq *devfreq)
 {
 }
+
+static inline int devfreq_update_stats(struct devfreq *df)
+{
+	return -EINVAL;
+}
 #endif /* CONFIG_PM_DEVFREQ */
 
 #endif /* __LINUX_DEVFREQ_H__ */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index d0b380e..e38681f 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 @@
 	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/irq.h b/include/linux/irq.h
index 6f8b340..11bf092 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -110,8 +110,8 @@
 /*
  * Return value for chip->irq_set_affinity()
  *
- * IRQ_SET_MASK_OK	- OK, core updates irq_data.affinity
- * IRQ_SET_MASK_NOCPY	- OK, chip did update irq_data.affinity
+ * IRQ_SET_MASK_OK	- OK, core updates irq_common_data.affinity
+ * IRQ_SET_MASK_NOCPY	- OK, chip did update irq_common_data.affinity
  * IRQ_SET_MASK_OK_DONE	- Same as IRQ_SET_MASK_OK for core. Special code to
  *			  support stacked irqchips, which indicates skipping
  *			  all descendent irqchips.
@@ -129,9 +129,19 @@
  * struct irq_common_data - per irq data shared by all irqchips
  * @state_use_accessors: status information for irq chip functions.
  *			Use accessor functions to deal with it
+ * @node:		node index useful for balancing
+ * @handler_data:	per-IRQ data for the irq_chip methods
+ * @affinity:		IRQ affinity on SMP
+ * @msi_desc:		MSI descriptor
  */
 struct irq_common_data {
 	unsigned int		state_use_accessors;
+#ifdef CONFIG_NUMA
+	unsigned int		node;
+#endif
+	void			*handler_data;
+	struct msi_desc		*msi_desc;
+	cpumask_var_t		affinity;
 };
 
 /**
@@ -139,38 +149,26 @@
  * @mask:		precomputed bitmask for accessing the chip registers
  * @irq:		interrupt number
  * @hwirq:		hardware interrupt number, local to the interrupt domain
- * @node:		node index useful for balancing
  * @common:		point to data shared by all irqchips
  * @chip:		low level interrupt hardware access
  * @domain:		Interrupt translation domain; responsible for mapping
  *			between hwirq number and linux irq number.
  * @parent_data:	pointer to parent struct irq_data to support hierarchy
  *			irq_domain
- * @handler_data:	per-IRQ data for the irq_chip methods
  * @chip_data:		platform-specific per-chip private data for the chip
  *			methods, to allow shared chip implementations
- * @msi_desc:		MSI descriptor
- * @affinity:		IRQ affinity on SMP
- *
- * The fields here need to overlay the ones in irq_desc until we
- * cleaned up the direct references and switched everything over to
- * irq_data.
  */
 struct irq_data {
 	u32			mask;
 	unsigned int		irq;
 	unsigned long		hwirq;
-	unsigned int		node;
 	struct irq_common_data	*common;
 	struct irq_chip		*chip;
 	struct irq_domain	*domain;
 #ifdef	CONFIG_IRQ_DOMAIN_HIERARCHY
 	struct irq_data		*parent_data;
 #endif
-	void			*handler_data;
 	void			*chip_data;
-	struct msi_desc		*msi_desc;
-	cpumask_var_t		affinity;
 };
 
 /*
@@ -190,6 +188,7 @@
  * IRQD_IRQ_MASKED		- Masked state of the interrupt
  * IRQD_IRQ_INPROGRESS		- In progress state of the interrupt
  * IRQD_WAKEUP_ARMED		- Wakeup mode armed
+ * IRQD_FORWARDED_TO_VCPU	- The interrupt is forwarded to a VCPU
  */
 enum {
 	IRQD_TRIGGER_MASK		= 0xf,
@@ -204,6 +203,7 @@
 	IRQD_IRQ_MASKED			= (1 << 17),
 	IRQD_IRQ_INPROGRESS		= (1 << 18),
 	IRQD_WAKEUP_ARMED		= (1 << 19),
+	IRQD_FORWARDED_TO_VCPU		= (1 << 20),
 };
 
 #define __irqd_to_state(d)		((d)->common->state_use_accessors)
@@ -282,6 +282,20 @@
 	return __irqd_to_state(d) & IRQD_WAKEUP_ARMED;
 }
 
+static inline bool irqd_is_forwarded_to_vcpu(struct irq_data *d)
+{
+	return __irqd_to_state(d) & IRQD_FORWARDED_TO_VCPU;
+}
+
+static inline void irqd_set_forwarded_to_vcpu(struct irq_data *d)
+{
+	__irqd_to_state(d) |= IRQD_FORWARDED_TO_VCPU;
+}
+
+static inline void irqd_clr_forwarded_to_vcpu(struct irq_data *d)
+{
+	__irqd_to_state(d) &= ~IRQD_FORWARDED_TO_VCPU;
+}
 
 /*
  * Functions for chained handlers which can be enabled/disabled by the
@@ -461,14 +475,14 @@
  * Built-in IRQ handlers for various IRQ types,
  * callable via desc->handle_irq()
  */
-extern void handle_level_irq(unsigned int irq, struct irq_desc *desc);
-extern void handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc);
-extern void handle_edge_irq(unsigned int irq, struct irq_desc *desc);
-extern void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc);
-extern void handle_simple_irq(unsigned int irq, struct irq_desc *desc);
-extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc);
-extern void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc);
-extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
+extern void handle_level_irq(struct irq_desc *desc);
+extern void handle_fasteoi_irq(struct irq_desc *desc);
+extern void handle_edge_irq(struct irq_desc *desc);
+extern void handle_edge_eoi_irq(struct irq_desc *desc);
+extern void handle_simple_irq(struct irq_desc *desc);
+extern void handle_percpu_irq(struct irq_desc *desc);
+extern void handle_percpu_devid_irq(struct irq_desc *desc);
+extern void handle_bad_irq(struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
 extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg);
@@ -627,23 +641,23 @@
 static inline void *irq_get_handler_data(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
-	return d ? d->handler_data : NULL;
+	return d ? d->common->handler_data : NULL;
 }
 
 static inline void *irq_data_get_irq_handler_data(struct irq_data *d)
 {
-	return d->handler_data;
+	return d->common->handler_data;
 }
 
 static inline struct msi_desc *irq_get_msi_desc(unsigned int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
-	return d ? d->msi_desc : NULL;
+	return d ? d->common->msi_desc : NULL;
 }
 
 static inline struct msi_desc *irq_data_get_msi_desc(struct irq_data *d)
 {
-	return d->msi_desc;
+	return d->common->msi_desc;
 }
 
 static inline u32 irq_get_trigger_type(unsigned int irq)
@@ -652,21 +666,30 @@
 	return d ? irqd_get_trigger_type(d) : 0;
 }
 
+static inline int irq_common_data_get_node(struct irq_common_data *d)
+{
+#ifdef CONFIG_NUMA
+	return d->node;
+#else
+	return 0;
+#endif
+}
+
 static inline int irq_data_get_node(struct irq_data *d)
 {
-	return d->node;
+	return irq_common_data_get_node(d->common);
 }
 
 static inline struct cpumask *irq_get_affinity_mask(int irq)
 {
 	struct irq_data *d = irq_get_irq_data(irq);
 
-	return d ? d->affinity : NULL;
+	return d ? d->common->affinity : NULL;
 }
 
 static inline struct cpumask *irq_data_get_affinity_mask(struct irq_data *d)
 {
-	return d->affinity;
+	return d->common->affinity;
 }
 
 unsigned int arch_dynirq_lower_bound(unsigned int from);
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 5acfa26..a587a33 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -98,11 +98,7 @@
 
 static inline struct irq_desc *irq_data_to_desc(struct irq_data *data)
 {
-#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
-	return irq_to_desc(data->irq);
-#else
-	return container_of(data, struct irq_desc, irq_data);
-#endif
+	return container_of(data->common, struct irq_desc, irq_common_data);
 }
 
 static inline unsigned int irq_desc_get_irq(struct irq_desc *desc)
@@ -127,23 +123,21 @@
 
 static inline void *irq_desc_get_handler_data(struct irq_desc *desc)
 {
-	return desc->irq_data.handler_data;
+	return desc->irq_common_data.handler_data;
 }
 
 static inline struct msi_desc *irq_desc_get_msi_desc(struct irq_desc *desc)
 {
-	return desc->irq_data.msi_desc;
+	return desc->irq_common_data.msi_desc;
 }
 
 /*
  * Architectures call this to let the generic IRQ layer
- * handle an interrupt. If the descriptor is attached to an
- * irqchip-style controller then we call the ->handle_irq() handler,
- * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
+ * handle an interrupt.
  */
-static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
+static inline void generic_handle_irq_desc(struct irq_desc *desc)
 {
-	desc->handle_irq(irq, desc);
+	desc->handle_irq(desc);
 }
 
 int generic_handle_irq(unsigned int irq);
@@ -176,29 +170,6 @@
 	return irq_desc_has_action(irq_to_desc(irq));
 }
 
-/* caller has locked the irq_desc and both params are valid */
-static inline void __irq_set_handler_locked(unsigned int irq,
-					    irq_flow_handler_t handler)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	desc->handle_irq = handler;
-}
-
-/* caller has locked the irq_desc and both params are valid */
-static inline void
-__irq_set_chip_handler_name_locked(unsigned int irq, struct irq_chip *chip,
-				   irq_flow_handler_t handler, const char *name)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	irq_desc_get_irq_data(desc)->chip = chip;
-	desc->handle_irq = handler;
-	desc->name = name;
-}
-
 /**
  * irq_set_handler_locked - Set irq handler from a locked region
  * @data:	Pointer to the irq_data structure which identifies the irq
diff --git a/include/linux/irqhandler.h b/include/linux/irqhandler.h
index 62d5430..661bed0 100644
--- a/include/linux/irqhandler.h
+++ b/include/linux/irqhandler.h
@@ -8,7 +8,7 @@
 
 struct irq_desc;
 struct irq_data;
-typedef	void (*irq_flow_handler_t)(unsigned int irq, struct irq_desc *desc);
+typedef	void (*irq_flow_handler_t)(struct irq_desc *desc);
 typedef	void (*irq_preflow_handler_t)(struct irq_data *data);
 
 #endif
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 7f653e8..f109423 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -21,8 +21,8 @@
  *
  * DEFINE_STATIC_KEY_TRUE(key);
  * DEFINE_STATIC_KEY_FALSE(key);
- * static_key_likely()
- * statick_key_unlikely()
+ * static_branch_likely()
+ * static_branch_unlikely()
  *
  * Jump labels provide an interface to generate dynamic branches using
  * self-modifying code. Assuming toolchain and architecture support, if we
@@ -45,12 +45,10 @@
  * statement, setting the key to true requires us to patch in a jump
  * to the out-of-line of true branch.
  *
- * In addtion to static_branch_{enable,disable}, we can also reference count
+ * In addition to static_branch_{enable,disable}, we can also reference count
  * the key or branch direction via static_branch_{inc,dec}. Thus,
  * static_branch_inc() can be thought of as a 'make more true' and
- * static_branch_dec() as a 'make more false'. The inc()/dec()
- * interface is meant to be used exclusively from the inc()/dec() for a given
- * key.
+ * static_branch_dec() as a 'make more false'.
  *
  * Since this relies on modifying code, the branch modifying functions
  * must be considered absolute slow paths (machine wide synchronization etc.).
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 88a0069..2d15e38 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -507,6 +507,7 @@
 	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 962387a..4a4e3a0 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 @@
  * 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 @@
 	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_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 a4ab9da..b7b9501 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -762,6 +762,18 @@
 	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 79d85dd..2f4c1f7 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -946,7 +946,7 @@
 				      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 2738d35..2b0a30a 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -179,6 +179,9 @@
 	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 @@
 		 * 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 @@
 {
 	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 269e8af..6b00f18 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -34,7 +34,7 @@
 
