diff --git a/.mailmap b/.mailmap
index d357e1b..0d971cf 100644
--- a/.mailmap
+++ b/.mailmap
@@ -73,6 +73,7 @@
 Juha Yrjola <juha.yrjola@solidboot.com>
 Kay Sievers <kay.sievers@vrfy.org>
 Kenneth W Chen <kenneth.w.chen@intel.com>
+Konstantin Khlebnikov <koct9i@gmail.com> <k.khlebnikov@samsung.com>
 Koushik <raghavendra.koushik@neterion.com>
 Kuninori Morimoto <kuninori.morimoto.gx@renesas.com>
 Leonid I Ananiev <leonid.i.ananiev@intel.com>
diff --git a/Documentation/networking/netlink_mmap.txt b/Documentation/networking/netlink_mmap.txt
index c6af4ba..54f1047 100644
--- a/Documentation/networking/netlink_mmap.txt
+++ b/Documentation/networking/netlink_mmap.txt
@@ -199,16 +199,9 @@
 TX limitations
 --------------
 
-Kernel processing usually involves validation of the message received by
-user-space, then processing its contents. The kernel must assure that
-userspace is not able to modify the message contents after they have been
-validated. In order to do so, the message is copied from the ring frame
-to an allocated buffer if either of these conditions is false:
-
-- only a single mapping of the ring exists
-- the file descriptor is not shared between processes
-
-This means that for threaded programs, the kernel will fall back to copying.
+As of Jan 2015 the message is always copied from the ring frame to an
+allocated buffer due to unresolved security concerns.
+See commit 4682a0358639b29cf ("netlink: Always copy on mmap TX.").
 
 Example
 -------
diff --git a/MAINTAINERS b/MAINTAINERS
index aaa039d..d66a97d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4953,6 +4953,16 @@
 F:	drivers/input/input-mt.c
 K:	\b(ABS|SYN)_MT_
 
+INTEL ASoC BDW/HSW DRIVERS
+M:	Jie Yang <yang.jie@linux.intel.com>
+L:	alsa-devel@alsa-project.org
+S:	Supported
+F:	sound/soc/intel/sst-haswell*
+F:	sound/soc/intel/sst-dsp*
+F:	sound/soc/intel/sst-firmware.c
+F:	sound/soc/intel/broadwell.c
+F:	sound/soc/intel/haswell.c
+
 INTEL C600 SERIES SAS CONTROLLER DRIVER
 M:	Intel SCU Linux support <intel-linux-scu@intel.com>
 M:	Artur Paszkiewicz <artur.paszkiewicz@intel.com>
@@ -9241,7 +9251,6 @@
 
 SUPERH
 L:	linux-sh@vger.kernel.org
-W:	http://www.linux-sh.org
 Q:	http://patchwork.kernel.org/project/linux-sh/list/
 S:	Orphan
 F:	Documentation/sh/
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 68be901..132c70e 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -263,16 +263,37 @@
 		 * OK... Let's do some funky business here.
 		 * If we do have a DTB appended to zImage, and we do have
 		 * an ATAG list around, we want the later to be translated
-		 * and folded into the former here.  To be on the safe side,
-		 * let's temporarily move  the stack away into the malloc
-		 * area.  No GOT fixup has occurred yet, but none of the
-		 * code we're about to call uses any global variable.
+		 * and folded into the former here. No GOT fixup has occurred
+		 * yet, but none of the code we're about to call uses any
+		 * global variable.
 		*/
-		add	sp, sp, #0x10000
+
+		/* Get the initial DTB size */
+		ldr	r5, [r6, #4]
+#ifndef __ARMEB__
+		/* convert to little endian */
+		eor	r1, r5, r5, ror #16
+		bic	r1, r1, #0x00ff0000
+		mov	r5, r5, ror #8
+		eor	r5, r5, r1, lsr #8
+#endif
+		/* 50% DTB growth should be good enough */
+		add	r5, r5, r5, lsr #1
+		/* preserve 64-bit alignment */
+		add	r5, r5, #7
+		bic	r5, r5, #7
+		/* clamp to 32KB min and 1MB max */
+		cmp	r5, #(1 << 15)
+		movlo	r5, #(1 << 15)
+		cmp	r5, #(1 << 20)
+		movhi	r5, #(1 << 20)
+		/* temporarily relocate the stack past the DTB work space */
+		add	sp, sp, r5
+
 		stmfd	sp!, {r0-r3, ip, lr}
 		mov	r0, r8
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bl	atags_to_fdt
 
 		/*
@@ -285,11 +306,11 @@
 		bic	r0, r0, #1
 		add	r0, r0, #0x100
 		mov	r1, r6
-		sub	r2, sp, r6
+		mov	r2, r5
 		bleq	atags_to_fdt
 
 		ldmfd	sp!, {r0-r3, ip, lr}
-		sub	sp, sp, #0x10000
+		sub	sp, sp, r5
 #endif
 
 		mov	r8, r6			@ use the appended device tree
@@ -306,7 +327,7 @@
 		subs	r1, r5, r1
 		addhi	r9, r9, r1
 
-		/* Get the dtb's size */
+		/* Get the current DTB size */
 		ldr	r5, [r6, #4]
 #ifndef __ARMEB__
 		/* convert r5 (dtb size) to little endian */
diff --git a/arch/arm/boot/dts/exynos4.dtsi b/arch/arm/boot/dts/exynos4.dtsi
index b8168f1..24ff270 100644
--- a/arch/arm/boot/dts/exynos4.dtsi
+++ b/arch/arm/boot/dts/exynos4.dtsi
@@ -368,7 +368,7 @@
 	};
 
 	i2s1: i2s@13960000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13960000 0x100>;
 		clocks = <&clock CLK_I2S1>;
 		clock-names = "iis";
@@ -378,7 +378,7 @@
 	};
 
 	i2s2: i2s@13970000 {
-		compatible = "samsung,s5pv210-i2s";
+		compatible = "samsung,s3c6410-i2s";
 		reg = <0x13970000 0x100>;
 		clocks = <&clock CLK_I2S2>;
 		clock-names = "iis";
diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S
index 2260f18..8944f49 100644
--- a/arch/arm/kernel/entry-v7m.S
+++ b/arch/arm/kernel/entry-v7m.S
@@ -22,10 +22,12 @@
 
 __invalid_entry:
 	v7m_exception_entry
+#ifdef CONFIG_PRINTK
 	adr	r0, strerr
 	mrs	r1, ipsr
 	mov	r2, lr
 	bl	printk
+#endif
 	mov	r0, sp
 	bl	show_regs
 1:	b	1b
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 03823e7..c43c714 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1012,6 +1012,7 @@
 
 config ARM_KERNMEM_PERMS
 	bool "Restrict kernel memory permissions"
+	depends on MMU
 	help
 	  If this is set, kernel memory other than kernel text (and rodata)
 	  will be made non-executable. The tradeoff is that each region is
diff --git a/arch/arm/mm/context.c b/arch/arm/mm/context.c
index 9189256..845769e 100644
--- a/arch/arm/mm/context.c
+++ b/arch/arm/mm/context.c
@@ -144,21 +144,17 @@
 	/* Update the list of reserved ASIDs and the ASID bitmap. */
 	bitmap_clear(asid_map, 0, NUM_USER_ASIDS);
 	for_each_possible_cpu(i) {
-		if (i == cpu) {
-			asid = 0;
-		} else {
-			asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
-			/*
-			 * If this CPU has already been through a
-			 * rollover, but hasn't run another task in
-			 * the meantime, we must preserve its reserved
-			 * ASID, as this is the only trace we have of
-			 * the process it is still running.
-			 */
-			if (asid == 0)
-				asid = per_cpu(reserved_asids, i);
-			__set_bit(asid & ~ASID_MASK, asid_map);
-		}
+		asid = atomic64_xchg(&per_cpu(active_asids, i), 0);
+		/*
+		 * If this CPU has already been through a
+		 * rollover, but hasn't run another task in
+		 * the meantime, we must preserve its reserved
+		 * ASID, as this is the only trace we have of
+		 * the process it is still running.
+		 */
+		if (asid == 0)
+			asid = per_cpu(reserved_asids, i);
+		__set_bit(asid & ~ASID_MASK, asid_map);
 		per_cpu(reserved_asids, i) = asid;
 	}
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index a673c7f..903dba0 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -2048,6 +2048,9 @@
 {
 	struct dma_iommu_mapping *mapping = dev->archdata.mapping;
 
+	if (!mapping)
+		return;
+
 	__arm_iommu_detach_device(dev);
 	arm_iommu_release_mapping(mapping);
 }
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 3289969..843713c 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -2656,27 +2656,21 @@
 	bool
 
 config MIPS32_COMPAT
-	bool "Kernel support for Linux/MIPS 32-bit binary compatibility"
-	depends on 64BIT
-	help
-	  Select this option if you want Linux/MIPS 32-bit binary
-	  compatibility. Since all software available for Linux/MIPS is
-	  currently 32-bit you should say Y here.
+	bool
 
 config COMPAT
 	bool
-	depends on MIPS32_COMPAT
-	select ARCH_WANT_OLD_COMPAT_IPC
-	default y
 
 config SYSVIPC_COMPAT
 	bool
-	depends on COMPAT && SYSVIPC
-	default y
 
 config MIPS32_O32
 	bool "Kernel support for o32 binaries"
-	depends on MIPS32_COMPAT
+	depends on 64BIT
+	select ARCH_WANT_OLD_COMPAT_IPC
+	select COMPAT
+	select MIPS32_COMPAT
+	select SYSVIPC_COMPAT if SYSVIPC
 	help
 	  Select this option if you want to run o32 binaries.  These are pure
 	  32-bit binaries as used by the 32-bit Linux/MIPS port.  Most of
@@ -2686,7 +2680,10 @@
 
 config MIPS32_N32
 	bool "Kernel support for n32 binaries"
-	depends on MIPS32_COMPAT
+	depends on 64BIT
+	select COMPAT
+	select MIPS32_COMPAT
+	select SYSVIPC_COMPAT if SYSVIPC
 	help
 	  Select this option if you want to run n32 binaries.  These are
 	  64-bit binaries using 32-bit quantities for addressing and certain
diff --git a/arch/mips/boot/elf2ecoff.c b/arch/mips/boot/elf2ecoff.c
index 8585078..2a4c52e 100644
--- a/arch/mips/boot/elf2ecoff.c
+++ b/arch/mips/boot/elf2ecoff.c
@@ -49,7 +49,8 @@
 /*
  * Some extra ELF definitions
  */
-#define PT_MIPS_REGINFO 0x70000000	/* Register usage information */
+#define PT_MIPS_REGINFO 	0x70000000	/* Register usage information */
+#define PT_MIPS_ABIFLAGS	0x70000003	/* Records ABI related flags  */
 
 /* -------------------------------------------------------------------- */
 
@@ -349,39 +350,46 @@
 
 	for (i = 0; i < ex.e_phnum; i++) {
 		/* Section types we can ignore... */
-		if (ph[i].p_type == PT_NULL || ph[i].p_type == PT_NOTE ||
-		    ph[i].p_type == PT_PHDR
-		    || ph[i].p_type == PT_MIPS_REGINFO)
+		switch (ph[i].p_type) {
+		case PT_NULL:
+		case PT_NOTE:
+		case PT_PHDR:
+		case PT_MIPS_REGINFO:
+		case PT_MIPS_ABIFLAGS:
 			continue;
-		/* Section types we can't handle... */
-		else if (ph[i].p_type != PT_LOAD) {
+
+		case PT_LOAD:
+			/* Writable (data) segment? */
+			if (ph[i].p_flags & PF_W) {
+				struct sect ndata, nbss;
+
+				ndata.vaddr = ph[i].p_vaddr;
+				ndata.len = ph[i].p_filesz;
+				nbss.vaddr = ph[i].p_vaddr + ph[i].p_filesz;
+				nbss.len = ph[i].p_memsz - ph[i].p_filesz;
+
+				combine(&data, &ndata, 0);
+				combine(&bss, &nbss, 1);
+			} else {
+				struct sect ntxt;
+
+				ntxt.vaddr = ph[i].p_vaddr;
+				ntxt.len = ph[i].p_filesz;
+
+				combine(&text, &ntxt, 0);
+			}
+			/* Remember the lowest segment start address. */
+			if (ph[i].p_vaddr < cur_vma)
+				cur_vma = ph[i].p_vaddr;
+			break;
+
+		default:
+			/* Section types we can't handle... */
 			fprintf(stderr,
 				"Program header %d type %d can't be converted.\n",
 				ex.e_phnum, ph[i].p_type);
 			exit(1);
 		}
-		/* Writable (data) segment? */
-		if (ph[i].p_flags & PF_W) {
-			struct sect ndata, nbss;
-
-			ndata.vaddr = ph[i].p_vaddr;
-			ndata.len = ph[i].p_filesz;
-			nbss.vaddr = ph[i].p_vaddr + ph[i].p_filesz;
-			nbss.len = ph[i].p_memsz - ph[i].p_filesz;
-
-			combine(&data, &ndata, 0);
-			combine(&bss, &nbss, 1);
-		} else {
-			struct sect ntxt;
-
-			ntxt.vaddr = ph[i].p_vaddr;
-			ntxt.len = ph[i].p_filesz;
-
-			combine(&text, &ntxt, 0);
-		}
-		/* Remember the lowest segment start address. */
-		if (ph[i].p_vaddr < cur_vma)
-			cur_vma = ph[i].p_vaddr;
 	}
 
 	/* Sections must be in order to be converted... */
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index ecd903d..8b1eeff 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -240,9 +240,7 @@
 
 	set_cpu_online(cpu, false);
 	cpu_clear(cpu, cpu_callin_map);
-	local_irq_disable();
 	octeon_fixup_irqs();
-	local_irq_enable();
 
 	flush_cache_all();
 	local_flush_tlb_all();
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index f57b96d..61a4460 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -132,7 +132,6 @@
 CONFIG_IP_NF_MATCH_TTL=m
 CONFIG_IP_NF_FILTER=m
 CONFIG_IP_NF_TARGET_REJECT=m
-CONFIG_IP_NF_TARGET_ULOG=m
 CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_CLUSTERIP=m
 CONFIG_IP_NF_TARGET_ECN=m
@@ -175,7 +174,6 @@
 CONFIG_BRIDGE_EBT_REDIRECT=m
 CONFIG_BRIDGE_EBT_SNAT=m
 CONFIG_BRIDGE_EBT_LOG=m
-CONFIG_BRIDGE_EBT_ULOG=m
 CONFIG_BRIDGE_EBT_NFLOG=m
 CONFIG_IP_SCTP=m
 CONFIG_BRIDGE=m
@@ -220,8 +218,6 @@
 CONFIG_NET_CLS_IND=y
 CONFIG_CFG80211=m
 CONFIG_MAC80211=m
-CONFIG_MAC80211_RC_PID=y
-CONFIG_MAC80211_RC_DEFAULT_PID=y
 CONFIG_MAC80211_MESH=y
 CONFIG_RFKILL=m
 CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug"
@@ -248,19 +244,13 @@
 CONFIG_IDE=y
 CONFIG_BLK_DEV_IDECD=y
 CONFIG_IDE_GENERIC=y
-CONFIG_BLK_DEV_GENERIC=y
-CONFIG_BLK_DEV_PIIX=y
-CONFIG_BLK_DEV_IT8213=m
-CONFIG_BLK_DEV_TC86C001=m
 CONFIG_RAID_ATTRS=m
-CONFIG_SCSI=m
-CONFIG_BLK_DEV_SD=m
+CONFIG_BLK_DEV_SD=y
 CONFIG_CHR_DEV_ST=m
 CONFIG_CHR_DEV_OSST=m
 CONFIG_BLK_DEV_SR=m
 CONFIG_BLK_DEV_SR_VENDOR=y
 CONFIG_CHR_DEV_SG=m
-CONFIG_SCSI_MULTI_LUN=y
 CONFIG_SCSI_CONSTANTS=y
 CONFIG_SCSI_LOGGING=y
 CONFIG_SCSI_SCAN_ASYNC=y
@@ -273,6 +263,8 @@
 CONFIG_SCSI_AIC7XXX=m
 CONFIG_AIC7XXX_RESET_DELAY_MS=15000
 # CONFIG_AIC7XXX_DEBUG_ENABLE is not set
+CONFIG_ATA=y
+CONFIG_ATA_PIIX=y
 CONFIG_MD=y
 CONFIG_BLK_DEV_MD=m
 CONFIG_MD_LINEAR=m
@@ -340,6 +332,7 @@
 CONFIG_UIO_CIF=m
 CONFIG_EXT2_FS=y
 CONFIG_EXT3_FS=y
+CONFIG_EXT4_FS=y
 CONFIG_REISERFS_FS=m
 CONFIG_REISERFS_PROC_INFO=y
 CONFIG_REISERFS_FS_XATTR=y
@@ -441,4 +434,3 @@
 CONFIG_CRYPTO_TEA=m
 CONFIG_CRYPTO_TWOFISH=m
 # CONFIG_CRYPTO_ANSI_CPRNG is not set
-CONFIG_CRC16=m
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 994d219..affebb7 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -64,7 +64,7 @@
 			return SIGFPE;
 
 		/* set FRE */
-		write_c0_config5(read_c0_config5() | MIPS_CONF5_FRE);
+		set_c0_config5(MIPS_CONF5_FRE);
 		goto fr_common;
 
 	case FPU_64BIT:
@@ -74,8 +74,10 @@
 #endif
 		/* fall through */
 	case FPU_32BIT:
-		/* clear FRE */
-		write_c0_config5(read_c0_config5() & ~MIPS_CONF5_FRE);
+		if (cpu_has_fre) {
+			/* clear FRE */
+			clear_c0_config5(MIPS_CONF5_FRE);
+		}
 fr_common:
 		/* set CU1 & change FR appropriately */
 		fr = (int)mode & FPU_FR_MASK;
@@ -182,25 +184,32 @@
 	int ret = 0;
 
 	if (cpu_has_fpu) {
+		unsigned int config5;
+
 		ret = __own_fpu();
-		if (!ret) {
-			unsigned int config5 = read_c0_config5();
+		if (ret)
+			return ret;
 
-			/*
-			 * Ensure FRE is clear whilst running _init_fpu, since
-			 * single precision FP instructions are used. If FRE
-			 * was set then we'll just end up initialising all 32
-			 * 64b registers.
-			 */
-			write_c0_config5(config5 & ~MIPS_CONF5_FRE);
-			enable_fpu_hazard();
-
+		if (!cpu_has_fre) {
 			_init_fpu();
 
-			/* Restore FRE */
-			write_c0_config5(config5);
-			enable_fpu_hazard();
+			return 0;
 		}
+
+		/*
+		 * Ensure FRE is clear whilst running _init_fpu, since
+		 * single precision FP instructions are used. If FRE
+		 * was set then we'll just end up initialising all 32
+		 * 64b registers.
+		 */
+		config5 = clear_c0_config5(MIPS_CONF5_FRE);
+		enable_fpu_hazard();
+
+		_init_fpu();
+
+		/* Restore FRE */
+		write_c0_config5(config5);
+		enable_fpu_hazard();
 	} else
 		fpu_emulator_init_fpu();
 
diff --git a/arch/mips/include/asm/fw/arc/hinv.h b/arch/mips/include/asm/fw/arc/hinv.h
index f8d37d1..9fac64a 100644
--- a/arch/mips/include/asm/fw/arc/hinv.h
+++ b/arch/mips/include/asm/fw/arc/hinv.h
@@ -119,7 +119,7 @@
 #define SGI_ARCS_REV	10			/* rev .10, 3/04/92 */
 #endif
 
-typedef struct component {
+typedef struct {
 	CONFIGCLASS	Class;
 	CONFIGTYPE	Type;
 	IDENTIFIERFLAG	Flags;
@@ -140,7 +140,7 @@
 };
 
 /* System ID */
-typedef struct systemid {
+typedef struct {
 	CHAR VendorId[8];
 	CHAR ProductId[8];
 } SYSTEMID;
@@ -166,7 +166,7 @@
 #endif	/* _NT_PROM */
 } MEMORYTYPE;
 
-typedef struct memorydescriptor {
+typedef struct {
 	MEMORYTYPE	Type;
 	LONG		BasePage;
 	LONG		PageCount;
diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
index b95a827..59c0901 100644
--- a/arch/mips/include/asm/mips-cm.h
+++ b/arch/mips/include/asm/mips-cm.h
@@ -89,9 +89,9 @@
 
 /* Macros to ease the creation of register access functions */
 #define BUILD_CM_R_(name, off)					\
-static inline u32 *addr_gcr_##name(void)			\
+static inline u32 __iomem *addr_gcr_##name(void)		\
 {								\
-	return (u32 *)(mips_cm_base + (off));			\
+	return (u32 __iomem *)(mips_cm_base + (off));		\
 }								\
 								\
 static inline u32 read_gcr_##name(void)				\
diff --git a/arch/mips/include/asm/mipsregs.h b/arch/mips/include/asm/mipsregs.h
index 5e4aef3..5b720d8 100644
--- a/arch/mips/include/asm/mipsregs.h
+++ b/arch/mips/include/asm/mipsregs.h
@@ -1386,12 +1386,27 @@
 	__res;								\
 })
 
+#define _write_32bit_cp1_register(dest, val, gas_hardfloat)		\
+do {									\
+	__asm__ __volatile__(						\
+	"	.set	push					\n"	\
+	"	.set	reorder					\n"	\
+	"	"STR(gas_hardfloat)"				\n"	\
+	"	ctc1	%0,"STR(dest)"				\n"	\
+	"	.set	pop					\n"	\
+	: : "r" (val));							\
+} while (0)
+
 #ifdef GAS_HAS_SET_HARDFLOAT
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, .set hardfloat)
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, .set hardfloat)
 #else
 #define read_32bit_cp1_register(source)					\
 	_read_32bit_cp1_register(source, )
+#define write_32bit_cp1_register(dest, val)				\
+	_write_32bit_cp1_register(dest, val, )
 #endif
 
 #ifdef HAVE_AS_DSP
diff --git a/arch/mips/include/asm/syscall.h b/arch/mips/include/asm/syscall.h
index bb79637..6499d93 100644
--- a/arch/mips/include/asm/syscall.h
+++ b/arch/mips/include/asm/syscall.h
@@ -29,13 +29,7 @@
 static inline long syscall_get_nr(struct task_struct *task,
 				  struct pt_regs *regs)
 {
-	/* O32 ABI syscall() - Either 64-bit with O32 or 32-bit */
-	if ((config_enabled(CONFIG_32BIT) ||
-	    test_tsk_thread_flag(task, TIF_32BIT_REGS)) &&
-	    (regs->regs[2] == __NR_syscall))
-		return regs->regs[4];
-	else
-		return regs->regs[2];
+	return current_thread_info()->syscall;
 }
 
 static inline unsigned long mips_get_syscall_arg(unsigned long *arg,
diff --git a/arch/mips/include/asm/thread_info.h b/arch/mips/include/asm/thread_info.h
index 99eea59..e4440f9 100644
--- a/arch/mips/include/asm/thread_info.h
+++ b/arch/mips/include/asm/thread_info.h
@@ -36,6 +36,7 @@
 						 */
 	struct restart_block	restart_block;
 	struct pt_regs		*regs;
+	long			syscall;	/* syscall number */
 };
 
 /*
diff --git a/arch/mips/include/uapi/asm/unistd.h b/arch/mips/include/uapi/asm/unistd.h
index d001bb1..c03088f 100644
--- a/arch/mips/include/uapi/asm/unistd.h
+++ b/arch/mips/include/uapi/asm/unistd.h
@@ -376,16 +376,17 @@
 #define __NR_getrandom			(__NR_Linux + 353)
 #define __NR_memfd_create		(__NR_Linux + 354)
 #define __NR_bpf			(__NR_Linux + 355)
+#define __NR_execveat			(__NR_Linux + 356)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		355
+#define __NR_Linux_syscalls		356
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		355
+#define __NR_O32_Linux_syscalls		356
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -709,16 +710,17 @@
 #define __NR_getrandom			(__NR_Linux + 313)
 #define __NR_memfd_create		(__NR_Linux + 314)
 #define __NR_bpf			(__NR_Linux + 315)
+#define __NR_execveat			(__NR_Linux + 316)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		315
+#define __NR_Linux_syscalls		316
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		315
+#define __NR_64_Linux_syscalls		316
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -1046,15 +1048,16 @@
 #define __NR_getrandom			(__NR_Linux + 317)
 #define __NR_memfd_create		(__NR_Linux + 318)
 #define __NR_bpf			(__NR_Linux + 319)
+#define __NR_execveat			(__NR_Linux + 320)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		319
+#define __NR_Linux_syscalls		320
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		319
+#define __NR_N32_Linux_syscalls		320
 
 #endif /* _UAPI_ASM_UNISTD_H */
diff --git a/arch/mips/jz4740/irq.c b/arch/mips/jz4740/irq.c
index 2531da1..97206b3 100644
--- a/arch/mips/jz4740/irq.c
+++ b/arch/mips/jz4740/irq.c
@@ -30,6 +30,9 @@
 #include <asm/irq_cpu.h>
 
 #include <asm/mach-jz4740/base.h>
+#include <asm/mach-jz4740/irq.h>
+
+#include "irq.h"
 
 static void __iomem *jz_intc_base;
 
diff --git a/arch/mips/kernel/elf.c b/arch/mips/kernel/elf.c
index c92b15d..a5b5b56 100644
--- a/arch/mips/kernel/elf.c
+++ b/arch/mips/kernel/elf.c
@@ -19,8 +19,8 @@
 int arch_elf_pt_proc(void *_ehdr, void *_phdr, struct file *elf,
 		     bool is_interp, struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
-	struct elf_phdr *phdr = _phdr;
+	struct elf32_hdr *ehdr = _ehdr;
+	struct elf32_phdr *phdr = _phdr;
 	struct mips_elf_abiflags_v0 abiflags;
 	int ret;
 
@@ -48,7 +48,7 @@
 	return 0;
 }
 
-static inline unsigned get_fp_abi(struct elfhdr *ehdr, int in_abi)
+static inline unsigned get_fp_abi(struct elf32_hdr *ehdr, int in_abi)
 {
 	/* If the ABI requirement is provided, simply return that */
 	if (in_abi != -1)
@@ -65,7 +65,7 @@
 int arch_check_elf(void *_ehdr, bool has_interpreter,
 		   struct arch_elf_state *state)
 {
-	struct elfhdr *ehdr = _ehdr;
+	struct elf32_hdr *ehdr = _ehdr;
 	unsigned fp_abi, interp_fp_abi, abi0, abi1;
 
 	/* Ignore non-O32 binaries */
diff --git a/arch/mips/kernel/irq_cpu.c b/arch/mips/kernel/irq_cpu.c
index 590c2c9..6eb7a3f 100644
--- a/arch/mips/kernel/irq_cpu.c
+++ b/arch/mips/kernel/irq_cpu.c
@@ -57,6 +57,8 @@
 	.irq_mask_ack	= mask_mips_irq,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 /*
@@ -93,6 +95,8 @@
 	.irq_mask_ack	= mips_mt_cpu_irq_ack,
 	.irq_unmask	= unmask_mips_irq,
 	.irq_eoi	= unmask_mips_irq,
+	.irq_disable	= mask_mips_irq,
+	.irq_enable	= unmask_mips_irq,
 };
 
 asmlinkage void __weak plat_irq_dispatch(void)
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index eb76434..85bff5d 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -82,6 +82,30 @@
 {
 }
 
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	/*
+	 * Save any process state which is live in hardware registers to the
+	 * parent context prior to duplication. This prevents the new child
+	 * state becoming stale if the parent is preempted before copy_thread()
+	 * gets a chance to save the parent's live hardware registers to the
+	 * child context.
+	 */
+	preempt_disable();
+
+	if (is_msa_enabled())
+		save_msa(current);
+	else if (is_fpu_owner())
+		_save_fp(current);
+
+	save_dsp(current);
+
+	preempt_enable();
+
+	*dst = *src;
+	return 0;
+}
+
 int copy_thread(unsigned long clone_flags, unsigned long usp,
 	unsigned long arg, struct task_struct *p)
 {
@@ -92,18 +116,6 @@
 
 	childksp = (unsigned long)task_stack_page(p) + THREAD_SIZE - 32;
 
