Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts:
	net/dsa/slave.c

net/dsa/slave.c simply had overlapping changes.

Signed-off-by: David S. Miller <davem@davemloft.net>

240 files changed, 2429 insertions, 1379 deletions

diff --git a/Documentation/Changes b/Documentation/Changes
index 6d8863004858..f447f0516f07 100644
--- a/Documentation/Changes
+++ b/Documentation/Changes
@@ -43,7 +43,7 @@ o  udev                   081                     # udevd --version
 o  grub                   0.93                    # grub --version || grub-install --version
 o  mcelog                 0.6                     # mcelog --version
 o  iptables               1.4.2                   # iptables -V
-o  openssl & libcrypto    1.0.1k                  # openssl version
+o  openssl & libcrypto    1.0.0                   # openssl version
 
 
 Kernel compilation
diff --git a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
index 391717a68f3b..ec96b1f01478 100644
--- a/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
+++ b/Documentation/devicetree/bindings/interrupt-controller/qca,ath79-misc-intc.txt
@@ -4,8 +4,8 @@ The MISC interrupt controller is a secondary controller for lower priority
 interrupt.
 
 Required Properties:
-- compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc"
-  as fallback
+- compatible: has to be "qca,<soctype>-cpu-intc", "qca,ar7100-misc-intc" or
+  "qca,<soctype>-cpu-intc", "qca,ar7240-misc-intc"
 - reg: Base address and size of the controllers memory area
 - interrupt-parent: phandle of the parent interrupt controller.
 - interrupts: Interrupt specifier for the controllers interrupt.
@@ -13,6 +13,9 @@ Required Properties:
 - #interrupt-cells : Specifies the number of cells needed to encode interrupt
 		     source, should be 1
 
+Compatible fallback depends on the SoC. Use ar7100 for ar71xx and ar913x,
+use ar7240 for all other SoCs.
+
 Please refer to interrupts.txt in this directory for details of the common
 Interrupt Controllers bindings used by client devices.
 
@@ -28,3 +31,16 @@ Example:
 		interrupt-controller;
 		#interrupt-cells = <1>;
 	};
+
+Another example:
+
+	interrupt-controller@18060010 {
+		compatible = "qca,ar9331-misc-intc", qca,ar7240-misc-intc";
+		reg = <0x18060010 0x4>;
+
+		interrupt-parent = <&cpuintc>;
+		interrupts = <6>;
+
+		interrupt-controller;
+		#interrupt-cells = <1>;
+	};
diff --git a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
index d71ef07bca5d..a057b75ba4b5 100644
--- a/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
+++ b/Documentation/devicetree/bindings/usb/ci-hdrc-usb2.txt
@@ -6,6 +6,7 @@ Required properties:
 	"lsi,zevio-usb"
 	"qcom,ci-hdrc"
 	"chipidea,usb2"
+	"xlnx,zynq-usb-2.20a"
 - reg: base address and length of the registers
 - interrupts: interrupt for the USB controller
 
diff --git a/Documentation/power/pci.txt b/Documentation/power/pci.txt
index 62328d76b55b..b0e911e0e8f5 100644
--- a/Documentation/power/pci.txt
+++ b/Documentation/power/pci.txt
@@ -979,20 +979,45 @@ every time right after the runtime_resume() callback has returned
 (alternatively, the runtime_suspend() callback will have to check if the
 device should really be suspended and return -EAGAIN if that is not the case).
 
-The runtime PM of PCI devices is disabled by default.  It is also blocked by
-pci_pm_init() that runs the pm_runtime_forbid() helper function.  If a PCI
-driver implements the runtime PM callbacks and intends to use the runtime PM
-framework provided by the PM core and the PCI subsystem, it should enable this
-feature by executing the pm_runtime_enable() helper function.  However, the
-driver should not call the pm_runtime_allow() helper function unblocking
-the runtime PM of the device.  Instead, it should allow user space or some
-platform-specific code to do that (user space can do it via sysfs), although
-once it has called pm_runtime_enable(), it must be prepared to handle the
+The runtime PM of PCI devices is enabled by default by the PCI core.  PCI
+device drivers do not need to enable it and should not attempt to do so.
+However, it is blocked by pci_pm_init() that runs the pm_runtime_forbid()
+helper function.  In addition to that, the runtime PM usage counter of
+each PCI device is incremented by local_pci_probe() before executing the
+probe callback provided by the device's driver.
+
+If a PCI driver implements the runtime PM callbacks and intends to use the
+runtime PM framework provided by the PM core and the PCI subsystem, it needs
+to decrement the device's runtime PM usage counter in its probe callback
+function.  If it doesn't do that, the counter will always be different from
+zero for the device and it will never be runtime-suspended.  The simplest
+way to do that is by calling pm_runtime_put_noidle(), but if the driver
+wants to schedule an autosuspend right away, for example, it may call
+pm_runtime_put_autosuspend() instead for this purpose.  Generally, it
+just needs to call a function that decrements the devices usage counter
+from its probe routine to make runtime PM work for the device.
+
+It is important to remember that the driver's runtime_suspend() callback
+may be executed right after the usage counter has been decremented, because
+user space may already have cuased the pm_runtime_allow() helper function
+unblocking the runtime PM of the device to run via sysfs, so the driver must
+be prepared to cope with that.
+
+The driver itself should not call pm_runtime_allow(), though.  Instead, it
+should let user space or some platform-specific code do that (user space can
+do it via sysfs as stated above), but it must be prepared to handle the
 runtime PM of the device correctly as soon as pm_runtime_allow() is called
-(which may happen at any time).  [It also is possible that user space causes
-pm_runtime_allow() to be called via sysfs before the driver is loaded, so in
-fact the driver has to be prepared to handle the runtime PM of the device as
-soon as it calls pm_runtime_enable().]
+(which may happen at any time, even before the driver is loaded).
+
+When the driver's remove callback runs, it has to balance the decrementation
+of the device's runtime PM usage counter at the probe time.  For this reason,
+if it has decremented the counter in its probe callback, it must run
+pm_runtime_get_noresume() in its remove callback.  [Since the core carries
+out a runtime resume of the device and bumps up the device's usage counter
+before running the driver's remove callback, the runtime PM of the device
+is effectively disabled for the duration of the remove execution and all
+runtime PM helper functions incrementing the device's usage counter are
+then effectively equivalent to pm_runtime_get_noresume().]
 
 The runtime PM framework works by processing requests to suspend or resume
 devices, or to check if they are idle (in which cases it is reasonable to
diff --git a/Documentation/ptp/testptp.c b/Documentation/ptp/testptp.c
index 2bc8abc57fa0..6c6247aaa7b9 100644
--- a/Documentation/ptp/testptp.c
+++ b/Documentation/ptp/testptp.c
@@ -18,6 +18,7 @@
  *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 #define _GNU_SOURCE
+#define __SANE_USERSPACE_TYPES__        /* For PPC64, to get LL64 types */
 #include <errno.h>
 #include <fcntl.h>
 #include <inttypes.h>
diff --git a/MAINTAINERS b/MAINTAINERS
index fa43fa2f30e4..c22e13e80b6a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -615,9 +615,8 @@ F:	Documentation/hwmon/fam15h_power
 F:	drivers/hwmon/fam15h_power.c
 
 AMD GEODE CS5536 USB DEVICE CONTROLLER DRIVER
-M:	Thomas Dahlmann <dahlmann.thomas@arcor.de>
 L:	linux-geode@lists.infradead.org (moderated for non-subscribers)
-S:	Supported
+S:	Orphan
 F:	drivers/usb/gadget/udc/amd5536udc.*
 
 AMD GEODE PROCESSOR/CHIPSET SUPPORT
@@ -3401,7 +3400,6 @@ F:	drivers/staging/dgnc/
 
 DIGI EPCA PCI PRODUCTS
 M:	Lidza Louina <lidza.louina@gmail.com>
-M:	Mark Hounschell <markh@compro.net>
 M:	Daeseok Youn <daeseok.youn@gmail.com>
 L:	driverdev-devel@linuxdriverproject.org
 S:	Maintained
@@ -5959,7 +5957,7 @@ F:	virt/kvm/
 KERNEL VIRTUAL MACHINE (KVM) FOR AMD-V
 M:	Joerg Roedel <joro@8bytes.org>
 L:	kvm@vger.kernel.org
-W:	http://kvm.qumranet.com
+W:	http://www.linux-kvm.org/
 S:	Maintained
 F:	arch/x86/include/asm/svm.h
 F:	arch/x86/kvm/svm.c
@@ -5967,7 +5965,7 @@ F:	arch/x86/kvm/svm.c
 KERNEL VIRTUAL MACHINE (KVM) FOR POWERPC
 M:	Alexander Graf <agraf@suse.com>
 L:	kvm-ppc@vger.kernel.org
-W:	http://kvm.qumranet.com
+W:	http://www.linux-kvm.org/
 T:	git git://github.com/agraf/linux-2.6.git
 S:	Supported
 F:	arch/powerpc/include/asm/kvm*
@@ -9916,8 +9914,8 @@ F:	drivers/staging/media/lirc/
 STAGING - LUSTRE PARALLEL FILESYSTEM
 M:	Oleg Drokin <oleg.drokin@intel.com>
 M:	Andreas Dilger <andreas.dilger@intel.com>
-L:	HPDD-discuss@lists.01.org (moderated for non-subscribers)
-W:	http://lustre.opensfs.org/
+L:	lustre-devel@lists.lustre.org (moderated for non-subscribers)
+W:	http://wiki.lustre.org/
 S:	Maintained
 F:	drivers/staging/lustre
 
@@ -11209,7 +11207,7 @@ F:	drivers/vlynq/vlynq.c
 F:	include/linux/vlynq.h
 
 VME SUBSYSTEM
-M:	Martyn Welch <martyn.welch@ge.com>
+M:	Martyn Welch <martyn@welchs.me.uk>
 M:	Manohar Vanga <manohar.vanga@gmail.com>
 M:	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
 L:	devel@driverdev.osuosl.org
diff --git a/Makefile b/Makefile
index 84f4b31e3c6e..1d341eba143d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 3
 SUBLEVEL = 0
-EXTRAVERSION = -rc2
+EXTRAVERSION = -rc3
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
diff --git a/arch/arm/boot/dts/am335x-phycore-som.dtsi b/arch/arm/boot/dts/am335x-phycore-som.dtsi
index 4d28fc3aac69..5dd084f3c81c 100644
--- a/arch/arm/boot/dts/am335x-phycore-som.dtsi
+++ b/arch/arm/boot/dts/am335x-phycore-som.dtsi
@@ -252,10 +252,10 @@
 		};
 
 		vdd1_reg: regulator@2 {
-			/* VDD_MPU voltage limits 0.95V - 1.26V with +/-4% tolerance */
+			/* VDD_MPU voltage limits 0.95V - 1.325V with +/-4% tolerance */
 			regulator-name = "vdd_mpu";
 			regulator-min-microvolt = <912500>;
-			regulator-max-microvolt = <1312500>;
+			regulator-max-microvolt = <1378000>;
 			regulator-boot-on;
 			regulator-always-on;
 		};
diff --git a/arch/arm/boot/dts/am57xx-beagle-x15.dts b/arch/arm/boot/dts/am57xx-beagle-x15.dts
index 3a05b94f59ed..568adf5efde0 100644
--- a/arch/arm/boot/dts/am57xx-beagle-x15.dts
+++ b/arch/arm/boot/dts/am57xx-beagle-x15.dts
@@ -98,13 +98,6 @@
 		pinctrl-0 = <&extcon_usb1_pins>;
 	};
 
-	extcon_usb2: extcon_usb2 {
-		compatible = "linux,extcon-usb-gpio";
-		id-gpio = <&gpio7 24 GPIO_ACTIVE_HIGH>;
-		pinctrl-names = "default";
-		pinctrl-0 = <&extcon_usb2_pins>;
-	};
-
 	hdmi0: connector {
 		compatible = "hdmi-connector";
 		label = "hdmi";
@@ -326,12 +319,6 @@
 		>;
 	};
 
-	extcon_usb2_pins: extcon_usb2_pins {
-		pinctrl-single,pins = <
-			0x3e8 (PIN_INPUT_PULLUP | MUX_MODE14) /* uart1_ctsn.gpio7_24 */
-		>;
-	};
-
 	tpd12s015_pins: pinmux_tpd12s015_pins {
 		pinctrl-single,pins = <
 			0x3b0 (PIN_OUTPUT | MUX_MODE14)		/* gpio7_10 CT_CP_HPD */
@@ -432,7 +419,7 @@
 				};
 
 				ldo3_reg: ldo3 {
-					/* VDDA_1V8_PHY */
+					/* VDDA_1V8_PHYA */
 					regulator-name = "ldo3";
 					regulator-min-microvolt = <1800000>;
 					regulator-max-microvolt = <1800000>;
@@ -440,6 +427,15 @@
 					regulator-boot-on;
 				};
 
+				ldo4_reg: ldo4 {
+					/* VDDA_1V8_PHYB */
+					regulator-name = "ldo4";
+					regulator-min-microvolt = <1800000>;
+					regulator-max-microvolt = <1800000>;
+					regulator-always-on;
+					regulator-boot-on;
+				};
+
 				ldo9_reg: ldo9 {
 					/* VDD_RTC */
 					regulator-name = "ldo9";
@@ -495,6 +491,14 @@
 			gpio-controller;
 			#gpio-cells = <2>;
 		};
+
+		extcon_usb2: tps659038_usb {
+			compatible = "ti,palmas-usb-vid";
+			ti,enable-vbus-detection;
+			ti,enable-id-detection;
+			id-gpios = <&gpio7 24 GPIO_ACTIVE_HIGH>;
+		};
+
 	};
 
 	tmp102: tmp102@48 {
@@ -517,7 +521,8 @@
 	mcp_rtc: rtc@6f {
 		compatible = "microchip,mcp7941x";
 		reg = <0x6f>;
-		interrupts = <GIC_SPI 2 IRQ_TYPE_EDGE_RISING>;  /* IRQ_SYS_1N */
+		interrupts-extended = <&crossbar_mpu GIC_SPI 2 IRQ_TYPE_EDGE_RISING>,
+				      <&dra7_pmx_core 0x424>;
 
 		pinctrl-names = "default";
 		pinctrl-0 = <&mcp79410_pins_default>;
@@ -579,7 +584,6 @@
 	pinctrl-0 = <&mmc1_pins_default>;
 
 	vmmc-supply = <&ldo1_reg>;
-	vmmc_aux-supply = <&vdd_3v3>;
 	bus-width = <4>;
 	cd-gpios = <&gpio6 27 0>; /* gpio 219 */
 };
@@ -623,6 +627,14 @@
 };
 
 &usb2 {
+	/*
+	 * Stand alone usage is peripheral only.
+	 * However, with some resistor modifications
+	 * this port can be used via expansion connectors
+	 * as "host" or "dual-role". If so, provide
+	 * the necessary dr_mode override in the expansion
+	 * board's DT.
+	 */
 	dr_mode = "peripheral";
 };
 
@@ -681,7 +693,7 @@
 
 &hdmi {
 	status = "ok";
-	vdda-supply = <&ldo3_reg>;
+	vdda-supply = <&ldo4_reg>;
 
 	pinctrl-names = "default";
 	pinctrl-0 = <&hdmi_pins>;
diff --git a/arch/arm/boot/dts/dm8148-evm.dts b/arch/arm/boot/dts/dm8148-evm.dts
index 92bacd3c8fab..109fd4711647 100644
--- a/arch/arm/boot/dts/dm8148-evm.dts
+++ b/arch/arm/boot/dts/dm8148-evm.dts
@@ -19,10 +19,10 @@
 
 &cpsw_emac0 {
 	phy_id = <&davinci_mdio>, <0>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
 
 &cpsw_emac1 {
 	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
diff --git a/arch/arm/boot/dts/dm8148-t410.dts b/arch/arm/boot/dts/dm8148-t410.dts
index 8c4bbc7573df..79838dd8dee7 100644
--- a/arch/arm/boot/dts/dm8148-t410.dts
+++ b/arch/arm/boot/dts/dm8148-t410.dts
@@ -8,7 +8,7 @@
 #include "dm814x.dtsi"
 
 / {
-	model = "DM8148 EVM";
+	model = "HP t410 Smart Zero Client";
 	compatible = "hp,t410", "ti,dm8148";
 
 	memory {
@@ -19,10 +19,10 @@
 
 &cpsw_emac0 {
 	phy_id = <&davinci_mdio>, <0>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
 
 &cpsw_emac1 {
 	phy_id = <&davinci_mdio>, <1>;
-	phy-mode = "mii";
+	phy-mode = "rgmii";
 };
diff --git a/arch/arm/boot/dts/dm814x.dtsi b/arch/arm/boot/dts/dm814x.dtsi
index 972c9c9e885b..7988b42e5764 100644
--- a/arch/arm/boot/dts/dm814x.dtsi
+++ b/arch/arm/boot/dts/dm814x.dtsi
@@ -181,9 +181,9 @@
 				ti,hwmods = "timer3";
 			};
 
-			control: control@160000 {
+			control: control@140000 {
 				compatible = "ti,dm814-scm", "simple-bus";
-				reg = <0x160000 0x16d000>;
+				reg = <0x140000 0x16d000>;
 				#address-cells = <1>;
 				#size-cells = <1>;
 				ranges = <0 0x160000 0x16d000>;
@@ -321,9 +321,9 @@
 				mac-address = [ 00 00 00 00 00 00 ];
 			};
 
-			phy_sel: cpsw-phy-sel@0x48160650 {
+			phy_sel: cpsw-phy-sel@48140650 {
 				compatible = "ti,am3352-cpsw-phy-sel";
-				reg= <0x48160650 0x4>;
+				reg= <0x48140650 0x4>;
 				reg-names = "gmii-sel";
 			};
 		};
diff --git a/arch/arm/boot/dts/dra7.dtsi b/arch/arm/boot/dts/dra7.dtsi
index 76c739d3da75..8fedddc35999 100644
--- a/arch/arm/boot/dts/dra7.dtsi
+++ b/arch/arm/boot/dts/dra7.dtsi
@@ -120,9 +120,10 @@
 					reg = <0x0 0x1400>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x0 0x1400>;
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-dra7", "ti,pbias-omap";
 						reg = <0xe00 0x4>;
 						syscon = <&scm_conf>;
 						pbias_mmc_reg: pbias_mmc_omap5 {
@@ -1417,7 +1418,7 @@
 			ti,irqs-safe-map = <0>;
 		};
 
-		mac: ethernet@4a100000 {
+		mac: ethernet@48484000 {
 			compatible = "ti,dra7-cpsw","ti,cpsw";
 			ti,hwmods = "gmac";
 			clocks = <&dpll_gmac_ck>, <&gmac_gmii_ref_clk_div>;
diff --git a/arch/arm/boot/dts/omap2430.dtsi b/arch/arm/boot/dts/omap2430.dtsi
index 2390f387c271..798dda072b2a 100644
--- a/arch/arm/boot/dts/omap2430.dtsi
+++ b/arch/arm/boot/dts/omap2430.dtsi
@@ -56,6 +56,7 @@
 					reg = <0x270 0x240>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x270 0x240>;
 
 					scm_clocks: clocks {
 						#address-cells = <1>;
@@ -63,7 +64,7 @@
 					};
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-omap2", "ti,pbias-omap";
 						reg = <0x230 0x4>;
 						syscon = <&scm_conf>;
 						pbias_mmc_reg: pbias_mmc_omap2430 {
diff --git a/arch/arm/boot/dts/omap3-beagle.dts b/arch/arm/boot/dts/omap3-beagle.dts
index a5474113cd50..67659a0ed13e 100644
--- a/arch/arm/boot/dts/omap3-beagle.dts
+++ b/arch/arm/boot/dts/omap3-beagle.dts
@@ -202,7 +202,7 @@
 
 	tfp410_pins: pinmux_tfp410_pins {
 		pinctrl-single,pins = <
-			0x194 (PIN_OUTPUT | MUX_MODE4)	/* hdq_sio.gpio_170 */
+			0x196 (PIN_OUTPUT | MUX_MODE4)	/* hdq_sio.gpio_170 */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/omap3-igep.dtsi b/arch/arm/boot/dts/omap3-igep.dtsi
index d5e5cd449b16..2230e1c03320 100644
--- a/arch/arm/boot/dts/omap3-igep.dtsi
+++ b/arch/arm/boot/dts/omap3-igep.dtsi
@@ -78,12 +78,6 @@
 		>;
 	};
 
-	smsc9221_pins: pinmux_smsc9221_pins {
-		pinctrl-single,pins = <
-			0x1a2 (PIN_INPUT | MUX_MODE4)		/* mcspi1_cs2.gpio_176 */
-		>;
-	};
-
 	i2c1_pins: pinmux_i2c1_pins {
 		pinctrl-single,pins = <
 			0x18a (PIN_INPUT | MUX_MODE0)   /* i2c1_scl.i2c1_scl */
diff --git a/arch/arm/boot/dts/omap3-igep0020-common.dtsi b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
index e458c2185e3c..5ad688c57a00 100644
--- a/arch/arm/boot/dts/omap3-igep0020-common.dtsi
+++ b/arch/arm/boot/dts/omap3-igep0020-common.dtsi
@@ -156,6 +156,12 @@
 			OMAP3_CORE1_IOPAD(0x217a, PIN_INPUT | MUX_MODE0)	/* uart2_rx.uart2_rx */
 		>;
 	};
+
+	smsc9221_pins: pinmux_smsc9221_pins {
+		pinctrl-single,pins = <
+			OMAP3_CORE1_IOPAD(0x21d2, PIN_INPUT | MUX_MODE4)	/* mcspi1_cs2.gpio_176 */
+		>;
+	};
 };
 
 &omap3_pmx_core2 {
diff --git a/arch/arm/boot/dts/omap3.dtsi b/arch/arm/boot/dts/omap3.dtsi
index 69a40cfc1f29..8a2b25332b8c 100644
--- a/arch/arm/boot/dts/omap3.dtsi
+++ b/arch/arm/boot/dts/omap3.dtsi
@@ -113,10 +113,22 @@
 				};
 
 				scm_conf: scm_conf@270 {
-					compatible = "syscon";
+					compatible = "syscon", "simple-bus";
 					reg = <0x270 0x330>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x270 0x330>;
+
+					pbias_regulator: pbias_regulator {
+						compatible = "ti,pbias-omap3", "ti,pbias-omap";
+						reg = <0x2b0 0x4>;
+						syscon = <&scm_conf>;
+						pbias_mmc_reg: pbias_mmc_omap2430 {
+							regulator-name = "pbias_mmc_omap2430";
+							regulator-min-microvolt = <1800000>;
+							regulator-max-microvolt = <3000000>;
+						};
+					};
 
 					scm_clocks: clocks {
 						#address-cells = <1>;
@@ -202,17 +214,6 @@
 			dma-requests = <96>;
 		};
 
-		pbias_regulator: pbias_regulator {
-			compatible = "ti,pbias-omap";
-			reg = <0x2b0 0x4>;
-			syscon = <&scm_conf>;
-			pbias_mmc_reg: pbias_mmc_omap2430 {
-				regulator-name = "pbias_mmc_omap2430";
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <3000000>;
-			};
-		};
-
 		gpio1: gpio@48310000 {
 			compatible = "ti,omap3-gpio";
 			reg = <0x48310000 0x200>;
diff --git a/arch/arm/boot/dts/omap4.dtsi b/arch/arm/boot/dts/omap4.dtsi
index abc4473e6f8a..5a206c100ce2 100644
--- a/arch/arm/boot/dts/omap4.dtsi
+++ b/arch/arm/boot/dts/omap4.dtsi
@@ -196,9 +196,10 @@
 					reg = <0x5a0 0x170>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x5a0 0x170>;
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-omap4", "ti,pbias-omap";
 						reg = <0x60 0x4>;
 						syscon = <&omap4_padconf_global>;
 						pbias_mmc_reg: pbias_mmc_omap4 {
diff --git a/arch/arm/boot/dts/omap5-uevm.dts b/arch/arm/boot/dts/omap5-uevm.dts
index 3cc8f357d5b8..3cb030f9d2c4 100644
--- a/arch/arm/boot/dts/omap5-uevm.dts
+++ b/arch/arm/boot/dts/omap5-uevm.dts
@@ -174,8 +174,8 @@
 
 	i2c5_pins: pinmux_i2c5_pins {
 		pinctrl-single,pins = <
-			0x184 (PIN_INPUT | MUX_MODE0)		/* i2c5_scl */
-			0x186 (PIN_INPUT | MUX_MODE0)		/* i2c5_sda */
+			0x186 (PIN_INPUT | MUX_MODE0)		/* i2c5_scl */
+			0x188 (PIN_INPUT | MUX_MODE0)		/* i2c5_sda */
 		>;
 	};
 
diff --git a/arch/arm/boot/dts/omap5.dtsi b/arch/arm/boot/dts/omap5.dtsi
index 4205a8ac9ddb..4c04389dab32 100644
--- a/arch/arm/boot/dts/omap5.dtsi
+++ b/arch/arm/boot/dts/omap5.dtsi
@@ -185,9 +185,10 @@
 					reg = <0x5a0 0xec>;
 					#address-cells = <1>;
 					#size-cells = <1>;
+					ranges = <0 0x5a0 0xec>;
 
 					pbias_regulator: pbias_regulator {
-						compatible = "ti,pbias-omap";
+						compatible = "ti,pbias-omap5", "ti,pbias-omap";
 						reg = <0x60 0x4>;
 						syscon = <&omap5_padconf_global>;
 						pbias_mmc_reg: pbias_mmc_omap5 {
diff --git a/arch/arm/boot/dts/rk3288-veyron.dtsi b/arch/arm/boot/dts/rk3288-veyron.dtsi
index 2fa7a0dc83f7..275c78ccc0f3 100644
--- a/arch/arm/boot/dts/rk3288-veyron.dtsi
+++ b/arch/arm/boot/dts/rk3288-veyron.dtsi
@@ -158,6 +158,7 @@
 };
 
 &hdmi {
+	ddc-i2c-bus = <&i2c5>;
 	status = "okay";
 };
 
diff --git a/arch/arm/boot/dts/stih407.dtsi b/arch/arm/boot/dts/stih407.dtsi
index 3efa3b2ebe90..6b914e4bb099 100644
--- a/arch/arm/boot/dts/stih407.dtsi
+++ b/arch/arm/boot/dts/stih407.dtsi
@@ -103,48 +103,46 @@
 							 <&clk_s_d0_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>;
-				ranges;
-
-				sti-hdmi@8d04000 {
-					compatible = "st,stih407-hdmi";
-					reg = <0x8d04000 0x1000>;
-					reg-names = "hdmi-reg";
-					interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
-					interrupt-names	= "irq";
-					clock-names = "pix",
-						      "tmds",
-						      "phy",
-						      "audio",
-						      "main_parent",
-						      "aux_parent";
-
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
-						 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
-						 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
-						 <&clk_s_d0_flexgen CLK_PCM_0>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-
-					hdmi,hpd-gpio = <&pio5 3>;
-					reset-names = "hdmi";
-					resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
-					ddc = <&hdmiddc>;
-
-				};
-
-				sti-hda@8d02000 {
-					compatible = "st,stih407-hda";
-					reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
-					reg-names = "hda-reg", "video-dacs-ctrl";
-					clock-names = "pix",
-						      "hddac",
-						      "main_parent",
-						      "aux_parent";
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
-						 <&clk_s_d2_flexgen CLK_HDDAC>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-				};
+			};
+
+			sti-hdmi@8d04000 {
+				compatible = "st,stih407-hdmi";
+				reg = <0x8d04000 0x1000>;
+				reg-names = "hdmi-reg";
+				interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
+				interrupt-names	= "irq";
+				clock-names = "pix",
+					      "tmds",
+					      "phy",
+					      "audio",
+					      "main_parent",
+					      "aux_parent";
+
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
+					 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
+					 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
+					 <&clk_s_d0_flexgen CLK_PCM_0>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
+
+				hdmi,hpd-gpio = <&pio5 3>;
+				reset-names = "hdmi";
+				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
+				ddc = <&hdmiddc>;
+			};
+
+			sti-hda@8d02000 {
+				compatible = "st,stih407-hda";
+				reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
+				reg-names = "hda-reg", "video-dacs-ctrl";
+				clock-names = "pix",
+					      "hddac",
+					      "main_parent",
+					      "aux_parent";
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
+					 <&clk_s_d2_flexgen CLK_HDDAC>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
 			};
 		};
 	};
diff --git a/arch/arm/boot/dts/stih410.dtsi b/arch/arm/boot/dts/stih410.dtsi
index 6f40bc99c22f..8c6e61a27234 100644
--- a/arch/arm/boot/dts/stih410.dtsi
+++ b/arch/arm/boot/dts/stih410.dtsi
@@ -178,48 +178,46 @@
 							 <&clk_s_d0_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>,
 							 <&clk_s_d2_quadfs 0>;
-				ranges;
-
-				sti-hdmi@8d04000 {
-					compatible = "st,stih407-hdmi";
-					reg = <0x8d04000 0x1000>;
-					reg-names = "hdmi-reg";
-					interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
-					interrupt-names	= "irq";
-					clock-names = "pix",
-						      "tmds",
-						      "phy",
-						      "audio",
-						      "main_parent",
-						      "aux_parent";
-
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
-						 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
-						 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
-						 <&clk_s_d0_flexgen CLK_PCM_0>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-
-					hdmi,hpd-gpio = <&pio5 3>;
-					reset-names = "hdmi";
-					resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
-					ddc = <&hdmiddc>;
-
-				};
-
-				sti-hda@8d02000 {
-					compatible = "st,stih407-hda";
-					reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
-					reg-names = "hda-reg", "video-dacs-ctrl";
-					clock-names = "pix",
-						      "hddac",
-						      "main_parent",
-						      "aux_parent";
-					clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
-						 <&clk_s_d2_flexgen CLK_HDDAC>,
-						 <&clk_s_d2_quadfs 0>,
-						 <&clk_s_d2_quadfs 1>;
-				};
+			};
+
+			sti-hdmi@8d04000 {
+				compatible = "st,stih407-hdmi";
+				reg = <0x8d04000 0x1000>;
+				reg-names = "hdmi-reg";
+				interrupts = <GIC_SPI 106 IRQ_TYPE_NONE>;
+				interrupt-names	= "irq";
+				clock-names = "pix",
+					      "tmds",
+					      "phy",
+					      "audio",
+					      "main_parent",
+					      "aux_parent";
+
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDMI>,
+					 <&clk_s_d2_flexgen CLK_TMDS_HDMI>,
+					 <&clk_s_d2_flexgen CLK_REF_HDMIPHY>,
+					 <&clk_s_d0_flexgen CLK_PCM_0>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
+
+				hdmi,hpd-gpio = <&pio5 3>;
+				reset-names = "hdmi";
+				resets = <&softreset STIH407_HDMI_TX_PHY_SOFTRESET>;
+				ddc = <&hdmiddc>;
+			};
+
+			sti-hda@8d02000 {
+				compatible = "st,stih407-hda";
+				reg = <0x8d02000 0x400>, <0x92b0120 0x4>;
+				reg-names = "hda-reg", "video-dacs-ctrl";
+				clock-names = "pix",
+					      "hddac",
+					      "main_parent",
+					      "aux_parent";
+				clocks = <&clk_s_d2_flexgen CLK_PIX_HDDAC>,
+					 <&clk_s_d2_flexgen CLK_HDDAC>,
+					 <&clk_s_d2_quadfs 0>,
+					 <&clk_s_d2_quadfs 1>;
 			};
 		};
 
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 50c84e1876fc..3f15a5cae167 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -240,7 +240,8 @@ CONFIG_SSI_PROTOCOL=m
 CONFIG_PINCTRL_SINGLE=y
 CONFIG_DEBUG_GPIO=y
 CONFIG_GPIO_SYSFS=y
-CONFIG_GPIO_PCF857X=m
+CONFIG_GPIO_PCA953X=m
+CONFIG_GPIO_PCF857X=y
 CONFIG_GPIO_TWL4030=y
 CONFIG_GPIO_PALMAS=y
 CONFIG_W1=m
@@ -350,6 +351,8 @@ CONFIG_USB_MUSB_HDRC=m
 CONFIG_USB_MUSB_OMAP2PLUS=m
 CONFIG_USB_MUSB_AM35X=m
 CONFIG_USB_MUSB_DSPS=m
+CONFIG_USB_INVENTRA_DMA=y
+CONFIG_USB_TI_CPPI41_DMA=y
 CONFIG_USB_DWC3=m
 CONFIG_USB_TEST=m
 CONFIG_AM335X_PHY_USB=y
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 32640c431a08..7cba573c2cc9 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -19,7 +19,7 @@
  * This may need to be greater than __NR_last_syscall+1 in order to
  * account for the padding in the syscall table
  */
-#define __NR_syscalls  (388)
+#define __NR_syscalls  (392)
 
 /*
  * *NOTE*: This is a ghost syscall private to the kernel.  Only the
diff --git a/arch/arm/include/uapi/asm/unistd.h b/arch/arm/include/uapi/asm/unistd.h
index 0c3f5a0dafd3..7a2a32a1d5a8 100644
--- a/arch/arm/include/uapi/asm/unistd.h
+++ b/arch/arm/include/uapi/asm/unistd.h
@@ -414,6 +414,8 @@
 #define __NR_memfd_create		(__NR_SYSCALL_BASE+385)
 #define __NR_bpf			(__NR_SYSCALL_BASE+386)
 #define __NR_execveat			(__NR_SYSCALL_BASE+387)
+#define __NR_userfaultfd		(__NR_SYSCALL_BASE+388)
+#define __NR_membarrier			(__NR_SYSCALL_BASE+389)
 
 /*
  * The following SWIs are ARM private.
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index 05745eb838c5..fde6c88d560c 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -397,6 +397,8 @@
 /* 385 */	CALL(sys_memfd_create)
 		CALL(sys_bpf)
 		CALL(sys_execveat)
+		CALL(sys_userfaultfd)
+		CALL(sys_membarrier)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/mach-omap2/Kconfig b/arch/arm/mach-omap2/Kconfig
index 07d2e100caab..b3a0dff67e3f 100644
--- a/arch/arm/mach-omap2/Kconfig
+++ b/arch/arm/mach-omap2/Kconfig
@@ -44,10 +44,11 @@ config SOC_OMAP5
 	select ARM_CPU_SUSPEND if PM
 	select ARM_GIC
 	select HAVE_ARM_SCU if SMP
-	select HAVE_ARM_TWD if SMP
 	select HAVE_ARM_ARCH_TIMER
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT
 	select OMAP_INTERCONNECT_BARRIER
+	select PM_OPP if PM
 
 config SOC_AM33XX
 	bool "TI AM33XX"
@@ -70,10 +71,13 @@ config SOC_DRA7XX
 	select ARCH_OMAP2PLUS
 	select ARM_CPU_SUSPEND if PM
 	select ARM_GIC
+	select HAVE_ARM_SCU if SMP
 	select HAVE_ARM_ARCH_TIMER
 	select IRQ_CROSSBAR
 	select ARM_ERRATA_798181 if SMP
+	select OMAP_INTERCONNECT
 	select OMAP_INTERCONNECT_BARRIER
+	select PM_OPP if PM
 
 config ARCH_OMAP2PLUS
 	bool
diff --git a/arch/arm/mach-omap2/board-generic.c b/arch/arm/mach-omap2/board-generic.c
index 24c9afc9e8a7..6133eaac685d 100644
--- a/arch/arm/mach-omap2/board-generic.c
+++ b/arch/arm/mach-omap2/board-generic.c
@@ -20,13 +20,6 @@
 
 #include "common.h"
 
-#if !(defined(CONFIG_ARCH_OMAP2) || defined(CONFIG_ARCH_OMAP3))
-#define intc_of_init	NULL
-#endif
-#ifndef CONFIG_ARCH_OMAP4
-#define gic_of_init		NULL
-#endif
-
 static const struct of_device_id omap_dt_match_table[] __initconst = {
 	{ .compatible = "simple-bus", },
 	{ .compatible = "ti,omap-infra", },
diff --git a/arch/arm/mach-omap2/id.c b/arch/arm/mach-omap2/id.c
index e3f713ffb06b..54a5ba54d2ff 100644
--- a/arch/arm/mach-omap2/id.c
+++ b/arch/arm/mach-omap2/id.c
@@ -653,8 +653,12 @@ void __init dra7xxx_check_revision(void)
 			omap_revision = DRA752_REV_ES1_0;
 			break;
 		case 1:
-		default:
 			omap_revision = DRA752_REV_ES1_1;
+			break;
+		case 2:
+		default:
+			omap_revision = DRA752_REV_ES2_0;
+			break;
 		}
 		break;
 
@@ -674,7 +678,7 @@ void __init dra7xxx_check_revision(void)
 		/* Unknown default to latest silicon rev as default*/
 		pr_warn("%s: unknown idcode=0x%08x (hawkeye=0x%08x,rev=0x%x)\n",
 			__func__, idcode, hawkeye, rev);
-		omap_revision = DRA752_REV_ES1_1;
+		omap_revision = DRA752_REV_ES2_0;
 	}
 
 	sprintf(soc_name, "DRA%03x", omap_rev() >> 16);
diff --git a/arch/arm/mach-omap2/io.c b/arch/arm/mach-omap2/io.c
index 980c9372e6fd..3eaeaca5da05 100644
--- a/arch/arm/mach-omap2/io.c
+++ b/arch/arm/mach-omap2/io.c
@@ -676,6 +676,7 @@ void __init am43xx_init_early(void)
 void __init am43xx_init_late(void)
 {
 	omap_common_late_init();
+	omap2_clk_enable_autoidle_all();
 }
 #endif
 
diff --git a/arch/arm/mach-omap2/omap_device.c b/arch/arm/mach-omap2/omap_device.c
index 4cb8fd9f741f..72ebc4c16bae 100644
--- a/arch/arm/mach-omap2/omap_device.c
+++ b/arch/arm/mach-omap2/omap_device.c
@@ -901,7 +901,8 @@ static int __init omap_device_late_idle(struct device *dev, void *data)
 		if (od->hwmods[i]->flags & HWMOD_INIT_NO_IDLE)
 			return 0;
 
-	if (od->_driver_status != BUS_NOTIFY_BOUND_DRIVER) {
+	if (od->_driver_status != BUS_NOTIFY_BOUND_DRIVER &&
+	    od->_driver_status != BUS_NOTIFY_BIND_DRIVER) {
 		if (od->_state == OMAP_DEVICE_STATE_ENABLED) {
 			dev_warn(dev, "%s: enabled but no driver.  Idling\n",
 				 __func__);
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 425bfcd67db6..b668719b9b25 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -103,7 +103,8 @@ static inline void enable_omap3630_toggle_l2_on_restore(void) { }
 #define PM_OMAP4_ROM_SMP_BOOT_ERRATUM_GICD	(1 << 0)
 #define PM_OMAP4_CPU_OSWR_DISABLE		(1 << 1)
 
-#if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP4)
+#if defined(CONFIG_PM) && (defined(CONFIG_ARCH_OMAP4) ||\
+	   defined(CONFIG_SOC_OMAP5) || defined(CONFIG_SOC_DRA7XX))
 extern u16 pm44xx_errata;
 #define IS_PM44XX_ERRATUM(id)		(pm44xx_errata & (id))
 #else
diff --git a/arch/arm/mach-omap2/soc.h b/arch/arm/mach-omap2/soc.h
index f97654d11ea5..2d1d3845253c 100644
--- a/arch/arm/mach-omap2/soc.h
+++ b/arch/arm/mach-omap2/soc.h
@@ -469,6 +469,8 @@ IS_OMAP_TYPE(3430, 0x3430)
 #define DRA7XX_CLASS		0x07000000
 #define DRA752_REV_ES1_0	(DRA7XX_CLASS | (0x52 << 16) | (0x10 << 8))
 #define DRA752_REV_ES1_1	(DRA7XX_CLASS | (0x52 << 16) | (0x11 << 8))
+#define DRA752_REV_ES2_0	(DRA7XX_CLASS | (0x52 << 16) | (0x20 << 8))
+#define DRA722_REV_ES1_0	(DRA7XX_CLASS | (0x22 << 16) | (0x10 << 8))
 #define DRA722_REV_ES1_0	(DRA7XX_CLASS | (0x22 << 16) | (0x10 << 8))
 
 void omap2xxx_check_revision(void);
diff --git a/arch/arm/mach-omap2/timer.c b/arch/arm/mach-omap2/timer.c
index e4d8701f99f9..a55655127ef2 100644
--- a/arch/arm/mach-omap2/timer.c
+++ b/arch/arm/mach-omap2/timer.c
@@ -297,12 +297,8 @@ static int __init omap_dm_timer_init_one(struct omap_dm_timer *timer,
 	if (IS_ERR(src))
 		return PTR_ERR(src);
 
-	r = clk_set_parent(timer->fclk, src);
-	if (r < 0) {
-		pr_warn("%s: %s cannot set source\n", __func__, oh->name);
-		clk_put(src);
-		return r;
-	}
+	WARN(clk_set_parent(timer->fclk, src) < 0,
+	     "Cannot set timer parent clock, no PLL clock driver?");
 
 	clk_put(src);
 
diff --git a/arch/arm/mach-omap2/vc.c b/arch/arm/mach-omap2/vc.c
index e5a35f6b83a7..d44d311704ba 100644
--- a/arch/arm/mach-omap2/vc.c
+++ b/arch/arm/mach-omap2/vc.c
@@ -300,7 +300,7 @@ static void __init omap3_vc_init_pmic_signaling(struct voltagedomain *voltdm)
 
 	val = voltdm->read(OMAP3_PRM_POLCTRL_OFFSET);
 	if (!(val & OMAP3430_PRM_POLCTRL_CLKREQ_POL) ||
-	    (val & OMAP3430_PRM_POLCTRL_CLKREQ_POL)) {
+	    (val & OMAP3430_PRM_POLCTRL_OFFMODE_POL)) {
 		val |= OMAP3430_PRM_POLCTRL_CLKREQ_POL;
 		val &= ~OMAP3430_PRM_POLCTRL_OFFMODE_POL;
 		pr_debug("PM: fixing sys_clkreq and sys_off_mode polarity to 0x%x\n",
diff --git a/arch/arm/mach-pxa/balloon3.c b/arch/arm/mach-pxa/balloon3.c
index a3ebb517cca1..a727282bfa99 100644
--- a/arch/arm/mach-pxa/balloon3.c
+++ b/arch/arm/mach-pxa/balloon3.c
@@ -502,7 +502,7 @@ static void balloon3_irq_handler(struct irq_desc *desc)
 					balloon3_irq_enabled;
 	do {
 		struct irq_data *d = irq_desc_get_irq_data(desc);
-		struct irq_chip *chip = irq_data_get_chip(d);
+		struct irq_chip *chip = irq_desc_get_chip(desc);
 		unsigned int irq;
 
