Merge commit 'fc69910f329d' into uaccess.mips

backmerge of a build fix from mainline
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 986e443..9adcc80 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1183,6 +1183,12 @@
 			functions that can be changed at run time by the
 			set_graph_notrace file in the debugfs tracing directory.
 
+	ftrace_graph_max_depth=<uint>
+			[FTRACE] Used with the function graph tracer. This is
+			the max depth it will trace into a function. This value
+			can be changed at run time by the max_graph_depth file
+			in the tracefs tracing directory. default: 0 (no limit)
+
 	gamecon.map[2|3]=
 			[HW,JOY] Multisystem joystick and NES/SNES/PSX pad
 			support via parallel port (up to 5 devices per port)
diff --git a/Documentation/trace/kprobetrace.txt b/Documentation/trace/kprobetrace.txt
index e4991fb..41ef9d8 100644
--- a/Documentation/trace/kprobetrace.txt
+++ b/Documentation/trace/kprobetrace.txt
@@ -12,7 +12,7 @@
 functions). Unlike the Tracepoint based event, this can be added and removed
 dynamically, on the fly.
 
-To enable this feature, build your kernel with CONFIG_KPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_KPROBE_EVENTS=y.
 
 Similar to the events tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/Documentation/trace/uprobetracer.txt b/Documentation/trace/uprobetracer.txt
index fa7b680..bf526a7c 100644
--- a/Documentation/trace/uprobetracer.txt
+++ b/Documentation/trace/uprobetracer.txt
@@ -7,7 +7,7 @@
 Overview
 --------
 Uprobe based trace events are similar to kprobe based trace events.
-To enable this feature, build your kernel with CONFIG_UPROBE_EVENT=y.
+To enable this feature, build your kernel with CONFIG_UPROBE_EVENTS=y.
 
 Similar to the kprobe-event tracer, this doesn't need to be activated via
 current_tracer. Instead of that, add probe points via
diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c
index ce18c91..f0325d9 100644
--- a/arch/arm/xen/mm.c
+++ b/arch/arm/xen/mm.c
@@ -198,6 +198,8 @@ static const struct dma_map_ops xen_swiotlb_dma_ops = {
 	.unmap_page = xen_swiotlb_unmap_page,
 	.dma_supported = xen_swiotlb_dma_supported,
 	.set_dma_mask = xen_swiotlb_set_dma_mask,
+	.mmap = xen_swiotlb_dma_mmap,
+	.get_sgtable = xen_swiotlb_get_sgtable,
 };
 
 int __init xen_mm_init(void)
diff --git a/arch/avr32/oprofile/backtrace.c b/arch/avr32/oprofile/backtrace.c
index 75d9ad6..29cf2f1 100644
--- a/arch/avr32/oprofile/backtrace.c
+++ b/arch/avr32/oprofile/backtrace.c
@@ -14,7 +14,7 @@
  */
 
 #include <linux/oprofile.h>
-#include <linux/sched.h>
+#include <linux/ptrace.h>
 #include <linux/uaccess.h>
 
 /* The first two words of each frame on the stack look like this if we have
diff --git a/arch/h8300/kernel/ptrace_h.c b/arch/h8300/kernel/ptrace_h.c
index fe3b567..f5ff3b7 100644
--- a/arch/h8300/kernel/ptrace_h.c
+++ b/arch/h8300/kernel/ptrace_h.c
@@ -9,7 +9,7 @@
  */
 
 #include <linux/linkage.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <asm/ptrace.h>
 
 #define BREAKINST 0x5730 /* trapa #3 */
diff --git a/arch/mips/cavium-octeon/cpu.c b/arch/mips/cavium-octeon/cpu.c
index a5b4279..036d56c 100644
--- a/arch/mips/cavium-octeon/cpu.c
+++ b/arch/mips/cavium-octeon/cpu.c
@@ -10,7 +10,9 @@
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>
diff --git a/arch/mips/cavium-octeon/crypto/octeon-crypto.c b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
index 4d22365..cfb4a14 100644
--- a/arch/mips/cavium-octeon/crypto/octeon-crypto.c
+++ b/arch/mips/cavium-octeon/crypto/octeon-crypto.c
@@ -9,6 +9,7 @@
 #include <asm/cop2.h>
 #include <linux/export.h>
 #include <linux/interrupt.h>
+#include <linux/sched/task_stack.h>
 
 #include "octeon-crypto.h"
 
diff --git a/arch/mips/cavium-octeon/smp.c b/arch/mips/cavium-octeon/smp.c
index 4b94b7f..3de7865 100644
--- a/arch/mips/cavium-octeon/smp.c
+++ b/arch/mips/cavium-octeon/smp.c
@@ -12,6 +12,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/init.h>
 #include <linux/export.h>
 
diff --git a/arch/mips/include/asm/fpu.h b/arch/mips/include/asm/fpu.h
index 321752b..f94455f 100644
--- a/arch/mips/include/asm/fpu.h
+++ b/arch/mips/include/asm/fpu.h
@@ -12,6 +12,7 @@
 
 #include <linux/sched.h>
 #include <linux/sched/task_stack.h>
+#include <linux/ptrace.h>
 #include <linux/thread_info.h>
 #include <linux/bitops.h>
 
diff --git a/arch/mips/kernel/smp-bmips.c b/arch/mips/kernel/smp-bmips.c
index 3daa2ca..1b070a7 100644
--- a/arch/mips/kernel/smp-bmips.c
+++ b/arch/mips/kernel/smp-bmips.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/sched/hotplug.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/smp.h>
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index e077ea3..e398cbc 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -23,6 +23,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/mips-gic.h>
 #include <linux/compiler.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 
 #include <linux/atomic.h>
diff --git a/arch/mips/loongson64/loongson-3/cop2-ex.c b/arch/mips/loongson64/loongson-3/cop2-ex.c
index ea13764..621d6af 100644
--- a/arch/mips/loongson64/loongson-3/cop2-ex.c
+++ b/arch/mips/loongson64/loongson-3/cop2-ex.c
@@ -13,6 +13,7 @@
 #include <linux/init.h>
 #include <linux/sched.h>
 #include <linux/notifier.h>
+#include <linux/ptrace.h>
 
 #include <asm/fpu.h>
 #include <asm/cop2.h>
diff --git a/arch/mips/netlogic/common/smp.c b/arch/mips/netlogic/common/smp.c
index 10d86d5..bddf1ef 100644
--- a/arch/mips/netlogic/common/smp.c
+++ b/arch/mips/netlogic/common/smp.c
@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/sched/task_stack.h>
 #include <linux/smp.h>
 #include <linux/irq.h>
 
diff --git a/arch/mips/netlogic/xlp/cop2-ex.c b/arch/mips/netlogic/xlp/cop2-ex.c
index 52bc5de..21e439b 100644
--- a/arch/mips/netlogic/xlp/cop2-ex.c
+++ b/arch/mips/netlogic/xlp/cop2-ex.c
@@ -9,11 +9,14 @@
  * Copyright (C) 2009 Wind River Systems,
  *   written by Ralf Baechle <ralf@linux-mips.org>
  */
+#include <linux/capability.h>
 #include <linux/init.h>
 #include <linux/irqflags.h>
 #include <linux/notifier.h>
 #include <linux/prefetch.h>
+#include <linux/ptrace.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 
 #include <asm/cop2.h>
 #include <asm/current.h>
diff --git a/arch/mips/sgi-ip22/ip28-berr.c b/arch/mips/sgi-ip22/ip28-berr.c
index 1f2a5bc..75460e1 100644
--- a/arch/mips/sgi-ip22/ip28-berr.c
+++ b/arch/mips/sgi-ip22/ip28-berr.c
@@ -9,6 +9,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <linux/seq_file.h>
 
