Merge tag 'v3.10.83' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable into linux-linaro-lsk-v3.10lsk-v3.10-15.07

This is the 3.10.83 stable release

* tag 'v3.10.83' of git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable: (29 commits)
  Linux 3.10.83
  bus: mvebu: pass the coherency availability information at init time
  KVM: nSVM: Check for NRIPS support before updating control field
  ARM: clk-imx6q: refine sata's parent
  d_walk() might skip too much
  ipv6: update ip6_rt_last_gc every time GC is run
  ipv6: prevent fib6_run_gc() contention
  xfrm: Increase the garbage collector threshold
  Btrfs: make xattr replace operations atomic
  x86/microcode/intel: Guard against stack overflow in the loader
  fs: take i_mutex during prepare_binprm for set[ug]id executables
  hpsa: add missing pci_set_master in kdump path
  hpsa: refine the pci enable/disable handling
  sb_edac: Fix erroneous bytes->gigabytes conversion
  ACPICA: Utilities: Cleanup to remove useless ACPI_PRINTF/FORMAT_xxx helpers.
  ACPICA: Utilities: Cleanup to convert physical address printing formats.
  __ptrace_may_access() should not deny sub-threads
  include/linux/sched.h: don't use task->pid/tgid in same_thread_group/has_group_leader_pid
  netfilter: Zero the tuple in nfnl_cthelper_parse_tuple()
  netfilter: nfnetlink_cthelper: Remove 'const' and '&' to avoid warnings
  ...

51 files changed, 410 insertions, 443 deletions

diff --git a/Makefile b/Makefile
index 6d19e37d36d5..21529dbcc11d 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 3
 PATCHLEVEL = 10
-SUBLEVEL = 81
+SUBLEVEL = 83
 EXTRAVERSION =
 NAME = TOSSUG Baby Fish
 
diff --git a/arch/arm/mach-dove/common.c b/arch/arm/mach-dove/common.c
index e2b5da031f96..8d4f5dc56910 100644
--- a/arch/arm/mach-dove/common.c
+++ b/arch/arm/mach-dove/common.c
@@ -226,7 +226,7 @@ void __init dove_init_early(void)
 	orion_time_set_base(TIMER_VIRT_BASE);
 	mvebu_mbus_init("marvell,dove-mbus",
 			BRIDGE_WINS_BASE, BRIDGE_WINS_SZ,
-			DOVE_MC_WINS_BASE, DOVE_MC_WINS_SZ);
+			DOVE_MC_WINS_BASE, DOVE_MC_WINS_SZ, 0);
 }
 
 static int __init dove_find_tclk(void)
diff --git a/arch/arm/mach-imx/clk-imx6q.c b/arch/arm/mach-imx/clk-imx6q.c
index 2acaded8025d..ed00c9e3bfc6 100644
--- a/arch/arm/mach-imx/clk-imx6q.c
+++ b/arch/arm/mach-imx/clk-imx6q.c
@@ -515,7 +515,7 @@ int __init mx6q_clocks_init(void)
 	clk[gpmi_io]      = imx_clk_gate2("gpmi_io",       "enfc",              base + 0x78, 28);
 	clk[gpmi_apb]     = imx_clk_gate2("gpmi_apb",      "usdhc3",            base + 0x78, 30);
 	clk[rom]          = imx_clk_gate2("rom",           "ahb",               base + 0x7c, 0);
-	clk[sata]         = imx_clk_gate2("sata",          "ipg",               base + 0x7c, 4);
+	clk[sata]         = imx_clk_gate2("sata",          "ahb",               base + 0x7c, 4);
 	clk[sdma]         = imx_clk_gate2("sdma",          "ahb",               base + 0x7c, 6);
 	clk[spba]         = imx_clk_gate2("spba",          "ipg",               base + 0x7c, 12);
 	clk[ssi1_ipg]     = imx_clk_gate2("ssi1_ipg",      "ipg",               base + 0x7c, 18);
diff --git a/arch/arm/mach-kirkwood/common.c b/arch/arm/mach-kirkwood/common.c
index f38922897563..4f6831ea88c5 100644
--- a/arch/arm/mach-kirkwood/common.c
+++ b/arch/arm/mach-kirkwood/common.c
@@ -530,7 +530,7 @@ void __init kirkwood_init_early(void)
 
 	mvebu_mbus_init("marvell,kirkwood-mbus",
 			BRIDGE_WINS_BASE, BRIDGE_WINS_SZ,
-			DDR_WINDOW_CPU_BASE, DDR_WINDOW_CPU_SZ);
+			DDR_WINDOW_CPU_BASE, DDR_WINDOW_CPU_SZ, 0);
 }
 
 int kirkwood_tclk;
diff --git a/arch/arm/mach-mv78xx0/common.c b/arch/arm/mach-mv78xx0/common.c
index 749a7f8c4992..4722c98dc1bb 100644
--- a/arch/arm/mach-mv78xx0/common.c
+++ b/arch/arm/mach-mv78xx0/common.c
@@ -337,11 +337,11 @@ void __init mv78xx0_init_early(void)
 	if (mv78xx0_core_index() == 0)
 		mvebu_mbus_init("marvell,mv78xx0-mbus",
 				BRIDGE_WINS_CPU0_BASE, BRIDGE_WINS_SZ,
-				DDR_WINDOW_CPU0_BASE, DDR_WINDOW_CPU_SZ);
+				DDR_WINDOW_CPU0_BASE, DDR_WINDOW_CPU_SZ, 0);
 	else
 		mvebu_mbus_init("marvell,mv78xx0-mbus",
 				BRIDGE_WINS_CPU1_BASE, BRIDGE_WINS_SZ,
-				DDR_WINDOW_CPU1_BASE, DDR_WINDOW_CPU_SZ);
+				DDR_WINDOW_CPU1_BASE, DDR_WINDOW_CPU_SZ, 0);
 }
 
 void __init_refok mv78xx0_timer_init(void)
diff --git a/arch/arm/mach-mvebu/armada-370-xp.c b/arch/arm/mach-mvebu/armada-370-xp.c
index 1c48890bb72b..4377c3484a62 100644
--- a/arch/arm/mach-mvebu/armada-370-xp.c
+++ b/arch/arm/mach-mvebu/armada-370-xp.c
@@ -66,7 +66,8 @@ void __init armada_370_xp_init_early(void)
 			ARMADA_370_XP_MBUS_WINS_BASE,
 			ARMADA_370_XP_MBUS_WINS_SIZE,
 			ARMADA_370_XP_SDRAM_WINS_BASE,
-			ARMADA_370_XP_SDRAM_WINS_SIZE);
+			ARMADA_370_XP_SDRAM_WINS_SIZE,
+			coherency_available());
 
 #ifdef CONFIG_CACHE_L2X0
 	l2x0_of_init(0, ~0UL);
diff --git a/arch/arm/mach-mvebu/coherency.c b/arch/arm/mach-mvebu/coherency.c
index 3ee701f1d38e..ea26ebb5bb5a 100644
--- a/arch/arm/mach-mvebu/coherency.c
+++ b/arch/arm/mach-mvebu/coherency.c
@@ -137,6 +137,20 @@ static struct notifier_block mvebu_hwcc_platform_nb = {
 	.notifier_call = mvebu_hwcc_platform_notifier,
 };
 
+/*
+ * Keep track of whether we have IO hardware coherency enabled or not.
+ * On Armada 370's we will not be using it for example. We need to make
+ * that available [through coherency_available()] so the mbus controller
+ * doesn't enable the IO coherency bit in the attribute bits of the
+ * chip selects.
+ */
+static int coherency_enabled;
+
+int coherency_available(void)
+{
+	return coherency_enabled;
+}
+
 int __init coherency_init(void)
 {
 	struct device_node *np;
@@ -170,6 +184,7 @@ int __init coherency_init(void)
 		coherency_base = of_iomap(np, 0);
 		coherency_cpu_base = of_iomap(np, 1);
 		set_cpu_coherent(cpu_logical_map(smp_processor_id()), 0);
+		coherency_enabled = 1;
 		bus_register_notifier(&platform_bus_type,
 					&mvebu_hwcc_platform_nb);
 	}
diff --git a/arch/arm/mach-mvebu/coherency.h b/arch/arm/mach-mvebu/coherency.h
index 2f428137f6fe..1501a4e5eea0 100644
--- a/arch/arm/mach-mvebu/coherency.h
+++ b/arch/arm/mach-mvebu/coherency.h
@@ -19,6 +19,7 @@ int coherency_get_cpu_count(void);
 #endif
 
 int set_cpu_coherent(int cpu_id, int smp_group_id);
+int coherency_available(void);
 int coherency_init(void);
 
 #endif	/* __MACH_370_XP_COHERENCY_H */
diff --git a/arch/arm/mach-orion5x/common.c b/arch/arm/mach-orion5x/common.c
index f8a6db9239bf..048773926ad4 100644
--- a/arch/arm/mach-orion5x/common.c
+++ b/arch/arm/mach-orion5x/common.c
@@ -213,7 +213,7 @@ void __init orion5x_init_early(void)
 		mbus_soc_name = NULL;
 	mvebu_mbus_init(mbus_soc_name, ORION5X_BRIDGE_WINS_BASE,
 			ORION5X_BRIDGE_WINS_SZ,
-			ORION5X_DDR_WINS_BASE, ORION5X_DDR_WINS_SZ);
+			ORION5X_DDR_WINS_BASE, ORION5X_DDR_WINS_SZ, 0);
 }
 
 void orion5x_setup_wins(void)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index b2c486f615df..252a986f69fc 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -155,7 +155,7 @@ config SBUS
 
 config NEED_DMA_MAP_STATE
 	def_bool y
-	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG
+	depends on X86_64 || INTEL_IOMMU || DMA_API_DEBUG || SWIOTLB
 
 config NEED_SG_DMA_LENGTH
 	def_bool y
diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c
index 2e9e12871c2b..a883942aee44 100644
--- a/arch/x86/kernel/microcode_intel_early.c
+++ b/arch/x86/kernel/microcode_intel_early.c
@@ -321,7 +321,7 @@ get_matching_model_microcode(int cpu, unsigned long start,
 	unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
 	int i;
 