-	preempt_disable();
-
-	if (is_msa_enabled())
-		save_msa(p);
-	else if (is_fpu_owner())
-		save_fp(p);
-
-	if (cpu_has_dsp)
-		save_dsp(p);
-
-	preempt_enable();
-
 	/* set up new TSS. */
 	childregs = (struct pt_regs *) childksp - 1;
 	/*  Put the stack after the struct pt_regs.  */
diff --git a/arch/mips/kernel/ptrace.c b/arch/mips/kernel/ptrace.c
index 9d1487d..5104528 100644
--- a/arch/mips/kernel/ptrace.c
+++ b/arch/mips/kernel/ptrace.c
@@ -770,6 +770,8 @@
 	long ret = 0;
 	user_exit();
 
+	current_thread_info()->syscall = syscall;
+
 	if (secure_computing() == -1)
 		return -1;
 
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 00cad10..6e8de80 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -181,6 +181,7 @@
 	sll	t1, t0, 2
 	beqz	v0, einval
 	lw	t2, sys_call_table(t1)		# syscall routine
+	sw	a0, PT_R2(sp)			# call routine directly on restart
 
 	/* Some syscalls like execve get their arguments from struct pt_regs
 	   and claim zero arguments in the syscall table. Thus we have to
@@ -580,3 +581,4 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 4355 */
+	PTR	sys_execveat
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 5251565..ad4d4463 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -435,4 +435,5 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 5315 */
+	PTR	sys_execveat
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index 77e7439..446cc65 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -428,4 +428,5 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf
+	PTR	compat_sys_execveat		/* 6320 */
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 6f8db9f..d07b210 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -186,6 +186,7 @@
 	dsll	t1, t0, 3
 	beqz	v0, einval
 	ld	t2, sys32_call_table(t1)		# syscall routine
+	sd	a0, PT_R2(sp)		# call routine directly on restart
 
 	move	a0, a1			# shift argument registers
 	move	a1, a2
@@ -565,4 +566,5 @@
 	PTR	sys_getrandom
 	PTR	sys_memfd_create
 	PTR	sys_bpf				/* 4355 */
+	PTR	compat_sys_execveat
 	.size	sys32_call_table,.-sys32_call_table
diff --git a/arch/mips/kernel/smp-cmp.c b/arch/mips/kernel/smp-cmp.c
index 1e0a93c..e36a859 100644
--- a/arch/mips/kernel/smp-cmp.c
+++ b/arch/mips/kernel/smp-cmp.c
@@ -44,8 +44,8 @@
 	struct cpuinfo_mips *c __maybe_unused = &current_cpu_data;
 
 	/* Assume GIC is present */
-	change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 | STATUSF_IP6 |
-				 STATUSF_IP7);
+	change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 | STATUSF_IP4 |
+				 STATUSF_IP5 | STATUSF_IP6 | STATUSF_IP7);
 
 	/* Enable per-cpu interrupts: platform specific */
 
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index ad86951..17ea705 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -161,7 +161,8 @@
 #ifdef CONFIG_MIPS_GIC
 	/* This is Malta specific: IPI,performance and timer interrupts */
 	if (gic_present)
-		change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
+		change_c0_status(ST0_IM, STATUSF_IP2 | STATUSF_IP3 |
+					 STATUSF_IP4 | STATUSF_IP5 |
 					 STATUSF_IP6 | STATUSF_IP7);
 	else
 #endif
diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c
index c94c4e9..1c0d8c5 100644
--- a/arch/mips/kernel/smp.c
+++ b/arch/mips/kernel/smp.c
@@ -123,10 +123,10 @@
 	unsigned int cpu;
 
 	cpu_probe();
-	cpu_report();
 	per_cpu_trap_init(false);
 	mips_clockevent_init();
 	mp_ops->init_secondary();
+	cpu_report();
 
 	/*
 	 * XXX parity protection should be folded in here when it's converted
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index ad3d203..c3b41e2 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -1231,7 +1231,8 @@
 
 		/* Restore the scalar FP control & status register */
 		if (!was_fpu_owner)
-			asm volatile("ctc1 %0, $31" : : "r"(current->thread.fpu.fcr31));
+			write_32bit_cp1_register(CP1_STATUS,
+						 current->thread.fpu.fcr31);
 	}
 
 out:
diff --git a/arch/mips/mm/tlb-r4k.c b/arch/mips/mm/tlb-r4k.c
index e90b2e8..30639a6 100644
--- a/arch/mips/mm/tlb-r4k.c
+++ b/arch/mips/mm/tlb-r4k.c
@@ -489,6 +489,8 @@
 #ifdef CONFIG_64BIT
 		pg |= PG_ELPA;
 #endif
+		if (cpu_has_rixiex)
+			pg |= PG_IEC;
 		write_c0_pagegrain(pg);
 	}
 
diff --git a/arch/mn10300/include/asm/cacheflush.h b/arch/mn10300/include/asm/cacheflush.h
index faed902..6d6df83 100644
--- a/arch/mn10300/include/asm/cacheflush.h
+++ b/arch/mn10300/include/asm/cacheflush.h
@@ -159,13 +159,6 @@
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 	memcpy(dst, src, len)
 
-/*
- * Internal debugging function
- */
-#ifdef CONFIG_DEBUG_PAGEALLOC
-extern void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_CACHEFLUSH_H */
diff --git a/arch/powerpc/include/asm/cacheflush.h b/arch/powerpc/include/asm/cacheflush.h
index 5b93122..30b35ff 100644
--- a/arch/powerpc/include/asm/cacheflush.h
+++ b/arch/powerpc/include/asm/cacheflush.h
@@ -60,13 +60,6 @@
 #define copy_from_user_page(vma, page, vaddr, dst, src, len) \
 	memcpy(dst, src, len)
 
-
-
-#ifdef CONFIG_DEBUG_PAGEALLOC
-/* internal debugging function */
-void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_POWERPC_CACHEFLUSH_H */
diff --git a/arch/s390/include/asm/cacheflush.h b/arch/s390/include/asm/cacheflush.h
index 3e20383..58fae7d 100644
--- a/arch/s390/include/asm/cacheflush.h
+++ b/arch/s390/include/asm/cacheflush.h
@@ -4,10 +4,6 @@
 /* Caches aren't brain-dead on the s390. */
 #include <asm-generic/cacheflush.h>
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
diff --git a/arch/sparc/include/asm/cacheflush_64.h b/arch/sparc/include/asm/cacheflush_64.h
index 3896537..68513c4 100644
--- a/arch/sparc/include/asm/cacheflush_64.h
+++ b/arch/sparc/include/asm/cacheflush_64.h
@@ -74,11 +74,6 @@
 #define flush_cache_vmap(start, end)		do { } while (0)
 #define flush_cache_vunmap(start, end)		do { } while (0)
 
-#ifdef CONFIG_DEBUG_PAGEALLOC
-/* internal debugging function */
-void kernel_map_pages(struct page *page, int numpages, int enable);
-#endif
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _SPARC64_CACHEFLUSH_H */
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 15c2909..36a8361 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -552,7 +552,7 @@
 	int error;
 
 	if (paravirt_enabled() || dis_ucode_ldr)
-		return 0;
+		return -EINVAL;
 
 	if (c->x86_vendor == X86_VENDOR_INTEL)
 		microcode_ops = init_intel_microcode();
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 7b20bcc..2fb3847 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -448,6 +448,22 @@
 			DMI_MATCH(DMI_PRODUCT_NAME, "ftServer"),
 		},
 	},
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R32"),
+                },
+        },
+        {
+                .callback = set_scan_all,
+                .ident = "Stratus/NEC ftServer",
+                .matches = {
+                        DMI_MATCH(DMI_SYS_VENDOR, "NEC"),
+                        DMI_MATCH(DMI_PRODUCT_NAME, "Express5800/R31"),
+                },
+        },
 	{}
 };
 
diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c
index 4f3febf..e75737f 100644
--- a/drivers/acpi/acpi_lpss.c
+++ b/drivers/acpi/acpi_lpss.c
@@ -1,7 +1,7 @@
 /*
  * ACPI support for Intel Lynxpoint LPSS.
  *
- * Copyright (C) 2013, 2014, Intel Corporation
+ * Copyright (C) 2013, Intel Corporation
  * Authors: Mika Westerberg <mika.westerberg@linux.intel.com>
  *          Rafael J. Wysocki <rafael.j.wysocki@intel.com>
  *
@@ -60,8 +60,6 @@
 #define LPSS_CLK_DIVIDER		BIT(2)
 #define LPSS_LTR			BIT(3)
 #define LPSS_SAVE_CTX			BIT(4)
-#define LPSS_DEV_PROXY			BIT(5)
-#define LPSS_PROXY_REQ			BIT(6)
 
 struct lpss_private_data;
 
@@ -72,10 +70,8 @@
 	void (*setup)(struct lpss_private_data *pdata);
 };
 
-static struct device *proxy_device;
-
 static struct lpss_device_desc lpss_dma_desc = {
-	.flags = LPSS_CLK | LPSS_PROXY_REQ,
+	.flags = LPSS_CLK,
 };
 
 struct lpss_private_data {
@@ -150,24 +146,22 @@
 };
 
 static struct lpss_device_desc byt_uart_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX |
-		 LPSS_DEV_PROXY,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
 	.setup = lpss_uart_setup,
 };
 
 static struct lpss_device_desc byt_spi_dev_desc = {
-	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX |
-		 LPSS_DEV_PROXY,
+	.flags = LPSS_CLK | LPSS_CLK_GATE | LPSS_CLK_DIVIDER | LPSS_SAVE_CTX,
 	.prv_offset = 0x400,
 };
 
 static struct lpss_device_desc byt_sdio_dev_desc = {
-	.flags = LPSS_CLK | LPSS_DEV_PROXY,
+	.flags = LPSS_CLK,
 };
 
 static struct lpss_device_desc byt_i2c_dev_desc = {
-	.flags = LPSS_CLK | LPSS_SAVE_CTX | LPSS_DEV_PROXY,
+	.flags = LPSS_CLK | LPSS_SAVE_CTX,
 	.prv_offset = 0x800,
 	.setup = byt_i2c_setup,
 };
@@ -374,8 +368,6 @@
 	adev->driver_data = pdata;
 	pdev = acpi_create_platform_device(adev);
 	if (!IS_ERR_OR_NULL(pdev)) {
-		if (!proxy_device && dev_desc->flags & LPSS_DEV_PROXY)
-			proxy_device = &pdev->dev;
 		return 1;
 	}
 
@@ -600,14 +592,7 @@
 	if (pdata->dev_desc->flags & LPSS_SAVE_CTX)
 		acpi_lpss_save_ctx(dev, pdata);
 
-	ret = acpi_dev_runtime_suspend(dev);
-	if (ret)
-		return ret;
-
-	if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device)
-		return pm_runtime_put_sync_suspend(proxy_device);
-
-	return 0;
+	return acpi_dev_runtime_suspend(dev);
 }
 
 static int acpi_lpss_runtime_resume(struct device *dev)
@@ -615,12 +600,6 @@
 	struct lpss_private_data *pdata = acpi_driver_data(ACPI_COMPANION(dev));
 	int ret;
 
-	if (pdata->dev_desc->flags & LPSS_PROXY_REQ && proxy_device) {
-		ret = pm_runtime_get_sync(proxy_device);
-		if (ret)
-			return ret;
-	}
-
 	ret = acpi_dev_runtime_resume(dev);
 	if (ret)
 		return ret;
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
index 0d8694f..0fd5927 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_device_queue_manager.c
@@ -822,7 +822,7 @@
 	 * Unconditionally decrement this counter, regardless of the queue's
 	 * type.
 	 */
-	dqm->total_queue_count++;
+	dqm->total_queue_count--;
 	pr_debug("Total of %d queues are accountable so far\n",
 			dqm->total_queue_count);
 	mutex_unlock(&dqm->lock);
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_module.c b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
index a8be6df..1c385c2 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_module.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_module.c
@@ -95,10 +95,10 @@
 	}
 
 	/* Verify module parameters */
-	if ((max_num_of_queues_per_device < 0) ||
+	if ((max_num_of_queues_per_device < 1) ||
 		(max_num_of_queues_per_device >
 			KFD_MAX_NUM_OF_QUEUES_PER_DEVICE)) {
-		pr_err("kfd: max_num_of_queues_per_device must be between 0 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
+		pr_err("kfd: max_num_of_queues_per_device must be between 1 to KFD_MAX_NUM_OF_QUEUES_PER_DEVICE\n");
 		return -1;
 	}
 
diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
index f37cf5e..2fda1927 100644
--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
@@ -315,7 +315,11 @@
 	BUG_ON(!pqm);
 
 	pqn = get_queue_by_qid(pqm, qid);
-	BUG_ON(!pqn);
+	if (!pqn) {
+		pr_debug("amdkfd: No queue %d exists for update operation\n",
+				qid);
+		return -EFAULT;
+	}
 
 	pqn->q->properties.queue_address = p->queue_address;
 	pqn->q->properties.queue_size = p->queue_size;
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.c b/drivers/gpu/drm/cirrus/cirrus_drv.c
index c2a1cba..b914003 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.c
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.c
@@ -16,9 +16,12 @@
 #include "cirrus_drv.h"
 
 int cirrus_modeset = -1;
+int cirrus_bpp = 24;
 
 MODULE_PARM_DESC(modeset, "Disable/Enable modesetting");
 module_param_named(modeset, cirrus_modeset, int, 0400);
+MODULE_PARM_DESC(bpp, "Max bits-per-pixel (default:24)");
+module_param_named(bpp, cirrus_bpp, int, 0400);
 
 /*
  * This is the generic driver code. This binds the driver to the drm core,
diff --git a/drivers/gpu/drm/cirrus/cirrus_drv.h b/drivers/gpu/drm/cirrus/cirrus_drv.h
index 693a456..7050615 100644
--- a/drivers/gpu/drm/cirrus/cirrus_drv.h
+++ b/drivers/gpu/drm/cirrus/cirrus_drv.h
@@ -262,4 +262,7 @@
 
 int cirrus_bo_push_sysram(struct cirrus_bo *bo);
 int cirrus_bo_pin(struct cirrus_bo *bo, u32 pl_flag, u64 *gpu_addr);
+
+extern int cirrus_bpp;
+
 #endif				/* __CIRRUS_DRV_H__ */
diff --git a/drivers/gpu/drm/cirrus/cirrus_main.c b/drivers/gpu/drm/cirrus/cirrus_main.c
index 4c2d68e..e4b9766 100644
--- a/drivers/gpu/drm/cirrus/cirrus_main.c
+++ b/drivers/gpu/drm/cirrus/cirrus_main.c
@@ -320,6 +320,8 @@
 	const int max_pitch = 0x1FF << 3; /* (4096 - 1) & ~111b bytes */
 	const int max_size = cdev->mc.vram_size;
 
+	if (bpp > cirrus_bpp)
+		return false;
 	if (bpp > 32)
 		return false;
 
diff --git a/drivers/gpu/drm/cirrus/cirrus_mode.c b/drivers/gpu/drm/cirrus/cirrus_mode.c
index 99d4a74..61385f2 100644
--- a/drivers/gpu/drm/cirrus/cirrus_mode.c
+++ b/drivers/gpu/drm/cirrus/cirrus_mode.c
@@ -501,8 +501,13 @@
 	int count;
 
 	/* Just add a static list of modes */
-	count = drm_add_modes_noedid(connector, 1280, 1024);
-	drm_set_preferred_mode(connector, 1024, 768);
+	if (cirrus_bpp <= 24) {
+		count = drm_add_modes_noedid(connector, 1280, 1024);
+		drm_set_preferred_mode(connector, 1024, 768);
+	} else {
+		count = drm_add_modes_noedid(connector, 800, 600);
+		drm_set_preferred_mode(connector, 800, 600);
+	}
 	return count;
 }
 
diff --git a/drivers/gpu/drm/radeon/radeon_benchmark.c b/drivers/gpu/drm/radeon/radeon_benchmark.c
index 9e7f23dd..87d5fb2 100644
--- a/drivers/gpu/drm/radeon/radeon_benchmark.c
+++ b/drivers/gpu/drm/radeon/radeon_benchmark.c
@@ -34,7 +34,8 @@
 
 static int radeon_benchmark_do_move(struct radeon_device *rdev, unsigned size,
 				    uint64_t saddr, uint64_t daddr,
-				    int flag, int n)
+				    int flag, int n,
+				    struct reservation_object *resv)
 {
 	unsigned long start_jiffies;
 	unsigned long end_jiffies;
@@ -47,12 +48,12 @@
 		case RADEON_BENCHMARK_COPY_DMA:
 			fence = radeon_copy_dma(rdev, saddr, daddr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						resv);
 			break;
 		case RADEON_BENCHMARK_COPY_BLIT:
 			fence = radeon_copy_blit(rdev, saddr, daddr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 resv);
 			break;
 		default:
 			DRM_ERROR("Unknown copy method\n");
@@ -120,7 +121,8 @@
 
 	if (rdev->asic->copy.dma) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_DMA, n);
+						RADEON_BENCHMARK_COPY_DMA, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
@@ -130,7 +132,8 @@
 
 	if (rdev->asic->copy.blit) {
 		time = radeon_benchmark_do_move(rdev, size, saddr, daddr,
-						RADEON_BENCHMARK_COPY_BLIT, n);
+						RADEON_BENCHMARK_COPY_BLIT, n,
+						dobj->tbo.resv);
 		if (time < 0)
 			goto out_cleanup;
 		if (time > 0)
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index 1021169..913fafa 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -960,6 +960,9 @@
 	if (pll->flags & RADEON_PLL_USE_FRAC_FB_DIV &&
 	    pll->flags & RADEON_PLL_USE_REF_DIV)
 		ref_div_max = pll->reference_div;
+	else if (pll->flags & RADEON_PLL_PREFER_MINM_OVER_MAXP)
+		/* fix for problems on RS880 */
+		ref_div_max = min(pll->max_ref_div, 7u);
 	else
 		ref_div_max = pll->max_ref_div;
 
diff --git a/drivers/gpu/drm/radeon/radeon_gem.c b/drivers/gpu/drm/radeon/radeon_gem.c
index d0b4f7d..ac3c131 100644
--- a/drivers/gpu/drm/radeon/radeon_gem.c
+++ b/drivers/gpu/drm/radeon/radeon_gem.c
@@ -146,7 +146,8 @@
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return 0;
 	}
 
@@ -176,7 +177,8 @@
 	struct radeon_bo_va *bo_va;
 	int r;
 
-	if (rdev->family < CHIP_CAYMAN) {
+	if ((rdev->family < CHIP_CAYMAN) ||
+	    (!rdev->accel_working)) {
 		return;
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_kms.c b/drivers/gpu/drm/radeon/radeon_kms.c
index 3cf9c1f..686411e 100644
--- a/drivers/gpu/drm/radeon/radeon_kms.c
+++ b/drivers/gpu/drm/radeon/radeon_kms.c
@@ -605,14 +605,14 @@
 			return -ENOMEM;
 		}
 
-		vm = &fpriv->vm;
-		r = radeon_vm_init(rdev, vm);
-		if (r) {
-			kfree(fpriv);
-			return r;
-		}
-
 		if (rdev->accel_working) {
+			vm = &fpriv->vm;
+			r = radeon_vm_init(rdev, vm);
+			if (r) {
+				kfree(fpriv);
+				return r;
+			}
+
 			r = radeon_bo_reserve(rdev->ring_tmp_bo.bo, false);
 			if (r) {
 				radeon_vm_fini(rdev, vm);
@@ -668,9 +668,9 @@
 					radeon_vm_bo_rmv(rdev, vm->ib_bo_va);
 				radeon_bo_unreserve(rdev->ring_tmp_bo.bo);
 			}
+			radeon_vm_fini(rdev, vm);
 		}
 
-		radeon_vm_fini(rdev, vm);
 		kfree(fpriv);
 		file_priv->driver_priv = NULL;
 	}
diff --git a/drivers/gpu/drm/radeon/radeon_test.c b/drivers/gpu/drm/radeon/radeon_test.c
index 07b506b..79181816 100644
--- a/drivers/gpu/drm/radeon/radeon_test.c
+++ b/drivers/gpu/drm/radeon/radeon_test.c
@@ -119,11 +119,11 @@
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, gtt_addr, vram_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, gtt_addr, vram_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed GTT->VRAM copy %d\n", i);
 			r = PTR_ERR(fence);
@@ -170,11 +170,11 @@
 		if (ring == R600_RING_TYPE_DMA_INDEX)
 			fence = radeon_copy_dma(rdev, vram_addr, gtt_addr,
 						size / RADEON_GPU_PAGE_SIZE,
-						NULL);
+						vram_obj->tbo.resv);
 		else
 			fence = radeon_copy_blit(rdev, vram_addr, gtt_addr,
 						 size / RADEON_GPU_PAGE_SIZE,
-						 NULL);
+						 vram_obj->tbo.resv);
 		if (IS_ERR(fence)) {
 			DRM_ERROR("Failed VRAM->GTT copy %d\n", i);
 			r = PTR_ERR(fence);
diff --git a/drivers/gpu/drm/radeon/radeon_vm.c b/drivers/gpu/drm/radeon/radeon_vm.c
index 06d2246..2a5a4a9 100644
--- a/drivers/gpu/drm/radeon/radeon_vm.c
+++ b/drivers/gpu/drm/radeon/radeon_vm.c
@@ -743,9 +743,11 @@
 	 */
 
 	/* NI is optimized for 256KB fragments, SI and newer for 64KB */
-	uint64_t frag_flags = rdev->family == CHIP_CAYMAN ?
+	uint64_t frag_flags = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ?
 			R600_PTE_FRAG_256KB : R600_PTE_FRAG_64KB;
-	uint64_t frag_align = rdev->family == CHIP_CAYMAN ? 0x200 : 0x80;
+	uint64_t frag_align = ((rdev->family == CHIP_CAYMAN) ||
+			       (rdev->family == CHIP_ARUBA)) ? 0x200 : 0x80;
 
 	uint64_t frag_start = ALIGN(pe_start, frag_align);
 	uint64_t frag_end = pe_end & ~(frag_align - 1);
diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index b716b08..643c08a 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -258,6 +258,5 @@
 
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
-IB_UVERBS_DECLARE_EX_CMD(query_device);
 
 #endif /* UVERBS_H */
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 532d8eba8..b7943ff 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -400,52 +400,6 @@
 	return ret;
 }
 
-static void copy_query_dev_fields(struct ib_uverbs_file *file,
-				  struct ib_uverbs_query_device_resp *resp,
-				  struct ib_device_attr *attr)
-{
-	resp->fw_ver		= attr->fw_ver;
-	resp->node_guid		= file->device->ib_dev->node_guid;
-	resp->sys_image_guid	= attr->sys_image_guid;
-	resp->max_mr_size	= attr->max_mr_size;
-	resp->page_size_cap	= attr->page_size_cap;
-	resp->vendor_id		= attr->vendor_id;
-	resp->vendor_part_id	= attr->vendor_part_id;
-	resp->hw_ver		= attr->hw_ver;
-	resp->max_qp		= attr->max_qp;
-	resp->max_qp_wr		= attr->max_qp_wr;
-	resp->device_cap_flags	= attr->device_cap_flags;
-	resp->max_sge		= attr->max_sge;
-	resp->max_sge_rd	= attr->max_sge_rd;
-	resp->max_cq		= attr->max_cq;
-	resp->max_cqe		= attr->max_cqe;
-	resp->max_mr		= attr->max_mr;
-	resp->max_pd		= attr->max_pd;
-	resp->max_qp_rd_atom	= attr->max_qp_rd_atom;
-	resp->max_ee_rd_atom	= attr->max_ee_rd_atom;
-	resp->max_res_rd_atom	= attr->max_res_rd_atom;
-	resp->max_qp_init_rd_atom	= attr->max_qp_init_rd_atom;
-	resp->max_ee_init_rd_atom	= attr->max_ee_init_rd_atom;
-	resp->atomic_cap		= attr->atomic_cap;
-	resp->max_ee			= attr->max_ee;
-	resp->max_rdd			= attr->max_rdd;
-	resp->max_mw			= attr->max_mw;
-	resp->max_raw_ipv6_qp		= attr->max_raw_ipv6_qp;
-	resp->max_raw_ethy_qp		= attr->max_raw_ethy_qp;
-	resp->max_mcast_grp		= attr->max_mcast_grp;
-	resp->max_mcast_qp_attach	= attr->max_mcast_qp_attach;
-	resp->max_total_mcast_qp_attach	= attr->max_total_mcast_qp_attach;
-	resp->max_ah			= attr->max_ah;
-	resp->max_fmr			= attr->max_fmr;
-	resp->max_map_per_fmr		= attr->max_map_per_fmr;
-	resp->max_srq			= attr->max_srq;
-	resp->max_srq_wr		= attr->max_srq_wr;
-	resp->max_srq_sge		= attr->max_srq_sge;
-	resp->max_pkeys			= attr->max_pkeys;
-	resp->local_ca_ack_delay	= attr->local_ca_ack_delay;
-	resp->phys_port_cnt		= file->device->ib_dev->phys_port_cnt;
-}
-
 ssize_t ib_uverbs_query_device(struct ib_uverbs_file *file,
 			       const char __user *buf,
 			       int in_len, int out_len)
@@ -466,7 +420,47 @@
 		return ret;
 
 	memset(&resp, 0, sizeof resp);
-	copy_query_dev_fields(file, &resp, &attr);
+
+	resp.fw_ver 		       = attr.fw_ver;
+	resp.node_guid 		       = file->device->ib_dev->node_guid;
+	resp.sys_image_guid 	       = attr.sys_image_guid;
+	resp.max_mr_size 	       = attr.max_mr_size;
+	resp.page_size_cap 	       = attr.page_size_cap;
+	resp.vendor_id 		       = attr.vendor_id;
+	resp.vendor_part_id 	       = attr.vendor_part_id;
+	resp.hw_ver 		       = attr.hw_ver;
+	resp.max_qp 		       = attr.max_qp;
+	resp.max_qp_wr 		       = attr.max_qp_wr;
+	resp.device_cap_flags 	       = attr.device_cap_flags;
+	resp.max_sge 		       = attr.max_sge;
+	resp.max_sge_rd 	       = attr.max_sge_rd;
+	resp.max_cq 		       = attr.max_cq;
+	resp.max_cqe 		       = attr.max_cqe;
+	resp.max_mr 		       = attr.max_mr;
+	resp.max_pd 		       = attr.max_pd;
+	resp.max_qp_rd_atom 	       = attr.max_qp_rd_atom;
+	resp.max_ee_rd_atom 	       = attr.max_ee_rd_atom;
+	resp.max_res_rd_atom 	       = attr.max_res_rd_atom;
+	resp.max_qp_init_rd_atom       = attr.max_qp_init_rd_atom;
+	resp.max_ee_init_rd_atom       = attr.max_ee_init_rd_atom;
+	resp.atomic_cap 	       = attr.atomic_cap;
+	resp.max_ee 		       = attr.max_ee;
+	resp.max_rdd 		       = attr.max_rdd;
+	resp.max_mw 		       = attr.max_mw;
+	resp.max_raw_ipv6_qp 	       = attr.max_raw_ipv6_qp;
+	resp.max_raw_ethy_qp 	       = attr.max_raw_ethy_qp;
+	resp.max_mcast_grp 	       = attr.max_mcast_grp;
+	resp.max_mcast_qp_attach       = attr.max_mcast_qp_attach;
+	resp.max_total_mcast_qp_attach = attr.max_total_mcast_qp_attach;
+	resp.max_ah 		       = attr.max_ah;
+	resp.max_fmr 		       = attr.max_fmr;
+	resp.max_map_per_fmr 	       = attr.max_map_per_fmr;
+	resp.max_srq 		       = attr.max_srq;
+	resp.max_srq_wr 	       = attr.max_srq_wr;
+	resp.max_srq_sge 	       = attr.max_srq_sge;
+	resp.max_pkeys 		       = attr.max_pkeys;
+	resp.local_ca_ack_delay        = attr.local_ca_ack_delay;
+	resp.phys_port_cnt	       = file->device->ib_dev->phys_port_cnt;
 
 	if (copy_to_user((void __user *) (unsigned long) cmd.response,
 			 &resp, sizeof resp))
@@ -3293,52 +3287,3 @@
 
 	return ret ? ret : in_len;
 }
-
-int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
-			      struct ib_udata *ucore,
-			      struct ib_udata *uhw)
-{
-	struct ib_uverbs_ex_query_device_resp resp;
-	struct ib_uverbs_ex_query_device  cmd;
-	struct ib_device_attr attr;
-	struct ib_device *device;
-	int err;
-
-	device = file->device->ib_dev;
-	if (ucore->inlen < sizeof(cmd))
-		return -EINVAL;
-
-	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
-	if (err)
-		return err;
-
-	if (cmd.reserved)
-		return -EINVAL;
-
-	err = device->query_device(device, &attr);
-	if (err)
-		return err;
-
-	memset(&resp, 0, sizeof(resp));
-	copy_query_dev_fields(file, &resp.base, &attr);
-	resp.comp_mask = 0;
-
-#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
-	if (cmd.comp_mask & IB_USER_VERBS_EX_QUERY_DEVICE_ODP) {
-		resp.odp_caps.general_caps = attr.odp_caps.general_caps;
-		resp.odp_caps.per_transport_caps.rc_odp_caps =
-			attr.odp_caps.per_transport_caps.rc_odp_caps;
-		resp.odp_caps.per_transport_caps.uc_odp_caps =
-			attr.odp_caps.per_transport_caps.uc_odp_caps;
-		resp.odp_caps.per_transport_caps.ud_odp_caps =
-			attr.odp_caps.per_transport_caps.ud_odp_caps;
-		resp.comp_mask |= IB_USER_VERBS_EX_QUERY_DEVICE_ODP;
-	}
-#endif
-
-	err = ib_copy_to_udata(ucore, &resp, sizeof(resp));
-	if (err)
-		return err;
-
-	return 0;
-}
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index e6c23b9..5db1a8c 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -123,7 +123,6 @@
 				    struct ib_udata *uhw) = {
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
 	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow,
-	[IB_USER_VERBS_EX_CMD_QUERY_DEVICE]	= ib_uverbs_ex_query_device
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index 8a87404..03bf812 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -1331,8 +1331,6 @@
 		(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ)		|
 		(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ)		|
 		(1ull << IB_USER_VERBS_CMD_OPEN_QP);
-	dev->ib_dev.uverbs_ex_cmd_mask =
-		(1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE);
 
 	dev->ib_dev.query_device	= mlx5_ib_query_device;
 	dev->ib_dev.query_port		= mlx5_ib_query_port;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index 8ba80a6..d7562be 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -98,15 +98,9 @@
 