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip27/ip27-berr.c b/arch/mips/sgi-ip27/ip27-berr.c
index d12879e..83efe03 100644
--- a/arch/mips/sgi-ip27/ip27-berr.c
+++ b/arch/mips/sgi-ip27/ip27-berr.c
@@ -12,7 +12,9 @@
 #include <linux/signal.h>	/* for SIGBUS */
 #include <linux/sched.h>	/* schow_regs(), force_sig() */
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 
+#include <asm/ptrace.h>
 #include <asm/sn/addrs.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/sn0/hub.h>
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index f5ed45e..4cd47d2 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -8,10 +8,13 @@
  */
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/topology.h>
 #include <linux/nodemask.h>
+
 #include <asm/page.h>
 #include <asm/processor.h>
+#include <asm/ptrace.h>
 #include <asm/sn/arch.h>
 #include <asm/sn/gda.h>
 #include <asm/sn/intr.h>
diff --git a/arch/mips/sgi-ip32/ip32-berr.c b/arch/mips/sgi-ip32/ip32-berr.c
index 57d8c74..c1f12a9 100644
--- a/arch/mips/sgi-ip32/ip32-berr.c
+++ b/arch/mips/sgi-ip32/ip32-berr.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/signal.h>
 #include <asm/traps.h>
 #include <linux/uaccess.h>
 #include <asm/addrspace.h>
diff --git a/arch/mips/sgi-ip32/ip32-reset.c b/arch/mips/sgi-ip32/ip32-reset.c
index 8bd415c..b3b442d 100644
--- a/arch/mips/sgi-ip32/ip32-reset.c
+++ b/arch/mips/sgi-ip32/ip32-reset.c
@@ -13,6 +13,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/notifier.h>
 #include <linux/delay.h>
 #include <linux/rtc/ds1685.h>
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 4940917..97a8bc8 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -80,93 +80,99 @@
 config PPC
 	bool
 	default y
-	select BUILDTIME_EXTABLE_SORT
+	#
+	# Please keep this list sorted alphabetically.
+	#
+	select ARCH_HAS_DEVMEM_IS_ALLOWED
+	select ARCH_HAS_DMA_SET_COHERENT_MASK
+	select ARCH_HAS_ELF_RANDOMIZE
+	select ARCH_HAS_GCOV_PROFILE_ALL
+	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE
+	select ARCH_HAS_SG_CHAIN
+	select ARCH_HAS_TICK_BROADCAST		if GENERIC_CLOCKEVENTS_BROADCAST
+	select ARCH_HAS_UBSAN_SANITIZE_ALL
+	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_SUPPORTS_ATOMIC_RMW
+	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
+	select ARCH_USE_BUILTIN_BSWAP
+	select ARCH_USE_CMPXCHG_LOCKREF		if PPC64
+	select ARCH_WANT_IPC_PARSE_VERSION
 	select BINFMT_ELF
-	select ARCH_HAS_ELF_RANDOMIZE
+	select BUILDTIME_EXTABLE_SORT
+	select CLONE_BACKWARDS
+	select DCACHE_WORD_ACCESS		if PPC64 && CPU_LITTLE_ENDIAN
+	select EDAC_ATOMIC_SCRUB
+	select EDAC_SUPPORT
+	select GENERIC_ATOMIC64			if PPC32
+	select GENERIC_CLOCKEVENTS
+	select GENERIC_CLOCKEVENTS_BROADCAST	if SMP
+	select GENERIC_CMOS_UPDATE
+	select GENERIC_CPU_AUTOPROBE
+	select GENERIC_IRQ_SHOW
+	select GENERIC_IRQ_SHOW_LEVEL
+	select GENERIC_SMP_IDLE_THREAD
+	select GENERIC_STRNCPY_FROM_USER
+	select GENERIC_STRNLEN_USER
+	select GENERIC_TIME_VSYSCALL_OLD
+	select HAVE_ARCH_AUDITSYSCALL
+	select HAVE_ARCH_HARDENED_USERCOPY
+	select HAVE_ARCH_JUMP_LABEL
+	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_SECCOMP_FILTER
+	select HAVE_ARCH_TRACEHOOK
+	select HAVE_CBPF_JIT			if !PPC64
+	select HAVE_CONTEXT_TRACKING		if PPC64
+	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_DEBUG_STACKOVERFLOW
+	select HAVE_DMA_API_DEBUG
+	select HAVE_DYNAMIC_FTRACE
+	select HAVE_DYNAMIC_FTRACE_WITH_REGS	if MPROFILE_KERNEL
+	select HAVE_EBPF_JIT			if PPC64
+	select HAVE_EFFICIENT_UNALIGNED_ACCESS	if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
+	select HAVE_FTRACE_MCOUNT_RECORD
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER
+	select HAVE_GCC_PLUGINS
+	select HAVE_GENERIC_RCU_GUP
+	select HAVE_HW_BREAKPOINT		if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
+	select HAVE_IDE
+	select HAVE_IOREMAP_PROT
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK
+	select HAVE_KERNEL_GZIP
+	select HAVE_KPROBES
+	select HAVE_KRETPROBES
+	select HAVE_LIVEPATCH			if HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_MEMBLOCK
+	select HAVE_MEMBLOCK_NODE_MAP
+	select HAVE_MOD_ARCH_SPECIFIC
+	select HAVE_NMI				if PERF_EVENTS
+	select HAVE_OPROFILE
+	select HAVE_OPTPROBES			if PPC64
+	select HAVE_PERF_EVENTS
+	select HAVE_PERF_EVENTS_NMI		if PPC64
+	select HAVE_PERF_REGS
+	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_RCU_TABLE_FREE		if SMP
+	select HAVE_REGS_AND_STACK_ACCESS_API
+	select HAVE_SYSCALL_TRACEPOINTS
+	select HAVE_VIRT_CPU_ACCOUNTING
+	select IRQ_DOMAIN
+	select IRQ_FORCED_THREADING
+	select MODULES_USE_ELF_RELA
+	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
 	select OF_RESERVED_MEM
-	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_DYNAMIC_FTRACE
-	select HAVE_DYNAMIC_FTRACE_WITH_REGS if MPROFILE_KERNEL
-	select HAVE_FUNCTION_TRACER
-	select HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_GCC_PLUGINS
-	select SYSCTL_EXCEPTION_TRACE
-	select VIRT_TO_BUS if !PPC64
-	select HAVE_IDE
-	select HAVE_IOREMAP_PROT
-	select HAVE_EFFICIENT_UNALIGNED_ACCESS if !(CPU_LITTLE_ENDIAN && POWER7_CPU)
-	select HAVE_KPROBES
-	select HAVE_OPTPROBES if PPC64
-	select HAVE_ARCH_KGDB
-	select HAVE_KRETPROBES
-	select HAVE_ARCH_TRACEHOOK
-	select HAVE_MEMBLOCK
-	select HAVE_MEMBLOCK_NODE_MAP
-	select HAVE_DMA_API_DEBUG
-	select HAVE_OPROFILE
-	select HAVE_DEBUG_KMEMLEAK
-	select ARCH_HAS_SG_CHAIN
-	select GENERIC_ATOMIC64 if PPC32
-	select HAVE_PERF_EVENTS
-	select HAVE_PERF_REGS
-	select HAVE_PERF_USER_STACK_DUMP
-	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (PPC_BOOK3S || PPC_8xx)
-	select ARCH_WANT_IPC_PARSE_VERSION
-	select SPARSE_IRQ
-	select IRQ_DOMAIN
-	select GENERIC_IRQ_SHOW
-	select GENERIC_IRQ_SHOW_LEVEL
-	select IRQ_FORCED_THREADING
-	select HAVE_RCU_TABLE_FREE if SMP
-	select HAVE_SYSCALL_TRACEPOINTS
-	select HAVE_CBPF_JIT if !PPC64
-	select HAVE_EBPF_JIT if PPC64
-	select HAVE_ARCH_JUMP_LABEL
-	select ARCH_HAVE_NMI_SAFE_CMPXCHG
-	select ARCH_HAS_GCOV_PROFILE_ALL
-	select GENERIC_SMP_IDLE_THREAD
-	select GENERIC_CMOS_UPDATE
-	select GENERIC_TIME_VSYSCALL_OLD
-	select GENERIC_CLOCKEVENTS
-	select GENERIC_CLOCKEVENTS_BROADCAST if SMP
-	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
-	select GENERIC_STRNCPY_FROM_USER
-	select GENERIC_STRNLEN_USER
-	select HAVE_MOD_ARCH_SPECIFIC
-	select MODULES_USE_ELF_RELA
-	select CLONE_BACKWARDS
-	select ARCH_USE_BUILTIN_BSWAP
+	select OLD_SIGACTION			if PPC32
 	select OLD_SIGSUSPEND
-	select OLD_SIGACTION if PPC32
-	select HAVE_DEBUG_STACKOVERFLOW
-	select HAVE_IRQ_EXIT_ON_IRQ_STACK
-	select ARCH_USE_CMPXCHG_LOCKREF if PPC64
-	select HAVE_ARCH_AUDITSYSCALL
-	select ARCH_SUPPORTS_ATOMIC_RMW
-	select DCACHE_WORD_ACCESS if PPC64 && CPU_LITTLE_ENDIAN
-	select NO_BOOTMEM
-	select HAVE_GENERIC_RCU_GUP
-	select HAVE_PERF_EVENTS_NMI if PPC64
-	select HAVE_NMI if PERF_EVENTS
-	select EDAC_SUPPORT
-	select EDAC_ATOMIC_SCRUB
-	select ARCH_HAS_DMA_SET_COHERENT_MASK
-	select ARCH_HAS_DEVMEM_IS_ALLOWED
-	select HAVE_ARCH_SECCOMP_FILTER
-	select ARCH_HAS_UBSAN_SANITIZE_ALL
-	select ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT
-	select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS
-	select GENERIC_CPU_AUTOPROBE
-	select HAVE_VIRT_CPU_ACCOUNTING
-	select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
-	select HAVE_ARCH_HARDENED_USERCOPY
-	select HAVE_KERNEL_GZIP
-	select HAVE_CONTEXT_TRACKING if PPC64
+	select SPARSE_IRQ
+	select SYSCTL_EXCEPTION_TRACE
+	select VIRT_TO_BUS			if !PPC64
+	#
+	# Please keep this list sorted alphabetically.
+	#
 
