Merge tag 'usb-4.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb

Pull USB fixes from Greg KH:
 "Here are some USB and PHY fixes for 4.2-rc6 that resolve some reported
  issues.

  All of these have been in the linux-next tree for a while, full
  details on the patches are in the shortlog below"

* tag 'usb-4.2-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb:
  ARM: dts: dra7: Add syscon-pllreset syscon to SATA PHY
  drivers/usb: Delete XHCI command timer if necessary
  xhci: fix off by one error in TRB DMA address boundary check
  usb: udc: core: add device_del() call to error pathway
  phy: ti-pipe3: i783 workaround for SATA lockup after dpll unlock/relock
  phy-sun4i-usb: Add missing EXPORT_SYMBOL_GPL for sun4i_usb_phy_set_squelch_detect
  USB: sierra: add 1199:68AB device ID
  usb: gadget: f_printer: actually limit the number of instances
  usb: gadget: f_hid: actually limit the number of instances
  usb: gadget: f_uac2: fix calculation of uac2->p_interval
  usb: gadget: bdc: fix a driver crash on disconnect
  usb: chipidea: ehci_init_driver is intended to call one time
  USB: qcserial: Add support for Dell Wireless 5809e 4G Modem
  USB: qcserial/option: make AT URCs work for Sierra Wireless MC7305/MC7355
diff --git a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
index d305876..c53e0b0 100644
--- a/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
+++ b/Documentation/devicetree/bindings/dma/apm-xgene-dma.txt
@@ -35,7 +35,7 @@
 			device_type = "dma";
 			reg = <0x0 0x1f270000 0x0 0x10000>,
 			      <0x0 0x1f200000 0x0 0x10000>,
-			      <0x0 0x1b008000 0x0 0x2000>,
+			      <0x0 0x1b000000 0x0 0x400000>,
 			      <0x0 0x1054a000 0x0 0x100>;
 			interrupts = <0x0 0x82 0x4>,
 				     <0x0 0xb8 0x4>,
diff --git a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
index 829bd26..519e97c 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-max98090.txt
@@ -3,11 +3,13 @@
 Required properties:
 - compatible : "mediatek,mt8173-max98090"
 - mediatek,audio-codec: the phandle of the MAX98090 audio codec
+- mediatek,platform: the phandle of MT8173 ASoC platform
 
 Example:
 
 	sound {
 		compatible = "mediatek,mt8173-max98090";
 		mediatek,audio-codec = <&max98090>;
+		mediatek,platform = <&afe>;
 	};
 
diff --git a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
index 61e98c9..f205ce9 100644
--- a/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
+++ b/Documentation/devicetree/bindings/sound/mt8173-rt5650-rt5676.txt
@@ -3,11 +3,13 @@
 Required properties:
 - compatible : "mediatek,mt8173-rt5650-rt5676"
 - mediatek,audio-codec: the phandles of rt5650 and rt5676 codecs
+- mediatek,platform: the phandle of MT8173 ASoC platform
 
 Example:
 
 	sound {
 		compatible = "mediatek,mt8173-rt5650-rt5676";
 		mediatek,audio-codec = <&rt5650 &rt5676>;
+		mediatek,platform = <&afe>;
 	};
 
diff --git a/Documentation/devicetree/bindings/spi/spi-ath79.txt b/Documentation/devicetree/bindings/spi/spi-ath79.txt
index f1ad9c3..9c696fa 100644
--- a/Documentation/devicetree/bindings/spi/spi-ath79.txt
+++ b/Documentation/devicetree/bindings/spi/spi-ath79.txt
@@ -3,7 +3,7 @@
 Required properties:
 - compatible: has to be "qca,<soc-type>-spi", "qca,ar7100-spi" as fallback.
 - reg: Base address and size of the controllers memory area
-- clocks: phandle to the AHB clock.
+- clocks: phandle of the AHB clock.
 - clock-names: has to be "ahb".
 - #address-cells: <1>, as required by generic SPI binding.
 - #size-cells: <0>, also as required by generic SPI binding.
@@ -12,9 +12,9 @@
 
 Example:
 
-	spi@1F000000 {
+	spi@1f000000 {
 		compatible = "qca,ar9132-spi", "qca,ar7100-spi";
-		reg = <0x1F000000 0x10>;
+		reg = <0x1f000000 0x10>;
 
 		clocks = <&pll 2>;
 		clock-names = "ahb";
diff --git a/Documentation/hwmon/nct7904 b/Documentation/hwmon/nct7904
index 014f112..57fffe3 100644
--- a/Documentation/hwmon/nct7904
+++ b/Documentation/hwmon/nct7904
@@ -35,11 +35,11 @@
 temp[2-9]_input		CPU temperatures (1/1000 degree,
 			0.125 degree resolution)
 
-fan[1-4]_mode		R/W, 0/1 for manual or SmartFan mode
+pwm[1-4]_enable		R/W, 1/2 for manual or SmartFan mode
 			Setting SmartFan mode is supported only if it has been
 			previously configured by BIOS (or configuration EEPROM)
 
-fan[1-4]_pwm		R/O in SmartFan mode, R/W in manual control mode
+pwm[1-4]		R/O in SmartFan mode, R/W in manual control mode
 
 The driver checks sensor control registers and does not export the sensors
 that are not enabled. Anyway, a sensor that is enabled may actually be not
diff --git a/Documentation/target/tcm_mod_builder.py b/Documentation/target/tcm_mod_builder.py
index 949de19..cda56df 100755
--- a/Documentation/target/tcm_mod_builder.py
+++ b/Documentation/target/tcm_mod_builder.py
@@ -199,7 +199,8 @@
 	buf += "#include <linux/string.h>\n"
 	buf += "#include <linux/configfs.h>\n"
 	buf += "#include <linux/ctype.h>\n"
-	buf += "#include <asm/unaligned.h>\n\n"
+	buf += "#include <asm/unaligned.h>\n"
+	buf += "#include <scsi/scsi_proto.h>\n\n"
 	buf += "#include <target/target_core_base.h>\n"
 	buf += "#include <target/target_core_fabric.h>\n"
 	buf += "#include <target/target_core_fabric_configfs.h>\n"
@@ -230,8 +231,14 @@
 	buf += "	}\n"
 	buf += "	tpg->" + fabric_mod_port + " = " + fabric_mod_port + ";\n"
 	buf += "	tpg->" + fabric_mod_port + "_tpgt = tpgt;\n\n"
-	buf += "	ret = core_tpg_register(&" + fabric_mod_name + "_ops, wwn,\n"
-	buf += "				&tpg->se_tpg, SCSI_PROTOCOL_SAS);\n"
+
+	if proto_ident == "FC":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_FCP);\n"
+	elif proto_ident == "SAS":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_SAS);\n"
+	elif proto_ident == "iSCSI":
+		buf += "	ret = core_tpg_register(wwn, &tpg->se_tpg, SCSI_PROTOCOL_ISCSI);\n"
+
 	buf += "	if (ret < 0) {\n"
 	buf += "		kfree(tpg);\n"
 	buf += "		return NULL;\n"
@@ -292,7 +299,7 @@
 
 	buf += "static const struct target_core_fabric_ops " + fabric_mod_name + "_ops = {\n"
 	buf += "	.module				= THIS_MODULE,\n"
-	buf += "	.name				= " + fabric_mod_name + ",\n"
+	buf += "	.name				= \"" + fabric_mod_name + "\",\n"
 	buf += "	.get_fabric_name		= " + fabric_mod_name + "_get_fabric_name,\n"
 	buf += "	.tpg_get_wwn			= " + fabric_mod_name + "_get_fabric_wwn,\n"
 	buf += "	.tpg_get_tag			= " + fabric_mod_name + "_get_tag,\n"
@@ -322,17 +329,17 @@
 	buf += "	.fabric_make_tpg		= " + fabric_mod_name + "_make_tpg,\n"
 	buf += "	.fabric_drop_tpg		= " + fabric_mod_name + "_drop_tpg,\n"
 	buf += "\n"
-	buf += "	.tfc_wwn_attrs			= " + fabric_mod_name + "_wwn_attrs;\n"
+	buf += "	.tfc_wwn_attrs			= " + fabric_mod_name + "_wwn_attrs,\n"
 	buf += "};\n\n"
 
 	buf += "static int __init " + fabric_mod_name + "_init(void)\n"
 	buf += "{\n"
-	buf += "	return target_register_template(" + fabric_mod_name + "_ops);\n"
+	buf += "	return target_register_template(&" + fabric_mod_name + "_ops);\n"
 	buf += "};\n\n"
 
 	buf += "static void __exit " + fabric_mod_name + "_exit(void)\n"
 	buf += "{\n"
-	buf += "	target_unregister_template(" + fabric_mod_name + "_ops);\n"
+	buf += "	target_unregister_template(&" + fabric_mod_name + "_ops);\n"
 	buf += "};\n\n"
 
 	buf += "MODULE_DESCRIPTION(\"" + fabric_mod_name.upper() + " series fabric driver\");\n"
diff --git a/MAINTAINERS b/MAINTAINERS
index 9289ecb..a9ae6c1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5600,6 +5600,7 @@
 IRQCHIP DRIVERS
 M:	Thomas Gleixner <tglx@linutronix.de>
 M:	Jason Cooper <jason@lakedaemon.net>
+M:	Marc Zyngier <marc.zyngier@arm.com>
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
@@ -5608,11 +5609,14 @@
 F:	drivers/irqchip/
 
 IRQ DOMAINS (IRQ NUMBER MAPPING LIBRARY)
-M:	Benjamin Herrenschmidt <benh@kernel.crashing.org>
+M:	Jiang Liu <jiang.liu@linux.intel.com>
+M:	Marc Zyngier <marc.zyngier@arm.com>
 S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git irq/core
 F:	Documentation/IRQ-domain.txt
 F:	include/linux/irqdomain.h
 F:	kernel/irq/irqdomain.c
+F:	kernel/irq/msi.c
 
 ISAPNP
 M:	Jaroslav Kysela <perex@perex.cz>
diff --git a/Makefile b/Makefile
index afabc44..15d3201 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 2
 SUBLEVEL = 0
-EXTRAVERSION = -rc4
+EXTRAVERSION = -rc5
 NAME = Hurr durr I'ma sheep
 
 # *DOCUMENTATION*
@@ -597,6 +597,11 @@
 # Defaults to vmlinux, but the arch makefile usually adds further targets
 all: vmlinux
 
+# The arch Makefile can set ARCH_{CPP,A,C}FLAGS to override the default
+# values of the respective KBUILD_* variables
+ARCH_CPPFLAGS :=
+ARCH_AFLAGS :=
+ARCH_CFLAGS :=
 include arch/$(SRCARCH)/Makefile
 
 KBUILD_CFLAGS	+= $(call cc-option,-fno-delete-null-pointer-checks,)
@@ -848,10 +853,10 @@
 mod_compress_cmd = true
 ifdef CONFIG_MODULE_COMPRESS
   ifdef CONFIG_MODULE_COMPRESS_GZIP
-    mod_compress_cmd = gzip -n
+    mod_compress_cmd = gzip -n -f
   endif # CONFIG_MODULE_COMPRESS_GZIP
   ifdef CONFIG_MODULE_COMPRESS_XZ
-    mod_compress_cmd = xz
+    mod_compress_cmd = xz -f
   endif # CONFIG_MODULE_COMPRESS_XZ
 endif # CONFIG_MODULE_COMPRESS
 export mod_compress_cmd
diff --git a/arch/arm/boot/dts/exynos3250.dtsi b/arch/arm/boot/dts/exynos3250.dtsi
index d720133..2db9943 100644
--- a/arch/arm/boot/dts/exynos3250.dtsi
+++ b/arch/arm/boot/dts/exynos3250.dtsi
@@ -138,8 +138,8 @@
 
 		mipi_phy: video-phy@10020710 {
 			compatible = "samsung,s5pv210-mipi-video-phy";
-			reg = <0x10020710 8>;
 			#phy-cells = <1>;
+			syscon = <&pmu_system_controller>;
 		};
 
 		pd_cam: cam-power-domain@10023C00 {
diff --git a/arch/arm/boot/dts/exynos4210-origen.dts b/arch/arm/boot/dts/exynos4210-origen.dts
index e0abfc3..e050d85 100644
--- a/arch/arm/boot/dts/exynos4210-origen.dts
+++ b/arch/arm/boot/dts/exynos4210-origen.dts
@@ -127,6 +127,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&buck1_reg>;
+};
+
 &fimd {
 	pinctrl-0 = <&lcd_en &lcd_clk &lcd_data24 &pwm0_out>;
 	pinctrl-names = "default";
diff --git a/arch/arm/boot/dts/exynos4210-trats.dts b/arch/arm/boot/dts/exynos4210-trats.dts
index 98f3ce6..ba34886 100644
--- a/arch/arm/boot/dts/exynos4210-trats.dts
+++ b/arch/arm/boot/dts/exynos4210-trats.dts
@@ -188,6 +188,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&varm_breg>;
+};
+
 &dsi_0 {
 	vddcore-supply = <&vusb_reg>;
 	vddio-supply = <&vmipi_reg>;
diff --git a/arch/arm/boot/dts/exynos4210-universal_c210.dts b/arch/arm/boot/dts/exynos4210-universal_c210.dts
index d4f2b11..775892b 100644
--- a/arch/arm/boot/dts/exynos4210-universal_c210.dts
+++ b/arch/arm/boot/dts/exynos4210-universal_c210.dts
@@ -548,6 +548,10 @@
 	};
 };
 
+&cpu0 {
+	cpu0-supply = <&vdd_arm_reg>;
+};
+
 &pinctrl_1 {
 	hdmi_hpd: hdmi-hpd {
 		samsung,pins = "gpx3-7";
diff --git a/arch/arm/boot/dts/exynos4210.dtsi b/arch/arm/boot/dts/exynos4210.dtsi
index 10d3c17..3e5ba66 100644
--- a/arch/arm/boot/dts/exynos4210.dtsi
+++ b/arch/arm/boot/dts/exynos4210.dtsi
@@ -40,6 +40,18 @@
 			device_type = "cpu";
 			compatible = "arm,cortex-a9";
 			reg = <0x900>;
+			clocks = <&clock CLK_ARM_CLK>;
+			clock-names = "cpu";
+			clock-latency = <160000>;
+
+			operating-points = <
+				1200000 1250000
+				1000000 1150000
+				800000	1075000
+				500000	975000
+				400000	975000
+				200000	950000
+			>;
 			cooling-min-level = <4>;
 			cooling-max-level = <2>;
 			#cooling-cells = <2>; /* min followed by max */
diff --git a/arch/arm/boot/dts/imx35.dtsi b/arch/arm/boot/dts/imx35.dtsi
index b6478e9..e6540b5 100644
--- a/arch/arm/boot/dts/imx35.dtsi
+++ b/arch/arm/boot/dts/imx35.dtsi
@@ -286,8 +286,8 @@
 			can1: can@53fe4000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe4000 0x1000>;
-				clocks = <&clks 33>;
-				clock-names = "ipg";
+				clocks = <&clks 33>, <&clks 33>;
+				clock-names = "ipg", "per";
 				interrupts = <43>;
 				status = "disabled";
 			};
@@ -295,8 +295,8 @@
 			can2: can@53fe8000 {
 				compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan";
 				reg = <0x53fe8000 0x1000>;
-				clocks = <&clks 34>;
-				clock-names = "ipg";
+				clocks = <&clks 34>, <&clks 34>;
+				clock-names = "ipg", "per";
 				interrupts = <44>;
 				status = "disabled";
 			};
diff --git a/arch/arm/boot/dts/k2e-clocks.dtsi b/arch/arm/boot/dts/k2e-clocks.dtsi
index 4773d6a..d56d68f 100644
--- a/arch/arm/boot/dts/k2e-clocks.dtsi
+++ b/arch/arm/boot/dts/k2e-clocks.dtsi
@@ -13,9 +13,8 @@
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2hk-clocks.dtsi b/arch/arm/boot/dts/k2hk-clocks.dtsi
index d5adee3..af9b719 100644
--- a/arch/arm/boot/dts/k2hk-clocks.dtsi
+++ b/arch/arm/boot/dts/k2hk-clocks.dtsi
@@ -22,9 +22,8 @@
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/k2l-clocks.dtsi b/arch/arm/boot/dts/k2l-clocks.dtsi
index eb1e3e2..ef8464b 100644
--- a/arch/arm/boot/dts/k2l-clocks.dtsi
+++ b/arch/arm/boot/dts/k2l-clocks.dtsi
@@ -22,9 +22,8 @@
 		#clock-cells = <0>;
 		compatible = "ti,keystone,main-pll-clock";
 		clocks = <&refclksys>;
-		reg = <0x02620350 4>, <0x02310110 4>;
-		reg-names = "control", "multiplier";
-		fixed-postdiv = <2>;
+		reg = <0x02620350 4>, <0x02310110 4>, <0x02310108 4>;
+		reg-names = "control", "multiplier", "post-divider";
 	};
 
 	papllclk: papllclk@2620358 {
diff --git a/arch/arm/boot/dts/ste-nomadik-nhk15.dts b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
index 3d0b875..3d25dba 100644
--- a/arch/arm/boot/dts/ste-nomadik-nhk15.dts
+++ b/arch/arm/boot/dts/ste-nomadik-nhk15.dts
@@ -17,6 +17,7 @@
 	};
 
 	aliases {
+		serial1 = &uart1;
 		stmpe-i2c0 = &stmpe0;
 		stmpe-i2c1 = &stmpe1;
 	};
diff --git a/arch/arm/boot/dts/ste-nomadik-s8815.dts b/arch/arm/boot/dts/ste-nomadik-s8815.dts
index 85d3b95..3c140d0 100644
--- a/arch/arm/boot/dts/ste-nomadik-s8815.dts
+++ b/arch/arm/boot/dts/ste-nomadik-s8815.dts
@@ -15,6 +15,10 @@
 		bootargs = "root=/dev/ram0 console=ttyAMA1,115200n8 earlyprintk";
 	};
 
+	aliases {
+		serial1 = &uart1;
+	};
+
 	src@101e0000 {
 		/* These chrystal drivers are not used on this board */
 		disable-sxtalo;
diff --git a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
index 9a5f2ba..ef794a3 100644
--- a/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
+++ b/arch/arm/boot/dts/ste-nomadik-stn8815.dtsi
@@ -757,6 +757,7 @@
 			clock-names = "uartclk", "apb_pclk";
 			pinctrl-names = "default";
 			pinctrl-0 = <&uart0_default_mux>;
+			status = "disabled";
 		};
 
 		uart1: uart@101fb000 {
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index d78c12e..486cc4d 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -2373,6 +2373,9 @@
  * registers.  This address is needed early so the OCP registers that
  * are part of the device's address space can be ioremapped properly.
  *
+ * If SYSC access is not needed, the registers will not be remapped
+ * and non-availability of MPU access is not treated as an error.
+ *
  * Returns 0 on success, -EINVAL if an invalid hwmod is passed, and
  * -ENXIO on absent or invalid register target address space.
  */
@@ -2387,6 +2390,11 @@
 
 	_save_mpu_port_index(oh);
 
+	/* if we don't need sysc access we don't need to ioremap */
+	if (!oh->class->sysc)
+		return 0;
+
+	/* we can't continue without MPU PORT if we need sysc access */
 	if (oh->_int_flags & _HWMOD_NO_MPU_PORT)
 		return -ENXIO;
 
@@ -2396,8 +2404,10 @@
 			 oh->name);
 
 		/* Extract the IO space from device tree blob */
-		if (!np)
+		if (!np) {
+			pr_err("omap_hwmod: %s: no dt node\n", oh->name);
 			return -ENXIO;
+		}
 
 		va_start = of_iomap(np, index + oh->mpu_rt_idx);
 	} else {
@@ -2456,13 +2466,11 @@
 				oh->name, np->name);
 	}
 
-	if (oh->class->sysc) {
-		r = _init_mpu_rt_base(oh, NULL, index, np);
-		if (r < 0) {
-			WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
-			     oh->name);
-			return 0;
-		}
+	r = _init_mpu_rt_base(oh, NULL, index, np);
+	if (r < 0) {
+		WARN(1, "omap_hwmod: %s: doesn't have mpu register target base\n",
+		     oh->name);
+		return 0;
 	}
 
 	r = _init_clocks(oh, NULL);
diff --git a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
index 2606c66..562247b 100644
--- a/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_7xx_data.c
@@ -827,8 +827,7 @@
 	.syss_offs	= 0x0014,
 	.sysc_flags	= (SYSC_HAS_AUTOIDLE | SYSC_HAS_SIDLEMODE |
 			   SYSC_HAS_SOFTRESET | SYSS_HAS_RESET_STATUS),
-	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART |
-			   SIDLE_SMART_WKUP),
+	.idlemodes	= (SIDLE_FORCE | SIDLE_NO | SIDLE_SMART),
 	.sysc_fields	= &omap_hwmod_sysc_type1,
 };
 
@@ -844,7 +843,7 @@
 	.class		= &dra7xx_gpmc_hwmod_class,
 	.clkdm_name	= "l3main1_clkdm",
 	/* Skip reset for CONFIG_OMAP_GPMC_DEBUG for bootloader timings */
-	.flags		= HWMOD_SWSUP_SIDLE | DEBUG_OMAP_GPMC_HWMOD_FLAGS,
+	.flags		= DEBUG_OMAP_GPMC_HWMOD_FLAGS,
 	.main_clk	= "l3_iclk_div",
 	.prcm = {
 		.omap4 = {
diff --git a/arch/arm64/boot/dts/apm/apm-storm.dtsi b/arch/arm64/boot/dts/apm/apm-storm.dtsi
index 0689c3f..58093ed 100644
--- a/arch/arm64/boot/dts/apm/apm-storm.dtsi
+++ b/arch/arm64/boot/dts/apm/apm-storm.dtsi
@@ -823,7 +823,7 @@
 			device_type = "dma";
 			reg = <0x0 0x1f270000 0x0 0x10000>,
 			      <0x0 0x1f200000 0x0 0x10000>,
-			      <0x0 0x1b008000 0x0 0x2000>,
+			      <0x0 0x1b000000 0x0 0x400000>,
 			      <0x0 0x1054a000 0x0 0x100>;
 			interrupts = <0x0 0x82 0x4>,
 				     <0x0 0xb8 0x4>,
diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c
index 9d4aa18..e8ca6ea 100644
--- a/arch/arm64/kernel/efi.c
+++ b/arch/arm64/kernel/efi.c
@@ -122,12 +122,12 @@
 
 	/* Show what we know for posterity */
 	c16 = early_memremap(efi_to_phys(efi.systab->fw_vendor),
-			     sizeof(vendor));
+			     sizeof(vendor) * sizeof(efi_char16_t));
 	if (c16) {
 		for (i = 0; i < (int) sizeof(vendor) - 1 && *c16; ++i)
 			vendor[i] = c16[i];
 		vendor[i] = '\0';
-		early_memunmap(c16, sizeof(vendor));
+		early_memunmap(c16, sizeof(vendor) * sizeof(efi_char16_t));
 	}
 
 	pr_info("EFI v%u.%.02u by %s\n",
diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c
index 1670f15..948f0ad 100644
--- a/arch/arm64/kernel/signal32.c
+++ b/arch/arm64/kernel/signal32.c
@@ -168,7 +168,8 @@
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitely for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 		break;
@@ -201,8 +202,6 @@
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, __ARCH_SI_PREAMBLE_SIZE) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE))
diff --git a/arch/avr32/mach-at32ap/clock.c b/arch/avr32/mach-at32ap/clock.c
index 23b1a97..52c179b 100644
--- a/arch/avr32/mach-at32ap/clock.c
+++ b/arch/avr32/mach-at32ap/clock.c
@@ -80,6 +80,9 @@
 {
 	unsigned long flags;
 
+	if (!clk)
+		return 0;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	__clk_enable(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -106,6 +109,9 @@
 {
 	unsigned long flags;
 
+	if (IS_ERR_OR_NULL(clk))
+		return;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	__clk_disable(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -117,6 +123,9 @@
 	unsigned long flags;
 	unsigned long rate;
 
+	if (!clk)
+		return 0;
+
 	spin_lock_irqsave(&clk_lock, flags);
 	rate = clk->get_rate(clk);
 	spin_unlock_irqrestore(&clk_lock, flags);
@@ -129,6 +138,9 @@
 {
 	unsigned long flags, actual_rate;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_rate)
 		return -ENOSYS;
 
@@ -145,6 +157,9 @@
 	unsigned long flags;
 	long ret;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_rate)
 		return -ENOSYS;
 
@@ -161,6 +176,9 @@
 	unsigned long flags;
 	int ret;
 
+	if (!clk)
+		return 0;
+
 	if (!clk->set_parent)
 		return -ENOSYS;
 
@@ -174,7 +192,7 @@
 
 struct clk *clk_get_parent(struct clk *clk)
 {
-	return clk->parent;
+	return !clk ? NULL : clk->parent;
 }
 EXPORT_SYMBOL(clk_get_parent);
 
diff --git a/arch/mips/kernel/signal32.c b/arch/mips/kernel/signal32.c
index 19a7705..5d7f263 100644
--- a/arch/mips/kernel/signal32.c
+++ b/arch/mips/kernel/signal32.c
@@ -409,8 +409,6 @@
 
 int copy_siginfo_from_user32(siginfo_t *to, compat_siginfo_t __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index d3a831a..da50e0c 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -966,8 +966,6 @@
 
 int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from)
 {
-	memset(to, 0, sizeof *to);
-
 	if (copy_from_user(to, from, 3*sizeof(int)) ||
 	    copy_from_user(to->_sifields._pad,
 			   from->_sifields._pad, SI_PAD_SIZE32))
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index 5cf5e6e..7cf0df8 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -1478,7 +1478,7 @@
 	}
 
 	/* Unmask the event */
-	if (eeh_enabled())
+	if (ret == EEH_NEXT_ERR_NONE && eeh_enabled())
 		enable_irq(eeh_event_irq);
 
 	return ret;
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index 5738d31..85cbc96 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -2220,7 +2220,7 @@
 
 static __be64 *pnv_pci_ioda2_table_do_alloc_pages(int nid, unsigned shift,
 		unsigned levels, unsigned long limit,
-		unsigned long *current_offset)
+		unsigned long *current_offset, unsigned long *total_allocated)
 {
 	struct page *tce_mem = NULL;
 	__be64 *addr, *tmp;
@@ -2236,6 +2236,7 @@
 	}
 	addr = page_address(tce_mem);
 	memset(addr, 0, allocated);
+	*total_allocated += allocated;
 
 	--levels;
 	if (!levels) {
@@ -2245,7 +2246,7 @@
 
 	for (i = 0; i < entries; ++i) {
 		tmp = pnv_pci_ioda2_table_do_alloc_pages(nid, shift,
-				levels, limit, current_offset);
+				levels, limit, current_offset, total_allocated);
 		if (!tmp)
 			break;
 
@@ -2267,7 +2268,7 @@
 		struct iommu_table *tbl)
 {
 	void *addr;
-	unsigned long offset = 0, level_shift;
+	unsigned long offset = 0, level_shift, total_allocated = 0;
 	const unsigned window_shift = ilog2(window_size);
 	unsigned entries_shift = window_shift - page_shift;
 	unsigned table_shift = max_t(unsigned, entries_shift + 3, PAGE_SHIFT);
@@ -2286,7 +2287,7 @@
 
 	/* Allocate TCE table */
 	addr = pnv_pci_ioda2_table_do_alloc_pages(nid, level_shift,
-			levels, tce_table_size, &offset);
+			levels, tce_table_size, &offset, &total_allocated);
 
 	/* addr==NULL means that the first level allocation failed */
 	if (!addr)
@@ -2308,7 +2309,7 @@
 			page_shift);
 	tbl->it_level_size = 1ULL << (level_shift - 3);
 	tbl->it_indirect_levels = levels - 1;
-	tbl->it_allocated_size = offset;
+	tbl->it_allocated_size = total_allocated;
 
 	pr_devel("Created TCE table: ws=%08llx ts=%lx @%08llx\n",
 			window_size, tce_table_size, bus_offset);
diff --git a/arch/s390/kernel/cache.c b/arch/s390/kernel/cache.c
index bff5e3b..8ba3243 100644
--- a/arch/s390/kernel/cache.c
+++ b/arch/s390/kernel/cache.c
@@ -138,6 +138,8 @@
 	union cache_topology ct;
 	enum cache_type ctype;
 
+	if (!test_facility(34))
+		return -EOPNOTSUPP;
 	if (!this_cpu_ci)
 		return -EINVAL;
 	ct.raw = ecag(EXTRACT_TOPOLOGY, 0, 0);
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 2078f92..f32f843 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -1742,10 +1742,10 @@
 
 static int kvm_s390_handle_requests(struct kvm_vcpu *vcpu)
 {
-	if (!vcpu->requests)
-		return 0;
 retry:
 	kvm_s390_vcpu_request_handled(vcpu);
+	if (!vcpu->requests)
+		return 0;
 	/*
 	 * We use MMU_RELOAD just to re-arm the ipte notifier for the
 	 * guest prefix page. gmap_ipte_notify will wait on the ptl lock.
diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c
index fee782a..8d2e516 100644
--- a/arch/s390/net/bpf_jit_comp.c
+++ b/arch/s390/net/bpf_jit_comp.c
@@ -448,13 +448,13 @@
 		EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0,
 			      BPF_REG_1, offsetof(struct sk_buff, data));
 	}
-	/* BPF compatibility: clear A (%b7) and X (%b8) registers */
-	if (REG_SEEN(BPF_REG_7))
-		/* lghi %b7,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_7, 0);
-	if (REG_SEEN(BPF_REG_8))
-		/* lghi %b8,0 */
-		EMIT4_IMM(0xa7090000, BPF_REG_8, 0);
+	/* BPF compatibility: clear A (%b0) and X (%b7) registers */
+	if (REG_SEEN(BPF_REG_A))
+		/* lghi %ba,0 */
+		EMIT4_IMM(0xa7090000, BPF_REG_A, 0);
+	if (REG_SEEN(BPF_REG_X))
+		/* lghi %bx,0 */
+		EMIT4_IMM(0xa7090000, BPF_REG_X, 0);
 }
 
 /*
diff --git a/arch/sparc/include/asm/visasm.h b/arch/sparc/include/asm/visasm.h
index 1f0aa20..6424249 100644
--- a/arch/sparc/include/asm/visasm.h
+++ b/arch/sparc/include/asm/visasm.h
@@ -28,16 +28,10 @@
  * Must preserve %o5 between VISEntryHalf and VISExitHalf */
 
 #define VISEntryHalf					\
-	rd		%fprs, %o5;			\
-	andcc		%o5, FPRS_FEF, %g0;		\
-	be,pt		%icc, 297f;			\
-	 sethi		%hi(298f), %g7;			\
-	sethi		%hi(VISenterhalf), %g1;		\
-	jmpl		%g1 + %lo(VISenterhalf), %g0;	\
-	 or		%g7, %lo(298f), %g7;		\
-	clr		%o5;				\
-297:	wr		%o5, FPRS_FEF, %fprs;		\
-298:
+	VISEntry
+
+#define VISExitHalf					\
+	VISExit
 
 #define VISEntryHalfFast(fail_label)			\
 	rd		%fprs, %o5;			\
@@ -47,7 +41,7 @@
 	ba,a,pt		%xcc, fail_label;		\
 297:	wr		%o5, FPRS_FEF, %fprs;
 
-#define VISExitHalf					\
+#define VISExitHalfFast					\
 	wr		%o5, 0, %fprs;
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/lib/NG4memcpy.S b/arch/sparc/lib/NG4memcpy.S
index 140527a..83aeeb1 100644
--- a/arch/sparc/lib/NG4memcpy.S
+++ b/arch/sparc/lib/NG4memcpy.S
@@ -240,8 +240,11 @@
 	add		%o0, 0x40, %o0
 	bne,pt		%icc, 1b
 	 LOAD(prefetch, %g1 + 0x200, #n_reads_strong)
+#ifdef NON_USER_COPY
+	VISExitHalfFast
+#else
 	VISExitHalf
-
+#endif
 	brz,pn		%o2, .Lexit
 	 cmp		%o2, 19
 	ble,pn		%icc, .Lsmall_unaligned
diff --git a/arch/sparc/lib/VISsave.S b/arch/sparc/lib/VISsave.S
index b320ae9..a063d84 100644
--- a/arch/sparc/lib/VISsave.S
+++ b/arch/sparc/lib/VISsave.S
@@ -44,9 +44,8 @@
 
 	 stx		%g3, [%g6 + TI_GSR]
 2:	add		%g6, %g1, %g3
-	cmp		%o5, FPRS_DU
-	be,pn		%icc, 6f
-	 sll		%g1, 3, %g1
+	mov		FPRS_DU | FPRS_DL | FPRS_FEF, %o5
+	sll		%g1, 3, %g1
 	stb		%o5, [%g3 + TI_FPSAVED]
 	rd		%gsr, %g2
 	add		%g6, %g1, %g3
@@ -80,65 +79,3 @@
 	.align		32
 80:	jmpl		%g7 + %g0, %g0
 	 nop
-
-6:	ldub		[%g3 + TI_FPSAVED], %o5
-	or		%o5, FPRS_DU, %o5
-	add		%g6, TI_FPREGS+0x80, %g2
-	stb		%o5, [%g3 + TI_FPSAVED]
-
-	sll		%g1, 5, %g1
-	add		%g6, TI_FPREGS+0xc0, %g3
-	wr		%g0, FPRS_FEF, %fprs
-	membar		#Sync
-	stda		%f32, [%g2 + %g1] ASI_BLK_P
-	stda		%f48, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 80f
-	 nop
-
-	.align		32
-80:	jmpl		%g7 + %g0, %g0
-	 nop
-
-	.align		32
-VISenterhalf:
-	ldub		[%g6 + TI_FPDEPTH], %g1
-	brnz,a,pn	%g1, 1f
-	 cmp		%g1, 1
-	stb		%g0, [%g6 + TI_FPSAVED]
-	stx		%fsr, [%g6 + TI_XFSR]
-	clr		%o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%g0, FPRS_FEF, %fprs
-
-1:	bne,pn		%icc, 2f
-	 srl		%g1, 1, %g1
-	ba,pt		%xcc, vis1
-	 sub		%g7, 8, %g7
-2:	addcc		%g6, %g1, %g3
-	sll		%g1, 3, %g1
-	andn		%o5, FPRS_DU, %g2
-	stb		%g2, [%g3 + TI_FPSAVED]
-
-	rd		%gsr, %g2
-	add		%g6, %g1, %g3
-	stx		%g2, [%g3 + TI_GSR]
-	add		%g6, %g1, %g2
-	stx		%fsr, [%g2 + TI_XFSR]
-	sll		%g1, 5, %g1
-3:	andcc		%o5, FPRS_DL, %g0
-	be,pn		%icc, 4f
-	 add		%g6, TI_FPREGS, %g2
-
-	add		%g6, TI_FPREGS+0x40, %g3
-	membar		#Sync
-	stda		%f0, [%g2 + %g1] ASI_BLK_P
-	stda		%f16, [%g3 + %g1] ASI_BLK_P
-	membar		#Sync
-	ba,pt		%xcc, 4f
-	 nop
-
-	.align		32
-4:	and		%o5, FPRS_DU, %o5
-	jmpl		%g7 + %g0, %g0
-	 wr		%o5, FPRS_FEF, %fprs
diff --git a/arch/sparc/lib/ksyms.c b/arch/sparc/lib/ksyms.c
index 1d649a9..8069ce1 100644
--- a/arch/sparc/lib/ksyms.c
+++ b/arch/sparc/lib/ksyms.c
@@ -135,10 +135,6 @@
 void VISenter(void);
 EXPORT_SYMBOL(VISenter);
 
-/* CRYPTO code needs this */
-void VISenterhalf(void);
-EXPORT_SYMBOL(VISenterhalf);
-
 extern void xor_vis_2(unsigned long, unsigned long *, unsigned long *);
 extern void xor_vis_3(unsigned long, unsigned long *, unsigned long *,
 		unsigned long *);
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index e8c2c04..c667e10 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -113,8 +113,6 @@
 	if (!access_ok(VERIFY_READ, from, sizeof(struct compat_siginfo)))
 		return -EFAULT;
 
-	memset(to, 0, sizeof(*to));
-
 	err = __get_user(to->si_signo, &from->si_signo);
 	err |= __get_user(to->si_errno, &from->si_errno);
 	err |= __get_user(to->si_code, &from->si_code);
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 2c82bd1..7d69afd 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -1193,6 +1193,10 @@
 		unsigned int e820_type = 0;
 		unsigned long m = efi->efi_memmap;
 
+#ifdef CONFIG_X86_64
+		m |= (u64)efi->efi_memmap_hi << 32;
+#endif
+
 		d = (efi_memory_desc_t *)(m + (i * efi->efi_memdesc_size));
 		switch (d->type) {
 		case EFI_RESERVED_TYPE:
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index a0bf89f..4e10d73 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -280,21 +280,6 @@
 	set_ldt(NULL, 0);
 }
 
-/*
- * load one particular LDT into the current CPU
- */
-static inline void load_LDT_nolock(mm_context_t *pc)
-{
-	set_ldt(pc->ldt, pc->size);
-}
-
-static inline void load_LDT(mm_context_t *pc)
-{
-	preempt_disable();
-	load_LDT_nolock(pc);
-	preempt_enable();
-}
-
 static inline unsigned long get_desc_base(const struct desc_struct *desc)
 {
 	return (unsigned)(desc->base0 | ((desc->base1) << 16) | ((desc->base2) << 24));
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 09b9620..364d274 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -9,8 +9,7 @@
  * we put the segment information here.
  */
 typedef struct {
-	void *ldt;
-	int size;
+	struct ldt_struct *ldt;
 
 #ifdef CONFIG_X86_64
 	/* True if mm supports a task running in 32 bit compatibility mode. */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 804a3a6..984abfe 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -34,6 +34,50 @@
 #endif
 
 /*
+ * ldt_structs can be allocated, used, and freed, but they are never
+ * modified while live.
+ */
+struct ldt_struct {
+	/*
+	 * Xen requires page-aligned LDTs with special permissions.  This is
+	 * needed to prevent us from installing evil descriptors such as
+	 * call gates.  On native, we could merge the ldt_struct and LDT
+	 * allocations, but it's not worth trying to optimize.
+	 */
+	struct desc_struct *entries;
+	int size;
+};
+
+static inline void load_mm_ldt(struct mm_struct *mm)
+{
+	struct ldt_struct *ldt;
+
+	/* lockless_dereference synchronizes with smp_store_release */
+	ldt = lockless_dereference(mm->context.ldt);
+
+	/*
+	 * Any change to mm->context.ldt is followed by an IPI to all
+	 * CPUs with the mm active.  The LDT will not be freed until
+	 * after the IPI is handled by all such CPUs.  This means that,
+	 * if the ldt_struct changes before we return, the values we see
+	 * will be safe, and the new values will be loaded before we run
+	 * any user code.
+	 *
+	 * NB: don't try to convert this to use RCU without extreme care.
+	 * We would still need IRQs off, because we don't want to change
+	 * the local LDT after an IPI loaded a newer value than the one
+	 * that we can see.
+	 */
+
+	if (unlikely(ldt))
+		set_ldt(ldt->entries, ldt->size);
+	else
+		clear_LDT();
+
+	DEBUG_LOCKS_WARN_ON(preemptible());
+}
+
+/*
  * Used for LDT copy/destruction.
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
@@ -78,12 +122,12 @@
 		 * was called and then modify_ldt changed
 		 * prev->context.ldt but suppressed an IPI to this CPU.
 		 * In this case, prev->context.ldt != NULL, because we
-		 * never free an LDT while the mm still exists.  That
-		 * means that next->context.ldt != prev->context.ldt,
-		 * because mms never share an LDT.
+		 * never set context.ldt to NULL while the mm still
+		 * exists.  That means that next->context.ldt !=
+		 * prev->context.ldt, because mms never share an LDT.
 		 */
 		if (unlikely(prev->context.ldt != next->context.ldt))
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 	}
 #ifdef CONFIG_SMP
 	  else {
@@ -106,7 +150,7 @@
 			load_cr3(next->pgd);
 			trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
 			load_mm_cr4(next);
-			load_LDT_nolock(&next->context);
+			load_mm_ldt(next);
 		}
 	}
 #endif
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 845dc0d..206052e 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -943,7 +943,7 @@
 	 */
 	if (irq < nr_legacy_irqs() && data->count == 1) {
 		if (info->ioapic_trigger != data->trigger)
-			mp_register_handler(irq, data->trigger);
+			mp_register_handler(irq, info->ioapic_trigger);
 		data->entry.trigger = data->trigger = info->ioapic_trigger;
 		data->entry.polarity = data->polarity = info->ioapic_polarity;
 	}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 922c5e0..cb9e5df 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1410,7 +1410,7 @@
 	load_sp0(t, &current->thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	clear_all_debug_regs();
 	dbg_restore_debug_regs();
@@ -1459,7 +1459,7 @@
 	load_sp0(t, thread);
 	set_tss_desc(cpu, t);
 	load_TR_desc();
-	load_LDT(&init_mm.context);
+	load_mm_ldt(&init_mm);
 
 	t->x86_tss.io_bitmap_base = offsetof(struct tss_struct, io_bitmap);
 
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index 3658de4..9469dfa 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -2179,21 +2179,25 @@
 	int idx = segment >> 3;
 
 	if ((segment & SEGMENT_TI_MASK) == SEGMENT_LDT) {
+		struct ldt_struct *ldt;
+
 		if (idx > LDT_ENTRIES)
 			return 0;
 
-		if (idx > current->active_mm->context.size)
+		/* IRQs are off, so this synchronizes with smp_store_release */
+		ldt = lockless_dereference(current->active_mm->context.ldt);
+		if (!ldt || idx > ldt->size)
 			return 0;
 
-		desc = current->active_mm->context.ldt;
+		desc = &ldt->entries[idx];
 	} else {
 		if (idx > GDT_ENTRIES)
 			return 0;
 
-		desc = raw_cpu_ptr(gdt_page.gdt);
+		desc = raw_cpu_ptr(gdt_page.gdt) + idx;
 	}
 
-	return get_desc_base(desc + idx);
+	return get_desc_base(desc);
 }
 
 #ifdef CONFIG_COMPAT
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index c37886d..2bcc052 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -12,6 +12,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/smp.h>
+#include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/uaccess.h>
 
@@ -20,82 +21,82 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
-#ifdef CONFIG_SMP
+/* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *current_mm)
 {
-	if (current->active_mm == current_mm)
-		load_LDT(&current->active_mm->context);
+	mm_context_t *pc;
+
+	if (current->active_mm != current_mm)
+		return;
+
+	pc = &current->active_mm->context;
+	set_ldt(pc->ldt->entries, pc->ldt->size);
 }
-#endif
 
-static int alloc_ldt(mm_context_t *pc, int mincount, int reload)
+/* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
+static struct ldt_struct *alloc_ldt_struct(int size)
 {
-	void *oldldt, *newldt;
-	int oldsize;
+	struct ldt_struct *new_ldt;
+	int alloc_size;
 
-	if (mincount <= pc->size)
-		return 0;
-	oldsize = pc->size;
-	mincount = (mincount + (PAGE_SIZE / LDT_ENTRY_SIZE - 1)) &
-			(~(PAGE_SIZE / LDT_ENTRY_SIZE - 1));
-	if (mincount * LDT_ENTRY_SIZE > PAGE_SIZE)
-		newldt = vmalloc(mincount * LDT_ENTRY_SIZE);
+	if (size > LDT_ENTRIES)
+		return NULL;
+
+	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+	if (!new_ldt)
+		return NULL;
+
+	BUILD_BUG_ON(LDT_ENTRY_SIZE != sizeof(struct desc_struct));
+	alloc_size = size * LDT_ENTRY_SIZE;
+
+	/*
+	 * Xen is very picky: it requires a page-aligned LDT that has no
+	 * trailing nonzero bytes in any page that contains LDT descriptors.
+	 * Keep it simple: zero the whole allocation and never allocate less
+	 * than PAGE_SIZE.
+	 */
+	if (alloc_size > PAGE_SIZE)
+		new_ldt->entries = vzalloc(alloc_size);
 	else
-		newldt = (void *)__get_free_page(GFP_KERNEL);
+		new_ldt->entries = kzalloc(PAGE_SIZE, GFP_KERNEL);
 
-	if (!newldt)
-		return -ENOMEM;
-
-	if (oldsize)
-		memcpy(newldt, pc->ldt, oldsize * LDT_ENTRY_SIZE);
-	oldldt = pc->ldt;
-	memset(newldt + oldsize * LDT_ENTRY_SIZE, 0,
-	       (mincount - oldsize) * LDT_ENTRY_SIZE);
-
-	paravirt_alloc_ldt(newldt, mincount);
-
-#ifdef CONFIG_X86_64
-	/* CHECKME: Do we really need this ? */
-	wmb();
-#endif
-	pc->ldt = newldt;
-	wmb();
-	pc->size = mincount;
-	wmb();
-
-	if (reload) {
-#ifdef CONFIG_SMP
-		preempt_disable();
-		load_LDT(pc);
-		if (!cpumask_equal(mm_cpumask(current->mm),
-				   cpumask_of(smp_processor_id())))
-			smp_call_function(flush_ldt, current->mm, 1);
-		preempt_enable();
-#else
-		load_LDT(pc);
-#endif
+	if (!new_ldt->entries) {
+		kfree(new_ldt);
+		return NULL;
 	}
-	if (oldsize) {
-		paravirt_free_ldt(oldldt, oldsize);
-		if (oldsize * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(oldldt);
-		else
-			put_page(virt_to_page(oldldt));
-	}
-	return 0;
+
+	new_ldt->size = size;
+	return new_ldt;
 }
 
-static inline int copy_ldt(mm_context_t *new, mm_context_t *old)
+/* After calling this, the LDT is immutable. */
+static void finalize_ldt_struct(struct ldt_struct *ldt)
 {
-	int err = alloc_ldt(new, old->size, 0);
-	int i;
+	paravirt_alloc_ldt(ldt->entries, ldt->size);
+}
 
-	if (err < 0)
-		return err;
+/* context.lock is held */
+static void install_ldt(struct mm_struct *current_mm,
+			struct ldt_struct *ldt)
+{
+	/* Synchronizes with lockless_dereference in load_mm_ldt. */
+	smp_store_release(&current_mm->context.ldt, ldt);
 
-	for (i = 0; i < old->size; i++)
-		write_ldt_entry(new->ldt, i, old->ldt + i * LDT_ENTRY_SIZE);
-	return 0;
+	/* Activate the LDT for all CPUs using current_mm. */
+	on_each_cpu_mask(mm_cpumask(current_mm), flush_ldt, current_mm, true);
+}
+
+static void free_ldt_struct(struct ldt_struct *ldt)
+{
+	if (likely(!ldt))
+		return;
+
+	paravirt_free_ldt(ldt->entries, ldt->size);
+	if (ldt->size * LDT_ENTRY_SIZE > PAGE_SIZE)
+		vfree(ldt->entries);
+	else
+		kfree(ldt->entries);
+	kfree(ldt);
 }
 
 /*
@@ -104,17 +105,37 @@
  */
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	struct ldt_struct *new_ldt;
 	struct mm_struct *old_mm;
 	int retval = 0;
 
 	mutex_init(&mm->context.lock);
-	mm->context.size = 0;
 	old_mm = current->mm;
-	if (old_mm && old_mm->context.size > 0) {
-		mutex_lock(&old_mm->context.lock);
-		retval = copy_ldt(&mm->context, &old_mm->context);
-		mutex_unlock(&old_mm->context.lock);
+	if (!old_mm) {
+		mm->context.ldt = NULL;
+		return 0;
 	}
+
+	mutex_lock(&old_mm->context.lock);
+	if (!old_mm->context.ldt) {
+		mm->context.ldt = NULL;
+		goto out_unlock;
+	}
+
+	new_ldt = alloc_ldt_struct(old_mm->context.ldt->size);
+	if (!new_ldt) {
+		retval = -ENOMEM;
+		goto out_unlock;
+	}
+
+	memcpy(new_ldt->entries, old_mm->context.ldt->entries,
+	       new_ldt->size * LDT_ENTRY_SIZE);
+	finalize_ldt_struct(new_ldt);
+
+	mm->context.ldt = new_ldt;
+
+out_unlock:
+	mutex_unlock(&old_mm->context.lock);
 	return retval;
 }
 
@@ -125,53 +146,47 @@
  */
 void destroy_context(struct mm_struct *mm)
 {
-	if (mm->context.size) {
-#ifdef CONFIG_X86_32
-		/* CHECKME: Can this ever happen ? */
-		if (mm == current->active_mm)
-			clear_LDT();
-#endif
-		paravirt_free_ldt(mm->context.ldt, mm->context.size);
-		if (mm->context.size * LDT_ENTRY_SIZE > PAGE_SIZE)
-			vfree(mm->context.ldt);
-		else
-			put_page(virt_to_page(mm->context.ldt));
-		mm->context.size = 0;
-	}
+	free_ldt_struct(mm->context.ldt);
+	mm->context.ldt = NULL;
 }
 
 static int read_ldt(void __user *ptr, unsigned long bytecount)
 {
-	int err;
+	int retval;
 	unsigned long size;
 	struct mm_struct *mm = current->mm;
 
-	if (!mm->context.size)
-		return 0;
+	mutex_lock(&mm->context.lock);
+
+	if (!mm->context.ldt) {
+		retval = 0;
+		goto out_unlock;
+	}
+
 	if (bytecount > LDT_ENTRY_SIZE * LDT_ENTRIES)
 		bytecount = LDT_ENTRY_SIZE * LDT_ENTRIES;
 
-	mutex_lock(&mm->context.lock);
-	size = mm->context.size * LDT_ENTRY_SIZE;
+	size = mm->context.ldt->size * LDT_ENTRY_SIZE;
 	if (size > bytecount)
 		size = bytecount;
 
-	err = 0;
-	if (copy_to_user(ptr, mm->context.ldt, size))
-		err = -EFAULT;
-	mutex_unlock(&mm->context.lock);
-	if (err < 0)
-		goto error_return;
+	if (copy_to_user(ptr, mm->context.ldt->entries, size)) {
+		retval = -EFAULT;
+		goto out_unlock;
+	}
+
 	if (size != bytecount) {
-		/* zero-fill the rest */
-		if (clear_user(ptr + size, bytecount - size) != 0) {
-			err = -EFAULT;
-			goto error_return;
+		/* Zero-fill the rest and pretend we read bytecount bytes. */
+		if (clear_user(ptr + size, bytecount - size)) {
+			retval = -EFAULT;
+			goto out_unlock;
 		}
 	}
-	return bytecount;
-error_return:
-	return err;
+	retval = bytecount;
+
+out_unlock:
+	mutex_unlock(&mm->context.lock);
+	return retval;
 }
 
 static int read_default_ldt(void __user *ptr, unsigned long bytecount)
@@ -195,6 +210,8 @@
 	struct desc_struct ldt;
 	int error;
 	struct user_desc ldt_info;
+	int oldsize, newsize;
+	struct ldt_struct *new_ldt, *old_ldt;
 
 	error = -EINVAL;
 	if (bytecount != sizeof(ldt_info))
@@ -213,34 +230,39 @@
 			goto out;
 	}
 
-	mutex_lock(&mm->context.lock);
-	if (ldt_info.entry_number >= mm->context.size) {
-		error = alloc_ldt(&current->mm->context,
-				  ldt_info.entry_number + 1, 1);
-		if (error < 0)
-			goto out_unlock;
-	}
-
-	/* Allow LDTs to be cleared by the user. */
-	if (ldt_info.base_addr == 0 && ldt_info.limit == 0) {
-		if (oldmode || LDT_empty(&ldt_info)) {
-			memset(&ldt, 0, sizeof(ldt));
-			goto install;
+	if ((oldmode && !ldt_info.base_addr && !ldt_info.limit) ||
+	    LDT_empty(&ldt_info)) {
+		/* The user wants to clear the entry. */
+		memset(&ldt, 0, sizeof(ldt));
+	} else {
+		if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
+			error = -EINVAL;
+			goto out;
 		}
+
+		fill_ldt(&ldt, &ldt_info);
+		if (oldmode)
+			ldt.avl = 0;
 	}
 
-	if (!IS_ENABLED(CONFIG_X86_16BIT) && !ldt_info.seg_32bit) {
-		error = -EINVAL;
+	mutex_lock(&mm->context.lock);
+
+	old_ldt = mm->context.ldt;
+	oldsize = old_ldt ? old_ldt->size : 0;
+	newsize = max((int)(ldt_info.entry_number + 1), oldsize);
+
+	error = -ENOMEM;
+	new_ldt = alloc_ldt_struct(newsize);
+	if (!new_ldt)
 		goto out_unlock;
-	}
 
-	fill_ldt(&ldt, &ldt_info);
-	if (oldmode)
-		ldt.avl = 0;
+	if (old_ldt)
+		memcpy(new_ldt->entries, old_ldt->entries, oldsize * LDT_ENTRY_SIZE);
+	new_ldt->entries[ldt_info.entry_number] = ldt;
+	finalize_ldt_struct(new_ldt);
 
-	/* Install the new entry ...  */
-install:
-	write_ldt_entry(mm->context.ldt, ldt_info.entry_number, &ldt);
+	install_ldt(mm, new_ldt);
+	free_ldt_struct(old_ldt);
 	error = 0;
 
 out_unlock:
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 71d7849..f6b9163 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -121,11 +121,11 @@
 void release_thread(struct task_struct *dead_task)
 {
 	if (dead_task->mm) {
-		if (dead_task->mm->context.size) {
+		if (dead_task->mm->context.ldt) {
 			pr_warn("WARNING: dead process %s still has LDT? <%p/%d>\n",
 				dead_task->comm,
 				dead_task->mm->context.ldt,
-				dead_task->mm->context.size);
+				dead_task->mm->context.ldt->size);
 			BUG();
 		}
 	}
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 9b4d51d..6273324 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/ptrace.h>
 #include <asm/desc.h>
+#include <asm/mmu_context.h>
 
 unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs)
 {
@@ -30,10 +31,11 @@
 		seg &= ~7UL;
 
 		mutex_lock(&child->mm->context.lock);
-		if (unlikely((seg >> 3) >= child->mm->context.size))
+		if (unlikely(!child->mm->context.ldt ||
+			     (seg >> 3) >= child->mm->context.ldt->size))
 			addr = -1L; /* bogus selector, access would fault */
 		else {
-			desc = child->mm->context.ldt + seg;
+			desc = &child->mm->context.ldt->entries[seg];
 			base = get_desc_base(desc);
 
 			/* 16-bit code segment? */
diff --git a/arch/x86/kvm/mtrr.c b/arch/x86/kvm/mtrr.c
index dc0a84a..9e8bf13 100644
--- a/arch/x86/kvm/mtrr.c
+++ b/arch/x86/kvm/mtrr.c
@@ -672,16 +672,16 @@
 	if (iter.mtrr_disabled)
 		return mtrr_disabled_type();
 
+	/* not contained in any MTRRs. */
+	if (type == -1)
+		return mtrr_default_type(mtrr_state);
+
 	/*
 	 * We just check one page, partially covered by MTRRs is
 	 * impossible.
 	 */
 	WARN_ON(iter.partial_map);
 
-	/* not contained in any MTRRs. */
-	if (type == -1)
-		return mtrr_default_type(mtrr_state);
-
 	return type;
 }
 EXPORT_SYMBOL_GPL(kvm_mtrr_get_guest_memory_type);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 579a8fd..be2e7a2 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -269,7 +269,7 @@
 	EMIT4(0x48, 0x8B, 0x46,                   /* mov rax, qword ptr [rsi + 16] */
 	      offsetof(struct bpf_array, map.max_entries));
 	EMIT3(0x48, 0x39, 0xD0);                  /* cmp rax, rdx */
-#define OFFSET1 44 /* number of bytes to jump */
+#define OFFSET1 47 /* number of bytes to jump */
 	EMIT2(X86_JBE, OFFSET1);                  /* jbe out */
 	label1 = cnt;
 
@@ -278,15 +278,15 @@
 	 */
 	EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */
 	EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT);     /* cmp eax, MAX_TAIL_CALL_CNT */
-#define OFFSET2 33
+#define OFFSET2 36
 	EMIT2(X86_JA, OFFSET2);                   /* ja out */
 	label2 = cnt;
 	EMIT3(0x83, 0xC0, 0x01);                  /* add eax, 1 */
 	EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */
 
 	/* prog = array->prog[index]; */
-	EMIT4(0x48, 0x8D, 0x44, 0xD6);            /* lea rax, [rsi + rdx * 8 + 0x50] */
-	EMIT1(offsetof(struct bpf_array, prog));
+	EMIT4_off32(0x48, 0x8D, 0x84, 0xD6,       /* lea rax, [rsi + rdx * 8 + offsetof(...)] */
+		    offsetof(struct bpf_array, prog));
 	EMIT3(0x48, 0x8B, 0x00);                  /* mov rax, qword ptr [rax] */
 
 	/* if (prog == NULL)
diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c
index cfba30f..e4308fe 100644
--- a/arch/x86/platform/efi/efi.c
+++ b/arch/x86/platform/efi/efi.c
@@ -972,6 +972,11 @@
 
 static int __init arch_parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "old_map"))
 		set_bit(EFI_OLD_MEMMAP, &efi.flags);
 	if (parse_option_str(str, "debug"))
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 0d7dd1f..9ab5279 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -22,6 +22,7 @@
 #include <asm/fpu/internal.h>
 #include <asm/debugreg.h>
 #include <asm/cpu.h>
+#include <asm/mmu_context.h>
 
 #ifdef CONFIG_X86_32
 __visible unsigned long saved_context_ebx;
@@ -153,7 +154,7 @@
 	syscall_init();				/* This sets MSR_*STAR and related */
 #endif
 	load_TR_desc();				/* This does ltr */
-	load_LDT(&current->active_mm->context);	/* This does lldt */
+	load_mm_ldt(current->active_mm);	/* This does lldt */
 
 	fpu__resume_cpu();
 }
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 0b95c9b..11d6fb4 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -483,6 +483,7 @@
 	pte_t pte;
 	unsigned long pfn;
 	struct page *page;
+	unsigned char dummy;
 
 	ptep = lookup_address((unsigned long)v, &level);
 	BUG_ON(ptep == NULL);
@@ -492,6 +493,32 @@
 
 	pte = pfn_pte(pfn, prot);
 
+	/*
+	 * Careful: update_va_mapping() will fail if the virtual address
+	 * we're poking isn't populated in the page tables.  We don't
+	 * need to worry about the direct map (that's always in the page
+	 * tables), but we need to be careful about vmap space.  In
+	 * particular, the top level page table can lazily propagate
+	 * entries between processes, so if we've switched mms since we
+	 * vmapped the target in the first place, we might not have the
+	 * top-level page table entry populated.
+	 *
+	 * We disable preemption because we want the same mm active when
+	 * we probe the target and when we issue the hypercall.  We'll
+	 * have the same nominal mm, but if we're a kernel thread, lazy
+	 * mm dropping could change our pgd.
+	 *
+	 * Out of an abundance of caution, this uses __get_user() to fault
+	 * in the target address just in case there's some obscure case
+	 * in which the target address isn't readable.
+	 */
+
+	preempt_disable();
+
+	pagefault_disable();	/* Avoid warnings due to being atomic. */
+	__get_user(dummy, (unsigned char __user __force *)v);
+	pagefault_enable();
+
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();
 
@@ -503,6 +530,8 @@
 				BUG();
 	} else
 		kmap_flush_unused();
+
+	preempt_enable();
 }
 
 static void xen_alloc_ldt(struct desc_struct *ldt, unsigned entries)
@@ -510,6 +539,17 @@
 	const unsigned entries_per_page = PAGE_SIZE / LDT_ENTRY_SIZE;
 	int i;
 
+	/*
+	 * We need to mark the all aliases of the LDT pages RO.  We
+	 * don't need to call vm_flush_aliases(), though, since that's
+	 * only responsible for flushing aliases out the TLBs, not the
+	 * page tables, and Xen will flush the TLB for us if needed.
+	 *
+	 * To avoid confusing future readers: none of this is necessary
+	 * to load the LDT.  The hypervisor only checks this when the
+	 * LDT is faulted in due to subsequent descriptor access.
+	 */
+
 	for(i = 0; i < entries; i += entries_per_page)
 		set_aliased_prot(ldt + i, PAGE_KERNEL_RO);
 }
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 717afcd..88dbbb1 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -231,7 +231,7 @@
 		dev_warn(&device->dev, "Failed to change power state to %s\n",
 			 acpi_power_state_string(state));
 	} else {
-		device->power.state = state;
+		device->power.state = target_state;
 		ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 				  "Device [%s] transitioned to %s\n",
 				  device->pnp.bus_id,
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index d94529d..bc67a93 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -523,6 +523,7 @@
 #  define rbd_assert(expr)	((void) 0)
 #endif /* !RBD_DEBUG */
 
+static void rbd_osd_copyup_callback(struct rbd_obj_request *obj_request);
 static int rbd_img_obj_request_submit(struct rbd_obj_request *obj_request);
 static void rbd_img_parent_read(struct rbd_obj_request *obj_request);
 static void rbd_dev_remove_parent(struct rbd_device *rbd_dev);
@@ -1818,6 +1819,16 @@
 	obj_request_done_set(obj_request);
 }
 
+static void rbd_osd_call_callback(struct rbd_obj_request *obj_request)
+{
+	dout("%s: obj %p\n", __func__, obj_request);
+
+	if (obj_request_img_data_test(obj_request))
+		rbd_osd_copyup_callback(obj_request);
+	else
+		obj_request_done_set(obj_request);
+}
+
 static void rbd_osd_req_callback(struct ceph_osd_request *osd_req,
 				struct ceph_msg *msg)
 {
@@ -1866,6 +1877,8 @@
 		rbd_osd_discard_callback(obj_request);
 		break;
 	case CEPH_OSD_OP_CALL:
+		rbd_osd_call_callback(obj_request);
+		break;
 	case CEPH_OSD_OP_NOTIFY_ACK:
 	case CEPH_OSD_OP_WATCH:
 		rbd_osd_trivial_callback(obj_request);
@@ -2530,13 +2543,15 @@
 }
 
 static void
-rbd_img_obj_copyup_callback(struct rbd_obj_request *obj_request)
+rbd_osd_copyup_callback(struct rbd_obj_request *obj_request)
 {
 	struct rbd_img_request *img_request;
 	struct rbd_device *rbd_dev;
 	struct page **pages;
 	u32 page_count;
 
