diff --git a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
index b878a1e..ed1456f 100644
--- a/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
+++ b/Documentation/devicetree/bindings/mmc/marvell,xenon-sdhci.txt
@@ -16,11 +16,13 @@
 
 - clocks:
   Array of clocks required for SDHC.
-  Require at least input clock for Xenon IP core.
+  Require at least input clock for Xenon IP core. For Armada AP806 and
+  CP110, the AXI clock is also mandatory.
 
 - clock-names:
   Array of names corresponding to clocks property.
   The input clock for Xenon IP core should be named as "core".
+  The input clock for the AXI bus must be named as "axi".
 
 - reg:
   * For "marvell,armada-3700-sdhci", two register areas.
@@ -106,8 +108,8 @@
 		compatible = "marvell,armada-ap806-sdhci";
 		reg = <0xaa0000 0x1000>;
 		interrupts = <GIC_SPI 13 IRQ_TYPE_LEVEL_HIGH>
-		clocks = <&emmc_clk>;
-		clock-names = "core";
+		clocks = <&emmc_clk>,<&axi_clk>;
+		clock-names = "core", "axi";
 		bus-width = <4>;
 		marvell,xenon-phy-slow-mode;
 		marvell,xenon-tun-count = <11>;
@@ -126,8 +128,8 @@
 		interrupts = <GIC_SPI 55 IRQ_TYPE_LEVEL_HIGH>
 		vqmmc-supply = <&sd_vqmmc_regulator>;
 		vmmc-supply = <&sd_vmmc_regulator>;
-		clocks = <&sdclk>;
-		clock-names = "core";
+		clocks = <&sdclk>, <&axi_clk>;
+		clock-names = "core", "axi";
 		bus-width = <4>;
 		marvell,xenon-tun-count = <9>;
 	};
diff --git a/Documentation/filesystems/overlayfs.txt b/Documentation/filesystems/overlayfs.txt
index 36f528a..8caa607 100644
--- a/Documentation/filesystems/overlayfs.txt
+++ b/Documentation/filesystems/overlayfs.txt
@@ -210,8 +210,11 @@
 beneath or above the path of another overlay lower layer path.
 
 Using an upper layer path and/or a workdir path that are already used by
-another overlay mount is not allowed and will fail with EBUSY.  Using
+another overlay mount is not allowed and may fail with EBUSY.  Using
 partially overlapping paths is not allowed but will not fail with EBUSY.
+If files are accessed from two overlayfs mounts which share or overlap the
+upper layer and/or workdir path the behavior of the overlay is undefined,
+though it will not result in a crash or deadlock.
 
 Mounting an overlay using an upper layer path, where the upper layer path
 was previously used by another mounted overlay in combination with a
diff --git a/Documentation/i2c/busses/i2c-i801 b/Documentation/i2c/busses/i2c-i801
index 0500193..d477024 100644
--- a/Documentation/i2c/busses/i2c-i801
+++ b/Documentation/i2c/busses/i2c-i801
@@ -36,6 +36,7 @@
   * Intel Gemini Lake (SOC)
   * Intel Cannon Lake-H (PCH)
   * Intel Cannon Lake-LP (PCH)
+  * Intel Cedar Fork (PCH)
    Datasheets: Publicly available at the Intel website
 
 On Intel Patsburg and later chipsets, both the normal host SMBus controller
diff --git a/MAINTAINERS b/MAINTAINERS
index cc42c83..2d3d750 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5259,7 +5259,8 @@
 F:	drivers/iommu/exynos-iommu.c
 
 EZchip NPS platform support
-M:	Noam Camus <noamc@ezchip.com>
+M:	Elad Kanfi <eladkan@mellanox.com>
+M:	Vineet Gupta <vgupta@synopsys.com>
 S:	Supported
 F:	arch/arc/plat-eznps
 F:	arch/arc/boot/dts/eznps.dts
@@ -9360,7 +9361,7 @@
 M:	Josef Bacik <jbacik@fb.com>
 S:	Maintained
 L:	linux-block@vger.kernel.org
-L:	nbd-general@lists.sourceforge.net
+L:	nbd@other.debian.org
 F:	Documentation/blockdev/nbd.txt
 F:	drivers/block/nbd.c
 F:	include/uapi/linux/nbd.h
diff --git a/Makefile b/Makefile
index cf007a3..2835863 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 4
 PATCHLEVEL = 14
 SUBLEVEL = 0
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Fearless Coyote
 
 # *DOCUMENTATION*
diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig
index a598641..c84e67f 100644
--- a/arch/arc/Kconfig
+++ b/arch/arc/Kconfig
@@ -24,7 +24,7 @@
 	select GENERIC_SMP_IDLE_THREAD
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
-	select HAVE_FUTEX_CMPXCHG
+	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_IOREMAP_PROT
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
diff --git a/arch/arc/Makefile b/arch/arc/Makefile
index 3a4b52b..d37f49d6 100644
--- a/arch/arc/Makefile
+++ b/arch/arc/Makefile
@@ -6,8 +6,6 @@
 # published by the Free Software Foundation.
 #
 
-UTS_MACHINE := arc
-
 ifeq ($(CROSS_COMPILE),)
 ifndef CONFIG_CPU_BIG_ENDIAN
 CROSS_COMPILE := arc-linux-
diff --git a/arch/arc/boot/dts/axs10x_mb.dtsi b/arch/arc/boot/dts/axs10x_mb.dtsi
index 2367a67..e114000 100644
--- a/arch/arc/boot/dts/axs10x_mb.dtsi
+++ b/arch/arc/boot/dts/axs10x_mb.dtsi
@@ -44,7 +44,14 @@
 
 			mmcclk: mmcclk {
 				compatible = "fixed-clock";
-				clock-frequency = <50000000>;
+				/*
+				 * DW sdio controller has external ciu clock divider
+				 * controlled via register in SDIO IP. It divides
+				 * sdio_ref_clk (which comes from CGU) by 16 for
+				 * default. So default mmcclk clock (which comes
+				 * to sdk_in) is 25000000 Hz.
+				 */
+				clock-frequency = <25000000>;
 				#clock-cells = <0>;
 			};
 
diff --git a/arch/arc/boot/dts/hsdk.dts b/arch/arc/boot/dts/hsdk.dts
index 229d13a..8adde1b 100644
--- a/arch/arc/boot/dts/hsdk.dts
+++ b/arch/arc/boot/dts/hsdk.dts
@@ -12,6 +12,7 @@
 /dts-v1/;
 
 #include <dt-bindings/net/ti-dp83867.h>
+#include <dt-bindings/reset/snps,hsdk-reset.h>
 
 / {
 	model = "snps,hsdk";
@@ -57,10 +58,10 @@
 		};
 	};
 
-	core_clk: core-clk {
+	input_clk: input-clk {
 		#clock-cells = <0>;
 		compatible = "fixed-clock";
-		clock-frequency = <500000000>;
+		clock-frequency = <33333333>;
 	};
 
 	cpu_intc: cpu-interrupt-controller {
@@ -102,6 +103,19 @@
 
 		ranges = <0x00000000 0xf0000000 0x10000000>;
 
+		cgu_rst: reset-controller@8a0 {
+			compatible = "snps,hsdk-reset";
+			#reset-cells = <1>;
+			reg = <0x8A0 0x4>, <0xFF0 0x4>;
+		};
+
+		core_clk: core-clk@0 {
+			compatible = "snps,hsdk-core-pll-clock";
+			reg = <0x00 0x10>, <0x14B8 0x4>;
+			#clock-cells = <0>;
+			clocks = <&input_clk>;
+		};
+
 		serial: serial@5000 {
 			compatible = "snps,dw-apb-uart";
 			reg = <0x5000 0x100>;
@@ -120,7 +134,17 @@
 
 		mmcclk_ciu: mmcclk-ciu {
 			compatible = "fixed-clock";
-			clock-frequency = <100000000>;
+			/*
+			 * DW sdio controller has external ciu clock divider
+			 * controlled via register in SDIO IP. Due to its
+			 * unexpected default value (it should devide by 1
+			 * but it devides by 8) SDIO IP uses wrong clock and
+			 * works unstable (see STAR 9001204800)
+			 * So add temporary fix and change clock frequency
+			 * from 100000000 to 12500000 Hz until we fix dw sdio
+			 * driver itself.
+			 */
+			clock-frequency = <12500000>;
 			#clock-cells = <0>;
 		};
 
@@ -141,6 +165,8 @@
 			clocks = <&gmacclk>;
 			clock-names = "stmmaceth";
 			phy-handle = <&phy0>;
+			resets = <&cgu_rst HSDK_ETH_RESET>;
+			reset-names = "stmmaceth";
 
 			mdio {
 				#address-cells = <1>;
diff --git a/arch/arc/configs/axs101_defconfig b/arch/arc/configs/axs101_defconfig
index 6980b96..ec7c849 100644
--- a/arch/arc/configs/axs101_defconfig
+++ b/arch/arc/configs/axs101_defconfig
@@ -105,7 +105,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/axs103_defconfig b/arch/arc/configs/axs103_defconfig
index 2233f57..63d3cf6 100644
--- a/arch/arc/configs/axs103_defconfig
+++ b/arch/arc/configs/axs103_defconfig
@@ -104,7 +104,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/axs103_smp_defconfig b/arch/arc/configs/axs103_smp_defconfig
index 30a3d4c..f613eca 100644
--- a/arch/arc/configs/axs103_smp_defconfig
+++ b/arch/arc/configs/axs103_smp_defconfig
@@ -107,7 +107,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/haps_hs_smp_defconfig b/arch/arc/configs/haps_hs_smp_defconfig
index 821a2e5..3507be2 100644
--- a/arch/arc/configs/haps_hs_smp_defconfig
+++ b/arch/arc/configs/haps_hs_smp_defconfig
@@ -84,5 +84,5 @@
 CONFIG_NFS_FS=y
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/hsdk_defconfig b/arch/arc/configs/hsdk_defconfig
index 9a3fcf4..15f0f6b 100644
--- a/arch/arc/configs/hsdk_defconfig
+++ b/arch/arc/configs/hsdk_defconfig
@@ -63,6 +63,7 @@
 CONFIG_MMC_SDHCI_PLTFM=y
 CONFIG_MMC_DW=y
 # CONFIG_IOMMU_SUPPORT is not set
+CONFIG_RESET_HSDK=y
 CONFIG_EXT3_FS=y
 CONFIG_VFAT_FS=y
 CONFIG_TMPFS=y
@@ -72,7 +73,7 @@
 # CONFIG_ENABLE_WARN_DEPRECATED is not set
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/vdk_hs38_defconfig b/arch/arc/configs/vdk_hs38_defconfig
index c0d6a01..4fcf4f2 100644
--- a/arch/arc/configs/vdk_hs38_defconfig
+++ b/arch/arc/configs/vdk_hs38_defconfig
@@ -94,7 +94,7 @@
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_SHIRQ=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/configs/vdk_hs38_smp_defconfig b/arch/arc/configs/vdk_hs38_smp_defconfig
index 5c09717..7b71464 100644
--- a/arch/arc/configs/vdk_hs38_smp_defconfig
+++ b/arch/arc/configs/vdk_hs38_smp_defconfig
@@ -98,7 +98,7 @@
 # CONFIG_ENABLE_MUST_CHECK is not set
 CONFIG_STRIP_ASM_SYMS=y
 CONFIG_DEBUG_SHIRQ=y
-CONFIG_LOCKUP_DETECTOR=y
+CONFIG_SOFTLOCKUP_DETECTOR=y
 CONFIG_DEFAULT_HUNG_TASK_TIMEOUT=10
 # CONFIG_SCHED_DEBUG is not set
 # CONFIG_DEBUG_PREEMPT is not set
diff --git a/arch/arc/include/asm/arcregs.h b/arch/arc/include/asm/arcregs.h
index ba8e802..b1c56d3 100644
--- a/arch/arc/include/asm/arcregs.h
+++ b/arch/arc/include/asm/arcregs.h
@@ -98,6 +98,7 @@
 
 /* Auxiliary registers */
 #define AUX_IDENTITY		4
+#define AUX_EXEC_CTRL		8
 #define AUX_INTR_VEC_BASE	0x25
 #define AUX_VOL			0x5e
 
@@ -135,12 +136,12 @@ struct bcr_identity {
 #endif
 };
 
-struct bcr_isa {
+struct bcr_isa_arcv2 {
 #ifdef CONFIG_CPU_BIG_ENDIAN
 	unsigned int div_rem:4, pad2:4, ldd:1, unalign:1, atomic:1, be:1,
-		     pad1:11, atomic1:1, ver:8;
+		     pad1:12, ver:8;
 #else
-	unsigned int ver:8, atomic1:1, pad1:11, be:1, atomic:1, unalign:1,
+	unsigned int ver:8, pad1:12, be:1, atomic:1, unalign:1,
 		     ldd:1, pad2:4, div_rem:4;
 #endif
 };
@@ -263,13 +264,13 @@ struct cpuinfo_arc {
 	struct cpuinfo_arc_mmu mmu;
 	struct cpuinfo_arc_bpu bpu;
 	struct bcr_identity core;
-	struct bcr_isa isa;
+	struct bcr_isa_arcv2 isa;
 	const char *details, *name;
 	unsigned int vec_base;
 	struct cpuinfo_arc_ccm iccm, dccm;
 	struct {
 		unsigned int swap:1, norm:1, minmax:1, barrel:1, crc:1, swape:1, pad1:2,
-			     fpu_sp:1, fpu_dp:1, pad2:6,
+			     fpu_sp:1, fpu_dp:1, dual_iss_enb:1, dual_iss_exist:1, pad2:4,
 			     debug:1, ap:1, smart:1, rtt:1, pad3:4,
 			     timer0:1, timer1:1, rtc:1, gfrc:1, pad4:4;
 	} extn;
diff --git a/arch/arc/kernel/setup.c b/arch/arc/kernel/setup.c
index 877cec8..fb83844 100644
--- a/arch/arc/kernel/setup.c
+++ b/arch/arc/kernel/setup.c
@@ -51,6 +51,7 @@ static const struct id_to_str arc_cpu_rel[] = {
 	{ 0x51, "R2.0" },
 	{ 0x52, "R2.1" },
 	{ 0x53, "R3.0" },
+	{ 0x54, "R4.0" },
 #endif
 	{ 0x00, NULL   }
 };
@@ -62,6 +63,7 @@ static const struct id_to_str arc_cpu_nm[] = {
 #else
 	{ 0x40, "ARC EM"  },
 	{ 0x50, "ARC HS38"  },
+	{ 0x54, "ARC HS48"  },
 #endif
 	{ 0x00, "Unknown"   }
 };
@@ -119,11 +121,11 @@ static void read_arc_build_cfg_regs(void)
 	struct bcr_generic bcr;
 	struct cpuinfo_arc *cpu = &cpuinfo_arc700[smp_processor_id()];
 	const struct id_to_str *tbl;
+	struct bcr_isa_arcv2 isa;
 
 	FIX_PTR(cpu);
 
 	READ_BCR(AUX_IDENTITY, cpu->core);
-	READ_BCR(ARC_REG_ISA_CFG_BCR, cpu->isa);
 
 	for (tbl = &arc_cpu_rel[0]; tbl->id != 0; tbl++) {
 		if (cpu->core.family == tbl->id) {
@@ -133,7 +135,7 @@ static void read_arc_build_cfg_regs(void)
 	}
 
 	for (tbl = &arc_cpu_nm[0]; tbl->id != 0; tbl++) {
-		if ((cpu->core.family & 0xF0) == tbl->id)
+		if ((cpu->core.family & 0xF4) == tbl->id)
 			break;
 	}
 	cpu->name = tbl->str;
@@ -192,6 +194,14 @@ static void read_arc_build_cfg_regs(void)
 		cpu->bpu.full = bpu.ft;
 		cpu->bpu.num_cache = 256 << bpu.bce;
 		cpu->bpu.num_pred = 2048 << bpu.pte;
+
+		if (cpu->core.family >= 0x54) {
+			unsigned int exec_ctrl;
+
+			READ_BCR(AUX_EXEC_CTRL, exec_ctrl);
+			cpu->extn.dual_iss_exist = 1;
+			cpu->extn.dual_iss_enb = exec_ctrl & 1;
+		}
 	}
 
 	READ_BCR(ARC_REG_AP_BCR, bcr);
@@ -205,18 +215,25 @@ static void read_arc_build_cfg_regs(void)
 
 	cpu->extn.debug = cpu->extn.ap | cpu->extn.smart | cpu->extn.rtt;
 
+	READ_BCR(ARC_REG_ISA_CFG_BCR, isa);
+
 	/* some hacks for lack of feature BCR info in old ARC700 cores */
 	if (is_isa_arcompact()) {
-		if (!cpu->isa.ver)	/* ISA BCR absent, use Kconfig info */
+		if (!isa.ver)	/* ISA BCR absent, use Kconfig info */
 			cpu->isa.atomic = IS_ENABLED(CONFIG_ARC_HAS_LLSC);
-		else
-			cpu->isa.atomic = cpu->isa.atomic1;
+		else {
+			/* ARC700_BUILD only has 2 bits of isa info */
+			struct bcr_generic bcr = *(struct bcr_generic *)&isa;
+			cpu->isa.atomic = bcr.info & 1;
+		}
 
 		cpu->isa.be = IS_ENABLED(CONFIG_CPU_BIG_ENDIAN);
 
 		 /* there's no direct way to distinguish 750 vs. 770 */
 		if (unlikely(cpu->core.family < 0x34 || cpu->mmu.ver < 3))
 			cpu->name = "ARC750";
+	} else {
+		cpu->isa = isa;
 	}
 }
 
@@ -232,10 +249,11 @@ static char *arc_cpu_mumbojumbo(int cpu_id, char *buf, int len)
 		       "\nIDENTITY\t: ARCVER [%#02x] ARCNUM [%#02x] CHIPID [%#4x]\n",
 		       core->family, core->cpu_id, core->chip_id);
 
-	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s\n",
+	n += scnprintf(buf + n, len - n, "processor [%d]\t: %s %s (%s ISA) %s%s%s\n",
 		       cpu_id, cpu->name, cpu->details,
 		       is_isa_arcompact() ? "ARCompact" : "ARCv2",
-		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"));
+		       IS_AVAIL1(cpu->isa.be, "[Big-Endian]"),
+		       IS_AVAIL3(cpu->extn.dual_iss_exist, cpu->extn.dual_iss_enb, " Dual-Issue"));
 
 	n += scnprintf(buf + n, len - n, "Timers\t\t: %s%s%s%s%s%s\nISA Extn\t: ",
 		       IS_AVAIL1(cpu->extn.timer0, "Timer0 "),
diff --git a/arch/arc/plat-axs10x/axs10x.c b/arch/arc/plat-axs10x/axs10x.c
index f1ac679..cf14ebc 100644
--- a/arch/arc/plat-axs10x/axs10x.c
+++ b/arch/arc/plat-axs10x/axs10x.c
@@ -111,6 +111,13 @@ static void __init axs10x_early_init(void)
 
 	axs10x_enable_gpio_intc_wire();
 
+	/*
+	 * Reset ethernet IP core.
+	 * TODO: get rid of this quirk after axs10x reset driver (or simple
+	 * reset driver) will be available in upstream.
+	 */
+	iowrite32((1 << 5), (void __iomem *) CREG_MB_SW_RESET);
+
 	scnprintf(mb, 32, "MainBoard v%d", mb_rev);
 	axs10x_print_board_ver(CREG_MB_VER, mb);
 }
diff --git a/arch/arc/plat-hsdk/Kconfig b/arch/arc/plat-hsdk/Kconfig
index 5a6ed5a..bd08de4 100644
--- a/arch/arc/plat-hsdk/Kconfig
+++ b/arch/arc/plat-hsdk/Kconfig
@@ -6,4 +6,5 @@
 #
 
 menuconfig ARC_SOC_HSDK
-       bool "ARC HS Development Kit SOC"
+	bool "ARC HS Development Kit SOC"
+	select CLK_HSDK
diff --git a/arch/arc/plat-hsdk/platform.c b/arch/arc/plat-hsdk/platform.c
index a2e7fd1..744e62e 100644
--- a/arch/arc/plat-hsdk/platform.c
+++ b/arch/arc/plat-hsdk/platform.c
@@ -38,6 +38,42 @@ static void __init hsdk_init_per_cpu(unsigned int cpu)
 #define CREG_PAE		(CREG_BASE + 0x180)
 #define CREG_PAE_UPDATE		(CREG_BASE + 0x194)
 
+#define CREG_CORE_IF_CLK_DIV	(CREG_BASE + 0x4B8)
+#define CREG_CORE_IF_CLK_DIV_2	0x1
+#define CGU_BASE		ARC_PERIPHERAL_BASE
+#define CGU_PLL_STATUS		(ARC_PERIPHERAL_BASE + 0x4)
+#define CGU_PLL_CTRL		(ARC_PERIPHERAL_BASE + 0x0)
+#define CGU_PLL_STATUS_LOCK	BIT(0)
+#define CGU_PLL_STATUS_ERR	BIT(1)
+#define CGU_PLL_CTRL_1GHZ	0x3A10
+#define HSDK_PLL_LOCK_TIMEOUT	500
+
+#define HSDK_PLL_LOCKED() \
+	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_LOCK)
+
+#define HSDK_PLL_ERR() \
+	!!(ioread32((void __iomem *) CGU_PLL_STATUS) & CGU_PLL_STATUS_ERR)
+
+static void __init hsdk_set_cpu_freq_1ghz(void)
+{
+	u32 timeout = HSDK_PLL_LOCK_TIMEOUT;
+
+	/*
+	 * As we set cpu clock which exceeds 500MHz, the divider for the interface
+	 * clock must be programmed to div-by-2.
+	 */
+	iowrite32(CREG_CORE_IF_CLK_DIV_2, (void __iomem *) CREG_CORE_IF_CLK_DIV);
+
+	/* Set cpu clock to 1GHz */
+	iowrite32(CGU_PLL_CTRL_1GHZ, (void __iomem *) CGU_PLL_CTRL);
+
+	while (!HSDK_PLL_LOCKED() && timeout--)
+		cpu_relax();
+
+	if (!HSDK_PLL_LOCKED() || HSDK_PLL_ERR())
+		pr_err("Failed to setup CPU frequency to 1GHz!");
+}
+
 static void __init hsdk_init_early(void)
 {
 	/*
@@ -52,6 +88,12 @@ static void __init hsdk_init_early(void)
 
 	/* Really apply settings made above */
 	writel(1, (void __iomem *) CREG_PAE_UPDATE);
+
+	/*
+	 * Setup CPU frequency to 1GHz.
+	 * TODO: remove it after smart hsdk pll driver will be introduced.
+	 */
+	hsdk_set_cpu_freq_1ghz();
 }
 
 static const char *hsdk_compat[] __initconst = {
diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h
index 3585a5e..f7c4d21 100644
--- a/arch/arm64/include/asm/memory.h
+++ b/arch/arm64/include/asm/memory.h
@@ -95,16 +95,19 @@
 #define KERNEL_END        _end
 