-	while (leftover) {
+	while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
 		mc_header = (struct microcode_header_intel *)ucode_ptr;
 
 		mc_size = get_totalsize(mc_header);
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 03f7d03c92a2..ee36e1e94a98 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -495,8 +495,10 @@ static void skip_emulated_instruction(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
 
-	if (svm->vmcb->control.next_rip != 0)
+	if (svm->vmcb->control.next_rip != 0) {
+		WARN_ON(!static_cpu_has(X86_FEATURE_NRIPS));
 		svm->next_rip = svm->vmcb->control.next_rip;
+	}
 
 	if (!svm->next_rip) {
 		if (emulate_instruction(vcpu, EMULTYPE_SKIP) !=
@@ -4229,7 +4231,9 @@ static int svm_check_intercept(struct kvm_vcpu *vcpu,
 		break;
 	}
 
-	vmcb->control.next_rip  = info->next_rip;
+	/* TODO: Advertise NRIPS to guest hypervisor unconditionally */
+	if (static_cpu_has(X86_FEATURE_NRIPS))
+		vmcb->control.next_rip  = info->next_rip;
 	vmcb->control.exit_code = icpt_info.exit_code;
 	vmexit = nested_svm_exit_handled(svm);
 
diff --git a/drivers/acpi/acpica/acmacros.h b/drivers/acpi/acpica/acmacros.h
index 53666bd9193d..32b0bf32364a 100644
--- a/drivers/acpi/acpica/acmacros.h
+++ b/drivers/acpi/acpica/acmacros.h
@@ -63,19 +63,15 @@
 #define ACPI_SET64(ptr, val)            (*ACPI_CAST64 (ptr) = (u64) (val))
 
 /*
- * printf() format helpers
+ * printf() format helper. This macros is a workaround for the difficulties
+ * with emitting 64-bit integers and 64-bit pointers with the same code
+ * for both 32-bit and 64-bit hosts.
  */
 
 /* Split 64-bit integer into two 32-bit values. Use with %8.8X%8.8X */
 
 #define ACPI_FORMAT_UINT64(i)           ACPI_HIDWORD(i), ACPI_LODWORD(i)
 
-#if ACPI_MACHINE_WIDTH == 64
-#define ACPI_FORMAT_NATIVE_UINT(i)      ACPI_FORMAT_UINT64(i)
-#else
-#define ACPI_FORMAT_NATIVE_UINT(i)      0, (i)
-#endif
-
 /*
  * Macros for moving data around to/from buffers that are possibly unaligned.
  * If the hardware supports the transfer of unaligned data, just do the store.
diff --git a/drivers/acpi/acpica/dsopcode.c b/drivers/acpi/acpica/dsopcode.c
index e9b13b92ba1e..46a37aeaedae 100644
--- a/drivers/acpi/acpica/dsopcode.c
+++ b/drivers/acpi/acpica/dsopcode.c
@@ -446,7 +446,7 @@ acpi_ds_eval_region_operands(struct acpi_walk_state *walk_state,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n",
 			  obj_desc,
-			  ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address),
+			  ACPI_FORMAT_UINT64(obj_desc->region.address),
 			  obj_desc->region.length));
 
 	/* Now the address and length are valid for this opregion */
@@ -544,7 +544,7 @@ acpi_ds_eval_table_region_operands(struct acpi_walk_state *walk_state,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_EXEC, "RgnObj %p Addr %8.8X%8.8X Len %X\n",
 			  obj_desc,
-			  ACPI_FORMAT_NATIVE_UINT(obj_desc->region.address),
+			  ACPI_FORMAT_UINT64(obj_desc->region.address),
 			  obj_desc->region.length));
 
 	/* Now the address and length are valid for this opregion */
diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
index 8fab9262d98a..ad698893e829 100644
--- a/drivers/acpi/acpica/evregion.c
+++ b/drivers/acpi/acpica/evregion.c
@@ -276,7 +276,7 @@ acpi_ev_address_space_dispatch(union acpi_operand_object *region_obj,
 	ACPI_DEBUG_PRINT((ACPI_DB_OPREGION,
 			  "Handler %p (@%p) Address %8.8X%8.8X [%s]\n",
 			  &region_obj->region.handler->address_space, handler,
-			  ACPI_FORMAT_NATIVE_UINT(address),
+			  ACPI_FORMAT_UINT64(address),
 			  acpi_ut_get_region_name(region_obj->region.
 						  space_id)));
 
diff --git a/drivers/acpi/acpica/exdump.c b/drivers/acpi/acpica/exdump.c
index e5a3c249f7fa..7e6a56fe1d6e 100644
--- a/drivers/acpi/acpica/exdump.c
+++ b/drivers/acpi/acpica/exdump.c
@@ -621,8 +621,8 @@ void acpi_ex_dump_operand(union acpi_operand_object *obj_desc, u32 depth)
 			acpi_os_printf("\n");
 		} else {
 			acpi_os_printf(" base %8.8X%8.8X Length %X\n",
-				       ACPI_FORMAT_NATIVE_UINT(obj_desc->region.
-							       address),
+				       ACPI_FORMAT_UINT64(obj_desc->region.
+							  address),
 				       obj_desc->region.length);
 		}
 		break;
diff --git a/drivers/acpi/acpica/exfldio.c b/drivers/acpi/acpica/exfldio.c
index c84ee956fa4c..dc210c379277 100644
--- a/drivers/acpi/acpica/exfldio.c
+++ b/drivers/acpi/acpica/exfldio.c
@@ -269,17 +269,15 @@ acpi_ex_access_region(union acpi_operand_object *obj_desc,
 	}
 
 	ACPI_DEBUG_PRINT_RAW((ACPI_DB_BFIELD,
-			      " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %p\n",
+			      " Region [%s:%X], Width %X, ByteBase %X, Offset %X at %8.8X%8.8X\n",
 			      acpi_ut_get_region_name(rgn_desc->region.
 						      space_id),
 			      rgn_desc->region.space_id,
 			      obj_desc->common_field.access_byte_width,
 			      obj_desc->common_field.base_byte_offset,
-			      field_datum_byte_offset, ACPI_CAST_PTR(void,
-								     (rgn_desc->
-								      region.
-								      address +
-								      region_offset))));
+			      field_datum_byte_offset,
+			      ACPI_FORMAT_UINT64(rgn_desc->region.address +
+						 region_offset)));
 
 	/* Invoke the appropriate address_space/op_region handler */
 
diff --git a/drivers/acpi/acpica/exregion.c b/drivers/acpi/acpica/exregion.c
index 182abaf045e1..e90c59d35a16 100644
--- a/drivers/acpi/acpica/exregion.c
+++ b/drivers/acpi/acpica/exregion.c
@@ -176,7 +176,7 @@ acpi_ex_system_memory_space_handler(u32 function,
 		if (!mem_info->mapped_logical_address) {
 			ACPI_ERROR((AE_INFO,
 				    "Could not map memory at 0x%8.8X%8.8X, size %u",
-				    ACPI_FORMAT_NATIVE_UINT(address),
+				    ACPI_FORMAT_UINT64(address),
 				    (u32) map_length));
 			mem_info->mapped_length = 0;
 			return_ACPI_STATUS(AE_NO_MEMORY);
@@ -197,8 +197,7 @@ acpi_ex_system_memory_space_handler(u32 function,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			  "System-Memory (width %u) R/W %u Address=%8.8X%8.8X\n",
-			  bit_width, function,
-			  ACPI_FORMAT_NATIVE_UINT(address)));
+			  bit_width, function, ACPI_FORMAT_UINT64(address)));
 
 	/*
 	 * Perform the memory read or write
@@ -300,8 +299,7 @@ acpi_ex_system_io_space_handler(u32 function,
 
 	ACPI_DEBUG_PRINT((ACPI_DB_INFO,
 			  "System-IO (width %u) R/W %u Address=%8.8X%8.8X\n",
-			  bit_width, function,
-			  ACPI_FORMAT_NATIVE_UINT(address)));
+			  bit_width, function, ACPI_FORMAT_UINT64(address)));
 
 	/* Decode the function parameter */
 
diff --git a/drivers/acpi/acpica/hwvalid.c b/drivers/acpi/acpica/hwvalid.c
index eab70d58852a..fae57584a182 100644
--- a/drivers/acpi/acpica/hwvalid.c
+++ b/drivers/acpi/acpica/hwvalid.c
@@ -142,17 +142,17 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 	byte_width = ACPI_DIV_8(bit_width);
 	last_address = address + byte_width - 1;
 
-	ACPI_DEBUG_PRINT((ACPI_DB_IO, "Address %p LastAddress %p Length %X",
-			  ACPI_CAST_PTR(void, address), ACPI_CAST_PTR(void,
-								      last_address),
-			  byte_width));
+	ACPI_DEBUG_PRINT((ACPI_DB_IO,
+			  "Address %8.8X%8.8X LastAddress %8.8X%8.8X Length %X",
+			  ACPI_FORMAT_UINT64(address),
+			  ACPI_FORMAT_UINT64(last_address), byte_width));
 
 	/* Maximum 16-bit address in I/O space */
 
 	if (last_address > ACPI_UINT16_MAX) {
 		ACPI_ERROR((AE_INFO,
-			    "Illegal I/O port address/length above 64K: %p/0x%X",
-			    ACPI_CAST_PTR(void, address), byte_width));
+			    "Illegal I/O port address/length above 64K: %8.8X%8.8X/0x%X",
+			    ACPI_FORMAT_UINT64(address), byte_width));
 		return_ACPI_STATUS(AE_LIMIT);
 	}
 