+	dout("%s: obj %p\n", __func__, obj_request);
+
 	rbd_assert(obj_request->type == OBJ_REQUEST_BIO ||
 		obj_request->type == OBJ_REQUEST_NODATA);
 	rbd_assert(obj_request_img_data_test(obj_request));
@@ -2563,9 +2578,7 @@
 	if (!obj_request->result)
 		obj_request->xferred = obj_request->length;
 
-	/* Finish up with the normal image object callback */
-
-	rbd_img_obj_callback(obj_request);
+	obj_request_done_set(obj_request);
 }
 
 static void
@@ -2650,7 +2663,6 @@
 
 	/* All set, send it off. */
 
-	orig_request->callback = rbd_img_obj_copyup_callback;
 	osdc = &rbd_dev->rbd_client->client->osdc;
 	img_result = rbd_obj_request_submit(osdc, orig_request);
 	if (!img_result)
diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
index da8faf7..5643b65 100644
--- a/drivers/char/hw_random/core.c
+++ b/drivers/char/hw_random/core.c
@@ -429,7 +429,7 @@
 static void start_khwrngd(void)
 {
 	hwrng_fill = kthread_run(hwrng_fillfn, NULL, "hwrng");
-	if (hwrng_fill == ERR_PTR(-ENOMEM)) {
+	if (IS_ERR(hwrng_fill)) {
 		pr_err("hwrng_fill thread creation failed");
 		hwrng_fill = NULL;
 	}
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 26063af..7a3c30c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -1002,7 +1002,7 @@
 	int ret = 0;
 
 	/* Some related CPUs might not be present (physically hotplugged) */
-	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+	for_each_cpu(j, policy->real_cpus) {
 		if (j == policy->kobj_cpu)
 			continue;
 
@@ -1019,7 +1019,7 @@
 	unsigned int j;
 
 	/* Some related CPUs might not be present (physically hotplugged) */
-	for_each_cpu_and(j, policy->related_cpus, cpu_present_mask) {
+	for_each_cpu(j, policy->real_cpus) {
 		if (j == policy->kobj_cpu)
 			continue;
 
@@ -1163,11 +1163,14 @@
 	if (!zalloc_cpumask_var(&policy->related_cpus, GFP_KERNEL))
 		goto err_free_cpumask;
 
+	if (!zalloc_cpumask_var(&policy->real_cpus, GFP_KERNEL))
+		goto err_free_rcpumask;
+
 	ret = kobject_init_and_add(&policy->kobj, &ktype_cpufreq, &dev->kobj,
 				   "cpufreq");
 	if (ret) {
 		pr_err("%s: failed to init policy->kobj: %d\n", __func__, ret);
-		goto err_free_rcpumask;
+		goto err_free_real_cpus;
 	}
 
 	INIT_LIST_HEAD(&policy->policy_list);
@@ -1184,6 +1187,8 @@
 
 	return policy;
 
+err_free_real_cpus:
+	free_cpumask_var(policy->real_cpus);
 err_free_rcpumask:
 	free_cpumask_var(policy->related_cpus);
 err_free_cpumask:
@@ -1234,6 +1239,7 @@
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 
 	cpufreq_policy_put_kobj(policy, notify);
+	free_cpumask_var(policy->real_cpus);
 	free_cpumask_var(policy->related_cpus);
 	free_cpumask_var(policy->cpus);
 	kfree(policy);
@@ -1258,14 +1264,17 @@
 
 	pr_debug("adding CPU %u\n", cpu);
 
-	/*
-	 * Only possible if 'cpu' wasn't physically present earlier and we are
-	 * here from subsys_interface add callback. A hotplug notifier will
-	 * follow and we will handle it like logical CPU hotplug then. For now,
-	 * just create the sysfs link.
-	 */
-	if (cpu_is_offline(cpu))
-		return add_cpu_dev_symlink(per_cpu(cpufreq_cpu_data, cpu), cpu);
+	if (cpu_is_offline(cpu)) {
+		/*
+		 * Only possible if we are here from the subsys_interface add
+		 * callback.  A hotplug notifier will follow and we will handle
+		 * it as CPU online then.  For now, just create the sysfs link,
+		 * unless there is no policy or the link is already present.
+		 */
+		policy = per_cpu(cpufreq_cpu_data, cpu);
+		return policy && !cpumask_test_and_set_cpu(cpu, policy->real_cpus)
+			? add_cpu_dev_symlink(policy, cpu) : 0;
+	}
 
 	if (!down_read_trylock(&cpufreq_rwsem))
 		return 0;
@@ -1307,6 +1316,10 @@
 	/* related cpus should atleast have policy->cpus */
 	cpumask_or(policy->related_cpus, policy->related_cpus, policy->cpus);
 
+	/* Remember which CPUs have been present at the policy creation time. */
+	if (!recover_policy)
+		cpumask_and(policy->real_cpus, policy->cpus, cpu_present_mask);
+
 	/*
 	 * affected cpus must always be the one, which are online. We aren't
 	 * managing offline cpus here.
@@ -1420,8 +1433,7 @@
 	return ret;
 }
 
-static int __cpufreq_remove_dev_prepare(struct device *dev,
-					struct subsys_interface *sif)
+static int __cpufreq_remove_dev_prepare(struct device *dev)
 {
 	unsigned int cpu = dev->id;
 	int ret = 0;
@@ -1437,10 +1449,8 @@
 
 	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_STOP);
-		if (ret) {
+		if (ret)
 			pr_err("%s: Failed to stop governor\n", __func__);
-			return ret;
-		}
 	}
 
 	down_write(&policy->rwsem);
@@ -1473,8 +1483,7 @@
 	return ret;
 }
 
-static int __cpufreq_remove_dev_finish(struct device *dev,
-				       struct subsys_interface *sif)
+static int __cpufreq_remove_dev_finish(struct device *dev)
 {
 	unsigned int cpu = dev->id;
 	int ret;
@@ -1492,10 +1501,8 @@
 	/* If cpu is last user of policy, free policy */
 	if (has_target()) {
 		ret = __cpufreq_governor(policy, CPUFREQ_GOV_POLICY_EXIT);
-		if (ret) {
+		if (ret)
 			pr_err("%s: Failed to exit governor\n", __func__);
-			return ret;
-		}
 	}
 
 	/*
@@ -1506,10 +1513,6 @@
 	if (cpufreq_driver->exit)
 		cpufreq_driver->exit(policy);
 
-	/* Free the policy only if the driver is getting removed. */
-	if (sif)
-		cpufreq_policy_free(policy, true);
-
 	return 0;
 }
 
@@ -1521,42 +1524,41 @@
 static int cpufreq_remove_dev(struct device *dev, struct subsys_interface *sif)
 {
 	unsigned int cpu = dev->id;
-	int ret;
+	struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
 
-	/*
-	 * Only possible if 'cpu' is getting physically removed now. A hotplug
-	 * notifier should have already been called and we just need to remove
-	 * link or free policy here.
-	 */
-	if (cpu_is_offline(cpu)) {
-		struct cpufreq_policy *policy = per_cpu(cpufreq_cpu_data, cpu);
-		struct cpumask mask;
+	if (!policy)
+		return 0;
 
-		if (!policy)
-			return 0;
+	if (cpu_online(cpu)) {
+		__cpufreq_remove_dev_prepare(dev);
+		__cpufreq_remove_dev_finish(dev);
+	}
 
-		cpumask_copy(&mask, policy->related_cpus);
-		cpumask_clear_cpu(cpu, &mask);
+	cpumask_clear_cpu(cpu, policy->real_cpus);
 
-		/*
-		 * Free policy only if all policy->related_cpus are removed
-		 * physically.
-		 */
-		if (cpumask_intersects(&mask, cpu_present_mask)) {
-			remove_cpu_dev_symlink(policy, cpu);
-			return 0;
-		}
-
+	if (cpumask_empty(policy->real_cpus)) {
 		cpufreq_policy_free(policy, true);
 		return 0;
 	}
 
-	ret = __cpufreq_remove_dev_prepare(dev, sif);
+	if (cpu != policy->kobj_cpu) {
+		remove_cpu_dev_symlink(policy, cpu);
+	} else {
+		/*
+		 * The CPU owning the policy object is going away.  Move it to
+		 * another suitable CPU.
+		 */
+		unsigned int new_cpu = cpumask_first(policy->real_cpus);
+		struct device *new_dev = get_cpu_device(new_cpu);
 
-	if (!ret)
-		ret = __cpufreq_remove_dev_finish(dev, sif);
+		dev_dbg(dev, "%s: Moving policy object to CPU%u\n", __func__, new_cpu);
 
-	return ret;
+		sysfs_remove_link(&new_dev->kobj, "cpufreq");
+		policy->kobj_cpu = new_cpu;
+		WARN_ON(kobject_move(&policy->kobj, &new_dev->kobj));
+	}
+
+	return 0;
 }
 
 static void handle_update(struct work_struct *work)
@@ -2395,11 +2397,11 @@
 			break;
 
 		case CPU_DOWN_PREPARE:
-			__cpufreq_remove_dev_prepare(dev, NULL);
+			__cpufreq_remove_dev_prepare(dev);
 			break;
 
 		case CPU_POST_DEAD:
-			__cpufreq_remove_dev_finish(dev, NULL);
+			__cpufreq_remove_dev_finish(dev);
 			break;
 
 		case CPU_DOWN_FAILED:
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 15ada47..fcb929e 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -681,6 +681,7 @@
 		.get_max = core_get_max_pstate,
 		.get_min = core_get_min_pstate,
 		.get_turbo = knl_get_turbo_pstate,
+		.get_scaling = core_get_scaling,
 		.set = core_set_pstate,
 	},
 };
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index 7ba495f..402631a 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -905,7 +905,6 @@
 		crypt->mode |= NPE_OP_NOT_IN_PLACE;
 		/* This was never tested by Intel
 		 * for more than one dst buffer, I think. */
-		BUG_ON(req->dst->length < nbytes);
 		req_ctx->dst = NULL;
 		if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook,
 					flags, DMA_FROM_DEVICE))
diff --git a/drivers/crypto/qat/qat_common/qat_algs.c b/drivers/crypto/qat/qat_common/qat_algs.c
index 067402c..df427c0 100644
--- a/drivers/crypto/qat/qat_common/qat_algs.c
+++ b/drivers/crypto/qat/qat_common/qat_algs.c
@@ -73,7 +73,8 @@
 				       ICP_QAT_HW_CIPHER_KEY_CONVERT, \
 				       ICP_QAT_HW_CIPHER_DECRYPT)
 
-static atomic_t active_dev;
+static DEFINE_MUTEX(algs_lock);
+static unsigned int active_devs;
 
 struct qat_alg_buf {
 	uint32_t len;
@@ -1280,7 +1281,10 @@
 
 int qat_algs_register(void)
 {
-	if (atomic_add_return(1, &active_dev) == 1) {
+	int ret = 0;
+
+	mutex_lock(&algs_lock);
+	if (++active_devs == 1) {
 		int i;
 
 		for (i = 0; i < ARRAY_SIZE(qat_algs); i++)
@@ -1289,21 +1293,25 @@
 				CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC :
 				CRYPTO_ALG_TYPE_ABLKCIPHER | CRYPTO_ALG_ASYNC;
 
-		return crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
+		ret = crypto_register_algs(qat_algs, ARRAY_SIZE(qat_algs));
 	}
-	return 0;
+	mutex_unlock(&algs_lock);
+	return ret;
 }
 
 int qat_algs_unregister(void)
 {
-	if (atomic_sub_return(1, &active_dev) == 0)
-		return crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
-	return 0;
+	int ret = 0;
+
+	mutex_lock(&algs_lock);
+	if (--active_devs == 0)
+		ret = crypto_unregister_algs(qat_algs, ARRAY_SIZE(qat_algs));
+	mutex_unlock(&algs_lock);
+	return ret;
 }
 
 int qat_algs_init(void)
 {
-	atomic_set(&active_dev, 0);
 	crypto_get_default_rng();
 	return 0;
 }
diff --git a/drivers/dma/at_hdmac.c b/drivers/dma/at_hdmac.c
index 59892126..d3629b7 100644
--- a/drivers/dma/at_hdmac.c
+++ b/drivers/dma/at_hdmac.c
@@ -48,6 +48,8 @@
 	BIT(DMA_SLAVE_BUSWIDTH_2_BYTES) |\
 	BIT(DMA_SLAVE_BUSWIDTH_4_BYTES))
 
+#define ATC_MAX_DSCR_TRIALS	10
+
 /*
  * Initial number of descriptors to allocate for each channel. This could
  * be increased during dma usage.
@@ -285,28 +287,19 @@
  *
  * @current_len: the number of bytes left before reading CTRLA
  * @ctrla: the value of CTRLA
- * @desc: the descriptor containing the transfer width
  */
-static inline int atc_calc_bytes_left(int current_len, u32 ctrla,
-					struct at_desc *desc)
+static inline int atc_calc_bytes_left(int current_len, u32 ctrla)
 {
-	return current_len - ((ctrla & ATC_BTSIZE_MAX) << desc->tx_width);
-}
+	u32 btsize = (ctrla & ATC_BTSIZE_MAX);
+	u32 src_width = ATC_REG_TO_SRC_WIDTH(ctrla);
 
-/**
- * atc_calc_bytes_left_from_reg - calculates the number of bytes left according
- * to the current value of CTRLA.
- *
- * @current_len: the number of bytes left before reading CTRLA
- * @atchan: the channel to read CTRLA for
- * @desc: the descriptor containing the transfer width
- */
-static inline int atc_calc_bytes_left_from_reg(int current_len,
-			struct at_dma_chan *atchan, struct at_desc *desc)
-{
-	u32 ctrla = channel_readl(atchan, CTRLA);
-
-	return atc_calc_bytes_left(current_len, ctrla, desc);
+	/*
+	 * According to the datasheet, when reading the Control A Register
+	 * (ctrla), the Buffer Transfer Size (btsize) bitfield refers to the
+	 * number of transfers completed on the Source Interface.
+	 * So btsize is always a number of source width transfers.
+	 */
+	return current_len - (btsize << src_width);
 }
 
 /**
@@ -320,7 +313,7 @@
 	struct at_desc *desc_first = atc_first_active(atchan);
 	struct at_desc *desc;
 	int ret;
-	u32 ctrla, dscr;
+	u32 ctrla, dscr, trials;
 
 	/*
 	 * If the cookie doesn't match to the currently running transfer then
@@ -346,15 +339,82 @@
 		 * the channel's DSCR register and compare it against the value
 		 * of the hardware linked list structure of each child
 		 * descriptor.
+		 *
+		 * The CTRLA register provides us with the amount of data
+		 * already read from the source for the current child
+		 * descriptor. So we can compute a more accurate residue by also
+		 * removing the number of bytes corresponding to this amount of
+		 * data.
+		 *
+		 * However, the DSCR and CTRLA registers cannot be read both
+		 * atomically. Hence a race condition may occur: the first read
+		 * register may refer to one child descriptor whereas the second
+		 * read may refer to a later child descriptor in the list
+		 * because of the DMA transfer progression inbetween the two
+		 * reads.
+		 *
+		 * One solution could have been to pause the DMA transfer, read
+		 * the DSCR and CTRLA then resume the DMA transfer. Nonetheless,
+		 * this approach presents some drawbacks:
+		 * - If the DMA transfer is paused, RX overruns or TX underruns
+		 *   are more likey to occur depending on the system latency.
+		 *   Taking the USART driver as an example, it uses a cyclic DMA
+		 *   transfer to read data from the Receive Holding Register
+		 *   (RHR) to avoid RX overruns since the RHR is not protected
+		 *   by any FIFO on most Atmel SoCs. So pausing the DMA transfer
+		 *   to compute the residue would break the USART driver design.
+		 * - The atc_pause() function masks interrupts but we'd rather
+		 *   avoid to do so for system latency purpose.
+		 *
+		 * Then we'd rather use another solution: the DSCR is read a
+		 * first time, the CTRLA is read in turn, next the DSCR is read
+		 * a second time. If the two consecutive read values of the DSCR
+		 * are the same then we assume both refers to the very same
+		 * child descriptor as well as the CTRLA value read inbetween
+		 * does. For cyclic tranfers, the assumption is that a full loop
+		 * is "not so fast".
+		 * If the two DSCR values are different, we read again the CTRLA
+		 * then the DSCR till two consecutive read values from DSCR are
+		 * equal or till the maxium trials is reach.
+		 * This algorithm is very unlikely not to find a stable value for
+		 * DSCR.
 		 */
 
-		ctrla = channel_readl(atchan, CTRLA);
-		rmb(); /* ensure CTRLA is read before DSCR */
 		dscr = channel_readl(atchan, DSCR);
+		rmb(); /* ensure DSCR is read before CTRLA */
+		ctrla = channel_readl(atchan, CTRLA);
+		for (trials = 0; trials < ATC_MAX_DSCR_TRIALS; ++trials) {
+			u32 new_dscr;
+
+			rmb(); /* ensure DSCR is read after CTRLA */
+			new_dscr = channel_readl(atchan, DSCR);
+
+			/*
+			 * If the DSCR register value has not changed inside the
+			 * DMA controller since the previous read, we assume
+			 * that both the dscr and ctrla values refers to the
+			 * very same descriptor.
+			 */
+			if (likely(new_dscr == dscr))
+				break;
+
+			/*
+			 * DSCR has changed inside the DMA controller, so the
+			 * previouly read value of CTRLA may refer to an already
+			 * processed descriptor hence could be outdated.
+			 * We need to update ctrla to match the current
+			 * descriptor.
+			 */
+			dscr = new_dscr;
+			rmb(); /* ensure DSCR is read before CTRLA */
+			ctrla = channel_readl(atchan, CTRLA);
+		}
+		if (unlikely(trials >= ATC_MAX_DSCR_TRIALS))
+			return -ETIMEDOUT;
 
 		/* for the first descriptor we can be more accurate */
 		if (desc_first->lli.dscr == dscr)
-			return atc_calc_bytes_left(ret, ctrla, desc_first);
+			return atc_calc_bytes_left(ret, ctrla);
 
 		ret -= desc_first->len;
 		list_for_each_entry(desc, &desc_first->tx_list, desc_node) {
@@ -365,16 +425,14 @@
 		}
 
 		/*
-		 * For the last descriptor in the chain we can calculate
+		 * For the current descriptor in the chain we can calculate
 		 * the remaining bytes using the channel's register.
-		 * Note that the transfer width of the first and last
-		 * descriptor may differ.
 		 */
-		if (!desc->lli.dscr)
-			ret = atc_calc_bytes_left_from_reg(ret, atchan, desc);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	} else {
 		/* single transfer */
-		ret = atc_calc_bytes_left_from_reg(ret, atchan, desc_first);
+		ctrla = channel_readl(atchan, CTRLA);
+		ret = atc_calc_bytes_left(ret, ctrla);
 	}
 
 	return ret;
@@ -726,7 +784,6 @@
 
 	desc->txd.cookie = -EBUSY;
 	desc->total_len = desc->len = len;
-	desc->tx_width = dwidth;
 
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
@@ -804,10 +861,6 @@
 	first->txd.cookie = -EBUSY;
 	first->total_len = len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = src_width;
-	prev->tx_width = src_width;
-
 	/* set end-of-link to the last link descriptor of list*/
 	set_desc_eol(desc);
 
@@ -956,10 +1009,6 @@
 	first->txd.cookie = -EBUSY;
 	first->total_len = total_len;
 
-	/* set transfer width for the calculation of the residue */
-	first->tx_width = reg_width;
-	prev->tx_width = reg_width;
-
 	/* first link descriptor of list is responsible of flags */
 	first->txd.flags = flags; /* client is in control of this ack */
 
@@ -1077,12 +1126,6 @@
 		desc->txd.cookie = 0;
 		desc->len = len;
 
-		/*
-		 * Although we only need the transfer width for the first and
-		 * the last descriptor, its easier to set it to all descriptors.
-		 */
-		desc->tx_width = src_width;
-
 		atc_desc_chain(&first, &prev, desc);
 
 		/* update the lengths and addresses for the next loop cycle */
@@ -1256,7 +1299,6 @@
 	/* First descriptor of the chain embedds additional information */
 	first->txd.cookie = -EBUSY;
 	first->total_len = buf_len;
-	first->tx_width = reg_width;
 
 	return &first->txd;
 
diff --git a/drivers/dma/at_hdmac_regs.h b/drivers/dma/at_hdmac_regs.h
index bc8d5eb..7f5a082 100644
--- a/drivers/dma/at_hdmac_regs.h
+++ b/drivers/dma/at_hdmac_regs.h
@@ -112,6 +112,7 @@
 #define		ATC_SRC_WIDTH_BYTE	(0x0 << 24)
 #define		ATC_SRC_WIDTH_HALFWORD	(0x1 << 24)
 #define		ATC_SRC_WIDTH_WORD	(0x2 << 24)
+#define		ATC_REG_TO_SRC_WIDTH(r)	(((r) >> 24) & 0x3)
 #define	ATC_DST_WIDTH_MASK	(0x3 << 28)	/* Destination Single Transfer Size */
 #define		ATC_DST_WIDTH(x)	((x) << 28)
 #define		ATC_DST_WIDTH_BYTE	(0x0 << 28)
@@ -182,7 +183,6 @@
  * @txd: support for the async_tx api
  * @desc_node: node on the channed descriptors list
  * @len: descriptor byte count
- * @tx_width: transfer width
  * @total_len: total transaction byte count
  */
 struct at_desc {
@@ -194,7 +194,6 @@
 	struct dma_async_tx_descriptor	txd;
 	struct list_head		desc_node;
 	size_t				len;
-	u32				tx_width;
 	size_t				total_len;
 
 	/* Interleaved data */
diff --git a/drivers/dma/at_xdmac.c b/drivers/dma/at_xdmac.c
index cf1213d..40afa2a 100644
--- a/drivers/dma/at_xdmac.c
+++ b/drivers/dma/at_xdmac.c
@@ -359,18 +359,19 @@
 	 * descriptor view 2 since some fields of the configuration register
 	 * depend on transfer size and src/dest addresses.
 	 */
-	if (at_xdmac_chan_is_cyclic(atchan)) {
+	if (at_xdmac_chan_is_cyclic(atchan))
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV1;
-		at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
-	} else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3) {
+	else if (first->lld.mbr_ubc & AT_XDMAC_MBR_UBC_NDV3)
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV3;
-	} else {
-		/*
-		 * No need to write AT_XDMAC_CC reg, it will be done when the
-		 * descriptor is fecthed.
-		 */
+	else
 		reg = AT_XDMAC_CNDC_NDVIEW_NDV2;
-	}
+	/*
+	 * Even if the register will be updated from the configuration in the
+	 * descriptor when using view 2 or higher, the PROT bit won't be set
+	 * properly. This bit can be modified only by using the channel
+	 * configuration register.
+	 */
+	at_xdmac_chan_write(atchan, AT_XDMAC_CC, first->lld.mbr_cfg);
 
 	reg |= AT_XDMAC_CNDC_NDDUP
 	       | AT_XDMAC_CNDC_NDSUP
@@ -681,15 +682,16 @@
 			desc->lld.mbr_sa = mem;
 			desc->lld.mbr_da = atchan->sconfig.dst_addr;
 		}
-		desc->lld.mbr_cfg = atchan->cfg;
-		dwidth = at_xdmac_get_dwidth(desc->lld.mbr_cfg);
+		dwidth = at_xdmac_get_dwidth(atchan->cfg);
 		fixed_dwidth = IS_ALIGNED(len, 1 << dwidth)
-			       ? at_xdmac_get_dwidth(desc->lld.mbr_cfg)
+			       ? dwidth
 			       : AT_XDMAC_CC_DWIDTH_BYTE;
 		desc->lld.mbr_ubc = AT_XDMAC_MBR_UBC_NDV2			/* next descriptor view */
 			| AT_XDMAC_MBR_UBC_NDEN					/* next descriptor dst parameter update */
 			| AT_XDMAC_MBR_UBC_NSEN					/* next descriptor src parameter update */
 			| (len >> fixed_dwidth);				/* microblock length */
+		desc->lld.mbr_cfg = (atchan->cfg & ~AT_XDMAC_CC_DWIDTH_MASK) |
+				    AT_XDMAC_CC_DWIDTH(fixed_dwidth);
 		dev_dbg(chan2dev(chan),
 			 "%s: lld: mbr_sa=%pad, mbr_da=%pad, mbr_ubc=0x%08x\n",
 			 __func__, &desc->lld.mbr_sa, &desc->lld.mbr_da, desc->lld.mbr_ubc);
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index fbaf1ea..f1325f6 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -162,10 +162,11 @@
 	config &= ~0x7;
 	config |= op_mode;
 
-	if (IS_ENABLED(__BIG_ENDIAN))
-		config |= XOR_DESCRIPTOR_SWAP;
-	else
-		config &= ~XOR_DESCRIPTOR_SWAP;
+#if defined(__BIG_ENDIAN)
+	config |= XOR_DESCRIPTOR_SWAP;
+#else
+	config &= ~XOR_DESCRIPTOR_SWAP;
+#endif
 
 	writel_relaxed(config, XOR_CONFIG(chan));
 	chan->current_type = type;
diff --git a/drivers/dma/pl330.c b/drivers/dma/pl330.c
index f513f77..ecab4ea0 100644
--- a/drivers/dma/pl330.c
+++ b/drivers/dma/pl330.c
@@ -2328,7 +2328,7 @@
 			desc->txd.callback = last->txd.callback;
 			desc->txd.callback_param = last->txd.callback_param;
 		}
-		last->last = false;
+		desc->last = false;
 
 		dma_cookie_assign(&desc->txd);
 
@@ -2623,6 +2623,7 @@
 		desc->rqcfg.brst_len = 1;
 
 	desc->rqcfg.brst_len = get_burst_len(desc, len);
+	desc->bytes_requested = len;
 
 	desc->txd.flags = flags;
 
diff --git a/drivers/dma/virt-dma.c b/drivers/dma/virt-dma.c
index 7d2c17d..6f80432 100644
--- a/drivers/dma/virt-dma.c
+++ b/drivers/dma/virt-dma.c
@@ -29,7 +29,7 @@
 	spin_lock_irqsave(&vc->lock, flags);
 	cookie = dma_cookie_assign(tx);
 
-	list_move_tail(&vd->node, &vc->desc_submitted);
+	list_add_tail(&vd->node, &vc->desc_submitted);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	dev_dbg(vc->chan.device->dev, "vchan %p: txd %p[%x]: submitted\n",
@@ -83,10 +83,8 @@
 		cb_data = vd->tx.callback_param;
 
 		list_del(&vd->node);
-		if (async_tx_test_ack(&vd->tx))
-			list_add(&vd->node, &vc->desc_allocated);
-		else
-			vc->desc_free(vd);
+
+		vc->desc_free(vd);
 
 		if (cb)
 			cb(cb_data);
@@ -98,13 +96,9 @@
 	while (!list_empty(head)) {
 		struct virt_dma_desc *vd = list_first_entry(head,
 			struct virt_dma_desc, node);
-		if (async_tx_test_ack(&vd->tx)) {
-			list_move_tail(&vd->node, &vc->desc_allocated);
-		} else {
-			dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
-			list_del(&vd->node);
-			vc->desc_free(vd);
-		}
+		list_del(&vd->node);
+		dev_dbg(vc->chan.device->dev, "txd %p: freeing\n", vd);
+		vc->desc_free(vd);
 	}
 }
 EXPORT_SYMBOL_GPL(vchan_dma_desc_free_list);
@@ -114,7 +108,6 @@
 	dma_cookie_init(&vc->chan);
 
 	spin_lock_init(&vc->lock);
-	INIT_LIST_HEAD(&vc->desc_allocated);
 	INIT_LIST_HEAD(&vc->desc_submitted);
 	INIT_LIST_HEAD(&vc->desc_issued);
 	INIT_LIST_HEAD(&vc->desc_completed);
diff --git a/drivers/dma/virt-dma.h b/drivers/dma/virt-dma.h
index 189e75d..181b952 100644
--- a/drivers/dma/virt-dma.h
+++ b/drivers/dma/virt-dma.h
@@ -29,7 +29,6 @@
 	spinlock_t lock;
 
 	/* protected by vc.lock */
-	struct list_head desc_allocated;
 	struct list_head desc_submitted;
 	struct list_head desc_issued;
 	struct list_head desc_completed;
@@ -56,16 +55,11 @@
 	struct virt_dma_desc *vd, unsigned long tx_flags)
 {
 	extern dma_cookie_t vchan_tx_submit(struct dma_async_tx_descriptor *);
-	unsigned long flags;
 
 	dma_async_tx_descriptor_init(&vd->tx, &vc->chan);
 	vd->tx.flags = tx_flags;
 	vd->tx.tx_submit = vchan_tx_submit;
 
-	spin_lock_irqsave(&vc->lock, flags);
-	list_add_tail(&vd->node, &vc->desc_allocated);
-	spin_unlock_irqrestore(&vc->lock, flags);
-
 	return &vd->tx;
 }
 
@@ -128,8 +122,7 @@
 }
 
 /**
- * vchan_get_all_descriptors - obtain all allocated, submitted and issued
- *                             descriptors
+ * vchan_get_all_descriptors - obtain all submitted and issued descriptors
  * vc: virtual channel to get descriptors from
  * head: list of descriptors found
  *
@@ -141,7 +134,6 @@
 static inline void vchan_get_all_descriptors(struct virt_dma_chan *vc,
 	struct list_head *head)
 {
-	list_splice_tail_init(&vc->desc_allocated, head);
 	list_splice_tail_init(&vc->desc_submitted, head);
 	list_splice_tail_init(&vc->desc_issued, head);
 	list_splice_tail_init(&vc->desc_completed, head);
@@ -149,14 +141,11 @@
 
 static inline void vchan_free_chan_resources(struct virt_dma_chan *vc)
 {
-	struct virt_dma_desc *vd;
 	unsigned long flags;
 	LIST_HEAD(head);
 
 	spin_lock_irqsave(&vc->lock, flags);
 	vchan_get_all_descriptors(vc, &head);
-	list_for_each_entry(vd, &head, node)
-		async_tx_clear_ack(&vd->tx);
 	spin_unlock_irqrestore(&vc->lock, flags);
 
 	vchan_dma_desc_free_list(vc, &head);
diff --git a/drivers/dma/xgene-dma.c b/drivers/dma/xgene-dma.c
index 620fd55ec..dff22ab 100644
--- a/drivers/dma/xgene-dma.c
+++ b/drivers/dma/xgene-dma.c
@@ -111,6 +111,7 @@
 #define XGENE_DMA_MEM_RAM_SHUTDOWN		0xD070
 #define XGENE_DMA_BLK_MEM_RDY			0xD074
 #define XGENE_DMA_BLK_MEM_RDY_VAL		0xFFFFFFFF
+#define XGENE_DMA_RING_CMD_SM_OFFSET		0x8000
 
 /* X-Gene SoC EFUSE csr register and bit defination */
 #define XGENE_SOC_JTAG1_SHADOW			0x18
@@ -1887,6 +1888,8 @@
 		return -ENOMEM;
 	}
 
+	pdma->csr_ring_cmd += XGENE_DMA_RING_CMD_SM_OFFSET;
+
 	/* Get efuse csr region */
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 3);
 	if (!res) {
diff --git a/drivers/extcon/extcon-palmas.c b/drivers/extcon/extcon-palmas.c
index 080d5cc..eebdf2a 100644
--- a/drivers/extcon/extcon-palmas.c
+++ b/drivers/extcon/extcon-palmas.c
@@ -200,7 +200,6 @@
 	status = devm_extcon_dev_register(&pdev->dev, palmas_usb->edev);
 	if (status) {
 		dev_err(&pdev->dev, "failed to register extcon device\n");
-		kfree(palmas_usb->edev->name);
 		return status;
 	}
 
@@ -214,7 +213,6 @@
 		if (status < 0) {
 			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->id_irq, status);
-			kfree(palmas_usb->edev->name);
 			return status;
 		}
 	}
@@ -229,7 +227,6 @@
 		if (status < 0) {
 			dev_err(&pdev->dev, "can't get IRQ %d, err %d\n",
 					palmas_usb->vbus_irq, status);
-			kfree(palmas_usb->edev->name);
 			return status;
 		}
 	}
@@ -239,15 +236,6 @@
 	return 0;
 }
 
-static int palmas_usb_remove(struct platform_device *pdev)
-{
-	struct palmas_usb *palmas_usb = platform_get_drvdata(pdev);
-
-	kfree(palmas_usb->edev->name);
-
-	return 0;
-}
-
 #ifdef CONFIG_PM_SLEEP
 static int palmas_usb_suspend(struct device *dev)
 {
@@ -288,7 +276,6 @@
 
 static struct platform_driver palmas_usb_driver = {
 	.probe = palmas_usb_probe,
-	.remove = palmas_usb_remove,
 	.driver = {
 		.name = "palmas-usb",
 		.of_match_table = of_palmas_match_tbl,
diff --git a/drivers/extcon/extcon.c b/drivers/extcon/extcon.c
index 76157ab..43b57b0 100644
--- a/drivers/extcon/extcon.c
+++ b/drivers/extcon/extcon.c
@@ -124,25 +124,35 @@
 	return -EINVAL;
 }
 
-static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
+static int find_cable_id_by_name(struct extcon_dev *edev, const char *name)
 {
-	unsigned int id = EXTCON_NONE;
+	unsigned int id = -EINVAL;
 	int i = 0;
 
-	if (edev->max_supported == 0)
-		return -EINVAL;
-
-	/* Find the the number of extcon cable */
+	/* Find the id of extcon cable */
 	while (extcon_name[i]) {
 		if (!strncmp(extcon_name[i], name, CABLE_NAME_MAX)) {
 			id = i;
 			break;
 		}
+		i++;
 	}
 
-	if (id == EXTCON_NONE)
+	return id;
+}
+
+static int find_cable_index_by_name(struct extcon_dev *edev, const char *name)
+{
+	unsigned int id;
+
+	if (edev->max_supported == 0)
 		return -EINVAL;
 
+	/* Find the the number of extcon cable */
+	id = find_cable_id_by_name(edev, name);
+	if (id < 0)
+		return id;
+
 	return find_cable_index_by_id(edev, id);
 }
 
@@ -228,9 +238,11 @@
 	struct extcon_cable *cable = container_of(attr, struct extcon_cable,
 						  attr_state);
 
+	int i = cable->cable_index;
+
 	return sprintf(buf, "%d\n",
 		       extcon_get_cable_state_(cable->edev,
-					       cable->cable_index));
+					       cable->edev->supported_cable[i]));
 }
 
 /**
@@ -263,20 +275,25 @@
 	spin_lock_irqsave(&edev->lock, flags);
 
 	if (edev->state != ((edev->state & ~mask) | (state & mask))) {
+		u32 old_state;
+
 		if (check_mutually_exclusive(edev, (edev->state & ~mask) |
 						   (state & mask))) {
 			spin_unlock_irqrestore(&edev->lock, flags);
 			return -EPERM;
 		}
 
-		for (index = 0; index < edev->max_supported; index++) {
-			if (is_extcon_changed(edev->state, state, index, &attached))
-				raw_notifier_call_chain(&edev->nh[index], attached, edev);
-		}
-
+		old_state = edev->state;
 		edev->state &= ~mask;
 		edev->state |= state & mask;
 
+		for (index = 0; index < edev->max_supported; index++) {
+			if (is_extcon_changed(old_state, edev->state, index,
+					      &attached))
+				raw_notifier_call_chain(&edev->nh[index],
+							attached, edev);
+		}
+
 		/* This could be in interrupt handler */
 		prop_buf = (char *)get_zeroed_page(GFP_ATOMIC);
 		if (prop_buf) {
@@ -361,8 +378,13 @@
  */
 int extcon_get_cable_state(struct extcon_dev *edev, const char *cable_name)
 {
-	return extcon_get_cable_state_(edev, find_cable_index_by_name
-						(edev, cable_name));
+	unsigned int id;
+
+	id = find_cable_id_by_name(edev, cable_name);
+	if (id < 0)
+		return id;
+
+	return extcon_get_cable_state_(edev, id);
 }
 EXPORT_SYMBOL_GPL(extcon_get_cable_state);
 
@@ -404,8 +426,13 @@
 int extcon_set_cable_state(struct extcon_dev *edev,
 			const char *cable_name, bool cable_state)
 {
-	return extcon_set_cable_state_(edev, find_cable_index_by_name
-					(edev, cable_name), cable_state);
+	unsigned int id;
+
+	id = find_cable_id_by_name(edev, cable_name);
+	if (id < 0)
+		return id;
+
+	return extcon_set_cable_state_(edev, id, cable_state);
 }
 EXPORT_SYMBOL_GPL(extcon_set_cable_state);
 
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index 9fa8084..d6144e3 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -58,6 +58,11 @@
 
 static int __init parse_efi_cmdline(char *str)
 {
+	if (!str) {
+		pr_warn("need at least one option\n");
+		return -EINVAL;
+	}
+
 	if (parse_option_str(str, "noruntime"))
 		disable_runtime = true;
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
index e9fde72..f7b49d5 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h
@@ -1130,6 +1130,9 @@
 	uint32_t			me_feature_version;
 	uint32_t			ce_feature_version;
 	uint32_t			pfp_feature_version;
+	uint32_t			rlc_feature_version;
+	uint32_t			mec_feature_version;
+	uint32_t			mec2_feature_version;
 	struct amdgpu_ring		gfx_ring[AMDGPU_MAX_GFX_RINGS];
 	unsigned			num_gfx_rings;
 	struct amdgpu_ring		compute_ring[AMDGPU_MAX_COMPUTE_RINGS];
@@ -1639,6 +1642,7 @@
 	/* SDMA firmware */
 	const struct firmware	*fw;
 	uint32_t		fw_version;
+	uint32_t		feature_version;
 
 	struct amdgpu_ring	ring;
 };
@@ -1866,6 +1870,12 @@
 typedef uint32_t (*amdgpu_block_rreg_t)(struct amdgpu_device*, uint32_t, uint32_t);
 typedef void (*amdgpu_block_wreg_t)(struct amdgpu_device*, uint32_t, uint32_t, uint32_t);
 
+struct amdgpu_ip_block_status {
+	bool valid;
+	bool sw;
+	bool hw;
+};
+
 struct amdgpu_device {
 	struct device			*dev;
 	struct drm_device		*ddev;
@@ -2008,7 +2018,7 @@
 
 	const struct amdgpu_ip_block_version *ip_blocks;
 	int				num_ip_blocks;
-	bool				*ip_block_enabled;
+	struct amdgpu_ip_block_status	*ip_block_status;
 	struct mutex	mn_lock;
 	DECLARE_HASHTABLE(mn_hash, 7);
 
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index d79009b..99f158e 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -1191,8 +1191,9 @@
 		return -EINVAL;
 	}
 
-	adev->ip_block_enabled = kcalloc(adev->num_ip_blocks, sizeof(bool), GFP_KERNEL);
-	if (adev->ip_block_enabled == NULL)
+	adev->ip_block_status = kcalloc(adev->num_ip_blocks,
+					sizeof(struct amdgpu_ip_block_status), GFP_KERNEL);
+	if (adev->ip_block_status == NULL)
 		return -ENOMEM;
 
 	if (adev->ip_blocks == NULL) {
@@ -1203,18 +1204,18 @@
 	for (i = 0; i < adev->num_ip_blocks; i++) {
 		if ((amdgpu_ip_block_mask & (1 << i)) == 0) {
 			DRM_ERROR("disabled ip block: %d\n", i);
-			adev->ip_block_enabled[i] = false;
+			adev->ip_block_status[i].valid = false;
 		} else {
 			if (adev->ip_blocks[i].funcs->early_init) {
 				r = adev->ip_blocks[i].funcs->early_init((void *)adev);
 				if (r == -ENOENT)
-					adev->ip_block_enabled[i] = false;
+					adev->ip_block_status[i].valid = false;
 				else if (r)
 					return r;
 				else
-					adev->ip_block_enabled[i] = true;
+					adev->ip_block_status[i].valid = true;
 			} else {
-				adev->ip_block_enabled[i] = true;
+				adev->ip_block_status[i].valid = true;
 			}
 		}
 	}
@@ -1227,11 +1228,12 @@
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		r = adev->ip_blocks[i].funcs->sw_init((void *)adev);
 		if (r)
 			return r;
+		adev->ip_block_status[i].sw = true;
 		/* need to do gmc hw init early so we can allocate gpu mem */
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) {
 			r = amdgpu_vram_scratch_init(adev);
@@ -1243,11 +1245,12 @@
 			r = amdgpu_wb_init(adev);
 			if (r)
 				return r;
+			adev->ip_block_status[i].hw = true;
 		}
 	}
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].sw)
 			continue;
 		/* gmc hw init is done early */
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC)
@@ -1255,6 +1258,7 @@
 		r = adev->ip_blocks[i].funcs->hw_init((void *)adev);
 		if (r)
 			return r;
+		adev->ip_block_status[i].hw = true;
 	}
 
 	return 0;
@@ -1265,7 +1269,7 @@
 	int i = 0, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		/* enable clockgating to save power */
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
@@ -1287,7 +1291,7 @@
 	int i, r;
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].hw)
 			continue;
 		if (adev->ip_blocks[i].type == AMD_IP_BLOCK_TYPE_GMC) {
 			amdgpu_wb_fini(adev);
@@ -1300,14 +1304,16 @@
 			return r;
 		r = adev->ip_blocks[i].funcs->hw_fini((void *)adev);
 		/* XXX handle errors */
+		adev->ip_block_status[i].hw = false;
 	}
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].sw)
 			continue;
 		r = adev->ip_blocks[i].funcs->sw_fini((void *)adev);
 		/* XXX handle errors */
-		adev->ip_block_enabled[i] = false;
+		adev->ip_block_status[i].sw = false;
+		adev->ip_block_status[i].valid = false;
 	}
 
 	return 0;
@@ -1318,7 +1324,7 @@
 	int i, r;
 
 	for (i = adev->num_ip_blocks - 1; i >= 0; i--) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		/* ungate blocks so that suspend can properly shut them down */
 		r = adev->ip_blocks[i].funcs->set_clockgating_state((void *)adev,
@@ -1336,7 +1342,7 @@
 	int i, r;
 
 	for (i = 0; i < adev->num_ip_blocks; i++) {
-		if (!adev->ip_block_enabled[i])
+		if (!adev->ip_block_status[i].valid)
 			continue;
 		r = adev->ip_blocks[i].funcs->resume(adev);
 		if (r)
@@ -1582,8 +1588,8 @@
 	amdgpu_fence_driver_fini(adev);
 	amdgpu_fbdev_fini(adev);
 	r = amdgpu_fini(adev);
-	kfree(adev->ip_block_enabled);
-	adev->ip_block_enabled = NULL;
+	kfree(adev->ip_block_status);
+	adev->ip_block_status = NULL;
 	adev->accel_working = false;
 	/* free i2c buses */
 	amdgpu_i2c_fini(adev);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
index ae43b58..4afc507 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
@@ -449,7 +449,7 @@
  * vital here, so they are not reported back to userspace.
  */
 static void amdgpu_gem_va_update_vm(struct amdgpu_device *adev,
-				    struct amdgpu_bo_va *bo_va)
+				    struct amdgpu_bo_va *bo_va, uint32_t operation)
 {
 	struct ttm_validate_buffer tv, *entry;
 	struct amdgpu_bo_list_entry *vm_bos;
@@ -485,7 +485,9 @@
 	if (r)
 		goto error_unlock;
 
-	r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem);
+
+	if (operation == AMDGPU_VA_OP_MAP)
+		r = amdgpu_vm_bo_update(adev, bo_va, &bo_va->bo->tbo.mem);
 
 error_unlock:
 	mutex_unlock(&bo_va->vm->mutex);
@@ -580,7 +582,7 @@
 	}
 
 	if (!r && !(args->flags & AMDGPU_VM_DELAY_UPDATE))
-		amdgpu_gem_va_update_vm(adev, bo_va);
+		amdgpu_gem_va_update_vm(adev, bo_va, args->operation);
 
 	drm_gem_object_unreference_unlocked(gobj);
 	return r;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
index 52dff75..bc0fac6 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ib.c
@@ -180,17 +180,17 @@
 	if (vm) {
 		/* do context switch */
 		amdgpu_vm_flush(ring, vm, ib->sync.last_vm_update);
+
+		if (ring->funcs->emit_gds_switch)
+			amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id,
+						    ib->gds_base, ib->gds_size,
+						    ib->gws_base, ib->gws_size,
+						    ib->oa_base, ib->oa_size);
+
+		if (ring->funcs->emit_hdp_flush)
+			amdgpu_ring_emit_hdp_flush(ring);
 	}
 
-	if (vm && ring->funcs->emit_gds_switch)
-		amdgpu_ring_emit_gds_switch(ring, ib->vm->ids[ring->idx].id,
-					    ib->gds_base, ib->gds_size,
-					    ib->gws_base, ib->gws_size,
-					    ib->oa_base, ib->oa_size);
-
-	if (ring->funcs->emit_hdp_flush)
-		amdgpu_ring_emit_hdp_flush(ring);
-
 	old_ctx = ring->current_ctx;
 	for (i = 0; i < num_ibs; ++i) {
 		ib = &ibs[i];
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
index 31ad444..3bfe67d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
@@ -235,7 +235,7 @@
 
 		for (i = 0; i < adev->num_ip_blocks; i++) {
 			if (adev->ip_blocks[i].type == type &&
-			    adev->ip_block_enabled[i]) {
+			    adev->ip_block_status[i].valid) {
 				ip.hw_ip_version_major = adev->ip_blocks[i].major;
 				ip.hw_ip_version_minor = adev->ip_blocks[i].minor;
 				ip.capabilities_flags = 0;
@@ -274,7 +274,7 @@
 
 		for (i = 0; i < adev->num_ip_blocks; i++)
 			if (adev->ip_blocks[i].type == type &&
-			    adev->ip_block_enabled[i] &&
+			    adev->ip_block_status[i].valid &&
 			    count < AMDGPU_HW_IP_INSTANCE_MAX_COUNT)
 				count++;
 
@@ -317,16 +317,17 @@
 			break;
 		case AMDGPU_INFO_FW_GFX_RLC:
 			fw_info.ver = adev->gfx.rlc_fw_version;
-			fw_info.feature = 0;
+			fw_info.feature = adev->gfx.rlc_feature_version;
 			break;
 		case AMDGPU_INFO_FW_GFX_MEC:
-			if (info->query_fw.index == 0)
+			if (info->query_fw.index == 0) {
 				fw_info.ver = adev->gfx.mec_fw_version;
-			else if (info->query_fw.index == 1)
+				fw_info.feature = adev->gfx.mec_feature_version;
+			} else if (info->query_fw.index == 1) {
 				fw_info.ver = adev->gfx.mec2_fw_version;
-			else
+				fw_info.feature = adev->gfx.mec2_feature_version;
+			} else
 				return -EINVAL;
-			fw_info.feature = 0;
 			break;
 		case AMDGPU_INFO_FW_SMC:
 			fw_info.ver = adev->pm.fw_version;
@@ -336,7 +337,7 @@
 			if (info->query_fw.index >= 2)
 				return -EINVAL;
 			fw_info.ver = adev->sdma[info->query_fw.index].fw_version;
-			fw_info.feature = 0;
+			fw_info.feature = adev->sdma[info->query_fw.index].feature_version;
 			break;
 		default:
 			return -EINVAL;
@@ -416,7 +417,7 @@
 		return n ? -EFAULT : 0;
 	}
 	case AMDGPU_INFO_DEV_INFO: {
-		struct drm_amdgpu_info_device dev_info;
+		struct drm_amdgpu_info_device dev_info = {};
 		struct amdgpu_cu_info cu_info;
 
 		dev_info.device_id = dev->pdev->device;
diff --git a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
index ab83cc1..15df46c 100644
--- a/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
+++ b/drivers/gpu/drm/amd/amdgpu/cik_sdma.c
@@ -500,6 +500,7 @@
 		amdgpu_ucode_print_sdma_hdr(&hdr->header);
 		fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
 		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+		adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
 		fw_data = (const __le32 *)
 			(adev->sdma[i].fw->data + le32_to_cpu(hdr->header.ucode_array_offset_bytes));
 		WREG32(mmSDMA0_UCODE_ADDR + sdma_offsets[i], 0);
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
index 2c188fb..0d8bf2c 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v7_0.c
@@ -2561,7 +2561,7 @@
  * sheduling on the ring.  This function schedules the IB
  * on the gfx ring for execution by the GPU.
  */
-static void gfx_v7_0_ring_emit_ib(struct amdgpu_ring *ring,
+static void gfx_v7_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib)
 {
 	bool need_ctx_switch = ring->current_ctx != ib->ctx;
@@ -2569,15 +2569,10 @@
 	u32 next_rptr = ring->wptr + 5;
 
 	/* drop the CE preamble IB for the same context */
-	if ((ring->type == AMDGPU_RING_TYPE_GFX) &&
-	    (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
-	    !need_ctx_switch)
+	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
 		return;
 
-	if (ring->type == AMDGPU_RING_TYPE_COMPUTE)
-		control |= INDIRECT_BUFFER_VALID;
-
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX)
+	if (need_ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -2588,7 +2583,7 @@
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) {
+	if (need_ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -2611,6 +2606,35 @@
 	amdgpu_ring_write(ring, control);
 }
 
+static void gfx_v7_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib)
+{
+	u32 header, control = 0;
+	u32 next_rptr = ring->wptr + 5;
+
+	control |= INDIRECT_BUFFER_VALID;
+	next_rptr += 4;
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
+	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+	amdgpu_ring_write(ring, next_rptr);
+
+	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
+
+	control |= ib->length_dw |
+			   (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0);
+
+	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring,
+#ifdef __BIG_ENDIAN
+					  (2 << 0) |
+#endif
+					  (ib->gpu_addr & 0xFFFFFFFC));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
+	amdgpu_ring_write(ring, control);
+}
+
 /**
  * gfx_v7_0_ring_test_ib - basic ring IB test
  *
@@ -3056,6 +3080,8 @@
 	mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
 	amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
 	adev->gfx.mec_fw_version = le32_to_cpu(mec_hdr->header.ucode_version);
+	adev->gfx.mec_feature_version = le32_to_cpu(
+					mec_hdr->ucode_feature_version);
 
 	gfx_v7_0_cp_compute_enable(adev, false);
 
@@ -3078,6 +3104,8 @@
 		mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data;
 		amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header);
 		adev->gfx.mec2_fw_version = le32_to_cpu(mec2_hdr->header.ucode_version);
+		adev->gfx.mec2_feature_version = le32_to_cpu(
+				mec2_hdr->ucode_feature_version);
 
 		/* MEC2 */
 		fw_data = (const __le32 *)
@@ -4042,6 +4070,8 @@
 	hdr = (const struct rlc_firmware_header_v1_0 *)adev->gfx.rlc_fw->data;
 	amdgpu_ucode_print_rlc_hdr(&hdr->header);
 	adev->gfx.rlc_fw_version = le32_to_cpu(hdr->header.ucode_version);
+	adev->gfx.rlc_feature_version = le32_to_cpu(
+					hdr->ucode_feature_version);
 
 	gfx_v7_0_rlc_stop(adev);
 
@@ -5098,7 +5128,7 @@
 		dev_info(adev->dev, "  CP_HPD_EOP_CONTROL=0x%08X\n",
 			 RREG32(mmCP_HPD_EOP_CONTROL));
 
-		for (queue = 0; queue < 8; i++) {
+		for (queue = 0; queue < 8; queue++) {
 			cik_srbm_select(adev, me, pipe, queue, 0);
 			dev_info(adev->dev, "  queue: %d\n", queue);
 			dev_info(adev->dev, "  CP_PQ_WPTR_POLL_CNTL=0x%08X\n",
@@ -5555,7 +5585,7 @@
 	.get_wptr = gfx_v7_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v7_0_ring_set_wptr_gfx,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v7_0_ring_emit_ib,
+	.emit_ib = gfx_v7_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v7_0_ring_emit_fence_gfx,
 	.emit_semaphore = gfx_v7_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v7_0_ring_emit_vm_flush,
@@ -5571,7 +5601,7 @@
 	.get_wptr = gfx_v7_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v7_0_ring_set_wptr_compute,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v7_0_ring_emit_ib,
+	.emit_ib = gfx_v7_0_ring_emit_ib_compute,
 	.emit_fence = gfx_v7_0_ring_emit_fence_compute,
 	.emit_semaphore = gfx_v7_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v7_0_ring_emit_vm_flush,
diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
index 1c7c992..f5a42ab 100644
--- a/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/gfx_v8_0.c
@@ -587,6 +587,7 @@
 	int err;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
+	const struct gfx_firmware_header_v1_0 *cp_hdr;
 
 	DRM_DEBUG("\n");
 
@@ -611,6 +612,9 @@
 	err = amdgpu_ucode_validate(adev->gfx.pfp_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.pfp_fw->data;
+	adev->gfx.pfp_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.pfp_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_me.bin", chip_name);
 	err = request_firmware(&adev->gfx.me_fw, fw_name, adev->dev);
@@ -619,6 +623,9 @@
 	err = amdgpu_ucode_validate(adev->gfx.me_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.me_fw->data;
+	adev->gfx.me_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.me_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_ce.bin", chip_name);
 	err = request_firmware(&adev->gfx.ce_fw, fw_name, adev->dev);
@@ -627,12 +634,18 @@
 	err = amdgpu_ucode_validate(adev->gfx.ce_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.ce_fw->data;
+	adev->gfx.ce_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.ce_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_rlc.bin", chip_name);
 	err = request_firmware(&adev->gfx.rlc_fw, fw_name, adev->dev);
 	if (err)
 		goto out;
 	err = amdgpu_ucode_validate(adev->gfx.rlc_fw);
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.rlc_fw->data;
+	adev->gfx.rlc_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.rlc_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec_fw, fw_name, adev->dev);
@@ -641,6 +654,9 @@
 	err = amdgpu_ucode_validate(adev->gfx.mec_fw);
 	if (err)
 		goto out;
+	cp_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
+	adev->gfx.mec_fw_version = le32_to_cpu(cp_hdr->header.ucode_version);
+	adev->gfx.mec_feature_version = le32_to_cpu(cp_hdr->ucode_feature_version);
 
 	snprintf(fw_name, sizeof(fw_name), "amdgpu/%s_mec2.bin", chip_name);
 	err = request_firmware(&adev->gfx.mec2_fw, fw_name, adev->dev);
@@ -648,6 +664,12 @@
 		err = amdgpu_ucode_validate(adev->gfx.mec2_fw);
 		if (err)
 			goto out;
+		cp_hdr = (const struct gfx_firmware_header_v1_0 *)
+						adev->gfx.mec2_fw->data;
+		adev->gfx.mec2_fw_version = le32_to_cpu(
+						cp_hdr->header.ucode_version);
+		adev->gfx.mec2_feature_version = le32_to_cpu(
+						cp_hdr->ucode_feature_version);
 	} else {
 		err = 0;
 		adev->gfx.mec2_fw = NULL;
@@ -1983,6 +2005,7 @@
 		adev->gfx.config.max_shader_engines = 1;
 		adev->gfx.config.max_tile_pipes = 2;
 		adev->gfx.config.max_sh_per_se = 1;
+		adev->gfx.config.max_backends_per_se = 2;
 
 		switch (adev->pdev->revision) {
 		case 0xc4:
@@ -1991,7 +2014,6 @@
 		case 0xcc:
 			/* B10 */
 			adev->gfx.config.max_cu_per_sh = 8;
-			adev->gfx.config.max_backends_per_se = 2;
 			break;
 		case 0xc5:
 		case 0x81:
@@ -2000,14 +2022,12 @@
 		case 0xcd:
 			/* B8 */
 			adev->gfx.config.max_cu_per_sh = 6;
-			adev->gfx.config.max_backends_per_se = 2;
 			break;
 		case 0xc6:
 		case 0xca:
 		case 0xce:
 			/* B6 */
 			adev->gfx.config.max_cu_per_sh = 6;
-			adev->gfx.config.max_backends_per_se = 2;
 			break;
 		case 0xc7:
 		case 0x87:
@@ -2015,7 +2035,6 @@
 		default:
 			/* B4 */
 			adev->gfx.config.max_cu_per_sh = 4;
-			adev->gfx.config.max_backends_per_se = 1;
 			break;
 		}
 
@@ -2275,7 +2294,6 @@
 
 	hdr = (const struct rlc_firmware_header_v2_0 *)adev->gfx.rlc_fw->data;
 	amdgpu_ucode_print_rlc_hdr(&hdr->header);
-	adev->gfx.rlc_fw_version = le32_to_cpu(hdr->header.ucode_version);
 
 	fw_data = (const __le32 *)(adev->gfx.rlc_fw->data +
 			   le32_to_cpu(hdr->header.ucode_array_offset_bytes));
@@ -2361,12 +2379,6 @@
 	amdgpu_ucode_print_gfx_hdr(&pfp_hdr->header);
 	amdgpu_ucode_print_gfx_hdr(&ce_hdr->header);
 	amdgpu_ucode_print_gfx_hdr(&me_hdr->header);
-	adev->gfx.pfp_fw_version = le32_to_cpu(pfp_hdr->header.ucode_version);
-	adev->gfx.ce_fw_version = le32_to_cpu(ce_hdr->header.ucode_version);
-	adev->gfx.me_fw_version = le32_to_cpu(me_hdr->header.ucode_version);
-	adev->gfx.me_feature_version = le32_to_cpu(me_hdr->ucode_feature_version);
-	adev->gfx.ce_feature_version = le32_to_cpu(ce_hdr->ucode_feature_version);
-	adev->gfx.pfp_feature_version = le32_to_cpu(pfp_hdr->ucode_feature_version);
 
 	gfx_v8_0_cp_gfx_enable(adev, false);
 
@@ -2622,7 +2634,6 @@
 
 	mec_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec_fw->data;
 	amdgpu_ucode_print_gfx_hdr(&mec_hdr->header);
-	adev->gfx.mec_fw_version = le32_to_cpu(mec_hdr->header.ucode_version);
 
 	fw_data = (const __le32 *)
 		(adev->gfx.mec_fw->data +
@@ -2641,7 +2652,6 @@
 
 		mec2_hdr = (const struct gfx_firmware_header_v1_0 *)adev->gfx.mec2_fw->data;
 		amdgpu_ucode_print_gfx_hdr(&mec2_hdr->header);
-		adev->gfx.mec2_fw_version = le32_to_cpu(mec2_hdr->header.ucode_version);
 
 		fw_data = (const __le32 *)
 			(adev->gfx.mec2_fw->data +
@@ -3753,7 +3763,7 @@
 	amdgpu_ring_write(ring, 0x20); /* poll interval */
 }
 
-static void gfx_v8_0_ring_emit_ib(struct amdgpu_ring *ring,
+static void gfx_v8_0_ring_emit_ib_gfx(struct amdgpu_ring *ring,
 				  struct amdgpu_ib *ib)
 {
 	bool need_ctx_switch = ring->current_ctx != ib->ctx;
@@ -3761,15 +3771,10 @@
 	u32 next_rptr = ring->wptr + 5;
 
 	/* drop the CE preamble IB for the same context */
-	if ((ring->type == AMDGPU_RING_TYPE_GFX) &&
-	    (ib->flags & AMDGPU_IB_FLAG_PREAMBLE) &&
-	    !need_ctx_switch)
+	if ((ib->flags & AMDGPU_IB_FLAG_PREAMBLE) && !need_ctx_switch)
 		return;
 
-	if (ring->type == AMDGPU_RING_TYPE_COMPUTE)
-		control |= INDIRECT_BUFFER_VALID;
-
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX)
+	if (need_ctx_switch)
 		next_rptr += 2;
 
 	next_rptr += 4;
@@ -3780,7 +3785,7 @@
 	amdgpu_ring_write(ring, next_rptr);
 
 	/* insert SWITCH_BUFFER packet before first IB in the ring frame */
-	if (need_ctx_switch && ring->type == AMDGPU_RING_TYPE_GFX) {
+	if (need_ctx_switch) {
 		amdgpu_ring_write(ring, PACKET3(PACKET3_SWITCH_BUFFER, 0));
 		amdgpu_ring_write(ring, 0);
 	}
@@ -3803,6 +3808,36 @@
 	amdgpu_ring_write(ring, control);
 }
 
+static void gfx_v8_0_ring_emit_ib_compute(struct amdgpu_ring *ring,
+				  struct amdgpu_ib *ib)
+{
+	u32 header, control = 0;
+	u32 next_rptr = ring->wptr + 5;
+
+	control |= INDIRECT_BUFFER_VALID;
+
+	next_rptr += 4;
+	amdgpu_ring_write(ring, PACKET3(PACKET3_WRITE_DATA, 3));
+	amdgpu_ring_write(ring, WRITE_DATA_DST_SEL(5) | WR_CONFIRM);
+	amdgpu_ring_write(ring, ring->next_rptr_gpu_addr & 0xfffffffc);
+	amdgpu_ring_write(ring, upper_32_bits(ring->next_rptr_gpu_addr) & 0xffffffff);
+	amdgpu_ring_write(ring, next_rptr);
+
+	header = PACKET3(PACKET3_INDIRECT_BUFFER, 2);
+
+	control |= ib->length_dw |
+			   (ib->vm ? (ib->vm->ids[ring->idx].id << 24) : 0);
+
+	amdgpu_ring_write(ring, header);
+	amdgpu_ring_write(ring,
+#ifdef __BIG_ENDIAN
+					  (2 << 0) |
+#endif
+					  (ib->gpu_addr & 0xFFFFFFFC));
+	amdgpu_ring_write(ring, upper_32_bits(ib->gpu_addr) & 0xFFFF);
+	amdgpu_ring_write(ring, control);
+}
+
 static void gfx_v8_0_ring_emit_fence_gfx(struct amdgpu_ring *ring, u64 addr,
 					 u64 seq, unsigned flags)
 {
@@ -4224,7 +4259,7 @@
 	.get_wptr = gfx_v8_0_ring_get_wptr_gfx,
 	.set_wptr = gfx_v8_0_ring_set_wptr_gfx,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v8_0_ring_emit_ib,
+	.emit_ib = gfx_v8_0_ring_emit_ib_gfx,
 	.emit_fence = gfx_v8_0_ring_emit_fence_gfx,
 	.emit_semaphore = gfx_v8_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v8_0_ring_emit_vm_flush,
@@ -4240,7 +4275,7 @@
 	.get_wptr = gfx_v8_0_ring_get_wptr_compute,
 	.set_wptr = gfx_v8_0_ring_set_wptr_compute,
 	.parse_cs = NULL,
-	.emit_ib = gfx_v8_0_ring_emit_ib,
+	.emit_ib = gfx_v8_0_ring_emit_ib_compute,
 	.emit_fence = gfx_v8_0_ring_emit_fence_compute,
 	.emit_semaphore = gfx_v8_0_ring_emit_semaphore,
 	.emit_vm_flush = gfx_v8_0_ring_emit_vm_flush,
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
index d789588..a988dfb 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v2_4.c
@@ -121,6 +121,7 @@
 	int err, i;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
+	const struct sdma_firmware_header_v1_0 *hdr;
 