 /**
  * 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 7591788..357e44c 100644
--- a/include/linux/sunrpc/xprtsock.h
+++ b/include/linux/sunrpc/xprtsock.h
@@ -42,6 +42,7 @@
 	/*
 	 * Connection of transports
 	 */
+	unsigned long		sock_state;
 	struct delayed_work	connect_worker;
 	struct sockaddr_storage	srcaddr;
 	unsigned short		srcport;
@@ -76,6 +77,8 @@
  */
 #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 17292fe..157d366 100644
--- a/include/linux/thermal.h
+++ b/include/linux/thermal.h
@@ -360,7 +360,7 @@
 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 @@
 
 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 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/tick.h b/include/linux/tick.h
index 48d901f..e312219 100644
--- a/include/linux/tick.h
+++ b/include/linux/tick.h
@@ -147,11 +147,20 @@
 		cpumask_or(mask, mask, tick_nohz_full_mask);
 }
 
+static inline int housekeeping_any_cpu(void)
+{
+	return cpumask_any_and(housekeeping_mask, cpu_online_mask);
+}
+
 extern void tick_nohz_full_kick(void);
 extern void tick_nohz_full_kick_cpu(int cpu);
 extern void tick_nohz_full_kick_all(void);
 extern void __tick_nohz_task_switch(void);
 #else
+static inline int housekeeping_any_cpu(void)
+{
+	return smp_processor_id();
+}
 static inline bool tick_nohz_full_enabled(void) { return false; }
 static inline bool tick_nohz_full_cpu(int cpu) { return false; }
 static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { }
diff --git a/include/linux/wait.h b/include/linux/wait.h
index d3d0772..1e1bf9f 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -147,8 +147,7 @@
 
 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 @@
 #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 acd6a09..9b85db8 100644
--- a/include/net/flow.h
+++ b/include/net/flow.h
@@ -35,6 +35,7 @@
 #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 879d6e5..186f3a1 100644
--- a/include/net/inet_timewait_sock.h
+++ b/include/net/inet_timewait_sock.h
@@ -110,7 +110,19 @@
 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 063d304..aaf9700 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -275,7 +275,8 @@
 	     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 b8529aa..fa915fa 100644
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -32,6 +32,12 @@
 	__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 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 @@
 	__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 @@
 	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 a37d043..727d6e9 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -236,8 +236,11 @@
 	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 @@
 			     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 @@
 
 	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);
 
-		tb = rcu_dereference_rtnl(net->ipv4.fib_default);
-		if (tb && !fib_table_lookup(tb, flp, res, flags))
-			break;
-	}
+	if (!err)
+		goto out;
+
+	tb = rcu_dereference_rtnl(net->ipv4.fib_default);
+	if (tb)
+		err = fib_table_lookup(tb, flp, res, flags);
+
+out:
+	if (err == -EAGAIN)
+		err = -ENETUNREACH;
 
 	rcu_read_unlock();
 
diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 9a6a3ba..f6dafec 100644
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -276,6 +276,8 @@
 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 cc61cb9..f46af25 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -255,7 +255,7 @@
 		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/rdma/opa_port_info.h b/include/rdma/opa_port_info.h
index 391dae1..a0fa975 100644
--- a/include/rdma/opa_port_info.h
+++ b/include/rdma/opa_port_info.h
@@ -294,8 +294,8 @@
 
 struct opa_port_state_info {
 	struct opa_port_states port_states;
-	u16 link_width_downgrade_tx_active;
-	u16 link_width_downgrade_rx_active;
+	__be16 link_width_downgrade_tx_active;
+	__be16 link_width_downgrade_rx_active;
 };
 
 struct opa_port_info {
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 8da542a..ee12400 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -709,17 +709,19 @@
 __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 34141a5..f8b0188 100644
--- a/include/uapi/linux/lwtunnel.h
+++ b/include/uapi/linux/lwtunnel.h
@@ -21,8 +21,6 @@
 	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 @@
 	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 2cf0f79..2c9eae6 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(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 @@
 	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 @@
 	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 @@
  * @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 @@
  * @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 @@
  * @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 @@
 	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 @@
 	 */
 	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 @@
 
 	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 @@
 				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 @@
 
 out_finish:
 	cgroup_migrate_finish(&preloaded_csets);
-	percpu_up_write(&cgroup_threadgroup_rwsem);
 	return ret;
 }
 
@@ -5024,7 +5083,6 @@
 	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 7d5f0f1..2845623 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1149,6 +1149,10 @@
 	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/irq/chip.c b/kernel/irq/chip.c
index 6e40a95..e28169d 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -83,7 +83,7 @@
 
 	if (!desc)
 		return -EINVAL;
-	desc->irq_data.handler_data = data;
+	desc->irq_common_data.handler_data = data;
 	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
@@ -105,7 +105,7 @@
 
 	if (!desc)
 		return -EINVAL;
-	desc->irq_data.msi_desc = entry;
+	desc->irq_common_data.msi_desc = entry;
 	if (entry && !irq_offset)
 		entry->irq = irq_base;
 	irq_put_desc_unlock(desc, flags);
@@ -372,7 +372,6 @@
 
 /**
  *	handle_simple_irq - Simple and software-decoded IRQs.
- *	@irq:	the interrupt number
  *	@desc:	the interrupt description structure for this irq
  *
  *	Simple interrupts are either sent from a demultiplexing interrupt
@@ -382,8 +381,7 @@
  *	Note: The caller is expected to handle the ack, clear, mask and
  *	unmask issues if necessary.
  */
-void
-handle_simple_irq(unsigned int irq, struct irq_desc *desc)
+void handle_simple_irq(struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
@@ -425,7 +423,6 @@
 
 /**
  *	handle_level_irq - Level type irq handler
- *	@irq:	the interrupt number
  *	@desc:	the interrupt description structure for this irq
  *
  *	Level type interrupts are active as long as the hardware line has
@@ -433,8 +430,7 @@
  *	it after the associated handler has acknowledged the device, so the
  *	interrupt line is back to inactive.
  */
-void
-handle_level_irq(unsigned int irq, struct irq_desc *desc)
+void handle_level_irq(struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 	mask_ack_irq(desc);
@@ -496,7 +492,6 @@
 
 /**
  *	handle_fasteoi_irq - irq handler for transparent controllers
- *	@irq:	the interrupt number
  *	@desc:	the interrupt description structure for this irq
  *
  *	Only a single callback will be issued to the chip: an ->eoi()
@@ -504,8 +499,7 @@
  *	for modern forms of interrupt handlers, which handle the flow
  *	details in hardware, transparently.
  */
-void
-handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
+void handle_fasteoi_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = desc->irq_data.chip;
 
@@ -546,7 +540,6 @@
 
 /**
  *	handle_edge_irq - edge type IRQ handler
- *	@irq:	the interrupt number
  *	@desc:	the interrupt description structure for this irq
  *
  *	Interrupt occures on the falling and/or rising edge of a hardware
@@ -560,8 +553,7 @@
  *	the handler was running. If all pending interrupts are handled, the
  *	loop is left.
  */
-void
-handle_edge_irq(unsigned int irq, struct irq_desc *desc)
+void handle_edge_irq(struct irq_desc *desc)
 {
 	raw_spin_lock(&desc->lock);
 
@@ -618,13 +610,12 @@
 #ifdef CONFIG_IRQ_EDGE_EOI_HANDLER
 /**
  *	handle_edge_eoi_irq - edge eoi type IRQ handler
- *	@irq:	the interrupt number
  *	@desc:	the interrupt description structure for this irq
  *
  * Similar as the above handle_edge_irq, but using eoi and w/o the
  * mask/unmask logic.
  */
-void handle_edge_eoi_irq(unsigned int irq, struct irq_desc *desc)
+void handle_edge_eoi_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
@@ -665,13 +656,11 @@
 
 /**
  *	handle_percpu_irq - Per CPU local irq handler
- *	@irq:	the interrupt number
  *	@desc:	the interrupt description structure for this irq
  *
  *	Per CPU interrupts on SMP machines without locking requirements
  */
-void
-handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
+void handle_percpu_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 
@@ -688,7 +677,6 @@
 
 /**
  * handle_percpu_devid_irq - Per CPU local irq handler with per cpu dev ids
- * @irq:	the interrupt number
  * @desc:	the interrupt description structure for this irq
  *
  * Per CPU interrupts on SMP machines without locking requirements. Same as
@@ -698,11 +686,12 @@
  * contain the real device id for the cpu on which this handler is
  * called
  */
-void handle_percpu_devid_irq(unsigned int irq, struct irq_desc *desc)
+void handle_percpu_devid_irq(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct irqaction *action = desc->action;
 	void *dev_id = raw_cpu_ptr(action->percpu_dev_id);
+	unsigned int irq = irq_desc_get_irq(desc);
 	irqreturn_t res;
 
 	kstat_incr_irqs_this_cpu(desc);
@@ -796,7 +785,7 @@
 		return;
 
 	__irq_do_set_handler(desc, handle, 1, NULL);
-	desc->irq_data.handler_data = data;
+	desc->irq_common_data.handler_data = data;
 
 	irq_put_desc_busunlock(desc, flags);
 }
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index b6eeea8..de41a68 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -27,8 +27,10 @@
  *
  * Handles spurious and unhandled IRQ's. It also prints a debugmessage.
  */
-void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
+void handle_bad_irq(struct irq_desc *desc)
 {
+	unsigned int irq = irq_desc_get_irq(desc);
+
 	print_irq_desc(irq, desc);
 	kstat_incr_irqs_this_cpu(desc);
 	ack_bad_irq(irq);
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index eee4b38..5ef0c2d 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -194,7 +194,7 @@
 
 static inline int irq_desc_get_node(struct irq_desc *desc)
 {
-	return irq_data_get_node(&desc->irq_data);
+	return irq_common_data_get_node(&desc->irq_common_data);
 }
 
 #ifdef CONFIG_PM_SLEEP
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 0a2a4b6..239e2ae 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -38,12 +38,13 @@
 #ifdef CONFIG_SMP
 static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
 {
-	if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node))
+	if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity,
+				     gfp, node))
 		return -ENOMEM;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
-		free_cpumask_var(desc->irq_data.affinity);
+		free_cpumask_var(desc->irq_common_data.affinity);
 		return -ENOMEM;
 	}
 #endif
@@ -52,11 +53,13 @@
 
 static void desc_smp_init(struct irq_desc *desc, int node)
 {
-	desc->irq_data.node = node;
-	cpumask_copy(desc->irq_data.affinity, irq_default_affinity);
+	cpumask_copy(desc->irq_common_data.affinity, irq_default_affinity);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	cpumask_clear(desc->pending_mask);
 #endif
+#ifdef CONFIG_NUMA
+	desc->irq_common_data.node = node;
+#endif
 }
 
 #else
@@ -70,12 +73,13 @@
 {
 	int cpu;
 
+	desc->irq_common_data.handler_data = NULL;
+	desc->irq_common_data.msi_desc = NULL;
+
 	desc->irq_data.common = &desc->irq_common_data;
 	desc->irq_data.irq = irq;
 	desc->irq_data.chip = &no_irq_chip;
 	desc->irq_data.chip_data = NULL;
-	desc->irq_data.handler_data = NULL;
-	desc->irq_data.msi_desc = NULL;
 	irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
 	irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED);
 	desc->handle_irq = handle_bad_irq;
@@ -121,7 +125,7 @@
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	free_cpumask_var(desc->pending_mask);
 #endif
-	free_cpumask_var(desc->irq_data.affinity);
+	free_cpumask_var(desc->irq_common_data.affinity);
 }
 #else
 static inline void free_masks(struct irq_desc *desc) { }
@@ -343,7 +347,7 @@
 
 	if (!desc)
 		return -EINVAL;
-	generic_handle_irq_desc(irq, desc);
+	generic_handle_irq_desc(desc);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(generic_handle_irq);
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 79baaf8..dc9d27c 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -844,7 +844,6 @@
 		child->parent_data = irq_data;
 		irq_data->irq = child->irq;
 		irq_data->common = child->common;
-		irq_data->node = child->node;
 		irq_data->domain = domain;
 	}
 