@@ -181,8 +181,8 @@ acpi_hw_validate_io_request(acpi_io_address address, u32 bit_width)
 
 			if (acpi_gbl_osi_data >= port_info->osi_dependency) {
 				ACPI_DEBUG_PRINT((ACPI_DB_IO,
-						  "Denied AML access to port 0x%p/%X (%s 0x%.4X-0x%.4X)",
-						  ACPI_CAST_PTR(void, address),
+						  "Denied AML access to port 0x%8.8X%8.8X/%X (%s 0x%.4X-0x%.4X)",
+						  ACPI_FORMAT_UINT64(address),
 						  byte_width, port_info->name,
 						  port_info->start,
 						  port_info->end));
diff --git a/drivers/acpi/acpica/nsdump.c b/drivers/acpi/acpica/nsdump.c
index ce6e97326205..20ae5b9bb9f2 100644
--- a/drivers/acpi/acpica/nsdump.c
+++ b/drivers/acpi/acpica/nsdump.c
@@ -258,12 +258,11 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 		switch (type) {
 		case ACPI_TYPE_PROCESSOR:
 
-			acpi_os_printf("ID %02X Len %02X Addr %p\n",
+			acpi_os_printf("ID %02X Len %02X Addr %8.8X%8.8X\n",
 				       obj_desc->processor.proc_id,
 				       obj_desc->processor.length,
-				       ACPI_CAST_PTR(void,
-						     obj_desc->processor.
-						     address));
+				       ACPI_FORMAT_UINT64(obj_desc->processor.
+							  address));
 			break;
 
 		case ACPI_TYPE_DEVICE:
@@ -334,8 +333,9 @@ acpi_ns_dump_one_object(acpi_handle obj_handle,
 							       space_id));
 			if (obj_desc->region.flags & AOPOBJ_DATA_VALID) {
 				acpi_os_printf(" Addr %8.8X%8.8X Len %.4X\n",
-					       ACPI_FORMAT_NATIVE_UINT
-					       (obj_desc->region.address),
+					       ACPI_FORMAT_UINT64(obj_desc->
+								  region.
+								  address),
 					       obj_desc->region.length);
 			} else {
 				acpi_os_printf
diff --git a/drivers/acpi/acpica/tbutils.c b/drivers/acpi/acpica/tbutils.c
index ce3d5db39a9c..5c67b2840c58 100644
--- a/drivers/acpi/acpica/tbutils.c
+++ b/drivers/acpi/acpica/tbutils.c
@@ -246,16 +246,12 @@ acpi_tb_print_table_header(acpi_physical_address address,
 {
 	struct acpi_table_header local_header;
 
-	/*
-	 * The reason that the Address is cast to a void pointer is so that we
-	 * can use %p which will work properly on both 32-bit and 64-bit hosts.
-	 */
 	if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_FACS)) {
 
 		/* FACS only has signature and length fields */
 
-		ACPI_INFO((AE_INFO, "%4.4s %p %05X",
-			   header->signature, ACPI_CAST_PTR(void, address),
+		ACPI_INFO((AE_INFO, "%4.4s 0x%8.8X%8.8X %05X",
+			   header->signature, ACPI_FORMAT_UINT64(address),
 			   header->length));
 	} else if (ACPI_COMPARE_NAME(header->signature, ACPI_SIG_RSDP)) {
 
@@ -266,8 +262,8 @@ acpi_tb_print_table_header(acpi_physical_address address,
 					  header)->oem_id, ACPI_OEM_ID_SIZE);
 		acpi_tb_fix_string(local_header.oem_id, ACPI_OEM_ID_SIZE);
 
-		ACPI_INFO((AE_INFO, "RSDP %p %05X (v%.2d %6.6s)",
-			   ACPI_CAST_PTR (void, address),
+		ACPI_INFO((AE_INFO, "RSDP 0x%8.8X%8.8X %05X (v%.2d %6.6s)",
+			   ACPI_FORMAT_UINT64(address),
 			   (ACPI_CAST_PTR(struct acpi_table_rsdp, header)->
 			    revision >
 			    0) ? ACPI_CAST_PTR(struct acpi_table_rsdp,
@@ -281,8 +277,8 @@ acpi_tb_print_table_header(acpi_physical_address address,
 		acpi_tb_cleanup_table_header(&local_header, header);
 
 		ACPI_INFO((AE_INFO,
-			   "%4.4s %p %05X (v%.2d %6.6s %8.8s %08X %4.4s %08X)",
-			   local_header.signature, ACPI_CAST_PTR(void, address),
+			   "%-4.4s 0x%8.8X%8.8X %05X (v%.2d %-6.6s %-8.8s %08X %-4.4s %08X)",
+			   local_header.signature, ACPI_FORMAT_UINT64(address),
 			   local_header.length, local_header.revision,
 			   local_header.oem_id, local_header.oem_table_id,
 			   local_header.oem_revision,
@@ -474,8 +470,8 @@ acpi_tb_install_table(acpi_physical_address address,
 	table = acpi_os_map_memory(address, sizeof(struct acpi_table_header));
 	if (!table) {
 		ACPI_ERROR((AE_INFO,
-			    "Could not map memory for table [%s] at %p",
-			    signature, ACPI_CAST_PTR(void, address)));
+			    "Could not map memory for table [%s] at %8.8X%8.8X",
+			    signature, ACPI_FORMAT_UINT64(address)));
 		return;
 	}
 
diff --git a/drivers/acpi/acpica/utaddress.c b/drivers/acpi/acpica/utaddress.c
index e0a2e2779c2e..3c7770d75773 100644
--- a/drivers/acpi/acpica/utaddress.c
+++ b/drivers/acpi/acpica/utaddress.c
@@ -107,10 +107,10 @@ acpi_ut_add_address_range(acpi_adr_space_type space_id,
 	acpi_gbl_address_range_list[space_id] = range_info;
 
 	ACPI_DEBUG_PRINT((ACPI_DB_NAMES,
-			  "\nAdded [%4.4s] address range: 0x%p-0x%p\n",
+			  "\nAdded [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n",
 			  acpi_ut_get_node_name(range_info->region_node),
-			  ACPI_CAST_PTR(void, address),
-			  ACPI_CAST_PTR(void, range_info->end_address)));
+			  ACPI_FORMAT_UINT64(address),
+			  ACPI_FORMAT_UINT64(range_info->end_address)));
 
 	(void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
 	return_ACPI_STATUS(AE_OK);
@@ -160,15 +160,13 @@ acpi_ut_remove_address_range(acpi_adr_space_type space_id,
 			}
 
 			ACPI_DEBUG_PRINT((ACPI_DB_NAMES,
-					  "\nRemoved [%4.4s] address range: 0x%p-0x%p\n",
+					  "\nRemoved [%4.4s] address range: 0x%8.8X%8.8X-0x%8.8X%8.8X\n",
 					  acpi_ut_get_node_name(range_info->
 								region_node),
-					  ACPI_CAST_PTR(void,
-							range_info->
-							start_address),
-					  ACPI_CAST_PTR(void,
-							range_info->
-							end_address)));
+					  ACPI_FORMAT_UINT64(range_info->
+							     start_address),
+					  ACPI_FORMAT_UINT64(range_info->
+							     end_address)));
 
 			ACPI_FREE(range_info);
 			return_VOID;
@@ -244,9 +242,9 @@ acpi_ut_check_address_range(acpi_adr_space_type space_id,
 								  region_node);
 
 				ACPI_WARNING((AE_INFO,
-					      "0x%p-0x%p %s conflicts with Region %s %d",
-					      ACPI_CAST_PTR(void, address),
-					      ACPI_CAST_PTR(void, end_address),
+					      "0x%8.8X%8.8X-0x%8.8X%8.8X %s conflicts with Region %s %d",
+					      ACPI_FORMAT_UINT64(address),
+					      ACPI_FORMAT_UINT64(end_address),
 					      acpi_ut_get_region_name(space_id),
 					      pathname, overlap_count));
 				ACPI_FREE(pathname);
diff --git a/drivers/bus/mvebu-mbus.c b/drivers/bus/mvebu-mbus.c
index 711dcf4a0313..7c437826c2f9 100644
--- a/drivers/bus/mvebu-mbus.c
+++ b/drivers/bus/mvebu-mbus.c
@@ -838,7 +838,7 @@ fs_initcall(mvebu_mbus_debugfs_init);
 int __init mvebu_mbus_init(const char *soc, phys_addr_t mbuswins_phys_base,
 			   size_t mbuswins_size,
 			   phys_addr_t sdramwins_phys_base,
-			   size_t sdramwins_size)
+			   size_t sdramwins_size, int is_coherent)
 {
 	struct mvebu_mbus_state *mbus = &mbus_state;
 	const struct of_device_id *of_id;
@@ -865,8 +865,7 @@ int __init mvebu_mbus_init(const char *soc, phys_addr_t mbuswins_phys_base,
 		return -ENOMEM;
 	}
 
-	if (of_find_compatible_node(NULL, NULL, "marvell,coherency-fabric"))
-		mbus->hw_io_coherency = 1;
+	mbus->hw_io_coherency = is_coherent;
 
 	for (win = 0; win < mbus->soc->num_wins; win++)
 		mvebu_mbus_disable_window(mbus, win);
diff --git a/drivers/crypto/caam/caamrng.c b/drivers/crypto/caam/caamrng.c
index d1939a9539c0..04aefffb4dd9 100644
--- a/drivers/crypto/caam/caamrng.c
+++ b/drivers/crypto/caam/caamrng.c
@@ -56,7 +56,7 @@
 
 /* Buffer, its dma address and lock */
 struct buf_data {
-	u8 buf[RN_BUF_SIZE];
+	u8 buf[RN_BUF_SIZE] ____cacheline_aligned;
 	dma_addr_t addr;
 	struct completion filled;
 	u32 hw_desc[DESC_JOB_O_LEN];
diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
index f505e4ca6d58..3bdefbfb4377 100644
--- a/drivers/edac/sb_edac.c
+++ b/drivers/edac/sb_edac.c
@@ -623,7 +623,7 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	u32 reg;
 	u64 limit, prv = 0;
 	u64 tmp_mb;
-	u32 mb, kb;
+	u32 gb, mb;
 	u32 rir_way;
 
 	/*
@@ -636,8 +636,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	pvt->tolm = GET_TOLM(reg);
 	tmp_mb = (1 + pvt->tolm) >> 20;
 