 		/* clear useless edge notification */
diff --git a/arch/arm/mach-pxa/include/mach/addr-map.h b/arch/arm/mach-pxa/include/mach/addr-map.h
index d28fe291233a..07b93fd24474 100644
--- a/arch/arm/mach-pxa/include/mach/addr-map.h
+++ b/arch/arm/mach-pxa/include/mach/addr-map.h
@@ -44,6 +44,13 @@
  */
 
 /*
+ * DFI Bus for NAND, PXA3xx only
+ */
+#define NAND_PHYS		0x43100000
+#define NAND_VIRT		IOMEM(0xf6300000)
+#define NAND_SIZE		0x00100000
+
+/*
  * Internal Memory Controller (PXA27x and later)
  */
 #define IMEMC_PHYS		0x58000000
diff --git a/arch/arm/mach-pxa/pxa3xx.c b/arch/arm/mach-pxa/pxa3xx.c
index ce0f8d6242e2..06005d3f2ba3 100644
--- a/arch/arm/mach-pxa/pxa3xx.c
+++ b/arch/arm/mach-pxa/pxa3xx.c
@@ -47,6 +47,13 @@ extern void __init pxa_dt_irq_init(int (*fn)(struct irq_data *, unsigned int));
 #define ISRAM_START	0x5c000000
 #define ISRAM_SIZE	SZ_256K
 
+/*
+ * NAND NFC: DFI bus arbitration subset
+ */
+#define NDCR			(*(volatile u32 __iomem*)(NAND_VIRT + 0))
+#define NDCR_ND_ARB_EN		(1 << 12)
+#define NDCR_ND_ARB_CNTL	(1 << 19)
+
 static void __iomem *sram;
 static unsigned long wakeup_src;
 
@@ -362,7 +369,12 @@ static struct map_desc pxa3xx_io_desc[] __initdata = {
 		.pfn		= __phys_to_pfn(PXA3XX_SMEMC_BASE),
 		.length		= SMEMC_SIZE,
 		.type		= MT_DEVICE
-	}
+	}, {
+		.virtual	= (unsigned long)NAND_VIRT,
+		.pfn		= __phys_to_pfn(NAND_PHYS),
+		.length		= NAND_SIZE,
+		.type		= MT_DEVICE
+	},
 };
 
 void __init pxa3xx_map_io(void)
@@ -419,6 +431,13 @@ static int __init pxa3xx_init(void)
 		 */
 		ASCR &= ~(ASCR_RDH | ASCR_D1S | ASCR_D2S | ASCR_D3S);
 
+		/*
+		 * Disable DFI bus arbitration, to prevent a system bus lock if
+		 * somebody disables the NAND clock (unused clock) while this
+		 * bit remains set.
+		 */
+		NDCR = (NDCR & ~NDCR_ND_ARB_EN) | NDCR_ND_ARB_CNTL;
+
 		if ((ret = pxa_init_dma(IRQ_DMA, 32)))
 			return ret;
 
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index 9769f1eefe3b..00b7f7de28a1 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -365,15 +365,21 @@ do_alignment_ldrhstrh(unsigned long addr, unsigned long instr, struct pt_regs *r
  user:
 	if (LDST_L_BIT(instr)) {
 		unsigned long val;
+		unsigned int __ua_flags = uaccess_save_and_enable();
+
 		get16t_unaligned_check(val, addr);
+		uaccess_restore(__ua_flags);
 
 		/* signed half-word? */
 		if (instr & 0x40)
 			val = (signed long)((signed short) val);
 
 		regs->uregs[rd] = val;
-	} else
+	} else {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		put16t_unaligned_check(regs->uregs[rd], addr);
+		uaccess_restore(__ua_flags);
+	}
 
 	return TYPE_LDST;
 
@@ -420,14 +426,21 @@ do_alignment_ldrdstrd(unsigned long addr, unsigned long instr,
 
  user:
 	if (load) {
-		unsigned long val;
+		unsigned long val, val2;
+		unsigned int __ua_flags = uaccess_save_and_enable();
+
 		get32t_unaligned_check(val, addr);
+		get32t_unaligned_check(val2, addr + 4);
+
+		uaccess_restore(__ua_flags);
+
 		regs->uregs[rd] = val;
-		get32t_unaligned_check(val, addr + 4);
-		regs->uregs[rd2] = val;
+		regs->uregs[rd2] = val2;
 	} else {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		put32t_unaligned_check(regs->uregs[rd], addr);
 		put32t_unaligned_check(regs->uregs[rd2], addr + 4);
+		uaccess_restore(__ua_flags);
 	}
 
 	return TYPE_LDST;
@@ -458,10 +471,15 @@ do_alignment_ldrstr(unsigned long addr, unsigned long instr, struct pt_regs *reg
  trans:
 	if (LDST_L_BIT(instr)) {
 		unsigned int val;
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		get32t_unaligned_check(val, addr);
+		uaccess_restore(__ua_flags);
 		regs->uregs[rd] = val;
-	} else
+	} else {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		put32t_unaligned_check(regs->uregs[rd], addr);
+		uaccess_restore(__ua_flags);
+	}
 	return TYPE_LDST;
 
  fault:
@@ -531,6 +549,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
 #endif
 
 	if (user_mode(regs)) {
+		unsigned int __ua_flags = uaccess_save_and_enable();
 		for (regbits = REGMASK_BITS(instr), rd = 0; regbits;
 		     regbits >>= 1, rd += 1)
 			if (regbits & 1) {
@@ -542,6 +561,7 @@ do_alignment_ldmstm(unsigned long addr, unsigned long instr, struct pt_regs *reg
 					put32t_unaligned_check(regs->uregs[rd], eaddr);
 				eaddr += 4;
 			}
+		uaccess_restore(__ua_flags);
 	} else {
 		for (regbits = REGMASK_BITS(instr), rd = 0; regbits;
 		     regbits >>= 1, rd += 1)
diff --git a/arch/arm/plat-pxa/ssp.c b/arch/arm/plat-pxa/ssp.c
index ad9529cc4203..daa1a65f2eb7 100644
--- a/arch/arm/plat-pxa/ssp.c
+++ b/arch/arm/plat-pxa/ssp.c
@@ -107,7 +107,6 @@ static const struct of_device_id pxa_ssp_of_ids[] = {
 	{ .compatible = "mvrl,pxa168-ssp",	.data = (void *) PXA168_SSP },
 	{ .compatible = "mrvl,pxa910-ssp",	.data = (void *) PXA910_SSP },
 	{ .compatible = "mrvl,ce4100-ssp",	.data = (void *) CE4100_SSP },
-	{ .compatible = "mrvl,lpss-ssp",	.data = (void *) LPSS_SSP },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, pxa_ssp_of_ids);
diff --git a/arch/mips/ath79/irq.c b/arch/mips/ath79/irq.c
index 15ecb4831e12..eeb3953ed8ac 100644
--- a/arch/mips/ath79/irq.c
+++ b/arch/mips/ath79/irq.c
@@ -293,8 +293,26 @@ static int __init ath79_misc_intc_of_init(
 
 	return 0;
 }
-IRQCHIP_DECLARE(ath79_misc_intc, "qca,ar7100-misc-intc",
-		ath79_misc_intc_of_init);
+
+static int __init ar7100_misc_intc_of_init(
+	struct device_node *node, struct device_node *parent)
+{
+	ath79_misc_irq_chip.irq_mask_ack = ar71xx_misc_irq_mask;
+	return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7100_misc_intc, "qca,ar7100-misc-intc",
+		ar7100_misc_intc_of_init);
+
+static int __init ar7240_misc_intc_of_init(
+	struct device_node *node, struct device_node *parent)
+{
+	ath79_misc_irq_chip.irq_ack = ar724x_misc_irq_ack;
+	return ath79_misc_intc_of_init(node, parent);
+}
+
+IRQCHIP_DECLARE(ar7240_misc_intc, "qca,ar7240-misc-intc",
+		ar7240_misc_intc_of_init);
 
 static int __init ar79_cpu_intc_of_init(
 	struct device_node *node, struct device_node *parent)
diff --git a/arch/mips/include/asm/cpu-features.h b/arch/mips/include/asm/cpu-features.h
index 9801ac982655..fe67f12ac239 100644
--- a/arch/mips/include/asm/cpu-features.h
+++ b/arch/mips/include/asm/cpu-features.h
@@ -20,6 +20,9 @@
 #ifndef cpu_has_tlb
 #define cpu_has_tlb		(cpu_data[0].options & MIPS_CPU_TLB)
 #endif
+#ifndef cpu_has_ftlb
+#define cpu_has_ftlb		(cpu_data[0].options & MIPS_CPU_FTLB)
+#endif
 #ifndef cpu_has_tlbinv
 #define cpu_has_tlbinv		(cpu_data[0].options & MIPS_CPU_TLBINV)
 #endif
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index cd89e9855775..82ad15f11049 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -385,6 +385,7 @@ enum cpu_type_enum {
 #define MIPS_CPU_CDMM		0x4000000000ull	/* CPU has Common Device Memory Map */
 #define MIPS_CPU_BP_GHIST	0x8000000000ull /* R12K+ Branch Prediction Global History */
 #define MIPS_CPU_SP		0x10000000000ull /* Small (1KB) page support */
+#define MIPS_CPU_FTLB		0x20000000000ull /* CPU has Fixed-page-size TLB */
 
 /*
  * CPU ASE encodings
diff --git a/arch/mips/include/asm/maar.h b/arch/mips/include/asm/maar.h
index b02891f9caaf..21d9607c80d7 100644
--- a/arch/mips/include/asm/maar.h
+++ b/arch/mips/include/asm/maar.h
@@ -66,6 +66,15 @@ static inline void write_maar_pair(unsigned idx, phys_addr_t lower,
 }
 
 /**
+ * maar_init() - initialise MAARs
+ *
+ * Performs initialisation of MAARs for the current CPU, making use of the
+ * platforms implementation of platform_maar_init where necessary and
+ * duplicating the setup it provides on secondary CPUs.
+ */
+extern void maar_init(void);
+
+/**
  * struct maar_config - MAAR configuration data
  * @lower:	The lowest address that the MAAR pair will affect. Must be
  *		aligned to a 2^16 byte boundary.
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index d75b75e78ebb..1f1927ab4269 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -194,6 +194,7 @@ BUILD_CM_RW(reg3_mask,		MIPS_CM_GCB_OFS + 0xc8)
 BUILD_CM_R_(gic_status,		MIPS_CM_GCB_OFS + 0xd0)
 BUILD_CM_R_(cpc_status,		MIPS_CM_GCB_OFS + 0xf0)
 BUILD_CM_RW(l2_config,		MIPS_CM_GCB_OFS + 0x130)
+BUILD_CM_RW(sys_config2,	MIPS_CM_GCB_OFS + 0x150)
 
 /* Core Local & Core Other register accessor functions */
 BUILD_CM_Cx_RW(reset_release,	0x00)
@@ -316,6 +317,10 @@ BUILD_CM_Cx_R_(tcid_8_priority,	0x80)
 #define CM_GCR_L2_CONFIG_ASSOC_SHF		0
 #define CM_GCR_L2_CONFIG_ASSOC_MSK		(_ULCAST_(0xff) << 0)
 
+/* GCR_SYS_CONFIG2 register fields */
+#define CM_GCR_SYS_CONFIG2_MAXVPW_SHF		0
+#define CM_GCR_SYS_CONFIG2_MAXVPW_MSK		(_ULCAST_(0xf) << 0)
+
 /* GCR_Cx_COHERENCE register fields */
 #define CM_GCR_Cx_COHERENCE_COHDOMAINEN_SHF	0
 #define CM_GCR_Cx_COHERENCE_COHDOMAINEN_MSK	(_ULCAST_(0xff) << 0)
@@ -405,4 +410,38 @@ static inline int mips_cm_revision(void)
 	return read_gcr_rev();
 }
 
+/**
+ * mips_cm_max_vp_width() - return the width in bits of VP indices
+ *
+ * Return: the width, in bits, of VP indices in fields that combine core & VP
+ * indices.
+ */
+static inline unsigned int mips_cm_max_vp_width(void)
+{
+	extern int smp_num_siblings;
+
+	if (mips_cm_revision() >= CM_REV_CM3)
+		return read_gcr_sys_config2() & CM_GCR_SYS_CONFIG2_MAXVPW_MSK;
+
+	return smp_num_siblings;
+}
+
+/**
+ * mips_cm_vp_id() - calculate the hardware VP ID for a CPU
+ * @cpu: the CPU whose VP ID to calculate
+ *
+ * Hardware such as the GIC uses identifiers for VPs which may not match the
+ * CPU numbers used by Linux. This function calculates the hardware VP
+ * identifier corresponding to a given CPU.
+ *
+ * Return: the VP ID for the CPU.
+ */
+static inline unsigned int mips_cm_vp_id(unsigned int cpu)
+{
+	unsigned int core = cpu_data[cpu].core;
+	unsigned int vp = cpu_vpe_id(&cpu_data[cpu]);
+
+	return (core * mips_cm_max_vp_width()) + vp;
+}
+
 #endif /* __MIPS_ASM_MIPS_CM_H__ */
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index d3cd8eac81e3..c64781cf649f 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -487,6 +487,8 @@
 
 /* Bits specific to the MIPS32/64 PRA.	*/
 #define MIPS_CONF_MT		(_ULCAST_(7) <<	 7)
+#define MIPS_CONF_MT_TLB	(_ULCAST_(1) <<  7)
+#define MIPS_CONF_MT_FTLB	(_ULCAST_(4) <<  7)
 #define MIPS_CONF_AR		(_ULCAST_(7) << 10)
 #define MIPS_CONF_AT		(_ULCAST_(3) << 13)
 #define MIPS_CONF_M		(_ULCAST_(1) << 31)
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 571a8e6ea5bd..09a51d091941 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -410,16 +410,18 @@ static int set_ftlb_enable(struct cpuinfo_mips *c, int enable)
 static inline unsigned int decode_config0(struct cpuinfo_mips *c)
 {
 	unsigned int config0;
-	int isa;
+	int isa, mt;
 
 	config0 = read_c0_config();
 
 	/*
 	 * Look for Standard TLB or Dual VTLB and FTLB
 	 */
-	if ((((config0 & MIPS_CONF_MT) >> 7) == 1) ||
-	    (((config0 & MIPS_CONF_MT) >> 7) == 4))
+	mt = config0 & MIPS_CONF_MT;
+	if (mt == MIPS_CONF_MT_TLB)
 		c->options |= MIPS_CPU_TLB;
+	else if (mt == MIPS_CONF_MT_FTLB)
+		c->options |= MIPS_CPU_TLB | MIPS_CPU_FTLB;
 
 	isa = (config0 & MIPS_CONF_AT) >> 13;
 	switch (isa) {
@@ -559,15 +561,18 @@ static inline unsigned int decode_config4(struct cpuinfo_mips *c)
 	if (cpu_has_tlb) {
 		if (((config4 & MIPS_CONF4_IE) >> 29) == 2)
 			c->options |= MIPS_CPU_TLBINV;
+
 		/*
-		 * This is a bit ugly. R6 has dropped that field from
-		 * config4 and the only valid configuration is VTLB+FTLB so
-		 * set a good value for mmuextdef for that case.
+		 * R6 has dropped the MMUExtDef field from config4.
+		 * On R6 the fields always describe the FTLB, and only if it is
+		 * present according to Config.MT.
 		 */
-		if (cpu_has_mips_r6)
+		if (!cpu_has_mips_r6)
+			mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+		else if (cpu_has_ftlb)
 			mmuextdef = MIPS_CONF4_MMUEXTDEF_VTLBSIZEEXT;
 		else
-			mmuextdef = config4 & MIPS_CONF4_MMUEXTDEF;
+			mmuextdef = 0;
 
 		switch (mmuextdef) {
 		case MIPS_CONF4_MMUEXTDEF_MMUSIZEEXT:
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index 35b8316002f8..479515109e5b 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -338,7 +338,7 @@ static void __init bootmem_init(void)
 		if (end <= reserved_end)
 			continue;
 #ifdef CONFIG_BLK_DEV_INITRD
-		/* mapstart should be after initrd_end */
+		/* Skip zones before initrd and initrd itself */
 		if (initrd_end && end <= (unsigned long)PFN_UP(__pa(initrd_end)))
 			continue;
 #endif
@@ -371,6 +371,14 @@ static void __init bootmem_init(void)
 		max_low_pfn = PFN_DOWN(HIGHMEM_START);
 	}
 
+#ifdef CONFIG_BLK_DEV_INITRD
+	/*
+	 * mapstart should be after initrd_end
+	 */
+	if (initrd_end)
+		mapstart = max(mapstart, (unsigned long)PFN_UP(__pa(initrd_end)));
+#endif
+
 	/*
 	 * Initialize the boot-time allocator with low memory only.
 	 */
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index a31896c33716..bd4385a8e6e8 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -42,6 +42,7 @@
 #include <asm/mmu_context.h>
 #include <asm/time.h>
 #include <asm/setup.h>
+#include <asm/maar.h>
 
 cpumask_t cpu_callin_map;		/* Bitmask of started secondaries */
 
@@ -157,6 +158,7 @@ asmlinkage void start_secondary(void)
 	mips_clockevent_init();
 	mp_ops->init_secondary();
 	cpu_report();
+	maar_init();
 
 	/*
 	 * XXX parity protection should be folded in here when it's converted
diff --git a/arch/mips/loongson64/common/env.c b/arch/mips/loongson64/common/env.c
index f6c44dd332e2..d6d07ad56180 100644
--- a/arch/mips/loongson64/common/env.c
+++ b/arch/mips/loongson64/common/env.c
@@ -64,6 +64,9 @@ void __init prom_init_env(void)
 	}
 	if (memsize == 0)
 		memsize = 256;
+
+	loongson_sysconf.nr_uarts = 1;
+
 	pr_info("memsize=%u, highmemsize=%u\n", memsize, highmemsize);
 #else
 	struct boot_params *boot_p;
diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c
index 66d0f49c5bec..8770e619185e 100644
--- a/arch/mips/mm/init.c
+++ b/arch/mips/mm/init.c
@@ -44,6 +44,7 @@
 #include <asm/pgalloc.h>
 #include <asm/tlb.h>
 #include <asm/fixmap.h>
+#include <asm/maar.h>
 
 /*
  * We have up to 8 empty zeroed pages so we can map one of the right colour
@@ -252,6 +253,119 @@ void __init fixrange_init(unsigned long start, unsigned long end,
 #endif
 }
 
+unsigned __weak platform_maar_init(unsigned num_pairs)
+{
+	struct maar_config cfg[BOOT_MEM_MAP_MAX];
+	unsigned i, num_configured, num_cfg = 0;
+	phys_addr_t skip;
+
+	for (i = 0; i < boot_mem_map.nr_map; i++) {
+		switch (boot_mem_map.map[i].type) {
+		case BOOT_MEM_RAM:
+		case BOOT_MEM_INIT_RAM:
+			break;
+		default:
+			continue;
+		}
+
+		skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
+
+		cfg[num_cfg].lower = boot_mem_map.map[i].addr;
+		cfg[num_cfg].lower += skip;
+
+		cfg[num_cfg].upper = cfg[num_cfg].lower;
+		cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
+		cfg[num_cfg].upper -= skip;
+
+		cfg[num_cfg].attrs = MIPS_MAAR_S;
+		num_cfg++;
+	}
+
+	num_configured = maar_config(cfg, num_cfg, num_pairs);
+	if (num_configured < num_cfg)
+		pr_warn("Not enough MAAR pairs (%u) for all bootmem regions (%u)\n",
+			num_pairs, num_cfg);
+
+	return num_configured;
+}
+
+void maar_init(void)
+{
+	unsigned num_maars, used, i;
+	phys_addr_t lower, upper, attr;
+	static struct {
+		struct maar_config cfgs[3];
+		unsigned used;
+	} recorded = { { { 0 } }, 0 };
+
+	if (!cpu_has_maar)
+		return;
+
+	/* Detect the number of MAARs */
+	write_c0_maari(~0);
+	back_to_back_c0_hazard();
+	num_maars = read_c0_maari() + 1;
+
+	/* MAARs should be in pairs */
+	WARN_ON(num_maars % 2);
+
+	/* Set MAARs using values we recorded already */
+	if (recorded.used) {
+		used = maar_config(recorded.cfgs, recorded.used, num_maars / 2);
+		BUG_ON(used != recorded.used);
+	} else {
+		/* Configure the required MAARs */
+		used = platform_maar_init(num_maars / 2);
+	}
+
+	/* Disable any further MAARs */
+	for (i = (used * 2); i < num_maars; i++) {
+		write_c0_maari(i);
+		back_to_back_c0_hazard();
+		write_c0_maar(0);
+		back_to_back_c0_hazard();
+	}
+
+	if (recorded.used)
+		return;
+
+	pr_info("MAAR configuration:\n");
+	for (i = 0; i < num_maars; i += 2) {
+		write_c0_maari(i);
+		back_to_back_c0_hazard();
+		upper = read_c0_maar();
+
+		write_c0_maari(i + 1);
+		back_to_back_c0_hazard();
+		lower = read_c0_maar();
+
+		attr = lower & upper;
+		lower = (lower & MIPS_MAAR_ADDR) << 4;
+		upper = ((upper & MIPS_MAAR_ADDR) << 4) | 0xffff;
+
+		pr_info("  [%d]: ", i / 2);
+		if (!(attr & MIPS_MAAR_V)) {
+			pr_cont("disabled\n");
+			continue;
+		}
+
+		pr_cont("%pa-%pa", &lower, &upper);
+
+		if (attr & MIPS_MAAR_S)
+			pr_cont(" speculate");
+
+		pr_cont("\n");
+
+		/* Record the setup for use on secondary CPUs */
+		if (used <= ARRAY_SIZE(recorded.cfgs)) {
+			recorded.cfgs[recorded.used].lower = lower;
+			recorded.cfgs[recorded.used].upper = upper;
+			recorded.cfgs[recorded.used].attrs = attr;
+			recorded.used++;
+		}
+	}
+}
+
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 int page_is_ram(unsigned long pagenr)
 {
@@ -334,69 +448,6 @@ static inline void mem_init_free_highmem(void)
 #endif
 }
 
-unsigned __weak platform_maar_init(unsigned num_pairs)
-{
-	struct maar_config cfg[BOOT_MEM_MAP_MAX];
-	unsigned i, num_configured, num_cfg = 0;
-	phys_addr_t skip;
-
-	for (i = 0; i < boot_mem_map.nr_map; i++) {
-		switch (boot_mem_map.map[i].type) {
-		case BOOT_MEM_RAM:
-		case BOOT_MEM_INIT_RAM:
-			break;
-		default:
-			continue;
-		}
-
-		skip = 0x10000 - (boot_mem_map.map[i].addr & 0xffff);
-
-		cfg[num_cfg].lower = boot_mem_map.map[i].addr;
-		cfg[num_cfg].lower += skip;
-
-		cfg[num_cfg].upper = cfg[num_cfg].lower;
-		cfg[num_cfg].upper += boot_mem_map.map[i].size - 1;
-		cfg[num_cfg].upper -= skip;
-
-		cfg[num_cfg].attrs = MIPS_MAAR_S;
-		num_cfg++;
-	}
-
-	num_configured = maar_config(cfg, num_cfg, num_pairs);
-	if (num_configured < num_cfg)
-		pr_warn("Not enough MAAR pairs (%u) for all bootmem regions (%u)\n",
-			num_pairs, num_cfg);
-
-	return num_configured;
-}
-
-static void maar_init(void)
-{
-	unsigned num_maars, used, i;
-
-	if (!cpu_has_maar)
-		return;
-
-	/* Detect the number of MAARs */
-	write_c0_maari(~0);
-	back_to_back_c0_hazard();
-	num_maars = read_c0_maari() + 1;
-
-	/* MAARs should be in pairs */
-	WARN_ON(num_maars % 2);
-
-	/* Configure the required MAARs */
-	used = platform_maar_init(num_maars / 2);
-
-	/* Disable any further MAARs */
-	for (i = (used * 2); i < num_maars; i++) {
-		write_c0_maari(i);
-		back_to_back_c0_hazard();
-		write_c0_maar(0);
-		back_to_back_c0_hazard();
-	}
-}
-
 void __init mem_init(void)
 {
 #ifdef CONFIG_HIGHMEM
diff --git a/arch/mips/net/bpf_jit_asm.S b/arch/mips/net/bpf_jit_asm.S
index e92726099be0..dabf4179cd7e 100644
--- a/arch/mips/net/bpf_jit_asm.S
+++ b/arch/mips/net/bpf_jit_asm.S
@@ -64,8 +64,20 @@ sk_load_word_positive:
 	PTR_ADDU t1, $r_skb_data, offset
 	lw	$r_A, 0(t1)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	wsbh	t0, $r_A
 	rotr	$r_A, t0, 16
+# else
+	sll	t0, $r_A, 24
+	srl	t1, $r_A, 24
+	srl	t2, $r_A, 8
+	or	t0, t0, t1
+	andi	t2, t2, 0xff00
+	andi	t1, $r_A, 0xff00
+	or	t0, t0, t2
+	sll	t1, t1, 8
+	or	$r_A, t0, t1
+# endif
 #endif
 	jr	$r_ra
 	 move	$r_ret, zero
@@ -80,8 +92,16 @@ sk_load_half_positive:
 	PTR_ADDU t1, $r_skb_data, offset
 	lh	$r_A, 0(t1)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	wsbh	t0, $r_A
 	seh	$r_A, t0
+# else
+	sll	t0, $r_A, 24
+	andi	t1, $r_A, 0xff00
+	sra	t0, t0, 16
+	srl	t1, t1, 8
+	or	$r_A, t0, t1
+# endif
 #endif
 	jr	$r_ra
 	 move	$r_ret, zero
@@ -148,23 +168,47 @@ sk_load_byte_positive:
 NESTED(bpf_slow_path_word, (6 * SZREG), $r_sp)
 	bpf_slow_path_common(4)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	wsbh	t0, $r_s0
 	jr	$r_ra
 	 rotr	$r_A, t0, 16
-#endif
+# else
+	sll	t0, $r_s0, 24
+	srl	t1, $r_s0, 24
+	srl	t2, $r_s0, 8
+	or	t0, t0, t1
+	andi	t2, t2, 0xff00
+	andi	t1, $r_s0, 0xff00
+	or	t0, t0, t2
+	sll	t1, t1, 8
+	jr	$r_ra
+	 or	$r_A, t0, t1
+# endif
+#else
 	jr	$r_ra
-	move	$r_A, $r_s0
+	 move	$r_A, $r_s0
+#endif
 
 	END(bpf_slow_path_word)
 
 NESTED(bpf_slow_path_half, (6 * SZREG), $r_sp)
 	bpf_slow_path_common(2)
 #ifdef CONFIG_CPU_LITTLE_ENDIAN
+# if defined(__mips_isa_rev) && (__mips_isa_rev >= 2)
 	jr	$r_ra
 	 wsbh	$r_A, $r_s0
-#endif
+# else
+	sll	t0, $r_s0, 8
+	andi	t1, $r_s0, 0xff00
+	andi	t0, t0, 0xff00
+	srl	t1, t1, 8
+	jr	$r_ra
+	 or	$r_A, t0, t1
+# endif
+#else
 	jr	$r_ra
 	 move	$r_A, $r_s0
+#endif
 
 	END(bpf_slow_path_half)
 
diff --git a/arch/tile/kernel/usb.c b/arch/tile/kernel/usb.c
index f0da5a237e94..9f1e05e12255 100644
--- a/arch/tile/kernel/usb.c
+++ b/arch/tile/kernel/usb.c
@@ -22,6 +22,7 @@
 #include <linux/platform_device.h>
 #include <linux/usb/tilegx.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/types.h>
 
 static u64 ehci_dmamask = DMA_BIT_MASK(32);
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index d3033183ed70..055a01de7c8d 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1128,7 +1128,18 @@ END(error_exit)
 
 /* Runs on exception stack */
 ENTRY(nmi)
+	/*
+	 * Fix up the exception frame if we're on Xen.
+	 * PARAVIRT_ADJUST_EXCEPTION_FRAME is guaranteed to push at most
+	 * one value to the stack on native, so it may clobber the rdx
+	 * scratch slot, but it won't clobber any of the important
+	 * slots past it.
+	 *
+	 * Xen is a different story, because the Xen frame itself overlaps
+	 * the "NMI executing" variable.
+	 */
 	PARAVIRT_ADJUST_EXCEPTION_FRAME
+
 	/*
 	 * We allow breakpoints in NMIs. If a breakpoint occurs, then
 	 * the iretq it performs will take us out of NMI context.
@@ -1179,9 +1190,12 @@ ENTRY(nmi)
 	 * we don't want to enable interrupts, because then we'll end
 	 * up in an awkward situation in which IRQs are on but NMIs
 	 * are off.
+	 *
+	 * We also must not push anything to the stack before switching
+	 * stacks lest we corrupt the "NMI executing" variable.
 	 */
 
-	SWAPGS
+	SWAPGS_UNSAFE_STACK
 	cld
 	movq	%rsp, %rdx
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index ab5f1d447ef9..ae68be92f755 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -86,6 +86,7 @@ extern u64 asmlinkage efi_call(void *fp, ...);
 extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 					u32 type, u64 attribute);
 
+#ifdef CONFIG_KASAN
 /*
  * 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
@@ -95,6 +96,7 @@ extern void __iomem *__init efi_ioremap(unsigned long addr, unsigned long size,
 #undef memcpy
 #undef memset
 #undef memmove
+#endif
 
 #endif /* CONFIG_X86_32 */
 
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index b98b471a3b7e..b8c14bb7fc8f 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -141,6 +141,8 @@
 #define DEBUGCTLMSR_BTS_OFF_USR		(1UL << 10)
 #define DEBUGCTLMSR_FREEZE_LBRS_ON_PMI	(1UL << 11)
 
+#define MSR_PEBS_FRONTEND		0x000003f7
+
 #define MSR_IA32_POWER_CTL		0x000001fc
 
 #define MSR_IA32_MC0_CTL		0x00000400
diff --git a/arch/x86/include/asm/pvclock-abi.h b/arch/x86/include/asm/pvclock-abi.h
index 655e07a48f6c..67f08230103a 100644
--- a/arch/x86/include/asm/pvclock-abi.h
+++ b/arch/x86/include/asm/pvclock-abi.h
@@ -41,6 +41,7 @@ struct pvclock_wall_clock {
 
 #define PVCLOCK_TSC_STABLE_BIT	(1 << 0)
 #define PVCLOCK_GUEST_STOPPED	(1 << 1)
+/* PVCLOCK_COUNTS_FROM_ZERO broke ABI and can't be used anymore. */
 #define PVCLOCK_COUNTS_FROM_ZERO (1 << 2)
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_PVCLOCK_ABI_H */
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index 5edf6d868fc1..165be83a7fa4 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -47,6 +47,7 @@ enum extra_reg_type {
 	EXTRA_REG_RSP_1 = 1,	/* offcore_response_1 */
 	EXTRA_REG_LBR   = 2,	/* lbr_select */
 	EXTRA_REG_LDLAT = 3,	/* ld_lat_threshold */
+	EXTRA_REG_FE    = 4,    /* fe_* */
 
 	EXTRA_REG_MAX		/* number of entries needed */
 };
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 3fefebfbdf4b..f63360be2238 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -205,6 +205,11 @@ static struct extra_reg intel_skl_extra_regs[] __read_mostly = {
 	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0),
 	INTEL_UEVENT_EXTRA_REG(0x01bb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1),
 	INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd),
+	/*
+	 * Note the low 8 bits eventsel code is not a continuous field, containing
+	 * some #GPing bits. These are masked out.
+	 */
+	INTEL_UEVENT_EXTRA_REG(0x01c6, MSR_PEBS_FRONTEND, 0x7fff17, FE),
 	EVENT_EXTRA_END
 };
 
@@ -250,7 +255,7 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
-	INTEL_EVENT_CONSTRAINT(0xa3, 0x4),	/* CYCLE_ACTIVITY.* */
+	INTEL_UEVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
 	EVENT_CONSTRAINT_END
 };
 
@@ -2891,6 +2896,8 @@ PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63");
 
 PMU_FORMAT_ATTR(ldlat, "config1:0-15");
 
+PMU_FORMAT_ATTR(frontend, "config1:0-23");
+
 static struct attribute *intel_arch3_formats_attr[] = {
 	&format_attr_event.attr,
 	&format_attr_umask.attr,
@@ -2907,6 +2914,11 @@ static struct attribute *intel_arch3_formats_attr[] = {
 	NULL,
 };
 
+static struct attribute *skl_format_attr[] = {
+	&format_attr_frontend.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu core_pmu = {
 	.name			= "core",
 	.handle_irq		= x86_pmu_handle_irq,
@@ -3516,7 +3528,8 @@ __init int intel_pmu_init(void)
 
 		x86_pmu.hw_config = hsw_hw_config;
 		x86_pmu.get_event_constraints = hsw_get_event_constraints;
-		x86_pmu.cpu_events = hsw_events_attrs;
+		x86_pmu.format_attrs = merge_attr(intel_arch3_formats_attr,
+						  skl_format_attr);
 		WARN_ON(!x86_pmu.format_attrs);
 		x86_pmu.cpu_events = hsw_events_attrs;
 		pr_cont("Skylake events, ");
diff --git a/arch/x86/kernel/cpu/perf_event_msr.c b/arch/x86/kernel/cpu/perf_event_msr.c
index 086b12eae794..f32ac13934f2 100644
--- a/arch/x86/kernel/cpu/perf_event_msr.c
+++ b/arch/x86/kernel/cpu/perf_event_msr.c
@@ -10,12 +10,12 @@ enum perf_msr_id {
 	PERF_MSR_EVENT_MAX,
 };
 
-bool test_aperfmperf(int idx)
+static bool test_aperfmperf(int idx)
 {
 	return boot_cpu_has(X86_FEATURE_APERFMPERF);
 }
 
-bool test_intel(int idx)
+static bool test_intel(int idx)
 {
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL ||
 	    boot_cpu_data.x86 != 6)
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index f68e48f5f6c2..c2130aef3f9d 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -41,10 +41,18 @@
 #include <asm/timer.h>
 #include <asm/special_insns.h>
 
-/* nop stub */
-void _paravirt_nop(void)
-{
-}
+/*
+ * nop stub, which must not clobber anything *including the stack* to
+ * avoid confusing the entry prologues.
+ */
+extern void _paravirt_nop(void);
+asm (".pushsection .entry.text, \"ax\"\n"
+     ".global _paravirt_nop\n"
+     "_paravirt_nop:\n\t"
+     "ret\n\t"
+     ".size _paravirt_nop, . - _paravirt_nop\n\t"
+     ".type _paravirt_nop, @function\n\t"
+     ".popsection");
 
 /* identity function, which can be inlined */
 u32 _paravirt_ident_32(u32 x)
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 94b7d15db3fc..2f9ed1ff0632 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -514,7 +514,7 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	struct vcpu_svm *svm = to_svm(vcpu);
 
 	if (svm->vmcb->control.next_rip != 0) {
-		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
+		WARN_ON_ONCE(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
 	}
 
@@ -866,64 +866,6 @@ static void svm_disable_lbrv(struct vcpu_svm *svm)
 	set_msr_interception(msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
 }
 
-#define MTRR_TYPE_UC_MINUS	7
-#define MTRR2PROTVAL_INVALID 0xff
-
-static u8 mtrr2protval[8];
-
-static u8 fallback_mtrr_type(int mtrr)
-{
-	/*
-	 * WT and WP aren't always available in the host PAT.  Treat
-	 * them as UC and UC- respectively.  Everything else should be
-	 * there.
-	 */
-	switch (mtrr)
-	{
-	case MTRR_TYPE_WRTHROUGH:
-		return MTRR_TYPE_UNCACHABLE;
-	case MTRR_TYPE_WRPROT:
-		return MTRR_TYPE_UC_MINUS;
-	default:
-		BUG();
-	}
-}
-
-static void build_mtrr2protval(void)
-{
-	int i;
-	u64 pat;
-
-	for (i = 0; i < 8; i++)
-		mtrr2protval[i] = MTRR2PROTVAL_INVALID;
-
-	/* Ignore the invalid MTRR types.  */
-	mtrr2protval[2] = 0;
-	mtrr2protval[3] = 0;
-
-	/*
-	 * Use host PAT value to figure out the mapping from guest MTRR
-	 * values to nested page table PAT/PCD/PWT values.  We do not
-	 * want to change the host PAT value every time we enter the
-	 * guest.
-	 */
-	rdmsrl(MSR_IA32_CR_PAT, pat);
-	for (i = 0; i < 8; i++) {
-		u8 mtrr = pat >> (8 * i);
-
-		if (mtrr2protval[mtrr] == MTRR2PROTVAL_INVALID)
-			mtrr2protval[mtrr] = __cm_idx2pte(i);
-	}
-
-	for (i = 0; i < 8; i++) {
-		if (mtrr2protval[i] == MTRR2PROTVAL_INVALID) {
-			u8 fallback = fallback_mtrr_type(i);
-			mtrr2protval[i] = mtrr2protval[fallback];
-			BUG_ON(mtrr2protval[i] == MTRR2PROTVAL_INVALID);
-		}
-	}
-}
-
 static __init int svm_hardware_setup(void)
 {
 	int cpu;
@@ -990,7 +932,6 @@ static __init int svm_hardware_setup(void)
 	} else
 		kvm_disable_tdp();
 
-	build_mtrr2protval();
 	return 0;
 
 err:
@@ -1145,43 +1086,6 @@ static u64 svm_compute_tsc_offset(struct kvm_vcpu *vcpu, u64 target_tsc)
 	return target_tsc - tsc;
 }
 
-static void svm_set_guest_pat(struct vcpu_svm *svm, u64 *g_pat)
-{
-	struct kvm_vcpu *vcpu = &svm->vcpu;
-
-	/* Unlike Intel, AMD takes the guest's CR0.CD into account.
-	 *
-	 * AMD does not have IPAT.  To emulate it for the case of guests
-	 * with no assigned devices, just set everything to WB.  If guests
-	 * have assigned devices, however, we cannot force WB for RAM
-	 * pages only, so use the guest PAT directly.
-	 */
-	if (!kvm_arch_has_assigned_device(vcpu->kvm))
-		*g_pat = 0x0606060606060606;
-	else
-		*g_pat = vcpu->arch.pat;
-}
-
-static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
-{
-	u8 mtrr;
-
-	/*
-	 * 1. MMIO: trust guest MTRR, so same as item 3.
-	 * 2. No passthrough: always map as WB, and force guest PAT to WB as well
-	 * 3. Passthrough: can't guarantee the result, try to trust guest.
-	 */
-	if (!is_mmio && !kvm_arch_has_assigned_device(vcpu->kvm))
-		return 0;
-
-	if (!kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED) &&
-	    kvm_read_cr0(vcpu) & X86_CR0_CD)
-		return _PAGE_NOCACHE;
-
-	mtrr = kvm_mtrr_get_guest_memory_type(vcpu, gfn);
-	return mtrr2protval[mtrr];
-}
-
 static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 {
 	struct vmcb_control_area *control = &svm->vmcb->control;
@@ -1278,7 +1182,6 @@ static void init_vmcb(struct vcpu_svm *svm, bool init_event)
 		clr_cr_intercept(svm, INTERCEPT_CR3_READ);
 		clr_cr_intercept(svm, INTERCEPT_CR3_WRITE);
 		save->g_pat = svm->vcpu.arch.pat;
-		svm_set_guest_pat(svm, &save->g_pat);
 		save->cr3 = 0;
 		save->cr4 = 0;
 	}
@@ -1673,10 +1576,13 @@ static void svm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 
 	if (!vcpu->fpu_active)
 		cr0 |= X86_CR0_TS;
-
-	/* These are emulated via page tables.  */
-	cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
-
+	/*
+	 * re-enable caching here because the QEMU bios
+	 * does not do it - this results in some delay at
+	 * reboot
+	 */
+	if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_CD_NW_CLEARED))
+		cr0 &= ~(X86_CR0_CD | X86_CR0_NW);
 	svm->vmcb->save.cr0 = cr0;
 	mark_dirty(svm->vmcb, VMCB_CR);
 	update_cr0_intercept(svm);
@@ -3351,16 +3257,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 	case MSR_VM_IGNNE:
 		vcpu_unimpl(vcpu, "unimplemented wrmsr: 0x%x data 0x%llx\n", ecx, data);
 		break;
-	case MSR_IA32_CR_PAT:
-		if (npt_enabled) {
-			if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
-				return 1;
-			vcpu->arch.pat = data;
-			svm_set_guest_pat(svm, &svm->vmcb->save.g_pat);
-			mark_dirty(svm->vmcb, VMCB_NPT);
-			break;
-		}
-		/* fall through */
 	default:
 		return kvm_set_msr_common(vcpu, msr);
 	}
@@ -4195,6 +4091,11 @@ static bool svm_has_high_real_mode_segbase(void)
 	return true;
 }
 
+static u64 svm_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
+{
+	return 0;
+}
+
 static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 {
 }
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 64076740251e..06ef4908ba61 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -8617,17 +8617,22 @@ static u64 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
 	u64 ipat = 0;
 
 	/* For VT-d and EPT combination
-	 * 1. MMIO: guest may want to apply WC, trust it.
+	 * 1. MMIO: always map as UC
 	 * 2. EPT with VT-d:
 	 *   a. VT-d without snooping control feature: can't guarantee the
-	 *	result, try to trust guest.  So the same as item 1.
+	 *	result, try to trust guest.
 	 *   b. VT-d with snooping control feature: snooping control feature of
 	 *	VT-d engine can guarantee the cache correctness. Just set it
 	 *	to WB to keep consistent with host. So the same as item 3.
 	 * 3. EPT without VT-d: always map as WB and set IPAT=1 to keep
 	 *    consistent with host MTRR
 	 */
-	if (!is_mmio && !kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
+	if (is_mmio) {
+		cache = MTRR_TYPE_UNCACHABLE;
+		goto exit;
+	}
+
+	if (!kvm_arch_has_noncoherent_dma(vcpu->kvm)) {
 		ipat = VMX_EPT_IPAT_BIT;
 		cache = MTRR_TYPE_WRBACK;
 		goto exit;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 991466bf8dee..92511d4b7236 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -1708,8 +1708,6 @@ static int kvm_guest_time_update(struct kvm_vcpu *v)
 		vcpu->pvclock_set_guest_stopped_request = false;
 	}
 