 	DRM_DEBUG("\n");
 
@@ -142,6 +143,9 @@
 		err = amdgpu_ucode_validate(adev->sdma[i].fw);
 		if (err)
 			goto out;
+		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
+		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+		adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
 
 		if (adev->firmware.smu_load) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
@@ -541,8 +545,6 @@
 			hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
 			amdgpu_ucode_print_sdma_hdr(&hdr->header);
 			fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
-			adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
-
 			fw_data = (const __le32 *)
 				(adev->sdma[i].fw->data +
 				 le32_to_cpu(hdr->header.ucode_array_offset_bytes));
diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
index 7bb37b9..2b86569 100644
--- a/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
+++ b/drivers/gpu/drm/amd/amdgpu/sdma_v3_0.c
@@ -159,6 +159,7 @@
 	int err, i;
 	struct amdgpu_firmware_info *info = NULL;
 	const struct common_firmware_header *header = NULL;
+	const struct sdma_firmware_header_v1_0 *hdr;
 
 	DRM_DEBUG("\n");
 
@@ -183,6 +184,9 @@
 		err = amdgpu_ucode_validate(adev->sdma[i].fw);
 		if (err)
 			goto out;
+		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
+		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
+		adev->sdma[i].feature_version = le32_to_cpu(hdr->ucode_feature_version);
 
 		if (adev->firmware.smu_load) {
 			info = &adev->firmware.ucode[AMDGPU_UCODE_ID_SDMA0 + i];
@@ -630,8 +634,6 @@
 		hdr = (const struct sdma_firmware_header_v1_0 *)adev->sdma[i].fw->data;
 		amdgpu_ucode_print_sdma_hdr(&hdr->header);
 		fw_size = le32_to_cpu(hdr->header.ucode_size_bytes) / 4;
-		adev->sdma[i].fw_version = le32_to_cpu(hdr->header.ucode_version);
-
 		fw_data = (const __le32 *)
 			(adev->sdma[i].fw->data +
 				le32_to_cpu(hdr->header.ucode_array_offset_bytes));
diff --git a/drivers/gpu/drm/drm_atomic_helper.c b/drivers/gpu/drm/drm_atomic_helper.c
index 5b59d5ad..9dcc728 100644
--- a/drivers/gpu/drm/drm_atomic_helper.c
+++ b/drivers/gpu/drm/drm_atomic_helper.c
@@ -196,7 +196,12 @@
 	}
 
 	funcs = connector->helper_private;
-	new_encoder = funcs->best_encoder(connector);
+
+	if (funcs->atomic_best_encoder)
+		new_encoder = funcs->atomic_best_encoder(connector,
+							 connector_state);
+	else
+		new_encoder = funcs->best_encoder(connector);
 
 	if (!new_encoder) {
 		DRM_DEBUG_ATOMIC("No suitable encoder found for [CONNECTOR:%d:%s]\n",
@@ -229,6 +234,9 @@
 		}
 	}
 
+	if (WARN_ON(!connector_state->crtc))
+		return -EINVAL;
+
 	connector_state->best_encoder = new_encoder;
 	idx = drm_crtc_index(connector_state->crtc);
 
diff --git a/drivers/gpu/drm/drm_dp_mst_topology.c b/drivers/gpu/drm/drm_dp_mst_topology.c
index 778bbb6..b0487c9 100644
--- a/drivers/gpu/drm/drm_dp_mst_topology.c
+++ b/drivers/gpu/drm/drm_dp_mst_topology.c
@@ -1294,7 +1294,6 @@
 				goto retry;
 			}
 			DRM_DEBUG_KMS("failed to dpcd write %d %d\n", tosend, ret);
-			WARN(1, "fail\n");
 
 			return -EIO;
 		}
diff --git a/drivers/gpu/drm/drm_irq.c b/drivers/gpu/drm/drm_irq.c
index f9cc68f..b50fa0a 100644
--- a/drivers/gpu/drm/drm_irq.c
+++ b/drivers/gpu/drm/drm_irq.c
@@ -75,7 +75,7 @@
 module_param_named(timestamp_monotonic, drm_timestamp_monotonic, int, 0600);
 
 static void store_vblank(struct drm_device *dev, int crtc,
-			 unsigned vblank_count_inc,
+			 u32 vblank_count_inc,
 			 struct timeval *t_vblank)
 {
 	struct drm_vblank_crtc *vblank = &dev->vblank[crtc];
diff --git a/drivers/gpu/drm/i2c/tda998x_drv.c b/drivers/gpu/drm/i2c/tda998x_drv.c
index fe1599d..424228b 100644
--- a/drivers/gpu/drm/i2c/tda998x_drv.c
+++ b/drivers/gpu/drm/i2c/tda998x_drv.c
@@ -606,8 +606,6 @@
 tda998x_write_if(struct tda998x_priv *priv, uint8_t bit, uint16_t addr,
 		 uint8_t *buf, size_t size)
 {
-	buf[PB(0)] = tda998x_cksum(buf, size);
-
 	reg_clear(priv, REG_DIP_IF_FLAGS, bit);
 	reg_write_range(priv, addr, buf, size);
 	reg_set(priv, REG_DIP_IF_FLAGS, bit);
@@ -627,6 +625,8 @@
 	buf[PB(4)] = p->audio_frame[4];
 	buf[PB(5)] = p->audio_frame[5] & 0xf8; /* DM_INH + LSV */
 
+	buf[PB(0)] = tda998x_cksum(buf, sizeof(buf));
+
 	tda998x_write_if(priv, DIP_IF_FLAGS_IF4, REG_IF4_HB0, buf,
 			 sizeof(buf));
 }
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 5f27290..fd1de45 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -3303,15 +3303,14 @@
 #define I915_READ64(reg)	dev_priv->uncore.funcs.mmio_readq(dev_priv, (reg), true)
 
 #define I915_READ64_2x32(lower_reg, upper_reg) ({			\
-		u32 upper = I915_READ(upper_reg);			\
-		u32 lower = I915_READ(lower_reg);			\
-		u32 tmp = I915_READ(upper_reg);				\
-		if (upper != tmp) {					\
-			upper = tmp;					\
-			lower = I915_READ(lower_reg);			\
-			WARN_ON(I915_READ(upper_reg) != upper);		\
-		}							\
-		(u64)upper << 32 | lower; })
+	u32 upper, lower, tmp;						\
+	tmp = I915_READ(upper_reg);					\
+	do {								\
+		upper = tmp;						\
+		lower = I915_READ(lower_reg);				\
+		tmp = I915_READ(upper_reg);				\
+	} while (upper != tmp);						\
+	(u64)upper << 32 | lower; })
 
 #define POSTING_READ(reg)	(void)I915_READ_NOTRACE(reg)
 #define POSTING_READ16(reg)	(void)I915_READ16_NOTRACE(reg)
diff --git a/drivers/gpu/drm/i915/i915_gem_gtt.c b/drivers/gpu/drm/i915/i915_gem_gtt.c
index 56b52a4..31e8269 100644
--- a/drivers/gpu/drm/i915/i915_gem_gtt.c
+++ b/drivers/gpu/drm/i915/i915_gem_gtt.c
@@ -1923,6 +1923,17 @@
 		vma->vm->insert_entries(vma->vm, pages,
 					vma->node.start,
 					cache_level, pte_flags);
+
+		/* Note the inconsistency here is due to absence of the
+		 * aliasing ppgtt on gen4 and earlier. Though we always
+		 * request PIN_USER for execbuffer (translated to LOCAL_BIND),
+		 * without the appgtt, we cannot honour that request and so
+		 * must substitute it with a global binding. Since we do this
+		 * behind the upper layers back, we need to explicitly set
+		 * the bound flag ourselves.
+		 */
+		vma->bound |= GLOBAL_BIND;
+
 	}
 
 	if (dev_priv->mm.aliasing_ppgtt && flags & LOCAL_BIND) {
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 633bd1f..d19c9db 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -464,7 +464,10 @@
 	}
 
 	/* Hide bit 17 from the user -- see comment in i915_gem_set_tiling */
-	args->phys_swizzle_mode = args->swizzle_mode;
+	if (dev_priv->quirks & QUIRK_PIN_SWIZZLED_PAGES)
+		args->phys_swizzle_mode = I915_BIT_6_SWIZZLE_UNKNOWN;
+	else
+		args->phys_swizzle_mode = args->swizzle_mode;
 	if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_17)
 		args->swizzle_mode = I915_BIT_6_SWIZZLE_9;
 	if (args->swizzle_mode == I915_BIT_6_SWIZZLE_9_10_17)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 198fc3c..3dcd59e 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1075,15 +1075,34 @@
 	const union child_device_config *p_child;
 	union child_device_config *child_dev_ptr;
 	int i, child_device_num, count;
-	u16	block_size;
+	u8 expected_size;
+	u16 block_size;
 
 	p_defs = find_section(bdb, BDB_GENERAL_DEFINITIONS);
 	if (!p_defs) {
 		DRM_DEBUG_KMS("No general definition block is found, no devices defined.\n");
 		return;
 	}
-	if (p_defs->child_dev_size < sizeof(*p_child)) {
-		DRM_ERROR("General definiton block child device size is too small.\n");
+	if (bdb->version < 195) {
+		expected_size = 33;
+	} else if (bdb->version == 195) {
+		expected_size = 37;
+	} else if (bdb->version <= 197) {
+		expected_size = 38;
+	} else {
+		expected_size = 38;
+		DRM_DEBUG_DRIVER("Expected child_device_config size for BDB version %u not known; assuming %u\n",
+				 expected_size, bdb->version);
+	}
+
+	if (expected_size > sizeof(*p_child)) {
+		DRM_ERROR("child_device_config cannot fit in p_child\n");
+		return;
+	}
+
+	if (p_defs->child_dev_size != expected_size) {
+		DRM_ERROR("Size mismatch; child_device_config size=%u (expected %u); bdb->version: %u\n",
+			  p_defs->child_dev_size, expected_size, bdb->version);
 		return;
 	}
 	/* get the block size of general definitions */
@@ -1130,7 +1149,7 @@
 
 		child_dev_ptr = dev_priv->vbt.child_dev + count;
 		count++;
-		memcpy(child_dev_ptr, p_child, sizeof(*p_child));
+		memcpy(child_dev_ptr, p_child, p_defs->child_dev_size);
 	}
 	return;
 }
diff --git a/drivers/gpu/drm/i915/intel_dp_mst.c b/drivers/gpu/drm/i915/intel_dp_mst.c
index 6e4cc53..600afdb 100644
--- a/drivers/gpu/drm/i915/intel_dp_mst.c
+++ b/drivers/gpu/drm/i915/intel_dp_mst.c
@@ -357,6 +357,16 @@
 	return MODE_OK;
 }
 
+static struct drm_encoder *intel_mst_atomic_best_encoder(struct drm_connector *connector,
+							 struct drm_connector_state *state)
+{
+	struct intel_connector *intel_connector = to_intel_connector(connector);
+	struct intel_dp *intel_dp = intel_connector->mst_port;
+	struct intel_crtc *crtc = to_intel_crtc(state->crtc);
+
+	return &intel_dp->mst_encoders[crtc->pipe]->base.base;
+}
+
 static struct drm_encoder *intel_mst_best_encoder(struct drm_connector *connector)
 {
 	struct intel_connector *intel_connector = to_intel_connector(connector);
@@ -367,6 +377,7 @@
 static const struct drm_connector_helper_funcs intel_dp_mst_connector_helper_funcs = {
 	.get_modes = intel_dp_mst_get_modes,
 	.mode_valid = intel_dp_mst_mode_valid,
+	.atomic_best_encoder = intel_mst_atomic_best_encoder,
 	.best_encoder = intel_mst_best_encoder,
 };
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
index 0d1dbb7..247a424 100644
--- a/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp4/mdp4_plane.c
@@ -220,13 +220,15 @@
 	uint32_t op_mode = 0;
 	uint32_t phasex_step = MDP4_VG_PHASE_STEP_DEFAULT;
 	uint32_t phasey_step = MDP4_VG_PHASE_STEP_DEFAULT;
-	enum mdp4_frame_format frame_type = mdp4_get_frame_format(fb);
+	enum mdp4_frame_format frame_type;
 
 	if (!(crtc && fb)) {
 		DBG("%s: disabled!", mdp4_plane->name);
 		return 0;
 	}
 
+	frame_type = mdp4_get_frame_format(fb);
+
 	/* src values are in Q16 fixed point, convert to integer: */
 	src_x = src_x >> 16;
 	src_y = src_y >> 16;
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
index 206f758..e253db5 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.c
@@ -76,7 +76,20 @@
 
 static void mdp5_complete_commit(struct msm_kms *kms, struct drm_atomic_state *state)
 {
+	int i;
 	struct mdp5_kms *mdp5_kms = to_mdp5_kms(to_mdp_kms(kms));
+	int nplanes = mdp5_kms->dev->mode_config.num_total_plane;
+
+	for (i = 0; i < nplanes; i++) {
+		struct drm_plane *plane = state->planes[i];
+		struct drm_plane_state *plane_state = state->plane_states[i];
+
+		if (!plane)
+			continue;
+
+		mdp5_plane_complete_commit(plane, plane_state);
+	}
+
 	mdp5_disable(mdp5_kms);
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
index e0eb245..e79ac09 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_kms.h
@@ -227,6 +227,8 @@
 		struct drm_mode_object *obj);
 uint32_t mdp5_plane_get_flush(struct drm_plane *plane);
 void mdp5_plane_complete_flip(struct drm_plane *plane);
+void mdp5_plane_complete_commit(struct drm_plane *plane,
+	struct drm_plane_state *state);
 enum mdp5_pipe mdp5_plane_pipe(struct drm_plane *plane);
 struct drm_plane *mdp5_plane_init(struct drm_device *dev,
 		enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset);
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
index 57b8f56..2227556 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_plane.c
@@ -31,8 +31,6 @@
 
 	uint32_t nformats;
 	uint32_t formats[32];
-
-	bool enabled;
 };
 #define to_mdp5_plane(x) container_of(x, struct mdp5_plane, base)
 
@@ -56,22 +54,6 @@
 	return state->fb && state->crtc;
 }
 
-static int mdp5_plane_disable(struct drm_plane *plane)
-{
-	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
-	struct mdp5_kms *mdp5_kms = get_kms(plane);
-	enum mdp5_pipe pipe = mdp5_plane->pipe;
-
-	DBG("%s: disable", mdp5_plane->name);
-
-	if (mdp5_kms) {
-		/* Release the memory we requested earlier from the SMP: */
-		mdp5_smp_release(mdp5_kms->smp, pipe);
-	}
-
-	return 0;
-}
-
 static void mdp5_plane_destroy(struct drm_plane *plane)
 {
 	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
@@ -224,7 +206,6 @@
 
 	if (!plane_enabled(state)) {
 		to_mdp5_plane_state(state)->pending = true;
-		mdp5_plane_disable(plane);
 	} else if (to_mdp5_plane_state(state)->mode_changed) {
 		int ret;
 		to_mdp5_plane_state(state)->pending = true;
@@ -602,6 +583,20 @@
 	return mdp5_plane->flush_mask;
 }
 
+/* called after vsync in thread context */
+void mdp5_plane_complete_commit(struct drm_plane *plane,
+	struct drm_plane_state *state)
+{
+	struct mdp5_kms *mdp5_kms = get_kms(plane);
+	struct mdp5_plane *mdp5_plane = to_mdp5_plane(plane);
+	enum mdp5_pipe pipe = mdp5_plane->pipe;
+
+	if (!plane_enabled(plane->state)) {
+		DBG("%s: free SMP", mdp5_plane->name);
+		mdp5_smp_release(mdp5_kms->smp, pipe);
+	}
+}
+
 /* initialize plane */
 struct drm_plane *mdp5_plane_init(struct drm_device *dev,
 		enum mdp5_pipe pipe, bool private_plane, uint32_t reg_offset)
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
index 16702ae..64a27d8 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.c
@@ -34,22 +34,44 @@
  * and CANNOT be re-allocated (eg: MMB0 and MMB1 both tied to RGB0).
  *
  * For each block that can be dynamically allocated, it can be either
- * free, or pending/in-use by a client. The updates happen in three steps:
+ *     free:
+ *     The block is free.
+ *
+ *     pending:
+ *     The block is allocated to some client and not free.
+ *
+ *     configured:
+ *     The block is allocated to some client, and assigned to that
+ *     client in MDP5_MDP_SMP_ALLOC registers.
+ *
+ *     inuse:
+ *     The block is being actively used by a client.
+ *
+ * The updates happen in the following steps:
  *
  *  1) mdp5_smp_request():
  *     When plane scanout is setup, calculate required number of
- *     blocks needed per client, and request.  Blocks not inuse or
- *     pending by any other client are added to client's pending
- *     set.
+ *     blocks needed per client, and request. Blocks neither inuse nor
+ *     configured nor pending by any other client are added to client's
+ *     pending set.
+ *     For shrinking, blocks in pending but not in configured can be freed
+ *     directly, but those already in configured will be freed later by
+ *     mdp5_smp_commit.
  *
  *  2) mdp5_smp_configure():
  *     As hw is programmed, before FLUSH, MDP5_MDP_SMP_ALLOC registers
  *     are configured for the union(pending, inuse)
+ *     Current pending is copied to configured.
+ *     It is assumed that mdp5_smp_request and mdp5_smp_configure not run
+ *     concurrently for the same pipe.
  *
  *  3) mdp5_smp_commit():
- *     After next vblank, copy pending -> inuse.  Optionally update
+ *     After next vblank, copy configured -> inuse.  Optionally update
  *     MDP5_SMP_ALLOC registers if there are newly unused blocks
  *
+ *  4) mdp5_smp_release():
+ *     Must be called after the pipe is disabled and no longer uses any SMB
+ *
  * On the next vblank after changes have been committed to hw, the
  * client's pending blocks become it's in-use blocks (and no-longer
  * in-use blocks become available to other clients).
@@ -77,6 +99,9 @@
 	struct mdp5_client_smp_state client_state[MAX_CLIENTS];
 };
 
+static void update_smp_state(struct mdp5_smp *smp,
+		u32 cid, mdp5_smp_state_t *assigned);
+
 static inline
 struct mdp5_kms *get_kms(struct mdp5_smp *smp)
 {
@@ -149,7 +174,12 @@
 		for (i = cur_nblks; i > nblks; i--) {
 			int blk = find_first_bit(ps->pending, cnt);
 			clear_bit(blk, ps->pending);
-			/* don't clear in global smp_state until _commit() */
+
+			/* clear in global smp_state if not in configured
+			 * otherwise until _commit()
+			 */
+			if (!test_bit(blk, ps->configured))
+				clear_bit(blk, smp->state);
 		}
 	}
 
@@ -223,10 +253,33 @@
 /* Release SMP blocks for all clients of the pipe */
 void mdp5_smp_release(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 {
-	int i, nblks;
+	int i;
+	unsigned long flags;
+	int cnt = smp->blk_cnt;
 
-	for (i = 0, nblks = 0; i < pipe2nclients(pipe); i++)
-		smp_request_block(smp, pipe2client(pipe, i), 0);
+	for (i = 0; i < pipe2nclients(pipe); i++) {
+		mdp5_smp_state_t assigned;
+		u32 cid = pipe2client(pipe, i);
+		struct mdp5_client_smp_state *ps = &smp->client_state[cid];
+
+		spin_lock_irqsave(&smp->state_lock, flags);
+
+		/* clear hw assignment */
+		bitmap_or(assigned, ps->inuse, ps->configured, cnt);
+		update_smp_state(smp, CID_UNUSED, &assigned);
+
+		/* free to global pool */
+		bitmap_andnot(smp->state, smp->state, ps->pending, cnt);
+		bitmap_andnot(smp->state, smp->state, assigned, cnt);
+
+		/* clear client's infor */
+		bitmap_zero(ps->pending, cnt);
+		bitmap_zero(ps->configured, cnt);
+		bitmap_zero(ps->inuse, cnt);
+
+		spin_unlock_irqrestore(&smp->state_lock, flags);
+	}
+
 	set_fifo_thresholds(smp, pipe, 0);
 }
 
@@ -274,12 +327,20 @@
 		u32 cid = pipe2client(pipe, i);
 		struct mdp5_client_smp_state *ps = &smp->client_state[cid];
 
-		bitmap_or(assigned, ps->inuse, ps->pending, cnt);
+		/*
+		 * if vblank has not happened since last smp_configure
+		 * skip the configure for now
+		 */
+		if (!bitmap_equal(ps->inuse, ps->configured, cnt))
+			continue;
+
+		bitmap_copy(ps->configured, ps->pending, cnt);
+		bitmap_or(assigned, ps->inuse, ps->configured, cnt);
 		update_smp_state(smp, cid, &assigned);
 	}
 }
 
-/* step #3: after vblank, copy pending -> inuse: */
+/* step #3: after vblank, copy configured -> inuse: */
 void mdp5_smp_commit(struct mdp5_smp *smp, enum mdp5_pipe pipe)
 {
 	int cnt = smp->blk_cnt;
@@ -295,7 +356,7 @@
 		 * using, which can be released and made available to other
 		 * clients:
 		 */
-		if (bitmap_andnot(released, ps->inuse, ps->pending, cnt)) {
+		if (bitmap_andnot(released, ps->inuse, ps->configured, cnt)) {
 			unsigned long flags;
 
 			spin_lock_irqsave(&smp->state_lock, flags);
@@ -306,7 +367,7 @@
 			update_smp_state(smp, CID_UNUSED, &released);
 		}
 
-		bitmap_copy(ps->inuse, ps->pending, cnt);
+		bitmap_copy(ps->inuse, ps->configured, cnt);
 	}
 }
 
diff --git a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
index e47179f..5b6c236 100644
--- a/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
+++ b/drivers/gpu/drm/msm/mdp/mdp5/mdp5_smp.h
@@ -23,6 +23,7 @@
 
 struct mdp5_client_smp_state {
 	mdp5_smp_state_t inuse;
+	mdp5_smp_state_t configured;
 	mdp5_smp_state_t pending;
 };
 
diff --git a/drivers/gpu/drm/msm/msm_atomic.c b/drivers/gpu/drm/msm/msm_atomic.c
index 1b22d8b..1ceb4f2 100644
--- a/drivers/gpu/drm/msm/msm_atomic.c
+++ b/drivers/gpu/drm/msm/msm_atomic.c
@@ -283,12 +283,8 @@
 
 	timeout = ktime_add_ms(ktime_get(), 1000);
 
-	ret = msm_wait_fence_interruptable(dev, c->fence, &timeout);
-	if (ret) {
-		WARN_ON(ret);  // TODO unswap state back?  or??
-		commit_destroy(c);
-		return ret;
-	}
+	/* uninterruptible wait */
+	msm_wait_fence(dev, c->fence, &timeout, false);
 
 	complete_commit(c);
 
diff --git a/drivers/gpu/drm/msm/msm_drv.c b/drivers/gpu/drm/msm/msm_drv.c
index b7ef56e..d3467b1 100644
--- a/drivers/gpu/drm/msm/msm_drv.c
+++ b/drivers/gpu/drm/msm/msm_drv.c
@@ -637,8 +637,8 @@
  * Fences:
  */
 
-int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
-		ktime_t *timeout)
+int msm_wait_fence(struct drm_device *dev, uint32_t fence,
+		ktime_t *timeout , bool interruptible)
 {
 	struct msm_drm_private *priv = dev->dev_private;
 	int ret;
@@ -667,7 +667,12 @@
 			remaining_jiffies = timespec_to_jiffies(&ts);
 		}
 
-		ret = wait_event_interruptible_timeout(priv->fence_event,
+		if (interruptible)
+			ret = wait_event_interruptible_timeout(priv->fence_event,
+				fence_completed(dev, fence),
+				remaining_jiffies);
+		else
+			ret = wait_event_timeout(priv->fence_event,
 				fence_completed(dev, fence),
 				remaining_jiffies);
 
@@ -853,7 +858,7 @@
 		return -EINVAL;
 	}
 
-	return msm_wait_fence_interruptable(dev, args->fence, &timeout);
+	return msm_wait_fence(dev, args->fence, &timeout, true);
 }
 
 static const struct drm_ioctl_desc msm_ioctls[] = {
diff --git a/drivers/gpu/drm/msm/msm_drv.h b/drivers/gpu/drm/msm/msm_drv.h
index e7c5ea1..4ff0ec9 100644
--- a/drivers/gpu/drm/msm/msm_drv.h
+++ b/drivers/gpu/drm/msm/msm_drv.h
@@ -164,8 +164,8 @@
 
 int msm_register_mmu(struct drm_device *dev, struct msm_mmu *mmu);
 
-int msm_wait_fence_interruptable(struct drm_device *dev, uint32_t fence,
-		ktime_t *timeout);
+int msm_wait_fence(struct drm_device *dev, uint32_t fence,
+		ktime_t *timeout, bool interruptible);
 int msm_queue_fence_cb(struct drm_device *dev,
 		struct msm_fence_cb *cb, uint32_t fence);
 void msm_update_fence(struct drm_device *dev, uint32_t fence);
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index f211b80..c76cc85 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -460,7 +460,7 @@
 		if (op & MSM_PREP_NOSYNC)
 			timeout = NULL;
 
-		ret = msm_wait_fence_interruptable(dev, fence, timeout);
+		ret = msm_wait_fence(dev, fence, timeout, true);
 	}
 
 	/* TODO cache maintenance */
diff --git a/drivers/gpu/drm/msm/msm_gem_prime.c b/drivers/gpu/drm/msm/msm_gem_prime.c
index dd7a7ab..831461b 100644
--- a/drivers/gpu/drm/msm/msm_gem_prime.c
+++ b/drivers/gpu/drm/msm/msm_gem_prime.c
@@ -23,8 +23,12 @@
 struct sg_table *msm_gem_prime_get_sg_table(struct drm_gem_object *obj)
 {
 	struct msm_gem_object *msm_obj = to_msm_bo(obj);
-	BUG_ON(!msm_obj->sgt);  /* should have already pinned! */
-	return msm_obj->sgt;
+	int npages = obj->size >> PAGE_SHIFT;
+
+	if (WARN_ON(!msm_obj->pages))  /* should have already pinned! */
+		return NULL;
+
+	return drm_prime_pages_to_sg(msm_obj->pages, npages);
 }
 
 void *msm_gem_prime_vmap(struct drm_gem_object *obj)
diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 649024d..477cbb1 100644
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -128,6 +128,7 @@
 	nvkm_vm_ref(NULL, &nvxx_client(&cli->base)->vm, NULL);
 	nvif_client_fini(&cli->base);
 	usif_client_fini(cli);
+	kfree(cli);
 }
 
 static void
@@ -865,8 +866,10 @@
 
 	pm_runtime_get_sync(dev->dev);
 
+	mutex_lock(&cli->mutex);
 	if (cli->abi16)
 		nouveau_abi16_fini(cli->abi16);
+	mutex_unlock(&cli->mutex);
 
 	mutex_lock(&drm->client.mutex);
 	list_del(&cli->head);
diff --git a/drivers/gpu/drm/nouveau/nouveau_platform.c b/drivers/gpu/drm/nouveau/nouveau_platform.c
index 775277f..dcfbbfa 100644
--- a/drivers/gpu/drm/nouveau/nouveau_platform.c
+++ b/drivers/gpu/drm/nouveau/nouveau_platform.c
@@ -92,6 +92,8 @@
 	return 0;
 }
 
+#if IS_ENABLED(CONFIG_IOMMU_API)
+
 static void nouveau_platform_probe_iommu(struct device *dev,
 					 struct nouveau_platform_gpu *gpu)
 {
@@ -158,6 +160,20 @@
 	}
 }
 
+#else
+
+static void nouveau_platform_probe_iommu(struct device *dev,
+					 struct nouveau_platform_gpu *gpu)
+{
+}
+
+static void nouveau_platform_remove_iommu(struct device *dev,
+					  struct nouveau_platform_gpu *gpu)
+{
+}
+
+#endif
+
 static int nouveau_platform_probe(struct platform_device *pdev)
 {
 	struct nouveau_platform_gpu *gpu;
diff --git a/drivers/gpu/drm/nouveau/nouveau_ttm.c b/drivers/gpu/drm/nouveau/nouveau_ttm.c
index 18f4497..7464aef3 100644
--- a/drivers/gpu/drm/nouveau/nouveau_ttm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_ttm.c
@@ -175,15 +175,24 @@
 	node->page_shift = 12;
 
 	switch (drm->device.info.family) {
+	case NV_DEVICE_INFO_V0_TNT:
+	case NV_DEVICE_INFO_V0_CELSIUS:
+	case NV_DEVICE_INFO_V0_KELVIN:
+	case NV_DEVICE_INFO_V0_RANKINE:
+	case NV_DEVICE_INFO_V0_CURIE:
+		break;
 	case NV_DEVICE_INFO_V0_TESLA:
 		if (drm->device.info.chipset != 0x50)
 			node->memtype = (nvbo->tile_flags & 0x7f00) >> 8;
 		break;
 	case NV_DEVICE_INFO_V0_FERMI:
 	case NV_DEVICE_INFO_V0_KEPLER:
+	case NV_DEVICE_INFO_V0_MAXWELL:
 		node->memtype = (nvbo->tile_flags & 0xff00) >> 8;
 		break;
 	default:
+		NV_WARN(drm, "%s: unhandled family type %x\n", __func__,
+			drm->device.info.family);
 		break;
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nv04_fbcon.c b/drivers/gpu/drm/nouveau/nv04_fbcon.c
index 4ef602c..495c576 100644
--- a/drivers/gpu/drm/nouveau/nv04_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv04_fbcon.c
@@ -203,7 +203,7 @@
 	if (ret)
 		return ret;
 
-	if (RING_SPACE(chan, 49)) {
+	if (RING_SPACE(chan, 49 + (device->info.chipset >= 0x11 ? 4 : 0))) {
 		nouveau_fbcon_gpu_lockup(info);
 		return 0;
 	}
diff --git a/drivers/gpu/drm/nouveau/nv50_display.c b/drivers/gpu/drm/nouveau/nv50_display.c
index 7da7958..981342d 100644
--- a/drivers/gpu/drm/nouveau/nv50_display.c
+++ b/drivers/gpu/drm/nouveau/nv50_display.c
@@ -979,7 +979,7 @@
 {
 	struct nv50_mast *mast = nv50_mast(nv_crtc->base.dev);
 
-	if (show && nv_crtc->cursor.nvbo)
+	if (show && nv_crtc->cursor.nvbo && nv_crtc->base.enabled)
 		nv50_crtc_cursor_show(nv_crtc);
 	else
 		nv50_crtc_cursor_hide(nv_crtc);
diff --git a/drivers/gpu/drm/nouveau/nv50_fbcon.c b/drivers/gpu/drm/nouveau/nv50_fbcon.c
index 394c89a..901130b 100644
--- a/drivers/gpu/drm/nouveau/nv50_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nv50_fbcon.c
@@ -188,7 +188,7 @@
 	if (ret)
 		return ret;
 
-	ret = RING_SPACE(chan, 59);
+	ret = RING_SPACE(chan, 58);
 	if (ret) {
 		nouveau_fbcon_gpu_lockup(info);
 		return ret;
@@ -252,6 +252,7 @@
 	OUT_RING(chan, info->var.yres_virtual);
 	OUT_RING(chan, upper_32_bits(fb->vma.offset));
 	OUT_RING(chan, lower_32_bits(fb->vma.offset));
+	FIRE_RING(chan);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/nouveau/nvc0_fbcon.c b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
index 6124667..fcd2e5f 100644
--- a/drivers/gpu/drm/nouveau/nvc0_fbcon.c
+++ b/drivers/gpu/drm/nouveau/nvc0_fbcon.c
@@ -188,7 +188,7 @@
 		return -EINVAL;
 	}
 
-	ret = RING_SPACE(chan, 60);
+	ret = RING_SPACE(chan, 58);
 	if (ret) {
 		WARN_ON(1);
 		nouveau_fbcon_gpu_lockup(info);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
index 9ef6728..7f2f05f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gf110.c
@@ -809,7 +809,7 @@
 		case 0x00000900: type = DCB_OUTPUT_DP; mask = 2; break;
 		default:
 			nv_error(priv, "unknown SOR mc 0x%08x\n", ctrl);
-			return 0x0000;
+			return NULL;
 		}
 	}
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
index e10f964..52c22b0 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/fifo/gk104.c
@@ -166,14 +166,30 @@
 }
 
 static int
+gk104_fifo_chan_kick(struct gk104_fifo_chan *chan)
+{
+	struct nvkm_object *obj = (void *)chan;
+	struct gk104_fifo_priv *priv = (void *)obj->engine;
+
+	nv_wr32(priv, 0x002634, chan->base.chid);
+	if (!nv_wait(priv, 0x002634, 0x100000, 0x000000)) {
+		nv_error(priv, "channel %d [%s] kick timeout\n",
+			 chan->base.chid, nvkm_client_name(chan));
+		return -EBUSY;
+	}
+
+	return 0;
+}
+
+static int
 gk104_fifo_context_detach(struct nvkm_object *parent, bool suspend,
 			  struct nvkm_object *object)
 {
 	struct nvkm_bar *bar = nvkm_bar(parent);
-	struct gk104_fifo_priv *priv = (void *)parent->engine;
 	struct gk104_fifo_base *base = (void *)parent->parent;
 	struct gk104_fifo_chan *chan = (void *)parent;
 	u32 addr;
+	int ret;
 
 	switch (nv_engidx(object->engine)) {
 	case NVDEV_ENGINE_SW    : return 0;
@@ -188,13 +204,9 @@
 		return -EINVAL;
 	}
 
-	nv_wr32(priv, 0x002634, chan->base.chid);
-	if (!nv_wait(priv, 0x002634, 0xffffffff, chan->base.chid)) {
-		nv_error(priv, "channel %d [%s] kick timeout\n",
-			 chan->base.chid, nvkm_client_name(chan));
-		if (suspend)
-			return -EBUSY;
-	}
+	ret = gk104_fifo_chan_kick(chan);
+	if (ret && suspend)
+		return ret;
 
 	if (addr) {
 		nv_wo32(base, addr + 0x00, 0x00000000);
@@ -319,6 +331,7 @@
 		gk104_fifo_runlist_update(priv, chan->engine);
 	}
 
+	gk104_fifo_chan_kick(chan);
 	nv_wr32(priv, 0x800000 + (chid * 8), 0x00000000);
 	return nvkm_fifo_channel_fini(&chan->base, suspend);
 }
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
index 5606c25..ca11ddb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.c
@@ -663,6 +663,37 @@
 		gf100_gr_zbc_clear_depth(priv, index);
 }
 
+/**
+ * Wait until GR goes idle. GR is considered idle if it is disabled by the
+ * MC (0x200) register, or GR is not busy and a context switch is not in
+ * progress.
+ */
+int
+gf100_gr_wait_idle(struct gf100_gr_priv *priv)
+{
+	unsigned long end_jiffies = jiffies + msecs_to_jiffies(2000);
+	bool gr_enabled, ctxsw_active, gr_busy;
+
+	do {
+		/*
+		 * required to make sure FIFO_ENGINE_STATUS (0x2640) is
+		 * up-to-date
+		 */
+		nv_rd32(priv, 0x400700);
+
+		gr_enabled = nv_rd32(priv, 0x200) & 0x1000;
+		ctxsw_active = nv_rd32(priv, 0x2640) & 0x8000;
+		gr_busy = nv_rd32(priv, 0x40060c) & 0x1;
+
+		if (!gr_enabled || (!gr_busy && !ctxsw_active))
+			return 0;
+	} while (time_before(jiffies, end_jiffies));
+
+	nv_error(priv, "wait for idle timeout (en: %d, ctxsw: %d, busy: %d)\n",
+		 gr_enabled, ctxsw_active, gr_busy);
+	return -EAGAIN;
+}
+
 void
 gf100_gr_mmio(struct gf100_gr_priv *priv, const struct gf100_gr_pack *p)
 {
@@ -699,7 +730,13 @@
 
 		while (addr < next) {
 			nv_wr32(priv, 0x400200, addr);
-			nv_wait(priv, 0x400700, 0x00000002, 0x00000000);
+			/**
+			 * Wait for GR to go idle after submitting a
+			 * GO_IDLE bundle
+			 */
+			if ((addr & 0xffff) == 0xe100)
+				gf100_gr_wait_idle(priv);
+			nv_wait(priv, 0x400700, 0x00000004, 0x00000000);
 			addr += init->pitch;
 		}
 	}
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
index 8af1a89..c9533fd 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/gr/gf100.h
@@ -181,6 +181,7 @@
 	int ppc_nr;
 };
 
+int  gf100_gr_wait_idle(struct gf100_gr_priv *);
 void gf100_gr_mmio(struct gf100_gr_priv *, const struct gf100_gr_pack *);
 void gf100_gr_icmd(struct gf100_gr_priv *, const struct gf100_gr_pack *);
 void gf100_gr_mthd(struct gf100_gr_priv *, const struct gf100_gr_pack *);
diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
index 2006c44..4cf36a3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
+++ b/drivers/gpu/drm/nouveau/nvkm/engine/pm/base.c
@@ -332,9 +332,12 @@
 nvkm_perfctx_dtor(struct nvkm_object *object)
 {
 	struct nvkm_pm *ppm = (void *)object->engine;
+	struct nvkm_perfctx *ctx = (void *)object;
+
 	mutex_lock(&nv_subdev(ppm)->mutex);
-	nvkm_engctx_destroy(&ppm->context->base);
-	ppm->context = NULL;
+	nvkm_engctx_destroy(&ctx->base);
+	if (ppm->context == ctx)
+		ppm->context = NULL;
 	mutex_unlock(&nv_subdev(ppm)->mutex);
 }
 
@@ -355,12 +358,11 @@
 	mutex_lock(&nv_subdev(ppm)->mutex);
 	if (ppm->context == NULL)
 		ppm->context = ctx;
+	if (ctx != ppm->context)
+		ret = -EBUSY;
 	mutex_unlock(&nv_subdev(ppm)->mutex);
 
-	if (ctx != ppm->context)
-		return -EBUSY;
-
-	return 0;
+	return ret;
 }
 
 struct nvkm_oclass
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
index f67cdae..f4611e3 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/bios/init.c
@@ -1285,6 +1285,44 @@
 }
 
 /**
+ * INIT_PLL_INDIRECT - opcode 0x59
+ *
+ */
+static void
+init_pll_indirect(struct nvbios_init *init)
+{
+	struct nvkm_bios *bios = init->bios;
+	u32  reg = nv_ro32(bios, init->offset + 1);
+	u16 addr = nv_ro16(bios, init->offset + 5);
+	u32 freq = (u32)nv_ro16(bios, addr) * 1000;
+
+	trace("PLL_INDIRECT\tR[0x%06x] =PLL= VBIOS[%04x] = %dkHz\n",
+	      reg, addr, freq);
+	init->offset += 7;
+
+	init_prog_pll(init, reg, freq);
+}
+
+/**
+ * INIT_ZM_REG_INDIRECT - opcode 0x5a
+ *
+ */
+static void
+init_zm_reg_indirect(struct nvbios_init *init)
+{
+	struct nvkm_bios *bios = init->bios;
+	u32  reg = nv_ro32(bios, init->offset + 1);
+	u16 addr = nv_ro16(bios, init->offset + 5);
+	u32 data = nv_ro32(bios, addr);
+
+	trace("ZM_REG_INDIRECT\tR[0x%06x] = VBIOS[0x%04x] = 0x%08x\n",
+	      reg, addr, data);
+	init->offset += 7;
+
+	init_wr32(init, addr, data);
+}
+
+/**
  * INIT_SUB_DIRECT - opcode 0x5b
  *
  */
@@ -2145,6 +2183,8 @@
 	[0x56] = { init_condition_time },
 	[0x57] = { init_ltime },
 	[0x58] = { init_zm_reg_sequence },
+	[0x59] = { init_pll_indirect },
+	[0x5a] = { init_zm_reg_indirect },
 	[0x5b] = { init_sub_direct },
 	[0x5c] = { init_jump },
 	[0x5e] = { init_i2c_if },
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
index 822d32a..065e9f5 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/clk/gt215.c
@@ -180,7 +180,8 @@
 	       struct gt215_clk_info *info)
 {
 	struct gt215_clk_priv *priv = (void *)clock;
-	u32 oclk, sclk, sdiv, diff;
+	u32 oclk, sclk, sdiv;
+	s32 diff;
 
 	info->clk = 0;
 
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
index c0fdb89..24dcdfb 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/ibus/gk20a.c
@@ -38,6 +38,14 @@
 	nv_wr32(priv, 0x12004c, 0x4);
 	nv_wr32(priv, 0x122204, 0x2);
 	nv_rd32(priv, 0x122204);
+
+	/*
+	 * Bug: increase clock timeout to avoid operation failure at high
+	 * gpcclk rate.
+	 */
+	nv_wr32(priv, 0x122354, 0x800);
+	nv_wr32(priv, 0x128328, 0x800);
+	nv_wr32(priv, 0x124320, 0x800);
 }
 
 static void
diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
index 80614f1..282143f 100644
--- a/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
+++ b/drivers/gpu/drm/nouveau/nvkm/subdev/instmem/nv04.c
@@ -50,7 +50,12 @@
 {
 	struct nv04_instmem_priv *priv = (void *)nvkm_instmem(object);
 	struct nv04_instobj_priv *node = (void *)object;
+	struct nvkm_subdev *subdev = (void *)priv;
+
+	mutex_lock(&subdev->mutex);
 	nvkm_mm_free(&priv->heap, &node->mem);
+	mutex_unlock(&subdev->mutex);
+
 	nvkm_instobj_destroy(&node->base);
 }
 
@@ -62,6 +67,7 @@
 	struct nv04_instmem_priv *priv = (void *)nvkm_instmem(parent);
 	struct nv04_instobj_priv *node;
 	struct nvkm_instobj_args *args = data;
+	struct nvkm_subdev *subdev = (void *)priv;
 	int ret;
 
 	if (!args->align)
@@ -72,8 +78,10 @@
 	if (ret)
 		return ret;
 
+	mutex_lock(&subdev->mutex);
 	ret = nvkm_mm_head(&priv->heap, 0, 1, args->size, args->size,
 			   args->align, &node->mem);
+	mutex_unlock(&subdev->mutex);
 	if (ret)
 		return ret;
 
diff --git a/drivers/gpu/drm/radeon/atombios_encoders.c b/drivers/gpu/drm/radeon/atombios_encoders.c
index dd39f43..c387259 100644
--- a/drivers/gpu/drm/radeon/atombios_encoders.c
+++ b/drivers/gpu/drm/radeon/atombios_encoders.c
@@ -2299,8 +2299,7 @@
 	encoder_mode = atombios_get_encoder_mode(encoder);
 	if (connector && (radeon_audio != 0) &&
 	    ((encoder_mode == ATOM_ENCODER_MODE_HDMI) ||
-	     (ENCODER_MODE_IS_DP(encoder_mode) &&
-	      drm_detect_monitor_audio(radeon_connector_edid(connector)))))
+	     ENCODER_MODE_IS_DP(encoder_mode)))
 		radeon_audio_mode_set(encoder, adjusted_mode);
 }
 
diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c
index 68fd9fc..44480c1 100644
--- a/drivers/gpu/drm/radeon/dce6_afmt.c
+++ b/drivers/gpu/drm/radeon/dce6_afmt.c
@@ -93,30 +93,26 @@
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->offset;
-
-	WREG32(AFMT_AUDIO_SRC_CONTROL + offset,
-	       AFMT_AUDIO_SRC_SELECT(dig->afmt->pin->id));
+	WREG32(AFMT_AUDIO_SRC_CONTROL +  dig->afmt->offset,
+	       AFMT_AUDIO_SRC_SELECT(dig->pin->id));
 }
 
 void dce6_afmt_write_latency_fields(struct drm_encoder *encoder,
-		struct drm_connector *connector, struct drm_display_mode *mode)
+				    struct drm_connector *connector,
+				    struct drm_display_mode *mode)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 tmp = 0, offset;
+	u32 tmp = 0;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	if (mode->flags & DRM_MODE_FLAG_INTERLACE) {
 		if (connector->latency_present[1])
 			tmp = VIDEO_LIPSYNC(connector->video_latency[1]) |
@@ -130,24 +126,24 @@
 		else
 			tmp = VIDEO_LIPSYNC(0) | AUDIO_LIPSYNC(0);
 	}
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_RESPONSE_LIPSYNC, tmp);
 }
 
 void dce6_afmt_hdmi_write_speaker_allocation(struct drm_encoder *encoder,
-	u8 *sadb, int sad_count)
+					     u8 *sadb, int sad_count)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset, tmp;
+	u32 tmp;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	/* program the speaker allocation */
-	tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
+	tmp = RREG32_ENDPOINT(dig->pin->offset,
+			      AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
 	tmp &= ~(DP_CONNECTION | SPEAKER_ALLOCATION_MASK);
 	/* set HDMI mode */
 	tmp |= HDMI_CONNECTION;
@@ -155,24 +151,24 @@
 		tmp |= SPEAKER_ALLOCATION(sadb[0]);
 	else
 		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
 }
 
 void dce6_afmt_dp_write_speaker_allocation(struct drm_encoder *encoder,
-	u8 *sadb, int sad_count)
+					   u8 *sadb, int sad_count)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	u32 offset, tmp;
+	u32 tmp;
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	/* program the speaker allocation */
-	tmp = RREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
+	tmp = RREG32_ENDPOINT(dig->pin->offset,
+			      AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER);
 	tmp &= ~(HDMI_CONNECTION | SPEAKER_ALLOCATION_MASK);
 	/* set DP mode */
 	tmp |= DP_CONNECTION;
@@ -180,13 +176,13 @@
 		tmp |= SPEAKER_ALLOCATION(sadb[0]);
 	else
 		tmp |= SPEAKER_ALLOCATION(5); /* stereo */
-	WREG32_ENDPOINT(offset, AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
+	WREG32_ENDPOINT(dig->pin->offset,
+			AZ_F0_CODEC_PIN_CONTROL_CHANNEL_SPEAKER, tmp);
 }
 
 void dce6_afmt_write_sad_regs(struct drm_encoder *encoder,
-	struct cea_sad *sads, int sad_count)
+			      struct cea_sad *sads, int sad_count)
 {
-	u32 offset;
 	int i;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
@@ -206,11 +202,9 @@
 		{ AZ_F0_CODEC_PIN_CONTROL_AUDIO_DESCRIPTOR13, HDMI_AUDIO_CODING_TYPE_WMA_PRO },
 	};
 
-	if (!dig || !dig->afmt || !dig->afmt->pin)
+	if (!dig || !dig->afmt || !dig->pin)
 		return;
 
-	offset = dig->afmt->pin->offset;
-
 	for (i = 0; i < ARRAY_SIZE(eld_reg_to_type); i++) {
 		u32 value = 0;
 		u8 stereo_freqs = 0;
@@ -237,7 +231,7 @@
 
 		value |= SUPPORTED_FREQUENCIES_STEREO(stereo_freqs);
 
-		WREG32_ENDPOINT(offset, eld_reg_to_type[i][0], value);
+		WREG32_ENDPOINT(dig->pin->offset, eld_reg_to_type[i][0], value);
 	}
 }
 
@@ -253,7 +247,7 @@
 }
 
 void dce6_hdmi_audio_set_dto(struct radeon_device *rdev,
-	struct radeon_crtc *crtc, unsigned int clock)
+			     struct radeon_crtc *crtc, unsigned int clock)
 {
 	/* Two dtos; generally use dto0 for HDMI */
 	u32 value = 0;
@@ -272,7 +266,7 @@
 }
 
 void dce6_dp_audio_set_dto(struct radeon_device *rdev,
-	struct radeon_crtc *crtc, unsigned int clock)
+			   struct radeon_crtc *crtc, unsigned int clock)
 {
 	/* Two dtos; generally use dto1 for DP */
 	u32 value = 0;
diff --git a/drivers/gpu/drm/radeon/radeon_audio.c b/drivers/gpu/drm/radeon/radeon_audio.c
index fa719c5..fbc8d88 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.c
+++ b/drivers/gpu/drm/radeon/radeon_audio.c
@@ -245,6 +245,28 @@
 static void radeon_audio_enable(struct radeon_device *rdev,
 				struct r600_audio_pin *pin, u8 enable_mask)
 {
+	struct drm_encoder *encoder;
+	struct radeon_encoder *radeon_encoder;
+	struct radeon_encoder_atom_dig *dig;
+	int pin_count = 0;
+
+	if (!pin)
+		return;
+
+	if (rdev->mode_info.mode_config_initialized) {
+		list_for_each_entry(encoder, &rdev->ddev->mode_config.encoder_list, head) {
+			if (radeon_encoder_is_digital(encoder)) {
+				radeon_encoder = to_radeon_encoder(encoder);
+				dig = radeon_encoder->enc_priv;
+				if (dig->pin == pin)
+					pin_count++;
+			}
+		}
+
+		if ((pin_count > 1) && (enable_mask == 0))
+			return;
+	}
+
 	if (rdev->audio.funcs->enable)
 		rdev->audio.funcs->enable(rdev, pin, enable_mask);
 }
@@ -336,24 +358,13 @@
 
 static void radeon_audio_write_sad_regs(struct drm_encoder *encoder)
 {
-	struct radeon_encoder *radeon_encoder;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct cea_sad *sads;
 	int sad_count;
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
 
 	sad_count = drm_edid_to_sad(radeon_connector_edid(connector), &sads);
 	if (sad_count <= 0) {
@@ -362,8 +373,6 @@
 	}
 	BUG_ON(!sads);
 
-	radeon_encoder = to_radeon_encoder(encoder);
-
 	if (radeon_encoder->audio && radeon_encoder->audio->write_sad_regs)
 		radeon_encoder->audio->write_sad_regs(encoder, sads, sad_count);
 
@@ -372,27 +381,16 @@
 
 static void radeon_audio_write_speaker_allocation(struct drm_encoder *encoder)
 {
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
 	u8 *sadb = NULL;
 	int sad_count;
 
-	list_for_each_entry(connector,
-			    &encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
 
-	sad_count = drm_edid_to_speaker_allocation(
-		radeon_connector_edid(connector), &sadb);
+	sad_count = drm_edid_to_speaker_allocation(radeon_connector_edid(connector),
+						   &sadb);
 	if (sad_count < 0) {
 		DRM_DEBUG("Couldn't read Speaker Allocation Data Block: %d\n",
 			  sad_count);
@@ -406,26 +404,13 @@
 }
 
 static void radeon_audio_write_latency_fields(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+					      struct drm_display_mode *mode)
 {
-	struct radeon_encoder *radeon_encoder;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = 0;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
+	if (!connector)
 		return;
-	}
-
-	radeon_encoder = to_radeon_encoder(encoder);
 
 	if (radeon_encoder->audio && radeon_encoder->audio->write_latency_fields)
 		radeon_encoder->audio->write_latency_fields(encoder, connector, mode);
@@ -451,29 +436,23 @@
 }
 
 void radeon_audio_detect(struct drm_connector *connector,
+			 struct drm_encoder *encoder,
 			 enum drm_connector_status status)
 {
-	struct radeon_device *rdev;
-	struct radeon_encoder *radeon_encoder;
+	struct drm_device *dev = connector->dev;
+	struct radeon_device *rdev = dev->dev_private;
+	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig;
 
-	if (!connector || !connector->encoder)
-		return;
-
-	rdev = connector->encoder->dev->dev_private;
-
 	if (!radeon_audio_chipset_supported(rdev))
 		return;
 
-	radeon_encoder = to_radeon_encoder(connector->encoder);
+	if (!radeon_encoder_is_digital(encoder))
+		return;
+
 	dig = radeon_encoder->enc_priv;
 
 	if (status == connector_status_connected) {
-		if (!drm_detect_monitor_audio(radeon_connector_edid(connector))) {
-			radeon_encoder->audio = NULL;
-			return;
-		}
-
 		if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort) {
 			struct radeon_connector *radeon_connector = to_radeon_connector(connector);
 
@@ -486,11 +465,17 @@
 			radeon_encoder->audio = rdev->audio.hdmi_funcs;
 		}
 
-		dig->afmt->pin = radeon_audio_get_pin(connector->encoder);
-		radeon_audio_enable(rdev, dig->afmt->pin, 0xf);
+		if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+			if (!dig->pin)
+				dig->pin = radeon_audio_get_pin(encoder);
+			radeon_audio_enable(rdev, dig->pin, 0xf);
+		} else {
+			radeon_audio_enable(rdev, dig->pin, 0);
+			dig->pin = NULL;
+		}
 	} else {
-		radeon_audio_enable(rdev, dig->afmt->pin, 0);
-		dig->afmt->pin = NULL;
+		radeon_audio_enable(rdev, dig->pin, 0);
+		dig->pin = NULL;
 	}
 }
 
@@ -518,29 +503,18 @@
 }
 
 static int radeon_audio_set_avi_packet(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+				       struct drm_display_mode *mode)
 {
 	struct radeon_device *rdev = encoder->dev->dev_private;
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
-	struct drm_connector *connector;
-	struct radeon_connector *radeon_connector = NULL;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 	u8 buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AVI_INFOFRAME_SIZE];
 	struct hdmi_avi_infoframe frame;
 	int err;
 
-	list_for_each_entry(connector,
-		&encoder->dev->mode_config.connector_list, head) {
-		if (connector->encoder == encoder) {
-			radeon_connector = to_radeon_connector(connector);
-			break;
-		}
-	}
-
-	if (!radeon_connector) {
-		DRM_ERROR("Couldn't find encoder's connector\n");
-		return -ENOENT;
-	}
+	if (!connector)
+		return -EINVAL;
 
 	err = drm_hdmi_avi_infoframe_from_display_mode(&frame, mode);
 	if (err < 0) {
@@ -563,8 +537,8 @@
 		return err;
 	}
 
-	if (dig && dig->afmt &&
-		radeon_encoder->audio && radeon_encoder->audio->set_avi_packet)
+	if (dig && dig->afmt && radeon_encoder->audio &&
+	    radeon_encoder->audio->set_avi_packet)
 		radeon_encoder->audio->set_avi_packet(rdev, dig->afmt->offset,
 			buffer, sizeof(buffer));
 
@@ -722,30 +696,41 @@
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 	struct radeon_encoder_atom_dig *dig = radeon_encoder->enc_priv;
+	struct drm_connector *connector = radeon_get_connector_for_encoder(encoder);
 
 	if (!dig || !dig->afmt)
 		return;
 
-	radeon_audio_set_mute(encoder, true);
-
-	radeon_audio_write_speaker_allocation(encoder);
-	radeon_audio_write_sad_regs(encoder);
-	radeon_audio_write_latency_fields(encoder, mode);
-	radeon_audio_set_dto(encoder, mode->clock);
-	radeon_audio_set_vbi_packet(encoder);
-	radeon_hdmi_set_color_depth(encoder);
-	radeon_audio_update_acr(encoder, mode->clock);
-	radeon_audio_set_audio_packet(encoder);
-	radeon_audio_select_pin(encoder);
-
-	if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+	if (!connector)
 		return;
 
-	radeon_audio_set_mute(encoder, false);
+	if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+		radeon_audio_set_mute(encoder, true);
+
+		radeon_audio_write_speaker_allocation(encoder);
+		radeon_audio_write_sad_regs(encoder);
+		radeon_audio_write_latency_fields(encoder, mode);
+		radeon_audio_set_dto(encoder, mode->clock);
+		radeon_audio_set_vbi_packet(encoder);
+		radeon_hdmi_set_color_depth(encoder);
+		radeon_audio_update_acr(encoder, mode->clock);
+		radeon_audio_set_audio_packet(encoder);
+		radeon_audio_select_pin(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+
+		radeon_audio_set_mute(encoder, false);
+	} else {
+		radeon_hdmi_set_color_depth(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+	}
 }
 
 static void radeon_audio_dp_mode_set(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+				     struct drm_display_mode *mode)
 {
 	struct drm_device *dev = encoder->dev;
 	struct radeon_device *rdev = dev->dev_private;
@@ -759,22 +744,27 @@
 	if (!dig || !dig->afmt)
 		return;
 
-	radeon_audio_write_speaker_allocation(encoder);
-	radeon_audio_write_sad_regs(encoder);
-	radeon_audio_write_latency_fields(encoder, mode);
-	if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev))
-		radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10);
-	else
-		radeon_audio_set_dto(encoder, dig_connector->dp_clock);
-	radeon_audio_set_audio_packet(encoder);
-	radeon_audio_select_pin(encoder);
-
-	if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+	if (!connector)
 		return;
+
+	if (drm_detect_monitor_audio(radeon_connector_edid(connector))) {
+		radeon_audio_write_speaker_allocation(encoder);
+		radeon_audio_write_sad_regs(encoder);
+		radeon_audio_write_latency_fields(encoder, mode);
+		if (rdev->clock.dp_extclk || ASIC_IS_DCE5(rdev))
+			radeon_audio_set_dto(encoder, rdev->clock.default_dispclk * 10);
+		else
+			radeon_audio_set_dto(encoder, dig_connector->dp_clock);
+		radeon_audio_set_audio_packet(encoder);
+		radeon_audio_select_pin(encoder);
+
+		if (radeon_audio_set_avi_packet(encoder, mode) < 0)
+			return;
+	}
 }
 
 void radeon_audio_mode_set(struct drm_encoder *encoder,
-	struct drm_display_mode *mode)
+			   struct drm_display_mode *mode)
 {
 	struct radeon_encoder *radeon_encoder = to_radeon_encoder(encoder);
 
diff --git a/drivers/gpu/drm/radeon/radeon_audio.h b/drivers/gpu/drm/radeon/radeon_audio.h
index 8438304..059cc30 100644
--- a/drivers/gpu/drm/radeon/radeon_audio.h
+++ b/drivers/gpu/drm/radeon/radeon_audio.h
@@ -68,7 +68,8 @@
 
 int radeon_audio_init(struct radeon_device *rdev);
 void radeon_audio_detect(struct drm_connector *connector,
-	enum drm_connector_status status);
+			 struct drm_encoder *encoder,
+			 enum drm_connector_status status);
 u32 radeon_audio_endpoint_rreg(struct radeon_device *rdev,
 	u32 offset, u32 reg);
 void radeon_audio_endpoint_wreg(struct radeon_device *rdev,
diff --git a/drivers/gpu/drm/radeon/radeon_combios.c b/drivers/gpu/drm/radeon/radeon_combios.c
index 3e5f6b7..c097d3a 100644
--- a/drivers/gpu/drm/radeon/radeon_combios.c
+++ b/drivers/gpu/drm/radeon/radeon_combios.c
@@ -1255,10 +1255,15 @@
 
 			if ((RBIOS16(tmp) == lvds->native_mode.hdisplay) &&
 			    (RBIOS16(tmp + 2) == lvds->native_mode.vdisplay)) {
+				u32 hss = (RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+
+				if (hss > lvds->native_mode.hdisplay)
+					hss = (10 - 1) * 8;
+
 				lvds->native_mode.htotal = lvds->native_mode.hdisplay +
 					(RBIOS16(tmp + 17) - RBIOS16(tmp + 19)) * 8;
 				lvds->native_mode.hsync_start = lvds->native_mode.hdisplay +
-					(RBIOS16(tmp + 21) - RBIOS16(tmp + 19) - 1) * 8;
+					hss;
 				lvds->native_mode.hsync_end = lvds->native_mode.hsync_start +
 					(RBIOS8(tmp + 23) * 8);
 
diff --git a/drivers/gpu/drm/radeon/radeon_connectors.c b/drivers/gpu/drm/radeon/radeon_connectors.c
index cebb65e..94b21ae 100644
--- a/drivers/gpu/drm/radeon/radeon_connectors.c
+++ b/drivers/gpu/drm/radeon/radeon_connectors.c
@@ -1379,8 +1379,16 @@
 	/* updated in get modes as well since we need to know if it's analog or digital */
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0)
-		radeon_audio_detect(connector, ret);
+	if ((radeon_audio != 0) && radeon_connector->use_digital) {
+		const struct drm_connector_helper_funcs *connector_funcs =
+			connector->helper_private;
+
+		encoder = connector_funcs->best_encoder(connector);
+		if (encoder && (encoder->encoder_type == DRM_MODE_ENCODER_TMDS)) {
+			radeon_connector_get_edid(connector);
+			radeon_audio_detect(connector, encoder, ret);
+		}
+	}
 
 exit:
 	pm_runtime_mark_last_busy(connector->dev->dev);
@@ -1717,8 +1725,10 @@
 
 	radeon_connector_update_scratch_regs(connector, ret);
 
-	if (radeon_audio != 0)
-		radeon_audio_detect(connector, ret);
+	if ((radeon_audio != 0) && encoder) {
+		radeon_connector_get_edid(connector);
+		radeon_audio_detect(connector, encoder, ret);
+	}
 
 out:
 	pm_runtime_mark_last_busy(connector->dev->dev);
diff --git a/drivers/gpu/drm/radeon/radeon_mode.h b/drivers/gpu/drm/radeon/radeon_mode.h
index 07909d8..aecc3e3 100644
--- a/drivers/gpu/drm/radeon/radeon_mode.h
+++ b/drivers/gpu/drm/radeon/radeon_mode.h
@@ -237,7 +237,6 @@
 	int offset;
 	bool last_buffer_filled_status;
 	int id;
-	struct r600_audio_pin *pin;
 };
 
 struct radeon_mode_info {
@@ -439,6 +438,7 @@
 	uint8_t backlight_level;
 	int panel_mode;
 	struct radeon_afmt *afmt;
+	struct r600_audio_pin *pin;
 	int active_mst_links;
 };
 