-	mb = div_u64_rem(tmp_mb, 1000, &kb);
-	edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tolm);
+	gb = div_u64_rem(tmp_mb, 1024, &mb);
+	edac_dbg(0, "TOLM: %u.%03u GB (0x%016Lx)\n",
+		gb, (mb*1000)/1024, (u64)pvt->tolm);
 
 	/* Address range is already 45:25 */
 	pci_read_config_dword(pvt->pci_sad1, TOHM,
@@ -645,8 +646,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 	pvt->tohm = GET_TOHM(reg);
 	tmp_mb = (1 + pvt->tohm) >> 20;
 
-	mb = div_u64_rem(tmp_mb, 1000, &kb);
-	edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n", mb, kb, (u64)pvt->tohm);
+	gb = div_u64_rem(tmp_mb, 1024, &mb);
+	edac_dbg(0, "TOHM: %u.%03u GB (0x%016Lx)\n",
+		gb, (mb*1000)/1024, (u64)pvt->tohm);
 
 	/*
 	 * Step 2) Get SAD range and SAD Interleave list
@@ -668,11 +670,11 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 
 		tmp_mb = (limit + 1) >> 20;
-		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		gb = div_u64_rem(tmp_mb, 1024, &mb);
 		edac_dbg(0, "SAD#%d %s up to %u.%03u GB (0x%016Lx) Interleave: %s reg=0x%08x\n",
 			 n_sads,
 			 get_dram_attr(reg),
-			 mb, kb,
+			 gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
 			 INTERLEAVE_MODE(reg) ? "8:6" : "[8:6]XOR[18:16]",
 			 reg);
@@ -702,9 +704,9 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 			break;
 		tmp_mb = (limit + 1) >> 20;
 
-		mb = div_u64_rem(tmp_mb, 1000, &kb);
+		gb = div_u64_rem(tmp_mb, 1024, &mb);
 		edac_dbg(0, "TAD#%d: up to %u.%03u GB (0x%016Lx), socket interleave %d, memory interleave %d, TGT: %d, %d, %d, %d, reg=0x%08x\n",
-			 n_tads, mb, kb,
+			 n_tads, gb, (mb*1000)/1024,
 			 ((u64)tmp_mb) << 20L,
 			 (u32)TAD_SOCK(reg),
 			 (u32)TAD_CH(reg),
@@ -727,10 +729,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 					      tad_ch_nilv_offset[j],
 					      &reg);
 			tmp_mb = TAD_OFFSET(reg) >> 20;
-			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			gb = div_u64_rem(tmp_mb, 1024, &mb);
 			edac_dbg(0, "TAD CH#%d, offset #%d: %u.%03u GB (0x%016Lx), reg=0x%08x\n",
 				 i, j,
-				 mb, kb,
+				 gb, (mb*1000)/1024,
 				 ((u64)tmp_mb) << 20L,
 				 reg);
 		}
@@ -752,10 +754,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 
 			tmp_mb = RIR_LIMIT(reg) >> 20;
 			rir_way = 1 << RIR_WAY(reg);
-			mb = div_u64_rem(tmp_mb, 1000, &kb);
+			gb = div_u64_rem(tmp_mb, 1024, &mb);
 			edac_dbg(0, "CH#%d RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d, reg=0x%08x\n",
 				 i, j,
-				 mb, kb,
+				 gb, (mb*1000)/1024,
 				 ((u64)tmp_mb) << 20L,
 				 rir_way,
 				 reg);
@@ -766,10 +768,10 @@ static void get_memory_layout(const struct mem_ctl_info *mci)
 						      &reg);
 				tmp_mb = RIR_OFFSET(reg) << 6;
 
-				mb = div_u64_rem(tmp_mb, 1000, &kb);
+				gb = div_u64_rem(tmp_mb, 1024, &mb);
 				edac_dbg(0, "CH#%d RIR#%d INTL#%d, offset %u.%03u GB (0x%016Lx), tgt: %d, reg=0x%08x\n",
 					 i, j, k,
-					 mb, kb,
+					 gb, (mb*1000)/1024,
 					 ((u64)tmp_mb) << 20L,
 					 (u32)RIR_RNK_TGT(reg),
 					 reg);
@@ -806,7 +808,7 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 	u8			ch_way,sck_way;
 	u32			tad_offset;
 	u32			rir_way;
-	u32			mb, kb;
+	u32			mb, gb;
 	u64			ch_addr, offset, limit, prv = 0;
 
 
@@ -1022,10 +1024,10 @@ static int get_memory_error_data(struct mem_ctl_info *mci,
 			continue;
 
 		limit = RIR_LIMIT(reg);
-		mb = div_u64_rem(limit >> 20, 1000, &kb);
+		gb = div_u64_rem(limit >> 20, 1024, &mb);
 		edac_dbg(0, "RIR#%d, limit: %u.%03u GB (0x%016Lx), way: %d\n",
 			 n_rir,
-			 mb, kb,
+			 gb, (mb*1000)/1024,
 			 limit,
 			 1 << RIR_WAY(reg));
 		if  (ch_addr <= limit)
diff --git a/drivers/gpu/drm/mgag200/mgag200_mode.c b/drivers/gpu/drm/mgag200/mgag200_mode.c
index f6341e8622ee..7bd2acce9f81 100644
--- a/drivers/gpu/drm/mgag200/mgag200_mode.c
+++ b/drivers/gpu/drm/mgag200/mgag200_mode.c
@@ -1487,6 +1487,11 @@ static int mga_vga_mode_valid(struct drm_connector *connector,
 		return MODE_BANDWIDTH;
 	}
 
+	if ((mode->hdisplay % 8) != 0 || (mode->hsync_start % 8) != 0 ||
+	    (mode->hsync_end % 8) != 0 || (mode->htotal % 8) != 0) {
+		return MODE_H_ILLEGAL;
+	}
+
 	if (mode->crtc_hdisplay > 2048 || mode->crtc_hsync_start > 4096 ||
 	    mode->crtc_hsync_end > 4096 || mode->crtc_htotal > 4096 ||
 	    mode->crtc_vdisplay > 2048 || mode->crtc_vsync_start > 4096 ||
diff --git a/drivers/scsi/hpsa.c b/drivers/scsi/hpsa.c
index 62ed744bbe06..a6cdf17e27dc 100644
--- a/drivers/scsi/hpsa.c
+++ b/drivers/scsi/hpsa.c
@@ -3898,10 +3898,6 @@ static int hpsa_kdump_hard_reset_controller(struct pci_dev *pdev)
 
 	/* Save the PCI command register */
 	pci_read_config_word(pdev, 4, &command_register);
-	/* Turn the board off.  This is so that later pci_restore_state()
-	 * won't turn the board on before the rest of config space is ready.
-	 */
-	pci_disable_device(pdev);
 	pci_save_state(pdev);
 
 	/* find the first memory BAR, so we can find the cfg table */
@@ -3949,11 +3945,6 @@ static int hpsa_kdump_hard_reset_controller(struct pci_dev *pdev)
 		goto unmap_cfgtable;
 
 	pci_restore_state(pdev);
-	rc = pci_enable_device(pdev);
-	if (rc) {
-		dev_warn(&pdev->dev, "failed to enable device.\n");
-		goto unmap_cfgtable;
-	}
 	pci_write_config_word(pdev, 4, command_register);
 
 	/* Some devices (notably the HP Smart Array 5i Controller)
@@ -4448,6 +4439,23 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev)
 	if (!reset_devices)
 		return 0;
 
+	/* kdump kernel is loading, we don't know in which state is
+	 * the pci interface. The dev->enable_cnt is equal zero
+	 * so we call enable+disable, wait a while and switch it on.
+	 */
+	rc = pci_enable_device(pdev);
+	if (rc) {
+		dev_warn(&pdev->dev, "Failed to enable PCI device\n");
+		return -ENODEV;
+	}
+	pci_disable_device(pdev);
+	msleep(260);			/* a randomly chosen number */
+	rc = pci_enable_device(pdev);
+	if (rc) {
+		dev_warn(&pdev->dev, "failed to enable device.\n");
+		return -ENODEV;
+	}
+	pci_set_master(pdev);
 	/* Reset the controller with a PCI power-cycle or via doorbell */
 	rc = hpsa_kdump_hard_reset_controller(pdev);
 
@@ -4456,10 +4464,11 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev)
 	 * "performant mode".  Or, it might be 640x, which can't reset
 	 * due to concerns about shared bbwc between 6402/6404 pair.
 	 */
-	if (rc == -ENOTSUPP)
-		return rc; /* just try to do the kdump anyhow. */
-	if (rc)
-		return -ENODEV;
+	if (rc) {
+		if (rc != -ENOTSUPP) /* just try to do the kdump anyhow. */
+			rc = -ENODEV;
+		goto out_disable;
+	}
 
 	/* Now try to get the controller to respond to a no-op */
 	dev_warn(&pdev->dev, "Waiting for controller to respond to no-op\n");
@@ -4470,7 +4479,11 @@ static int hpsa_init_reset_devices(struct pci_dev *pdev)
 			dev_warn(&pdev->dev, "no-op failed%s\n",
 					(i < 11 ? "; re-trying" : ""));
 	}
-	return 0;
+
+out_disable:
+
+	pci_disable_device(pdev);
+	return rc;
 }
 
 static int hpsa_allocate_cmd_pool(struct ctlr_info *h)
@@ -4613,6 +4626,7 @@ static void hpsa_undo_allocations_after_kdump_soft_reset(struct ctlr_info *h)
 		iounmap(h->transtable);
 	if (h->cfgtable)
 		iounmap(h->cfgtable);
+	pci_disable_device(h->pdev);
 	pci_release_regions(h->pdev);
 	kfree(h);
 }
diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
index 572579f87de4..90861416b9e9 100644
--- a/drivers/scsi/lpfc/lpfc_sli.c
+++ b/drivers/scsi/lpfc/lpfc_sli.c
@@ -263,6 +263,16 @@ lpfc_sli4_eq_get(struct lpfc_queue *q)
 		return NULL;
 
 	q->hba_index = idx;
+
+	/*
+	 * insert barrier for instruction interlock : data from the hardware
+	 * must have the valid bit checked before it can be copied and acted
+	 * upon. Given what was seen in lpfc_sli4_cq_get() of speculative
+	 * instructions allowing action on content before valid bit checked,
+	 * add barrier here as well. May not be needed as "content" is a
+	 * single 32-bit entity here (vs multi word structure for cq's).
+	 */
+	mb();
 	return eqe;
 }
 