 config GENERIC_CSUM
 	def_bool n
diff --git a/arch/powerpc/Makefile b/arch/powerpc/Makefile
index 31286fa..19b0d1a 100644
--- a/arch/powerpc/Makefile
+++ b/arch/powerpc/Makefile
@@ -72,8 +72,15 @@
 MULTIPLEWORD	:= -mmultiple
 endif
 
-cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
+ifdef CONFIG_PPC64
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mcall-aixdesc)
+aflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mabi=elfv1)
+aflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mabi=elfv2
+endif
+
 cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mlittle-endian
+cflags-$(CONFIG_CPU_BIG_ENDIAN)		+= $(call cc-option,-mbig-endian)
 ifneq ($(cc-name),clang)
   cflags-$(CONFIG_CPU_LITTLE_ENDIAN)	+= -mno-strict-align
 endif
@@ -113,7 +120,9 @@
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2,$(call cc-option,-mcall-aixdesc))
 AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv2)
 else
+CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcall-aixdesc)
+AFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mabi=elfv1)
 endif
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mcmodel=medium,$(call cc-option,-mminimal-toc))
 CFLAGS-$(CONFIG_PPC64)	+= $(call cc-option,-mno-pointers-to-nested-functions)
diff --git a/arch/powerpc/include/asm/checksum.h b/arch/powerpc/include/asm/checksum.h
index 4e63787..842124b 100644
--- a/arch/powerpc/include/asm/checksum.h
+++ b/arch/powerpc/include/asm/checksum.h
@@ -112,7 +112,7 @@ static inline __wsum csum_add(__wsum csum, __wsum addend)
 
 #ifdef __powerpc64__
 	res += (__force u64)addend;
-	return (__force __wsum)((u32)res + (res >> 32));
+	return (__force __wsum) from64to32(res);
 #else
 	asm("addc %0,%0,%1;"
 	    "addze %0,%0;"
diff --git a/arch/powerpc/include/asm/cpuidle.h b/arch/powerpc/include/asm/cpuidle.h
index fd321eb4..1557315 100644
--- a/arch/powerpc/include/asm/cpuidle.h
+++ b/arch/powerpc/include/asm/cpuidle.h
@@ -70,8 +70,8 @@ static inline void report_invalid_psscr_val(u64 psscr_val, int err)
 	std	r0,0(r1);					\
 	ptesync;						\
 	ld	r0,0(r1);					\
-1:	cmpd	cr0,r0,r0;					\
-	bne	1b;						\
+236:	cmpd	cr0,r0,r0;					\
+	bne	236b;						\
 	IDLE_INST;						\
 
 #define	IDLE_STATE_ENTER_SEQ_NORET(IDLE_INST)			\
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index 93b9b84..09bde6e 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -144,8 +144,8 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 #define ARCH_DLINFO_CACHE_GEOMETRY					\
 	NEW_AUX_ENT(AT_L1I_CACHESIZE, ppc64_caches.l1i.size);		\
 	NEW_AUX_ENT(AT_L1I_CACHEGEOMETRY, get_cache_geometry(l1i));	\
-	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1i.size);		\
-	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1i));	\
+	NEW_AUX_ENT(AT_L1D_CACHESIZE, ppc64_caches.l1d.size);		\
+	NEW_AUX_ENT(AT_L1D_CACHEGEOMETRY, get_cache_geometry(l1d));	\
 	NEW_AUX_ENT(AT_L2_CACHESIZE, ppc64_caches.l2.size);		\
 	NEW_AUX_ENT(AT_L2_CACHEGEOMETRY, get_cache_geometry(l2));	\
 	NEW_AUX_ENT(AT_L3_CACHESIZE, ppc64_caches.l3.size);		\
diff --git a/arch/powerpc/include/asm/nohash/pgtable.h b/arch/powerpc/include/asm/nohash/pgtable.h
index 0cd8a38..e5805ad 100644
--- a/arch/powerpc/include/asm/nohash/pgtable.h
+++ b/arch/powerpc/include/asm/nohash/pgtable.h
@@ -230,7 +230,7 @@ static inline int hugepd_ok(hugepd_t hpd)
 	return ((hpd_val(hpd) & 0x4) != 0);
 #else
 	/* We clear the top bit to indicate hugepd */
-	return ((hpd_val(hpd) & PD_HUGE) ==  0);
+	return (hpd_val(hpd) && (hpd_val(hpd) & PD_HUGE) == 0);
 #endif
 }
 
diff --git a/arch/powerpc/include/asm/ppc-opcode.h b/arch/powerpc/include/asm/ppc-opcode.h
index d99bd44..e7d6d86 100644
--- a/arch/powerpc/include/asm/ppc-opcode.h
+++ b/arch/powerpc/include/asm/ppc-opcode.h
@@ -284,6 +284,13 @@
 #define PPC_INST_BRANCH_COND		0x40800000
 #define PPC_INST_LBZCIX			0x7c0006aa
 #define PPC_INST_STBCIX			0x7c0007aa
+#define PPC_INST_LWZX			0x7c00002e
+#define PPC_INST_LFSX			0x7c00042e
+#define PPC_INST_STFSX			0x7c00052e
+#define PPC_INST_LFDX			0x7c0004ae
+#define PPC_INST_STFDX			0x7c0005ae
+#define PPC_INST_LVX			0x7c0000ce
+#define PPC_INST_STVX			0x7c0001ce
 