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index ad1b064..f9a59f6 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -192,7 +192,7 @@
 	switch (ret) {
 	case IRQ_SET_MASK_OK:
 	case IRQ_SET_MASK_OK_DONE:
-		cpumask_copy(data->affinity, mask);
+		cpumask_copy(desc->irq_common_data.affinity, mask);
 	case IRQ_SET_MASK_OK_NOCOPY:
 		irq_set_thread_affinity(desc);
 		ret = 0;
@@ -304,7 +304,7 @@
 	if (irq_move_pending(&desc->irq_data))
 		irq_get_pending(cpumask, desc);
 	else
-		cpumask_copy(cpumask, desc->irq_data.affinity);
+		cpumask_copy(cpumask, desc->irq_common_data.affinity);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	notify->notify(notify, cpumask);
@@ -375,9 +375,9 @@
 	 * one of the targets is online.
 	 */
 	if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
-		if (cpumask_intersects(desc->irq_data.affinity,
+		if (cpumask_intersects(desc->irq_common_data.affinity,
 				       cpu_online_mask))
-			set = desc->irq_data.affinity;
+			set = desc->irq_common_data.affinity;
 		else
 			irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
 	}
@@ -829,8 +829,8 @@
 	 * This code is triggered unconditionally. Check the affinity
 	 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
 	 */
-	if (desc->irq_data.affinity)
-		cpumask_copy(mask, desc->irq_data.affinity);
+	if (desc->irq_common_data.affinity)
+		cpumask_copy(mask, desc->irq_common_data.affinity);
 	else
 		valid = false;
 	raw_spin_unlock_irq(&desc->lock);
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index 0e97c14..e3a8c95 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -39,7 +39,7 @@
 static int show_irq_affinity(int type, struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = desc->irq_data.affinity;
+	const struct cpumask *mask = desc->irq_common_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (irqd_is_setaffinity_pending(&desc->irq_data))
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index dd95f44..b86886b 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -38,7 +38,7 @@
 		clear_bit(irq, irqs_resend);
 		desc = irq_to_desc(irq);
 		local_irq_disable();
-		desc->handle_irq(irq, desc);
+		desc->handle_irq(desc);
 		local_irq_enable();
 	}
 }
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index 337c881..87e9ce6a 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -289,7 +289,7 @@
 	if (pv_enabled())
 		goto queue;
 
-	if (virt_queued_spin_lock(lock))
+	if (virt_spin_lock(lock))
 		return;
 
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3595403..2f9c928 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -621,18 +621,21 @@
 	int i, cpu = smp_processor_id();
 	struct sched_domain *sd;
 
-	if (!idle_cpu(cpu))
+	if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu))
 		return cpu;
 
 	rcu_read_lock();
 	for_each_domain(cpu, sd) {
 		for_each_cpu(i, sched_domain_span(sd)) {
-			if (!idle_cpu(i)) {
+			if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) {
 				cpu = i;
 				goto unlock;
 			}
 		}
 	}
+
+	if (!is_housekeeping_cpu(cpu))
+		cpu = housekeeping_any_cpu();
 unlock:
 	rcu_read_unlock();
 	return cpu;
@@ -2666,13 +2669,20 @@
 
 /*
  * Check if only the current task is running on the cpu.
+ *
+ * Caution: this function does not check that the caller has disabled
+ * preemption, thus the result might have a time-of-check-to-time-of-use
+ * race.  The caller is responsible to use it correctly, for example:
+ *
+ * - from a non-preemptable section (of course)
+ *
+ * - from a thread that is bound to a single CPU
+ *
+ * - in a loop with very short iterations (e.g. a polling loop)
  */
 bool single_task_running(void)
 {
-	if (cpu_rq(smp_processor_id())->nr_running == 1)
-		return true;
-	else
-		return false;
+	return raw_rq()->nr_running == 1;
 }
 EXPORT_SYMBOL(single_task_running);
 
@@ -5178,24 +5188,47 @@
 			break;
 
 		/*
-		 * Ensure rq->lock covers the entire task selection
-		 * until the migration.
+		 * pick_next_task assumes pinned rq->lock.
 		 */
 		lockdep_pin_lock(&rq->lock);
 		next = pick_next_task(rq, &fake_task);
 		BUG_ON(!next);
 		next->sched_class->put_prev_task(rq, next);
 
+		/*
+		 * Rules for changing task_struct::cpus_allowed are holding
+		 * both pi_lock and rq->lock, such that holding either
+		 * stabilizes the mask.
+		 *
+		 * Drop rq->lock is not quite as disastrous as it usually is
+		 * because !cpu_active at this point, which means load-balance
+		 * will not interfere. Also, stop-machine.
+		 */
+		lockdep_unpin_lock(&rq->lock);
+		raw_spin_unlock(&rq->lock);
+		raw_spin_lock(&next->pi_lock);
+		raw_spin_lock(&rq->lock);
+
+		/*
+		 * Since we're inside stop-machine, _nothing_ should have
+		 * changed the task, WARN if weird stuff happened, because in
+		 * that case the above rq->lock drop is a fail too.
+		 */
+		if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) {
+			raw_spin_unlock(&next->pi_lock);
+			continue;
+		}
+
 		/* Find suitable destination for @next, with force if needed. */
 		dest_cpu = select_fallback_rq(dead_rq->cpu, next);
 
-		lockdep_unpin_lock(&rq->lock);
 		rq = __migrate_task(rq, next, dest_cpu);
 		if (rq != dead_rq) {
 			raw_spin_unlock(&rq->lock);
 			rq = dead_rq;
 			raw_spin_lock(&rq->lock);
 		}
+		raw_spin_unlock(&next->pi_lock);
 	}
 
 	rq->stop = stop;
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 272d932..052e026 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -106,10 +106,9 @@
 }
 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 @@
 	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/kernel/time/clockevents.c b/kernel/time/clockevents.c
index 50eb107..a9b76a4 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -97,20 +97,6 @@
 static int __clockevents_switch_state(struct clock_event_device *dev,
 				      enum clock_event_state state)
 {
-	/* Transition with legacy set_mode() callback */
-	if (dev->set_mode) {
-		/* Legacy callback doesn't support new modes */
-		if (state > CLOCK_EVT_STATE_ONESHOT)
-			return -ENOSYS;
-		/*
-		 * 'clock_event_state' and 'clock_event_mode' have 1-to-1
-		 * mapping until *_ONESHOT, and so a simple cast will work.
-		 */
-		dev->set_mode((enum clock_event_mode)state, dev);
-		dev->mode = (enum clock_event_mode)state;
-		return 0;
-	}
-
 	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
 		return 0;
 
@@ -204,12 +190,8 @@
 {
 	int ret = 0;
 
-	if (dev->set_mode) {
-		dev->set_mode(CLOCK_EVT_MODE_RESUME, dev);
-		dev->mode = CLOCK_EVT_MODE_RESUME;
-	} else if (dev->tick_resume) {
+	if (dev->tick_resume)
 		ret = dev->tick_resume(dev);
-	}
 
 	return ret;
 }
@@ -460,26 +442,6 @@
 }
 EXPORT_SYMBOL_GPL(clockevents_unbind_device);
 
-/* Sanity check of state transition callbacks */
-static int clockevents_sanity_check(struct clock_event_device *dev)
-{
-	/* Legacy set_mode() callback */
-	if (dev->set_mode) {
-		/* We shouldn't be supporting new modes now */
-		WARN_ON(dev->set_state_periodic || dev->set_state_oneshot ||
-			dev->set_state_shutdown || dev->tick_resume ||
-			dev->set_state_oneshot_stopped);
-
-		BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
-		return 0;
-	}
-
-	if (dev->features & CLOCK_EVT_FEAT_DUMMY)
-		return 0;
-
-	return 0;
-}
-
 /**
  * clockevents_register_device - register a clock event device
  * @dev:	device to register
@@ -488,8 +450,6 @@
 {
 	unsigned long flags;
 
-	BUG_ON(clockevents_sanity_check(dev));
-
 	/* Initialize state to DETACHED */
 	clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
 
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index d11c55b..4fcd99e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -398,7 +398,6 @@
 		 * the set mode function!
 		 */
 		clockevent_set_state(dev, CLOCK_EVT_STATE_DETACHED);
-		dev->mode = CLOCK_EVT_MODE_UNUSED;
 		clockevents_exchange_device(dev, NULL);
 		dev->event_handler = clockevents_handle_noop;
 		td->evtdev = NULL;
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 3319e16..7c7ec45 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -290,16 +290,17 @@
 __setup("nohz_full=", tick_nohz_full_setup);
 
 static int tick_nohz_cpu_down_callback(struct notifier_block *nfb,
-						 unsigned long action,
-						 void *hcpu)
+				       unsigned long action,
+				       void *hcpu)
 {
 	unsigned int cpu = (unsigned long)hcpu;
 
 	switch (action & ~CPU_TASKS_FROZEN) {
 	case CPU_DOWN_PREPARE:
 		/*
-		 * If we handle the timekeeping duty for full dynticks CPUs,
-		 * we can't safely shutdown that CPU.
+		 * The boot CPU handles housekeeping duty (unbound timers,
+		 * workqueues, timekeeping, ...) on behalf of full dynticks
+		 * CPUs. It must remain online when nohz full is enabled.
 		 */
 		if (tick_nohz_full_running && tick_do_timer_cpu == cpu)
 			return NOTIFY_BAD;
@@ -370,6 +371,12 @@
 	cpu_notifier(tick_nohz_cpu_down_callback, 0);
 	pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n",
 		cpumask_pr_args(tick_nohz_full_mask));
+
+	/*
+	 * We need at least one CPU to handle housekeeping work such
+	 * as timekeeping, unbound timers, workqueues, ...
+	 */
+	WARN_ON_ONCE(cpumask_empty(housekeeping_mask));
 }
 #endif
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index f6ee2e6..3739ac6 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1614,7 +1614,7 @@
 	negative = (tick_error < 0);
 
 	/* Sort out the magnitude of the correction */
-	tick_error = abs(tick_error);
+	tick_error = abs64(tick_error);
 	for (adj = 0; tick_error > interval; adj++)
 		tick_error >>= 1;
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 129c960..f75e35b 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -225,7 +225,7 @@
 		   (unsigned long long) dev->min_delta_ns);
 	SEQ_printf(m, " mult:           %u\n", dev->mult);
 	SEQ_printf(m, " shift:          %u\n", dev->shift);
-	SEQ_printf(m, " mode:           %d\n", dev->mode);
+	SEQ_printf(m, " mode:           %d\n", clockevent_get_state(dev));
 	SEQ_printf(m, " next_event:     %Ld nsecs\n",
 		   (unsigned long long) ktime_to_ns(dev->next_event));
 
@@ -233,40 +233,34 @@
 	print_name_offset(m, dev->set_next_event);
 	SEQ_printf(m, "\n");
 
-	if (dev->set_mode) {
-		SEQ_printf(m, " set_mode:       ");
-		print_name_offset(m, dev->set_mode);
+	if (dev->set_state_shutdown) {
+		SEQ_printf(m, " shutdown: ");
+		print_name_offset(m, dev->set_state_shutdown);
 		SEQ_printf(m, "\n");
-	} else {
-		if (dev->set_state_shutdown) {
-			SEQ_printf(m, " shutdown: ");
-			print_name_offset(m, dev->set_state_shutdown);
-			SEQ_printf(m, "\n");
-		}
+	}
 
-		if (dev->set_state_periodic) {
-			SEQ_printf(m, " periodic: ");
-			print_name_offset(m, dev->set_state_periodic);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->set_state_periodic) {
+		SEQ_printf(m, " periodic: ");
+		print_name_offset(m, dev->set_state_periodic);
+		SEQ_printf(m, "\n");
+	}
 
-		if (dev->set_state_oneshot) {
-			SEQ_printf(m, " oneshot:  ");
-			print_name_offset(m, dev->set_state_oneshot);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->set_state_oneshot) {
+		SEQ_printf(m, " oneshot:  ");
+		print_name_offset(m, dev->set_state_oneshot);
+		SEQ_printf(m, "\n");
+	}
 
-		if (dev->set_state_oneshot_stopped) {
-			SEQ_printf(m, " oneshot stopped: ");
-			print_name_offset(m, dev->set_state_oneshot_stopped);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->set_state_oneshot_stopped) {
+		SEQ_printf(m, " oneshot stopped: ");
+		print_name_offset(m, dev->set_state_oneshot_stopped);
+		SEQ_printf(m, "\n");
+	}
 