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index f822fd2..884d82f 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -546,6 +546,12 @@
 		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
 		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI),
+		.driver_data = APPLE_HAS_FN },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS),
+		.driver_data = APPLE_HAS_FN | APPLE_RDESC_JIS },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO),
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 157c627..e6fce23 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1782,6 +1782,9 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ANSI) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_ISO) },
 	{ HID_BLUETOOTH_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_WIRELESS_2009_JIS) },
@@ -2463,6 +2466,9 @@
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING8_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_WELLSPRING9_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY) },
 	{ }
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index b04b082..b3b225b 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -142,6 +142,9 @@
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI	0x0272
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO		0x0273
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS		0x0274
 #define USB_DEVICE_ID_APPLE_FOUNTAIN_TP_ONLY	0x030a
 #define USB_DEVICE_ID_APPLE_GEYSER1_TP_ONLY	0x030b
 #define USB_DEVICE_ID_APPLE_IRCONTROL	0x8240
diff --git a/drivers/hwmon/nct7802.c b/drivers/hwmon/nct7802.c
index 28fcb2e..fbfc02b 100644
--- a/drivers/hwmon/nct7802.c
+++ b/drivers/hwmon/nct7802.c
@@ -195,7 +195,7 @@
 }
 
 static int nct7802_write_voltage(struct nct7802_data *data, int nr, int index,
-				 unsigned int voltage)
+				 unsigned long voltage)
 {
 	int shift = 8 - REG_VOLTAGE_LIMIT_MSB_SHIFT[index - 1][nr];
 	int err;
diff --git a/drivers/hwmon/nct7904.c b/drivers/hwmon/nct7904.c
index b77b82f..6153df73 100644
--- a/drivers/hwmon/nct7904.c
+++ b/drivers/hwmon/nct7904.c
@@ -412,8 +412,9 @@
 	return sprintf(buf, "%d\n", val);
 }
 
-static ssize_t store_mode(struct device *dev, struct device_attribute *devattr,
-			  const char *buf, size_t count)
+static ssize_t store_enable(struct device *dev,
+			    struct device_attribute *devattr,
+			    const char *buf, size_t count)
 {
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct nct7904_data *data = dev_get_drvdata(dev);
@@ -422,18 +423,18 @@
 
 	if (kstrtoul(buf, 10, &val) < 0)
 		return -EINVAL;
-	if (val > 1 || (val && !data->fan_mode[index]))
+	if (val < 1 || val > 2 || (val == 2 && !data->fan_mode[index]))
 		return -EINVAL;
 
 	ret = nct7904_write_reg(data, BANK_3, FANCTL1_FMR_REG + index,
-				val ? data->fan_mode[index] : 0);
+				val == 2 ? data->fan_mode[index] : 0);
 
 	return ret ? ret : count;
 }
 
-/* Return 0 for manual mode or 1 for SmartFan mode */
-static ssize_t show_mode(struct device *dev,
-			 struct device_attribute *devattr, char *buf)
+/* Return 1 for manual mode or 2 for SmartFan mode */
+static ssize_t show_enable(struct device *dev,
+			   struct device_attribute *devattr, char *buf)
 {
 	int index = to_sensor_dev_attr(devattr)->index;
 	struct nct7904_data *data = dev_get_drvdata(dev);
@@ -443,36 +444,36 @@
 	if (val < 0)
 		return val;
 
-	return sprintf(buf, "%d\n", val ? 1 : 0);
+	return sprintf(buf, "%d\n", val ? 2 : 1);
 }
 
 /* 2 attributes per channel: pwm and mode */
-static SENSOR_DEVICE_ATTR(fan1_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm1, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 0);
-static SENSOR_DEVICE_ATTR(fan1_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 0);
-static SENSOR_DEVICE_ATTR(fan2_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm1_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 0);
+static SENSOR_DEVICE_ATTR(pwm2, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 1);
-static SENSOR_DEVICE_ATTR(fan2_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 1);
-static SENSOR_DEVICE_ATTR(fan3_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm2_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 1);
+static SENSOR_DEVICE_ATTR(pwm3, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 2);
-static SENSOR_DEVICE_ATTR(fan3_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 2);
-static SENSOR_DEVICE_ATTR(fan4_pwm, S_IRUGO | S_IWUSR,
+static SENSOR_DEVICE_ATTR(pwm3_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 2);
+static SENSOR_DEVICE_ATTR(pwm4, S_IRUGO | S_IWUSR,
 			show_pwm, store_pwm, 3);
-static SENSOR_DEVICE_ATTR(fan4_mode, S_IRUGO | S_IWUSR,
-			show_mode, store_mode, 3);
+static SENSOR_DEVICE_ATTR(pwm4_enable, S_IRUGO | S_IWUSR,
+			show_enable, store_enable, 3);
 
 static struct attribute *nct7904_fanctl_attrs[] = {
-	&sensor_dev_attr_fan1_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan1_mode.dev_attr.attr,
-	&sensor_dev_attr_fan2_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan2_mode.dev_attr.attr,
-	&sensor_dev_attr_fan3_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan3_mode.dev_attr.attr,
-	&sensor_dev_attr_fan4_pwm.dev_attr.attr,
-	&sensor_dev_attr_fan4_mode.dev_attr.attr,
+	&sensor_dev_attr_pwm1.dev_attr.attr,
+	&sensor_dev_attr_pwm1_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm2.dev_attr.attr,
+	&sensor_dev_attr_pwm2_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm3.dev_attr.attr,
+	&sensor_dev_attr_pwm3_enable.dev_attr.attr,
+	&sensor_dev_attr_pwm4.dev_attr.attr,
+	&sensor_dev_attr_pwm4_enable.dev_attr.attr,
 	NULL
 };
 
diff --git a/drivers/i2c/busses/i2c-bfin-twi.c b/drivers/i2c/busses/i2c-bfin-twi.c
index af162b4..025686d 100644
--- a/drivers/i2c/busses/i2c-bfin-twi.c
+++ b/drivers/i2c/busses/i2c-bfin-twi.c
@@ -692,7 +692,7 @@
 
 	platform_set_drvdata(pdev, iface);
 
-	dev_info(&pdev->dev, "Blackfin BF5xx on-chip I2C TWI Contoller, "
+	dev_info(&pdev->dev, "Blackfin BF5xx on-chip I2C TWI Controller, "
 		"regs_base@%p\n", iface->regs_base);
 
 	return 0;
@@ -735,6 +735,6 @@
 module_exit(i2c_bfin_twi_exit);
 
 MODULE_AUTHOR("Bryan Wu, Sonic Zhang");
-MODULE_DESCRIPTION("Blackfin BF5xx on-chip I2C TWI Contoller Driver");
+MODULE_DESCRIPTION("Blackfin BF5xx on-chip I2C TWI Controller Driver");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:i2c-bfin-twi");
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index d1c22e3..fc9bf7f 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1247,7 +1247,14 @@
 	u32 reg;
 
 	reg = omap_i2c_read_reg(dev, OMAP_I2C_SYSTEST_REG);
+	/* enable test mode */
 	reg |= OMAP_I2C_SYSTEST_ST_EN;
+	/* select SDA/SCL IO mode */
+	reg |= 3 << OMAP_I2C_SYSTEST_TMODE_SHIFT;
+	/* set SCL to high-impedance state (reset value is 0) */
+	reg |= OMAP_I2C_SYSTEST_SCL_O;
+	/* set SDA to high-impedance state (reset value is 0) */
+	reg |= OMAP_I2C_SYSTEST_SDA_O;
 	omap_i2c_write_reg(dev, OMAP_I2C_SYSTEST_REG, reg);
 }
 
@@ -1257,7 +1264,11 @@
 	u32 reg;
 
 	reg = omap_i2c_read_reg(dev, OMAP_I2C_SYSTEST_REG);
+	/* restore reset values */
 	reg &= ~OMAP_I2C_SYSTEST_ST_EN;
+	reg &= ~OMAP_I2C_SYSTEST_TMODE_MASK;
+	reg &= ~OMAP_I2C_SYSTEST_SCL_O;
+	reg &= ~OMAP_I2C_SYSTEST_SDA_O;
 	omap_i2c_write_reg(dev, OMAP_I2C_SYSTEST_REG, reg);
 }
 
diff --git a/drivers/i2c/i2c-core.c b/drivers/i2c/i2c-core.c
index e6d4935..c83e4d1 100644
--- a/drivers/i2c/i2c-core.c
+++ b/drivers/i2c/i2c-core.c
@@ -567,6 +567,9 @@
 	if (bri->prepare_recovery)
 		bri->prepare_recovery(adap);
 
+	bri->set_scl(adap, val);
+	ndelay(RECOVERY_NDELAY);
+
 	/*
 	 * By this time SCL is high, as we need to give 9 falling-rising edges
 	 */
@@ -597,7 +600,6 @@
 
 int i2c_generic_scl_recovery(struct i2c_adapter *adap)
 {
-	adap->bus_recovery_info->set_scl(adap, 1);
 	return i2c_generic_recovery(adap);
 }
 EXPORT_SYMBOL_GPL(i2c_generic_scl_recovery);
@@ -1338,13 +1340,17 @@
 struct i2c_client *of_find_i2c_device_by_node(struct device_node *node)
 {
 	struct device *dev;
+	struct i2c_client *client;
 
-	dev = bus_find_device(&i2c_bus_type, NULL, node,
-					 of_dev_node_match);
+	dev = bus_find_device(&i2c_bus_type, NULL, node, of_dev_node_match);
 	if (!dev)
 		return NULL;
 
-	return i2c_verify_client(dev);
+	client = i2c_verify_client(dev);
+	if (!client)
+		put_device(dev);
+
+	return client;
 }
 EXPORT_SYMBOL(of_find_i2c_device_by_node);
 
@@ -1352,13 +1358,17 @@
 struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node)
 {
 	struct device *dev;
+	struct i2c_adapter *adapter;
 
-	dev = bus_find_device(&i2c_bus_type, NULL, node,
-					 of_dev_node_match);
+	dev = bus_find_device(&i2c_bus_type, NULL, node, of_dev_node_match);
 	if (!dev)
 		return NULL;
 
-	return i2c_verify_adapter(dev);
+	adapter = i2c_verify_adapter(dev);
+	if (!adapter)
+		put_device(dev);
+
+	return adapter;
 }
 EXPORT_SYMBOL(of_find_i2c_adapter_by_node);
 #else
diff --git a/drivers/i2c/i2c-slave-eeprom.c b/drivers/i2c/i2c-slave-eeprom.c
index 8223746..1da4496 100644
--- a/drivers/i2c/i2c-slave-eeprom.c
+++ b/drivers/i2c/i2c-slave-eeprom.c
@@ -80,9 +80,6 @@
 	struct eeprom_data *eeprom;
 	unsigned long flags;
 
-	if (off + count > attr->size)
-		return -EFBIG;
-
 	eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj));
 
 	spin_lock_irqsave(&eeprom->buffer_lock, flags);
@@ -98,9 +95,6 @@
 	struct eeprom_data *eeprom;
 	unsigned long flags;
 
-	if (off + count > attr->size)
-		return -EFBIG;
-
 	eeprom = dev_get_drvdata(container_of(kobj, struct device, kobj));
 
 	spin_lock_irqsave(&eeprom->buffer_lock, flags);
diff --git a/drivers/infiniband/hw/cxgb3/iwch_provider.c b/drivers/infiniband/hw/cxgb3/iwch_provider.c
index b1b7323..bbbe018 100644
--- a/drivers/infiniband/hw/cxgb3/iwch_provider.c
+++ b/drivers/infiniband/hw/cxgb3/iwch_provider.c
@@ -736,6 +736,10 @@
 	/*
 	 * T3 only supports 32 bits of size.
 	 */
+	if (sizeof(phys_addr_t) > 4) {
+		pr_warn_once(MOD "Cannot support dma_mrs on this platform.\n");
+		return ERR_PTR(-ENOTSUPP);
+	}
 	bl.size = 0xffffffff;
 	bl.addr = 0;
 	kva = 0;
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma.h b/drivers/infiniband/hw/ocrdma/ocrdma.h
index b396344..6a36338 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_H__
 #define __OCRDMA_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
index 1554cca..430b135 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_abi.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_ABI_H__
 #define __OCRDMA_ABI_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
index 29b2767..44766fe 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <net/neighbour.h>
 #include <net/netevent.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
index cf366fe..04a30ae 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_ah.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_AH_H__
 #define __OCRDMA_AH_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
index 47615ff..aab391a 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) CNA Adapters.              *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/sched.h>
 #include <linux/interrupt.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
index e905972..7ed885c 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_hw.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) CNA Adapters.              *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_HW_H__
 #define __OCRDMA_HW_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_main.c b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
index d98a707..b119a34 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_main.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_main.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/module.h>
 #include <linux/idr.h>
@@ -46,7 +61,7 @@
 MODULE_VERSION(OCRDMA_ROCE_DRV_VERSION);
 MODULE_DESCRIPTION(OCRDMA_ROCE_DRV_DESC " " OCRDMA_ROCE_DRV_VERSION);
 MODULE_AUTHOR("Emulex Corporation");
-MODULE_LICENSE("GPL");
+MODULE_LICENSE("Dual BSD/GPL");
 
 static LIST_HEAD(ocrdma_dev_list);
 static DEFINE_SPINLOCK(ocrdma_devlist_lock);
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
index 02ad0ae..80006b2 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_sli.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_SLI_H__
 #define __OCRDMA_SLI_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
index 48d7ef5..69334e2 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2014 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <rdma/ib_addr.h>
 #include <rdma/ib_pma.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
index 091edd6..c9e58d0 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_stats.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2014 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_STATS_H__
 #define __OCRDMA_STATS_H__
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
index 5bb61eb..bc84cd4 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.c
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #include <linux/dma-mapping.h>
 #include <rdma/ib_verbs.h>
diff --git a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
index b15c608..eaccb2d 100644
--- a/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
+++ b/drivers/infiniband/hw/ocrdma/ocrdma_verbs.h
@@ -1,21 +1,36 @@
-/*******************************************************************
- * This file is part of the Emulex RoCE Device Driver for          *
- * RoCE (RDMA over Converged Ethernet) adapters.                   *
- * Copyright (C) 2008-2012 Emulex. All rights reserved.            *
- * EMULEX and SLI are trademarks of Emulex.                        *
- * www.emulex.com                                                  *
- *                                                                 *
- * This program is free software; you can redistribute it and/or   *
- * modify it under the terms of version 2 of the GNU General       *
- * Public License as published by the Free Software Foundation.    *
- * This program is distributed in the hope that it will be useful. *
- * ALL EXPRESS OR IMPLIED CONDITIONS, REPRESENTATIONS AND          *
- * WARRANTIES, INCLUDING ANY IMPLIED WARRANTY OF MERCHANTABILITY,  *
- * FITNESS FOR A PARTICULAR PURPOSE, OR NON-INFRINGEMENT, ARE      *
- * DISCLAIMED, EXCEPT TO THE EXTENT THAT SUCH DISCLAIMERS ARE HELD *
- * TO BE LEGALLY INVALID.  See the GNU General Public License for  *
- * more details, a copy of which can be found in the file COPYING  *
- * included with this package.                                     *
+/* This file is part of the Emulex RoCE Device Driver for
+ * RoCE (RDMA over Converged Ethernet) adapters.
+ * Copyright (C) 2012-2015 Emulex. All rights reserved.
+ * EMULEX and SLI are trademarks of Emulex.
+ * www.emulex.com
+ *
+ * This software is available to you under a choice of one of two licenses.
+ * You may choose to be licensed under the terms of the GNU General Public
+ * License (GPL) Version 2, available from the file COPYING in the main
+ * directory of this source tree, or the BSD license below:
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ *
+ * - Redistributions of source code must retain the above copyright notice,
+ *   this list of conditions and the following disclaimer.
+ *
+ * - Redistributions in binary form must reproduce the above copyright
+ *   notice, this list of conditions and the following disclaimer in
+ *   the documentation and/or other materials provided with the distribution.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO,THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
+ * BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
+ * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
+ * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
+ * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  *
  * Contact Information:
  * linux-drivers@emulex.com
@@ -23,7 +38,7 @@
  * Emulex
  * 3333 Susan Street
  * Costa Mesa, CA 92626
- *******************************************************************/
+ */
 
 #ifndef __OCRDMA_VERBS_H__
 #define __OCRDMA_VERBS_H__
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index 9e6ee82..851c821 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -177,7 +177,8 @@
 		else
 			size += ipoib_recvq_size * ipoib_max_conn_qp;
 	} else
-		goto out_free_wq;
+		if (ret != -ENOSYS)
+			goto out_free_wq;
 
 	cq_attr.cqe = size;
 	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL,
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index 7717009..d851e18 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -775,6 +775,17 @@
 	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)
@@ -836,11 +847,6 @@
 
 	isert_info("conn %p\n", isert_conn);
 
-	if (!kref_get_unless_zero(&isert_conn->kref)) {
-		isert_warn("conn %p connect_release is running\n", isert_conn);
-		return;
-	}
-
 	mutex_lock(&isert_conn->mutex);
 	if (isert_conn->state != ISER_CONN_FULL_FEATURE)
 		isert_conn->state = ISER_CONN_UP;
diff --git a/drivers/input/mouse/bcm5974.c b/drivers/input/mouse/bcm5974.c
index b10709f..30e3442 100644
--- a/drivers/input/mouse/bcm5974.c
+++ b/drivers/input/mouse/bcm5974.c
@@ -2,6 +2,7 @@
  * Apple USB BCM5974 (Macbook Air and Penryn Macbook Pro) multitouch driver
  *
  * Copyright (C) 2008	   Henrik Rydberg (rydberg@euromail.se)
+ * Copyright (C) 2015      John Horan (knasher@gmail.com)
  *
  * The USB initialization and package decoding was made by
  * Scott Shawcroft as part of the touchd user-space driver project:
@@ -91,6 +92,10 @@
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI	0x0290
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_ISO	0x0291
 #define USB_DEVICE_ID_APPLE_WELLSPRING8_JIS	0x0292
+/* MacbookPro12,1 (2015) */
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI	0x0272
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_ISO	0x0273
+#define USB_DEVICE_ID_APPLE_WELLSPRING9_JIS	0x0274
 
 #define BCM5974_DEVICE(prod) {					\
 	.match_flags = (USB_DEVICE_ID_MATCH_DEVICE |		\
@@ -152,6 +157,10 @@
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ANSI),
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_ISO),
 	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING8_JIS),
+	/* MacbookPro12,1 */
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI),
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_ISO),
+	BCM5974_DEVICE(USB_DEVICE_ID_APPLE_WELLSPRING9_JIS),
 	/* Terminating entry */
 	{}
 };
@@ -180,21 +189,47 @@
 enum tp_type {
 	TYPE1,			/* plain trackpad */
 	TYPE2,			/* button integrated in trackpad */
-	TYPE3			/* additional header fields since June 2013 */
+	TYPE3,			/* additional header fields since June 2013 */
+	TYPE4			/* additional header field for pressure data */
 };
 
 /* trackpad finger data offsets, le16-aligned */
-#define FINGER_TYPE1		(13 * sizeof(__le16))
-#define FINGER_TYPE2		(15 * sizeof(__le16))
-#define FINGER_TYPE3		(19 * sizeof(__le16))
+#define HEADER_TYPE1		(13 * sizeof(__le16))
+#define HEADER_TYPE2		(15 * sizeof(__le16))
+#define HEADER_TYPE3		(19 * sizeof(__le16))
+#define HEADER_TYPE4		(23 * sizeof(__le16))
 
 /* trackpad button data offsets */
+#define BUTTON_TYPE1		0
 #define BUTTON_TYPE2		15
 #define BUTTON_TYPE3		23
+#define BUTTON_TYPE4		31
 
 /* list of device capability bits */
 #define HAS_INTEGRATED_BUTTON	1
 
+/* trackpad finger data block size */
+#define FSIZE_TYPE1		(14 * sizeof(__le16))
+#define FSIZE_TYPE2		(14 * sizeof(__le16))
+#define FSIZE_TYPE3		(14 * sizeof(__le16))
+#define FSIZE_TYPE4		(15 * sizeof(__le16))
+
+/* offset from header to finger struct */
+#define DELTA_TYPE1		(0 * sizeof(__le16))
+#define DELTA_TYPE2		(0 * sizeof(__le16))
+#define DELTA_TYPE3		(0 * sizeof(__le16))
+#define DELTA_TYPE4		(1 * sizeof(__le16))
+
+/* usb control message mode switch data */
+#define USBMSG_TYPE1		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE2		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE3		8, 0x300, 0, 0, 0x1, 0x8
+#define USBMSG_TYPE4		2, 0x302, 2, 1, 0x1, 0x0
+
+/* Wellspring initialization constants */
+#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID		1
+#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID	9
+
 /* trackpad finger structure, le16-aligned */
 struct tp_finger {
 	__le16 origin;		/* zero when switching track finger */
@@ -207,14 +242,13 @@
 	__le16 orientation;	/* 16384 when point, else 15 bit angle */
 	__le16 touch_major;	/* touch area, major axis */
 	__le16 touch_minor;	/* touch area, minor axis */
-	__le16 unused[3];	/* zeros */
+	__le16 unused[2];	/* zeros */
+	__le16 pressure;	/* pressure on forcetouch touchpad */
 	__le16 multi;		/* one finger: varies, more fingers: constant */
 } __attribute__((packed,aligned(2)));
 
 /* trackpad finger data size, empirically at least ten fingers */
 #define MAX_FINGERS		16
-#define SIZEOF_FINGER		sizeof(struct tp_finger)
-#define SIZEOF_ALL_FINGERS	(MAX_FINGERS * SIZEOF_FINGER)
 #define MAX_FINGER_ORIENTATION	16384
 
 /* device-specific parameters */
@@ -232,8 +266,17 @@
 	int bt_datalen;		/* data length of the button interface */
 	int tp_ep;		/* the endpoint of the trackpad interface */
 	enum tp_type tp_type;	/* type of trackpad interface */
-	int tp_offset;		/* offset to trackpad finger data */
+	int tp_header;		/* bytes in header block */
 	int tp_datalen;		/* data length of the trackpad interface */
+	int tp_button;		/* offset to button data */
+	int tp_fsize;		/* bytes in single finger block */
+	int tp_delta;		/* offset from header to finger struct */
+	int um_size;		/* usb control message length */
+	int um_req_val;		/* usb control message value */
+	int um_req_idx;		/* usb control message index */
+	int um_switch_idx;	/* usb control message mode switch index */
+	int um_switch_on;	/* usb control message mode switch on */
+	int um_switch_off;	/* usb control message mode switch off */
 	struct bcm5974_param p;	/* finger pressure limits */
 	struct bcm5974_param w;	/* finger width limits */
 	struct bcm5974_param x;	/* horizontal limits */
@@ -259,6 +302,24 @@
 	int slots[MAX_FINGERS];				/* slot assignments */
 };
 
+/* trackpad finger block data, le16-aligned */
+static const struct tp_finger *get_tp_finger(const struct bcm5974 *dev, int i)
+{
+	const struct bcm5974_config *c = &dev->cfg;
+	u8 *f_base = dev->tp_data + c->tp_header + c->tp_delta;
+
+	return (const struct tp_finger *)(f_base + i * c->tp_fsize);
+}
+
+#define DATAFORMAT(type)				\
+	type,						\
+	HEADER_##type,					\
+	HEADER_##type + (MAX_FINGERS) * (FSIZE_##type),	\
+	BUTTON_##type,					\
+	FSIZE_##type,					\
+	DELTA_##type,					\
+	USBMSG_##type
+
 /* logical signal quality */
 #define SN_PRESSURE	45		/* pressure signal-to-noise ratio */
 #define SN_WIDTH	25		/* width signal-to-noise ratio */
@@ -273,7 +334,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING_JIS,
 		0,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE1),
 		{ SN_PRESSURE, 0, 256 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4824, 5342 },
@@ -286,7 +347,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING2_JIS,
 		0,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE1, FINGER_TYPE1, FINGER_TYPE1 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE1),
 		{ SN_PRESSURE, 0, 256 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4824, 4824 },
@@ -299,7 +360,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING3_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4460, 5166 },
@@ -312,7 +373,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING4_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -325,7 +386,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING4A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4616, 5112 },
@@ -338,7 +399,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING5_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4415, 5050 },
@@ -351,7 +412,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING6_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -364,7 +425,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING5A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -377,7 +438,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING6A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
@@ -390,7 +451,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING7_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -403,7 +464,7 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING7A_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0x84, sizeof(struct bt_data),
-		0x81, TYPE2, FINGER_TYPE2, FINGER_TYPE2 + SIZEOF_ALL_FINGERS,
+		0x81, DATAFORMAT(TYPE2),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4750, 5280 },
@@ -416,13 +477,26 @@
 		USB_DEVICE_ID_APPLE_WELLSPRING8_JIS,
 		HAS_INTEGRATED_BUTTON,
 		0, sizeof(struct bt_data),
-		0x83, TYPE3, FINGER_TYPE3, FINGER_TYPE3 + SIZEOF_ALL_FINGERS,
+		0x83, DATAFORMAT(TYPE3),
 		{ SN_PRESSURE, 0, 300 },
 		{ SN_WIDTH, 0, 2048 },
 		{ SN_COORD, -4620, 5140 },
 		{ SN_COORD, -150, 6600 },
 		{ SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
 	},
+	{
+		USB_DEVICE_ID_APPLE_WELLSPRING9_ANSI,
+		USB_DEVICE_ID_APPLE_WELLSPRING9_ISO,
+		USB_DEVICE_ID_APPLE_WELLSPRING9_JIS,
+		HAS_INTEGRATED_BUTTON,
+		0, sizeof(struct bt_data),
+		0x83, DATAFORMAT(TYPE4),
+		{ SN_PRESSURE, 0, 300 },
+		{ SN_WIDTH, 0, 2048 },
+		{ SN_COORD, -4828, 5345 },
+		{ SN_COORD, -203, 6803 },
+		{ SN_ORIENT, -MAX_FINGER_ORIENTATION, MAX_FINGER_ORIENTATION }
+	},
 	{}
 };
 
@@ -549,19 +623,18 @@
 	struct input_dev *input = dev->input;
 	int raw_n, i, n = 0;
 
-	if (size < c->tp_offset || (size - c->tp_offset) % SIZEOF_FINGER != 0)
+	if (size < c->tp_header || (size - c->tp_header) % c->tp_fsize != 0)
 		return -EIO;
 
-	/* finger data, le16-aligned */
-	f = (const struct tp_finger *)(dev->tp_data + c->tp_offset);
-	raw_n = (size - c->tp_offset) / SIZEOF_FINGER;
+	raw_n = (size - c->tp_header) / c->tp_fsize;
 
 	for (i = 0; i < raw_n; i++) {
-		if (raw2int(f[i].touch_major) == 0)
+		f = get_tp_finger(dev, i);
+		if (raw2int(f->touch_major) == 0)
 			continue;
-		dev->pos[n].x = raw2int(f[i].abs_x);
-		dev->pos[n].y = c->y.min + c->y.max - raw2int(f[i].abs_y);
-		dev->index[n++] = &f[i];
+		dev->pos[n].x = raw2int(f->abs_x);
+		dev->pos[n].y = c->y.min + c->y.max - raw2int(f->abs_y);
+		dev->index[n++] = f;
 	}
 
 	input_mt_assign_slots(input, dev->slots, dev->pos, n, 0);
@@ -572,32 +645,22 @@
 
 	input_mt_sync_frame(input);
 
-	report_synaptics_data(input, c, f, raw_n);
+	report_synaptics_data(input, c, get_tp_finger(dev, 0), raw_n);
 
-	/* type 2 reports button events via ibt only */
-	if (c->tp_type == TYPE2) {
-		int ibt = raw2int(dev->tp_data[BUTTON_TYPE2]);
+	/* later types report button events via integrated button only */
+	if (c->caps & HAS_INTEGRATED_BUTTON) {
+		int ibt = raw2int(dev->tp_data[c->tp_button]);
 		input_report_key(input, BTN_LEFT, ibt);
 	}
 
-	if (c->tp_type == TYPE3)
-		input_report_key(input, BTN_LEFT, dev->tp_data[BUTTON_TYPE3]);
-
 	input_sync(input);
 
 	return 0;
 }
 
-/* Wellspring initialization constants */
-#define BCM5974_WELLSPRING_MODE_READ_REQUEST_ID		1
-#define BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID	9
-#define BCM5974_WELLSPRING_MODE_REQUEST_VALUE		0x300
-#define BCM5974_WELLSPRING_MODE_REQUEST_INDEX		0
-#define BCM5974_WELLSPRING_MODE_VENDOR_VALUE		0x01
-#define BCM5974_WELLSPRING_MODE_NORMAL_VALUE		0x08
-
 static int bcm5974_wellspring_mode(struct bcm5974 *dev, bool on)
 {
+	const struct bcm5974_config *c = &dev->cfg;
 	int retval = 0, size;
 	char *data;
 
@@ -605,7 +668,7 @@
 	if (dev->cfg.tp_type == TYPE3)
 		return 0;
 
-	data = kmalloc(8, GFP_KERNEL);
+	data = kmalloc(c->um_size, GFP_KERNEL);
 	if (!data) {
 		dev_err(&dev->intf->dev, "out of memory\n");
 		retval = -ENOMEM;
@@ -616,28 +679,24 @@
 	size = usb_control_msg(dev->udev, usb_rcvctrlpipe(dev->udev, 0),
 			BCM5974_WELLSPRING_MODE_READ_REQUEST_ID,
 			USB_DIR_IN | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-			BCM5974_WELLSPRING_MODE_REQUEST_VALUE,
-			BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000);
+			c->um_req_val, c->um_req_idx, data, c->um_size, 5000);
 
-	if (size != 8) {
+	if (size != c->um_size) {
 		dev_err(&dev->intf->dev, "could not read from device\n");
 		retval = -EIO;
 		goto out;
 	}
 
 	/* apply the mode switch */
-	data[0] = on ?
-		BCM5974_WELLSPRING_MODE_VENDOR_VALUE :
-		BCM5974_WELLSPRING_MODE_NORMAL_VALUE;
+	data[c->um_switch_idx] = on ? c->um_switch_on : c->um_switch_off;
 
 	/* write configuration */
 	size = usb_control_msg(dev->udev, usb_sndctrlpipe(dev->udev, 0),
 			BCM5974_WELLSPRING_MODE_WRITE_REQUEST_ID,
 			USB_DIR_OUT | USB_TYPE_CLASS | USB_RECIP_INTERFACE,
-			BCM5974_WELLSPRING_MODE_REQUEST_VALUE,
-			BCM5974_WELLSPRING_MODE_REQUEST_INDEX, data, 8, 5000);
+			c->um_req_val, c->um_req_idx, data, c->um_size, 5000);
 
-	if (size != 8) {
+	if (size != c->um_size) {
 		dev_err(&dev->intf->dev, "could not write to device\n");
 		retval = -EIO;
 		goto out;
diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
index 3a32caf..6025eb4 100644
--- a/drivers/input/mouse/synaptics.c
+++ b/drivers/input/mouse/synaptics.c
@@ -1484,12 +1484,12 @@
 	priv->pkt_type = SYN_MODEL_NEWABS(priv->model_id) ? SYN_NEWABS : SYN_OLDABS;
 
 	psmouse_info(psmouse,
-		     "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n",
+		     "Touchpad model: %ld, fw: %ld.%ld, id: %#lx, caps: %#lx/%#lx/%#lx/%#lx, board id: %lu, fw id: %lu\n",
 		     SYN_ID_MODEL(priv->identity),
 		     SYN_ID_MAJOR(priv->identity), SYN_ID_MINOR(priv->identity),
 		     priv->model_id,
 		     priv->capabilities, priv->ext_cap, priv->ext_cap_0c,
-		     priv->board_id, priv->firmware_id);
+		     priv->ext_cap_10, priv->board_id, priv->firmware_id);
 
 	set_input_params(psmouse, priv);
 
diff --git a/drivers/input/touchscreen/zforce_ts.c b/drivers/input/touchscreen/zforce_ts.c
index 80285c7..f58a196 100644
--- a/drivers/input/touchscreen/zforce_ts.c
+++ b/drivers/input/touchscreen/zforce_ts.c
@@ -429,7 +429,7 @@
 		goto unlock;
 	}
 
-	if (buf[PAYLOAD_LENGTH] == 0 || buf[PAYLOAD_LENGTH] > FRAME_MAXSIZE) {
+	if (buf[PAYLOAD_LENGTH] == 0) {
 		dev_err(&client->dev, "invalid payload length: %d\n",
 			buf[PAYLOAD_LENGTH]);
 		ret = -EIO;
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index a57e9b7..658ee39 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -76,8 +76,6 @@
  * Domain for untranslated devices - only allocated
  * if iommu=pt passed on kernel cmd line.
  */
-static struct protection_domain *pt_domain;
-
 static const struct iommu_ops amd_iommu_ops;
 
 static ATOMIC_NOTIFIER_HEAD(ppr_notifier);
@@ -96,7 +94,7 @@
 	struct protection_domain *domain; /* Domain the device is bound to */
 	u16 devid;			  /* PCI Device ID */
 	bool iommu_v2;			  /* Device can make use of IOMMUv2 */
-	bool passthrough;		  /* Default for device is pt_domain */
+	bool passthrough;		  /* Device is identity mapped */
 	struct {
 		bool enabled;
 		int qdep;
@@ -116,7 +114,6 @@
 struct kmem_cache *amd_iommu_irq_cache;
 
 static void update_domain(struct protection_domain *domain);
-static int alloc_passthrough_domain(void);
 static int protection_domain_init(struct protection_domain *domain);
 
 /****************************************************************************
@@ -2167,15 +2164,17 @@
 	dev_data = get_dev_data(dev);
 
 	if (domain->flags & PD_IOMMUV2_MASK) {
-		if (!dev_data->iommu_v2 || !dev_data->passthrough)
+		if (!dev_data->passthrough)
 			return -EINVAL;
 
-		if (pdev_iommuv2_enable(pdev) != 0)
-			return -EINVAL;
+		if (dev_data->iommu_v2) {
+			if (pdev_iommuv2_enable(pdev) != 0)
+				return -EINVAL;
 
-		dev_data->ats.enabled = true;
-		dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
-		dev_data->pri_tlp     = pci_pri_tlp_required(pdev);
+			dev_data->ats.enabled = true;
+			dev_data->ats.qdep    = pci_ats_queue_depth(pdev);
+			dev_data->pri_tlp     = pci_pri_tlp_required(pdev);
+		}
 	} else if (amd_iommu_iotlb_sup &&
 		   pci_enable_ats(pdev, PAGE_SHIFT) == 0) {
 		dev_data->ats.enabled = true;
@@ -2221,15 +2220,6 @@
 	do_detach(head);
 
 	spin_unlock_irqrestore(&domain->lock, flags);
-
-	/*
-	 * If we run in passthrough mode the device must be assigned to the
-	 * passthrough domain if it is detached from any other domain.
-	 * Make sure we can deassign from the pt_domain itself.
-	 */
-	if (dev_data->passthrough &&
-	    (dev_data->domain == NULL && domain != pt_domain))
-		__attach_device(dev_data, pt_domain);
 }
 
 /*
@@ -2249,7 +2239,7 @@
 	__detach_device(dev_data);
 	write_unlock_irqrestore(&amd_iommu_devtable_lock, flags);
 
-	if (domain->flags & PD_IOMMUV2_MASK)
+	if (domain->flags & PD_IOMMUV2_MASK && dev_data->iommu_v2)
 		pdev_iommuv2_disable(to_pci_dev(dev));
 	else if (dev_data->ats.enabled)
 		pci_disable_ats(to_pci_dev(dev));
@@ -2287,17 +2277,15 @@
 
 	BUG_ON(!dev_data);
 
-	if (dev_data->iommu_v2)
+	if (iommu_pass_through || dev_data->iommu_v2)
 		iommu_request_dm_for_dev(dev);
 
 	/* Domains are initialized for this device - have a look what we ended up with */
 	domain = iommu_get_domain_for_dev(dev);
-	if (domain->type == IOMMU_DOMAIN_IDENTITY) {
+	if (domain->type == IOMMU_DOMAIN_IDENTITY)
 		dev_data->passthrough = true;
-		dev->archdata.dma_ops = &nommu_dma_ops;
-	} else {
+	else
 		dev->archdata.dma_ops = &amd_iommu_dma_ops;
-	}
 
 out:
 	iommu_completion_wait(iommu);
@@ -2862,8 +2850,17 @@
 
 int __init amd_iommu_init_dma_ops(void)
 {
+	swiotlb        = iommu_pass_through ? 1 : 0;
 	iommu_detected = 1;
-	swiotlb = 0;
+
+	/*
+	 * In case we don't initialize SWIOTLB (actually the common case
+	 * when AMD IOMMU is enabled), make sure there are global
+	 * dma_ops set as a fall-back for devices not handled by this
+	 * driver (for example non-PCI devices).
+	 */
+	if (!swiotlb)
+		dma_ops = &nommu_dma_ops;
 
 	amd_iommu_stats_init();
 
@@ -2947,21 +2944,6 @@
 	return NULL;
 }
 
-static int alloc_passthrough_domain(void)
-{
-	if (pt_domain != NULL)
-		return 0;
-
-	/* allocate passthrough domain */
-	pt_domain = protection_domain_alloc();
-	if (!pt_domain)
-		return -ENOMEM;
-
-	pt_domain->mode = PAGE_MODE_NONE;
-
-	return 0;
-}
-
 static struct iommu_domain *amd_iommu_domain_alloc(unsigned type)
 {
 	struct protection_domain *pdomain;
@@ -3222,33 +3204,6 @@
  *
  *****************************************************************************/
 
-int __init amd_iommu_init_passthrough(void)
-{
-	struct iommu_dev_data *dev_data;
-	struct pci_dev *dev = NULL;
-	int ret;
-
-	ret = alloc_passthrough_domain();
-	if (ret)
-		return ret;
-
-	for_each_pci_dev(dev) {
-		if (!check_device(&dev->dev))
-			continue;
-
-		dev_data = get_dev_data(&dev->dev);
-		dev_data->passthrough = true;
-
-		attach_device(&dev->dev, pt_domain);
-	}
-
-	amd_iommu_stats_init();
-
-	pr_info("AMD-Vi: Initialized for Passthrough Mode\n");
-
-	return 0;
-}
-
 /* IOMMUv2 specific functions */
 int amd_iommu_register_ppr_notifier(struct notifier_block *nb)
 {
@@ -3363,7 +3318,12 @@
 		struct amd_iommu *iommu;
 		int qdep;
 
-		BUG_ON(!dev_data->ats.enabled);
+		/*
+		   There might be non-IOMMUv2 capable devices in an IOMMUv2
+		 * domain.
+		 */
+		if (!dev_data->ats.enabled)
+			continue;
 
 		qdep  = dev_data->ats.qdep;
 		iommu = amd_iommu_rlookup_table[dev_data->devid];
diff --git a/drivers/iommu/amd_iommu_init.c b/drivers/iommu/amd_iommu_init.c
index dbda9ae..a24495e 100644
--- a/drivers/iommu/amd_iommu_init.c
+++ b/drivers/iommu/amd_iommu_init.c
@@ -2026,14 +2026,6 @@
 	return true;
 }
 
-static int amd_iommu_init_dma(void)
-{
-	if (iommu_pass_through)
-		return amd_iommu_init_passthrough();
-	else
-		return amd_iommu_init_dma_ops();
-}
-
 /****************************************************************************
  *
  * AMD IOMMU Initialization State Machine
@@ -2073,7 +2065,7 @@
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_INTERRUPTS_EN;
 		break;
 	case IOMMU_INTERRUPTS_EN:
-		ret = amd_iommu_init_dma();
+		ret = amd_iommu_init_dma_ops();
 		init_state = ret ? IOMMU_INIT_ERROR : IOMMU_DMA_OPS;
 		break;
 	case IOMMU_DMA_OPS:
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index 3465faf..f7b875b 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -132,11 +132,19 @@
 
 static void free_device_state(struct device_state *dev_state)
 {
+	struct iommu_group *group;
+
 	/*
 	 * First detach device from domain - No more PRI requests will arrive
 	 * from that device after it is unbound from the IOMMUv2 domain.
 	 */
-	iommu_detach_device(dev_state->domain, &dev_state->pdev->dev);
+	group = iommu_group_get(&dev_state->pdev->dev);
+	if (WARN_ON(!group))
+		return;
+
+	iommu_detach_group(dev_state->domain, group);
+
+	iommu_group_put(group);
 
 	/* Everything is down now, free the IOMMUv2 domain */
 	iommu_domain_free(dev_state->domain);
@@ -731,6 +739,7 @@
 int amd_iommu_init_device(struct pci_dev *pdev, int pasids)
 {
 	struct device_state *dev_state;
+	struct iommu_group *group;
 	unsigned long flags;
 	int ret, tmp;
 	u16 devid;
@@ -776,10 +785,16 @@
 	if (ret)
 		goto out_free_domain;
 
-	ret = iommu_attach_device(dev_state->domain, &pdev->dev);
-	if (ret != 0)
+	group = iommu_group_get(&pdev->dev);
+	if (!group)
 		goto out_free_domain;
 
+	ret = iommu_attach_group(dev_state->domain, group);
+	if (ret != 0)
+		goto out_drop_group;
+
+	iommu_group_put(group);
+
 	spin_lock_irqsave(&state_lock, flags);
 
 	if (__get_device_state(devid) != NULL) {
@@ -794,6 +809,9 @@
 
 	return 0;
 
+out_drop_group:
+	iommu_group_put(group);
+
 out_free_domain:
 	iommu_domain_free(dev_state->domain);
 
diff --git a/drivers/macintosh/ans-lcd.c b/drivers/macintosh/ans-lcd.c
index 1a57e88..cd35079 100644
--- a/drivers/macintosh/ans-lcd.c
+++ b/drivers/macintosh/ans-lcd.c
@@ -7,7 +7,7 @@
 #include <linux/kernel.h>
 #include <linux/miscdevice.h>
 #include <linux/fcntl.h>
-#include <linux/init.h>
+#include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index b597273..bfec3bd 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -259,7 +259,7 @@
 	  the ciphers you're going to use in the cryptoapi configuration.
 
 	  For further information on dm-crypt and userspace tools see:
-	  <http://code.google.com/p/cryptsetup/wiki/DMCrypt>
+	  <https://gitlab.com/cryptsetup/cryptsetup/wikis/DMCrypt>
 
 	  To compile this code as a module, choose M here: the module will
 	  be called dm-crypt.
diff --git a/drivers/md/dm-cache-policy-smq.c b/drivers/md/dm-cache-policy-smq.c
index b6f2265..48a4a82 100644
--- a/drivers/md/dm-cache-policy-smq.c
+++ b/drivers/md/dm-cache-policy-smq.c
@@ -1686,7 +1686,7 @@
 
 	if (from_cblock(cache_size)) {
 		mq->cache_hit_bits = alloc_bitset(from_cblock(cache_size));
-		if (!mq->cache_hit_bits && mq->cache_hit_bits) {
+		if (!mq->cache_hit_bits) {
 			DMERR("couldn't allocate cache hit bitset");
 			goto bad_cache_hit_bits;
 		}
diff --git a/drivers/md/dm-cache-target.c b/drivers/md/dm-cache-target.c
index b680da5..1fe93cf 100644
--- a/drivers/md/dm-cache-target.c
+++ b/drivers/md/dm-cache-target.c
@@ -424,6 +424,7 @@
 		wake_up(&cache->migration_wait);
 
 	mempool_free(mg, cache->migration_pool);
+	wake_worker(cache);
 }
 
 static int prealloc_data_structs(struct cache *cache, struct prealloc *p)
@@ -1966,6 +1967,7 @@
 		 * this bio might require one, we pause until there are some
 		 * prepared mappings to process.
 		 */
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs)) {
 			spin_lock_irqsave(&cache->lock, flags);
 			bio_list_merge(&cache->deferred_bios, &bios);
@@ -1981,7 +1983,6 @@
 			process_discard_bio(cache, &structs, bio);
 		else
 			process_bio(cache, &structs, bio);
-		prealloc_used = true;
 	}
 
 	if (prealloc_used)
@@ -2010,6 +2011,7 @@
 		 * this bio might require one, we pause until there are some
 		 * prepared mappings to process.
 		 */
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs)) {
 			spin_lock_irqsave(&cache->lock, flags);
 			list_splice(&cells, &cache->deferred_cells);
@@ -2018,7 +2020,6 @@
 		}
 
 		process_cell(cache, &structs, cell);
-		prealloc_used = true;
 	}
 
 	if (prealloc_used)
@@ -2080,6 +2081,7 @@
 		if (policy_writeback_work(cache->policy, &oblock, &cblock, busy))
 			break; /* no work to do */
 
+		prealloc_used = true;
 		if (prealloc_data_structs(cache, &structs) ||
 		    get_cell(cache, oblock, &structs, &old_ocell)) {
 			policy_set_dirty(cache->policy, oblock);
@@ -2087,7 +2089,6 @@
 		}
 
 		writeback(cache, &structs, oblock, cblock, old_ocell);
-		prealloc_used = true;
 	}
 
 	if (prealloc_used)
diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c
index 1c50c58..d2bbe8c 100644
--- a/drivers/md/dm-thin.c
+++ b/drivers/md/dm-thin.c
@@ -666,16 +666,21 @@
 	requeue_deferred_cells(tc);
 }
 
-static void error_retry_list(struct pool *pool)
+static void error_retry_list_with_code(struct pool *pool, int error)
 {
 	struct thin_c *tc;
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(tc, &pool->active_thins, list)
-		error_thin_bio_list(tc, &tc->retry_on_resume_list, -EIO);
+		error_thin_bio_list(tc, &tc->retry_on_resume_list, error);
 	rcu_read_unlock();
 }
 
+static void error_retry_list(struct pool *pool)
+{
+	return error_retry_list_with_code(pool, -EIO);
+}
+
 /*
  * This section of code contains the logic for processing a thin device's IO.
  * Much of the code depends on pool object resources (lists, workqueues, etc)
@@ -2297,7 +2302,7 @@
 	if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) {
 		pool->pf.error_if_no_space = true;
 		notify_of_pool_mode_change_to_oods(pool);
-		error_retry_list(pool);
+		error_retry_list_with_code(pool, -ENOSPC);
 	}
 }
 
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 0c2a4e8..e25f00f 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -5759,7 +5759,7 @@
 	char *ptr;
 	int err;
 
-	file = kmalloc(sizeof(*file), GFP_NOIO);
+	file = kzalloc(sizeof(*file), GFP_NOIO);
 	if (!file)
 		return -ENOMEM;
 
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 94f5b55..967a4ed 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -1476,6 +1476,7 @@
 {
 	char b[BDEVNAME_SIZE];
 	struct r1conf *conf = mddev->private;
+	unsigned long flags;
 
 	/*
 	 * If it is not operational, then we have already marked it as dead
@@ -1495,14 +1496,13 @@
 		return;
 	}
 	set_bit(Blocked, &rdev->flags);
+	spin_lock_irqsave(&conf->device_lock, flags);
 	if (test_and_clear_bit(In_sync, &rdev->flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(&conf->device_lock, flags);
 		mddev->degraded++;
 		set_bit(Faulty, &rdev->flags);
-		spin_unlock_irqrestore(&conf->device_lock, flags);
 	} else
 		set_bit(Faulty, &rdev->flags);
+	spin_unlock_irqrestore(&conf->device_lock, flags);
 	/*
 	 * if recovery is running, make sure it aborts.
 	 */
@@ -1568,7 +1568,10 @@
 	 * Find all failed disks within the RAID1 configuration
 	 * and mark them readable.
 	 * Called under mddev lock, so rcu protection not needed.
+	 * device_lock used to avoid races with raid1_end_read_request
+	 * which expects 'In_sync' flags and ->degraded to be consistent.
 	 */
+	spin_lock_irqsave(&conf->device_lock, flags);
 	for (i = 0; i < conf->raid_disks; i++) {
 		struct md_rdev *rdev = conf->mirrors[i].rdev;
 		struct md_rdev *repl = conf->mirrors[conf->raid_disks + i].rdev;
@@ -1599,7 +1602,6 @@
 			sysfs_notify_dirent_safe(rdev->sysfs_state);
 		}
 	}
-	spin_lock_irqsave(&conf->device_lock, flags);
 	mddev->degraded -= count;
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index 643d217..f757023 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -2256,7 +2256,7 @@
 static int drop_one_stripe(struct r5conf *conf)
 {
 	struct stripe_head *sh;
-	int hash = (conf->max_nr_stripes - 1) % NR_STRIPE_HASH_LOCKS;
+	int hash = (conf->max_nr_stripes - 1) & STRIPE_HASH_LOCKS_MASK;
 
 	spin_lock_irq(conf->hash_locks + hash);
 	sh = get_free_stripe(conf, hash);
@@ -6388,7 +6388,8 @@
 
 	if (mutex_trylock(&conf->cache_size_mutex)) {
 		ret= 0;
-		while (ret < sc->nr_to_scan) {
+		while (ret < sc->nr_to_scan &&
+		       conf->max_nr_stripes > conf->min_nr_stripes) {
 			if (drop_one_stripe(conf) == 0) {
 				ret = SHRINK_STOP;
 				break;
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index 2d3db81..6ded3dc 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -438,9 +438,6 @@
 {
 	struct at24_data *at24;
 
-	if (unlikely(off >= attr->size))
-		return -EFBIG;
-
 	at24 = dev_get_drvdata(container_of(kobj, struct device, kobj));
 	return at24_write(at24, buf, off, count);
 }
diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c
index caeb395..bf9eb2e 100644
--- a/drivers/net/ethernet/cadence/macb.c
+++ b/drivers/net/ethernet/cadence/macb.c
@@ -104,6 +104,57 @@
 	return bp->rx_buffers + bp->rx_buffer_size * macb_rx_ring_wrap(index);
 }
 
+/* I/O accessors */
+static u32 hw_readl_native(struct macb *bp, int offset)
+{
+	return __raw_readl(bp->regs + offset);
+}
+
+static void hw_writel_native(struct macb *bp, int offset, u32 value)
+{
+	__raw_writel(value, bp->regs + offset);
+}
+
+static u32 hw_readl(struct macb *bp, int offset)
+{
+	return readl_relaxed(bp->regs + offset);
+}
+
+static void hw_writel(struct macb *bp, int offset, u32 value)
+{
+	writel_relaxed(value, bp->regs + offset);
+}
+
+/*
+ * Find the CPU endianness by using the loopback bit of NCR register. When the
+ * CPU is in big endian we need to program swaped mode for management
+ * descriptor access.
+ */
+static bool hw_is_native_io(void __iomem *addr)
+{
+	u32 value = MACB_BIT(LLB);
+
+	__raw_writel(value, addr + MACB_NCR);
+	value = __raw_readl(addr + MACB_NCR);
+
+	/* Write 0 back to disable everything */
+	__raw_writel(0, addr + MACB_NCR);
+
+	return value == MACB_BIT(LLB);
+}
+
+static bool hw_is_gem(void __iomem *addr, bool native_io)
+{
+	u32 id;
+
+	if (native_io)
+		id = __raw_readl(addr + MACB_MID);
+	else
+		id = readl_relaxed(addr + MACB_MID);
+
+	return MACB_BFEXT(IDNUM, id) >= 0x2;
+}
+
 static void macb_set_hwaddr(struct macb *bp)
 {
 	u32 bottom;
@@ -160,7 +211,7 @@
 		}
 	}
 
-	netdev_info(bp->dev, "invalid hw address, using random\n");
+	dev_info(&bp->pdev->dev, "invalid hw address, using random\n");
 	eth_hw_addr_random(bp->dev);
 }
 
@@ -252,7 +303,6 @@
 	struct macb *bp = netdev_priv(dev);
 	struct phy_device *phydev = bp->phy_dev;
 	unsigned long flags;
-
 	int status_change = 0;
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -449,14 +499,14 @@
 
 static void macb_update_stats(struct macb *bp)
 {
-	u32 __iomem *reg = bp->regs + MACB_PFR;
 	u32 *p = &bp->hw_stats.macb.rx_pause_frames;
 	u32 *end = &bp->hw_stats.macb.tx_pause_frames + 1;
+	int offset = MACB_PFR;
 
 	WARN_ON((unsigned long)(end - p - 1) != (MACB_TPF - MACB_PFR) / 4);
 
-	for(; p < end; p++, reg++)
-		*p += readl_relaxed(reg);
+	for(; p < end; p++, offset += 4)
+		*p += bp->macb_reg_readl(bp, offset);
 }
 
 static int macb_halt_tx(struct macb *bp)
@@ -1107,12 +1157,6 @@
 }
 #endif
 
-static inline unsigned int macb_count_tx_descriptors(struct macb *bp,
-						     unsigned int len)
-{
-	return (len + bp->max_tx_length - 1) / bp->max_tx_length;
-}
-
 static unsigned int macb_tx_map(struct macb *bp,
 				struct macb_queue *queue,
 				struct sk_buff *skb)
@@ -1263,11 +1307,11 @@
 	 * socket buffer: skb fragments of jumbo frames may need to be
 	 * splitted into many buffer descriptors.
 	 */
-	count = macb_count_tx_descriptors(bp, skb_headlen(skb));
+	count = DIV_ROUND_UP(skb_headlen(skb), bp->max_tx_length);
 	nr_frags = skb_shinfo(skb)->nr_frags;
 	for (f = 0; f < nr_frags; f++) {
 		frag_size = skb_frag_size(&skb_shinfo(skb)->frags[f]);
-		count += macb_count_tx_descriptors(bp, frag_size);
+		count += DIV_ROUND_UP(frag_size, bp->max_tx_length);
 	}
 
 	spin_lock_irqsave(&bp->lock, flags);
@@ -1603,7 +1647,6 @@
 static void macb_configure_dma(struct macb *bp)
 {
 	u32 dmacfg;
-	u32 tmp, ncr;
 
 	if (macb_is_gem(bp)) {
 		dmacfg = gem_readl(bp, DMACFG) & ~GEM_BF(RXBS, -1L);
@@ -1613,22 +1656,11 @@
 		dmacfg |= GEM_BIT(TXPBMS) | GEM_BF(RXBMS, -1L);
 		dmacfg &= ~GEM_BIT(ENDIA_PKT);
 
-		/* Find the CPU endianness by using the loopback bit of net_ctrl
-		 * register. save it first. When the CPU is in big endian we
-		 * need to program swaped mode for management descriptor access.
-		 */
-		ncr = macb_readl(bp, NCR);
-		__raw_writel(MACB_BIT(LLB), bp->regs + MACB_NCR);
-		tmp =  __raw_readl(bp->regs + MACB_NCR);
-
-		if (tmp == MACB_BIT(LLB))
+		if (bp->native_io)
 			dmacfg &= ~GEM_BIT(ENDIA_DESC);
 		else
 			dmacfg |= GEM_BIT(ENDIA_DESC); /* CPU in big endian */
 
-		/* Restore net_ctrl */
-		macb_writel(bp, NCR, ncr);
-
 		if (bp->dev->features & NETIF_F_HW_CSUM)
 			dmacfg |= GEM_BIT(TXCOEN);
 		else
@@ -1897,19 +1929,19 @@
 
 static void gem_update_stats(struct macb *bp)
 {
-	int i;
+	unsigned int i;
 	u32 *p = &bp->hw_stats.gem.tx_octets_31_0;
 
 	for (i = 0; i < GEM_STATS_LEN; ++i, ++p) {
 		u32 offset = gem_statistics[i].offset;
-		u64 val = readl_relaxed(bp->regs + offset);
+		u64 val = bp->macb_reg_readl(bp, offset);
 
 		bp->ethtool_stats[i] += val;
 		*p += val;
 
 		if (offset == GEM_OCTTXL || offset == GEM_OCTRXL) {
 			/* Add GEM_OCTTXH, GEM_OCTRXH */
-			val = readl_relaxed(bp->regs + offset + 4);
+			val = bp->macb_reg_readl(bp, offset + 4);
 			bp->ethtool_stats[i] += ((u64)val) << 32;
 			*(++p) += val;
 		}
@@ -1976,7 +2008,7 @@
 
 static void gem_get_ethtool_strings(struct net_device *dev, u32 sset, u8 *p)
 {
-	int i;
+	unsigned int i;
 
 	switch (sset) {
 	case ETH_SS_STATS:
@@ -2190,7 +2222,7 @@
 	if (dt_conf)
 		bp->caps = dt_conf->caps;
 
-	if (macb_is_gem_hw(bp->regs)) {
+	if (hw_is_gem(bp->regs, bp->native_io)) {
 		bp->caps |= MACB_CAPS_MACB_IS_GEM;
 
 		dcfg = gem_readl(bp, DCFG1);
@@ -2201,10 +2233,11 @@
 			bp->caps |= MACB_CAPS_FIFO_MODE;
 	}
 
-	netdev_dbg(bp->dev, "Cadence caps 0x%08x\n", bp->caps);
+	dev_dbg(&bp->pdev->dev, "Cadence caps 0x%08x\n", bp->caps);
 }
 
 static void macb_probe_queues(void __iomem *mem,
+			      bool native_io,
 			      unsigned int *queue_mask,
 			      unsigned int *num_queues)
 {
@@ -2219,7 +2252,7 @@
 	 * we are early in the probe process and don't have the
 	 * MACB_CAPS_MACB_IS_GEM flag positioned
 	 */
-	if (!macb_is_gem_hw(mem))
+	if (!hw_is_gem(mem, native_io))
 		return;
 
 	/* bit 0 is never set but queue 0 always exists */
@@ -2786,6 +2819,7 @@
 	struct clk *pclk, *hclk, *tx_clk;
 	unsigned int queue_mask, num_queues;
 	struct macb_platform_data *pdata;
+	bool native_io;
 	struct phy_device *phydev;
 	struct net_device *dev;
 	struct resource *regs;
@@ -2794,6 +2828,11 @@
 	struct macb *bp;
 	int err;
 
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	mem = devm_ioremap_resource(&pdev->dev, regs);
+	if (IS_ERR(mem))
+		return PTR_ERR(mem);
+
 	if (np) {
 		const struct of_device_id *match;
 
@@ -2809,14 +2848,9 @@
 	if (err)
 		return err;
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	mem = devm_ioremap_resource(&pdev->dev, regs);
-	if (IS_ERR(mem)) {
-		err = PTR_ERR(mem);
-		goto err_disable_clocks;
-	}
+	native_io = hw_is_native_io(mem);
 
-	macb_probe_queues(mem, &queue_mask, &num_queues);
+	macb_probe_queues(mem, native_io, &queue_mask, &num_queues);
 	dev = alloc_etherdev_mq(sizeof(*bp), num_queues);
 	if (!dev) {
 		err = -ENOMEM;
@@ -2831,6 +2865,14 @@
 	bp->pdev = pdev;
 	bp->dev = dev;
 	bp->regs = mem;
+	bp->native_io = native_io;
+	if (native_io) {
+		bp->macb_reg_readl = hw_readl_native;
+		bp->macb_reg_writel = hw_writel_native;
+	} else {
+		bp->macb_reg_readl = hw_readl;
+		bp->macb_reg_writel = hw_writel;
+	}
 	bp->num_queues = num_queues;
 	bp->queue_mask = queue_mask;
 	if (macb_config)
@@ -2838,9 +2880,8 @@
 	bp->pclk = pclk;
 	bp->hclk = hclk;
 	bp->tx_clk = tx_clk;
-	if (macb_config->jumbo_max_len) {
+	if (macb_config)
 		bp->jumbo_max_len = macb_config->jumbo_max_len;
-	}
 
 	spin_lock_init(&bp->lock);
 
diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h
index d746559..1895b6b 100644
--- a/drivers/net/ethernet/cadence/macb.h
+++ b/drivers/net/ethernet/cadence/macb.h
@@ -429,18 +429,12 @@
 	 | GEM_BF(name, value))
 
 /* Register access macros */
-#define macb_readl(port,reg)				\
-	readl_relaxed((port)->regs + MACB_##reg)
-#define macb_writel(port,reg,value)			\
-	writel_relaxed((value), (port)->regs + MACB_##reg)
-#define gem_readl(port, reg)				\
-	readl_relaxed((port)->regs + GEM_##reg)
-#define gem_writel(port, reg, value)			\
-	writel_relaxed((value), (port)->regs + GEM_##reg)
-#define queue_readl(queue, reg)				\
-	readl_relaxed((queue)->bp->regs + (queue)->reg)
-#define queue_writel(queue, reg, value)			\
-	writel_relaxed((value), (queue)->bp->regs + (queue)->reg)
+#define macb_readl(port, reg)		(port)->macb_reg_readl((port), MACB_##reg)
+#define macb_writel(port, reg, value)	(port)->macb_reg_writel((port), MACB_##reg, (value))
+#define gem_readl(port, reg)		(port)->macb_reg_readl((port), GEM_##reg)
+#define gem_writel(port, reg, value)	(port)->macb_reg_writel((port), GEM_##reg, (value))
+#define queue_readl(queue, reg)		(queue)->bp->macb_reg_readl((queue)->bp, (queue)->reg)
+#define queue_writel(queue, reg, value)	(queue)->bp->macb_reg_writel((queue)->bp, (queue)->reg, (value))
 
 /* Conditional GEM/MACB macros.  These perform the operation to the correct
  * register dependent on whether the device is a GEM or a MACB.  For registers
@@ -785,6 +779,11 @@
 
 struct macb {
 	void __iomem		*regs;
+	bool			native_io;
+
+	/* hardware IO accessors */
+	u32	(*macb_reg_readl)(struct macb *bp, int offset);
+	void	(*macb_reg_writel)(struct macb *bp, int offset, u32 value);
 
 	unsigned int		rx_tail;
 	unsigned int		rx_prepared_head;
@@ -817,9 +816,9 @@
 
 	struct mii_bus		*mii_bus;
 	struct phy_device	*phy_dev;
-	unsigned int 		link;
-	unsigned int 		speed;
-	unsigned int 		duplex;
+	int 			link;
+	int 			speed;
+	int 			duplex;
 
 	u32			caps;
 	unsigned int		dma_burst_length;
@@ -843,9 +842,4 @@
 	return !!(bp->caps & MACB_CAPS_MACB_IS_GEM);
 }
 