 /*
- * The size of the KASAN shadow region. This should be 1/8th of the
- * size of the entire kernel virtual address space.
+ * KASAN requires 1/8th of the kernel virtual address space for the shadow
+ * region. KASAN can bloat the stack significantly, so double the (minimum)
+ * stack size when KASAN is in use.
  */
 #ifdef CONFIG_KASAN
 #define KASAN_SHADOW_SIZE	(UL(1) << (VA_BITS - 3))
+#define KASAN_THREAD_SHIFT	1
 #else
 #define KASAN_SHADOW_SIZE	(0)
+#define KASAN_THREAD_SHIFT	0
 #endif
 
-#define MIN_THREAD_SHIFT	14
+#define MIN_THREAD_SHIFT	(14 + KASAN_THREAD_SHIFT)
 
 /*
  * VMAP'd stacks are allocated at page granularity, so we must ensure that such
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index f0e6d71..d06fbe4 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -649,4 +649,4 @@ static int __init armv8_deprecated_init(void)
 	return 0;
 }
 
-late_initcall(armv8_deprecated_init);
+core_initcall(armv8_deprecated_init);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index cd52d36..21e2c95 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1307,4 +1307,4 @@ static int __init enable_mrs_emulation(void)
 	return 0;
 }
 
-late_initcall(enable_mrs_emulation);
+core_initcall(enable_mrs_emulation);
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index f444f37..5d547de 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -444,4 +444,4 @@ static int __init fpsimd_init(void)
 
 	return 0;
 }
-late_initcall(fpsimd_init);
+core_initcall(fpsimd_init);
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2069e9b..b64958b 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -97,7 +97,7 @@ static void data_abort_decode(unsigned int esr)
 			 (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT,
 			 (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT);
 	} else {
-		pr_alert("  ISV = 0, ISS = 0x%08lu\n", esr & ESR_ELx_ISS_MASK);
+		pr_alert("  ISV = 0, ISS = 0x%08lx\n", esr & ESR_ELx_ISS_MASK);
 	}
 
 	pr_alert("  CM = %lu, WnR = %lu\n",
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index a45a67d..30f9239 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -146,7 +146,7 @@ void machine_power_off(void)
 
 	/* prevent soft lockup/stalled CPU messages for endless loop. */
 	rcu_sysrq_start();
-	lockup_detector_suspend();
+	lockup_detector_soft_poweroff();
 	for (;;);
 }
 
diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c
index 1df770e..7275fed 100644
--- a/arch/powerpc/kernel/dt_cpu_ftrs.c
+++ b/arch/powerpc/kernel/dt_cpu_ftrs.c
@@ -102,10 +102,10 @@ static void cpufeatures_flush_tlb(void)
 	case PVR_POWER8:
 	case PVR_POWER8E:
 	case PVR_POWER8NVL:
-		__flush_tlb_power8(POWER8_TLB_SETS);
+		__flush_tlb_power8(TLB_INVAL_SCOPE_GLOBAL);
 		break;
 	case PVR_POWER9:
-		__flush_tlb_power9(POWER9_TLB_SETS_HASH);
+		__flush_tlb_power9(TLB_INVAL_SCOPE_GLOBAL);
 		break;
 	default:
 		pr_err("unknown CPU version for boot TLB flush\n");
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index b76ca19..72f153c6 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -624,5 +624,18 @@ long __machine_check_early_realmode_p8(struct pt_regs *regs)
 
 long __machine_check_early_realmode_p9(struct pt_regs *regs)
 {
+	/*
+	 * On POWER9 DD2.1 and below, it's possible to get a machine check
+	 * caused by a paste instruction where only DSISR bit 25 is set. This
+	 * will result in the MCE handler seeing an unknown event and the kernel
+	 * crashing. An MCE that occurs like this is spurious, so we don't need
+	 * to do anything in terms of servicing it. If there is something that
+	 * needs to be serviced, the CPU will raise the MCE again with the
+	 * correct DSISR so that it can be serviced properly. So detect this
+	 * case and mark it as handled.
+	 */
+	if (SRR1_MC_LOADSTORE(regs->msr) && regs->dsisr == 0x02000000)
+		return 1;
+
 	return mce_handle_error(regs, mce_p9_derror_table, mce_p9_ierror_table);
 }
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 0ac741f..2e3bc16 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -904,9 +904,6 @@ void __init setup_arch(char **cmdline_p)
 #endif
 #endif
 
-#ifdef CONFIG_PPC_64K_PAGES
-	init_mm.context.pte_frag = NULL;
-#endif
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 	mm_iommu_init(&init_mm);
 #endif
diff --git a/arch/powerpc/kernel/watchdog.c b/arch/powerpc/kernel/watchdog.c
index 2f6eadd..c702a89 100644
--- a/arch/powerpc/kernel/watchdog.c
+++ b/arch/powerpc/kernel/watchdog.c
@@ -310,9 +310,6 @@ static int start_wd_on_cpu(unsigned int cpu)
 	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
 		return 0;
 
-	if (watchdog_suspended)
-		return 0;
-
 	if (!cpumask_test_cpu(cpu, &watchdog_cpumask))
 		return 0;
 
@@ -358,36 +355,39 @@ static void watchdog_calc_timeouts(void)
 	wd_timer_period_ms = watchdog_thresh * 1000 * 2 / 5;
 }
 
-void watchdog_nmi_reconfigure(void)
+void watchdog_nmi_stop(void)
+{
+	int cpu;
+
+	for_each_cpu(cpu, &wd_cpus_enabled)
+		stop_wd_on_cpu(cpu);
+}
+
+void watchdog_nmi_start(void)
 {
 	int cpu;
 
 	watchdog_calc_timeouts();
-
-	for_each_cpu(cpu, &wd_cpus_enabled)
-		stop_wd_on_cpu(cpu);
-
 	for_each_cpu_and(cpu, cpu_online_mask, &watchdog_cpumask)
 		start_wd_on_cpu(cpu);
 }
 
 /*
- * This runs after lockup_detector_init() which sets up watchdog_cpumask.
+ * Invoked from core watchdog init.
  */
-static int __init powerpc_watchdog_init(void)
+int __init watchdog_nmi_probe(void)
 {
 	int err;
 
-	watchdog_calc_timeouts();
-
-	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/watchdog:online",
-				start_wd_on_cpu, stop_wd_on_cpu);
-	if (err < 0)
+	err = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"powerpc/watchdog:online",
+					start_wd_on_cpu, stop_wd_on_cpu);
+	if (err < 0) {
 		pr_warn("Watchdog could not be initialized");
-
+		return err;
+	}
 	return 0;
 }
-arch_initcall(powerpc_watchdog_init);
 
 static void handle_backtrace_ipi(struct pt_regs *regs)
 {
diff --git a/arch/powerpc/kvm/book3s_xive.c b/arch/powerpc/kvm/book3s_xive.c
index 1330462..bf45784 100644
--- a/arch/powerpc/kvm/book3s_xive.c
+++ b/arch/powerpc/kvm/book3s_xive.c
@@ -622,7 +622,7 @@ int kvmppc_xive_get_xive(struct kvm *kvm, u32 irq, u32 *server,
 		return -EINVAL;
 	state = &sb->irq_state[idx];
 	arch_spin_lock(&sb->lock);
-	*server = state->guest_server;
+	*server = state->act_server;
 	*priority = state->guest_priority;
 	arch_spin_unlock(&sb->lock);
 
@@ -1331,7 +1331,7 @@ static int xive_get_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	xive->saved_src_count++;
 
 	/* Convert saved state into something compatible with xics */
-	val = state->guest_server;
+	val = state->act_server;
 	prio = state->saved_scan_prio;
 
 	if (prio == MASKED) {
@@ -1507,7 +1507,6 @@ static int xive_set_source(struct kvmppc_xive *xive, long irq, u64 addr)
 	/* First convert prio and mark interrupt as untargetted */
 	act_prio = xive_prio_from_guest(guest_prio);
 	state->act_priority = MASKED;
-	state->guest_server = server;
 
 	/*
 	 * We need to drop the lock due to the mutex below. Hopefully
diff --git a/arch/powerpc/kvm/book3s_xive.h b/arch/powerpc/kvm/book3s_xive.h
index 5938f76..6ba63f8 100644
--- a/arch/powerpc/kvm/book3s_xive.h
+++ b/arch/powerpc/kvm/book3s_xive.h
@@ -35,7 +35,6 @@ struct kvmppc_xive_irq_state {
 	struct xive_irq_data *pt_data;	/* XIVE Pass-through associated data */
 
 	/* Targetting as set by guest */
-	u32 guest_server;		/* Current guest selected target */
 	u8 guest_priority;		/* Guest set priority */
 	u8 saved_priority;		/* Saved priority when masking */
 
diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c
index 65eda19..f6c7f54 100644
--- a/arch/powerpc/mm/pgtable_32.c
+++ b/arch/powerpc/mm/pgtable_32.c
@@ -361,9 +361,9 @@ static int change_page_attr(struct page *page, int numpages, pgprot_t prot)
 			break;
 	}
 	wmb();
+	local_irq_restore(flags);
 	flush_tlb_kernel_range((unsigned long)page_address(start),
 			       (unsigned long)page_address(page));
-	local_irq_restore(flags);
 	return err;
 }
 
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 897aa14..bbb73aa 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -272,7 +272,15 @@ static void pnv_kexec_cpu_down(int crash_shutdown, int secondary)
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
 static unsigned long pnv_memory_block_size(void)
 {
-	return 256UL * 1024 * 1024;
+	/*
+	 * We map the kernel linear region with 1GB large pages on radix. For
+	 * memory hot unplug to work our memory block size must be at least
+	 * this size.
+	 */
+	if (radix_enabled())
+		return 1UL * 1024 * 1024 * 1024;
+	else
+		return 256UL * 1024 * 1024;
 }
 #endif
 
diff --git a/arch/powerpc/sysdev/xive/common.c b/arch/powerpc/sysdev/xive/common.c
index f387318..a3b8d7d 100644
--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -1402,6 +1402,14 @@ void xive_teardown_cpu(void)
 
 	if (xive_ops->teardown_cpu)
 		xive_ops->teardown_cpu(cpu, xc);
+
+#ifdef CONFIG_SMP
+	/* Get rid of IPI */
+	xive_cleanup_cpu_ipi(cpu, xc);
+#endif
+
+	/* Disable and free the queues */
+	xive_cleanup_cpu_queues(cpu, xc);
 }
 
 void xive_kexec_teardown_cpu(int secondary)
diff --git a/arch/powerpc/sysdev/xive/spapr.c b/arch/powerpc/sysdev/xive/spapr.c
index f24a70b..d9c4c93 100644
--- a/arch/powerpc/sysdev/xive/spapr.c
+++ b/arch/powerpc/sysdev/xive/spapr.c
@@ -431,7 +431,11 @@ static int xive_spapr_get_ipi(unsigned int cpu, struct xive_cpu *xc)
 
 static void xive_spapr_put_ipi(unsigned int cpu, struct xive_cpu *xc)
 {
+	if (!xc->hw_ipi)
+		return;
+
 	xive_irq_bitmap_free(xc->hw_ipi);
+	xc->hw_ipi = 0;
 }
 #endif /* CONFIG_SMP */
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 829e89c..9fb9a1f 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -4409,10 +4409,9 @@ static __init int fixup_ht_bug(void)
 		return 0;
 	}
 
-	if (lockup_detector_suspend() != 0) {
-		pr_debug("failed to disable PMU erratum BJ122, BV98, HSD29 workaround\n");
-		return 0;
-	}
+	cpus_read_lock();
+
+	hardlockup_detector_perf_stop();
 
 	x86_pmu.flags &= ~(PMU_FL_EXCL_CNTRS | PMU_FL_EXCL_ENABLED);
 
@@ -4420,9 +4419,7 @@ static __init int fixup_ht_bug(void)
 	x86_pmu.commit_scheduling = NULL;
 	x86_pmu.stop_scheduling = NULL;
 
-	lockup_detector_resume();
-
-	cpus_read_lock();
+	hardlockup_detector_perf_restart();
 
 	for_each_online_cpu(c)
 		free_excl_cntrs(c);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index bc62e7c..59ad3d1 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -88,7 +88,7 @@ static inline long kvm_hypercall4(unsigned int nr, unsigned long p1,
 bool kvm_para_available(void);
 unsigned int kvm_arch_para_features(void);
 void __init kvm_guest_init(void);
-void kvm_async_pf_task_wait(u32 token);
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel);
 void kvm_async_pf_task_wake(u32 token);
 u32 kvm_read_and_reset_pf_reason(void);
 extern void kvm_disable_steal_time(void);
@@ -103,7 +103,7 @@ static inline void kvm_spinlock_init(void)
 
 #else /* CONFIG_KVM_GUEST */
 #define kvm_guest_init() do {} while (0)
-#define kvm_async_pf_task_wait(T) do {} while(0)
+#define kvm_async_pf_task_wait(T, I) do {} while(0)
 #define kvm_async_pf_task_wake(T) do {} while(0)
 
 static inline bool kvm_para_available(void)
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index e675704..8bb9594 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -117,7 +117,11 @@ static struct kvm_task_sleep_node *_find_apf_task(struct kvm_task_sleep_head *b,
 	return NULL;
 }
 
-void kvm_async_pf_task_wait(u32 token)
+/*
+ * @interrupt_kernel: Is this called from a routine which interrupts the kernel
+ * 		      (other than user space)?
+ */
+void kvm_async_pf_task_wait(u32 token, int interrupt_kernel)
 {
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
@@ -140,8 +144,10 @@ void kvm_async_pf_task_wait(u32 token)
 
 	n.token = token;
 	n.cpu = smp_processor_id();
-	n.halted = is_idle_task(current) || preempt_count() > 1 ||
-		   rcu_preempt_depth();
+	n.halted = is_idle_task(current) ||
+		   (IS_ENABLED(CONFIG_PREEMPT_COUNT)
+		    ? preempt_count() > 1 || rcu_preempt_depth()
+		    : interrupt_kernel);
 	init_swait_queue_head(&n.wq);
 	hlist_add_head(&n.link, &b->list);
 	raw_spin_unlock(&b->lock);
@@ -269,7 +275,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		/* page is swapped out by the host. */
 		prev_state = exception_enter();
-		kvm_async_pf_task_wait((u32)read_cr2());
+		kvm_async_pf_task_wait((u32)read_cr2(), !user_mode(regs));
 		exception_exit(prev_state);
 		break;
 	case KVM_PV_REASON_PAGE_READY:
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 3ea6244..3c48bc8 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -23,6 +23,7 @@
 	depends on HIGH_RES_TIMERS
 	# for TASKSTATS/TASK_DELAY_ACCT:
 	depends on NET && MULTIUSER
+	depends on X86_LOCAL_APIC
 	select PREEMPT_NOTIFIERS
 	select MMU_NOTIFIER
 	select ANON_INODES
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index a36254c..d90cdc7 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -425,8 +425,10 @@ static int fastop(struct x86_emulate_ctxt *ctxt, void (*fop)(struct fastop *));
 	#op " %al \n\t" \
 	FOP_RET
 
-asm(".global kvm_fastop_exception \n"
-    "kvm_fastop_exception: xor %esi, %esi; ret");
+asm(".pushsection .fixup, \"ax\"\n"
+    ".global kvm_fastop_exception \n"
+    "kvm_fastop_exception: xor %esi, %esi; ret\n"
+    ".popsection");
 
 FOP_START(setcc)
 FOP_SETCC(seto)
diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c
index eca30c1..106d4a0 100644
--- a/arch/x86/kvm/mmu.c
+++ b/arch/x86/kvm/mmu.c
@@ -3837,7 +3837,7 @@ int kvm_handle_page_fault(struct kvm_vcpu *vcpu, u64 error_code,
 	case KVM_PV_REASON_PAGE_NOT_PRESENT:
 		vcpu->arch.apf.host_apf_reason = 0;
 		local_irq_disable();
-		kvm_async_pf_task_wait(fault_address);
+		kvm_async_pf_task_wait(fault_address, 0);
 		local_irq_enable();
 		break;
 	case KVM_PV_REASON_PAGE_READY:
diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c
index 980e730..de294d7 100644
--- a/block/blk-mq-debugfs.c
+++ b/block/blk-mq-debugfs.c
@@ -815,10 +815,14 @@ int blk_mq_debugfs_register(struct request_queue *q)
 		goto err;
 
 	/*
-	 * blk_mq_init_hctx() attempted to do this already, but q->debugfs_dir
+	 * blk_mq_init_sched() attempted to do this already, but q->debugfs_dir
 	 * didn't exist yet (because we don't know what to name the directory
 	 * until the queue is registered to a gendisk).
 	 */
+	if (q->elevator && !q->sched_debugfs_dir)
+		blk_mq_debugfs_register_sched(q);
+
+	/* Similarly, blk_mq_init_hctx() couldn't do this previously. */
 	queue_for_each_hw_ctx(q, hctx, i) {
 		if (!hctx->debugfs_dir && blk_mq_debugfs_register_hctx(q, hctx))
 			goto err;
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 0fea76a..17816a0 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -1911,11 +1911,11 @@ static void throtl_upgrade_state(struct throtl_data *td)
 
 		tg->disptime = jiffies - 1;
 		throtl_select_dispatch(sq);
-		throtl_schedule_next_dispatch(sq, false);
+		throtl_schedule_next_dispatch(sq, true);
 	}
 	rcu_read_unlock();
 	throtl_select_dispatch(&td->service_queue);
-	throtl_schedule_next_dispatch(&td->service_queue, false);
+	throtl_schedule_next_dispatch(&td->service_queue, true);
 	queue_work(kthrotld_workqueue, &td->dispatch_work);
 }
 
diff --git a/block/bsg-lib.c b/block/bsg-lib.c
index dbddff8..15d25cc 100644
--- a/block/bsg-lib.c
+++ b/block/bsg-lib.c
@@ -207,20 +207,34 @@ static int bsg_init_rq(struct request_queue *q, struct request *req, gfp_t gfp)
 	struct bsg_job *job = blk_mq_rq_to_pdu(req);
 	struct scsi_request *sreq = &job->sreq;
 
-	memset(job, 0, sizeof(*job));
+	/* called right after the request is allocated for the request_queue */
 
-	scsi_req_init(sreq);
-	sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
-	sreq->sense = kzalloc(sreq->sense_len, gfp);
+	sreq->sense = kzalloc(SCSI_SENSE_BUFFERSIZE, gfp);
 	if (!sreq->sense)
 		return -ENOMEM;
 
+	return 0;
+}
+
+static void bsg_initialize_rq(struct request *req)
+{
+	struct bsg_job *job = blk_mq_rq_to_pdu(req);
+	struct scsi_request *sreq = &job->sreq;
+	void *sense = sreq->sense;
+
+	/* called right before the request is given to the request_queue user */
+
+	memset(job, 0, sizeof(*job));
+
+	scsi_req_init(sreq);
+
+	sreq->sense = sense;
+	sreq->sense_len = SCSI_SENSE_BUFFERSIZE;
+
 	job->req = req;
-	job->reply = sreq->sense;
+	job->reply = sense;
 	job->reply_len = sreq->sense_len;
 	job->dd_data = job + 1;
-
-	return 0;
 }
 
 static void bsg_exit_rq(struct request_queue *q, struct request *req)
@@ -251,6 +265,7 @@ struct request_queue *bsg_setup_queue(struct device *dev, const char *name,
 	q->cmd_size = sizeof(struct bsg_job) + dd_job_size;
 	q->init_rq_fn = bsg_init_rq;
 	q->exit_rq_fn = bsg_exit_rq;
+	q->initialize_rq_fn = bsg_initialize_rq;
 	q->request_fn = bsg_request_fn;
 
 	ret = blk_init_allocated_queue(q);
diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c
index 9565d57..de56394 100644
--- a/drivers/acpi/arm64/iort.c
+++ b/drivers/acpi/arm64/iort.c
@@ -1178,12 +1178,44 @@ static int __init iort_add_smmu_platform_device(struct acpi_iort_node *node)
 	return ret;
 }
 
+static bool __init iort_enable_acs(struct acpi_iort_node *iort_node)
+{
+	if (iort_node->type == ACPI_IORT_NODE_PCI_ROOT_COMPLEX) {
+		struct acpi_iort_node *parent;
+		struct acpi_iort_id_mapping *map;
+		int i;
+
+		map = ACPI_ADD_PTR(struct acpi_iort_id_mapping, iort_node,
+				   iort_node->mapping_offset);
+
+		for (i = 0; i < iort_node->mapping_count; i++, map++) {
+			if (!map->output_reference)
+				continue;
+
+			parent = ACPI_ADD_PTR(struct acpi_iort_node,
+					iort_table,  map->output_reference);
+			/*
+			 * If we detect a RC->SMMU mapping, make sure
+			 * we enable ACS on the system.
+			 */
+			if ((parent->type == ACPI_IORT_NODE_SMMU) ||
+				(parent->type == ACPI_IORT_NODE_SMMU_V3)) {
+				pci_request_acs();
+				return true;
+			}
+		}
+	}
+
+	return false;
+}
+
 static void __init iort_init_platform_devices(void)
 {
 	struct acpi_iort_node *iort_node, *iort_end;
 	struct acpi_table_iort *iort;
 	struct fwnode_handle *fwnode;
 	int i, ret;
+	bool acs_enabled = false;
 
 	/*
 	 * iort_table and iort both point to the start of IORT table, but
@@ -1203,6 +1235,9 @@ static void __init iort_init_platform_devices(void)
 			return;
 		}
 
+		if (!acs_enabled)
+			acs_enabled = iort_enable_acs(iort_node);
+
 		if ((iort_node->type == ACPI_IORT_NODE_SMMU) ||
 			(iort_node->type == ACPI_IORT_NODE_SMMU_V3)) {
 
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 4a438b8..2dfe99b 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -17,7 +17,7 @@
 
 config BLK_DEV_NULL_BLK
 	tristate "Null test block driver"
-	depends on CONFIGFS_FS
+	select CONFIGFS_FS
 
 config BLK_DEV_FD
 	tristate "Normal floppy disk support"
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 3684e21..883dfeb 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -820,9 +820,13 @@ static blk_status_t nbd_queue_rq(struct blk_mq_hw_ctx *hctx,
 	 * appropriate.
 	 */
 	ret = nbd_handle_cmd(cmd, hctx->queue_num);
+	if (ret < 0)
+		ret = BLK_STS_IOERR;
+	else if (!ret)
+		ret = BLK_STS_OK;
 	complete(&cmd->send_complete);
 
-	return ret < 0 ? BLK_STS_IOERR : BLK_STS_OK;
+	return ret;
 }
 
 static int nbd_add_socket(struct nbd_device *nbd, unsigned long arg,
diff --git a/drivers/clk/clk-bulk.c b/drivers/clk/clk-bulk.c
index c834f5a..4c10456 100644
--- a/drivers/clk/clk-bulk.c
+++ b/drivers/clk/clk-bulk.c
@@ -105,6 +105,7 @@ int __must_check clk_bulk_prepare(int num_clks,
 
 	return  ret;
 }
+EXPORT_SYMBOL_GPL(clk_bulk_prepare);
 