 	IPOIB_MCAST_FLAG_FOUND	  = 0,	/* used in set_multicast_list */
 	IPOIB_MCAST_FLAG_SENDONLY = 1,
-	/*
-	 * For IPOIB_MCAST_FLAG_BUSY
-	 * When set, in flight join and mcast->mc is unreliable
-	 * When clear and mcast->mc IS_ERR_OR_NULL, need to restart or
-	 *   haven't started yet
-	 * When clear and mcast->mc is valid pointer, join was successful
-	 */
-	IPOIB_MCAST_FLAG_BUSY	  = 2,
+	IPOIB_MCAST_FLAG_BUSY	  = 2,	/* joining or already joined */
 	IPOIB_MCAST_FLAG_ATTACHED = 3,
+	IPOIB_MCAST_JOIN_STARTED  = 4,
 
 	MAX_SEND_CQE		  = 16,
 	IPOIB_CM_COPYBREAK	  = 256,
@@ -323,7 +317,6 @@
 	struct list_head multicast_list;
 	struct rb_root multicast_tree;
 
-	struct workqueue_struct *wq;
 	struct delayed_work mcast_task;
 	struct work_struct carrier_on_task;
 	struct work_struct flush_light;
@@ -484,10 +477,10 @@
 void ipoib_pkey_event(struct work_struct *work);
 void ipoib_ib_dev_cleanup(struct net_device *dev);
 
-int ipoib_ib_dev_open(struct net_device *dev);
+int ipoib_ib_dev_open(struct net_device *dev, int flush);
 int ipoib_ib_dev_up(struct net_device *dev);
-int ipoib_ib_dev_down(struct net_device *dev);
-int ipoib_ib_dev_stop(struct net_device *dev);
+int ipoib_ib_dev_down(struct net_device *dev, int flush);
+int ipoib_ib_dev_stop(struct net_device *dev, int flush);
 void ipoib_pkey_dev_check_presence(struct net_device *dev);
 
 int ipoib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
@@ -499,7 +492,7 @@
 
 void ipoib_mcast_restart_task(struct work_struct *work);
 int ipoib_mcast_start_thread(struct net_device *dev);
-int ipoib_mcast_stop_thread(struct net_device *dev);
+int ipoib_mcast_stop_thread(struct net_device *dev, int flush);
 
 void ipoib_mcast_dev_down(struct net_device *dev);
 void ipoib_mcast_dev_flush(struct net_device *dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_cm.c b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
index 56959ad..933efce 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_cm.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_cm.c
@@ -474,7 +474,7 @@
 	}
 
 	spin_lock_irq(&priv->lock);
-	queue_delayed_work(priv->wq,
+	queue_delayed_work(ipoib_workqueue,
 			   &priv->cm.stale_task, IPOIB_CM_RX_DELAY);
 	/* Add this entry to passive ids list head, but do not re-add it
 	 * if IB_EVENT_QP_LAST_WQE_REACHED has moved it to flush list. */
@@ -576,7 +576,7 @@
 			spin_lock_irqsave(&priv->lock, flags);
 			list_splice_init(&priv->cm.rx_drain_list, &priv->cm.rx_reap_list);
 			ipoib_cm_start_rx_drain(priv);
-			queue_work(priv->wq, &priv->cm.rx_reap_task);
+			queue_work(ipoib_workqueue, &priv->cm.rx_reap_task);
 			spin_unlock_irqrestore(&priv->lock, flags);
 		} else
 			ipoib_warn(priv, "cm recv completion event with wrid %d (> %d)\n",
@@ -603,7 +603,7 @@
 				spin_lock_irqsave(&priv->lock, flags);
 				list_move(&p->list, &priv->cm.rx_reap_list);
 				spin_unlock_irqrestore(&priv->lock, flags);
-				queue_work(priv->wq, &priv->cm.rx_reap_task);
+				queue_work(ipoib_workqueue, &priv->cm.rx_reap_task);
 			}
 			return;
 		}
@@ -827,7 +827,7 @@
 
 		if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 			list_move(&tx->list, &priv->cm.reap_list);
-			queue_work(priv->wq, &priv->cm.reap_task);
+			queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		}
 
 		clear_bit(IPOIB_FLAG_OPER_UP, &tx->flags);
@@ -1255,7 +1255,7 @@
 
 		if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 			list_move(&tx->list, &priv->cm.reap_list);
-			queue_work(priv->wq, &priv->cm.reap_task);
+			queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		}
 
 		spin_unlock_irqrestore(&priv->lock, flags);
@@ -1284,7 +1284,7 @@
 	tx->dev = dev;
 	list_add(&tx->list, &priv->cm.start_list);
 	set_bit(IPOIB_FLAG_INITIALIZED, &tx->flags);
-	queue_work(priv->wq, &priv->cm.start_task);
+	queue_work(ipoib_workqueue, &priv->cm.start_task);
 	return tx;
 }
 
@@ -1295,7 +1295,7 @@
 	if (test_and_clear_bit(IPOIB_FLAG_INITIALIZED, &tx->flags)) {
 		spin_lock_irqsave(&priv->lock, flags);
 		list_move(&tx->list, &priv->cm.reap_list);
-		queue_work(priv->wq, &priv->cm.reap_task);
+		queue_work(ipoib_workqueue, &priv->cm.reap_task);
 		ipoib_dbg(priv, "Reap connection for gid %pI6\n",
 			  tx->neigh->daddr + 4);
 		tx->neigh = NULL;
@@ -1417,7 +1417,7 @@
 
 	skb_queue_tail(&priv->cm.skb_queue, skb);
 	if (e)
-		queue_work(priv->wq, &priv->cm.skb_task);
+		queue_work(ipoib_workqueue, &priv->cm.skb_task);
 }
 
 static void ipoib_cm_rx_reap(struct work_struct *work)
@@ -1450,7 +1450,7 @@
 	}
 
 	if (!list_empty(&priv->cm.passive_ids))
-		queue_delayed_work(priv->wq,
+		queue_delayed_work(ipoib_workqueue,
 				   &priv->cm.stale_task, IPOIB_CM_RX_DELAY);
 	spin_unlock_irq(&priv->lock);
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index fe65abb..72626c34 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -655,7 +655,7 @@
 	__ipoib_reap_ah(dev);
 
 	if (!test_bit(IPOIB_STOP_REAPER, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->ah_reap_task,
+		queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
 				   round_jiffies_relative(HZ));
 }
 
@@ -664,7 +664,7 @@
 	drain_tx_cq((struct net_device *)ctx);
 }
 
-int ipoib_ib_dev_open(struct net_device *dev)
+int ipoib_ib_dev_open(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	int ret;
@@ -696,7 +696,7 @@
 	}
 
 	clear_bit(IPOIB_STOP_REAPER, &priv->flags);
-	queue_delayed_work(priv->wq, &priv->ah_reap_task,
+	queue_delayed_work(ipoib_workqueue, &priv->ah_reap_task,
 			   round_jiffies_relative(HZ));
 
 	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
@@ -706,7 +706,7 @@
 dev_stop:
 	if (!test_and_set_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
 		napi_enable(&priv->napi);
-	ipoib_ib_dev_stop(dev);
+	ipoib_ib_dev_stop(dev, flush);
 	return -1;
 }
 
@@ -738,7 +738,7 @@
 	return ipoib_mcast_start_thread(dev);
 }
 
-int ipoib_ib_dev_down(struct net_device *dev)
+int ipoib_ib_dev_down(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -747,7 +747,7 @@
 	clear_bit(IPOIB_FLAG_OPER_UP, &priv->flags);
 	netif_carrier_off(dev);
 
-	ipoib_mcast_stop_thread(dev);
+	ipoib_mcast_stop_thread(dev, flush);
 	ipoib_mcast_dev_flush(dev);
 
 	ipoib_flush_paths(dev);
@@ -807,7 +807,7 @@
 	local_bh_enable();
 }
 
-int ipoib_ib_dev_stop(struct net_device *dev)
+int ipoib_ib_dev_stop(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 	struct ib_qp_attr qp_attr;
@@ -880,7 +880,8 @@
 	/* Wait for all AHs to be reaped */
 	set_bit(IPOIB_STOP_REAPER, &priv->flags);
 	cancel_delayed_work(&priv->ah_reap_task);
-	flush_workqueue(priv->wq);
+	if (flush)
+		flush_workqueue(ipoib_workqueue);
 
 	begin = jiffies;
 
@@ -917,7 +918,7 @@
 		    (unsigned long) dev);
 
 	if (dev->flags & IFF_UP) {
-		if (ipoib_ib_dev_open(dev)) {
+		if (ipoib_ib_dev_open(dev, 1)) {
 			ipoib_transport_dev_cleanup(dev);
 			return -ENODEV;
 		}
@@ -1039,12 +1040,12 @@
 	}
 
 	if (level >= IPOIB_FLUSH_NORMAL)
-		ipoib_ib_dev_down(dev);
+		ipoib_ib_dev_down(dev, 0);
 
 	if (level == IPOIB_FLUSH_HEAVY) {
 		if (test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags))
-			ipoib_ib_dev_stop(dev);
-		if (ipoib_ib_dev_open(dev) != 0)
+			ipoib_ib_dev_stop(dev, 0);
+		if (ipoib_ib_dev_open(dev, 0) != 0)
 			return;
 		if (netif_queue_stopped(dev))
 			netif_start_queue(dev);
@@ -1096,7 +1097,7 @@
 	 */
 	ipoib_flush_paths(dev);
 
-	ipoib_mcast_stop_thread(dev);
+	ipoib_mcast_stop_thread(dev, 1);
 	ipoib_mcast_dev_flush(dev);
 
 	ipoib_transport_dev_cleanup(dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 6bad17d..58b5aa3 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -108,7 +108,7 @@
 
 	set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
 
-	if (ipoib_ib_dev_open(dev)) {
+	if (ipoib_ib_dev_open(dev, 1)) {
 		if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
 			return 0;
 		goto err_disable;
@@ -139,7 +139,7 @@
 	return 0;
 
 err_stop:
-	ipoib_ib_dev_stop(dev);
+	ipoib_ib_dev_stop(dev, 1);
 
 err_disable:
 	clear_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
@@ -157,8 +157,8 @@
 
 	netif_stop_queue(dev);
 
-	ipoib_ib_dev_down(dev);
-	ipoib_ib_dev_stop(dev);
+	ipoib_ib_dev_down(dev, 1);
+	ipoib_ib_dev_stop(dev, 0);
 
 	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
 		struct ipoib_dev_priv *cpriv;
@@ -839,7 +839,7 @@
 		return;
 	}
 
-	queue_work(priv->wq, &priv->restart_task);
+	queue_work(ipoib_workqueue, &priv->restart_task);
 }
 
 static u32 ipoib_addr_hash(struct ipoib_neigh_hash *htbl, u8 *daddr)
@@ -954,7 +954,7 @@
 	__ipoib_reap_neigh(priv);
 
 	if (!test_bit(IPOIB_STOP_NEIGH_GC, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->neigh_reap_task,
+		queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
 				   arp_tbl.gc_interval);
 }
 
@@ -1133,7 +1133,7 @@
 
 	/* start garbage collection */
 	clear_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
-	queue_delayed_work(priv->wq, &priv->neigh_reap_task,
+	queue_delayed_work(ipoib_workqueue, &priv->neigh_reap_task,
 			   arp_tbl.gc_interval);
 
 	return 0;
@@ -1262,13 +1262,15 @@
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
+	if (ipoib_neigh_hash_init(priv) < 0)
+		goto out;
 	/* Allocate RX/TX "rings" to hold queued skbs */
 	priv->rx_ring =	kzalloc(ipoib_recvq_size * sizeof *priv->rx_ring,
 				GFP_KERNEL);
 	if (!priv->rx_ring) {
 		printk(KERN_WARNING "%s: failed to allocate RX ring (%d entries)\n",
 		       ca->name, ipoib_recvq_size);
-		goto out;
+		goto out_neigh_hash_cleanup;
 	}
 
 	priv->tx_ring = vzalloc(ipoib_sendq_size * sizeof *priv->tx_ring);
@@ -1283,24 +1285,16 @@
 	if (ipoib_ib_dev_init(dev, ca, port))
 		goto out_tx_ring_cleanup;
 
-	/*
-	 * Must be after ipoib_ib_dev_init so we can allocate a per
-	 * device wq there and use it here
-	 */
-	if (ipoib_neigh_hash_init(priv) < 0)
-		goto out_dev_uninit;
-
 	return 0;
 
-out_dev_uninit:
-	ipoib_ib_dev_cleanup(dev);
-
 out_tx_ring_cleanup:
 	vfree(priv->tx_ring);
 
 out_rx_ring_cleanup:
 	kfree(priv->rx_ring);
 
+out_neigh_hash_cleanup:
+	ipoib_neigh_hash_uninit(dev);
 out:
 	return -ENOMEM;
 }
@@ -1323,12 +1317,6 @@
 	}
 	unregister_netdevice_many(&head);
 
-	/*
-	 * Must be before ipoib_ib_dev_cleanup or we delete an in use
-	 * work queue
-	 */
-	ipoib_neigh_hash_uninit(dev);
-
 	ipoib_ib_dev_cleanup(dev);
 
 	kfree(priv->rx_ring);
@@ -1336,6 +1324,8 @@
 
 	priv->rx_ring = NULL;
 	priv->tx_ring = NULL;
+
+	ipoib_neigh_hash_uninit(dev);
 }
 
 static const struct header_ops ipoib_header_ops = {
@@ -1646,7 +1636,7 @@
 	/* Stop GC if started before flush */
 	set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 	cancel_delayed_work(&priv->neigh_reap_task);
-	flush_workqueue(priv->wq);
+	flush_workqueue(ipoib_workqueue);
 
 event_failed:
 	ipoib_dev_cleanup(priv->dev);
@@ -1717,7 +1707,7 @@
 		/* Stop GC */
 		set_bit(IPOIB_STOP_NEIGH_GC, &priv->flags);
 		cancel_delayed_work(&priv->neigh_reap_task);
-		flush_workqueue(priv->wq);
+		flush_workqueue(ipoib_workqueue);
 
 		unregister_netdev(priv->dev);
 		free_netdev(priv->dev);
@@ -1758,13 +1748,8 @@
 	 * unregister_netdev() and linkwatch_event take the rtnl lock,
 	 * so flush_scheduled_work() can deadlock during device
 	 * removal.
-	 *
-	 * In addition, bringing one device up and another down at the
-	 * same time can deadlock a single workqueue, so we have this
-	 * global fallback workqueue, but we also attempt to open a
-	 * per device workqueue each time we bring an interface up
 	 */
-	ipoib_workqueue = create_singlethread_workqueue("ipoib_flush");
+	ipoib_workqueue = create_singlethread_workqueue("ipoib");
 	if (!ipoib_workqueue) {
 		ret = -ENOMEM;
 		goto err_fs;
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index bc50dd0..ffb83b5 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -190,6 +190,12 @@
 		spin_unlock_irq(&priv->lock);
 		priv->tx_wr.wr.ud.remote_qkey = priv->qkey;
 		set_qkey = 1;
+
+		if (!ipoib_cm_admin_enabled(dev)) {
+			rtnl_lock();
+			dev_set_mtu(dev, min(priv->mcast_mtu, priv->admin_mtu));
+			rtnl_unlock();
+		}
 	}
 
 	if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)) {
@@ -271,27 +277,16 @@
 	struct ipoib_mcast *mcast = multicast->context;
 	struct net_device *dev = mcast->dev;
 
-	/*
-	 * We have to take the mutex to force mcast_sendonly_join to
-	 * return from ib_sa_multicast_join and set mcast->mc to a
-	 * valid value.  Otherwise we were racing with ourselves in
-	 * that we might fail here, but get a valid return from
-	 * ib_sa_multicast_join after we had cleared mcast->mc here,
-	 * resulting in mis-matched joins and leaves and a deadlock
-	 */
-	mutex_lock(&mcast_mutex);
-
 	/* We trap for port events ourselves. */
 	if (status == -ENETRESET)
-		goto out;
+		return 0;
 
 	if (!status)
 		status = ipoib_mcast_join_finish(mcast, &multicast->rec);
 
 	if (status) {
 		if (mcast->logcount++ < 20)
-			ipoib_dbg_mcast(netdev_priv(dev), "sendonly multicast "
-					"join failed for %pI6, status %d\n",
+			ipoib_dbg_mcast(netdev_priv(dev), "multicast join failed for %pI6, status %d\n",
 					mcast->mcmember.mgid.raw, status);
 
 		/* Flush out any queued packets */
@@ -301,15 +296,11 @@
 			dev_kfree_skb_any(skb_dequeue(&mcast->pkt_queue));
 		}
 		netif_tx_unlock_bh(dev);
+
+		/* Clear the busy flag so we try again */
+		status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY,
+					    &mcast->flags);
 	}
-out:
-	clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-	if (status)
-		mcast->mc = NULL;
-	complete(&mcast->done);
-	if (status == -ENETRESET)
-		status = 0;
-	mutex_unlock(&mcast_mutex);
 	return status;
 }
 
@@ -327,14 +318,12 @@
 	int ret = 0;
 
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags)) {
-		ipoib_dbg_mcast(priv, "device shutting down, no sendonly "
-				"multicast joins\n");
+		ipoib_dbg_mcast(priv, "device shutting down, no multicast joins\n");
 		return -ENODEV;
 	}
 
-	if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
-		ipoib_dbg_mcast(priv, "multicast entry busy, skipping "
-				"sendonly join\n");
+	if (test_and_set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)) {
+		ipoib_dbg_mcast(priv, "multicast entry busy, skipping\n");
 		return -EBUSY;
 	}
 
@@ -342,9 +331,6 @@
 	rec.port_gid = priv->local_gid;
 	rec.pkey     = cpu_to_be16(priv->pkey);
 
-	mutex_lock(&mcast_mutex);
-	init_completion(&mcast->done);
-	set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
 	mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca,
 					 priv->port, &rec,
 					 IB_SA_MCMEMBER_REC_MGID	|
@@ -357,14 +343,12 @@
 	if (IS_ERR(mcast->mc)) {
 		ret = PTR_ERR(mcast->mc);
 		clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-		complete(&mcast->done);
-		ipoib_warn(priv, "ib_sa_join_multicast for sendonly join "
-			   "failed (ret = %d)\n", ret);
+		ipoib_warn(priv, "ib_sa_join_multicast failed (ret = %d)\n",
+			   ret);
 	} else {
-		ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting "
-				"sendonly join\n", mcast->mcmember.mgid.raw);
+		ipoib_dbg_mcast(priv, "no multicast record for %pI6, starting join\n",
+				mcast->mcmember.mgid.raw);
 	}
-	mutex_unlock(&mcast_mutex);
 
 	return ret;
 }
@@ -375,29 +359,18 @@
 						   carrier_on_task);
 	struct ib_port_attr attr;
 
+	/*
+	 * Take rtnl_lock to avoid racing with ipoib_stop() and
+	 * turning the carrier back on while a device is being
+	 * removed.
+	 */
 	if (ib_query_port(priv->ca, priv->port, &attr) ||
 	    attr.state != IB_PORT_ACTIVE) {
 		ipoib_dbg(priv, "Keeping carrier off until IB port is active\n");
 		return;
 	}
 
-	/*
-	 * Take rtnl_lock to avoid racing with ipoib_stop() and
-	 * turning the carrier back on while a device is being
-	 * removed.  However, ipoib_stop() will attempt to flush
-	 * the workqueue while holding the rtnl lock, so loop
-	 * on trylock until either we get the lock or we see
-	 * FLAG_ADMIN_UP go away as that signals that we are bailing
-	 * and can safely ignore the carrier on work.
-	 */
-	while (!rtnl_trylock()) {
-		if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
-			return;
-		else
-			msleep(20);
-	}
-	if (!ipoib_cm_admin_enabled(priv->dev))
-		dev_set_mtu(priv->dev, min(priv->mcast_mtu, priv->admin_mtu));
+	rtnl_lock();
 	netif_carrier_on(priv->dev);
 	rtnl_unlock();
 }
@@ -412,63 +385,60 @@
 	ipoib_dbg_mcast(priv, "join completion for %pI6 (status %d)\n",
 			mcast->mcmember.mgid.raw, status);
 
-	/*
-	 * We have to take the mutex to force mcast_join to
-	 * return from ib_sa_multicast_join and set mcast->mc to a
-	 * valid value.  Otherwise we were racing with ourselves in
-	 * that we might fail here, but get a valid return from
-	 * ib_sa_multicast_join after we had cleared mcast->mc here,
-	 * resulting in mis-matched joins and leaves and a deadlock
-	 */
-	mutex_lock(&mcast_mutex);
-
 	/* We trap for port events ourselves. */
-	if (status == -ENETRESET)
+	if (status == -ENETRESET) {
+		status = 0;
 		goto out;
+	}
 
 	if (!status)
 		status = ipoib_mcast_join_finish(mcast, &multicast->rec);
 
 	if (!status) {
 		mcast->backoff = 1;
+		mutex_lock(&mcast_mutex);
 		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
-			queue_delayed_work(priv->wq, &priv->mcast_task, 0);
+			queue_delayed_work(ipoib_workqueue,
+					   &priv->mcast_task, 0);
+		mutex_unlock(&mcast_mutex);
 
 		/*
-		 * Defer carrier on work to priv->wq to avoid a
+		 * Defer carrier on work to ipoib_workqueue to avoid a
 		 * deadlock on rtnl_lock here.
 		 */
 		if (mcast == priv->broadcast)
-			queue_work(priv->wq, &priv->carrier_on_task);
-	} else {
-		if (mcast->logcount++ < 20) {
-			if (status == -ETIMEDOUT || status == -EAGAIN) {
-				ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n",
-						mcast->mcmember.mgid.raw, status);
-			} else {
-				ipoib_warn(priv, "multicast join failed for %pI6, status %d\n",
-					   mcast->mcmember.mgid.raw, status);
-			}
-		}
+			queue_work(ipoib_workqueue, &priv->carrier_on_task);
 
-		mcast->backoff *= 2;
-		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
-			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
-	}
-out:
-	spin_lock_irq(&priv->lock);
-	clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
-	if (status)
-		mcast->mc = NULL;
-	complete(&mcast->done);
-	if (status == -ENETRESET)
 		status = 0;
-	if (status && test_bit(IPOIB_MCAST_RUN, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->mcast_task,
+		goto out;
+	}
+
+	if (mcast->logcount++ < 20) {
+		if (status == -ETIMEDOUT || status == -EAGAIN) {
+			ipoib_dbg_mcast(priv, "multicast join failed for %pI6, status %d\n",
+					mcast->mcmember.mgid.raw, status);
+		} else {
+			ipoib_warn(priv, "multicast join failed for %pI6, status %d\n",
+				   mcast->mcmember.mgid.raw, status);
+		}
+	}
+
+	mcast->backoff *= 2;
+	if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
+		mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
+
+	/* Clear the busy flag so we try again */
+	status = test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+
+	mutex_lock(&mcast_mutex);
+	spin_lock_irq(&priv->lock);
+	if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
+		queue_delayed_work(ipoib_workqueue, &priv->mcast_task,
 				   mcast->backoff * HZ);
 	spin_unlock_irq(&priv->lock);
 	mutex_unlock(&mcast_mutex);
-
+out:
+	complete(&mcast->done);
 	return status;
 }
 
@@ -517,9 +487,10 @@
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
 	}
 
-	mutex_lock(&mcast_mutex);
-	init_completion(&mcast->done);
 	set_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags);
+	init_completion(&mcast->done);
+	set_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags);
+
 	mcast->mc = ib_sa_join_multicast(&ipoib_sa_client, priv->ca, priv->port,
 					 &rec, comp_mask, GFP_KERNEL,
 					 ipoib_mcast_join_complete, mcast);
@@ -533,11 +504,13 @@
 		if (mcast->backoff > IPOIB_MAX_BACKOFF_SECONDS)
 			mcast->backoff = IPOIB_MAX_BACKOFF_SECONDS;
 
+		mutex_lock(&mcast_mutex);
 		if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
-			queue_delayed_work(priv->wq, &priv->mcast_task,
+			queue_delayed_work(ipoib_workqueue,
+					   &priv->mcast_task,
 					   mcast->backoff * HZ);
+		mutex_unlock(&mcast_mutex);
 	}
-	mutex_unlock(&mcast_mutex);
 }
 
 void ipoib_mcast_join_task(struct work_struct *work)
@@ -574,8 +547,8 @@
 			ipoib_warn(priv, "failed to allocate broadcast group\n");
 			mutex_lock(&mcast_mutex);
 			if (test_bit(IPOIB_MCAST_RUN, &priv->flags))
-				queue_delayed_work(priv->wq, &priv->mcast_task,
-						   HZ);
+				queue_delayed_work(ipoib_workqueue,
+						   &priv->mcast_task, HZ);
 			mutex_unlock(&mcast_mutex);
 			return;
 		}
@@ -590,8 +563,7 @@
 	}
 
 	if (!test_bit(IPOIB_MCAST_FLAG_ATTACHED, &priv->broadcast->flags)) {
-		if (IS_ERR_OR_NULL(priv->broadcast->mc) &&
-		    !test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags))
+		if (!test_bit(IPOIB_MCAST_FLAG_BUSY, &priv->broadcast->flags))
 			ipoib_mcast_join(dev, priv->broadcast, 0);
 		return;
 	}
@@ -599,33 +571,23 @@
 	while (1) {
 		struct ipoib_mcast *mcast = NULL;
 
-		/*
-		 * Need the mutex so our flags are consistent, need the
-		 * priv->lock so we don't race with list removals in either
-		 * mcast_dev_flush or mcast_restart_task
-		 */
-		mutex_lock(&mcast_mutex);
 		spin_lock_irq(&priv->lock);
 		list_for_each_entry(mcast, &priv->multicast_list, list) {
-			if (IS_ERR_OR_NULL(mcast->mc) &&
-			    !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags) &&
-			    !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
+			if (!test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags)
+			    && !test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags)
+			    && !test_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
 				/* Found the next unjoined group */
 				break;
 			}
 		}
 		spin_unlock_irq(&priv->lock);
-		mutex_unlock(&mcast_mutex);
 
 		if (&mcast->list == &priv->multicast_list) {
 			/* All done */
 			break;
 		}
 
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			ipoib_mcast_sendonly_join(mcast);
-		else
-			ipoib_mcast_join(dev, mcast, 1);
+		ipoib_mcast_join(dev, mcast, 1);
 		return;
 	}
 