-	pvclock_flags |= PVCLOCK_COUNTS_FROM_ZERO;
-
 	/* If the host uses TSC clocksource, then it is stable */
 	if (use_master_clock)
 		pvclock_flags |= PVCLOCK_TSC_STABLE_BIT;
@@ -2007,8 +2005,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
 					&vcpu->requests);
 
 			ka->boot_vcpu_runs_old_kvmclock = tmp;
-
-			ka->kvmclock_offset = -get_kernel_ns();
 		}
 
 		vcpu->arch.time = data;
diff --git a/crypto/asymmetric_keys/x509_public_key.c b/crypto/asymmetric_keys/x509_public_key.c
index 6d88dd15c98d..197096632412 100644
--- a/crypto/asymmetric_keys/x509_public_key.c
+++ b/crypto/asymmetric_keys/x509_public_key.c
@@ -332,10 +332,6 @@ static int x509_key_preparse(struct key_preparsed_payload *prep)
 		srlen = cert->raw_serial_size;
 		q = cert->raw_serial;
 	}
-	if (srlen > 1 && *q == 0) {
-		srlen--;
-		q++;
-	}
 
 	ret = -ENOMEM;
 	desc = kmalloc(sulen + 2 + srlen * 2 + 1, GFP_KERNEL);
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 2614a839c60d..42c66b64c12c 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1044,8 +1044,10 @@ static int acpi_ec_query(struct acpi_ec *ec, u8 *data)
 		goto err_exit;
 
 	mutex_lock(&ec->mutex);
+	result = -ENODATA;
 	list_for_each_entry(handler, &ec->list, node) {
 		if (value == handler->query_bit) {
+			result = 0;
 			q->handler = acpi_ec_get_query_handler(handler);
 			ec_dbg_evt("Query(0x%02x) scheduled",
 				   q->handler->query_bit);
diff --git a/drivers/acpi/pci_irq.c b/drivers/acpi/pci_irq.c
index 6da0f9beab19..c9336751e5e3 100644
--- a/drivers/acpi/pci_irq.c
+++ b/drivers/acpi/pci_irq.c
@@ -372,6 +372,7 @@ static int acpi_isa_register_gsi(struct pci_dev *dev)
 
 	/* Interrupt Line values above 0xF are forbidden */
 	if (dev->irq > 0 && (dev->irq <= 0xF) &&
+	    acpi_isa_irq_available(dev->irq) &&
 	    (acpi_isa_irq_to_gsi(dev->irq, &dev_gsi) == 0)) {
 		dev_warn(&dev->dev, "PCI INT %c: no GSI - using ISA IRQ %d\n",
 			 pin_name(dev->pin), dev->irq);
diff --git a/drivers/acpi/pci_link.c b/drivers/acpi/pci_link.c
index 3b4ea98e3ea0..7c8408b946ca 100644
--- a/drivers/acpi/pci_link.c
+++ b/drivers/acpi/pci_link.c
@@ -498,8 +498,7 @@ int __init acpi_irq_penalty_init(void)
 			    PIRQ_PENALTY_PCI_POSSIBLE;
 		}
 	}
-	/* Add a penalty for the SCI */
-	acpi_irq_penalty[acpi_gbl_FADT.sci_interrupt] += PIRQ_PENALTY_PCI_USING;
+
 	return 0;
 }
 
@@ -553,6 +552,13 @@ static int acpi_pci_link_allocate(struct acpi_pci_link *link)
 				irq = link->irq.possible[i];
 		}
 	}
+	if (acpi_irq_penalty[irq] >= PIRQ_PENALTY_ISA_ALWAYS) {
+		printk(KERN_ERR PREFIX "No IRQ available for %s [%s]. "
+			    "Try pci=noacpi or acpi=off\n",
+			    acpi_device_name(link->device),
+			    acpi_device_bid(link->device));
+		return -ENODEV;
+	}
 
 	/* Attempt to enable the link device at this IRQ. */
 	if (acpi_pci_link_set(link, irq)) {
@@ -821,6 +827,12 @@ void acpi_penalize_isa_irq(int irq, int active)
 	}
 }
 
+bool acpi_isa_irq_available(int irq)
+{
+	return irq >= 0 && (irq >= ARRAY_SIZE(acpi_irq_penalty) ||
+			    acpi_irq_penalty[irq] < PIRQ_PENALTY_ISA_ALWAYS);
+}
+
 /*
  * Penalize IRQ used by ACPI SCI. If ACPI SCI pin attributes conflict with
  * PCI IRQ attributes, mark ACPI SCI as ISA_ALWAYS so it won't be use for
diff --git a/drivers/base/cacheinfo.c b/drivers/base/cacheinfo.c
index 764280a91776..e9fd32e91668 100644
--- a/drivers/base/cacheinfo.c
+++ b/drivers/base/cacheinfo.c
@@ -148,7 +148,11 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 			if (sibling == cpu) /* skip itself */
 				continue;
+
 			sib_cpu_ci = get_cpu_cacheinfo(sibling);
+			if (!sib_cpu_ci->info_list)
+				continue;
+
 			sib_leaf = sib_cpu_ci->info_list + index;
 			cpumask_clear_cpu(cpu, &sib_leaf->shared_cpu_map);
 			cpumask_clear_cpu(sibling, &this_leaf->shared_cpu_map);
@@ -159,6 +163,9 @@ static void cache_shared_cpu_map_remove(unsigned int cpu)
 
 static void free_cache_attributes(unsigned int cpu)
 {
+	if (!per_cpu_cacheinfo(cpu))
+		return;
+
 	cache_shared_cpu_map_remove(cpu);
 
 	kfree(per_cpu_cacheinfo(cpu));
@@ -514,8 +521,7 @@ static int cacheinfo_cpu_callback(struct notifier_block *nfb,
 		break;
 	case CPU_DEAD:
 		cache_remove_dev(cpu);
-		if (per_cpu_cacheinfo(cpu))
-			free_cache_attributes(cpu);
+		free_cache_attributes(cpu);
 		break;
 	}
 	return notifier_from_errno(rc);
diff --git a/drivers/base/power/opp.c b/drivers/base/power/opp.c
index 28cd75c535b0..7ae7cd990fbf 100644
--- a/drivers/base/power/opp.c
+++ b/drivers/base/power/opp.c
@@ -892,10 +892,17 @@ static int opp_get_microvolt(struct dev_pm_opp *opp, struct device *dev)
 	u32 microvolt[3] = {0};
 	int count, ret;
 
-	count = of_property_count_u32_elems(opp->np, "opp-microvolt");
-	if (!count)
+	/* Missing property isn't a problem, but an invalid entry is */
+	if (!of_find_property(opp->np, "opp-microvolt", NULL))
 		return 0;
 
+	count = of_property_count_u32_elems(opp->np, "opp-microvolt");
+	if (count < 0) {
+		dev_err(dev, "%s: Invalid opp-microvolt property (%d)\n",
+			__func__, count);
+		return count;
+	}
+
 	/* There can be one or three elements here */
 	if (count != 1 && count != 3) {
 		dev_err(dev, "%s: Invalid number of elements in opp-microvolt property (%d)\n",
@@ -1063,7 +1070,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_add);
  * share a common logic which is isolated here.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
  * successful.
  *
  * Locking: The internal device_opp and opp structures are RCU protected.
@@ -1151,7 +1158,7 @@ unlock:
  * mutex locking or synchronize_rcu() blocking calls cannot be used.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
  * successful.
  */
 int dev_pm_opp_enable(struct device *dev, unsigned long freq)
@@ -1177,7 +1184,7 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_enable);
  * mutex locking or synchronize_rcu() blocking calls cannot be used.
  *
  * Return: -EINVAL for bad pointers, -ENOMEM if no memory available for the
- * copy operation, returns 0 if no modifcation was done OR modification was
+ * copy operation, returns 0 if no modification was done OR modification was
  * successful.
  */
 int dev_pm_opp_disable(struct device *dev, unsigned long freq)
diff --git a/drivers/char/hw_random/xgene-rng.c b/drivers/char/hw_random/xgene-rng.c
index c37cf754a985..3c77645405e5 100644
--- a/drivers/char/hw_random/xgene-rng.c
+++ b/drivers/char/hw_random/xgene-rng.c
@@ -344,11 +344,12 @@ static int xgene_rng_probe(struct platform_device *pdev)
 	if (IS_ERR(ctx->csr_base))
 		return PTR_ERR(ctx->csr_base);
 
-	ctx->irq = platform_get_irq(pdev, 0);
-	if (ctx->irq < 0) {
+	rc = platform_get_irq(pdev, 0);
+	if (rc < 0) {
 		dev_err(&pdev->dev, "No IRQ resource\n");
-		return ctx->irq;
+		return rc;
 	}
+	ctx->irq = rc;
 
 	dev_dbg(&pdev->dev, "APM X-Gene RNG BASE %p ALARM IRQ %d",
 		ctx->csr_base, ctx->irq);
diff --git a/drivers/crypto/marvell/cesa.h b/drivers/crypto/marvell/cesa.h
index b60698b30d30..bc2a55bc35e4 100644
--- a/drivers/crypto/marvell/cesa.h
+++ b/drivers/crypto/marvell/cesa.h
@@ -687,6 +687,33 @@ static inline u32 mv_cesa_get_int_mask(struct mv_cesa_engine *engine)
 
 int mv_cesa_queue_req(struct crypto_async_request *req);
 
+/*
+ * Helper function that indicates whether a crypto request needs to be
+ * cleaned up or not after being enqueued using mv_cesa_queue_req().
+ */
+static inline int mv_cesa_req_needs_cleanup(struct crypto_async_request *req,
+					    int ret)
+{
+	/*
+	 * The queue still had some space, the request was queued
+	 * normally, so there's no need to clean it up.
+	 */
+	if (ret == -EINPROGRESS)
+		return false;
+
+	/*
+	 * The queue had not space left, but since the request is
+	 * flagged with CRYPTO_TFM_REQ_MAY_BACKLOG, it was added to
+	 * the backlog and will be processed later. There's no need to
+	 * clean it up.
+	 */
+	if (ret == -EBUSY && req->flags & CRYPTO_TFM_REQ_MAY_BACKLOG)
+		return false;
+
+	/* Request wasn't queued, we need to clean it up */
+	return true;
+}
+
 /* TDMA functions */
 
 static inline void mv_cesa_req_dma_iter_init(struct mv_cesa_dma_iter *iter,
diff --git a/drivers/crypto/marvell/cipher.c b/drivers/crypto/marvell/cipher.c
index 0745cf3b9c0e..3df2f4e7adb2 100644
--- a/drivers/crypto/marvell/cipher.c
+++ b/drivers/crypto/marvell/cipher.c
@@ -189,7 +189,6 @@ static inline void mv_cesa_ablkcipher_prepare(struct crypto_async_request *req,
 {
 	struct ablkcipher_request *ablkreq = ablkcipher_request_cast(req);
 	struct mv_cesa_ablkcipher_req *creq = ablkcipher_request_ctx(ablkreq);
-
 	creq->req.base.engine = engine;
 
 	if (creq->req.base.type == CESA_DMA_REQ)
@@ -431,7 +430,7 @@ static int mv_cesa_des_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -551,7 +550,7 @@ static int mv_cesa_des3_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
@@ -693,7 +692,7 @@ static int mv_cesa_aes_op(struct ablkcipher_request *req,
 		return ret;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ablkcipher_cleanup(req);
 
 	return ret;
diff --git a/drivers/crypto/marvell/hash.c b/drivers/crypto/marvell/hash.c
index ae9272eb9c1a..e8d0d7128137 100644
--- a/drivers/crypto/marvell/hash.c
+++ b/drivers/crypto/marvell/hash.c
@@ -739,10 +739,8 @@ static int mv_cesa_ahash_update(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS) {
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
-		return ret;
-	}
 
 	return ret;
 }
@@ -766,7 +764,7 @@ static int mv_cesa_ahash_final(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
@@ -791,7 +789,7 @@ static int mv_cesa_ahash_finup(struct ahash_request *req)
 		return 0;
 
 	ret = mv_cesa_queue_req(&req->base);
-	if (ret && ret != -EINPROGRESS)
+	if (mv_cesa_req_needs_cleanup(&req->base, ret))
 		mv_cesa_ahash_cleanup(req);
 
 	return ret;
diff --git a/drivers/crypto/qat/qat_common/adf_aer.c b/drivers/crypto/qat/qat_common/adf_aer.c
index a57b4194de28..0a5ca0ba5d64 100644
--- a/drivers/crypto/qat/qat_common/adf_aer.c
+++ b/drivers/crypto/qat/qat_common/adf_aer.c
@@ -88,6 +88,9 @@ static void adf_dev_restore(struct adf_accel_dev *accel_dev)
 	struct pci_dev *parent = pdev->bus->self;
 	uint16_t bridge_ctl = 0;
 
+	if (accel_dev->is_vf)
+		return;
+
 	dev_info(&GET_DEV(accel_dev), "Resetting device qat_dev%d\n",
 		 accel_dev->accel_id);
 
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index a07addde297b..8dd0af1d50bc 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -159,7 +159,7 @@ static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
 static bool is_extcon_changed(u32 prev, u32 new, int idx, bool *attached)
 {
 	if (((prev >> idx) & 0x1) != ((new >> idx) & 0x1)) {
-		*attached = new ? true : false;
+		*attached = ((new >> idx) & 0x1) ? true : false;
 		return true;
 	}
 
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index d8de6a8dd4de..665efca59487 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -139,6 +139,14 @@ config QCOM_SCM
 	bool
 	depends on ARM || ARM64
 
+config QCOM_SCM_32
+	def_bool y
+	depends on QCOM_SCM && ARM
+
+config QCOM_SCM_64
+	def_bool y
+	depends on QCOM_SCM && ARM64
+
 source "drivers/firmware/broadcom/Kconfig"
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 000830fc6707..2ee83474a3c1 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -13,7 +13,8 @@ obj-$(CONFIG_ISCSI_IBFT_FIND)	+= iscsi_ibft_find.o
 obj-$(CONFIG_ISCSI_IBFT)	+= iscsi_ibft.o
 obj-$(CONFIG_FIRMWARE_MEMMAP)	+= memmap.o
 obj-$(CONFIG_QCOM_SCM)		+= qcom_scm.o
-obj-$(CONFIG_QCOM_SCM)		+= qcom_scm-32.o
+obj-$(CONFIG_QCOM_SCM_64)	+= qcom_scm-64.o
+obj-$(CONFIG_QCOM_SCM_32)	+= qcom_scm-32.o
 CFLAGS_qcom_scm-32.o :=$(call as-instr,.arch_extension sec,-DREQUIRES_SEC=1)
 
 obj-y				+= broadcom/
diff --git a/drivers/firmware/qcom_scm-64.c b/drivers/firmware/qcom_scm-64.c
new file mode 100644
index 000000000000..bb6555f6d63b
--- /dev/null
+++ b/drivers/firmware/qcom_scm-64.c
@@ -0,0 +1,63 @@
+/* Copyright (c) 2015, The Linux Foundation. All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 and
+ * only version 2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/qcom_scm.h>
+
+/**
+ * qcom_scm_set_cold_boot_addr() - Set the cold boot address for cpus
+ * @entry: Entry point function for the cpus
+ * @cpus: The cpumask of cpus that will use the entry point
+ *
+ * Set the cold boot address of the cpus. Any cpu outside the supported
+ * range would be removed from the cpu present mask.
+ */
+int __qcom_scm_set_cold_boot_addr(void *entry, const cpumask_t *cpus)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * qcom_scm_set_warm_boot_addr() - Set the warm boot address for cpus
+ * @entry: Entry point function for the cpus
+ * @cpus: The cpumask of cpus that will use the entry point
+ *
+ * Set the Linux entry point for the SCM to transfer control to when coming
+ * out of a power down. CPU power down may be executed on cpuidle or hotplug.
+ */
+int __qcom_scm_set_warm_boot_addr(void *entry, const cpumask_t *cpus)
+{
+	return -ENOTSUPP;
+}
+
+/**
+ * qcom_scm_cpu_power_down() - Power down the cpu
+ * @flags - Flags to flush cache
+ *
+ * This is an end point to power down cpu. If there was a pending interrupt,
+ * the control would return from this function, otherwise, the cpu jumps to the
+ * warm boot entry point set for this cpu upon reset.
+ */
+void __qcom_scm_cpu_power_down(u32 flags)
+{
+}
+
+int __qcom_scm_is_call_available(u32 svc_id, u32 cmd_id)
+{
+	return -ENOTSUPP;
+}
+
+int __qcom_scm_hdcp_req(struct qcom_scm_hdcp_req *req, u32 req_cnt, u32 *resp)
+{
+	return -ENOTSUPP;
+}
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 2f9aead4ecfc..652afd11a9ef 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -204,6 +204,8 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 		spin_lock_irqsave(&vmbus_connection.channel_lock, flags);
 		list_del(&channel->listentry);
 		spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags);
+
+		primary_channel = channel;
 	} else {
 		primary_channel = channel->primary_channel;
 		spin_lock_irqsave(&primary_channel->lock, flags);
@@ -211,6 +213,14 @@ void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid)
 		primary_channel->num_sc--;
 		spin_unlock_irqrestore(&primary_channel->lock, flags);
 	}
+
+	/*
+	 * We need to free the bit for init_vp_index() to work in the case
+	 * of sub-channel, when we reload drivers like hv_netvsc.
+	 */
+	cpumask_clear_cpu(channel->target_cpu,
+			  &primary_channel->alloced_cpus_in_node);
+
 	free_channel(channel);
 }
 
@@ -458,6 +468,13 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 			continue;
 		}
 
+		/*
+		 * NOTE: in the case of sub-channel, we clear the sub-channel
+		 * related bit(s) in primary->alloced_cpus_in_node in
+		 * hv_process_channel_removal(), so when we reload drivers
+		 * like hv_netvsc in SMP guest, here we're able to re-allocate
+		 * bit from primary->alloced_cpus_in_node.
+		 */
 		if (!cpumask_test_cpu(cur_cpu,
 				&primary->alloced_cpus_in_node)) {
 			cpumask_set_cpu(cur_cpu,
diff --git a/drivers/hwmon/abx500.c b/drivers/hwmon/abx500.c
index 6cb89c0ebab6..1fd46859ed29 100644
--- a/drivers/hwmon/abx500.c
+++ b/drivers/hwmon/abx500.c
@@ -470,6 +470,7 @@ static const struct of_device_id abx500_temp_match[] = {
 	{ .compatible = "stericsson,abx500-temp" },
 	{},
 };
+MODULE_DEVICE_TABLE(of, abx500_temp_match);
 #endif
 
 static struct platform_driver abx500_temp_driver = {
diff --git a/drivers/hwmon/gpio-fan.c b/drivers/hwmon/gpio-fan.c
index a3dae6d0082a..82de3deeb18a 100644
--- a/drivers/hwmon/gpio-fan.c
+++ b/drivers/hwmon/gpio-fan.c
@@ -539,6 +539,7 @@ static const struct of_device_id of_gpio_fan_match[] = {
 	{ .compatible = "gpio-fan", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, of_gpio_fan_match);
 #endif /* CONFIG_OF_GPIO */
 
 static int gpio_fan_probe(struct platform_device *pdev)
diff --git a/drivers/hwmon/pwm-fan.c b/drivers/hwmon/pwm-fan.c
index 2d9a712699ff..3e23003f78b0 100644
--- a/drivers/hwmon/pwm-fan.c
+++ b/drivers/hwmon/pwm-fan.c
@@ -323,6 +323,7 @@ static const struct of_device_id of_pwm_fan_match[] = {
 	{ .compatible = "pwm-fan", },
 	{},
 };
+MODULE_DEVICE_TABLE(of, of_pwm_fan_match);
 
 static struct platform_driver pwm_fan_driver = {
 	.probe		= pwm_fan_probe,
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 3a3738fe016b..cd4510a63375 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -620,7 +620,7 @@ static struct cpuidle_state skl_cstates[] = {
 		.name = "C6-SKL",
 		.desc = "MWAIT 0x20",
 		.flags = MWAIT2flg(0x20) | CPUIDLE_FLAG_TLB_FLUSHED,
-		.exit_latency = 75,
+		.exit_latency = 85,
 		.target_residency = 200,
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
@@ -636,11 +636,19 @@ static struct cpuidle_state skl_cstates[] = {
 		.name = "C8-SKL",
 		.desc = "MWAIT 0x40",
 		.flags = MWAIT2flg(0x40) | CPUIDLE_FLAG_TLB_FLUSHED,
-		.exit_latency = 174,
+		.exit_latency = 200,
 		.target_residency = 800,
 		.enter = &intel_idle,
 		.enter_freeze = intel_idle_freeze, },
 	{
+		.name = "C9-SKL",
+		.desc = "MWAIT 0x50",
+		.flags = MWAIT2flg(0x50) | CPUIDLE_FLAG_TLB_FLUSHED,
+		.exit_latency = 480,
+		.target_residency = 5000,
+		.enter = &intel_idle,
+		.enter_freeze = intel_idle_freeze, },
+	{
 		.name = "C10-SKL",
 		.desc = "MWAIT 0x60",
 		.flags = MWAIT2flg(0x60) | CPUIDLE_FLAG_TLB_FLUSHED,
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 41d6911e244e..f1ccd40beae9 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -245,7 +245,6 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->device_cap_flags |= IB_DEVICE_BAD_QKEY_CNTR;
 	if (MLX5_CAP_GEN(mdev, apm))
 		props->device_cap_flags |= IB_DEVICE_AUTO_PATH_MIG;
-	props->device_cap_flags |= IB_DEVICE_LOCAL_DMA_LKEY;
 	if (MLX5_CAP_GEN(mdev, xrc))
 		props->device_cap_flags |= IB_DEVICE_XRC;
 	props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS;
@@ -795,53 +794,6 @@ static int mlx5_ib_mmap(struct ib_ucontext *ibcontext, struct vm_area_struct *vm
 	return 0;
 }
 
-static int alloc_pa_mkey(struct mlx5_ib_dev *dev, u32 *key, u32 pdn)
-{
-	struct mlx5_create_mkey_mbox_in *in;
-	struct mlx5_mkey_seg *seg;
-	struct mlx5_core_mr mr;
-	int err;
-
-	in = kzalloc(sizeof(*in), GFP_KERNEL);
-	if (!in)
-		return -ENOMEM;
-
-	seg = &in->seg;
-	seg->flags = MLX5_PERM_LOCAL_READ | MLX5_ACCESS_MODE_PA;
-	seg->flags_pd = cpu_to_be32(pdn | MLX5_MKEY_LEN64);
-	seg->qpn_mkey7_0 = cpu_to_be32(0xffffff << 8);
-	seg->start_addr = 0;
-
-	err = mlx5_core_create_mkey(dev->mdev, &mr, in, sizeof(*in),
-				    NULL, NULL, NULL);
-	if (err) {
-		mlx5_ib_warn(dev, "failed to create mkey, %d\n", err);
-		goto err_in;
-	}
-
-	kfree(in);
-	*key = mr.key;
-
-	return 0;
-
-err_in:
-	kfree(in);
-
-	return err;
-}
-
-static void free_pa_mkey(struct mlx5_ib_dev *dev, u32 key)
-{
-	struct mlx5_core_mr mr;
-	int err;
-
-	memset(&mr, 0, sizeof(mr));
-	mr.key = key;
-	err = mlx5_core_destroy_mkey(dev->mdev, &mr);
-	if (err)
-		mlx5_ib_warn(dev, "failed to destroy mkey 0x%x\n", key);
-}
-
 static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
 				      struct ib_ucontext *context,
 				      struct ib_udata *udata)
@@ -867,13 +819,6 @@ static struct ib_pd *mlx5_ib_alloc_pd(struct ib_device *ibdev,
 			kfree(pd);
 			return ERR_PTR(-EFAULT);
 		}
-	} else {
-		err = alloc_pa_mkey(to_mdev(ibdev), &pd->pa_lkey, pd->pdn);
-		if (err) {
-			mlx5_core_dealloc_pd(to_mdev(ibdev)->mdev, pd->pdn);
-			kfree(pd);
-			return ERR_PTR(err);
-		}
 	}
 
 	return &pd->ibpd;
@@ -884,9 +829,6 @@ static int mlx5_ib_dealloc_pd(struct ib_pd *pd)
 	struct mlx5_ib_dev *mdev = to_mdev(pd->device);
 	struct mlx5_ib_pd *mpd = to_mpd(pd);
 
-	if (!pd->uobject)
-		free_pa_mkey(mdev, mpd->pa_lkey);
-
 	mlx5_core_dealloc_pd(mdev->mdev, mpd->pdn);
 	kfree(mpd);
 
@@ -1245,18 +1187,10 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	struct ib_srq_init_attr attr;
 	struct mlx5_ib_dev *dev;
 	struct ib_cq_init_attr cq_attr = {.cqe = 1};
-	u32 rsvd_lkey;
 	int ret = 0;
 
 	dev = container_of(devr, struct mlx5_ib_dev, devr);
 
-	ret = mlx5_core_query_special_context(dev->mdev, &rsvd_lkey);
-	if (ret) {
-		pr_err("Failed to query special context %d\n", ret);
-		return ret;
-	}
-	dev->ib_dev.local_dma_lkey = rsvd_lkey;
-
 	devr->p0 = mlx5_ib_alloc_pd(&dev->ib_dev, NULL, NULL);
 	if (IS_ERR(devr->p0)) {
 		ret = PTR_ERR(devr->p0);
@@ -1418,6 +1352,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	strlcpy(dev->ib_dev.name, "mlx5_%d", IB_DEVICE_NAME_MAX);
 	dev->ib_dev.owner		= THIS_MODULE;
 	dev->ib_dev.node_type		= RDMA_NODE_IB_CA;
+	dev->ib_dev.local_dma_lkey	= 0 /* not supported for now */;
 	dev->num_ports		= MLX5_CAP_GEN(mdev, num_ports);
 	dev->ib_dev.phys_port_cnt     = dev->num_ports;
 	dev->ib_dev.num_comp_vectors    =
diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
index bb8cda79e881..22123b79d550 100644
--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
+++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
@@ -103,7 +103,6 @@ static inline struct mlx5_ib_ucontext *to_mucontext(struct ib_ucontext *ibuconte
 struct mlx5_ib_pd {
 	struct ib_pd		ibpd;
 	u32			pdn;
-	u32			pa_lkey;
 };
 
 /* Use macros here so that don't have to duplicate
@@ -213,7 +212,6 @@ struct mlx5_ib_qp {
 	int			uuarn;
 
 	int			create_type;
-	u32			pa_lkey;
 
 	/* Store signature errors */
 	bool			signature_en;
diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index c745c6c5e10d..6f521a3418e8 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -925,8 +925,6 @@ static int create_qp_common(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			err = create_kernel_qp(dev, init_attr, qp, &in, &inlen);
 			if (err)
 				mlx5_ib_dbg(dev, "err %d\n", err);
-			else
-				qp->pa_lkey = to_mpd(pd)->pa_lkey;
 		}
 
 		if (err)
@@ -2045,7 +2043,7 @@ static void set_frwr_pages(struct mlx5_wqe_data_seg *dseg,
 		mfrpl->mapped_page_list[i] = cpu_to_be64(page_list[i] | perm);
 	dseg->addr = cpu_to_be64(mfrpl->map);
 	dseg->byte_count = cpu_to_be32(ALIGN(sizeof(u64) * wr->wr.fast_reg.page_list_len, 64));
-	dseg->lkey = cpu_to_be32(pd->pa_lkey);
+	dseg->lkey = cpu_to_be32(pd->ibpd.local_dma_lkey);
 }
 
 static __be32 send_ieth(struct ib_send_wr *wr)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index ca2873698d75..4cd5428a2399 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -80,7 +80,7 @@ enum {
 	IPOIB_NUM_WC		  = 4,
 
 	IPOIB_MAX_PATH_REC_QUEUE  = 3,
-	IPOIB_MAX_MCAST_QUEUE	  = 3,
+	IPOIB_MAX_MCAST_QUEUE	  = 64,
 
 	IPOIB_FLAG_OPER_UP	  = 0,
 	IPOIB_FLAG_INITIALIZED	  = 1,
@@ -548,6 +548,8 @@ void ipoib_path_iter_read(struct ipoib_path_iter *iter,
 
 int ipoib_mcast_attach(struct net_device *dev, u16 mlid,
 		       union ib_gid *mgid, int set_qkey);
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast);
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid);
 
 int ipoib_init_qp(struct net_device *dev);
 int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 36536ce5a3e2..f74316e679d2 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -1149,6 +1149,9 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 	unsigned long dt;
 	unsigned long flags;
 	int i;
+	LIST_HEAD(remove_list);
+	struct ipoib_mcast *mcast, *tmcast;
+	struct net_device *dev = priv->dev;
 
 	if (test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
 		return;
@@ -1176,6 +1179,19 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 							  lockdep_is_held(&priv->lock))) != NULL) {
 			/* was the neigh idle for two GC periods */
 			if (time_after(neigh_obsolete, neigh->alive)) {
+				u8 *mgid = neigh->daddr + 4;
+
+				/* Is this multicast ? */
+				if (*mgid == 0xff) {
+					mcast = __ipoib_mcast_find(dev, mgid);
+
+					if (mcast && test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
+						list_del(&mcast->list);
+						rb_erase(&mcast->rb_node, &priv->multicast_tree);
+						list_add_tail(&mcast->list, &remove_list);
+					}
+				}
+
 				rcu_assign_pointer(*np,
 						   rcu_dereference_protected(neigh->hnext,
 									     lockdep_is_held(&priv->lock)));
@@ -1191,6 +1207,8 @@ static void __ipoib_reap_neigh(struct ipoib_dev_priv *priv)
 
 out_unlock:
 	spin_unlock_irqrestore(&priv->lock, flags);
+	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
+		ipoib_mcast_leave(dev, mcast);
 }
 
 static void ipoib_reap_neigh(struct work_struct *work)
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 09a1748f9d13..136cbefe00f8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -153,7 +153,7 @@ static struct ipoib_mcast *ipoib_mcast_alloc(struct net_device *dev,
 	return mcast;
 }
 
-static struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
+struct ipoib_mcast *__ipoib_mcast_find(struct net_device *dev, void *mgid)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct rb_node *n = priv->multicast_tree.rb_node;
@@ -508,17 +508,19 @@ static void ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
 
 		/*
-		 * Historically Linux IPoIB has never properly supported SEND
-		 * ONLY join. It emulated it by not providing all the required
-		 * attributes, which is enough to prevent group creation and
-		 * detect if there are full members or not. A major problem
-		 * with supporting SEND ONLY is detecting when the group is
-		 * auto-destroyed as IPoIB will cache the MLID..
+		 * Send-only IB Multicast joins do not work at the core
+		 * IB layer yet, so we can't use them here.  However,
+		 * we are emulating an Ethernet multicast send, which
+		 * does not require a multicast subscription and will
+		 * still send properly.  The most appropriate thing to
+		 * do is to create the group if it doesn't exist as that
+		 * most closely emulates the behavior, from a user space
+		 * application perspecitive, of Ethernet multicast
+		 * operation.  For now, we do a full join, maybe later
+		 * when the core IB layers support send only joins we
+		 * will use them.
 		 */
-#if 1
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			comp_mask &= ~IB_SA_MCMEMBER_REC_TRAFFIC_CLASS;
-#else
+#if 0
 		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
 			rec.join_state = 4;
 #endif
@@ -675,7 +677,7 @@ int ipoib_mcast_stop_thread(struct net_device *dev)
 	return 0;
 }
 
-static int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
+int ipoib_mcast_leave(struct net_device *dev, struct ipoib_mcast *mcast)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret = 0;
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c
index 1ace5d83a4d7..f58ff96b6cbb 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.c
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.c
@@ -97,6 +97,11 @@ unsigned int iser_max_sectors = ISER_DEF_MAX_SECTORS;
 module_param_named(max_sectors, iser_max_sectors, uint, S_IRUGO | S_IWUSR);
 MODULE_PARM_DESC(max_sectors, "Max number of sectors in a single scsi command (default:1024");
 
+bool iser_always_reg = true;
+module_param_named(always_register, iser_always_reg, bool, S_IRUGO);
+MODULE_PARM_DESC(always_register,
+		 "Always register memory, even for continuous memory regions (default:true)");
+
 bool iser_pi_enable = false;
 module_param_named(pi_enable, iser_pi_enable, bool, S_IRUGO);
 MODULE_PARM_DESC(pi_enable, "Enable T10-PI offload support (default:disabled)");
diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h
index 86f6583485ef..a5edd6ede692 100644
--- a/drivers/infiniband/ulp/iser/iscsi_iser.h
+++ b/drivers/infiniband/ulp/iser/iscsi_iser.h
@@ -611,6 +611,7 @@ extern int iser_debug_level;
 extern bool iser_pi_enable;
 extern int iser_pi_guard;
 extern unsigned int iser_max_sectors;
+extern bool iser_always_reg;
 
 int iser_assign_reg_ops(struct iser_device *device);
 
diff --git a/drivers/infiniband/ulp/iser/iser_memory.c b/drivers/infiniband/ulp/iser/iser_memory.c
index 2493cc748db8..4c46d67d37a1 100644
--- a/drivers/infiniband/ulp/iser/iser_memory.c
+++ b/drivers/infiniband/ulp/iser/iser_memory.c
@@ -803,11 +803,12 @@ static int
 iser_reg_prot_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->pi_ctx->rsc, reg);
@@ -817,11 +818,12 @@ static int
 iser_reg_data_sg(struct iscsi_iser_task *task,
 		 struct iser_data_buf *mem,
 		 struct iser_fr_desc *desc,
+		 bool use_dma_key,
 		 struct iser_mem_reg *reg)
 {
 	struct iser_device *device = task->iser_conn->ib_conn.device;
 
-	if (mem->dma_nents == 1)
+	if (use_dma_key)
 		return iser_reg_dma(device, mem, reg);
 
 	return device->reg_ops->reg_mem(task, mem, &desc->rsc, reg);
@@ -836,14 +838,17 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	struct iser_mem_reg *reg = &task->rdma_reg[dir];
 	struct iser_mem_reg *data_reg;
 	struct iser_fr_desc *desc = NULL;
+	bool use_dma_key;
 	int err;
 
 	err = iser_handle_unaligned_buf(task, mem, dir);
 	if (unlikely(err))
 		return err;
 
-	if (mem->dma_nents != 1 ||
-	    scsi_get_prot_op(task->sc) != SCSI_PROT_NORMAL) {
+	use_dma_key = (mem->dma_nents == 1 && !iser_always_reg &&
+		       scsi_get_prot_op(task->sc) == SCSI_PROT_NORMAL);
+
+	if (!use_dma_key) {
 		desc = device->reg_ops->reg_desc_get(ib_conn);
 		reg->mem_h = desc;
 	}
@@ -853,7 +858,7 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 	else
 		data_reg = &task->desc.data_reg;
 
-	err = iser_reg_data_sg(task, mem, desc, data_reg);
+	err = iser_reg_data_sg(task, mem, desc, use_dma_key, data_reg);
 	if (unlikely(err))
 		goto err_reg;
 
@@ -866,7 +871,8 @@ int iser_reg_rdma_mem(struct iscsi_iser_task *task,
 			if (unlikely(err))
 				goto err_reg;
 
-			err = iser_reg_prot_sg(task, mem, desc, prot_reg);
+			err = iser_reg_prot_sg(task, mem, desc,
+					       use_dma_key, prot_reg);
 			if (unlikely(err))
 				goto err_reg;
 		}
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index ae70cc1463ac..85132d867bc8 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -133,11 +133,15 @@ static int iser_create_device_ib_res(struct iser_device *device)
 			     (unsigned long)comp);
 	}
 
-	device->mr = ib_get_dma_mr(device->pd, IB_ACCESS_LOCAL_WRITE |
-				   IB_ACCESS_REMOTE_WRITE |
-				   IB_ACCESS_REMOTE_READ);
-	if (IS_ERR(device->mr))
-		goto dma_mr_err;
+	if (!iser_always_reg) {
+		int access = IB_ACCESS_LOCAL_WRITE |
+			     IB_ACCESS_REMOTE_WRITE |
+			     IB_ACCESS_REMOTE_READ;
+
+		device->mr = ib_get_dma_mr(device->pd, access);
+		if (IS_ERR(device->mr))
+			goto dma_mr_err;
+	}
 
 	INIT_IB_EVENT_HANDLER(&device->event_handler, device->ib_device,
 				iser_event_handler);
@@ -147,7 +151,8 @@ static int iser_create_device_ib_res(struct iser_device *device)
 	return 0;
 
 handler_err:
-	ib_dereg_mr(device->mr);
+	if (device->mr)
+		ib_dereg_mr(device->mr);
 dma_mr_err:
 	for (i = 0; i < device->comps_used; i++)
 		tasklet_kill(&device->comps[i].tasklet);
@@ -173,7 +178,6 @@ comps_err:
 static void iser_free_device_ib_res(struct iser_device *device)
 {
 	int i;
-	BUG_ON(device->mr == NULL);
 
 	for (i = 0; i < device->comps_used; i++) {
 		struct iser_comp *comp = &device->comps[i];
@@ -184,7 +188,8 @@ static void iser_free_device_ib_res(struct iser_device *device)
 	}
 
 	(void)ib_unregister_event_handler(&device->event_handler);
-	(void)ib_dereg_mr(device->mr);
+	if (device->mr)
+		(void)ib_dereg_mr(device->mr);
 	ib_dealloc_pd(device->pd);
 
 	kfree(device->comps);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 403bd29443b8..aa59037d7504 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -238,8 +238,6 @@ isert_alloc_rx_descriptors(struct isert_conn *isert_conn)
 		rx_sg->lkey = device->pd->local_dma_lkey;
 	}
 
-	isert_conn->rx_desc_head = 0;
-
 	return 0;
 
 dma_map_fail:
@@ -634,7 +632,7 @@ static void
 isert_init_conn(struct isert_conn *isert_conn)
 {
 	isert_conn->state = ISER_CONN_INIT;
-	INIT_LIST_HEAD(&isert_conn->accept_node);
+	INIT_LIST_HEAD(&isert_conn->node);
 	init_completion(&isert_conn->login_comp);
 	init_completion(&isert_conn->login_req_comp);
 	init_completion(&isert_conn->wait);
@@ -762,28 +760,15 @@ isert_connect_request(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 	ret = isert_rdma_post_recvl(isert_conn);
 	if (ret)
 		goto out_conn_dev;
-	/*
-	 * Obtain the second reference now before isert_rdma_accept() to
-	 * ensure that any initiator generated REJECT CM event that occurs
-	 * asynchronously won't drop the last reference until the error path
-	 * in iscsi_target_login_sess_out() does it's ->iscsit_free_conn() ->
-	 * isert_free_conn() -> isert_put_conn() -> kref_put().
-	 */
-	if (!kref_get_unless_zero(&isert_conn->kref)) {
-		isert_warn("conn %p connect_release is running\n", isert_conn);
-		goto out_conn_dev;
-	}
 
 	ret = isert_rdma_accept(isert_conn);
 	if (ret)
 		goto out_conn_dev;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	list_add_tail(&isert_conn->accept_node, &isert_np->np_accept_list);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	list_add_tail(&isert_conn->node, &isert_np->accepted);
+	mutex_unlock(&isert_np->mutex);
 
-	isert_info("np %p: Allow accept_np to continue\n", np);
-	up(&isert_np->np_sem);
 	return 0;
 
 out_conn_dev:
@@ -831,13 +816,21 @@ static void
 isert_connected_handler(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
+	struct isert_np *isert_np = cma_id->context;
 
 	isert_info("conn %p\n", isert_conn);
 
 	mutex_lock(&isert_conn->mutex);
-	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
-		isert_conn->state = ISER_CONN_UP;
+	isert_conn->state = ISER_CONN_UP;
+	kref_get(&isert_conn->kref);
 	mutex_unlock(&isert_conn->mutex);
+
+	mutex_lock(&isert_np->mutex);
+	list_move_tail(&isert_conn->node, &isert_np->pending);
+	mutex_unlock(&isert_np->mutex);
+
+	isert_info("np %p: Allow accept_np to continue\n", isert_np);
+	up(&isert_np->sem);
 }
 
 static void
@@ -903,14 +896,14 @@ isert_np_cma_handler(struct isert_np *isert_np,
 
 	switch (event) {
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
-		isert_np->np_cm_id = NULL;
+		isert_np->cm_id = NULL;
 		break;
 	case RDMA_CM_EVENT_ADDR_CHANGE:
-		isert_np->np_cm_id = isert_setup_id(isert_np);
-		if (IS_ERR(isert_np->np_cm_id)) {
+		isert_np->cm_id = isert_setup_id(isert_np);
+		if (IS_ERR(isert_np->cm_id)) {
 			isert_err("isert np %p setup id failed: %ld\n",
-				  isert_np, PTR_ERR(isert_np->np_cm_id));
-			isert_np->np_cm_id = NULL;
+				  isert_np, PTR_ERR(isert_np->cm_id));
+			isert_np->cm_id = NULL;
 		}
 		break;
 	default:
@@ -929,7 +922,7 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	struct isert_conn *isert_conn;
 	bool terminating = false;
 
-	if (isert_np->np_cm_id == cma_id)
+	if (isert_np->cm_id == cma_id)
 		return isert_np_cma_handler(cma_id->context, event);
 
 	isert_conn = cma_id->qp->qp_context;
@@ -945,13 +938,13 @@ isert_disconnected_handler(struct rdma_cm_id *cma_id,
 	if (terminating)
 		goto out;
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_conn->accept_node)) {
-		list_del_init(&isert_conn->accept_node);
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_conn->node)) {
+		list_del_init(&isert_conn->node);
 		isert_put_conn(isert_conn);
 		queue_work(isert_release_wq, &isert_conn->release_work);
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 out:
 	return 0;
@@ -962,6 +955,7 @@ isert_connect_error(struct rdma_cm_id *cma_id)
 {
 	struct isert_conn *isert_conn = cma_id->qp->qp_context;
 
+	list_del_init(&isert_conn->node);
 	isert_conn->cm_id = NULL;
 	isert_put_conn(isert_conn);
 
@@ -1006,35 +1000,51 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 }
 
 static int
-isert_post_recv(struct isert_conn *isert_conn, u32 count)
+isert_post_recvm(struct isert_conn *isert_conn, u32 count)
 {
 	struct ib_recv_wr *rx_wr, *rx_wr_failed;
 	int i, ret;
-	unsigned int rx_head = isert_conn->rx_desc_head;
 	struct iser_rx_desc *rx_desc;
 
 	for (rx_wr = isert_conn->rx_wr, i = 0; i < count; i++, rx_wr++) {
-		rx_desc		= &isert_conn->rx_descs[rx_head];
-		rx_wr->wr_id	= (uintptr_t)rx_desc;
-		rx_wr->sg_list	= &rx_desc->rx_sg;
-		rx_wr->num_sge	= 1;
-		rx_wr->next	= rx_wr + 1;
-		rx_head = (rx_head + 1) & (ISERT_QP_MAX_RECV_DTOS - 1);
+		rx_desc = &isert_conn->rx_descs[i];
+		rx_wr->wr_id = (uintptr_t)rx_desc;
+		rx_wr->sg_list = &rx_desc->rx_sg;
+		rx_wr->num_sge = 1;
+		rx_wr->next = rx_wr + 1;
 	}
-
 	rx_wr--;
 	rx_wr->next = NULL; /* mark end of work requests list */
 
 	isert_conn->post_recv_buf_count += count;
 	ret = ib_post_recv(isert_conn->qp, isert_conn->rx_wr,
-				&rx_wr_failed);
+			   &rx_wr_failed);
 	if (ret) {
 		isert_err("ib_post_recv() failed with ret: %d\n", ret);
 		isert_conn->post_recv_buf_count -= count;
-	} else {
-		isert_dbg("Posted %d RX buffers\n", count);
-		isert_conn->rx_desc_head = rx_head;
 	}
+
+	return ret;
+}
+
+static int
+isert_post_recv(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc)
+{
+	struct ib_recv_wr *rx_wr_failed, rx_wr;
+	int ret;
+
+	rx_wr.wr_id = (uintptr_t)rx_desc;
+	rx_wr.sg_list = &rx_desc->rx_sg;
+	rx_wr.num_sge = 1;
+	rx_wr.next = NULL;
+
+	isert_conn->post_recv_buf_count++;
+	ret = ib_post_recv(isert_conn->qp, &rx_wr, &rx_wr_failed);
+	if (ret) {
+		isert_err("ib_post_recv() failed with ret: %d\n", ret);
+		isert_conn->post_recv_buf_count--;
+	}
+
 	return ret;
 }
 