 #endif /* CONFIG_HAVE_CLK_PREPARE */
 
diff --git a/drivers/clk/rockchip/clk-rk3128.c b/drivers/clk/rockchip/clk-rk3128.c
index 62d7854..5970a50 100644
--- a/drivers/clk/rockchip/clk-rk3128.c
+++ b/drivers/clk/rockchip/clk-rk3128.c
@@ -315,13 +315,13 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 			RK2928_CLKGATE_CON(10), 8, GFLAGS),
 
 	GATE(SCLK_PVTM_CORE, "clk_pvtm_core", "xin24m", 0,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(10), 0, GFLAGS),
 	GATE(SCLK_PVTM_GPU, "clk_pvtm_gpu", "xin24m", 0,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(10), 1, GFLAGS),
 	GATE(SCLK_PVTM_FUNC, "clk_pvtm_func", "xin24m", 0,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(10), 2, GFLAGS),
 	GATE(SCLK_MIPI_24M, "clk_mipi_24m", "xin24m", CLK_IGNORE_UNUSED,
-			RK2928_CLKGATE_CON(10), 8, GFLAGS),
+			RK2928_CLKGATE_CON(2), 15, GFLAGS),
 
 	COMPOSITE(SCLK_SDMMC, "sclk_sdmmc0", mux_mmc_src_p, 0,
 			RK2928_CLKSEL_CON(11), 6, 2, MFLAGS, 0, 6, DFLAGS,
@@ -541,7 +541,7 @@ static struct rockchip_clk_branch common_clk_branches[] __initdata = {
 	GATE(0, "pclk_grf", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 4, GFLAGS),
 	GATE(0, "pclk_mipiphy", "pclk_cpu", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(5), 0, GFLAGS),
 
-	GATE(0, "pclk_pmu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 2, GFLAGS),
+	GATE(0, "pclk_pmu", "pclk_pmu_pre", 0, RK2928_CLKGATE_CON(9), 2, GFLAGS),
 	GATE(0, "pclk_pmu_niu", "pclk_pmu_pre", CLK_IGNORE_UNUSED, RK2928_CLKGATE_CON(9), 3, GFLAGS),
 
 	/* PD_MMC */
@@ -577,6 +577,8 @@ static const char *const rk3128_critical_clocks[] __initconst = {
 	"aclk_peri",
 	"hclk_peri",
 	"pclk_peri",
+	"pclk_pmu",
+	"sclk_timer5",
 };
 
 static struct rockchip_clk_provider *__init rk3128_common_clk_init(struct device_node *np)
diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
index e40b775..d8d3cb6 100644
--- a/drivers/clk/samsung/clk-exynos4.c
+++ b/drivers/clk/samsung/clk-exynos4.c
@@ -294,6 +294,18 @@ static const struct samsung_clk_reg_dump src_mask_suspend_e4210[] = {
 #define PLL_ENABLED	(1 << 31)
 #define PLL_LOCKED	(1 << 29)
 
+static void exynos4_clk_enable_pll(u32 reg)
+{
+	u32 pll_con = readl(reg_base + reg);
+	pll_con |= PLL_ENABLED;
+	writel(pll_con, reg_base + reg);
+
+	while (!(pll_con & PLL_LOCKED)) {
+		cpu_relax();
+		pll_con = readl(reg_base + reg);
+	}
+}
+
 static void exynos4_clk_wait_for_pll(u32 reg)
 {
 	u32 pll_con;
@@ -315,6 +327,9 @@ static int exynos4_clk_suspend(void)
 	samsung_clk_save(reg_base, exynos4_save_pll,
 				ARRAY_SIZE(exynos4_clk_pll_regs));
 
+	exynos4_clk_enable_pll(EPLL_CON0);
+	exynos4_clk_enable_pll(VPLL_CON0);
+
 	if (exynos4_soc == EXYNOS4210) {
 		samsung_clk_save(reg_base, exynos4_save_soc,
 					ARRAY_SIZE(exynos4210_clk_save));
diff --git a/drivers/gpu/drm/i915/intel_audio.c b/drivers/gpu/drm/i915/intel_audio.c
index d805b6e..27743be 100644
--- a/drivers/gpu/drm/i915/intel_audio.c
+++ b/drivers/gpu/drm/i915/intel_audio.c
@@ -606,11 +606,6 @@ void intel_audio_codec_enable(struct intel_encoder *intel_encoder,
 			 connector->encoder->base.id,
 			 connector->encoder->name);
 
-	/* ELD Conn_Type */
-	connector->eld[5] &= ~(3 << 2);
-	if (intel_crtc_has_dp_encoder(crtc_state))
-		connector->eld[5] |= (1 << 2);
-
 	connector->eld[6] = drm_av_sync_delay(connector, adjusted_mode) / 2;
 
 	if (dev_priv->display.audio_codec_enable)
diff --git a/drivers/gpu/drm/i915/intel_bios.c b/drivers/gpu/drm/i915/intel_bios.c
index 183e87e..00c6aee 100644
--- a/drivers/gpu/drm/i915/intel_bios.c
+++ b/drivers/gpu/drm/i915/intel_bios.c
@@ -1163,6 +1163,13 @@ static void parse_ddi_port(struct drm_i915_private *dev_priv, enum port port,
 	is_hdmi = is_dvi && (child->common.device_type & DEVICE_TYPE_NOT_HDMI_OUTPUT) == 0;
 	is_edp = is_dp && (child->common.device_type & DEVICE_TYPE_INTERNAL_CONNECTOR);
 
+	if (port == PORT_A && is_dvi) {
+		DRM_DEBUG_KMS("VBT claims port A supports DVI%s, ignoring\n",
+			      is_hdmi ? "/HDMI" : "");
+		is_dvi = false;
+		is_hdmi = false;
+	}
+
 	info->supports_dvi = is_dvi;
 	info->supports_hdmi = is_hdmi;
 	info->supports_dp = is_dp;
diff --git a/drivers/gpu/drm/i915/intel_csr.c b/drivers/gpu/drm/i915/intel_csr.c
index 965988f..92c1f8e 100644
--- a/drivers/gpu/drm/i915/intel_csr.c
+++ b/drivers/gpu/drm/i915/intel_csr.c
@@ -216,7 +216,7 @@ static void gen9_set_dc_state_debugmask(struct drm_i915_private *dev_priv)
 
 	mask = DC_STATE_DEBUG_MASK_MEMORY_UP;
 
-	if (IS_BROXTON(dev_priv))
+	if (IS_GEN9_LP(dev_priv))
 		mask |= DC_STATE_DEBUG_MASK_CORES;
 
 	/* The below bit doesn't need to be cleared ever afterwards */
diff --git a/drivers/gpu/drm/i915/intel_ddi.c b/drivers/gpu/drm/i915/intel_ddi.c
index 4b4fd1f..476681d 100644
--- a/drivers/gpu/drm/i915/intel_ddi.c
+++ b/drivers/gpu/drm/i915/intel_ddi.c
@@ -1655,7 +1655,8 @@ bool intel_ddi_get_hw_state(struct intel_encoder *encoder,
 out:
 	if (ret && IS_GEN9_LP(dev_priv)) {
 		tmp = I915_READ(BXT_PHY_CTL(port));
-		if ((tmp & (BXT_PHY_LANE_POWERDOWN_ACK |
+		if ((tmp & (BXT_PHY_CMNLANE_POWERDOWN_ACK |
+			    BXT_PHY_LANE_POWERDOWN_ACK |
 			    BXT_PHY_LANE_ENABLED)) != BXT_PHY_LANE_ENABLED)
 			DRM_ERROR("Port %c enabled but PHY powered down? "
 				  "(PHY_CTL %08x)\n", port_name(port), tmp);
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 00cd17c..64f7b51 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -12359,7 +12359,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
 	struct drm_crtc *crtc;
 	struct intel_crtc_state *intel_cstate;
-	bool hw_check = intel_state->modeset;
 	u64 put_domains[I915_MAX_PIPES] = {};
 	unsigned crtc_vblank_mask = 0;
 	int i;
@@ -12376,7 +12375,6 @@ static void intel_atomic_commit_tail(struct drm_atomic_state *state)
 
 		if (needs_modeset(new_crtc_state) ||
 		    to_intel_crtc_state(new_crtc_state)->update_pipe) {
-			hw_check = true;
 
 			put_domains[to_intel_crtc(crtc)->pipe] =
 				modeset_get_crtc_power_domains(crtc,
diff --git a/drivers/gpu/drm/i915/intel_dpio_phy.c b/drivers/gpu/drm/i915/intel_dpio_phy.c
index 09b6709..de38d01 100644
--- a/drivers/gpu/drm/i915/intel_dpio_phy.c
+++ b/drivers/gpu/drm/i915/intel_dpio_phy.c
@@ -208,12 +208,6 @@ static const struct bxt_ddi_phy_info glk_ddi_phy_info[] = {
 	},
 };
 
-static u32 bxt_phy_port_mask(const struct bxt_ddi_phy_info *phy_info)
-{
-	return (phy_info->dual_channel * BIT(phy_info->channel[DPIO_CH1].port)) |
-		BIT(phy_info->channel[DPIO_CH0].port);
-}
-
 static const struct bxt_ddi_phy_info *
 bxt_get_phy_list(struct drm_i915_private *dev_priv, int *count)
 {
@@ -313,7 +307,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv,
 			    enum dpio_phy phy)
 {
 	const struct bxt_ddi_phy_info *phy_info;
-	enum port port;
 
 	phy_info = bxt_get_phy_info(dev_priv, phy);
 
@@ -335,19 +328,6 @@ bool bxt_ddi_phy_is_enabled(struct drm_i915_private *dev_priv,
 		return false;
 	}
 
-	for_each_port_masked(port, bxt_phy_port_mask(phy_info)) {
-		u32 tmp = I915_READ(BXT_PHY_CTL(port));
-
-		if (tmp & BXT_PHY_CMNLANE_POWERDOWN_ACK) {
-			DRM_DEBUG_DRIVER("DDI PHY %d powered, but common lane "
-					 "for port %c powered down "
-					 "(PHY_CTL %08x)\n",
-					 phy, port_name(port), tmp);
-
-			return false;
-		}
-	}
-
 	return true;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index 951e834..28a778b 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -30,6 +30,21 @@
 #include "intel_drv.h"
 #include "i915_drv.h"
 
+static void intel_connector_update_eld_conn_type(struct drm_connector *connector)
+{
+	u8 conn_type;
+
+	if (connector->connector_type == DRM_MODE_CONNECTOR_DisplayPort ||
+	    connector->connector_type == DRM_MODE_CONNECTOR_eDP) {
+		conn_type = DRM_ELD_CONN_TYPE_DP;
+	} else {
+		conn_type = DRM_ELD_CONN_TYPE_HDMI;
+	}
+
+	connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] &= ~DRM_ELD_CONN_TYPE_MASK;
+	connector->eld[DRM_ELD_SAD_COUNT_CONN_TYPE] |= conn_type;
+}
+
 /**
  * intel_connector_update_modes - update connector from edid
  * @connector: DRM connector device to use
@@ -44,6 +59,8 @@ int intel_connector_update_modes(struct drm_connector *connector,
 	ret = drm_add_edid_modes(connector, edid);
 	drm_edid_to_eld(connector, edid);
 
+	intel_connector_update_eld_conn_type(connector);
+
 	return ret;
 }
 
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index b66d8e1..b3a087c 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -2782,6 +2782,9 @@ static void cnl_display_core_init(struct drm_i915_private *dev_priv, bool resume
 
 	/* 6. Enable DBUF */
 	gen9_dbuf_enable(dev_priv);
+
+	if (resume && dev_priv->csr.dmc_payload)
+		intel_csr_load_program(dev_priv);
 }
 
 #undef CNL_PROCMON_IDX
diff --git a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
index 9ea6cd5..3cf1a69 100644
--- a/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
+++ b/drivers/gpu/drm/sun4i/sun4i_hdmi_enc.c
@@ -302,26 +302,29 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 	hdmi->mod_clk = devm_clk_get(dev, "mod");
 	if (IS_ERR(hdmi->mod_clk)) {
 		dev_err(dev, "Couldn't get the HDMI mod clock\n");
-		return PTR_ERR(hdmi->mod_clk);
+		ret = PTR_ERR(hdmi->mod_clk);
+		goto err_disable_bus_clk;
 	}
 	clk_prepare_enable(hdmi->mod_clk);
 
 	hdmi->pll0_clk = devm_clk_get(dev, "pll-0");
 	if (IS_ERR(hdmi->pll0_clk)) {
 		dev_err(dev, "Couldn't get the HDMI PLL 0 clock\n");
-		return PTR_ERR(hdmi->pll0_clk);
+		ret = PTR_ERR(hdmi->pll0_clk);
+		goto err_disable_mod_clk;
 	}
 
 	hdmi->pll1_clk = devm_clk_get(dev, "pll-1");
 	if (IS_ERR(hdmi->pll1_clk)) {
 		dev_err(dev, "Couldn't get the HDMI PLL 1 clock\n");
-		return PTR_ERR(hdmi->pll1_clk);
+		ret = PTR_ERR(hdmi->pll1_clk);
+		goto err_disable_mod_clk;
 	}
 
 	ret = sun4i_tmds_create(hdmi);
 	if (ret) {
 		dev_err(dev, "Couldn't create the TMDS clock\n");
-		return ret;
+		goto err_disable_mod_clk;
 	}
 
 	writel(SUN4I_HDMI_CTRL_ENABLE, hdmi->base + SUN4I_HDMI_CTRL_REG);
@@ -362,7 +365,7 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 	ret = sun4i_hdmi_i2c_create(dev, hdmi);
 	if (ret) {
 		dev_err(dev, "Couldn't create the HDMI I2C adapter\n");
-		return ret;
+		goto err_disable_mod_clk;
 	}
 
 	drm_encoder_helper_add(&hdmi->encoder,
@@ -422,6 +425,10 @@ static int sun4i_hdmi_bind(struct device *dev, struct device *master,
 	drm_encoder_cleanup(&hdmi->encoder);
 err_del_i2c_adapter:
 	i2c_del_adapter(hdmi->i2c);
+err_disable_mod_clk:
+	clk_disable_unprepare(hdmi->mod_clk);
+err_disable_bus_clk:
+	clk_disable_unprepare(hdmi->bus_clk);
 	return ret;
 }
 
@@ -434,6 +441,8 @@ static void sun4i_hdmi_unbind(struct device *dev, struct device *master,
 	drm_connector_cleanup(&hdmi->connector);
 	drm_encoder_cleanup(&hdmi->encoder);
 	i2c_del_adapter(hdmi->i2c);
+	clk_disable_unprepare(hdmi->mod_clk);
+	clk_disable_unprepare(hdmi->bus_clk);
 }
 
 static const struct component_ops sun4i_hdmi_ops = {
diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c
index 9c0dbb8..e1be610 100644
--- a/drivers/hwmon/xgene-hwmon.c
+++ b/drivers/hwmon/xgene-hwmon.c
@@ -630,7 +630,7 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 			 sizeof(struct slimpro_resp_msg) * ASYNC_MSG_FIFO_SIZE,
 			 GFP_KERNEL);
 	if (rc)
-		goto out_mbox_free;
+		return -ENOMEM;
 
 	INIT_WORK(&ctx->workq, xgene_hwmon_evt_work);
 
@@ -646,7 +646,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 		if (IS_ERR(ctx->mbox_chan)) {
 			dev_err(&pdev->dev,
 				"SLIMpro mailbox channel request failed\n");
-			return -ENODEV;
+			rc = -ENODEV;
+			goto out_mbox_free;
 		}
 	} else {
 		struct acpi_pcct_hw_reduced *cppc_ss;
@@ -654,7 +655,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 		if (device_property_read_u32(&pdev->dev, "pcc-channel",
 					     &ctx->mbox_idx)) {
 			dev_err(&pdev->dev, "no pcc-channel property\n");
-			return -ENODEV;
+			rc = -ENODEV;
+			goto out_mbox_free;
 		}
 
 		cl->rx_callback = xgene_hwmon_pcc_rx_cb;
@@ -662,7 +664,8 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 		if (IS_ERR(ctx->mbox_chan)) {
 			dev_err(&pdev->dev,
 				"PPC channel request failed\n");
-			return -ENODEV;
+			rc = -ENODEV;
+			goto out_mbox_free;
 		}
 
 		/*
@@ -675,13 +678,13 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 		if (!cppc_ss) {
 			dev_err(&pdev->dev, "PPC subspace not found\n");
 			rc = -ENODEV;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		if (!ctx->mbox_chan->mbox->txdone_irq) {
 			dev_err(&pdev->dev, "PCC IRQ not supported\n");
 			rc = -ENODEV;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		/*
@@ -696,14 +699,14 @@ static int xgene_hwmon_probe(struct platform_device *pdev)
 		} else {
 			dev_err(&pdev->dev, "Failed to get PCC comm region\n");
 			rc = -ENODEV;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		if (!ctx->pcc_comm_addr) {
 			dev_err(&pdev->dev,
 				"Failed to ioremap PCC comm region\n");
 			rc = -ENOMEM;
-			goto out_mbox_free;
+			goto out;
 		}
 
 		/*
diff --git a/drivers/i2c/busses/Kconfig b/drivers/i2c/busses/Kconfig
index c06dce2c..45a3f3ca 100644
--- a/drivers/i2c/busses/Kconfig
+++ b/drivers/i2c/busses/Kconfig
@@ -131,6 +131,7 @@
 	    Gemini Lake (SOC)
 	    Cannon Lake-H (PCH)
 	    Cannon Lake-LP (PCH)
+	    Cedar Fork (PCH)
 
 	  This driver can also be built as a module.  If so, the module
 	  will be called i2c-i801.
diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c
index e114e4e..9e12a53 100644
--- a/drivers/i2c/busses/i2c-i801.c
+++ b/drivers/i2c/busses/i2c-i801.c
@@ -68,6 +68,7 @@
  * Gemini Lake (SOC)		0x31d4	32	hard	yes	yes	yes
  * Cannon Lake-H (PCH)		0xa323	32	hard	yes	yes	yes
  * Cannon Lake-LP (PCH)		0x9da3	32	hard	yes	yes	yes
+ * Cedar Fork (PCH)		0x18df	32	hard	yes	yes	yes
  *
  * Features supported by this driver:
  * Software PEC				no
@@ -204,6 +205,7 @@
 
 /* Older devices have their ID defined in <linux/pci_ids.h> */
 #define PCI_DEVICE_ID_INTEL_BAYTRAIL_SMBUS		0x0f12
+#define PCI_DEVICE_ID_INTEL_CDF_SMBUS			0x18df
 #define PCI_DEVICE_ID_INTEL_DNV_SMBUS			0x19df
 #define PCI_DEVICE_ID_INTEL_COUGARPOINT_SMBUS		0x1c22
 #define PCI_DEVICE_ID_INTEL_PATSBURG_SMBUS		0x1d22
@@ -1025,6 +1027,7 @@ static const struct pci_device_id i801_ids[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BRASWELL_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_H_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_SUNRISEPOINT_LP_SMBUS) },
+	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_CDF_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_DNV_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_BROXTON_SMBUS) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS) },
@@ -1513,6 +1516,7 @@ static int i801_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	case PCI_DEVICE_ID_INTEL_CANNONLAKE_LP_SMBUS:
 	case PCI_DEVICE_ID_INTEL_LEWISBURG_SMBUS:
 	case PCI_DEVICE_ID_INTEL_LEWISBURG_SSKU_SMBUS:
+	case PCI_DEVICE_ID_INTEL_CDF_SMBUS:
 	case PCI_DEVICE_ID_INTEL_DNV_SMBUS:
 	case PCI_DEVICE_ID_INTEL_KABYLAKE_PCH_H_SMBUS:
 		priv->features |= FEATURE_I2C_BLOCK_READ;
diff --git a/drivers/i2c/busses/i2c-sprd.c b/drivers/i2c/busses/i2c-sprd.c
index 22e08ae..25fcc3c 100644
--- a/drivers/i2c/busses/i2c-sprd.c
+++ b/drivers/i2c/busses/i2c-sprd.c
@@ -627,6 +627,7 @@ static const struct dev_pm_ops sprd_i2c_pm_ops = {
 
 static const struct of_device_id sprd_i2c_of_match[] = {
 	{ .compatible = "sprd,sc9860-i2c", },
+	{},
 };
 
 static struct platform_driver sprd_i2c_driver = {
diff --git a/drivers/i2c/busses/i2c-stm32f7.c b/drivers/i2c/busses/i2c-stm32f7.c
index 47c67b0..d4a6e9c 100644
--- a/drivers/i2c/busses/i2c-stm32f7.c
+++ b/drivers/i2c/busses/i2c-stm32f7.c
@@ -215,7 +215,7 @@ struct stm32f7_i2c_dev {
 	unsigned int msg_num;
 	unsigned int msg_id;
 	struct stm32f7_i2c_msg f7_msg;
-	struct stm32f7_i2c_setup *setup;
+	struct stm32f7_i2c_setup setup;
 	struct stm32f7_i2c_timings timing;
 };
 
@@ -265,7 +265,7 @@ static struct stm32f7_i2c_spec i2c_specs[] = {
 	},
 };
 
-struct stm32f7_i2c_setup stm32f7_setup = {
+static const struct stm32f7_i2c_setup stm32f7_setup = {
 	.rise_time = STM32F7_I2C_RISE_TIME_DEFAULT,
 	.fall_time = STM32F7_I2C_FALL_TIME_DEFAULT,
 	.dnf = STM32F7_I2C_DNF_DEFAULT,
@@ -537,7 +537,7 @@ static void stm32f7_i2c_hw_config(struct stm32f7_i2c_dev *i2c_dev)
 	writel_relaxed(timing, i2c_dev->base + STM32F7_I2C_TIMINGR);
 
 	/* Enable I2C */
-	if (i2c_dev->setup->analog_filter)
+	if (i2c_dev->setup.analog_filter)
 		stm32f7_i2c_clr_bits(i2c_dev->base + STM32F7_I2C_CR1,
 				     STM32F7_I2C_CR1_ANFOFF);
 	else
@@ -887,22 +887,19 @@ static int stm32f7_i2c_probe(struct platform_device *pdev)
 	}
 
 	setup = of_device_get_match_data(&pdev->dev);
-	i2c_dev->setup->rise_time = setup->rise_time;
-	i2c_dev->setup->fall_time = setup->fall_time;
-	i2c_dev->setup->dnf = setup->dnf;
-	i2c_dev->setup->analog_filter = setup->analog_filter;
+	i2c_dev->setup = *setup;
 