 /* macros to insert fields into opcodes */
 #define ___PPC_RA(a)	(((a) & 0x1f) << 16)
diff --git a/arch/powerpc/include/asm/prom.h b/arch/powerpc/include/asm/prom.h
index 4a90634..35c00d7 100644
--- a/arch/powerpc/include/asm/prom.h
+++ b/arch/powerpc/include/asm/prom.h
@@ -160,12 +160,18 @@ struct of_drconf_cell {
 #define OV5_PFO_HW_ENCR		0x1120	/* PFO Encryption Accelerator */
 #define OV5_SUB_PROCESSORS	0x1501	/* 1,2,or 4 Sub-Processors supported */
 #define OV5_XIVE_EXPLOIT	0x1701	/* XIVE exploitation supported */
-#define OV5_MMU_RADIX_300	0x1880	/* ISA v3.00 radix MMU supported */
-#define OV5_MMU_HASH_300	0x1840	/* ISA v3.00 hash MMU supported */
-#define OV5_MMU_SEGM_RADIX	0x1820	/* radix mode (no segmentation) */
-#define OV5_MMU_PROC_TBL	0x1810	/* hcall selects SLB or proc table */
-#define OV5_MMU_SLB		0x1800	/* always use SLB */
-#define OV5_MMU_GTSE		0x1808	/* Guest translation shootdown */
+/* MMU Base Architecture */
+#define OV5_MMU_SUPPORT		0x18C0	/* MMU Mode Support Mask */
+#define OV5_MMU_HASH		0x1800	/* Hash MMU Only */
+#define OV5_MMU_RADIX		0x1840	/* Radix MMU Only */
+#define OV5_MMU_EITHER		0x1880	/* Hash or Radix Supported */
+#define OV5_MMU_DYNAMIC		0x18C0	/* Hash or Radix Can Switch Later */
+#define OV5_NMMU		0x1820	/* Nest MMU Available */
+/* Hash Table Extensions */
+#define OV5_HASH_SEG_TBL	0x1980	/* In Memory Segment Tables Available */
+#define OV5_HASH_GTSE		0x1940	/* Guest Translation Shoot Down Avail */
+/* Radix Table Extensions */
+#define OV5_RADIX_GTSE		0x1A40	/* Guest Translation Shoot Down Avail */
 
 /* Option Vector 6: IBM PAPR hints */
 #define OV6_LINUX		0x02	/* Linux is our OS */
diff --git a/arch/powerpc/kernel/idle_book3s.S b/arch/powerpc/kernel/idle_book3s.S
index 5f61cc0..9957287 100644
--- a/arch/powerpc/kernel/idle_book3s.S
+++ b/arch/powerpc/kernel/idle_book3s.S
@@ -276,19 +276,21 @@
  */
 	andis.   r4,r3,PSSCR_EC_ESL_MASK_SHIFTED
 	clrldi   r3,r3,60 /* r3 = Bits[60:63] = Requested Level (RL) */
-	bne	 1f
+	bne	 .Lhandle_esl_ec_set
 	IDLE_STATE_ENTER_SEQ(PPC_STOP)
 	li	r3,0  /* Since we didn't lose state, return 0 */
 	b 	pnv_wakeup_noloss
+
+.Lhandle_esl_ec_set:
 /*
  * Check if the requested state is a deep idle state.
  */
-1:	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
+	LOAD_REG_ADDRBASE(r5,pnv_first_deep_stop_state)
 	ld	r4,ADDROFF(pnv_first_deep_stop_state)(r5)
 	cmpd	r3,r4
-	bge	2f
+	bge	.Lhandle_deep_stop
 	IDLE_STATE_ENTER_SEQ_NORET(PPC_STOP)
-2:
+.Lhandle_deep_stop:
 /*
  * Entering deep idle state.
  * Clear thread bit in PACA_CORE_IDLE_STATE, save SPRs to
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a394454..1c1b44e 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -168,6 +168,14 @@ static unsigned long __initdata prom_tce_alloc_start;
 static unsigned long __initdata prom_tce_alloc_end;
 #endif
 
+static bool __initdata prom_radix_disable;
+
+struct platform_support {
+	bool hash_mmu;
+	bool radix_mmu;
+	bool radix_gtse;
+};
+
 /* Platforms codes are now obsolete in the kernel. Now only used within this
  * file and ultimately gone too. Feel free to change them if you need, they
  * are not shared with anything outside of this file anymore
@@ -626,6 +634,12 @@ static void __init early_cmdline_parse(void)
 		prom_memory_limit = ALIGN(prom_memory_limit, 0x1000000);
 #endif
 	}
+
+	opt = strstr(prom_cmd_line, "disable_radix");
+	if (opt) {
+		prom_debug("Radix disabled from cmdline\n");
+		prom_radix_disable = true;
+	}
 }
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
@@ -695,6 +709,8 @@ struct option_vector5 {
 	u8 byte22;
 	u8 intarch;
 	u8 mmu;
+	u8 hash_ext;
+	u8 radix_ext;
 } __packed;
 
 struct option_vector6 {
@@ -850,8 +866,9 @@ struct ibm_arch_vec __cacheline_aligned ibm_architecture_vec = {
 		.reserved3 = 0,
 		.subprocessors = 1,
 		.intarch = 0,
-		.mmu = OV5_FEAT(OV5_MMU_RADIX_300) | OV5_FEAT(OV5_MMU_HASH_300) |
-			OV5_FEAT(OV5_MMU_PROC_TBL) | OV5_FEAT(OV5_MMU_GTSE),
+		.mmu = 0,
+		.hash_ext = 0,
+		.radix_ext = 0,
 	},
 
 	/* option vector 6: IBM PAPR hints */
@@ -990,6 +1007,92 @@ static int __init prom_count_smt_threads(void)
 