@@ -642,13 +604,13 @@
 
 	mutex_lock(&mcast_mutex);
 	if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
-		queue_delayed_work(priv->wq, &priv->mcast_task, 0);
+		queue_delayed_work(ipoib_workqueue, &priv->mcast_task, 0);
 	mutex_unlock(&mcast_mutex);
 
 	return 0;
 }
 
-int ipoib_mcast_stop_thread(struct net_device *dev)
+int ipoib_mcast_stop_thread(struct net_device *dev, int flush)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
 
@@ -659,7 +621,8 @@
 	cancel_delayed_work(&priv->mcast_task);
 	mutex_unlock(&mcast_mutex);
 
-	flush_workqueue(priv->wq);
+	if (flush)
+		flush_workqueue(ipoib_workqueue);
 
 	return 0;
 }
@@ -670,9 +633,6 @@
 	int ret = 0;
 
 	if (test_and_clear_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-		ipoib_warn(priv, "ipoib_mcast_leave on an in-flight join\n");
-
-	if (!IS_ERR_OR_NULL(mcast->mc))
 		ib_sa_free_multicast(mcast->mc);
 
 	if (test_and_clear_bit(IPOIB_MCAST_FLAG_ATTACHED, &mcast->flags)) {
@@ -725,8 +685,6 @@
 		memcpy(mcast->mcmember.mgid.raw, mgid, sizeof (union ib_gid));
 		__ipoib_mcast_add(dev, mcast);
 		list_add_tail(&mcast->list, &priv->multicast_list);
-		if (!test_and_set_bit(IPOIB_MCAST_RUN, &priv->flags))
-			queue_delayed_work(priv->wq, &priv->mcast_task, 0);
 	}
 
 	if (!mcast->ah) {
@@ -740,6 +698,8 @@
 		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
 			ipoib_dbg_mcast(priv, "no address vector, "
 					"but multicast join already started\n");
+		else if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
+			ipoib_mcast_sendonly_join(mcast);
 
 		/*
 		 * If lookup completes between here and out:, don't
@@ -799,12 +759,9 @@
 
 	spin_unlock_irqrestore(&priv->lock, flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
+	/* seperate between the wait to the leave*/
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
+		if (test_bit(IPOIB_MCAST_JOIN_STARTED, &mcast->flags))
 			wait_for_completion(&mcast->done);
 
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
@@ -837,6 +794,8 @@
 
 	ipoib_dbg_mcast(priv, "restarting multicast task\n");
 
+	ipoib_mcast_stop_thread(dev, 0);
+
 	local_irq_save(flags);
 	netif_addr_lock(dev);
 	spin_lock(&priv->lock);
@@ -921,38 +880,14 @@
 	netif_addr_unlock(dev);
 	local_irq_restore(flags);
 
-	/*
-	 * make sure the in-flight joins have finished before we attempt
-	 * to leave
-	 */
-	list_for_each_entry_safe(mcast, tmcast, &remove_list, list)
-		if (test_bit(IPOIB_MCAST_FLAG_BUSY, &mcast->flags))
-			wait_for_completion(&mcast->done);
-
-	/*
-	 * We have to cancel outside of the spinlock, but we have to
-	 * take the rtnl lock or else we race with the removal of
-	 * entries from the remove list in mcast_dev_flush as part
-	 * of ipoib_stop().  We detect the drop of the ADMIN_UP flag
-	 * to signal that we have hit this particular race, and we
-	 * return since we know we don't need to do anything else
-	 * anyway.
-	 */
-	while (!rtnl_trylock()) {
-		if (!test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
-			return;
-		else
-			msleep(20);
-	}
+	/* We have to cancel outside of the spinlock */
 	list_for_each_entry_safe(mcast, tmcast, &remove_list, list) {
 		ipoib_mcast_leave(mcast->dev, mcast);
 		ipoib_mcast_free(mcast);
 	}
-	/*
-	 * Restart our join task if needed
-	 */
-	ipoib_mcast_start_thread(dev);
-	rtnl_unlock();
+
+	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags))
+		ipoib_mcast_start_thread(dev);
 }
 
 #ifdef CONFIG_INFINIBAND_IPOIB_DEBUG
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index b72a753..c56d5d4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -145,20 +145,10 @@
 	int ret, size;
 	int i;
 
-	/*
-	 * the various IPoIB tasks assume they will never race against
-	 * themselves, so always use a single thread workqueue
-	 */
-	priv->wq = create_singlethread_workqueue("ipoib_wq");
-	if (!priv->wq) {
-		printk(KERN_WARNING "ipoib: failed to allocate device WQ\n");
-		return -ENODEV;
-	}
-
 	priv->pd = ib_alloc_pd(priv->ca);
 	if (IS_ERR(priv->pd)) {
 		printk(KERN_WARNING "%s: failed to allocate PD\n", ca->name);
-		goto out_free_wq;
+		return -ENODEV;
 	}
 
 	priv->mr = ib_get_dma_mr(priv->pd, IB_ACCESS_LOCAL_WRITE);
@@ -252,10 +242,6 @@
 
 out_free_pd:
 	ib_dealloc_pd(priv->pd);
-
-out_free_wq:
-	destroy_workqueue(priv->wq);
-	priv->wq = NULL;
 	return -ENODEV;
 }
 
@@ -284,12 +270,6 @@
 
 	if (ib_dealloc_pd(priv->pd))
 		ipoib_warn(priv, "ib_dealloc_pd failed\n");
-
-	if (priv->wq) {
-		flush_workqueue(priv->wq);
-		destroy_workqueue(priv->wq);
-		priv->wq = NULL;
-	}
 }
 
 void ipoib_event(struct ib_event_handler *handler,
diff --git a/drivers/irqchip/irq-mips-gic.c b/drivers/irqchip/irq-mips-gic.c
index 2b0468e..56b96c6 100644
--- a/drivers/irqchip/irq-mips-gic.c
+++ b/drivers/irqchip/irq-mips-gic.c
@@ -37,6 +37,7 @@
 static int gic_shared_intrs;
 static int gic_vpes;
 static unsigned int gic_cpu_pin;
+static unsigned int timer_cpu_pin;
 static struct irq_chip gic_level_irq_controller, gic_edge_irq_controller;
 
 static void __gic_irq_dispatch(void);
@@ -616,6 +617,8 @@
 			gic_write(GIC_REG(VPE_OTHER, GIC_VPE_COMPARE_MAP), val);
 			break;
 		case GIC_LOCAL_INT_TIMER:
+			/* CONFIG_MIPS_CMP workaround (see __gic_init) */
+			val = GIC_MAP_TO_PIN_MSK | timer_cpu_pin;
 			gic_write(GIC_REG(VPE_OTHER, GIC_VPE_TIMER_MAP), val);
 			break;
 		case GIC_LOCAL_INT_PERFCTR:
@@ -713,12 +716,36 @@
 	if (cpu_has_veic) {
 		/* Always use vector 1 in EIC mode */
 		gic_cpu_pin = 0;
+		timer_cpu_pin = gic_cpu_pin;
 		set_vi_handler(gic_cpu_pin + GIC_PIN_TO_VEC_OFFSET,
 			       __gic_irq_dispatch);
 	} else {
 		gic_cpu_pin = cpu_vec - GIC_CPU_PIN_OFFSET;
 		irq_set_chained_handler(MIPS_CPU_IRQ_BASE + cpu_vec,
 					gic_irq_dispatch);
+		/*
+		 * With the CMP implementation of SMP (deprecated), other CPUs
+		 * are started by the bootloader and put into a timer based
+		 * waiting poll loop. We must not re-route those CPU's local
+		 * timer interrupts as the wait instruction will never finish,
+		 * so just handle whatever CPU interrupt it is routed to by
+		 * default.
+		 *
+		 * This workaround should be removed when CMP support is
+		 * dropped.
+		 */
+		if (IS_ENABLED(CONFIG_MIPS_CMP) &&
+		    gic_local_irq_is_routable(GIC_LOCAL_INT_TIMER)) {
+			timer_cpu_pin = gic_read(GIC_REG(VPE_LOCAL,
+							 GIC_VPE_TIMER_MAP)) &
+					GIC_MAP_MSK;
+			irq_set_chained_handler(MIPS_CPU_IRQ_BASE +
+						GIC_CPU_PIN_OFFSET +
+						timer_cpu_pin,
+						gic_irq_dispatch);
+		} else {
+			timer_cpu_pin = gic_cpu_pin;
+		}
 	}
 
 	gic_irq_domain = irq_domain_add_simple(node, GIC_NUM_LOCAL_INTRS +
diff --git a/drivers/isdn/hardware/eicon/message.c b/drivers/isdn/hardware/eicon/message.c
index 0b38060..d7c2866 100644
--- a/drivers/isdn/hardware/eicon/message.c
+++ b/drivers/isdn/hardware/eicon/message.c
@@ -1474,7 +1474,7 @@
 					add_ai(plci, &parms[5]);
 					sig_req(plci, REJECT, 0);
 				}
-				else if (Reject == 1 || Reject > 9)
+				else if (Reject == 1 || Reject >= 9)
 				{
 					add_ai(plci, &parms[5]);
 					sig_req(plci, HANGUP, 0);
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index da3604e..1695ee5 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -72,6 +72,19 @@
 	/* this page has not been allocated yet */
 
 	spin_unlock_irq(&bitmap->lock);
+	/* It is possible that this is being called inside a
+	 * prepare_to_wait/finish_wait loop from raid5c:make_request().
+	 * In general it is not permitted to sleep in that context as it
+	 * can cause the loop to spin freely.
+	 * That doesn't apply here as we can only reach this point
+	 * once with any loop.
+	 * When this function completes, either bp[page].map or
+	 * bp[page].hijacked.  In either case, this function will
+	 * abort before getting to this point again.  So there is
+	 * no risk of a free-spin, and so it is safe to assert
+	 * that sleeping here is allowed.
+	 */
+	sched_annotate_sleep();
 	mappage = kzalloc(PAGE_SIZE, GFP_NOIO);
 	spin_lock_irq(&bitmap->lock);
 
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index c1b0d52..b98765f 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -3195,6 +3195,11 @@
 					  (unsigned long long)sh->sector,
 					  rcw, qread, test_bit(STRIPE_DELAYED, &sh->state));
 	}
+
+	if (rcw > disks && rmw > disks &&
+	    !test_bit(STRIPE_PREREAD_ACTIVE, &sh->state))
+		set_bit(STRIPE_DELAYED, &sh->state);
+
 	/* now if nothing is locked, and if we have enough data,
 	 * we can start a write request
 	 */
diff --git a/drivers/net/caif/caif_hsi.c b/drivers/net/caif/caif_hsi.c
index 5e40a8b..b3b922a 100644
--- a/drivers/net/caif/caif_hsi.c
+++ b/drivers/net/caif/caif_hsi.c
@@ -1415,7 +1415,6 @@
 
 	cfhsi = netdev_priv(dev);
 	cfhsi_netlink_parms(data, cfhsi);
-	dev_net_set(cfhsi->ndev, src_net);
 
 	get_ops = symbol_get(cfhsi_get_ops);
 	if (!get_ops) {
diff --git a/drivers/net/ethernet/amd/Kconfig b/drivers/net/ethernet/amd/Kconfig
index 7a5e4aa..77f1f60 100644
--- a/drivers/net/ethernet/amd/Kconfig
+++ b/drivers/net/ethernet/amd/Kconfig
@@ -45,7 +45,7 @@
 
 config LANCE
 	tristate "AMD LANCE and PCnet (AT1500 and NE2100) support"
-	depends on ISA && ISA_DMA_API
+	depends on ISA && ISA_DMA_API && !ARM
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y and read
 	  the Ethernet-HOWTO, available from
@@ -142,7 +142,7 @@
 
 config NI65
 	tristate "NI6510 support"
-	depends on ISA && ISA_DMA_API
+	depends on ISA && ISA_DMA_API && !ARM
 	---help---
 	  If you have a network (Ethernet) card of this type, say Y and read
 	  the Ethernet-HOWTO, available from
diff --git a/drivers/net/ethernet/amd/nmclan_cs.c b/drivers/net/ethernet/amd/nmclan_cs.c
index 5b22764..27245ef 100644
--- a/drivers/net/ethernet/amd/nmclan_cs.c
+++ b/drivers/net/ethernet/amd/nmclan_cs.c
@@ -952,6 +952,8 @@
   do {
     /* WARNING: MACE_IR is a READ/CLEAR port! */
     status = inb(ioaddr + AM2150_MACE_BASE + MACE_IR);
+    if (!(status & ~MACE_IMR_DEFAULT) && IntrCnt == MACE_MAX_IR_ITERATIONS)
+      return IRQ_NONE;
 
     pr_debug("mace_interrupt: irq 0x%X status 0x%X.\n", irq, status);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
index 7bb5f07..e5ffb2c 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c
@@ -523,6 +523,7 @@
 	hw_feat->sph           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, SPHEN);
 	hw_feat->tso           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, TSOEN);
 	hw_feat->dma_debug     = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, DBGMEMA);
+	hw_feat->rss           = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, RSSEN);
 	hw_feat->tc_cnt	       = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R, NUMTC);
 	hw_feat->hash_table_size = XGMAC_GET_BITS(mac_hfr1, MAC_HWF1R,
 						  HASHTBLSZ);
@@ -552,13 +553,14 @@
 		break;
 	}
 
-	/* The Queue and Channel counts are zero based so increment them
+	/* The Queue, Channel and TC counts are zero based so increment them
 	 * to get the actual number
 	 */
 	hw_feat->rx_q_cnt++;
 	hw_feat->tx_q_cnt++;
 	hw_feat->rx_ch_cnt++;
 	hw_feat->tx_ch_cnt++;
+	hw_feat->tc_cnt++;
 
 	DBGPR("<--xgbe_get_all_hw_features\n");
 }
diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
index 83a5028..793f3b7 100644
--- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
+++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c
@@ -369,6 +369,8 @@
 		if (unlikely(xgene_enet_is_desc_slot_empty(raw_desc)))
 			break;
 
+		/* read fpqnum field after dataaddr field */
+		dma_rmb();
 		if (is_rx_desc(raw_desc))
 			ret = xgene_enet_rx_frame(ring, raw_desc);
 		else
diff --git a/drivers/net/ethernet/cirrus/Kconfig b/drivers/net/ethernet/cirrus/Kconfig
index 7403dff..905ac5f 100644
--- a/drivers/net/ethernet/cirrus/Kconfig
+++ b/drivers/net/ethernet/cirrus/Kconfig
@@ -32,7 +32,8 @@
 	  will be called cs89x0.
 
 config CS89x0_PLATFORM
-	bool "CS89x0 platform driver support"
+	bool "CS89x0 platform driver support" if HAS_IOPORT_MAP
+	default !HAS_IOPORT_MAP
 	depends on CS89x0
 	help
 	  Say Y to compile the cs89x0 driver as a platform driver. This
diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c
index 3e1a9c1..fda12fb 100644
--- a/drivers/net/ethernet/freescale/gianfar_ethtool.c
+++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c
@@ -1586,7 +1586,7 @@
 		return -EBUSY;
 
 	/* Fill regular entries */
-	for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].ctrl);
+	for (; i < MAX_FILER_IDX - 1 && (tab->fe[i].ctrl | tab->fe[i].prop);
 	     i++)
 		gfar_write_filer(priv, i, tab->fe[i].ctrl, tab->fe[i].prop);
 	/* Fill the rest with fall-troughs */
diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c
index 63c807c..edea13b 100644
--- a/drivers/net/ethernet/intel/igbvf/netdev.c
+++ b/drivers/net/ethernet/intel/igbvf/netdev.c
@@ -1907,7 +1907,8 @@
 
 static int igbvf_tso(struct igbvf_adapter *adapter,
                      struct igbvf_ring *tx_ring,
-                     struct sk_buff *skb, u32 tx_flags, u8 *hdr_len)
+		     struct sk_buff *skb, u32 tx_flags, u8 *hdr_len,
+		     __be16 protocol)
 {
 	struct e1000_adv_tx_context_desc *context_desc;
 	struct igbvf_buffer *buffer_info;
@@ -1927,7 +1928,7 @@
 	l4len = tcp_hdrlen(skb);
 	*hdr_len += l4len;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	if (protocol == htons(ETH_P_IP)) {
 		struct iphdr *iph = ip_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
@@ -1958,7 +1959,7 @@
 	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
 	tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
 
-	if (skb->protocol == htons(ETH_P_IP))
+	if (protocol == htons(ETH_P_IP))
 		tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
 	tu_cmd |= E1000_ADVTXD_TUCMD_L4T_TCP;
 
@@ -1984,7 +1985,8 @@
 
 static inline bool igbvf_tx_csum(struct igbvf_adapter *adapter,
                                  struct igbvf_ring *tx_ring,
-                                 struct sk_buff *skb, u32 tx_flags)
+				 struct sk_buff *skb, u32 tx_flags,
+				 __be16 protocol)
 {
 	struct e1000_adv_tx_context_desc *context_desc;
 	unsigned int i;
@@ -2011,7 +2013,7 @@
 		tu_cmd |= (E1000_TXD_CMD_DEXT | E1000_ADVTXD_DTYP_CTXT);
 
 		if (skb->ip_summed == CHECKSUM_PARTIAL) {
-			switch (skb->protocol) {
+			switch (protocol) {
 			case htons(ETH_P_IP):
 				tu_cmd |= E1000_ADVTXD_TUCMD_IPV4;
 				if (ip_hdr(skb)->protocol == IPPROTO_TCP)
@@ -2211,6 +2213,7 @@
 	u8 hdr_len = 0;
 	int count = 0;
 	int tso = 0;
+	__be16 protocol = vlan_get_protocol(skb);
 
 	if (test_bit(__IGBVF_DOWN, &adapter->state)) {
 		dev_kfree_skb_any(skb);
@@ -2239,13 +2242,13 @@
 		tx_flags |= (vlan_tx_tag_get(skb) << IGBVF_TX_FLAGS_VLAN_SHIFT);
 	}
 
-	if (skb->protocol == htons(ETH_P_IP))
+	if (protocol == htons(ETH_P_IP))
 		tx_flags |= IGBVF_TX_FLAGS_IPV4;
 
 	first = tx_ring->next_to_use;
 
 	tso = skb_is_gso(skb) ?
-		igbvf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len) : 0;
+		igbvf_tso(adapter, tx_ring, skb, tx_flags, &hdr_len, protocol) : 0;
 	if (unlikely(tso < 0)) {
 		dev_kfree_skb_any(skb);
 		return NETDEV_TX_OK;
@@ -2253,7 +2256,7 @@
 
 	if (tso)
 		tx_flags |= IGBVF_TX_FLAGS_TSO;
-	else if (igbvf_tx_csum(adapter, tx_ring, skb, tx_flags) &&
+	else if (igbvf_tx_csum(adapter, tx_ring, skb, tx_flags, protocol) &&
 	         (skb->ip_summed == CHECKSUM_PARTIAL))
 		tx_flags |= IGBVF_TX_FLAGS_CSUM;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
index 2ed2c7d..67b02bd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c
@@ -7227,11 +7227,11 @@
 		if (!vhdr)
 			goto out_drop;
 
-		protocol = vhdr->h_vlan_encapsulated_proto;
 		tx_flags |= ntohs(vhdr->h_vlan_TCI) <<
 				  IXGBE_TX_FLAGS_VLAN_SHIFT;
 		tx_flags |= IXGBE_TX_FLAGS_SW_VLAN;
 	}
+	protocol = vlan_get_protocol(skb);
 
 	if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 	    adapter->ptp_clock &&
diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
index 62a0d8e..38c7a0b 100644
--- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
+++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c
@@ -3099,7 +3099,7 @@
 	/* ADV DTYP TUCMD MKRLOC/ISCSIHEDLEN */
 	type_tucmd = IXGBE_ADVTXD_TUCMD_L4T_TCP;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
+	if (first->protocol == htons(ETH_P_IP)) {
 		struct iphdr *iph = ip_hdr(skb);
 		iph->tot_len = 0;
 		iph->check = 0;
@@ -3156,7 +3156,7 @@
 
 	if (skb->ip_summed == CHECKSUM_PARTIAL) {
 		u8 l4_hdr = 0;
-		switch (skb->protocol) {
+		switch (first->protocol) {
 		case htons(ETH_P_IP):
 			vlan_macip_lens |= skb_network_header_len(skb);
 			type_tucmd |= IXGBE_ADVTXD_TUCMD_IPV4;
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index bdd4eea..210691c 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -235,7 +235,8 @@
 extern int mlx4_log_num_mgm_entry_size;
 extern int log_mtts_per_seg;
 
-#define MLX4_MAX_NUM_SLAVES	(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF)
+#define MLX4_MAX_NUM_SLAVES	(min(MLX4_MAX_NUM_PF + MLX4_MAX_NUM_VF, \
+				     MLX4_MFUNC_MAX))
 #define ALL_SLAVES 0xff
 
 struct mlx4_bitmap {
diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
index 18e5de7..4e1f58c 100644
--- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
+++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c
@@ -967,7 +967,12 @@
 	tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring,
 					      budget);
 	work_done = qlcnic_process_rcv_ring(sds_ring, budget);
-	if ((work_done < budget) && tx_complete) {
+
+	/* Check if we need a repoll */
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		if (test_bit(__QLCNIC_DEV_UP, &adapter->state)) {
 			qlcnic_enable_sds_intr(adapter, sds_ring);
@@ -992,6 +997,9 @@
 		napi_complete(&tx_ring->napi);
 		if (test_bit(__QLCNIC_DEV_UP, &adapter->state))
 			qlcnic_enable_tx_intr(adapter, tx_ring);
+	} else {
+		/* As qlcnic_process_cmd_ring() returned 0, we need a repoll*/
+		work_done = budget;
 	}
 
 	return work_done;
@@ -1950,7 +1958,12 @@
 
 	tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget);
 	work_done = qlcnic_83xx_process_rcv_ring(sds_ring, budget);
-	if ((work_done < budget) && tx_complete) {
+
+	/* Check if we need a repoll */
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		qlcnic_enable_sds_intr(adapter, sds_ring);
 	}
@@ -1973,7 +1986,12 @@
 
 	tx_complete = qlcnic_process_cmd_ring(adapter, tx_ring, budget);
 	work_done = qlcnic_83xx_process_rcv_ring(sds_ring, budget);
-	if ((work_done < budget) && tx_complete) {
+
+	/* Check if we need a repoll */
+	if (!tx_complete)
+		work_done = budget;
+
+	if (work_done < budget) {
 		napi_complete(&sds_ring->napi);
 		qlcnic_enable_sds_intr(adapter, sds_ring);
 	}
@@ -1995,6 +2013,9 @@
 		napi_complete(&tx_ring->napi);
 		if (test_bit(__QLCNIC_DEV_UP , &adapter->state))
 			qlcnic_enable_tx_intr(adapter, tx_ring);
+	} else {
+		/* need a repoll */
+		work_done = budget;
 	}
 
 	return work_done;
diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
index 6c904a6..ef5aed3 100644
--- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c
+++ b/drivers/net/ethernet/qlogic/qlge/qlge_main.c
@@ -2351,23 +2351,29 @@
 {
 	struct ql_adapter *qdev = netdev_priv(ndev);
 	int status = 0;
+	bool need_restart = netif_running(ndev);
 
-	status = ql_adapter_down(qdev);
-	if (status) {
-		netif_err(qdev, link, qdev->ndev,
-			  "Failed to bring down the adapter\n");
-		return status;
+	if (need_restart) {
+		status = ql_adapter_down(qdev);
+		if (status) {
+			netif_err(qdev, link, qdev->ndev,
+				  "Failed to bring down the adapter\n");
+			return status;
+		}
 	}
 
 	/* update the features with resent change */
 	ndev->features = features;
 
-	status = ql_adapter_up(qdev);
-	if (status) {
-		netif_err(qdev, link, qdev->ndev,
-			  "Failed to bring up the adapter\n");
-		return status;
+	if (need_restart) {
+		status = ql_adapter_up(qdev);
+		if (status) {
+			netif_err(qdev, link, qdev->ndev,
+				  "Failed to bring up the adapter\n");
+			return status;
+		}
 	}
+
 	return status;
 }
 
diff --git a/drivers/net/ethernet/sun/sunvnet.c b/drivers/net/ethernet/sun/sunvnet.c
index d2835bf..3699b98 100644
--- a/drivers/net/ethernet/sun/sunvnet.c
+++ b/drivers/net/ethernet/sun/sunvnet.c
@@ -1119,6 +1119,7 @@
 			skb_shinfo(nskb)->gso_size = skb_shinfo(skb)->gso_size;
 			skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type;
 		}
+		nskb->queue_mapping = skb->queue_mapping;
 		dev_kfree_skb(skb);
 		skb = nskb;
 	}
diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c
index 9f49c01..7cd4eb3 100644
--- a/drivers/net/hyperv/netvsc.c
+++ b/drivers/net/hyperv/netvsc.c
@@ -716,7 +716,7 @@
 	u64 req_id;
 	unsigned int section_index = NETVSC_INVALID_INDEX;
 	u32 msg_size = 0;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	u16 q_idx = packet->q_idx;
 
 
@@ -743,8 +743,6 @@
 							   packet);
 			skb = (struct sk_buff *)
 			      (unsigned long)packet->send_completion_tid;
-			if (skb)
-				dev_kfree_skb_any(skb);
 			packet->page_buf_cnt = 0;
 		}
 	}
@@ -810,6 +808,13 @@
 			   packet, ret);
 	}
 
+	if (ret != 0) {
+		if (section_index != NETVSC_INVALID_INDEX)
+			netvsc_free_send_slot(net_device, section_index);
+	} else if (skb) {
+		dev_kfree_skb_any(skb);
+	}
+
 	return ret;
 }
 
diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c
index 7df2217..919f4fc 100644
--- a/drivers/net/macvtap.c
+++ b/drivers/net/macvtap.c
@@ -17,7 +17,6 @@
 #include <linux/fs.h>
 #include <linux/uio.h>
 
-#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/rtnetlink.h>
 #include <net/sock.h>
@@ -81,7 +80,7 @@
 static const struct proto_ops macvtap_socket_ops;
 
 #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \
-		      NETIF_F_TSO6)
+		      NETIF_F_TSO6 | NETIF_F_UFO)
 #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO)
 #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG)
 
@@ -586,11 +585,7 @@
 			gso_type = SKB_GSO_TCPV6;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-			pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n",
-				     current->comm);
 			gso_type = SKB_GSO_UDP;
-			if (skb->protocol == htons(ETH_P_IPV6))
-				ipv6_proxy_select_ident(skb);
 			break;
 		default:
 			return -EINVAL;
@@ -636,6 +631,8 @@
 			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (sinfo->gso_type & SKB_GSO_TCPV6)
 			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (sinfo->gso_type & SKB_GSO_UDP)
+			vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP;
 		else
 			BUG();
 		if (sinfo->gso_type & SKB_GSO_TCP_ECN)
@@ -965,6 +962,9 @@
 			if (arg & TUN_F_TSO6)
 				feature_mask |= NETIF_F_TSO6;
 		}
+
+		if (arg & TUN_F_UFO)
+			feature_mask |= NETIF_F_UFO;
 	}
 