 	ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-rising-time-ns",
 				       &rise_time);
 	if (!ret)
-		i2c_dev->setup->rise_time = rise_time;
+		i2c_dev->setup.rise_time = rise_time;
 
 	ret = device_property_read_u32(i2c_dev->dev, "i2c-scl-falling-time-ns",
 				       &fall_time);
 	if (!ret)
-		i2c_dev->setup->fall_time = fall_time;
+		i2c_dev->setup.fall_time = fall_time;
 
-	ret = stm32f7_i2c_setup_timing(i2c_dev, i2c_dev->setup);
+	ret = stm32f7_i2c_setup_timing(i2c_dev, &i2c_dev->setup);
 	if (ret)
 		goto clk_free;
 
diff --git a/drivers/ide/ide-probe.c b/drivers/ide/ide-probe.c
index 01b2adf..eaf39e5 100644
--- a/drivers/ide/ide-probe.c
+++ b/drivers/ide/ide-probe.c
@@ -1451,6 +1451,7 @@ int ide_host_register(struct ide_host *host, const struct ide_port_info *d,
 		if (hwif_init(hwif) == 0) {
 			printk(KERN_INFO "%s: failed to initialize IDE "
 					 "interface\n", hwif->name);
+			device_unregister(hwif->portdev);
 			device_unregister(&hwif->gendev);
 			ide_disable_port(hwif);
 			continue;
diff --git a/drivers/ide/ide-scan-pci.c b/drivers/ide/ide-scan-pci.c
index 86aa88a..acf8748 100644
--- a/drivers/ide/ide-scan-pci.c
+++ b/drivers/ide/ide-scan-pci.c
@@ -56,6 +56,7 @@ static int __init ide_scan_pcidev(struct pci_dev *dev)
 {
 	struct list_head *l;
 	struct pci_driver *d;
+	int ret;
 
 	list_for_each(l, &ide_pci_drivers) {
 		d = list_entry(l, struct pci_driver, node);
@@ -63,10 +64,14 @@ static int __init ide_scan_pcidev(struct pci_dev *dev)
 			const struct pci_device_id *id =
 				pci_match_id(d->id_table, dev);
 
-			if (id != NULL && d->probe(dev, id) >= 0) {
-				dev->driver = d;
-				pci_dev_get(dev);
-				return 1;
+			if (id != NULL) {
+				pci_assign_irq(dev);
+				ret = d->probe(dev, id);
+				if (ret >= 0) {
+					dev->driver = d;
+					pci_dev_get(dev);
+					return 1;
+				}
 			}
 		}
 	}
diff --git a/drivers/ide/setup-pci.c b/drivers/ide/setup-pci.c
index 112d2fe..fdc8e81 100644
--- a/drivers/ide/setup-pci.c
+++ b/drivers/ide/setup-pci.c
@@ -179,6 +179,7 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise);
 /**
  *	ide_pci_enable	-	do PCI enables
  *	@dev: PCI device
+ *	@bars: PCI BARs mask
  *	@d: IDE port info
  *
  *	Enable the IDE PCI device. We attempt to enable the device in full
@@ -189,9 +190,10 @@ EXPORT_SYMBOL_GPL(ide_setup_pci_noise);
  *	Returns zero on success or an error code
  */
 
-static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d)
+static int ide_pci_enable(struct pci_dev *dev, int bars,
+			  const struct ide_port_info *d)
 {
-	int ret, bars;
+	int ret;
 
 	if (pci_enable_device(dev)) {
 		ret = pci_enable_device_io(dev);
@@ -216,18 +218,6 @@ static int ide_pci_enable(struct pci_dev *dev, const struct ide_port_info *d)
 		goto out;
 	}
 
-	if (d->host_flags & IDE_HFLAG_SINGLE)
-		bars = (1 << 2) - 1;
-	else
-		bars = (1 << 4) - 1;
-
-	if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) {
-		if (d->host_flags & IDE_HFLAG_CS5520)
-			bars |= (1 << 2);
-		else
-			bars |= (1 << 4);
-	}
-
 	ret = pci_request_selected_regions(dev, bars, d->name);
 	if (ret < 0)
 		printk(KERN_ERR "%s %s: can't reserve resources\n",
@@ -403,6 +393,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d)
 /**
  *	ide_setup_pci_controller	-	set up IDE PCI
  *	@dev: PCI device
+ *	@bars: PCI BARs mask
  *	@d: IDE port info
  *	@noisy: verbose flag
  *
@@ -411,7 +402,7 @@ int ide_hwif_setup_dma(ide_hwif_t *hwif, const struct ide_port_info *d)
  *	and enables it if need be
  */
 
-static int ide_setup_pci_controller(struct pci_dev *dev,
+static int ide_setup_pci_controller(struct pci_dev *dev, int bars,
 				    const struct ide_port_info *d, int noisy)
 {
 	int ret;
@@ -420,7 +411,7 @@ static int ide_setup_pci_controller(struct pci_dev *dev,
 	if (noisy)
 		ide_setup_pci_noise(dev, d);
 
-	ret = ide_pci_enable(dev, d);
+	ret = ide_pci_enable(dev, bars, d);
 	if (ret < 0)
 		goto out;
 
@@ -428,16 +419,20 @@ static int ide_setup_pci_controller(struct pci_dev *dev,
 	if (ret < 0) {
 		printk(KERN_ERR "%s %s: error accessing PCI regs\n",
 			d->name, pci_name(dev));
-		goto out;
+		goto out_free_bars;
 	}
 	if (!(pcicmd & PCI_COMMAND_IO)) {	/* is device disabled? */
 		ret = ide_pci_configure(dev, d);
 		if (ret < 0)
-			goto out;
+			goto out_free_bars;
 		printk(KERN_INFO "%s %s: device enabled (Linux)\n",
 			d->name, pci_name(dev));
 	}
 
+	goto out;
+
+out_free_bars:
+	pci_release_selected_regions(dev, bars);
 out:
 	return ret;
 }
@@ -540,13 +535,28 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2,
 {
 	struct pci_dev *pdev[] = { dev1, dev2 };
 	struct ide_host *host;
-	int ret, i, n_ports = dev2 ? 4 : 2;
+	int ret, i, n_ports = dev2 ? 4 : 2, bars;
 	struct ide_hw hw[4], *hws[] = { NULL, NULL, NULL, NULL };
 
+	if (d->host_flags & IDE_HFLAG_SINGLE)
+		bars = (1 << 2) - 1;
+	else
+		bars = (1 << 4) - 1;
+
+	if ((d->host_flags & IDE_HFLAG_NO_DMA) == 0) {
+		if (d->host_flags & IDE_HFLAG_CS5520)
+			bars |= (1 << 2);
+		else
+			bars |= (1 << 4);
+	}
+
 	for (i = 0; i < n_ports / 2; i++) {
-		ret = ide_setup_pci_controller(pdev[i], d, !i);
-		if (ret < 0)
+		ret = ide_setup_pci_controller(pdev[i], bars, d, !i);
+		if (ret < 0) {
+			if (i == 1)
+				pci_release_selected_regions(pdev[0], bars);
 			goto out;
+		}
 
 		ide_pci_setup_ports(pdev[i], d, &hw[i*2], &hws[i*2]);
 	}
@@ -554,7 +564,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2,
 	host = ide_host_alloc(d, hws, n_ports);
 	if (host == NULL) {
 		ret = -ENOMEM;
-		goto out;
+		goto out_free_bars;
 	}
 
 	host->dev[0] = &dev1->dev;
@@ -576,7 +586,7 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2,
 		 * do_ide_setup_pci_device() on the first device!
 		 */
 		if (ret < 0)
-			goto out;
+			goto out_free_bars;
 
 		/* fixup IRQ */
 		if (ide_pci_is_in_compatibility_mode(pdev[i])) {
@@ -589,6 +599,13 @@ int ide_pci_init_two(struct pci_dev *dev1, struct pci_dev *dev2,
 	ret = ide_host_register(host, d, hws);
 	if (ret)
 		ide_host_free(host);
+	else
+		goto out;
+
+out_free_bars:
+	i = n_ports / 2;
+	while (i--)
+		pci_release_selected_regions(pdev[i], bars);
 out:
 	return ret;
 }
diff --git a/drivers/infiniband/core/iwpm_msg.c b/drivers/infiniband/core/iwpm_msg.c
index 30825bb..8861c05 100644
--- a/drivers/infiniband/core/iwpm_msg.c
+++ b/drivers/infiniband/core/iwpm_msg.c
@@ -100,6 +100,8 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 	if (ret)
 		goto pid_query_error;
 
+	nlmsg_end(skb, nlh);
+
 	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
 		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
 
@@ -170,6 +172,8 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 				&pm_msg->loc_addr, IWPM_NLA_MANAGE_ADDR);
 	if (ret)
 		goto add_mapping_error;
+
+	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
 	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
@@ -246,6 +250,8 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 				&pm_msg->rem_addr, IWPM_NLA_QUERY_REMOTE_ADDR);
 	if (ret)
 		goto query_mapping_error;
+
+	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
 	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
@@ -308,6 +314,8 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 	if (ret)
 		goto remove_mapping_error;
 
+	nlmsg_end(skb, nlh);
+
 	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
diff --git a/drivers/infiniband/core/iwpm_util.c b/drivers/infiniband/core/iwpm_util.c
index c81c559..3c4faad 100644
--- a/drivers/infiniband/core/iwpm_util.c
+++ b/drivers/infiniband/core/iwpm_util.c
@@ -597,6 +597,9 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
 				&mapping_num, IWPM_NLA_MAPINFO_SEND_NUM);
 	if (ret)
 		goto mapinfo_num_error;
+
+	nlmsg_end(skb, nlh);
+
 	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
@@ -678,6 +681,8 @@ int iwpm_send_mapinfo(u8 nl_client, int iwpm_pid)
 			if (ret)
 				goto send_mapping_info_unlock;
 
+			nlmsg_end(skb, nlh);
+
 			iwpm_print_sockaddr(&map_info->local_sockaddr,
 				"send_mapping_info: Local sockaddr:");
 			iwpm_print_sockaddr(&map_info->mapped_sockaddr,
diff --git a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
index d1f5345..42ca534 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_ctrl.c
@@ -48,7 +48,7 @@
  * @wqe: cqp wqe for header
  * @header: header for the cqp wqe
  */
-static inline void i40iw_insert_wqe_hdr(u64 *wqe, u64 header)
+void i40iw_insert_wqe_hdr(u64 *wqe, u64 header)
 {
 	wmb();            /* make sure WQE is populated before polarity is set */
 	set_64bit_val(wqe, 24, header);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_p.h b/drivers/infiniband/hw/i40iw/i40iw_p.h
index e217a12..5498ad0 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_p.h
+++ b/drivers/infiniband/hw/i40iw/i40iw_p.h
@@ -59,6 +59,8 @@ enum i40iw_status_code i40iw_sc_mr_fast_register(struct i40iw_sc_qp *qp,
 						 struct i40iw_fast_reg_stag_info *info,
 						 bool post_sq);
 
+void i40iw_insert_wqe_hdr(u64 *wqe, u64 header);
+
 /* HMC/FPM functions */
 enum i40iw_status_code i40iw_sc_init_iw_hmc(struct i40iw_sc_dev *dev,
 					    u8 hmc_fn_id);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_puda.c b/drivers/infiniband/hw/i40iw/i40iw_puda.c
index c2cab20..59f7067 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_puda.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_puda.c
@@ -123,12 +123,11 @@ static void i40iw_puda_post_recvbuf(struct i40iw_puda_rsrc *rsrc, u32 wqe_idx,
 		get_64bit_val(wqe, 24, &offset24);
 
 	offset24 = (offset24) ? 0 : LS_64(1, I40IWQPSQ_VALID);
-	set_64bit_val(wqe, 24, offset24);
 
 	set_64bit_val(wqe, 0, buf->mem.pa);
 	set_64bit_val(wqe, 8,
 		      LS_64(buf->mem.size, I40IWQPSQ_FRAG_LEN));
-	set_64bit_val(wqe, 24, offset24);
+	i40iw_insert_wqe_hdr(wqe, offset24);
 }
 
 /**
@@ -409,9 +408,7 @@ enum i40iw_status_code i40iw_puda_send(struct i40iw_sc_qp *qp,
 	set_64bit_val(wqe, 8, LS_64(info->len, I40IWQPSQ_FRAG_LEN));
 	set_64bit_val(wqe, 16, header[0]);
 
-	/* Ensure all data is written before writing valid bit */
-	wmb();
-	set_64bit_val(wqe, 24, header[1]);
+	i40iw_insert_wqe_hdr(wqe, header[1]);
 
 	i40iw_debug_buf(qp->dev, I40IW_DEBUG_PUDA, "PUDA SEND WQE", wqe, 32);
 	i40iw_qp_post_wr(&qp->qp_uk);
@@ -539,7 +536,7 @@ static enum i40iw_status_code i40iw_puda_qp_wqe(struct i40iw_sc_dev *dev, struct
 		 LS_64(2, I40IW_CQPSQ_QP_NEXTIWSTATE) |
 		 LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID);
 
-	set_64bit_val(wqe, 24, header);
+	i40iw_insert_wqe_hdr(wqe, header);
 
 	i40iw_debug_buf(cqp->dev, I40IW_DEBUG_PUDA, "PUDA CQE", wqe, 32);
 	i40iw_sc_cqp_post_sq(cqp);
@@ -655,7 +652,7 @@ static enum i40iw_status_code i40iw_puda_cq_wqe(struct i40iw_sc_dev *dev, struct
 	    LS_64(1, I40IW_CQPSQ_CQ_ENCEQEMASK) |
 	    LS_64(1, I40IW_CQPSQ_CQ_CEQIDVALID) |
 	    LS_64(cqp->polarity, I40IW_CQPSQ_WQEVALID);
-	set_64bit_val(wqe, 24, header);
+	i40iw_insert_wqe_hdr(wqe, header);
 
 	i40iw_debug_buf(dev, I40IW_DEBUG_PUDA, "PUDA CQE",
 			wqe, I40IW_CQP_WQE_SIZE * 8);
diff --git a/drivers/infiniband/hw/i40iw/i40iw_verbs.c b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
index 28b3d02..62be0a4 100644
--- a/drivers/infiniband/hw/i40iw/i40iw_verbs.c
+++ b/drivers/infiniband/hw/i40iw/i40iw_verbs.c
@@ -826,12 +826,14 @@ static int i40iw_query_qp(struct ib_qp *ibqp,
 	attr->cap.max_inline_data = I40IW_MAX_INLINE_DATA_SIZE;
 	attr->cap.max_send_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
 	attr->cap.max_recv_sge = I40IW_MAX_WQ_FRAGMENT_COUNT;
+	attr->port_num = 1;
 	init_attr->event_handler = iwqp->ibqp.event_handler;
 	init_attr->qp_context = iwqp->ibqp.qp_context;
 	init_attr->send_cq = iwqp->ibqp.send_cq;
 	init_attr->recv_cq = iwqp->ibqp.recv_cq;
 	init_attr->srq = iwqp->ibqp.srq;
 	init_attr->cap = attr->cap;
+	init_attr->port_num = 1;
 	return 0;
 }
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index d6fbad8..552f7bd 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4174,9 +4174,9 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 err_uar_page:
 	mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar);
 
-err_cnt:
-	mlx5_ib_cleanup_cong_debugfs(dev);
 err_cong:
+	mlx5_ib_cleanup_cong_debugfs(dev);
+err_cnt:
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
 		mlx5_ib_dealloc_counters(dev);
 
diff --git a/drivers/infiniband/hw/qedr/qedr.h b/drivers/infiniband/hw/qedr/qedr.h
index b2bb42e..254083b 100644
--- a/drivers/infiniband/hw/qedr/qedr.h
+++ b/drivers/infiniband/hw/qedr/qedr.h
@@ -387,7 +387,7 @@ struct qedr_qp {
 		u8 wqe_size;
 
 		u8 smac[ETH_ALEN];
-		u16 vlan_id;
+		u16 vlan;
 		int rc;
 	} *rqe_wr_id;
 
diff --git a/drivers/infiniband/hw/qedr/qedr_cm.c b/drivers/infiniband/hw/qedr/qedr_cm.c
index 4689e802..ad896539 100644
--- a/drivers/infiniband/hw/qedr/qedr_cm.c
+++ b/drivers/infiniband/hw/qedr/qedr_cm.c
@@ -105,7 +105,7 @@ void qedr_ll2_complete_rx_packet(void *cxt,
 
 	qp->rqe_wr_id[qp->rq.gsi_cons].rc = data->u.data_length_error ?
 		-EINVAL : 0;
-	qp->rqe_wr_id[qp->rq.gsi_cons].vlan_id = data->vlan;
+	qp->rqe_wr_id[qp->rq.gsi_cons].vlan = data->vlan;
 	/* note: length stands for data length i.e. GRH is excluded */
 	qp->rqe_wr_id[qp->rq.gsi_cons].sg_list[0].length =
 		data->length.data_length;
@@ -694,6 +694,7 @@ int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 	struct qedr_cq *cq = get_qedr_cq(ibcq);
 	struct qedr_qp *qp = dev->gsi_qp;
 	unsigned long flags;
+	u16 vlan_id;
 	int i = 0;
 
 	spin_lock_irqsave(&cq->cq_lock, flags);
@@ -712,9 +713,14 @@ int qedr_gsi_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc)
 		wc[i].wc_flags |= IB_WC_GRH | IB_WC_IP_CSUM_OK;
 		ether_addr_copy(wc[i].smac, qp->rqe_wr_id[qp->rq.cons].smac);
 		wc[i].wc_flags |= IB_WC_WITH_SMAC;
-		if (qp->rqe_wr_id[qp->rq.cons].vlan_id) {
+
+		vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan &
+			  VLAN_VID_MASK;
+		if (vlan_id) {
 			wc[i].wc_flags |= IB_WC_WITH_VLAN;
-			wc[i].vlan_id = qp->rqe_wr_id[qp->rq.cons].vlan_id;
+			wc[i].vlan_id = vlan_id;
+			wc[i].sl = (qp->rqe_wr_id[qp->rq.cons].vlan &
+				    VLAN_PRIO_MASK) >> VLAN_PRIO_SHIFT;
 		}
 
 		qedr_inc_sw_cons(&qp->rq);
diff --git a/drivers/md/bcache/closure.c b/drivers/md/bcache/closure.c
index 7d5286b..1841d03 100644
--- a/drivers/md/bcache/closure.c
+++ b/drivers/md/bcache/closure.c
@@ -64,7 +64,7 @@ EXPORT_SYMBOL(closure_put);
 void __closure_wake_up(struct closure_waitlist *wait_list)
 {
 	struct llist_node *list;
-	struct closure *cl;
+	struct closure *cl, *t;
 	struct llist_node *reverse = NULL;
 
 	list = llist_del_all(&wait_list->list);
@@ -73,7 +73,7 @@ void __closure_wake_up(struct closure_waitlist *wait_list)
 	reverse = llist_reverse_order(list);
 
 	/* Then do the wakeups */
-	llist_for_each_entry(cl, reverse, list) {
+	llist_for_each_entry_safe(cl, t, reverse, list) {
 		closure_set_waiting(cl, 0);
 		closure_sub(cl, CLOSURE_WAITING + 1);
 	}
diff --git a/drivers/misc/cxl/cxllib.c b/drivers/misc/cxl/cxllib.c
index 5dba23c..dc9bc18 100644
--- a/drivers/misc/cxl/cxllib.c
+++ b/drivers/misc/cxl/cxllib.c
@@ -219,8 +219,17 @@ int cxllib_handle_fault(struct mm_struct *mm, u64 addr, u64 size, u64 flags)
 
 	down_read(&mm->mmap_sem);
 
-	for (dar = addr; dar < addr + size; dar += page_size) {
-		if (!vma || dar < vma->vm_start || dar > vma->vm_end) {
+	vma = find_vma(mm, addr);
+	if (!vma) {
+		pr_err("Can't find vma for addr %016llx\n", addr);
+		rc = -EFAULT;
+		goto out;
+	}
+	/* get the size of the pages allocated */
+	page_size = vma_kernel_pagesize(vma);
+
+	for (dar = (addr & ~(page_size - 1)); dar < (addr + size); dar += page_size) {
+		if (dar < vma->vm_start || dar >= vma->vm_end) {
 			vma = find_vma(mm, addr);
 			if (!vma) {
 				pr_err("Can't find vma for addr %016llx\n", addr);
diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c
index 29fc1e6..2ad7b5c 100644
--- a/drivers/mmc/core/block.c
+++ b/drivers/mmc/core/block.c
@@ -1634,8 +1634,6 @@ static void mmc_blk_data_prep(struct mmc_queue *mq, struct mmc_queue_req *mqrq,
 	}
 
 	mqrq->areq.mrq = &brq->mrq;
-
-	mmc_queue_bounce_pre(mqrq);
 }
 
 static void mmc_blk_rw_rq_prep(struct mmc_queue_req *mqrq,
@@ -1829,7 +1827,6 @@ static void mmc_blk_issue_rw_rq(struct mmc_queue *mq, struct request *new_req)
 		brq = &mq_rq->brq;
 		old_req = mmc_queue_req_to_req(mq_rq);
 		type = rq_data_dir(old_req) == READ ? MMC_BLK_READ : MMC_BLK_WRITE;
-		mmc_queue_bounce_post(mq_rq);
 
 		switch (status) {
 		case MMC_BLK_SUCCESS:
diff --git a/drivers/mmc/core/mmc.c b/drivers/mmc/core/mmc.c
index a7eb623..36217ad 100644
--- a/drivers/mmc/core/mmc.c
+++ b/drivers/mmc/core/mmc.c
@@ -1286,6 +1286,23 @@ int mmc_hs400_to_hs200(struct mmc_card *card)
 	return err;
 }
 
+static void mmc_select_driver_type(struct mmc_card *card)
+{
+	int card_drv_type, drive_strength, drv_type;
+
+	card_drv_type = card->ext_csd.raw_driver_strength |
+			mmc_driver_type_mask(0);
+
+	drive_strength = mmc_select_drive_strength(card,
+						   card->ext_csd.hs200_max_dtr,
+						   card_drv_type, &drv_type);
+
+	card->drive_strength = drive_strength;
+
+	if (drv_type)
+		mmc_set_driver_type(card->host, drv_type);
+}
+
 static int mmc_select_hs400es(struct mmc_card *card)
 {
 	struct mmc_host *host = card->host;
@@ -1341,6 +1358,8 @@ static int mmc_select_hs400es(struct mmc_card *card)
 		goto out_err;
 	}
 
+	mmc_select_driver_type(card);
+
 	/* Switch card to HS400 */
 	val = EXT_CSD_TIMING_HS400 |
 	      card->drive_strength << EXT_CSD_DRV_STR_SHIFT;
@@ -1374,23 +1393,6 @@ static int mmc_select_hs400es(struct mmc_card *card)
 	return err;
 }
 