-static inline bool macb_is_gem_hw(void __iomem *addr)
-{
-	return !!(MACB_BFEXT(IDNUM, readl_relaxed(addr + MACB_MID)) >= 0x2);
-}
-
 #endif /* _MACB_H */
diff --git a/drivers/net/ethernet/cavium/thunder/nic.h b/drivers/net/ethernet/cavium/thunder/nic.h
index dda8a02..8aee250 100644
--- a/drivers/net/ethernet/cavium/thunder/nic.h
+++ b/drivers/net/ethernet/cavium/thunder/nic.h
@@ -125,6 +125,15 @@
  */
 #define NICPF_CLK_PER_INT_TICK		2
 
+/* Time to wait before we decide that a SQ is stuck.
+ *
+ * Since both pkt rx and tx notifications are done with same CQ,
+ * when packets are being received at very high rate (eg: L2 forwarding)
+ * then freeing transmitted skbs will be delayed and watchdog
+ * will kick in, resetting interface. Hence keeping this value high.
+ */
+#define	NICVF_TX_TIMEOUT		(50 * HZ)
+
 struct nicvf_cq_poll {
 	u8	cq_idx;		/* Completion queue index */
 	struct	napi_struct napi;
@@ -216,8 +225,9 @@
 	/* Tx */
 	u64 tx_frames_ok;
 	u64 tx_drops;
-	u64 tx_busy;
 	u64 tx_tso;
+	u64 txq_stop;
+	u64 txq_wake;
 };
 
 struct nicvf {
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
index 16bd2d7..a4228e6 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_ethtool.c
@@ -66,9 +66,10 @@
 	NICVF_DRV_STAT(rx_frames_jumbo),
 	NICVF_DRV_STAT(rx_drops),
 	NICVF_DRV_STAT(tx_frames_ok),
-	NICVF_DRV_STAT(tx_busy),
 	NICVF_DRV_STAT(tx_tso),
 	NICVF_DRV_STAT(tx_drops),
+	NICVF_DRV_STAT(txq_stop),
+	NICVF_DRV_STAT(txq_wake),
 };
 
 static const struct nicvf_stat nicvf_queue_stats[] = {
@@ -126,6 +127,7 @@
 
 static void nicvf_get_strings(struct net_device *netdev, u32 sset, u8 *data)
 {
+	struct nicvf *nic = netdev_priv(netdev);
 	int stats, qidx;
 
 	if (sset != ETH_SS_STATS)
@@ -141,7 +143,7 @@
 		data += ETH_GSTRING_LEN;
 	}
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "rxq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -149,7 +151,7 @@
 		}
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stats = 0; stats < nicvf_n_queue_stats; stats++) {
 			sprintf(data, "txq%d: %s", qidx,
 				nicvf_queue_stats[stats].name);
@@ -170,12 +172,14 @@
 
 static int nicvf_get_sset_count(struct net_device *netdev, int sset)
 {
+	struct nicvf *nic = netdev_priv(netdev);
+
 	if (sset != ETH_SS_STATS)
 		return -EINVAL;
 
 	return nicvf_n_hw_stats + nicvf_n_drv_stats +
 		(nicvf_n_queue_stats *
-		 (MAX_RCV_QUEUES_PER_QS + MAX_SND_QUEUES_PER_QS)) +
+		 (nic->qs->rq_cnt + nic->qs->sq_cnt)) +
 		BGX_RX_STATS_COUNT + BGX_TX_STATS_COUNT;
 }
 
@@ -197,13 +201,13 @@
 		*(data++) = ((u64 *)&nic->drv_stats)
 				[nicvf_drv_stats[stat].index];
 
-	for (qidx = 0; qidx < MAX_RCV_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->rq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->rq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
 	}
 
-	for (qidx = 0; qidx < MAX_SND_QUEUES_PER_QS; qidx++) {
+	for (qidx = 0; qidx < nic->qs->sq_cnt; qidx++) {
 		for (stat = 0; stat < nicvf_n_queue_stats; stat++)
 			*(data++) = ((u64 *)&nic->qs->sq[qidx].stats)
 					[nicvf_queue_stats[stat].index];
@@ -543,6 +547,7 @@
 {
 	struct nicvf *nic = netdev_priv(dev);
 	int err = 0;
+	bool if_up = netif_running(dev);
 
 	if (!channel->rx_count || !channel->tx_count)
 		return -EINVAL;
@@ -551,6 +556,9 @@
 	if (channel->tx_count > MAX_SND_QUEUES_PER_QS)
 		return -EINVAL;
 
+	if (if_up)
+		nicvf_stop(dev);
+
 	nic->qs->rq_cnt = channel->rx_count;
 	nic->qs->sq_cnt = channel->tx_count;
 	nic->qs->cq_cnt = max(nic->qs->rq_cnt, nic->qs->sq_cnt);
@@ -559,11 +567,9 @@
 	if (err)
 		return err;
 
-	if (!netif_running(dev))
-		return err;
+	if (if_up)
+		nicvf_open(dev);
 
-	nicvf_stop(dev);
-	nicvf_open(dev);
 	netdev_info(dev, "Setting num Tx rings to %d, Rx rings to %d success\n",
 		    nic->qs->sq_cnt, nic->qs->rq_cnt);
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
index 8b119a0..3b90afb 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c
@@ -234,7 +234,7 @@
 				    nic->duplex == DUPLEX_FULL ?
 				"Full duplex" : "Half duplex");
 			netif_carrier_on(nic->netdev);
-			netif_tx_wake_all_queues(nic->netdev);
+			netif_tx_start_all_queues(nic->netdev);
 		} else {
 			netdev_info(nic->netdev, "%s: Link is Down\n",
 				    nic->netdev->name);
@@ -425,6 +425,7 @@
 	if (skb) {
 		prefetch(skb);
 		dev_consume_skb_any(skb);
+		sq->skbuff[cqe_tx->sqe_ptr] = (u64)NULL;
 	}
 }
 
@@ -476,12 +477,13 @@
 static int nicvf_cq_intr_handler(struct net_device *netdev, u8 cq_idx,
 				 struct napi_struct *napi, int budget)
 {
-	int processed_cqe, work_done = 0;
+	int processed_cqe, work_done = 0, tx_done = 0;
 	int cqe_count, cqe_head;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct queue_set *qs = nic->qs;
 	struct cmp_queue *cq = &qs->cq[cq_idx];
 	struct cqe_rx_t *cq_desc;
+	struct netdev_queue *txq;
 
 	spin_lock_bh(&cq->lock);
 loop:
@@ -496,8 +498,8 @@
 	cqe_head = nicvf_queue_reg_read(nic, NIC_QSET_CQ_0_7_HEAD, cq_idx) >> 9;
 	cqe_head &= 0xFFFF;
 
-	netdev_dbg(nic->netdev, "%s cqe_count %d cqe_head %d\n",
-		   __func__, cqe_count, cqe_head);
+	netdev_dbg(nic->netdev, "%s CQ%d cqe_count %d cqe_head %d\n",
+		   __func__, cq_idx, cqe_count, cqe_head);
 	while (processed_cqe < cqe_count) {
 		/* Get the CQ descriptor */
 		cq_desc = (struct cqe_rx_t *)GET_CQ_DESC(cq, cqe_head);
@@ -511,8 +513,8 @@
 			break;
 		}
 
-		netdev_dbg(nic->netdev, "cq_desc->cqe_type %d\n",
-			   cq_desc->cqe_type);
+		netdev_dbg(nic->netdev, "CQ%d cq_desc->cqe_type %d\n",
+			   cq_idx, cq_desc->cqe_type);
 		switch (cq_desc->cqe_type) {
 		case CQE_TYPE_RX:
 			nicvf_rcv_pkt_handler(netdev, napi, cq,
@@ -522,6 +524,7 @@
 		case CQE_TYPE_SEND:
 			nicvf_snd_pkt_handler(netdev, cq,
 					      (void *)cq_desc, CQE_TYPE_SEND);
+			tx_done++;
 		break;
 		case CQE_TYPE_INVALID:
 		case CQE_TYPE_RX_SPLIT:
@@ -532,8 +535,9 @@
 		}
 		processed_cqe++;
 	}
-	netdev_dbg(nic->netdev, "%s processed_cqe %d work_done %d budget %d\n",
-		   __func__, processed_cqe, work_done, budget);
+	netdev_dbg(nic->netdev,
+		   "%s CQ%d processed_cqe %d work_done %d budget %d\n",
+		   __func__, cq_idx, processed_cqe, work_done, budget);
 
 	/* Ring doorbell to inform H/W to reuse processed CQEs */
 	nicvf_queue_reg_write(nic, NIC_QSET_CQ_0_7_DOOR,
@@ -543,6 +547,19 @@
 		goto loop;
 
 done:
+	/* Wakeup TXQ if its stopped earlier due to SQ full */
+	if (tx_done) {
+		txq = netdev_get_tx_queue(netdev, cq_idx);
+		if (netif_tx_queue_stopped(txq)) {
+			netif_tx_start_queue(txq);
+			nic->drv_stats.txq_wake++;
+			if (netif_msg_tx_err(nic))
+				netdev_warn(netdev,
+					    "%s: Transmit queue wakeup SQ%d\n",
+					    netdev->name, cq_idx);
+		}
+	}
+
 	spin_unlock_bh(&cq->lock);
 	return work_done;
 }
@@ -554,15 +571,10 @@
 	struct net_device *netdev = napi->dev;
 	struct nicvf *nic = netdev_priv(netdev);
 	struct nicvf_cq_poll *cq;
-	struct netdev_queue *txq;
 
 	cq = container_of(napi, struct nicvf_cq_poll, napi);
 	work_done = nicvf_cq_intr_handler(netdev, cq->cq_idx, napi, budget);
 
-	txq = netdev_get_tx_queue(netdev, cq->cq_idx);
-	if (netif_tx_queue_stopped(txq))
-		netif_tx_wake_queue(txq);
-
 	if (work_done < budget) {
 		/* Slow packet rate, exit polling */
 		napi_complete(napi);
@@ -833,9 +845,9 @@
 		return NETDEV_TX_OK;
 	}
 
-	if (!nicvf_sq_append_skb(nic, skb) && !netif_tx_queue_stopped(txq)) {
+	if (!netif_tx_queue_stopped(txq) && !nicvf_sq_append_skb(nic, skb)) {
 		netif_tx_stop_queue(txq);
-		nic->drv_stats.tx_busy++;
+		nic->drv_stats.txq_stop++;
 		if (netif_msg_tx_err(nic))
 			netdev_warn(netdev,
 				    "%s: Transmit ring full, stopping SQ%d\n",
@@ -859,7 +871,6 @@
 	nicvf_send_msg_to_pf(nic, &mbx);
 
 	netif_carrier_off(netdev);
-	netif_tx_disable(netdev);
 
 	/* Disable RBDR & QS error interrupts */
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++) {
@@ -894,6 +905,8 @@
 		kfree(cq_poll);
 	}
 
+	netif_tx_disable(netdev);
+
 	/* Free resources */
 	nicvf_config_data_transfer(nic, false);
 
@@ -988,6 +1001,9 @@
 	for (qidx = 0; qidx < qs->rbdr_cnt; qidx++)
 		nicvf_enable_intr(nic, NICVF_INTR_RBDR, qidx);
 
+	nic->drv_stats.txq_stop = 0;
+	nic->drv_stats.txq_wake = 0;
+
 	netif_carrier_on(netdev);
 	netif_tx_start_all_queues(netdev);
 
@@ -1278,6 +1294,7 @@
 	netdev->hw_features = netdev->features;
 
 	netdev->netdev_ops = &nicvf_netdev_ops;
+	netdev->watchdog_timeo = NICVF_TX_TIMEOUT;
 
 	INIT_WORK(&nic->reset_task, nicvf_reset_task);
 
@@ -1318,11 +1335,17 @@
 	pci_disable_device(pdev);
 }
 
+static void nicvf_shutdown(struct pci_dev *pdev)
+{
+	nicvf_remove(pdev);
+}
+
 static struct pci_driver nicvf_driver = {
 	.name = DRV_NAME,
 	.id_table = nicvf_id_table,
 	.probe = nicvf_probe,
 	.remove = nicvf_remove,
+	.shutdown = nicvf_shutdown,
 };
 
 static int __init nicvf_init_module(void)
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
index d69d228..ca4240a 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c
@@ -103,9 +103,11 @@
 
 	/* Allocate a new page */
 	if (!nic->rb_page) {
-		nic->rb_page = alloc_pages(gfp | __GFP_COMP, order);
+		nic->rb_page = alloc_pages(gfp | __GFP_COMP | __GFP_NOWARN,
+					   order);
 		if (!nic->rb_page) {
-			netdev_err(nic->netdev, "Failed to allocate new rcv buffer\n");
+			netdev_err(nic->netdev,
+				   "Failed to allocate new rcv buffer\n");
 			return -ENOMEM;
 		}
 		nic->rb_page_offset = 0;
@@ -382,7 +384,8 @@
 		return;
 
 	if (sq->tso_hdrs)
-		dma_free_coherent(&nic->pdev->dev, sq->dmem.q_len,
+		dma_free_coherent(&nic->pdev->dev,
+				  sq->dmem.q_len * TSO_HEADER_SIZE,
 				  sq->tso_hdrs, sq->tso_hdrs_phys);
 
 	kfree(sq->skbuff);
@@ -863,10 +866,11 @@
 			continue;
 		}
 		skb = (struct sk_buff *)sq->skbuff[sq->head];
+		if (skb)
+			dev_kfree_skb_any(skb);
 		atomic64_add(1, (atomic64_t *)&netdev->stats.tx_packets);
 		atomic64_add(hdr->tot_len,
 			     (atomic64_t *)&netdev->stats.tx_bytes);
-		dev_kfree_skb_any(skb);
 		nicvf_put_sq_desc(sq, hdr->subdesc_cnt + 1);
 	}
 }
@@ -992,7 +996,7 @@
 
 	memset(gather, 0, SND_QUEUE_DESC_SIZE);
 	gather->subdesc_type = SQ_DESC_TYPE_GATHER;
-	gather->ld_type = NIC_SEND_LD_TYPE_E_LDWB;
+	gather->ld_type = NIC_SEND_LD_TYPE_E_LDD;
 	gather->size = size;
 	gather->addr = data;
 }
@@ -1048,7 +1052,7 @@
 		}
 		nicvf_sq_add_hdr_subdesc(sq, hdr_qentry,
 					 seg_subdescs - 1, skb, seg_len);
-		sq->skbuff[hdr_qentry] = 0;
+		sq->skbuff[hdr_qentry] = (u64)NULL;
 		qentry = nicvf_get_nxt_sqentry(sq, qentry);
 
 		desc_cnt += seg_subdescs;
@@ -1062,6 +1066,7 @@
 	/* Inform HW to xmit all TSO segments */
 	nicvf_queue_reg_write(nic, NIC_QSET_SQ_0_7_DOOR,
 			      skb_get_queue_mapping(skb), desc_cnt);
+	nic->drv_stats.tx_tso++;
 	return 1;
 }
 
diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
index 8341bdf..f0937b7 100644
--- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
+++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.h
@@ -62,7 +62,7 @@
 #define SND_QUEUE_CNT		8
 #define CMP_QUEUE_CNT		8 /* Max of RCV and SND qcount */
 
-#define SND_QSIZE		SND_QUEUE_SIZE4
+#define SND_QSIZE		SND_QUEUE_SIZE2
 #define SND_QUEUE_LEN		(1ULL << (SND_QSIZE + 10))
 #define MAX_SND_QUEUE_LEN	(1ULL << (SND_QUEUE_SIZE6 + 10))
 #define SND_QUEUE_THRESH	2ULL
@@ -70,7 +70,10 @@
 /* Since timestamp not enabled, otherwise 2 */
 #define MAX_CQE_PER_PKT_XMIT		1
 
-#define CMP_QSIZE		CMP_QUEUE_SIZE4
+/* Keep CQ and SQ sizes same, if timestamping
+ * is enabled this equation will change.
+ */
+#define CMP_QSIZE		CMP_QUEUE_SIZE2
 #define CMP_QUEUE_LEN		(1ULL << (CMP_QSIZE + 10))
 #define CMP_QUEUE_CQE_THRESH	0
 #define CMP_QUEUE_TIMER_THRESH	220 /* 10usec */
@@ -87,7 +90,12 @@
 
 #define MAX_CQES_FOR_TX		((SND_QUEUE_LEN / MIN_SQ_DESC_PER_PKT_XMIT) * \
 				 MAX_CQE_PER_PKT_XMIT)
-#define RQ_CQ_DROP		((CMP_QUEUE_LEN - MAX_CQES_FOR_TX) / 256)
+/* Calculate number of CQEs to reserve for all SQEs.
+ * Its 1/256th level of CQ size.
+ * '+ 1' to account for pipelining
+ */
+#define RQ_CQ_DROP		((256 / (CMP_QUEUE_LEN / \
+				 (CMP_QUEUE_LEN - MAX_CQES_FOR_TX))) + 1)
 
 /* Descriptor size in bytes */
 #define SND_QUEUE_DESC_SIZE	16
diff --git a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
index 633ec05..b961a89 100644
--- a/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
+++ b/drivers/net/ethernet/cavium/thunder/thunder_bgx.c
@@ -673,7 +673,10 @@
 	bgx_reg_write(bgx, lmacid, BGX_CMRX_CFG, cmrx_cfg);
 	bgx_flush_dmac_addrs(bgx, lmacid);
 
-	if (lmac->phydev)
+	if ((bgx->lmac_type != BGX_MODE_XFI) &&
+	    (bgx->lmac_type != BGX_MODE_XLAUI) &&
+	    (bgx->lmac_type != BGX_MODE_40G_KR) &&
+	    (bgx->lmac_type != BGX_MODE_10G_KR) && lmac->phydev)
 		phy_disconnect(lmac->phydev);
 
 	lmac->phydev = NULL;
diff --git a/drivers/net/ethernet/freescale/fec.h b/drivers/net/ethernet/freescale/fec.h
index 1eee73c..99d33e2 100644
--- a/drivers/net/ethernet/freescale/fec.h
+++ b/drivers/net/ethernet/freescale/fec.h
@@ -562,6 +562,7 @@
 };
 
 void fec_ptp_init(struct platform_device *pdev);
+void fec_ptp_stop(struct platform_device *pdev);
 void fec_ptp_start_cyclecounter(struct net_device *ndev);
 int fec_ptp_set(struct net_device *ndev, struct ifreq *ifr);
 int fec_ptp_get(struct net_device *ndev, struct ifreq *ifr);
diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
index 1f89c59..32e3807c 100644
--- a/drivers/net/ethernet/freescale/fec_main.c
+++ b/drivers/net/ethernet/freescale/fec_main.c
@@ -24,6 +24,7 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
+#include <linux/pm_runtime.h>
 #include <linux/ptrace.h>
 #include <linux/errno.h>
 #include <linux/ioport.h>
@@ -77,6 +78,7 @@
 #define FEC_ENET_RAEM_V	0x8
 #define FEC_ENET_RAFL_V	0x8
 #define FEC_ENET_OPD_V	0xFFF0
+#define FEC_MDIO_PM_TIMEOUT  100 /* ms */
 
 static struct platform_device_id fec_devtype[] = {
 	{
@@ -1767,7 +1769,13 @@
 static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret = 0;
+
+	ret = pm_runtime_get_sync(dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
 
 	fep->mii_timeout = 0;
 	init_completion(&fep->mdio_done);
@@ -1783,18 +1791,30 @@
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO read timeout\n");
-		return -ETIMEDOUT;
+		ret = -ETIMEDOUT;
+		goto out;
 	}
 
-	/* return value */
-	return FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+	ret = FEC_MMFR_DATA(readl(fep->hwp + FEC_MII_DATA));
+
+out:
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum,
 			   u16 value)
 {
 	struct fec_enet_private *fep = bus->priv;
+	struct device *dev = &fep->pdev->dev;
 	unsigned long time_left;
+	int ret = 0;
+
+	ret = pm_runtime_get_sync(dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
 
 	fep->mii_timeout = 0;
 	init_completion(&fep->mdio_done);
@@ -1811,10 +1831,13 @@
 	if (time_left == 0) {
 		fep->mii_timeout = 1;
 		netdev_err(fep->netdev, "MDIO write timeout\n");
-		return -ETIMEDOUT;
+		ret  = -ETIMEDOUT;
 	}
 
-	return 0;
+	pm_runtime_mark_last_busy(dev);
+	pm_runtime_put_autosuspend(dev);
+
+	return ret;
 }
 
 static int fec_enet_clk_enable(struct net_device *ndev, bool enable)
@@ -1826,9 +1849,6 @@
 		ret = clk_prepare_enable(fep->clk_ahb);
 		if (ret)
 			return ret;
-		ret = clk_prepare_enable(fep->clk_ipg);
-		if (ret)
-			goto failed_clk_ipg;
 		if (fep->clk_enet_out) {
 			ret = clk_prepare_enable(fep->clk_enet_out);
 			if (ret)
@@ -1852,7 +1872,6 @@
 		}
 	} else {
 		clk_disable_unprepare(fep->clk_ahb);
-		clk_disable_unprepare(fep->clk_ipg);
 		if (fep->clk_enet_out)
 			clk_disable_unprepare(fep->clk_enet_out);
 		if (fep->clk_ptp) {
@@ -1874,8 +1893,6 @@
 	if (fep->clk_enet_out)
 		clk_disable_unprepare(fep->clk_enet_out);
 failed_clk_enet_out:
-		clk_disable_unprepare(fep->clk_ipg);
-failed_clk_ipg:
 		clk_disable_unprepare(fep->clk_ahb);
 
 	return ret;
@@ -2847,10 +2864,14 @@
 	struct fec_enet_private *fep = netdev_priv(ndev);
 	int ret;
 
+	ret = pm_runtime_get_sync(&fep->pdev->dev);
+	if (IS_ERR_VALUE(ret))
+		return ret;
+
 	pinctrl_pm_select_default_state(&fep->pdev->dev);
 	ret = fec_enet_clk_enable(ndev, true);
 	if (ret)
-		return ret;
+		goto clk_enable;
 
 	/* I should reset the ring buffers here, but I don't yet know
 	 * a simple way to do that.
@@ -2881,6 +2902,9 @@
 	fec_enet_free_buffers(ndev);
 err_enet_alloc:
 	fec_enet_clk_enable(ndev, false);
+clk_enable:
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
 	return ret;
 }
@@ -2903,6 +2927,9 @@
 
 	fec_enet_clk_enable(ndev, false);
 	pinctrl_pm_select_sleep_state(&fep->pdev->dev);
+	pm_runtime_mark_last_busy(&fep->pdev->dev);
+	pm_runtime_put_autosuspend(&fep->pdev->dev);
+
 	fec_enet_free_buffers(ndev);
 
 	return 0;
@@ -3115,8 +3142,8 @@
 			fep->bufdesc_size;
 
 	/* Allocate memory for buffer descriptors. */
-	cbd_base = dma_alloc_coherent(NULL, bd_size, &bd_dma,
-				      GFP_KERNEL);
+	cbd_base = dmam_alloc_coherent(&fep->pdev->dev, bd_size, &bd_dma,
+				       GFP_KERNEL);
 	if (!cbd_base) {
 		return -ENOMEM;
 	}
@@ -3388,6 +3415,10 @@
 	if (ret)
 		goto failed_clk;
 
+	ret = clk_prepare_enable(fep->clk_ipg);
+	if (ret)
+		goto failed_clk_ipg;
+
 	fep->reg_phy = devm_regulator_get(&pdev->dev, "phy");
 	if (!IS_ERR(fep->reg_phy)) {
 		ret = regulator_enable(fep->reg_phy);
@@ -3400,6 +3431,11 @@
 		fep->reg_phy = NULL;
 	}
 
+	pm_runtime_set_autosuspend_delay(&pdev->dev, FEC_MDIO_PM_TIMEOUT);
+	pm_runtime_use_autosuspend(&pdev->dev);
+	pm_runtime_set_active(&pdev->dev);
+	pm_runtime_enable(&pdev->dev);
+
 	fec_reset_phy(pdev);
 
 	if (fep->bufdesc_ex)
@@ -3447,6 +3483,10 @@
 
 	fep->rx_copybreak = COPYBREAK_DEFAULT;
 	INIT_WORK(&fep->tx_timeout_work, fec_enet_timeout_work);
+
+	pm_runtime_mark_last_busy(&pdev->dev);
+	pm_runtime_put_autosuspend(&pdev->dev);
+
 	return 0;
 
 failed_register:
@@ -3454,9 +3494,12 @@
 failed_mii_init:
 failed_irq:
 failed_init:
+	fec_ptp_stop(pdev);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
 failed_regulator:
+	clk_disable_unprepare(fep->clk_ipg);
+failed_clk_ipg:
 	fec_enet_clk_enable(ndev, false);
 failed_clk:
 failed_phy:
@@ -3473,14 +3516,12 @@
 	struct net_device *ndev = platform_get_drvdata(pdev);
 	struct fec_enet_private *fep = netdev_priv(ndev);
 
-	cancel_delayed_work_sync(&fep->time_keep);
 	cancel_work_sync(&fep->tx_timeout_work);
+	fec_ptp_stop(pdev);
 	unregister_netdev(ndev);
 	fec_enet_mii_remove(fep);
 	if (fep->reg_phy)
 		regulator_disable(fep->reg_phy);
-	if (fep->ptp_clock)
-		ptp_clock_unregister(fep->ptp_clock);
 	of_node_put(fep->phy_node);
 	free_netdev(ndev);
 
@@ -3568,7 +3609,28 @@
 	return ret;
 }
 
-static SIMPLE_DEV_PM_OPS(fec_pm_ops, fec_suspend, fec_resume);
+static int __maybe_unused fec_runtime_suspend(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	clk_disable_unprepare(fep->clk_ipg);
+
+	return 0;
+}
+
+static int __maybe_unused fec_runtime_resume(struct device *dev)
+{
+	struct net_device *ndev = dev_get_drvdata(dev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	return clk_prepare_enable(fep->clk_ipg);
+}
+
+static const struct dev_pm_ops fec_pm_ops = {
+	SET_SYSTEM_SLEEP_PM_OPS(fec_suspend, fec_resume)
+	SET_RUNTIME_PM_OPS(fec_runtime_suspend, fec_runtime_resume, NULL)
+};
 
 static struct platform_driver fec_driver = {
 	.driver	= {
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index a15663a..f457a23 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -604,6 +604,16 @@
 	schedule_delayed_work(&fep->time_keep, HZ);
 }
 
+void fec_ptp_stop(struct platform_device *pdev)
+{
+	struct net_device *ndev = platform_get_drvdata(pdev);
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	cancel_delayed_work_sync(&fep->time_keep);
+	if (fep->ptp_clock)
+		ptp_clock_unregister(fep->ptp_clock);
+}
+
 /**
  * fec_ptp_check_pps_event
  * @fep: the fec_enet_private structure handle
diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c
index ff87502..2b7610f 100644
--- a/drivers/net/ethernet/freescale/gianfar.c
+++ b/drivers/net/ethernet/freescale/gianfar.c
@@ -565,22 +565,6 @@
 	}
 }
 
-static void lock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_lock(&priv->tx_queue[i]->txlock);
-}
-
-static void unlock_tx_qs(struct gfar_private *priv)
-{
-	int i;
-
-	for (i = 0; i < priv->num_tx_queues; i++)
-		spin_unlock(&priv->tx_queue[i]->txlock);
-}
-
 static int gfar_alloc_tx_queues(struct gfar_private *priv)
 {
 	int i;
@@ -1376,7 +1360,6 @@
 	priv->dev = &ofdev->dev;
 	SET_NETDEV_DEV(dev, &ofdev->dev);
 
-	spin_lock_init(&priv->bflock);
 	INIT_WORK(&priv->reset_task, gfar_reset_task);
 
 	platform_set_drvdata(ofdev, priv);
@@ -1470,9 +1453,8 @@
 		goto register_fail;
 	}
 
-	device_init_wakeup(&dev->dev,
-			   priv->device_flags &
-			   FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
+	device_set_wakeup_capable(&dev->dev, priv->device_flags &
+				  FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
 	/* fill out IRQ number and name fields */
 	for (i = 0; i < priv->num_grps; i++) {
@@ -1540,48 +1522,37 @@
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
-
 	int magic_packet = priv->wol_en &&
 			   (priv->device_flags &
 			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
+	if (!netif_running(ndev))
+		return 0;
+
+	disable_napi(priv);
+	netif_tx_lock(ndev);
 	netif_device_detach(ndev);
+	netif_tx_unlock(ndev);
 
-	if (netif_running(ndev)) {
+	gfar_halt(priv);
 
-		local_irq_save(flags);
-		lock_tx_qs(priv);
+	if (magic_packet) {
+		/* Enable interrupt on Magic Packet */
+		gfar_write(&regs->imask, IMASK_MAG);
 
-		gfar_halt_nodisable(priv);
+		/* Enable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval |= MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
 
-		/* Disable Tx, and Rx if wake-on-LAN is disabled. */
+		/* re-enable the Rx block */
 		tempval = gfar_read(&regs->maccfg1);
-
-		tempval &= ~MACCFG1_TX_EN;
-
-		if (!magic_packet)
-			tempval &= ~MACCFG1_RX_EN;
-
+		tempval |= MACCFG1_RX_EN;
 		gfar_write(&regs->maccfg1, tempval);
 
-		unlock_tx_qs(priv);
-		local_irq_restore(flags);
-
-		disable_napi(priv);
-
-		if (magic_packet) {
-			/* Enable interrupt on Magic Packet */
-			gfar_write(&regs->imask, IMASK_MAG);
-
-			/* Enable Magic Packet mode */
-			tempval = gfar_read(&regs->maccfg2);
-			tempval |= MACCFG2_MPEN;
-			gfar_write(&regs->maccfg2, tempval);
-		} else {
-			phy_stop(priv->phydev);
-		}
+	} else {
+		phy_stop(priv->phydev);
 	}
 
 	return 0;
@@ -1592,37 +1563,26 @@
 	struct gfar_private *priv = dev_get_drvdata(dev);
 	struct net_device *ndev = priv->ndev;
 	struct gfar __iomem *regs = priv->gfargrp[0].regs;
-	unsigned long flags;
 	u32 tempval;
 	int magic_packet = priv->wol_en &&
 			   (priv->device_flags &
 			    FSL_GIANFAR_DEV_HAS_MAGIC_PACKET);
 
-	if (!netif_running(ndev)) {
-		netif_device_attach(ndev);
+	if (!netif_running(ndev))
 		return 0;
-	}
 
-	if (!magic_packet && priv->phydev)
+	if (magic_packet) {
+		/* Disable Magic Packet mode */
+		tempval = gfar_read(&regs->maccfg2);
+		tempval &= ~MACCFG2_MPEN;
+		gfar_write(&regs->maccfg2, tempval);
+	} else {
 		phy_start(priv->phydev);
-
-	/* Disable Magic Packet mode, in case something
-	 * else woke us up.
-	 */
-	local_irq_save(flags);
-	lock_tx_qs(priv);
-
-	tempval = gfar_read(&regs->maccfg2);
-	tempval &= ~MACCFG2_MPEN;
-	gfar_write(&regs->maccfg2, tempval);
+	}
 
 	gfar_start(priv);
 
-	unlock_tx_qs(priv);
-	local_irq_restore(flags);
-
 	netif_device_attach(ndev);
-
 	enable_napi(priv);
 
 	return 0;
@@ -2045,7 +2005,8 @@
 		/* Install our interrupt handlers for Error,
 		 * Transmit, and Receive
 		 */
-		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0,
+		err = request_irq(gfar_irq(grp, ER)->irq, gfar_error,
+				  IRQF_NO_SUSPEND,
 				  gfar_irq(grp, ER)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2068,7 +2029,8 @@
 			goto rx_irq_fail;
 		}
 	} else {
-		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0,
+		err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt,
+				  IRQF_NO_SUSPEND,
 				  gfar_irq(grp, TX)->name, grp);
 		if (err < 0) {
 			netif_err(priv, intr, dev, "Can't get IRQ %d\n",
@@ -2169,8 +2131,6 @@
 	if (err)
 		return err;
 
-	device_set_wakeup_enable(&dev->dev, priv->wol_en);
-
 	return err;
 }
 
diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h
index daa1d37..5545e41 100644
--- a/drivers/net/ethernet/freescale/gianfar.h
+++ b/drivers/net/ethernet/freescale/gianfar.h
@@ -1145,9 +1145,6 @@
 	int oldduplex;
 	int oldlink;
 
-	/* Bitfield update lock */
-	spinlock_t bflock;
-
 	uint32_t msg_enable;
 
 	struct work_struct reset_task;
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index fda12fb..3c0a8f8 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -653,7 +653,6 @@
 static int gfar_set_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
 {
 	struct gfar_private *priv = netdev_priv(dev);
-	unsigned long flags;
 
 	if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) &&
 	    wol->wolopts != 0)
@@ -664,9 +663,7 @@
 
 	device_set_wakeup_enable(&dev->dev, wol->wolopts & WAKE_MAGIC);
 
-	spin_lock_irqsave(&priv->bflock, flags);
-	priv->wol_en =  !!device_may_wakeup(&dev->dev);
-	spin_unlock_irqrestore(&priv->bflock, flags);
+	priv->wol_en = !!device_may_wakeup(&dev->dev);
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index 8204013..0a32020 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -686,6 +686,7 @@
 {
 	struct mlx4_cmd *cmd = &mlx4_priv(dev)->cmd;
 	struct mlx4_cmd_context *context;
+	long ret_wait;
 	int err = 0;
 
 	down(&cmd->event_sem);
@@ -711,8 +712,20 @@
 	if (err)
 		goto out_reset;
 
-	if (!wait_for_completion_timeout(&context->done,
-					 msecs_to_jiffies(timeout))) {
+	if (op == MLX4_CMD_SENSE_PORT) {
+		ret_wait =
+			wait_for_completion_interruptible_timeout(&context->done,
+								  msecs_to_jiffies(timeout));
+		if (ret_wait < 0) {
+			context->fw_status = 0;
+			context->out_param = 0;
+			context->result = 0;
+		}
+	} else {
+		ret_wait = (long)wait_for_completion_timeout(&context->done,
+							     msecs_to_jiffies(timeout));
+	}
+	if (!ret_wait) {
 		mlx4_warn(dev, "command 0x%x timed out (go bit not cleared)\n",
 			  op);
 		if (op == MLX4_CMD_NOP) {
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index 7a4f20b..9c145dd 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -246,7 +246,6 @@
 
 static inline bool mlx4_en_is_ring_empty(struct mlx4_en_rx_ring *ring)
 {
-	BUG_ON((u32)(ring->prod - ring->cons) > ring->actual_size);
 	return ring->prod == ring->cons;
 }
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c
index aae13ad..8e81e53 100644
--- a/drivers/net/ethernet/mellanox/mlx4/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx4/eq.c
@@ -601,7 +601,7 @@
 							continue;
 						mlx4_dbg(dev, "%s: Sending MLX4_PORT_CHANGE_SUBTYPE_DOWN to slave: %d, port:%d\n",
 							 __func__, i, port);
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
@@ -640,7 +640,7 @@
 							continue;
 						if (i == mlx4_master_func_num(dev))
 							continue;
-						s_info = &priv->mfunc.master.vf_oper[slave].vport[port].state;
+						s_info = &priv->mfunc.master.vf_oper[i].vport[port].state;
 						if (IFLA_VF_LINK_STATE_AUTO == s_info->link_state) {
 							eqe->event.port_change.port =
 								cpu_to_be32(
diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c
index 12fbfcb..29c2a01 100644
--- a/drivers/net/ethernet/mellanox/mlx4/main.c
+++ b/drivers/net/ethernet/mellanox/mlx4/main.c
@@ -2273,6 +2273,11 @@
 		} else if (err == -ENOENT) {
 			err = 0;
 			continue;
+		} else if (mlx4_is_slave(dev) && err == -EINVAL) {
+			priv->def_counter[port] = MLX4_SINK_COUNTER_INDEX(dev);
+			mlx4_warn(dev, "can't allocate counter from old PF driver, using index %d\n",
+				  MLX4_SINK_COUNTER_INDEX(dev));
+			err = 0;
 		} else {
 			mlx4_err(dev, "%s: failed to allocate default counter port %d err %d\n",
 				 __func__, port + 1, err);
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
index 33669c2..753ea8b 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_83xx_init.c
@@ -1415,7 +1415,7 @@
 	if (fw->size & 0xF) {
 		addr = dest + size;
 		for (i = 0; i < (fw->size & 0xF); i++)
-			data[i] = temp[size + i];
+			data[i] = ((u8 *)temp)[size + i];
 		for (; i < 16; i++)
 			data[i] = 0;
 		ret = qlcnic_ms_mem_write128(adapter, addr,
diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
index f3918c7..bcdc895 100644
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c
@@ -413,3 +413,7 @@
 SIMPLE_DEV_PM_OPS(stmmac_pltfr_pm_ops, stmmac_pltfr_suspend,
 				       stmmac_pltfr_resume);
 EXPORT_SYMBOL_GPL(stmmac_pltfr_pm_ops);
+
+MODULE_DESCRIPTION("STMMAC 10/100/1000 Ethernet platform support");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c
index 0c5842a..ab6051a 100644
--- a/drivers/net/ethernet/sun/niu.c
+++ b/drivers/net/ethernet/sun/niu.c
@@ -6658,10 +6658,8 @@
 		struct sk_buff *skb_new;
 
 		skb_new = skb_realloc_headroom(skb, len);
-		if (!skb_new) {
-			rp->tx_errors++;
+		if (!skb_new)
 			goto out_drop;
-		}
 		kfree_skb(skb);
 		skb = skb_new;
 	} else
diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h
index bbacf5c..a8a7306 100644
--- a/drivers/net/ethernet/ti/netcp.h
+++ b/drivers/net/ethernet/ti/netcp.h
@@ -223,6 +223,7 @@
 
 /* SGMII functions */
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port);
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set);
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port);
 int netcp_sgmii_config(void __iomem *sgmii_ofs, int port, u32 interface);
 
diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c
index ec8ed30..9749dfd 100644
--- a/drivers/net/ethernet/ti/netcp_core.c
+++ b/drivers/net/ethernet/ti/netcp_core.c
@@ -2112,6 +2112,7 @@
 static int netcp_remove(struct platform_device *pdev)
 {
 	struct netcp_device *netcp_device = platform_get_drvdata(pdev);
+	struct netcp_intf *netcp_intf, *netcp_tmp;
 	struct netcp_inst_modpriv *inst_modpriv, *tmp;
 	struct netcp_module *module;
 
@@ -2123,10 +2124,17 @@
 		list_del(&inst_modpriv->inst_list);
 		kfree(inst_modpriv);
 	}
-	WARN(!list_empty(&netcp_device->interface_head), "%s interface list not empty!\n",
-	     pdev->name);
 
-	devm_kfree(&pdev->dev, netcp_device);
+	/* now that all modules are removed, clean up the interfaces */
+	list_for_each_entry_safe(netcp_intf, netcp_tmp,
+				 &netcp_device->interface_head,
+				 interface_list) {
+		netcp_delete_interface(netcp_device, netcp_intf->ndev);
+	}
+
+	WARN(!list_empty(&netcp_device->interface_head),
+	     "%s interface list not empty!\n", pdev->name);
+
 	pm_runtime_put_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 	platform_set_drvdata(pdev, NULL);
diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c
index 9b7e0a3..1974a8a 100644
--- a/drivers/net/ethernet/ti/netcp_ethss.c
+++ b/drivers/net/ethernet/ti/netcp_ethss.c
@@ -1901,11 +1901,28 @@
 	writel(slave->mac_control, GBE_REG_ADDR(slave, emac_regs, mac_control));
 }
 
+static void gbe_sgmii_rtreset(struct gbe_priv *priv,
+			      struct gbe_slave *slave, bool set)
+{
+	void __iomem *sgmii_port_regs;
+
+	if (SLAVE_LINK_IS_XGMII(slave))
+		return;
+
+	if ((priv->ss_version == GBE_SS_VERSION_14) && (slave->slave_num >= 2))
+		sgmii_port_regs = priv->sgmii_port34_regs;
+	else
+		sgmii_port_regs = priv->sgmii_port_regs;
+
+	netcp_sgmii_rtreset(sgmii_port_regs, slave->slave_num, set);
+}
+
 static void gbe_slave_stop(struct gbe_intf *intf)
 {
 	struct gbe_priv *gbe_dev = intf->gbe_dev;
 	struct gbe_slave *slave = intf->slave;
 
+	gbe_sgmii_rtreset(gbe_dev, slave, true);
 	gbe_port_reset(slave);
 	/* Disable forwarding */
 	cpsw_ale_control_set(gbe_dev->ale, slave->port_num,
@@ -1947,6 +1964,7 @@
 
 	gbe_sgmii_config(priv, slave);
 	gbe_port_reset(slave);
+	gbe_sgmii_rtreset(priv, slave, false);
 	gbe_port_config(priv, slave, priv->rx_packet_max);
 	gbe_set_slave_mac(slave, gbe_intf);
 	/* enable forwarding */
@@ -2490,10 +2508,9 @@
 {
 	struct gbe_slave *slave;
 
-	for (;;) {
+	while (!list_empty(&gbe_dev->secondary_slaves)) {
 		slave = first_sec_slave(gbe_dev);
-		if (!slave)
-			break;
+
 		if (slave->phy)
 			phy_disconnect(slave->phy);
 		list_del(&slave->slave_list);
@@ -2839,14 +2856,13 @@
 				      &gbe_dev->dma_chan_name);
 	if (ret < 0) {
 		dev_err(dev, "missing \"tx-channel\" parameter\n");
-		ret = -ENODEV;
-		goto quit;
+		return -EINVAL;
 	}
 
 	if (!strcmp(node->name, "gbe")) {
 		ret = get_gbe_resource_version(gbe_dev, node);
 		if (ret)
-			goto quit;
+			return ret;
 
 		dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version);
 
@@ -2857,22 +2873,20 @@
 		else
 			ret = -ENODEV;
 
-		if (ret)
-			goto quit;
 	} else if (!strcmp(node->name, "xgbe")) {
 		ret = set_xgbe_ethss10_priv(gbe_dev, node);
 		if (ret)
-			goto quit;
+			return ret;
 		ret = netcp_xgbe_serdes_init(gbe_dev->xgbe_serdes_regs,
 					     gbe_dev->ss_regs);
-		if (ret)
-			goto quit;
 	} else {
 		dev_err(dev, "unknown GBE node(%s)\n", node->name);
 		ret = -ENODEV;
-		goto quit;
 	}
 
+	if (ret)
+		return ret;
+
 	interfaces = of_get_child_by_name(node, "interfaces");
 	if (!interfaces)
 		dev_err(dev, "could not find interfaces\n");
@@ -2880,11 +2894,11 @@
 	ret = netcp_txpipe_init(&gbe_dev->tx_pipe, netcp_device,
 				gbe_dev->dma_chan_name, gbe_dev->tx_queue_id);
 	if (ret)
-		goto quit;
+		return ret;
 
 	ret = netcp_txpipe_open(&gbe_dev->tx_pipe);
 	if (ret)
-		goto quit;
+		return ret;
 
 	/* Create network interfaces */
 	INIT_LIST_HEAD(&gbe_dev->gbe_intf_head);
@@ -2899,6 +2913,7 @@
 		if (gbe_dev->num_slaves >= gbe_dev->max_num_slaves)
 			break;
 	}
+	of_node_put(interfaces);
 
 	if (!gbe_dev->num_slaves)
 		dev_warn(dev, "No network interface configured\n");
@@ -2911,9 +2926,10 @@
 	of_node_put(secondary_ports);
 
 	if (!gbe_dev->num_slaves) {
-		dev_err(dev, "No network interface or secondary ports configured\n");
+		dev_err(dev,
+			"No network interface or secondary ports configured\n");
 		ret = -ENODEV;
-		goto quit;
+		goto free_sec_ports;
 	}
 
 	memset(&ale_params, 0, sizeof(ale_params));
@@ -2927,7 +2943,7 @@
 	if (!gbe_dev->ale) {
 		dev_err(gbe_dev->dev, "error initializing ale engine\n");
 		ret = -ENODEV;
-		goto quit;
+		goto free_sec_ports;
 	} else {
 		dev_dbg(gbe_dev->dev, "Created a gbe ale engine\n");
 	}
@@ -2943,14 +2959,8 @@
 	*inst_priv = gbe_dev;
 	return 0;
 
-quit:
-	if (gbe_dev->hw_stats)
-		devm_kfree(dev, gbe_dev->hw_stats);
-	cpsw_ale_destroy(gbe_dev->ale);
-	if (gbe_dev->ss_regs)
-		devm_iounmap(dev, gbe_dev->ss_regs);
-	of_node_put(interfaces);
-	devm_kfree(dev, gbe_dev);
+free_sec_ports:
+	free_secondary_ports(gbe_dev);
 	return ret;
 }
 
@@ -3023,12 +3033,9 @@
 	free_secondary_ports(gbe_dev);
 
 	if (!list_empty(&gbe_dev->gbe_intf_head))
-		dev_alert(gbe_dev->dev, "unreleased ethss interfaces present\n");
+		dev_alert(gbe_dev->dev,
+			  "unreleased ethss interfaces present\n");
 
-	devm_kfree(gbe_dev->dev, gbe_dev->hw_stats);
-	devm_iounmap(gbe_dev->dev, gbe_dev->ss_regs);
-	memset(gbe_dev, 0x00, sizeof(*gbe_dev));
-	devm_kfree(gbe_dev->dev, gbe_dev);
 	return 0;
 }
 
diff --git a/drivers/net/ethernet/ti/netcp_sgmii.c b/drivers/net/ethernet/ti/netcp_sgmii.c
index dbeb142..5d8419f 100644
--- a/drivers/net/ethernet/ti/netcp_sgmii.c
+++ b/drivers/net/ethernet/ti/netcp_sgmii.c
@@ -18,6 +18,9 @@
 
 #include "netcp.h"
 
+#define SGMII_SRESET_RESET		BIT(0)
+#define SGMII_SRESET_RTRESET		BIT(1)
+
 #define SGMII_REG_STATUS_LOCK		BIT(4)
 #define	SGMII_REG_STATUS_LINK		BIT(0)
 #define SGMII_REG_STATUS_AUTONEG	BIT(2)
@@ -51,12 +54,35 @@
 int netcp_sgmii_reset(void __iomem *sgmii_ofs, int port)
 {
 	/* Soft reset */
-	sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port), 0x1);
-	while (sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) != 0x0)
+	sgmii_write_reg_bit(sgmii_ofs, SGMII_SRESET_REG(port),
+			    SGMII_SRESET_RESET);
+
+	while ((sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port)) &
+		SGMII_SRESET_RESET) != 0x0)
 		;
+
 	return 0;
 }
 
+/* port is 0 based */
+bool netcp_sgmii_rtreset(void __iomem *sgmii_ofs, int port, bool set)
+{
+	u32 reg;
+	bool oldval;
+
+	/* Initiate a soft reset */
+	reg = sgmii_read_reg(sgmii_ofs, SGMII_SRESET_REG(port));
+	oldval = (reg & SGMII_SRESET_RTRESET) != 0x0;
+	if (set)
+		reg |= SGMII_SRESET_RTRESET;
+	else
+		reg &= ~SGMII_SRESET_RTRESET;
+	sgmii_write_reg(sgmii_ofs, SGMII_SRESET_REG(port), reg);
+	wmb();
+
+	return oldval;
+}
+
 int netcp_sgmii_get_port_link(void __iomem *sgmii_ofs, int port)
 {
 	u32 status = 0, link = 0;
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 3b933bb..edd7734 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -719,6 +719,7 @@
 	struct virtio_net_hdr vnet_hdr = { 0 };
 	int vnet_hdr_len = 0;
 	int copylen = 0;
+	int depth;
 	bool zerocopy = false;
 	size_t linear;
 	ssize_t n;
@@ -804,6 +805,12 @@
 
 	skb_probe_transport_header(skb, ETH_HLEN);
 
+	/* Move network header to the right position for VLAN tagged packets */
+	if ((skb->protocol == htons(ETH_P_8021Q) ||
+	     skb->protocol == htons(ETH_P_8021AD)) &&
+	    __vlan_get_protocol(skb, skb->protocol, &depth) != 0)
+		skb_set_network_header(skb, depth);
+
 	rcu_read_lock();
 	vlan = rcu_dereference(q->vlan);
 	/* copy skb_ubuf_info for callback when skb has no error */
diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
index 7f6419e..ad8cbc6 100644
--- a/drivers/net/usb/r8152.c
+++ b/drivers/net/usb/r8152.c
@@ -27,7 +27,7 @@
 #include <linux/usb/cdc.h>
 
 /* Version Information */
-#define DRIVER_VERSION "v1.08.0 (2015/01/13)"
+#define DRIVER_VERSION "v1.08.1 (2015/07/28)"
 #define DRIVER_AUTHOR "Realtek linux nic maintainers <nic_swsd@realtek.com>"
 #define DRIVER_DESC "Realtek RTL8152/RTL8153 Based USB Ethernet Adapters"
 #define MODULENAME "r8152"
@@ -1902,11 +1902,10 @@
 static void rtl8152_tx_timeout(struct net_device *netdev)
 {
 	struct r8152 *tp = netdev_priv(netdev);
-	int i;
 
 	netif_warn(tp, tx_err, netdev, "Tx timeout\n");
-	for (i = 0; i < RTL8152_MAX_TX; i++)
-		usb_unlink_urb(tp->tx_info[i].urb);
+
+	usb_queue_reset_device(tp->intf);
 }
 
 static void rtl8152_set_rx_mode(struct net_device *netdev)
@@ -2075,7 +2074,6 @@
 {
 	int i, ret = 0;
 
-	napi_disable(&tp->napi);
 	INIT_LIST_HEAD(&tp->rx_done);
 	for (i = 0; i < RTL8152_MAX_RX; i++) {
 		INIT_LIST_HEAD(&tp->rx_info[i].list);
@@ -2083,7 +2081,6 @@
 		if (ret)
 			break;
 	}
-	napi_enable(&tp->napi);
 
 	if (ret && ++i < RTL8152_MAX_RX) {
 		struct list_head rx_queue;
@@ -2166,6 +2163,7 @@
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return -ENODEV;
 
+	usb_disable_lpm(tp->udev);
 	set_tx_qlen(tp);
 	rtl_set_eee_plus(tp);
 	r8153_set_rx_early_timeout(tp);
@@ -2337,11 +2335,61 @@
 		device_set_wakeup_enable(&tp->udev->dev, false);
 }
 
+static void r8153_u1u2en(struct r8152 *tp, bool enable)
+{
+	u8 u1u2[8];
+
+	if (enable)
+		memset(u1u2, 0xff, sizeof(u1u2));
+	else
+		memset(u1u2, 0x00, sizeof(u1u2));
+
+	usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
+}
+
+static void r8153_u2p3en(struct r8152 *tp, bool enable)
+{
+	u32 ocp_data;
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
+	if (enable && tp->version != RTL_VER_03 && tp->version != RTL_VER_04)
+		ocp_data |= U2P3_ENABLE;
+	else
+		ocp_data &= ~U2P3_ENABLE;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
+}
+
+static void r8153_power_cut_en(struct r8152 *tp, bool enable)
+{
+	u32 ocp_data;
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
+	if (enable)
+		ocp_data |= PWR_EN | PHASE2_EN;
+	else
+		ocp_data &= ~(PWR_EN | PHASE2_EN);
+	ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
+
+	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
+	ocp_data &= ~PCUT_STATUS;
+	ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
+}
+
+static bool rtl_can_wakeup(struct r8152 *tp)
+{
+	struct usb_device *udev = tp->udev;
+
+	return (udev->actconfig->desc.bmAttributes & USB_CONFIG_ATT_WAKEUP);
+}
+
 static void rtl_runtime_suspend_enable(struct r8152 *tp, bool enable)
 {
 	if (enable) {
 		u32 ocp_data;
 
+		r8153_u1u2en(tp, false);
+		r8153_u2p3en(tp, false);
+
 		__rtl_set_wol(tp, WAKE_ANY);
 
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_CONFIG);
@@ -2353,6 +2401,8 @@
 		ocp_write_byte(tp, MCU_TYPE_PLA, PLA_CRWECR, CRWECR_NORAML);
 	} else {
 		__rtl_set_wol(tp, tp->saved_wolopts);
+		r8153_u2p3en(tp, true);
+		r8153_u1u2en(tp, true);
 	}
 }
 
@@ -2599,46 +2649,6 @@
 	set_bit(PHY_RESET, &tp->flags);
 }
 
-static void r8153_u1u2en(struct r8152 *tp, bool enable)
-{
-	u8 u1u2[8];
-
-	if (enable)
-		memset(u1u2, 0xff, sizeof(u1u2));
-	else
-		memset(u1u2, 0x00, sizeof(u1u2));
-
-	usb_ocp_write(tp, USB_TOLERANCE, BYTE_EN_SIX_BYTES, sizeof(u1u2), u1u2);
-}
-
-static void r8153_u2p3en(struct r8152 *tp, bool enable)
-{
-	u32 ocp_data;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL);
-	if (enable)
-		ocp_data |= U2P3_ENABLE;
-	else
-		ocp_data &= ~U2P3_ENABLE;
-	ocp_write_word(tp, MCU_TYPE_USB, USB_U2P3_CTRL, ocp_data);
-}
-
-static void r8153_power_cut_en(struct r8152 *tp, bool enable)
-{
-	u32 ocp_data;
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_POWER_CUT);
-	if (enable)
-		ocp_data |= PWR_EN | PHASE2_EN;
-	else
-		ocp_data &= ~(PWR_EN | PHASE2_EN);
-	ocp_write_word(tp, MCU_TYPE_USB, USB_POWER_CUT, ocp_data);
-
-	ocp_data = ocp_read_word(tp, MCU_TYPE_USB, USB_MISC_0);
-	ocp_data &= ~PCUT_STATUS;
-	ocp_write_word(tp, MCU_TYPE_USB, USB_MISC_0, ocp_data);
-}
-
 static void r8153_first_init(struct r8152 *tp)
 {
 	u32 ocp_data;
@@ -2781,6 +2791,7 @@
 	r8153_disable_aldps(tp);
 	rtl_disable(tp);
 	r8153_enable_aldps(tp);
+	usb_enable_lpm(tp->udev);
 }
 
 static int rtl8152_set_speed(struct r8152 *tp, u8 autoneg, u16 speed, u8 duplex)
@@ -2901,9 +2912,13 @@
 	if (test_bit(RTL8152_UNPLUG, &tp->flags))
 		return;
 
+	r8153_u1u2en(tp, false);
 	r8153_disable_aldps(tp);
 	r8153_first_init(tp);
 	r8153_enable_aldps(tp);
+	r8153_u2p3en(tp, true);
+	r8153_u1u2en(tp, true);
+	usb_enable_lpm(tp->udev);
 }
 
 static void rtl8153_down(struct r8152 *tp)
@@ -2914,6 +2929,7 @@
 	}
 
 	r8153_u1u2en(tp, false);
+	r8153_u2p3en(tp, false);
 	r8153_power_cut_en(tp, false);
 	r8153_disable_aldps(tp);
 	r8153_enter_oob(tp);
@@ -2932,8 +2948,10 @@
 		if (!netif_carrier_ok(netdev)) {
 			tp->rtl_ops.enable(tp);
 			set_bit(RTL8152_SET_RX_MODE, &tp->flags);
+			napi_disable(&tp->napi);
 			netif_carrier_on(netdev);
 			rtl_start_rx(tp);
+			napi_enable(&tp->napi);
 		}
 	} else {
 		if (netif_carrier_ok(netdev)) {
@@ -3252,6 +3270,7 @@
 		msleep(20);
 	}
 
+	usb_disable_lpm(tp->udev);
 	r8153_u2p3en(tp, false);
 
 	if (tp->version == RTL_VER_04) {
@@ -3319,6 +3338,59 @@
 	r8153_enable_aldps(tp);
 	r8152b_enable_fc(tp);
 	rtl_tally_reset(tp);
+	r8153_u2p3en(tp, true);
+}
+
+static int rtl8152_pre_reset(struct usb_interface *intf)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev;
+
+	if (!tp)
+		return 0;
+
+	netdev = tp->netdev;
+	if (!netif_running(netdev))
+		return 0;
+
+	napi_disable(&tp->napi);
+	clear_bit(WORK_ENABLE, &tp->flags);
+	usb_kill_urb(tp->intr_urb);
+	cancel_delayed_work_sync(&tp->schedule);
+	if (netif_carrier_ok(netdev)) {
+		netif_stop_queue(netdev);
+		mutex_lock(&tp->control);
+		tp->rtl_ops.disable(tp);
+		mutex_unlock(&tp->control);
+	}
+
+	return 0;
+}
+
+static int rtl8152_post_reset(struct usb_interface *intf)
+{
+	struct r8152 *tp = usb_get_intfdata(intf);
+	struct net_device *netdev;
+
+	if (!tp)
+		return 0;
+
+	netdev = tp->netdev;
+	if (!netif_running(netdev))
+		return 0;
+
+	set_bit(WORK_ENABLE, &tp->flags);
+	if (netif_carrier_ok(netdev)) {
+		mutex_lock(&tp->control);
+		tp->rtl_ops.enable(tp);
+		rtl8152_set_rx_mode(netdev);
+		mutex_unlock(&tp->control);
+		netif_wake_queue(netdev);
+	}
+
+	napi_enable(&tp->napi);
+
+	return 0;
 }
 
 static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message)
@@ -3374,9 +3446,11 @@
 		if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) {
 			rtl_runtime_suspend_enable(tp, false);
 			clear_bit(SELECTIVE_SUSPEND, &tp->flags);
+			napi_disable(&tp->napi);
 			set_bit(WORK_ENABLE, &tp->flags);
 			if (netif_carrier_ok(tp->netdev))
 				rtl_start_rx(tp);
+			napi_enable(&tp->napi);
 		} else {
 			tp->rtl_ops.up(tp);
 			rtl8152_set_speed(tp, AUTONEG_ENABLE,
@@ -3403,12 +3477,15 @@
 	if (usb_autopm_get_interface(tp->intf) < 0)
 		return;
 
-	mutex_lock(&tp->control);
-
-	wol->supported = WAKE_ANY;
-	wol->wolopts = __rtl_get_wol(tp);
-
-	mutex_unlock(&tp->control);
+	if (!rtl_can_wakeup(tp)) {
+		wol->supported = 0;
+		wol->wolopts = 0;
+	} else {
+		mutex_lock(&tp->control);
+		wol->supported = WAKE_ANY;
+		wol->wolopts = __rtl_get_wol(tp);
+		mutex_unlock(&tp->control);
+	}
 
 	usb_autopm_put_interface(tp->intf);
 }
@@ -3418,6 +3495,9 @@
 	struct r8152 *tp = netdev_priv(dev);
 	int ret;
 
+	if (!rtl_can_wakeup(tp))
+		return -EOPNOTSUPP;
+
 	ret = usb_autopm_get_interface(tp->intf);
 	if (ret < 0)
 		goto out_set_wol;
@@ -4059,6 +4139,9 @@
 		goto out1;
 	}
 
+	if (!rtl_can_wakeup(tp))
+		__rtl_set_wol(tp, 0);
+
 	tp->saved_wolopts = __rtl_get_wol(tp);
 	if (tp->saved_wolopts)
 		device_set_wakeup_enable(&udev->dev, true);
@@ -4132,6 +4215,8 @@
 	.suspend =	rtl8152_suspend,
 	.resume =	rtl8152_resume,
 	.reset_resume =	rtl8152_resume,
+	.pre_reset =	rtl8152_pre_reset,
+	.post_reset =	rtl8152_post_reset,
 	.supports_autosuspend = 1,
 	.disable_hub_initiated_lpm = 1,
 };
diff --git a/drivers/of/Kconfig b/drivers/of/Kconfig
index 8df1b17..59bb855 100644
--- a/drivers/of/Kconfig
+++ b/drivers/of/Kconfig
@@ -47,7 +47,7 @@
 
 config OF_ADDRESS
 	def_bool y
-	depends on !SPARC
+	depends on !SPARC && HAS_IOMEM
 	select OF_ADDRESS_PCI if PCI
 
 config OF_ADDRESS_PCI
diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c
index 1801634..9f71770b6 100644
--- a/drivers/of/unittest.c
+++ b/drivers/of/unittest.c
@@ -979,7 +979,6 @@
 	.remove			= unittest_remove,
 	.driver = {
 		.name		= "unittest",
-		.owner		= THIS_MODULE,
 		.of_match_table	= of_match_ptr(unittest_match),
 	},
 };
@@ -1666,7 +1665,6 @@
 static struct i2c_driver unittest_i2c_dev_driver = {
 	.driver = {
 		.name = "unittest-i2c-dev",
-		.owner = THIS_MODULE,
 	},
 	.probe = unittest_i2c_dev_probe,
 	.remove = unittest_i2c_dev_remove,
@@ -1761,7 +1759,6 @@
 static struct i2c_driver unittest_i2c_mux_driver = {
 	.driver = {
 		.name = "unittest-i2c-mux",
-		.owner = THIS_MODULE,
 	},
 	.probe = unittest_i2c_mux_probe,
 	.remove = unittest_i2c_mux_remove,
diff --git a/drivers/scsi/ipr.c b/drivers/scsi/ipr.c
index 8827448..a9aa389 100644
--- a/drivers/scsi/ipr.c
+++ b/drivers/scsi/ipr.c
@@ -599,9 +599,10 @@
 {
 	struct ipr_trace_entry *trace_entry;
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
+	unsigned int trace_index;
 
-	trace_entry = &ioa_cfg->trace[atomic_add_return
-			(1, &ioa_cfg->trace_index)%IPR_NUM_TRACE_ENTRIES];
+	trace_index = atomic_add_return(1, &ioa_cfg->trace_index) & IPR_TRACE_INDEX_MASK;
+	trace_entry = &ioa_cfg->trace[trace_index];
 	trace_entry->time = jiffies;
 	trace_entry->op_code = ipr_cmd->ioarcb.cmd_pkt.cdb[0];
 	trace_entry->type = type;
@@ -1051,10 +1052,15 @@
 
 static int ipr_get_hrrq_index(struct ipr_ioa_cfg *ioa_cfg)
 {
+	unsigned int hrrq;
+
 	if (ioa_cfg->hrrq_num == 1)
-		return 0;
-	else
-		return (atomic_add_return(1, &ioa_cfg->hrrq_index) % (ioa_cfg->hrrq_num - 1)) + 1;
+		hrrq = 0;
+	else {
+		hrrq = atomic_add_return(1, &ioa_cfg->hrrq_index);
+		hrrq = (hrrq % (ioa_cfg->hrrq_num - 1)) + 1;
+	}
+	return hrrq;
 }
 