 	/* tun/tap driver inverts the usage for TSO offloads, where
@@ -975,7 +975,7 @@
 	 * When user space turns off TSO, we turn off GSO/LRO so that
 	 * user-space will not receive TSO frames.
 	 */
-	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6))
+	if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO))
 		features |= RX_OFFLOADS;
 	else
 		features &= ~RX_OFFLOADS;
@@ -1090,7 +1090,7 @@
 	case TUNSETOFFLOAD:
 		/* let the user check for future flags */
 		if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 |
-			    TUN_F_TSO_ECN))
+			    TUN_F_TSO_ECN | TUN_F_UFO))
 			return -EINVAL;
 
 		rtnl_lock();
diff --git a/drivers/net/ppp/ppp_deflate.c b/drivers/net/ppp/ppp_deflate.c
index 602c625..b5edc7f 100644
--- a/drivers/net/ppp/ppp_deflate.c
+++ b/drivers/net/ppp/ppp_deflate.c
@@ -246,7 +246,7 @@
 	/*
 	 * See if we managed to reduce the size of the packet.
 	 */
-	if (olen < isize) {
+	if (olen < isize && olen <= osize) {
 		state->stats.comp_bytes += olen;
 		state->stats.comp_packets++;
 	} else {
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 8c8dc16..10f9e40 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -65,7 +65,6 @@
 #include <linux/nsproxy.h>
 #include <linux/virtio_net.h>
 #include <linux/rcupdate.h>
-#include <net/ipv6.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 #include <net/rtnetlink.h>
@@ -187,7 +186,7 @@
 	struct net_device	*dev;
 	netdev_features_t	set_features;
 #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \
-			  NETIF_F_TSO6)
+			  NETIF_F_TSO6|NETIF_F_UFO)
 
 	int			vnet_hdr_sz;
 	int			sndbuf;
@@ -1167,8 +1166,6 @@
 		break;
 	}
 
-	skb_reset_network_header(skb);
-
 	if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		pr_debug("GSO!\n");
 		switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
@@ -1179,20 +1176,8 @@
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-		{
-			static bool warned;
-
-			if (!warned) {
-				warned = true;
-				netdev_warn(tun->dev,
-					    "%s: using disabled UFO feature; please fix this program\n",
-					    current->comm);
-			}
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
-			if (skb->protocol == htons(ETH_P_IPV6))
-				ipv6_proxy_select_ident(skb);
 			break;
-		}
 		default:
 			tun->dev->stats.rx_frame_errors++;
 			kfree_skb(skb);
@@ -1221,6 +1206,7 @@
 		skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
 	}
 
+	skb_reset_network_header(skb);
 	skb_probe_transport_header(skb, 0);
 
 	rxhash = skb_get_hash(skb);
@@ -1298,6 +1284,8 @@
 				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 			else if (sinfo->gso_type & SKB_GSO_TCPV6)
 				gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+			else if (sinfo->gso_type & SKB_GSO_UDP)
+				gso.gso_type = VIRTIO_NET_HDR_GSO_UDP;
 			else {
 				pr_err("unexpected GSO type: "
 				       "0x%x, gso_size %d, hdr_len %d\n",
@@ -1746,6 +1734,11 @@
 				features |= NETIF_F_TSO6;
 			arg &= ~(TUN_F_TSO4|TUN_F_TSO6);
 		}
+
+		if (arg & TUN_F_UFO) {
+			features |= NETIF_F_UFO;
+			arg &= ~TUN_F_UFO;
+		}
 	}
 
 	/* This gives the user a way to test for new features in future by
diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
index 99b69af..4a1e9c4 100644
--- a/drivers/net/usb/sr9700.c
+++ b/drivers/net/usb/sr9700.c
@@ -77,7 +77,7 @@
 		int ret;
 
 		udelay(1);
-		ret = sr_read_reg(dev, EPCR, &tmp);
+		ret = sr_read_reg(dev, SR_EPCR, &tmp);
 		if (ret < 0)
 			return ret;
 
@@ -98,15 +98,15 @@
 
 	mutex_lock(&dev->phy_mutex);
 
-	sr_write_reg(dev, EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
-	sr_write_reg(dev, EPCR, phy ? (EPCR_EPOS | EPCR_ERPRR) : EPCR_ERPRR);
+	sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
+	sr_write_reg(dev, SR_EPCR, phy ? (EPCR_EPOS | EPCR_ERPRR) : EPCR_ERPRR);
 
 	ret = wait_phy_eeprom_ready(dev, phy);
 	if (ret < 0)
 		goto out_unlock;
 
-	sr_write_reg(dev, EPCR, 0x0);
-	ret = sr_read(dev, EPDR, 2, value);
+	sr_write_reg(dev, SR_EPCR, 0x0);
+	ret = sr_read(dev, SR_EPDR, 2, value);
 
 	netdev_dbg(dev->net, "read shared %d 0x%02x returned 0x%04x, %d\n",
 		   phy, reg, *value, ret);
@@ -123,19 +123,19 @@
 
 	mutex_lock(&dev->phy_mutex);
 
-	ret = sr_write(dev, EPDR, 2, &value);
+	ret = sr_write(dev, SR_EPDR, 2, &value);
 	if (ret < 0)
 		goto out_unlock;
 
-	sr_write_reg(dev, EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
-	sr_write_reg(dev, EPCR, phy ? (EPCR_WEP | EPCR_EPOS | EPCR_ERPRW) :
+	sr_write_reg(dev, SR_EPAR, phy ? (reg | EPAR_PHY_ADR) : reg);
+	sr_write_reg(dev, SR_EPCR, phy ? (EPCR_WEP | EPCR_EPOS | EPCR_ERPRW) :
 		    (EPCR_WEP | EPCR_ERPRW));
 
 	ret = wait_phy_eeprom_ready(dev, phy);
 	if (ret < 0)
 		goto out_unlock;
 
-	sr_write_reg(dev, EPCR, 0x0);
+	sr_write_reg(dev, SR_EPCR, 0x0);
 
 out_unlock:
 	mutex_unlock(&dev->phy_mutex);
@@ -188,7 +188,7 @@
 	if (loc == MII_BMSR) {
 		u8 value;
 
-		sr_read_reg(dev, NSR, &value);
+		sr_read_reg(dev, SR_NSR, &value);
 		if (value & NSR_LINKST)
 			rc = 1;
 	}
@@ -228,7 +228,7 @@
 	int rc = 0;
 
 	/* Get the Link Status directly */
-	sr_read_reg(dev, NSR, &value);
+	sr_read_reg(dev, SR_NSR, &value);
 	if (value & NSR_LINKST)
 		rc = 1;
 
@@ -281,8 +281,8 @@
 		}
 	}
 
-	sr_write_async(dev, MAR, SR_MCAST_SIZE, hashes);
-	sr_write_reg_async(dev, RCR, rx_ctl);
+	sr_write_async(dev, SR_MAR, SR_MCAST_SIZE, hashes);
+	sr_write_reg_async(dev, SR_RCR, rx_ctl);
 }
 
 static int sr9700_set_mac_address(struct net_device *netdev, void *p)
@@ -297,7 +297,7 @@
 	}
 
 	memcpy(netdev->dev_addr, addr->sa_data, netdev->addr_len);
-	sr_write_async(dev, PAR, 6, netdev->dev_addr);
+	sr_write_async(dev, SR_PAR, 6, netdev->dev_addr);
 
 	return 0;
 }
@@ -340,7 +340,7 @@
 	mii->phy_id_mask = 0x1f;
 	mii->reg_num_mask = 0x1f;
 
-	sr_write_reg(dev, NCR, NCR_RST);
+	sr_write_reg(dev, SR_NCR, NCR_RST);
 	udelay(20);
 
 	/* read MAC
@@ -348,17 +348,17 @@
 	 * EEPROM automatically to PAR. In case there is no EEPROM externally,
 	 * a default MAC address is stored in PAR for making chip work properly.
 	 */
-	if (sr_read(dev, PAR, ETH_ALEN, netdev->dev_addr) < 0) {
+	if (sr_read(dev, SR_PAR, ETH_ALEN, netdev->dev_addr) < 0) {
 		netdev_err(netdev, "Error reading MAC address\n");
 		ret = -ENODEV;
 		goto out;
 	}
 
 	/* power up and reset phy */
-	sr_write_reg(dev, PRR, PRR_PHY_RST);
+	sr_write_reg(dev, SR_PRR, PRR_PHY_RST);
 	/* at least 10ms, here 20ms for safe */
 	mdelay(20);
-	sr_write_reg(dev, PRR, 0);
+	sr_write_reg(dev, SR_PRR, 0);
 	/* at least 1ms, here 2ms for reading right register */
 	udelay(2 * 1000);
 
diff --git a/drivers/net/usb/sr9700.h b/drivers/net/usb/sr9700.h
index fd687c5..258b030 100644
--- a/drivers/net/usb/sr9700.h
+++ b/drivers/net/usb/sr9700.h
@@ -14,13 +14,13 @@
 /* sr9700 spec. register table on Linux platform */
 
 /* Network Control Reg */
-#define	NCR			0x00
+#define	SR_NCR			0x00
 #define		NCR_RST			(1 << 0)
 #define		NCR_LBK			(3 << 1)
 #define		NCR_FDX			(1 << 3)
 #define		NCR_WAKEEN		(1 << 6)
 /* Network Status Reg */
-#define	NSR			0x01
+#define	SR_NSR			0x01
 #define		NSR_RXRDY		(1 << 0)
 #define		NSR_RXOV		(1 << 1)
 #define		NSR_TX1END		(1 << 2)
@@ -30,7 +30,7 @@
 #define		NSR_LINKST		(1 << 6)
 #define		NSR_SPEED		(1 << 7)
 /* Tx Control Reg */
-#define	TCR			0x02
+#define	SR_TCR			0x02
 #define		TCR_CRC_DIS		(1 << 1)
 #define		TCR_PAD_DIS		(1 << 2)
 #define		TCR_LC_CARE		(1 << 3)
@@ -38,7 +38,7 @@
 #define		TCR_EXCECM		(1 << 5)
 #define		TCR_LF_EN		(1 << 6)
 /* Tx Status Reg for Packet Index 1 */
-#define	TSR1		0x03
+#define	SR_TSR1		0x03
 #define		TSR1_EC			(1 << 2)
 #define		TSR1_COL		(1 << 3)
 #define		TSR1_LC			(1 << 4)
@@ -46,7 +46,7 @@
 #define		TSR1_LOC		(1 << 6)
 #define		TSR1_TLF		(1 << 7)
 /* Tx Status Reg for Packet Index 2 */
-#define	TSR2		0x04
+#define	SR_TSR2		0x04
 #define		TSR2_EC			(1 << 2)
 #define		TSR2_COL		(1 << 3)
 #define		TSR2_LC			(1 << 4)
@@ -54,7 +54,7 @@
 #define		TSR2_LOC		(1 << 6)
 #define		TSR2_TLF		(1 << 7)
 /* Rx Control Reg*/
-#define	RCR			0x05
+#define	SR_RCR			0x05
 #define		RCR_RXEN		(1 << 0)
 #define		RCR_PRMSC		(1 << 1)
 #define		RCR_RUNT		(1 << 2)
@@ -62,87 +62,87 @@
 #define		RCR_DIS_CRC		(1 << 4)
 #define		RCR_DIS_LONG	(1 << 5)
 /* Rx Status Reg */
-#define	RSR			0x06
+#define	SR_RSR			0x06
 #define		RSR_AE			(1 << 2)
 #define		RSR_MF			(1 << 6)
 #define		RSR_RF			(1 << 7)
 /* Rx Overflow Counter Reg */
-#define	ROCR		0x07
+#define	SR_ROCR		0x07
 #define		ROCR_ROC		(0x7F << 0)
 #define		ROCR_RXFU		(1 << 7)
 /* Back Pressure Threshold Reg */
-#define	BPTR		0x08
+#define	SR_BPTR		0x08
 #define		BPTR_JPT		(0x0F << 0)
 #define		BPTR_BPHW		(0x0F << 4)
 /* Flow Control Threshold Reg */
-#define	FCTR		0x09
+#define	SR_FCTR		0x09
 #define		FCTR_LWOT		(0x0F << 0)
 #define		FCTR_HWOT		(0x0F << 4)
 /* rx/tx Flow Control Reg */
-#define	FCR			0x0A
+#define	SR_FCR			0x0A
 #define		FCR_FLCE		(1 << 0)
 #define		FCR_BKPA		(1 << 4)
 #define		FCR_TXPEN		(1 << 5)
 #define		FCR_TXPF		(1 << 6)
 #define		FCR_TXP0		(1 << 7)
 /* Eeprom & Phy Control Reg */
-#define	EPCR		0x0B
+#define	SR_EPCR		0x0B
 #define		EPCR_ERRE		(1 << 0)
 #define		EPCR_ERPRW		(1 << 1)
 #define		EPCR_ERPRR		(1 << 2)
 #define		EPCR_EPOS		(1 << 3)
 #define		EPCR_WEP		(1 << 4)
 /* Eeprom & Phy Address Reg */
-#define	EPAR		0x0C
+#define	SR_EPAR		0x0C
 #define		EPAR_EROA		(0x3F << 0)
 #define		EPAR_PHY_ADR_MASK	(0x03 << 6)
 #define		EPAR_PHY_ADR		(0x01 << 6)
 /* Eeprom &	Phy Data Reg */
-#define	EPDR		0x0D	/* 0x0D ~ 0x0E for Data Reg Low & High */
+#define	SR_EPDR		0x0D	/* 0x0D ~ 0x0E for Data Reg Low & High */
 /* Wakeup Control Reg */
-#define	WCR			0x0F
+#define	SR_WCR			0x0F
 #define		WCR_MAGICST		(1 << 0)
 #define		WCR_LINKST		(1 << 2)
 #define		WCR_MAGICEN		(1 << 3)
 #define		WCR_LINKEN		(1 << 5)
 /* Physical Address Reg */
-#define	PAR			0x10	/* 0x10 ~ 0x15 6 bytes for PAR */
+#define	SR_PAR			0x10	/* 0x10 ~ 0x15 6 bytes for PAR */
 /* Multicast Address Reg */
-#define	MAR			0x16	/* 0x16 ~ 0x1D 8 bytes for MAR */
+#define	SR_MAR			0x16	/* 0x16 ~ 0x1D 8 bytes for MAR */
 /* 0x1e unused */
 /* Phy Reset Reg */
-#define	PRR			0x1F
+#define	SR_PRR			0x1F
 #define		PRR_PHY_RST		(1 << 0)
 /* Tx sdram Write Pointer Address Low */
-#define	TWPAL		0x20
+#define	SR_TWPAL		0x20
 /* Tx sdram Write Pointer Address High */
-#define	TWPAH		0x21
+#define	SR_TWPAH		0x21
 /* Tx sdram Read Pointer Address Low */
-#define	TRPAL		0x22
+#define	SR_TRPAL		0x22
 /* Tx sdram Read Pointer Address High */
-#define	TRPAH		0x23
+#define	SR_TRPAH		0x23
 /* Rx sdram Write Pointer Address Low */
-#define	RWPAL		0x24
+#define	SR_RWPAL		0x24
 /* Rx sdram Write Pointer Address High */
-#define	RWPAH		0x25
+#define	SR_RWPAH		0x25
 /* Rx sdram Read Pointer Address Low */
-#define	RRPAL		0x26
+#define	SR_RRPAL		0x26
 /* Rx sdram Read Pointer Address High */
-#define	RRPAH		0x27
+#define	SR_RRPAH		0x27
 /* Vendor ID register */
-#define	VID			0x28	/* 0x28 ~ 0x29 2 bytes for VID */
+#define	SR_VID			0x28	/* 0x28 ~ 0x29 2 bytes for VID */
 /* Product ID register */
-#define	PID			0x2A	/* 0x2A ~ 0x2B 2 bytes for PID */
+#define	SR_PID			0x2A	/* 0x2A ~ 0x2B 2 bytes for PID */
 /* CHIP Revision register */
-#define	CHIPR		0x2C
+#define	SR_CHIPR		0x2C
 /* 0x2D --> 0xEF unused */
 /* USB Device Address */
-#define	USBDA		0xF0
+#define	SR_USBDA		0xF0
 #define		USBDA_USBFA		(0x7F << 0)
 /* RX packet Counter Reg */
-#define	RXC			0xF1
+#define	SR_RXC			0xF1
 /* Tx packet Counter & USB Status Reg */
-#define	TXC_USBS	0xF2
+#define	SR_TXC_USBS		0xF2
 #define		TXC_USBS_TXC0		(1 << 0)
 #define		TXC_USBS_TXC1		(1 << 1)
 #define		TXC_USBS_TXC2		(1 << 2)
@@ -150,7 +150,7 @@
 #define		TXC_USBS_SUSFLAG	(1 << 6)
 #define		TXC_USBS_RXFAULT	(1 << 7)
 /* USB Control register */
-#define	USBC		0xF4
+#define	SR_USBC			0xF4
 #define		USBC_EP3NAK		(1 << 4)
 #define		USBC_EP3ACK		(1 << 5)
 
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 5ca9771..059fdf1 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -490,17 +490,8 @@
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4;
 			break;
 		case VIRTIO_NET_HDR_GSO_UDP:
-		{
-			static bool warned;
-
-			if (!warned) {
-				warned = true;
-				netdev_warn(dev,
-					    "host using disabled UFO feature; please fix it\n");
-			}
 			skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
 			break;
-		}
 		case VIRTIO_NET_HDR_GSO_TCPV6:
 			skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6;
 			break;
@@ -888,6 +879,8 @@
 			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4;
 		else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
 			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6;
+		else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP)
+			hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP;
 		else
 			BUG();
 		if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN)
@@ -1748,7 +1741,7 @@
 			dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST;
 
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) {
-			dev->hw_features |= NETIF_F_TSO
+			dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO
 				| NETIF_F_TSO_ECN | NETIF_F_TSO6;
 		}
 		/* Individual feature bits: what can host handle? */
@@ -1758,9 +1751,11 @@
 			dev->hw_features |= NETIF_F_TSO6;
 		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN))
 			dev->hw_features |= NETIF_F_TSO_ECN;
+		if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO))
+			dev->hw_features |= NETIF_F_UFO;
 
 		if (gso)
-			dev->features |= dev->hw_features & NETIF_F_ALL_TSO;
+			dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO);
 		/* (!csum && gso) case will be fixed by register_netdev() */
 	}
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM))
@@ -1798,7 +1793,8 @@
 	/* If we can receive ANY GSO packets, we must allocate large ones. */
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) ||
 	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) ||
-	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN))
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) ||
+	    virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO))
 		vi->big_packets = true;
 
 	if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF))
@@ -1994,9 +1990,9 @@
 static unsigned int features[] = {
 	VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM,
 	VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC,
-	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6,
+	VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6,
 	VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6,
-	VIRTIO_NET_F_GUEST_ECN,
+	VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO,
 	VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ,
 	VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN,
 	VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ,
diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index 7fbd89f..a8c755d 100644
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2432,10 +2432,10 @@
 	dev_put(vxlan->dev);
 }
 
-static int vxlan_newlink(struct net *net, struct net_device *dev,
+static int vxlan_newlink(struct net *src_net, struct net_device *dev,
 			 struct nlattr *tb[], struct nlattr *data[])
 {
-	struct vxlan_net *vn = net_generic(net, vxlan_net_id);
+	struct vxlan_net *vn = net_generic(src_net, vxlan_net_id);
 	struct vxlan_dev *vxlan = netdev_priv(dev);
 	struct vxlan_rdst *dst = &vxlan->default_dst;
 	__u32 vni;
@@ -2445,7 +2445,7 @@
 	if (!data[IFLA_VXLAN_ID])
 		return -EINVAL;
 
-	vxlan->net = dev_net(dev);
+	vxlan->net = src_net;
 
 	vni = nla_get_u32(data[IFLA_VXLAN_ID]);
 	dst->remote_vni = vni;
@@ -2481,7 +2481,7 @@
 	if (data[IFLA_VXLAN_LINK] &&
 	    (dst->remote_ifindex = nla_get_u32(data[IFLA_VXLAN_LINK]))) {
 		struct net_device *lowerdev
-			 = __dev_get_by_index(net, dst->remote_ifindex);
+			 = __dev_get_by_index(src_net, dst->remote_ifindex);
 
 		if (!lowerdev) {
 			pr_info("ifindex %d does not exist\n", dst->remote_ifindex);
@@ -2557,7 +2557,7 @@
 	    nla_get_u8(data[IFLA_VXLAN_UDP_ZERO_CSUM6_RX]))
 		vxlan->flags |= VXLAN_F_UDP_ZERO_CSUM6_RX;
 
-	if (vxlan_find_vni(net, vni, use_ipv6 ? AF_INET6 : AF_INET,
+	if (vxlan_find_vni(src_net, vni, use_ipv6 ? AF_INET6 : AF_INET,
 			   vxlan->dst_port)) {
 		pr_info("duplicate VNI %u\n", vni);
 		return -EEXIST;
diff --git a/drivers/net/wan/Kconfig b/drivers/net/wan/Kconfig
index 94e2349..a2fdd15 100644
--- a/drivers/net/wan/Kconfig
+++ b/drivers/net/wan/Kconfig
@@ -25,7 +25,7 @@
 # There is no way to detect a comtrol sv11 - force it modular for now.
 config HOSTESS_SV11
 	tristate "Comtrol Hostess SV-11 support"
-	depends on ISA && m && ISA_DMA_API && INET && HDLC
+	depends on ISA && m && ISA_DMA_API && INET && HDLC && VIRT_TO_BUS
 	help
 	  Driver for Comtrol Hostess SV-11 network card which
 	  operates on low speed synchronous serial links at up to
@@ -37,7 +37,7 @@
 # The COSA/SRP driver has not been tested as non-modular yet.
 config COSA
 	tristate "COSA/SRP sync serial boards support"
-	depends on ISA && m && ISA_DMA_API && HDLC
+	depends on ISA && m && ISA_DMA_API && HDLC && VIRT_TO_BUS
 	---help---
 	  Driver for COSA and SRP synchronous serial boards.
 
@@ -87,7 +87,7 @@
 # There is no way to detect a Sealevel board. Force it modular
 config SEALEVEL_4021
 	tristate "Sealevel Systems 4021 support"
-	depends on ISA && m && ISA_DMA_API && INET && HDLC
+	depends on ISA && m && ISA_DMA_API && INET && HDLC && VIRT_TO_BUS
 	help
 	  This is a driver for the Sealevel Systems ACB 56 serial I/O adapter.
 
diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c
index 9259a73..037f74f 100644
--- a/drivers/net/xen-netback/interface.c
+++ b/drivers/net/xen-netback/interface.c
@@ -578,6 +578,7 @@
 		goto err_rx_unbind;
 	}
 	queue->task = task;
+	get_task_struct(task);
 
 	task = kthread_create(xenvif_dealloc_kthread,
 			      (void *)queue, "%s-dealloc", queue->name);
@@ -634,6 +635,7 @@
 
 		if (queue->task) {
 			kthread_stop(queue->task);
+			put_task_struct(queue->task);
 			queue->task = NULL;
 		}
 
diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c
index 908e65e..c8ce701 100644
--- a/drivers/net/xen-netback/netback.c
+++ b/drivers/net/xen-netback/netback.c
@@ -2109,8 +2109,7 @@
 		 */
 		if (unlikely(vif->disabled && queue->id == 0)) {
 			xenvif_carrier_off(vif);
-			xenvif_rx_queue_purge(queue);
-			continue;
+			break;
 		}
 
 		if (!skb_queue_empty(&queue->rx_queue))
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index df781cd..17ca986 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -283,6 +283,9 @@
 	struct msi_msg msg;
 	struct pcie_port *pp = sys_to_pcie(pdev->bus->sysdata);
 
+	if (desc->msi_attrib.is_msix)
+		return -EINVAL;
+
 	irq = assign_irq(1, desc, &pos);
 	if (irq < 0)
 		return irq;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index e52356a..903d507 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -324,18 +324,52 @@
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_868,		quirk_s3_64M);
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_S3,	PCI_DEVICE_ID_S3_968,		quirk_s3_64M);
 
+static void quirk_io(struct pci_dev *dev, int pos, unsigned size,
+		     const char *name)
+{
+	u32 region;
+	struct pci_bus_region bus_region;
+	struct resource *res = dev->resource + pos;
+
+	pci_read_config_dword(dev, PCI_BASE_ADDRESS_0 + (pos << 2), &region);
+
+	if (!region)
+		return;
+
+	res->name = pci_name(dev);
+	res->flags = region & ~PCI_BASE_ADDRESS_IO_MASK;
+	res->flags |=
+		(IORESOURCE_IO | IORESOURCE_PCI_FIXED | IORESOURCE_SIZEALIGN);
+	region &= ~(size - 1);
+
+	/* Convert from PCI bus to resource space */
+	bus_region.start = region;
+	bus_region.end = region + size - 1;
+	pcibios_bus_to_resource(dev->bus, res, &bus_region);
+
+	dev_info(&dev->dev, FW_BUG "%s quirk: reg 0x%x: %pR\n",
+		 name, PCI_BASE_ADDRESS_0 + (pos << 2), res);
+}
+
 /*
  * Some CS5536 BIOSes (for example, the Soekris NET5501 board w/ comBIOS
  * ver. 1.33  20070103) don't set the correct ISA PCI region header info.
  * BAR0 should be 8 bytes; instead, it may be set to something like 8k
  * (which conflicts w/ BAR1's memory range).
+ *
+ * CS553x's ISA PCI BARs may also be read-only (ref:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=85991 - Comment #4 forward).
  */
 static void quirk_cs5536_vsa(struct pci_dev *dev)
 {
+	static char *name = "CS5536 ISA bridge";
+
 	if (pci_resource_len(dev, 0) != 8) {
-		struct resource *res = &dev->resource[0];
-		res->end = res->start + 8 - 1;
-		dev_info(&dev->dev, "CS5536 ISA bridge bug detected (incorrect header); workaround applied\n");
+		quirk_io(dev, 0,   8, name);	/* SMB */
+		quirk_io(dev, 1, 256, name);	/* GPIO */
+		quirk_io(dev, 2,  64, name);	/* MFGPT */
+		dev_info(&dev->dev, "%s bug detected (incorrect header); workaround applied\n",
+			 name);
 	}
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_CS5536_ISA, quirk_cs5536_vsa);
diff --git a/drivers/scsi/device_handler/scsi_dh.c b/drivers/scsi/device_handler/scsi_dh.c
index 1dba62c..1efebc9 100644
--- a/drivers/scsi/device_handler/scsi_dh.c
+++ b/drivers/scsi/device_handler/scsi_dh.c
@@ -136,11 +136,12 @@
 	struct scsi_device_handler *scsi_dh = scsi_dh_data->scsi_dh;
 	struct scsi_device *sdev = scsi_dh_data->sdev;
 
+	scsi_dh->detach(sdev);
+
 	spin_lock_irq(sdev->request_queue->queue_lock);
 	sdev->scsi_dh_data = NULL;
 	spin_unlock_irq(sdev->request_queue->queue_lock);
 
-	scsi_dh->detach(sdev);
 	sdev_printk(KERN_NOTICE, sdev, "%s: Detached\n", scsi_dh->name);
 	module_put(scsi_dh->module);
 }
diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
index 3995169..05ea0d4 100644
--- a/drivers/scsi/sd.c
+++ b/drivers/scsi/sd.c
@@ -2800,9 +2800,11 @@
 	 */
 	sd_set_flush_flag(sdkp);
 
-	max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue),
-				sdkp->max_xfer_blocks);
+	max_xfer = sdkp->max_xfer_blocks;
 	max_xfer <<= ilog2(sdp->sector_size) - 9;
+
+	max_xfer = min_not_zero(queue_max_hw_sectors(sdkp->disk->queue),
+				max_xfer);
 	blk_queue_max_hw_sectors(sdkp->disk->queue, max_xfer);
 	set_capacity(disk, sdkp->capacity);
 	sd_config_write_same(sdkp);
diff --git a/drivers/spi/spi-fsl-dspi.c b/drivers/spi/spi-fsl-dspi.c
index 4cda994..9b80d54 100644
--- a/drivers/spi/spi-fsl-dspi.c
+++ b/drivers/spi/spi-fsl-dspi.c
@@ -342,8 +342,7 @@
 	/* Only alloc on first setup */
 	chip = spi_get_ctldata(spi);
 	if (chip == NULL) {
-		chip = devm_kzalloc(&spi->dev, sizeof(struct chip_data),
-				    GFP_KERNEL);
+		chip = kzalloc(sizeof(struct chip_data), GFP_KERNEL);
 		if (!chip)
 			return -ENOMEM;
 	}
@@ -382,6 +381,16 @@
 	return dspi_setup_transfer(spi, NULL);
 }
 