-static void mmc_select_driver_type(struct mmc_card *card)
-{
-	int card_drv_type, drive_strength, drv_type;
-
-	card_drv_type = card->ext_csd.raw_driver_strength |
-			mmc_driver_type_mask(0);
-
-	drive_strength = mmc_select_drive_strength(card,
-						   card->ext_csd.hs200_max_dtr,
-						   card_drv_type, &drv_type);
-
-	card->drive_strength = drive_strength;
-
-	if (drv_type)
-		mmc_set_driver_type(card->host, drv_type);
-}
-
 /*
  * For device supporting HS200 mode, the following sequence
  * should be done before executing the tuning process.
diff --git a/drivers/mmc/core/queue.c b/drivers/mmc/core/queue.c
index 74c663b..0a4e77a 100644
--- a/drivers/mmc/core/queue.c
+++ b/drivers/mmc/core/queue.c
@@ -23,8 +23,6 @@
 #include "core.h"
 #include "card.h"
 
-#define MMC_QUEUE_BOUNCESZ	65536
-
 /*
  * Prepare a MMC request. This just filters out odd stuff.
  */
@@ -150,26 +148,6 @@ static void mmc_queue_setup_discard(struct request_queue *q,
 		queue_flag_set_unlocked(QUEUE_FLAG_SECERASE, q);
 }
 
-static unsigned int mmc_queue_calc_bouncesz(struct mmc_host *host)
-{
-	unsigned int bouncesz = MMC_QUEUE_BOUNCESZ;
-
-	if (host->max_segs != 1 || (host->caps & MMC_CAP_NO_BOUNCE_BUFF))
-		return 0;
-
-	if (bouncesz > host->max_req_size)
-		bouncesz = host->max_req_size;
-	if (bouncesz > host->max_seg_size)
-		bouncesz = host->max_seg_size;
-	if (bouncesz > host->max_blk_count * 512)
-		bouncesz = host->max_blk_count * 512;
-
-	if (bouncesz <= 512)
-		return 0;
-
-	return bouncesz;
-}
-
 /**
  * mmc_init_request() - initialize the MMC-specific per-request data
  * @q: the request queue
@@ -184,26 +162,9 @@ static int mmc_init_request(struct request_queue *q, struct request *req,
 	struct mmc_card *card = mq->card;
 	struct mmc_host *host = card->host;
 
-	if (card->bouncesz) {
-		mq_rq->bounce_buf = kmalloc(card->bouncesz, gfp);
-		if (!mq_rq->bounce_buf)
-			return -ENOMEM;
-		if (card->bouncesz > 512) {
-			mq_rq->sg = mmc_alloc_sg(1, gfp);
-			if (!mq_rq->sg)
-				return -ENOMEM;
-			mq_rq->bounce_sg = mmc_alloc_sg(card->bouncesz / 512,
-							gfp);
-			if (!mq_rq->bounce_sg)
-				return -ENOMEM;
-		}
-	} else {
-		mq_rq->bounce_buf = NULL;
-		mq_rq->bounce_sg = NULL;
-		mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp);
-		if (!mq_rq->sg)
-			return -ENOMEM;
-	}
+	mq_rq->sg = mmc_alloc_sg(host->max_segs, gfp);
+	if (!mq_rq->sg)
+		return -ENOMEM;
 
 	return 0;
 }
@@ -212,13 +173,6 @@ static void mmc_exit_request(struct request_queue *q, struct request *req)
 {
 	struct mmc_queue_req *mq_rq = req_to_mmc_queue_req(req);
 
-	/* It is OK to kfree(NULL) so this will be smooth */
-	kfree(mq_rq->bounce_sg);
-	mq_rq->bounce_sg = NULL;
-
-	kfree(mq_rq->bounce_buf);
-	mq_rq->bounce_buf = NULL;
-
 	kfree(mq_rq->sg);
 	mq_rq->sg = NULL;
 }
@@ -242,12 +196,6 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	if (mmc_dev(host)->dma_mask && *mmc_dev(host)->dma_mask)
 		limit = (u64)dma_max_pfn(mmc_dev(host)) << PAGE_SHIFT;
 
-	/*
-	 * mmc_init_request() depends on card->bouncesz so it must be calculated
-	 * before blk_init_allocated_queue() starts allocating requests.
-	 */
-	card->bouncesz = mmc_queue_calc_bouncesz(host);
-
 	mq->card = card;
 	mq->queue = blk_alloc_queue(GFP_KERNEL);
 	if (!mq->queue)
@@ -271,17 +219,11 @@ int mmc_init_queue(struct mmc_queue *mq, struct mmc_card *card,
 	if (mmc_can_erase(card))
 		mmc_queue_setup_discard(mq->queue, card);
 
-	if (card->bouncesz) {
-		blk_queue_max_hw_sectors(mq->queue, card->bouncesz / 512);
-		blk_queue_max_segments(mq->queue, card->bouncesz / 512);
-		blk_queue_max_segment_size(mq->queue, card->bouncesz);
-	} else {
-		blk_queue_bounce_limit(mq->queue, limit);
-		blk_queue_max_hw_sectors(mq->queue,
-			min(host->max_blk_count, host->max_req_size / 512));
-		blk_queue_max_segments(mq->queue, host->max_segs);
-		blk_queue_max_segment_size(mq->queue, host->max_seg_size);
-	}
+	blk_queue_bounce_limit(mq->queue, limit);
+	blk_queue_max_hw_sectors(mq->queue,
+		min(host->max_blk_count, host->max_req_size / 512));
+	blk_queue_max_segments(mq->queue, host->max_segs);
+	blk_queue_max_segment_size(mq->queue, host->max_seg_size);
 
 	sema_init(&mq->thread_sem, 1);
 
@@ -370,56 +312,7 @@ void mmc_queue_resume(struct mmc_queue *mq)
  */
 unsigned int mmc_queue_map_sg(struct mmc_queue *mq, struct mmc_queue_req *mqrq)
 {
-	unsigned int sg_len;
-	size_t buflen;
-	struct scatterlist *sg;
 	struct request *req = mmc_queue_req_to_req(mqrq);
-	int i;
 
-	if (!mqrq->bounce_buf)
-		return blk_rq_map_sg(mq->queue, req, mqrq->sg);
-
-	sg_len = blk_rq_map_sg(mq->queue, req, mqrq->bounce_sg);
-
-	mqrq->bounce_sg_len = sg_len;
-
-	buflen = 0;
-	for_each_sg(mqrq->bounce_sg, sg, sg_len, i)
-		buflen += sg->length;
-
-	sg_init_one(mqrq->sg, mqrq->bounce_buf, buflen);
-
-	return 1;
-}
-
-/*
- * If writing, bounce the data to the buffer before the request
- * is sent to the host driver
- */
-void mmc_queue_bounce_pre(struct mmc_queue_req *mqrq)
-{
-	if (!mqrq->bounce_buf)
-		return;
-
-	if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != WRITE)
-		return;
-
-	sg_copy_to_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
-		mqrq->bounce_buf, mqrq->sg[0].length);
-}
-
-/*
- * If reading, bounce the data from the buffer after the request
- * has been handled by the host driver
- */
-void mmc_queue_bounce_post(struct mmc_queue_req *mqrq)
-{
-	if (!mqrq->bounce_buf)
-		return;
-
-	if (rq_data_dir(mmc_queue_req_to_req(mqrq)) != READ)
-		return;
-
-	sg_copy_from_buffer(mqrq->bounce_sg, mqrq->bounce_sg_len,
-		mqrq->bounce_buf, mqrq->sg[0].length);
+	return blk_rq_map_sg(mq->queue, req, mqrq->sg);
 }
diff --git a/drivers/mmc/core/queue.h b/drivers/mmc/core/queue.h
index 04fc893..f18d3f6 100644
--- a/drivers/mmc/core/queue.h
+++ b/drivers/mmc/core/queue.h
@@ -49,9 +49,6 @@ enum mmc_drv_op {
 struct mmc_queue_req {
 	struct mmc_blk_request	brq;
 	struct scatterlist	*sg;
-	char			*bounce_buf;
-	struct scatterlist	*bounce_sg;
-	unsigned int		bounce_sg_len;
 	struct mmc_async_req	areq;
 	enum mmc_drv_op		drv_op;
 	int			drv_op_result;
@@ -81,11 +78,8 @@ extern int mmc_init_queue(struct mmc_queue *, struct mmc_card *, spinlock_t *,
 extern void mmc_cleanup_queue(struct mmc_queue *);
 extern void mmc_queue_suspend(struct mmc_queue *);
 extern void mmc_queue_resume(struct mmc_queue *);
-
 extern unsigned int mmc_queue_map_sg(struct mmc_queue *,
 				     struct mmc_queue_req *);
-extern void mmc_queue_bounce_pre(struct mmc_queue_req *);
-extern void mmc_queue_bounce_post(struct mmc_queue_req *);
 
 extern int mmc_access_rpmb(struct mmc_queue *);
 
diff --git a/drivers/mmc/host/cavium.c b/drivers/mmc/host/cavium.c
index 27fb625..fbd29f0 100644
--- a/drivers/mmc/host/cavium.c
+++ b/drivers/mmc/host/cavium.c
@@ -1038,7 +1038,7 @@ int cvm_mmc_of_slot_probe(struct device *dev, struct cvm_mmc_host *host)
 	 */
 	mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED |
 		     MMC_CAP_ERASE | MMC_CAP_CMD23 | MMC_CAP_POWER_OFF_CARD |
-		     MMC_CAP_3_3V_DDR | MMC_CAP_NO_BOUNCE_BUFF;
+		     MMC_CAP_3_3V_DDR;
 
 	if (host->use_sg)
 		mmc->max_segs = 16;
diff --git a/drivers/mmc/host/meson-gx-mmc.c b/drivers/mmc/host/meson-gx-mmc.c
index c885c2d..85745ef 100644
--- a/drivers/mmc/host/meson-gx-mmc.c
+++ b/drivers/mmc/host/meson-gx-mmc.c
@@ -531,8 +531,7 @@ static int meson_mmc_clk_init(struct meson_host *host)
 	div->shift = __ffs(CLK_DIV_MASK);
 	div->width = __builtin_popcountl(CLK_DIV_MASK);
 	div->hw.init = &init;
-	div->flags = (CLK_DIVIDER_ONE_BASED |
-		      CLK_DIVIDER_ROUND_CLOSEST);
+	div->flags = CLK_DIVIDER_ONE_BASED;
 
 	clk = devm_clk_register(host->dev, &div->hw);
 	if (WARN_ON(IS_ERR(clk)))
@@ -717,6 +716,22 @@ static int meson_mmc_clk_phase_tuning(struct mmc_host *mmc, u32 opcode,
 static int meson_mmc_execute_tuning(struct mmc_host *mmc, u32 opcode)
 {
 	struct meson_host *host = mmc_priv(mmc);
+	int ret;
+
+	/*
+	 * If this is the initial tuning, try to get a sane Rx starting
+	 * phase before doing the actual tuning.
+	 */
+	if (!mmc->doing_retune) {
+		ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk);
+
+		if (ret)
+			return ret;
+	}
+
+	ret = meson_mmc_clk_phase_tuning(mmc, opcode, host->tx_clk);
+	if (ret)
+		return ret;
 
 	return meson_mmc_clk_phase_tuning(mmc, opcode, host->rx_clk);
 }
@@ -746,6 +761,11 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	case MMC_POWER_UP:
 		if (!IS_ERR(mmc->supply.vmmc))
 			mmc_regulator_set_ocr(mmc, mmc->supply.vmmc, ios->vdd);
+
+		/* Reset phases */
+		clk_set_phase(host->rx_clk, 0);
+		clk_set_phase(host->tx_clk, 270);
+
 		break;
 
 	case MMC_POWER_ON:
@@ -759,8 +779,6 @@ static void meson_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 				host->vqmmc_enabled = true;
 		}
 
-		/* Reset rx phase */
-		clk_set_phase(host->rx_clk, 0);
 		break;
 	}
 
diff --git a/drivers/mmc/host/pxamci.c b/drivers/mmc/host/pxamci.c
index 59ab194..c763b40 100644
--- a/drivers/mmc/host/pxamci.c
+++ b/drivers/mmc/host/pxamci.c
@@ -702,11 +702,7 @@ static int pxamci_probe(struct platform_device *pdev)
 
 	pxamci_init_ocr(host);
 
-	/*
-	 * This architecture used to disable bounce buffers through its
-	 * defconfig, now it is done at runtime as a host property.
-	 */
-	mmc->caps = MMC_CAP_NO_BOUNCE_BUFF;
+	mmc->caps = 0;
 	host->cmdat = 0;
 	if (!cpu_is_pxa25x()) {
 		mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ;
diff --git a/drivers/mmc/host/sdhci-xenon.c b/drivers/mmc/host/sdhci-xenon.c
index 2eec2e6..0842bbc 100644
--- a/drivers/mmc/host/sdhci-xenon.c
+++ b/drivers/mmc/host/sdhci-xenon.c
@@ -466,6 +466,7 @@ static int xenon_probe(struct platform_device *pdev)
 {
 	struct sdhci_pltfm_host *pltfm_host;
 	struct sdhci_host *host;
+	struct xenon_priv *priv;
 	int err;
 
 	host = sdhci_pltfm_init(pdev, &sdhci_xenon_pdata,
@@ -474,6 +475,7 @@ static int xenon_probe(struct platform_device *pdev)
 		return PTR_ERR(host);
 
 	pltfm_host = sdhci_priv(host);
+	priv = sdhci_pltfm_priv(pltfm_host);
 
 	/*
 	 * Link Xenon specific mmc_host_ops function,
@@ -491,9 +493,20 @@ static int xenon_probe(struct platform_device *pdev)
 	if (err)
 		goto free_pltfm;
 
+	priv->axi_clk = devm_clk_get(&pdev->dev, "axi");
+	if (IS_ERR(priv->axi_clk)) {
+		err = PTR_ERR(priv->axi_clk);
+		if (err == -EPROBE_DEFER)
+			goto err_clk;
+	} else {
+		err = clk_prepare_enable(priv->axi_clk);
+		if (err)
+			goto err_clk;
+	}
+
 	err = mmc_of_parse(host->mmc);
 	if (err)
-		goto err_clk;
+		goto err_clk_axi;
 
 	sdhci_get_of_property(pdev);
 
@@ -502,11 +515,11 @@ static int xenon_probe(struct platform_device *pdev)
 	/* Xenon specific dt parse */
 	err = xenon_probe_dt(pdev);
 	if (err)
-		goto err_clk;
+		goto err_clk_axi;
 
 	err = xenon_sdhc_prepare(host);
 	if (err)
-		goto err_clk;
+		goto err_clk_axi;
 
 	pm_runtime_get_noresume(&pdev->dev);
 	pm_runtime_set_active(&pdev->dev);
@@ -527,6 +540,8 @@ static int xenon_probe(struct platform_device *pdev)
 	pm_runtime_disable(&pdev->dev);
 	pm_runtime_put_noidle(&pdev->dev);
 	xenon_sdhc_unprepare(host);
+err_clk_axi:
+	clk_disable_unprepare(priv->axi_clk);
 err_clk:
 	clk_disable_unprepare(pltfm_host->clk);
 free_pltfm:
@@ -538,6 +553,7 @@ static int xenon_remove(struct platform_device *pdev)
 {
 	struct sdhci_host *host = platform_get_drvdata(pdev);
 	struct sdhci_pltfm_host *pltfm_host = sdhci_priv(host);
+	struct xenon_priv *priv = sdhci_pltfm_priv(pltfm_host);
 
 	pm_runtime_get_sync(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
@@ -546,7 +562,7 @@ static int xenon_remove(struct platform_device *pdev)
 	sdhci_remove_host(host, 0);
 
 	xenon_sdhc_unprepare(host);
-
+	clk_disable_unprepare(priv->axi_clk);
 	clk_disable_unprepare(pltfm_host->clk);
 
 	sdhci_pltfm_free(pdev);
diff --git a/drivers/mmc/host/sdhci-xenon.h b/drivers/mmc/host/sdhci-xenon.h
index 2bc0510..9994995 100644
--- a/drivers/mmc/host/sdhci-xenon.h
+++ b/drivers/mmc/host/sdhci-xenon.h
@@ -83,6 +83,7 @@ struct xenon_priv {
 	unsigned char	bus_width;
 	unsigned char	timing;
 	unsigned int	clock;
+	struct clk      *axi_clk;
 
 	int		phy_type;
 	/*
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index bb2aad0..5a14cc7 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -2136,7 +2136,7 @@ static umode_t nvme_ns_attrs_are_visible(struct kobject *kobj,
 	struct nvme_ns *ns = nvme_get_ns_from_dev(dev);
 
 	if (a == &dev_attr_uuid.attr) {
-		if (uuid_is_null(&ns->uuid) ||
+		if (uuid_is_null(&ns->uuid) &&
 		    !memchr_inv(ns->nguid, 0, sizeof(ns->nguid)))
 			return 0;
 	}
diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index cb73bc8..3f5a04c 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -94,7 +94,7 @@ struct nvme_dev {
 	struct mutex shutdown_lock;
 	bool subsystem;
 	void __iomem *cmb;
-	dma_addr_t cmb_dma_addr;
+	pci_bus_addr_t cmb_bus_addr;
 	u64 cmb_size;
 	u32 cmbsz;
 	u32 cmbloc;
@@ -1226,7 +1226,7 @@ static int nvme_alloc_sq_cmds(struct nvme_dev *dev, struct nvme_queue *nvmeq,
 	if (qid && dev->cmb && use_cmb_sqes && NVME_CMB_SQS(dev->cmbsz)) {
 		unsigned offset = (qid - 1) * roundup(SQ_SIZE(depth),
 						      dev->ctrl.page_size);
-		nvmeq->sq_dma_addr = dev->cmb_dma_addr + offset;
+		nvmeq->sq_dma_addr = dev->cmb_bus_addr + offset;
 		nvmeq->sq_cmds_io = dev->cmb + offset;
 	} else {
 		nvmeq->sq_cmds = dma_alloc_coherent(dev->dev, SQ_SIZE(depth),
@@ -1527,7 +1527,7 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
 	resource_size_t bar_size;
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
 	void __iomem *cmb;
-	dma_addr_t dma_addr;
+	int bar;
 
 	dev->cmbsz = readl(dev->bar + NVME_REG_CMBSZ);
 	if (!(NVME_CMB_SZ(dev->cmbsz)))
@@ -1540,7 +1540,8 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
 	szu = (u64)1 << (12 + 4 * NVME_CMB_SZU(dev->cmbsz));
 	size = szu * NVME_CMB_SZ(dev->cmbsz);
 	offset = szu * NVME_CMB_OFST(dev->cmbloc);
-	bar_size = pci_resource_len(pdev, NVME_CMB_BIR(dev->cmbloc));
+	bar = NVME_CMB_BIR(dev->cmbloc);
+	bar_size = pci_resource_len(pdev, bar);
 
 	if (offset > bar_size)
 		return NULL;
@@ -1553,12 +1554,11 @@ static void __iomem *nvme_map_cmb(struct nvme_dev *dev)
 	if (size > bar_size - offset)
 		size = bar_size - offset;
 
-	dma_addr = pci_resource_start(pdev, NVME_CMB_BIR(dev->cmbloc)) + offset;
-	cmb = ioremap_wc(dma_addr, size);
+	cmb = ioremap_wc(pci_resource_start(pdev, bar) + offset, size);
 	if (!cmb)
 		return NULL;
 
-	dev->cmb_dma_addr = dma_addr;
+	dev->cmb_bus_addr = pci_bus_address(pdev, bar) + offset;
 	dev->cmb_size = size;
 	return cmb;
 }
diff --git a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
index 785fb42..2799a6b 100644
--- a/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
+++ b/drivers/scsi/ibmvscsi_tgt/ibmvscsi_tgt.c
@@ -3767,7 +3767,7 @@ static int ibmvscsis_write_pending(struct se_cmd *se_cmd)
 	 */
 	if ((vscsi->flags & (CLIENT_FAILED | RESPONSE_Q_DOWN))) {
 		pr_err("write_pending failed since: %d\n", vscsi->flags);
-		return 0;
+		return -EIO;
 	}
 
 	rc = srp_transfer_data(cmd, &vio_iu(iue)->srp.cmd, ibmvscsis_rdma,
diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c
index bd4605a..c62e8d11 100644
--- a/drivers/scsi/libiscsi.c
+++ b/drivers/scsi/libiscsi.c
@@ -2851,9 +2851,6 @@ EXPORT_SYMBOL_GPL(iscsi_session_setup);
 /**
  * iscsi_session_teardown - destroy session, host, and cls_session
  * @cls_session: iscsi session
- *
- * The driver must have called iscsi_remove_session before
- * calling this.
  */
 void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 {
@@ -2863,6 +2860,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 
 	iscsi_pool_free(&session->cmdpool);
 
+	iscsi_remove_session(cls_session);
+
 	kfree(session->password);
 	kfree(session->password_in);
 	kfree(session->username);
@@ -2877,7 +2876,8 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session)
 	kfree(session->portal_type);
 	kfree(session->discovery_parent_type);
 
-	iscsi_destroy_session(cls_session);
+	iscsi_free_session(cls_session);
+
 	iscsi_host_dec_session_cnt(shost);
 	module_put(owner);
 }
diff --git a/drivers/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index e7818af..15590a0 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -956,6 +956,9 @@ static int scsi_add_lun(struct scsi_device *sdev, unsigned char *inq_result,
 	if (*bflags & BLIST_NO_DIF)
 		sdev->no_dif = 1;
 
+	if (*bflags & BLIST_UNMAP_LIMIT_WS)
+		sdev->unmap_limit_for_ws = 1;
+
 	sdev->eh_timeout = SCSI_DEFAULT_EH_TIMEOUT;
 
 	if (*bflags & BLIST_TRY_VPD_PAGES)
diff --git a/drivers/scsi/scsi_transport_iscsi.c b/drivers/scsi/scsi_transport_iscsi.c
index 0190aef..7404d26 100644
--- a/drivers/scsi/scsi_transport_iscsi.c
+++ b/drivers/scsi/scsi_transport_iscsi.c
@@ -2211,22 +2211,6 @@ void iscsi_free_session(struct iscsi_cls_session *session)
 EXPORT_SYMBOL_GPL(iscsi_free_session);
 