 /**
@@ -6263,21 +6269,23 @@
 	struct ipr_ioa_cfg *ioa_cfg = ipr_cmd->ioa_cfg;
 	struct scsi_cmnd *scsi_cmd = ipr_cmd->scsi_cmd;
 	u32 ioasc = be32_to_cpu(ipr_cmd->s.ioasa.hdr.ioasc);
-	unsigned long hrrq_flags;
+	unsigned long lock_flags;
 
 	scsi_set_resid(scsi_cmd, be32_to_cpu(ipr_cmd->s.ioasa.hdr.residual_data_len));
 
 	if (likely(IPR_IOASC_SENSE_KEY(ioasc) == 0)) {
 		scsi_dma_unmap(scsi_cmd);
 
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ipr_cmd->hrrq->lock, lock_flags);
 		list_add_tail(&ipr_cmd->queue, &ipr_cmd->hrrq->hrrq_free_q);
 		scsi_cmd->scsi_done(scsi_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, lock_flags);
 	} else {
-		spin_lock_irqsave(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_lock_irqsave(ioa_cfg->host->host_lock, lock_flags);
+		spin_lock(&ipr_cmd->hrrq->_lock);
 		ipr_erp_start(ioa_cfg, ipr_cmd);
-		spin_unlock_irqrestore(ipr_cmd->hrrq->lock, hrrq_flags);
+		spin_unlock(&ipr_cmd->hrrq->_lock);
+		spin_unlock_irqrestore(ioa_cfg->host->host_lock, lock_flags);
 	}
 }
 
diff --git a/drivers/scsi/ipr.h b/drivers/scsi/ipr.h
index 73790a1..6b97ee4 100644
--- a/drivers/scsi/ipr.h
+++ b/drivers/scsi/ipr.h
@@ -1486,6 +1486,7 @@
 
 #define IPR_NUM_TRACE_INDEX_BITS	8
 #define IPR_NUM_TRACE_ENTRIES		(1 << IPR_NUM_TRACE_INDEX_BITS)
+#define IPR_TRACE_INDEX_MASK		(IPR_NUM_TRACE_ENTRIES - 1)
 #define IPR_TRACE_SIZE	(sizeof(struct ipr_trace_entry) * IPR_NUM_TRACE_ENTRIES)
 	char trace_start[8];
 #define IPR_TRACE_START_LABEL			"trace"
diff --git a/drivers/scsi/qla2xxx/qla_attr.c b/drivers/scsi/qla2xxx/qla_attr.c
index 82b92c4..437254e 100644
--- a/drivers/scsi/qla2xxx/qla_attr.c
+++ b/drivers/scsi/qla2xxx/qla_attr.c
@@ -738,7 +738,7 @@
 		ql_log(ql_log_info, vha, 0x706f,
 		    "Issuing MPI reset.\n");
 
-		if (IS_QLA83XX(ha)) {
+		if (IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 			uint32_t idc_control;
 
 			qla83xx_idc_lock(vha, 0);
diff --git a/drivers/scsi/qla2xxx/qla_dbg.c b/drivers/scsi/qla2xxx/qla_dbg.c
index 0e6ee3c..8b011ae 100644
--- a/drivers/scsi/qla2xxx/qla_dbg.c
+++ b/drivers/scsi/qla2xxx/qla_dbg.c
@@ -67,10 +67,10 @@
  * |                              |                    | 0xd031-0xd0ff	|
  * |                              |                    | 0xd101-0xd1fe	|
  * |                              |                    | 0xd214-0xd2fe	|
- * | Target Mode		  |	  0xe079       |		|
- * | Target Mode Management	  |	  0xf072       | 0xf002		|
+ * | Target Mode		  |	  0xe080       |		|
+ * | Target Mode Management	  |	  0xf096       | 0xf002		|
  * |                              |                    | 0xf046-0xf049  |
- * | Target Mode Task Management  |	  0x1000b      |		|
+ * | Target Mode Task Management  |	  0x1000d      |		|
  * ----------------------------------------------------------------------
  */
 
diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
index e86201d..9ad819e 100644
--- a/drivers/scsi/qla2xxx/qla_def.h
+++ b/drivers/scsi/qla2xxx/qla_def.h
@@ -274,6 +274,7 @@
 #define RESPONSE_ENTRY_CNT_FX00		256     /* Number of response entries.*/
 
 struct req_que;
+struct qla_tgt_sess;
 
 /*
  * (sd.h is not exported, hence local inclusion)
@@ -2026,6 +2027,7 @@
 	uint16_t port_id;
 
 	unsigned long retry_delay_timestamp;
+	struct qla_tgt_sess *tgt_session;
 } fc_port_t;
 
 #include "qla_mr.h"
@@ -3154,13 +3156,13 @@
 /* Bit 21 of fw_attributes decides the MCTP capabilities */
 #define IS_MCTP_CAPABLE(ha)	(IS_QLA2031(ha) && \
 				((ha)->fw_attributes_ext[0] & BIT_0))
-#define IS_PI_UNINIT_CAPABLE(ha)	(IS_QLA83XX(ha))
-#define IS_PI_IPGUARD_CAPABLE(ha)	(IS_QLA83XX(ha))
+#define IS_PI_UNINIT_CAPABLE(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
+#define IS_PI_IPGUARD_CAPABLE(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_PI_DIFB_DIX0_CAPABLE(ha)	(0)
-#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha)	(IS_QLA83XX(ha))
+#define IS_PI_SPLIT_DET_CAPABLE_HBA(ha)	(IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_PI_SPLIT_DET_CAPABLE(ha)	(IS_PI_SPLIT_DET_CAPABLE_HBA(ha) && \
     (((ha)->fw_attributes_h << 16 | (ha)->fw_attributes) & BIT_22))
-#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha))
+#define IS_ATIO_MSIX_CAPABLE(ha) (IS_QLA83XX(ha) || IS_QLA27XX(ha))
 #define IS_TGT_MODE_CAPABLE(ha)	(ha->tgt.atio_q_length)
 #define IS_SHADOW_REG_CAPABLE(ha)  (IS_QLA27XX(ha))
 #define IS_DPORT_CAPABLE(ha)  (IS_QLA83XX(ha) || IS_QLA27XX(ha))
@@ -3579,6 +3581,16 @@
 	uint16_t	fcoe_fcf_idx;
 	uint8_t		fcoe_vn_port_mac[6];
 
+	/* list of commands waiting on workqueue */
+	struct list_head	qla_cmd_list;
+	struct list_head	qla_sess_op_cmd_list;
+	spinlock_t		cmd_list_lock;
+
+	/* Counter to detect races between ELS and RSCN events */
+	atomic_t		generation_tick;
+	/* Time when global fcport update has been scheduled */
+	int			total_fcport_update_gen;
+
 	uint32_t	vp_abort_cnt;
 
 	struct fc_vport	*fc_vport;	/* holds fc_vport * for each vport */
diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
index 6640131..11f2f32 100644
--- a/drivers/scsi/qla2xxx/qla_init.c
+++ b/drivers/scsi/qla2xxx/qla_init.c
@@ -115,6 +115,8 @@
 			QLA_LOGIO_LOGIN_RETRIED : 0;
 		qla2x00_post_async_login_done_work(fcport->vha, fcport,
 			lio->u.logio.data);
+	} else if (sp->type == SRB_LOGOUT_CMD) {
+		qlt_logo_completion_handler(fcport, QLA_FUNCTION_TIMEOUT);
 	}
 }
 
@@ -497,7 +499,10 @@
 qla2x00_async_logout_done(struct scsi_qla_host *vha, fc_port_t *fcport,
     uint16_t *data)
 {
-	qla2x00_mark_device_lost(vha, fcport, 1, 0);
+	/* Don't re-login in target mode */
+	if (!fcport->tgt_session)
+		qla2x00_mark_device_lost(vha, fcport, 1, 0);
+	qlt_logo_completion_handler(fcport, data[0]);
 	return;
 }
 
@@ -1538,7 +1543,7 @@
 		mem_size = (ha->fw_memory_size - 0x11000 + 1) *
 		    sizeof(uint16_t);
 	} else if (IS_FWI2_CAPABLE(ha)) {
-		if (IS_QLA83XX(ha))
+		if (IS_QLA83XX(ha) || IS_QLA27XX(ha))
 			fixed_size = offsetof(struct qla83xx_fw_dump, ext_mem);
 		else if (IS_QLA81XX(ha))
 			fixed_size = offsetof(struct qla81xx_fw_dump, ext_mem);
@@ -1550,7 +1555,7 @@
 		mem_size = (ha->fw_memory_size - 0x100000 + 1) *
 		    sizeof(uint32_t);
 		if (ha->mqenable) {
-			if (!IS_QLA83XX(ha))
+			if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 				mq_size = sizeof(struct qla2xxx_mq_chain);
 			/*
 			 * Allocate maximum buffer size for all queues.
@@ -2922,21 +2927,14 @@
 {
 	fc_port_t *fcport = data;
 	struct fc_rport *rport;
-	scsi_qla_host_t *vha = fcport->vha;
 	unsigned long flags;
 
 	spin_lock_irqsave(fcport->vha->host->host_lock, flags);
 	rport = fcport->drport ? fcport->drport: fcport->rport;
 	fcport->drport = NULL;
 	spin_unlock_irqrestore(fcport->vha->host->host_lock, flags);
-	if (rport) {
+	if (rport)
 		fc_remote_port_delete(rport);
-		/*
-		 * Release the target mode FC NEXUS in qla_target.c code
-		 * if target mod is enabled.
-		 */
-		qlt_fc_port_deleted(vha, fcport);
-	}
 }
 
 /**
@@ -3303,6 +3301,7 @@
 	 * Create target mode FC NEXUS in qla_target.c if target mode is
 	 * enabled..
 	 */
+
 	qlt_fc_port_added(vha, fcport);
 
 	spin_lock_irqsave(fcport->vha->host->host_lock, flags);
@@ -3341,8 +3340,7 @@
 
 	if (IS_QLAFX00(vha->hw)) {
 		qla2x00_set_fcport_state(fcport, FCS_ONLINE);
-		qla2x00_reg_remote_port(vha, fcport);
-		return;
+		goto reg_port;
 	}
 	fcport->login_retry = 0;
 	fcport->flags &= ~(FCF_LOGIN_NEEDED | FCF_ASYNC_SENT);
@@ -3350,7 +3348,16 @@
 	qla2x00_set_fcport_state(fcport, FCS_ONLINE);
 	qla2x00_iidma_fcport(vha, fcport);
 	qla24xx_update_fcport_fcp_prio(vha, fcport);
-	qla2x00_reg_remote_port(vha, fcport);
+
+reg_port:
+	if (qla_ini_mode_enabled(vha))
+		qla2x00_reg_remote_port(vha, fcport);
+	else {
+		/*
+		 * Create target mode FC NEXUS in qla_target.c
+		 */
+		qlt_fc_port_added(vha, fcport);
+	}
 }
 
 /*
@@ -3375,6 +3382,7 @@
 	LIST_HEAD(new_fcports);
 	struct qla_hw_data *ha = vha->hw;
 	struct scsi_qla_host *base_vha = pci_get_drvdata(ha->pdev);
+	int		discovery_gen;
 
 	/* If FL port exists, then SNS is present */
 	if (IS_FWI2_CAPABLE(ha))
@@ -3445,6 +3453,14 @@
 			fcport->scan_state = QLA_FCPORT_SCAN;
 		}
 
+		/* Mark the time right before querying FW for connected ports.
+		 * This process is long, asynchronous and by the time it's done,
+		 * collected information might not be accurate anymore. E.g.
+		 * disconnected port might have re-connected and a brand new
+		 * session has been created. In this case session's generation
+		 * will be newer than discovery_gen. */
+		qlt_do_generation_tick(vha, &discovery_gen);
+
 		rval = qla2x00_find_all_fabric_devs(vha, &new_fcports);
 		if (rval != QLA_SUCCESS)
 			break;
@@ -3460,20 +3476,44 @@
 			if ((fcport->flags & FCF_FABRIC_DEVICE) == 0)
 				continue;
 
-			if (fcport->scan_state == QLA_FCPORT_SCAN &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
-				qla2x00_mark_device_lost(vha, fcport,
-				    ql2xplogiabsentdevice, 0);
-				if (fcport->loop_id != FC_NO_LOOP_ID &&
-				    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
-				    fcport->port_type != FCT_INITIATOR &&
-				    fcport->port_type != FCT_BROADCAST) {
-					ha->isp_ops->fabric_logout(vha,
-					    fcport->loop_id,
-					    fcport->d_id.b.domain,
-					    fcport->d_id.b.area,
-					    fcport->d_id.b.al_pa);
-					qla2x00_clear_loop_id(fcport);
+			if (fcport->scan_state == QLA_FCPORT_SCAN) {
+				if (qla_ini_mode_enabled(base_vha) &&
+				    atomic_read(&fcport->state) == FCS_ONLINE) {
+					qla2x00_mark_device_lost(vha, fcport,
+					    ql2xplogiabsentdevice, 0);
+					if (fcport->loop_id != FC_NO_LOOP_ID &&
+					    (fcport->flags & FCF_FCP2_DEVICE) == 0 &&
+					    fcport->port_type != FCT_INITIATOR &&
+					    fcport->port_type != FCT_BROADCAST) {
+						ha->isp_ops->fabric_logout(vha,
+						    fcport->loop_id,
+						    fcport->d_id.b.domain,
+						    fcport->d_id.b.area,
+						    fcport->d_id.b.al_pa);
+						qla2x00_clear_loop_id(fcport);
+					}
+				} else if (!qla_ini_mode_enabled(base_vha)) {
+					/*
+					 * In target mode, explicitly kill
+					 * sessions and log out of devices
+					 * that are gone, so that we don't
+					 * end up with an initiator using the
+					 * wrong ACL (if the fabric recycles
+					 * an FC address and we have a stale
+					 * session around) and so that we don't
+					 * report initiators that are no longer
+					 * on the fabric.
+					 */
+					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf077,
+					    "port gone, logging out/killing session: "
+					    "%8phC state 0x%x flags 0x%x fc4_type 0x%x "
+					    "scan_state %d\n",
+					    fcport->port_name,
+					    atomic_read(&fcport->state),
+					    fcport->flags, fcport->fc4_type,
+					    fcport->scan_state);
+					qlt_fc_port_deleted(vha, fcport,
+					    discovery_gen);
 				}
 			}
 		}
@@ -3494,6 +3534,28 @@
 			    (fcport->flags & FCF_LOGIN_NEEDED) == 0)
 				continue;
 
+			/*
+			 * If we're not an initiator, skip looking for devices
+			 * and logging in.  There's no reason for us to do it,
+			 * and it seems to actively cause problems in target
+			 * mode if we race with the initiator logging into us
+			 * (we might get the "port ID used" status back from
+			 * our login command and log out the initiator, which
+			 * seems to cause havoc).
+			 */
+			if (!qla_ini_mode_enabled(base_vha)) {
+				if (fcport->scan_state == QLA_FCPORT_FOUND) {
+					ql_dbg(ql_dbg_tgt_mgt, vha, 0xf078,
+					    "port %8phC state 0x%x flags 0x%x fc4_type 0x%x "
+					    "scan_state %d (initiator mode disabled; skipping "
+					    "login)\n", fcport->port_name,
+					    atomic_read(&fcport->state),
+					    fcport->flags, fcport->fc4_type,
+					    fcport->scan_state);
+				}
+				continue;
+			}
+
 			if (fcport->loop_id == FC_NO_LOOP_ID) {
 				fcport->loop_id = next_loopid;
 				rval = qla2x00_find_new_loop_id(
@@ -3520,16 +3582,38 @@
 			    test_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags))
 				break;
 
-			/* Find a new loop ID to use. */
-			fcport->loop_id = next_loopid;
-			rval = qla2x00_find_new_loop_id(base_vha, fcport);
-			if (rval != QLA_SUCCESS) {
-				/* Ran out of IDs to use */
-				break;
-			}
+			/*
+			 * If we're not an initiator, skip looking for devices
+			 * and logging in.  There's no reason for us to do it,
+			 * and it seems to actively cause problems in target
+			 * mode if we race with the initiator logging into us
+			 * (we might get the "port ID used" status back from
+			 * our login command and log out the initiator, which
+			 * seems to cause havoc).
+			 */
+			if (qla_ini_mode_enabled(base_vha)) {
+				/* Find a new loop ID to use. */
+				fcport->loop_id = next_loopid;
+				rval = qla2x00_find_new_loop_id(base_vha,
+				    fcport);
+				if (rval != QLA_SUCCESS) {
+					/* Ran out of IDs to use */
+					break;
+				}
 
-			/* Login and update database */
-			qla2x00_fabric_dev_login(vha, fcport, &next_loopid);
+				/* Login and update database */
+				qla2x00_fabric_dev_login(vha, fcport,
+				    &next_loopid);
+			} else {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf079,
+					"new port %8phC state 0x%x flags 0x%x fc4_type "
+					"0x%x scan_state %d (initiator mode disabled; "
+					"skipping login)\n",
+					fcport->port_name,
+					atomic_read(&fcport->state),
+					fcport->flags, fcport->fc4_type,
+					fcport->scan_state);
+			}
 
 			list_move_tail(&fcport->list, &vha->vp_fcports);
 		}
@@ -3725,11 +3809,12 @@
 			fcport->fp_speed = new_fcport->fp_speed;
 
 			/*
-			 * If address the same and state FCS_ONLINE, nothing
-			 * changed.
+			 * If address the same and state FCS_ONLINE
+			 * (or in target mode), nothing changed.
 			 */
 			if (fcport->d_id.b24 == new_fcport->d_id.b24 &&
-			    atomic_read(&fcport->state) == FCS_ONLINE) {
+			    (atomic_read(&fcport->state) == FCS_ONLINE ||
+			     !qla_ini_mode_enabled(base_vha))) {
 				break;
 			}
 
@@ -3749,6 +3834,22 @@
 			 * Log it out if still logged in and mark it for
 			 * relogin later.
 			 */
+			if (!qla_ini_mode_enabled(base_vha)) {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf080,
+					 "port changed FC ID, %8phC"
+					 " old %x:%x:%x (loop_id 0x%04x)-> new %x:%x:%x\n",
+					 fcport->port_name,
+					 fcport->d_id.b.domain,
+					 fcport->d_id.b.area,
+					 fcport->d_id.b.al_pa,
+					 fcport->loop_id,
+					 new_fcport->d_id.b.domain,
+					 new_fcport->d_id.b.area,
+					 new_fcport->d_id.b.al_pa);
+				fcport->d_id.b24 = new_fcport->d_id.b24;
+				break;
+			}
+
 			fcport->d_id.b24 = new_fcport->d_id.b24;
 			fcport->flags |= FCF_LOGIN_NEEDED;
 			if (fcport->loop_id != FC_NO_LOOP_ID &&
@@ -3768,6 +3869,7 @@
 		if (found)
 			continue;
 		/* If device was not in our fcports list, then add it. */
+		new_fcport->scan_state = QLA_FCPORT_FOUND;
 		list_add_tail(&new_fcport->list, new_fcports);
 
 		/* Allocate a new replacement fcport. */
@@ -4188,6 +4290,14 @@
 			    atomic_read(&fcport->state) != FCS_UNCONFIGURED) {
 				spin_unlock_irqrestore(&ha->vport_slock, flags);
 				qla2x00_rport_del(fcport);
+
+				/*
+				 * Release the target mode FC NEXUS in
+				 * qla_target.c, if target mod is enabled.
+				 */
+				qlt_fc_port_deleted(vha, fcport,
+				    base_vha->total_fcport_update_gen);
+
 				spin_lock_irqsave(&ha->vport_slock, flags);
 			}
 		}
diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c
index 36fbd4c..6f02b26 100644
--- a/drivers/scsi/qla2xxx/qla_iocb.c
+++ b/drivers/scsi/qla2xxx/qla_iocb.c
@@ -1943,6 +1943,9 @@
 	logio->entry_type = LOGINOUT_PORT_IOCB_TYPE;
 	logio->control_flags =
 	    cpu_to_le16(LCF_COMMAND_LOGO|LCF_IMPL_LOGO);
+	if (!sp->fcport->tgt_session ||
+	    !sp->fcport->tgt_session->keep_nport_handle)
+		logio->control_flags |= cpu_to_le16(LCF_FREE_NPORT);
 	logio->nport_handle = cpu_to_le16(sp->fcport->loop_id);
 	logio->port_id[0] = sp->fcport->d_id.b.al_pa;
 	logio->port_id[1] = sp->fcport->d_id.b.area;
diff --git a/drivers/scsi/qla2xxx/qla_mbx.c b/drivers/scsi/qla2xxx/qla_mbx.c
index 02b1c1c..b2f713a 100644
--- a/drivers/scsi/qla2xxx/qla_mbx.c
+++ b/drivers/scsi/qla2xxx/qla_mbx.c
@@ -2415,7 +2415,8 @@
 			*orig_iocb_cnt = mcp->mb[10];
 		if (vha->hw->flags.npiv_supported && max_npiv_vports)
 			*max_npiv_vports = mcp->mb[11];
-		if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw)) && max_fcfs)
+		if ((IS_QLA81XX(vha->hw) || IS_QLA83XX(vha->hw) ||
+		    IS_QLA27XX(vha->hw)) && max_fcfs)
 			*max_fcfs = mcp->mb[12];
 	}
 
@@ -3898,7 +3899,7 @@
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (!(rsp->options & BIT_0)) {
 		WRT_REG_DWORD(rsp->rsp_q_out, 0);
-		if (!IS_QLA83XX(ha))
+		if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 			WRT_REG_DWORD(rsp->rsp_q_in, 0);
 	}
 
@@ -5345,7 +5346,7 @@
 	mbx_cmd_t *mcp = &mc;
 	struct qla_hw_data *ha = vha->hw;
 
-	if (!IS_QLA83XX(ha))
+	if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 		return QLA_FUNCTION_FAILED;
 
 	ql_dbg(ql_dbg_mbx, vha, 0x1143, "Entered %s.\n", __func__);
diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
index a28815b..8a5cac8 100644
--- a/drivers/scsi/qla2xxx/qla_os.c
+++ b/drivers/scsi/qla2xxx/qla_os.c
@@ -2504,6 +2504,7 @@
 		ha->mbx_count = MAILBOX_REGISTER_COUNT;
 		req_length = REQUEST_ENTRY_CNT_24XX;
 		rsp_length = RESPONSE_ENTRY_CNT_2300;
+		ha->tgt.atio_q_length = ATIO_ENTRY_CNT_24XX;
 		ha->max_loop_id = SNS_LAST_LOOP_ID_2300;
 		ha->init_cb_size = sizeof(struct mid_init_cb_81xx);
 		ha->gid_list_info_size = 8;
@@ -3229,11 +3230,15 @@
 		spin_lock_irqsave(vha->host->host_lock, flags);
 		fcport->drport = rport;
 		spin_unlock_irqrestore(vha->host->host_lock, flags);
+		qlt_do_generation_tick(vha, &base_vha->total_fcport_update_gen);
 		set_bit(FCPORT_UPDATE_NEEDED, &base_vha->dpc_flags);
 		qla2xxx_wake_dpc(base_vha);
 	} else {
-		fc_remote_port_delete(rport);
-		qlt_fc_port_deleted(vha, fcport);
+		int now;
+		if (rport)
+			fc_remote_port_delete(rport);
+		qlt_do_generation_tick(vha, &now);
+		qlt_fc_port_deleted(vha, fcport, now);
 	}
 }
 
@@ -3763,8 +3768,11 @@
 	INIT_LIST_HEAD(&vha->vp_fcports);
 	INIT_LIST_HEAD(&vha->work_list);
 	INIT_LIST_HEAD(&vha->list);
+	INIT_LIST_HEAD(&vha->qla_cmd_list);
+	INIT_LIST_HEAD(&vha->qla_sess_op_cmd_list);
 
 	spin_lock_init(&vha->work_lock);
+	spin_lock_init(&vha->cmd_list_lock);
 
 	sprintf(vha->host_str, "%s_%ld", QLA2XXX_DRIVER_NAME, vha->host_no);
 	ql_dbg(ql_dbg_init, vha, 0x0041,
diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
index 028e8c8..2feb5f3 100644
--- a/drivers/scsi/qla2xxx/qla_sup.c
+++ b/drivers/scsi/qla2xxx/qla_sup.c
@@ -1697,7 +1697,7 @@
 {
 	uint32_t led_select_value = 0;
 
-	if (!IS_QLA83XX(ha))
+	if (!IS_QLA83XX(ha) && !IS_QLA27XX(ha))
 		goto out;
 
 	if (ha->port_no == 0)
diff --git a/drivers/scsi/qla2xxx/qla_target.c b/drivers/scsi/qla2xxx/qla_target.c
index b749026..58651ec 100644
--- a/drivers/scsi/qla2xxx/qla_target.c
+++ b/drivers/scsi/qla2xxx/qla_target.c
@@ -113,6 +113,11 @@
 static void qlt_alloc_qfull_cmd(struct scsi_qla_host *vha,
 	struct atio_from_isp *atio, uint16_t status, int qfull);
 static void qlt_disable_vha(struct scsi_qla_host *vha);
+static void qlt_clear_tgt_db(struct qla_tgt *tgt);
+static void qlt_send_notify_ack(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *ntfy,
+	uint32_t add_flags, uint16_t resp_code, int resp_code_valid,
+	uint16_t srr_flags, uint16_t srr_reject_code, uint8_t srr_explan);
 /*
  * Global Variables
  */
@@ -122,6 +127,16 @@
 static DEFINE_MUTEX(qla_tgt_mutex);
 static LIST_HEAD(qla_tgt_glist);
 
+/* This API intentionally takes dest as a parameter, rather than returning
+ * int value to avoid caller forgetting to issue wmb() after the store */
+void qlt_do_generation_tick(struct scsi_qla_host *vha, int *dest)
+{
+	scsi_qla_host_t *base_vha = pci_get_drvdata(vha->hw->pdev);
+	*dest = atomic_inc_return(&base_vha->generation_tick);
+	/* memory barrier */
+	wmb();
+}
+
 /* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list) */
 static struct qla_tgt_sess *qlt_find_sess_by_port_name(
 	struct qla_tgt *tgt,
@@ -381,14 +396,73 @@
 	struct qla_tgt *tgt = sess->tgt;
 	struct scsi_qla_host *vha = sess->vha;
 	struct qla_hw_data *ha = vha->hw;
+	unsigned long flags;
+	bool logout_started = false;
+	fc_port_t fcport;
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf084,
+		"%s: se_sess %p / sess %p from port %8phC loop_id %#04x"
+		" s_id %02x:%02x:%02x logout %d keep %d plogi %d\n",
+		__func__, sess->se_sess, sess, sess->port_name, sess->loop_id,
+		sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+		sess->logout_on_delete, sess->keep_nport_handle,
+		sess->plogi_ack_needed);
 
 	BUG_ON(!tgt);
+
+	if (sess->logout_on_delete) {
+		int rc;
+
+		memset(&fcport, 0, sizeof(fcport));
+		fcport.loop_id = sess->loop_id;
+		fcport.d_id = sess->s_id;
+		memcpy(fcport.port_name, sess->port_name, WWN_SIZE);
+		fcport.vha = vha;
+		fcport.tgt_session = sess;
+
+		rc = qla2x00_post_async_logout_work(vha, &fcport, NULL);
+		if (rc != QLA_SUCCESS)
+			ql_log(ql_log_warn, vha, 0xf085,
+			       "Schedule logo failed sess %p rc %d\n",
+			       sess, rc);
+		else
+			logout_started = true;
+	}
+
 	/*
 	 * Release the target session for FC Nexus from fabric module code.
 	 */
 	if (sess->se_sess != NULL)
 		ha->tgt.tgt_ops->free_session(sess);
 
+	if (logout_started) {
+		bool traced = false;
+
+		while (!ACCESS_ONCE(sess->logout_completed)) {
+			if (!traced) {
+				ql_dbg(ql_dbg_tgt_mgt, vha, 0xf086,
+					"%s: waiting for sess %p logout\n",
+					__func__, sess);
+				traced = true;
+			}
+			msleep(100);
+		}
+
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf087,
+			"%s: sess %p logout completed\n",
+			__func__, sess);
+	}
+
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+
+	if (sess->plogi_ack_needed)
+		qlt_send_notify_ack(vha, &sess->tm_iocb,
+				    0, 0, 0, 0, 0, 0);
+
+	list_del(&sess->sess_list_entry);
+
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf001,
 	    "Unregistration of sess %p finished\n", sess);
 
@@ -409,9 +483,9 @@
 
 	vha->hw->tgt.tgt_ops->clear_nacl_from_fcport_map(sess);
 
-	list_del(&sess->sess_list_entry);
-	if (sess->deleted)
-		list_del(&sess->del_list_entry);
+	if (!list_empty(&sess->del_list_entry))
+		list_del_init(&sess->del_list_entry);
+	sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 
 	INIT_WORK(&sess->free_work, qlt_free_session_done);
 	schedule_work(&sess->free_work);
@@ -431,10 +505,10 @@
 
 	loop_id = le16_to_cpu(n->u.isp24.nport_handle);
 	if (loop_id == 0xFFFF) {
-#if 0 /* FIXME: Re-enable Global event handling.. */
 		/* Global event */
-		atomic_inc(&ha->tgt.qla_tgt->tgt_global_resets_count);
-		qlt_clear_tgt_db(ha->tgt.qla_tgt);
+		atomic_inc(&vha->vha_tgt.qla_tgt->tgt_global_resets_count);
+		qlt_clear_tgt_db(vha->vha_tgt.qla_tgt);
+#if 0 /* FIXME: do we need to choose a session here? */
 		if (!list_empty(&ha->tgt.qla_tgt->sess_list)) {
 			sess = list_entry(ha->tgt.qla_tgt->sess_list.next,
 			    typeof(*sess), sess_list_entry);
@@ -489,27 +563,38 @@
 	struct qla_tgt *tgt = sess->tgt;
 	uint32_t dev_loss_tmo = tgt->ha->port_down_retry_count + 5;
 
-	if (sess->deleted)
-		return;
+	if (sess->deleted) {
+		/* Upgrade to unconditional deletion in case it was temporary */
+		if (immediate && sess->deleted == QLA_SESS_DELETION_PENDING)
+			list_del(&sess->del_list_entry);
+		else
+			return;
+	}
 
 	ql_dbg(ql_dbg_tgt, sess->vha, 0xe001,
 	    "Scheduling sess %p for deletion\n", sess);
-	list_add_tail(&sess->del_list_entry, &tgt->del_sess_list);
-	sess->deleted = 1;
 
-	if (immediate)
+	if (immediate) {
 		dev_loss_tmo = 0;
+		sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
+		list_add(&sess->del_list_entry, &tgt->del_sess_list);
+	} else {
+		sess->deleted = QLA_SESS_DELETION_PENDING;
+		list_add_tail(&sess->del_list_entry, &tgt->del_sess_list);
+	}
 
 	sess->expires = jiffies + dev_loss_tmo * HZ;
 
 	ql_dbg(ql_dbg_tgt, sess->vha, 0xe048,
-	    "qla_target(%d): session for port %8phC (loop ID %d) scheduled for "
-	    "deletion in %u secs (expires: %lu) immed: %d\n",
-	    sess->vha->vp_idx, sess->port_name, sess->loop_id, dev_loss_tmo,
-	    sess->expires, immediate);
+	    "qla_target(%d): session for port %8phC (loop ID %d s_id %02x:%02x:%02x)"
+	    " scheduled for deletion in %u secs (expires: %lu) immed: %d, logout: %d, gen: %#x\n",
+	    sess->vha->vp_idx, sess->port_name, sess->loop_id,
+	    sess->s_id.b.domain, sess->s_id.b.area, sess->s_id.b.al_pa,
+	    dev_loss_tmo, sess->expires, immediate, sess->logout_on_delete,
+	    sess->generation);
 
 	if (immediate)
-		schedule_delayed_work(&tgt->sess_del_work, 0);
+		mod_delayed_work(system_wq, &tgt->sess_del_work, 0);
 	else
 		schedule_delayed_work(&tgt->sess_del_work,
 		    sess->expires - jiffies);
@@ -578,9 +663,9 @@
 /* ha->hardware_lock supposed to be held on entry */
 static void qlt_undelete_sess(struct qla_tgt_sess *sess)
 {
-	BUG_ON(!sess->deleted);
+	BUG_ON(sess->deleted != QLA_SESS_DELETION_PENDING);
 
-	list_del(&sess->del_list_entry);
+	list_del_init(&sess->del_list_entry);
 	sess->deleted = 0;
 }
 
@@ -599,7 +684,9 @@
 		    del_list_entry);
 		elapsed = jiffies;
 		if (time_after_eq(elapsed, sess->expires)) {
-			qlt_undelete_sess(sess);
+			/* No turning back */
+			list_del_init(&sess->del_list_entry);
+			sess->deleted = QLA_SESS_DELETION_IN_PROGRESS;
 
 			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf004,
 			    "Timeout: sess %p about to be deleted\n",
@@ -643,6 +730,13 @@
 			    fcport->d_id.b.al_pa, fcport->d_id.b.area,
 			    fcport->loop_id);
 
+			/* Cannot undelete at this point */
+			if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+				spin_unlock_irqrestore(&ha->hardware_lock,
+				    flags);
+				return NULL;
+			}
+
 			if (sess->deleted)
 				qlt_undelete_sess(sess);
 
@@ -652,6 +746,9 @@
 
 			if (sess->local && !local)
 				sess->local = 0;
+
+			qlt_do_generation_tick(vha, &sess->generation);
+
 			spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 			return sess;
@@ -673,6 +770,14 @@
 	sess->s_id = fcport->d_id;
 	sess->loop_id = fcport->loop_id;
 	sess->local = local;
+	INIT_LIST_HEAD(&sess->del_list_entry);
+
+	/* Under normal circumstances we want to logout from firmware when
+	 * session eventually ends and release corresponding nport handle.
+	 * In the exception cases (e.g. when new PLOGI is waiting) corresponding
+	 * code will adjust these flags as necessary. */
+	sess->logout_on_delete = 1;
+	sess->keep_nport_handle = 0;
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf006,
 	    "Adding sess %p to tgt %p via ->check_initiator_node_acl()\n",
@@ -705,6 +810,7 @@
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 	list_add_tail(&sess->sess_list_entry, &vha->vha_tgt.qla_tgt->sess_list);
 	vha->vha_tgt.qla_tgt->sess_count++;
+	qlt_do_generation_tick(vha, &sess->generation);
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf04b,
@@ -718,7 +824,7 @@
 }
 
 /*
- * Called from drivers/scsi/qla2xxx/qla_init.c:qla2x00_reg_remote_port()
+ * Called from qla2x00_reg_remote_port()
  */
 void qlt_fc_port_added(struct scsi_qla_host *vha, fc_port_t *fcport)
 {
@@ -750,6 +856,10 @@
 		mutex_unlock(&vha->vha_tgt.tgt_mutex);
 
 		spin_lock_irqsave(&ha->hardware_lock, flags);
+	} else if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		/* Point of no return */
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return;
 	} else {
 		kref_get(&sess->se_sess->sess_kref);
 
@@ -780,27 +890,36 @@
 	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
-void qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport)
+/*
+ * max_gen - specifies maximum session generation
+ * at which this deletion requestion is still valid
+ */
+void
+qlt_fc_port_deleted(struct scsi_qla_host *vha, fc_port_t *fcport, int max_gen)
 {
-	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
 	struct qla_tgt_sess *sess;
-	unsigned long flags;
 
 	if (!vha->hw->tgt.tgt_ops)
 		return;
 
-	if (!tgt || (fcport->port_type != FCT_INITIATOR))
+	if (!tgt)
 		return;
 
-	spin_lock_irqsave(&ha->hardware_lock, flags);
 	if (tgt->tgt_stop) {
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
 		return;
 	}
 	sess = qlt_find_sess_by_port_name(tgt, fcport->port_name);
 	if (!sess) {
-		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return;
+	}
+
+	if (max_gen - sess->generation < 0) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf092,
+		    "Ignoring stale deletion request for se_sess %p / sess %p"
+		    " for port %8phC, req_gen %d, sess_gen %d\n",
+		    sess->se_sess, sess, sess->port_name, max_gen,
+		    sess->generation);
 		return;
 	}
 
@@ -808,7 +927,6 @@
 
 	sess->local = 1;
 	qlt_schedule_sess_for_deletion(sess, false);
-	spin_unlock_irqrestore(&ha->hardware_lock, flags);
 }
 
 static inline int test_tgt_sess_count(struct qla_tgt *tgt)
@@ -1175,6 +1293,70 @@
 	    FCP_TMF_CMPL, true);
 }
 
+static int abort_cmd_for_tag(struct scsi_qla_host *vha, uint32_t tag)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+
+	spin_lock(&vha->cmd_list_lock);
+
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		if (tag == op->atio.u.isp24.exchange_addr) {
+			op->aborted = true;
+			spin_unlock(&vha->cmd_list_lock);
+			return 1;
+		}
+	}
+
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		if (tag == cmd->atio.u.isp24.exchange_addr) {
+			cmd->state = QLA_TGT_STATE_ABORTED;
+			spin_unlock(&vha->cmd_list_lock);
+			return 1;
+		}
+	}
+
+	spin_unlock(&vha->cmd_list_lock);
+	return 0;
+}
+
+/* drop cmds for the given lun
+ * XXX only looks for cmds on the port through which lun reset was recieved
+ * XXX does not go through the list of other port (which may have cmds
+ *     for the same lun)
+ */
+static void abort_cmds_for_lun(struct scsi_qla_host *vha,
+				uint32_t lun, uint8_t *s_id)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+	uint32_t key;
+
+	key = sid_to_key(s_id);
+	spin_lock(&vha->cmd_list_lock);
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		uint32_t op_key;
+		uint32_t op_lun;
+
+		op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		op_lun = scsilun_to_int(
+			(struct scsi_lun *)&op->atio.u.isp24.fcp_cmnd.lun);
+		if (op_key == key && op_lun == lun)
+			op->aborted = true;
+	}
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		uint32_t cmd_key;
+		uint32_t cmd_lun;
+
+		cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id);
+		cmd_lun = scsilun_to_int(
+			(struct scsi_lun *)&cmd->atio.u.isp24.fcp_cmnd.lun);
+		if (cmd_key == key && cmd_lun == lun)
+			cmd->state = QLA_TGT_STATE_ABORTED;
+	}
+	spin_unlock(&vha->cmd_list_lock);
+}
+
 /* ha->hardware_lock supposed to be held on entry */
 static int __qlt_24xx_handle_abts(struct scsi_qla_host *vha,
 	struct abts_recv_from_24xx *abts, struct qla_tgt_sess *sess)
@@ -1199,8 +1381,19 @@
 	}
 	spin_unlock(&se_sess->sess_cmd_lock);
 
-	if (!found_lun)
-		return -ENOENT;
+	/* cmd not in LIO lists, look in qla list */
+	if (!found_lun) {
+		if (abort_cmd_for_tag(vha, abts->exchange_addr_to_abort)) {
+			/* send TASK_ABORT response immediately */
+			qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_CMPL, false);
+			return 0;
+		} else {
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf081,
+			    "unable to find cmd in driver or LIO for tag 0x%x\n",
+			    abts->exchange_addr_to_abort);
+			return -ENOENT;
+		}
+	}
 
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf00f,
 	    "qla_target(%d): task abort (tag=%d)\n",
@@ -1284,6 +1477,11 @@
 		return;
 	}
 
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		qlt_24xx_send_abts_resp(vha, abts, FCP_TMF_REJECTED, false);
+		return;
+	}
+
 	rc = __qlt_24xx_handle_abts(vha, abts, sess);
 	if (rc != 0) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf054,
@@ -1726,20 +1924,6 @@
 	struct qla_hw_data *ha = vha->hw;
 	struct se_cmd *se_cmd = &cmd->se_cmd;
 
-	if (unlikely(cmd->aborted)) {
-		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
-		       "qla_target(%d): terminating exchange for aborted cmd=%p (se_cmd=%p, tag=%lld)",
-		       vha->vp_idx, cmd, se_cmd, se_cmd->tag);
-
-		cmd->state = QLA_TGT_STATE_ABORTED;
-		cmd->cmd_flags |= BIT_6;
-
-		qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
-
-		/* !! At this point cmd could be already freed !! */
-		return QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED;
-	}
-
 	prm->cmd = cmd;
 	prm->tgt = tgt;
 	prm->rq_result = scsi_status;
@@ -2301,6 +2485,19 @@
 	unsigned long flags = 0;
 	int res;
 
+	spin_lock_irqsave(&ha->hardware_lock, flags);
+	if (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		cmd->state = QLA_TGT_STATE_PROCESSED;
+		if (cmd->sess->logout_completed)
+			/* no need to terminate. FW already freed exchange. */
+			qlt_abort_cmd_on_host_reset(cmd->vha, cmd);
+		else
+			qlt_send_term_exchange(vha, cmd, &cmd->atio, 1);
+		spin_unlock_irqrestore(&ha->hardware_lock, flags);
+		return 0;
+	}
+	spin_unlock_irqrestore(&ha->hardware_lock, flags);
+
 	memset(&prm, 0, sizeof(prm));
 	qlt_check_srr_debug(cmd, &xmit_type);
 
@@ -2313,9 +2510,6 @@
 	res = qlt_pre_xmit_response(cmd, &prm, xmit_type, scsi_status,
 	    &full_req_cnt);
 	if (unlikely(res != 0)) {
-		if (res == QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED)
-			return 0;
-
 		return res;
 	}
 
@@ -2345,9 +2539,10 @@
 		res = qlt_build_ctio_crc2_pkt(&prm, vha);
 	else
 		res = qlt_24xx_build_ctio_pkt(&prm, vha);
-	if (unlikely(res != 0))
+	if (unlikely(res != 0)) {
+		vha->req->cnt += full_req_cnt;
 		goto out_unmap_unlock;
-
+	}
 
 	pkt = (struct ctio7_to_24xx *)prm.pkt;
 
@@ -2461,7 +2656,8 @@
 
 	spin_lock_irqsave(&ha->hardware_lock, flags);
 
-	if (qla2x00_reset_active(vha) || cmd->reset_count != ha->chip_reset) {
+	if (qla2x00_reset_active(vha) || (cmd->reset_count != ha->chip_reset) ||
+	    (cmd->sess && cmd->sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)) {
 		/*
 		 * Either a chip reset is active or this request was from
 		 * previous life, just abort the processing.
@@ -2485,8 +2681,11 @@
 	else
 		res = qlt_24xx_build_ctio_pkt(&prm, vha);
 
-	if (unlikely(res != 0))
+	if (unlikely(res != 0)) {
+		vha->req->cnt += prm.req_cnt;
 		goto out_unlock_free_unmap;
+	}
+
 	pkt = (struct ctio7_to_24xx *)prm.pkt;
 	pkt->u.status0.flags |= __constant_cpu_to_le16(CTIO7_FLAGS_DATA_OUT |
 	    CTIO7_FLAGS_STATUS_MODE_0);
@@ -2651,6 +2850,89 @@
 
 /* If hardware_lock held on entry, might drop it, then reaquire */
 /* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
+static int __qlt_send_term_imm_notif(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *ntfy)
+{
+	struct nack_to_isp *nack;
+	struct qla_hw_data *ha = vha->hw;
+	request_t *pkt;
+	int ret = 0;
+
+	ql_dbg(ql_dbg_tgt_tmr, vha, 0xe01c,
+	    "Sending TERM ELS CTIO (ha=%p)\n", ha);
+
+	pkt = (request_t *)qla2x00_alloc_iocbs_ready(vha, NULL);
+	if (pkt == NULL) {
+		ql_dbg(ql_dbg_tgt, vha, 0xe080,
+		    "qla_target(%d): %s failed: unable to allocate "
+		    "request packet\n", vha->vp_idx, __func__);
+		return -ENOMEM;
+	}
+
+	pkt->entry_type = NOTIFY_ACK_TYPE;
+	pkt->entry_count = 1;
+	pkt->handle = QLA_TGT_SKIP_HANDLE | CTIO_COMPLETION_HANDLE_MARK;
+
+	nack = (struct nack_to_isp *)pkt;
+	nack->ox_id = ntfy->ox_id;
+
+	nack->u.isp24.nport_handle = ntfy->u.isp24.nport_handle;
+	if (le16_to_cpu(ntfy->u.isp24.status) == IMM_NTFY_ELS) {
+		nack->u.isp24.flags = ntfy->u.isp24.flags &
+			__constant_cpu_to_le32(NOTIFY24XX_FLAGS_PUREX_IOCB);
+	}
+
+	/* terminate */
+	nack->u.isp24.flags |=
+		__constant_cpu_to_le16(NOTIFY_ACK_FLAGS_TERMINATE);
+
+	nack->u.isp24.srr_rx_id = ntfy->u.isp24.srr_rx_id;
+	nack->u.isp24.status = ntfy->u.isp24.status;
+	nack->u.isp24.status_subcode = ntfy->u.isp24.status_subcode;
+	nack->u.isp24.fw_handle = ntfy->u.isp24.fw_handle;
+	nack->u.isp24.exchange_address = ntfy->u.isp24.exchange_address;
+	nack->u.isp24.srr_rel_offs = ntfy->u.isp24.srr_rel_offs;
+	nack->u.isp24.srr_ui = ntfy->u.isp24.srr_ui;
+	nack->u.isp24.vp_index = ntfy->u.isp24.vp_index;
+
+	qla2x00_start_iocbs(vha, vha->req);
+	return ret;
+}
+
+static void qlt_send_term_imm_notif(struct scsi_qla_host *vha,
+	struct imm_ntfy_from_isp *imm, int ha_locked)
+{
+	unsigned long flags = 0;
+	int rc;
+
+	if (qlt_issue_marker(vha, ha_locked) < 0)
+		return;
+
+	if (ha_locked) {
+		rc = __qlt_send_term_imm_notif(vha, imm);
+
+#if 0	/* Todo  */
+		if (rc == -ENOMEM)
+			qlt_alloc_qfull_cmd(vha, imm, 0, 0);
+#endif
+		goto done;
+	}
+
+	spin_lock_irqsave(&vha->hw->hardware_lock, flags);
+	rc = __qlt_send_term_imm_notif(vha, imm);
+
+#if 0	/* Todo */
+	if (rc == -ENOMEM)
+		qlt_alloc_qfull_cmd(vha, imm, 0, 0);
+#endif
+
+done:
+	if (!ha_locked)
+		spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
+}
+
+/* If hardware_lock held on entry, might drop it, then reaquire */
+/* This function sends the appropriate CTIO to ISP 2xxx or 24xx */
 static int __qlt_send_term_exchange(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd,
 	struct atio_from_isp *atio)
@@ -2715,7 +2997,7 @@
 static void qlt_send_term_exchange(struct scsi_qla_host *vha,
 	struct qla_tgt_cmd *cmd, struct atio_from_isp *atio, int ha_locked)
 {
-	unsigned long flags;
+	unsigned long flags = 0;
 	int rc;
 
 	if (qlt_issue_marker(vha, ha_locked) < 0)
@@ -2731,17 +3013,18 @@
 	rc = __qlt_send_term_exchange(vha, cmd, atio);
 	if (rc == -ENOMEM)
 		qlt_alloc_qfull_cmd(vha, atio, 0, 0);
-	spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
 
 done:
 	if (cmd && ((cmd->state != QLA_TGT_STATE_ABORTED) ||
 	    !cmd->cmd_sent_to_fw)) {
-		if (!ha_locked && !in_interrupt())
-			msleep(250); /* just in case */
-
-		qlt_unmap_sg(vha, cmd);
+		if (cmd->sg_mapped)
+			qlt_unmap_sg(vha, cmd);
 		vha->hw->tgt.tgt_ops->free_cmd(cmd);
 	}
+
+	if (!ha_locked)
+		spin_unlock_irqrestore(&vha->hw->hardware_lock, flags);
+
 	return;
 }
 
@@ -2792,6 +3075,24 @@
 
 }
 
+void qlt_abort_cmd(struct qla_tgt_cmd *cmd)
+{
+	struct qla_tgt *tgt = cmd->tgt;
+	struct scsi_qla_host *vha = tgt->vha;
+	struct se_cmd *se_cmd = &cmd->se_cmd;
+
+	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf014,
+	    "qla_target(%d): terminating exchange for aborted cmd=%p "
+	    "(se_cmd=%p, tag=%llu)", vha->vp_idx, cmd, &cmd->se_cmd,
+	    se_cmd->tag);
+
+	cmd->state = QLA_TGT_STATE_ABORTED;
+	cmd->cmd_flags |= BIT_6;
+
+	qlt_send_term_exchange(vha, cmd, &cmd->atio, 0);
+}
+EXPORT_SYMBOL(qlt_abort_cmd);
+
 void qlt_free_cmd(struct qla_tgt_cmd *cmd)
 {
 	struct qla_tgt_sess *sess = cmd->sess;
@@ -3015,7 +3316,7 @@
 		dump_stack();
 	}
 
-	cmd->cmd_flags |= BIT_12;
+	cmd->cmd_flags |= BIT_17;
 	ha->tgt.tgt_ops->free_cmd(cmd);
 }
 
@@ -3177,7 +3478,7 @@
 skip_term:
 
 	if (cmd->state == QLA_TGT_STATE_PROCESSED) {
-		;
+		cmd->cmd_flags |= BIT_12;
 	} else if (cmd->state == QLA_TGT_STATE_NEED_DATA) {
 		int rx_status = 0;
 
@@ -3191,9 +3492,11 @@
 		ha->tgt.tgt_ops->handle_data(cmd);
 		return;
 	} else if (cmd->state == QLA_TGT_STATE_ABORTED) {
+		cmd->cmd_flags |= BIT_18;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf01e,
 		  "Aborted command %p (tag %lld) finished\n", cmd, se_cmd->tag);
 	} else {
+		cmd->cmd_flags |= BIT_19;
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf05c,
 		    "qla_target(%d): A command in state (%d) should "
 		    "not return a CTIO complete\n", vha->vp_idx, cmd->state);
@@ -3205,7 +3508,6 @@
 		dump_stack();
 	}
 
-
 	ha->tgt.tgt_ops->free_cmd(cmd);
 }
 
@@ -3263,6 +3565,13 @@
 	if (tgt->tgt_stop)
 		goto out_term;
 
+	if (cmd->state == QLA_TGT_STATE_ABORTED) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf082,
+		    "cmd with tag %u is aborted\n",
+		    cmd->atio.u.isp24.exchange_addr);
+		goto out_term;
+	}
+
 	cdb = &atio->u.isp24.fcp_cmnd.cdb[0];
 	cmd->se_cmd.tag = atio->u.isp24.exchange_addr;
 	cmd->unpacked_lun = scsilun_to_int(
@@ -3316,6 +3625,12 @@
 static void qlt_do_work(struct work_struct *work)
 {
 	struct qla_tgt_cmd *cmd = container_of(work, struct qla_tgt_cmd, work);
+	scsi_qla_host_t *vha = cmd->vha;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
+	list_del(&cmd->cmd_list);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
 
 	__qlt_do_work(cmd);
 }
@@ -3345,6 +3660,11 @@
 	cmd->loop_id = sess->loop_id;
 	cmd->conf_compl_supported = sess->conf_compl_supported;
 
+	cmd->cmd_flags = 0;
+	cmd->jiffies_at_alloc = get_jiffies_64();
+
+	cmd->reset_count = vha->hw->chip_reset;
+
 	return cmd;
 }
 
@@ -3362,14 +3682,25 @@
 	unsigned long flags;
 	uint8_t *s_id = op->atio.u.isp24.fcp_hdr.s_id;
 
+	spin_lock_irqsave(&vha->cmd_list_lock, flags);
+	list_del(&op->cmd_list);
+	spin_unlock_irqrestore(&vha->cmd_list_lock, flags);
+
+	if (op->aborted) {
+		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf083,
+		    "sess_op with tag %u is aborted\n",
+		    op->atio.u.isp24.exchange_addr);
+		goto out_term;
+	}
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf022,
-		"qla_target(%d): Unable to find wwn login"
-		" (s_id %x:%x:%x), trying to create it manually\n",
-		vha->vp_idx, s_id[0], s_id[1], s_id[2]);
+	    "qla_target(%d): Unable to find wwn login"
+	    " (s_id %x:%x:%x), trying to create it manually\n",
+	    vha->vp_idx, s_id[0], s_id[1], s_id[2]);
 
 	if (op->atio.u.raw.entry_count > 1) {
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf023,
-		        "Dropping multy entry atio %p\n", &op->atio);
+		    "Dropping multy entry atio %p\n", &op->atio);
 		goto out_term;
 	}
 
@@ -3434,10 +3765,25 @@
 
 		memcpy(&op->atio, atio, sizeof(*atio));
 		op->vha = vha;
+
+		spin_lock(&vha->cmd_list_lock);
+		list_add_tail(&op->cmd_list, &vha->qla_sess_op_cmd_list);
+		spin_unlock(&vha->cmd_list_lock);
+
 		INIT_WORK(&op->work, qlt_create_sess_from_atio);
 		queue_work(qla_tgt_wq, &op->work);
 		return 0;
 	}
+
+	/* Another WWN used to have our s_id. Our PLOGI scheduled its
+	 * session deletion, but it's still in sess_del_work wq */
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+		ql_dbg(ql_dbg_io, vha, 0x3061,
+		    "New command while old session %p is being deleted\n",
+		    sess);
+		return -EFAULT;
+	}
+
 	/*
 	 * Do kref_get() before returning + dropping qla_hw_data->hardware_lock.
 	 */
@@ -3451,13 +3797,13 @@
 		return -ENOMEM;
 	}
 
-	cmd->cmd_flags = 0;
-	cmd->jiffies_at_alloc = get_jiffies_64();
-
-	cmd->reset_count = vha->hw->chip_reset;
-
 	cmd->cmd_in_wq = 1;
 	cmd->cmd_flags |= BIT_0;
+
+	spin_lock(&vha->cmd_list_lock);
+	list_add_tail(&cmd->cmd_list, &vha->qla_cmd_list);
+	spin_unlock(&vha->cmd_list_lock);
+
 	INIT_WORK(&cmd->work, qlt_do_work);
 	queue_work(qla_tgt_wq, &cmd->work);
 	return 0;
@@ -3471,6 +3817,7 @@
 	struct scsi_qla_host *vha = sess->vha;
 	struct qla_hw_data *ha = vha->hw;
 	struct qla_tgt_mgmt_cmd *mcmd;
+	struct atio_from_isp *a = (struct atio_from_isp *)iocb;
 	int res;
 	uint8_t tmr_func;
 
@@ -3511,6 +3858,7 @@
 		ql_dbg(ql_dbg_tgt_tmr, vha, 0x10002,
 		    "qla_target(%d): LUN_RESET received\n", sess->vha->vp_idx);
 		tmr_func = TMR_LUN_RESET;
+		abort_cmds_for_lun(vha, lun, a->u.isp24.fcp_hdr.s_id);
 		break;
 
 	case QLA_TGT_CLEAR_TS:
@@ -3599,6 +3947,9 @@
 		    sizeof(struct atio_from_isp));
 	}
 
+	if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS)
+		return -EFAULT;
+
 	return qlt_issue_task_mgmt(sess, unpacked_lun, fn, iocb, 0);
 }
 
@@ -3664,22 +4015,280 @@
 	return __qlt_abort_task(vha, iocb, sess);
 }
 
+void qlt_logo_completion_handler(fc_port_t *fcport, int rc)
+{
+	if (fcport->tgt_session) {
+		if (rc != MBS_COMMAND_COMPLETE) {
+			ql_dbg(ql_dbg_tgt_mgt, fcport->vha, 0xf093,
+				"%s: se_sess %p / sess %p from"
+				" port %8phC loop_id %#04x s_id %02x:%02x:%02x"
+				" LOGO failed: %#x\n",
+				__func__,
+				fcport->tgt_session->se_sess,
+				fcport->tgt_session,
+				fcport->port_name, fcport->loop_id,
+				fcport->d_id.b.domain, fcport->d_id.b.area,
+				fcport->d_id.b.al_pa, rc);
+		}
+
+		fcport->tgt_session->logout_completed = 1;
+	}
+}
+
+static void qlt_swap_imm_ntfy_iocb(struct imm_ntfy_from_isp *a,
+    struct imm_ntfy_from_isp *b)
+{
+	struct imm_ntfy_from_isp tmp;
+	memcpy(&tmp, a, sizeof(struct imm_ntfy_from_isp));
+	memcpy(a, b, sizeof(struct imm_ntfy_from_isp));
+	memcpy(b, &tmp, sizeof(struct imm_ntfy_from_isp));
+}
+
+/*
+* ha->hardware_lock supposed to be held on entry (to protect tgt->sess_list)
+*
+* Schedules sessions with matching port_id/loop_id but different wwn for
+* deletion. Returns existing session with matching wwn if present.
+* Null otherwise.
+*/
+static struct qla_tgt_sess *
+qlt_find_sess_invalidate_other(struct qla_tgt *tgt, uint64_t wwn,
+    port_id_t port_id, uint16_t loop_id)
+{
+	struct qla_tgt_sess *sess = NULL, *other_sess;
+	uint64_t other_wwn;
+
+	list_for_each_entry(other_sess, &tgt->sess_list, sess_list_entry) {
+
+		other_wwn = wwn_to_u64(other_sess->port_name);
+
+		if (wwn == other_wwn) {
+			WARN_ON(sess);
+			sess = other_sess;
+			continue;
+		}
+
+		/* find other sess with nport_id collision */
+		if (port_id.b24 == other_sess->s_id.b24) {
+			if (loop_id != other_sess->loop_id) {
+				ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000c,
+				    "Invalidating sess %p loop_id %d wwn %llx.\n",
+				    other_sess, other_sess->loop_id, other_wwn);
+
+				/*
+				 * logout_on_delete is set by default, but another
+				 * session that has the same s_id/loop_id combo
+				 * might have cleared it when requested this session
+				 * deletion, so don't touch it
+				 */
+				qlt_schedule_sess_for_deletion(other_sess, true);
+			} else {
+				/*
+				 * Another wwn used to have our s_id/loop_id
+				 * combo - kill the session, but don't log out
+				 */
+				sess->logout_on_delete = 0;
+				qlt_schedule_sess_for_deletion(other_sess,
+				    true);
+			}
+			continue;
+		}
+
+		/* find other sess with nport handle collision */
+		if (loop_id == other_sess->loop_id) {
+			ql_dbg(ql_dbg_tgt_tmr, tgt->vha, 0x1000d,
+			       "Invalidating sess %p loop_id %d wwn %llx.\n",
+			       other_sess, other_sess->loop_id, other_wwn);
+
+			/* Same loop_id but different s_id
+			 * Ok to kill and logout */
+			qlt_schedule_sess_for_deletion(other_sess, true);
+		}
+	}
+
+	return sess;
+}
+
+/* Abort any commands for this s_id waiting on qla_tgt_wq workqueue */
+static int abort_cmds_for_s_id(struct scsi_qla_host *vha, port_id_t *s_id)
+{
+	struct qla_tgt_sess_op *op;
+	struct qla_tgt_cmd *cmd;
+	uint32_t key;
+	int count = 0;
+
+	key = (((u32)s_id->b.domain << 16) |
+	       ((u32)s_id->b.area   <<  8) |
+	       ((u32)s_id->b.al_pa));
+
+	spin_lock(&vha->cmd_list_lock);
+	list_for_each_entry(op, &vha->qla_sess_op_cmd_list, cmd_list) {
+		uint32_t op_key = sid_to_key(op->atio.u.isp24.fcp_hdr.s_id);
+		if (op_key == key) {
+			op->aborted = true;
+			count++;
+		}
+	}
+	list_for_each_entry(cmd, &vha->qla_cmd_list, cmd_list) {
+		uint32_t cmd_key = sid_to_key(cmd->atio.u.isp24.fcp_hdr.s_id);
+		if (cmd_key == key) {
+			cmd->state = QLA_TGT_STATE_ABORTED;
+			count++;
+		}
+	}
+	spin_unlock(&vha->cmd_list_lock);
+
+	return count;
+}
+
 /*
  * ha->hardware_lock supposed to be held on entry. Might drop it, then reaquire
  */
 static int qlt_24xx_handle_els(struct scsi_qla_host *vha,
 	struct imm_ntfy_from_isp *iocb)
 {
+	struct qla_tgt *tgt = vha->vha_tgt.qla_tgt;
+	struct qla_hw_data *ha = vha->hw;
+	struct qla_tgt_sess *sess = NULL;
+	uint64_t wwn;
+	port_id_t port_id;
+	uint16_t loop_id;
+	uint16_t wd3_lo;
 	int res = 0;
 
+	wwn = wwn_to_u64(iocb->u.isp24.port_name);
+
+	port_id.b.domain = iocb->u.isp24.port_id[2];
+	port_id.b.area   = iocb->u.isp24.port_id[1];
+	port_id.b.al_pa  = iocb->u.isp24.port_id[0];
+	port_id.b.rsvd_1 = 0;
+
+	loop_id = le16_to_cpu(iocb->u.isp24.nport_handle);
+
 	ql_dbg(ql_dbg_tgt_mgt, vha, 0xf026,
 	    "qla_target(%d): Port ID: 0x%3phC ELS opcode: 0x%02x\n",
 	    vha->vp_idx, iocb->u.isp24.port_id, iocb->u.isp24.status_subcode);
 