 }
 
+static void __init prom_parse_mmu_model(u8 val,
+					struct platform_support *support)
+{
+	switch (val) {
+	case OV5_FEAT(OV5_MMU_DYNAMIC):
+	case OV5_FEAT(OV5_MMU_EITHER): /* Either Available */
+		prom_debug("MMU - either supported\n");
+		support->radix_mmu = !prom_radix_disable;
+		support->hash_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_RADIX): /* Only Radix */
+		prom_debug("MMU - radix only\n");
+		if (prom_radix_disable) {
+			/*
+			 * If we __have__ to do radix, we're better off ignoring
+			 * the command line rather than not booting.
+			 */
+			prom_printf("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		support->radix_mmu = true;
+		break;
+	case OV5_FEAT(OV5_MMU_HASH):
+		prom_debug("MMU - hash only\n");
+		support->hash_mmu = true;
+		break;
+	default:
+		prom_debug("Unknown mmu support option: 0x%x\n", val);
+		break;
+	}
+}
+
+static void __init prom_parse_platform_support(u8 index, u8 val,
+					       struct platform_support *support)
+{
+	switch (index) {
+	case OV5_INDX(OV5_MMU_SUPPORT): /* MMU Model */
+		prom_parse_mmu_model(val & OV5_FEAT(OV5_MMU_SUPPORT), support);
+		break;
+	case OV5_INDX(OV5_RADIX_GTSE): /* Radix Extensions */
+		if (val & OV5_FEAT(OV5_RADIX_GTSE)) {
+			prom_debug("Radix - GTSE supported\n");
+			support->radix_gtse = true;
+		}
+		break;
+	}
+}
+
+static void __init prom_check_platform_support(void)
+{
+	struct platform_support supported = {
+		.hash_mmu = false,
+		.radix_mmu = false,
+		.radix_gtse = false
+	};
+	int prop_len = prom_getproplen(prom.chosen,
+				       "ibm,arch-vec-5-platform-support");
+	if (prop_len > 1) {
+		int i;
+		u8 vec[prop_len];
+		prom_debug("Found ibm,arch-vec-5-platform-support, len: %d\n",
+			   prop_len);
+		prom_getprop(prom.chosen, "ibm,arch-vec-5-platform-support",
+			     &vec, sizeof(vec));
+		for (i = 0; i < prop_len; i += 2) {
+			prom_debug("%d: index = 0x%x val = 0x%x\n", i / 2
+								  , vec[i]
+								  , vec[i + 1]);
+			prom_parse_platform_support(vec[i], vec[i + 1],
+						    &supported);
+		}
+	}
+
+	if (supported.radix_mmu && supported.radix_gtse) {
+		/* Radix preferred - but we require GTSE for now */
+		prom_debug("Asking for radix with GTSE\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_RADIX);
+		ibm_architecture_vec.vec5.radix_ext = OV5_FEAT(OV5_RADIX_GTSE);
+	} else if (supported.hash_mmu) {
+		/* Default to hash mmu (if we can) */
+		prom_debug("Asking for hash\n");
+		ibm_architecture_vec.vec5.mmu = OV5_FEAT(OV5_MMU_HASH);
+	} else {
+		/* We're probably on a legacy hypervisor */
+		prom_debug("Assuming legacy hash support\n");
+	}
+}
 
 static void __init prom_send_capabilities(void)
 {
@@ -997,6 +1100,9 @@ static void __init prom_send_capabilities(void)
 	prom_arg_t ret;
 	u32 cores;
 
+	/* Check ibm,arch-vec-5-platform-support and fixup vec5 if required */
+	prom_check_platform_support();
+
 	root = call_prom("open", 1, 1, ADDR("/"));
 	if (root != 0) {
 		/* We need to tell the FW about the number of cores we support.
@@ -2993,6 +3099,11 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 */
 	prom_check_initrd(r3, r4);
 
+	/*
+	 * Do early parsing of command line
+	 */
+	early_cmdline_parse();
+
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 	/*
 	 * On pSeries, inform the firmware about our capabilities
@@ -3009,11 +3120,6 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 		copy_and_flush(0, kbase, 0x100, 0);
 
 	/*
-	 * Do early parsing of command line
-	 */
-	early_cmdline_parse();
-
-	/*
 	 * Initialize memory management within prom_init
 	 */
 	prom_init_mem();
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index adf2084..9cfaa8b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -408,7 +408,10 @@ static void init_cache_info(struct ppc_cache_info *info, u32 size, u32 lsize,
 	info->line_size = lsize;
 	info->block_size = bsize;
 	info->log_block_size = __ilog2(bsize);
-	info->blocks_per_page = PAGE_SIZE / bsize;
+	if (bsize)
+		info->blocks_per_page = PAGE_SIZE / bsize;
+	else
+		info->blocks_per_page = 0;
 
 	if (sets == 0)
 		info->assoc = 0xffff;
diff --git a/arch/powerpc/lib/Makefile b/arch/powerpc/lib/Makefile
index 0e649d7..2b5e090 100644
--- a/arch/powerpc/lib/Makefile
+++ b/arch/powerpc/lib/Makefile
@@ -20,6 +20,7 @@
 
 obj64-$(CONFIG_SMP)	+= locks.o
 obj64-$(CONFIG_ALTIVEC)	+= vmx-helper.o
+obj64-$(CONFIG_KPROBES_SANITY_TEST) += test_emulate_step.o
 
 obj-y			+= checksum_$(BITS).o checksum_wrappers.o
 
diff --git a/arch/powerpc/lib/sstep.c b/arch/powerpc/lib/sstep.c
index 846dba2..9c542ec 100644
--- a/arch/powerpc/lib/sstep.c
+++ b/arch/powerpc/lib/sstep.c
@@ -1799,8 +1799,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case LARX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1823,8 +1821,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case STCX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (op.ea & (size - 1))
 			break;		/* can't handle misaligned */
 		if (!address_ok(regs, op.ea, size))
@@ -1849,8 +1845,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto ldst_done;
 
 	case LOAD:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = read_mem(&regs->gpr[op.reg], op.ea, size, regs);
 		if (!err) {
 			if (op.type & SIGNEXT)
@@ -1862,8 +1856,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case LOAD_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_load(op.reg, do_lfs, op.ea, size, regs);
 		else
@@ -1872,15 +1864,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case LOAD_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_load(op.reg, do_lvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case LOAD_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_load(op.reg, do_lxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
@@ -1903,8 +1891,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 		goto instr_done;
 