 /**
- * iscsi_destroy_session - destroy iscsi session
- * @session: iscsi_session
- *
- * Can be called by a LLD or iscsi_transport. There must not be
- * any running connections.
- */
-int iscsi_destroy_session(struct iscsi_cls_session *session)
-{
-	iscsi_remove_session(session);
-	ISCSI_DBG_TRANS_SESSION(session, "Completing session destruction\n");
-	iscsi_free_session(session);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(iscsi_destroy_session);
-
-/**
  * iscsi_create_conn - create iscsi class connection
  * @session: iscsi cls session
  * @dd_size: private driver data size
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index fb9f8b5..d175c5c 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -715,13 +715,21 @@ static void sd_config_discard(struct scsi_disk *sdkp, unsigned int mode)
 		break;
 
 	case SD_LBP_WS16:
-		max_blocks = min_not_zero(sdkp->max_ws_blocks,
-					  (u32)SD_MAX_WS16_BLOCKS);
+		if (sdkp->device->unmap_limit_for_ws)
+			max_blocks = sdkp->max_unmap_blocks;
+		else
+			max_blocks = sdkp->max_ws_blocks;
+
+		max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS16_BLOCKS);
 		break;
 
 	case SD_LBP_WS10:
-		max_blocks = min_not_zero(sdkp->max_ws_blocks,
-					  (u32)SD_MAX_WS10_BLOCKS);
+		if (sdkp->device->unmap_limit_for_ws)
+			max_blocks = sdkp->max_unmap_blocks;
+		else
+			max_blocks = sdkp->max_ws_blocks;
+
+		max_blocks = min_not_zero(max_blocks, (u32)SD_MAX_WS10_BLOCKS);
 		break;
 
 	case SD_LBP_ZERO:
@@ -3099,8 +3107,6 @@ static int sd_revalidate_disk(struct gendisk *disk)
 		sd_read_security(sdkp, buffer);
 	}
 
-	sdkp->first_scan = 0;
-
 	/*
 	 * We now have all cache related info, determine how we deal
 	 * with flush requests.
@@ -3115,7 +3121,7 @@ static int sd_revalidate_disk(struct gendisk *disk)
 	q->limits.max_dev_sectors = logical_to_sectors(sdp, dev_max);
 
 	/*
-	 * Use the device's preferred I/O size for reads and writes
+	 * Determine the device's preferred I/O size for reads and writes
 	 * unless the reported value is unreasonably small, large, or
 	 * garbage.
 	 */
@@ -3129,8 +3135,19 @@ static int sd_revalidate_disk(struct gendisk *disk)
 		rw_max = min_not_zero(logical_to_sectors(sdp, dev_max),
 				      (sector_t)BLK_DEF_MAX_SECTORS);
 
-	/* Combine with controller limits */
-	q->limits.max_sectors = min(rw_max, queue_max_hw_sectors(q));
+	/* Do not exceed controller limit */
+	rw_max = min(rw_max, queue_max_hw_sectors(q));
+
+	/*
+	 * Only update max_sectors if previously unset or if the current value
+	 * exceeds the capabilities of the hardware.
+	 */
+	if (sdkp->first_scan ||
+	    q->limits.max_sectors > q->limits.max_dev_sectors ||
+	    q->limits.max_sectors > q->limits.max_hw_sectors)
+		q->limits.max_sectors = rw_max;
+
+	sdkp->first_scan = 0;
 
 	set_capacity(disk, logical_to_sectors(sdp, sdkp->capacity));
 	sd_config_write_same(sdkp);
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 899ddae..8fc6903 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -722,7 +722,7 @@ struct btrfs_delayed_root;
  * Indicate that a whole-filesystem exclusive operation is running
  * (device replace, resize, device add/delete, balance)
  */
-#define BTRFS_FS_EXCL_OP			14
+#define BTRFS_FS_EXCL_OP			16
 
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 12ab19a..970190c 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2801,7 +2801,7 @@ static int submit_extent_page(unsigned int opf, struct extent_io_tree *tree,
 		}
 	}
 
-	bio = btrfs_bio_alloc(bdev, sector << 9);
+	bio = btrfs_bio_alloc(bdev, (u64)sector << 9);
 	bio_add_page(bio, page, page_size, offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index 84edfc6..f23c820 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -734,12 +734,13 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 			inode = req->r_inode;
 			ihold(inode);
 		} else {
-			/* req->r_dentry is non-null for LSSNAP request.
-			 * fall-thru */
-			WARN_ON_ONCE(!req->r_dentry);
+			/* req->r_dentry is non-null for LSSNAP request */
+			rcu_read_lock();
+			inode = get_nonsnap_parent(req->r_dentry);
+			rcu_read_unlock();
+			dout("__choose_mds using snapdir's parent %p\n", inode);
 		}
-	}
-	if (!inode && req->r_dentry) {
+	} else if (req->r_dentry) {
 		/* ignore race with rename; old or new d_parent is okay */
 		struct dentry *parent;
 		struct inode *dir;
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 1ffc8b4..7fc0b85 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -374,12 +374,10 @@ static int build_snap_context(struct ceph_snap_realm *realm,
 	     realm->ino, realm, snapc, snapc->seq,
 	     (unsigned int) snapc->num_snaps);
 
-	if (realm->cached_context) {
-		ceph_put_snap_context(realm->cached_context);
-		/* queue realm for cap_snap creation */
-		list_add_tail(&realm->dirty_item, dirty_realms);
-	}
+	ceph_put_snap_context(realm->cached_context);
 	realm->cached_context = snapc;
+	/* queue realm for cap_snap creation */
+	list_add_tail(&realm->dirty_item, dirty_realms);
 	return 0;
 
 fail:
diff --git a/fs/namespace.c b/fs/namespace.c
index 54059b1..3b601f1 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -468,7 +468,9 @@ static inline int may_write_real(struct file *file)
 
 	/* File refers to upper, writable layer? */
 	upperdentry = d_real(dentry, NULL, 0, D_REAL_UPPER);
-	if (upperdentry && file_inode(file) == d_inode(upperdentry))
+	if (upperdentry &&
+	    (file_inode(file) == d_inode(upperdentry) ||
+	     file_inode(file) == d_inode(dentry)))
 		return 0;
 
 	/* Lower layer: can't write to real file, sorry... */
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index efebe6c..22880ef 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -218,7 +218,6 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
 static void pnfs_init_server(struct nfs_server *server)
 {
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
-	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 }
 
 #else
@@ -888,6 +887,7 @@ struct nfs_server *nfs_alloc_server(void)
 	ida_init(&server->openowner_id);
 	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
+	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 
 	return server;
 }
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 44c638b..508126e 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -745,7 +745,8 @@ filelayout_free_lseg(struct pnfs_layout_segment *lseg)
 	struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg);
 
 	dprintk("--> %s\n", __func__);
-	nfs4_fl_put_deviceid(fl->dsaddr);
+	if (fl->dsaddr != NULL)
+		nfs4_fl_put_deviceid(fl->dsaddr);
 	/* This assumes a single RW lseg */
 	if (lseg->pls_range.iomode == IOMODE_RW) {
 		struct nfs4_filelayout *flo;
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index dd5d27d..30426c1 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -274,7 +274,7 @@ static struct key *nfs_idmap_request_key(const char *name, size_t namelen,
 	ssize_t ret;
 
 	ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc);
-	if (ret <= 0)
+	if (ret < 0)
 		return ERR_PTR(ret);
 
 	rkey = request_key(&key_type_id_resolver, desc, "");
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 6c61e2b..f90090e 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -8399,8 +8399,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 		lo = NFS_I(inode)->layout;
 		/* If the open stateid was bad, then recover it. */
 		if (!lo || test_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags) ||
-		    nfs4_stateid_match_other(&lgp->args.stateid,
-					&lgp->args.ctx->state->stateid)) {
+		    !nfs4_stateid_match_other(&lgp->args.stateid, &lo->plh_stateid)) {
 			spin_unlock(&inode->i_lock);
 			exception->state = lgp->args.ctx->state;
 			exception->stateid = &lgp->args.stateid;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 37c8af0..14ed979 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1842,8 +1842,8 @@ static void encode_create_session(struct xdr_stream *xdr,
 	 * Assumes OPEN is the biggest non-idempotent compound.
 	 * 2 is the verifier.
 	 */
-	max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE +
-			      RPC_MAX_AUTH_SIZE + 2) * XDR_UNIT;
+	max_resp_sz_cached = (NFS4_dec_open_sz + RPC_REPHDRSIZE + 2)
+				* XDR_UNIT + RPC_MAX_AUTH_SIZE;
 
 	encode_op_hdr(xdr, OP_CREATE_SESSION, decode_create_session_maxsz, hdr);
 	p = reserve_space(xdr, 16 + 2*28 + 20 + clnt->cl_nodelen + 12);
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index aad97b3..c441f93 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -561,10 +561,8 @@ static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
 		c->tmpfile = true;
 		err = ovl_copy_up_locked(c);
 	} else {
-		err = -EIO;
-		if (lock_rename(c->workdir, c->destdir) != NULL) {
-			pr_err("overlayfs: failed to lock workdir+upperdir\n");
-		} else {
+		err = ovl_lock_rename_workdir(c->workdir, c->destdir);
+		if (!err) {
 			err = ovl_copy_up_locked(c);
 			unlock_rename(c->workdir, c->destdir);
 		}
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 3309b19..cc961a3 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -216,26 +216,6 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 	return err;
 }
 
-static int ovl_lock_rename_workdir(struct dentry *workdir,
-				   struct dentry *upperdir)
-{
-	/* Workdir should not be the same as upperdir */
-	if (workdir == upperdir)
-		goto err;
-
-	/* Workdir should not be subdir of upperdir and vice versa */
-	if (lock_rename(workdir, upperdir) != NULL)
-		goto err_unlock;
-
-	return 0;
-
-err_unlock:
-	unlock_rename(workdir, upperdir);
-err:
-	pr_err("overlayfs: failed to lock workdir+upperdir\n");
-	return -EIO;
-}
-
 static struct dentry *ovl_clear_empty(struct dentry *dentry,
 				      struct list_head *list)
 {
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index c3addd1..654bea1 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -506,6 +506,7 @@ static struct dentry *ovl_lookup_index(struct dentry *dentry,
 
 	index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len);
 	if (IS_ERR(index)) {
+		err = PTR_ERR(index);
 		pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n"
 				    "overlayfs: mount with '-o index=off' to disable inodes index.\n",
 				    d_inode(origin)->i_ino, name.len, name.name,
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index d4e8c1a..c706a6f 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -235,6 +235,7 @@ bool ovl_inuse_trylock(struct dentry *dentry);
 void ovl_inuse_unlock(struct dentry *dentry);
 int ovl_nlink_start(struct dentry *dentry, bool *locked);
 void ovl_nlink_end(struct dentry *dentry, bool locked);
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir);
 
 static inline bool ovl_is_impuredir(struct dentry *dentry)
 {
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index 878a750..25d9b5a 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -37,6 +37,9 @@ struct ovl_fs {
 	bool noxattr;
 	/* sb common to all layers */
 	struct super_block *same_sb;
+	/* Did we take the inuse lock? */
+	bool upperdir_locked;
+	bool workdir_locked;
 };
 
 /* private information held for every overlayfs dentry */
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 62e9b22..0f85ee9 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -988,6 +988,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 			 struct path *lowerstack, unsigned int numlower)
 {
 	int err;
+	struct dentry *index = NULL;
 	struct inode *dir = dentry->d_inode;
 	struct path path = { .mnt = mnt, .dentry = dentry };
 	LIST_HEAD(list);
@@ -1007,8 +1008,6 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 
 	inode_lock_nested(dir, I_MUTEX_PARENT);
 	list_for_each_entry(p, &list, l_node) {
-		struct dentry *index;
-
 		if (p->name[0] == '.') {
 			if (p->len == 1)
 				continue;
@@ -1018,6 +1017,7 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 		index = lookup_one_len(p->name, dentry, p->len);
 		if (IS_ERR(index)) {
 			err = PTR_ERR(index);
+			index = NULL;
 			break;
 		}
 		err = ovl_verify_index(index, lowerstack, numlower);
@@ -1029,7 +1029,9 @@ int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
 				break;
 		}
 		dput(index);
+		index = NULL;
 	}
+	dput(index);
 	inode_unlock(dir);
 out:
 	ovl_cache_free(&list);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index fd5ea4f..092d150 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -211,9 +211,10 @@ static void ovl_put_super(struct super_block *sb)
 
 	dput(ufs->indexdir);
 	dput(ufs->workdir);
-	ovl_inuse_unlock(ufs->workbasedir);
+	if (ufs->workdir_locked)
+		ovl_inuse_unlock(ufs->workbasedir);
 	dput(ufs->workbasedir);
-	if (ufs->upper_mnt)
+	if (ufs->upper_mnt && ufs->upperdir_locked)
 		ovl_inuse_unlock(ufs->upper_mnt->mnt_root);
 	mntput(ufs->upper_mnt);
 	for (i = 0; i < ufs->numlower; i++)
@@ -881,9 +882,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			goto out_put_upperpath;
 
 		err = -EBUSY;
-		if (!ovl_inuse_trylock(upperpath.dentry)) {
-			pr_err("overlayfs: upperdir is in-use by another mount\n");
+		if (ovl_inuse_trylock(upperpath.dentry)) {
+			ufs->upperdir_locked = true;
+		} else if (ufs->config.index) {
+			pr_err("overlayfs: upperdir is in-use by another mount, mount with '-o index=off' to override exclusive upperdir protection.\n");
 			goto out_put_upperpath;
+		} else {
+			pr_warn("overlayfs: upperdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
 		}
 
 		err = ovl_mount_dir(ufs->config.workdir, &workpath);
@@ -901,9 +906,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		}
 
 		err = -EBUSY;
-		if (!ovl_inuse_trylock(workpath.dentry)) {
-			pr_err("overlayfs: workdir is in-use by another mount\n");
+		if (ovl_inuse_trylock(workpath.dentry)) {
+			ufs->workdir_locked = true;
+		} else if (ufs->config.index) {
+			pr_err("overlayfs: workdir is in-use by another mount, mount with '-o index=off' to override exclusive workdir protection.\n");
 			goto out_put_workpath;
+		} else {
+			pr_warn("overlayfs: workdir is in-use by another mount, accessing files from both mounts will result in undefined behavior.\n");
 		}
 
 		ufs->workbasedir = workpath.dentry;
@@ -1156,11 +1165,13 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 out_free_lowertmp:
 	kfree(lowertmp);
 out_unlock_workdentry:
-	ovl_inuse_unlock(workpath.dentry);
+	if (ufs->workdir_locked)
+		ovl_inuse_unlock(workpath.dentry);
 out_put_workpath:
 	path_put(&workpath);
 out_unlock_upperdentry:
-	ovl_inuse_unlock(upperpath.dentry);
+	if (ufs->upperdir_locked)
+		ovl_inuse_unlock(upperpath.dentry);
 out_put_upperpath:
 	path_put(&upperpath);
 out_free_config:
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 1177945..b9b239f 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -430,7 +430,7 @@ void ovl_inuse_unlock(struct dentry *dentry)
 	}
 }
 
-/* Called must hold OVL_I(inode)->oi_lock */
+/* Caller must hold OVL_I(inode)->lock */
 static void ovl_cleanup_index(struct dentry *dentry)
 {
 	struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode;
@@ -469,6 +469,9 @@ static void ovl_cleanup_index(struct dentry *dentry)
 	err = PTR_ERR(index);
 	if (!IS_ERR(index))
 		err = ovl_cleanup(dir, index);
+	else
+		index = NULL;
+
 	inode_unlock(dir);
 	if (err)
 		goto fail;
@@ -557,3 +560,22 @@ void ovl_nlink_end(struct dentry *dentry, bool locked)
 		mutex_unlock(&OVL_I(d_inode(dentry))->lock);
 	}
 }
+
+int ovl_lock_rename_workdir(struct dentry *workdir, struct dentry *upperdir)
+{
+	/* Workdir should not be the same as upperdir */
+	if (workdir == upperdir)
+		goto err;
+
+	/* Workdir should not be subdir of upperdir and vice versa */
+	if (lock_rename(workdir, upperdir) != NULL)
+		goto err_unlock;
+
+	return 0;
+
+err_unlock:
+	unlock_rename(workdir, upperdir);
+err:
+	pr_err("overlayfs: failed to lock workdir+upperdir\n");
+	return -EIO;
+}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index bc6c6e1..e9db7fc 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -2122,11 +2122,31 @@ xfs_swap_extents(
 		ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
 		tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
+	}
+
+	/* Swap the cow forks. */
+	if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+		xfs_extnum_t	extnum;
+
+		ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+		ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+
+		extnum = ip->i_cnextents;
+		ip->i_cnextents = tip->i_cnextents;
+		tip->i_cnextents = extnum;
+
 		cowfp = ip->i_cowfp;
 		ip->i_cowfp = tip->i_cowfp;
 		tip->i_cowfp = cowfp;
-		xfs_inode_set_cowblocks_tag(ip);
-		xfs_inode_set_cowblocks_tag(tip);
+
+		if (ip->i_cowfp && ip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(ip);
+		else
+			xfs_inode_clear_cowblocks_tag(ip);
+		if (tip->i_cowfp && tip->i_cnextents)
+			xfs_inode_set_cowblocks_tag(tip);
+		else
+			xfs_inode_clear_cowblocks_tag(tip);
 	}
 
 	xfs_trans_log_inode(tp, ip,  src_log_flags);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 3246815..37e603b 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -736,7 +736,13 @@ xfs_reflink_end_cow(
 	/* If there is a hole at end_fsb - 1 go to the previous extent */
 	if (!xfs_iext_lookup_extent(ip, ifp, end_fsb - 1, &idx, &got) ||
 	    got.br_startoff > end_fsb) {
-		ASSERT(idx > 0);
+		/*
+		 * In case of racing, overlapping AIO writes no COW extents
+		 * might be left by the time I/O completes for the loser of
+		 * the race.  In that case we are done.
+		 */
+		if (idx <= 0)
+			goto out_cancel;
 		xfs_iext_get_extent(ifp, --idx, &got);
 	}
 
@@ -809,6 +815,7 @@ xfs_reflink_end_cow(
 
 out_defer:
 	xfs_defer_cancel(&dfops);
+out_cancel:
 	xfs_trans_cancel(tp);
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out:
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index f3f2d07..9a43763a 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -316,7 +316,7 @@ struct mmc_host {
 #define MMC_CAP_UHS_SDR50	(1 << 18)	/* Host supports UHS SDR50 mode */
 #define MMC_CAP_UHS_SDR104	(1 << 19)	/* Host supports UHS SDR104 mode */
 #define MMC_CAP_UHS_DDR50	(1 << 20)	/* Host supports UHS DDR50 mode */
-#define MMC_CAP_NO_BOUNCE_BUFF	(1 << 21)	/* Disable bounce buffers on host */
+/* (1 << 21) is free for reuse */
 #define MMC_CAP_DRIVER_TYPE_A	(1 << 23)	/* Host supports Driver Type A */
 #define MMC_CAP_DRIVER_TYPE_C	(1 << 24)	/* Host supports Driver Type C */
 #define MMC_CAP_DRIVER_TYPE_D	(1 << 25)	/* Host supports Driver Type D */
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index a36abe2..27e249e 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -12,11 +12,31 @@
 
 #ifdef CONFIG_LOCKUP_DETECTOR
 void lockup_detector_init(void);
+void lockup_detector_soft_poweroff(void);
+void lockup_detector_cleanup(void);
+bool is_hardlockup(void);
+
+extern int watchdog_user_enabled;
+extern int nmi_watchdog_user_enabled;
+extern int soft_watchdog_user_enabled;
+extern int watchdog_thresh;
+extern unsigned long watchdog_enabled;
+
+extern struct cpumask watchdog_cpumask;
+extern unsigned long *watchdog_cpumask_bits;
+#ifdef CONFIG_SMP
+extern int sysctl_softlockup_all_cpu_backtrace;
+extern int sysctl_hardlockup_all_cpu_backtrace;
 #else
-static inline void lockup_detector_init(void)
-{
-}
-#endif
+#define sysctl_softlockup_all_cpu_backtrace 0
+#define sysctl_hardlockup_all_cpu_backtrace 0
+#endif /* !CONFIG_SMP */
+
+#else /* CONFIG_LOCKUP_DETECTOR */
+static inline void lockup_detector_init(void) { }
+static inline void lockup_detector_soft_poweroff(void) { }
+static inline void lockup_detector_cleanup(void) { }
+#endif /* !CONFIG_LOCKUP_DETECTOR */
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 extern void touch_softlockup_watchdog_sched(void);
@@ -24,29 +44,17 @@ extern void touch_softlockup_watchdog(void);
 extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern unsigned int  softlockup_panic;
-extern int soft_watchdog_enabled;
-extern atomic_t watchdog_park_in_progress;
 #else
-static inline void touch_softlockup_watchdog_sched(void)
-{
-}
-static inline void touch_softlockup_watchdog(void)
-{
-}
-static inline void touch_softlockup_watchdog_sync(void)
-{
-}
-static inline void touch_all_softlockup_watchdogs(void)
-{
-}
+static inline void touch_softlockup_watchdog_sched(void) { }
+static inline void touch_softlockup_watchdog(void) { }
+static inline void touch_softlockup_watchdog_sync(void) { }
+static inline void touch_all_softlockup_watchdogs(void) { }
 #endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK
 void reset_hung_task_detector(void);
 #else
-static inline void reset_hung_task_detector(void)
-{
-}
+static inline void reset_hung_task_detector(void) { }
 #endif
 
 /*
@@ -54,12 +62,12 @@ static inline void reset_hung_task_detector(void)
  * 'watchdog_enabled' variable. Each lockup detector has its dedicated bit -
  * bit 0 for the hard lockup detector and bit 1 for the soft lockup detector.
  *
- * 'watchdog_user_enabled', 'nmi_watchdog_enabled' and 'soft_watchdog_enabled'
- * are variables that are only used as an 'interface' between the parameters
- * in /proc/sys/kernel and the internal state bits in 'watchdog_enabled'. The
- * 'watchdog_thresh' variable is handled differently because its value is not
- * boolean, and the lockup detectors are 'suspended' while 'watchdog_thresh'
- * is equal zero.
+ * 'watchdog_user_enabled', 'nmi_watchdog_user_enabled' and
+ * 'soft_watchdog_user_enabled' are variables that are only used as an
+ * 'interface' between the parameters in /proc/sys/kernel and the internal
+ * state bits in 'watchdog_enabled'. The 'watchdog_thresh' variable is
+ * handled differently because its value is not boolean, and the lockup
+ * detectors are 'suspended' while 'watchdog_thresh' is equal zero.
  */
 #define NMI_WATCHDOG_ENABLED_BIT   0
 #define SOFT_WATCHDOG_ENABLED_BIT  1
@@ -73,17 +81,41 @@ extern unsigned int hardlockup_panic;
 static inline void hardlockup_detector_disable(void) {}
 #endif
 
+#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
+# define NMI_WATCHDOG_SYSCTL_PERM	0644
+#else
+# define NMI_WATCHDOG_SYSCTL_PERM	0444
+#endif
+
 #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void arch_touch_nmi_watchdog(void);
+extern void hardlockup_detector_perf_stop(void);
+extern void hardlockup_detector_perf_restart(void);
+extern void hardlockup_detector_perf_disable(void);
+extern void hardlockup_detector_perf_enable(void);
+extern void hardlockup_detector_perf_cleanup(void);
+extern int hardlockup_detector_perf_init(void);
 #else
-#if !defined(CONFIG_HAVE_NMI_WATCHDOG)
+static inline void hardlockup_detector_perf_stop(void) { }
+static inline void hardlockup_detector_perf_restart(void) { }
+static inline void hardlockup_detector_perf_disable(void) { }
+static inline void hardlockup_detector_perf_enable(void) { }
+static inline void hardlockup_detector_perf_cleanup(void) { }
+# if !defined(CONFIG_HAVE_NMI_WATCHDOG)
+static inline int hardlockup_detector_perf_init(void) { return -ENODEV; }
 static inline void arch_touch_nmi_watchdog(void) {}
+# else
+static inline int hardlockup_detector_perf_init(void) { return 0; }
+# endif
 #endif
-#endif
+
+void watchdog_nmi_stop(void);
+void watchdog_nmi_start(void);
+int watchdog_nmi_probe(void);
 