@@ -368,6 +378,17 @@ lpfc_sli4_cq_get(struct lpfc_queue *q)
 
 	cqe = q->qe[q->hba_index].cqe;
 	q->hba_index = idx;
+
+	/*
+	 * insert barrier for instruction interlock : data from the hardware
+	 * must have the valid bit checked before it can be copied and acted
+	 * upon. Speculative instructions were allowing a bcopy at the start
+	 * of lpfc_sli4_fp_handle_wcqe(), which is called immediately
+	 * after our return, to copy data before the valid bit check above
+	 * was done. As such, some of the copied data was stale. The barrier
+	 * ensures the check is before any data is copied.
+	 */
+	mb();
 	return cqe;
 }
 
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index 7fb054ba1b60..82f14a1da542 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -2769,7 +2769,7 @@ done:
 	 */
 	if (!p->leave_spinning)
 		btrfs_set_path_blocking(p);
-	if (ret < 0)
+	if (ret < 0 && !p->skip_release_on_error)
 		btrfs_release_path(p);
 	return ret;
 }
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index d6dd49b51ba8..c19444e412be 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -586,6 +586,7 @@ struct btrfs_path {
 	unsigned int skip_locking:1;
 	unsigned int leave_spinning:1;
 	unsigned int search_commit_root:1;
+	unsigned int skip_release_on_error:1;
 };
 
 /*
@@ -3406,6 +3407,10 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 int verify_dir_item(struct btrfs_root *root,
 		    struct extent_buffer *leaf,
 		    struct btrfs_dir_item *dir_item);
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+						 struct btrfs_path *path,
+						 const char *name,
+						 int name_len);
 
 /* orphan.c */
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index 79e594e341c7..6f61b9b1526f 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -21,10 +21,6 @@
 #include "hash.h"
 #include "transaction.h"
 
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
-			      struct btrfs_path *path,
-			      const char *name, int name_len);
-
 /*
  * insert a name into a directory, doing overflow properly if there is a hash
  * collision.  data_size indicates how big the item inserted should be.  On
@@ -383,9 +379,9 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
  * this walks through all the entries in a dir item and finds one
  * for a specific name.
  */
-static struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
-			      struct btrfs_path *path,
-			      const char *name, int name_len)
+struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_root *root,
+						 struct btrfs_path *path,
+						 const char *name, int name_len)
 {
 	struct btrfs_dir_item *dir_item;
 	unsigned long name_ptr;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 05740b9789e4..9cf20d63cc99 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -27,6 +27,7 @@
 #include "transaction.h"
 #include "xattr.h"
 #include "disk-io.h"
+#include "locking.h"
 
 
 ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
@@ -89,7 +90,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		       struct inode *inode, const char *name,
 		       const void *value, size_t size, int flags)
 {
-	struct btrfs_dir_item *di;
+	struct btrfs_dir_item *di = NULL;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_path *path;
 	size_t name_len = strlen(name);
@@ -101,84 +102,128 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
+	path->skip_release_on_error = 1;
+
+	if (!value) {
+		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
+					name, name_len, -1);
+		if (!di && (flags & XATTR_REPLACE))
+			ret = -ENODATA;
+		else if (di)
+			ret = btrfs_delete_one_dir_name(trans, root, path, di);
+		goto out;
+	}
 
+	/*
+	 * For a replace we can't just do the insert blindly.
+	 * Do a lookup first (read-only btrfs_search_slot), and return if xattr
+	 * doesn't exist. If it exists, fall down below to the insert/replace
+	 * path - we can't race with a concurrent xattr delete, because the VFS
+	 * locks the inode's i_mutex before calling setxattr or removexattr.
+	 */
 	if (flags & XATTR_REPLACE) {
-		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode), name,
-					name_len, -1);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
-			goto out;
-		} else if (!di) {
+		if(!mutex_is_locked(&inode->i_mutex)) {
+			pr_err("BTRFS: assertion failed: %s, file: %s, line: %d",
+			       "mutex_is_locked(&inode->i_mutex)", __FILE__,
+			       __LINE__);
+			BUG();
+		}
+		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
+					name, name_len, 0);
+		if (!di) {
 			ret = -ENODATA;
 			goto out;
 		}
-		ret = btrfs_delete_one_dir_name(trans, root, path, di);
-		if (ret)
-			goto out;
 		btrfs_release_path(path);
+		di = NULL;
+	}
 
+	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
+				      name, name_len, value, size);
+	if (ret == -EOVERFLOW) {
 		/*
-		 * remove the attribute
+		 * We have an existing item in a leaf, split_leaf couldn't
+		 * expand it. That item might have or not a dir_item that
+		 * matches our target xattr, so lets check.
 		 */
-		if (!value)
-			goto out;
-	} else {
-		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
-					name, name_len, 0);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
+		ret = 0;
+		btrfs_assert_tree_locked(path->nodes[0]);
+		di = btrfs_match_dir_item_name(root, path, name, name_len);
+		if (!di && !(flags & XATTR_REPLACE)) {
+			ret = -ENOSPC;
 			goto out;
 		}
-		if (!di && !value)
-			goto out;
-		btrfs_release_path(path);
+	} else if (ret == -EEXIST) {
+		ret = 0;
+		di = btrfs_match_dir_item_name(root, path, name, name_len);
+		if(!di) { /* logic error */
+			pr_err("BTRFS: assertion failed: %s, file: %s, line: %d",
+			       "di", __FILE__, __LINE__);
+			BUG();
+		}
+	} else if (ret) {
+		goto out;
 	}
 
-again:
-	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
-				      name, name_len, value, size);
-	/*
-	 * If we're setting an xattr to a new value but the new value is say
-	 * exactly BTRFS_MAX_XATTR_SIZE, we could end up with EOVERFLOW getting
-	 * back from split_leaf.  This is because it thinks we'll be extending
-	 * the existing item size, but we're asking for enough space to add the
-	 * item itself.  So if we get EOVERFLOW just set ret to EEXIST and let
-	 * the rest of the function figure it out.
-	 */
-	if (ret == -EOVERFLOW)
+	if (di && (flags & XATTR_CREATE)) {
 		ret = -EEXIST;
+		goto out;
+	}
 
-	if (ret == -EEXIST) {
-		if (flags & XATTR_CREATE)
-			goto out;
+	if (di) {
 		/*
-		 * We can't use the path we already have since we won't have the
-		 * proper locking for a delete, so release the path and
-		 * re-lookup to delete the thing.
+		 * We're doing a replace, and it must be atomic, that is, at
+		 * any point in time we have either the old or the new xattr
+		 * value in the tree. We don't want readers (getxattr and
+		 * listxattrs) to miss a value, this is specially important
+		 * for ACLs.
 		 */
-		btrfs_release_path(path);
-		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
-					name, name_len, -1);
-		if (IS_ERR(di)) {
-			ret = PTR_ERR(di);
-			goto out;
-		} else if (!di) {
-			/* Shouldn't happen but just in case... */
-			btrfs_release_path(path);
-			goto again;
+		const int slot = path->slots[0];
+		struct extent_buffer *leaf = path->nodes[0];
+		const u16 old_data_len = btrfs_dir_data_len(leaf, di);
+		const u32 item_size = btrfs_item_size_nr(leaf, slot);
+		const u32 data_size = sizeof(*di) + name_len + size;
+		struct btrfs_item *item;
+		unsigned long data_ptr;
+		char *ptr;
+
+		if (size > old_data_len) {
+			if (btrfs_leaf_free_space(root, leaf) <
+			    (size - old_data_len)) {
+				ret = -ENOSPC;
+				goto out;
+			}
 		}
 
-		ret = btrfs_delete_one_dir_name(trans, root, path, di);
-		if (ret)
-			goto out;
+		if (old_data_len + name_len + sizeof(*di) == item_size) {
+			/* No other xattrs packed in the same leaf item. */
+			if (size > old_data_len)
+				btrfs_extend_item(root, path,
+						  size - old_data_len);
+			else if (size < old_data_len)
+				btrfs_truncate_item(root, path, data_size, 1);
+		} else {
+			/* There are other xattrs packed in the same item. */
+			ret = btrfs_delete_one_dir_name(trans, root, path, di);
+			if (ret)
+				goto out;
+			btrfs_extend_item(root, path, data_size);
+		}
 
+		item = btrfs_item_nr(NULL, slot);
+		ptr = btrfs_item_ptr(leaf, slot, char);
+		ptr += btrfs_item_size(leaf, item) - data_size;
+		di = (struct btrfs_dir_item *)ptr;
+		btrfs_set_dir_data_len(leaf, di, size);
+		data_ptr = ((unsigned long)(di + 1)) + name_len;
+		write_extent_buffer(leaf, value, data_ptr, size);
+		btrfs_mark_buffer_dirty(leaf);
+	} else {
 		/*
-		 * We have a value to set, so go back and try to insert it now.
+		 * Insert, and we had space for the xattr, so path->slots[0] is
+		 * where our xattr dir_item is and btrfs_insert_xattr_item()
+		 * filled it.
 		 */
-		if (value) {
-			btrfs_release_path(path);
-			goto again;
-		}
 	}
 out:
 	btrfs_free_path(path);
diff --git a/fs/dcache.c b/fs/dcache.c
index e2800926ae05..38c4a302fab4 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1053,13 +1053,13 @@ ascend:
 		/* might go back up the wrong parent if we have had a rename. */
 		if (!locked && read_seqretry(&rename_lock, seq))
 			goto rename_retry;
-		next = child->d_child.next;
-		while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+		/* go into the first sibling still alive */
+		do {
+			next = child->d_child.next;
 			if (next == &this_parent->d_subdirs)
 				goto ascend;
 			child = list_entry(next, struct dentry, d_child);
-			next = next->next;
-		}
+		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
 		rcu_read_unlock();
 		goto resume;
 	}
@@ -2977,13 +2977,13 @@ ascend:
 		/* might go back up the wrong parent if we have had a rename. */
 		if (!locked && read_seqretry(&rename_lock, seq))
 			goto rename_retry;
-		next = child->d_child.next;
-		while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED)) {
+		/* go into the first sibling still alive */
+		do {
+			next = child->d_child.next;
 			if (next == &this_parent->d_subdirs)
 				goto ascend;
 			child = list_entry(next, struct dentry, d_child);
-			next = next->next;
-		}
+		} while (unlikely(child->d_flags & DCACHE_DENTRY_KILLED));
 		rcu_read_unlock();
 		goto resume;
 	}
diff --git a/fs/exec.c b/fs/exec.c
index dd6aa61c8548..acbd7ac2deda 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1265,6 +1265,53 @@ static int check_unsafe_exec(struct linux_binprm *bprm)
 	return res;
 }
 