+	/* res = 1 means ack at the end of thread
+	 * res = 0 means ack async/later.
+	 */
 	switch (iocb->u.isp24.status_subcode) {
 	case ELS_PLOGI:
-	case ELS_FLOGI:
+
+		/* Mark all stale commands in qla_tgt_wq for deletion */
+		abort_cmds_for_s_id(vha, &port_id);
+
+		if (wwn)
+			sess = qlt_find_sess_invalidate_other(tgt, wwn,
+			    port_id, loop_id);
+
+		if (!sess || IS_SW_RESV_ADDR(sess->s_id)) {
+			res = 1;
+			break;
+		}
+
+		if (sess->plogi_ack_needed) {
+			/*
+			 * Initiator sent another PLOGI before last PLOGI could
+			 * finish. Swap plogi iocbs and terminate old one
+			 * without acking, new one will get acked when session
+			 * deletion completes.
+			 */
+			ql_log(ql_log_warn, sess->vha, 0xf094,
+			    "sess %p received double plogi.\n", sess);
+
+			qlt_swap_imm_ntfy_iocb(iocb, &sess->tm_iocb);
+
+			qlt_send_term_imm_notif(vha, iocb, 1);
+
+			res = 0;
+			break;
+		}
+
+		res = 0;
+
+		/*
+		 * Save immediate Notif IOCB for Ack when sess is done
+		 * and being deleted.
+		 */
+		memcpy(&sess->tm_iocb, iocb, sizeof(sess->tm_iocb));
+		sess->plogi_ack_needed  = 1;
+
+		 /*
+		  * Under normal circumstances we want to release nport handle
+		  * during LOGO process to avoid nport handle leaks inside FW.
+		  * The exception is when LOGO is done while another PLOGI with
+		  * the same nport handle is waiting as might be the case here.
+		  * Note: there is always a possibily of a race where session
+		  * deletion has already started for other reasons (e.g. ACL
+		  * removal) and now PLOGI arrives:
+		  * 1. if PLOGI arrived in FW after nport handle has been freed,
+		  *    FW must have assigned this PLOGI a new/same handle and we
+		  *    can proceed ACK'ing it as usual when session deletion
+		  *    completes.
+		  * 2. if PLOGI arrived in FW before LOGO with LCF_FREE_NPORT
+		  *    bit reached it, the handle has now been released. We'll
+		  *    get an error when we ACK this PLOGI. Nothing will be sent
+		  *    back to initiator. Initiator should eventually retry
+		  *    PLOGI and situation will correct itself.
+		  */
+		sess->keep_nport_handle = ((sess->loop_id == loop_id) &&
+					   (sess->s_id.b24 == port_id.b24));
+		qlt_schedule_sess_for_deletion(sess, true);
+		break;
+
 	case ELS_PRLI:
+		wd3_lo = le16_to_cpu(iocb->u.isp24.u.prli.wd3_lo);
+
+		if (wwn)
+			sess = qlt_find_sess_invalidate_other(tgt, wwn, port_id,
+			    loop_id);
+
+		if (sess != NULL) {
+			if (sess->deleted) {
+				/*
+				 * Impatient initiator sent PRLI before last
+				 * PLOGI could finish. Will force him to re-try,
+				 * while last one finishes.
+				 */
+				ql_log(ql_log_warn, sess->vha, 0xf095,
+				    "sess %p PRLI received, before plogi ack.\n",
+				    sess);
+				qlt_send_term_imm_notif(vha, iocb, 1);
+				res = 0;
+				break;
+			}
+
+			/*
+			 * This shouldn't happen under normal circumstances,
+			 * since we have deleted the old session during PLOGI
+			 */
+			ql_dbg(ql_dbg_tgt_mgt, vha, 0xf096,
+			    "PRLI (loop_id %#04x) for existing sess %p (loop_id %#04x)\n",
+			    sess->loop_id, sess, iocb->u.isp24.nport_handle);
+
+			sess->local = 0;
+			sess->loop_id = loop_id;
+			sess->s_id = port_id;
+
+			if (wd3_lo & BIT_7)
+				sess->conf_compl_supported = 1;
+
+		}
+		res = 1; /* send notify ack */
+
+		/* Make session global (not used in fabric mode) */
+		if (ha->current_topology != ISP_CFG_F) {
+			set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+			set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+			qla2xxx_wake_dpc(vha);
+		} else {
+			/* todo: else - create sess here. */
+			res = 1; /* send notify ack */
+		}
+
+		break;
+
 	case ELS_LOGO:
 	case ELS_PRLO:
 		res = qlt_reset(vha, iocb, QLA_TGT_NEXUS_LOSS_SESS);
@@ -3697,6 +4306,7 @@
 		break;
 	}
 
+	case ELS_FLOGI:	/* should never happen */
 	default:
 		ql_dbg(ql_dbg_tgt_mgt, vha, 0xf061,
 		    "qla_target(%d): Unsupported ELS command %x "
@@ -5012,6 +5622,11 @@
 		if (!sess)
 			goto out_term;
 	} else {
+		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+			sess = NULL;
+			goto out_term;
+		}
+
 		kref_get(&sess->se_sess->sess_kref);
 	}
 
@@ -5066,6 +5681,11 @@
 		if (!sess)
 			goto out_term;
 	} else {
+		if (sess->deleted == QLA_SESS_DELETION_IN_PROGRESS) {
+			sess = NULL;
+			goto out_term;
+		}
+
 		kref_get(&sess->se_sess->sess_kref);
 	}
 
@@ -5552,6 +6172,7 @@
 
 	/* Adjust ring index */
 	WRT_REG_DWORD(ISP_ATIO_Q_OUT(vha), ha->tgt.atio_ring_index);
+	RD_REG_DWORD_RELAXED(ISP_ATIO_Q_OUT(vha));
 }
 
 void
@@ -5793,7 +6414,7 @@
 	if (!QLA_TGT_MODE_ENABLED())
 		return;
 
-	if  (ha->mqenable || IS_QLA83XX(ha)) {
+	if  (ha->mqenable || IS_QLA83XX(ha) || IS_QLA27XX(ha)) {
 		ISP_ATIO_Q_IN(base_vha) = &ha->mqiobase->isp25mq.atio_q_in;
 		ISP_ATIO_Q_OUT(base_vha) = &ha->mqiobase->isp25mq.atio_q_out;
 	} else {
diff --git a/drivers/scsi/qla2xxx/qla_target.h b/drivers/scsi/qla2xxx/qla_target.h
index 985d76d..bca584a 100644
--- a/drivers/scsi/qla2xxx/qla_target.h
+++ b/drivers/scsi/qla2xxx/qla_target.h
@@ -167,7 +167,24 @@
 			uint32_t srr_rel_offs;
 			uint16_t srr_ui;
 			uint16_t srr_ox_id;
-			uint8_t  reserved_4[19];
+			union {
+				struct {
+					uint8_t node_name[8];
+				} plogi; /* PLOGI/ADISC/PDISC */
+				struct {
+					/* PRLI word 3 bit 0-15 */
+					uint16_t wd3_lo;
+					uint8_t resv0[6];
+				} prli;
+				struct {
+					uint8_t port_id[3];
+					uint8_t resv1;
+					uint16_t nport_handle;
+					uint16_t resv2;
+				} req_els;
+			} u;
+			uint8_t port_name[8];
+			uint8_t resv3[3];
 			uint8_t  vp_index;
 			uint32_t reserved_5;
 			uint8_t  port_id[3];
@@ -234,6 +251,7 @@
 	uint8_t  reserved[2];
 	uint16_t ox_id;
 } __packed;
+#define NOTIFY_ACK_FLAGS_TERMINATE	BIT_3
 #define NOTIFY_ACK_SRR_FLAGS_ACCEPT	0
 #define NOTIFY_ACK_SRR_FLAGS_REJECT	1
 
@@ -790,13 +808,6 @@
 #define	FC_TM_REJECT                4
 #define FC_TM_FAILED                5
 
-/*
- * Error code of qlt_pre_xmit_response() meaning that cmd's exchange was
- * terminated, so no more actions is needed and success should be returned
- * to target.
- */
-#define QLA_TGT_PRE_XMIT_RESP_CMD_ABORTED	0x1717
-
 #if (BITS_PER_LONG > 32) || defined(CONFIG_HIGHMEM64G)
 #define pci_dma_lo32(a) (a & 0xffffffff)
 #define pci_dma_hi32(a) ((((a) >> 16)>>16) & 0xffffffff)
@@ -874,6 +885,15 @@
 	struct scsi_qla_host *vha;
 	struct atio_from_isp atio;
 	struct work_struct work;
+	struct list_head cmd_list;
+	bool aborted;
+};
+
+enum qla_sess_deletion {
+	QLA_SESS_DELETION_NONE		= 0,
+	QLA_SESS_DELETION_PENDING	= 1, /* hopefully we can get rid of
+					      * this one */
+	QLA_SESS_DELETION_IN_PROGRESS	= 2,
 };
 
 /*
@@ -884,8 +904,15 @@
 	port_id_t s_id;
 
 	unsigned int conf_compl_supported:1;
-	unsigned int deleted:1;
+	unsigned int deleted:2;
 	unsigned int local:1;
+	unsigned int logout_on_delete:1;
+	unsigned int plogi_ack_needed:1;
+	unsigned int keep_nport_handle:1;
+
+	unsigned char logout_completed;
+
+	int generation;
 
 	struct se_session *se_sess;
 	struct scsi_qla_host *vha;
@@ -897,6 +924,10 @@
 
 	uint8_t port_name[WWN_SIZE];
 	struct work_struct free_work;
+
+	union {
+		struct imm_ntfy_from_isp tm_iocb;
+	};
 };
 
 struct qla_tgt_cmd {
@@ -912,7 +943,6 @@
 	unsigned int conf_compl_supported:1;
 	unsigned int sg_mapped:1;
 	unsigned int free_sg:1;
-	unsigned int aborted:1; /* Needed in case of SRR */
 	unsigned int write_data_transferred:1;
 	unsigned int ctx_dsd_alloced:1;
 	unsigned int q_full:1;
@@ -961,6 +991,9 @@
 	 * BIT_14 - Back end data received/sent.
 	 * BIT_15 - SRR prepare ctio
 	 * BIT_16 - complete free
+	 * BIT_17 - flush - qlt_abort_cmd_on_host_reset
+	 * BIT_18 - completion w/abort status
+	 * BIT_19 - completion w/unknown status
 	 */
 	uint32_t cmd_flags;
 };
@@ -1026,6 +1059,10 @@
 	struct qla_tgt_cmd *cmd;
 };
 
+/* Check for Switch reserved address */
+#define IS_SW_RESV_ADDR(_s_id) \
+	((_s_id.b.domain == 0xff) && (_s_id.b.area == 0xfc))
+
 #define QLA_TGT_XMIT_DATA		1
 #define QLA_TGT_XMIT_STATUS		2
 #define QLA_TGT_XMIT_ALL		(QLA_TGT_XMIT_STATUS|QLA_TGT_XMIT_DATA)
@@ -1043,7 +1080,7 @@
 extern void qlt_lport_deregister(struct scsi_qla_host *);
 extern void qlt_unreg_sess(struct qla_tgt_sess *);
 extern void qlt_fc_port_added(struct scsi_qla_host *, fc_port_t *);
-extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *);
+extern void qlt_fc_port_deleted(struct scsi_qla_host *, fc_port_t *, int);
 extern int __init qlt_init(void);
 extern void qlt_exit(void);
 extern void qlt_update_vp_map(struct scsi_qla_host *, int);
@@ -1073,12 +1110,23 @@
 		ha->host->active_mode |= MODE_INITIATOR;
 }
 
+static inline uint32_t sid_to_key(const uint8_t *s_id)
+{
+	uint32_t key;
+
+	key = (((unsigned long)s_id[0] << 16) |
+	       ((unsigned long)s_id[1] << 8) |
+	       (unsigned long)s_id[2]);
+	return key;
+}
+
 /*
  * Exported symbols from qla_target.c LLD logic used by qla2xxx code..
  */
 extern void qlt_response_pkt_all_vps(struct scsi_qla_host *, response_t *);
 extern int qlt_rdy_to_xfer(struct qla_tgt_cmd *);
 extern int qlt_xmit_response(struct qla_tgt_cmd *, int, uint8_t);
+extern void qlt_abort_cmd(struct qla_tgt_cmd *);
 extern void qlt_xmit_tm_rsp(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_mcmd(struct qla_tgt_mgmt_cmd *);
 extern void qlt_free_cmd(struct qla_tgt_cmd *cmd);
@@ -1109,5 +1157,7 @@
 extern irqreturn_t qla83xx_msix_atio_q(int, void *);
 extern void qlt_83xx_iospace_config(struct qla_hw_data *);
 extern int qlt_free_qfull_cmds(struct scsi_qla_host *);
+extern void qlt_logo_completion_handler(fc_port_t *, int);
+extern void qlt_do_generation_tick(struct scsi_qla_host *, int *);
 
 #endif /* __QLA_TARGET_H */
diff --git a/drivers/scsi/qla2xxx/tcm_qla2xxx.c b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
index d9a8c60..9224a06 100644
--- a/drivers/scsi/qla2xxx/tcm_qla2xxx.c
+++ b/drivers/scsi/qla2xxx/tcm_qla2xxx.c
@@ -374,7 +374,7 @@
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-
+	cmd->cmd_flags |= BIT_3;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
 
@@ -405,7 +405,7 @@
 	    se_cmd->t_state == TRANSPORT_COMPLETE_QF_WP) {
 		spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
 		wait_for_completion_timeout(&se_cmd->t_transport_stop_comp,
-						3000);
+					    3 * HZ);
 		return 0;
 	}
 	spin_unlock_irqrestore(&se_cmd->t_state_lock, flags);
@@ -541,12 +541,10 @@
 	cmd->cmd_flags |= BIT_4;
 	cmd->bufflen = se_cmd->data_length;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
 
 	cmd->sg_cnt = se_cmd->t_data_nents;
 	cmd->sg = se_cmd->t_data_sg;
 	cmd->offset = 0;
-	cmd->cmd_flags |= BIT_3;
 
 	cmd->prot_sg_cnt = se_cmd->t_prot_nents;
 	cmd->prot_sg = se_cmd->t_prot_sg;
@@ -571,7 +569,6 @@
 	cmd->sg_cnt = 0;
 	cmd->offset = 0;
 	cmd->dma_data_direction = target_reverse_dma_direction(se_cmd);
-	cmd->aborted = (se_cmd->transport_state & CMD_T_ABORTED);
 	if (cmd->cmd_flags &  BIT_5) {
 		pr_crit("Bit_5 already set for cmd = %p.\n", cmd);
 		dump_stack();
@@ -636,14 +633,7 @@
 {
 	struct qla_tgt_cmd *cmd = container_of(se_cmd,
 				struct qla_tgt_cmd, se_cmd);
-	struct scsi_qla_host *vha = cmd->vha;
-	struct qla_hw_data *ha = vha->hw;
-
-	if (!cmd->sg_mapped)
-		return;
-
-	pci_unmap_sg(ha->pdev, cmd->sg, cmd->sg_cnt, cmd->dma_data_direction);
-	cmd->sg_mapped = 0;
+	qlt_abort_cmd(cmd);
 }
 
 static void tcm_qla2xxx_clear_sess_lookup(struct tcm_qla2xxx_lport *,
@@ -1149,9 +1139,7 @@
 		return NULL;
 	}
 
-	key = (((unsigned long)s_id[0] << 16) |
-	       ((unsigned long)s_id[1] << 8) |
-	       (unsigned long)s_id[2]);
+	key = sid_to_key(s_id);
 	pr_debug("find_sess_by_s_id: 0x%06x\n", key);
 
 	se_nacl = btree_lookup32(&lport->lport_fcport_map, key);
@@ -1186,9 +1174,7 @@
 	void *slot;
 	int rc;
 
-	key = (((unsigned long)s_id[0] << 16) |
-	       ((unsigned long)s_id[1] << 8) |
-	       (unsigned long)s_id[2]);
+	key = sid_to_key(s_id);
 	pr_debug("set_sess_by_s_id: %06x\n", key);
 
 	slot = btree_lookup32(&lport->lport_fcport_map, key);
@@ -1544,6 +1530,10 @@
 	}
 
 	sess->conf_compl_supported = conf_compl_supported;
+
+	/* Reset logout parameters to default */
+	sess->logout_on_delete = 1;
+	sess->keep_nport_handle = 0;
 }
 
 /*
diff --git a/drivers/scsi/scsi_error.c b/drivers/scsi/scsi_error.c
index 106884a..cfadcce 100644
--- a/drivers/scsi/scsi_error.c
+++ b/drivers/scsi/scsi_error.c
@@ -944,7 +944,7 @@
 			    scmd->sdb.length);
 		scmd->sdb.table.sgl = &ses->sense_sgl;
 		scmd->sc_data_direction = DMA_FROM_DEVICE;
-		scmd->sdb.table.nents = 1;
+		scmd->sdb.table.nents = scmd->sdb.table.orig_nents = 1;
 		scmd->cmnd[0] = REQUEST_SENSE;
 		scmd->cmnd[4] = scmd->sdb.length;
 		scmd->cmd_len = COMMAND_SIZE(scmd->cmnd[0]);
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index b1a2631..448ebda 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -583,7 +583,7 @@
 
 static void scsi_free_sgtable(struct scsi_data_buffer *sdb, bool mq)
 {
-	if (mq && sdb->table.nents <= SCSI_MAX_SG_SEGMENTS)
+	if (mq && sdb->table.orig_nents <= SCSI_MAX_SG_SEGMENTS)
 		return;
 	__sg_free_table(&sdb->table, SCSI_MAX_SG_SEGMENTS, mq, scsi_sg_free);
 }
@@ -597,8 +597,8 @@
 
 	if (mq) {
 		if (nents <= SCSI_MAX_SG_SEGMENTS) {
-			sdb->table.nents = nents;
-			sg_init_table(sdb->table.sgl, sdb->table.nents);
+			sdb->table.nents = sdb->table.orig_nents = nents;
+			sg_init_table(sdb->table.sgl, nents);
 			return 0;
 		}
 		first_chunk = sdb->table.sgl;
diff --git a/drivers/staging/comedi/drivers/das1800.c b/drivers/staging/comedi/drivers/das1800.c
index bfa4262..94078118 100644
--- a/drivers/staging/comedi/drivers/das1800.c
+++ b/drivers/staging/comedi/drivers/das1800.c
@@ -1266,6 +1266,7 @@
 		if (index == das1801hc || index == das1802hc)
 			return board;
 		index = das1801hc;
+		break;
 	default:
 		dev_err(dev->class_dev,
 			"Board model: probe returned 0x%x (unknown, please report)\n",
diff --git a/drivers/staging/lustre/lustre/obdclass/debug.c b/drivers/staging/lustre/lustre/obdclass/debug.c
index 9c934e6..c61add4 100644
--- a/drivers/staging/lustre/lustre/obdclass/debug.c
+++ b/drivers/staging/lustre/lustre/obdclass/debug.c
@@ -40,7 +40,7 @@
 
 #define DEBUG_SUBSYSTEM D_OTHER
 
-#include <linux/unaligned/access_ok.h>
+#include <asm/unaligned.h>
 
 #include "../include/obd_support.h"
 #include "../include/lustre_debug.h"
diff --git a/drivers/staging/vt6655/device_main.c b/drivers/staging/vt6655/device_main.c
index b0c8e23..69bdc8f 100644
--- a/drivers/staging/vt6655/device_main.c
+++ b/drivers/staging/vt6655/device_main.c
@@ -1483,8 +1483,9 @@
 		}
 	}
 
-	if (changed & BSS_CHANGED_ASSOC && priv->op_mode != NL80211_IFTYPE_AP) {
-		if (conf->assoc) {
+	if (changed & (BSS_CHANGED_ASSOC | BSS_CHANGED_BEACON_INFO) &&
+	    priv->op_mode != NL80211_IFTYPE_AP) {
+		if (conf->assoc && conf->beacon_rate) {
 			CARDbUpdateTSF(priv, conf->beacon_rate->hw_value,
 				       conf->sync_tsf);
 
diff --git a/drivers/target/iscsi/iscsi_target.c b/drivers/target/iscsi/iscsi_target.c
index 4e68b62..cd77a06 100644
--- a/drivers/target/iscsi/iscsi_target.c
+++ b/drivers/target/iscsi/iscsi_target.c
@@ -3998,7 +3998,13 @@
 	}
 
 transport_err:
-	iscsit_take_action_for_connection_exit(conn);
+	/*
+	 * Avoid the normal connection failure code-path if this connection
+	 * is still within LOGIN mode, and iscsi_np process context is
+	 * responsible for cleaning up the early connection failure.
+	 */
+	if (conn->conn_state != TARG_CONN_STATE_IN_LOGIN)
+		iscsit_take_action_for_connection_exit(conn);
 out:
 	return 0;
 }
@@ -4082,7 +4088,7 @@
 
 int iscsi_target_rx_thread(void *arg)
 {
-	int ret;
+	int ret, rc;
 	u8 buffer[ISCSI_HDR_LEN], opcode;
 	u32 checksum = 0, digest = 0;
 	struct iscsi_conn *conn = arg;
@@ -4092,10 +4098,16 @@
 	 * connection recovery / failure event can be triggered externally.
 	 */
 	allow_signal(SIGINT);
+	/*
+	 * Wait for iscsi_post_login_handler() to complete before allowing
+	 * incoming iscsi/tcp socket I/O, and/or failing the connection.
+	 */
+	rc = wait_for_completion_interruptible(&conn->rx_login_comp);
+	if (rc < 0)
+		return 0;
 
 	if (conn->conn_transport->transport_type == ISCSI_INFINIBAND) {
 		struct completion comp;
-		int rc;
 
 		init_completion(&comp);
 		rc = wait_for_completion_interruptible(&comp);
@@ -4532,7 +4544,18 @@
 	struct iscsi_conn *conn)
 {
 	struct iscsi_session *sess = conn->sess;
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+	/*
+	 * Traditional iscsi/tcp will invoke this logic from TX thread
+	 * context during session logout, so clear tx_thread_active and
+	 * sleep if iscsit_close_connection() has not already occured.
+	 *
+	 * Since iser-target invokes this logic from it's own workqueue,
+	 * always sleep waiting for RX/TX thread shutdown to complete
+	 * within iscsit_close_connection().
+	 */
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4546,7 +4569,10 @@
 static void iscsit_logout_post_handler_samecid(
 	struct iscsi_conn *conn)
 {
-	int sleep = cmpxchg(&conn->tx_thread_active, true, false);
+	int sleep = 1;
+
+	if (conn->conn_transport->transport_type == ISCSI_TCP)
+		sleep = cmpxchg(&conn->tx_thread_active, true, false);
 
 	atomic_set(&conn->conn_logout_remove, 0);
 	complete(&conn->conn_logout_comp);
@@ -4765,6 +4791,7 @@
 	struct iscsi_session *sess;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
 	struct se_session *se_sess, *se_sess_tmp;
+	LIST_HEAD(free_list);
 	int session_count = 0;
 
 	spin_lock_bh(&se_tpg->session_lock);
@@ -4786,15 +4813,18 @@
 		}
 		atomic_set(&sess->session_reinstatement, 1);
 		spin_unlock(&sess->conn_lock);
-		spin_unlock_bh(&se_tpg->session_lock);
 
-		iscsit_free_session(sess);
-		spin_lock_bh(&se_tpg->session_lock);
-
-		session_count++;
+		list_move_tail(&se_sess->sess_list, &free_list);
 	}
 	spin_unlock_bh(&se_tpg->session_lock);
 
+	list_for_each_entry_safe(se_sess, se_sess_tmp, &free_list, sess_list) {
+		sess = (struct iscsi_session *)se_sess->fabric_sess_ptr;
+
+		iscsit_free_session(sess);
+		session_count++;
+	}
+
 	pr_debug("Released %d iSCSI Session(s) from Target Portal"
 			" Group: %hu\n", session_count, tpg->tpgt);
 	return 0;
diff --git a/drivers/target/iscsi/iscsi_target_login.c b/drivers/target/iscsi/iscsi_target_login.c
index 3d0fe4f..7e8f65e 100644
--- a/drivers/target/iscsi/iscsi_target_login.c
+++ b/drivers/target/iscsi/iscsi_target_login.c
@@ -82,6 +82,7 @@
 	init_completion(&conn->conn_logout_comp);
 	init_completion(&conn->rx_half_close_comp);
 	init_completion(&conn->tx_half_close_comp);
+	init_completion(&conn->rx_login_comp);
 	spin_lock_init(&conn->cmd_lock);
 	spin_lock_init(&conn->conn_usage_lock);
 	spin_lock_init(&conn->immed_queue_lock);
@@ -644,7 +645,7 @@
 		iscsit_start_nopin_timer(conn);
 }
 
-static int iscsit_start_kthreads(struct iscsi_conn *conn)
+int iscsit_start_kthreads(struct iscsi_conn *conn)
 {
 	int ret = 0;
 
@@ -679,6 +680,7 @@
 
 	return 0;
 out_tx:
+	send_sig(SIGINT, conn->tx_thread, 1);
 	kthread_stop(conn->tx_thread);
 	conn->tx_thread_active = false;
 out_bitmap:
@@ -689,7 +691,7 @@
 	return ret;
 }
 
-int iscsi_post_login_handler(
+void iscsi_post_login_handler(
 	struct iscsi_np *np,
 	struct iscsi_conn *conn,
 	u8 zero_tsih)
@@ -699,7 +701,6 @@
 	struct se_session *se_sess = sess->se_sess;
 	struct iscsi_portal_group *tpg = sess->tpg;
 	struct se_portal_group *se_tpg = &tpg->tpg_se_tpg;
-	int rc;
 
 	iscsit_inc_conn_usage_count(conn);
 
@@ -739,10 +740,6 @@
 			sess->sess_ops->InitiatorName);
 		spin_unlock_bh(&sess->conn_lock);
 
-		rc = iscsit_start_kthreads(conn);
-		if (rc)
-			return rc;
-
 		iscsi_post_login_start_timers(conn);
 		/*
 		 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -751,15 +748,20 @@
 		iscsit_thread_get_cpumask(conn);
 		conn->conn_rx_reset_cpumask = 1;
 		conn->conn_tx_reset_cpumask = 1;
-
+		/*
+		 * Wakeup the sleeping iscsi_target_rx_thread() now that
+		 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+		 */
+		complete(&conn->rx_login_comp);
 		iscsit_dec_conn_usage_count(conn);
+
 		if (stop_timer) {
 			spin_lock_bh(&se_tpg->session_lock);
 			iscsit_stop_time2retain_timer(sess);
 			spin_unlock_bh(&se_tpg->session_lock);
 		}
 		iscsit_dec_session_usage_count(sess);
-		return 0;
+		return;
 	}
 
 	iscsi_set_session_parameters(sess->sess_ops, conn->param_list, 1);
@@ -800,10 +802,6 @@
 		" iSCSI Target Portal Group: %hu\n", tpg->nsessions, tpg->tpgt);
 	spin_unlock_bh(&se_tpg->session_lock);
 
-	rc = iscsit_start_kthreads(conn);
-	if (rc)
-		return rc;
-
 	iscsi_post_login_start_timers(conn);
 	/*
 	 * Determine CPU mask to ensure connection's RX and TX kthreads
@@ -812,10 +810,12 @@
 	iscsit_thread_get_cpumask(conn);
 	conn->conn_rx_reset_cpumask = 1;
 	conn->conn_tx_reset_cpumask = 1;
-
+	/*
+	 * Wakeup the sleeping iscsi_target_rx_thread() now that
+	 * iscsi_conn is in TARG_CONN_STATE_LOGGED_IN state.
+	 */
+	complete(&conn->rx_login_comp);
 	iscsit_dec_conn_usage_count(conn);
-
-	return 0;
 }
 
 static void iscsi_handle_login_thread_timeout(unsigned long data)
@@ -1380,23 +1380,12 @@
 	if (ret < 0)
 		goto new_sess_out;
 
-	if (!conn->sess) {
-		pr_err("struct iscsi_conn session pointer is NULL!\n");
-		goto new_sess_out;
-	}
-
 	iscsi_stop_login_thread_timer(np);
 
-	if (signal_pending(current))
-		goto new_sess_out;
-
 	if (ret == 1) {
 		tpg_np = conn->tpg_np;
 
-		ret = iscsi_post_login_handler(np, conn, zero_tsih);
-		if (ret < 0)
-			goto new_sess_out;
-
+		iscsi_post_login_handler(np, conn, zero_tsih);
 		iscsit_deaccess_np(np, tpg, tpg_np);
 	}
 
diff --git a/drivers/target/iscsi/iscsi_target_login.h b/drivers/target/iscsi/iscsi_target_login.h
index 1c73580..57aa0d0 100644
--- a/drivers/target/iscsi/iscsi_target_login.h
+++ b/drivers/target/iscsi/iscsi_target_login.h
@@ -12,7 +12,8 @@
 extern int iscsit_get_login_rx(struct iscsi_conn *, struct iscsi_login *);
 extern int iscsit_put_login_tx(struct iscsi_conn *, struct iscsi_login *, u32);
 extern void iscsit_free_conn(struct iscsi_np *, struct iscsi_conn *);
-extern int iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
+extern int iscsit_start_kthreads(struct iscsi_conn *);
+extern void iscsi_post_login_handler(struct iscsi_np *, struct iscsi_conn *, u8);
 extern void iscsi_target_login_sess_out(struct iscsi_conn *, struct iscsi_np *,
 				bool, bool);
 extern int iscsi_target_login_thread(void *);
diff --git a/drivers/target/iscsi/iscsi_target_nego.c b/drivers/target/iscsi/iscsi_target_nego.c
index 8c02fa3..f9cde91 100644
--- a/drivers/target/iscsi/iscsi_target_nego.c
+++ b/drivers/target/iscsi/iscsi_target_nego.c
@@ -17,6 +17,7 @@
  ******************************************************************************/
 
 #include <linux/ctype.h>
+#include <linux/kthread.h>
 #include <scsi/iscsi_proto.h>
 #include <target/target_core_base.h>
 #include <target/target_core_fabric.h>
@@ -361,10 +362,24 @@
 		ntohl(login_rsp->statsn), login->rsp_length);
 
 	padding = ((-login->rsp_length) & 3);
+	/*
+	 * Before sending the last login response containing the transition
+	 * bit for full-feature-phase, go ahead and start up TX/RX threads
+	 * now to avoid potential resource allocation failures after the
+	 * final login response has been sent.
+	 */
+	if (login->login_complete) {
+		int rc = iscsit_start_kthreads(conn);
+		if (rc) {
+			iscsit_tx_login_rsp(conn, ISCSI_STATUS_CLS_TARGET_ERR,
+					    ISCSI_LOGIN_STATUS_NO_RESOURCES);
+			return -1;
+		}
+	}
 
 	if (conn->conn_transport->iscsit_put_login_tx(conn, login,
 					login->rsp_length + padding) < 0)
-		return -1;
+		goto err;
 
 	login->rsp_length		= 0;
 	mutex_lock(&sess->cmdsn_mutex);
@@ -373,6 +388,23 @@
 	mutex_unlock(&sess->cmdsn_mutex);
 
 	return 0;
+
+err:
+	if (login->login_complete) {
+		if (conn->rx_thread && conn->rx_thread_active) {
+			send_sig(SIGINT, conn->rx_thread, 1);
+			kthread_stop(conn->rx_thread);
+		}
+		if (conn->tx_thread && conn->tx_thread_active) {
+			send_sig(SIGINT, conn->tx_thread, 1);
+			kthread_stop(conn->tx_thread);
+		}
+		spin_lock(&iscsit_global->ts_bitmap_lock);
+		bitmap_release_region(iscsit_global->ts_bitmap, conn->bitmap_id,
+				      get_order(1));
+		spin_unlock(&iscsit_global->ts_bitmap_lock);
+	}
+	return -1;
 }
 
 static void iscsi_target_sk_data_ready(struct sock *sk)
diff --git a/drivers/target/target_core_configfs.c b/drivers/target/target_core_configfs.c
index 0b0de36..c2e9fea 100644
--- a/drivers/target/target_core_configfs.c
+++ b/drivers/target/target_core_configfs.c
@@ -747,7 +747,7 @@
 	if (!dev->transport->init_prot || !dev->transport->free_prot) {
 		/* 0 is only allowed value for non-supporting backends */
 		if (flag == 0)
-			return 0;
+			return count;
 
 		pr_err("DIF protection not supported by backend: %s\n",
 		       dev->transport->name);
@@ -1590,9 +1590,9 @@
 	u8 type = 0;
 
 	if (dev->transport->transport_flags & TRANSPORT_FLAG_PASSTHROUGH)
-		return 0;
+		return count;
 	if (dev->dev_reservation_flags & DRF_SPC2_RESERVATIONS)
-		return 0;
+		return count;
 
 	if (dev->export_count) {
 		pr_debug("Unable to process APTPL metadata while"
@@ -1658,22 +1658,32 @@
 		 * PR APTPL Metadata for Reservation
 		 */
 		case Opt_res_holder:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			res_holder = arg;
 			break;
 		case Opt_res_type:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			type = (u8)arg;
 			break;
 		case Opt_res_scope:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			break;
 		case Opt_res_all_tg_pt:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			all_tg_pt = (int)arg;
 			break;
 		case Opt_mapped_lun:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			mapped_lun = (u64)arg;
 			break;
 		/*
@@ -1701,14 +1711,20 @@
 			}
 			break;
 		case Opt_tpgt:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			tpgt = (u16)arg;
 			break;
 		case Opt_port_rtpi:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			break;
 		case Opt_target_lun:
-			match_int(args, &arg);
+			ret = match_int(args, &arg);
+			if (ret)
+				goto out;
 			target_lun = (u64)arg;
 			break;
 		default:
@@ -1985,7 +2001,7 @@
 
 	lu_gp_mem = dev->dev_alua_lu_gp_mem;
 	if (!lu_gp_mem)
-		return 0;
+		return count;
 
 	if (count > LU_GROUP_NAME_BUF) {
 		pr_err("ALUA LU Group Alias too large!\n");
diff --git a/drivers/target/target_core_pr.c b/drivers/target/target_core_pr.c
index 0fdbe43..5ab7100 100644
--- a/drivers/target/target_core_pr.c
+++ b/drivers/target/target_core_pr.c
@@ -1474,7 +1474,7 @@
 	LIST_HEAD(tid_dest_list);
 	struct pr_transport_id_holder *tidh_new, *tidh, *tidh_tmp;
 	unsigned char *buf, *ptr, proto_ident;
-	const unsigned char *i_str;
+	const unsigned char *i_str = NULL;
 	char *iport_ptr = NULL, i_buf[PR_REG_ISID_ID_LEN];
 	sense_reason_t ret;
 	u32 tpdl, tid_len = 0;
diff --git a/drivers/target/target_core_rd.c b/drivers/target/target_core_rd.c
index 4703f40..384cf88 100644
--- a/drivers/target/target_core_rd.c
+++ b/drivers/target/target_core_rd.c
@@ -333,6 +333,7 @@
 	dev->dev_attrib.hw_block_size = RD_BLOCKSIZE;
 	dev->dev_attrib.hw_max_sectors = UINT_MAX;
 	dev->dev_attrib.hw_queue_depth = RD_MAX_DEVICE_QUEUE_DEPTH;
+	dev->dev_attrib.is_nonrot = 1;
 
 	rd_dev->rd_dev_id = rd_host->rd_host_dev_id_count++;
 
diff --git a/drivers/target/target_core_spc.c b/drivers/target/target_core_spc.c
index b074443..b5ba1ec 100644
--- a/drivers/target/target_core_spc.c
+++ b/drivers/target/target_core_spc.c
@@ -454,10 +454,17 @@
 		    cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE1_PROT)
 			buf[4] = 0x5;
 		else if (dev->dev_attrib.pi_prot_type == TARGET_DIF_TYPE3_PROT ||
-			cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT)
+			 cmd->se_sess->sess_prot_type == TARGET_DIF_TYPE3_PROT)
 			buf[4] = 0x4;
 	}
 
+	/* logical unit supports type 1 and type 3 protection */
+	if ((dev->transport->get_device_type(dev) == TYPE_DISK) &&
+	    (sess->sup_prot_ops & (TARGET_PROT_DIN_PASS | TARGET_PROT_DOUT_PASS)) &&
+	    (dev->dev_attrib.pi_prot_type || cmd->se_sess->sess_prot_type)) {
+		buf[4] |= (0x3 << 3);
+	}
+
 	/* Set HEADSUP, ORDSUP, SIMPSUP */
 	buf[5] = 0x07;
 
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index 2fb29df..563c510 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -689,6 +689,23 @@
 }
 EXPORT_SYMBOL_GPL(vfio_device_get_from_dev);
 
+static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
+						     char *buf)
+{
+	struct vfio_device *device;
+
+	mutex_lock(&group->device_lock);
+	list_for_each_entry(device, &group->device_list, group_next) {
+		if (!strcmp(dev_name(device->dev), buf)) {
+			vfio_device_get(device);
+			break;
+		}
+	}
+	mutex_unlock(&group->device_lock);
+
+	return device;
+}
+
 /*
  * Caller must hold a reference to the vfio_device
  */
@@ -1198,53 +1215,53 @@
 {
 	struct vfio_device *device;
 	struct file *filep;
-	int ret = -ENODEV;
+	int ret;
 
 	if (0 == atomic_read(&group->container_users) ||
 	    !group->container->iommu_driver || !vfio_group_viable(group))
 		return -EINVAL;
 
-	mutex_lock(&group->device_lock);
-	list_for_each_entry(device, &group->device_list, group_next) {
-		if (strcmp(dev_name(device->dev), buf))
-			continue;
+	device = vfio_device_get_from_name(group, buf);
+	if (!device)
+		return -ENODEV;
 
-		ret = device->ops->open(device->device_data);
-		if (ret)
-			break;
-		/*
-		 * We can't use anon_inode_getfd() because we need to modify
-		 * the f_mode flags directly to allow more than just ioctls
-		 */
-		ret = get_unused_fd_flags(O_CLOEXEC);
-		if (ret < 0) {
-			device->ops->release(device->device_data);
-			break;
-		}
-
-		filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
-					   device, O_RDWR);
-		if (IS_ERR(filep)) {
-			put_unused_fd(ret);
-			ret = PTR_ERR(filep);
-			device->ops->release(device->device_data);
-			break;
-		}
-
-		/*
-		 * TODO: add an anon_inode interface to do this.
-		 * Appears to be missing by lack of need rather than
-		 * explicitly prevented.  Now there's need.
-		 */
-		filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
-
-		vfio_device_get(device);
-		atomic_inc(&group->container_users);
-
-		fd_install(ret, filep);
-		break;
+	ret = device->ops->open(device->device_data);
+	if (ret) {
+		vfio_device_put(device);
+		return ret;
 	}
-	mutex_unlock(&group->device_lock);
+
+	/*
+	 * We can't use anon_inode_getfd() because we need to modify
+	 * the f_mode flags directly to allow more than just ioctls
+	 */
+	ret = get_unused_fd_flags(O_CLOEXEC);
+	if (ret < 0) {
+		device->ops->release(device->device_data);
+		vfio_device_put(device);
+		return ret;
+	}
+
+	filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
+				   device, O_RDWR);
+	if (IS_ERR(filep)) {
+		put_unused_fd(ret);
+		ret = PTR_ERR(filep);
+		device->ops->release(device->device_data);
+		vfio_device_put(device);
+		return ret;
+	}
+
+	/*
+	 * TODO: add an anon_inode interface to do this.
+	 * Appears to be missing by lack of need rather than
+	 * explicitly prevented.  Now there's need.
+	 */
+	filep->f_mode |= (FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
+
+	atomic_inc(&group->container_users);
+
+	fd_install(ret, filep);
 
 	return ret;
 }
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
index a9fe859..eec2f11 100644
--- a/drivers/vhost/vhost.c
+++ b/drivers/vhost/vhost.c
@@ -683,11 +683,8 @@
 {
 	void *n = kzalloc(size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
 
-	if (!n) {
+	if (!n)
 		n = vzalloc(size);
-		if (!n)
-			return ERR_PTR(-ENOMEM);
-	}
 	return n;
 }
 
@@ -995,6 +992,7 @@
 		}
 		if (eventfp != d->log_file) {
 			filep = d->log_file;
+			d->log_file = eventfp;
 			ctx = d->log_ctx;
 			d->log_ctx = eventfp ?
 				eventfd_ctx_fileget(eventfp) : NULL;
diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c
index fd93369..bf4a23c 100644
--- a/drivers/xen/balloon.c
+++ b/drivers/xen/balloon.c
@@ -472,7 +472,7 @@
 }
 
 /*
- * We avoid multiple worker processes conflicting via the balloon mutex.
+ * As this is a work item it is guaranteed to run as a single instance only.
  * We may of course race updates of the target counts (which are protected
  * by the balloon lock), or with changes to the Xen hard limit, but we will
  * recover from these in time.
@@ -482,9 +482,10 @@
 	enum bp_state state = BP_DONE;
 	long credit;
 
-	mutex_lock(&balloon_mutex);
 
 	do {
+		mutex_lock(&balloon_mutex);
+
 		credit = current_credit();
 
 		if (credit > 0) {
@@ -499,17 +500,15 @@
 
 		state = update_schedule(state);
 
-#ifndef CONFIG_PREEMPT
-		if (need_resched())
-			schedule();
-#endif
+		mutex_unlock(&balloon_mutex);
+
+		cond_resched();
+
 	} while (credit && state == BP_DONE);
 
 	/* Schedule more work if there is some still to be done. */
 	if (state == BP_EAGAIN)
 		schedule_delayed_work(&balloon_worker, balloon_stats.schedule_delay * HZ);
-
-	mutex_unlock(&balloon_mutex);
 }
 
 /* Resets the Xen limit, sets new target, and kicks off processing. */
diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c
index 96093ae..1495ecc 100644
--- a/drivers/xen/events/events_base.c
+++ b/drivers/xen/events/events_base.c
@@ -452,10 +452,12 @@
 	irq_free_desc(irq);
 }
 
-static void xen_evtchn_close(unsigned int port)
+static void xen_evtchn_close(unsigned int port, unsigned int cpu)
 {
 	struct evtchn_close close;
 
+	xen_evtchn_op_close(port, cpu);
+
 	close.port = port;
 	if (HYPERVISOR_event_channel_op(EVTCHNOP_close, &close) != 0)
 		BUG();
@@ -544,7 +546,7 @@
 
 err:
 	pr_err("irq%d: Failed to set port to irq mapping (%d)\n", irq, rc);
-	xen_evtchn_close(evtchn);
+	xen_evtchn_close(evtchn, NR_CPUS);
 	return 0;
 }
 
@@ -565,7 +567,7 @@
 		return;
 
 	mask_evtchn(evtchn);
-	xen_evtchn_close(evtchn);
+	xen_evtchn_close(evtchn, cpu_from_evtchn(evtchn));
 	xen_irq_info_cleanup(info);
 }
 
@@ -609,7 +611,7 @@
 	if (VALID_EVTCHN(evtchn)) {
 		unsigned int cpu = cpu_from_irq(irq);
 
-		xen_evtchn_close(evtchn);
+		xen_evtchn_close(evtchn, cpu);
 
 		switch (type_from_irq(irq)) {
 		case IRQT_VIRQ:
diff --git a/drivers/xen/events/events_fifo.c b/drivers/xen/events/events_fifo.c
index ed673e1..6df8aac 100644
--- a/drivers/xen/events/events_fifo.c
+++ b/drivers/xen/events/events_fifo.c
@@ -255,6 +255,12 @@
 	}
 }
 
+static bool evtchn_fifo_is_linked(unsigned port)
+{
+	event_word_t *word = event_word_from_port(port);
+	return sync_test_bit(EVTCHN_FIFO_BIT(LINKED, word), BM(word));
+}
+
 static uint32_t clear_linked(volatile event_word_t *word)
 {
 	event_word_t new, old, w;
@@ -281,7 +287,8 @@
 
 static void consume_one_event(unsigned cpu,
 			      struct evtchn_fifo_control_block *control_block,
-			      unsigned priority, unsigned long *ready)
+			      unsigned priority, unsigned long *ready,
+			      bool drop)
 {
 	struct evtchn_fifo_queue *q = &per_cpu(cpu_queue, cpu);
 	uint32_t head;
@@ -313,13 +320,15 @@
 	if (head == 0)
 		clear_bit(priority, ready);
 
-	if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port))
-		handle_irq_for_port(port);
+	if (evtchn_fifo_is_pending(port) && !evtchn_fifo_is_masked(port)) {
+		if (likely(!drop))
+			handle_irq_for_port(port);
+	}
 
 	q->head[priority] = head;
 }
 
-static void evtchn_fifo_handle_events(unsigned cpu)
+static void __evtchn_fifo_handle_events(unsigned cpu, bool drop)
 {
 	struct evtchn_fifo_control_block *control_block;
 	unsigned long ready;
@@ -331,11 +340,16 @@
 
 	while (ready) {
 		q = find_first_bit(&ready, EVTCHN_FIFO_MAX_QUEUES);
-		consume_one_event(cpu, control_block, q, &ready);
+		consume_one_event(cpu, control_block, q, &ready, drop);
 		ready |= xchg(&control_block->ready, 0);
 	}
 }
 
+static void evtchn_fifo_handle_events(unsigned cpu)
+{
+	__evtchn_fifo_handle_events(cpu, false);
+}
+
 static void evtchn_fifo_resume(void)
 {
 	unsigned cpu;
@@ -371,6 +385,26 @@
 	event_array_pages = 0;
 }
 
+static void evtchn_fifo_close(unsigned port, unsigned int cpu)
+{
+	if (cpu == NR_CPUS)
+		return;
+
+	get_online_cpus();
+	if (cpu_online(cpu)) {
+		if (WARN_ON(irqs_disabled()))
+			goto out;
+
+		while (evtchn_fifo_is_linked(port))
+			cpu_relax();
+	} else {
+		__evtchn_fifo_handle_events(cpu, true);
+	}
+
+out:
+	put_online_cpus();
+}
+
 static const struct evtchn_ops evtchn_ops_fifo = {
 	.max_channels      = evtchn_fifo_max_channels,
 	.nr_channels       = evtchn_fifo_nr_channels,
@@ -384,6 +418,7 @@
 	.unmask            = evtchn_fifo_unmask,
 	.handle_events     = evtchn_fifo_handle_events,
 	.resume            = evtchn_fifo_resume,
+	.close             = evtchn_fifo_close,
 };
 
 static int evtchn_fifo_alloc_control_block(unsigned cpu)
diff --git a/drivers/xen/events/events_internal.h b/drivers/xen/events/events_internal.h
index 50c2050a..d18e123 100644
--- a/drivers/xen/events/events_internal.h
+++ b/drivers/xen/events/events_internal.h
@@ -68,6 +68,7 @@
 	bool (*test_and_set_mask)(unsigned port);
 	void (*mask)(unsigned port);
 	void (*unmask)(unsigned port);
+	void (*close)(unsigned port, unsigned cpu);
 
 	void (*handle_events)(unsigned cpu);
 	void (*resume)(void);
@@ -145,6 +146,12 @@
 		evtchn_ops->resume();
 }
 
+static inline void xen_evtchn_op_close(unsigned port, unsigned cpu)
+{
+	if (evtchn_ops->close)
+		return evtchn_ops->close(port, cpu);
+}
+
 void xen_evtchn_2l_init(void);
 int xen_evtchn_fifo_init(void);
 
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 67b9163..0dbb222 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -568,12 +568,14 @@
 
 	pr_debug("priv %p\n", priv);
 
+	mutex_lock(&priv->lock);
 	while (!list_empty(&priv->maps)) {
 		map = list_entry(priv->maps.next, struct grant_map, next);
 		list_del(&map->next);
 		gntdev_put_map(NULL /* already removed */, map);
 	}
 	WARN_ON(!list_empty(&priv->freeable_maps));
+	mutex_unlock(&priv->lock);
 
 	if (use_ptemod)
 		mmu_notifier_unregister(&priv->mn, priv->mm);
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 862fbc2..564a7de 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -378,7 +378,7 @@
 
 	ret = btrfs_kobj_add_device(tgt_device->fs_devices, tgt_device);
 	if (ret)
-		btrfs_error(root->fs_info, ret, "kobj add dev failed");
+		btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
 
 	printk_in_rcu(KERN_INFO
 		      "BTRFS: dev_replace from %s (devid %llu) to %s started\n",
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index a9aadb2..f556c37 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2842,6 +2842,7 @@
 	    !extent_buffer_uptodate(chunk_root->node)) {
 		printk(KERN_ERR "BTRFS: failed to read chunk root on %s\n",
 		       sb->s_id);
+		chunk_root->node = NULL;
 		goto fail_tree_roots;
 	}
 	btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
@@ -2879,7 +2880,7 @@
 	    !extent_buffer_uptodate(tree_root->node)) {
 		printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
 		       sb->s_id);
-
+		tree_root->node = NULL;
 		goto recovery_tree_root;
 	}
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 171312d..07204bf 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -4227,6 +4227,24 @@
 	space_info->chunk_alloc = 0;
 	spin_unlock(&space_info->lock);
 	mutex_unlock(&fs_info->chunk_mutex);
+	/*
+	 * When we allocate a new chunk we reserve space in the chunk block
+	 * reserve to make sure we can COW nodes/leafs in the chunk tree or
+	 * add new nodes/leafs to it if we end up needing to do it when
+	 * inserting the chunk item and updating device items as part of the
+	 * second phase of chunk allocation, performed by
+	 * btrfs_finish_chunk_alloc(). So make sure we don't accumulate a
+	 * large number of new block groups to create in our transaction
+	 * handle's new_bgs list to avoid exhausting the chunk block reserve
+	 * in extreme cases - like having a single transaction create many new
+	 * block groups when starting to write out the free space caches of all
+	 * the block groups that were made dirty during the lifetime of the
+	 * transaction.
+	 */
+	if (trans->chunk_bytes_reserved >= (2 * 1024 * 1024ull)) {
+		btrfs_create_pending_block_groups(trans, trans->root);
+		btrfs_trans_release_chunk_metadata(trans);
+	}
 	return ret;
 }
 
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 51e0f0d..f5021fc 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -2152,7 +2152,8 @@
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 
-	if (current != root->fs_info->transaction_kthread)
+	if (current != root->fs_info->transaction_kthread &&
+	    current != root->fs_info->cleaner_kthread)
 		btrfs_run_delayed_iputs(root);
 
 	return ret;
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index dc10c9d..ddd5e94 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -1506,7 +1506,6 @@
 
 	swap(cf, ci->i_prealloc_cap_flush);
 	cf->caps = flushing;
-	cf->kick = false;
 
 	spin_lock(&mdsc->cap_dirty_lock);
 	list_del_init(&ci->i_dirty_item);
@@ -2123,8 +2122,7 @@
 
 static int __kick_flushing_caps(struct ceph_mds_client *mdsc,
 				struct ceph_mds_session *session,
-				struct ceph_inode_info *ci,
-				bool kick_all)
+				struct ceph_inode_info *ci)
 {
 	struct inode *inode = &ci->vfs_inode;
 	struct ceph_cap *cap;
@@ -2150,9 +2148,7 @@
 
 		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
 			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			if (cf->tid < first_tid)
-				continue;
-			if (kick_all || cf->kick)
+			if (cf->tid >= first_tid)
 				break;
 		}
 		if (!n) {
@@ -2161,7 +2157,6 @@
 		}
 
 		cf = rb_entry(n, struct ceph_cap_flush, i_node);
-		cf->kick = false;
 
 		first_tid = cf->tid + 1;
 
@@ -2181,8 +2176,6 @@
 {
 	struct ceph_inode_info *ci;
 	struct ceph_cap *cap;
-	struct ceph_cap_flush *cf;
-	struct rb_node *n;
 
 	dout("early_kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
@@ -2205,16 +2198,11 @@
 		if ((cap->issued & ci->i_flushing_caps) !=
 		    ci->i_flushing_caps) {
 			spin_unlock(&ci->i_ceph_lock);
-			if (!__kick_flushing_caps(mdsc, session, ci, true))
+			if (!__kick_flushing_caps(mdsc, session, ci))
 				continue;
 			spin_lock(&ci->i_ceph_lock);
 		}
 
-		for (n = rb_first(&ci->i_cap_flush_tree); n; n = rb_next(n)) {
-			cf = rb_entry(n, struct ceph_cap_flush, i_node);
-			cf->kick = true;
-		}
-
 		spin_unlock(&ci->i_ceph_lock);
 	}
 }
@@ -2228,7 +2216,7 @@
 
 	dout("kick_flushing_caps mds%d\n", session->s_mds);
 	list_for_each_entry(ci, &session->s_cap_flushing, i_flushing_item) {
-		int delayed = __kick_flushing_caps(mdsc, session, ci, false);
+		int delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
@@ -2261,7 +2249,7 @@
 
 		spin_unlock(&ci->i_ceph_lock);
 
-		delayed = __kick_flushing_caps(mdsc, session, ci, true);
+		delayed = __kick_flushing_caps(mdsc, session, ci);
 		if (delayed) {
 			spin_lock(&ci->i_ceph_lock);
 			__cap_delay_requeue(mdsc, ci);
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 4347039..6706bde 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -287,7 +287,7 @@
 		return 0;
 
 	spin_lock(&ctx->flc_lock);
-	list_for_each_entry(lock, &ctx->flc_flock, fl_list) {
+	list_for_each_entry(lock, &ctx->flc_posix, fl_list) {
 		++seen_fcntl;
 		if (seen_fcntl > num_fcntl_locks) {
 			err = -ENOSPC;
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 860cc016..2f2460d 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -189,7 +189,6 @@
 struct ceph_cap_flush {
 	u64 tid;
 	int caps;
-	bool kick;
 	struct rb_node g_node; // global
 	union {
 		struct rb_node i_node; // inode
diff --git a/fs/dax.c b/fs/dax.c
index c3e21cc..a7f77e1 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -319,6 +319,12 @@
  * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  * @get_block: The filesystem method used to translate file offsets to blocks
+ * @complete_unwritten: The filesystem method used to convert unwritten blocks
+ *	to written so the data written to them is exposed. This is required for
+ *	required by write faults for filesystems that will return unwritten
+ *	extent mappings from @get_block, but it is optional for reads as
+ *	dax_insert_mapping() will always zero unwritten blocks. If the fs does
+ *	not support unwritten extents, the it should pass NULL.
  *
  * When a page fault occurs, filesystems may call this helper in their
  * fault handler for DAX files. __dax_fault() assumes the caller has done all
@@ -437,8 +443,12 @@
 	 * as for normal BH based IO completions.
 	 */
 	error = dax_insert_mapping(inode, &bh, vma, vmf);
-	if (buffer_unwritten(&bh))
-		complete_unwritten(&bh, !error);
+	if (buffer_unwritten(&bh)) {
+		if (complete_unwritten)
+			complete_unwritten(&bh, !error);
+		else
+			WARN_ON_ONCE(!(vmf->flags & FAULT_FLAG_WRITE));
+	}
 
  out:
 	if (error == -ENOMEM)
diff --git a/fs/dcache.c b/fs/dcache.c
index 5c8ea15..9b5fe50 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -3442,22 +3442,15 @@
 	inode_init_early();
 }
 
-void __init vfs_caches_init(unsigned long mempages)
+void __init vfs_caches_init(void)
 {
-	unsigned long reserve;
-
-	/* Base hash sizes on available memory, with a reserve equal to
-           150% of current kernel size */
-
-	reserve = min((mempages - nr_free_pages()) * 3/2, mempages - 1);
-	mempages -= reserve;
-
 	names_cachep = kmem_cache_create("names_cache", PATH_MAX, 0,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 
 	dcache_init();
 	inode_init();
-	files_init(mempages);
+	files_init();
+	files_maxfiles_init();
 	mnt_init();
 	bdev_cache_init();
 	chrdev_init();
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9bedfa8..f71e19a 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2072,8 +2072,6 @@
 		return 1;
 	}
 
-	mark_inode_dirty(inode);
-
 	if (!PageDirty(page)) {
 		__set_page_dirty_nobuffers(page);
 		update_dirty_page(inode, page);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index ada2a3d..b0f38c3 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -1331,12 +1331,13 @@
 	if (ret)
 		return ret;
 
-	if (f2fs_is_atomic_file(inode))
+	if (f2fs_is_atomic_file(inode)) {
+		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 		commit_inmem_pages(inode, false);
+	}
 
 	ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
 	mnt_drop_write_file(filp);
-	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
 	return ret;
 }
 
@@ -1387,8 +1388,8 @@
 	f2fs_balance_fs(F2FS_I_SB(inode));
 
 	if (f2fs_is_atomic_file(inode)) {
-		commit_inmem_pages(inode, false);
 		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
+		commit_inmem_pages(inode, false);
 	}
 
 	if (f2fs_is_volatile_file(inode))
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index e1e7361..22fb5ef 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -556,27 +556,39 @@
 	if (!fio.encrypted_page)
 		goto put_out;
 
-	f2fs_submit_page_bio(&fio);
-
-	/* allocate block address */
-	f2fs_wait_on_page_writeback(dn.node_page, NODE);
-
-	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
-					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
-	dn.data_blkaddr = fio.blk_addr;
+	err = f2fs_submit_page_bio(&fio);
+	if (err)
+		goto put_page_out;
 
 	/* write page */
 	lock_page(fio.encrypted_page);
+
+	if (unlikely(!PageUptodate(fio.encrypted_page)))
+		goto put_page_out;
+	if (unlikely(fio.encrypted_page->mapping != META_MAPPING(fio.sbi)))
+		goto put_page_out;
+
+	set_page_dirty(fio.encrypted_page);
+	f2fs_wait_on_page_writeback(fio.encrypted_page, META);
+	if (clear_page_dirty_for_io(fio.encrypted_page))
+		dec_page_count(fio.sbi, F2FS_DIRTY_META);
+
 	set_page_writeback(fio.encrypted_page);
+
+	/* allocate block address */
+	f2fs_wait_on_page_writeback(dn.node_page, NODE);
+	allocate_data_block(fio.sbi, NULL, fio.blk_addr,
+					&fio.blk_addr, &sum, CURSEG_COLD_DATA);
 	fio.rw = WRITE_SYNC;
 	f2fs_submit_page_mbio(&fio);
 
+	dn.data_blkaddr = fio.blk_addr;
 	set_data_blkaddr(&dn);
 	f2fs_update_extent_cache(&dn);
 	set_inode_flag(F2FS_I(inode), FI_APPEND_WRITE);
 	if (page->index == 0)
 		set_inode_flag(F2FS_I(inode), FI_FIRST_BLOCK_WRITTEN);
-
+put_page_out:
 	f2fs_put_page(fio.encrypted_page, 1);
 put_out:
 	f2fs_put_dnode(&dn);
@@ -605,8 +617,8 @@
 			.page = page,
 			.encrypted_page = NULL,
 		};
+		set_page_dirty(page);
 		f2fs_wait_on_page_writeback(page, DATA);
-
 		if (clear_page_dirty_for_io(page))
 			inode_dec_dirty_pages(inode);
 		set_cold_data(page);
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 38e75fb..a13ffcc 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -141,6 +141,8 @@
 	kunmap_atomic(dst_addr);
 	SetPageUptodate(page);
 no_update:
+	set_page_dirty(page);
+
 	/* clear dirty state */
 	dirty = clear_page_dirty_for_io(page);
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 1eb3437..61b97f9 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -257,6 +257,7 @@
 		if (!abort) {
 			lock_page(cur->page);
 			if (cur->page->mapping == inode->i_mapping) {
+				set_page_dirty(cur->page);
 				f2fs_wait_on_page_writeback(cur->page, DATA);
 				if (clear_page_dirty_for_io(cur->page))
 					inode_dec_dirty_pages(inode);
diff --git a/fs/file_table.c b/fs/file_table.c
index 7f9d407..ad17e05 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -25,6 +25,7 @@
 #include <linux/hardirq.h>
 #include <linux/task_work.h>
 #include <linux/ima.h>
+#include <linux/swap.h>
 
 #include <linux/atomic.h>
 
@@ -308,19 +309,24 @@
 	}
 }
 
-void __init files_init(unsigned long mempages)
+void __init files_init(void)
 { 
-	unsigned long n;
-
 	filp_cachep = kmem_cache_create("filp", sizeof(struct file), 0,
 			SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
-
-	/*
-	 * One file with associated inode and dcache is very roughly 1K.
-	 * Per default don't use more than 10% of our memory for files. 
-	 */ 
-
-	n = (mempages * (PAGE_SIZE / 1024)) / 10;
-	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 	percpu_counter_init(&nr_files, 0, GFP_KERNEL);
+}
+
+/*
+ * One file with associated inode and dcache is very roughly 1K. Per default
+ * do not use more than 10% of our memory for files.
+ */
+void __init files_maxfiles_init(void)
+{
+	unsigned long n;
+	unsigned long memreserve = (totalram_pages - nr_free_pages()) * 3/2;
+
+	memreserve = min(memreserve, totalram_pages - 1);
+	n = ((totalram_pages - memreserve) * (PAGE_SIZE / 1024)) / 10;
+
+	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 } 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 0cf74df..973c24c 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1010,6 +1010,8 @@
 	inode = hugetlbfs_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0);
 	if (!inode)
 		goto out_dentry;
+	if (creat_flags == HUGETLB_SHMFS_INODE)
+		inode->i_flags |= S_PRIVATE;
 
 	file = ERR_PTR(-ENOMEM);
 	if (hugetlb_reserve_pages(inode, 0,
diff --git a/fs/namei.c b/fs/namei.c
index ae4e4c1..fbbcf09 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1954,8 +1954,13 @@
 				continue;
 			}
 		}
-		if (unlikely(!d_can_lookup(nd->path.dentry)))
+		if (unlikely(!d_can_lookup(nd->path.dentry))) {
+			if (nd->flags & LOOKUP_RCU) {
+				if (unlazy_walk(nd, NULL, 0))
+					return -ECHILD;
+			}
 			return -ENOTDIR;
+		}
 	}
 }
 
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index ecebb40..4a90c9b 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -775,7 +775,7 @@
 	server->options = data->options;
 	server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
 		NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
-		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME|NFS_CAP_CHANGE_ATTR;
+		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index c12951b..b3289d7 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -1852,7 +1852,7 @@
 	struct nfs42_layoutstat_devinfo *devinfo;
 	int i;
 
-	for (i = 0; i <= FF_LAYOUT_MIRROR_COUNT(pls); i++) {
+	for (i = 0; i < FF_LAYOUT_MIRROR_COUNT(pls); i++) {
 		if (*dev_count >= dev_limit)
 			break;
 		mirror = FF_LAYOUT_COMP(pls, i);
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index b77b328..0adc7d2 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -442,8 +442,9 @@
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode->i_version = fattr->change_attr;
-		else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
-			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR);
+		else
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_ATTR
+				| NFS_INO_REVAL_PAGECACHE);
 		if (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			inode->i_size = nfs_size_to_loff_t(fattr->size);
 		else
@@ -1244,9 +1245,11 @@
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		cur_size = i_size_read(inode);
 		new_isize = nfs_size_to_loff_t(fattr->size);
-		if (cur_size != new_isize && nfsi->nrequests == 0)
+		if (cur_size != new_isize)
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE;
 	}
+	if (nfsi->nrequests != 0)
+		invalid &= ~NFS_INO_REVAL_PAGECACHE;
 