 /**
  * touch_nmi_watchdog - restart NMI watchdog timeout.
- * 
+ *
  * If the architecture supports the NMI watchdog, touch_nmi_watchdog()
  * may be used to reset the timeout - for code which intentionally
  * disables interrupts for a long time. This call is stateless.
@@ -153,22 +185,6 @@ static inline bool trigger_single_cpu_backtrace(int cpu)
 u64 hw_nmi_get_sample_period(int watchdog_thresh);
 #endif
 
-#ifdef CONFIG_LOCKUP_DETECTOR
-extern int nmi_watchdog_enabled;
-extern int watchdog_user_enabled;
-extern int watchdog_thresh;
-extern unsigned long watchdog_enabled;
-extern struct cpumask watchdog_cpumask;
-extern unsigned long *watchdog_cpumask_bits;
-extern int __read_mostly watchdog_suspended;
-#ifdef CONFIG_SMP
-extern int sysctl_softlockup_all_cpu_backtrace;
-extern int sysctl_hardlockup_all_cpu_backtrace;
-#else
-#define sysctl_softlockup_all_cpu_backtrace 0
-#define sysctl_hardlockup_all_cpu_backtrace 0
-#endif
-
 #if defined(CONFIG_HARDLOCKUP_CHECK_TIMESTAMP) && \
     defined(CONFIG_HARDLOCKUP_DETECTOR)
 void watchdog_update_hrtimer_threshold(u64 period);
@@ -176,7 +192,6 @@ void watchdog_update_hrtimer_threshold(u64 period);
 static inline void watchdog_update_hrtimer_threshold(u64 period) { }
 #endif
 
-extern bool is_hardlockup(void);
 struct ctl_table;
 extern int proc_watchdog(struct ctl_table *, int ,
 			 void __user *, size_t *, loff_t *);
@@ -188,18 +203,6 @@ extern int proc_watchdog_thresh(struct ctl_table *, int ,
 				void __user *, size_t *, loff_t *);
 extern int proc_watchdog_cpumask(struct ctl_table *, int,
 				 void __user *, size_t *, loff_t *);
-extern int lockup_detector_suspend(void);
-extern void lockup_detector_resume(void);
-#else
-static inline int lockup_detector_suspend(void)
-{
-	return 0;
-}
-
-static inline void lockup_detector_resume(void)
-{
-}
-#endif
 
 #ifdef CONFIG_HAVE_ACPI_APEI_NMI
 #include <asm/nmi.h>
diff --git a/include/linux/smpboot.h b/include/linux/smpboot.h
index 12910cf..c149aa7 100644
--- a/include/linux/smpboot.h
+++ b/include/linux/smpboot.h
@@ -55,7 +55,7 @@ smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
 }
 
 void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
-int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					 const struct cpumask *);
+void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
+					  const struct cpumask *);
 
 #endif
diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h
index 82e93ee..67c5a9f 100644
--- a/include/scsi/scsi_device.h
+++ b/include/scsi/scsi_device.h
@@ -192,6 +192,7 @@ struct scsi_device {
 	unsigned no_dif:1;	/* T10 PI (DIF) should be disabled */
 	unsigned broken_fua:1;		/* Don't set FUA bit */
 	unsigned lun_in_cdb:1;		/* Store LUN bits in CDB[1] */
+	unsigned unmap_limit_for_ws:1;	/* Use the UNMAP limit for WRITE SAME */
 
 	atomic_t disk_events_disable_depth; /* disable depth for disk events */
 
diff --git a/include/scsi/scsi_devinfo.h b/include/scsi/scsi_devinfo.h
index 9592570..36b0301 100644
--- a/include/scsi/scsi_devinfo.h
+++ b/include/scsi/scsi_devinfo.h
@@ -29,5 +29,6 @@
 #define BLIST_TRY_VPD_PAGES	0x10000000 /* Attempt to read VPD pages */
 #define BLIST_NO_RSOC		0x20000000 /* don't try to issue RSOC */
 #define BLIST_MAX_1024		0x40000000 /* maximum 1024 sector cdb length */
+#define BLIST_UNMAP_LIMIT_WS	0x80000000 /* Use UNMAP limit for WRITE SAME */
 
 #endif
diff --git a/include/scsi/scsi_transport_iscsi.h b/include/scsi/scsi_transport_iscsi.h
index 6183d20..b266d2a 100644
--- a/include/scsi/scsi_transport_iscsi.h
+++ b/include/scsi/scsi_transport_iscsi.h
@@ -434,7 +434,6 @@ extern struct iscsi_cls_session *iscsi_create_session(struct Scsi_Host *shost,
 						unsigned int target_id);
 extern void iscsi_remove_session(struct iscsi_cls_session *session);
 extern void iscsi_free_session(struct iscsi_cls_session *session);
-extern int iscsi_destroy_session(struct iscsi_cls_session *session);
 extern struct iscsi_cls_conn *iscsi_create_conn(struct iscsi_cls_session *sess,
 						int dd_size, uint32_t cid);
 extern int iscsi_destroy_conn(struct iscsi_cls_conn *conn);
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 8de11a2..d851df2 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -24,6 +24,7 @@
 #include <linux/lockdep.h>
 #include <linux/tick.h>
 #include <linux/irq.h>
+#include <linux/nmi.h>
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
@@ -897,6 +898,11 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 
 out:
 	cpus_write_unlock();
+	/*
+	 * Do post unplug cleanup. This is still protected against
+	 * concurrent CPU hotplug via cpu_add_remove_lock.
+	 */
+	lockup_detector_cleanup();
 	return ret;
 }
 
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index 1d71c05..5043e74 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -344,39 +344,30 @@ EXPORT_SYMBOL_GPL(smpboot_unregister_percpu_thread);
  * by the client, but only by calling this function.
  * This function can only be called on a registered smp_hotplug_thread.
  */
-int smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
-					 const struct cpumask *new)
+void smpboot_update_cpumask_percpu_thread(struct smp_hotplug_thread *plug_thread,
+					  const struct cpumask *new)
 {
 	struct cpumask *old = plug_thread->cpumask;
-	cpumask_var_t tmp;
+	static struct cpumask tmp;
 	unsigned int cpu;
 
-	if (!alloc_cpumask_var(&tmp, GFP_KERNEL))
-		return -ENOMEM;
-
-	get_online_cpus();
+	lockdep_assert_cpus_held();
 	mutex_lock(&smpboot_threads_lock);
 
 	/* Park threads that were exclusively enabled on the old mask. */
-	cpumask_andnot(tmp, old, new);
-	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+	cpumask_andnot(&tmp, old, new);
+	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
 		smpboot_park_thread(plug_thread, cpu);
 
 	/* Unpark threads that are exclusively enabled on the new mask. */
-	cpumask_andnot(tmp, new, old);
-	for_each_cpu_and(cpu, tmp, cpu_online_mask)
+	cpumask_andnot(&tmp, new, old);
+	for_each_cpu_and(cpu, &tmp, cpu_online_mask)
 		smpboot_unpark_thread(plug_thread, cpu);
 
 	cpumask_copy(old, new);
 
 	mutex_unlock(&smpboot_threads_lock);
-	put_online_cpus();
-
-	free_cpumask_var(tmp);
-
-	return 0;
 }
-EXPORT_SYMBOL_GPL(smpboot_update_cpumask_percpu_thread);
 
 static DEFINE_PER_CPU(atomic_t, cpu_hotplug_state) = ATOMIC_INIT(CPU_POST_DEAD);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4da9e62..d9c31bc 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -872,9 +872,9 @@ static struct ctl_table kern_table[] = {
 #if defined(CONFIG_LOCKUP_DETECTOR)
 	{
 		.procname       = "watchdog",
-		.data           = &watchdog_user_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler   = proc_watchdog,
 		.extra1		= &zero,
 		.extra2		= &one,
@@ -890,16 +890,12 @@ static struct ctl_table kern_table[] = {
 	},
 	{
 		.procname       = "nmi_watchdog",
-		.data           = &nmi_watchdog_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &nmi_watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= NMI_WATCHDOG_SYSCTL_PERM,
 		.proc_handler   = proc_nmi_watchdog,
 		.extra1		= &zero,
-#if defined(CONFIG_HAVE_NMI_WATCHDOG) || defined(CONFIG_HARDLOCKUP_DETECTOR)
 		.extra2		= &one,
-#else
-		.extra2		= &zero,
-#endif
 	},
 	{
 		.procname	= "watchdog_cpumask",
@@ -911,9 +907,9 @@ static struct ctl_table kern_table[] = {
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 	{
 		.procname       = "soft_watchdog",
-		.data           = &soft_watchdog_enabled,
-		.maxlen         = sizeof (int),
-		.mode           = 0644,
+		.data		= &soft_watchdog_user_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
 		.proc_handler   = proc_soft_watchdog,
 		.extra1		= &zero,
 		.extra2		= &one,
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f5d5202..6bcb854 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -29,20 +29,29 @@
 #include <linux/kvm_para.h>
 #include <linux/kthread.h>
 
-/* Watchdog configuration */
-static DEFINE_MUTEX(watchdog_proc_mutex);
-
-int __read_mostly nmi_watchdog_enabled;
+static DEFINE_MUTEX(watchdog_mutex);
 
 #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG)
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED |
-						NMI_WATCHDOG_ENABLED;
+# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED)
+# define NMI_WATCHDOG_DEFAULT	1
 #else
-unsigned long __read_mostly watchdog_enabled = SOFT_WATCHDOG_ENABLED;
+# define WATCHDOG_DEFAULT	(SOFT_WATCHDOG_ENABLED)
+# define NMI_WATCHDOG_DEFAULT	0
 #endif
 
+unsigned long __read_mostly watchdog_enabled;
+int __read_mostly watchdog_user_enabled = 1;
+int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT;
+int __read_mostly soft_watchdog_user_enabled = 1;
+int __read_mostly watchdog_thresh = 10;
+int __read_mostly nmi_watchdog_available;
+
+struct cpumask watchdog_allowed_mask __read_mostly;
+
+struct cpumask watchdog_cpumask __read_mostly;
+unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
+
 #ifdef CONFIG_HARDLOCKUP_DETECTOR
-/* boot commands */
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:
  */
@@ -56,9 +65,9 @@ unsigned int __read_mostly hardlockup_panic =
  * kernel command line parameters are parsed, because otherwise it is not
  * possible to override this in hardlockup_panic_setup().
  */
-void hardlockup_detector_disable(void)
+void __init hardlockup_detector_disable(void)
 {
-	watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+	nmi_watchdog_user_enabled = 0;
 }
 
 static int __init hardlockup_panic_setup(char *str)
@@ -68,48 +77,24 @@ static int __init hardlockup_panic_setup(char *str)
 	else if (!strncmp(str, "nopanic", 7))
 		hardlockup_panic = 0;
 	else if (!strncmp(str, "0", 1))
-		watchdog_enabled &= ~NMI_WATCHDOG_ENABLED;
+		nmi_watchdog_user_enabled = 0;
 	else if (!strncmp(str, "1", 1))
-		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+		nmi_watchdog_user_enabled = 1;
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
 
-#endif
-
-#ifdef CONFIG_SOFTLOCKUP_DETECTOR
-int __read_mostly soft_watchdog_enabled;
-#endif
-
-int __read_mostly watchdog_user_enabled;
-int __read_mostly watchdog_thresh = 10;
-
-#ifdef CONFIG_SMP
-int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+# ifdef CONFIG_SMP
 int __read_mostly sysctl_hardlockup_all_cpu_backtrace;
-#endif
-struct cpumask watchdog_cpumask __read_mostly;
-unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask);
 
-/*
- * The 'watchdog_running' variable is set to 1 when the watchdog threads
- * are registered/started and is set to 0 when the watchdog threads are
- * unregistered/stopped, so it is an indicator whether the threads exist.
- */
-static int __read_mostly watchdog_running;
-/*
- * If a subsystem has a need to deactivate the watchdog temporarily, it
- * can use the suspend/resume interface to achieve this. The content of
- * the 'watchdog_suspended' variable reflects this state. Existing threads
- * are parked/unparked by the lockup_detector_{suspend|resume} functions
- * (see comment blocks pertaining to those functions for further details).
- *
- * 'watchdog_suspended' also prevents threads from being registered/started
- * or unregistered/stopped via parameters in /proc/sys/kernel, so the state
- * of 'watchdog_running' cannot change while the watchdog is deactivated
- * temporarily (see related code in 'proc' handlers).
- */
-int __read_mostly watchdog_suspended;
+static int __init hardlockup_all_cpu_backtrace_setup(char *str)
+{
+	sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
+	return 1;
+}
+__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
+# endif /* CONFIG_SMP */
+#endif /* CONFIG_HARDLOCKUP_DETECTOR */
 
 /*
  * These functions can be overridden if an architecture implements its
@@ -121,36 +106,68 @@ int __read_mostly watchdog_suspended;
  */
 int __weak watchdog_nmi_enable(unsigned int cpu)
 {
+	hardlockup_detector_perf_enable();
 	return 0;
 }
+
 void __weak watchdog_nmi_disable(unsigned int cpu)
 {
+	hardlockup_detector_perf_disable();
 }
 
-/*
- * watchdog_nmi_reconfigure can be implemented to be notified after any
- * watchdog configuration change. The arch hardlockup watchdog should
- * respond to the following variables:
- * - nmi_watchdog_enabled
+/* Return 0, if a NMI watchdog is available. Error code otherwise */
+int __weak __init watchdog_nmi_probe(void)
+{
+	return hardlockup_detector_perf_init();
+}
+
+/**
+ * watchdog_nmi_stop - Stop the watchdog for reconfiguration
+ *
+ * The reconfiguration steps are:
+ * watchdog_nmi_stop();
+ * update_variables();
+ * watchdog_nmi_start();
+ */
+void __weak watchdog_nmi_stop(void) { }
+
+/**
+ * watchdog_nmi_start - Start the watchdog after reconfiguration
+ *
+ * Counterpart to watchdog_nmi_stop().
+ *
+ * The following variables have been updated in update_variables() and
+ * contain the currently valid configuration:
+ * - watchdog_enabled
  * - watchdog_thresh
  * - watchdog_cpumask
- * - sysctl_hardlockup_all_cpu_backtrace
- * - hardlockup_panic
- * - watchdog_suspended
  */
-void __weak watchdog_nmi_reconfigure(void)
-{
-}
+void __weak watchdog_nmi_start(void) { }
 
+/**
+ * lockup_detector_update_enable - Update the sysctl enable bit
+ *
+ * Caller needs to make sure that the NMI/perf watchdogs are off, so this
+ * can't race with watchdog_nmi_disable().
+ */
+static void lockup_detector_update_enable(void)
+{
+	watchdog_enabled = 0;
+	if (!watchdog_user_enabled)
+		return;
+	if (nmi_watchdog_available && nmi_watchdog_user_enabled)
+		watchdog_enabled |= NMI_WATCHDOG_ENABLED;
+	if (soft_watchdog_user_enabled)
+		watchdog_enabled |= SOFT_WATCHDOG_ENABLED;
+}
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
 
-/* Helper for online, unparked cpus. */
-#define for_each_watchdog_cpu(cpu) \
-	for_each_cpu_and((cpu), cpu_online_mask, &watchdog_cpumask)
+/* Global variables, exported for sysctl */
+unsigned int __read_mostly softlockup_panic =
+			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
 
-atomic_t watchdog_park_in_progress = ATOMIC_INIT(0);
-
+static bool softlockup_threads_initialized __read_mostly;
 static u64 __read_mostly sample_period;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -164,49 +181,39 @@ static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved);
 static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static unsigned long soft_lockup_nmi_warn;
 
-unsigned int __read_mostly softlockup_panic =
-			CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE;
-
 static int __init softlockup_panic_setup(char *str)
 {
 	softlockup_panic = simple_strtoul(str, NULL, 0);
-
 	return 1;
 }
 __setup("softlockup_panic=", softlockup_panic_setup);
 
 static int __init nowatchdog_setup(char *str)
 {
-	watchdog_enabled = 0;
+	watchdog_user_enabled = 0;
 	return 1;
 }
 __setup("nowatchdog", nowatchdog_setup);
 
 static int __init nosoftlockup_setup(char *str)
 {
-	watchdog_enabled &= ~SOFT_WATCHDOG_ENABLED;
+	soft_watchdog_user_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);
 
 #ifdef CONFIG_SMP
+int __read_mostly sysctl_softlockup_all_cpu_backtrace;
+
 static int __init softlockup_all_cpu_backtrace_setup(char *str)
 {
-	sysctl_softlockup_all_cpu_backtrace =
-		!!simple_strtol(str, NULL, 0);
+	sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0);
 	return 1;
 }
 __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup);
-#ifdef CONFIG_HARDLOCKUP_DETECTOR
-static int __init hardlockup_all_cpu_backtrace_setup(char *str)
-{
-	sysctl_hardlockup_all_cpu_backtrace =
-		!!simple_strtol(str, NULL, 0);
-	return 1;
-}
-__setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup);
 #endif
-#endif
+
+static void __lockup_detector_cleanup(void);
 
 /*
  * Hard-lockup warnings should be triggered after just a few seconds. Soft-
@@ -278,11 +285,15 @@ void touch_all_softlockup_watchdogs(void)
 	int cpu;
 
 	/*
-	 * this is done lockless
-	 * do we care if a 0 races with a timestamp?
-	 * all it means is the softlock check starts one cycle later
+	 * watchdog_mutex cannpt be taken here, as this might be called
+	 * from (soft)interrupt context, so the access to
+	 * watchdog_allowed_cpumask might race with a concurrent update.
+	 *
+	 * The watchdog time stamp can race against a concurrent real
+	 * update as well, the only side effect might be a cycle delay for
+	 * the softlockup check.
 	 */
-	for_each_watchdog_cpu(cpu)
+	for_each_cpu(cpu, &watchdog_allowed_mask)
 		per_cpu(watchdog_touch_ts, cpu) = 0;
 	wq_watchdog_touch(-1);
 }
@@ -322,9 +333,6 @@ static void watchdog_interrupt_count(void)
 	__this_cpu_inc(hrtimer_interrupts);
 }
 
-static int watchdog_enable_all_cpus(void);
-static void watchdog_disable_all_cpus(void);
-
 /* watchdog kicker functions */
 static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 {
@@ -333,7 +341,7 @@ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer)
 	int duration;
 	int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace;
 
-	if (atomic_read(&watchdog_park_in_progress) != 0)
+	if (!watchdog_enabled)
 		return HRTIMER_NORESTART;
 
 	/* kick the hardlockup detector */
@@ -447,32 +455,38 @@ static void watchdog_set_prio(unsigned int policy, unsigned int prio)
 
 static void watchdog_enable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
-	/* kick off the timer for the hardlockup detector */
+	/*
+	 * Start the timer first to prevent the NMI watchdog triggering
+	 * before the timer has a chance to fire.
+	 */
 	hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
 	hrtimer->function = watchdog_timer_fn;
-
-	/* Enable the perf event */
-	watchdog_nmi_enable(cpu);
-
-	/* done here because hrtimer_start can only pin to smp_processor_id() */
 	hrtimer_start(hrtimer, ns_to_ktime(sample_period),
 		      HRTIMER_MODE_REL_PINNED);
 
-	/* initialize timestamp */
-	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
+	/* Initialize timestamp */
 	__touch_watchdog();
+	/* Enable the perf event */
+	if (watchdog_enabled & NMI_WATCHDOG_ENABLED)
+		watchdog_nmi_enable(cpu);
+
+	watchdog_set_prio(SCHED_FIFO, MAX_RT_PRIO - 1);
 }
 
 static void watchdog_disable(unsigned int cpu)
 {
-	struct hrtimer *hrtimer = raw_cpu_ptr(&watchdog_hrtimer);
+	struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer);
 
 	watchdog_set_prio(SCHED_NORMAL, 0);
-	hrtimer_cancel(hrtimer);
-	/* disable the perf event */
+	/*
+	 * Disable the perf event first. That prevents that a large delay
+	 * between disabling the timer and disabling the perf event causes
+	 * the perf NMI to detect a false positive.
+	 */
 	watchdog_nmi_disable(cpu);
+	hrtimer_cancel(hrtimer);
 }
 
 static void watchdog_cleanup(unsigned int cpu, bool online)
@@ -499,21 +513,6 @@ static void watchdog(unsigned int cpu)
 	__this_cpu_write(soft_lockup_hrtimer_cnt,
 			 __this_cpu_read(hrtimer_interrupts));
 	__touch_watchdog();
-
-	/*
-	 * watchdog_nmi_enable() clears the NMI_WATCHDOG_ENABLED bit in the
-	 * failure path. Check for failures that can occur asynchronously -
-	 * for example, when CPUs are on-lined - and shut down the hardware
-	 * perf event on each CPU accordingly.
-	 *
-	 * The only non-obvious place this bit can be cleared is through
-	 * watchdog_nmi_enable(), so a pr_info() is placed there.  Placing a
-	 * pr_info here would be too noisy as it would result in a message
-	 * every few seconds if the hardlockup was disabled but the softlockup
-	 * enabled.
-	 */
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		watchdog_nmi_disable(cpu);
 }
 
 static struct smp_hotplug_thread watchdog_threads = {
@@ -527,295 +526,174 @@ static struct smp_hotplug_thread watchdog_threads = {
 	.unpark			= watchdog_enable,
 };
 
-/*
- * park all watchdog threads that are specified in 'watchdog_cpumask'
- *
- * This function returns an error if kthread_park() of a watchdog thread
- * fails. In this situation, the watchdog threads of some CPUs can already
- * be parked and the watchdog threads of other CPUs can still be runnable.
- * Callers are expected to handle this special condition as appropriate in
- * their context.
- *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
- */
-static int watchdog_park_threads(void)
+static void softlockup_update_smpboot_threads(void)
 {
-	int cpu, ret = 0;
+	lockdep_assert_held(&watchdog_mutex);
 
-	atomic_set(&watchdog_park_in_progress, 1);
+	if (!softlockup_threads_initialized)
+		return;
 
-	for_each_watchdog_cpu(cpu) {
-		ret = kthread_park(per_cpu(softlockup_watchdog, cpu));
-		if (ret)
-			break;
-	}
+	smpboot_update_cpumask_percpu_thread(&watchdog_threads,
+					     &watchdog_allowed_mask);
+}
 