+static void bprm_fill_uid(struct linux_binprm *bprm)
+{
+	struct inode *inode;
+	unsigned int mode;
+	kuid_t uid;
+	kgid_t gid;
+
+	/* clear any previous set[ug]id data from a previous binary */
+	bprm->cred->euid = current_euid();
+	bprm->cred->egid = current_egid();
+
+	if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)
+		return;
+
+	if (current->no_new_privs)
+		return;
+
+	inode = file_inode(bprm->file);
+	mode = ACCESS_ONCE(inode->i_mode);
+	if (!(mode & (S_ISUID|S_ISGID)))
+		return;
+
+	/* Be careful if suid/sgid is set */
+	mutex_lock(&inode->i_mutex);
+
+	/* reload atomically mode/uid/gid now that lock held */
+	mode = inode->i_mode;
+	uid = inode->i_uid;
+	gid = inode->i_gid;
+	mutex_unlock(&inode->i_mutex);
+
+	/* We ignore suid/sgid if there are no mappings for them in the ns */
+	if (!kuid_has_mapping(bprm->cred->user_ns, uid) ||
+		 !kgid_has_mapping(bprm->cred->user_ns, gid))
+		return;
+
+	if (mode & S_ISUID) {
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+		bprm->cred->euid = uid;
+	}
+
+	if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
+		bprm->per_clear |= PER_CLEAR_ON_SETID;
+		bprm->cred->egid = gid;
+	}
+}
+
 /* 
  * Fill the binprm structure from the inode. 
  * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes
@@ -1273,39 +1320,12 @@ static int check_unsafe_exec(struct linux_binprm *bprm)
  */
 int prepare_binprm(struct linux_binprm *bprm)
 {
-	umode_t mode;
-	struct inode * inode = file_inode(bprm->file);
 	int retval;
 
-	mode = inode->i_mode;
 	if (bprm->file->f_op == NULL)
 		return -EACCES;
 
-	/* clear any previous set[ug]id data from a previous binary */
-	bprm->cred->euid = current_euid();
-	bprm->cred->egid = current_egid();
-
-	if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) &&
-	    !current->no_new_privs &&
-	    kuid_has_mapping(bprm->cred->user_ns, inode->i_uid) &&
-	    kgid_has_mapping(bprm->cred->user_ns, inode->i_gid)) {
-		/* Set-uid? */
-		if (mode & S_ISUID) {
-			bprm->per_clear |= PER_CLEAR_ON_SETID;
-			bprm->cred->euid = inode->i_uid;
-		}
-
-		/* Set-gid? */
-		/*
-		 * If setgid is set but no group execute bit then this
-		 * is a candidate for mandatory locking, not a setgid
-		 * executable.
-		 */
-		if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) {
-			bprm->per_clear |= PER_CLEAR_ON_SETID;
-			bprm->cred->egid = inode->i_gid;
-		}
-	}
+	bprm_fill_uid(bprm);
 
 	/* fill in binprm security blob */
 	retval = security_bprm_set_creds(bprm);
diff --git a/fs/file_table.c b/fs/file_table.c
index 54a34be444f9..28f02a7cbba1 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -36,8 +36,6 @@ struct files_stat_struct files_stat = {
 	.max_files = NR_FILE
 };
 
-DEFINE_STATIC_LGLOCK(files_lglock);
-
 /* SLAB cache for file structures */
 static struct kmem_cache *filp_cachep __read_mostly;
 
@@ -134,7 +132,6 @@ struct file *get_empty_filp(void)
 		return ERR_PTR(error);
 	}
 
-	INIT_LIST_HEAD(&f->f_u.fu_list);
 	atomic_long_set(&f->f_count, 1);
 	rwlock_init(&f->f_owner.lock);
 	spin_lock_init(&f->f_lock);
@@ -265,18 +262,15 @@ static void __fput(struct file *file)
 	mntput(mnt);
 }
 
-static DEFINE_SPINLOCK(delayed_fput_lock);
-static LIST_HEAD(delayed_fput_list);
+static LLIST_HEAD(delayed_fput_list);
 static void delayed_fput(struct work_struct *unused)
 {
-	LIST_HEAD(head);
-	spin_lock_irq(&delayed_fput_lock);
-	list_splice_init(&delayed_fput_list, &head);
-	spin_unlock_irq(&delayed_fput_lock);
-	while (!list_empty(&head)) {
-		struct file *f = list_first_entry(&head, struct file, f_u.fu_list);
-		list_del_init(&f->f_u.fu_list);
-		__fput(f);
+	struct llist_node *node = llist_del_all(&delayed_fput_list);
+	struct llist_node *next;
+
+	for (; node; node = next) {
+		next = llist_next(node);
+		__fput(llist_entry(node, struct file, f_u.fu_llist));
 	}
 }
 
@@ -306,18 +300,15 @@ void fput(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
-		unsigned long flags;
 
-		file_sb_list_del(file);
 		if (likely(!in_interrupt() && !(task->flags & PF_KTHREAD))) {
 			init_task_work(&file->f_u.fu_rcuhead, ____fput);
 			if (!task_work_add(task, &file->f_u.fu_rcuhead, true))
 				return;
 		}
-		spin_lock_irqsave(&delayed_fput_lock, flags);
-		list_add(&file->f_u.fu_list, &delayed_fput_list);
-		schedule_work(&delayed_fput_work);
-		spin_unlock_irqrestore(&delayed_fput_lock, flags);
+
+		if (llist_add(&file->f_u.fu_llist, &delayed_fput_list))
+			schedule_work(&delayed_fput_work);
 	}
 }
 
@@ -333,7 +324,6 @@ void __fput_sync(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		struct task_struct *task = current;
-		file_sb_list_del(file);
 		BUG_ON(!(task->flags & PF_KTHREAD));
 		__fput(file);
 	}
@@ -345,127 +335,10 @@ void put_filp(struct file *file)
 {
 	if (atomic_long_dec_and_test(&file->f_count)) {
 		security_file_free(file);
-		file_sb_list_del(file);
 		file_free(file);
 	}
 }
 
-static inline int file_list_cpu(struct file *file)
-{
-#ifdef CONFIG_SMP
-	return file->f_sb_list_cpu;
-#else
-	return smp_processor_id();
-#endif
-}
-
-/* helper for file_sb_list_add to reduce ifdefs */
-static inline void __file_sb_list_add(struct file *file, struct super_block *sb)
-{
-	struct list_head *list;
-#ifdef CONFIG_SMP
-	int cpu;
-	cpu = smp_processor_id();
-	file->f_sb_list_cpu = cpu;
-	list = per_cpu_ptr(sb->s_files, cpu);
-#else
-	list = &sb->s_files;
-#endif
-	list_add(&file->f_u.fu_list, list);
-}
-
-/**
- * file_sb_list_add - add a file to the sb's file list
- * @file: file to add
- * @sb: sb to add it to
- *
- * Use this function to associate a file with the superblock of the inode it
- * refers to.
- */
-void file_sb_list_add(struct file *file, struct super_block *sb)
-{
-	lg_local_lock(&files_lglock);
-	__file_sb_list_add(file, sb);
-	lg_local_unlock(&files_lglock);
-}
-
-/**
- * file_sb_list_del - remove a file from the sb's file list
- * @file: file to remove
- * @sb: sb to remove it from
- *
- * Use this function to remove a file from its superblock.
- */
-void file_sb_list_del(struct file *file)
-{
-	if (!list_empty(&file->f_u.fu_list)) {
-		lg_local_lock_cpu(&files_lglock, file_list_cpu(file));
-		list_del_init(&file->f_u.fu_list);
-		lg_local_unlock_cpu(&files_lglock, file_list_cpu(file));
-	}
-}
-
-#ifdef CONFIG_SMP
-
-/*
- * These macros iterate all files on all CPUs for a given superblock.
- * files_lglock must be held globally.
- */
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	int i;							\
-	for_each_possible_cpu(i) {				\
-		struct list_head *list;				\
-		list = per_cpu_ptr((__sb)->s_files, i);		\
-		list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
-	}							\
-}
-
-#else
-
-#define do_file_list_for_each_entry(__sb, __file)		\
-{								\
-	struct list_head *list;					\
-	list = &(sb)->s_files;					\
-	list_for_each_entry((__file), list, f_u.fu_list)
-
-#define while_file_list_for_each_entry				\
-}
-
-#endif
-
-/**
- *	mark_files_ro - mark all files read-only
- *	@sb: superblock in question
- *
- *	All files are marked read-only.  We don't care about pending
- *	delete files so this should be used in 'force' mode only.
- */
-void mark_files_ro(struct super_block *sb)
-{
-	struct file *f;
-
-	lg_global_lock(&files_lglock);
-	do_file_list_for_each_entry(sb, f) {
-		if (!S_ISREG(file_inode(f)->i_mode))
-		       continue;
-		if (!file_count(f))
-			continue;
-		if (!(f->f_mode & FMODE_WRITE))
-			continue;
-		spin_lock(&f->f_lock);
-		f->f_mode &= ~FMODE_WRITE;
-		spin_unlock(&f->f_lock);
-		if (file_check_writeable(f) != 0)
-			continue;
-		__mnt_drop_write(f->f_path.mnt);
-		file_release_write(f);
-	} while_file_list_for_each_entry;
-	lg_global_unlock(&files_lglock);
-}
-
 void __init files_init(unsigned long mempages)
 { 
 	unsigned long n;
@@ -481,6 +354,5 @@ void __init files_init(unsigned long mempages)
 	n = (mempages * (PAGE_SIZE / 1024)) / 10;
 	files_stat.max_files = max_t(unsigned long, n, NR_FILE);
 	files_defer_init();
-	lg_lock_init(&files_lglock, "files_lglock");
 	percpu_counter_init(&nr_files, 0);
 } 
diff --git a/fs/internal.h b/fs/internal.h
index 68121584ae37..2ffa65a36ca0 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -74,9 +74,6 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 /*
  * file_table.c
  */
-extern void file_sb_list_add(struct file *f, struct super_block *sb);
-extern void file_sb_list_del(struct file *f);
-extern void mark_files_ro(struct super_block *);
 extern struct file *get_empty_filp(void);
 