-		if (dev->tick_resume) {
-			SEQ_printf(m, " resume:   ");
-			print_name_offset(m, dev->tick_resume);
-			SEQ_printf(m, "\n");
-		}
+	if (dev->tick_resume) {
+		SEQ_printf(m, " resume:   ");
+		print_name_offset(m, dev->tick_resume);
+		SEQ_printf(m, "\n");
 	}
 
 	SEQ_printf(m, " event_handler:  ");
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
index ff19f66..b1c93e9 100644
--- a/lib/iommu-common.c
+++ b/lib/iommu-common.c
@@ -21,8 +21,7 @@
 
 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 @@
 			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 cc0c697..a54ff89 100644
--- a/lib/rhashtable.c
+++ b/lib/rhashtable.c
@@ -187,10 +187,7 @@
 	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/lib/string_helpers.c b/lib/string_helpers.c
index 54036ce..5939f63 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -59,7 +59,11 @@
 	}
 
 	exp = divisor[units] / (u32)blk_size;
-	if (size >= exp) {
+	/*
+	 * size must be strictly greater than exp here to ensure that remainder
+	 * is greater than divisor[units] coming out of the if below.
+	 */
+	if (size > exp) {
 		remainder = do_div(size, divisor[units]);
 		remainder *= blk_size;
 		i++;
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 7b28e9c..8da2114 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -135,12 +135,11 @@
 
 	if (unlikely(*shadow_addr)) {
 		u16 shadow_first_bytes = *(u16 *)shadow_addr;
-		s8 last_byte = (addr + 15) & KASAN_SHADOW_MASK;
 
 		if (unlikely(shadow_first_bytes))
 			return true;
 
-		if (likely(!last_byte))
+		if (likely(IS_ALIGNED(addr, 8)))
 			return false;
 
 		return memory_is_poisoned_1(addr + 15);
diff --git a/mm/migrate.c b/mm/migrate.c
index c3cb566..7452a00 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1075,7 +1075,7 @@
 	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 971dd2c..79bcc9f 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -612,8 +612,6 @@
 void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct rb_node **rb_link, struct rb_node *rb_parent)
 {
-	WARN_ONCE(vma->vm_file && !vma->vm_ops, "missing vma->vm_ops");
-
 	/* Update tracking information for the gap following the new vma. */
 	if (vma->vm_next)
 		vma_gap_update(vma->vm_next);
@@ -1492,13 +1490,14 @@
 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
@@ -1638,12 +1637,6 @@
 		 */
 		WARN_ON_ONCE(addr != vma->vm_start);
 
-		/* All file mapping must have ->vm_ops set */
-		if (!vma->vm_ops) {
-			static const struct vm_operations_struct dummy_ops = {};
-			vma->vm_ops = &dummy_ops;
-		}
-
 		addr = vma->vm_start;
 		vm_flags = vma->vm_flags;
 	} else if (vm_flags & VM_SHARED) {
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2d978b2..7f63a93 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -175,7 +175,7 @@
 	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 17e55df..e07f551 100644
--- a/net/atm/clip.c
+++ b/net/atm/clip.c
@@ -317,6 +317,9 @@
 
 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 ad82324..0510a57 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -2311,12 +2311,6 @@
 	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 @@
 		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 66efdc2..480b3de 100644
--- a/net/bridge/br_multicast.c
+++ b/net/bridge/br_multicast.c
@@ -1006,7 +1006,7 @@
 
 	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 @@
 
 	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/ceph/messenger.c b/net/ceph/messenger.c
index 525f454..b9b0e3b 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -1353,11 +1353,12 @@
 	dout("prepare_write_keepalive %p\n", con);
 	con_out_kvec_reset(con);
 	if (con->peer_features & CEPH_FEATURE_MSGR_KEEPALIVE2) {
-		struct timespec ts = CURRENT_TIME;
-		struct ceph_timespec ceph_ts;
-		ceph_encode_timespec(&ceph_ts, &ts);
+		struct timespec now = CURRENT_TIME;
+
 		con_out_kvec_add(con, sizeof(tag_keepalive2), &tag_keepalive2);
-		con_out_kvec_add(con, sizeof(ceph_ts), &ceph_ts);
+		ceph_encode_timespec(&con->out_temp_keepalive2, &now);
+		con_out_kvec_add(con, sizeof(con->out_temp_keepalive2),
+				 &con->out_temp_keepalive2);
 	} else {
 		con_out_kvec_add(con, sizeof(tag_keepalive), &tag_keepalive);
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index 877c848..6bb6470 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4713,6 +4713,8 @@
 
 	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 bf77e36..365de66 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -631,15 +631,17 @@
 {
 	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 @@
 	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 @@
 		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 13079f0..05a04ea 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -478,9 +478,9 @@
 				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 b279077..805a95a 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -1481,6 +1481,15 @@
 	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 6aa3db8..8bdada2 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -142,7 +142,7 @@
  */
 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 @@
 	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 @@
 
 	clear_bit(NAPI_STATE_NPSVC, &napi->state);
 
+out:
 	return budget - work;
 }
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a466821..0ec4840 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3047,6 +3047,7 @@
 	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 @@
 		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 ca2984a..3307c02 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2740,10 +2740,8 @@
 		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 @@
 	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 bd9e718..3de0d03 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -398,12 +398,8 @@
 
 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 8349897..90f77d0 100644
--- a/net/dccp/ccid.c
+++ b/net/dccp/ccid.c
@@ -95,8 +95,7 @@
 
 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 30addee..838f524 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -48,8 +48,6 @@
 			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 @@
 			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 76e380076..c59fa5d 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -634,6 +634,10 @@
 			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 @@
 		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 @@
 		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 @@
 				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 @@
 		}
 	}
 
+	/* 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:
 	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 @@
 		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 d25efc9..b6ca089 100644
--- a/net/dsa/tag_trailer.c
+++ b/net/dsa/tag_trailer.c
@@ -78,7 +78,7 @@
 
 	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 30409b7..f03db8b 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 @@
 			 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 @@
 	if (!skb)
 		return;
 
-	if (oskb)
-		skb_dst_copy(skb, oskb);
-
+	skb_dst_set(skb, dst);
 	arp_xmit(skb);
 }
 
@@ -333,6 +334,7 @@
 	__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 @@
 		}
 	}
 
+	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 @@
 	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 @@
  *  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 @@
 			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 @@
 				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 26d6ffb..6c2af79 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1426,7 +1426,7 @@
 			    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 79fe05b..e5eb8ac 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -427,7 +427,7 @@
 	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 @@
 	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 1349571..7bb9c39 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -685,20 +685,20 @@
 	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 ae22cc2..c67f9bd 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -123,13 +123,15 @@
 	/*
 	 * 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 @@
 }
 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 @@
 	 */
 
 	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 29ed6c5..84dce6a 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 @@
 }
 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 @@
 	[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 @@
 	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 @@
 	    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 @@
 		+ 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 @@
 	[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 @@
 	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 @@
 	    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 @@
 		+ 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 5f4a556..c6ad99a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2045,6 +2045,7 @@
 	struct fib_result res;
 	struct rtable *rth;
 	int orig_oif;
+	int err = -ENETUNREACH;
 
 	res.tclassid	= 0;
 	res.fi		= NULL;
@@ -2153,7 +2154,8 @@
 		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 @@
 			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 c6ded6b..448c261 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -154,14 +154,20 @@
 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 6d8795b..def7659 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -162,9 +162,9 @@
 		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 @@
 				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 @@
 		 * 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 @@
 		} 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 @@
 		}
 
 		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 f9a8a12..1100ffe 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2897,6 +2897,7 @@
 	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 c0a15e7..f7d1d5e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1024,7 +1024,8 @@
 		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 bb919b2..c10a9ee 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -33,6 +33,8 @@
 	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 030fefd..9001133 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -5127,13 +5127,12 @@
 
 			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 418d982..7d2e002 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -155,6 +155,11 @@
 	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 @@
 		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 @@
 {
 	if (atomic_dec_and_test(&rt->rt6i_ref)) {
 		rt6_free_pcpu(rt);
-		dst_free(&rt->dst);
+		rt6_rcu_free(rt);
 	}
 }
 
@@ -846,7 +851,7 @@
 		*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 @@
 		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 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 @@
 		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 @@
 			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 @@
 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 @@
 
 	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 4038c69..3c7b931 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -404,13 +404,13 @@
 		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 @@
 		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 @@
 	}
 
 	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 @@
 		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 @@
 	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 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 @@
 	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 @@
 	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 int ip6gre_tap_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);
 
-	tunnel->dev = dev;
-	tunnel->net = dev_net(dev);
-	strcpy(tunnel->parms.name, dev->name);
-
 	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 26ea479..92b1aa3 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -586,20 +586,22 @@
 	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 @@
 
 		err = 0;
 		offset = 0;
-		frag = skb_shinfo(skb)->frag_list;
-		skb_frag_list_init(skb);
 		/* BUILD HEADER */
 
 		*prevhdr = NEXTHDR_FRAGMENT;
@@ -625,8 +625,11 @@
 		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 @@
 	 */
 
 	*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 b0ab420..eabffbb 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -126,36 +126,92 @@
  * 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;
-
-	if (dst && dst->obsolete &&
-	    !dst->ops->check(dst, t->dst_cookie)) {
-		t->dst_cache = NULL;
-		dst_release(dst);
-		return NULL;
+	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;
+
+	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);
+		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)
 {
-	struct rt6_info *rt = (struct rt6_info *) dst;
-	t->dst_cookie = rt6_get_cookie(rt);
-	dst_release(t->dst_cache);
-	t->dst_cache = dst;
+	ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst);
+
 }
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_store);
+EXPORT_SYMBOL_GPL(ip6_tnl_dst_set);
+
+void ip6_tnl_dst_destroy(struct ip6_tnl *t)
+{
+	if (!t->dst_cache)
+		return;
+
+	ip6_tnl_dst_reset(t);
+	free_percpu(t->dst_cache);
+}
+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 @@
 
 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 @@
 		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 @@
 		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 @@
 		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 @@
 		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 @@
 	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 @@
 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 53617d7..f204089 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1322,8 +1322,7 @@
 	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 @@
 			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 @@
 	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 @@
 	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 @@
 	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 @@
 		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 17b1fe9..7a77a14 100644
--- a/net/mac80211/cfg.c
+++ b/net/mac80211/cfg.c
@@ -2474,6 +2474,7 @@
 
 	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 @@
 			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;
-
-			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;
+			}
+		}
+
+		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;
+				break;
+			}
 		}
 	}
 
diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c
index 675d12c..a5d41df 100644
--- a/net/netfilter/nf_log.c
+++ b/net/netfilter/nf_log.c
@@ -107,12 +107,17 @@
 
 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 66def31..9c8fab0 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -619,6 +619,13 @@
 
 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 @@
 	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 @@
 	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 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 @@
 	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 @@
 	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 7f86d3b..8f060d7 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -125,6 +125,24 @@
 	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 @@
 	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 @@
 }
 
 #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 @@
 }
 
 #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 @@
 
 	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 @@
 			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 @@
 	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 @@
 			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 @@
 		}
 	}
 
-	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 @@
 	    !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 @@
 		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 8900840..14437d9 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -35,6 +35,7 @@
 	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 @@
 	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 2a071f4..d143aa9 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 e8e524a..002a755 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -275,13 +275,15 @@
 	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 6fbd2de..b816ff8 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -952,7 +952,7 @@
 	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 @@
 	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 c92d6a2..5c030a4 100644
--- a/net/openvswitch/flow_netlink.c
+++ b/net/openvswitch/flow_netlink.c
@@ -57,6 +57,7 @@
 };
 
 #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 @@
 		+ 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 @@
 	[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 @@
 	[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 @@
 		}
 
 		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 @@
 	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 @@
 			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 @@
 
 	/* 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 @@
 		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 d22d8e9..f2ea83b 100644
--- a/net/openvswitch/flow_table.c
+++ b/net/openvswitch/flow_table.c
@@ -57,20 +57,21 @@
 }
 