@@ -1205,7 +1215,8 @@ isert_put_login_tx(struct iscsi_conn *conn, struct iscsi_login *login,
 			if (ret)
 				return ret;
 
-			ret = isert_post_recv(isert_conn, ISERT_MIN_POSTED_RX);
+			ret = isert_post_recvm(isert_conn,
+					       ISERT_QP_MAX_RECV_DTOS);
 			if (ret)
 				return ret;
 
@@ -1278,7 +1289,7 @@ isert_rx_login_req(struct isert_conn *isert_conn)
 }
 
 static struct iscsi_cmd
-*isert_allocate_cmd(struct iscsi_conn *conn)
+*isert_allocate_cmd(struct iscsi_conn *conn, struct iser_rx_desc *rx_desc)
 {
 	struct isert_conn *isert_conn = conn->context;
 	struct isert_cmd *isert_cmd;
@@ -1292,6 +1303,7 @@ static struct iscsi_cmd
 	isert_cmd = iscsit_priv_cmd(cmd);
 	isert_cmd->conn = isert_conn;
 	isert_cmd->iscsi_cmd = cmd;
+	isert_cmd->rx_desc = rx_desc;
 
 	return cmd;
 }
@@ -1303,9 +1315,9 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 {
 	struct iscsi_conn *conn = isert_conn->conn;
 	struct iscsi_scsi_req *hdr = (struct iscsi_scsi_req *)buf;
-	struct scatterlist *sg;
 	int imm_data, imm_data_len, unsol_data, sg_nents, rc;
 	bool dump_payload = false;
+	unsigned int data_len;
 
 	rc = iscsit_setup_scsi_cmd(conn, cmd, buf);
 	if (rc < 0)
@@ -1314,7 +1326,10 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	imm_data = cmd->immediate_data;
 	imm_data_len = cmd->first_burst_len;
 	unsol_data = cmd->unsolicited_data;
+	data_len = cmd->se_cmd.data_length;
 
+	if (imm_data && imm_data_len == data_len)
+		cmd->se_cmd.se_cmd_flags |= SCF_PASSTHROUGH_SG_TO_MEM_NOALLOC;
 	rc = iscsit_process_scsi_cmd(conn, cmd, hdr);
 	if (rc < 0) {
 		return 0;
@@ -1326,13 +1341,20 @@ isert_handle_scsi_cmd(struct isert_conn *isert_conn,
 	if (!imm_data)
 		return 0;
 
-	sg = &cmd->se_cmd.t_data_sg[0];
-	sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
-
-	isert_dbg("Copying Immediate SG: %p sg_nents: %u from %p imm_data_len: %d\n",
-		  sg, sg_nents, &rx_desc->data[0], imm_data_len);
-
-	sg_copy_from_buffer(sg, sg_nents, &rx_desc->data[0], imm_data_len);
+	if (imm_data_len != data_len) {
+		sg_nents = max(1UL, DIV_ROUND_UP(imm_data_len, PAGE_SIZE));
+		sg_copy_from_buffer(cmd->se_cmd.t_data_sg, sg_nents,
+				    &rx_desc->data[0], imm_data_len);
+		isert_dbg("Copy Immediate sg_nents: %u imm_data_len: %d\n",
+			  sg_nents, imm_data_len);
+	} else {
+		sg_init_table(&isert_cmd->sg, 1);
+		cmd->se_cmd.t_data_sg = &isert_cmd->sg;
+		cmd->se_cmd.t_data_nents = 1;
+		sg_set_buf(&isert_cmd->sg, &rx_desc->data[0], imm_data_len);
+		isert_dbg("Transfer Immediate imm_data_len: %d\n",
+			  imm_data_len);
+	}
 
 	cmd->write_data_done += imm_data_len;
 
@@ -1407,6 +1429,15 @@ isert_handle_iscsi_dataout(struct isert_conn *isert_conn,
 	if (rc < 0)
 		return rc;
 
+	/*
+	 * multiple data-outs on the same command can arrive -
+	 * so post the buffer before hand
+	 */
+	rc = isert_post_recv(isert_conn, rx_desc);
+	if (rc) {
+		isert_err("ib_post_recv failed with %d\n", rc);
+		return rc;
+	}
 	return 0;
 }
 
@@ -1479,7 +1510,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 
 	switch (opcode) {
 	case ISCSI_OP_SCSI_CMD:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1493,7 +1524,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 					rx_desc, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_NOOP_OUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1506,7 +1537,7 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_SCSI_TMFUNC:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
@@ -1514,22 +1545,20 @@ isert_rx_opcode(struct isert_conn *isert_conn, struct iser_rx_desc *rx_desc,
 						(unsigned char *)hdr);
 		break;
 	case ISCSI_OP_LOGOUT:
-		cmd = isert_allocate_cmd(conn);
+		cmd = isert_allocate_cmd(conn, rx_desc);
 		if (!cmd)
 			break;
 
 		ret = iscsit_handle_logout_cmd(conn, cmd, (unsigned char *)hdr);
 		break;
 	case ISCSI_OP_TEXT:
-		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF) {
+		if (be32_to_cpu(hdr->ttt) != 0xFFFFFFFF)
 			cmd = iscsit_find_cmd_from_itt(conn, hdr->itt);
-			if (!cmd)
-				break;
-		} else {
-			cmd = isert_allocate_cmd(conn);
-			if (!cmd)
-				break;
-		}
+		else
+			cmd = isert_allocate_cmd(conn, rx_desc);
+
+		if (!cmd)
+			break;
 
 		isert_cmd = iscsit_priv_cmd(cmd);
 		ret = isert_handle_text_cmd(isert_conn, isert_cmd, cmd,
@@ -1589,7 +1618,7 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 	struct ib_device *ib_dev = isert_conn->cm_id->device;
 	struct iscsi_hdr *hdr;
 	u64 rx_dma;
-	int rx_buflen, outstanding;
+	int rx_buflen;
 
 	if ((char *)desc == isert_conn->login_req_buf) {
 		rx_dma = isert_conn->login_req_dma;
@@ -1629,22 +1658,6 @@ isert_rcv_completion(struct iser_rx_desc *desc,
 				      DMA_FROM_DEVICE);
 
 	isert_conn->post_recv_buf_count--;
-	isert_dbg("Decremented post_recv_buf_count: %d\n",
-		  isert_conn->post_recv_buf_count);
-
-	if ((char *)desc == isert_conn->login_req_buf)
-		return;
-
-	outstanding = isert_conn->post_recv_buf_count;
-	if (outstanding + ISERT_MIN_POSTED_RX <= ISERT_QP_MAX_RECV_DTOS) {
-		int err, count = min(ISERT_QP_MAX_RECV_DTOS - outstanding,
-				ISERT_MIN_POSTED_RX);
-		err = isert_post_recv(isert_conn, count);
-		if (err) {
-			isert_err("isert_post_recv() count: %d failed, %d\n",
-			       count, err);
-		}
-	}
 }
 
 static int
@@ -2156,6 +2169,12 @@ isert_post_response(struct isert_conn *isert_conn, struct isert_cmd *isert_cmd)
 	struct ib_send_wr *wr_failed;
 	int ret;
 
+	ret = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+	if (ret) {
+		isert_err("ib_post_recv failed with %d\n", ret);
+		return ret;
+	}
+
 	ret = ib_post_send(isert_conn->qp, &isert_cmd->tx_desc.send_wr,
 			   &wr_failed);
 	if (ret) {
@@ -2950,6 +2969,12 @@ isert_put_datain(struct iscsi_conn *conn, struct iscsi_cmd *cmd)
 				   &isert_cmd->tx_desc.send_wr);
 		isert_cmd->rdma_wr.s_send_wr.next = &isert_cmd->tx_desc.send_wr;
 		wr->send_wr_num += 1;
+
+		rc = isert_post_recv(isert_conn, isert_cmd->rx_desc);
+		if (rc) {
+			isert_err("ib_post_recv failed with %d\n", rc);
+			return rc;
+		}
 	}
 
 	rc = ib_post_send(isert_conn->qp, wr->send_wr, &wr_failed);
@@ -2999,9 +3024,16 @@ isert_get_dataout(struct iscsi_conn *conn, struct iscsi_cmd *cmd, bool recovery)
 static int
 isert_immediate_queue(struct iscsi_conn *conn, struct iscsi_cmd *cmd, int state)
 {
-	int ret;
+	struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+	int ret = 0;
 
 	switch (state) {
+	case ISTATE_REMOVE:
+		spin_lock_bh(&conn->cmd_lock);
+		list_del_init(&cmd->i_conn_node);
+		spin_unlock_bh(&conn->cmd_lock);
+		isert_put_cmd(isert_cmd, true);
+		break;
 	case ISTATE_SEND_NOPIN_WANT_RESPONSE:
 		ret = isert_put_nopin(cmd, conn, false);
 		break;
@@ -3106,10 +3138,10 @@ isert_setup_np(struct iscsi_np *np,
 		isert_err("Unable to allocate struct isert_np\n");
 		return -ENOMEM;
 	}
-	sema_init(&isert_np->np_sem, 0);
-	mutex_init(&isert_np->np_accept_mutex);
-	INIT_LIST_HEAD(&isert_np->np_accept_list);
-	init_completion(&isert_np->np_login_comp);
+	sema_init(&isert_np->sem, 0);
+	mutex_init(&isert_np->mutex);
+	INIT_LIST_HEAD(&isert_np->accepted);
+	INIT_LIST_HEAD(&isert_np->pending);
 	isert_np->np = np;
 
 	/*
@@ -3125,7 +3157,7 @@ isert_setup_np(struct iscsi_np *np,
 		goto out;
 	}
 
-	isert_np->np_cm_id = isert_lid;
+	isert_np->cm_id = isert_lid;
 	np->np_context = isert_np;
 
 	return 0;
@@ -3214,7 +3246,7 @@ isert_accept_np(struct iscsi_np *np, struct iscsi_conn *conn)
 	int ret;
 
 accept_wait:
-	ret = down_interruptible(&isert_np->np_sem);
+	ret = down_interruptible(&isert_np->sem);
 	if (ret)
 		return -ENODEV;
 
@@ -3231,15 +3263,15 @@ accept_wait:
 	}
 	spin_unlock_bh(&np->np_thread_lock);
 
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (list_empty(&isert_np->np_accept_list)) {
-		mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_lock(&isert_np->mutex);
+	if (list_empty(&isert_np->pending)) {
+		mutex_unlock(&isert_np->mutex);
 		goto accept_wait;
 	}
-	isert_conn = list_first_entry(&isert_np->np_accept_list,
-			struct isert_conn, accept_node);
-	list_del_init(&isert_conn->accept_node);
-	mutex_unlock(&isert_np->np_accept_mutex);
+	isert_conn = list_first_entry(&isert_np->pending,
+			struct isert_conn, node);
+	list_del_init(&isert_conn->node);
+	mutex_unlock(&isert_np->mutex);
 
 	conn->context = isert_conn;
 	isert_conn->conn = conn;
@@ -3257,28 +3289,39 @@ isert_free_np(struct iscsi_np *np)
 	struct isert_np *isert_np = np->np_context;
 	struct isert_conn *isert_conn, *n;
 
-	if (isert_np->np_cm_id)
-		rdma_destroy_id(isert_np->np_cm_id);
+	if (isert_np->cm_id)
+		rdma_destroy_id(isert_np->cm_id);
 
 	/*
 	 * FIXME: At this point we don't have a good way to insure
 	 * that at this point we don't have hanging connections that
 	 * completed RDMA establishment but didn't start iscsi login
 	 * process. So work-around this by cleaning up what ever piled
-	 * up in np_accept_list.
+	 * up in accepted and pending lists.
 	 */
-	mutex_lock(&isert_np->np_accept_mutex);
-	if (!list_empty(&isert_np->np_accept_list)) {
-		isert_info("Still have isert connections, cleaning up...\n");
+	mutex_lock(&isert_np->mutex);
+	if (!list_empty(&isert_np->pending)) {
+		isert_info("Still have isert pending connections\n");
+		list_for_each_entry_safe(isert_conn, n,
+					 &isert_np->pending,
+					 node) {
+			isert_info("cleaning isert_conn %p state (%d)\n",
+				   isert_conn, isert_conn->state);
+			isert_connect_release(isert_conn);
+		}
+	}
+
+	if (!list_empty(&isert_np->accepted)) {
+		isert_info("Still have isert accepted connections\n");
 		list_for_each_entry_safe(isert_conn, n,
-					 &isert_np->np_accept_list,
-					 accept_node) {
+					 &isert_np->accepted,
+					 node) {
 			isert_info("cleaning isert_conn %p state (%d)\n",
 				   isert_conn, isert_conn->state);
 			isert_connect_release(isert_conn);
 		}
 	}
-	mutex_unlock(&isert_np->np_accept_mutex);
+	mutex_unlock(&isert_np->mutex);
 
 	np->np_context = NULL;
 	kfree(isert_np);
@@ -3345,6 +3388,41 @@ isert_wait4flush(struct isert_conn *isert_conn)
 	wait_for_completion(&isert_conn->wait_comp_err);
 }
 
+/**
+ * isert_put_unsol_pending_cmds() - Drop commands waiting for
+ *     unsolicitate dataout
+ * @conn:    iscsi connection
+ *
+ * We might still have commands that are waiting for unsolicited
+ * dataouts messages. We must put the extra reference on those
+ * before blocking on the target_wait_for_session_cmds
+ */
+static void
+isert_put_unsol_pending_cmds(struct iscsi_conn *conn)
+{
+	struct iscsi_cmd *cmd, *tmp;
+	static LIST_HEAD(drop_cmd_list);
+
+	spin_lock_bh(&conn->cmd_lock);
+	list_for_each_entry_safe(cmd, tmp, &conn->conn_cmd_list, i_conn_node) {
+		if ((cmd->cmd_flags & ICF_NON_IMMEDIATE_UNSOLICITED_DATA) &&
+		    (cmd->write_data_done < conn->sess->sess_ops->FirstBurstLength) &&
+		    (cmd->write_data_done < cmd->se_cmd.data_length))
+			list_move_tail(&cmd->i_conn_node, &drop_cmd_list);
+	}
+	spin_unlock_bh(&conn->cmd_lock);
+
+	list_for_each_entry_safe(cmd, tmp, &drop_cmd_list, i_conn_node) {
+		list_del_init(&cmd->i_conn_node);
+		if (cmd->i_state != ISTATE_REMOVE) {
+			struct isert_cmd *isert_cmd = iscsit_priv_cmd(cmd);
+
+			isert_info("conn %p dropping cmd %p\n", conn, cmd);
+			isert_put_cmd(isert_cmd, true);
+		}
+	}
+}
+
 static void isert_wait_conn(struct iscsi_conn *conn)
 {
 	struct isert_conn *isert_conn = conn->context;
@@ -3363,8 +3441,9 @@ static void isert_wait_conn(struct iscsi_conn *conn)
 	isert_conn_terminate(isert_conn);
 	mutex_unlock(&isert_conn->mutex);
 
-	isert_wait4cmds(conn);
 	isert_wait4flush(isert_conn);
+	isert_put_unsol_pending_cmds(conn);
+	isert_wait4cmds(conn);
 	isert_wait4logout(isert_conn);
 
 	queue_work(isert_release_wq, &isert_conn->release_work);
diff --git a/drivers/infiniband/ulp/isert/ib_isert.h b/drivers/infiniband/ulp/isert/ib_isert.h
index 6a04ba3c0f72..c5b99bcecbcf 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.h
+++ b/drivers/infiniband/ulp/isert/ib_isert.h
@@ -113,7 +113,6 @@ enum {
 };
 
 struct isert_rdma_wr {
-	struct list_head	wr_list;
 	struct isert_cmd	*isert_cmd;
 	enum iser_ib_op_code	iser_ib_op;
 	struct ib_sge		*ib_sge;
@@ -134,14 +133,13 @@ struct isert_cmd {
 	uint64_t		write_va;
 	u64			pdu_buf_dma;
 	u32			pdu_buf_len;
-	u32			read_va_off;
-	u32			write_va_off;
-	u32			rdma_wr_num;
 	struct isert_conn	*conn;
 	struct iscsi_cmd	*iscsi_cmd;
 	struct iser_tx_desc	tx_desc;
+	struct iser_rx_desc	*rx_desc;
 	struct isert_rdma_wr	rdma_wr;
 	struct work_struct	comp_work;
+	struct scatterlist	sg;
 };
 
 struct isert_device;
@@ -159,11 +157,10 @@ struct isert_conn {
 	u64			login_req_dma;
 	int			login_req_len;
 	u64			login_rsp_dma;
-	unsigned int		rx_desc_head;
 	struct iser_rx_desc	*rx_descs;
-	struct ib_recv_wr	rx_wr[ISERT_MIN_POSTED_RX];
+	struct ib_recv_wr	rx_wr[ISERT_QP_MAX_RECV_DTOS];
 	struct iscsi_conn	*conn;
-	struct list_head	accept_node;
+	struct list_head	node;
 	struct completion	login_comp;
 	struct completion	login_req_comp;
 	struct iser_tx_desc	login_tx_desc;
@@ -222,9 +219,9 @@ struct isert_device {
 
 struct isert_np {
 	struct iscsi_np         *np;
-	struct semaphore	np_sem;
-	struct rdma_cm_id	*np_cm_id;
-	struct mutex		np_accept_mutex;
-	struct list_head	np_accept_list;
-	struct completion	np_login_comp;
+	struct semaphore	sem;
+	struct rdma_cm_id	*cm_id;
+	struct mutex		mutex;
+	struct list_head	accepted;
+	struct list_head	pending;
 };
diff --git a/drivers/input/joystick/Kconfig b/drivers/input/joystick/Kconfig
index 56eb471b5576..4215b5382092 100644
--- a/drivers/input/joystick/Kconfig
+++ b/drivers/input/joystick/Kconfig
@@ -196,6 +196,7 @@ config JOYSTICK_TWIDJOY
 config JOYSTICK_ZHENHUA
 	tristate "5-byte Zhenhua RC transmitter"
 	select SERIO
+	select BITREVERSE
 	help
 	  Say Y here if you have a Zhen Hua PPM-4CH transmitter which is
 	  supplied with a ready to fly micro electric indoor helicopters
diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig
index 4664c2a96c67..d9da766719c8 100644
--- a/drivers/iommu/Kconfig
+++ b/drivers/iommu/Kconfig
@@ -43,7 +43,7 @@ config IOMMU_IO_PGTABLE_LPAE_SELFTEST
 endmenu
 
 config IOMMU_IOVA
-	bool
+	tristate
 
 config OF_IOMMU
        def_bool y
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 2d7349a3ee14..041bc1810a86 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -3215,6 +3215,8 @@ static struct iova *intel_alloc_iova(struct device *dev,
 
 	/* Restrict dma_mask to the width that the iommu can handle */
 	dma_mask = min_t(uint64_t, DOMAIN_MAX_ADDR(domain->gaw), dma_mask);
+	/* Ensure we reserve the whole size-aligned region */
+	nrpages = __roundup_pow_of_two(nrpages);
 
 	if (!dmar_forcedac && dma_mask > DMA_BIT_MASK(32)) {
 		/*
@@ -3711,7 +3713,7 @@ static inline int iommu_devinfo_cache_init(void)
 static int __init iommu_init_mempool(void)
 {
 	int ret;
-	ret = iommu_iova_cache_init();
+	ret = iova_cache_get();
 	if (ret)
 		return ret;
 
@@ -3725,7 +3727,7 @@ static int __init iommu_init_mempool(void)
 
 	kmem_cache_destroy(iommu_domain_cache);
 domain_error:
-	iommu_iova_cache_destroy();
+	iova_cache_put();
 
 	return -ENOMEM;
 }
@@ -3734,7 +3736,7 @@ static void __init iommu_exit_mempool(void)
 {
 	kmem_cache_destroy(iommu_devinfo_cache);
 	kmem_cache_destroy(iommu_domain_cache);
-	iommu_iova_cache_destroy();
+	iova_cache_put();
 }
 
 static void quirk_ioat_snb_local_iommu(struct pci_dev *pdev)
diff --git a/drivers/iommu/iova.c b/drivers/iommu/iova.c
index b7c3d923f3e1..fa0adef32bd6 100644
--- a/drivers/iommu/iova.c
+++ b/drivers/iommu/iova.c
@@ -18,42 +18,9 @@
  */
 
 #include <linux/iova.h>
+#include <linux/module.h>
 #include <linux/slab.h>
 
-static struct kmem_cache *iommu_iova_cache;
-
-int iommu_iova_cache_init(void)
-{
-	int ret = 0;
-
-	iommu_iova_cache = kmem_cache_create("iommu_iova",
-					 sizeof(struct iova),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-					 NULL);
-	if (!iommu_iova_cache) {
-		pr_err("Couldn't create iova cache\n");
-		ret = -ENOMEM;
-	}
-
-	return ret;
-}
-
-void iommu_iova_cache_destroy(void)
-{
-	kmem_cache_destroy(iommu_iova_cache);
-}
-
-struct iova *alloc_iova_mem(void)
-{
-	return kmem_cache_alloc(iommu_iova_cache, GFP_ATOMIC);
-}
-
-void free_iova_mem(struct iova *iova)
-{
-	kmem_cache_free(iommu_iova_cache, iova);
-}
-
 void
 init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	unsigned long start_pfn, unsigned long pfn_32bit)
@@ -72,6 +39,7 @@ init_iova_domain(struct iova_domain *iovad, unsigned long granule,
 	iovad->start_pfn = start_pfn;
 	iovad->dma_32bit_pfn = pfn_32bit;
 }
+EXPORT_SYMBOL_GPL(init_iova_domain);
 
 static struct rb_node *
 __get_cached_rbnode(struct iova_domain *iovad, unsigned long *limit_pfn)
@@ -120,19 +88,14 @@ __cached_rbnode_delete_update(struct iova_domain *iovad, struct iova *free)
 	}
 }
 
-/* Computes the padding size required, to make the
- * the start address naturally aligned on its size
+/*
+ * Computes the padding size required, to make the start address
+ * naturally aligned on the power-of-two order of its size
  */
-static int
-iova_get_pad_size(int size, unsigned int limit_pfn)
+static unsigned int
+iova_get_pad_size(unsigned int size, unsigned int limit_pfn)
 {
-	unsigned int pad_size = 0;
-	unsigned int order = ilog2(size);
-
-	if (order)
-		pad_size = (limit_pfn + 1) % (1 << order);
-
-	return pad_size;
+	return (limit_pfn + 1 - size) & (__roundup_pow_of_two(size) - 1);
 }
 
 static int __alloc_and_insert_iova_range(struct iova_domain *iovad,
@@ -242,6 +205,57 @@ iova_insert_rbtree(struct rb_root *root, struct iova *iova)
 	rb_insert_color(&iova->node, root);
 }
 
+static struct kmem_cache *iova_cache;
+static unsigned int iova_cache_users;
+static DEFINE_MUTEX(iova_cache_mutex);
+
+struct iova *alloc_iova_mem(void)
+{
+	return kmem_cache_alloc(iova_cache, GFP_ATOMIC);
+}
+EXPORT_SYMBOL(alloc_iova_mem);
+
+void free_iova_mem(struct iova *iova)
+{
+	kmem_cache_free(iova_cache, iova);
+}
+EXPORT_SYMBOL(free_iova_mem);
+
+int iova_cache_get(void)
+{
+	mutex_lock(&iova_cache_mutex);
+	if (!iova_cache_users) {
+		iova_cache = kmem_cache_create(
+			"iommu_iova", sizeof(struct iova), 0,
+			SLAB_HWCACHE_ALIGN, NULL);
+		if (!iova_cache) {
+			mutex_unlock(&iova_cache_mutex);
+			printk(KERN_ERR "Couldn't create iova cache\n");
+			return -ENOMEM;
+		}
+	}
+
+	iova_cache_users++;
+	mutex_unlock(&iova_cache_mutex);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iova_cache_get);
+
+void iova_cache_put(void)
+{
+	mutex_lock(&iova_cache_mutex);
+	if (WARN_ON(!iova_cache_users)) {
+		mutex_unlock(&iova_cache_mutex);
+		return;
+	}
+	iova_cache_users--;
+	if (!iova_cache_users)
+		kmem_cache_destroy(iova_cache);
+	mutex_unlock(&iova_cache_mutex);
+}
+EXPORT_SYMBOL_GPL(iova_cache_put);
+
 /**
  * alloc_iova - allocates an iova
  * @iovad: - iova domain in question
@@ -265,12 +279,6 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
 	if (!new_iova)
 		return NULL;
 
-	/* If size aligned is set then round the size to
-	 * to next power of two.
-	 */
-	if (size_aligned)
-		size = __roundup_pow_of_two(size);
-
 	ret = __alloc_and_insert_iova_range(iovad, size, limit_pfn,
 			new_iova, size_aligned);
 
@@ -281,6 +289,7 @@ alloc_iova(struct iova_domain *iovad, unsigned long size,
 
 	return new_iova;
 }
+EXPORT_SYMBOL_GPL(alloc_iova);
 
 /**
  * find_iova - find's an iova for a given pfn
@@ -321,6 +330,7 @@ struct iova *find_iova(struct iova_domain *iovad, unsigned long pfn)
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(find_iova);
 
 /**
  * __free_iova - frees the given iova
@@ -339,6 +349,7 @@ __free_iova(struct iova_domain *iovad, struct iova *iova)
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 	free_iova_mem(iova);
 }
+EXPORT_SYMBOL_GPL(__free_iova);
 
 /**
  * free_iova - finds and frees the iova for a given pfn
@@ -356,6 +367,7 @@ free_iova(struct iova_domain *iovad, unsigned long pfn)
 		__free_iova(iovad, iova);
 
 }
+EXPORT_SYMBOL_GPL(free_iova);
 
 /**
  * put_iova_domain - destroys the iova doamin
@@ -378,6 +390,7 @@ void put_iova_domain(struct iova_domain *iovad)
 	}
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 }
+EXPORT_SYMBOL_GPL(put_iova_domain);
 
 static int
 __is_range_overlap(struct rb_node *node,
@@ -467,6 +480,7 @@ finish:
 	spin_unlock_irqrestore(&iovad->iova_rbtree_lock, flags);
 	return iova;
 }
+EXPORT_SYMBOL_GPL(reserve_iova);
 
 /**
  * copy_reserved_iova - copies the reserved between domains
@@ -493,6 +507,7 @@ copy_reserved_iova(struct iova_domain *from, struct iova_domain *to)
 	}
 	spin_unlock_irqrestore(&from->iova_rbtree_lock, flags);
 }
+EXPORT_SYMBOL_GPL(copy_reserved_iova);
 
 struct iova *
 split_and_remove_iova(struct iova_domain *iovad, struct iova *iova,
@@ -534,3 +549,6 @@ error:
 		free_iova_mem(prev);
 	return NULL;
 }
+
+MODULE_AUTHOR("Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/irqchip/irq-atmel-aic5.c b/drivers/irqchip/irq-atmel-aic5.c
index 9da9942ac83c..f6d680485bee 100644
--- a/drivers/irqchip/irq-atmel-aic5.c
+++ b/drivers/irqchip/irq-atmel-aic5.c
@@ -88,28 +88,36 @@ static void aic5_mask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Disable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Disable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IDCR);
 	gc->mask_cache &= ~d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static void aic5_unmask(struct irq_data *d)
 {
 	struct irq_domain *domain = d->domain;
 	struct irq_domain_chip_generic *dgc = domain->gc;
-	struct irq_chip_generic *gc = dgc->gc[0];
+	struct irq_chip_generic *bgc = dgc->gc[0];
+	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
 
-	/* Enable interrupt on AIC5 */
-	irq_gc_lock(gc);
+	/*
+	 * Enable interrupt on AIC5. We always take the lock of the
+	 * first irq chip as all chips share the same registers.
+	 */
+	irq_gc_lock(bgc);
 	irq_reg_writel(gc, d->hwirq, AT91_AIC5_SSR);
 	irq_reg_writel(gc, 1, AT91_AIC5_IECR);
 	gc->mask_cache |= d->mask;
-	irq_gc_unlock(gc);
+	irq_gc_unlock(bgc);
 }
 
 static int aic5_retrigger(struct irq_data *d)
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index af2f16bb8a94..aeaa061f0dbf 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -320,6 +320,14 @@ static void gic_handle_shared_int(bool chained)
 		intrmask[i] = gic_read(intrmask_reg);
 		pending_reg += gic_reg_step;
 		intrmask_reg += gic_reg_step;
+
+		if (!config_enabled(CONFIG_64BIT) || mips_cm_is64)
+			continue;
+
+		pending[i] |= (u64)gic_read(pending_reg) << 32;
+		intrmask[i] |= (u64)gic_read(intrmask_reg) << 32;
+		pending_reg += gic_reg_step;
+		intrmask_reg += gic_reg_step;
 	}
 
 	bitmap_and(pending, pending, intrmask, gic_shared_intrs);
@@ -426,7 +434,7 @@ static int gic_set_affinity(struct irq_data *d, const struct cpumask *cpumask,
 	spin_lock_irqsave(&gic_lock, flags);
 
 	/* Re-route this IRQ */
-	gic_map_to_vpe(irq, cpumask_first(&tmp));
+	gic_map_to_vpe(irq, mips_cm_vp_id(cpumask_first(&tmp)));
 
 	/* Update the pcpu_masks */
 	for (i = 0; i < NR_CPUS; i++)
@@ -599,7 +607,7 @@ static __init void gic_ipi_init_one(unsigned int intr, int cpu,
 				      GIC_SHARED_TO_HWIRQ(intr));
 	int i;
 
-	gic_map_to_vpe(intr, cpu);
+	gic_map_to_vpe(intr, mips_cm_vp_id(cpu));
 	for (i = 0; i < NR_CPUS; i++)
 		clear_bit(intr, pcpu_masks[i].pcpu_mask);
 	set_bit(intr, pcpu_masks[cpu].pcpu_mask);
diff --git a/drivers/misc/mei/debugfs.c b/drivers/misc/mei/debugfs.c
index 4b469cf9e60f..8504dbeacd3b 100644
--- a/drivers/misc/mei/debugfs.c
+++ b/drivers/misc/mei/debugfs.c
@@ -204,6 +204,8 @@ int mei_dbgfs_register(struct mei_device *dev, const char *name)
 	if (!dir)
 		return -ENOMEM;
 
+	dev->dbgfs_dir = dir;
+
 	f = debugfs_create_file("meclients", S_IRUSR, dir,
 				dev, &mei_dbgfs_fops_meclients);
 	if (!f) {
@@ -228,7 +230,6 @@ int mei_dbgfs_register(struct mei_device *dev, const char *name)
 		dev_err(dev->dev, "allow_fixed_address: registration failed\n");
 		goto err;
 	}
-	dev->dbgfs_dir = dir;
 	return 0;
 err:
 	mei_dbgfs_deregister(dev);
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index 0520064dc33b..a3eb20bdcd97 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -134,9 +134,11 @@ void mmc_request_done(struct mmc_host *host, struct mmc_request *mrq)
 	int err = cmd->error;
 
 	/* Flag re-tuning needed on CRC errors */
-	if (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
+	if ((cmd->opcode != MMC_SEND_TUNING_BLOCK &&
+	    cmd->opcode != MMC_SEND_TUNING_BLOCK_HS200) &&
+	    (err == -EILSEQ || (mrq->sbc && mrq->sbc->error == -EILSEQ) ||
 	    (mrq->data && mrq->data->error == -EILSEQ) ||
-	    (mrq->stop && mrq->stop->error == -EILSEQ))
+	    (mrq->stop && mrq->stop->error == -EILSEQ)))
 		mmc_retune_needed(host);
 
 	if (err && cmd->retries && mmc_host_is_spi(host)) {
diff --git a/drivers/mmc/core/host.c b/drivers/mmc/core/host.c
index abd933b7029b..5466f25f0281 100644
--- a/drivers/mmc/core/host.c
+++ b/drivers/mmc/core/host.c
@@ -457,7 +457,7 @@ int mmc_of_parse(struct mmc_host *host)
 					   0, &cd_gpio_invert);
 		if (!ret)
 			dev_info(host->parent, "Got CD GPIO\n");
-		else if (ret != -ENOENT)
+		else if (ret != -ENOENT && ret != -ENOSYS)
 			return ret;
 
 		/*
@@ -481,7 +481,7 @@ int mmc_of_parse(struct mmc_host *host)
 	ret = mmc_gpiod_request_ro(host, "wp", 0, false, 0, &ro_gpio_invert);
 	if (!ret)
 		dev_info(host->parent, "Got WP GPIO\n");
-	else if (ret != -ENOENT)
+	else if (ret != -ENOENT && ret != -ENOSYS)
 		return ret;
 
 	if (of_property_read_bool(np, "disable-wp"))
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 1420f29628c7..8cadd74e8407 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -28,6 +28,7 @@
 #include <linux/clk.h>
 #include <linux/err.h>
 #include <linux/mmc/host.h>
+#include <linux/mmc/slot-gpio.h>
 #include <linux/io.h>
 #include <linux/regulator/consumer.h>
 #include <linux/gpio.h>
@@ -454,12 +455,8 @@ static int pxamci_get_ro(struct mmc_host *mmc)
 {
 	struct pxamci_host *host = mmc_priv(mmc);
 
-	if (host->pdata && gpio_is_valid(host->pdata->gpio_card_ro)) {
-		if (host->pdata->gpio_card_ro_invert)
-			return !gpio_get_value(host->pdata->gpio_card_ro);
-		else
-			return gpio_get_value(host->pdata->gpio_card_ro);
-	}
+	if (host->pdata && gpio_is_valid(host->pdata->gpio_card_ro))
+		return mmc_gpio_get_ro(mmc);
 	if (host->pdata && host->pdata->get_ro)
 		return !!host->pdata->get_ro(mmc_dev(mmc));
 	/*
@@ -551,6 +548,7 @@ static void pxamci_enable_sdio_irq(struct mmc_host *host, int enable)
 
 static const struct mmc_host_ops pxamci_ops = {
 	.request		= pxamci_request,
+	.get_cd			= mmc_gpio_get_cd,
 	.get_ro			= pxamci_get_ro,
 	.set_ios		= pxamci_set_ios,
 	.enable_sdio_irq	= pxamci_enable_sdio_irq,
@@ -790,37 +788,31 @@ static int pxamci_probe(struct platform_device *pdev)
 		gpio_power = host->pdata->gpio_power;
 	}
 	if (gpio_is_valid(gpio_power)) {
-		ret = gpio_request(gpio_power, "mmc card power");
+		ret = devm_gpio_request(&pdev->dev, gpio_power,
+					"mmc card power");
 		if (ret) {
-			dev_err(&pdev->dev, "Failed requesting gpio_power %d\n", gpio_power);
+			dev_err(&pdev->dev, "Failed requesting gpio_power %d\n",
+				gpio_power);
 			goto out;
 		}
 		gpio_direction_output(gpio_power,
 				      host->pdata->gpio_power_invert);
 	}
-	if (gpio_is_valid(gpio_ro)) {
-		ret = gpio_request(gpio_ro, "mmc card read only");
-		if (ret) {
-			dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
-			goto err_gpio_ro;
-		}
-		gpio_direction_input(gpio_ro);
+	if (gpio_is_valid(gpio_ro))
+		ret = mmc_gpio_request_ro(mmc, gpio_ro);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed requesting gpio_ro %d\n", gpio_ro);
+		goto out;
+	} else {
+		mmc->caps |= host->pdata->gpio_card_ro_invert ?
+			MMC_CAP2_RO_ACTIVE_HIGH : 0;
 	}
-	if (gpio_is_valid(gpio_cd)) {
-		ret = gpio_request(gpio_cd, "mmc card detect");
-		if (ret) {
-			dev_err(&pdev->dev, "Failed requesting gpio_cd %d\n", gpio_cd);
-			goto err_gpio_cd;
-		}
-		gpio_direction_input(gpio_cd);
 
-		ret = request_irq(gpio_to_irq(gpio_cd), pxamci_detect_irq,
-				  IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING,
-				  "mmc card detect", mmc);
-		if (ret) {
-			dev_err(&pdev->dev, "failed to request card detect IRQ\n");
-			goto err_request_irq;
-		}
+	if (gpio_is_valid(gpio_cd))
+		ret = mmc_gpio_request_cd(mmc, gpio_cd, 0);
+	if (ret) {
+		dev_err(&pdev->dev, "Failed requesting gpio_cd %d\n", gpio_cd);
+		goto out;
 	}
 
 	if (host->pdata && host->pdata->init)
@@ -835,13 +827,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	return 0;
 
-err_request_irq:
-	gpio_free(gpio_cd);
-err_gpio_cd:
-	gpio_free(gpio_ro);
-err_gpio_ro:
-	gpio_free(gpio_power);
- out:
+out:
 	if (host) {
 		if (host->dma_chan_rx)
 			dma_release_channel(host->dma_chan_rx);
@@ -873,14 +859,6 @@ static int pxamci_remove(struct platform_device *pdev)
 			gpio_ro = host->pdata->gpio_card_ro;
 			gpio_power = host->pdata->gpio_power;
 		}
-		if (gpio_is_valid(gpio_cd)) {
-			free_irq(gpio_to_irq(gpio_cd), mmc);
-			gpio_free(gpio_cd);
-		}
-		if (gpio_is_valid(gpio_ro))
-			gpio_free(gpio_ro);
-		if (gpio_is_valid(gpio_power))
-			gpio_free(gpio_power);
 		if (host->vcc)
 			regulator_put(host->vcc);
 
diff --git a/drivers/mmc/host/sunxi-mmc.c b/drivers/mmc/host/sunxi-mmc.c
index a7b7a6771598..b981b8552e43 100644
--- a/drivers/mmc/host/sunxi-mmc.c
+++ b/drivers/mmc/host/sunxi-mmc.c
@@ -210,6 +210,16 @@
 #define SDXC_IDMAC_DES0_CES	BIT(30) /* card error summary */
 #define SDXC_IDMAC_DES0_OWN	BIT(31) /* 1-idma owns it, 0-host owns it */
 
+#define SDXC_CLK_400K		0
+#define SDXC_CLK_25M		1
+#define SDXC_CLK_50M		2
+#define SDXC_CLK_50M_DDR	3
+
+struct sunxi_mmc_clk_delay {
+	u32 output;
+	u32 sample;
+};
+
 struct sunxi_idma_des {
 	u32	config;
 	u32	buf_size;
@@ -229,6 +239,7 @@ struct sunxi_mmc_host {
 	struct clk	*clk_mmc;
 	struct clk	*clk_sample;
 	struct clk	*clk_output;
+	const struct sunxi_mmc_clk_delay *clk_delays;
 
 	/* irq */
 	spinlock_t	lock;
@@ -654,25 +665,19 @@ static int sunxi_mmc_clk_set_rate(struct sunxi_mmc_host *host,
 
 	/* determine delays */
 	if (rate <= 400000) {
-		oclk_dly = 180;
-		sclk_dly = 42;
+		oclk_dly = host->clk_delays[SDXC_CLK_400K].output;
+		sclk_dly = host->clk_delays[SDXC_CLK_400K].sample;
 	} else if (rate <= 25000000) {
-		oclk_dly = 180;
-		sclk_dly = 75;
+		oclk_dly = host->clk_delays[SDXC_CLK_25M].output;
+		sclk_dly = host->clk_delays[SDXC_CLK_25M].sample;
 	} else if (rate <= 50000000) {
 		if (ios->timing == MMC_TIMING_UHS_DDR50) {
-			oclk_dly = 60;
-			sclk_dly = 120;
+			oclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].output;
+			sclk_dly = host->clk_delays[SDXC_CLK_50M_DDR].sample;
 		} else {
-			oclk_dly = 90;
-			sclk_dly = 150;
+			oclk_dly = host->clk_delays[SDXC_CLK_50M].output;
+			sclk_dly = host->clk_delays[SDXC_CLK_50M].sample;
 		}
-	} else if (rate <= 100000000) {
-		oclk_dly = 6;
-		sclk_dly = 24;
-	} else if (rate <= 200000000) {
-		oclk_dly = 3;
-		sclk_dly = 12;
 	} else {
 		return -EINVAL;
 	}
@@ -871,6 +876,7 @@ static void sunxi_mmc_request(struct mmc_host *mmc, struct mmc_request *mrq)
 static const struct of_device_id sunxi_mmc_of_match[] = {
 	{ .compatible = "allwinner,sun4i-a10-mmc", },
 	{ .compatible = "allwinner,sun5i-a13-mmc", },
+	{ .compatible = "allwinner,sun9i-a80-mmc", },
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, sunxi_mmc_of_match);
@@ -884,6 +890,20 @@ static struct mmc_host_ops sunxi_mmc_ops = {
 	.hw_reset	 = sunxi_mmc_hw_reset,
 };
 
+static const struct sunxi_mmc_clk_delay sunxi_mmc_clk_delays[] = {
+	[SDXC_CLK_400K]		= { .output = 180, .sample = 180 },
+	[SDXC_CLK_25M]		= { .output = 180, .sample =  75 },
+	[SDXC_CLK_50M]		= { .output =  90, .sample = 120 },
+	[SDXC_CLK_50M_DDR]	= { .output =  60, .sample = 120 },
+};
+
+static const struct sunxi_mmc_clk_delay sun9i_mmc_clk_delays[] = {
+	[SDXC_CLK_400K]		= { .output = 180, .sample = 180 },
+	[SDXC_CLK_25M]		= { .output = 180, .sample =  75 },
+	[SDXC_CLK_50M]		= { .output = 150, .sample = 120 },
+	[SDXC_CLK_50M_DDR]	= { .output =  90, .sample = 120 },
+};
+
 static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
 				      struct platform_device *pdev)
 {
@@ -895,6 +915,11 @@ static int sunxi_mmc_resource_request(struct sunxi_mmc_host *host,
 	else
 		host->idma_des_size_bits = 16;
 