+static void dspi_cleanup(struct spi_device *spi)
+{
+	struct chip_data *chip = spi_get_ctldata((struct spi_device *)spi);
+
+	dev_dbg(&spi->dev, "spi_device %u.%u cleanup\n",
+			spi->master->bus_num, spi->chip_select);
+
+	kfree(chip);
+}
+
 static irqreturn_t dspi_interrupt(int irq, void *dev_id)
 {
 	struct fsl_dspi *dspi = (struct fsl_dspi *)dev_id;
@@ -467,6 +476,7 @@
 	dspi->bitbang.master->setup = dspi_setup;
 	dspi->bitbang.master->dev.of_node = pdev->dev.of_node;
 
+	master->cleanup = dspi_cleanup;
 	master->mode_bits = SPI_CPOL | SPI_CPHA;
 	master->bits_per_word_mask = SPI_BPW_MASK(4) | SPI_BPW_MASK(8) |
 					SPI_BPW_MASK(16);
diff --git a/drivers/spi/spi-imx.c b/drivers/spi/spi-imx.c
index 961b97d..fe1b769 100644
--- a/drivers/spi/spi-imx.c
+++ b/drivers/spi/spi-imx.c
@@ -823,6 +823,10 @@
 	struct dma_slave_config slave_config = {};
 	int ret;
 
+	/* use pio mode for i.mx6dl chip TKT238285 */
+	if (of_machine_is_compatible("fsl,imx6dl"))
+		return 0;
+
 	/* Prepare for TX DMA: */
 	master->dma_tx = dma_request_slave_channel(dev, "tx");
 	if (!master->dma_tx) {
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index d415d69..9484d56 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -650,8 +650,10 @@
 			break;
 		}
 		/* TODO: Should check and handle checksum. */
+
+		hdr.num_buffers = cpu_to_vhost16(vq, headcount);
 		if (likely(mergeable) &&
-		    memcpy_toiovecend(nvq->hdr, (unsigned char *)&headcount,
+		    memcpy_toiovecend(nvq->hdr, (void *)&hdr.num_buffers,
 				      offsetof(typeof(hdr), num_buffers),
 				      sizeof hdr.num_buffers)) {
 			vq_err(vq, "Failed num_buffers write");
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 9a02da1..1a9585d 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2591,6 +2591,7 @@
 	}
 
 	if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
+		blk_finish_plug(&plug);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c
index 9c56ef7..7febcf2 100644
--- a/fs/cifs/cifs_debug.c
+++ b/fs/cifs/cifs_debug.c
@@ -606,9 +606,11 @@
 		*flags = CIFSSEC_MUST_NTLMV2;
 	else if ((*flags & CIFSSEC_MUST_NTLM) == CIFSSEC_MUST_NTLM)
 		*flags = CIFSSEC_MUST_NTLM;
-	else if ((*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN)
+	else if (CIFSSEC_MUST_LANMAN &&
+		 (*flags & CIFSSEC_MUST_LANMAN) == CIFSSEC_MUST_LANMAN)
 		*flags = CIFSSEC_MUST_LANMAN;
-	else if ((*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT)
+	else if (CIFSSEC_MUST_PLNTXT &&
+		 (*flags & CIFSSEC_MUST_PLNTXT) == CIFSSEC_MUST_PLNTXT)
 		*flags = CIFSSEC_MUST_PLNTXT;
 
 	*flags |= signflags;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 96b7e9b..74f1287 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -366,6 +366,7 @@
 	struct cifsLockInfo *li, *tmp;
 	struct cifs_fid fid;
 	struct cifs_pending_open open;
+	bool oplock_break_cancelled;
 
 	spin_lock(&cifs_file_list_lock);
 	if (--cifs_file->count > 0) {
@@ -397,7 +398,7 @@
 	}
 	spin_unlock(&cifs_file_list_lock);
 
-	cancel_work_sync(&cifs_file->oplock_break);
+	oplock_break_cancelled = cancel_work_sync(&cifs_file->oplock_break);
 
 	if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
 		struct TCP_Server_Info *server = tcon->ses->server;
@@ -409,6 +410,9 @@
 		_free_xid(xid);
 	}
 
+	if (oplock_break_cancelled)
+		cifs_done_oplock_break(cifsi);
+
 	cifs_del_pending_open(&open);
 
 	/*
diff --git a/fs/cifs/smbencrypt.c b/fs/cifs/smbencrypt.c
index 6c15663..a4232ec 100644
--- a/fs/cifs/smbencrypt.c
+++ b/fs/cifs/smbencrypt.c
@@ -221,7 +221,7 @@
 	}
 
 	rc = mdfour(p16, (unsigned char *) wpwd, len * sizeof(__le16));
-	memset(wpwd, 0, 129 * sizeof(__le16));
+	memzero_explicit(wpwd, sizeof(wpwd));
 
 	return rc;
 }
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 91093cd..3857040 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -141,7 +141,6 @@
  * @ti_save: Backup of journal_info field of task_struct
  * @ti_flags: Flags
  * @ti_count: Nest level
- * @ti_garbage:	List of inode to be put when releasing semaphore
  */
 struct nilfs_transaction_info {
 	u32			ti_magic;
@@ -150,7 +149,6 @@
 				   one of other filesystems has a bug. */
 	unsigned short		ti_flags;
 	unsigned short		ti_count;
-	struct list_head	ti_garbage;
 };
 
 /* ti_magic */
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 7ef18fc..469086b 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -305,7 +305,6 @@
 	ti->ti_count = 0;
 	ti->ti_save = cur_ti;
 	ti->ti_magic = NILFS_TI_MAGIC;
-	INIT_LIST_HEAD(&ti->ti_garbage);
 	current->journal_info = ti;
 
 	for (;;) {
@@ -332,8 +331,6 @@
 
 	up_write(&nilfs->ns_segctor_sem);
 	current->journal_info = ti->ti_save;
-	if (!list_empty(&ti->ti_garbage))
-		nilfs_dispose_list(nilfs, &ti->ti_garbage, 0);
 }
 
 static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
@@ -746,6 +743,15 @@
 	}
 }
 
+static void nilfs_iput_work_func(struct work_struct *work)
+{
+	struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info,
+						 sc_iput_work);
+	struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+	nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0);
+}
+
 static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
 				     struct nilfs_root *root)
 {
@@ -1900,8 +1906,8 @@
 static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
 					     struct the_nilfs *nilfs)
 {
-	struct nilfs_transaction_info *ti = current->journal_info;
 	struct nilfs_inode_info *ii, *n;
+	int defer_iput = false;
 
 	spin_lock(&nilfs->ns_inode_lock);
 	list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
@@ -1912,9 +1918,24 @@
 		clear_bit(NILFS_I_BUSY, &ii->i_state);
 		brelse(ii->i_bh);
 		ii->i_bh = NULL;
-		list_move_tail(&ii->i_dirty, &ti->ti_garbage);
+		list_del_init(&ii->i_dirty);
+		if (!ii->vfs_inode.i_nlink) {
+			/*
+			 * Defer calling iput() to avoid a deadlock
+			 * over I_SYNC flag for inodes with i_nlink == 0
+			 */
+			list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
+			defer_iput = true;
+		} else {
+			spin_unlock(&nilfs->ns_inode_lock);
+			iput(&ii->vfs_inode);
+			spin_lock(&nilfs->ns_inode_lock);
+		}
 	}
 	spin_unlock(&nilfs->ns_inode_lock);
+
+	if (defer_iput)
+		schedule_work(&sci->sc_iput_work);
 }
 
 /*
@@ -2583,6 +2604,8 @@
 	INIT_LIST_HEAD(&sci->sc_segbufs);
 	INIT_LIST_HEAD(&sci->sc_write_logs);
 	INIT_LIST_HEAD(&sci->sc_gc_inodes);
+	INIT_LIST_HEAD(&sci->sc_iput_queue);
+	INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
 	init_timer(&sci->sc_timer);
 
 	sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
@@ -2609,6 +2632,8 @@
 		ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
 		nilfs_transaction_unlock(sci->sc_super);
 
+		flush_work(&sci->sc_iput_work);
+
 	} while (ret && retrycount-- > 0);
 }
 
@@ -2633,6 +2658,9 @@
 		|| sci->sc_seq_request != sci->sc_seq_done);
 	spin_unlock(&sci->sc_state_lock);
 
+	if (flush_work(&sci->sc_iput_work))
+		flag = true;
+
 	if (flag || !nilfs_segctor_confirm(sci))
 		nilfs_segctor_write_out(sci);
 
@@ -2642,6 +2670,12 @@
 		nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
 	}
 
+	if (!list_empty(&sci->sc_iput_queue)) {
+		nilfs_warning(sci->sc_super, __func__,
+			      "iput queue is not empty\n");
+		nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
+	}
+
 	WARN_ON(!list_empty(&sci->sc_segbufs));
 	WARN_ON(!list_empty(&sci->sc_write_logs));
 
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 38a1d00..a48d6de 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
+#include <linux/workqueue.h>
 #include <linux/nilfs2_fs.h>
 #include "nilfs.h"
 
@@ -92,6 +93,8 @@
  * @sc_nblk_inc: Block count of current generation
  * @sc_dirty_files: List of files to be written
  * @sc_gc_inodes: List of GC inodes having blocks to be written
+ * @sc_iput_queue: list of inodes for which iput should be done
+ * @sc_iput_work: work struct to defer iput call
  * @sc_freesegs: array of segment numbers to be freed
  * @sc_nfreesegs: number of segments on @sc_freesegs
  * @sc_dsync_inode: inode whose data pages are written for a sync operation
@@ -135,6 +138,8 @@
 
 	struct list_head	sc_dirty_files;
 	struct list_head	sc_gc_inodes;
+	struct list_head	sc_iput_queue;
+	struct work_struct	sc_iput_work;
 
 	__u64		       *sc_freesegs;
 	size_t			sc_nfreesegs;
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 515a35e2..960e666 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -472,27 +472,59 @@
 /**
  * vlan_get_protocol - get protocol EtherType.
  * @skb: skbuff to query
+ * @type: first vlan protocol
+ * @depth: buffer to store length of eth and vlan tags in bytes
  *
  * Returns the EtherType of the packet, regardless of whether it is
  * vlan encapsulated (normal or hardware accelerated) or not.
  */
-static inline __be16 vlan_get_protocol(const struct sk_buff *skb)
+static inline __be16 __vlan_get_protocol(struct sk_buff *skb, __be16 type,
+					 int *depth)
 {
-	__be16 protocol = 0;
+	unsigned int vlan_depth = skb->mac_len;
 
-	if (vlan_tx_tag_present(skb) ||
-	     skb->protocol != cpu_to_be16(ETH_P_8021Q))
-		protocol = skb->protocol;
-	else {
-		__be16 proto, *protop;
-		protop = skb_header_pointer(skb, offsetof(struct vlan_ethhdr,
-						h_vlan_encapsulated_proto),
-						sizeof(proto), &proto);
-		if (likely(protop))
-			protocol = *protop;
+	/* if type is 802.1Q/AD then the header should already be
+	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
+	 * ETH_HLEN otherwise
+	 */
+	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
+		if (vlan_depth) {
+			if (WARN_ON(vlan_depth < VLAN_HLEN))
+				return 0;
+			vlan_depth -= VLAN_HLEN;
+		} else {
+			vlan_depth = ETH_HLEN;
+		}
+		do {
+			struct vlan_hdr *vh;
+
+			if (unlikely(!pskb_may_pull(skb,
+						    vlan_depth + VLAN_HLEN)))
+				return 0;
+
+			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
+			type = vh->h_vlan_encapsulated_proto;
+			vlan_depth += VLAN_HLEN;
+		} while (type == htons(ETH_P_8021Q) ||
+			 type == htons(ETH_P_8021AD));
 	}
 
-	return protocol;
+	if (depth)
+		*depth = vlan_depth;
+
+	return type;
+}
+
+/**
+ * vlan_get_protocol - get protocol EtherType.
+ * @skb: skbuff to query
+ *
+ * Returns the EtherType of the packet, regardless of whether it is
+ * vlan encapsulated (normal or hardware accelerated) or not.
+ */
+static inline __be16 vlan_get_protocol(struct sk_buff *skb)
+{
+	return __vlan_get_protocol(skb, skb->protocol, NULL);
 }
 
 static inline void vlan_set_encap_proto(struct sk_buff *skb,
diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h
index 25c791e..5f3a9aa 100644
--- a/include/linux/mlx4/device.h
+++ b/include/linux/mlx4/device.h
@@ -97,7 +97,7 @@
 	MLX4_MAX_NUM_PF		= 16,
 	MLX4_MAX_NUM_VF		= 126,
 	MLX4_MAX_NUM_VF_P_PORT  = 64,
-	MLX4_MFUNC_MAX		= 80,
+	MLX4_MFUNC_MAX		= 128,
 	MLX4_MAX_EQ_NUM		= 1024,
 	MLX4_MFUNC_EQ_NUM	= 4,
 	MLX4_MFUNC_MAX_EQES     = 8,
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index e08e21e..c728513 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -173,7 +173,7 @@
 				TP_PROTO(data_proto),			\
 				TP_ARGS(data_args),			\
 				TP_CONDITION(cond),,);			\
-		if (IS_ENABLED(CONFIG_LOCKDEP)) {			\
+		if (IS_ENABLED(CONFIG_LOCKDEP) && (cond)) {		\
 			rcu_read_lock_sched_notrace();			\
 			rcu_dereference_sched(__tracepoint_##name.funcs);\
 			rcu_read_unlock_sched_notrace();		\
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 2232ed1..37423e0 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -363,7 +363,6 @@
  */
 #define wait_event_cmd(wq, condition, cmd1, cmd2)			\
 do {									\
-	might_sleep();							\
 	if (condition)							\
 		break;							\
 	__wait_event_cmd(wq, condition, cmd1, cmd2);			\
diff --git a/include/net/flow_keys.h b/include/net/flow_keys.h
index 7ee2df0..dc8fd81 100644
--- a/include/net/flow_keys.h
+++ b/include/net/flow_keys.h
@@ -22,9 +22,9 @@
 		__be32 ports;
 		__be16 port16[2];
 	};
-	u16 thoff;
-	u16 n_proto;
-	u8 ip_proto;
+	u16	thoff;
+	__be16	n_proto;
+	u8	ip_proto;
 };
 
 bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
diff --git a/include/net/ip.h b/include/net/ip.h
index f7cbd70..09cf5ae 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -181,7 +181,7 @@
 	return (arg->flags & IP_REPLY_ARG_NOSRCCHECK) ? FLOWI_FLAG_ANYSRC : 0;
 }
 
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index 4292929..6e416f6 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -671,6 +671,9 @@
 	return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr));
 }
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst,
+			struct in6_addr *src);
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt);
 void ipv6_proxy_select_ident(struct sk_buff *skb);
 
 int ip6_dst_hoplimit(struct dst_entry *dst);
@@ -708,7 +711,7 @@
 					__be32 flowlabel, bool autolabel)
 {
 	if (!flowlabel && (autolabel || net->ipv6.sysctl.auto_flowlabels)) {
-		__be32 hash;
+		u32 hash;
 
 		hash = skb_get_hash(skb);
 
@@ -718,7 +721,7 @@
 		 */
 		hash ^= hash >> 12;
 
-		flowlabel = hash & IPV6_FLOWLABEL_MASK;
+		flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 	}
 
 	return flowlabel;
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 3ae969e..9eaaa78 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -530,6 +530,8 @@
 
 int nft_chain_validate_dependency(const struct nft_chain *chain,
 				  enum nft_chain_type type);
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+                             unsigned int hook_flags);
 
 struct nft_stats {
 	u64			bytes;
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 24945ce..0ffef1a 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -52,6 +52,7 @@
 	struct inet_peer_base	*peers;
 	struct tcpm_hash_bucket	*tcp_metrics_hash;
 	unsigned int		tcp_metrics_hash_log;
+	struct sock  * __percpu	*tcp_sk;
 	struct netns_frags	frags;
 #ifdef CONFIG_NETFILTER
 	struct xt_table		*iptable_filter;
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 3d282cb..c605d30 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -79,6 +79,9 @@
 	struct netdev_queue	*dev_queue;
 
 	struct gnet_stats_rate_est64	rate_est;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct gnet_stats_queue	__percpu *cpu_qstats;
+
 	struct Qdisc		*next_sched;
 	struct sk_buff		*gso_skb;
 	/*
@@ -86,15 +89,9 @@
 	 */
 	unsigned long		state;
 	struct sk_buff_head	q;
-	union {
-		struct gnet_stats_basic_packed bstats;
-		struct gnet_stats_basic_cpu __percpu *cpu_bstats;
-	} __packed;
+	struct gnet_stats_basic_packed bstats;
 	unsigned int		__state;
-	union {
-		struct gnet_stats_queue	qstats;
-		struct gnet_stats_queue	__percpu *cpu_qstats;
-	} __packed;
+	struct gnet_stats_queue	qstats;
 	struct rcu_head		rcu_head;
 	int			padded;
 	atomic_t		refcnt;
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f50f29faf..9d9111e 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -834,8 +834,8 @@
 void tcp_get_allowed_congestion_control(char *buf, size_t len);
 int tcp_set_allowed_congestion_control(char *allowed);
 int tcp_set_congestion_control(struct sock *sk, const char *name);
-void tcp_slow_start(struct tcp_sock *tp, u32 acked);
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w);
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked);
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked);
 
 u32 tcp_reno_ssthresh(struct sock *sk);
 void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked);
diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 0d74f1d..65994a1 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1707,10 +1707,7 @@
 
 static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
 {
-	size_t copy_sz;
-
-	copy_sz = min_t(size_t, len, udata->outlen);
-	return copy_to_user(udata->outbuf, src, copy_sz) ? -EFAULT : 0;
+	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
 }
 
 /**
diff --git a/include/sound/ak4113.h b/include/sound/ak4113.h
index 2609048..3a34f6e 100644
--- a/include/sound/ak4113.h
+++ b/include/sound/ak4113.h
@@ -286,7 +286,7 @@
 	ak4113_write_t *write;
 	ak4113_read_t *read;
 	void *private_data;
-	unsigned int init:1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[AK4113_WRITABLE_REGS];
 	struct snd_kcontrol *kctls[AK4113_CONTROLS];
diff --git a/include/sound/ak4114.h b/include/sound/ak4114.h
index 52f02a6..069299a 100644
--- a/include/sound/ak4114.h
+++ b/include/sound/ak4114.h
@@ -168,7 +168,7 @@
 	ak4114_write_t * write;
 	ak4114_read_t * read;
 	void * private_data;
-	unsigned int init: 1;
+	atomic_t wq_processing;
 	spinlock_t lock;
 	unsigned char regmap[6];
 	unsigned char txcsb[5];
diff --git a/include/sound/soc.h b/include/sound/soc.h
index b4fca9a..ac8b333 100644
--- a/include/sound/soc.h
+++ b/include/sound/soc.h
@@ -498,6 +498,7 @@
 				unsigned int mask, unsigned int value);
 
 #ifdef CONFIG_SND_SOC_AC97_BUS
+struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec);
 struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec);
 void snd_soc_free_ac97_codec(struct snd_ac97 *ac97);
 
diff --git a/include/trace/events/tlb.h b/include/trace/events/tlb.h
index 13391d2..0e76357 100644
--- a/include/trace/events/tlb.h
+++ b/include/trace/events/tlb.h
@@ -13,11 +13,13 @@
 	{ TLB_LOCAL_SHOOTDOWN,		"local shootdown" },		\
 	{ TLB_LOCAL_MM_SHOOTDOWN,	"local mm shootdown" }
 
-TRACE_EVENT(tlb_flush,
+TRACE_EVENT_CONDITION(tlb_flush,
 
 	TP_PROTO(int reason, unsigned long pages),
 	TP_ARGS(reason, pages),
 
+	TP_CONDITION(cpu_online(smp_processor_id())),
+
 	TP_STRUCT__entry(
 		__field(	  int, reason)
 		__field(unsigned long,  pages)
diff --git a/include/uapi/rdma/ib_user_verbs.h b/include/uapi/rdma/ib_user_verbs.h
index 4275b96..867cc50 100644
--- a/include/uapi/rdma/ib_user_verbs.h
+++ b/include/uapi/rdma/ib_user_verbs.h
@@ -90,7 +90,6 @@
 };
 
 enum {
-	IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE,
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
 	IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
 };
@@ -202,32 +201,6 @@
 	__u8  reserved[4];
 };
 
-enum {
-	IB_USER_VERBS_EX_QUERY_DEVICE_ODP =		1ULL << 0,
-};
-
-struct ib_uverbs_ex_query_device {
-	__u32 comp_mask;
-	__u32 reserved;
-};
-
-struct ib_uverbs_odp_caps {
-	__u64 general_caps;
-	struct {
-		__u32 rc_odp_caps;
-		__u32 uc_odp_caps;
-		__u32 ud_odp_caps;
-	} per_transport_caps;
-	__u32 reserved;
-};
-
-struct ib_uverbs_ex_query_device_resp {
-	struct ib_uverbs_query_device_resp base;
-	__u32 comp_mask;
-	__u32 reserved;
-	struct ib_uverbs_odp_caps odp_caps;
-};
-
 struct ib_uverbs_query_port {
 	__u64 response;
 	__u8  port_num;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e628cb1..5eab11d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1814,6 +1814,10 @@
 	dl_se->dl_period = 0;
 	dl_se->flags = 0;
 	dl_se->dl_bw = 0;
+
+	dl_se->dl_throttled = 0;
+	dl_se->dl_new = 1;
+	dl_se->dl_yielded = 0;
 }
 
 /*
@@ -1839,7 +1843,7 @@
 #endif
 
 	RB_CLEAR_NODE(&p->dl.rb_node);
-	hrtimer_init(&p->dl.dl_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+	init_dl_task_timer(&p->dl);
 	__dl_clear_params(p);
 
 	INIT_LIST_HEAD(&p->rt.run_list);
@@ -2049,6 +2053,9 @@
  * allocated bandwidth to reflect the new situation.
  *
  * This function is called while holding p's rq->lock.
+ *
+ * XXX we should delay bw change until the task's 0-lag point, see
+ * __setparam_dl().
  */
 static int dl_overflow(struct task_struct *p, int policy,
 		       const struct sched_attr *attr)
@@ -3251,15 +3258,31 @@
 {
 	struct sched_dl_entity *dl_se = &p->dl;
 
-	init_dl_task_timer(dl_se);
 	dl_se->dl_runtime = attr->sched_runtime;
 	dl_se->dl_deadline = attr->sched_deadline;
 	dl_se->dl_period = attr->sched_period ?: dl_se->dl_deadline;
 	dl_se->flags = attr->sched_flags;
 	dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime);
-	dl_se->dl_throttled = 0;
-	dl_se->dl_new = 1;
-	dl_se->dl_yielded = 0;
+
+	/*
+	 * Changing the parameters of a task is 'tricky' and we're not doing
+	 * the correct thing -- also see task_dead_dl() and switched_from_dl().
+	 *
+	 * What we SHOULD do is delay the bandwidth release until the 0-lag
+	 * point. This would include retaining the task_struct until that time
+	 * and change dl_overflow() to not immediately decrement the current
+	 * amount.
+	 *
+	 * Instead we retain the current runtime/deadline and let the new
+	 * parameters take effect after the current reservation period lapses.
+	 * This is safe (albeit pessimistic) because the 0-lag point is always
+	 * before the current scheduling deadline.
+	 *
+	 * We can still have temporary overloads because we do not delay the
+	 * change in bandwidth until that time; so admission control is
+	 * not on the safe side. It does however guarantee tasks will never
+	 * consume more than promised.
+	 */
 }
 
 /*
@@ -4642,6 +4665,9 @@
 	struct dl_bw *cur_dl_b;
 	unsigned long flags;
 
+	if (!cpumask_weight(cur))
+		return ret;
+
 	rcu_read_lock_sched();
 	cur_dl_b = dl_bw_of(cpumask_any(cur));
 	trial_cpus = cpumask_weight(trial);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index b52092f..726470d 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1094,6 +1094,7 @@
 	 * Since we are TASK_DEAD we won't slip out of the domain!
 	 */
 	raw_spin_lock_irq(&dl_b->lock);
+	/* XXX we should retain the bw until 0-lag */
 	dl_b->total_bw -= p->dl.dl_bw;
 	raw_spin_unlock_irq(&dl_b->lock);
 
@@ -1614,8 +1615,8 @@
 
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
+	/* XXX we should retain the bw until 0-lag */
 	cancel_dl_timer(rq, p);
-
 	__dl_clear_params(p);
 
 	/*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 40667cb..fe331fc 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1730,7 +1730,7 @@
 	nodes = node_online_map;
 	for (dist = sched_max_numa_distance; dist > LOCAL_DISTANCE; dist--) {
 		unsigned long max_faults = 0;
-		nodemask_t max_group;
+		nodemask_t max_group = NODE_MASK_NONE;
 		int a, b;
 
 		/* Are there nodes at this distance from each other? */
diff --git a/kernel/smpboot.c b/kernel/smpboot.c
index f032fb5..40190f2 100644
--- a/kernel/smpboot.c
+++ b/kernel/smpboot.c
@@ -280,6 +280,7 @@
 	unsigned int cpu;
 	int ret = 0;
 
+	get_online_cpus();
 	mutex_lock(&smpboot_threads_lock);
 	for_each_online_cpu(cpu) {
 		ret = __smpboot_create_thread(plug_thread, cpu);
@@ -292,6 +293,7 @@
 	list_add(&plug_thread->list, &hotplug_threads);
 out:
 	mutex_unlock(&smpboot_threads_lock);
+	put_online_cpus();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(smpboot_register_percpu_thread);
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 37e50aa..d8c724c 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -122,7 +122,7 @@
 	mono = ktime_get_update_offsets_tick(&off_real, &off_boot, &off_tai);
 	boot = ktime_add(mono, off_boot);
 	xtim = ktime_add(mono, off_real);
-	tai = ktime_add(xtim, off_tai);
+	tai = ktime_add(mono, off_tai);
 
 	base->clock_base[HRTIMER_BASE_REALTIME].softirq_time = xtim;
 	base->clock_base[HRTIMER_BASE_MONOTONIC].softirq_time = mono;
diff --git a/lib/checksum.c b/lib/checksum.c
index 129775e..8b39e86 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -181,6 +181,15 @@
 EXPORT_SYMBOL(csum_partial_copy);
 
 #ifndef csum_tcpudp_nofold
+static inline u32 from64to32(u64 x)
+{
+	/* add up 32-bit and 32-bit for 32+c bit */
+	x = (x & 0xffffffff) + (x >> 32);
+	/* add up carry.. */
+	x = (x & 0xffffffff) + (x >> 32);
+	return (u32)x;
+}
+
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 			unsigned short len,
 			unsigned short proto,
@@ -195,8 +204,7 @@
 #else
 	s += (proto + len) << 8;
 #endif
-	s += (s >> 32);
-	return (__force __wsum)s;
+	return (__force __wsum)from64to32(s);
 }
 EXPORT_SYMBOL(csum_tcpudp_nofold);
 #endif
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 683b478..2f6893c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5773,7 +5773,7 @@
  * mem_cgroup_migrate - migrate a charge to another page
  * @oldpage: currently charged page
  * @newpage: page to transfer the charge to
- * @lrucare: both pages might be on the LRU already
+ * @lrucare: either or both pages might be on the LRU already
  *
  * Migrate the charge from @oldpage to @newpage.
  *
diff --git a/mm/nommu.c b/mm/nommu.c
index b51eadf..28bd8c4 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -59,6 +59,7 @@
 #endif
 
 void *high_memory;
+EXPORT_SYMBOL(high_memory);
 struct page *mem_map;
 unsigned long max_mapnr;
 unsigned long highest_memmap_pfn;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ad83195..b264bda 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -199,7 +199,10 @@
 			 */
 			if ((vma->vm_start <= addr) &&
 			    (vma->vm_flags & VM_PFNMAP)) {
-				next = vma->vm_end;
+				if (walk->pte_hole)
+					err = walk->pte_hole(addr, next, walk);
+				if (err)
+					break;
 				pgd = pgd_offset(walk->mm, next);
 				continue;
 			}
diff --git a/mm/shmem.c b/mm/shmem.c
index 73ba1df..993e6ba 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1013,7 +1013,7 @@
 		 */
 		oldpage = newpage;
 	} else {
-		mem_cgroup_migrate(oldpage, newpage, false);
+		mem_cgroup_migrate(oldpage, newpage, true);
 		lru_cache_add_anon(newpage);
 		*pagep = newpage;
 	}
diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c
index b0330ae..3244aea 100644
--- a/net/bridge/netfilter/nft_reject_bridge.c
+++ b/net/bridge/netfilter/nft_reject_bridge.c
@@ -265,22 +265,12 @@
 	data[NFT_REG_VERDICT].verdict = NF_DROP;
 }
 