 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 @@
 	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 616eda1..2dd9900 100644
--- a/net/openvswitch/flow_table.h
+++ b/net/openvswitch/flow_table.h
@@ -86,5 +86,5 @@
 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 7b8e39a..aa4b15c 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -230,6 +230,8 @@
 	} 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 @@
 			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 @@
 	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 @@
 
 	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 @@
 		}
 
 		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 @@
 
 			/* 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 @@
 
 		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 715e01e..f23a3b6 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 @@
 			}
 		}
 	} 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 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 @@
 	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 @@
 	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 b714333..3d9ea9a 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -1186,7 +1186,7 @@
 	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 @@
 
 	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 @@
 
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 	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 @@
 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 @@
 	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 b140c09..f14f24e 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -297,7 +297,7 @@
 	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 @@
 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 ab5dd62..2e98f4a 100644
--- a/net/sunrpc/xprt.c
+++ b/net/sunrpc/xprt.c
@@ -614,6 +614,7 @@
 	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 @@
 	xprt->ops->release_xprt(xprt, NULL);
 out:
 	spin_unlock_bh(&xprt->transport_lock);
+	wake_up_bit(&xprt->state, XPRT_LOCKED);
 }
 
 /**
@@ -1394,6 +1396,10 @@
 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 7be90bc..1a85e0e 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -777,7 +777,6 @@
 	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_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 @@
 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 @@
 			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 @@
 			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 @@
 		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 @@
 	/* 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 @@
 	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 562c926..c5ac436 100644
--- a/net/tipc/msg.c
+++ b/net/tipc/msg.c
@@ -539,6 +539,7 @@
 	*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/scripts/extract-cert.c b/scripts/extract-cert.c
index 10d23ca..6ce5945 100644
--- a/scripts/extract-cert.c
+++ b/scripts/extract-cert.c
@@ -1,15 +1,15 @@
 /* Extract X.509 certificate in DER form from PKCS#11 or PEM.
  *
- * Copyright © 2014 Red Hat, Inc. All Rights Reserved.
- * Copyright © 2015 Intel Corporation.
+ * Copyright © 2014-2015 Red Hat, Inc. All Rights Reserved.
+ * Copyright © 2015      Intel Corporation.
  *
  * Authors: David Howells <dhowells@redhat.com>
  *          David Woodhouse <dwmw2@infradead.org>
  *
  * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
+ * modify it under the terms of the GNU Lesser General Public License
+ * as published by the Free Software Foundation; either version 2.1
+ * of the licence, or (at your option) any later version.
  */
 #define _GNU_SOURCE
 #include <stdio.h>
diff --git a/scripts/sign-file.c b/scripts/sign-file.c
index 058bba3..c3899ca 100755
--- a/scripts/sign-file.c
+++ b/scripts/sign-file.c
@@ -1,12 +1,15 @@
 /* Sign a module file using the given key.
  *
- * Copyright (C) 2014 Red Hat, Inc. All Rights Reserved.
- * Written by David Howells (dhowells@redhat.com)
+ * Copyright © 2014-2015 Red Hat, Inc. All Rights Reserved.
+ * Copyright © 2015      Intel Corporation.
+ *
+ * Authors: David Howells <dhowells@redhat.com>
+ *          David Woodhouse <dwmw2@infradead.org>
  *
  * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public Licence
- * as published by the Free Software Foundation; either version
- * 2 of the Licence, or (at your option) any later version.
+ * modify it under the terms of the GNU Lesser General Public License
+ * as published by the Free Software Foundation; either version 2.1
+ * of the licence, or (at your option) any later version.
  */
 #define _GNU_SOURCE
 #include <stdio.h>
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 73455089..03c1652 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -401,7 +401,7 @@
 	bool match = false;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held() &&
-			 lockdep_is_held(&devcgroup_mutex),
+			 !lockdep_is_held(&devcgroup_mutex),
 			 "device_cgroup:verify_new_ex called without proper synchronization");
 
 	if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) {
diff --git a/sound/arm/Kconfig b/sound/arm/Kconfig
index 885683a..e040621 100644
--- a/sound/arm/Kconfig
+++ b/sound/arm/Kconfig
@@ -9,6 +9,14 @@
 	  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 @@
 	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 477742c..58c0aad 100644
--- a/sound/pci/hda/hda_tegra.c
+++ b/sound/pci/hda/hda_tegra.c
@@ -73,6 +73,7 @@
 	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_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 @@
 /*
  * 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 @@
 	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 @@
 	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 @@
 	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 a75b561..afec6dc 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -4188,6 +4188,24 @@
 	}
 }
 
+/* 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 @@
 	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 @@
 	},
 	[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 38e853a..0bf9d62 100644
--- a/sound/soc/au1x/psc-i2s.c
+++ b/sound/soc/au1x/psc-i2s.c
@@ -296,7 +296,6 @@
 {
 	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 4972bf3..268a28b 100644
--- a/sound/soc/codecs/rt5645.c
+++ b/sound/soc/codecs/rt5645.c
@@ -732,14 +732,14 @@
 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 @@
 				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 @@
 			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 @@
 		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 @@
 			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 f2c6ad4..581ec15 100644
--- a/sound/soc/codecs/wm0010.c
+++ b/sound/soc/codecs/wm0010.c
@@ -577,7 +577,6 @@
 	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 @@
 	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 @@
 
 		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 @@
 		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 @@
 
 	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 e3b7d0c..dbd8840 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -211,28 +211,38 @@
 	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 b4eb975..293e47a 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -2944,7 +2944,8 @@
 				   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 add6bb9..7d45d98 100644
--- a/sound/soc/davinci/davinci-mcasp.c
+++ b/sound/soc/davinci/davinci-mcasp.c
@@ -663,7 +663,7 @@
 	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 @@
 	 * 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 @@
 		.ops 		= &davinci_mcasp_dai_ops,
 
 		.symmetric_samplebits	= 1,
+		.symmetric_rates	= 1,
 	},
 	{
 		.name		= "davinci-mcasp.1",
@@ -1685,7 +1685,7 @@
 
 	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 @@
 
 	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 @@
 
 	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 5aeb6ed..96f55ae 100644
--- a/sound/soc/fsl/fsl-asoc-card.c
+++ b/sound/soc/fsl/fsl-asoc-card.c
@@ -488,7 +488,8 @@
 		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 8ec6fb2..37c5cd4 100644
--- a/sound/soc/fsl/fsl_ssi.c
+++ b/sound/soc/fsl/fsl_ssi.c
@@ -249,7 +249,8 @@
 
 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 @@
 				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 f6efa9d..b27f25f 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_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 @@
 
 	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 @@
 		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 d190fe0..f5baf3c 100644
--- a/sound/soc/mediatek/mtk-afe-pcm.c
+++ b/sound/soc/mediatek/mtk-afe-pcm.c
@@ -549,6 +549,23 @@
 	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 39cea80..f2bf866 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_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 1f60546..9e4b04e 100644
--- a/sound/soc/pxa/pxa2xx-ac97.c
+++ b/sound/soc/pxa/pxa2xx-ac97.c
@@ -49,7 +49,7 @@
 	.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 @@
 	.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 f4bf21a..ff8bda4 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -3501,7 +3501,7 @@
 
 	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 362c69a..53dd085 100644
--- a/sound/soc/soc-utils.c
+++ b/sound/soc/soc-utils.c
@@ -101,6 +101,15 @@
 			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 0a53053..4fb9141 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 f6eefe1..843f037 100644
--- a/sound/soc/sti/uniperif_player.c
+++ b/sound/soc/sti/uniperif_player.c
@@ -989,8 +989,8 @@
 	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 @@
 	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 c502626..f791239 100644
--- a/sound/soc/sti/uniperif_reader.c
+++ b/sound/soc/sti/uniperif_reader.c
@@ -316,7 +316,11 @@
 	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/perf/builtin-script.c b/tools/perf/builtin-script.c
index eb51325..284a76e 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -768,8 +768,8 @@
 	if (!evsel->attr.sample_id_all) {
 		sample->cpu = 0;
 		sample->time = 0;
-		sample->tid = event->comm.tid;
-		sample->pid = event->comm.pid;
+		sample->tid = event->fork.tid;
+		sample->pid = event->fork.pid;
 	}
 	print_sample_start(sample, thread, evsel);
 	perf_event__fprintf(event, stdout);
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 1aa21c9..5b83f56 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -34,6 +34,8 @@
 		.disabled = 1,
 		.freq = 1,
 	};
+	struct cpu_map *cpus;
+	struct thread_map *threads;
 
 	attr.sample_freq = 500;
 
@@ -50,14 +52,19 @@
 	}
 	perf_evlist__add(evlist, evsel);
 
-	evlist->cpus = cpu_map__dummy_new();
-	evlist->threads = thread_map__new_by_tid(getpid());
-	if (!evlist->cpus || !evlist->threads) {
+	cpus = cpu_map__dummy_new();
+	threads = thread_map__new_by_tid(getpid());
+	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_delete_evlist;
+		goto out_free_maps;
 	}
 
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	cpus	= NULL;
+	threads = NULL;
+
 	if (perf_evlist__open(evlist)) {
 		const char *knob = "/proc/sys/kernel/perf_event_max_sample_rate";
 
@@ -107,6 +114,9 @@
 		err = -1;
 	}
 
+out_free_maps:
+	cpu_map__put(cpus);
+	thread_map__put(threads);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 3a8fedef..add1638 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -43,6 +43,8 @@
 	};
 	const char *argv[] = { "true", NULL };
 	char sbuf[STRERR_BUFSIZE];
+	struct cpu_map *cpus;
+	struct thread_map *threads;
 
 	signal(SIGCHLD, sig_handler);
 
@@ -58,14 +60,19 @@
 	 * perf_evlist__prepare_workload we'll fill in the only thread
 	 * we're monitoring, the one forked there.
 	 */
-	evlist->cpus = cpu_map__dummy_new();
-	evlist->threads = thread_map__new_by_tid(-1);
-	if (!evlist->cpus || !evlist->threads) {
+	cpus = cpu_map__dummy_new();
+	threads = thread_map__new_by_tid(-1);
+	if (!cpus || !threads) {
 		err = -ENOMEM;
 		pr_debug("Not enough memory to create thread/cpu maps\n");
-		goto out_delete_evlist;
+		goto out_free_maps;
 	}
 
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	cpus	= NULL;
+	threads = NULL;
+
 	err = perf_evlist__prepare_workload(evlist, &target, argv, false,
 					    workload_exec_failed_signal);
 	if (err < 0) {
@@ -114,6 +121,9 @@
 		err = -1;
 	}
 
+out_free_maps:
+	cpu_map__put(cpus);
+	thread_map__put(threads);
 out_delete_evlist:
 	perf_evlist__delete(evlist);
 	return err;
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index cf86f2d..c04c60d 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -1968,7 +1968,8 @@
 					  &options[nr_options], dso);
 		nr_options += add_map_opt(browser, &actions[nr_options],
 					  &options[nr_options],
-					  browser->selection->map);
+					  browser->selection ?
+						browser->selection->map : NULL);
 
 		/* perf script support */
 		if (browser->he_selection) {
@@ -1976,6 +1977,15 @@
 						     &actions[nr_options],
 						     &options[nr_options],
 						     thread, NULL);
+			/*
+			 * Note that browser->selection != NULL
+			 * when browser->he_selection is not NULL,
+			 * so we don't need to check browser->selection
+			 * before fetching browser->selection->sym like what
+			 * we do before fetching browser->selection->map.
+			 *
+			 * See hist_browser__show_entry.
+			 */
 			nr_options += add_script_opt(browser,
 						     &actions[nr_options],
 						     &options[nr_options],
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index d51a520..c8fc8a2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -124,6 +124,33 @@
 	free(evlist);
 }
 