 /*
diff --git a/fs/open.c b/fs/open.c
index 86092bde31f4..5f129683b7d7 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -674,7 +674,6 @@ static int do_dentry_open(struct file *f,
 	}
 
 	f->f_mapping = inode->i_mapping;
-	file_sb_list_add(f, inode->i_sb);
 
 	if (unlikely(f->f_mode & FMODE_PATH)) {
 		f->f_op = &empty_fops;
@@ -709,7 +708,6 @@ static int do_dentry_open(struct file *f,
 
 cleanup_all:
 	fops_put(f->f_op);
-	file_sb_list_del(f);
 	if (f->f_mode & FMODE_WRITE) {
 		if (!special_file(inode->i_mode)) {
 			/*
diff --git a/fs/pipe.c b/fs/pipe.c
index 0e0752ef2715..3e7ab278bb0c 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -117,25 +117,27 @@ void pipe_wait(struct pipe_inode_info *pipe)
 }
 
 static int
-pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len,
-			int atomic)
+pipe_iov_copy_from_user(void *addr, int *offset, struct iovec *iov,
+			size_t *remaining, int atomic)
 {
 	unsigned long copy;
 
-	while (len > 0) {
+	while (*remaining > 0) {
 		while (!iov->iov_len)
 			iov++;
-		copy = min_t(unsigned long, len, iov->iov_len);
+		copy = min_t(unsigned long, *remaining, iov->iov_len);
 
 		if (atomic) {
-			if (__copy_from_user_inatomic(to, iov->iov_base, copy))
+			if (__copy_from_user_inatomic(addr + *offset,
+						      iov->iov_base, copy))
 				return -EFAULT;
 		} else {
-			if (copy_from_user(to, iov->iov_base, copy))
+			if (copy_from_user(addr + *offset,
+					   iov->iov_base, copy))
 				return -EFAULT;
 		}
-		to += copy;
-		len -= copy;
+		*offset += copy;
+		*remaining -= copy;
 		iov->iov_base += copy;
 		iov->iov_len -= copy;
 	}
@@ -143,25 +145,27 @@ pipe_iov_copy_from_user(void *to, struct iovec *iov, unsigned long len,
 }
 
 static int
-pipe_iov_copy_to_user(struct iovec *iov, const void *from, unsigned long len,
-		      int atomic)
+pipe_iov_copy_to_user(struct iovec *iov, void *addr, int *offset,
+		      size_t *remaining, int atomic)
 {
 	unsigned long copy;
 
-	while (len > 0) {
+	while (*remaining > 0) {
 		while (!iov->iov_len)
 			iov++;
-		copy = min_t(unsigned long, len, iov->iov_len);
+		copy = min_t(unsigned long, *remaining, iov->iov_len);
 
 		if (atomic) {
-			if (__copy_to_user_inatomic(iov->iov_base, from, copy))
+			if (__copy_to_user_inatomic(iov->iov_base,
+						    addr + *offset, copy))
 				return -EFAULT;
 		} else {
-			if (copy_to_user(iov->iov_base, from, copy))
+			if (copy_to_user(iov->iov_base,
+					 addr + *offset, copy))
 				return -EFAULT;
 		}
-		from += copy;
-		len -= copy;
+		*offset += copy;
+		*remaining -= copy;
 		iov->iov_base += copy;
 		iov->iov_len -= copy;
 	}
@@ -395,7 +399,7 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 			struct pipe_buffer *buf = pipe->bufs + curbuf;
 			const struct pipe_buf_operations *ops = buf->ops;
 			void *addr;
-			size_t chars = buf->len;
+			size_t chars = buf->len, remaining;
 			int error, atomic;
 
 			if (chars > total_len)
@@ -409,9 +413,11 @@ pipe_read(struct kiocb *iocb, const struct iovec *_iov,
 			}
 
 			atomic = !iov_fault_in_pages_write(iov, chars);
+			remaining = chars;
 redo:
 			addr = ops->map(pipe, buf, atomic);
-			error = pipe_iov_copy_to_user(iov, addr + buf->offset, chars, atomic);
+			error = pipe_iov_copy_to_user(iov, addr, &buf->offset,
+						      &remaining, atomic);
 			ops->unmap(pipe, buf, addr);
 			if (unlikely(error)) {
 				/*
@@ -426,7 +432,6 @@ redo:
 				break;
 			}
 			ret += chars;
-			buf->offset += chars;
 			buf->len -= chars;
 
 			/* Was it a packet buffer? Clean up and exit */
@@ -531,6 +536,7 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
 		if (ops->can_merge && offset + chars <= PAGE_SIZE) {
 			int error, atomic = 1;
 			void *addr;
+			size_t remaining = chars;
 
 			error = ops->confirm(pipe, buf);
 			if (error)
@@ -539,8 +545,8 @@ pipe_write(struct kiocb *iocb, const struct iovec *_iov,
 			iov_fault_in_pages_read(iov, chars);
 redo1:
 			addr = ops->map(pipe, buf, atomic);
-			error = pipe_iov_copy_from_user(offset + addr, iov,
-							chars, atomic);
+			error = pipe_iov_copy_from_user(addr, &offset, iov,
+							&remaining, atomic);
 			ops->unmap(pipe, buf, addr);
 			ret = error;
 			do_wakeup = 1;
@@ -575,6 +581,8 @@ redo1:
 			struct page *page = pipe->tmp_page;
 			char *src;
 			int error, atomic = 1;
+			int offset = 0;
+			size_t remaining;
 
 			if (!page) {
 				page = alloc_page(GFP_HIGHUSER);
@@ -595,14 +603,15 @@ redo1:
 				chars = total_len;
 
 			iov_fault_in_pages_read(iov, chars);
+			remaining = chars;
 redo2:
 			if (atomic)
 				src = kmap_atomic(page);
 			else
 				src = kmap(page);
 
-			error = pipe_iov_copy_from_user(src, iov, chars,
-							atomic);
+			error = pipe_iov_copy_from_user(src, &offset, iov,
+							&remaining, atomic);
 			if (atomic)
 				kunmap_atomic(src);
 			else
diff --git a/fs/super.c b/fs/super.c
index e028b508db25..97280e76179c 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -163,19 +163,6 @@ static struct super_block *alloc_super(struct file_system_type *type, int flags)
 			s = NULL;
 			goto out;
 		}
-#ifdef CONFIG_SMP
-		s->s_files = alloc_percpu(struct list_head);
-		if (!s->s_files)
-			goto err_out;
-		else {
-			int i;
-
-			for_each_possible_cpu(i)
-				INIT_LIST_HEAD(per_cpu_ptr(s->s_files, i));
-		}
-#else
-		INIT_LIST_HEAD(&s->s_files);
-#endif
 		if (init_sb_writers(s, type))
 			goto err_out;
 		s->s_flags = flags;
@@ -225,10 +212,6 @@ out:
 	return s;
 err_out:
 	security_sb_free(s);
-#ifdef CONFIG_SMP
-	if (s->s_files)
-		free_percpu(s->s_files);
-#endif
 	destroy_sb_writers(s);
 	kfree(s);
 	s = NULL;
@@ -243,9 +226,6 @@ err_out:
  */
 static inline void destroy_super(struct super_block *s)
 {
-#ifdef CONFIG_SMP
-	free_percpu(s->s_files);
-#endif
 	destroy_sb_writers(s);
 	security_sb_free(s);
 	WARN_ON(!list_empty(&s->s_mounts));
@@ -727,7 +707,8 @@ int do_remount_sb(struct super_block *sb, int flags, void *data, int force)
 	   make sure there are no rw files opened */
 	if (remount_ro) {
 		if (force) {
-			mark_files_ro(sb);
+			sb->s_readonly_remount = 1;
+			smp_wmb();
 		} else {
 			retval = sb_prepare_remount_readonly(sb);
 			if (retval)
diff --git a/include/linux/fs.h b/include/linux/fs.h
index d57bc5df7225..5c9dc8471da5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -10,6 +10,7 @@
 #include <linux/stat.h>
 #include <linux/cache.h>
 #include <linux/list.h>
+#include <linux/llist.h>
 #include <linux/radix-tree.h>
 #include <linux/rbtree.h>
 #include <linux/init.h>
@@ -761,12 +762,8 @@ static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
 #define FILE_MNT_WRITE_RELEASED	2
 
 struct file {
-	/*
-	 * fu_list becomes invalid after file_free is called and queued via
-	 * fu_rcuhead for RCU freeing
-	 */
 	union {
-		struct list_head	fu_list;
+		struct llist_node	fu_llist;
 		struct rcu_head 	fu_rcuhead;
 	} f_u;
 	struct path		f_path;
@@ -779,9 +776,6 @@ struct file {
 	 * Must not be taken from IRQ context.
 	 */
 	spinlock_t		f_lock;
-#ifdef CONFIG_SMP
-	int			f_sb_list_cpu;
-#endif
 	atomic_long_t		f_count;
 	unsigned int 		f_flags;
 	fmode_t			f_mode;
@@ -1257,11 +1251,6 @@ struct super_block {
 
 	struct list_head	s_inodes;	/* all inodes */
 	struct hlist_bl_head	s_anon;		/* anonymous dentries for (nfs) exporting */
-#ifdef CONFIG_SMP
-	struct list_head __percpu *s_files;
-#else
-	struct list_head	s_files;
-#endif
 	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
 	/* s_dentry_lru, s_nr_dentry_unused protected by dcache.c lru locks */
 	struct list_head	s_dentry_lru;	/* unused dentry lru */
diff --git a/include/linux/mbus.h b/include/linux/mbus.h
index dba482e31a13..e80b9c7ec8da 100644
--- a/include/linux/mbus.h
+++ b/include/linux/mbus.h
@@ -67,6 +67,6 @@ int mvebu_mbus_add_window(const char *devname, phys_addr_t base,
 int mvebu_mbus_del_window(phys_addr_t base, size_t size);
 int mvebu_mbus_init(const char *soc, phys_addr_t mbus_phys_base,
 		    size_t mbus_size, phys_addr_t sdram_phys_base,
-		    size_t sdram_size);
+		    size_t sdram_size, int is_coherent);
 