+	if (of_device_is_compatible(np, "allwinner,sun9i-a80-mmc"))
+		host->clk_delays = sun9i_mmc_clk_delays;
+	else
+		host->clk_delays = sunxi_mmc_clk_delays;
+
 	ret = mmc_regulator_get_supply(host->mmc);
 	if (ret) {
 		if (ret != -EPROBE_DEFER)
diff --git a/drivers/mtd/ubi/io.c b/drivers/mtd/ubi/io.c
index 5bbd1f094f4e..1fc23e48fe8e 100644
--- a/drivers/mtd/ubi/io.c
+++ b/drivers/mtd/ubi/io.c
@@ -926,6 +926,11 @@ static int validate_vid_hdr(const struct ubi_device *ubi,
 		goto bad;
 	}
 
+	if (data_size > ubi->leb_size) {
+		ubi_err(ubi, "bad data_size");
+		goto bad;
+	}
+
 	if (vol_type == UBI_VID_STATIC) {
 		/*
 		 * Although from high-level point of view static volumes may
diff --git a/drivers/mtd/ubi/vtbl.c b/drivers/mtd/ubi/vtbl.c
index 80bdd5b88bac..d85c19762160 100644
--- a/drivers/mtd/ubi/vtbl.c
+++ b/drivers/mtd/ubi/vtbl.c
@@ -649,6 +649,7 @@ static int init_volumes(struct ubi_device *ubi,
 		if (ubi->corr_peb_count)
 			ubi_err(ubi, "%d PEBs are corrupted and not used",
 				ubi->corr_peb_count);
+		return -ENOSPC;
 	}
 	ubi->rsvd_pebs += reserved_pebs;
 	ubi->avail_pebs -= reserved_pebs;
diff --git a/drivers/mtd/ubi/wl.c b/drivers/mtd/ubi/wl.c
index 275d9fb6fe5c..eb4489f9082f 100644
--- a/drivers/mtd/ubi/wl.c
+++ b/drivers/mtd/ubi/wl.c
@@ -1601,6 +1601,7 @@ int ubi_wl_init(struct ubi_device *ubi, struct ubi_attach_info *ai)
 		if (ubi->corr_peb_count)
 			ubi_err(ubi, "%d PEBs are corrupted and not used",
 				ubi->corr_peb_count);
+		err = -ENOSPC;
 		goto out_free;
 	}
 	ubi->avail_pebs -= reserved_pebs;
diff --git a/drivers/net/dsa/mv88e6xxx.c b/drivers/net/dsa/mv88e6xxx.c
index b3849267ae7a..932fb720be24 100644
--- a/drivers/net/dsa/mv88e6xxx.c
+++ b/drivers/net/dsa/mv88e6xxx.c
@@ -2126,6 +2126,8 @@ static int mv88e6xxx_setup_port(struct dsa_switch *ds, int port)
 				reg |= PORT_CONTROL_FRAME_ETHER_TYPE_DSA;
 			else
 				reg |= PORT_CONTROL_FRAME_MODE_DSA;
+			reg |= PORT_CONTROL_FORWARD_UNKNOWN |
+				PORT_CONTROL_FORWARD_UNKNOWN_MC;
 		}
 
 		if (mv88e6xxx_6352_family(ds) || mv88e6xxx_6351_family(ds) ||
diff --git a/drivers/net/ethernet/brocade/bna/bfa_ioc.c b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
index b7a0f7879de2..9e59663a6ead 100644
--- a/drivers/net/ethernet/brocade/bna/bfa_ioc.c
+++ b/drivers/net/ethernet/brocade/bna/bfa_ioc.c
@@ -1543,7 +1543,7 @@ bfa_flash_cmd_act_check(void __iomem *pci_bar)
 }
 
 /* Flush FLI data fifo. */
-static u32
+static int
 bfa_flash_fifo_flush(void __iomem *pci_bar)
 {
 	u32 i;
@@ -1573,11 +1573,11 @@ bfa_flash_fifo_flush(void __iomem *pci_bar)
 }
 
 /* Read flash status. */
-static u32
+static int
 bfa_flash_status_read(void __iomem *pci_bar)
 {
 	union bfa_flash_dev_status_reg	dev_status;
-	u32				status;
+	int				status;
 	u32			ret_status;
 	int				i;
 
@@ -1611,11 +1611,11 @@ bfa_flash_status_read(void __iomem *pci_bar)
 }
 
 /* Start flash read operation. */
-static u32
+static int
 bfa_flash_read_start(void __iomem *pci_bar, u32 offset, u32 len,
 		     char *buf)
 {
-	u32 status;
+	int status;
 
 	/* len must be mutiple of 4 and not exceeding fifo size */
 	if (len == 0 || len > BFA_FLASH_FIFO_SIZE || (len & 0x03) != 0)
@@ -1703,7 +1703,8 @@ static enum bfa_status
 bfa_flash_raw_read(void __iomem *pci_bar, u32 offset, char *buf,
 		   u32 len)
 {
-	u32 n, status;
+	u32 n;
+	int status;
 	u32 off, l, s, residue, fifo_sz;
 
 	residue = len;
diff --git a/drivers/net/ethernet/hisilicon/hip04_eth.c b/drivers/net/ethernet/hisilicon/hip04_eth.c
index cc2d8b4b18e3..253f8ed0537a 100644
--- a/drivers/net/ethernet/hisilicon/hip04_eth.c
+++ b/drivers/net/ethernet/hisilicon/hip04_eth.c
@@ -816,7 +816,7 @@ static int hip04_mac_probe(struct platform_device *pdev)
 	struct net_device *ndev;
 	struct hip04_priv *priv;
 	struct resource *res;
-	unsigned int irq;
+	int irq;
 	int ret;
 
 	ndev = alloc_etherdev(sizeof(struct hip04_priv));
diff --git a/drivers/net/ethernet/ibm/emac/core.h b/drivers/net/ethernet/ibm/emac/core.h
index f379e474ba7c..93ae11494810 100644
--- a/drivers/net/ethernet/ibm/emac/core.h
+++ b/drivers/net/ethernet/ibm/emac/core.h
@@ -460,8 +460,8 @@ struct emac_ethtool_regs_subhdr {
 	u32 index;
 };
 
-#define EMAC_ETHTOOL_REGS_VER		0
-#define EMAC4_ETHTOOL_REGS_VER		1
-#define EMAC4SYNC_ETHTOOL_REGS_VER	2
+#define EMAC_ETHTOOL_REGS_VER		3
+#define EMAC4_ETHTOOL_REGS_VER		4
+#define EMAC4SYNC_ETHTOOL_REGS_VER	5
 
 #endif /* __IBM_NEWEMAC_CORE_H */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 199275dbe624..e59ffb2e7b4c 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -953,6 +953,13 @@ i40e_status i40e_clean_arq_element(struct i40e_hw *hw,
 	/* take the lock before we start messing with the ring */
 	mutex_lock(&hw->aq.arq_mutex);
 
+	if (hw->aq.arq.count == 0) {
+		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+			   "AQRX: Admin queue not initialized.\n");
+		ret_code = I40E_ERR_QUEUE_EMPTY;
+		goto clean_arq_element_err;
+	}
+
 	/* set next_to_use to head */
 	ntu = (rd32(hw, hw->aq.arq.head) & I40E_PF_ARQH_ARQH_MASK);
 	if (ntu == ntc) {
@@ -1014,6 +1021,8 @@ clean_arq_element_out:
 	/* Set pending if needed, unlock and return */
 	if (pending != NULL)
 		*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+
+clean_arq_element_err:
 	mutex_unlock(&hw->aq.arq_mutex);
 
 	if (i40e_is_nvm_update_op(&e->desc)) {
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 52e58f304b21..efd5335631d8 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2688,7 +2688,8 @@ static int i40e_configure_rx_ring(struct i40e_ring *ring)
 		rx_ctx.lrxqthresh = 2;
 	rx_ctx.crcstrip = 1;
 	rx_ctx.l2tsel = 1;
-	rx_ctx.showiv = 1;
+	/* this controls whether VLAN is stripped from inner headers */
+	rx_ctx.showiv = 0;
 #ifdef I40E_FCOE
 	rx_ctx.fc_ena = (vsi->type == I40E_VSI_FCOE);
 #endif
diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
index 0940db731382..5026773a7c26 100644
--- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c
@@ -894,6 +894,13 @@ i40e_status i40evf_clean_arq_element(struct i40e_hw *hw,
 	/* take the lock before we start messing with the ring */
 	mutex_lock(&hw->aq.arq_mutex);
 
+	if (hw->aq.arq.count == 0) {
+		i40e_debug(hw, I40E_DEBUG_AQ_MESSAGE,
+			   "AQRX: Admin queue not initialized.\n");
+		ret_code = I40E_ERR_QUEUE_EMPTY;
+		goto clean_arq_element_err;
+	}
+
 	/* set next_to_use to head */
 	ntu = (rd32(hw, hw->aq.arq.head) & I40E_VF_ARQH1_ARQH_MASK);
 	if (ntu == ntc) {
@@ -955,6 +962,8 @@ clean_arq_element_out:
 	/* Set pending if needed, unlock and return */
 	if (pending != NULL)
 		*pending = (ntc > ntu ? hw->aq.arq.count : 0) + (ntu - ntc);
+
+clean_arq_element_err:
 	mutex_unlock(&hw->aq.arq_mutex);
 
 	return ret_code;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c
index bd9ea0d01aae..1d4e2e054647 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mcg.c
+++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c
@@ -1184,10 +1184,11 @@ out:
 	if (prot == MLX4_PROT_ETH) {
 		/* manage the steering entry for promisc mode */
 		if (new_entry)
-			new_steering_entry(dev, port, steer, index, qp->qpn);
+			err = new_steering_entry(dev, port, steer,
+						 index, qp->qpn);
 		else
-			existing_steering_entry(dev, port, steer,
-						index, qp->qpn);
+			err = existing_steering_entry(dev, port, steer,
+						      index, qp->qpn);
 	}
 	if (err && link && index != -1) {
 		if (index < dev->caps.num_mgms)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw.c b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
index aa0d5ffe92d8..9335e5ae18cc 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fw.c
@@ -200,25 +200,3 @@ int mlx5_cmd_teardown_hca(struct mlx5_core_dev *dev)
 
 	return err;
 }
-
-int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey)
-{
-	struct mlx5_cmd_query_special_contexts_mbox_in in;
-	struct mlx5_cmd_query_special_contexts_mbox_out out;
-	int err;
-
-	memset(&in, 0, sizeof(in));
-	memset(&out, 0, sizeof(out));
-	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_QUERY_SPECIAL_CONTEXTS);
-	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
-	if (err)
-		return err;
-
-	if (out.hdr.status)
-		err = mlx5_cmd_status_to_err(&out.hdr);
-
-	*rsvd_lkey = be32_to_cpu(out.resd_lkey);
-
-	return err;
-}
-EXPORT_SYMBOL(mlx5_core_query_special_context);
diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c
index 2b32e0c5a0b4..b4f21232019a 100644
--- a/drivers/net/ethernet/realtek/r8169.c
+++ b/drivers/net/ethernet/realtek/r8169.c
@@ -6081,7 +6081,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp)
 {
 	void __iomem *ioaddr = tp->mmio_addr;
 	struct pci_dev *pdev = tp->pci_dev;
-	u16 rg_saw_cnt;
+	int rg_saw_cnt;
 	u32 data;
 	static const struct ephy_info e_info_8168h_1[] = {
 		{ 0x1e, 0x0800,	0x0001 },
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index dd652f2ae03d..108a3118ace7 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -299,9 +299,10 @@ static long local_pci_probe(void *_ddi)
 	 * Unbound PCI devices are always put in D0, regardless of
 	 * runtime PM status.  During probe, the device is set to
 	 * active and the usage count is incremented.  If the driver
-	 * supports runtime PM, it should call pm_runtime_put_noidle()
-	 * in its probe routine and pm_runtime_get_noresume() in its
-	 * remove routine.
+	 * supports runtime PM, it should call pm_runtime_put_noidle(),
+	 * or any other runtime PM helper function decrementing the usage
+	 * count, in its probe routine and pm_runtime_get_noresume() in
+	 * its remove routine.
 	 */
 	pm_runtime_get_sync(dev);
 	pci_dev->driver = pci_drv;
diff --git a/drivers/staging/android/TODO b/drivers/staging/android/TODO
index 20288fc53946..8f3ac37bfe12 100644
--- a/drivers/staging/android/TODO
+++ b/drivers/staging/android/TODO
@@ -5,5 +5,25 @@ TODO:
 	- add proper arch dependencies as needed
 	- audit userspace interfaces to make sure they are sane
 
+
+ion/
+ - Remove ION_IOC_SYNC: Flushing for devices should be purely a kernel internal
+   interface on top of dma-buf. flush_for_device needs to be added to dma-buf
+   first.
+ - Remove ION_IOC_CUSTOM: Atm used for cache flushing for cpu access in some
+   vendor trees. Should be replaced with an ioctl on the dma-buf to expose the
+   begin/end_cpu_access hooks to userspace.
+ - Clarify the tricks ion plays with explicitly managing coherency behind the
+   dma api's back (this is absolutely needed for high-perf gpu drivers): Add an
+   explicit coherency management mode to flush_for_device to be used by drivers
+   which want to manage caches themselves and which indicates whether cpu caches
+   need flushing.
+ - With those removed there's probably no use for ION_IOC_IMPORT anymore either
+   since ion would just be the central allocator for shared buffers.
+ - Add dt-binding to expose cma regions as ion heaps, with the rule that any
+   such cma regions must already be used by some device for dma. I.e. ion only
+   exposes existing cma regions and doesn't reserve unecessarily memory when
+   booting a system which doesn't use ion.
+
 Please send patches to Greg Kroah-Hartman <greg@kroah.com> and Cc:
 Arve Hjønnevåg <arve@android.com> and Riley Andrews <riandrews@android.com>
diff --git a/drivers/staging/android/ion/ion.c b/drivers/staging/android/ion/ion.c
index 217aa537c4eb..6e8d8392ca38 100644
--- a/drivers/staging/android/ion/ion.c
+++ b/drivers/staging/android/ion/ion.c
@@ -1179,13 +1179,13 @@ struct ion_handle *ion_import_dma_buf(struct ion_client *client, int fd)
 		mutex_unlock(&client->lock);
 		goto end;
 	}
-	mutex_unlock(&client->lock);
 
 	handle = ion_handle_create(client, buffer);
-	if (IS_ERR(handle))
+	if (IS_ERR(handle)) {
+		mutex_unlock(&client->lock);
 		goto end;
+	}
 
-	mutex_lock(&client->lock);
 	ret = ion_handle_add(client, handle);
 	mutex_unlock(&client->lock);
 	if (ret) {
diff --git a/drivers/staging/fbtft/fb_uc1611.c b/drivers/staging/fbtft/fb_uc1611.c
index 32f3a9d921d6..5cafa50d1fac 100644
--- a/drivers/staging/fbtft/fb_uc1611.c
+++ b/drivers/staging/fbtft/fb_uc1611.c
@@ -76,7 +76,7 @@ static int init_display(struct fbtft_par *par)
 
 	/* Set CS active high */
 	par->spi->mode |= SPI_CS_HIGH;
-	ret = par->spi->master->setup(par->spi);
+	ret = spi_setup(par->spi);
 	if (ret) {
 		dev_err(par->info->device, "Could not set SPI_CS_HIGH\n");
 		return ret;
diff --git a/drivers/staging/fbtft/fb_watterott.c b/drivers/staging/fbtft/fb_watterott.c
index 88fb2c0132d5..8eae6ef25846 100644
--- a/drivers/staging/fbtft/fb_watterott.c
+++ b/drivers/staging/fbtft/fb_watterott.c
@@ -169,7 +169,7 @@ static int init_display(struct fbtft_par *par)
 	/* enable SPI interface by having CS and MOSI low during reset */
 	save_mode = par->spi->mode;
 	par->spi->mode |= SPI_CS_HIGH;
-	ret = par->spi->master->setup(par->spi); /* set CS inactive low */
+	ret = spi_setup(par->spi); /* set CS inactive low */
 	if (ret) {
 		dev_err(par->info->device, "Could not set SPI_CS_HIGH\n");
 		return ret;
@@ -180,7 +180,7 @@ static int init_display(struct fbtft_par *par)
 	par->fbtftops.reset(par);
 	mdelay(1000);
 	par->spi->mode = save_mode;
-	ret = par->spi->master->setup(par->spi);
+	ret = spi_setup(par->spi);
 	if (ret) {
 		dev_err(par->info->device, "Could not restore SPI mode\n");
 		return ret;
diff --git a/drivers/staging/fbtft/fbtft-core.c b/drivers/staging/fbtft/fbtft-core.c
index 23392eb6799e..7f5fa3d1cab0 100644
--- a/drivers/staging/fbtft/fbtft-core.c
+++ b/drivers/staging/fbtft/fbtft-core.c
@@ -1436,15 +1436,11 @@ int fbtft_probe_common(struct fbtft_display *display,
 
 	/* 9-bit SPI setup */
 	if (par->spi && display->buswidth == 9) {
-		par->spi->bits_per_word = 9;
-		ret = par->spi->master->setup(par->spi);
-		if (ret) {
+		if (par->spi->master->bits_per_word_mask & SPI_BPW_MASK(9)) {
+			par->spi->bits_per_word = 9;
+		} else {
 			dev_warn(&par->spi->dev,
 				"9-bit SPI not available, emulating using 8-bit.\n");
-			par->spi->bits_per_word = 8;
-			ret = par->spi->master->setup(par->spi);
-			if (ret)
-				goto out_release;
 			/* allocate buffer with room for dc bits */
 			par->extra = devm_kzalloc(par->info->device,
 				par->txbuf.len + (par->txbuf.len / 8) + 8,
diff --git a/drivers/staging/fbtft/flexfb.c b/drivers/staging/fbtft/flexfb.c
index c763efc5de7d..3f380a0086c3 100644
--- a/drivers/staging/fbtft/flexfb.c
+++ b/drivers/staging/fbtft/flexfb.c
@@ -463,15 +463,12 @@ static int flexfb_probe_common(struct spi_device *sdev,
 			}
 			par->fbtftops.write_register = fbtft_write_reg8_bus9;
 			par->fbtftops.write_vmem = fbtft_write_vmem16_bus9;
-			sdev->bits_per_word = 9;
-			ret = sdev->master->setup(sdev);
-			if (ret) {
+			if (par->spi->master->bits_per_word_mask
+			    & SPI_BPW_MASK(9)) {
+				par->spi->bits_per_word = 9;
+			} else {
 				dev_warn(dev,
 					"9-bit SPI not available, emulating using 8-bit.\n");
-				sdev->bits_per_word = 8;
-				ret = sdev->master->setup(sdev);
-				if (ret)
-					goto out_release;
 				/* allocate buffer with room for dc bits */
 				par->extra = devm_kzalloc(par->info->device,
 						par->txbuf.len + (par->txbuf.len / 8) + 8,
diff --git a/drivers/staging/lustre/README.txt b/drivers/staging/lustre/README.txt
index cf0ca50ff83b..0676243eea9e 100644
--- a/drivers/staging/lustre/README.txt
+++ b/drivers/staging/lustre/README.txt
@@ -14,10 +14,8 @@ Unlike shared disk storage cluster filesystems (e.g. OCFS2, GFS, GPFS),
 Lustre has independent Metadata and Data servers that clients can access
 in parallel to maximize performance.
 
-In order to use Lustre client you will need to download lustre client
-tools from
-https://downloads.hpdd.intel.com/public/lustre/latest-feature-release/
-the package name is lustre-client.
+In order to use Lustre client you will need to download the "lustre-client"
+package that contains the userspace tools from http://lustre.org/download/
 
 You will need to install and configure your Lustre servers separately.
 
@@ -76,12 +74,10 @@ Mount Options
 
 More Information
 ================
-You can get more information at
-OpenSFS website: http://lustre.opensfs.org/about/
-Intel HPDD wiki: https://wiki.hpdd.intel.com
+You can get more information at the Lustre website: http://wiki.lustre.org/
 
-Out of tree Lustre client and server code is available at:
-http://git.whamcloud.com/fs/lustre-release.git
+Source for the userspace tools and out-of-tree client and server code
+is available at: http://git.hpdd.intel.com/fs/lustre-release.git
 
 Latest binary packages:
-http://lustre.opensfs.org/download-lustre/
+http://lustre.org/download/
diff --git a/drivers/staging/most/Kconfig b/drivers/staging/most/Kconfig
index d50de03de7b9..0b9b9b539f70 100644
--- a/drivers/staging/most/Kconfig
+++ b/drivers/staging/most/Kconfig
@@ -1,5 +1,6 @@
 menuconfig MOST
         tristate "MOST driver"
+	depends on HAS_DMA
         select MOSTCORE
         default n
         ---help---
diff --git a/drivers/staging/most/hdm-dim2/Kconfig b/drivers/staging/most/hdm-dim2/Kconfig
index 1d4ad1d67758..fc548769479b 100644
--- a/drivers/staging/most/hdm-dim2/Kconfig
+++ b/drivers/staging/most/hdm-dim2/Kconfig
@@ -5,6 +5,7 @@
 config HDM_DIM2
 	tristate "DIM2 HDM"
 	depends on AIM_NETWORK
+	depends on HAS_IOMEM
 
 	---help---
 	  Say Y here if you want to connect via MediaLB to network transceiver.
diff --git a/drivers/staging/most/hdm-usb/Kconfig b/drivers/staging/most/hdm-usb/Kconfig
index a482c3fdf34b..ec1546312ee6 100644
--- a/drivers/staging/most/hdm-usb/Kconfig
+++ b/drivers/staging/most/hdm-usb/Kconfig
@@ -4,7 +4,7 @@
 
 config HDM_USB
 	tristate "USB HDM"
-	depends on USB
+	depends on USB && NET
 	select AIM_NETWORK
 	---help---
 	  Say Y here if you want to connect via USB to network tranceiver.
diff --git a/drivers/staging/most/mostcore/Kconfig b/drivers/staging/most/mostcore/Kconfig
index 38abf1b21b66..47172546d728 100644
--- a/drivers/staging/most/mostcore/Kconfig
+++ b/drivers/staging/most/mostcore/Kconfig
@@ -4,6 +4,7 @@
 
 config MOSTCORE
 	tristate "MOST Core"
+	depends on HAS_DMA
 
 	---help---
 	  Say Y here if you want to enable MOST support.
diff --git a/drivers/staging/unisys/visorbus/Makefile b/drivers/staging/unisys/visorbus/Makefile
index fa27ee5f336c..fc790e7592fc 100644
--- a/drivers/staging/unisys/visorbus/Makefile
+++ b/drivers/staging/unisys/visorbus/Makefile
@@ -10,4 +10,3 @@ visorbus-y += visorchipset.o
 visorbus-y += periodic_work.o
 
 ccflags-y += -Idrivers/staging/unisys/include
-ccflags-y += -Idrivers/staging/unisys/visorutil
diff --git a/drivers/staging/unisys/visorbus/visorbus_main.c b/drivers/staging/unisys/visorbus/visorbus_main.c
index 2309f5f2b238..a272b48bab28 100644
--- a/drivers/staging/unisys/visorbus/visorbus_main.c
+++ b/drivers/staging/unisys/visorbus/visorbus_main.c
@@ -37,6 +37,8 @@ static int visorbus_debugref;
 #define POLLJIFFIES_TESTWORK         100
 #define POLLJIFFIES_NORMALCHANNEL     10
 
+static int busreg_rc = -ENODEV; /* stores the result from bus registration */
+
 static int visorbus_uevent(struct device *xdev, struct kobj_uevent_env *env);
 static int visorbus_match(struct device *xdev, struct device_driver *xdrv);
 static void fix_vbus_dev_info(struct visor_device *visordev);
@@ -863,6 +865,9 @@ int visorbus_register_visor_driver(struct visor_driver *drv)
 {
 	int rc = 0;
 
+	if (busreg_rc < 0)
+		return -ENODEV; /*can't register on a nonexistent bus*/
+
 	drv->driver.name = drv->name;
 	drv->driver.bus = &visorbus_type;
 	drv->driver.probe = visordriver_probe_device;
@@ -885,6 +890,8 @@ int visorbus_register_visor_driver(struct visor_driver *drv)
 	if (rc < 0)
 		return rc;
 	rc = register_driver_attributes(drv);
+	if (rc < 0)
+		driver_unregister(&drv->driver);
 	return rc;
 }
 EXPORT_SYMBOL_GPL(visorbus_register_visor_driver);
@@ -1260,10 +1267,8 @@ remove_bus_instance(struct visor_device *dev)
 static int
 create_bus_type(void)
 {
-	int rc = 0;
-
-	rc = bus_register(&visorbus_type);
-	return rc;
+	busreg_rc = bus_register(&visorbus_type);
+	return busreg_rc;
 }
 
 /** Remove the one-and-only one instance of the visor bus type (visorbus_type).
diff --git a/drivers/staging/unisys/visornic/visornic_main.c b/drivers/staging/unisys/visornic/visornic_main.c
index 8c9da7ea7845..9d3c1e282062 100644
--- a/drivers/staging/unisys/visornic/visornic_main.c
+++ b/drivers/staging/unisys/visornic/visornic_main.c
@@ -1189,16 +1189,16 @@ visornic_rx(struct uiscmdrsp *cmdrsp)
 	spin_lock_irqsave(&devdata->priv_lock, flags);
 	atomic_dec(&devdata->num_rcvbuf_in_iovm);
 
-	/* update rcv stats - call it with priv_lock held */
-	devdata->net_stats.rx_packets++;
-	devdata->net_stats.rx_bytes = skb->len;
-
 	/* set length to how much was ACTUALLY received -
 	 * NOTE: rcv_done_len includes actual length of data rcvd
 	 * including ethhdr
 	 */
 	skb->len = cmdrsp->net.rcv.rcv_done_len;
 
+	/* update rcv stats - call it with priv_lock held */
+	devdata->net_stats.rx_packets++;
+	devdata->net_stats.rx_bytes += skb->len;
+
 	/* test enabled while holding lock */
 	if (!(devdata->enabled && devdata->enab_dis_acked)) {
 		/* don't process it unless we're in enable mode and until
@@ -1924,13 +1924,16 @@ static int visornic_probe(struct visor_device *dev)
 			"%s debugfs_create_dir %s failed\n",
 			__func__, netdev->name);
 		err = -ENOMEM;
-		goto cleanup_xmit_cmdrsp;
+		goto cleanup_register_netdev;
 	}
 
 	dev_info(&dev->device, "%s success netdev=%s\n",
 		 __func__, netdev->name);
 	return 0;
 
+cleanup_register_netdev:
+	unregister_netdev(netdev);
+
 cleanup_napi_add:
 	del_timer_sync(&devdata->irq_poll_timer);
 	netif_napi_del(&devdata->napi);
@@ -2128,8 +2131,9 @@ static int visornic_init(void)
 	if (!dev_num_pool)
 		goto cleanup_workqueue;
 
-	visorbus_register_visor_driver(&visornic_driver);
-	return 0;
+	err = visorbus_register_visor_driver(&visornic_driver);
+	if (!err)
+		return 0;
 
 cleanup_workqueue:
 	if (visornic_timeout_reset_workqueue) {
diff --git a/drivers/target/iscsi/iscsi_target_parameters.c b/drivers/target/iscsi/iscsi_target_parameters.c
index e8a52f7d6204..51d1734d5390 100644
--- a/drivers/target/iscsi/iscsi_target_parameters.c
+++ b/drivers/target/iscsi/iscsi_target_parameters.c
@@ -407,6 +407,7 @@ int iscsi_create_default_params(struct iscsi_param_list **param_list_ptr)
 			TYPERANGE_UTF8, USE_INITIAL_ONLY);
 	if (!param)
 		goto out;
+
 	/*
 	 * Extra parameters for ISER from RFC-5046
 	 */
@@ -496,9 +497,9 @@ int iscsi_set_keys_to_negotiate(
 		} else if (!strcmp(param->name, SESSIONTYPE)) {
 			SET_PSTATE_NEGOTIATE(param);
 		} else if (!strcmp(param->name, IFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKER)) {
-			SET_PSTATE_NEGOTIATE(param);
+			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, IFMARKINT)) {
 			SET_PSTATE_REJECT(param);
 		} else if (!strcmp(param->name, OFMARKINT)) {
diff --git a/drivers/target/target_core_device.c b/drivers/target/target_core_device.c
index dcc424ac35d4..88ea4e4f124b 100644
--- a/drivers/target/target_core_device.c
+++ b/drivers/target/target_core_device.c
@@ -62,22 +62,13 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	struct se_session *se_sess = se_cmd->se_sess;
 	struct se_node_acl *nacl = se_sess->se_node_acl;
 	struct se_dev_entry *deve;
+	sense_reason_t ret = TCM_NO_SENSE;
 
 	rcu_read_lock();
 	deve = target_nacl_find_deve(nacl, unpacked_lun);
 	if (deve) {
 		atomic_long_inc(&deve->total_cmds);
 
-		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
-		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
-			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
-				" Access for 0x%08llx\n",
-				se_cmd->se_tfo->get_fabric_name(),
-				unpacked_lun);
-			rcu_read_unlock();
-			return TCM_WRITE_PROTECTED;
-		}
-
 		if (se_cmd->data_direction == DMA_TO_DEVICE)
 			atomic_long_add(se_cmd->data_length,
 					&deve->write_bytes);
@@ -93,6 +84,17 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
+
+		if ((se_cmd->data_direction == DMA_TO_DEVICE) &&
+		    (deve->lun_flags & TRANSPORT_LUNFLAGS_READ_ONLY)) {
+			pr_err("TARGET_CORE[%s]: Detected WRITE_PROTECTED LUN"
+				" Access for 0x%08llx\n",
+				se_cmd->se_tfo->get_fabric_name(),
+				unpacked_lun);
+			rcu_read_unlock();
+			ret = TCM_WRITE_PROTECTED;
+			goto ref_dev;
+		}
 	}
 	rcu_read_unlock();
 
@@ -109,12 +111,6 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 				unpacked_lun);
 			return TCM_NON_EXISTENT_LUN;
 		}
-		/*
-		 * Force WRITE PROTECT for virtual LUN 0
-		 */
-		if ((se_cmd->data_direction != DMA_FROM_DEVICE) &&
-		    (se_cmd->data_direction != DMA_NONE))
-			return TCM_WRITE_PROTECTED;
 
 		se_lun = se_sess->se_tpg->tpg_virt_lun0;
 		se_cmd->se_lun = se_sess->se_tpg->tpg_virt_lun0;
@@ -123,6 +119,15 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 
 		percpu_ref_get(&se_lun->lun_ref);
 		se_cmd->lun_ref_active = true;
+
+		/*
+		 * Force WRITE PROTECT for virtual LUN 0
+		 */
+		if ((se_cmd->data_direction != DMA_FROM_DEVICE) &&
+		    (se_cmd->data_direction != DMA_NONE)) {
+			ret = TCM_WRITE_PROTECTED;
+			goto ref_dev;
+		}
 	}
 	/*
 	 * RCU reference protected by percpu se_lun->lun_ref taken above that
@@ -130,6 +135,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 	 * pointer can be kfree_rcu() by the final se_lun->lun_group put via
 	 * target_core_fabric_configfs.c:target_fabric_port_release
 	 */
+ref_dev:
 	se_cmd->se_dev = rcu_dereference_raw(se_lun->lun_se_dev);
 	atomic_long_inc(&se_cmd->se_dev->num_cmds);
 
@@ -140,7 +146,7 @@ transport_lookup_cmd_lun(struct se_cmd *se_cmd, u64 unpacked_lun)
 		atomic_long_add(se_cmd->data_length,
 				&se_cmd->se_dev->read_bytes);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(transport_lookup_cmd_lun);
 
@@ -427,8 +433,6 @@ void core_disable_device_list_for_node(
 
 	hlist_del_rcu(&orig->link);
 	clear_bit(DEF_PR_REG_ACTIVE, &orig->deve_flags);
-	rcu_assign_pointer(orig->se_lun, NULL);
-	rcu_assign_pointer(orig->se_lun_acl, NULL);
 	orig->lun_flags = 0;
 	orig->creation_time = 0;
 	orig->attach_count--;
@@ -439,6 +443,9 @@ void core_disable_device_list_for_node(
 	kref_put(&orig->pr_kref, target_pr_kref_release);
 	wait_for_completion(&orig->pr_comp);
 
+	rcu_assign_pointer(orig->se_lun, NULL);
+	rcu_assign_pointer(orig->se_lun_acl, NULL);
+
 	kfree_rcu(orig, rcu_head);
 
 	core_scsi3_free_pr_reg_from_nacl(dev, nacl);
diff --git a/drivers/target/target_core_hba.c b/drivers/target/target_core_hba.c
index 9522960c7fdd..22390e0e046c 100644
--- a/drivers/target/target_core_hba.c
+++ b/drivers/target/target_core_hba.c
@@ -187,5 +187,5 @@ core_delete_hba(struct se_hba *hba)
 
 bool target_sense_desc_format(struct se_device *dev)
 {
-	return dev->transport->get_blocks(dev) > U32_MAX;
+	return (dev) ? dev->transport->get_blocks(dev) > U32_MAX : false;
 }
diff --git a/drivers/target/target_core_iblock.c b/drivers/target/target_core_iblock.c
index 5a9982f5d5d6..0f19e11acac2 100644
--- a/drivers/target/target_core_iblock.c
+++ b/drivers/target/target_core_iblock.c
@@ -105,6 +105,8 @@ static int iblock_configure_device(struct se_device *dev)
 	mode = FMODE_READ|FMODE_EXCL;
 	if (!ib_dev->ibd_readonly)
 		mode |= FMODE_WRITE;
+	else
+		dev->dev_flags |= DF_READ_ONLY;
 
 	bd = blkdev_get_by_path(ib_dev->ibd_udev_path, mode, ib_dev);
 	if (IS_ERR(bd)) {
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 5ab7100de17e..e7933115087a 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -618,7 +618,7 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	struct se_device *dev,
 	struct se_node_acl *nacl,
 	struct se_lun *lun,
-	struct se_dev_entry *deve,
+	struct se_dev_entry *dest_deve,
 	u64 mapped_lun,
 	unsigned char *isid,
 	u64 sa_res_key,
@@ -640,7 +640,29 @@ static struct t10_pr_registration *__core_scsi3_do_alloc_registration(
 	INIT_LIST_HEAD(&pr_reg->pr_reg_atp_mem_list);
 	atomic_set(&pr_reg->pr_res_holders, 0);
 	pr_reg->pr_reg_nacl = nacl;
-	pr_reg->pr_reg_deve = deve;
+	/*
+	 * For destination registrations for ALL_TG_PT=1 and SPEC_I_PT=1,
+	 * the se_dev_entry->pr_ref will have been already obtained by
+	 * core_get_se_deve_from_rtpi() or __core_scsi3_alloc_registration().
+	 *
+	 * Otherwise, locate se_dev_entry now and obtain a reference until
+	 * registration completes in __core_scsi3_add_registration().
+	 */
+	if (dest_deve) {
+		pr_reg->pr_reg_deve = dest_deve;
+	} else {
+		rcu_read_lock();
+		pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+		if (!pr_reg->pr_reg_deve) {
+			rcu_read_unlock();
+			pr_err("Unable to locate PR deve %s mapped_lun: %llu\n",
+				nacl->initiatorname, mapped_lun);
+			kmem_cache_free(t10_pr_reg_cache, pr_reg);
+			return NULL;
+		}
+		kref_get(&pr_reg->pr_reg_deve->pr_kref);
+		rcu_read_unlock();
+	}
 	pr_reg->pr_res_mapped_lun = mapped_lun;
 	pr_reg->pr_aptpl_target_lun = lun->unpacked_lun;
 	pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
@@ -936,17 +958,29 @@ static int __core_scsi3_check_aptpl_registration(
 		    !(strcmp(pr_reg->pr_tport, t_port)) &&
 		     (pr_reg->pr_reg_tpgt == tpgt) &&
 		     (pr_reg->pr_aptpl_target_lun == target_lun)) {
+			/*
+			 * Obtain the ->pr_reg_deve pointer + reference, that
+			 * is released by __core_scsi3_add_registration() below.
+			 */
+			rcu_read_lock();
+			pr_reg->pr_reg_deve = target_nacl_find_deve(nacl, mapped_lun);
+			if (!pr_reg->pr_reg_deve) {
+				pr_err("Unable to locate PR APTPL %s mapped_lun:"
+					" %llu\n", nacl->initiatorname, mapped_lun);
+				rcu_read_unlock();
+				continue;
+			}
+			kref_get(&pr_reg->pr_reg_deve->pr_kref);
+			rcu_read_unlock();
 
 			pr_reg->pr_reg_nacl = nacl;
 			pr_reg->tg_pt_sep_rtpi = lun->lun_rtpi;
-
 			list_del(&pr_reg->pr_reg_aptpl_list);
 			spin_unlock(&pr_tmpl->aptpl_reg_lock);
 			/*
 			 * At this point all of the pointers in *pr_reg will
 			 * be setup, so go ahead and add the registration.
 			 */
-
 			__core_scsi3_add_registration(dev, nacl, pr_reg, 0, 0);
 			/*
 			 * If this registration is the reservation holder,
@@ -1044,18 +1078,11 @@ static void __core_scsi3_add_registration(
 
 	__core_scsi3_dump_registration(tfo, dev, nacl, pr_reg, register_type);
 	spin_unlock(&pr_tmpl->registration_lock);
-
-	rcu_read_lock();
-	deve = pr_reg->pr_reg_deve;
-	if (deve)
-		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
-	rcu_read_unlock();
-
 	/*
 	 * Skip extra processing for ALL_TG_PT=0 or REGISTER_AND_MOVE.
 	 */
 	if (!pr_reg->pr_reg_all_tg_pt || register_move)
-		return;
+		goto out;
 	/*
 	 * Walk pr_reg->pr_reg_atp_list and add registrations for ALL_TG_PT=1
 	 * allocated in __core_scsi3_alloc_registration()
@@ -1075,19 +1102,31 @@ static void __core_scsi3_add_registration(
 		__core_scsi3_dump_registration(tfo, dev, nacl_tmp, pr_reg_tmp,
 					       register_type);
 		spin_unlock(&pr_tmpl->registration_lock);
-
+		/*
+		 * Drop configfs group dependency reference and deve->pr_kref
+		 * obtained from  __core_scsi3_alloc_registration() code.
+		 */
 		rcu_read_lock();
 		deve = pr_reg_tmp->pr_reg_deve;
-		if (deve)
+		if (deve) {
 			set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+			core_scsi3_lunacl_undepend_item(deve);
+			pr_reg_tmp->pr_reg_deve = NULL;
+		}
 		rcu_read_unlock();
-
-		/*
-		 * Drop configfs group dependency reference from
-		 * __core_scsi3_alloc_registration()
-		 */
-		core_scsi3_lunacl_undepend_item(pr_reg_tmp->pr_reg_deve);
 	}
+out:
+	/*
+	 * Drop deve->pr_kref obtained in __core_scsi3_do_alloc_registration()
+	 */
+	rcu_read_lock();
+	deve = pr_reg->pr_reg_deve;
+	if (deve) {
+		set_bit(DEF_PR_REG_ACTIVE, &deve->deve_flags);
+		kref_put(&deve->pr_kref, target_pr_kref_release);
+		pr_reg->pr_reg_deve = NULL;
+	}
+	rcu_read_unlock();
 }
 
 static int core_scsi3_alloc_registration(
@@ -1785,9 +1824,11 @@ core_scsi3_decode_spec_i_port(
 			dest_node_acl->initiatorname, i_buf, (dest_se_deve) ?
 			dest_se_deve->mapped_lun : 0);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
@@ -1823,9 +1864,11 @@ out:
 
 		kmem_cache_free(t10_pr_reg_cache, dest_pr_reg);
 
-		if (!dest_se_deve)
+		if (!dest_se_deve) {
+			kref_put(&local_pr_reg->pr_reg_deve->pr_kref,
+				 target_pr_kref_release);
 			continue;
-
+		}
 		core_scsi3_lunacl_undepend_item(dest_se_deve);
 		core_scsi3_nodeacl_undepend_item(dest_node_acl);
 		core_scsi3_tpg_undepend_item(dest_tpg);
diff --git a/drivers/target/target_core_tpg.c b/drivers/target/target_core_tpg.c
index 2d0381dd105c..5fb9dd7f08bb 100644
--- a/drivers/target/target_core_tpg.c
+++ b/drivers/target/target_core_tpg.c
@@ -668,7 +668,10 @@ int core_tpg_add_lun(
 	list_add_tail(&lun->lun_dev_link, &dev->dev_sep_list);
 	spin_unlock(&dev->se_port_lock);
 
-	lun->lun_access = lun_access;
+	if (dev->dev_flags & DF_READ_ONLY)
+		lun->lun_access = TRANSPORT_LUNFLAGS_READ_ONLY;
+	else
+		lun->lun_access = lun_access;
 	if (!(dev->se_hba->hba_flags & HBA_FLAGS_INTERNAL_USE))
 		hlist_add_head_rcu(&lun->link, &tpg->tpg_lun_hlist);
 	mutex_unlock(&tpg->tpg_lun_mutex);
diff --git a/drivers/thermal/power_allocator.c b/drivers/thermal/power_allocator.c
index 7ff96270c933..e570ff084add 100644
--- a/drivers/thermal/power_allocator.c
+++ b/drivers/thermal/power_allocator.c
@@ -144,6 +144,16 @@ static void estimate_pid_constants(struct thermal_zone_device *tz,
 		switch_on_temp = 0;
 
 	temperature_threshold = control_temp - switch_on_temp;
+	/*
+	 * estimate_pid_constants() tries to find appropriate default
+	 * values for thermal zones that don't provide them. If a
+	 * system integrator has configured a thermal zone with two
+	 * passive trip points at the same temperature, that person
+	 * hasn't put any effort to set up the thermal zone properly
+	 * so just give up.
+	 */
+	if (!temperature_threshold)
+		return;
 
 	if (!tz->tzp->k_po || force)
 		tz->tzp->k_po = int_to_frac(sustainable_power) /
diff --git a/drivers/thunderbolt/nhi.c b/drivers/thunderbolt/nhi.c
index c68fe1222c16..20a41f7de76f 100644
--- a/drivers/thunderbolt/nhi.c
+++ b/drivers/thunderbolt/nhi.c
@@ -643,7 +643,7 @@ static struct pci_device_id nhi_ids[] = {
 	{
 		.class = PCI_CLASS_SYSTEM_OTHER << 8, .class_mask = ~0,
 		.vendor = PCI_VENDOR_ID_INTEL, .device = 0x156c,
-		.subvendor = 0x2222, .subdevice = 0x1111,
+		.subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID,
 	},
 	{ 0,}
 };
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 54e6c8ddef5d..b1e0ba3e525b 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -2910,3 +2910,5 @@ int serial8250_console_setup(struct uart_port *port, char *options, bool probe)
 }
 