+static void __perf_evlist__propagate_maps(struct perf_evlist *evlist,
+					  struct perf_evsel *evsel)
+{
+	/*
+	 * We already have cpus for evsel (via PMU sysfs) so
+	 * keep it, if there's no target cpu list defined.
+	 */
+	if (!evsel->own_cpus || evlist->has_user_cpus) {
+		cpu_map__put(evsel->cpus);
+		evsel->cpus = cpu_map__get(evlist->cpus);
+	} else if (evsel->cpus != evsel->own_cpus) {
+		cpu_map__put(evsel->cpus);
+		evsel->cpus = cpu_map__get(evsel->own_cpus);
+	}
+
+	thread_map__put(evsel->threads);
+	evsel->threads = thread_map__get(evlist->threads);
+}
+
+static void perf_evlist__propagate_maps(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(evlist, evsel)
+		__perf_evlist__propagate_maps(evlist, evsel);
+}
+
 void perf_evlist__add(struct perf_evlist *evlist, struct perf_evsel *entry)
 {
 	entry->evlist = evlist;
@@ -133,18 +160,19 @@
 
 	if (!evlist->nr_entries++)
 		perf_evlist__set_id_pos(evlist);
+
+	__perf_evlist__propagate_maps(evlist, entry);
 }
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-				   struct list_head *list,
-				   int nr_entries)
+				   struct list_head *list)
 {
-	bool set_id_pos = !evlist->nr_entries;
+	struct perf_evsel *evsel, *temp;
 
-	list_splice_tail(list, &evlist->entries);
-	evlist->nr_entries += nr_entries;
-	if (set_id_pos)
-		perf_evlist__set_id_pos(evlist);
+	__evlist__for_each_safe(list, temp, evsel) {
+		list_del_init(&evsel->node);
+		perf_evlist__add(evlist, evsel);
+	}
 }
 
 void __perf_evlist__set_leader(struct list_head *list)
@@ -210,7 +238,7 @@
 		list_add_tail(&evsel->node, &head);
 	}
 
-	perf_evlist__splice_list_tail(evlist, &head, nr_attrs);
+	perf_evlist__splice_list_tail(evlist, &head);
 
 	return 0;
 
@@ -1103,71 +1131,56 @@
 	return perf_evlist__mmap_ex(evlist, pages, overwrite, 0, false);
 }
 
-static int perf_evlist__propagate_maps(struct perf_evlist *evlist,
-				       bool has_user_cpus)
-{
-	struct perf_evsel *evsel;
-
-	evlist__for_each(evlist, evsel) {
-		/*
-		 * We already have cpus for evsel (via PMU sysfs) so
-		 * keep it, if there's no target cpu list defined.
-		 */
-		if (evsel->cpus && has_user_cpus)
-			cpu_map__put(evsel->cpus);
-
-		if (!evsel->cpus || has_user_cpus)
-			evsel->cpus = cpu_map__get(evlist->cpus);
-
-		evsel->threads = thread_map__get(evlist->threads);
-
-		if ((evlist->cpus && !evsel->cpus) ||
-		    (evlist->threads && !evsel->threads))
-			return -ENOMEM;
-	}
-
-	return 0;
-}
-
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
-	evlist->threads = thread_map__new_str(target->pid, target->tid,
-					      target->uid);
+	struct cpu_map *cpus;
+	struct thread_map *threads;
 
-	if (evlist->threads == NULL)
+	threads = thread_map__new_str(target->pid, target->tid, target->uid);
+
+	if (!threads)
 		return -1;
 
 	if (target__uses_dummy_map(target))
-		evlist->cpus = cpu_map__dummy_new();
+		cpus = cpu_map__dummy_new();
 	else
-		evlist->cpus = cpu_map__new(target->cpu_list);
+		cpus = cpu_map__new(target->cpu_list);
 
-	if (evlist->cpus == NULL)
+	if (!cpus)
 		goto out_delete_threads;
 
-	return perf_evlist__propagate_maps(evlist, !!target->cpu_list);
+	evlist->has_user_cpus = !!target->cpu_list;
+
+	perf_evlist__set_maps(evlist, cpus, threads);
+
+	return 0;
 
 out_delete_threads:
-	thread_map__put(evlist->threads);
-	evlist->threads = NULL;
+	thread_map__put(threads);
 	return -1;
 }
 
-int perf_evlist__set_maps(struct perf_evlist *evlist,
-			  struct cpu_map *cpus,
-			  struct thread_map *threads)
+void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
+			   struct thread_map *threads)
 {
-	if (evlist->cpus)
+	/*
+	 * Allow for the possibility that one or another of the maps isn't being
+	 * changed i.e. don't put it.  Note we are assuming the maps that are
+	 * being applied are brand new and evlist is taking ownership of the
+	 * original reference count of 1.  If that is not the case it is up to
+	 * the caller to increase the reference count.
+	 */
+	if (cpus != evlist->cpus) {
 		cpu_map__put(evlist->cpus);
+		evlist->cpus = cpus;
+	}
 
-	evlist->cpus = cpus;
-
-	if (evlist->threads)
+	if (threads != evlist->threads) {
 		thread_map__put(evlist->threads);
+		evlist->threads = threads;
+	}
 
-	evlist->threads = threads;
-
-	return perf_evlist__propagate_maps(evlist, false);
+	perf_evlist__propagate_maps(evlist);
 }
 
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel)
@@ -1387,6 +1400,8 @@
 
 static int perf_evlist__create_syswide_maps(struct perf_evlist *evlist)
 {
+	struct cpu_map	  *cpus;
+	struct thread_map *threads;
 	int err = -ENOMEM;
 
 	/*
@@ -1398,20 +1413,19 @@
 	 * error, and we may not want to do that fallback to a
 	 * default cpu identity map :-\
 	 */
-	evlist->cpus = cpu_map__new(NULL);
-	if (evlist->cpus == NULL)
+	cpus = cpu_map__new(NULL);
+	if (!cpus)
 		goto out;
 
-	evlist->threads = thread_map__new_dummy();
-	if (evlist->threads == NULL)
-		goto out_free_cpus;
+	threads = thread_map__new_dummy();
+	if (!threads)
+		goto out_put;
 
-	err = 0;
+	perf_evlist__set_maps(evlist, cpus, threads);
 out:
 	return err;
-out_free_cpus:
-	cpu_map__put(evlist->cpus);
-	evlist->cpus = NULL;
+out_put:
+	cpu_map__put(cpus);
 	goto out;
 }
 
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index b39a619..115d8b5 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -42,6 +42,7 @@
 	int		 nr_mmaps;
 	bool		 overwrite;
 	bool		 enabled;
+	bool		 has_user_cpus;
 	size_t		 mmap_len;
 	int		 id_pos;
 	int		 is_pos;
@@ -155,9 +156,8 @@
 void perf_evlist__set_selected(struct perf_evlist *evlist,
 			       struct perf_evsel *evsel);
 
-int perf_evlist__set_maps(struct perf_evlist *evlist,
-			  struct cpu_map *cpus,
-			  struct thread_map *threads);
+void perf_evlist__set_maps(struct perf_evlist *evlist, struct cpu_map *cpus,
+			   struct thread_map *threads);
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target);
 int perf_evlist__apply_filters(struct perf_evlist *evlist, struct perf_evsel **err_evsel);
 
@@ -179,8 +179,7 @@
 bool perf_evlist__valid_read_format(struct perf_evlist *evlist);
 
 void perf_evlist__splice_list_tail(struct perf_evlist *evlist,
-				   struct list_head *list,
-				   int nr_entries);
+				   struct list_head *list);
 
 static inline struct perf_evsel *perf_evlist__first(struct perf_evlist *evlist)
 {
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index c53f791..5410483 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1033,6 +1033,7 @@
 	perf_evsel__free_config_terms(evsel);
 	close_cgroup(evsel->cgrp);
 	cpu_map__put(evsel->cpus);
+	cpu_map__put(evsel->own_cpus);
 	thread_map__put(evsel->threads);
 	zfree(&evsel->group_name);
 	zfree(&evsel->name);
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 298e6bb..ef8925f 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -98,6 +98,7 @@
 	struct cgroup_sel	*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
+	struct cpu_map		*own_cpus;
 	struct thread_map	*threads;
 	unsigned int		sample_size;
 	int			id_pos;
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 4181454..fce6634 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -1438,7 +1438,7 @@
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
-	ph->env.nr_cpus_online = nr;
+	ph->env.nr_cpus_avail = nr;
 
 	ret = readn(fd, &nr, sizeof(nr));
 	if (ret != sizeof(nr))
@@ -1447,7 +1447,7 @@
 	if (ph->needs_swap)
 		nr = bswap_32(nr);
 
-	ph->env.nr_cpus_avail = nr;
+	ph->env.nr_cpus_online = nr;
 	return 0;
 }
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index ea76862..eb0e7f8 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -623,7 +623,7 @@
 	if (err)
 		return err;
 	if (event->header.type == PERF_RECORD_EXIT) {
-		err = intel_bts_process_tid_exit(bts, event->comm.tid);
+		err = intel_bts_process_tid_exit(bts, event->fork.tid);
 		if (err)
 			return err;
 	}
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index bb41c20..535d86f 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -1494,7 +1494,7 @@
 	if (pt->timeless_decoding) {
 		if (event->header.type == PERF_RECORD_EXIT) {
 			err = intel_pt_process_timeless_queues(pt,
-							       event->comm.tid,
+							       event->fork.tid,
 							       sample->time);
 		}
 	} else if (timestamp) {
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index d826e6f..21ed6ee 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -287,8 +287,8 @@
 	if (!evsel)
 		return NULL;
 
-	if (cpus)
-		evsel->cpus = cpu_map__get(cpus);
+	evsel->cpus     = cpu_map__get(cpus);
+	evsel->own_cpus = cpu_map__get(cpus);
 
 	if (name)
 		evsel->name = strdup(name);
@@ -1140,10 +1140,9 @@
 	ret = parse_events__scanner(str, &data, PE_START_EVENTS);
 	perf_pmu__parse_cleanup();
 	if (!ret) {
-		int entries = data.idx - evlist->nr_entries;
 		struct perf_evsel *last;
 
-		perf_evlist__splice_list_tail(evlist, &data.list, entries);
+		perf_evlist__splice_list_tail(evlist, &data.list);
 		evlist->nr_groups += data.nr_groups;
 		last = perf_evlist__last(evlist);
 		last->cmdline_group_boundary = true;
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index 591905a..9cd7081 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -255,7 +255,7 @@
 	list_add_tail(&term->list, head);
 
 	ALLOC_LIST(list);
-	ABORT_ON(parse_events_add_pmu(list, &data->idx, "cpu", head));
+	ABORT_ON(parse_events_add_pmu(data, list, "cpu", head));
 	parse_events__free_terms(head);
 	$$ = list;
 }
diff --git a/tools/testing/selftests/Makefile b/tools/testing/selftests/Makefile
index 89b05e2..cfe1213 100644
--- a/tools/testing/selftests/Makefile
+++ b/tools/testing/selftests/Makefile
@@ -16,12 +16,12 @@
 TARGETS += ptrace
 TARGETS += seccomp
 TARGETS += size
+TARGETS += static_keys
 TARGETS += sysctl
 ifneq (1, $(quicktest))
 TARGETS += timers
 endif
 TARGETS += user
-TARGETS += jumplabel
 TARGETS += vm
 TARGETS += x86
 TARGETS += zram
diff --git a/tools/testing/selftests/exec/Makefile b/tools/testing/selftests/exec/Makefile
index 6b76bfd..4e400eb 100644
--- a/tools/testing/selftests/exec/Makefile
+++ b/tools/testing/selftests/exec/Makefile
@@ -1,6 +1,6 @@
 CFLAGS = -Wall
 BINARIES = execveat
-DEPS = execveat.symlink execveat.denatured script
+DEPS = execveat.symlink execveat.denatured script subdir
 all: $(BINARIES) $(DEPS)
 
 subdir:
@@ -22,7 +22,5 @@
 
 include ../lib.mk
 
-override EMIT_TESTS := echo "mkdir -p subdir; (./execveat && echo \"selftests: execveat [PASS]\") || echo \"selftests: execveat [FAIL]\""
-
 clean:
 	rm -rf $(BINARIES) $(DEPS) subdir.moved execveat.moved xxxxx*
diff --git a/tools/testing/selftests/ftrace/Makefile b/tools/testing/selftests/ftrace/Makefile
index 0acbeca..4e6ed13 100644
--- a/tools/testing/selftests/ftrace/Makefile
+++ b/tools/testing/selftests/ftrace/Makefile
@@ -1,7 +1,7 @@
 all:
 