 #endif /* __LINUX_MBUS_H */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6ca9630fde2d..55225af46134 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2224,15 +2224,15 @@ static inline bool thread_group_leader(struct task_struct *p)
  * all we care about is that we have a task with the appropriate
  * pid, we don't actually care if we have the right task.
  */
-static inline int has_group_leader_pid(struct task_struct *p)
+static inline bool has_group_leader_pid(struct task_struct *p)
 {
-	return p->pid == p->tgid;
+	return task_pid(p) == p->signal->leader_pid;
 }
 
 static inline
-int same_thread_group(struct task_struct *p1, struct task_struct *p2)
+bool same_thread_group(struct task_struct *p1, struct task_struct *p2)
 {
-	return p1->tgid == p2->tgid;
+	return p1->signal == p2->signal;
 }
 
 static inline struct task_struct *next_thread(const struct task_struct *p)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 665e0cee59bd..5e661a979694 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -301,7 +301,7 @@ extern void			inet6_rt_notify(int event, struct rt6_info *rt,
 						struct nl_info *info);
 
 extern void			fib6_run_gc(unsigned long expires,
-					    struct net *net);
+					    struct net *net, bool force);
 
 extern void			fib6_gc_cleanup(void);
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 118323bc8529..30ab20623bca 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -236,7 +236,7 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
 	 */
 	int dumpable = 0;
 	/* Don't let security modules deny introspection */
-	if (task == current)
+	if (same_thread_group(task, current))
 		return 0;
 	rcu_read_lock();
 	tcred = __task_cred(task);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 0a1edc694d67..fe3e086d38e9 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -1328,19 +1328,24 @@ static int check_preds(struct filter_parse_state *ps)
 {
 	int n_normal_preds = 0, n_logical_preds = 0;
 	struct postfix_elt *elt;
+	int cnt = 0;
 
 	list_for_each_entry(elt, &ps->postfix, list) {
-		if (elt->op == OP_NONE)
+		if (elt->op == OP_NONE) {
+			cnt++;
 			continue;
+		}
 
+		cnt--;
 		if (elt->op == OP_AND || elt->op == OP_OR) {
 			n_logical_preds++;
 			continue;
 		}
 		n_normal_preds++;
+		WARN_ON_ONCE(cnt < 0);
 	}
 
-	if (!n_normal_preds || n_logical_preds >= n_normal_preds) {
+	if (cnt != 1 || !n_normal_preds || n_logical_preds >= n_normal_preds) {
 		parse_error(ps, FILT_ERR_INVALID_FILTER, 0);
 		return -EINVAL;
 	}
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 9a459be24af7..9b5b5ddf8cd4 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -235,7 +235,7 @@ static struct dst_ops xfrm4_dst_ops = {
 	.destroy =		xfrm4_dst_destroy,
 	.ifdown =		xfrm4_dst_ifdown,
 	.local_out =		__ip_local_out,
-	.gc_thresh =		1024,
+	.gc_thresh =		32768,
 };
 
 static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index ceeb9458bb60..46458ee31939 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -1648,27 +1648,28 @@ static int fib6_age(struct rt6_info *rt, void *arg)
 
 static DEFINE_SPINLOCK(fib6_gc_lock);
 
-void fib6_run_gc(unsigned long expires, struct net *net)
+void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 {
-	if (expires != ~0UL) {
+	unsigned long now;
+
+	if (force) {
 		spin_lock_bh(&fib6_gc_lock);
-		gc_args.timeout = expires ? (int)expires :
-			net->ipv6.sysctl.ip6_rt_gc_interval;
-	} else {
-		if (!spin_trylock_bh(&fib6_gc_lock)) {
-			mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ);
-			return;
-		}
-		gc_args.timeout = net->ipv6.sysctl.ip6_rt_gc_interval;
+	} else if (!spin_trylock_bh(&fib6_gc_lock)) {
+		mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ);
+		return;
 	}
+	gc_args.timeout = expires ? (int)expires :
+			  net->ipv6.sysctl.ip6_rt_gc_interval;
 
 	gc_args.more = icmp6_dst_gc();
 
 	fib6_clean_all(net, fib6_age, 0, NULL);
+	now = jiffies;
+	net->ipv6.ip6_rt_last_gc = now;
 
 	if (gc_args.more)
 		mod_timer(&net->ipv6.ip6_fib_timer,
-			  round_jiffies(jiffies
+			  round_jiffies(now
 					+ net->ipv6.sysctl.ip6_rt_gc_interval));
 	else
 		del_timer(&net->ipv6.ip6_fib_timer);
@@ -1677,7 +1678,7 @@ void fib6_run_gc(unsigned long expires, struct net *net)
 
 static void fib6_gc_timer_cb(unsigned long arg)
 {
-	fib6_run_gc(0, (struct net *)arg);
+	fib6_run_gc(0, (struct net *)arg, true);
 }
 
 static int __net_init fib6_net_init(struct net *net)
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 05f361338c2e..deedf7ddbc6e 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1584,7 +1584,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 	switch (event) {
 	case NETDEV_CHANGEADDR:
 		neigh_changeaddr(&nd_tbl, dev);
-		fib6_run_gc(~0UL, net);
+		fib6_run_gc(0, net, false);
 		idev = in6_dev_get(dev);
 		if (!idev)
 			break;
@@ -1594,7 +1594,7 @@ static int ndisc_netdev_event(struct notifier_block *this, unsigned long event,
 		break;
 	case NETDEV_DOWN:
 		neigh_ifdown(&nd_tbl, dev);
-		fib6_run_gc(~0UL, net);
+		fib6_run_gc(0, net, false);
 		break;
 	case NETDEV_NOTIFY_PEERS:
 		ndisc_send_unsol_na(dev);
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index d94d224f7e68..6ebefd46f718 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1334,7 +1334,6 @@ static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg),
 
 static int ip6_dst_gc(struct dst_ops *ops)
 {
-	unsigned long now = jiffies;
 	struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops);
 	int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval;
 	int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size;
@@ -1344,13 +1343,12 @@ static int ip6_dst_gc(struct dst_ops *ops)
 	int entries;
 
 	entries = dst_entries_get_fast(ops);
-	if (time_after(rt_last_gc + rt_min_interval, now) &&
+	if (time_after(rt_last_gc + rt_min_interval, jiffies) &&
 	    entries <= rt_max_size)
 		goto out;
 
 	net->ipv6.ip6_rt_gc_expire++;
-	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net);
-	net->ipv6.ip6_rt_last_gc = now;
+	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net, entries > rt_max_size);
 	entries = dst_entries_get_slow(ops);
 	if (entries < ops->gc_thresh)
 		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
@@ -2849,7 +2847,7 @@ int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
 	net = (struct net *)ctl->extra1;
 	delay = net->ipv6.sysctl.flush_delay;
 	proc_dointvec(ctl, write, buffer, lenp, ppos);
-	fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
+	fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0);
 	return 0;
 }
 
diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c
index 23ed03d786c8..1c2e0c9ba8a1 100644
--- a/net/ipv6/xfrm6_policy.c
+++ b/net/ipv6/xfrm6_policy.c
@@ -284,7 +284,7 @@ static struct dst_ops xfrm6_dst_ops = {
 	.destroy =		xfrm6_dst_destroy,
 	.ifdown =		xfrm6_dst_ifdown,
 	.local_out =		__ip6_local_out,
-	.gc_thresh =		1024,
+	.gc_thresh =		32768,
 };
 
 static struct xfrm_policy_afinfo xfrm6_policy_afinfo = {
diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c
index a191b6db657e..3b283edec027 100644
--- a/net/netfilter/nfnetlink_cthelper.c
+++ b/net/netfilter/nfnetlink_cthelper.c
@@ -74,6 +74,9 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 	if (!tb[NFCTH_TUPLE_L3PROTONUM] || !tb[NFCTH_TUPLE_L4PROTONUM])
 		return -EINVAL;
 
+	/* Not all fields are initialized so first zero the tuple */
+	memset(tuple, 0, sizeof(struct nf_conntrack_tuple));
+
 	tuple->src.l3num = ntohs(nla_get_be16(tb[NFCTH_TUPLE_L3PROTONUM]));
 	tuple->dst.protonum = nla_get_u8(tb[NFCTH_TUPLE_L4PROTONUM]);
 
@@ -83,7 +86,7 @@ nfnl_cthelper_parse_tuple(struct nf_conntrack_tuple *tuple,
 static int
 nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 {
-	const struct nf_conn_help *help = nfct_help(ct);
+	struct nf_conn_help *help = nfct_help(ct);
 
 	if (attr == NULL)
 		return -EINVAL;
@@ -91,7 +94,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct)
 	if (help->helper->data_len == 0)
 		return -EINVAL;
 
-	memcpy(&help->data, nla_data(attr), help->helper->data_len);
+	memcpy(help->data, nla_data(attr), help->helper->data_len);
 	return 0;
 }