 #endif /* CONFIG_SERIAL_8250_CONSOLE */
+
+MODULE_LICENSE("GPL");
diff --git a/drivers/usb/chipidea/ci_hdrc_imx.c b/drivers/usb/chipidea/ci_hdrc_imx.c
index 867e9f3f3859..dcc50c878159 100644
--- a/drivers/usb/chipidea/ci_hdrc_imx.c
+++ b/drivers/usb/chipidea/ci_hdrc_imx.c
@@ -61,7 +61,7 @@ static const struct of_device_id ci_hdrc_imx_dt_ids[] = {
 	{ .compatible = "fsl,imx27-usb", .data = &imx27_usb_data},
 	{ .compatible = "fsl,imx6q-usb", .data = &imx6q_usb_data},
 	{ .compatible = "fsl,imx6sl-usb", .data = &imx6sl_usb_data},
-	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sl_usb_data},
+	{ .compatible = "fsl,imx6sx-usb", .data = &imx6sx_usb_data},
 	{ /* sentinel */ }
 };
 MODULE_DEVICE_TABLE(of, ci_hdrc_imx_dt_ids);
diff --git a/drivers/usb/chipidea/ci_hdrc_usb2.c b/drivers/usb/chipidea/ci_hdrc_usb2.c
index 9eae1a16cef9..4456d2cf80ff 100644
--- a/drivers/usb/chipidea/ci_hdrc_usb2.c
+++ b/drivers/usb/chipidea/ci_hdrc_usb2.c
@@ -12,6 +12,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/module.h>
 #include <linux/of.h>
+#include <linux/of_platform.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/usb/chipidea.h>
@@ -30,18 +31,36 @@ static const struct ci_hdrc_platform_data ci_default_pdata = {
 	.flags		= CI_HDRC_DISABLE_STREAMING,
 };
 
+static struct ci_hdrc_platform_data ci_zynq_pdata = {
+	.capoffset	= DEF_CAPOFFSET,
+};
+
+static const struct of_device_id ci_hdrc_usb2_of_match[] = {
+	{ .compatible = "chipidea,usb2"},
+	{ .compatible = "xlnx,zynq-usb-2.20a", .data = &ci_zynq_pdata},
+	{ }
+};
+MODULE_DEVICE_TABLE(of, ci_hdrc_usb2_of_match);
+
 static int ci_hdrc_usb2_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct ci_hdrc_usb2_priv *priv;
 	struct ci_hdrc_platform_data *ci_pdata = dev_get_platdata(dev);
 	int ret;
+	const struct of_device_id *match;
 
 	if (!ci_pdata) {
 		ci_pdata = devm_kmalloc(dev, sizeof(*ci_pdata), GFP_KERNEL);
 		*ci_pdata = ci_default_pdata;	/* struct copy */
 	}
 
+	match = of_match_device(ci_hdrc_usb2_of_match, &pdev->dev);
+	if (match && match->data) {
+		/* struct copy */
+		*ci_pdata = *(struct ci_hdrc_platform_data *)match->data;
+	}
+
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
 	if (!priv)
 		return -ENOMEM;
@@ -96,12 +115,6 @@ static int ci_hdrc_usb2_remove(struct platform_device *pdev)
 	return 0;
 }
 
-static const struct of_device_id ci_hdrc_usb2_of_match[] = {
-	{ .compatible = "chipidea,usb2" },
-	{ }
-};
-MODULE_DEVICE_TABLE(of, ci_hdrc_usb2_of_match);
-
 static struct platform_driver ci_hdrc_usb2_driver = {
 	.probe	= ci_hdrc_usb2_probe,
 	.remove	= ci_hdrc_usb2_remove,
diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index a637da25dda0..8223fe73ea85 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -656,6 +656,44 @@ __acquires(hwep->lock)
 	return 0;
 }
 
+static int _ep_set_halt(struct usb_ep *ep, int value, bool check_transfer)
+{
+	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
+	int direction, retval = 0;
+	unsigned long flags;
+
+	if (ep == NULL || hwep->ep.desc == NULL)
+		return -EINVAL;
+
+	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
+		return -EOPNOTSUPP;
+
+	spin_lock_irqsave(hwep->lock, flags);
+
+	if (value && hwep->dir == TX && check_transfer &&
+		!list_empty(&hwep->qh.queue) &&
+			!usb_endpoint_xfer_control(hwep->ep.desc)) {
+		spin_unlock_irqrestore(hwep->lock, flags);
+		return -EAGAIN;
+	}
+
+	direction = hwep->dir;
+	do {
+		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
+
+		if (!value)
+			hwep->wedge = 0;
+
+		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
+			hwep->dir = (hwep->dir == TX) ? RX : TX;
+
+	} while (hwep->dir != direction);
+
+	spin_unlock_irqrestore(hwep->lock, flags);
+	return retval;
+}
+
+
 /**
  * _gadget_stop_activity: stops all USB activity, flushes & disables all endpts
  * @gadget: gadget
@@ -1051,7 +1089,7 @@ __acquires(ci->lock)
 				num += ci->hw_ep_max / 2;
 
 			spin_unlock(&ci->lock);
-			err = usb_ep_set_halt(&ci->ci_hw_ep[num].ep);
+			err = _ep_set_halt(&ci->ci_hw_ep[num].ep, 1, false);
 			spin_lock(&ci->lock);
 			if (!err)
 				isr_setup_status_phase(ci);
@@ -1117,8 +1155,8 @@ delegate:
 
 	if (err < 0) {
 		spin_unlock(&ci->lock);
-		if (usb_ep_set_halt(&hwep->ep))
-			dev_err(ci->dev, "error: ep_set_halt\n");
+		if (_ep_set_halt(&hwep->ep, 1, false))
+			dev_err(ci->dev, "error: _ep_set_halt\n");
 		spin_lock(&ci->lock);
 	}
 }
@@ -1149,9 +1187,9 @@ __acquires(ci->lock)
 					err = isr_setup_status_phase(ci);
 				if (err < 0) {
 					spin_unlock(&ci->lock);
-					if (usb_ep_set_halt(&hwep->ep))
+					if (_ep_set_halt(&hwep->ep, 1, false))
 						dev_err(ci->dev,
-							"error: ep_set_halt\n");
+						"error: _ep_set_halt\n");
 					spin_lock(&ci->lock);
 				}
 			}
@@ -1397,41 +1435,7 @@ static int ep_dequeue(struct usb_ep *ep, struct usb_request *req)
  */
 static int ep_set_halt(struct usb_ep *ep, int value)
 {
-	struct ci_hw_ep *hwep = container_of(ep, struct ci_hw_ep, ep);
-	int direction, retval = 0;
-	unsigned long flags;
-
-	if (ep == NULL || hwep->ep.desc == NULL)
-		return -EINVAL;
-
-	if (usb_endpoint_xfer_isoc(hwep->ep.desc))
-		return -EOPNOTSUPP;
-
-	spin_lock_irqsave(hwep->lock, flags);
-
-#ifndef STALL_IN
-	/* g_file_storage MS compliant but g_zero fails chapter 9 compliance */
-	if (value && hwep->type == USB_ENDPOINT_XFER_BULK && hwep->dir == TX &&
-	    !list_empty(&hwep->qh.queue)) {
-		spin_unlock_irqrestore(hwep->lock, flags);
-		return -EAGAIN;
-	}
-#endif
-
-	direction = hwep->dir;
-	do {
-		retval |= hw_ep_set_halt(hwep->ci, hwep->num, hwep->dir, value);
-
-		if (!value)
-			hwep->wedge = 0;
-
-		if (hwep->type == USB_ENDPOINT_XFER_CONTROL)
-			hwep->dir = (hwep->dir == TX) ? RX : TX;
-
-	} while (hwep->dir != direction);
-
-	spin_unlock_irqrestore(hwep->lock, flags);
-	return retval;
+	return _ep_set_halt(ep, value, true);
 }
 
 /**
diff --git a/drivers/usb/core/config.c b/drivers/usb/core/config.c
index b2a540b43f97..b9ddf0c1ffe5 100644
--- a/drivers/usb/core/config.c
+++ b/drivers/usb/core/config.c
@@ -112,7 +112,7 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 				cfgno, inum, asnum, ep->desc.bEndpointAddress);
 		ep->ss_ep_comp.bmAttributes = 16;
 	} else if (usb_endpoint_xfer_isoc(&ep->desc) &&
-			desc->bmAttributes > 2) {
+		   USB_SS_MULT(desc->bmAttributes) > 3) {
 		dev_warn(ddev, "Isoc endpoint has Mult of %d in "
 				"config %d interface %d altsetting %d ep %d: "
 				"setting to 3\n", desc->bmAttributes + 1,
@@ -121,7 +121,8 @@ static void usb_parse_ss_endpoint_companion(struct device *ddev, int cfgno,
 	}
 
 	if (usb_endpoint_xfer_isoc(&ep->desc))
-		max_tx = (desc->bMaxBurst + 1) * (desc->bmAttributes + 1) *
+		max_tx = (desc->bMaxBurst + 1) *
+			(USB_SS_MULT(desc->bmAttributes)) *
 			usb_endpoint_maxp(&ep->desc);
 	else if (usb_endpoint_xfer_int(&ep->desc))
 		max_tx = usb_endpoint_maxp(&ep->desc) *
diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
index a5a1b7c45743..22e9606d8e08 100644
--- a/drivers/usb/dwc3/dwc3-omap.c
+++ b/drivers/usb/dwc3/dwc3-omap.c
@@ -514,8 +514,6 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 		goto err1;
 	}
 
-	dwc3_omap_enable_irqs(omap);
-
 	ret = dwc3_omap_extcon_register(omap);
 	if (ret < 0)
 		goto err2;
@@ -526,6 +524,8 @@ static int dwc3_omap_probe(struct platform_device *pdev)
 		goto err3;
 	}
 
+	dwc3_omap_enable_irqs(omap);
+
 	return 0;
 
 err3:
diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
index 0c25704dcb6b..1e8bdf817811 100644
--- a/drivers/usb/dwc3/gadget.c
+++ b/drivers/usb/dwc3/gadget.c
@@ -2665,8 +2665,6 @@ static irqreturn_t dwc3_interrupt(int irq, void *_dwc)
 	int				i;
 	irqreturn_t			ret = IRQ_NONE;
 
-	spin_lock(&dwc->lock);
-
 	for (i = 0; i < dwc->num_event_buffers; i++) {
 		irqreturn_t status;
 
@@ -2675,8 +2673,6 @@ static irqreturn_t dwc3_interrupt(int irq, void *_dwc)
 			ret = status;
 	}
 
-	spin_unlock(&dwc->lock);
-
 	return ret;
 }
 
diff --git a/drivers/usb/gadget/epautoconf.c b/drivers/usb/gadget/epautoconf.c
index 978435a51038..6399c106a3a5 100644
--- a/drivers/usb/gadget/epautoconf.c
+++ b/drivers/usb/gadget/epautoconf.c
@@ -186,6 +186,7 @@ void usb_ep_autoconfig_reset (struct usb_gadget *gadget)
 
 	list_for_each_entry (ep, &gadget->ep_list, ep_list) {
 		ep->claimed = false;
+		ep->driver_data = NULL;
 	}
 	gadget->in_epnum = 0;
 	gadget->out_epnum = 0;
diff --git a/drivers/usb/gadget/udc/amd5536udc.c b/drivers/usb/gadget/udc/amd5536udc.c
index fdacddb18c00..175ca93fe5e2 100644
--- a/drivers/usb/gadget/udc/amd5536udc.c
+++ b/drivers/usb/gadget/udc/amd5536udc.c
@@ -3138,8 +3138,8 @@ static void udc_pci_remove(struct pci_dev *pdev)
 	writel(AMD_BIT(UDC_DEVCFG_SOFTRESET), &dev->regs->cfg);
 	if (dev->irq_registered)
 		free_irq(pdev->irq, dev);
-	if (dev->regs)
-		iounmap(dev->regs);
+	if (dev->virt_addr)
+		iounmap(dev->virt_addr);
 	if (dev->mem_region)
 		release_mem_region(pci_resource_start(pdev, 0),
 				pci_resource_len(pdev, 0));
@@ -3226,17 +3226,13 @@ static int udc_pci_probe(
 
 	/* init */
 	dev = kzalloc(sizeof(struct udc), GFP_KERNEL);
-	if (!dev) {
-		retval = -ENOMEM;
-		goto finished;
-	}
+	if (!dev)
+		return -ENOMEM;
 
 	/* pci setup */
 	if (pci_enable_device(pdev) < 0) {
-		kfree(dev);
-		dev = NULL;
 		retval = -ENODEV;
-		goto finished;
+		goto err_pcidev;
 	}
 	dev->active = 1;
 
@@ -3246,28 +3242,22 @@ static int udc_pci_probe(
 
 	if (!request_mem_region(resource, len, name)) {
 		dev_dbg(&pdev->dev, "pci device used already\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -EBUSY;
-		goto finished;
+		goto err_memreg;
 	}
 	dev->mem_region = 1;
 
 	dev->virt_addr = ioremap_nocache(resource, len);
 	if (dev->virt_addr == NULL) {
 		dev_dbg(&pdev->dev, "start address cannot be mapped\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -EFAULT;
-		goto finished;
+		goto err_ioremap;
 	}
 
 	if (!pdev->irq) {
 		dev_err(&pdev->dev, "irq not set\n");
-		kfree(dev);
-		dev = NULL;
 		retval = -ENODEV;
-		goto finished;
+		goto err_irq;
 	}
 
 	spin_lock_init(&dev->lock);
@@ -3283,10 +3273,8 @@ static int udc_pci_probe(
 
 	if (request_irq(pdev->irq, udc_irq, IRQF_SHARED, name, dev) != 0) {
 		dev_dbg(&pdev->dev, "request_irq(%d) fail\n", pdev->irq);
-		kfree(dev);
-		dev = NULL;
 		retval = -EBUSY;
-		goto finished;
+		goto err_irq;
 	}
 	dev->irq_registered = 1;
 
@@ -3314,8 +3302,17 @@ static int udc_pci_probe(
 		return 0;
 
 finished:
-	if (dev)
-		udc_pci_remove(pdev);
+	udc_pci_remove(pdev);
+	return retval;
+
+err_irq:
+	iounmap(dev->virt_addr);
+err_ioremap:
+	release_mem_region(resource, len);
+err_memreg:
+	pci_disable_device(pdev);
+err_pcidev:
+	kfree(dev);
 	return retval;
 }
 
diff --git a/drivers/usb/gadget/udc/atmel_usba_udc.c b/drivers/usb/gadget/udc/atmel_usba_udc.c
index 3dfada8d6061..f0f2b066ac08 100644
--- a/drivers/usb/gadget/udc/atmel_usba_udc.c
+++ b/drivers/usb/gadget/udc/atmel_usba_udc.c
@@ -2002,6 +2002,17 @@ static struct usba_ep * atmel_udc_of_init(struct platform_device *pdev,
 		ep->udc = udc;
 		INIT_LIST_HEAD(&ep->queue);
 
+		if (ep->index == 0) {
+			ep->ep.caps.type_control = true;
+		} else {
+			ep->ep.caps.type_iso = ep->can_isoc;
+			ep->ep.caps.type_bulk = true;
+			ep->ep.caps.type_int = true;
+		}
+
+		ep->ep.caps.dir_in = true;
+		ep->ep.caps.dir_out = true;
+
 		if (i)
 			list_add_tail(&ep->ep.ep_list, &udc->gadget.ep_list);
 
diff --git a/drivers/usb/gadget/udc/bdc/bdc_core.c b/drivers/usb/gadget/udc/bdc/bdc_core.c
index 5c8f4effb62a..ccb9c213cc9f 100644
--- a/drivers/usb/gadget/udc/bdc/bdc_core.c
+++ b/drivers/usb/gadget/udc/bdc/bdc_core.c
@@ -324,8 +324,7 @@ static void bdc_mem_free(struct bdc *bdc)
 				bdc->scratchpad.buff, bdc->scratchpad.sp_dma);
 
 	/* Destroy the dma pools */
-	if (bdc->bd_table_pool)
-		dma_pool_destroy(bdc->bd_table_pool);
+	dma_pool_destroy(bdc->bd_table_pool);
 
 	/* Free the bdc_ep array */
 	kfree(bdc->bdc_ep_array);
diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
index 1379ad40d864..27af0f008b57 100644
--- a/drivers/usb/gadget/udc/dummy_hcd.c
+++ b/drivers/usb/gadget/udc/dummy_hcd.c
@@ -1348,6 +1348,7 @@ static int transfer(struct dummy_hcd *dum_hcd, struct urb *urb,
 {
 	struct dummy		*dum = dum_hcd->dum;
 	struct dummy_request	*req;
+	int			sent = 0;
 
 top:
 	/* if there's no request queued, the device is NAKing; return */
@@ -1385,12 +1386,15 @@ top:
 			if (len == 0)
 				break;
 
-			/* use an extra pass for the final short packet */
-			if (len > ep->ep.maxpacket) {
-				rescan = 1;
-				len -= (len % ep->ep.maxpacket);
+			/* send multiple of maxpacket first, then remainder */
+			if (len >= ep->ep.maxpacket) {
+				is_short = 0;
+				if (len % ep->ep.maxpacket)
+					rescan = 1;
+				len -= len % ep->ep.maxpacket;
+			} else {
+				is_short = 1;
 			}
-			is_short = (len % ep->ep.maxpacket) != 0;
 
 			len = dummy_perform_transfer(urb, req, len);
 
@@ -1399,6 +1403,7 @@ top:
 				req->req.status = len;
 			} else {
 				limit -= len;
+				sent += len;
 				urb->actual_length += len;
 				req->req.actual += len;
 			}
@@ -1421,7 +1426,7 @@ top:
 					*status = -EOVERFLOW;
 				else
 					*status = 0;
-			} else if (!to_host) {
+			} else {
 				*status = 0;
 				if (host_len > dev_len)
 					req->req.status = -EOVERFLOW;
@@ -1429,15 +1434,24 @@ top:
 					req->req.status = 0;
 			}
 
-		/* many requests terminate without a short packet */
+		/*
+		 * many requests terminate without a short packet.
+		 * send a zlp if demanded by flags.
+		 */
 		} else {
-			if (req->req.length == req->req.actual
-					&& !req->req.zero)
-				req->req.status = 0;
-			if (urb->transfer_buffer_length == urb->actual_length
-					&& !(urb->transfer_flags
-						& URB_ZERO_PACKET))
-				*status = 0;
+			if (req->req.length == req->req.actual) {
+				if (req->req.zero && to_host)
+					rescan = 1;
+				else
+					req->req.status = 0;
+			}
+			if (urb->transfer_buffer_length == urb->actual_length) {
+				if (urb->transfer_flags & URB_ZERO_PACKET &&
+				    !to_host)
+					rescan = 1;
+				else
+					*status = 0;
+			}
 		}
 
 		/* device side completion --> continuable */
@@ -1460,7 +1474,7 @@ top:
 		if (rescan)
 			goto top;
 	}
-	return limit;
+	return sent;
 }
 
 static int periodic_bytes(struct dummy *dum, struct dummy_ep *ep)
@@ -1890,7 +1904,7 @@ restart:
 		default:
 treat_control_like_bulk:
 			ep->last_io = jiffies;
-			total = transfer(dum_hcd, urb, ep, limit, &status);
+			total -= transfer(dum_hcd, urb, ep, limit, &status);
 			break;
 		}
 
diff --git a/drivers/usb/gadget/udc/gr_udc.c b/drivers/usb/gadget/udc/gr_udc.c
index 8aa2593c2c36..b9429bc42511 100644
--- a/drivers/usb/gadget/udc/gr_udc.c
+++ b/drivers/usb/gadget/udc/gr_udc.c
@@ -2117,8 +2117,7 @@ static int gr_remove(struct platform_device *pdev)
 		return -EBUSY;
 
 	gr_dfs_delete(dev);
-	if (dev->desc_pool)
-		dma_pool_destroy(dev->desc_pool);
+	dma_pool_destroy(dev->desc_pool);
 	platform_set_drvdata(pdev, NULL);
 
 	gr_free_request(&dev->epi[0].ep, &dev->ep0reqi->req);
diff --git a/drivers/usb/gadget/udc/mv_u3d_core.c b/drivers/usb/gadget/udc/mv_u3d_core.c
index 4c489692745e..dafe74eb9ade 100644
--- a/drivers/usb/gadget/udc/mv_u3d_core.c
+++ b/drivers/usb/gadget/udc/mv_u3d_core.c
@@ -1767,8 +1767,7 @@ static int mv_u3d_remove(struct platform_device *dev)
 	usb_del_gadget_udc(&u3d->gadget);
 
 	/* free memory allocated in probe */
-	if (u3d->trb_pool)
-		dma_pool_destroy(u3d->trb_pool);
+	dma_pool_destroy(u3d->trb_pool);
 
 	if (u3d->ep_context)
 		dma_free_coherent(&dev->dev, u3d->ep_context_size,
diff --git a/drivers/usb/gadget/udc/mv_udc_core.c b/drivers/usb/gadget/udc/mv_udc_core.c
index 339af51df57d..81b6229c7805 100644
--- a/drivers/usb/gadget/udc/mv_udc_core.c
+++ b/drivers/usb/gadget/udc/mv_udc_core.c
@@ -2100,8 +2100,7 @@ static int mv_udc_remove(struct platform_device *pdev)
 	}
 
 	/* free memory allocated in probe */
-	if (udc->dtd_pool)
-		dma_pool_destroy(udc->dtd_pool);
+	dma_pool_destroy(udc->dtd_pool);
 
 	if (udc->ep_dqh)
 		dma_free_coherent(&pdev->dev, udc->ep_dqh_size,
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 9a8c936cd42c..41f841fa6c4d 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1498,10 +1498,10 @@ int xhci_endpoint_init(struct xhci_hcd *xhci,
 	 * use Event Data TRBs, and we don't chain in a link TRB on short
 	 * transfers, we're basically dividing by 1.
 	 *
-	 * xHCI 1.0 specification indicates that the Average TRB Length should
-	 * be set to 8 for control endpoints.
+	 * xHCI 1.0 and 1.1 specification indicates that the Average TRB Length
+	 * should be set to 8 for control endpoints.
 	 */
-	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version == 0x100)
+	if (usb_endpoint_xfer_control(&ep->desc) && xhci->hci_version >= 0x100)
 		ep_ctx->tx_info |= cpu_to_le32(AVG_TRB_LENGTH_FOR_EP(8));
 	else
 		ep_ctx->tx_info |=
@@ -1792,8 +1792,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
 	int size;
 	int i, j, num_ports;
 
-	if (timer_pending(&xhci->cmd_timer))
-		del_timer_sync(&xhci->cmd_timer);
+	del_timer_sync(&xhci->cmd_timer);
 
 	/* Free the Event Ring Segment Table and the actual Event Ring */
 	size = sizeof(struct xhci_erst_entry)*(xhci->erst.num_entries);
@@ -2321,6 +2320,10 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 
 	INIT_LIST_HEAD(&xhci->cmd_list);
 
+	/* init command timeout timer */
+	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
+		    (unsigned long)xhci);
+
 	page_size = readl(&xhci->op_regs->page_size);
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"Supported page size register = 0x%x", page_size);
@@ -2505,10 +2508,6 @@ int xhci_mem_init(struct xhci_hcd *xhci, gfp_t flags)
 			"Wrote ERST address to ir_set 0.");
 	xhci_print_ir_set(xhci, 0);
 
-	/* init command timeout timer */
-	setup_timer(&xhci->cmd_timer, xhci_handle_command_timeout,
-		    (unsigned long)xhci);
-
 	/*
 	 * XXX: Might need to set the Interrupter Moderation Register to
 	 * something other than the default (~1ms minimum between interrupts).
diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
index 5590eac2b22d..c79d33676672 100644
--- a/drivers/usb/host/xhci-pci.c
+++ b/drivers/usb/host/xhci-pci.c
@@ -180,51 +180,6 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
 				"QUIRK: Resetting on resume");
 }
 
-/*
- * In some Intel xHCI controllers, in order to get D3 working,
- * through a vendor specific SSIC CONFIG register at offset 0x883c,
- * SSIC PORT need to be marked as "unused" before putting xHCI
- * into D3. After D3 exit, the SSIC port need to be marked as "used".
- * Without this change, xHCI might not enter D3 state.
- * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
- * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
- */
-static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
-{
-	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
-	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
-	u32 val;
-	void __iomem *reg;
-
-	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
-		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
-
-		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
-
-		/* Notify SSIC that SSIC profile programming is not done */
-		val = readl(reg) & ~PROG_DONE;
-		writel(val, reg);
-
-		/* Mark SSIC port as unused(suspend) or used(resume) */
-		val = readl(reg);
-		if (suspend)
-			val |= SSIC_PORT_UNUSED;
-		else
-			val &= ~SSIC_PORT_UNUSED;
-		writel(val, reg);
-
-		/* Notify SSIC that SSIC profile programming is done */
-		val = readl(reg) | PROG_DONE;
-		writel(val, reg);
-		readl(reg);
-	}
-
-	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
-	val = readl(reg);
-	writel(val | BIT(28), reg);
-	readl(reg);
-}
-
 #ifdef CONFIG_ACPI
 static void xhci_pme_acpi_rtd3_enable(struct pci_dev *dev)
 {
@@ -345,6 +300,51 @@ static void xhci_pci_remove(struct pci_dev *dev)
 }
 
 #ifdef CONFIG_PM
+/*
+ * In some Intel xHCI controllers, in order to get D3 working,
+ * through a vendor specific SSIC CONFIG register at offset 0x883c,
+ * SSIC PORT need to be marked as "unused" before putting xHCI
+ * into D3. After D3 exit, the SSIC port need to be marked as "used".
+ * Without this change, xHCI might not enter D3 state.
+ * Make sure PME works on some Intel xHCI controllers by writing 1 to clear
+ * the Internal PME flag bit in vendor specific PMCTRL register at offset 0x80a4
+ */
+static void xhci_pme_quirk(struct usb_hcd *hcd, bool suspend)
+{
+	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
+	struct pci_dev		*pdev = to_pci_dev(hcd->self.controller);
+	u32 val;
+	void __iomem *reg;
+
+	if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+		 pdev->device == PCI_DEVICE_ID_INTEL_CHERRYVIEW_XHCI) {
+
+		reg = (void __iomem *) xhci->cap_regs + PORT2_SSIC_CONFIG_REG2;
+
+		/* Notify SSIC that SSIC profile programming is not done */
+		val = readl(reg) & ~PROG_DONE;
+		writel(val, reg);
+
+		/* Mark SSIC port as unused(suspend) or used(resume) */
+		val = readl(reg);
+		if (suspend)
+			val |= SSIC_PORT_UNUSED;
+		else
+			val &= ~SSIC_PORT_UNUSED;
+		writel(val, reg);
+
+		/* Notify SSIC that SSIC profile programming is done */
+		val = readl(reg) | PROG_DONE;
+		writel(val, reg);
+		readl(reg);
+	}
+
+	reg = (void __iomem *) xhci->cap_regs + 0x80a4;
+	val = readl(reg);
+	writel(val | BIT(28), reg);
+	readl(reg);
+}
+
 static int xhci_pci_suspend(struct usb_hcd *hcd, bool do_wakeup)
 {
 	struct xhci_hcd	*xhci = hcd_to_xhci(hcd);
diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
index a47a1e897086..43291f93afeb 100644
--- a/drivers/usb/host/xhci-ring.c
+++ b/drivers/usb/host/xhci-ring.c
@@ -302,6 +302,15 @@ static int xhci_abort_cmd_ring(struct xhci_hcd *xhci)
 	ret = xhci_handshake(&xhci->op_regs->cmd_ring,
 			CMD_RING_RUNNING, 0, 5 * 1000 * 1000);
 	if (ret < 0) {
+		/* we are about to kill xhci, give it one more chance */
+		xhci_write_64(xhci, temp_64 | CMD_RING_ABORT,
+			      &xhci->op_regs->cmd_ring);
+		udelay(1000);
+		ret = xhci_handshake(&xhci->op_regs->cmd_ring,
+				     CMD_RING_RUNNING, 0, 3 * 1000 * 1000);
+		if (ret == 0)
+			return 0;
+
 		xhci_err(xhci, "Stopped the command ring failed, "
 				"maybe the host is dead\n");
 		xhci->xhc_state |= XHCI_STATE_DYING;
@@ -3461,8 +3470,8 @@ int xhci_queue_ctrl_tx(struct xhci_hcd *xhci, gfp_t mem_flags,
 	if (start_cycle == 0)
 		field |= 0x1;
 
-	/* xHCI 1.0 6.4.1.2.1: Transfer Type field */
-	if (xhci->hci_version == 0x100) {
+	/* xHCI 1.0/1.1 6.4.1.2.1: Transfer Type field */
+	if (xhci->hci_version >= 0x100) {
 		if (urb->transfer_buffer_length > 0) {
 			if (setup->bRequestType & USB_DIR_IN)
 				field |= TRB_TX_TYPE(TRB_DATA_IN);
diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
index 6b0f4a47e402..9957bd96d4bc 100644
--- a/drivers/usb/host/xhci.c
+++ b/drivers/usb/host/xhci.c
@@ -146,7 +146,8 @@ static int xhci_start(struct xhci_hcd *xhci)
 				"waited %u microseconds.\n",
 				XHCI_MAX_HALT_USEC);
 	if (!ret)
-		xhci->xhc_state &= ~XHCI_STATE_HALTED;
+		xhci->xhc_state &= ~(XHCI_STATE_HALTED | XHCI_STATE_DYING);
+
 	return ret;
 }
 
@@ -654,15 +655,6 @@ int xhci_run(struct usb_hcd *hcd)
 }
 EXPORT_SYMBOL_GPL(xhci_run);
 
-static void xhci_only_stop_hcd(struct usb_hcd *hcd)
-{
-	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
-
-	spin_lock_irq(&xhci->lock);
-	xhci_halt(xhci);
-	spin_unlock_irq(&xhci->lock);
-}
-
 /*
  * Stop xHCI driver.
  *
@@ -677,12 +669,14 @@ void xhci_stop(struct usb_hcd *hcd)
 	u32 temp;
 	struct xhci_hcd *xhci = hcd_to_xhci(hcd);
 
-	if (!usb_hcd_is_primary_hcd(hcd)) {
-		xhci_only_stop_hcd(xhci->shared_hcd);
+	if (xhci->xhc_state & XHCI_STATE_HALTED)
 		return;
-	}
 
+	mutex_lock(&xhci->mutex);
 	spin_lock_irq(&xhci->lock);
+	xhci->xhc_state |= XHCI_STATE_HALTED;
+	xhci->cmd_ring_state = CMD_RING_STATE_STOPPED;
+
 	/* Make sure the xHC is halted for a USB3 roothub
 	 * (xhci_stop() could be called as part of failed init).
 	 */
@@ -717,6 +711,7 @@ void xhci_stop(struct usb_hcd *hcd)
 	xhci_dbg_trace(xhci, trace_xhci_dbg_init,
 			"xhci_stop completed - status = %x",
 			readl(&xhci->op_regs->status));
+	mutex_unlock(&xhci->mutex);
 }
 
 /*
@@ -3793,6 +3788,9 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
 
 	mutex_lock(&xhci->mutex);
 
+	if (xhci->xhc_state)	/* dying or halted */
+		goto out;
+
 	if (!udev->slot_id) {
 		xhci_dbg_trace(xhci, trace_xhci_dbg_address,
 				"Bad Slot ID %d", udev->slot_id);
diff --git a/drivers/usb/musb/musb_core.c b/drivers/usb/musb/musb_core.c
index 514a6cdaeff6..4a518ff12310 100644
--- a/drivers/usb/musb/musb_core.c
+++ b/drivers/usb/musb/musb_core.c
@@ -1051,6 +1051,7 @@ void musb_start(struct musb *musb)
 	 * (c) peripheral initiates, using SRP
 	 */
 	if (musb->port_mode != MUSB_PORT_MODE_HOST &&
+			musb->xceiv->otg->state != OTG_STATE_A_WAIT_BCON &&
 			(devctl & MUSB_DEVCTL_VBUS) == MUSB_DEVCTL_VBUS) {
 		musb->is_active = 1;
 	} else {
@@ -2448,6 +2449,9 @@ static int musb_suspend(struct device *dev)
 	struct musb	*musb = dev_to_musb(dev);
 	unsigned long	flags;
 
+	musb_platform_disable(musb);
+	musb_generic_disable(musb);
+
 	spin_lock_irqsave(&musb->lock, flags);
 
 	if (is_peripheral_active(musb)) {
@@ -2501,6 +2505,9 @@ static int musb_resume(struct device *dev)
 	pm_runtime_disable(dev);
 	pm_runtime_set_active(dev);
 	pm_runtime_enable(dev);
+
+	musb_start(musb);
+
 	return 0;
 }
 
diff --git a/drivers/usb/musb/musb_cppi41.c b/drivers/usb/musb/musb_cppi41.c
index d07cafb7d5f5..e499b862a946 100644
--- a/drivers/usb/musb/musb_cppi41.c
+++ b/drivers/usb/musb/musb_cppi41.c
@@ -551,6 +551,9 @@ static int cppi41_dma_channel_abort(struct dma_channel *channel)
 	} else {
 		cppi41_set_autoreq_mode(cppi41_channel, EP_MODE_AUTOREQ_NONE);
 
+		/* delay to drain to cppi dma pipeline for isoch */
+		udelay(250);
+
 		csr = musb_readw(epio, MUSB_RXCSR);
 		csr &= ~(MUSB_RXCSR_H_REQPKT | MUSB_RXCSR_DMAENAB);
 		musb_writew(epio, MUSB_RXCSR, csr);
diff --git a/drivers/usb/musb/musb_dsps.c b/drivers/usb/musb/musb_dsps.c
index a0cfead6150f..84512d1d5eee 100644
--- a/drivers/usb/musb/musb_dsps.c
+++ b/drivers/usb/musb/musb_dsps.c
@@ -225,8 +225,11 @@ static void dsps_musb_enable(struct musb *musb)
 
 	dsps_writel(reg_base, wrp->epintr_set, epmask);
 	dsps_writel(reg_base, wrp->coreintr_set, coremask);
-	/* start polling for ID change. */
-	mod_timer(&glue->timer, jiffies + msecs_to_jiffies(wrp->poll_timeout));
+	/* start polling for ID change in dual-role idle mode */
+	if (musb->xceiv->otg->state == OTG_STATE_B_IDLE &&
+			musb->port_mode == MUSB_PORT_MODE_DUAL_ROLE)
+		mod_timer(&glue->timer, jiffies +
+				msecs_to_jiffies(wrp->poll_timeout));
 	dsps_musb_try_idle(musb, 0);
 }
 
diff --git a/drivers/usb/musb/ux500.c b/drivers/usb/musb/ux500.c
index 39168fe9b406..b2685e75a683 100644
--- a/drivers/usb/musb/ux500.c
+++ b/drivers/usb/musb/ux500.c
@@ -379,6 +379,8 @@ static const struct of_device_id ux500_match[] = {
         {}
 };
 
+MODULE_DEVICE_TABLE(of, ux500_match);
+
 static struct platform_driver ux500_driver = {
 	.probe		= ux500_probe,
 	.remove		= ux500_remove,
diff --git a/drivers/usb/phy/Kconfig b/drivers/usb/phy/Kconfig
index 7d3beee2a587..173132416170 100644
--- a/drivers/usb/phy/Kconfig
+++ b/drivers/usb/phy/Kconfig
@@ -155,7 +155,7 @@ config USB_MSM_OTG
 config USB_QCOM_8X16_PHY
 	tristate "Qualcomm APQ8016/MSM8916 on-chip USB PHY controller support"
 	depends on ARCH_QCOM || COMPILE_TEST
-	depends on RESET_CONTROLLER
+	depends on RESET_CONTROLLER && EXTCON
 	select USB_PHY
 	select USB_ULPI_VIEWPORT
 	help
diff --git a/drivers/usb/phy/phy-generic.c b/drivers/usb/phy/phy-generic.c
index ec6ecd03269c..5320cb8642cb 100644
--- a/drivers/usb/phy/phy-generic.c
+++ b/drivers/usb/phy/phy-generic.c
@@ -232,7 +232,8 @@ int usb_phy_gen_create_phy(struct device *dev, struct usb_phy_generic *nop,
 		clk_rate = pdata->clk_rate;
 		needs_vcc = pdata->needs_vcc;
 		if (gpio_is_valid(pdata->gpio_reset)) {
-			err = devm_gpio_request_one(dev, pdata->gpio_reset, 0,
+			err = devm_gpio_request_one(dev, pdata->gpio_reset,
+						    GPIOF_ACTIVE_LOW,
 						    dev_name(dev));
 			if (!err)
 				nop->gpiod_reset =
diff --git a/drivers/usb/phy/phy-isp1301.c b/drivers/usb/phy/phy-isp1301.c
index 8a55b37d1a02..db68156568e6 100644
--- a/drivers/usb/phy/phy-isp1301.c
+++ b/drivers/usb/phy/phy-isp1301.c
@@ -31,6 +31,7 @@ static const struct i2c_device_id isp1301_id[] = {
 	{ "isp1301", 0 },
 	{ }
 };
+MODULE_DEVICE_TABLE(i2c, isp1301_id);
 
 static struct i2c_client *isp1301_i2c_client;
 
diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
index 6d1941a2396a..6956c4f62216 100644
--- a/drivers/usb/serial/option.c
+++ b/drivers/usb/serial/option.c
@@ -278,6 +278,10 @@ static void option_instat_callback(struct urb *urb);
 #define ZTE_PRODUCT_MF622			0x0001
 #define ZTE_PRODUCT_MF628			0x0015
 #define ZTE_PRODUCT_MF626			0x0031
+#define ZTE_PRODUCT_ZM8620_X			0x0396
+#define ZTE_PRODUCT_ME3620_MBIM			0x0426
+#define ZTE_PRODUCT_ME3620_X			0x1432
+#define ZTE_PRODUCT_ME3620_L			0x1433
 #define ZTE_PRODUCT_AC2726			0xfff1
 #define ZTE_PRODUCT_MG880			0xfffd
 #define ZTE_PRODUCT_CDMA_TECH			0xfffe
@@ -544,6 +548,18 @@ static const struct option_blacklist_info zte_mc2716_z_blacklist = {
 	.sendsetup = BIT(1) | BIT(2) | BIT(3),
 };
 
+static const struct option_blacklist_info zte_me3620_mbim_blacklist = {
+	.reserved = BIT(2) | BIT(3) | BIT(4),
+};
+
+static const struct option_blacklist_info zte_me3620_xl_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
+static const struct option_blacklist_info zte_zm8620_x_blacklist = {
+	.reserved = BIT(3) | BIT(4) | BIT(5),
+};
+
 static const struct option_blacklist_info huawei_cdc12_blacklist = {
 	.reserved = BIT(1) | BIT(2),
 };
@@ -1591,6 +1607,14 @@ static const struct usb_device_id option_ids[] = {
 	 .driver_info = (kernel_ulong_t)&zte_ad3812_z_blacklist },
 	{ USB_DEVICE_AND_INTERFACE_INFO(ZTE_VENDOR_ID, ZTE_PRODUCT_MC2716, 0xff, 0xff, 0xff),
 	 .driver_info = (kernel_ulong_t)&zte_mc2716_z_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_L),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_MBIM),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_mbim_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ME3620_X),
+	 .driver_info = (kernel_ulong_t)&zte_me3620_xl_blacklist },
+	{ USB_DEVICE(ZTE_VENDOR_ID, ZTE_PRODUCT_ZM8620_X),
+	 .driver_info = (kernel_ulong_t)&zte_zm8620_x_blacklist },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x01) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x02, 0x05) },
 	{ USB_VENDOR_AND_INTERFACE_INFO(ZTE_VENDOR_ID, 0xff, 0x86, 0x10) },
diff --git a/drivers/usb/serial/whiteheat.c b/drivers/usb/serial/whiteheat.c
index 6c3734d2b45a..d3ea90bef84d 100644
--- a/drivers/usb/serial/whiteheat.c
+++ b/drivers/usb/serial/whiteheat.c
@@ -80,6 +80,8 @@ static int  whiteheat_firmware_download(struct usb_serial *serial,
 static int  whiteheat_firmware_attach(struct usb_serial *serial);
 
 /* function prototypes for the Connect Tech WhiteHEAT serial converter */
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id);
 static int  whiteheat_attach(struct usb_serial *serial);
 static void whiteheat_release(struct usb_serial *serial);
 static int  whiteheat_port_probe(struct usb_serial_port *port);
@@ -116,6 +118,7 @@ static struct usb_serial_driver whiteheat_device = {
 	.description =		"Connect Tech - WhiteHEAT",
 	.id_table =		id_table_std,
 	.num_ports =		4,
+	.probe =		whiteheat_probe,
 	.attach =		whiteheat_attach,
 	.release =		whiteheat_release,
 	.port_probe =		whiteheat_port_probe,
@@ -217,6 +220,34 @@ static int whiteheat_firmware_attach(struct usb_serial *serial)
 /*****************************************************************************
  * Connect Tech's White Heat serial driver functions
  *****************************************************************************/
+
+static int whiteheat_probe(struct usb_serial *serial,
+				const struct usb_device_id *id)
+{
+	struct usb_host_interface *iface_desc;
+	struct usb_endpoint_descriptor *endpoint;
+	size_t num_bulk_in = 0;
+	size_t num_bulk_out = 0;
+	size_t min_num_bulk;
+	unsigned int i;
+
+	iface_desc = serial->interface->cur_altsetting;
+
+	for (i = 0; i < iface_desc->desc.bNumEndpoints; i++) {
+		endpoint = &iface_desc->endpoint[i].desc;
+		if (usb_endpoint_is_bulk_in(endpoint))
+			++num_bulk_in;
+		if (usb_endpoint_is_bulk_out(endpoint))
+			++num_bulk_out;
+	}
+
+	min_num_bulk = COMMAND_PORT + 1;
+	if (num_bulk_in < min_num_bulk || num_bulk_out < min_num_bulk)
+		return -ENODEV;
+
+	return 0;
+}
+
 static int whiteheat_attach(struct usb_serial *serial)
 {
 	struct usb_serial_port *command_port;
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index c68edc16aa54..79e1aa1b0959 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -817,8 +817,9 @@ config ITCO_WDT
 	tristate "Intel TCO Timer/Watchdog"
 	depends on (X86 || IA64) && PCI
 	select WATCHDOG_CORE
+	depends on I2C || I2C=n
 	select LPC_ICH if !EXPERT
-	select I2C_I801 if !EXPERT
+	select I2C_I801 if !EXPERT && I2C
 	---help---
 	  Hardware driver for the intel TCO timer based watchdog devices.
 	  These drivers are included in the Intel 82801 I/O Controller
diff --git a/drivers/watchdog/bcm2835_wdt.c b/drivers/watchdog/bcm2835_wdt.c
index 66c3e656a616..8a5ce5b5a0b6 100644
--- a/drivers/watchdog/bcm2835_wdt.c
+++ b/drivers/watchdog/bcm2835_wdt.c
@@ -36,6 +36,13 @@
 #define PM_RSTC_WRCFG_FULL_RESET	0x00000020
 #define PM_RSTC_RESET			0x00000102
 