 	/* Have any file permissions changed? */
 	if ((fattr->valid & NFS_ATTR_FATTR_MODE) && (inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO))
@@ -1684,13 +1687,12 @@
 			invalid |= NFS_INO_INVALID_ATTR
 				| NFS_INO_INVALID_DATA
 				| NFS_INO_INVALID_ACCESS
-				| NFS_INO_INVALID_ACL
-				| NFS_INO_REVAL_PAGECACHE;
+				| NFS_INO_INVALID_ACL;
 			if (S_ISDIR(inode->i_mode))
 				nfs_force_lookup_revalidate(inode);
 			inode->i_version = fattr->change_attr;
 		}
-	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
+	} else
 		nfsi->cache_validity |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
@@ -1717,7 +1719,6 @@
 			if ((nfsi->nrequests == 0) || new_isize > cur_isize) {
 				i_size_write(inode, new_isize);
 				invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
-				invalid &= ~NFS_INO_REVAL_PAGECACHE;
 			}
 			dprintk("NFS: isize change on server for file %s/%ld "
 					"(%Ld to %Ld)\n",
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7e3c460..9b372b8 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -296,6 +296,22 @@
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
 extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags);
+static inline struct nfs4_label *
+nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
+{
+	if (!dst || !src)
+		return NULL;
+
+	if (src->len > NFS4_MAXLABELLEN)
+		return NULL;
+
+	dst->lfs = src->lfs;
+	dst->pi = src->pi;
+	dst->len = src->len;
+	memcpy(dst->label, src->label, src->len);
+
+	return dst;
+}
 static inline void nfs4_label_free(struct nfs4_label *label)
 {
 	if (label) {
@@ -316,6 +332,11 @@
 static inline void nfs_zap_label_cache_locked(struct nfs_inode *nfsi)
 {
 }
+static inline struct nfs4_label *
+nfs4_label_copy(struct nfs4_label *dst, struct nfs4_label *src)
+{
+	return NULL;
+}
 #endif /* CONFIG_NFS_V4_SECURITY_LABEL */
 
 /* proc.c */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index f486b80..d731bbf 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -135,7 +135,7 @@
 	return err;
 }
 
-loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+static loff_t _nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
 {
 	struct inode *inode = file_inode(filep);
 	struct nfs42_seek_args args = {
@@ -171,6 +171,23 @@
 	return vfs_setpos(filep, res.sr_offset, inode->i_sb->s_maxbytes);
 }
 
+loff_t nfs42_proc_llseek(struct file *filep, loff_t offset, int whence)
+{
+	struct nfs_server *server = NFS_SERVER(file_inode(filep));
+	struct nfs4_exception exception = { };
+	int err;
+
+	do {
+		err = _nfs42_proc_llseek(filep, offset, whence);
+		if (err == -ENOTSUPP)
+			return -EOPNOTSUPP;
+		err = nfs4_handle_exception(server, err, &exception);
+	} while (exception.retry);
+
+	return err;
+}
+
+
 static void
 nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
 {
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 8bee934..3acb1eb 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -467,7 +467,10 @@
 
 static void renew_lease(const struct nfs_server *server, unsigned long timestamp)
 {
-	do_renew_lease(server->nfs_client, timestamp);
+	struct nfs_client *clp = server->nfs_client;
+
+	if (!nfs4_has_session(clp))
+		do_renew_lease(clp, timestamp);
 }
 
 struct nfs4_call_sync_data {
@@ -616,8 +619,7 @@
 		clp = session->clp;
 		do_renew_lease(clp, res->sr_timestamp);
 		/* Check sequence flags */
-		if (res->sr_status_flags != 0)
-			nfs4_schedule_lease_recovery(clp);
+		nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
 		nfs41_update_target_slotid(slot->table, slot, res);
 		break;
 	case 1:
@@ -910,6 +912,7 @@
 	struct nfs_open_confirmres c_res;
 	struct nfs4_string owner_name;
 	struct nfs4_string group_name;
+	struct nfs4_label *a_label;
 	struct nfs_fattr f_attr;
 	struct nfs4_label *f_label;
 	struct dentry *dir;
@@ -1013,6 +1016,10 @@
 	if (IS_ERR(p->f_label))
 		goto err_free_p;
 
+	p->a_label = nfs4_label_alloc(server, gfp_mask);
+	if (IS_ERR(p->a_label))
+		goto err_free_f;
+
 	alloc_seqid = server->nfs_client->cl_mvops->alloc_seqid;
 	p->o_arg.seqid = alloc_seqid(&sp->so_seqid, gfp_mask);
 	if (IS_ERR(p->o_arg.seqid))
@@ -1041,7 +1048,7 @@
 	p->o_arg.server = server;
 	p->o_arg.bitmask = nfs4_bitmask(server, label);
 	p->o_arg.open_bitmap = &nfs4_fattr_bitmap[0];
-	p->o_arg.label = label;
+	p->o_arg.label = nfs4_label_copy(p->a_label, label);
 	p->o_arg.claim = nfs4_map_atomic_open_claim(server, claim);
 	switch (p->o_arg.claim) {
 	case NFS4_OPEN_CLAIM_NULL:
@@ -1074,6 +1081,8 @@
 	return p;
 
 err_free_label:
+	nfs4_label_free(p->a_label);
+err_free_f:
 	nfs4_label_free(p->f_label);
 err_free_p:
 	kfree(p);
@@ -1093,6 +1102,7 @@
 		nfs4_put_open_state(p->state);
 	nfs4_put_state_owner(p->owner);
 
+	nfs4_label_free(p->a_label);
 	nfs4_label_free(p->f_label);
 
 	dput(p->dir);
@@ -1198,12 +1208,15 @@
 
 static void nfs_resync_open_stateid_locked(struct nfs4_state *state)
 {
+	if (!(state->n_wronly || state->n_rdonly || state->n_rdwr))
+		return;
 	if (state->n_wronly)
 		set_bit(NFS_O_WRONLY_STATE, &state->flags);
 	if (state->n_rdonly)
 		set_bit(NFS_O_RDONLY_STATE, &state->flags);
 	if (state->n_rdwr)
 		set_bit(NFS_O_RDWR_STATE, &state->flags);
+	set_bit(NFS_OPEN_STATE, &state->flags);
 }
 
 static void nfs_clear_open_stateid_locked(struct nfs4_state *state,
@@ -7571,13 +7584,8 @@
 		goto out;
 	}
 	ret = rpc_wait_for_completion_task(task);
-	if (!ret) {
-		struct nfs4_sequence_res *res = task->tk_msg.rpc_resp;
-
-		if (task->tk_status == 0)
-			nfs41_handle_sequence_flag_errors(clp, res->sr_status_flags);
+	if (!ret)
 		ret = task->tk_status;
-	}
 	rpc_put_task(task);
 out:
 	dprintk("<-- %s status=%d\n", __func__, ret);
@@ -7965,16 +7973,17 @@
 {
 	struct nfs4_layoutreturn *lrp = calldata;
 	struct pnfs_layout_hdr *lo = lrp->args.layout;
+	LIST_HEAD(freeme);
 
 	dprintk("--> %s\n", __func__);
 	spin_lock(&lo->plh_inode->i_lock);
 	if (lrp->res.lrs_present)
 		pnfs_set_layout_stateid(lo, &lrp->res.stateid, true);
+	pnfs_mark_matching_lsegs_invalid(lo, &freeme, &lrp->args.range);
 	pnfs_clear_layoutreturn_waitbit(lo);
-	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
-	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 	lo->plh_block_lgets--;
 	spin_unlock(&lo->plh_inode->i_lock);
+	pnfs_free_lseg_list(&freeme);
 	pnfs_put_layout_hdr(lrp->args.layout);
 	nfs_iput_and_deactive(lrp->inode);
 	kfree(calldata);
@@ -8588,7 +8597,6 @@
 	.minor_version = 0,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK,
 	.init_client = nfs40_init_client,
 	.shutdown_client = nfs40_shutdown_client,
@@ -8614,7 +8622,6 @@
 	.minor_version = 1,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1,
@@ -8637,7 +8644,6 @@
 	.minor_version = 2,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
-		| NFS_CAP_CHANGE_ATTR
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 605840d..f2e2ad8 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -2191,25 +2191,35 @@
 	}
 }
 
-static void nfs41_handle_state_revoked(struct nfs_client *clp)
+static void nfs41_handle_all_state_revoked(struct nfs_client *clp)
 {
 	nfs4_reset_all_state(clp);
 	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
 }
 
+static void nfs41_handle_some_state_revoked(struct nfs_client *clp)
+{
+	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce);
+	nfs4_schedule_state_manager(clp);
+
+	dprintk("%s: state revoked on server %s\n", __func__, clp->cl_hostname);
+}
+
 static void nfs41_handle_recallable_state_revoked(struct nfs_client *clp)
 {
-	/* This will need to handle layouts too */
-	nfs_expire_all_delegations(clp);
+	/* FIXME: For now, we destroy all layouts. */
+	pnfs_destroy_all_layouts(clp);
+	/* FIXME: For now, we test all delegations+open state+locks. */
+	nfs41_handle_some_state_revoked(clp);
 	dprintk("%s: Recallable state revoked on server %s!\n", __func__,
 			clp->cl_hostname);
 }
 
 static void nfs41_handle_backchannel_fault(struct nfs_client *clp)
 {
-	nfs_expire_all_delegations(clp);
-	if (test_and_set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) == 0)
-		nfs4_schedule_state_manager(clp);
+	set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+	nfs4_schedule_state_manager(clp);
+
 	dprintk("%s: server %s declared a backchannel fault\n", __func__,
 			clp->cl_hostname);
 }
@@ -2231,10 +2241,11 @@
 
 	if (flags & SEQ4_STATUS_RESTART_RECLAIM_NEEDED)
 		nfs41_handle_server_reboot(clp);
-	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED |
-			    SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
+	if (flags & (SEQ4_STATUS_EXPIRED_ALL_STATE_REVOKED))
+		nfs41_handle_all_state_revoked(clp);
+	if (flags & (SEQ4_STATUS_EXPIRED_SOME_STATE_REVOKED |
 			    SEQ4_STATUS_ADMIN_STATE_REVOKED))
-		nfs41_handle_state_revoked(clp);
+		nfs41_handle_some_state_revoked(clp);
 	if (flags & SEQ4_STATUS_LEASE_MOVED)
 		nfs4_schedule_lease_moved_recovery(clp);
 	if (flags & SEQ4_STATUS_RECALLABLE_STATE_REVOKED)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 1da68d3..4984bbe 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -1100,8 +1100,6 @@
 		mirror->pg_base = 0;
 		mirror->pg_recoalesce = 0;
 
-		desc->pg_moreio = 0;
-
 		while (!list_empty(&head)) {
 			struct nfs_page *req;
 
@@ -1109,8 +1107,11 @@
 			nfs_list_remove_request(req);
 			if (__nfs_pageio_add_request(desc, req))
 				continue;
-			if (desc->pg_error < 0)
+			if (desc->pg_error < 0) {
+				list_splice_tail(&head, &mirror->pg_list);
+				mirror->pg_recoalesce = 1;
 				return 0;
+			}
 			break;
 		}
 	} while (mirror->pg_recoalesce);
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index 0ba9a02..70bf706 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -352,7 +352,7 @@
 {
 	struct pnfs_layout_segment *s;
 
-	if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+	if (!test_and_clear_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
 		return false;
 
 	list_for_each_entry(s, &lo->plh_segs, pls_list)
@@ -362,6 +362,18 @@
 	return true;
 }
 
+static bool
+pnfs_prepare_layoutreturn(struct pnfs_layout_hdr *lo)
+{
+	if (test_and_set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		return false;
+	lo->plh_return_iomode = 0;
+	lo->plh_block_lgets++;
+	pnfs_get_layout_hdr(lo);
+	clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE, &lo->plh_flags);
+	return true;
+}
+
 static void pnfs_layoutreturn_before_put_lseg(struct pnfs_layout_segment *lseg,
 		struct pnfs_layout_hdr *lo, struct inode *inode)
 {
@@ -372,17 +384,16 @@
 	if (pnfs_layout_need_return(lo, lseg)) {
 		nfs4_stateid stateid;
 		enum pnfs_iomode iomode;
+		bool send;
 
 		stateid = lo->plh_stateid;
 		iomode = lo->plh_return_iomode;
-		/* decreased in pnfs_send_layoutreturn() */
-		lo->plh_block_lgets++;
-		lo->plh_return_iomode = 0;
+		send = pnfs_prepare_layoutreturn(lo);
 		spin_unlock(&inode->i_lock);
-		pnfs_get_layout_hdr(lo);
-
-		/* Send an async layoutreturn so we dont deadlock */
-		pnfs_send_layoutreturn(lo, stateid, iomode, false);
+		if (send) {
+			/* Send an async layoutreturn so we dont deadlock */
+			pnfs_send_layoutreturn(lo, stateid, iomode, false);
+		}
 	} else
 		spin_unlock(&inode->i_lock);
 }
@@ -411,6 +422,10 @@
 		pnfs_layoutreturn_before_put_lseg(lseg, lo, inode);
 
 	if (atomic_dec_and_lock(&lseg->pls_refcount, &inode->i_lock)) {
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags)) {
+			spin_unlock(&inode->i_lock);
+			return;
+		}
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
 		spin_unlock(&inode->i_lock);
@@ -451,6 +466,8 @@
 		test_bit(NFS_LSEG_VALID, &lseg->pls_flags));
 	if (atomic_dec_and_test(&lseg->pls_refcount)) {
 		struct pnfs_layout_hdr *lo = lseg->pls_layout;
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
+			return;
 		pnfs_get_layout_hdr(lo);
 		pnfs_layout_remove_lseg(lo, lseg);
 		pnfs_free_lseg_async(lseg);
@@ -924,6 +941,7 @@
 	clear_bit_unlock(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	smp_mb__after_atomic();
 	wake_up_bit(&lo->plh_flags, NFS_LAYOUT_RETURN);
+	rpc_wake_up(&NFS_SERVER(lo->plh_inode)->roc_rpcwaitq);
 }
 
 static int
@@ -978,6 +996,7 @@
 	LIST_HEAD(tmp_list);
 	nfs4_stateid stateid;
 	int status = 0, empty;
+	bool send;
 
 	dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino);
 
@@ -1007,17 +1026,18 @@
 	/* Don't send a LAYOUTRETURN if list was initially empty */
 	if (empty) {
 		spin_unlock(&ino->i_lock);
-		pnfs_put_layout_hdr(lo);
 		dprintk("NFS: %s no layout segments to return\n", __func__);
-		goto out;
+		goto out_put_layout_hdr;
 	}
 
 	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-	lo->plh_block_lgets++;
+	send = pnfs_prepare_layoutreturn(lo);
 	spin_unlock(&ino->i_lock);
 	pnfs_free_lseg_list(&tmp_list);
-
-	status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+	if (send)
+		status = pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, true);
+out_put_layout_hdr:
+	pnfs_put_layout_hdr(lo);
 out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
@@ -1097,13 +1117,9 @@
 out_noroc:
 	if (lo) {
 		stateid = lo->plh_stateid;
-		layoutreturn =
-			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					   &lo->plh_flags);
-		if (layoutreturn) {
-			lo->plh_block_lgets++;
-			pnfs_get_layout_hdr(lo);
-		}
+		if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags))
+			layoutreturn = pnfs_prepare_layoutreturn(lo);
 	}
 	spin_unlock(&ino->i_lock);
 	if (layoutreturn) {
@@ -1146,15 +1162,18 @@
 	struct pnfs_layout_segment *lseg;
 	nfs4_stateid stateid;
 	u32 current_seqid;
-	bool found = false, layoutreturn = false;
+	bool layoutreturn = false;
 
 	spin_lock(&ino->i_lock);
-	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list)
-		if (test_bit(NFS_LSEG_ROC, &lseg->pls_flags)) {
-			rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
-			found = true;
-			goto out;
-		}
+	list_for_each_entry(lseg, &nfsi->layout->plh_segs, pls_list) {
+		if (!test_bit(NFS_LSEG_ROC, &lseg->pls_flags))
+			continue;
+		if (test_bit(NFS_LSEG_VALID, &lseg->pls_flags))
+			continue;
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+		spin_unlock(&ino->i_lock);
+		return true;
+	}
 	lo = nfsi->layout;
 	current_seqid = be32_to_cpu(lo->plh_stateid.seqid);
 
@@ -1162,23 +1181,19 @@
 	 * a barrier, we choose the worst-case barrier.
 	 */
 	*barrier = current_seqid + atomic_read(&lo->plh_outstanding);
-out:
-	if (!found) {
-		stateid = lo->plh_stateid;
-		layoutreturn =
-			test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
-					   &lo->plh_flags);
-		if (layoutreturn) {
-			lo->plh_block_lgets++;
-			pnfs_get_layout_hdr(lo);
-		}
-	}
+	stateid = lo->plh_stateid;
+	if (test_and_clear_bit(NFS_LAYOUT_RETURN_BEFORE_CLOSE,
+					   &lo->plh_flags))
+		layoutreturn = pnfs_prepare_layoutreturn(lo);
+	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags))
+		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
+
 	spin_unlock(&ino->i_lock);
 	if (layoutreturn) {
-		rpc_sleep_on(&NFS_SERVER(ino)->roc_rpcwaitq, task, NULL);
 		pnfs_send_layoutreturn(lo, stateid, IOMODE_ANY, false);
+		return true;
 	}
-	return found;
+	return false;
 }
 
 /*
@@ -1695,7 +1710,6 @@
 	spin_lock(&inode->i_lock);
 	/* set failure bit so that pnfs path will be retried later */
 	pnfs_layout_set_fail_bit(lo, iomode);
-	set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	if (lo->plh_return_iomode == 0)
 		lo->plh_return_iomode = range.iomode;
 	else if (lo->plh_return_iomode != range.iomode)
@@ -2207,13 +2221,12 @@
 	if (ld->prepare_layoutcommit) {
 		status = ld->prepare_layoutcommit(&data->args);
 		if (status) {
+			put_rpccred(data->cred);
 			spin_lock(&inode->i_lock);
 			set_bit(NFS_INO_LAYOUTCOMMIT, &nfsi->flags);
 			if (end_pos > nfsi->layout->plh_lwb)
 				nfsi->layout->plh_lwb = end_pos;
-			spin_unlock(&inode->i_lock);
-			put_rpccred(data->cred);
-			goto clear_layoutcommitting;
+			goto out_unlock;
 		}
 	}
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 65869ca..75a35a1 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -1379,24 +1379,27 @@
 {
 	struct nfs_pgio_args *argp = &hdr->args;
 	struct nfs_pgio_res *resp = &hdr->res;
+	u64 size = argp->offset + resp->count;
 
 	if (!(fattr->valid & NFS_ATTR_FATTR_SIZE))
+		fattr->size = size;
+	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode)) {
+		fattr->valid &= ~NFS_ATTR_FATTR_SIZE;
 		return;
-	if (argp->offset + resp->count != fattr->size)
-		return;
-	if (nfs_size_to_loff_t(fattr->size) < i_size_read(hdr->inode))
+	}
+	if (size != fattr->size)
 		return;
 	/* Set attribute barrier */
 	nfs_fattr_set_barrier(fattr);
+	/* ...and update size */
+	fattr->valid |= NFS_ATTR_FATTR_SIZE;
 }
 
 void nfs_writeback_update_inode(struct nfs_pgio_header *hdr)
 {
-	struct nfs_fattr *fattr = hdr->res.fattr;
+	struct nfs_fattr *fattr = &hdr->fattr;
 	struct inode *inode = hdr->inode;
 
-	if (fattr == NULL)
-		return;
 	spin_lock(&inode->i_lock);
 	nfs_writeback_check_extend(hdr, fattr);
 	nfs_post_op_update_inode_force_wcc_locked(inode, fattr);
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 6904213..ebf90e4 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -212,6 +212,7 @@
 	BUG_ON(!ls->ls_file);
 
 	if (nfsd4_layout_setlease(ls)) {
+		fput(ls->ls_file);
 		put_nfs4_file(fp);
 		kmem_cache_free(nfs4_layout_stateid_cache, ls);
 		return NULL;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 61dfb33..9520271 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -4396,9 +4396,9 @@
 	queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ);
 }
 
-static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_ol_stateid *stp)
+static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp)
 {
-	if (!fh_match(&fhp->fh_handle, &stp->st_stid.sc_file->fi_fhandle))
+	if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle))
 		return nfserr_bad_stateid;
 	return nfs_ok;
 }
@@ -4601,9 +4601,6 @@
 {
 	__be32 status;
 
-	status = nfs4_check_fh(fhp, ols);
-	if (status)
-		return status;
 	status = nfsd4_check_openowner_confirmed(ols);
 	if (status)
 		return status;
@@ -4690,6 +4687,9 @@
 		status = nfserr_bad_stateid;
 		break;
 	}
+	if (status)
+		goto out;
+	status = nfs4_check_fh(fhp, s);
 
 done:
 	if (!status && filpp)
@@ -4798,7 +4798,7 @@
 	status = check_stateid_generation(stateid, &stp->st_stid.sc_stateid, nfsd4_has_session(cstate));
 	if (status)
 		return status;
-	return nfs4_check_fh(current_fh, stp);
+	return nfs4_check_fh(current_fh, &stp->st_stid);
 }
 
 /* 
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 5463385..75e0563 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2143,6 +2143,7 @@
 #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
 			      FATTR4_WORD0_RDATTR_ERROR)
 #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID
+#define WORD2_ABSENT_FS_ATTRS 0
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 static inline __be32
@@ -2171,7 +2172,7 @@
 { return 0; }
 #endif
 
-static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *rdattr_err)
+static __be32 fattr_handle_absent_fs(u32 *bmval0, u32 *bmval1, u32 *bmval2, u32 *rdattr_err)
 {
 	/* As per referral draft:  */
 	if (*bmval0 & ~WORD0_ABSENT_FS_ATTRS ||
@@ -2184,6 +2185,7 @@
 	}
 	*bmval0 &= WORD0_ABSENT_FS_ATTRS;
 	*bmval1 &= WORD1_ABSENT_FS_ATTRS;
+	*bmval2 &= WORD2_ABSENT_FS_ATTRS;
 	return 0;
 }
 
@@ -2246,8 +2248,7 @@
 	BUG_ON(bmval2 & ~nfsd_suppattrs2(minorversion));
 
 	if (exp->ex_fslocs.migrated) {
-		BUG_ON(bmval[2]);
-		status = fattr_handle_absent_fs(&bmval0, &bmval1, &rdattr_err);
+		status = fattr_handle_absent_fs(&bmval0, &bmval1, &bmval2, &rdattr_err);
 		if (status)
 			goto out;
 	}
@@ -2286,8 +2287,8 @@
 	}
 
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
-	if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) ||
-			bmval[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+	if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) ||
+	     bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
 		err = security_inode_getsecctx(d_inode(dentry),
 						&context, &contextlen);
 		contextsupport = (err == 0);
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 92e48c7..39ddcaf 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -412,16 +412,36 @@
 					 unsigned int flags)
 {
 	struct fsnotify_mark *lmark, *mark;
+	LIST_HEAD(to_free);
 
+	/*
+	 * We have to be really careful here. Anytime we drop mark_mutex, e.g.
+	 * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
+	 * to_free list so we have to use mark_mutex even when accessing that
+	 * list. And freeing mark requires us to drop mark_mutex. So we can
+	 * reliably free only the first mark in the list. That's why we first
+	 * move marks to free to to_free list in one go and then free marks in
+	 * to_free list one by one.
+	 */
 	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
-		if (mark->flags & flags) {
-			fsnotify_get_mark(mark);
-			fsnotify_destroy_mark_locked(mark, group);
-			fsnotify_put_mark(mark);
-		}
+		if (mark->flags & flags)
+			list_move(&mark->g_list, &to_free);
 	}
 	mutex_unlock(&group->mark_mutex);
+
+	while (1) {
+		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
+		if (list_empty(&to_free)) {
+			mutex_unlock(&group->mark_mutex);
+			break;
+		}
+		mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
+		fsnotify_get_mark(mark);
+		fsnotify_destroy_mark_locked(mark, group);
+		mutex_unlock(&group->mark_mutex);
+		fsnotify_put_mark(mark);
+	}
 }
 
 /*
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 1a35c61..0f5fd9d 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -685,7 +685,7 @@
 
 	if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
 		u64 s = i_size_read(inode);
-		sector_t sector = (p_cpos << (osb->s_clustersize_bits - 9)) +
+		sector_t sector = ((u64)p_cpos << (osb->s_clustersize_bits - 9)) +
 			(do_div(s, osb->s_clustersize) >> 9);
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev, sector,
@@ -910,7 +910,7 @@
 		BUG_ON(!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN));
 
 		ret = blkdev_issue_zeroout(osb->sb->s_bdev,
-				p_cpos << (osb->s_clustersize_bits - 9),
+				(u64)p_cpos << (osb->s_clustersize_bits - 9),
 				zero_len_head >> 9, GFP_NOFS, false);
 		if (ret < 0)
 			mlog_errno(ret);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 8b23aa2..23157e4 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -4025,9 +4025,13 @@
 	osb->dc_work_sequence = osb->dc_wake_sequence;
 
 	processed = osb->blocked_lock_count;
-	while (processed) {
-		BUG_ON(list_empty(&osb->blocked_lock_list));
-
+	/*
+	 * blocked lock processing in this loop might call iput which can
+	 * remove items off osb->blocked_lock_list. Downconvert up to
+	 * 'processed' number of locks, but stop short if we had some
+	 * removed in ocfs2_mark_lockres_freeing when downconverting.
+	 */
+	while (processed && !list_empty(&osb->blocked_lock_list)) {
 		lockres = list_entry(osb->blocked_lock_list.next,
 				     struct ocfs2_lock_res, l_blocked_list);
 		list_del_init(&lockres->l_blocked_list);
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 7e412ad..270221f 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -121,8 +121,9 @@
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (kinfo->si_code == BUS_MCEERR_AR ||
-		    kinfo->si_code == BUS_MCEERR_AO)
+		if (kinfo->si_signo == SIGBUS &&
+		    (kinfo->si_code == BUS_MCEERR_AR ||
+		     kinfo->si_code == BUS_MCEERR_AO))
 			err |= __put_user((short) kinfo->si_addr_lsb,
 					  &uinfo->ssi_addr_lsb);
 #endif
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index 20de88d..dd71403 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -159,11 +159,10 @@
 	struct xfs_buf	*bp)
 {
 	struct xfs_mount *mp = bp->b_target->bt_mount;
-	struct xfs_buf_log_item	*bip = bp->b_fspriv;
+	int		blksize = mp->m_attr_geo->blksize;
 	char		*ptr;
 	int		len;
 	xfs_daddr_t	bno;
-	int		blksize = mp->m_attr_geo->blksize;
 
 	/* no verification of non-crc buffers */
 	if (!xfs_sb_version_hascrc(&mp->m_sb))
@@ -175,16 +174,22 @@
 	ASSERT(len >= blksize);
 
 	while (len > 0) {
+		struct xfs_attr3_rmt_hdr *rmt = (struct xfs_attr3_rmt_hdr *)ptr;
+
 		if (!xfs_attr3_rmt_verify(mp, ptr, blksize, bno)) {
 			xfs_buf_ioerror(bp, -EFSCORRUPTED);
 			xfs_verifier_error(bp);
 			return;
 		}
-		if (bip) {
-			struct xfs_attr3_rmt_hdr *rmt;
 
-			rmt = (struct xfs_attr3_rmt_hdr *)ptr;
-			rmt->rm_lsn = cpu_to_be64(bip->bli_item.li_lsn);
+		/*
+		 * Ensure we aren't writing bogus LSNs to disk. See
+		 * xfs_attr3_rmt_hdr_set() for the explanation.
+		 */
+		if (rmt->rm_lsn != cpu_to_be64(NULLCOMMITLSN)) {
+			xfs_buf_ioerror(bp, -EFSCORRUPTED);
+			xfs_verifier_error(bp);
+			return;
 		}
 		xfs_update_cksum(ptr, blksize, XFS_ATTR3_RMT_CRC_OFF);
 
@@ -221,6 +226,18 @@
 	rmt->rm_owner = cpu_to_be64(ino);
 	rmt->rm_blkno = cpu_to_be64(bno);
 
+	/*
+	 * Remote attribute blocks are written synchronously, so we don't
+	 * have an LSN that we can stamp in them that makes any sense to log
+	 * recovery. To ensure that log recovery handles overwrites of these
+	 * blocks sanely (i.e. once they've been freed and reallocated as some
+	 * other type of metadata) we need to ensure that the LSN has a value
+	 * that tells log recovery to ignore the LSN and overwrite the buffer
+	 * with whatever is in it's log. To do this, we use the magic
+	 * NULLCOMMITLSN to indicate that the LSN is invalid.
+	 */
+	rmt->rm_lsn = cpu_to_be64(NULLCOMMITLSN);
+
 	return sizeof(struct xfs_attr3_rmt_hdr);
 }
 
@@ -434,14 +451,21 @@
 
 		/*
 		 * Allocate a single extent, up to the size of the value.
+		 *
+		 * Note that we have to consider this a data allocation as we
+		 * write the remote attribute without logging the contents.
+		 * Hence we must ensure that we aren't using blocks that are on
+		 * the busy list so that we don't overwrite blocks which have
+		 * recently been freed but their transactions are not yet
+		 * committed to disk. If we overwrite the contents of a busy
+		 * extent and then crash then the block may not contain the
+		 * correct metadata after log recovery occurs.
 		 */
 		xfs_bmap_init(args->flist, args->firstblock);
 		nmap = 1;
 		error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)lblkno,
-				  blkcnt,
-				  XFS_BMAPI_ATTRFORK | XFS_BMAPI_METADATA,
-				  args->firstblock, args->total, &map, &nmap,
-				  args->flist);
+				  blkcnt, XFS_BMAPI_ATTRFORK, args->firstblock,
+				  args->total, &map, &nmap, args->flist);
 		if (!error) {
 			error = xfs_bmap_finish(&args->trans, args->flist,
 						&committed);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index f0e8249..db4acc1 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1514,18 +1514,27 @@
 	struct vm_area_struct	*vma,
 	struct vm_fault		*vmf)
 {
-	struct xfs_inode	*ip = XFS_I(file_inode(vma->vm_file));
+	struct inode		*inode = file_inode(vma->vm_file);
 	int			ret;
 
-	trace_xfs_filemap_fault(ip);
+	trace_xfs_filemap_fault(XFS_I(inode));
 
 	/* DAX can shortcut the normal fault path on write faults! */
-	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(VFS_I(ip)))
+	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
 		return xfs_filemap_page_mkwrite(vma, vmf);
 
-	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
-	ret = filemap_fault(vma, vmf);
-	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
+	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
+	if (IS_DAX(inode)) {
+		/*
+		 * we do not want to trigger unwritten extent conversion on read
+		 * faults - that is unnecessary overhead and would also require
+		 * changes to xfs_get_blocks_direct() to map unwritten extent
+		 * ioend for conversion on read-only mappings.
+		 */
+		ret = __dax_fault(vma, vmf, xfs_get_blocks_direct, NULL);
+	} else
+		ret = filemap_fault(vma, vmf);
+	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	return ret;
 }
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 01dd228..480ebba 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -1886,9 +1886,14 @@
 		uuid = &((struct xfs_dir3_blk_hdr *)blk)->uuid;
 		break;
 	case XFS_ATTR3_RMT_MAGIC:
-		lsn = be64_to_cpu(((struct xfs_attr3_rmt_hdr *)blk)->rm_lsn);
-		uuid = &((struct xfs_attr3_rmt_hdr *)blk)->rm_uuid;
-		break;
+		/*
+		 * Remote attr blocks are written synchronously, rather than
+		 * being logged. That means they do not contain a valid LSN
+		 * (i.e. transactionally ordered) in them, and hence any time we
+		 * see a buffer to replay over the top of a remote attribute
+		 * block we should simply do so.
+		 */
+		goto recover_immediately;
 	case XFS_SB_MAGIC:
 		lsn = be64_to_cpu(((struct xfs_dsb *)blk)->sb_lsn);
 		uuid = &((struct xfs_dsb *)blk)->sb_uuid;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index 48db6a5..5aa5197 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -691,7 +691,7 @@
 	struct timer_list disable_timer;		/* delayed disable timer */
 
 	/* vblank counter, protected by dev->vblank_time_lock for writes */
-	unsigned long count;
+	u32 count;
 	/* vblank timestamps, protected by dev->vblank_time_lock for writes */
 	struct timeval time[DRM_VBLANKTIME_RBSIZE];
 
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index c8fc187..918aa68 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -168,6 +168,7 @@
  * @get_modes: get mode list for this connector
  * @mode_valid: is this mode valid on the given connector? (optional)
  * @best_encoder: return the preferred encoder for this connector
+ * @atomic_best_encoder: atomic version of @best_encoder
  *
  * The helper operations are called by the mid-layer CRTC helper.
  */
@@ -176,6 +177,8 @@
 	enum drm_mode_status (*mode_valid)(struct drm_connector *connector,
 					   struct drm_display_mode *mode);
 	struct drm_encoder *(*best_encoder)(struct drm_connector *connector);
+	struct drm_encoder *(*atomic_best_encoder)(struct drm_connector *connector,
+						   struct drm_connector_state *connector_state);
 };
 
 extern void drm_helper_disable_unused_functions(struct drm_device *dev);
diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h
index 29ad97c..bde1e56 100644
--- a/include/linux/cpufreq.h
+++ b/include/linux/cpufreq.h
@@ -62,6 +62,7 @@
 	/* CPUs sharing clock, require sw coordination */
 	cpumask_var_t		cpus;	/* Online CPUs only */
 	cpumask_var_t		related_cpus; /* Online + Offline CPUs */
+	cpumask_var_t		real_cpus; /* Related and present */
 
 	unsigned int		shared_type; /* ACPI: ANY or ALL affected CPUs
 						should set cpufreq */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cc008c3..84b783f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -55,7 +55,8 @@
 
 extern void __init inode_init(void);
 extern void __init inode_init_early(void);
-extern void __init files_init(unsigned long);
+extern void __init files_init(void);
+extern void __init files_maxfiles_init(void);
 
 extern struct files_stat_struct files_stat;
 extern unsigned long get_max_files(void);
@@ -2245,7 +2246,7 @@
 
 /* fs/dcache.c */
 extern void __init vfs_caches_init_early(void);
-extern void __init vfs_caches_init(unsigned long);
+extern void __init vfs_caches_init(void);
 
 extern struct kmem_cache *names_cachep;
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index f91b5ad..874b772 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -292,9 +292,12 @@
 	struct nfs_inode *nfsi = NFS_I(inode);
 
 	spin_lock(&inode->i_lock);
-	nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS;
+	nfsi->cache_validity |= NFS_INO_INVALID_ATTR |
+				NFS_INO_REVAL_PAGECACHE |
+				NFS_INO_INVALID_ACCESS |
+				NFS_INO_INVALID_ACL;
 	if (S_ISDIR(inode->i_mode))
-		nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA;
+		nfsi->cache_validity |= NFS_INO_INVALID_DATA;
 	spin_unlock(&inode->i_lock);
 }
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a2ea149..20bc8e5 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -220,7 +220,7 @@
 #define NFS_CAP_SYMLINKS	(1U << 2)
 #define NFS_CAP_ACLS		(1U << 3)
 #define NFS_CAP_ATOMIC_OPEN	(1U << 4)
-#define NFS_CAP_CHANGE_ATTR	(1U << 5)
+/* #define NFS_CAP_CHANGE_ATTR	(1U << 5) */
 #define NFS_CAP_FILEID		(1U << 6)
 #define NFS_CAP_MODE		(1U << 7)
 #define NFS_CAP_NLINK		(1U << 8)
diff --git a/include/linux/of_device.h b/include/linux/of_device.h
index 4c50854..cc7dd687 100644
--- a/include/linux/of_device.h
+++ b/include/linux/of_device.h
@@ -59,7 +59,7 @@
 #else /* CONFIG_OF */
 
 static inline int of_driver_match_device(struct device *dev,
-					 struct device_driver *drv)
+					 const struct device_driver *drv)
 {
 	return 0;
 }
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index f34e040..41c9384 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -631,15 +631,19 @@
 	 1 << PG_private | 1 << PG_private_2 | \
 	 1 << PG_writeback | 1 << PG_reserved | \
 	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
-	 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON | \
+	 1 << PG_unevictable | __PG_MLOCKED | \
 	 __PG_COMPOUND_LOCK)
 
 /*
  * Flags checked when a page is prepped for return by the page allocator.
- * Pages being prepped should not have any flags set.  It they are set,
+ * Pages being prepped should not have these flags set.  It they are set,
  * there has been a kernel bug or struct page corruption.
+ *
+ * __PG_HWPOISON is exceptional because it needs to be kept beyond page's
+ * alloc-free cycle to prevent from reusing the page.
  */
-#define PAGE_FLAGS_CHECK_AT_PREP	((1 << NR_PAGEFLAGS) - 1)
+#define PAGE_FLAGS_CHECK_AT_PREP	\
+	(((1 << NR_PAGEFLAGS) - 1) & ~__PG_HWPOISON)
 
 #define PAGE_FLAGS_PRIVATE				\
 	(1 << PG_private | 1 << PG_private_2)
diff --git a/include/linux/platform_data/macb.h b/include/linux/platform_data/macb.h
index 044a124..21b15f6 100644
--- a/include/linux/platform_data/macb.h
+++ b/include/linux/platform_data/macb.h
@@ -8,11 +8,19 @@
 #ifndef __MACB_PDATA_H__
 #define __MACB_PDATA_H__
 
+/**
+ * struct macb_platform_data - platform data for MACB Ethernet
+ * @phy_mask:		phy mask passed when register the MDIO bus
+ *			within the driver
+ * @phy_irq_pin:	PHY IRQ
+ * @is_rmii:		using RMII interface?
+ * @rev_eth_addr:	reverse Ethernet address byte order
+ */
 struct macb_platform_data {
 	u32		phy_mask;
-	int		phy_irq_pin;	/* PHY IRQ */
-	u8		is_rmii;	/* using RMII interface? */
-	u8		rev_eth_addr;	/* reverse Ethernet address byte order */
+	int		phy_irq_pin;
+	u8		is_rmii;
+	u8		rev_eth_addr;
 };
 
 #endif /* __MACB_PDATA_H__ */
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 3ee4c92..931738b 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -99,7 +99,6 @@
 
 int tcf_hash_search(struct tc_action *a, u32 index);
 void tcf_hash_destroy(struct tc_action *a);
-int tcf_hash_release(struct tc_action *a, int bind);
 u32 tcf_hash_new_index(struct tcf_hashinfo *hinfo);
 int tcf_hash_check(u32 index, struct tc_action *a, int bind);
 int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
@@ -107,6 +106,13 @@
 void tcf_hash_cleanup(struct tc_action *a, struct nlattr *est);
 void tcf_hash_insert(struct tc_action *a);
 
+int __tcf_hash_release(struct tc_action *a, bool bind, bool strict);
+
+static inline int tcf_hash_release(struct tc_action *a, bool bind)
+{
+	return __tcf_hash_release(a, bind, false);
+}
+
 int tcf_register_action(struct tc_action_ops *a, unsigned int mask);
 int tcf_unregister_action(struct tc_action_ops *a);
 int tcf_action_destroy(struct list_head *actions, int bind);
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index e1300b3..53eead2 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -21,13 +21,11 @@
  * @INET_FRAG_FIRST_IN: first fragment has arrived
  * @INET_FRAG_LAST_IN: final fragment has arrived
  * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction
- * @INET_FRAG_EVICTED: frag queue is being evicted
  */
 enum {
 	INET_FRAG_FIRST_IN	= BIT(0),
 	INET_FRAG_LAST_IN	= BIT(1),
 	INET_FRAG_COMPLETE	= BIT(2),
-	INET_FRAG_EVICTED	= BIT(3)
 };
 
 /**
@@ -45,6 +43,7 @@
  * @flags: fragment queue flags
  * @max_size: maximum received fragment size
  * @net: namespace that this frag belongs to
+ * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
  */
 struct inet_frag_queue {
 	spinlock_t		lock;
@@ -59,6 +58,7 @@
 	__u8			flags;
 	u16			max_size;
 	struct netns_frags	*net;
+	struct hlist_node	list_evictor;
 };
 
 #define INETFRAGS_HASHSZ	1024
@@ -125,6 +125,11 @@
 		inet_frag_destroy(q, f);
 }
 
+static inline bool inet_frag_evicting(struct inet_frag_queue *q)
+{
+	return !hlist_unhashed(&q->list_evictor);
+}
+
 /* Memory Tracking Functions. */
 
 /* The default percpu_counter batch size is not big enough to scale to
@@ -139,14 +144,14 @@
 	return percpu_counter_read(&nf->mem);
 }
 
-static inline void sub_frag_mem_limit(struct inet_frag_queue *q, int i)
+static inline void sub_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&q->net->mem, -i, frag_percpu_counter_batch);
+	__percpu_counter_add(&nf->mem, -i, frag_percpu_counter_batch);
 }
 
-static inline void add_frag_mem_limit(struct inet_frag_queue *q, int i)
+static inline void add_frag_mem_limit(struct netns_frags *nf, int i)
 {
-	__percpu_counter_add(&q->net->mem, i, frag_percpu_counter_batch);
+	__percpu_counter_add(&nf->mem, i, frag_percpu_counter_batch);
 }
 
 static inline void init_frag_mem_limit(struct netns_frags *nf)
diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
index 49c142b..5fa643b 100644
--- a/include/net/ip_fib.h
+++ b/include/net/ip_fib.h
@@ -183,7 +183,6 @@
 struct fib_table {
 	struct hlist_node	tb_hlist;
 	u32			tb_id;
-	int			tb_default;
 	int			tb_num_default;
 	struct rcu_head		rcu;
 	unsigned long 		*tb_data;
@@ -290,7 +289,7 @@
 int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
 			u8 tos, int oif, struct net_device *dev,
 			struct in_device *idev, u32 *itag);
-void fib_select_default(struct fib_result *res);
+void fib_select_default(const struct flowi4 *flp, struct fib_result *res);
 #ifdef CONFIG_IP_ROUTE_CLASSID
 static inline int fib_num_tclassid_users(struct net *net)
 {
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 095433b..37cd391 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -291,7 +291,7 @@
 extern unsigned int nf_conntrack_hash_rnd;
 void init_nf_conntrack_hash_rnd(void);
 
-void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+struct nf_conn *nf_ct_tmpl_alloc(struct net *net, u16 zone, gfp_t flags);
 
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index 29d6a94..723b61c 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -68,7 +68,6 @@
 	spinlock_t		lock;
 	struct hlist_nulls_head unconfirmed;
 	struct hlist_nulls_head dying;
-	struct hlist_nulls_head tmpl;
 };
 
 struct netns_ct {
diff --git a/include/net/sock.h b/include/net/sock.h
index 05a8c1a..f21f070 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -902,7 +902,7 @@
 void sk_set_memalloc(struct sock *sk);
 void sk_clear_memalloc(struct sock *sk);
 
-int sk_wait_data(struct sock *sk, long *timeo);
+int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb);
 
 struct request_sock_ops;
 struct timewait_sock_ops;
diff --git a/include/target/iscsi/iscsi_target_core.h b/include/target/iscsi/iscsi_target_core.h
index 34117b8..0aedbb2 100644
--- a/include/target/iscsi/iscsi_target_core.h
+++ b/include/target/iscsi/iscsi_target_core.h
@@ -595,6 +595,7 @@
 	int			bitmap_id;
 	int			rx_thread_active;
 	struct task_struct	*rx_thread;
+	struct completion	rx_login_comp;
 	int			tx_thread_active;
 	struct task_struct	*tx_thread;
 	/* list_head for session connection list */
diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h
index d708a53..fbdd118 100644
--- a/include/uapi/drm/amdgpu_drm.h
+++ b/include/uapi/drm/amdgpu_drm.h
@@ -32,7 +32,7 @@
 #ifndef __AMDGPU_DRM_H__
 #define __AMDGPU_DRM_H__
 
-#include <drm/drm.h>
+#include "drm.h"
 
 #define DRM_AMDGPU_GEM_CREATE		0x00
 #define DRM_AMDGPU_GEM_MMAP		0x01
diff --git a/include/uapi/drm/radeon_drm.h b/include/uapi/drm/radeon_drm.h
index 1ef7666..01aa2a8 100644
--- a/include/uapi/drm/radeon_drm.h
+++ b/include/uapi/drm/radeon_drm.h
@@ -33,7 +33,7 @@
 #ifndef __RADEON_DRM_H__
 #define __RADEON_DRM_H__
 
-#include <drm/drm.h>
+#include "drm.h"
 
 /* WARNING: If you change any of these defines, make sure to change the
  * defines in the X server file (radeon_sarea.h)
diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h
index efe3443..413417f 100644
--- a/include/uapi/linux/pci_regs.h
+++ b/include/uapi/linux/pci_regs.h
@@ -319,6 +319,7 @@
 #define PCI_MSIX_PBA		8	/* Pending Bit Array offset */
 #define  PCI_MSIX_PBA_BIR	0x00000007 /* BAR index */
 #define  PCI_MSIX_PBA_OFFSET	0xfffffff8 /* Offset into specified BAR */
+#define PCI_MSIX_FLAGS_BIRMASK	PCI_MSIX_PBA_BIR /* deprecated */
 #define PCI_CAP_MSIX_SIZEOF	12	/* size of MSIX registers */
 
 /* MSI-X Table entry format */
diff --git a/include/uapi/sound/asoc.h b/include/uapi/sound/asoc.h
index 1221520..785c5ca 100644
--- a/include/uapi/sound/asoc.h
+++ b/include/uapi/sound/asoc.h
@@ -110,7 +110,7 @@
 
 /*
  * Block Header.
- * This header preceeds all object and object arrays below.
+ * This header precedes all object and object arrays below.
  */
 struct snd_soc_tplg_hdr {
 	__le32 magic;		/* magic number */
@@ -222,7 +222,7 @@
 /*
  * Manifest. List totals for each payload type. Not used in parsing, but will
  * be passed to the component driver before any other objects in order for any
- * global componnent resource allocations.
+ * global component resource allocations.
  *
  * File block representation for manifest :-
  * +-----------------------------------+----+
diff --git a/init/main.c b/init/main.c
index c5d5626..5650655 100644
--- a/init/main.c
+++ b/init/main.c
@@ -656,7 +656,7 @@
 	key_init();
 	security_init();
 	dbg_late_init();
-	vfs_caches_init(totalram_pages);
+	vfs_caches_init();
 	signals_init();
 	/* rootfs populating might need page-writeback */
 	page_writeback_init();
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index a24ba9f..161a180 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -142,7 +142,6 @@
 		if (!leaf)
 			return -ENOMEM;
 		INIT_LIST_HEAD(&leaf->msg_list);
-		info->qsize += sizeof(*leaf);
 	}
 	leaf->priority = msg->m_type;
 	rb_link_node(&leaf->rb_node, parent, p);
@@ -187,7 +186,6 @@
 			     "lazy leaf delete!\n");
 		rb_erase(&leaf->rb_node, &info->msg_tree);
 		if (info->node_cache) {
-			info->qsize -= sizeof(*leaf);
 			kfree(leaf);
 		} else {
 			info->node_cache = leaf;
@@ -200,7 +198,6 @@
 		if (list_empty(&leaf->msg_list)) {
 			rb_erase(&leaf->rb_node, &info->msg_tree);
 			if (info->node_cache) {
-				info->qsize -= sizeof(*leaf);
 				kfree(leaf);
 			} else {
 				info->node_cache = leaf;
@@ -1034,7 +1031,6 @@
 		/* Save our speculative allocation into the cache */
 		INIT_LIST_HEAD(&new_leaf->msg_list);
 		info->node_cache = new_leaf;
-		info->qsize += sizeof(*new_leaf);
 		new_leaf = NULL;
 	} else {
 		kfree(new_leaf);
@@ -1142,7 +1138,6 @@
 		/* Save our speculative allocation into the cache */
 		INIT_LIST_HEAD(&new_leaf->msg_list);
 		info->node_cache = new_leaf;
-		info->qsize += sizeof(*new_leaf);
 	} else {
 		kfree(new_leaf);
 	}
diff --git a/ipc/shm.c b/ipc/shm.c
index 06e5cf2..4aef24d 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -545,7 +545,7 @@
 		if  ((shmflg & SHM_NORESERVE) &&
 				sysctl_overcommit_memory != OVERCOMMIT_NEVER)
 			acctflag = VM_NORESERVE;
-		file = shmem_file_setup(name, size, acctflag);
+		file = shmem_kernel_file_setup(name, size, acctflag);
 	}
 	error = PTR_ERR(file);
 	if (IS_ERR(file))
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 10e489c..fdea0be 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -97,6 +97,7 @@
 {
 	return test_bit(KTHREAD_SHOULD_PARK, &to_kthread(current)->flags);
 }
+EXPORT_SYMBOL_GPL(kthread_should_park);
 
 /**
  * kthread_freezable_should_stop - should this freezable kthread return now?
@@ -171,6 +172,7 @@
 {
 	__kthread_parkme(to_kthread(current));
 }
+EXPORT_SYMBOL_GPL(kthread_parkme);
 
 static int kthread(void *_create)
 {
@@ -411,6 +413,7 @@
 	if (kthread)
 		__kthread_unpark(k, kthread);
 }
+EXPORT_SYMBOL_GPL(kthread_unpark);
 
 /**
  * kthread_park - park a thread created by kthread_create().
@@ -441,6 +444,7 @@
 	}
 	return ret;
 }
+EXPORT_SYMBOL_GPL(kthread_park);
 
 /**
  * kthread_stop - stop a thread created by kthread_create().
diff --git a/kernel/module.c b/kernel/module.c
index 4d2b82e..b86b7bf 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -602,13 +602,16 @@
 }
 EXPORT_SYMBOL_GPL(find_symbol);
 
-/* Search for module by name: must hold module_mutex. */
+/*
+ * Search for module by name: must hold module_mutex (or preempt disabled
+ * for read-only access).
+ */
 static struct module *find_module_all(const char *name, size_t len,
 				      bool even_unformed)
 {
 	struct module *mod;
 
-	module_assert_mutex();
+	module_assert_mutex_or_preempt();
 
 	list_for_each_entry(mod, &modules, list) {
 		if (!even_unformed && mod->state == MODULE_STATE_UNFORMED)
@@ -621,6 +624,7 @@
 
 struct module *find_module(const char *name)
 {
+	module_assert_mutex();
 	return find_module_all(name, strlen(name), false);
 }
 EXPORT_SYMBOL_GPL(find_module);
diff --git a/kernel/signal.c b/kernel/signal.c
index 836df8d..0f6bbbe 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -2748,12 +2748,15 @@
 		 * Other callers might not initialize the si_lsb field,
 		 * so check explicitly for the right codes here.
 		 */
-		if (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO)
+		if (from->si_signo == SIGBUS &&
+		    (from->si_code == BUS_MCEERR_AR || from->si_code == BUS_MCEERR_AO))
 			err |= __put_user(from->si_addr_lsb, &to->si_addr_lsb);
 #endif
 #ifdef SEGV_BNDERR
-		err |= __put_user(from->si_lower, &to->si_lower);
-		err |= __put_user(from->si_upper, &to->si_upper);
+		if (from->si_signo == SIGSEGV && from->si_code == SEGV_BNDERR) {
+			err |= __put_user(from->si_lower, &to->si_lower);
+			err |= __put_user(from->si_upper, &to->si_upper);
+		}
 #endif
 		break;
 	case __SI_CHLD:
@@ -3017,7 +3020,7 @@
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 	int ret = copy_siginfo_from_user32(&info, uinfo);
 	if (unlikely(ret))
 		return ret;
@@ -3061,7 +3064,7 @@
 			int, sig,
 			struct compat_siginfo __user *, uinfo)
 {
-	siginfo_t info;
+	siginfo_t info = {};
 
 	if (copy_siginfo_from_user32(&info, uinfo))
 		return -EFAULT;
diff --git a/lib/iommu-common.c b/lib/iommu-common.c
index df30632..ff19f66 100644
--- a/lib/iommu-common.c
+++ b/lib/iommu-common.c
@@ -119,7 +119,7 @@
 	unsigned long align_mask = 0;
 
 	if (align_order > 0)
-		align_mask = 0xffffffffffffffffl >> (64 - align_order);
+		align_mask = ~0ul >> (BITS_PER_LONG - align_order);
 
 	/* Sanity check */
 	if (unlikely(npages == 0)) {
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c107094..097c7a4 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1676,12 +1676,7 @@
 		/* after clearing PageTail the gup refcount can be released */
 		smp_mb__after_atomic();
 
-		/*
-		 * retain hwpoison flag of the poisoned tail page:
-		 *   fix for the unsuitable process killed on Guest Machine(KVM)
-		 *   by the memory-failure.
-		 */
-		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
+		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 		page_tail->flags |= (page->flags &
 				     ((1L << PG_referenced) |
 				      (1L << PG_swapbacked) |
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index c53543d..ea5a936 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -909,6 +909,18 @@
 	 * directly for tail pages.
 	 */
 	if (PageTransHuge(head)) {
+		/*
+		 * Non anonymous thp exists only in allocation/free time. We
+		 * can't handle such a case correctly, so let's give it up.
+		 * This should be better than triggering BUG_ON when kernel
+		 * tries to touch the "partially handled" page.
+		 */
+		if (!PageAnon(head)) {
+			pr_err("MCE: %#lx: non anonymous thp\n",
+				page_to_pfn(page));
+			return 0;
+		}
+
 		if (get_page_unless_zero(head)) {
 			if (PageTail(page))
 				get_page(page);
@@ -1134,15 +1146,6 @@
 	}
 
 	if (!PageHuge(p) && PageTransHuge(hpage)) {
-		if (!PageAnon(hpage)) {
-			pr_err("MCE: %#lx: non anonymous thp\n", pfn);
-			if (TestClearPageHWPoison(p))
-				atomic_long_sub(nr_pages, &num_poisoned_pages);
-			put_page(p);
-			if (p != hpage)
-				put_page(hpage);
-			return -EBUSY;
-		}
 		if (unlikely(split_huge_page(hpage))) {
 			pr_err("MCE: %#lx: thp split failed\n", pfn);
 			if (TestClearPageHWPoison(p))
@@ -1209,9 +1212,9 @@
 	if (!PageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: just unpoisoned\n", pfn);
 		atomic_long_sub(nr_pages, &num_poisoned_pages);
+		unlock_page(hpage);
 		put_page(hpage);
-		res = 0;
-		goto out;
+		return 0;
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
@@ -1656,6 +1659,8 @@
 		inc_zone_page_state(page, NR_ISOLATED_ANON +
 					page_is_file_cache(page));
 		list_add(&page->lru, &pagelist);
+		if (!TestSetPageHWPoison(page))
+			atomic_long_inc(&num_poisoned_pages);
 		ret = migrate_pages(&pagelist, new_page, NULL, MPOL_MF_MOVE_ALL,
 					MIGRATE_SYNC, MR_MEMORY_FAILURE);
 		if (ret) {
@@ -1670,9 +1675,8 @@
 				pfn, ret, page->flags);
 			if (ret > 0)
 				ret = -EIO;
-		} else {
-			SetPageHWPoison(page);
-			atomic_long_inc(&num_poisoned_pages);
+			if (TestClearPageHWPoison(page))
+				atomic_long_dec(&num_poisoned_pages);
 		}
 	} else {
 		pr_info("soft offline: %#lx: isolation failed: %d, page count %d, type %lx\n",
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 26fbba7..003dbe4 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -446,7 +446,7 @@
 	int nr_pages = PAGES_PER_SECTION;
 	int nid = pgdat->node_id;
 	int zone_type;
-	unsigned long flags;
+	unsigned long flags, pfn;
 	int ret;
 
 	zone_type = zone - pgdat->node_zones;
@@ -461,6 +461,14 @@
 	pgdat_resize_unlock(zone->zone_pgdat, &flags);
 	memmap_init_zone(nr_pages, nid, zone_type,
 			 phys_start_pfn, MEMMAP_HOTPLUG);
+
+	/* online_page_range is called later and expects pages reserved */
+	for (pfn = phys_start_pfn; pfn < phys_start_pfn + nr_pages; pfn++) {
+		if (!pfn_valid(pfn))
+			continue;
+
+		SetPageReserved(pfn_to_page(pfn));
+	}
 	return 0;
 }
 
diff --git a/mm/migrate.c b/mm/migrate.c
index ee401e4..eb42671 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -880,7 +880,8 @@
 	/* Establish migration ptes or remove ptes */
 	if (page_mapped(page)) {
 		try_to_unmap(page,
-			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+			TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS|
+			TTU_IGNORE_HWPOISON);
 		page_was_mapped = 1;
 	}
 
@@ -950,7 +951,10 @@
 		list_del(&page->lru);
 		dec_zone_page_state(page, NR_ISOLATED_ANON +
 				page_is_file_cache(page));
-		if (reason != MR_MEMORY_FAILURE)
+		/* Soft-offlined page shouldn't go through lru cache list */
+		if (reason == MR_MEMORY_FAILURE)
+			put_page(page);
+		else
 			putback_lru_page(page);
 	}
 
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 22cddd3..5cccc12 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -2063,10 +2063,10 @@
  */
 void __init page_writeback_init(void)
 {
+	BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
+
 	writeback_set_ratelimit();
 	register_cpu_notifier(&ratelimit_nb);
-
-	BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
 }
 
 /**
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ef19f22..beda417 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -18,7 +18,6 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/interrupt.h>
-#include <linux/rwsem.h>
 #include <linux/pagemap.h>
 #include <linux/jiffies.h>
 #include <linux/bootmem.h>
@@ -981,21 +980,21 @@
 
 #if defined(CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID) || \
 	defined(CONFIG_HAVE_MEMBLOCK_NODE_MAP)
-/* Only safe to use early in boot when initialisation is single-threaded */
+
 static struct mminit_pfnnid_cache early_pfnnid_cache __meminitdata;
 
 int __meminit early_pfn_to_nid(unsigned long pfn)
 {
+	static DEFINE_SPINLOCK(early_pfn_lock);
 	int nid;
 
-	/* The system will behave unpredictably otherwise */
-	BUG_ON(system_state != SYSTEM_BOOTING);
-
+	spin_lock(&early_pfn_lock);
 	nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
-	if (nid >= 0)
-		return nid;
-	/* just returns 0 */
-	return 0;
+	if (nid < 0)
+		nid = 0;
+	spin_unlock(&early_pfn_lock);
+
+	return nid;
 }
 #endif
 
@@ -1060,7 +1059,15 @@
 		__free_pages_boot_core(page, pfn, 0);
 }
 
-static __initdata DECLARE_RWSEM(pgdat_init_rwsem);
+/* Completion tracking for deferred_init_memmap() threads */
+static atomic_t pgdat_init_n_undone __initdata;
+static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
+
+static inline void __init pgdat_init_report_one_done(void)
+{
+	if (atomic_dec_and_test(&pgdat_init_n_undone))
+		complete(&pgdat_init_all_done_comp);
+}
 
 /* Initialise remaining memory on a node */
 static int __init deferred_init_memmap(void *data)
@@ -1077,7 +1084,7 @@
 	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
 	if (first_init_pfn == ULONG_MAX) {
-		up_read(&pgdat_init_rwsem);
+		pgdat_init_report_one_done();
 		return 0;
 	}
 
@@ -1177,7 +1184,8 @@
 
 	pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
 					jiffies_to_msecs(jiffies - start));
-	up_read(&pgdat_init_rwsem);
+
+	pgdat_init_report_one_done();
 	return 0;
 }
 
@@ -1185,14 +1193,17 @@
 {
 	int nid;
 
+	/* There will be num_node_state(N_MEMORY) threads */
+	atomic_set(&pgdat_init_n_undone, num_node_state(N_MEMORY));
 	for_each_node_state(nid, N_MEMORY) {
-		down_read(&pgdat_init_rwsem);
 		kthread_run(deferred_init_memmap, NODE_DATA(nid), "pgdatinit%d", nid);
 	}
 
 	/* Block until all are initialised */
-	down_write(&pgdat_init_rwsem);
-	up_write(&pgdat_init_rwsem);
+	wait_for_completion(&pgdat_init_all_done_comp);
+
+	/* Reinit limits that are based on free pages after the kernel is up */
+	files_maxfiles_init();
 }
 #endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
 
@@ -1285,6 +1296,10 @@
 		bad_reason = "non-NULL mapping";
 	if (unlikely(atomic_read(&page->_count) != 0))
 		bad_reason = "nonzero _count";
+	if (unlikely(page->flags & __PG_HWPOISON)) {
+		bad_reason = "HWPoisoned (hardware-corrupted)";
+		bad_flags = __PG_HWPOISON;
+	}
 	if (unlikely(page->flags & PAGE_FLAGS_CHECK_AT_PREP)) {
 		bad_reason = "PAGE_FLAGS_CHECK_AT_PREP flag set";
 		bad_flags = PAGE_FLAGS_CHECK_AT_PREP;
diff --git a/mm/shmem.c b/mm/shmem.c
index 4caf8ed..dbe0c1e 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3363,8 +3363,8 @@
  * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
  * 	kernel internal.  There will be NO LSM permission checks against the
  * 	underlying inode.  So users of this interface must do LSM checks at a
- * 	higher layer.  The one user is the big_key implementation.  LSM checks
- * 	are provided at the key level rather than the inode level.
+ *	higher layer.  The users are the big_key and shm implementations.  LSM
+ *	checks are provided at the key or shm level rather than the inode.
  * @name: name for dentry (to be seen in /proc/<pid>/maps
  * @size: size to be set for the file
  * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 3e5f8f2..8683110 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -37,8 +37,7 @@
 		SLAB_TRACE | SLAB_DESTROY_BY_RCU | SLAB_NOLEAKTRACE | \
 		SLAB_FAILSLAB)
 
-#define SLAB_MERGE_SAME (SLAB_DEBUG_FREE | SLAB_RECLAIM_ACCOUNT | \
-		SLAB_CACHE_DMA | SLAB_NOTRACK)
+#define SLAB_MERGE_SAME (SLAB_RECLAIM_ACCOUNT | SLAB_CACHE_DMA | SLAB_NOTRACK)
 
 /*
  * Merge control. If this is set then no merging of slab caches will occur.
diff --git a/mm/vmscan.c b/mm/vmscan.c
index e61445d..8286938 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -973,22 +973,18 @@
 		 *    caller can stall after page list has been processed.