 	case STORE:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if ((op.type & UPDATE) && size == sizeof(long) &&
 		    op.reg == 1 && op.update_reg == 1 &&
 		    !(regs->msr & MSR_PR) &&
@@ -1917,8 +1903,6 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 
 #ifdef CONFIG_PPC_FPU
 	case STORE_FP:
-		if (regs->msr & MSR_LE)
-			return 0;
 		if (size == 4)
 			err = do_fp_store(op.reg, do_stfs, op.ea, size, regs);
 		else
@@ -1927,15 +1911,11 @@ int __kprobes emulate_step(struct pt_regs *regs, unsigned int instr)
 #endif
 #ifdef CONFIG_ALTIVEC
 	case STORE_VMX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vec_store(op.reg, do_stvx, op.ea & ~0xfUL, regs);
 		goto ldst_done;
 #endif
 #ifdef CONFIG_VSX
 	case STORE_VSX:
-		if (regs->msr & MSR_LE)
-			return 0;
 		err = do_vsx_store(op.reg, do_stxvd2x, op.ea, regs);
 		goto ldst_done;
 #endif
diff --git a/arch/powerpc/lib/test_emulate_step.c b/arch/powerpc/lib/test_emulate_step.c
new file mode 100644
index 0000000..2534c14
--- /dev/null
+++ b/arch/powerpc/lib/test_emulate_step.c
@@ -0,0 +1,434 @@
+/*
+ * Simple sanity test for emulate_step load/store instructions.
+ *
+ * Copyright IBM Corp. 2016
+ *
+ * This program is free software;  you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "emulate_step_test: " fmt
+
+#include <linux/ptrace.h>
+#include <asm/sstep.h>
+#include <asm/ppc-opcode.h>
+
+#define IMM_L(i)		((uintptr_t)(i) & 0xffff)
+
+/*
+ * Defined with TEST_ prefix so it does not conflict with other
+ * definitions.
+ */
+#define TEST_LD(r, base, i)	(PPC_INST_LD | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZ(r, base, i)	(PPC_INST_LWZ | ___PPC_RT(r) |		\
+					___PPC_RA(base) | IMM_L(i))
+#define TEST_LWZX(t, a, b)	(PPC_INST_LWZX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STD(r, base, i)	(PPC_INST_STD | ___PPC_RS(r) |		\
+					___PPC_RA(base) | ((i) & 0xfffc))
+#define TEST_LDARX(t, a, b, eh)	(PPC_INST_LDARX | ___PPC_RT(t) |	\
+					___PPC_RA(a) | ___PPC_RB(b) |	\
+					__PPC_EH(eh))
+#define TEST_STDCX(s, a, b)	(PPC_INST_STDCX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFSX(t, a, b)	(PPC_INST_LFSX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFSX(s, a, b)	(PPC_INST_STFSX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LFDX(t, a, b)	(PPC_INST_LFDX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STFDX(s, a, b)	(PPC_INST_STFDX | ___PPC_RS(s) |	\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LVX(t, a, b)	(PPC_INST_LVX | ___PPC_RT(t) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_STVX(s, a, b)	(PPC_INST_STVX | ___PPC_RS(s) |		\
+					___PPC_RA(a) | ___PPC_RB(b))
+#define TEST_LXVD2X(s, a, b)	(PPC_INST_LXVD2X | VSX_XX1((s), R##a, R##b))
+#define TEST_STXVD2X(s, a, b)	(PPC_INST_STXVD2X | VSX_XX1((s), R##a, R##b))
+
+
+static void __init init_pt_regs(struct pt_regs *regs)
+{
+	static unsigned long msr;
+	static bool msr_cached;
+
+	memset(regs, 0, sizeof(struct pt_regs));
+
+	if (likely(msr_cached)) {
+		regs->msr = msr;
+		return;
+	}
+
+	asm volatile("mfmsr %0" : "=r"(regs->msr));
+
+	regs->msr |= MSR_FP;
+	regs->msr |= MSR_VEC;
+	regs->msr |= MSR_VSX;
+
+	msr = regs->msr;
+	msr_cached = true;
+}
+
+static void __init show_result(char *ins, char *result)
+{
+	pr_info("%-14s : %s\n", ins, result);
+}
+
+static void __init test_ld(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x23;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* ld r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LD(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("ld", "PASS");
+	else
+		show_result("ld", "FAIL");
+}
+
+static void __init test_lwz(void)
+{
+	struct pt_regs regs;
+	unsigned int a = 0x4545;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+
+	/* lwz r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_LWZ(5, 3, 0));
+
+	if (stepped == 1 && regs.gpr[5] == a)
+		show_result("lwz", "PASS");
+	else
+		show_result("lwz", "FAIL");
+}
+
+static void __init test_lwzx(void)
+{
+	struct pt_regs regs;
+	unsigned int a[3] = {0x0, 0x0, 0x1234};
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) a;
+	regs.gpr[4] = 8;
+	regs.gpr[5] = 0x8765;
+
+	/* lwzx r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LWZX(5, 3, 4));
+	if (stepped == 1 && regs.gpr[5] == a[2])
+		show_result("lwzx", "PASS");
+	else
+		show_result("lwzx", "FAIL");
+}
+
+static void __init test_std(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[5] = 0x5678;
+
+	/* std r5, 0(r3) */
+	stepped = emulate_step(&regs, TEST_STD(5, 3, 0));
+	if (stepped == 1 || regs.gpr[5] == a)
+		show_result("std", "PASS");
+	else
+		show_result("std", "FAIL");
+}
+
+static void __init test_ldarx_stdcx(void)
+{
+	struct pt_regs regs;
+	unsigned long a = 0x1234;
+	int stepped = -1;
+	unsigned long cr0_eq = 0x1 << 29; /* eq bit of CR0 */
+
+	init_pt_regs(&regs);
+	asm volatile("mfcr %0" : "=r"(regs.ccr));
+
+
+	/*** ldarx ***/
+
+	regs.gpr[3] = (unsigned long) &a;
+	regs.gpr[4] = 0;
+	regs.gpr[5] = 0x5678;
+
+	/* ldarx r5, r3, r4, 0 */
+	stepped = emulate_step(&regs, TEST_LDARX(5, 3, 4, 0));
+
+	/*
+	 * Don't touch 'a' here. Touching 'a' can do Load/store
+	 * of 'a' which result in failure of subsequent stdcx.
+	 * Instead, use hardcoded value for comparison.
+	 */
+	if (stepped <= 0 || regs.gpr[5] != 0x1234) {
+		show_result("ldarx / stdcx.", "FAIL (ldarx)");
+		return;
+	}
+
+
+	/*** stdcx. ***/
+
+	regs.gpr[5] = 0x9ABC;
+
+	/* stdcx. r5, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STDCX(5, 3, 4));
+
+	/*
+	 * Two possible scenarios that indicates successful emulation
+	 * of stdcx. :
+	 *  1. Reservation is active and store is performed. In this
+	 *     case cr0.eq bit will be set to 1.
+	 *  2. Reservation is not active and store is not performed.
+	 *     In this case cr0.eq bit will be set to 0.
+	 */
+	if (stepped == 1 && ((regs.gpr[5] == a && (regs.ccr & cr0_eq))
+			|| (regs.gpr[5] != a && !(regs.ccr & cr0_eq))))
+		show_result("ldarx / stdcx.", "PASS");
+	else
+		show_result("ldarx / stdcx.", "FAIL (stdcx.)");
+}
+
+#ifdef CONFIG_PPC_FPU
+static void __init test_lfsx_stfsx(void)
+{
+	struct pt_regs regs;
+	union {
+		float a;
+		int b;
+	} c;
+	int cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfsx ***/
+
+	c.a = 123.45;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfsx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFSX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfsx", "PASS");
+	else
+		show_result("lfsx", "FAIL");
+
+
+	/*** stfsx ***/
+
+	c.a = 678.91;
+
+	/* stfsx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFSX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfsx", "PASS");
+	else
+		show_result("stfsx", "FAIL");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	struct pt_regs regs;
+	union {
+		double a;
+		long b;
+	} c;
+	long cached_b;
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lfdx ***/
+
+	c.a = 123456.78;
+	cached_b = c.b;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lfdx frt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LFDX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lfdx", "PASS");
+	else
+		show_result("lfdx", "FAIL");
+
+
+	/*** stfdx ***/
+
+	c.a = 987654.32;
+
+	/* stfdx frs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STFDX(10, 3, 4));
+
+	if (stepped == 1 && c.b == cached_b)
+		show_result("stfdx", "PASS");
+	else
+		show_result("stfdx", "FAIL");
+}
+#else
+static void __init test_lfsx_stfsx(void)
+{
+	show_result("lfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfsx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+
+static void __init test_lfdx_stfdx(void)
+{
+	show_result("lfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+	show_result("stfdx", "SKIP (CONFIG_PPC_FPU is not set)");
+}
+#endif /* CONFIG_PPC_FPU */
+
+#ifdef CONFIG_ALTIVEC
+static void __init test_lvx_stvx(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lvx ***/
+
+	cached_b[0] = c.b[0] = 923745;
+	cached_b[1] = c.b[1] = 2139478;
+	cached_b[2] = c.b[2] = 9012;
+	cached_b[3] = c.b[3] = 982134;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lvx vrt10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LVX(10, 3, 4));
+
+	if (stepped == 1)
+		show_result("lvx", "PASS");
+	else
+		show_result("lvx", "FAIL");
+
+
+	/*** stvx ***/
+
+	c.b[0] = 4987513;
+	c.b[1] = 84313948;
+	c.b[2] = 71;
+	c.b[3] = 498532;
+
+	/* stvx vrs10, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STVX(10, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stvx", "PASS");
+	else
+		show_result("stvx", "FAIL");
+}
+#else
+static void __init test_lvx_stvx(void)
+{
+	show_result("lvx", "SKIP (CONFIG_ALTIVEC is not set)");
+	show_result("stvx", "SKIP (CONFIG_ALTIVEC is not set)");
+}
+#endif /* CONFIG_ALTIVEC */
+
+#ifdef CONFIG_VSX
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	struct pt_regs regs;
+	union {
+		vector128 a;
+		u32 b[4];
+	} c;
+	u32 cached_b[4];
+	int stepped = -1;
+
+	init_pt_regs(&regs);
+
+
+	/*** lxvd2x ***/
+
+	cached_b[0] = c.b[0] = 18233;
+	cached_b[1] = c.b[1] = 34863571;
+	cached_b[2] = c.b[2] = 834;
+	cached_b[3] = c.b[3] = 6138911;
+
+	regs.gpr[3] = (unsigned long) &c.a;
+	regs.gpr[4] = 0;
+
+	/* lxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_LXVD2X(39, 3, 4));
+
+	if (stepped == 1)
+		show_result("lxvd2x", "PASS");
+	else
+		show_result("lxvd2x", "FAIL");
+
+
+	/*** stxvd2x ***/
+
+	c.b[0] = 21379463;
+	c.b[1] = 87;
+	c.b[2] = 374234;
+	c.b[3] = 4;
+
+	/* stxvd2x vsr39, r3, r4 */
+	stepped = emulate_step(&regs, TEST_STXVD2X(39, 3, 4));
+
+	if (stepped == 1 && cached_b[0] == c.b[0] && cached_b[1] == c.b[1] &&
+	    cached_b[2] == c.b[2] && cached_b[3] == c.b[3])
+		show_result("stxvd2x", "PASS");
+	else
+		show_result("stxvd2x", "FAIL");
+}
+#else
+static void __init test_lxvd2x_stxvd2x(void)
+{
+	show_result("lxvd2x", "SKIP (CONFIG_VSX is not set)");
+	show_result("stxvd2x", "SKIP (CONFIG_VSX is not set)");
+}
+#endif /* CONFIG_VSX */
+
+static int __init test_emulate_step(void)
+{
+	test_ld();
+	test_lwz();
+	test_lwzx();
+	test_std();
+	test_ldarx_stdcx();
+	test_lfsx_stfsx();
+	test_lfdx_stfdx();
+	test_lvx_stvx();
+	test_lxvd2x_stxvd2x();
+
+	return 0;
+}
+late_initcall(test_emulate_step);
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 6aa3b76..9be9920 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -356,18 +356,42 @@ static void early_check_vec5(void)
 	unsigned long root, chosen;
 	int size;
 	const u8 *vec5;
+	u8 mmu_supported;
 