+/*
+ * The Raspberry Pi firmware uses the RSTS register to know which partiton
+ * to boot from. The partiton value is spread into bits 0, 2, 4, 6, 8, 10.
+ * Partiton 63 is a special partition used by the firmware to indicate halt.
+ */
+#define PM_RSTS_RASPBERRYPI_HALT	0x555
+
 #define SECS_TO_WDOG_TICKS(x) ((x) << 16)
 #define WDOG_TICKS_TO_SECS(x) ((x) >> 16)
 
@@ -151,8 +158,7 @@ static void bcm2835_power_off(void)
 	 * hard reset.
 	 */
 	val = readl_relaxed(wdt->base + PM_RSTS);
-	val &= PM_RSTC_WRCFG_CLR;
-	val |= PM_PASSWORD | PM_RSTS_HADWRH_SET;
+	val |= PM_PASSWORD | PM_RSTS_RASPBERRYPI_HALT;
 	writel_relaxed(val, wdt->base + PM_RSTS);
 
 	/* Continue with normal reset mechanism */
diff --git a/drivers/watchdog/gef_wdt.c b/drivers/watchdog/gef_wdt.c
index cc1bdfc2ff71..006e2348022c 100644
--- a/drivers/watchdog/gef_wdt.c
+++ b/drivers/watchdog/gef_wdt.c
@@ -303,6 +303,7 @@ static const struct of_device_id gef_wdt_ids[] = {
 	},
 	{},
 };
+MODULE_DEVICE_TABLE(of, gef_wdt_ids);
 
 static struct platform_driver gef_wdt_driver = {
 	.driver = {
diff --git a/drivers/watchdog/mena21_wdt.c b/drivers/watchdog/mena21_wdt.c
index 69013007dc47..098fa9c34d6d 100644
--- a/drivers/watchdog/mena21_wdt.c
+++ b/drivers/watchdog/mena21_wdt.c
@@ -253,6 +253,7 @@ static const struct of_device_id a21_wdt_ids[] = {
 	{ .compatible = "men,a021-wdt" },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, a21_wdt_ids);
 
 static struct platform_driver a21_wdt_driver = {
 	.probe = a21_wdt_probe,
diff --git a/drivers/watchdog/moxart_wdt.c b/drivers/watchdog/moxart_wdt.c
index 2789da2c0515..60b0605bd7e6 100644
--- a/drivers/watchdog/moxart_wdt.c
+++ b/drivers/watchdog/moxart_wdt.c
@@ -168,6 +168,7 @@ static const struct of_device_id moxart_watchdog_match[] = {
 	{ .compatible = "moxa,moxart-watchdog" },
 	{ },
 };
+MODULE_DEVICE_TABLE(of, moxart_watchdog_match);
 
 static struct platform_driver moxart_wdt_driver = {
 	.probe      = moxart_wdt_probe,
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index aa0dc2573374..afa09fce8151 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -444,6 +444,48 @@ find_domain_name(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	return 0;
 }
 
+/* Server has provided av pairs/target info in the type 2 challenge
+ * packet and we have plucked it and stored within smb session.
+ * We parse that blob here to find the server given timestamp
+ * as part of ntlmv2 authentication (or local current time as
+ * default in case of failure)
+ */
+static __le64
+find_timestamp(struct cifs_ses *ses)
+{
+	unsigned int attrsize;
+	unsigned int type;
+	unsigned int onesize = sizeof(struct ntlmssp2_name);
+	unsigned char *blobptr;
+	unsigned char *blobend;
+	struct ntlmssp2_name *attrptr;
+
+	if (!ses->auth_key.len || !ses->auth_key.response)
+		return 0;
+
+	blobptr = ses->auth_key.response;
+	blobend = blobptr + ses->auth_key.len;
+
+	while (blobptr + onesize < blobend) {
+		attrptr = (struct ntlmssp2_name *) blobptr;
+		type = le16_to_cpu(attrptr->type);
+		if (type == NTLMSSP_AV_EOL)
+			break;
+		blobptr += 2; /* advance attr type */
+		attrsize = le16_to_cpu(attrptr->length);
+		blobptr += 2; /* advance attr size */
+		if (blobptr + attrsize > blobend)
+			break;
+		if (type == NTLMSSP_AV_TIMESTAMP) {
+			if (attrsize == sizeof(u64))
+				return *((__le64 *)blobptr);
+		}
+		blobptr += attrsize; /* advance attr value */
+	}
+
+	return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+}
+
 static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
 			    const struct nls_table *nls_cp)
 {
@@ -641,6 +683,7 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 	struct ntlmv2_resp *ntlmv2;
 	char ntlmv2_hash[16];
 	unsigned char *tiblob = NULL; /* target info blob */
+	__le64 rsp_timestamp;
 
 	if (ses->server->negflavor == CIFS_NEGFLAVOR_EXTENDED) {
 		if (!ses->domainName) {
@@ -659,6 +702,12 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 		}
 	}
 
+	/* Must be within 5 minutes of the server (or in range +/-2h
+	 * in case of Mac OS X), so simply carry over server timestamp
+	 * (as Windows 7 does)
+	 */
+	rsp_timestamp = find_timestamp(ses);
+
 	baselen = CIFS_SESS_KEY_SIZE + sizeof(struct ntlmv2_resp);
 	tilen = ses->auth_key.len;
 	tiblob = ses->auth_key.response;
@@ -675,8 +724,8 @@ setup_ntlmv2_rsp(struct cifs_ses *ses, const struct nls_table *nls_cp)
 			(ses->auth_key.response + CIFS_SESS_KEY_SIZE);
 	ntlmv2->blob_signature = cpu_to_le32(0x00000101);
 	ntlmv2->reserved = 0;
-	/* Must be within 5 minutes of the server */
-	ntlmv2->time = cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+	ntlmv2->time = rsp_timestamp;
+
 	get_random_bytes(&ntlmv2->client_chal, sizeof(ntlmv2->client_chal));
 	ntlmv2->reserved2 = 0;
 
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index df91bcf56d67..18da19f4f811 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -50,9 +50,13 @@ change_conf(struct TCP_Server_Info *server)
 		break;
 	default:
 		server->echoes = true;
-		server->oplocks = true;
+		if (enable_oplocks) {
+			server->oplocks = true;
+			server->oplock_credits = 1;
+		} else
+			server->oplocks = false;
+
 		server->echo_credits = 1;
-		server->oplock_credits = 1;
 	}
 	server->credits -= server->echo_credits + server->oplock_credits;
 	return 0;
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 070fb2ad85ce..ce83e2edbe0a 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -46,6 +46,7 @@
 #include "smb2status.h"
 #include "smb2glob.h"
 #include "cifspdu.h"
+#include "cifs_spnego.h"
 
 /*
  *  The following table defines the expected "StructureSize" of SMB2 requests
@@ -486,19 +487,15 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 		cifs_dbg(FYI, "missing security blob on negprot\n");
 
 	rc = cifs_enable_signing(server, ses->sign);
-#ifdef CONFIG_SMB2_ASN1  /* BB REMOVEME when updated asn1.c ready */
 	if (rc)
 		goto neg_exit;
-	if (blob_length)
+	if (blob_length) {
 		rc = decode_negTokenInit(security_blob, blob_length, server);
-	if (rc == 1)
-		rc = 0;
-	else if (rc == 0) {
-		rc = -EIO;
-		goto neg_exit;
+		if (rc == 1)
+			rc = 0;
+		else if (rc == 0)
+			rc = -EIO;
 	}
-#endif
-
 neg_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -592,7 +589,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	__le32 phase = NtLmNegotiate; /* NTLMSSP, if needed, is multistage */
 	struct TCP_Server_Info *server = ses->server;
 	u16 blob_length = 0;
-	char *security_blob;
+	struct key *spnego_key = NULL;
+	char *security_blob = NULL;
 	char *ntlmssp_blob = NULL;
 	bool use_spnego = false; /* else use raw ntlmssp */
 
@@ -620,7 +618,8 @@ SMB2_sess_setup(const unsigned int xid, struct cifs_ses *ses,
 	ses->ntlmssp->sesskey_per_smbsess = true;
 
 	/* FIXME: allow for other auth types besides NTLMSSP (e.g. krb5) */
-	ses->sectype = RawNTLMSSP;
+	if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
+		ses->sectype = RawNTLMSSP;
 
 ssetup_ntlmssp_authenticate:
 	if (phase == NtLmChallenge)
@@ -649,7 +648,48 @@ ssetup_ntlmssp_authenticate:
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field and 1 for pad */
 	iov[0].iov_len = get_rfc1002_length(req) + 4 - 1;
-	if (phase == NtLmNegotiate) {
+
+	if (ses->sectype == Kerberos) {
+#ifdef CONFIG_CIFS_UPCALL
+		struct cifs_spnego_msg *msg;
+
+		spnego_key = cifs_get_spnego_key(ses);
+		if (IS_ERR(spnego_key)) {
+			rc = PTR_ERR(spnego_key);
+			spnego_key = NULL;
+			goto ssetup_exit;
+		}
+
+		msg = spnego_key->payload.data;
+		/*
+		 * check version field to make sure that cifs.upcall is
+		 * sending us a response in an expected form
+		 */
+		if (msg->version != CIFS_SPNEGO_UPCALL_VERSION) {
+			cifs_dbg(VFS,
+				  "bad cifs.upcall version. Expected %d got %d",
+				  CIFS_SPNEGO_UPCALL_VERSION, msg->version);
+			rc = -EKEYREJECTED;
+			goto ssetup_exit;
+		}
+		ses->auth_key.response = kmemdup(msg->data, msg->sesskey_len,
+						 GFP_KERNEL);
+		if (!ses->auth_key.response) {
+			cifs_dbg(VFS,
+				"Kerberos can't allocate (%u bytes) memory",
+				msg->sesskey_len);
+			rc = -ENOMEM;
+			goto ssetup_exit;
+		}
+		ses->auth_key.len = msg->sesskey_len;
+		blob_length = msg->secblob_len;
+		iov[1].iov_base = msg->data + msg->sesskey_len;
+		iov[1].iov_len = blob_length;
+#else
+		rc = -EOPNOTSUPP;
+		goto ssetup_exit;
+#endif /* CONFIG_CIFS_UPCALL */
+	} else if (phase == NtLmNegotiate) { /* if not krb5 must be ntlmssp */
 		ntlmssp_blob = kmalloc(sizeof(struct _NEGOTIATE_MESSAGE),
 				       GFP_KERNEL);
 		if (ntlmssp_blob == NULL) {
@@ -672,6 +712,8 @@ ssetup_ntlmssp_authenticate:
 			/* with raw NTLMSSP we don't encapsulate in SPNEGO */
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else if (phase == NtLmAuthenticate) {
 		req->hdr.SessionId = ses->Suid;
 		ntlmssp_blob = kzalloc(sizeof(struct _NEGOTIATE_MESSAGE) + 500,
@@ -699,6 +741,8 @@ ssetup_ntlmssp_authenticate:
 		} else {
 			security_blob = ntlmssp_blob;
 		}
+		iov[1].iov_base = security_blob;
+		iov[1].iov_len = blob_length;
 	} else {
 		cifs_dbg(VFS, "illegal ntlmssp phase\n");
 		rc = -EIO;
@@ -710,8 +754,6 @@ ssetup_ntlmssp_authenticate:
 				cpu_to_le16(sizeof(struct smb2_sess_setup_req) -
 					    1 /* pad */ - 4 /* rfc1001 len */);
 	req->SecurityBufferLength = cpu_to_le16(blob_length);
-	iov[1].iov_base = security_blob;
-	iov[1].iov_len = blob_length;
 
 	inc_rfc1001_len(req, blob_length - 1 /* pad */);
 
@@ -722,6 +764,7 @@ ssetup_ntlmssp_authenticate:
 
 	kfree(security_blob);
 	rsp = (struct smb2_sess_setup_rsp *)iov[0].iov_base;
+	ses->Suid = rsp->hdr.SessionId;
 	if (resp_buftype != CIFS_NO_BUFFER &&
 	    rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED) {
 		if (phase != NtLmNegotiate) {
@@ -739,7 +782,6 @@ ssetup_ntlmssp_authenticate:
 		/* NTLMSSP Negotiate sent now processing challenge (response) */
 		phase = NtLmChallenge; /* process ntlmssp challenge */
 		rc = 0; /* MORE_PROCESSING is not an error here but expected */
-		ses->Suid = rsp->hdr.SessionId;
 		rc = decode_ntlmssp_challenge(rsp->Buffer,
 				le16_to_cpu(rsp->SecurityBufferLength), ses);
 	}
@@ -796,6 +838,10 @@ keygen_exit:
 		kfree(ses->auth_key.response);
 		ses->auth_key.response = NULL;
 	}
+	if (spnego_key) {
+		key_invalidate(spnego_key);
+		key_put(spnego_key);
+	}
 	kfree(ses->ntlmssp);
 
 	return rc;
@@ -876,6 +922,12 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	if (tcon && tcon->bad_network_name)
 		return -ENOENT;
 
+	if ((tcon->seal) &&
+	    ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) {
+		cifs_dbg(VFS, "encryption requested but no server support");
+		return -EOPNOTSUPP;
+	}
+
 	unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
 	if (unc_path == NULL)
 		return -ENOMEM;
@@ -955,6 +1007,8 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
 		cifs_dbg(VFS, "DFS capability contradicts DFS flag\n");
 	init_copy_chunk_defaults(tcon);
+	if (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)
+		cifs_dbg(VFS, "Encrypted shares not supported");
 	if (tcon->ses->server->ops->validate_negotiate)
 		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
diff --git a/fs/dax.c b/fs/dax.c
index 7ae6df7ea1d2..bcfb14bfc1e4 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -569,8 +569,20 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if (!buffer_size_valid(&bh) || bh.b_size < PMD_SIZE)
 		goto fallback;
 
+	sector = bh.b_blocknr << (blkbits - 9);
+
 	if (buffer_unwritten(&bh) || buffer_new(&bh)) {
 		int i;
+
+		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
+						bh.b_size);
+		if (length < 0) {
+			result = VM_FAULT_SIGBUS;
+			goto out;
+		}
+		if ((length < PMD_SIZE) || (pfn & PG_PMD_COLOUR))
+			goto fallback;
+
 		for (i = 0; i < PTRS_PER_PMD; i++)
 			clear_pmem(kaddr + i * PAGE_SIZE, PAGE_SIZE);
 		wmb_pmem();
@@ -623,7 +635,6 @@ int __dax_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		result = VM_FAULT_NOPAGE;
 		spin_unlock(ptl);
 	} else {
-		sector = bh.b_blocknr << (blkbits - 9);
 		length = bdev_direct_access(bh.b_bdev, sector, &kaddr, &pfn,
 						bh.b_size);
 		if (length < 0) {
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index 96f3448b6eb4..fd65b3f1923c 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -652,11 +652,8 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode,
 {
 	int err;
 
-	mutex_lock(&inode->i_mutex);
 	err = security_inode_init_security(inode, dentry, qstr,
 					   &init_xattrs, 0);
-	mutex_unlock(&inode->i_mutex);
-
 	if (err) {
 		struct ubifs_info *c = dentry->i_sb->s_fs_info;
 		ubifs_err(c, "cannot initialize security for inode %lu, error %d",
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 7235c4851460..43856d19cf4d 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -217,6 +217,7 @@ struct pci_dev;
 
 int acpi_pci_irq_enable (struct pci_dev *dev);
 void acpi_penalize_isa_irq(int irq, int active);
+bool acpi_isa_irq_available(int irq);
 void acpi_penalize_sci_irq(int irq, int trigger, int polarity);
 void acpi_pci_irq_disable (struct pci_dev *dev);
 
diff --git a/include/linux/iova.h b/include/linux/iova.h
index 3920a19d8194..92f7177db2ce 100644
--- a/include/linux/iova.h
+++ b/include/linux/iova.h
@@ -68,8 +68,8 @@ static inline unsigned long iova_pfn(struct iova_domain *iovad, dma_addr_t iova)
 	return iova >> iova_shift(iovad);
 }
 
-int iommu_iova_cache_init(void);
-void iommu_iova_cache_destroy(void);
+int iova_cache_get(void);
+void iova_cache_put(void);
 
 struct iova *alloc_iova_mem(void);
 void free_iova_mem(struct iova *iova);
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index ad800e62cb7a..6452ff4c463f 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -242,7 +242,6 @@ struct mem_cgroup {
 	 * percpu counter.
 	 */
 	struct mem_cgroup_stat_cpu __percpu *stat;
-	spinlock_t pcp_counter_lock;
 
 #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET)
 	struct cg_proto tcp_mem;
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 41e9f3bd663c..2a0b95662548 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -402,17 +402,6 @@ struct mlx5_cmd_teardown_hca_mbox_out {
 	u8			rsvd[8];
 };
 
-struct mlx5_cmd_query_special_contexts_mbox_in {
-	struct mlx5_inbox_hdr	hdr;
-	u8			rsvd[8];
-};
-
-struct mlx5_cmd_query_special_contexts_mbox_out {
-	struct mlx5_outbox_hdr	hdr;
-	__be32                  dump_fill_mkey;
-	__be32                  resd_lkey;
-};
-
 struct mlx5_cmd_layout {
 	u8		type;
 	u8		rsvd0[3];
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index 27b53f9a24ad..8b6d6f2154a4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -845,7 +845,6 @@ void *mlx5_get_protocol_dev(struct mlx5_core_dev *mdev, int protocol);
 int mlx5_register_interface(struct mlx5_interface *intf);
 void mlx5_unregister_interface(struct mlx5_interface *intf);
 int mlx5_core_query_vendor_id(struct mlx5_core_dev *mdev, u32 *vendor_id);
-int mlx5_core_query_special_context(struct mlx5_core_dev *dev, u32 *rsvd_lkey);
 
 struct mlx5_profile {
 	u64	mask;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 91c08f6f0dc9..80001de019ba 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -905,6 +905,27 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 #endif
 }
 
+#ifdef CONFIG_MEMCG
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	return page->mem_cgroup;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+	page->mem_cgroup = memcg;
+}
+#else
+static inline struct mem_cgroup *page_memcg(struct page *page)
+{
+	return NULL;
+}
+
+static inline void set_page_memcg(struct page *page, struct mem_cgroup *memcg)
+{
+}
+#endif
+
 /*
  * Some inline functions in vmstat.h depend on page_zone()
  */
diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
index ff476515f716..581abf848566 100644
--- a/include/linux/rcupdate.h
+++ b/include/linux/rcupdate.h
@@ -230,12 +230,11 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
 		   struct rcu_synchronize *rs_array);
 
 #define _wait_rcu_gp(checktiny, ...) \
-do { \
-	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ }; \
-	const int __n = ARRAY_SIZE(__crcu_array); \
-	struct rcu_synchronize __rs_array[__n]; \
-	\
-	__wait_rcu_gp(checktiny, __n, __crcu_array, __rs_array); \
+do {									\
+	call_rcu_func_t __crcu_array[] = { __VA_ARGS__ };		\
+	struct rcu_synchronize __rs_array[ARRAY_SIZE(__crcu_array)];	\
+	__wait_rcu_gp(checktiny, ARRAY_SIZE(__crcu_array),		\
+			__crcu_array, __rs_array);			\
 } while (0)
 
 #define wait_rcu_gp(...) _wait_rcu_gp(false, __VA_ARGS__)
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 2b0a30a6e31c..4398411236f1 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -2708,7 +2708,7 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb,
 	if (skb->ip_summed == CHECKSUM_COMPLETE)
 		skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0));
 	else if (skb->ip_summed == CHECKSUM_PARTIAL &&
-		 skb_checksum_start_offset(skb) <= len)
+		 skb_checksum_start_offset(skb) < 0)
 		skb->ip_summed = CHECKSUM_NONE;
 }
 
diff --git a/include/net/af_unix.h b/include/net/af_unix.h
index 4a167b30a12f..cb1b9bbda332 100644
--- a/include/net/af_unix.h
+++ b/include/net/af_unix.h
@@ -63,7 +63,11 @@ struct unix_sock {
 #define UNIX_GC_MAYBE_CYCLE	1
 	struct socket_wq	peer_wq;
 };
-#define unix_sk(__sk) ((struct unix_sock *)__sk)
+
+static inline struct unix_sock *unix_sk(struct sock *sk)
+{
+	return (struct unix_sock *)sk;
+}
 
 #define peer_wait peer_wq.wait
 
diff --git a/include/target/target_core_base.h b/include/target/target_core_base.h
index ac9bf1c0e42d..5f48754dc36a 100644
--- a/include/target/target_core_base.h
+++ b/include/target/target_core_base.h
@@ -730,6 +730,7 @@ struct se_device {
 #define DF_EMULATED_VPD_UNIT_SERIAL		0x00000004
 #define DF_USING_UDEV_PATH			0x00000008
 #define DF_USING_ALIAS				0x00000010
+#define DF_READ_ONLY				0x00000020
 	/* Physical device queue depth */
 	u32			queue_depth;
 	/* Used for SPC-2 reservations enforce of ISIDs */
diff --git a/include/uapi/linux/userfaultfd.h b/include/uapi/linux/userfaultfd.h
index df0e09bb7dd5..9057d7af3ae1 100644
--- a/include/uapi/linux/userfaultfd.h
+++ b/include/uapi/linux/userfaultfd.h
@@ -11,8 +11,6 @@
 
 #include <linux/types.h>
 
-#include <linux/compiler.h>
-
 #define UFFD_API ((__u64)0xAA)
 /*
  * After implementing the respective features it will become:
diff --git a/ipc/msg.c b/ipc/msg.c
index 66c4f567eb73..1471db9a7e61 100644
--- a/ipc/msg.c
+++ b/ipc/msg.c
@@ -137,13 +137,6 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 		return retval;
 	}
 
-	/* ipc_addid() locks msq upon success. */
-	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
-	if (id < 0) {
-		ipc_rcu_putref(msq, msg_rcu_free);
-		return id;
-	}
-
 	msq->q_stime = msq->q_rtime = 0;
 	msq->q_ctime = get_seconds();
 	msq->q_cbytes = msq->q_qnum = 0;
@@ -153,6 +146,13 @@ static int newque(struct ipc_namespace *ns, struct ipc_params *params)
 	INIT_LIST_HEAD(&msq->q_receivers);
 	INIT_LIST_HEAD(&msq->q_senders);
 
+	/* ipc_addid() locks msq upon success. */
+	id = ipc_addid(&msg_ids(ns), &msq->q_perm, ns->msg_ctlmni);
+	if (id < 0) {
+		ipc_rcu_putref(msq, msg_rcu_free);
+		return id;
+	}
+
 	ipc_unlock_object(&msq->q_perm);
 	rcu_read_unlock();
 
diff --git a/ipc/shm.c b/ipc/shm.c
index 222131e8e38f..41787276e141 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -551,12 +551,6 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	if (IS_ERR(file))
 		goto no_file;
 
-	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
-	if (id < 0) {
-		error = id;
-		goto no_id;
-	}
-
 	shp->shm_cprid = task_tgid_vnr(current);
 	shp->shm_lprid = 0;
 	shp->shm_atim = shp->shm_dtim = 0;
@@ -565,6 +559,13 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params)
 	shp->shm_nattch = 0;
 	shp->shm_file = file;
 	shp->shm_creator = current;
+
+	id = ipc_addid(&shm_ids(ns), &shp->shm_perm, ns->shm_ctlmni);
+	if (id < 0) {
+		error = id;
+		goto no_id;
+	}
+
 	list_add(&shp->shm_clist, &current->sysvshm.shm_clist);
 
 	/*
diff --git a/ipc/util.c b/ipc/util.c
index be4230020a1f..0f401d94b7c6 100644
--- a/ipc/util.c
+++ b/ipc/util.c
@@ -237,6 +237,10 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
 	rcu_read_lock();
 	spin_lock(&new->lock);
 
+	current_euid_egid(&euid, &egid);
+	new->cuid = new->uid = euid;
+	new->gid = new->cgid = egid;
+
 	id = idr_alloc(&ids->ipcs_idr, new,
 		       (next_id < 0) ? 0 : ipcid_to_idx(next_id), 0,
 		       GFP_NOWAIT);
@@ -249,10 +253,6 @@ int ipc_addid(struct ipc_ids *ids, struct kern_ipc_perm *new, int size)
 
 	ids->in_use++;
 
-	current_euid_egid(&euid, &egid);
-	new->cuid = new->uid = euid;
-	new->gid = new->cgid = egid;
-
 	if (next_id < 0) {
 		new->seq = ids->seq++;
 		if (ids->seq > IPCID_SEQ_MAX)
diff --git a/kernel/events/core.c b/kernel/events/core.c
index f548f69c4299..b11756f9b6dc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1243,11 +1243,7 @@ static inline void perf_event__state_init(struct perf_event *event)
 					      PERF_EVENT_STATE_INACTIVE;
 }
 
-/*
- * Called at perf_event creation and when events are attached/detached from a
- * group.
- */
-static void perf_event__read_size(struct perf_event *event)
+static void __perf_event_read_size(struct perf_event *event, int nr_siblings)
 {
 	int entry = sizeof(u64); /* value */
 	int size = 0;
@@ -1263,7 +1259,7 @@ static void perf_event__read_size(struct perf_event *event)
 		entry += sizeof(u64);
 
 	if (event->attr.read_format & PERF_FORMAT_GROUP) {
-		nr += event->group_leader->nr_siblings;
+		nr += nr_siblings;
 		size += sizeof(u64);
 	}
 
@@ -1271,14 +1267,11 @@ static void perf_event__read_size(struct perf_event *event)
 	event->read_size = size;
 }
 
-static void perf_event__header_size(struct perf_event *event)
+static void __perf_event_header_size(struct perf_event *event, u64 sample_type)
 {
 	struct perf_sample_data *data;
-	u64 sample_type = event->attr.sample_type;
 	u16 size = 0;
 
-	perf_event__read_size(event);
-
 	if (sample_type & PERF_SAMPLE_IP)
 		size += sizeof(data->ip);
 
@@ -1303,6 +1296,17 @@ static void perf_event__header_size(struct perf_event *event)
 	event->header_size = size;
 }
 
+/*
+ * Called at perf_event creation and when events are attached/detached from a
+ * group.
+ */
+static void perf_event__header_size(struct perf_event *event)
+{
+	__perf_event_read_size(event,
+			       event->group_leader->nr_siblings);
+	__perf_event_header_size(event, event->attr.sample_type);
+}
+
 static void perf_event__id_header_size(struct perf_event *event)
 {
 	struct perf_sample_data *data;
@@ -1330,6 +1334,27 @@ static void perf_event__id_header_size(struct perf_event *event)
 	event->id_header_size = size;
 }
 
+static bool perf_event_validate_size(struct perf_event *event)
+{
+	/*
+	 * The values computed here will be over-written when we actually
+	 * attach the event.
+	 */
+	__perf_event_read_size(event, event->group_leader->nr_siblings + 1);
+	__perf_event_header_size(event, event->attr.sample_type & ~PERF_SAMPLE_READ);
+	perf_event__id_header_size(event);
+
+	/*
+	 * Sum the lot; should not exceed the 64k limit we have on records.
+	 * Conservative limit to allow for callchains and other variable fields.
+	 */
+	if (event->read_size + event->header_size +
+	    event->id_header_size + sizeof(struct perf_event_header) >= 16*1024)
+		return false;
+
+	return true;
+}
+
 static void perf_group_attach(struct perf_event *event)
 {
 	struct perf_event *group_leader = event->group_leader, *pos;
@@ -8297,13 +8322,35 @@ SYSCALL_DEFINE5(perf_event_open,
 
 	if (move_group) {
 		gctx = group_leader->ctx;
+		mutex_lock_double(&gctx->mutex, &ctx->mutex);
+	} else {
+		mutex_lock(&ctx->mutex);
+	}
 
+	if (!perf_event_validate_size(event)) {
+		err = -E2BIG;
+		goto err_locked;
+	}
+
+	/*
+	 * Must be under the same ctx::mutex as perf_install_in_context(),
+	 * because we need to serialize with concurrent event creation.
+	 */
+	if (!exclusive_event_installable(event, ctx)) {
+		/* exclusive and group stuff are assumed mutually exclusive */
+		WARN_ON_ONCE(move_group);
+
+		err = -EBUSY;
+		goto err_locked;
+	}
+
+	WARN_ON_ONCE(ctx->parent_ctx);
+
+	if (move_group) {
 		/*
 		 * See perf_event_ctx_lock() for comments on the details
 		 * of swizzling perf_event::ctx.
 		 */
-		mutex_lock_double(&gctx->mutex, &ctx->mutex);
-
 		perf_remove_from_context(group_leader, false);
 
 		list_for_each_entry(sibling, &group_leader->sibling_list,
@@ -8311,13 +8358,7 @@ SYSCALL_DEFINE5(perf_event_open,
 			perf_remove_from_context(sibling, false);
 			put_ctx(gctx);
 		}
-	} else {
-		mutex_lock(&ctx->mutex);
-	}
 
-	WARN_ON_ONCE(ctx->parent_ctx);
-
-	if (move_group) {
 		/*
 		 * Wait for everybody to stop referencing the events through
 		 * the old lists, before installing it on new lists.
@@ -8349,22 +8390,29 @@ SYSCALL_DEFINE5(perf_event_open,
 		perf_event__state_init(group_leader);
 		perf_install_in_context(ctx, group_leader, group_leader->cpu);
 		get_ctx(ctx);
-	}
 
-	if (!exclusive_event_installable(event, ctx)) {
-		err = -EBUSY;
-		mutex_unlock(&ctx->mutex);
-		fput(event_file);
-		goto err_context;
+		/*
+		 * Now that all events are installed in @ctx, nothing
+		 * references @gctx anymore, so drop the last reference we have
+		 * on it.
+		 */
+		put_ctx(gctx);
 	}
 
+	/*
+	 * Precalculate sample_data sizes; do while holding ctx::mutex such
+	 * that we're serialized against further additions and before
+	 * perf_install_in_context() which is the point the event is active and
+	 * can use these values.
+	 */
+	perf_event__header_size(event);
+	perf_event__id_header_size(event);
+
 	perf_install_in_context(ctx, event, event->cpu);
 	perf_unpin_context(ctx);
 
-	if (move_group) {
+	if (move_group)
 		mutex_unlock(&gctx->mutex);
-		put_ctx(gctx);
-	}
 	mutex_unlock(&ctx->mutex);
 
 	put_online_cpus();
@@ -8376,12 +8424,6 @@ SYSCALL_DEFINE5(perf_event_open,
 	mutex_unlock(&current->perf_event_mutex);
 
 	/*
-	 * Precalculate sample_data sizes
-	 */
-	perf_event__header_size(event);
-	perf_event__id_header_size(event);
-
-	/*
 	 * Drop the reference on the group_event after placing the
 	 * new event on the sibling_list. This ensures destruction
 	 * of the group leader will find the pointer to itself in
@@ -8391,6 +8433,12 @@ SYSCALL_DEFINE5(perf_event_open,
 	fd_install(event_fd, event_file);
 	return event_fd;
 
+err_locked:
+	if (move_group)
+		mutex_unlock(&gctx->mutex);
+	mutex_unlock(&ctx->mutex);
+/* err_file: */
+	fput(event_file);
 err_context:
 	perf_unpin_context(ctx);
 	put_ctx(ctx);
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 8acfbf773e06..4e49cc4c9952 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3068,7 +3068,7 @@ static int __lock_is_held(struct lockdep_map *lock);
 static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 			  int trylock, int read, int check, int hardirqs_off,
 			  struct lockdep_map *nest_lock, unsigned long ip,
-			  int references)
+			  int references, int pin_count)
 {
 	struct task_struct *curr = current;
 	struct lock_class *class = NULL;
@@ -3157,7 +3157,7 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	hlock->waittime_stamp = 0;
 	hlock->holdtime_stamp = lockstat_clock();
 #endif
-	hlock->pin_count = 0;
+	hlock->pin_count = pin_count;
 
 	if (check && !mark_irqflags(curr, hlock))
 		return 0;
@@ -3343,7 +3343,7 @@ found_it:
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
 				hlock->nest_lock, hlock->acquire_ip,
-				hlock->references))
+				hlock->references, hlock->pin_count))
 			return 0;
 	}
 
@@ -3433,7 +3433,7 @@ found_it:
 			hlock_class(hlock)->subclass, hlock->trylock,
 				hlock->read, hlock->check, hlock->hardirqs_off,
 				hlock->nest_lock, hlock->acquire_ip,
-				hlock->references))
+				hlock->references, hlock->pin_count))
 			return 0;
 	}
 
@@ -3583,7 +3583,7 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	current->lockdep_recursion = 1;
 	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
-		       irqs_disabled_flags(flags), nest_lock, ip, 0);
+		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	current->lockdep_recursion = 0;
 	raw_local_irq_restore(flags);
 }
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9f75f25cc5d9..775d36cc0050 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3868,6 +3868,7 @@ static void rcu_init_new_rnp(struct rcu_node *rnp_leaf)
 static void __init
 rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 {
+	static struct lock_class_key rcu_exp_sched_rdp_class;
 	unsigned long flags;
 	struct rcu_data *rdp = per_cpu_ptr(rsp->rda, cpu);
 	struct rcu_node *rnp = rcu_get_root(rsp);
@@ -3883,6 +3884,10 @@ rcu_boot_init_percpu_data(int cpu, struct rcu_state *rsp)
 	mutex_init(&rdp->exp_funnel_mutex);
 	rcu_boot_init_nocb_percpu_data(rdp);
 	raw_spin_unlock_irqrestore(&rnp->lock, flags);
+	if (rsp == &rcu_sched_state)
+		lockdep_set_class_and_name(&rdp->exp_funnel_mutex,
+					   &rcu_exp_sched_rdp_class,
+					   "rcu_data_exp_sched");
 }
 
 /*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2f9c92884817..615953141951 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4934,7 +4934,15 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->state = TASK_RUNNING;
 	idle->se.exec_start = sched_clock();
 
-	do_set_cpus_allowed(idle, cpumask_of(cpu));
+#ifdef CONFIG_SMP
+	/*
+	 * Its possible that init_idle() gets called multiple times on a task,
+	 * in that case do_set_cpus_allowed() will not do the right thing.
+	 *
+	 * And since this is boot we can forgo the serialization.
+	 */
+	set_cpus_allowed_common(idle, cpumask_of(cpu));
+#endif
 	/*
 	 * We're having a chicken and egg problem, even though we are
 	 * holding rq->lock, the cpu isn't yet set to this cpu so the
@@ -4951,7 +4959,7 @@ void init_idle(struct task_struct *idle, int cpu)
 
 	rq->curr = rq->idle = idle;
 	idle->on_rq = TASK_ON_RQ_QUEUED;
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	idle->on_cpu = 1;
 #endif
 	raw_spin_unlock(&rq->lock);
@@ -4966,7 +4974,7 @@ void init_idle(struct task_struct *idle, int cpu)
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
 	vtime_init_idle(idle, cpu);
-#if defined(CONFIG_SMP)
+#ifdef CONFIG_SMP
 	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
 #endif
 }
diff --git a/mm/dmapool.c b/mm/dmapool.c
index 71a8998cd03a..312a716fa14c 100644
--- a/mm/dmapool.c
+++ b/mm/dmapool.c
@@ -394,7 +394,7 @@ static struct dma_page *pool_find_page(struct dma_pool *pool, dma_addr_t dma)
 	list_for_each_entry(page, &pool->page_list, page_list) {
 		if (dma < page->dma)
 			continue;
-		if (dma < (page->dma + pool->allocation))
+		if ((dma - page->dma) < pool->allocation)
 			return page;
 	}
 	return NULL;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 999fb0aef8f1..9cc773483624 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3202,6 +3202,14 @@ static void unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 			continue;
 
 		/*
+		 * Shared VMAs have their own reserves and do not affect
+		 * MAP_PRIVATE accounting but it is possible that a shared
+		 * VMA is using the same page so check and skip such VMAs.
+		 */
+		if (iter_vma->vm_flags & VM_MAYSHARE)
+			continue;
+
+		/*
 		 * Unmap the page from other VMAs without their own reserves.
 		 * They get marked to be SIGKILLed if they fault in these
 		 * areas. This is because a future no-page fault on this VMA
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6ddaeba34e09..1fedbde68f59 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -644,12 +644,14 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
 }
 
 /*
+ * Return page count for single (non recursive) @memcg.
+ *
  * Implementation Note: reading percpu statistics for memcg.
  *
  * Both of vmstat[] and percpu_counter has threshold and do periodic
  * synchronization to implement "quick" read. There are trade-off between
  * reading cost and precision of value. Then, we may have a chance to implement
- * a periodic synchronizion of counter in memcg's counter.
+ * a periodic synchronization of counter in memcg's counter.
  *
  * But this _read() function is used for user interface now. The user accounts
  * memory usage by memory cgroup and he _always_ requires exact value because
@@ -659,17 +661,24 @@ mem_cgroup_largest_soft_limit_node(struct mem_cgroup_tree_per_zone *mctz)
  *
  * If there are kernel internal actions which can make use of some not-exact
  * value, and reading all cpu value can be performance bottleneck in some
- * common workload, threashold and synchonization as vmstat[] should be
+ * common workload, threshold and synchronization as vmstat[] should be
  * implemented.
  */
-static long mem_cgroup_read_stat(struct mem_cgroup *memcg,
-				 enum mem_cgroup_stat_index idx)
+static unsigned long
+mem_cgroup_read_stat(struct mem_cgroup *memcg, enum mem_cgroup_stat_index idx)
 {
 	long val = 0;
 	int cpu;
 
+	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_possible_cpu(cpu)
 		val += per_cpu(memcg->stat->count[idx], cpu);
+	/*
+	 * Summing races with updates, so val may be negative.  Avoid exposing
+	 * transient negative values.
+	 */
+	if (val < 0)
+		val = 0;
 	return val;
 }
 
@@ -1254,7 +1263,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 		for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 			if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 				continue;
-			pr_cont(" %s:%ldKB", mem_cgroup_stat_names[i],
+			pr_cont(" %s:%luKB", mem_cgroup_stat_names[i],
 				K(mem_cgroup_read_stat(iter, i)));
 		}
 
@@ -2819,14 +2828,11 @@ static unsigned long tree_stat(struct mem_cgroup *memcg,
 			       enum mem_cgroup_stat_index idx)
 {
 	struct mem_cgroup *iter;
-	long val = 0;
+	unsigned long val = 0;
 
-	/* Per-cpu values can be negative, use a signed accumulator */
 	for_each_mem_cgroup_tree(iter, memcg)
 		val += mem_cgroup_read_stat(iter, idx);
 
-	if (val < 0) /* race ? */
-		val = 0;
 	return val;
 }
 
@@ -3169,7 +3175,7 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
-		seq_printf(m, "%s %ld\n", mem_cgroup_stat_names[i],
+		seq_printf(m, "%s %lu\n", mem_cgroup_stat_names[i],
 			   mem_cgroup_read_stat(memcg, i) * PAGE_SIZE);
 	}
 
@@ -3194,13 +3200,13 @@ static int memcg_stat_show(struct seq_file *m, void *v)
 			   (u64)memsw * PAGE_SIZE);
 
 	for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) {
-		long long val = 0;
+		unsigned long long val = 0;
 
 		if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account)
 			continue;
 		for_each_mem_cgroup_tree(mi, memcg)
 			val += mem_cgroup_read_stat(mi, i) * PAGE_SIZE;
-		seq_printf(m, "total_%s %lld\n", mem_cgroup_stat_names[i], val);
+		seq_printf(m, "total_%s %llu\n", mem_cgroup_stat_names[i], val);
 	}
 
 	for (i = 0; i < MEM_CGROUP_EVENTS_NSTATS; i++) {
@@ -4179,7 +4185,6 @@ static struct mem_cgroup *mem_cgroup_alloc(void)
 	if (memcg_wb_domain_init(memcg, GFP_KERNEL))
 		goto out_free_stat;
 
-	spin_lock_init(&memcg->pcp_counter_lock);
 	return memcg;
 
 out_free_stat:
diff --git a/mm/migrate.c b/mm/migrate.c
index 7452a00bbb50..842ecd7aaf7f 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -740,6 +740,15 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 	if (PageSwapBacked(page))
 		SetPageSwapBacked(newpage);
 
+	/*
+	 * Indirectly called below, migrate_page_copy() copies PG_dirty and thus
+	 * needs newpage's memcg set to transfer memcg dirty page accounting.
+	 * So perform memcg migration in two steps:
+	 * 1. set newpage->mem_cgroup (here)
+	 * 2. clear page->mem_cgroup (below)
+	 */
+	set_page_memcg(newpage, page_memcg(page));
+
 	mapping = page_mapping(page);
 	if (!mapping)
 		rc = migrate_page(mapping, newpage, page, mode);
@@ -756,9 +765,10 @@ static int move_to_new_page(struct page *newpage, struct page *page,
 		rc = fallback_migrate_page(mapping, newpage, page, mode);
 
 	if (rc != MIGRATEPAGE_SUCCESS) {
+		set_page_memcg(newpage, NULL);
 		newpage->mapping = NULL;
 	} else {
-		mem_cgroup_migrate(page, newpage, false);
+		set_page_memcg(page, NULL);
 		if (page_was_mapped)
 			remove_migration_ptes(page, newpage);
 		page->mapping = NULL;
diff --git a/mm/slab.c b/mm/slab.c
index c77ebe6cc87c..4fcc5dd8d5a6 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -2190,9 +2190,16 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
 			size += BYTES_PER_WORD;
 	}
 #if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
-	if (size >= kmalloc_size(INDEX_NODE + 1)
-	    && cachep->object_size > cache_line_size()
-	    && ALIGN(size, cachep->align) < PAGE_SIZE) {
+	/*
+	 * To activate debug pagealloc, off-slab management is necessary
+	 * requirement. In early phase of initialization, small sized slab
+	 * doesn't get initialized so it would not be possible. So, we need
+	 * to check size >= 256. It guarantees that all necessary small
+	 * sized slab is initialized in current slab initialization sequence.
+	 */
+	if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
+		size >= 256 && cachep->object_size > cache_line_size() &&
+		ALIGN(size, cachep->align) < PAGE_SIZE) {
 		cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
 		size = PAGE_SIZE;
 	}
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index b4c530065106..410c6e42bf1f 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -31,7 +31,6 @@
 static const char fmt_hex[] = "%#x\n";
 static const char fmt_long_hex[] = "%#lx\n";
 static const char fmt_dec[] = "%d\n";
-static const char fmt_udec[] = "%u\n";
 static const char fmt_ulong[] = "%lu\n";
 static const char fmt_u64[] = "%llu\n";
 