-	atomic_set(&watchdog_park_in_progress, 0);
+/* Temporarily park all watchdog threads */
+static void softlockup_park_all_threads(void)
+{
+	cpumask_clear(&watchdog_allowed_mask);
+	softlockup_update_smpboot_threads();
+}
 
-	return ret;
+/* Unpark enabled threads */
+static void softlockup_unpark_threads(void)
+{
+	cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask);
+	softlockup_update_smpboot_threads();
+}
+
+static void lockup_detector_reconfigure(void)
+{
+	cpus_read_lock();
+	watchdog_nmi_stop();
+	softlockup_park_all_threads();
+	set_sample_period();
+	lockup_detector_update_enable();
+	if (watchdog_enabled && watchdog_thresh)
+		softlockup_unpark_threads();
+	watchdog_nmi_start();
+	cpus_read_unlock();
+	/*
+	 * Must be called outside the cpus locked section to prevent
+	 * recursive locking in the perf code.
+	 */
+	__lockup_detector_cleanup();
 }
 
 /*
- * unpark all watchdog threads that are specified in 'watchdog_cpumask'
+ * Create the watchdog thread infrastructure and configure the detector(s).
  *
- * This function may only be called in a context that is protected against
- * races with CPU hotplug - for example, via get_online_cpus().
+ * The threads are not unparked as watchdog_allowed_mask is empty.  When
+ * the threads are sucessfully initialized, take the proper locks and
+ * unpark the threads in the watchdog_cpumask if the watchdog is enabled.
  */
-static void watchdog_unpark_threads(void)
-{
-	int cpu;
-
-	for_each_watchdog_cpu(cpu)
-		kthread_unpark(per_cpu(softlockup_watchdog, cpu));
-}
-
-static int update_watchdog_all_cpus(void)
+static __init void lockup_detector_setup(void)
 {
 	int ret;
 
-	ret = watchdog_park_threads();
-	if (ret)
-		return ret;
-
-	watchdog_unpark_threads();
-
-	return 0;
-}
-
-static int watchdog_enable_all_cpus(void)
-{
-	int err = 0;
-
-	if (!watchdog_running) {
-		err = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
-							     &watchdog_cpumask);
-		if (err)
-			pr_err("Failed to create watchdog threads, disabled\n");
-		else
-			watchdog_running = 1;
-	} else {
-		/*
-		 * Enable/disable the lockup detectors or
-		 * change the sample period 'on the fly'.
-		 */
-		err = update_watchdog_all_cpus();
-
-		if (err) {
-			watchdog_disable_all_cpus();
-			pr_err("Failed to update lockup detectors, disabled\n");
-		}
-	}
-
-	if (err)
-		watchdog_enabled = 0;
-
-	return err;
-}
-
-static void watchdog_disable_all_cpus(void)
-{
-	if (watchdog_running) {
-		watchdog_running = 0;
-		smpboot_unregister_percpu_thread(&watchdog_threads);
-	}
-}
-
-#ifdef CONFIG_SYSCTL
-static int watchdog_update_cpus(void)
-{
-	return smpboot_update_cpumask_percpu_thread(
-		    &watchdog_threads, &watchdog_cpumask);
-}
-#endif
-
-#else /* SOFTLOCKUP */
-static int watchdog_park_threads(void)
-{
-	return 0;
-}
-
-static void watchdog_unpark_threads(void)
-{
-}
-
-static int watchdog_enable_all_cpus(void)
-{
-	return 0;
-}
-
-static void watchdog_disable_all_cpus(void)
-{
-}
-
-#ifdef CONFIG_SYSCTL
-static int watchdog_update_cpus(void)
-{
-	return 0;
-}
-#endif
-
-static void set_sample_period(void)
-{
-}
-#endif /* SOFTLOCKUP */
-
-/*
- * Suspend the hard and soft lockup detector by parking the watchdog threads.
- */
-int lockup_detector_suspend(void)
-{
-	int ret = 0;
-
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
 	/*
-	 * Multiple suspend requests can be active in parallel (counted by
-	 * the 'watchdog_suspended' variable). If the watchdog threads are
-	 * running, the first caller takes care that they will be parked.
-	 * The state of 'watchdog_running' cannot change while a suspend
-	 * request is active (see related code in 'proc' handlers).
+	 * If sysctl is off and watchdog got disabled on the command line,
+	 * nothing to do here.
 	 */
-	if (watchdog_running && !watchdog_suspended)
-		ret = watchdog_park_threads();
+	lockup_detector_update_enable();
 
-	if (ret == 0)
-		watchdog_suspended++;
-	else {
-		watchdog_disable_all_cpus();
-		pr_err("Failed to suspend lockup detectors, disabled\n");
-		watchdog_enabled = 0;
+	if (!IS_ENABLED(CONFIG_SYSCTL) &&
+	    !(watchdog_enabled && watchdog_thresh))
+		return;
+
+	ret = smpboot_register_percpu_thread_cpumask(&watchdog_threads,
+						     &watchdog_allowed_mask);
+	if (ret) {
+		pr_err("Failed to initialize soft lockup detector threads\n");
+		return;
 	}
 
-	watchdog_nmi_reconfigure();
-
-	mutex_unlock(&watchdog_proc_mutex);
-
-	return ret;
+	mutex_lock(&watchdog_mutex);
+	softlockup_threads_initialized = true;
+	lockup_detector_reconfigure();
+	mutex_unlock(&watchdog_mutex);
 }
 
-/*
- * Resume the hard and soft lockup detector by unparking the watchdog threads.
- */
-void lockup_detector_resume(void)
+#else /* CONFIG_SOFTLOCKUP_DETECTOR */
+static inline int watchdog_park_threads(void) { return 0; }
+static inline void watchdog_unpark_threads(void) { }
+static inline int watchdog_enable_all_cpus(void) { return 0; }
+static inline void watchdog_disable_all_cpus(void) { }
+static void lockup_detector_reconfigure(void)
 {
-	mutex_lock(&watchdog_proc_mutex);
+	cpus_read_lock();
+	watchdog_nmi_stop();
+	lockup_detector_update_enable();
+	watchdog_nmi_start();
+	cpus_read_unlock();
+}
+static inline void lockup_detector_setup(void)
+{
+	lockup_detector_reconfigure();
+}
+#endif /* !CONFIG_SOFTLOCKUP_DETECTOR */
 
-	watchdog_suspended--;
-	/*
-	 * The watchdog threads are unparked if they were previously running
-	 * and if there is no more active suspend request.
-	 */
-	if (watchdog_running && !watchdog_suspended)
-		watchdog_unpark_threads();
+static void __lockup_detector_cleanup(void)
+{
+	lockdep_assert_held(&watchdog_mutex);
+	hardlockup_detector_perf_cleanup();
+}
 
-	watchdog_nmi_reconfigure();
+/**
+ * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes
+ *
+ * Caller must not hold the cpu hotplug rwsem.
+ */
+void lockup_detector_cleanup(void)
+{
+	mutex_lock(&watchdog_mutex);
+	__lockup_detector_cleanup();
+	mutex_unlock(&watchdog_mutex);
+}
 
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+/**
+ * lockup_detector_soft_poweroff - Interface to stop lockup detector(s)
+ *
+ * Special interface for parisc. It prevents lockup detector warnings from
+ * the default pm_poweroff() function which busy loops forever.
+ */
+void lockup_detector_soft_poweroff(void)
+{
+	watchdog_enabled = 0;
 }
 
 #ifdef CONFIG_SYSCTL
 
-/*
- * Update the run state of the lockup detectors.
- */
-static int proc_watchdog_update(void)
+/* Propagate any changes to the watchdog threads */
+static void proc_watchdog_update(void)
 {
-	int err = 0;
-
-	/*
-	 * Watchdog threads won't be started if they are already active.
-	 * The 'watchdog_running' variable in watchdog_*_all_cpus() takes
-	 * care of this. If those threads are already active, the sample
-	 * period will be updated and the lockup detectors will be enabled
-	 * or disabled 'on the fly'.
-	 */
-	if (watchdog_enabled && watchdog_thresh)
-		err = watchdog_enable_all_cpus();
-	else
-		watchdog_disable_all_cpus();
-
-	watchdog_nmi_reconfigure();
-
-	return err;
-
+	/* Remove impossible cpus to keep sysctl output clean. */
+	cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask);
+	lockup_detector_reconfigure();
 }
 
 /*
  * common function for watchdog, nmi_watchdog and soft_watchdog parameter
  *
- * caller             | table->data points to | 'which' contains the flag(s)
- * -------------------|-----------------------|-----------------------------
- * proc_watchdog      | watchdog_user_enabled | NMI_WATCHDOG_ENABLED or'ed
- *                    |                       | with SOFT_WATCHDOG_ENABLED
- * -------------------|-----------------------|-----------------------------
- * proc_nmi_watchdog  | nmi_watchdog_enabled  | NMI_WATCHDOG_ENABLED
- * -------------------|-----------------------|-----------------------------
- * proc_soft_watchdog | soft_watchdog_enabled | SOFT_WATCHDOG_ENABLED
+ * caller             | table->data points to      | 'which'
+ * -------------------|----------------------------|--------------------------
+ * proc_watchdog      | watchdog_user_enabled      | NMI_WATCHDOG_ENABLED |
+ *                    |                            | SOFT_WATCHDOG_ENABLED
+ * -------------------|----------------------------|--------------------------
+ * proc_nmi_watchdog  | nmi_watchdog_user_enabled  | NMI_WATCHDOG_ENABLED
+ * -------------------|----------------------------|--------------------------
+ * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED
  */
 static int proc_watchdog_common(int which, struct ctl_table *table, int write,
 				void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old, new;
-	int *watchdog_param = (int *)table->data;
+	int err, old, *param = table->data;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
+	mutex_lock(&watchdog_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
-	/*
-	 * If the parameter is being read return the state of the corresponding
-	 * bit(s) in 'watchdog_enabled', else update 'watchdog_enabled' and the
-	 * run state of the lockup detectors.
-	 */
 	if (!write) {
-		*watchdog_param = (watchdog_enabled & which) != 0;
+		/*
+		 * On read synchronize the userspace interface. This is a
+		 * racy snapshot.
+		 */
+		*param = (watchdog_enabled & which) != 0;
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 	} else {
+		old = READ_ONCE(*param);
 		err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
-		if (err)
-			goto out;
-
-		/*
-		 * There is a race window between fetching the current value
-		 * from 'watchdog_enabled' and storing the new value. During
-		 * this race window, watchdog_nmi_enable() can sneak in and
-		 * clear the NMI_WATCHDOG_ENABLED bit in 'watchdog_enabled'.
-		 * The 'cmpxchg' detects this race and the loop retries.
-		 */
-		do {
-			old = watchdog_enabled;
-			/*
-			 * If the parameter value is not zero set the
-			 * corresponding bit(s), else clear it(them).
-			 */
-			if (*watchdog_param)
-				new = old | which;
-			else
-				new = old & ~which;
-		} while (cmpxchg(&watchdog_enabled, old, new) != old);
-
-		/*
-		 * Update the run state of the lockup detectors. There is _no_
-		 * need to check the value returned by proc_watchdog_update()
-		 * and to restore the previous value of 'watchdog_enabled' as
-		 * both lockup detectors are disabled if proc_watchdog_update()
-		 * returns an error.
-		 */
-		if (old == new)
-			goto out;
-
-		err = proc_watchdog_update();
+		if (!err && old != READ_ONCE(*param))
+			proc_watchdog_update();
 	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
 
@@ -835,6 +713,8 @@ int proc_watchdog(struct ctl_table *table, int write,
 int proc_nmi_watchdog(struct ctl_table *table, int write,
 		      void __user *buffer, size_t *lenp, loff_t *ppos)
 {
+	if (!nmi_watchdog_available && write)
+		return -ENOTSUPP;
 	return proc_watchdog_common(NMI_WATCHDOG_ENABLED,
 				    table, write, buffer, lenp, ppos);
 }
@@ -855,39 +735,17 @@ int proc_soft_watchdog(struct ctl_table *table, int write,
 int proc_watchdog_thresh(struct ctl_table *table, int write,
 			 void __user *buffer, size_t *lenp, loff_t *ppos)
 {
-	int err, old, new;
+	int err, old;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
+	mutex_lock(&watchdog_mutex);
 
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
-
-	old = ACCESS_ONCE(watchdog_thresh);
+	old = READ_ONCE(watchdog_thresh);
 	err = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
 
-	if (err || !write)
-		goto out;
+	if (!err && write && old != READ_ONCE(watchdog_thresh))
+		proc_watchdog_update();
 
-	/*
-	 * Update the sample period. Restore on failure.
-	 */
-	new = ACCESS_ONCE(watchdog_thresh);
-	if (old == new)
-		goto out;
-
-	set_sample_period();
-	err = proc_watchdog_update();
-	if (err) {
-		watchdog_thresh = old;
-		set_sample_period();
-	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
 
@@ -902,45 +760,19 @@ int proc_watchdog_cpumask(struct ctl_table *table, int write,
 {
 	int err;
 
-	get_online_cpus();
-	mutex_lock(&watchdog_proc_mutex);
-
-	if (watchdog_suspended) {
-		/* no parameter changes allowed while watchdog is suspended */
-		err = -EAGAIN;
-		goto out;
-	}
+	mutex_lock(&watchdog_mutex);
 
 	err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
-	if (!err && write) {
-		/* Remove impossible cpus to keep sysctl output cleaner. */
-		cpumask_and(&watchdog_cpumask, &watchdog_cpumask,
-			    cpu_possible_mask);
+	if (!err && write)
+		proc_watchdog_update();
 
-		if (watchdog_running) {
-			/*
-			 * Failure would be due to being unable to allocate
-			 * a temporary cpumask, so we are likely not in a
-			 * position to do much else to make things better.
-			 */
-			if (watchdog_update_cpus() != 0)
-				pr_err("cpumask update failed\n");
-		}
-
-		watchdog_nmi_reconfigure();
-	}
-out:
-	mutex_unlock(&watchdog_proc_mutex);
-	put_online_cpus();
+	mutex_unlock(&watchdog_mutex);
 	return err;
 }
-
 #endif /* CONFIG_SYSCTL */
 
 void __init lockup_detector_init(void)
 {
-	set_sample_period();
-
 #ifdef CONFIG_NO_HZ_FULL
 	if (tick_nohz_full_enabled()) {
 		pr_info("Disabling watchdog on nohz_full cores by default\n");
@@ -951,6 +783,7 @@ void __init lockup_detector_init(void)
 	cpumask_copy(&watchdog_cpumask, cpu_possible_mask);
 #endif
 
-	if (watchdog_enabled)
-		watchdog_enable_all_cpus();
+	if (!watchdog_nmi_probe())
+		nmi_watchdog_available = true;
+	lockup_detector_setup();
 }
diff --git a/kernel/watchdog_hld.c b/kernel/watchdog_hld.c
index 3a09ea1..71a62ce 100644
--- a/kernel/watchdog_hld.c
+++ b/kernel/watchdog_hld.c
@@ -21,8 +21,10 @@
 static DEFINE_PER_CPU(bool, hard_watchdog_warn);
 static DEFINE_PER_CPU(bool, watchdog_nmi_touch);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
+static struct cpumask dead_events_mask;
 
 static unsigned long hardlockup_allcpu_dumped;
+static unsigned int watchdog_cpus;
 
 void arch_touch_nmi_watchdog(void)
 {
@@ -103,15 +105,12 @@ static struct perf_event_attr wd_hw_attr = {
 
 /* Callback function for perf event subsystem */
 static void watchdog_overflow_callback(struct perf_event *event,
-		 struct perf_sample_data *data,
-		 struct pt_regs *regs)
+				       struct perf_sample_data *data,
+				       struct pt_regs *regs)
 {
 	/* Ensure the watchdog never gets throttled */
 	event->hw.interrupts = 0;
 
-	if (atomic_read(&watchdog_park_in_progress) != 0)
-		return;
-
 	if (__this_cpu_read(watchdog_nmi_touch) == true) {
 		__this_cpu_write(watchdog_nmi_touch, false);
 		return;
@@ -160,104 +159,131 @@ static void watchdog_overflow_callback(struct perf_event *event,
 	return;
 }
 
-/*
- * People like the simple clean cpu node info on boot.
- * Reduce the watchdog noise by only printing messages
- * that are different from what cpu0 displayed.
- */
-static unsigned long firstcpu_err;
-static atomic_t watchdog_cpus;
-
-int watchdog_nmi_enable(unsigned int cpu)
+static int hardlockup_detector_event_create(void)
 {
+	unsigned int cpu = smp_processor_id();
 	struct perf_event_attr *wd_attr;
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
-	int firstcpu = 0;
-
-	/* nothing to do if the hard lockup detector is disabled */
-	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
-		goto out;
-
-	/* is it already setup and enabled? */
-	if (event && event->state > PERF_EVENT_STATE_OFF)
-		goto out;
-
-	/* it is setup but not enabled */
-	if (event != NULL)
-		goto out_enable;
-
-	if (atomic_inc_return(&watchdog_cpus) == 1)
-		firstcpu = 1;
+	struct perf_event *evt;
 
 	wd_attr = &wd_hw_attr;
 	wd_attr->sample_period = hw_nmi_get_sample_period(watchdog_thresh);
 
 	/* Try to register using hardware perf events */
-	event = perf_event_create_kernel_counter(wd_attr, cpu, NULL, watchdog_overflow_callback, NULL);
-
-	/* save the first cpu's error for future comparision */
-	if (firstcpu && IS_ERR(event))
-		firstcpu_err = PTR_ERR(event);
-
-	if (!IS_ERR(event)) {
-		/* only print for the first cpu initialized */
-		if (firstcpu || firstcpu_err)
-			pr_info("enabled on all CPUs, permanently consumes one hw-PMU counter.\n");
-		goto out_save;
+	evt = perf_event_create_kernel_counter(wd_attr, cpu, NULL,
+					       watchdog_overflow_callback, NULL);
+	if (IS_ERR(evt)) {
+		pr_info("Perf event create on CPU %d failed with %ld\n", cpu,
+			PTR_ERR(evt));
+		return PTR_ERR(evt);
 	}
-
-	/*
-	 * Disable the hard lockup detector if _any_ CPU fails to set up
-	 * set up the hardware perf event. The watchdog() function checks
-	 * the NMI_WATCHDOG_ENABLED bit periodically.
-	 *
-	 * The barriers are for syncing up watchdog_enabled across all the
-	 * cpus, as clear_bit() does not use barriers.
-	 */
-	smp_mb__before_atomic();
-	clear_bit(NMI_WATCHDOG_ENABLED_BIT, &watchdog_enabled);
-	smp_mb__after_atomic();
-
-	/* skip displaying the same error again */
-	if (!firstcpu && (PTR_ERR(event) == firstcpu_err))
-		return PTR_ERR(event);
-
-	/* vary the KERN level based on the returned errno */
-	if (PTR_ERR(event) == -EOPNOTSUPP)
-		pr_info("disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
-	else if (PTR_ERR(event) == -ENOENT)
-		pr_warn("disabled (cpu%i): hardware events not enabled\n",
-			 cpu);
-	else
-		pr_err("disabled (cpu%i): unable to create perf event: %ld\n",
-			cpu, PTR_ERR(event));
-
-	pr_info("Shutting down hard lockup detector on all cpus\n");
-
-	return PTR_ERR(event);
-
-	/* success path */
-out_save:
-	per_cpu(watchdog_ev, cpu) = event;
-out_enable:
-	perf_event_enable(per_cpu(watchdog_ev, cpu));
-out:
+	this_cpu_write(watchdog_ev, evt);
 	return 0;
 }
 
-void watchdog_nmi_disable(unsigned int cpu)
+/**
+ * hardlockup_detector_perf_enable - Enable the local event
+ */
+void hardlockup_detector_perf_enable(void)
 {
-	struct perf_event *event = per_cpu(watchdog_ev, cpu);
+	if (hardlockup_detector_event_create())
+		return;
+
+	if (!watchdog_cpus++)
+		pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
+
+	perf_event_enable(this_cpu_read(watchdog_ev));
+}
+
+/**
+ * hardlockup_detector_perf_disable - Disable the local event
+ */
+void hardlockup_detector_perf_disable(void)
+{
+	struct perf_event *event = this_cpu_read(watchdog_ev);
 
 	if (event) {
 		perf_event_disable(event);
-		per_cpu(watchdog_ev, cpu) = NULL;
-
-		/* should be in cleanup, but blocks oprofile */
-		perf_event_release_kernel(event);
-
-		/* watchdog_nmi_enable() expects this to be zero initially. */
-		if (atomic_dec_and_test(&watchdog_cpus))
-			firstcpu_err = 0;
+		cpumask_set_cpu(smp_processor_id(), &dead_events_mask);
+		watchdog_cpus--;
 	}
 }
+
+/**
+ * hardlockup_detector_perf_cleanup - Cleanup disabled events and destroy them
+ *
+ * Called from lockup_detector_cleanup(). Serialized by the caller.
+ */
+void hardlockup_detector_perf_cleanup(void)
+{
+	int cpu;
+
+	for_each_cpu(cpu, &dead_events_mask) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		/*
+		 * Required because for_each_cpu() reports  unconditionally
+		 * CPU0 as set on UP kernels. Sigh.
+		 */
+		if (event)
+			perf_event_release_kernel(event);
+		per_cpu(watchdog_ev, cpu) = NULL;
+	}
+	cpumask_clear(&dead_events_mask);
+}
+
+/**
+ * hardlockup_detector_perf_stop - Globally stop watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_stop(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_disable(event);
+	}
+}
+
+/**
+ * hardlockup_detector_perf_restart - Globally restart watchdog events
+ *
+ * Special interface for x86 to handle the perf HT bug.
+ */
+void __init hardlockup_detector_perf_restart(void)
+{
+	int cpu;
+
+	lockdep_assert_cpus_held();
+
+	if (!(watchdog_enabled & NMI_WATCHDOG_ENABLED))
+		return;
+
+	for_each_online_cpu(cpu) {
+		struct perf_event *event = per_cpu(watchdog_ev, cpu);
+
+		if (event)
+			perf_event_enable(event);
+	}
+}
+
+/**
+ * hardlockup_detector_perf_init - Probe whether NMI event is available at all
+ */
+int __init hardlockup_detector_perf_init(void)
+{
+	int ret = hardlockup_detector_event_create();
+
+	if (ret) {
+		pr_info("Perf NMI watchdog permanently disabled\n");
+	} else {
+		perf_event_release_kernel(this_cpu_read(watchdog_ev));
+		this_cpu_write(watchdog_ev, NULL);
+	}
+	return ret;
+}
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 9b5de31a..c1841f2 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -2203,7 +2203,7 @@ static void xs_udp_setup_socket(struct work_struct *work)
 	struct sock_xprt *transport =
 		container_of(work, struct sock_xprt, connect_worker.work);
 	struct rpc_xprt *xprt = &transport->xprt;
-	struct socket *sock = transport->sock;
+	struct socket *sock;
 	int status = -EIO;
 
 	sock = xs_create_sock(xprt, transport,