-static int nft_reject_bridge_validate_hooks(const struct nft_chain *chain)
+static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
+				      const struct nft_expr *expr,
+				      const struct nft_data **data)
 {
-	struct nft_base_chain *basechain;
-
-	if (chain->flags & NFT_BASE_CHAIN) {
-		basechain = nft_base_chain(chain);
-
-		switch (basechain->ops[0].hooknum) {
-		case NF_BR_PRE_ROUTING:
-		case NF_BR_LOCAL_IN:
-			break;
-		default:
-			return -EOPNOTSUPP;
-		}
-	}
-	return 0;
+	return nft_chain_validate_hooks(ctx->chain, (1 << NF_BR_PRE_ROUTING) |
+						    (1 << NF_BR_LOCAL_IN));
 }
 
 static int nft_reject_bridge_init(const struct nft_ctx *ctx,
@@ -290,7 +280,7 @@
 	struct nft_reject *priv = nft_expr_priv(expr);
 	int icmp_code, err;
 
-	err = nft_reject_bridge_validate_hooks(ctx->chain);
+	err = nft_reject_bridge_validate(ctx, expr, NULL);
 	if (err < 0)
 		return err;
 
@@ -341,13 +331,6 @@
 	return -1;
 }
 
-static int nft_reject_bridge_validate(const struct nft_ctx *ctx,
-				      const struct nft_expr *expr,
-				      const struct nft_data **data)
-{
-	return nft_reject_bridge_validate_hooks(ctx->chain);
-}
-
 static struct nft_expr_type nft_reject_bridge_type;
 static const struct nft_expr_ops nft_reject_bridge_ops = {
 	.type		= &nft_reject_bridge_type,
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 4589ff67..67a4a36 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -470,7 +470,6 @@
 	ASSERT_RTNL();
 	caifdev = netdev_priv(dev);
 	caif_netlink_parms(data, &caifdev->conn_req);
-	dev_net_set(caifdev->netdev, src_net);
 
 	ret = register_netdevice(dev);
 	if (ret)
diff --git a/net/core/dev.c b/net/core/dev.c
index 171420e..7fe8292 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2352,7 +2352,6 @@
 
 __be16 skb_network_protocol(struct sk_buff *skb, int *depth)
 {
-	unsigned int vlan_depth = skb->mac_len;
 	__be16 type = skb->protocol;
 
 	/* Tunnel gso handlers can set protocol to ethernet. */
@@ -2366,35 +2365,7 @@
 		type = eth->h_proto;
 	}
 
-	/* if skb->protocol is 802.1Q/AD then the header should already be
-	 * present at mac_len - VLAN_HLEN (if mac_len > 0), or at
-	 * ETH_HLEN otherwise
-	 */
-	if (type == htons(ETH_P_8021Q) || type == htons(ETH_P_8021AD)) {
-		if (vlan_depth) {
-			if (WARN_ON(vlan_depth < VLAN_HLEN))
-				return 0;
-			vlan_depth -= VLAN_HLEN;
-		} else {
-			vlan_depth = ETH_HLEN;
-		}
-		do {
-			struct vlan_hdr *vh;
-
-			if (unlikely(!pskb_may_pull(skb,
-						    vlan_depth + VLAN_HLEN)))
-				return 0;
-
-			vh = (struct vlan_hdr *)(skb->data + vlan_depth);
-			type = vh->h_vlan_encapsulated_proto;
-			vlan_depth += VLAN_HLEN;
-		} while (type == htons(ETH_P_8021Q) ||
-			 type == htons(ETH_P_8021AD));
-	}
-
-	*depth = vlan_depth;
-
-	return type;
+	return __vlan_get_protocol(skb, type, depth);
 }
 
 /**
@@ -5323,7 +5294,7 @@
 }
 EXPORT_SYMBOL(netdev_upper_dev_unlink);
 
-void netdev_adjacent_add_links(struct net_device *dev)
+static void netdev_adjacent_add_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
 
@@ -5348,7 +5319,7 @@
 	}
 }
 
-void netdev_adjacent_del_links(struct net_device *dev)
+static void netdev_adjacent_del_links(struct net_device *dev)
 {
 	struct netdev_adjacent *iter;
 
@@ -6656,7 +6627,7 @@
 	if (!queue)
 		return NULL;
 	netdev_init_one_queue(dev, queue, NULL);
-	queue->qdisc = &noop_qdisc;
+	RCU_INIT_POINTER(queue->qdisc, &noop_qdisc);
 	queue->qdisc_sleeping = &noop_qdisc;
 	rcu_assign_pointer(dev->ingress_queue, queue);
 #endif
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 9cf6fe9..446cbaf 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2895,12 +2895,16 @@
 			goto errout;
 	}
 
+	if (!skb->len)
+		goto errout;
+
 	rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC);
 	return 0;
 errout:
 	WARN_ON(err == -EMSGSIZE);
 	kfree_skb(skb);
-	rtnl_set_sk_err(net, RTNLGRP_LINK, err);
+	if (err)
+		rtnl_set_sk_err(net, RTNLGRP_LINK, err);
 	return err;
 }
 
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index b50861b..c373c07 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1506,23 +1506,8 @@
 /*
  *	Generic function to send a packet as reply to another packet.
  *	Used to send some TCP resets/acks so far.
- *
- *	Use a fake percpu inet socket to avoid false sharing and contention.
  */
-static DEFINE_PER_CPU(struct inet_sock, unicast_sock) = {
-	.sk = {
-		.__sk_common = {
-			.skc_refcnt = ATOMIC_INIT(1),
-		},
-		.sk_wmem_alloc	= ATOMIC_INIT(1),
-		.sk_allocation	= GFP_ATOMIC,
-		.sk_flags	= (1UL << SOCK_USE_WRITE_QUEUE),
-	},
-	.pmtudisc	= IP_PMTUDISC_WANT,
-	.uc_ttl		= -1,
-};
-
-void ip_send_unicast_reply(struct net *net, struct sk_buff *skb,
+void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb,
 			   const struct ip_options *sopt,
 			   __be32 daddr, __be32 saddr,
 			   const struct ip_reply_arg *arg,
@@ -1532,9 +1517,8 @@
 	struct ipcm_cookie ipc;
 	struct flowi4 fl4;
 	struct rtable *rt = skb_rtable(skb);
+	struct net *net = sock_net(sk);
 	struct sk_buff *nskb;
-	struct sock *sk;
-	struct inet_sock *inet;
 	int err;
 
 	if (__ip_options_echo(&replyopts.opt.opt, skb, sopt))
@@ -1565,15 +1549,11 @@
 	if (IS_ERR(rt))
 		return;
 
-	inet = &get_cpu_var(unicast_sock);
+	inet_sk(sk)->tos = arg->tos;
 
-	inet->tos = arg->tos;
-	sk = &inet->sk;
 	sk->sk_priority = skb->priority;
 	sk->sk_protocol = ip_hdr(skb)->protocol;
 	sk->sk_bound_dev_if = arg->bound_dev_if;
-	sock_net_set(sk, net);
-	__skb_queue_head_init(&sk->sk_write_queue);
 	sk->sk_sndbuf = sysctl_wmem_default;
 	err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
 			     len, 0, &ipc, &rt, MSG_DONTWAIT);
@@ -1589,13 +1569,10 @@
 			  arg->csumoffset) = csum_fold(csum_add(nskb->csum,
 								arg->csum));
 		nskb->ip_summed = CHECKSUM_NONE;
-		skb_orphan(nskb);
 		skb_set_queue_mapping(nskb, skb_get_queue_mapping(skb));
 		ip_push_pending_frames(sk, &fl4);
 	}
 out:
-	put_cpu_var(unicast_sock);
-
 	ip_rt_put(rt);
 }
 
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d58dd0e..52e1f2b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -966,6 +966,9 @@
 	if (dst->dev->mtu < mtu)
 		return;
 
+	if (rt->rt_pmtu && rt->rt_pmtu < mtu)
+		return;
+
 	if (mtu < ip_rt_min_pmtu)
 		mtu = ip_rt_min_pmtu;
 
diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c
index bb395d4..c037644 100644
--- a/net/ipv4/tcp_bic.c
+++ b/net/ipv4/tcp_bic.c
@@ -150,7 +150,7 @@
 		tcp_slow_start(tp, acked);
 	else {
 		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		tcp_cong_avoid_ai(tp, ca->cnt, 1);
 	}
 }
 
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 27ead0d..8670e68 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -291,26 +291,32 @@
  * ABC caps N to 2. Slow start exits when cwnd grows over ssthresh and
  * returns the leftover acks to adjust cwnd in congestion avoidance mode.
  */
-void tcp_slow_start(struct tcp_sock *tp, u32 acked)
+u32 tcp_slow_start(struct tcp_sock *tp, u32 acked)
 {
 	u32 cwnd = tp->snd_cwnd + acked;
 
 	if (cwnd > tp->snd_ssthresh)
 		cwnd = tp->snd_ssthresh + 1;
+	acked -= cwnd - tp->snd_cwnd;
 	tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp);
+
+	return acked;
 }
 EXPORT_SYMBOL_GPL(tcp_slow_start);
 
-/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w) */
-void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w)
+/* In theory this is tp->snd_cwnd += 1 / tp->snd_cwnd (or alternative w),
+ * for every packet that was ACKed.
+ */
+void tcp_cong_avoid_ai(struct tcp_sock *tp, u32 w, u32 acked)
 {
+	tp->snd_cwnd_cnt += acked;
 	if (tp->snd_cwnd_cnt >= w) {
-		if (tp->snd_cwnd < tp->snd_cwnd_clamp)
-			tp->snd_cwnd++;
-		tp->snd_cwnd_cnt = 0;
-	} else {
-		tp->snd_cwnd_cnt++;
+		u32 delta = tp->snd_cwnd_cnt / w;
+
+		tp->snd_cwnd_cnt -= delta * w;
+		tp->snd_cwnd += delta;
 	}
+	tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_cwnd_clamp);
 }
 EXPORT_SYMBOL_GPL(tcp_cong_avoid_ai);
 
@@ -329,11 +335,13 @@
 		return;
 
 	/* In "safe" area, increase. */
-	if (tp->snd_cwnd <= tp->snd_ssthresh)
-		tcp_slow_start(tp, acked);
+	if (tp->snd_cwnd <= tp->snd_ssthresh) {
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
+	}
 	/* In dangerous area, increase slowly. */
-	else
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+	tcp_cong_avoid_ai(tp, tp->snd_cwnd, acked);
 }
 EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
 
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 6b60024..4b276d1 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -93,9 +93,7 @@
 	u32	epoch_start;	/* beginning of an epoch */
 	u32	ack_cnt;	/* number of acks */
 	u32	tcp_cwnd;	/* estimated tcp cwnd */
-#define ACK_RATIO_SHIFT	4
-#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT)
-	u16	delayed_ack;	/* estimate the ratio of Packets/ACKs << 4 */
+	u16	unused;
 	u8	sample_cnt;	/* number of samples to decide curr_rtt */
 	u8	found;		/* the exit point is found? */
 	u32	round_start;	/* beginning of each round */
@@ -114,7 +112,6 @@
 	ca->bic_K = 0;
 	ca->delay_min = 0;
 	ca->epoch_start = 0;
-	ca->delayed_ack = 2 << ACK_RATIO_SHIFT;
 	ca->ack_cnt = 0;
 	ca->tcp_cwnd = 0;
 	ca->found = 0;
@@ -205,23 +202,30 @@
 /*
  * Compute congestion window to use.
  */
-static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
+static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked)
 {
 	u32 delta, bic_target, max_cnt;
 	u64 offs, t;
 
-	ca->ack_cnt++;	/* count the number of ACKs */
+	ca->ack_cnt += acked;	/* count the number of ACKed packets */
 
 	if (ca->last_cwnd == cwnd &&
 	    (s32)(tcp_time_stamp - ca->last_time) <= HZ / 32)
 		return;
 
+	/* The CUBIC function can update ca->cnt at most once per jiffy.
+	 * On all cwnd reduction events, ca->epoch_start is set to 0,
+	 * which will force a recalculation of ca->cnt.
+	 */
+	if (ca->epoch_start && tcp_time_stamp == ca->last_time)
+		goto tcp_friendliness;
+
 	ca->last_cwnd = cwnd;
 	ca->last_time = tcp_time_stamp;
 
 	if (ca->epoch_start == 0) {
 		ca->epoch_start = tcp_time_stamp;	/* record beginning */
-		ca->ack_cnt = 1;			/* start counting */
+		ca->ack_cnt = acked;			/* start counting */
 		ca->tcp_cwnd = cwnd;			/* syn with cubic */
 
 		if (ca->last_max_cwnd <= cwnd) {
@@ -283,6 +287,7 @@
 	if (ca->last_max_cwnd == 0 && ca->cnt > 20)
 		ca->cnt = 20;	/* increase cwnd 5% per RTT */
 
+tcp_friendliness:
 	/* TCP Friendly */
 	if (tcp_friendliness) {
 		u32 scale = beta_scale;
@@ -301,7 +306,6 @@
 		}
 	}
 
-	ca->cnt = (ca->cnt << ACK_RATIO_SHIFT) / ca->delayed_ack;
 	if (ca->cnt == 0)			/* cannot be zero */
 		ca->cnt = 1;
 }
@@ -317,11 +321,12 @@
 	if (tp->snd_cwnd <= tp->snd_ssthresh) {
 		if (hystart && after(ack, ca->end_seq))
 			bictcp_hystart_reset(sk);
-		tcp_slow_start(tp, acked);
-	} else {
-		bictcp_update(ca, tp->snd_cwnd);
-		tcp_cong_avoid_ai(tp, ca->cnt);
+		acked = tcp_slow_start(tp, acked);
+		if (!acked)
+			return;
 	}
+	bictcp_update(ca, tp->snd_cwnd, acked);
+	tcp_cong_avoid_ai(tp, ca->cnt, acked);
 }
 
 static u32 bictcp_recalc_ssthresh(struct sock *sk)
@@ -411,20 +416,10 @@
  */
 static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
 {
-	const struct inet_connection_sock *icsk = inet_csk(sk);
 	const struct tcp_sock *tp = tcp_sk(sk);
 	struct bictcp *ca = inet_csk_ca(sk);
 	u32 delay;
 
-	if (icsk->icsk_ca_state == TCP_CA_Open) {
-		u32 ratio = ca->delayed_ack;
-
-		ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT;
-		ratio += cnt;
-
-		ca->delayed_ack = clamp(ratio, 1U, ACK_RATIO_LIMIT);
-	}
-
 	/* Some calls are for duplicates without timetamps */
 	if (rtt_us < 0)
 		return;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a3f72d7..d22f544 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -683,7 +683,8 @@
 		arg.bound_dev_if = sk->sk_bound_dev_if;
 
 	arg.tos = ip_hdr(skb)->tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -767,7 +768,8 @@
 	if (oif)
 		arg.bound_dev_if = oif;
 	arg.tos = tos;
-	ip_send_unicast_reply(net, skb, &TCP_SKB_CB(skb)->header.h4.opt,
+	ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk),
+			      skb, &TCP_SKB_CB(skb)->header.h4.opt,
 			      ip_hdr(skb)->saddr, ip_hdr(skb)->daddr,
 			      &arg, arg.iov[0].iov_len);
 
@@ -2428,14 +2430,39 @@
 };
 EXPORT_SYMBOL(tcp_prot);
 
-static int __net_init tcp_sk_init(struct net *net)
-{
-	net->ipv4.sysctl_tcp_ecn = 2;
-	return 0;
-}
-
 static void __net_exit tcp_sk_exit(struct net *net)
 {
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
+	free_percpu(net->ipv4.tcp_sk);
+}
+
+static int __net_init tcp_sk_init(struct net *net)
+{
+	int res, cpu;
+
+	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
+	if (!net->ipv4.tcp_sk)
+		return -ENOMEM;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, net);
+		if (res)
+			goto fail;
+		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
+	}
+	net->ipv4.sysctl_tcp_ecn = 2;
+	return 0;
+
+fail:
+	tcp_sk_exit(net);
+
+	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c
index 6824afb..333bcb2 100644
--- a/net/ipv4/tcp_scalable.c
+++ b/net/ipv4/tcp_scalable.c
@@ -25,7 +25,8 @@
 	if (tp->snd_cwnd <= tp->snd_ssthresh)
 		tcp_slow_start(tp, acked);
 	else
-		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT));
+		tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT),
+				  1);
 }
 
 static u32 tcp_scalable_ssthresh(struct sock *sk)
diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c
index a4d2d2d..112151e 100644
--- a/net/ipv4/tcp_veno.c
+++ b/net/ipv4/tcp_veno.c
@@ -159,7 +159,7 @@
 				/* In the "non-congestive state", increase cwnd
 				 *  every rtt.
 				 */
-				tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+				tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 			} else {
 				/* In the "congestive state", increase cwnd
 				 * every other rtt.
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index cd72732..17d3566 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -92,7 +92,7 @@
 
 	} else {
 		/* Reno */
-		tcp_cong_avoid_ai(tp, tp->snd_cwnd);
+		tcp_cong_avoid_ai(tp, tp->snd_cwnd, 1);
 	}
 
 	/* The key players are v_vegas.beg_snd_una and v_beg_snd_nxt.
diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index 13cda4c..01ccc28 100644
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -417,7 +417,7 @@
 		if (code == ICMPV6_HDR_FIELD)
 			teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data);
 
-		if (teli && teli == info - 2) {
+		if (teli && teli == be32_to_cpu(info) - 2) {
 			tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli];
 			if (tel->encap_limit == 0) {
 				net_warn_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n",
@@ -429,7 +429,7 @@
 		}
 		break;
 	case ICMPV6_PKT_TOOBIG:
-		mtu = info - offset;
+		mtu = be32_to_cpu(info) - offset;
 		if (mtu < IPV6_MIN_MTU)
 			mtu = IPV6_MIN_MTU;
 		t->dev->mtu = mtu;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ce69a12..d28f2a2 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -537,20 +537,6 @@
 	skb_copy_secmark(to, from);
 }
 
-static void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
-{
-	static u32 ip6_idents_hashrnd __read_mostly;
-	u32 hash, id;
-
-	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
-
-	hash = __ipv6_addr_jhash(&rt->rt6i_dst.addr, ip6_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&rt->rt6i_src.addr, hash);
-
-	id = ip_idents_reserve(hash, 1);
-	fhdr->identification = htonl(id);
-}
-
 int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
 {
 	struct sk_buff *frag;
diff --git a/net/ipv6/output_core.c b/net/ipv6/output_core.c
index 97f41a3..54520a0 100644
--- a/net/ipv6/output_core.c
+++ b/net/ipv6/output_core.c
@@ -9,6 +9,24 @@
 #include <net/addrconf.h>
 #include <net/secure_seq.h>
 
+u32 __ipv6_select_ident(u32 hashrnd, struct in6_addr *dst, struct in6_addr *src)
+{
+	u32 hash, id;
+
+	hash = __ipv6_addr_jhash(dst, hashrnd);
+	hash = __ipv6_addr_jhash(src, hash);
+
+	/* Treat id of 0 as unset and if we get 0 back from ip_idents_reserve,
+	 * set the hight order instead thus minimizing possible future
+	 * collisions.
+	 */
+	id = ip_idents_reserve(hash, 1);
+	if (unlikely(!id))
+		id = 1 << 31;
+
+	return id;
+}
+
 /* This function exists only for tap drivers that must support broken
  * clients requesting UFO without specifying an IPv6 fragment ID.
  *
@@ -22,7 +40,7 @@
 	static u32 ip6_proxy_idents_hashrnd __read_mostly;
 	struct in6_addr buf[2];
 	struct in6_addr *addrs;
-	u32 hash, id;
+	u32 id;
 
 	addrs = skb_header_pointer(skb,
 				   skb_network_offset(skb) +
@@ -34,14 +52,25 @@
 	net_get_random_once(&ip6_proxy_idents_hashrnd,
 			    sizeof(ip6_proxy_idents_hashrnd));
 
-	hash = __ipv6_addr_jhash(&addrs[1], ip6_proxy_idents_hashrnd);
-	hash = __ipv6_addr_jhash(&addrs[0], hash);
-
-	id = ip_idents_reserve(hash, 1);
-	skb_shinfo(skb)->ip6_frag_id = htonl(id);
+	id = __ipv6_select_ident(ip6_proxy_idents_hashrnd,
+				 &addrs[1], &addrs[0]);
+	skb_shinfo(skb)->ip6_frag_id = id;
 }
 EXPORT_SYMBOL_GPL(ipv6_proxy_select_ident);
 
+void ipv6_select_ident(struct frag_hdr *fhdr, struct rt6_info *rt)
+{
+	static u32 ip6_idents_hashrnd __read_mostly;
+	u32 id;
+
+	net_get_random_once(&ip6_idents_hashrnd, sizeof(ip6_idents_hashrnd));
+
+	id = __ipv6_select_ident(ip6_idents_hashrnd, &rt->rt6i_dst.addr,
+				 &rt->rt6i_src.addr);
+	fhdr->identification = htonl(id);
+}
+EXPORT_SYMBOL(ipv6_select_ident);
+
 int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
 {
 	u16 offset = sizeof(struct ipv6hdr);
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 213546b..cdbfe5a 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -1506,12 +1506,12 @@
 
 	if (data[IFLA_IPTUN_ENCAP_SPORT]) {
 		ret = true;
-		ipencap->sport = nla_get_u16(data[IFLA_IPTUN_ENCAP_SPORT]);
+		ipencap->sport = nla_get_be16(data[IFLA_IPTUN_ENCAP_SPORT]);
 	}
 
 	if (data[IFLA_IPTUN_ENCAP_DPORT]) {
 		ret = true;
-		ipencap->dport = nla_get_u16(data[IFLA_IPTUN_ENCAP_DPORT]);
+		ipencap->dport = nla_get_be16(data[IFLA_IPTUN_ENCAP_DPORT]);
 	}
 
 	return ret;
@@ -1707,9 +1707,9 @@
 
 	if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE,
 			tunnel->encap.type) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_SPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT,
 			tunnel->encap.sport) ||
-	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_DPORT,
+	    nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT,
 			tunnel->encap.dport) ||
 	    nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS,
 			tunnel->encap.flags))
diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c
index b6aa8ed..a562769 100644
--- a/net/ipv6/udp_offload.c
+++ b/net/ipv6/udp_offload.c
@@ -52,6 +52,10 @@
 
 		skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss);
 
+		/* Set the IPv6 fragment id if not set yet */
+		if (!skb_shinfo(skb)->ip6_frag_id)
+			ipv6_proxy_select_ident(skb);
+
 		segs = NULL;
 		goto out;
 	}
@@ -108,7 +112,11 @@
 		fptr = (struct frag_hdr *)(skb_network_header(skb) + unfrag_ip6hlen);
 		fptr->nexthdr = nexthdr;
 		fptr->reserved = 0;
-		fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		if (skb_shinfo(skb)->ip6_frag_id)
+			fptr->identification = skb_shinfo(skb)->ip6_frag_id;
+		else
+			ipv6_select_ident(fptr,
+					  (struct rt6_info *)skb_dst(skb));
 
 		/* Fragment the skb. ipv6 header and the remaining fields of the
 		 * fragment header are updated in ipv6_gso_segment()
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index 990decb..b87ca32 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -659,16 +659,24 @@
 	return err;
 }
 
-static int ip_vs_route_me_harder(int af, struct sk_buff *skb)
+static int ip_vs_route_me_harder(int af, struct sk_buff *skb,
+				 unsigned int hooknum)
 {
+	if (!sysctl_snat_reroute(skb))
+		return 0;
+	/* Reroute replies only to remote clients (FORWARD and LOCAL_OUT) */
+	if (NF_INET_LOCAL_IN == hooknum)
+		return 0;
 #ifdef CONFIG_IP_VS_IPV6
 	if (af == AF_INET6) {
-		if (sysctl_snat_reroute(skb) && ip6_route_me_harder(skb) != 0)
+		struct dst_entry *dst = skb_dst(skb);
+
+		if (dst->dev && !(dst->dev->flags & IFF_LOOPBACK) &&
+		    ip6_route_me_harder(skb) != 0)
 			return 1;
 	} else
 #endif
-		if ((sysctl_snat_reroute(skb) ||
-		     skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
+		if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL) &&
 		    ip_route_me_harder(skb, RTN_LOCAL) != 0)
 			return 1;
 
@@ -791,7 +799,8 @@
 				union nf_inet_addr *snet,
 				__u8 protocol, struct ip_vs_conn *cp,
 				struct ip_vs_protocol *pp,
-				unsigned int offset, unsigned int ihl)
+				unsigned int offset, unsigned int ihl,
+				unsigned int hooknum)
 {
 	unsigned int verdict = NF_DROP;
 
@@ -821,7 +830,7 @@
 #endif
 		ip_vs_nat_icmp(skb, pp, cp, 1);
 
-	if (ip_vs_route_me_harder(af, skb))
+	if (ip_vs_route_me_harder(af, skb, hooknum))
 		goto out;
 
 	/* do the statistics and put it back */
@@ -916,7 +925,7 @@
 
 	snet.ip = iph->saddr;
 	return handle_response_icmp(AF_INET, skb, &snet, cih->protocol, cp,
-				    pp, ciph.len, ihl);
+				    pp, ciph.len, ihl, hooknum);
 }
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -981,7 +990,8 @@
 	snet.in6 = ciph.saddr.in6;
 	writable = ciph.len;
 	return handle_response_icmp(AF_INET6, skb, &snet, ciph.protocol, cp,
-				    pp, writable, sizeof(struct ipv6hdr));
+				    pp, writable, sizeof(struct ipv6hdr),
+				    hooknum);
 }
 #endif
 
@@ -1040,7 +1050,8 @@
  */
 static unsigned int
 handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd,
-		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)
+		struct ip_vs_conn *cp, struct ip_vs_iphdr *iph,
+		unsigned int hooknum)
 {
 	struct ip_vs_protocol *pp = pd->pp;
 
@@ -1078,7 +1089,7 @@
 	 * if it came from this machine itself.  So re-compute
 	 * the routing information.
 	 */
-	if (ip_vs_route_me_harder(af, skb))
+	if (ip_vs_route_me_harder(af, skb, hooknum))
 		goto drop;
 
 	IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT");
@@ -1181,7 +1192,7 @@
 	cp = pp->conn_out_get(af, skb, &iph, 0);
 
 	if (likely(cp))
-		return handle_response(af, skb, pd, cp, &iph);
+		return handle_response(af, skb, pd, cp, &iph, hooknum);
 	if (sysctl_nat_icmp_send(net) &&
 	    (pp->protocol == IPPROTO_TCP ||
 	     pp->protocol == IPPROTO_UDP ||
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 3b3ddb4..1ff04bc 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1134,9 +1134,11 @@
 	/* Restore old counters on this cpu, no problem. Per-cpu statistics
 	 * are not exposed to userspace.
 	 */
+	preempt_disable();
 	stats = this_cpu_ptr(newstats);
 	stats->bytes = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_BYTES]));
 	stats->pkts = be64_to_cpu(nla_get_be64(tb[NFTA_COUNTER_PACKETS]));
+	preempt_enable();
 
 	return newstats;
 }
@@ -1262,8 +1264,10 @@
 		nft_ctx_init(&ctx, skb, nlh, afi, table, chain, nla);
 		trans = nft_trans_alloc(&ctx, NFT_MSG_NEWCHAIN,
 					sizeof(struct nft_trans_chain));
-		if (trans == NULL)
+		if (trans == NULL) {
+			free_percpu(stats);
 			return -ENOMEM;
+		}
 
 		nft_trans_chain_stats(trans) = stats;
 		nft_trans_chain_update(trans) = true;
@@ -1319,8 +1323,10 @@
 		hookfn = type->hooks[hooknum];
 
 		basechain = kzalloc(sizeof(*basechain), GFP_KERNEL);
-		if (basechain == NULL)
+		if (basechain == NULL) {
+			module_put(type->owner);
 			return -ENOMEM;
+		}
 
 		if (nla[NFTA_CHAIN_COUNTERS]) {
 			stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]);
@@ -3753,6 +3759,24 @@
 }
 EXPORT_SYMBOL_GPL(nft_chain_validate_dependency);
 