@@ -202,7 +201,7 @@ static ssize_t speed_show(struct device *dev,
 	if (netif_running(netdev)) {
 		struct ethtool_cmd cmd;
 		if (!__ethtool_get_settings(netdev, &cmd))
-			ret = sprintf(buf, fmt_udec, ethtool_cmd_speed(&cmd));
+			ret = sprintf(buf, fmt_dec, ethtool_cmd_speed(&cmd));
 	}
 	rtnl_unlock();
 	return ret;
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index dad4dd37e2aa..fab4599ba8b2 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -2958,11 +2958,12 @@ EXPORT_SYMBOL_GPL(skb_append_pagefrags);
  */
 unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len)
 {
+	unsigned char *data = skb->data;
+
 	BUG_ON(len > skb->len);
-	skb->len -= len;
-	BUG_ON(skb->len < skb->data_len);
-	skb_postpull_rcsum(skb, skb->data, len);
-	return skb->data += len;
+	__skb_pull(skb, len);
+	skb_postpull_rcsum(skb, data, len);
+	return skb->data;
 }
 EXPORT_SYMBOL_GPL(skb_pull_rcsum);
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index fac172370276..d7c2bb0c4f65 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -340,6 +340,7 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 	fl4.flowi4_tos = tos;
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
 	fl4.flowi4_tun_key.tun_id = 0;
+	fl4.flowi4_flags = 0;
 
 	no_addr = idev->ifa_list == NULL;
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 1441de1550e6..76ca4e75f785 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1743,6 +1743,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 	fl4.flowi4_mark = skb->mark;
 	fl4.flowi4_tos = tos;
 	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+	fl4.flowi4_flags = 0;
 	fl4.daddr = daddr;
 	fl4.saddr = saddr;
 	err = fib_lookup(net, &fl4, &res, 0);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 66a6b2c485dd..d3d946773a3e 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1169,7 +1169,8 @@ struct dst_entry *ip6_route_output(struct net *net, const struct sock *sk,
 
 	fl6->flowi6_iif = LOOPBACK_IFINDEX;
 
-	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr))
+	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl6->daddr) ||
+	    fl6->flowi6_oif)
 		flags |= RT6_LOOKUP_F_IFACE;
 
 	if (!ipv6_addr_any(&fl6->saddr))
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index f6b090df3930..afca2eb4dfa7 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -1319,7 +1319,7 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	tunnel = container_of(work, struct l2tp_tunnel, del_work);
 	sk = l2tp_tunnel_sock_lookup(tunnel);
 	if (!sk)
-		return;
+		goto out;
 
 	sock = sk->sk_socket;
 
@@ -1341,6 +1341,8 @@ static void l2tp_tunnel_del_work(struct work_struct *work)
 	}
 
 	l2tp_tunnel_sock_put(sk);
+out:
+	l2tp_tunnel_dec_refcount(tunnel);
 }
 
 /* Create a socket for the tunnel, if one isn't set up by
@@ -1636,8 +1638,13 @@ EXPORT_SYMBOL_GPL(l2tp_tunnel_create);
  */
 int l2tp_tunnel_delete(struct l2tp_tunnel *tunnel)
 {
+	l2tp_tunnel_inc_refcount(tunnel);
 	l2tp_tunnel_closeall(tunnel);
-	return (false == queue_work(l2tp_wq, &tunnel->del_work));
+	if (false == queue_work(l2tp_wq, &tunnel->del_work)) {
+		l2tp_tunnel_dec_refcount(tunnel);
+		return 1;
+	}
+	return 0;
 }
 EXPORT_SYMBOL_GPL(l2tp_tunnel_delete);
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 197c3f59ecbf..b00f1f9611d6 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -1208,20 +1208,22 @@ void sctp_assoc_update(struct sctp_association *asoc,
  *   within this document.
  *
  * Our basic strategy is to round-robin transports in priorities
- * according to sctp_state_prio_map[] e.g., if no such
+ * according to sctp_trans_score() e.g., if no such
  * transport with state SCTP_ACTIVE exists, round-robin through
  * SCTP_UNKNOWN, etc. You get the picture.
  */
-static const u8 sctp_trans_state_to_prio_map[] = {
-	[SCTP_ACTIVE]	= 3,	/* best case */
-	[SCTP_UNKNOWN]	= 2,
-	[SCTP_PF]	= 1,
-	[SCTP_INACTIVE] = 0,	/* worst case */
-};
-
 static u8 sctp_trans_score(const struct sctp_transport *trans)
 {
-	return sctp_trans_state_to_prio_map[trans->state];
+	switch (trans->state) {
+	case SCTP_ACTIVE:
+		return 3;	/* best case */
+	case SCTP_UNKNOWN:
+		return 2;
+	case SCTP_PF:
+		return 1;
+	default: /* case SCTP_INACTIVE */
+		return 0;	/* worst case */
+	}
 }
 
 static struct sctp_transport *sctp_trans_elect_tie(struct sctp_transport *trans1,
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index 35df1266bf07..6098d4c42fa9 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -244,12 +244,13 @@ void sctp_generate_t3_rtx_event(unsigned long peer)
 	int error;
 	struct sctp_transport *transport = (struct sctp_transport *) peer;
 	struct sctp_association *asoc = transport->asoc;
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 
 	/* Check whether a task is in the sock.  */
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
@@ -272,10 +273,10 @@ void sctp_generate_t3_rtx_event(unsigned long peer)
 			   transport, GFP_ATOMIC);
 
 	if (error)
-		asoc->base.sk->sk_err = -error;
+		sk->sk_err = -error;
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_transport_put(transport);
 }
 
@@ -285,11 +286,12 @@ out_unlock:
 static void sctp_generate_timeout_event(struct sctp_association *asoc,
 					sctp_event_timeout_t timeout_type)
 {
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 	int error = 0;
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy: timer %d\n", __func__,
 			 timeout_type);
 
@@ -312,10 +314,10 @@ static void sctp_generate_timeout_event(struct sctp_association *asoc,
 			   (void *)timeout_type, GFP_ATOMIC);
 
 	if (error)
-		asoc->base.sk->sk_err = -error;
+		sk->sk_err = -error;
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_association_put(asoc);
 }
 
@@ -365,10 +367,11 @@ void sctp_generate_heartbeat_event(unsigned long data)
 	int error = 0;
 	struct sctp_transport *transport = (struct sctp_transport *) data;
 	struct sctp_association *asoc = transport->asoc;
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
@@ -388,11 +391,11 @@ void sctp_generate_heartbeat_event(unsigned long data)
 			   asoc->state, asoc->ep, asoc,
 			   transport, GFP_ATOMIC);
 
-	 if (error)
-		 asoc->base.sk->sk_err = -error;
+	if (error)
+		sk->sk_err = -error;
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_transport_put(transport);
 }
 
@@ -403,10 +406,11 @@ void sctp_generate_proto_unreach_event(unsigned long data)
 {
 	struct sctp_transport *transport = (struct sctp_transport *) data;
 	struct sctp_association *asoc = transport->asoc;
-	struct net *net = sock_net(asoc->base.sk);
+	struct sock *sk = asoc->base.sk;
+	struct net *net = sock_net(sk);
 
-	bh_lock_sock(asoc->base.sk);
-	if (sock_owned_by_user(asoc->base.sk)) {
+	bh_lock_sock(sk);
+	if (sock_owned_by_user(sk)) {
 		pr_debug("%s: sock is busy\n", __func__);
 
 		/* Try again later.  */
@@ -427,7 +431,7 @@ void sctp_generate_proto_unreach_event(unsigned long data)
 		   asoc->state, asoc->ep, asoc, transport, GFP_ATOMIC);
 
 out_unlock:
-	bh_unlock_sock(asoc->base.sk);
+	bh_unlock_sock(sk);
 	sctp_association_put(asoc);
 }
 
diff --git a/net/sunrpc/xprtrdma/fmr_ops.c b/net/sunrpc/xprtrdma/fmr_ops.c
index cb25c89da623..f1e8dafbd507 100644
--- a/net/sunrpc/xprtrdma/fmr_ops.c
+++ b/net/sunrpc/xprtrdma/fmr_ops.c
@@ -39,25 +39,6 @@ static int
 fmr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 	    struct rpcrdma_create_data_internal *cdata)
 {
-	struct ib_device_attr *devattr = &ia->ri_devattr;
-	struct ib_mr *mr;
-
-	/* Obtain an lkey to use for the regbufs, which are
-	 * protected from remote access.
-	 */
-	if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY) {
-		ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
-	} else {
-		mr = ib_get_dma_mr(ia->ri_pd, IB_ACCESS_LOCAL_WRITE);
-		if (IS_ERR(mr)) {
-			pr_err("%s: ib_get_dma_mr for failed with %lX\n",
-			       __func__, PTR_ERR(mr));
-			return -ENOMEM;
-		}
-		ia->ri_dma_lkey = ia->ri_dma_mr->lkey;
-		ia->ri_dma_mr = mr;
-	}
-
 	return 0;
 }
 
diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
index d6653f5d0830..5318951b3b53 100644
--- a/net/sunrpc/xprtrdma/frwr_ops.c
+++ b/net/sunrpc/xprtrdma/frwr_ops.c
@@ -189,11 +189,6 @@ frwr_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 	struct ib_device_attr *devattr = &ia->ri_devattr;
 	int depth, delta;
 
-	/* Obtain an lkey to use for the regbufs, which are
-	 * protected from remote access.
-	 */
-	ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
-
 	ia->ri_max_frmr_depth =
 			min_t(unsigned int, RPCRDMA_MAX_DATA_SEGS,
 			      devattr->max_fast_reg_page_list_len);
diff --git a/net/sunrpc/xprtrdma/physical_ops.c b/net/sunrpc/xprtrdma/physical_ops.c
index 72cf8b15bbb4..617b76f22154 100644
--- a/net/sunrpc/xprtrdma/physical_ops.c
+++ b/net/sunrpc/xprtrdma/physical_ops.c
@@ -23,7 +23,6 @@ static int
 physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 		 struct rpcrdma_create_data_internal *cdata)
 {
-	struct ib_device_attr *devattr = &ia->ri_devattr;
 	struct ib_mr *mr;
 
 	/* Obtain an rkey to use for RPC data payloads.
@@ -37,15 +36,8 @@ physical_op_open(struct rpcrdma_ia *ia, struct rpcrdma_ep *ep,
 		       __func__, PTR_ERR(mr));
 		return -ENOMEM;
 	}
-	ia->ri_dma_mr = mr;
-
-	/* Obtain an lkey to use for regbufs.
-	 */
-	if (devattr->device_cap_flags & IB_DEVICE_LOCAL_DMA_LKEY)
-		ia->ri_dma_lkey = ia->ri_device->local_dma_lkey;
-	else
-		ia->ri_dma_lkey = ia->ri_dma_mr->lkey;
 
+	ia->ri_dma_mr = mr;
 	return 0;
 }
 
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 682996779970..eb081ad05e33 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -1252,7 +1252,7 @@ rpcrdma_alloc_regbuf(struct rpcrdma_ia *ia, size_t size, gfp_t flags)
 		goto out_free;
 
 	iov->length = size;
-	iov->lkey = ia->ri_dma_lkey;
+	iov->lkey = ia->ri_pd->local_dma_lkey;
 	rb->rg_size = size;
 	rb->rg_owner = NULL;
 	return rb;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index 02512221b8bc..c09414e6f91b 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -65,7 +65,6 @@ struct rpcrdma_ia {
 	struct rdma_cm_id 	*ri_id;
 	struct ib_pd		*ri_pd;
 	struct ib_mr		*ri_dma_mr;
-	u32			ri_dma_lkey;
 	struct completion	ri_done;
 	int			ri_async_rc;
 	unsigned int		ri_max_frmr_depth;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 03ee4d359f6a..ef31b40ad550 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2179,8 +2179,21 @@ unlock:
 			if (UNIXCB(skb).fp)
 				scm.fp = scm_fp_dup(UNIXCB(skb).fp);
 
-			sk_peek_offset_fwd(sk, chunk);
+			if (skip) {
+				sk_peek_offset_fwd(sk, chunk);
+				skip -= chunk;
+			}
 
+			if (UNIXCB(skb).fp)
+				break;
+
+			last = skb;
+			last_len = skb->len;
+			unix_state_lock(sk);
+			skb = skb_peek_next(skb, &sk->sk_receive_queue);
+			if (skb)
+				goto again;
+			unix_state_unlock(sk);
 			break;
 		}
 	} while (size);
diff --git a/samples/kprobes/jprobe_example.c b/samples/kprobes/jprobe_example.c
index 9119ac6a8270..c285a3b8a9f1 100644
--- a/samples/kprobes/jprobe_example.c
+++ b/samples/kprobes/jprobe_example.c
@@ -1,13 +1,13 @@
 /*
  * Here's a sample kernel module showing the use of jprobes to dump
- * the arguments of do_fork().
+ * the arguments of _do_fork().
  *
  * For more information on theory of operation of jprobes, see
  * Documentation/kprobes.txt
  *
  * Build and insert the kernel module as done in the kprobe example.
  * You will see the trace data in /var/log/messages and on the
- * console whenever do_fork() is invoked to create a new process.
+ * console whenever _do_fork() is invoked to create a new process.
  * (Some messages may be suppressed if syslogd is configured to
  * eliminate duplicate messages.)
  */
@@ -17,13 +17,13 @@
 #include <linux/kprobes.h>
 
 /*
- * Jumper probe for do_fork.
+ * Jumper probe for _do_fork.
  * Mirror principle enables access to arguments of the probed routine
  * from the probe handler.
  */
 
-/* Proxy routine having the same arguments as actual do_fork() routine */
-static long jdo_fork(unsigned long clone_flags, unsigned long stack_start,
+/* Proxy routine having the same arguments as actual _do_fork() routine */
+static long j_do_fork(unsigned long clone_flags, unsigned long stack_start,
 	      unsigned long stack_size, int __user *parent_tidptr,
 	      int __user *child_tidptr)
 {
@@ -36,9 +36,9 @@ static long jdo_fork(unsigned long clone_flags, unsigned long stack_start,
 }
 
 static struct jprobe my_jprobe = {
-	.entry			= jdo_fork,
+	.entry			= j_do_fork,
 	.kp = {
-		.symbol_name	= "do_fork",
+		.symbol_name	= "_do_fork",
 	},
 };
 
diff --git a/samples/kprobes/kprobe_example.c b/samples/kprobes/kprobe_example.c
index 366db1a9fb65..727eb21c9c56 100644
--- a/samples/kprobes/kprobe_example.c
+++ b/samples/kprobes/kprobe_example.c
@@ -1,13 +1,13 @@
 /*
  * NOTE: This example is works on x86 and powerpc.
  * Here's a sample kernel module showing the use of kprobes to dump a
- * stack trace and selected registers when do_fork() is called.
+ * stack trace and selected registers when _do_fork() is called.
  *
  * For more information on theory of operation of kprobes, see
  * Documentation/kprobes.txt
  *
  * You will see the trace data in /var/log/messages and on the console
- * whenever do_fork() is invoked to create a new process.
+ * whenever _do_fork() is invoked to create a new process.
  */
 
 #include <linux/kernel.h>
@@ -16,7 +16,7 @@
 
 /* For each probe you need to allocate a kprobe structure */
 static struct kprobe kp = {
-	.symbol_name	= "do_fork",
+	.symbol_name	= "_do_fork",
 };
 
 /* kprobe pre_handler: called just before the probed instruction is executed */
diff --git a/samples/kprobes/kretprobe_example.c b/samples/kprobes/kretprobe_example.c
index 1041b6731598..ebb1d1aed547 100644
--- a/samples/kprobes/kretprobe_example.c
+++ b/samples/kprobes/kretprobe_example.c
@@ -7,7 +7,7 @@
  *
  * usage: insmod kretprobe_example.ko func=<func_name>
  *
- * If no func_name is specified, do_fork is instrumented
+ * If no func_name is specified, _do_fork is instrumented
  *
  * For more information on theory of operation of kretprobes, see
  * Documentation/kprobes.txt
@@ -25,7 +25,7 @@
 #include <linux/limits.h>
 #include <linux/sched.h>
 
-static char func_name[NAME_MAX] = "do_fork";
+static char func_name[NAME_MAX] = "_do_fork";
 module_param_string(func, func_name, NAME_MAX, S_IRUGO);
 MODULE_PARM_DESC(func, "Function to kretprobe; this module will report the"
 			" function's execution time");
diff --git a/scripts/extract-cert.c b/scripts/extract-cert.c
index 6ce5945a0b89..b071bf476fea 100644
--- a/scripts/extract-cert.c
+++ b/scripts/extract-cert.c
@@ -17,13 +17,9 @@
 #include <stdint.h>
 #include <stdbool.h>
 #include <string.h>
-#include <getopt.h>
 #include <err.h>
-#include <arpa/inet.h>
 #include <openssl/bio.h>
-#include <openssl/evp.h>
 #include <openssl/pem.h>
-#include <openssl/pkcs7.h>
 #include <openssl/err.h>
 #include <openssl/engine.h>
 
diff --git a/scripts/sign-file.c b/scripts/sign-file.c
index c3899ca4811c..250a7a645033 100755
--- a/scripts/sign-file.c
+++ b/scripts/sign-file.c
@@ -20,13 +20,34 @@
 #include <getopt.h>
 #include <err.h>
 #include <arpa/inet.h>
+#include <openssl/opensslv.h>
 #include <openssl/bio.h>
 #include <openssl/evp.h>
 #include <openssl/pem.h>
-#include <openssl/cms.h>
 #include <openssl/err.h>
 #include <openssl/engine.h>
 
+/*
+ * Use CMS if we have openssl-1.0.0 or newer available - otherwise we have to
+ * assume that it's not available and its header file is missing and that we
+ * should use PKCS#7 instead.  Switching to the older PKCS#7 format restricts
+ * the options we have on specifying the X.509 certificate we want.
+ *
+ * Further, older versions of OpenSSL don't support manually adding signers to
+ * the PKCS#7 message so have to accept that we get a certificate included in
+ * the signature message.  Nor do such older versions of OpenSSL support
+ * signing with anything other than SHA1 - so we're stuck with that if such is
+ * the case.
+ */
+#if OPENSSL_VERSION_NUMBER < 0x10000000L
+#define USE_PKCS7
+#endif
+#ifndef USE_PKCS7
+#include <openssl/cms.h>
+#else
+#include <openssl/pkcs7.h>
+#endif
+
 struct module_signature {
 	uint8_t		algo;		/* Public-key crypto algorithm [0] */
 	uint8_t		hash;		/* Digest algorithm [0] */
@@ -110,30 +131,42 @@ int main(int argc, char **argv)
 	struct module_signature sig_info = { .id_type = PKEY_ID_PKCS7 };
 	char *hash_algo = NULL;
 	char *private_key_name, *x509_name, *module_name, *dest_name;
-	bool save_cms = false, replace_orig;
+	bool save_sig = false, replace_orig;
 	bool sign_only = false;
 	unsigned char buf[4096];
-	unsigned long module_size, cms_size;
-	unsigned int use_keyid = 0, use_signed_attrs = CMS_NOATTR;
+	unsigned long module_size, sig_size;
+	unsigned int use_signed_attrs;
 	const EVP_MD *digest_algo;
 	EVP_PKEY *private_key;
+#ifndef USE_PKCS7
 	CMS_ContentInfo *cms;
+	unsigned int use_keyid = 0;
+#else
+	PKCS7 *pkcs7;
+#endif
 	X509 *x509;
 	BIO *b, *bd = NULL, *bm;
 	int opt, n;
-
 	OpenSSL_add_all_algorithms();
 	ERR_load_crypto_strings();
 	ERR_clear_error();
 
 	key_pass = getenv("KBUILD_SIGN_PIN");
 
+#ifndef USE_PKCS7
+	use_signed_attrs = CMS_NOATTR;
+#else
+	use_signed_attrs = PKCS7_NOATTR;
+#endif
+
 	do {
 		opt = getopt(argc, argv, "dpk");
 		switch (opt) {
-		case 'p': save_cms = true; break;
-		case 'd': sign_only = true; save_cms = true; break;
+		case 'p': save_sig = true; break;
+		case 'd': sign_only = true; save_sig = true; break;
+#ifndef USE_PKCS7
 		case 'k': use_keyid = CMS_USE_KEYID; break;
+#endif
 		case -1: break;
 		default: format();
 		}
@@ -157,6 +190,14 @@ int main(int argc, char **argv)
 		replace_orig = true;
 	}
 
+#ifdef USE_PKCS7
+	if (strcmp(hash_algo, "sha1") != 0) {
+		fprintf(stderr, "sign-file: %s only supports SHA1 signing\n",
+			OPENSSL_VERSION_TEXT);
+		exit(3);
+	}
+#endif
+
 	/* Read the private key and the X.509 cert the PKCS#7 message
 	 * will point to.
 	 */
@@ -213,7 +254,8 @@ int main(int argc, char **argv)
 	bm = BIO_new_file(module_name, "rb");
 	ERR(!bm, "%s", module_name);
 
-	/* Load the CMS message from the digest buffer. */
+#ifndef USE_PKCS7
+	/* Load the signature message from the digest buffer. */
 	cms = CMS_sign(NULL, NULL, NULL, NULL,
 		       CMS_NOCERTS | CMS_PARTIAL | CMS_BINARY | CMS_DETACHED | CMS_STREAM);
 	ERR(!cms, "CMS_sign");
@@ -221,17 +263,31 @@ int main(int argc, char **argv)
 	ERR(!CMS_add1_signer(cms, x509, private_key, digest_algo,
 			     CMS_NOCERTS | CMS_BINARY | CMS_NOSMIMECAP |
 			     use_keyid | use_signed_attrs),
-	    "CMS_sign_add_signer");
+	    "CMS_add1_signer");
 	ERR(CMS_final(cms, bm, NULL, CMS_NOCERTS | CMS_BINARY) < 0,
 	    "CMS_final");
 
-	if (save_cms) {
-		char *cms_name;
+#else
+	pkcs7 = PKCS7_sign(x509, private_key, NULL, bm,
+			   PKCS7_NOCERTS | PKCS7_BINARY |
+			   PKCS7_DETACHED | use_signed_attrs);
+	ERR(!pkcs7, "PKCS7_sign");
+#endif
 
-		ERR(asprintf(&cms_name, "%s.p7s", module_name) < 0, "asprintf");
-		b = BIO_new_file(cms_name, "wb");
-		ERR(!b, "%s", cms_name);
-		ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0, "%s", cms_name);
+	if (save_sig) {
+		char *sig_file_name;
+
+		ERR(asprintf(&sig_file_name, "%s.p7s", module_name) < 0,
+		    "asprintf");
+		b = BIO_new_file(sig_file_name, "wb");
+		ERR(!b, "%s", sig_file_name);
+#ifndef USE_PKCS7
+		ERR(i2d_CMS_bio_stream(b, cms, NULL, 0) < 0,
+		    "%s", sig_file_name);
+#else
+		ERR(i2d_PKCS7_bio(b, pkcs7) < 0,
+			"%s", sig_file_name);
+#endif
 		BIO_free(b);
 	}
 
@@ -247,9 +303,13 @@ int main(int argc, char **argv)
 	ERR(n < 0, "%s", module_name);
 	module_size = BIO_number_written(bd);
 
+#ifndef USE_PKCS7
 	ERR(i2d_CMS_bio_stream(bd, cms, NULL, 0) < 0, "%s", dest_name);
-	cms_size = BIO_number_written(bd) - module_size;
-	sig_info.sig_len = htonl(cms_size);
+#else
+	ERR(i2d_PKCS7_bio(bd, pkcs7) < 0, "%s", dest_name);
+#endif
+	sig_size = BIO_number_written(bd) - module_size;
+	sig_info.sig_len = htonl(sig_size);
 	ERR(BIO_write(bd, &sig_info, sizeof(sig_info)) < 0, "%s", dest_name);
 	ERR(BIO_write(bd, magic_number, sizeof(magic_number) - 1) < 0, "%s", dest_name);
 
diff --git a/security/keys/gc.c b/security/keys/gc.c
index c7952375ac53..39eac1fd5706 100644
--- a/security/keys/gc.c
+++ b/security/keys/gc.c
@@ -134,6 +134,10 @@ static noinline void key_gc_unused_keys(struct list_head *keys)
 		kdebug("- %u", key->serial);
 		key_check(key);
 
+		/* Throw away the key data */
+		if (key->type->destroy)
+			key->type->destroy(key);
+
 		security_key_free(key);
 
 		/* deal with the user's key tracking and quota */
@@ -148,10 +152,6 @@ static noinline void key_gc_unused_keys(struct list_head *keys)
 		if (test_bit(KEY_FLAG_INSTANTIATED, &key->flags))
 			atomic_dec(&key->user->nikeys);
 
-		/* now throw away the key memory */
-		if (key->type->destroy)
-			key->type->destroy(key);
-
 		key_user_put(key->user);
 
 		kfree(key->description);
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index 2975632d51e2..c8fe6d177119 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -41,6 +41,7 @@ FEATURE_TESTS ?=			\
 	libelf-getphdrnum		\
 	libelf-mmap			\
 	libnuma				\
+	numa_num_possible_cpus		\
 	libperl				\
 	libpython			\
 	libpython-version		\
@@ -51,7 +52,8 @@ FEATURE_TESTS ?=			\
 	timerfd				\
 	libdw-dwarf-unwind		\
 	zlib				\
-	lzma
+	lzma				\
+	get_cpuid
 
 FEATURE_DISPLAY ?=			\
 	dwarf				\
@@ -61,13 +63,15 @@ FEATURE_DISPLAY ?=			\
 	libbfd				\
 	libelf				\
 	libnuma				\
+	numa_num_possible_cpus		\
 	libperl				\
 	libpython			\
 	libslang			\
 	libunwind			\
 	libdw-dwarf-unwind		\
 	zlib				\
-	lzma
+	lzma				\
+	get_cpuid
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 74ca42093d70..e43a2971bf56 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -19,6 +19,7 @@ FILES=					\
 	test-libelf-getphdrnum.bin	\
 	test-libelf-mmap.bin		\
 	test-libnuma.bin		\
+	test-numa_num_possible_cpus.bin	\
 	test-libperl.bin		\
 	test-libpython.bin		\
 	test-libpython-version.bin	\
@@ -34,7 +35,8 @@ FILES=					\
 	test-compile-x32.bin		\
 	test-zlib.bin			\
 	test-lzma.bin			\
-	test-bpf.bin
+	test-bpf.bin			\
+	test-get_cpuid.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -87,6 +89,9 @@ test-libelf-getphdrnum.bin:
 test-libnuma.bin:
 	$(BUILD) -lnuma
 
+test-numa_num_possible_cpus.bin:
+	$(BUILD) -lnuma
+
 test-libunwind.bin:
 	$(BUILD) -lelf
 
@@ -162,6 +167,9 @@ test-zlib.bin:
 test-lzma.bin:
 	$(BUILD) -llzma
 
+test-get_cpuid.bin:
+	$(BUILD)
+
 test-bpf.bin:
 	$(BUILD)
 
diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
index 84689a67814a..33cf6f20bd4e 100644
--- a/tools/build/feature/test-all.c
+++ b/tools/build/feature/test-all.c
@@ -77,6 +77,10 @@
 # include "test-libnuma.c"
 #undef main
 
+#define main main_test_numa_num_possible_cpus
+# include "test-numa_num_possible_cpus.c"
+#undef main
+
 #define main main_test_timerfd
 # include "test-timerfd.c"
 #undef main
@@ -117,6 +121,10 @@
 # include "test-lzma.c"
 #undef main
 
+#define main main_test_get_cpuid
+# include "test-get_cpuid.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -136,6 +144,7 @@ int main(int argc, char *argv[])
 	main_test_libbfd();
 	main_test_backtrace();
 	main_test_libnuma();
+	main_test_numa_num_possible_cpus();
 	main_test_timerfd();
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
@@ -143,6 +152,7 @@ int main(int argc, char *argv[])
 	main_test_zlib();
 	main_test_pthread_attr_setaffinity_np();
 	main_test_lzma();
+	main_test_get_cpuid();
 
 	return 0;
 }
diff --git a/tools/build/feature/test-get_cpuid.c b/tools/build/feature/test-get_cpuid.c
new file mode 100644
index 000000000000..d7a2c407130d
--- /dev/null
+++ b/tools/build/feature/test-get_cpuid.c
@@ -0,0 +1,7 @@
+#include <cpuid.h>
+
+int main(void)
+{
+	unsigned int eax = 0, ebx = 0, ecx = 0, edx = 0;
+	return __get_cpuid(0x15, &eax, &ebx, &ecx, &edx);
+}
diff --git a/tools/build/feature/test-numa_num_possible_cpus.c b/tools/build/feature/test-numa_num_possible_cpus.c
new file mode 100644
index 000000000000..2606e94b0659
--- /dev/null
+++ b/tools/build/feature/test-numa_num_possible_cpus.c
@@ -0,0 +1,6 @@
+#include <numa.h>
+
+int main(void)
+{
+	return numa_num_possible_cpus();
+}
diff --git a/tools/lib/traceevent/event-parse.c b/tools/lib/traceevent/event-parse.c
index 4d885934b919..cf42b090477b 100644
--- a/tools/lib/traceevent/event-parse.c
+++ b/tools/lib/traceevent/event-parse.c
@@ -3795,7 +3795,7 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 	struct format_field *field;
 	struct printk_map *printk;
 	long long val, fval;
-	unsigned long addr;
+	unsigned long long addr;
 	char *str;
 	unsigned char *hex;
 	int print;
@@ -3828,13 +3828,30 @@ static void print_str_arg(struct trace_seq *s, void *data, int size,
 		 */
 		if (!(field->flags & FIELD_IS_ARRAY) &&
 		    field->size == pevent->long_size) {
-			addr = *(unsigned long *)(data + field->offset);
+
+			/* Handle heterogeneous recording and processing
+			 * architectures
+			 *
+			 * CASE I:
+			 * Traces recorded on 32-bit devices (32-bit
+			 * addressing) and processed on 64-bit devices:
+			 * In this case, only 32 bits should be read.
+			 *
+			 * CASE II:
+			 * Traces recorded on 64 bit devices and processed
+			 * on 32-bit devices:
+			 * In this case, 64 bits must be read.
+			 */
+			addr = (pevent->long_size == 8) ?
+				*(unsigned long long *)(data + field->offset) :
+				(unsigned long long)*(unsigned int *)(data + field->offset);
+
 			/* Check if it matches a print format */
 			printk = find_printk(pevent, addr);
 			if (printk)
 				trace_seq_puts(s, printk->printk);
 			else
-				trace_seq_printf(s, "%lx", addr);
+				trace_seq_printf(s, "%llx", addr);
 			break;
 		}
 		str = malloc(len + 1);
diff --git a/tools/perf/Documentation/intel-pt.txt b/tools/perf/Documentation/intel-pt.txt
index 4a0501d7a3b4..c94c9de3173e 100644
--- a/tools/perf/Documentation/intel-pt.txt
+++ b/tools/perf/Documentation/intel-pt.txt
@@ -364,21 +364,6 @@ cyc_thresh	Specifies how frequently CYC packets are produced - see cyc
 
 		CYC packets are not requested by default.
 
-no_force_psb	This is a driver option and is not in the IA32_RTIT_CTL MSR.
-
-		It stops the driver resetting the byte count to zero whenever
-		enabling the trace (for example on context switches) which in
-		turn results in no PSB being forced.  However some processors
-		will produce a PSB anyway.
-
-		In any case, there is still a PSB when the trace is enabled for
-		the first time.
-
-		no_force_psb can be used to slightly decrease the trace size but
-		may make it harder for the decoder to recover from errors.
-
-		no_force_psb is not selected by default.
-
 
 new snapshot option
 -------------------
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 827557fc7511..38a08539f4bf 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -573,9 +573,14 @@ ifndef NO_LIBNUMA
     msg := $(warning No numa.h found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev);
     NO_LIBNUMA := 1
   else
-    CFLAGS += -DHAVE_LIBNUMA_SUPPORT
-    EXTLIBS += -lnuma
-    $(call detected,CONFIG_NUMA)
+    ifeq ($(feature-numa_num_possible_cpus), 0)
+      msg := $(warning Old numa library found, disables 'perf bench numa mem' benchmark, please install numactl-devel/libnuma-devel/libnuma-dev >= 2.0.8);
+      NO_LIBNUMA := 1
+    else
+      CFLAGS += -DHAVE_LIBNUMA_SUPPORT
+      EXTLIBS += -lnuma
+      $(call detected,CONFIG_NUMA)
+    endif
   endif
 endif
 
@@ -621,8 +626,13 @@ ifdef LIBBABELTRACE
 endif
 
 ifndef NO_AUXTRACE
-  $(call detected,CONFIG_AUXTRACE)
-  CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  ifeq ($(feature-get_cpuid), 0)
+    msg := $(warning Your gcc lacks the __get_cpuid() builtin, disables support for auxtrace/Intel PT, please install a newer gcc);
+    NO_AUXTRACE := 1
+  else
+    $(call detected,CONFIG_AUXTRACE)
+    CFLAGS += -DHAVE_AUXTRACE_SUPPORT
+  endif
 endif
 
 # Among the variables below, these:
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index eb5f18b75402..c6f9af78f6f5 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -270,12 +270,13 @@ static int kernel_get_module_dso(const char *module, struct dso **pdso)
 	int ret = 0;
 
 	if (module) {
-		list_for_each_entry(dso, &host_machine->dsos.head, node) {
-			if (!dso->kernel)
-				continue;
-			if (strncmp(dso->short_name + 1, module,
-				    dso->short_name_len - 2) == 0)
-				goto found;
+		char module_name[128];
+
+		snprintf(module_name, sizeof(module_name), "[%s]", module);
+		map = map_groups__find_by_name(&host_machine->kmaps, MAP__FUNCTION, module_name);
+		if (map) {
+			dso = map->dso;
+			goto found;
 		}
 		pr_debug("Failed to find module %s.\n", module);
 		return -ENOENT;
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 8a4537ee9bc3..fc3f7c922f99 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -1580,7 +1580,10 @@ static int __perf_session__process_events(struct perf_session *session,
 	file_offset = page_offset;
 	head = data_offset - page_offset;
 
-	if (data_size && (data_offset + data_size < file_size))
+	if (data_size == 0)
+		goto out;
+
+	if (data_offset + data_size < file_size)
 		file_size = data_offset + data_size;
 
 	ui_progress__init(&prog, file_size, "Processing events...");
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 415c359de465..2d065d065b67 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -196,7 +196,8 @@ static void zero_per_pkg(struct perf_evsel *counter)
 		memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
 }
 
-static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+static int check_per_pkg(struct perf_evsel *counter,
+			 struct perf_counts_values *vals, int cpu, bool *skip)
 {
 	unsigned long *mask = counter->per_pkg_mask;
 	struct cpu_map *cpus = perf_evsel__cpus(counter);
@@ -218,6 +219,17 @@ static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
 		counter->per_pkg_mask = mask;
 	}
 
+	/*
+	 * we do not consider an event that has not run as a good
+	 * instance to mark a package as used (skip=1). Otherwise
+	 * we may run into a situation where the first CPU in a package
+	 * is not running anything, yet the second is, and this function
+	 * would mark the package as used after the first CPU and would
+	 * not read the values from the second CPU.
+	 */
+	if (!(vals->run && vals->ena))
+		return 0;
+
 	s = cpu_map__get_socket(cpus, cpu);
 	if (s < 0)
 		return -1;
@@ -235,7 +247,7 @@ process_counter_values(struct perf_stat_config *config, struct perf_evsel *evsel
 	static struct perf_counts_values zero;
 	bool skip = false;
 
-	if (check_per_pkg(evsel, cpu, &skip)) {
+	if (check_per_pkg(evsel, count, cpu, &skip)) {
 		pr_err("failed to read per-pkg counter\n");
 		return -1;
 	}
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 53bb5f59ec58..475d88d0a1c9 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -38,7 +38,7 @@ static inline char *bfd_demangle(void __maybe_unused *v,
 #endif
 
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
-int elf_getphdrnum(Elf *elf, size_t *dst)
+static int elf_getphdrnum(Elf *elf, size_t *dst)
 {
 	GElf_Ehdr gehdr;
 	GElf_Ehdr *ehdr;
@@ -1271,8 +1271,6 @@ out_close:
 static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
 		       bool temp)
 {
-	GElf_Ehdr *ehdr;
-
 	kcore->elfclass = elfclass;
 
 	if (temp)
@@ -1289,9 +1287,7 @@ static int kcore__init(struct kcore *kcore, char *filename, int elfclass,
 	if (!gelf_newehdr(kcore->elf, elfclass))
 		goto out_end;
 
-	ehdr = gelf_getehdr(kcore->elf, &kcore->ehdr);
-	if (!ehdr)
-		goto out_end;
+	memset(&kcore->ehdr, 0, sizeof(GElf_Ehdr));
 
 	return 0;
 
@@ -1348,23 +1344,18 @@ static int kcore__copy_hdr(struct kcore *from, struct kcore *to, size_t count)
 static int kcore__add_phdr(struct kcore *kcore, int idx, off_t offset,
 			   u64 addr, u64 len)
 {
-	GElf_Phdr gphdr;
-	GElf_Phdr *phdr;
-
-	phdr = gelf_getphdr(kcore->elf, idx, &gphdr);
-	if (!phdr)
-		return -1;
-
-	phdr->p_type	= PT_LOAD;
-	phdr->p_flags	= PF_R | PF_W | PF_X;
-	phdr->p_offset	= offset;
-	phdr->p_vaddr	= addr;
-	phdr->p_paddr	= 0;
-	phdr->p_filesz	= len;
-	phdr->p_memsz	= len;
-	phdr->p_align	= page_size;
-
-	if (!gelf_update_phdr(kcore->elf, idx, phdr))
+	GElf_Phdr phdr = {
+		.p_type		= PT_LOAD,
+		.p_flags	= PF_R | PF_W | PF_X,
+		.p_offset	= offset,
+		.p_vaddr	= addr,
+		.p_paddr	= 0,
+		.p_filesz	= len,
+		.p_memsz	= len,
+		.p_align	= page_size,
+	};
+
+	if (!gelf_update_phdr(kcore->elf, idx, &phdr))
 		return -1;
 
 	return 0;
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 7acafb3c5592..c2cd9bf2348b 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -709,7 +709,7 @@ bool find_process(const char *name)
 
 	dir = opendir(procfs__mountpoint());
 	if (!dir)
-		return -1;
+		return false;
 
 	/* Walk through the directory. */
 	while (ret && (d = readdir(dir)) != NULL) {
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 9655cb49c7cb..bde0ef1a63df 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -71,8 +71,11 @@ unsigned int extra_msr_offset32;
 unsigned int extra_msr_offset64;
 unsigned int extra_delta_offset32;
 unsigned int extra_delta_offset64;
+unsigned int aperf_mperf_multiplier = 1;
 int do_smi;
 double bclk;
+double base_hz;
+double tsc_tweak = 1.0;
 unsigned int show_pkg;
 unsigned int show_core;
 unsigned int show_cpu;
@@ -502,7 +505,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	/* %Busy */
 	if (has_aperf) {
 		if (!skip_c0)
-			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc);
+			outp += sprintf(outp, "%8.2f", 100.0 * t->mperf/t->tsc/tsc_tweak);
 		else
 			outp += sprintf(outp, "********");
 	}
@@ -510,7 +513,7 @@ int format_counters(struct thread_data *t, struct core_data *c,
 	/* Bzy_MHz */
 	if (has_aperf)
 		outp += sprintf(outp, "%8.0f",
-			1.0 * t->tsc / units * t->aperf / t->mperf / interval_float);
+			1.0 * t->tsc * tsc_tweak / units * t->aperf / t->mperf / interval_float);
 
 	/* TSC_MHz */
 	outp += sprintf(outp, "%8.0f", 1.0 * t->tsc/units/interval_float);
@@ -984,6 +987,8 @@ int get_counters(struct thread_data *t, struct core_data *c, struct pkg_data *p)
 			return -3;
 		if (get_msr(cpu, MSR_IA32_MPERF, &t->mperf))
 			return -4;
+		t->aperf = t->aperf * aperf_mperf_multiplier;
+		t->mperf = t->mperf * aperf_mperf_multiplier;
 	}
 
 	if (do_smi) {
@@ -1149,6 +1154,19 @@ int slv_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCLRSV, PCLRSV, PCL__4, PCLRSV,
 int amt_pkg_cstate_limits[16] = {PCL__0, PCL__1, PCL__2, PCLRSV, PCLRSV, PCLRSV, PCL__6, PCL__7, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 int phi_pkg_cstate_limits[16] = {PCL__0, PCL__2, PCL_6N, PCL_6R, PCLRSV, PCLRSV, PCLRSV, PCLUNL, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV, PCLRSV};
 
+
+static void
+calculate_tsc_tweak()
+{
+	unsigned long long msr;
+	unsigned int base_ratio;
+
+	get_msr(base_cpu, MSR_NHM_PLATFORM_INFO, &msr);
+	base_ratio = (msr >> 8) & 0xFF;
+	base_hz = base_ratio * bclk * 1000000;
+	tsc_tweak = base_hz / tsc_hz;
+}
+
 static void
 dump_nhm_platform_info(void)
 {
@@ -1926,8 +1944,6 @@ int has_config_tdp(unsigned int family, unsigned int model)
 
 	switch (model) {
 	case 0x3A:	/* IVB */
-	case 0x3E:	/* IVB Xeon */
-
 	case 0x3C:	/* HSW */
 	case 0x3F:	/* HSX */
 	case 0x45:	/* HSW */
@@ -2543,6 +2559,13 @@ int is_knl(unsigned int family, unsigned int model)
 	return 0;
 }
 
+unsigned int get_aperf_mperf_multiplier(unsigned int family, unsigned int model)
+{
+	if (is_knl(family, model))
+		return 1024;
+	return 1;
+}
+
 #define SLM_BCLK_FREQS 5
 double slm_freq_table[SLM_BCLK_FREQS] = { 83.3, 100.0, 133.3, 116.7, 80.0};
 
@@ -2744,6 +2767,9 @@ void process_cpuid()
 		}
 	}
 
+	if (has_aperf)
+		aperf_mperf_multiplier = get_aperf_mperf_multiplier(family, model);
+
 	do_nhm_platform_info = do_nhm_cstates = do_smi = probe_nhm_msrs(family, model);
 	do_snb_cstates = has_snb_msrs(family, model);
 	do_pc2 = do_snb_cstates && (pkg_cstate_limit >= PCL__2);
@@ -2762,6 +2788,9 @@ void process_cpuid()
 	if (debug)
 		dump_cstate_pstate_config_info();
 
+	if (has_skl_msrs(family, model))
+		calculate_tsc_tweak();
+
 	return;
 }
 
@@ -3090,7 +3119,7 @@ int get_and_dump_counters(void)
 }
 
 void print_version() {
-	fprintf(stderr, "turbostat version 4.7 17-June, 2015"
+	fprintf(stderr, "turbostat version 4.8 26-Sep, 2015"
 		" - Len Brown <lenb@kernel.org>\n");
 }