 	root = of_get_flat_dt_root();
 	chosen = of_get_flat_dt_subnode_by_name(root, "chosen");
-	if (chosen == -FDT_ERR_NOTFOUND)
-		return;
-	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
-	if (!vec5)
-		return;
-	if (size <= OV5_INDX(OV5_MMU_RADIX_300) ||
-	    !(vec5[OV5_INDX(OV5_MMU_RADIX_300)] & OV5_FEAT(OV5_MMU_RADIX_300)))
-		/* Hypervisor doesn't support radix */
+	if (chosen == -FDT_ERR_NOTFOUND) {
 		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+		return;
+	}
+	vec5 = of_get_flat_dt_prop(chosen, "ibm,architecture-vec-5", &size);
+	if (!vec5) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+		return;
+	}
+	if (size <= OV5_INDX(OV5_MMU_SUPPORT)) {
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+		return;
+	}
+
+	/* Check for supported configuration */
+	mmu_supported = vec5[OV5_INDX(OV5_MMU_SUPPORT)] &
+			OV5_FEAT(OV5_MMU_SUPPORT);
+	if (mmu_supported == OV5_FEAT(OV5_MMU_RADIX)) {
+		/* Hypervisor only supports radix - check enabled && GTSE */
+		if (!early_radix_enabled()) {
+			pr_warn("WARNING: Ignoring cmdline option disable_radix\n");
+		}
+		if (!(vec5[OV5_INDX(OV5_RADIX_GTSE)] &
+						OV5_FEAT(OV5_RADIX_GTSE))) {
+			pr_warn("WARNING: Hypervisor doesn't support RADIX with GTSE\n");
+		}
+		/* Do radix anyway - the hypervisor said we had to */
+		cur_cpu_spec->mmu_features |= MMU_FTR_TYPE_RADIX;
+	} else if (mmu_supported == OV5_FEAT(OV5_MMU_HASH)) {
+		/* Hypervisor only supports hash - disable radix */
+		cur_cpu_spec->mmu_features &= ~MMU_FTR_TYPE_RADIX;
+	}
 }
 
 void __init mmu_early_init_devtree(void)
@@ -383,7 +407,7 @@ void __init mmu_early_init_devtree(void)
 	 * even though the ibm,architecture-vec-5 property created by
 	 * skiboot doesn't have the necessary bits set.
 	 */
-	if (early_radix_enabled() && !(mfmsr() & MSR_HV))
+	if (!(mfmsr() & MSR_HV))
 		early_check_vec5();
 
 	if (early_radix_enabled())
diff --git a/arch/powerpc/mm/pgtable-radix.c b/arch/powerpc/mm/pgtable-radix.c
index 2a590a9..c28165d 100644
--- a/arch/powerpc/mm/pgtable-radix.c
+++ b/arch/powerpc/mm/pgtable-radix.c
@@ -186,6 +186,10 @@ static void __init radix_init_pgtable(void)
 	 */
 	register_process_table(__pa(process_tb), 0, PRTB_SIZE_SHIFT - 12);
 	pr_info("Process table %p and radix root for kernel: %p\n", process_tb, init_mm.pgd);
+	asm volatile("ptesync" : : : "memory");
+	asm volatile(PPC_TLBIE_5(%0,%1,2,1,1) : :
+		     "r" (TLBIEL_INVAL_SET_LPID), "r" (0));
+	asm volatile("eieio; tlbsync; ptesync" : : : "memory");
 }
 
 static void __init radix_init_partition_table(void)
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 6693f75..da8a0f7 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -39,8 +39,8 @@
 BEGIN_FTR_SECTION;						\
 	b	1f;						\
 END_FTR_SECTION(0, 1);						\
-	ld	r12,opal_tracepoint_refcount@toc(r2);		\
-	cmpdi	r12,0;						\
+	ld	r11,opal_tracepoint_refcount@toc(r2);		\
+	cmpdi	r11,0;						\
 	bne-	LABEL;						\
 1:
 
diff --git a/arch/powerpc/sysdev/xics/icp-opal.c b/arch/powerpc/sysdev/xics/icp-opal.c
index f9670ea..b53f80f 100644
--- a/arch/powerpc/sysdev/xics/icp-opal.c
+++ b/arch/powerpc/sysdev/xics/icp-opal.c
@@ -91,6 +91,16 @@ static unsigned int icp_opal_get_irq(void)
 
 static void icp_opal_set_cpu_priority(unsigned char cppr)
 {
+	/*
+	 * Here be dragons. The caller has asked to allow only IPI's and not
+	 * external interrupts. But OPAL XIVE doesn't support that. So instead
+	 * of allowing no interrupts allow all. That's still not right, but
+	 * currently the only caller who does this is xics_migrate_irqs_away()
+	 * and it works in that case.
+	 */
+	if (cppr >= DEFAULT_PRIORITY)
+		cppr = LOWEST_PRIORITY;
+
 	xics_set_base_cppr(cppr);
 	opal_int_set_cppr(cppr);
 	iosync();
diff --git a/arch/powerpc/sysdev/xics/xics-common.c b/arch/powerpc/sysdev/xics/xics-common.c
index 69d858e..23efe4e 100644
--- a/arch/powerpc/sysdev/xics/xics-common.c
+++ b/arch/powerpc/sysdev/xics/xics-common.c
@@ -20,6 +20,7 @@
 #include <linux/of.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/delay.h>
 