 TEST_PROGS := ftracetest
-TEST_DIRS := test.d/
+TEST_DIRS := test.d
 
 include ../lib.mk
 
diff --git a/tools/testing/selftests/lib.mk b/tools/testing/selftests/lib.mk
index 97f1c67..50a93f5 100644
--- a/tools/testing/selftests/lib.mk
+++ b/tools/testing/selftests/lib.mk
@@ -12,13 +12,10 @@
 	$(RUN_TESTS)
 
 define INSTALL_RULE
-	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then			\
-		mkdir -p $(INSTALL_PATH);								\
-		for TEST_DIR in $(TEST_DIRS); do							\
-			cp -r $$TEST_DIR $(INSTALL_PATH);						\
-		done;											\
-		echo "install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES)";	\
-		install -t $(INSTALL_PATH) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES);		\
+	@if [ "X$(TEST_PROGS)$(TEST_PROGS_EXTENDED)$(TEST_FILES)" != "X" ]; then					\
+		mkdir -p ${INSTALL_PATH};										\
+		echo "rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/";	\
+		rsync -a $(TEST_DIRS) $(TEST_PROGS) $(TEST_PROGS_EXTENDED) $(TEST_FILES) $(INSTALL_PATH)/;		\
 	fi
 endef
 
diff --git a/tools/testing/selftests/membarrier/Makefile b/tools/testing/selftests/membarrier/Makefile
index 877a503..a1a9708 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 dde3125..535f0fe 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/mqueue/Makefile b/tools/testing/selftests/mqueue/Makefile
index 0e3b41e..eebac29 100644
--- a/tools/testing/selftests/mqueue/Makefile
+++ b/tools/testing/selftests/mqueue/Makefile
@@ -1,8 +1,8 @@
-CFLAGS = -O2
+CFLAGS += -O2
+LDLIBS = -lrt -lpthread -lpopt
+TEST_PROGS := mq_open_tests mq_perf_tests
 
-all:
-	$(CC) $(CFLAGS) mq_open_tests.c -o mq_open_tests -lrt
-	$(CC) $(CFLAGS) -o mq_perf_tests mq_perf_tests.c -lrt -lpthread -lpopt
+all: $(TEST_PROGS)
 
 include ../lib.mk
 
@@ -11,8 +11,6 @@
 	@./mq_perf_tests || echo "selftests: mq_perf_tests [FAIL]"
 endef
 
-TEST_PROGS := mq_open_tests mq_perf_tests
-
 override define EMIT_TESTS
 	echo "./mq_open_tests /test1 || echo \"selftests: mq_open_tests [FAIL]\""
 	echo "./mq_perf_tests || echo \"selftests: mq_perf_tests [FAIL]\""
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index a004b4c..770f47a 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -1210,6 +1210,10 @@
 # define ARCH_REGS	struct pt_regs
 # define SYSCALL_NUM	gpr[0]
 # define SYSCALL_RET	gpr[3]
+#elif defined(__s390__)
+# define ARCH_REGS     s390_regs
+# define SYSCALL_NUM   gprs[2]
+# define SYSCALL_RET   gprs[2]
 #else
 # error "Do not know how to find your architecture's registers and syscalls"
 #endif
@@ -1243,7 +1247,8 @@
 	ret = ptrace(PTRACE_GETREGSET, tracee, NT_PRSTATUS, &iov);
 	EXPECT_EQ(0, ret);
 
-#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) || defined(__powerpc__)
+#if defined(__x86_64__) || defined(__i386__) || defined(__aarch64__) || \
+    defined(__powerpc__) || defined(__s390__)
 	{
 		regs.SYSCALL_NUM = syscall;
 	}
@@ -1281,17 +1286,21 @@
 	ret = ptrace(PTRACE_GETEVENTMSG, tracee, NULL, &msg);
 	EXPECT_EQ(0, ret);
 
+	/* Validate and take action on expected syscalls. */
 	switch (msg) {
 	case 0x1002:
 		/* change getpid to getppid. */
+		EXPECT_EQ(__NR_getpid, get_syscall(_metadata, tracee));
 		change_syscall(_metadata, tracee, __NR_getppid);
 		break;
 	case 0x1003:
 		/* skip gettid. */
+		EXPECT_EQ(__NR_gettid, get_syscall(_metadata, tracee));
 		change_syscall(_metadata, tracee, -1);
 		break;
 	case 0x1004:
 		/* do nothing (allow getppid) */
+		EXPECT_EQ(__NR_getppid, get_syscall(_metadata, tracee));
 		break;
 	default:
 		EXPECT_EQ(0, msg) {
@@ -1409,6 +1418,8 @@
 #  define __NR_seccomp 277
 # elif defined(__powerpc__)
 #  define __NR_seccomp 358
+# elif defined(__s390__)
+#  define __NR_seccomp 348
 # else
 #  warning "seccomp syscall number unknown for this architecture"
 #  define __NR_seccomp 0xffff
@@ -1453,6 +1464,9 @@
 
 	/* Reject insane operation. */
 	ret = seccomp(-1, 0, &prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	EXPECT_EQ(EINVAL, errno) {
 		TH_LOG("Did not reject crazy op value!");
 	}
@@ -1501,6 +1515,9 @@
 	}
 
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	EXPECT_EQ(0, ret) {
 		TH_LOG("Could not install filter!");
 	}
@@ -1535,6 +1552,9 @@
 
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
 		      &prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	EXPECT_EQ(0, ret) {
 		TH_LOG("Could not install initial filter with TSYNC!");
 	}
@@ -1694,6 +1714,9 @@
 
 	/* Check prctl failure detection by requesting sib 0 diverge. */
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	ASSERT_EQ(0, ret) {
 		TH_LOG("setting filter failed");
 	}
@@ -1731,6 +1754,9 @@
 	}
 
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
 	}
@@ -1805,6 +1831,9 @@
 
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, SECCOMP_FLAG_FILTER_TSYNC,
 		      &self->apply_prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Could install filter on all threads!");
 	}
@@ -1833,6 +1862,9 @@
 	}
 
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
 	}
@@ -1890,6 +1922,9 @@
 	}
 
 	ret = seccomp(SECCOMP_SET_MODE_FILTER, 0, &self->root_prog);
+	ASSERT_NE(ENOSYS, errno) {
+		TH_LOG("Kernel does not support seccomp syscall!");
+	}
 	ASSERT_EQ(0, ret) {
 		TH_LOG("Kernel does not support SECCOMP_SET_MODE_FILTER!");
 	}
diff --git a/tools/testing/selftests/seccomp/test_harness.h b/tools/testing/selftests/seccomp/test_harness.h
index 977a6af..fb28416 100644
--- a/tools/testing/selftests/seccomp/test_harness.h
+++ b/tools/testing/selftests/seccomp/test_harness.h
@@ -370,11 +370,8 @@
 	__typeof__(_expected) __exp = (_expected); \
 	__typeof__(_seen) __seen = (_seen); \
 	if (!(__exp _t __seen)) { \
-		unsigned long long __exp_print = 0; \
-		unsigned long long __seen_print = 0; \
-		/* Avoid casting complaints the scariest way we can. */ \
-		memcpy(&__exp_print, &__exp, sizeof(__exp)); \
-		memcpy(&__seen_print, &__seen, sizeof(__seen)); \
+		unsigned long long __exp_print = (unsigned long long)__exp; \
+		unsigned long long __seen_print = (unsigned long long)__seen; \
 		__TH_LOG("Expected %s (%llu) %s %s (%llu)", \
 			 #_expected, __exp_print, #_t, \
 			 #_seen, __seen_print); \
diff --git a/tools/testing/selftests/vm/Makefile b/tools/testing/selftests/vm/Makefile
index d36fab7..3c53cac 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 @@
 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 2c7cca6..d77ed41 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"
+#include <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
+#ifdef __NR_userfaultfd
 
 static unsigned long nr_cpus, nr_pages, nr_pages_per_cpu, page_size;
 
@@ -430,7 +422,7 @@
 	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 @@
 		*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 @@
 	pthread_attr_init(&attr);
 	pthread_attr_setstacksize(&attr, 16*1024*1024);
 
+	err = 0;
 	while (bounces--) {
 		unsigned long expected_ioctls;
 
@@ -579,20 +580,13 @@
 		/* 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 @@
 		printf("\n");
 	}
 
-	return 0;
+	return err;
 }
 
 int main(int argc, char **argv)
@@ -618,8 +612,8 @@
 		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 @@
 	       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/tools/testing/selftests/x86/entry_from_vm86.c b/tools/testing/selftests/x86/entry_from_vm86.c
index 9a43a59..421c607 100644
--- a/tools/testing/selftests/x86/entry_from_vm86.c
+++ b/tools/testing/selftests/x86/entry_from_vm86.c
@@ -116,8 +116,9 @@
 	v86->regs.eip = eip;
 	ret = vm86(VM86_ENTER, v86);
 
-	if (ret == -1 && errno == ENOSYS) {
-		printf("[SKIP]\tvm86 not supported\n");
+	if (ret == -1 && (errno == ENOSYS || errno == EPERM)) {
+		printf("[SKIP]\tvm86 %s\n",
+		       errno == ENOSYS ? "not supported" : "not allowed");
 		return false;
 	}
 
diff --git a/tools/testing/selftests/zram/zram.sh b/tools/testing/selftests/zram/zram.sh
index 20de9a7..683a292 100755
--- a/tools/testing/selftests/zram/zram.sh
+++ b/tools/testing/selftests/zram/zram.sh
@@ -1,15 +1,7 @@
 #!/bin/bash
 TCID="zram.sh"
 
-check_prereqs()
-{
-	local msg="skip all tests:"
-
-	if [ $UID != 0 ]; then
-		echo $msg must be run as root >&2
-		exit 0
-	fi
-}
+. ./zram_lib.sh
 
 run_zram () {
 echo "--------------------"
diff --git a/tools/testing/selftests/zram/zram_lib.sh b/tools/testing/selftests/zram/zram_lib.sh
index 424e68e..f6a9c73 100755
--- a/tools/testing/selftests/zram/zram_lib.sh
+++ b/tools/testing/selftests/zram/zram_lib.sh
@@ -23,8 +23,9 @@
 check_prereqs()
 {
 	local msg="skip all tests:"
+	local uid=$(id -u)
 
-	if [ $UID != 0 ]; then
+	if [ $uid -ne 0 ]; then
 		echo $msg must be run as root >&2
 		exit 0
 	fi
diff --git a/tools/virtio/Makefile b/tools/virtio/Makefile
index 505ad51..39c89a5 100644
--- a/tools/virtio/Makefile
+++ b/tools/virtio/Makefile
@@ -6,7 +6,7 @@
 CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-pointer-sign -fno-strict-overflow -fno-strict-aliasing -fno-common -MMD -U_FORTIFY_SOURCE
 vpath %.c ../../drivers/virtio ../../drivers/vhost
 mod:
-	${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test
+	${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V}
 .PHONY: all test mod clean
 clean:
 	${RM} *.o vringh_test virtio_test vhost_test/*.o vhost_test/.*.cmd \
diff --git a/tools/virtio/asm/barrier.h b/tools/virtio/asm/barrier.h
index aff61e1..26b7926 100644
--- a/tools/virtio/asm/barrier.h
+++ b/tools/virtio/asm/barrier.h
@@ -3,6 +3,8 @@
 #define mb() __sync_synchronize()
 