+int nft_chain_validate_hooks(const struct nft_chain *chain,
+			     unsigned int hook_flags)
+{
+	struct nft_base_chain *basechain;
+
+	if (chain->flags & NFT_BASE_CHAIN) {
+		basechain = nft_base_chain(chain);
+
+		if ((1 << basechain->ops[0].hooknum) & hook_flags)
+			return 0;
+
+		return -EOPNOTSUPP;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(nft_chain_validate_hooks);
+
 /*
  * Loop detection - walk through the ruleset beginning at the destination chain
  * of a new jump until either the source chain is reached (loop) or all
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index d1ffd5e..9aea747 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -21,6 +21,21 @@
 };
 EXPORT_SYMBOL_GPL(nft_masq_policy);
 
+int nft_masq_validate(const struct nft_ctx *ctx,
+		      const struct nft_expr *expr,
+		      const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+				        (1 << NF_INET_POST_ROUTING));
+}
+EXPORT_SYMBOL_GPL(nft_masq_validate);
+
 int nft_masq_init(const struct nft_ctx *ctx,
 		  const struct nft_expr *expr,
 		  const struct nlattr * const tb[])
@@ -28,8 +43,8 @@
 	struct nft_masq *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-	if (err < 0)
+	err = nft_masq_validate(ctx, expr, NULL);
+	if (err)
 		return err;
 
 	if (tb[NFTA_MASQ_FLAGS] == NULL)
@@ -60,12 +75,5 @@
 }
 EXPORT_SYMBOL_GPL(nft_masq_dump);
 
-int nft_masq_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		      const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-EXPORT_SYMBOL_GPL(nft_masq_validate);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index aff54fb1..a0837c6 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -88,6 +88,33 @@
 	[NFTA_NAT_FLAGS]	 = { .type = NLA_U32 },
 };
 
+static int nft_nat_validate(const struct nft_ctx *ctx,
+			    const struct nft_expr *expr,
+			    const struct nft_data **data)
+{
+	struct nft_nat *priv = nft_expr_priv(expr);
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	switch (priv->type) {
+	case NFT_NAT_SNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_POST_ROUTING) |
+					       (1 << NF_INET_LOCAL_IN));
+		break;
+	case NFT_NAT_DNAT:
+		err = nft_chain_validate_hooks(ctx->chain,
+					       (1 << NF_INET_PRE_ROUTING) |
+					       (1 << NF_INET_LOCAL_OUT));
+		break;
+	}
+
+	return err;
+}
+
 static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
 			const struct nlattr * const tb[])
 {
@@ -95,10 +122,6 @@
 	u32 family;
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-	if (err < 0)
-		return err;
-
 	if (tb[NFTA_NAT_TYPE] == NULL ||
 	    (tb[NFTA_NAT_REG_ADDR_MIN] == NULL &&
 	     tb[NFTA_NAT_REG_PROTO_MIN] == NULL))
@@ -115,6 +138,10 @@
 		return -EINVAL;
 	}
 
+	err = nft_nat_validate(ctx, expr, NULL);
+	if (err < 0)
+		return err;
+
 	if (tb[NFTA_NAT_FAMILY] == NULL)
 		return -EINVAL;
 
@@ -219,13 +246,6 @@
 	return -1;
 }
 
-static int nft_nat_validate(const struct nft_ctx *ctx,
-			    const struct nft_expr *expr,
-			    const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-
 static struct nft_expr_type nft_nat_type;
 static const struct nft_expr_ops nft_nat_ops = {
 	.type           = &nft_nat_type,
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index 9e8093f..d7e9e93 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -23,6 +23,22 @@
 };
 EXPORT_SYMBOL_GPL(nft_redir_policy);
 
+int nft_redir_validate(const struct nft_ctx *ctx,
+		       const struct nft_expr *expr,
+		       const struct nft_data **data)
+{
+	int err;
+
+	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	if (err < 0)
+		return err;
+
+	return nft_chain_validate_hooks(ctx->chain,
+					(1 << NF_INET_PRE_ROUTING) |
+					(1 << NF_INET_LOCAL_OUT));
+}
+EXPORT_SYMBOL_GPL(nft_redir_validate);
+
 int nft_redir_init(const struct nft_ctx *ctx,
 		   const struct nft_expr *expr,
 		   const struct nlattr * const tb[])
@@ -30,7 +46,7 @@
 	struct nft_redir *priv = nft_expr_priv(expr);
 	int err;
 
-	err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
+	err = nft_redir_validate(ctx, expr, NULL);
 	if (err < 0)
 		return err;
 
@@ -88,12 +104,5 @@
 }
 EXPORT_SYMBOL_GPL(nft_redir_dump);
 
-int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		       const struct nft_data **data)
-{
-	return nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT);
-}
-EXPORT_SYMBOL_GPL(nft_redir_validate);
-
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo.borrero.glez@gmail.com>");
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 02fdde2..75532ef 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1438,7 +1438,7 @@
 
 	for (undo = 0; undo < group; undo++)
 		if (test_bit(undo, &groups))
-			nlk->netlink_unbind(sock_net(sk), undo);
+			nlk->netlink_unbind(sock_net(sk), undo + 1);
 }
 
 static int netlink_bind(struct socket *sock, struct sockaddr *addr,
@@ -1476,7 +1476,7 @@
 		for (group = 0; group < nlk->ngroups; group++) {
 			if (!test_bit(group, &groups))
 				continue;
-			err = nlk->netlink_bind(net, group);
+			err = nlk->netlink_bind(net, group + 1);
 			if (!err)
 				continue;
 			netlink_undo_bind(group, groups, sk);
diff --git a/net/rds/sysctl.c b/net/rds/sysctl.c
index c3b0cd43..c173f69 100644
--- a/net/rds/sysctl.c
+++ b/net/rds/sysctl.c
@@ -71,14 +71,14 @@
 	{
 		.procname	= "max_unacked_packets",
 		.data		= &rds_sysctl_max_unacked_packets,
-		.maxlen         = sizeof(unsigned long),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
 	{
 		.procname	= "max_unacked_bytes",
 		.data		= &rds_sysctl_max_unacked_bytes,
-		.maxlen         = sizeof(unsigned long),
+		.maxlen         = sizeof(int),
 		.mode           = 0644,
 		.proc_handler   = proc_dointvec,
 	},
diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c
index aad6a67..baef987 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -556,8 +556,9 @@
 }
 EXPORT_SYMBOL(tcf_exts_change);
 
-#define tcf_exts_first_act(ext) \
-		list_first_entry(&(exts)->actions, struct tc_action, list)
+#define tcf_exts_first_act(ext)					\
+	list_first_entry_or_null(&(exts)->actions,		\
+				 struct tc_action, list)
 
 int tcf_exts_dump(struct sk_buff *skb, struct tcf_exts *exts)
 {
@@ -603,7 +604,7 @@
 {
 #ifdef CONFIG_NET_CLS_ACT
 	struct tc_action *a = tcf_exts_first_act(exts);
-	if (tcf_action_copy_stats(skb, a, 1) < 0)
+	if (a != NULL && tcf_action_copy_stats(skb, a, 1) < 0)
 		return -1;
 #endif
 	return 0;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 9b05924..333cd94 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -670,8 +670,14 @@
 	if (tb[TCA_FQ_FLOW_PLIMIT])
 		q->flow_plimit = nla_get_u32(tb[TCA_FQ_FLOW_PLIMIT]);
 
-	if (tb[TCA_FQ_QUANTUM])
-		q->quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
+	if (tb[TCA_FQ_QUANTUM]) {
+		u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]);
+
+		if (quantum > 0)
+			q->quantum = quantum;
+		else
+			err = -EINVAL;
+	}
 
 	if (tb[TCA_FQ_INITIAL_QUANTUM])
 		q->initial_quantum = nla_get_u32(tb[TCA_FQ_INITIAL_QUANTUM]);
diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c
index e49e231..06320c8 100644
--- a/net/sctp/sm_make_chunk.c
+++ b/net/sctp/sm_make_chunk.c
@@ -2608,7 +2608,7 @@
 
 		addr_param = param.v + sizeof(sctp_addip_param_t);
 
-		af = sctp_get_af_specific(param_type2af(param.p->type));
+		af = sctp_get_af_specific(param_type2af(addr_param->p.type));
 		if (af == NULL)
 			break;
 
diff --git a/sound/i2c/other/ak4113.c b/sound/i2c/other/ak4113.c
index 1a3a6fa..c6bba99 100644
--- a/sound/i2c/other/ak4113.c
+++ b/sound/i2c/other/ak4113.c
@@ -56,8 +56,7 @@
 
 static void snd_ak4113_free(struct ak4113 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -89,6 +88,7 @@
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4113_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < AK4113_WRITABLE_REGS ; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -139,13 +139,11 @@
 
 void snd_ak4113_reinit(struct ak4113 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4113_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 EXPORT_SYMBOL_GPL(snd_ak4113_reinit);
@@ -632,8 +630,9 @@
 {
 	struct ak4113 *chip = container_of(work, struct ak4113, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4113_check_rate_and_errors(chip, chip->check_flags);
 
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
diff --git a/sound/i2c/other/ak4114.c b/sound/i2c/other/ak4114.c
index c7f5633..b70e6ec 100644
--- a/sound/i2c/other/ak4114.c
+++ b/sound/i2c/other/ak4114.c
@@ -66,8 +66,7 @@
 
 static void snd_ak4114_free(struct ak4114 *chip)
 {
-	chip->init = 1;	/* don't schedule new work */
-	mb();
+	atomic_inc(&chip->wq_processing);	/* don't schedule new work */
 	cancel_delayed_work_sync(&chip->work);
 	kfree(chip);
 }
@@ -100,6 +99,7 @@
 	chip->write = write;
 	chip->private_data = private_data;
 	INIT_DELAYED_WORK(&chip->work, ak4114_stats);
+	atomic_set(&chip->wq_processing, 0);
 
 	for (reg = 0; reg < 6; reg++)
 		chip->regmap[reg] = pgm[reg];
@@ -152,13 +152,11 @@
 
 void snd_ak4114_reinit(struct ak4114 *chip)
 {
-	chip->init = 1;
-	mb();
-	flush_delayed_work(&chip->work);
+	if (atomic_inc_return(&chip->wq_processing) == 1)
+		cancel_delayed_work_sync(&chip->work);
 	ak4114_init_regs(chip);
 	/* bring up statistics / event queing */
-	chip->init = 0;
-	if (chip->kctls[0])
+	if (atomic_dec_and_test(&chip->wq_processing))
 		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
@@ -612,10 +610,10 @@
 {
 	struct ak4114 *chip = container_of(work, struct ak4114, work.work);
 
-	if (!chip->init)
+	if (atomic_inc_return(&chip->wq_processing) == 1)
 		snd_ak4114_check_rate_and_errors(chip, chip->check_flags);
-
-	schedule_delayed_work(&chip->work, HZ / 10);
+	if (atomic_dec_and_test(&chip->wq_processing))
+		schedule_delayed_work(&chip->work, HZ / 10);
 }
 
 EXPORT_SYMBOL(snd_ak4114_create);
diff --git a/sound/soc/atmel/atmel_ssc_dai.c b/sound/soc/atmel/atmel_ssc_dai.c
index 99ff35e..35e44e4 100644
--- a/sound/soc/atmel/atmel_ssc_dai.c
+++ b/sound/soc/atmel/atmel_ssc_dai.c
@@ -348,7 +348,6 @@
 	struct atmel_pcm_dma_params *dma_params;
 	int dir, channels, bits;
 	u32 tfmr, rfmr, tcmr, rcmr;
-	int start_event;
 	int ret;
 	int fslen, fslen_ext;
 
@@ -457,19 +456,10 @@
 		 * The SSC transmit clock is obtained from the BCLK signal on
 		 * on the TK line, and the SSC receive clock is
 		 * generated from the transmit clock.
-		 *
-		 *  For single channel data, one sample is transferred
-		 * on the falling edge of the LRC clock.
-		 * For two channel data, one sample is
-		 * transferred on both edges of the LRC clock.
 		 */
-		start_event = ((channels == 1)
-				? SSC_START_FALLING_RF
-				: SSC_START_EDGE_RF);
-
 		rcmr =	  SSC_BF(RCMR_PERIOD, 0)
 			| SSC_BF(RCMR_STTDLY, START_DELAY)
-			| SSC_BF(RCMR_START, start_event)
+			| SSC_BF(RCMR_START, SSC_START_FALLING_RF)
 			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
@@ -478,14 +468,14 @@
 		rfmr =	  SSC_BF(RFMR_FSEDGE, SSC_FSEDGE_POSITIVE)
 			| SSC_BF(RFMR_FSOS, SSC_FSOS_NONE)
 			| SSC_BF(RFMR_FSLEN, 0)
-			| SSC_BF(RFMR_DATNB, 0)
+			| SSC_BF(RFMR_DATNB, (channels - 1))
 			| SSC_BIT(RFMR_MSBF)
 			| SSC_BF(RFMR_LOOP, 0)
 			| SSC_BF(RFMR_DATLEN, (bits - 1));
 
 		tcmr =	  SSC_BF(TCMR_PERIOD, 0)
 			| SSC_BF(TCMR_STTDLY, START_DELAY)
-			| SSC_BF(TCMR_START, start_event)
+			| SSC_BF(TCMR_START, SSC_START_FALLING_RF)
 			| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(TCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(TCMR_CKS, ssc->clk_from_rk_pin ?
@@ -495,7 +485,7 @@
 			| SSC_BF(TFMR_FSDEN, 0)
 			| SSC_BF(TFMR_FSOS, SSC_FSOS_NONE)
 			| SSC_BF(TFMR_FSLEN, 0)
-			| SSC_BF(TFMR_DATNB, 0)
+			| SSC_BF(TFMR_DATNB, (channels - 1))
 			| SSC_BIT(TFMR_MSBF)
 			| SSC_BF(TFMR_DATDEF, 0)
 			| SSC_BF(TFMR_DATLEN, (bits - 1));
@@ -512,7 +502,7 @@
 		rcmr =	  SSC_BF(RCMR_PERIOD, ssc_p->rcmr_period)
 			| SSC_BF(RCMR_STTDLY, 1)
 			| SSC_BF(RCMR_START, SSC_START_RISING_RF)
-			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
+			| SSC_BF(RCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(RCMR_CKS, SSC_CKS_DIV);
 
@@ -527,7 +517,7 @@
 		tcmr =	  SSC_BF(TCMR_PERIOD, ssc_p->tcmr_period)
 			| SSC_BF(TCMR_STTDLY, 1)
 			| SSC_BF(TCMR_START, SSC_START_RISING_RF)
-			| SSC_BF(TCMR_CKI, SSC_CKI_RISING)
+			| SSC_BF(TCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(TCMR_CKO, SSC_CKO_CONTINUOUS)
 			| SSC_BF(TCMR_CKS, SSC_CKS_DIV);
 
@@ -556,7 +546,7 @@
 		rcmr =	  SSC_BF(RCMR_PERIOD, 0)
 			| SSC_BF(RCMR_STTDLY, START_DELAY)
 			| SSC_BF(RCMR_START, SSC_START_RISING_RF)
-			| SSC_BF(RCMR_CKI, SSC_CKI_RISING)
+			| SSC_BF(RCMR_CKI, SSC_CKI_FALLING)
 			| SSC_BF(RCMR_CKO, SSC_CKO_NONE)
 			| SSC_BF(RCMR_CKS, ssc->clk_from_rk_pin ?
 					   SSC_CKS_PIN : SSC_CKS_CLOCK);
diff --git a/sound/soc/codecs/rt5640.c b/sound/soc/codecs/rt5640.c
index c3f2dec..1ff726c 100644
--- a/sound/soc/codecs/rt5640.c
+++ b/sound/soc/codecs/rt5640.c
@@ -2124,6 +2124,7 @@
 static struct acpi_device_id rt5640_acpi_match[] = {
 	{ "INT33CA", 0 },
 	{ "10EC5640", 0 },
+	{ "10EC5642", 0 },
 	{ },
 };
 MODULE_DEVICE_TABLE(acpi, rt5640_acpi_match);
diff --git a/sound/soc/codecs/sgtl5000.c b/sound/soc/codecs/sgtl5000.c
index 29cf7ce..aa98be3 100644
--- a/sound/soc/codecs/sgtl5000.c
+++ b/sound/soc/codecs/sgtl5000.c
@@ -483,21 +483,21 @@
 	/* setting i2s data format */
 	switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
 	case SND_SOC_DAIFMT_DSP_A:
-		i2sctl |= SGTL5000_I2S_MODE_PCM;
+		i2sctl |= SGTL5000_I2S_MODE_PCM << SGTL5000_I2S_MODE_SHIFT;
 		break;
 	case SND_SOC_DAIFMT_DSP_B:
-		i2sctl |= SGTL5000_I2S_MODE_PCM;
+		i2sctl |= SGTL5000_I2S_MODE_PCM << SGTL5000_I2S_MODE_SHIFT;
 		i2sctl |= SGTL5000_I2S_LRALIGN;
 		break;
 	case SND_SOC_DAIFMT_I2S:
-		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ;
+		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ << SGTL5000_I2S_MODE_SHIFT;
 		break;
 	case SND_SOC_DAIFMT_RIGHT_J:
-		i2sctl |= SGTL5000_I2S_MODE_RJ;
+		i2sctl |= SGTL5000_I2S_MODE_RJ << SGTL5000_I2S_MODE_SHIFT;
 		i2sctl |= SGTL5000_I2S_LRPOL;
 		break;
 	case SND_SOC_DAIFMT_LEFT_J:
-		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ;
+		i2sctl |= SGTL5000_I2S_MODE_I2S_LJ << SGTL5000_I2S_MODE_SHIFT;
 		i2sctl |= SGTL5000_I2S_LRALIGN;
 		break;
 	default:
@@ -1462,6 +1462,9 @@
 	if (ret)
 		return ret;
 
+	/* Need 8 clocks before I2C accesses */
+	udelay(1);
+
 	/* read chip information */
 	ret = regmap_read(sgtl5000->regmap, SGTL5000_CHIP_ID, &reg);
 	if (ret)
diff --git a/sound/soc/codecs/tlv320aic3x.c b/sound/soc/codecs/tlv320aic3x.c
index b7ebce0..dd222b1 100644
--- a/sound/soc/codecs/tlv320aic3x.c
+++ b/sound/soc/codecs/tlv320aic3x.c
@@ -1046,7 +1046,7 @@
 		delay += aic3x->tdm_delay;
 
 	/* Configure data delay */
-	snd_soc_write(codec, AIC3X_ASD_INTF_CTRLC, aic3x->tdm_delay);
+	snd_soc_write(codec, AIC3X_ASD_INTF_CTRLC, delay);
 
 	return 0;
 }
diff --git a/sound/soc/codecs/wm8731.c b/sound/soc/codecs/wm8731.c
index b9211b4..b115ed8 100644
--- a/sound/soc/codecs/wm8731.c
+++ b/sound/soc/codecs/wm8731.c
@@ -717,6 +717,8 @@
 	if (wm8731 == NULL)
 		return -ENOMEM;
 
+	mutex_init(&wm8731->lock);
+
 	wm8731->regmap = devm_regmap_init_i2c(i2c, &wm8731_regmap);
 	if (IS_ERR(wm8731->regmap)) {
 		ret = PTR_ERR(wm8731->regmap);
diff --git a/sound/soc/codecs/wm9705.c b/sound/soc/codecs/wm9705.c
index 3eddb18..5cc457e 100644
--- a/sound/soc/codecs/wm9705.c
+++ b/sound/soc/codecs/wm9705.c
@@ -344,23 +344,27 @@
 	struct snd_ac97 *ac97;
 	int ret = 0;
 
-	ac97 = snd_soc_new_ac97_codec(codec);
+	ac97 = snd_soc_alloc_ac97_codec(codec);
 	if (IS_ERR(ac97)) {
 		ret = PTR_ERR(ac97);
 		dev_err(codec->dev, "Failed to register AC97 codec\n");
 		return ret;
 	}
 
-	snd_soc_codec_set_drvdata(codec, ac97);
-
 	ret = wm9705_reset(codec);
 	if (ret)
-		goto reset_err;
+		goto err_put_device;
+
+	ret = device_add(&ac97->dev);
+	if (ret)
+		goto err_put_device;
+
+	snd_soc_codec_set_drvdata(codec, ac97);
 
 	return 0;
 
-reset_err:
-	snd_soc_free_ac97_codec(ac97);
+err_put_device:
+	put_device(&ac97->dev);
 	return ret;
 }
 
diff --git a/sound/soc/codecs/wm9712.c b/sound/soc/codecs/wm9712.c
index e04643d..9517571 100644
--- a/sound/soc/codecs/wm9712.c
+++ b/sound/soc/codecs/wm9712.c
@@ -666,7 +666,7 @@
 	struct wm9712_priv *wm9712 = snd_soc_codec_get_drvdata(codec);
 	int ret = 0;
 
-	wm9712->ac97 = snd_soc_new_ac97_codec(codec);
+	wm9712->ac97 = snd_soc_alloc_ac97_codec(codec);
 	if (IS_ERR(wm9712->ac97)) {
 		ret = PTR_ERR(wm9712->ac97);
 		dev_err(codec->dev, "Failed to register AC97 codec: %d\n", ret);
@@ -675,15 +675,19 @@
 
 	ret = wm9712_reset(codec, 0);
 	if (ret < 0)
-		goto reset_err;
+		goto err_put_device;
+
+	ret = device_add(&wm9712->ac97->dev);
+	if (ret)
+		goto err_put_device;
 
 	/* set alc mux to none */
 	ac97_write(codec, AC97_VIDEO, ac97_read(codec, AC97_VIDEO) | 0x3000);
 
 	return 0;
 
-reset_err:
-	snd_soc_free_ac97_codec(wm9712->ac97);
+err_put_device:
+	put_device(&wm9712->ac97->dev);
 	return ret;
 }
 
diff --git a/sound/soc/codecs/wm9713.c b/sound/soc/codecs/wm9713.c
index 71b9d5b..6ab1122 100644
--- a/sound/soc/codecs/wm9713.c
+++ b/sound/soc/codecs/wm9713.c
@@ -1225,7 +1225,7 @@
 	struct wm9713_priv *wm9713 = snd_soc_codec_get_drvdata(codec);
 	int ret = 0, reg;
 
-	wm9713->ac97 = snd_soc_new_ac97_codec(codec);
+	wm9713->ac97 = snd_soc_alloc_ac97_codec(codec);
 	if (IS_ERR(wm9713->ac97))
 		return PTR_ERR(wm9713->ac97);
 
@@ -1234,7 +1234,11 @@
 	wm9713_reset(codec, 0);
 	ret = wm9713_reset(codec, 1);
 	if (ret < 0)
-		goto reset_err;
+		goto err_put_device;
+
+	ret = device_add(&wm9713->ac97->dev);
+	if (ret)
+		goto err_put_device;
 
 	/* unmute the adc - move to kcontrol */
 	reg = ac97_read(codec, AC97_CD) & 0x7fff;
@@ -1242,8 +1246,8 @@
 
 	return 0;
 
-reset_err:
-	snd_soc_free_ac97_codec(wm9713->ac97);
+err_put_device:
+	put_device(&wm9713->ac97->dev);
 	return ret;
 }
 
diff --git a/sound/soc/intel/sst-haswell-ipc.c b/sound/soc/intel/sst-haswell-ipc.c
index 5bf1404..8156cc1 100644
--- a/sound/soc/intel/sst-haswell-ipc.c
+++ b/sound/soc/intel/sst-haswell-ipc.c
@@ -651,11 +651,11 @@
 	}
 
 	/* tell DSP that notification has been handled */
-	sst_dsp_shim_update_bits_unlocked(hsw->dsp, SST_IPCD,
+	sst_dsp_shim_update_bits(hsw->dsp, SST_IPCD,
 		SST_IPCD_BUSY | SST_IPCD_DONE, SST_IPCD_DONE);
 
 	/* unmask busy interrupt */
-	sst_dsp_shim_update_bits_unlocked(hsw->dsp, SST_IMRX, SST_IMRX_BUSY, 0);
+	sst_dsp_shim_update_bits(hsw->dsp, SST_IMRX, SST_IMRX_BUSY, 0);
 }
 
 static struct ipc_message *reply_find_msg(struct sst_hsw *hsw, u32 header)
diff --git a/sound/soc/intel/sst/sst_acpi.c b/sound/soc/intel/sst/sst_acpi.c
index 2ac72eb..b336013 100644
--- a/sound/soc/intel/sst/sst_acpi.c
+++ b/sound/soc/intel/sst/sst_acpi.c
@@ -350,7 +350,7 @@
 
 /* Cherryview-based platforms: CherryTrail and Braswell */
 static struct sst_machines sst_acpi_chv[] = {
-	{"10EC5670", "cht-bsw", "cht-bsw-rt5672", NULL, "fw_sst_22a8.bin",
+	{"10EC5670", "cht-bsw", "cht-bsw-rt5672", NULL, "intel/fw_sst_22a8.bin",
 						&chv_platform_data },
 	{},
 };
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index 2e10e9a..08d7259 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -48,15 +48,18 @@
 }
 
 /**
- * snd_soc_new_ac97_codec - initailise AC97 device
- * @codec: audio codec
+ * snd_soc_alloc_ac97_codec() - Allocate new a AC'97 device
+ * @codec: The CODEC for which to create the AC'97 device
  *
- * Initialises AC97 codec resources for use by ad-hoc devices only.
+ * Allocated a new snd_ac97 device and intializes it, but does not yet register
+ * it. The caller is responsible to either call device_add(&ac97->dev) to
+ * register the device, or to call put_device(&ac97->dev) to free the device.
+ *
+ * Returns: A snd_ac97 device or a PTR_ERR in case of an error.
  */
-struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
+struct snd_ac97 *snd_soc_alloc_ac97_codec(struct snd_soc_codec *codec)
 {
 	struct snd_ac97 *ac97;
-	int ret;
 
 	ac97 = kzalloc(sizeof(struct snd_ac97), GFP_KERNEL);
 	if (ac97 == NULL)
@@ -73,7 +76,28 @@
 		     codec->component.card->snd_card->number, 0,
 		     codec->component.name);
 
-	ret = device_register(&ac97->dev);
+	device_initialize(&ac97->dev);
+
+	return ac97;
+}
+EXPORT_SYMBOL(snd_soc_alloc_ac97_codec);
+
+/**
+ * snd_soc_new_ac97_codec - initailise AC97 device
+ * @codec: audio codec
+ *
+ * Initialises AC97 codec resources for use by ad-hoc devices only.
+ */
+struct snd_ac97 *snd_soc_new_ac97_codec(struct snd_soc_codec *codec)
+{
+	struct snd_ac97 *ac97;
+	int ret;
+
+	ac97 = snd_soc_alloc_ac97_codec(codec);
+	if (IS_ERR(ac97))
+		return ac97;
+
+	ret = device_add(&ac97->dev);
 	if (ret) {
 		put_device(&ac97->dev);
 		return ERR_PTR(ret);
diff --git a/tools/lib/lockdep/.gitignore b/tools/lib/lockdep/.gitignore
new file mode 100644
index 0000000..cc0e7a9
--- /dev/null
+++ b/tools/lib/lockdep/.gitignore
@@ -0,0 +1 @@
+liblockdep.so.*
diff --git a/tools/lib/lockdep/Makefile b/tools/lib/lockdep/Makefile
index 52f9279..4b866c5 100644
--- a/tools/lib/lockdep/Makefile
+++ b/tools/lib/lockdep/Makefile
@@ -104,7 +104,7 @@
 
 export Q VERBOSE
 
-INCLUDES = -I. -I/usr/local/include -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES)
+INCLUDES = -I. -I./uinclude -I./include -I../../include $(CONFIG_INCLUDES)
 
 # Set compile option CFLAGS if not set elsewhere
 CFLAGS ?= -g -DCONFIG_LOCKDEP -DCONFIG_STACKTRACE -DCONFIG_PROVE_LOCKING -DBITS_PER_LONG=__WORDSIZE -DLIBLOCKDEP_VERSION='"$(LIBLOCKDEP_VERSION)"' -rdynamic -O0 -g