 #define smp_mb()	mb()
+# define dma_rmb()	barrier()
+# define dma_wmb()	barrier()
 # define smp_rmb()	barrier()
 # define smp_wmb()	barrier()
 /* Weak barriers should be used. If not - it's a bug */
diff --git a/tools/virtio/linux/export.h b/tools/virtio/linux/export.h
new file mode 100644
index 0000000..416875e
--- /dev/null
+++ b/tools/virtio/linux/export.h
@@ -0,0 +1,3 @@
+#define EXPORT_SYMBOL_GPL(sym) extern typeof(sym) sym
+#define EXPORT_SYMBOL(sym) extern typeof(sym) sym
+
diff --git a/tools/virtio/linux/kernel.h b/tools/virtio/linux/kernel.h
index 1e8ce69..0a3da64 100644
--- a/tools/virtio/linux/kernel.h
+++ b/tools/virtio/linux/kernel.h
@@ -22,6 +22,7 @@
 
 typedef unsigned long long dma_addr_t;
 typedef size_t __kernel_size_t;
+typedef unsigned int __wsum;
 
 struct page {
 	unsigned long long dummy;
@@ -47,6 +48,13 @@
 		return __kmalloc_fake;
 	return malloc(s);
 }
+static inline void *kzalloc(size_t s, gfp_t gfp)
+{
+	void *p = kmalloc(s, gfp);
+
+	memset(p, 0, s);
+	return p;
+}
 
 static inline void kfree(void *p)
 {
diff --git a/virt/kvm/arm/arch_timer.c b/virt/kvm/arm/arch_timer.c
index 76e38d2..48c6e1a 100644
--- a/virt/kvm/arm/arch_timer.c
+++ b/virt/kvm/arm/arch_timer.c
@@ -200,6 +200,14 @@
 	timer->irq = irq;
 
 	/*
+	 * The bits in CNTV_CTL are architecturally reset to UNKNOWN for ARMv8
+	 * and to 0 for ARMv7.  We provide an implementation that always
+	 * resets the timer to be disabled and unmasked and is compliant with
+	 * the ARMv7 architecture.
+	 */
+	timer->cntv_ctl = 0;
+
+	/*
 	 * Tell the VGIC that the virtual interrupt is tied to a
 	 * physical interrupt. We do that once per VCPU.
 	 */
diff --git a/virt/kvm/arm/vgic-v3.c b/virt/kvm/arm/vgic-v3.c
index afbf925..7dd5d62 100644
--- a/virt/kvm/arm/vgic-v3.c
+++ b/virt/kvm/arm/vgic-v3.c
@@ -288,7 +288,7 @@
 
 	vgic->vctrl_base = NULL;
 	vgic->type = VGIC_V3;
-	vgic->max_gic_vcpus = KVM_MAX_VCPUS;
+	vgic->max_gic_vcpus = VGIC_V3_MAX_CPUS;
 
 	kvm_info("%s@%llx IRQ%d\n", vgic_node->name,
 		 vcpu_res.start, vgic->maint_irq);
diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c
index 9eb489a..6bd1c9b 100644
--- a/virt/kvm/arm/vgic.c
+++ b/virt/kvm/arm/vgic.c
@@ -1144,26 +1144,11 @@
 		struct irq_phys_map *map;
 		map = vgic_irq_map_search(vcpu, irq);
 
-		/*
-		 * If we have a mapping, and the virtual interrupt is
-		 * being injected, then we must set the state to
-		 * active in the physical world. Otherwise the
-		 * physical interrupt will fire and the guest will
-		 * exit before processing the virtual interrupt.
-		 */
 		if (map) {
-			int ret;
-
-			BUG_ON(!map->active);
 			vlr.hwirq = map->phys_irq;
 			vlr.state |= LR_HW;
 			vlr.state &= ~LR_EOI_INT;
 
-			ret = irq_set_irqchip_state(map->irq,
-						    IRQCHIP_STATE_ACTIVE,
-						    true);
-			WARN_ON(ret);
-
 			/*
 			 * Make sure we're not going to sample this
 			 * again, as a HW-backed interrupt cannot be
@@ -1255,7 +1240,7 @@
 	struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
 	struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
 	unsigned long *pa_percpu, *pa_shared;
-	int i, vcpu_id;
+	int i, vcpu_id, lr, ret;
 	int overflow = 0;
 	int nr_shared = vgic_nr_shared_irqs(dist);
 
@@ -1310,6 +1295,31 @@
 		 */
 		clear_bit(vcpu_id, dist->irq_pending_on_cpu);
 	}
+
+	for (lr = 0; lr < vgic->nr_lr; lr++) {
+		struct vgic_lr vlr;
+
+		if (!test_bit(lr, vgic_cpu->lr_used))
+			continue;
+
+		vlr = vgic_get_lr(vcpu, lr);
+
+		/*
+		 * If we have a mapping, and the virtual interrupt is
+		 * presented to the guest (as pending or active), then we must
+		 * set the state to active in the physical world. See
+		 * Documentation/virtual/kvm/arm/vgic-mapped-irqs.txt.
+		 */
+		if (vlr.state & LR_HW) {
+			struct irq_phys_map *map;
+			map = vgic_irq_map_search(vcpu, vlr.irq);
+
+			ret = irq_set_irqchip_state(map->irq,
+						    IRQCHIP_STATE_ACTIVE,
+						    true);
+			WARN_ON(ret);
+		}
+	}
 }
 
 static bool vgic_process_maintenance(struct kvm_vcpu *vcpu)
diff --git a/virt/kvm/coalesced_mmio.h b/virt/kvm/coalesced_mmio.h
index 5cbf190..6bca74c 100644
--- a/virt/kvm/coalesced_mmio.h
+++ b/virt/kvm/coalesced_mmio.h
@@ -24,9 +24,9 @@
 int kvm_coalesced_mmio_init(struct kvm *kvm);
 void kvm_coalesced_mmio_free(struct kvm *kvm);
 int kvm_vm_ioctl_register_coalesced_mmio(struct kvm *kvm,
-																				struct kvm_coalesced_mmio_zone *zone);
+					struct kvm_coalesced_mmio_zone *zone);
 int kvm_vm_ioctl_unregister_coalesced_mmio(struct kvm *kvm,
-																				struct kvm_coalesced_mmio_zone *zone);
+					struct kvm_coalesced_mmio_zone *zone);
 
 #else
 
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 9ff4193..79db453 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -771,40 +771,14 @@
 	return KVM_MMIO_BUS;
 }
 
-static int
-kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+static int kvm_assign_ioeventfd_idx(struct kvm *kvm,
+				enum kvm_bus bus_idx,
+				struct kvm_ioeventfd *args)
 {
-	enum kvm_bus              bus_idx;
-	struct _ioeventfd        *p;
-	struct eventfd_ctx       *eventfd;
-	int                       ret;
 
-	bus_idx = ioeventfd_bus_from_flags(args->flags);
-	/* must be natural-word sized, or 0 to ignore length */
-	switch (args->len) {
-	case 0:
-	case 1:
-	case 2:
-	case 4:
-	case 8:
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	/* check for range overflow */
-	if (args->addr + args->len < args->addr)
-		return -EINVAL;
-
-	/* check for extra flags that we don't understand */
-	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
-		return -EINVAL;
-
-	/* ioeventfd with no length can't be combined with DATAMATCH */
-	if (!args->len &&
-	    args->flags & (KVM_IOEVENTFD_FLAG_PIO |
-			   KVM_IOEVENTFD_FLAG_DATAMATCH))
-		return -EINVAL;
+	struct eventfd_ctx *eventfd;
+	struct _ioeventfd *p;
+	int ret;
 
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
@@ -843,16 +817,6 @@
 	if (ret < 0)
 		goto unlock_fail;
 
-	/* When length is ignored, MMIO is also put on a separate bus, for
-	 * faster lookups.
-	 */
-	if (!args->len && !(args->flags & KVM_IOEVENTFD_FLAG_PIO)) {
-		ret = kvm_io_bus_register_dev(kvm, KVM_FAST_MMIO_BUS,
-					      p->addr, 0, &p->dev);
-		if (ret < 0)
-			goto register_fail;
-	}
-
 	kvm->buses[bus_idx]->ioeventfd_count++;
 	list_add_tail(&p->list, &kvm->ioeventfds);
 
@@ -860,8 +824,6 @@
 
 	return 0;
 
-register_fail:
-	kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
 unlock_fail:
 	mutex_unlock(&kvm->slots_lock);
 
@@ -873,14 +835,13 @@
 }
 
 static int
-kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+kvm_deassign_ioeventfd_idx(struct kvm *kvm, enum kvm_bus bus_idx,
+			   struct kvm_ioeventfd *args)
 {
-	enum kvm_bus              bus_idx;
 	struct _ioeventfd        *p, *tmp;
 	struct eventfd_ctx       *eventfd;
 	int                       ret = -ENOENT;
 
-	bus_idx = ioeventfd_bus_from_flags(args->flags);
 	eventfd = eventfd_ctx_fdget(args->fd);
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
@@ -901,10 +862,6 @@
 			continue;
 
 		kvm_io_bus_unregister_dev(kvm, bus_idx, &p->dev);
-		if (!p->length) {
-			kvm_io_bus_unregister_dev(kvm, KVM_FAST_MMIO_BUS,
-						  &p->dev);
-		}
 		kvm->buses[bus_idx]->ioeventfd_count--;
 		ioeventfd_release(p);
 		ret = 0;
@@ -918,6 +875,71 @@
 	return ret;
 }
 
+static int kvm_deassign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	enum kvm_bus bus_idx = ioeventfd_bus_from_flags(args->flags);
+	int ret = kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+
+	if (!args->len && bus_idx == KVM_MMIO_BUS)
+		kvm_deassign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
+
+	return ret;
+}
+
+static int
+kvm_assign_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
+{
+	enum kvm_bus              bus_idx;
+	int ret;
+
+	bus_idx = ioeventfd_bus_from_flags(args->flags);
+	/* must be natural-word sized, or 0 to ignore length */
+	switch (args->len) {
+	case 0:
+	case 1:
+	case 2:
+	case 4:
+	case 8:
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* check for range overflow */
+	if (args->addr + args->len < args->addr)
+		return -EINVAL;
+
+	/* check for extra flags that we don't understand */
+	if (args->flags & ~KVM_IOEVENTFD_VALID_FLAG_MASK)
+		return -EINVAL;
+
+	/* ioeventfd with no length can't be combined with DATAMATCH */
+	if (!args->len &&
+	    args->flags & (KVM_IOEVENTFD_FLAG_PIO |
+			   KVM_IOEVENTFD_FLAG_DATAMATCH))
+		return -EINVAL;
+
+	ret = kvm_assign_ioeventfd_idx(kvm, bus_idx, args);
+	if (ret)
+		goto fail;
+
+	/* When length is ignored, MMIO is also put on a separate bus, for
+	 * faster lookups.
+	 */
+	if (!args->len && bus_idx == KVM_MMIO_BUS) {
+		ret = kvm_assign_ioeventfd_idx(kvm, KVM_FAST_MMIO_BUS, args);
+		if (ret < 0)
+			goto fast_fail;
+	}
+
+	return 0;
+
+fast_fail:
+	kvm_deassign_ioeventfd_idx(kvm, bus_idx, args);
+fail:
+	return ret;
+}
+
 int
 kvm_ioeventfd(struct kvm *kvm, struct kvm_ioeventfd *args)
 {
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index a25a731..8db1d93 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. */
@@ -2004,6 +2004,7 @@
 	if (vcpu->halt_poll_ns) {
 		ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
 
+		++vcpu->stat.halt_attempted_poll;
 		do {
 			/*
 			 * This sets KVM_REQ_UNHALT if an interrupt
@@ -2043,7 +2044,8 @@
 		else if (vcpu->halt_poll_ns < halt_poll_ns &&
 			block_ns < halt_poll_ns)
 			grow_halt_poll_ns(vcpu);
-	}
+	} else
+		vcpu->halt_poll_ns = 0;
 
 	trace_kvm_vcpu_wakeup(block_ns, waited);
 }
@@ -3156,10 +3158,25 @@
 static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1,
 				 const struct kvm_io_range *r2)
 {
-	if (r1->addr < r2->addr)
+	gpa_t addr1 = r1->addr;
+	gpa_t addr2 = r2->addr;
+
+	if (addr1 < addr2)
 		return -1;
-	if (r1->addr + r1->len > r2->addr + r2->len)
+
+	/* If r2->len == 0, match the exact address.  If r2->len != 0,
+	 * accept any overlapping write.  Any order is acceptable for
+	 * overlapping ranges, because kvm_io_bus_get_first_dev ensures
+	 * we process all of them.
+	 */
+	if (r2->len) {
+		addr1 += r1->len;
+		addr2 += r2->len;
+	}
+
+	if (addr1 > addr2)
 		return 1;
+
 	return 0;
 }