 #include <asm/prom.h>
 #include <asm/io.h>
@@ -198,9 +199,6 @@ void xics_migrate_irqs_away(void)
 	/* Remove ourselves from the global interrupt queue */
 	xics_set_cpu_giq(xics_default_distrib_server, 0);
 
-	/* Allow IPIs again... */
-	icp_ops->set_priority(DEFAULT_PRIORITY);
-
 	for_each_irq_desc(virq, desc) {
 		struct irq_chip *chip;
 		long server;
@@ -255,6 +253,19 @@ void xics_migrate_irqs_away(void)
 unlock:
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 	}
+
+	/* Allow "sufficient" time to drop any inflight IRQ's */
+	mdelay(5);
+
+	/*
+	 * Allow IPIs again. This is done at the very end, after migrating all
+	 * interrupts, the expectation is that we'll only get woken up by an IPI
+	 * interrupt beyond this point, but leave externals masked just to be
+	 * safe. If we're using icp-opal this may actually allow all
+	 * interrupts anyway, but that should be OK.
+	 */
+	icp_ops->set_priority(DEFAULT_PRIORITY);
+
 }
 #endif /* CONFIG_HOTPLUG_CPU */
 
diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig
index 143b1e0..4b176fe 100644
--- a/arch/s390/configs/default_defconfig
+++ b/arch/s390/configs/default_defconfig
@@ -609,7 +609,7 @@
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig
index f05d2d6..0de46cc 100644
--- a/arch/s390/configs/gcov_defconfig
+++ b/arch/s390/configs/gcov_defconfig
@@ -560,7 +560,7 @@
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig
index 2358bf3..e167557 100644
--- a/arch/s390/configs/performance_defconfig
+++ b/arch/s390/configs/performance_defconfig
@@ -558,7 +558,7 @@
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_HIST_TRIGGERS=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
diff --git a/arch/s390/defconfig b/arch/s390/defconfig
index 68bfd09..97189db 100644
--- a/arch/s390/defconfig
+++ b/arch/s390/defconfig
@@ -179,7 +179,7 @@
 CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y
 CONFIG_STACK_TRACER=y
 CONFIG_BLK_DEV_IO_TRACE=y
-CONFIG_UPROBE_EVENT=y
+CONFIG_UPROBE_EVENTS=y
 CONFIG_FUNCTION_PROFILER=y
 CONFIG_TRACE_ENUM_MAP_FILE=y
 CONFIG_KPROBES_SANITY_TEST=y
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 7ef4a09..6205d3b 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -176,6 +176,7 @@
 CONFIG_SKY2=y
 CONFIG_FORCEDETH=y
 CONFIG_8139TOO=y
+CONFIG_R8169=y
 CONFIG_FDDI=y
 CONFIG_INPUT_POLLDEV=y
 # CONFIG_INPUT_MOUSEDEV_PSAUX is not set
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index afb222b..c84584b 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -604,7 +604,7 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, int idx,
 			return &amd_f15_PMC20;
 		}
 	case AMD_EVENT_NB:
-		/* moved to perf_event_amd_uncore.c */
+		/* moved to uncore.c */
 		return &emptyconstraint;
 	default:
 		return &emptyconstraint;
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index aff4b5b..238ae32 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -1,5 +1,5 @@
 /*
- * perf_event_intel_cstate.c: support cstate residency counters
+ * Support cstate residency counters
  *
  * Copyright (C) 2015, Intel Corp.
  * Author: Kan Liang (kan.liang@intel.com)
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index 22054ca..9d05c7e 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -1,5 +1,5 @@
 /*
- * perf_event_intel_rapl.c: support Intel RAPL energy consumption counters
+ * Support Intel RAPL energy consumption counters
  * Copyright (C) 2013 Google, Inc., Stephane Eranian
  *
  * Intel RAPL interface is specified in the IA-32 Manual Vol3b
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index ad986c1..df5989f 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -360,7 +360,7 @@ extern struct list_head pci2phy_map_head;
 extern struct pci_extra_dev *uncore_extra_pci_dev;
 extern struct event_constraint uncore_constraint_empty;
 
-/* perf_event_intel_uncore_snb.c */
+/* uncore_snb.c */
 int snb_uncore_pci_init(void);
 int ivb_uncore_pci_init(void);
 int hsw_uncore_pci_init(void);
@@ -371,7 +371,7 @@ void nhm_uncore_cpu_init(void);
 void skl_uncore_cpu_init(void);
 int snb_pci2phy_map_init(int devid);
 
-/* perf_event_intel_uncore_snbep.c */
+/* uncore_snbep.c */
 int snbep_uncore_pci_init(void);
 void snbep_uncore_cpu_init(void);
 int ivbep_uncore_pci_init(void);
@@ -385,5 +385,5 @@ void knl_uncore_cpu_init(void);
 int skx_uncore_pci_init(void);
 void skx_uncore_cpu_init(void);
 
-/* perf_event_intel_uncore_nhmex.c */
+/* uncore_nhmex.c */
 void nhmex_uncore_cpu_init(void);
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index db64baf0..8bef70e 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -158,13 +158,13 @@ void hyperv_init(void)
 		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 		return;
 	}
+register_msr_cs:
 #endif
 	/*
 	 * For 32 bit guests just use the MSR based mechanism for reading
 	 * the partition counter.
 	 */
 
-register_msr_cs:
 	hyperv_cs = &hyperv_cs_msr;
 	if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE)
 		clocksource_register_hz(&hyperv_cs_msr, NSEC_PER_SEC/100);
diff --git a/arch/x86/include/asm/pkeys.h b/arch/x86/include/asm/pkeys.h
index 34684ad..b3b09b9 100644
--- a/arch/x86/include/asm/pkeys.h
+++ b/arch/x86/include/asm/pkeys.h
@@ -46,6 +46,15 @@ extern int __arch_set_user_pkey_access(struct task_struct *tsk, int pkey,
 static inline
 bool mm_pkey_is_allocated(struct mm_struct *mm, int pkey)
 {
+	/*
+	 * "Allocated" pkeys are those that have been returned
+	 * from pkey_alloc().  pkey 0 is special, and never
+	 * returned from pkey_alloc().
+	 */
+	if (pkey <= 0)
+		return false;
+	if (pkey >= arch_max_pkey())
+		return false;
 	return mm_pkey_allocation_map(mm) & (1U << pkey);
 }
 
@@ -82,12 +91,6 @@ int mm_pkey_alloc(struct mm_struct *mm)
 static inline
 int mm_pkey_free(struct mm_struct *mm, int pkey)
 {
-	/*
-	 * pkey 0 is special, always allocated and can never
-	 * be freed.
-	 */
-	if (!pkey)
-		return -EINVAL;
 	if (!mm_pkey_is_allocated(mm, pkey))
 		return -EINVAL;
 
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 5138dac..07244ea 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -58,7 +58,7 @@ struct setup_header {
 	__u32	header;
 	__u16	version;
 	__u32	realmode_swtch;
-	__u16	start_sys;
+	__u16	start_sys_seg;
 	__u16	kernel_version;
 	__u8	type_of_loader;
 	__u8	loadflags;
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 4261b32..aee7ded 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1610,24 +1610,15 @@ static inline void try_to_enable_x2apic(int remap_mode) { }
 static inline void __x2apic_enable(void) { }
 #endif /* !CONFIG_X86_X2APIC */
 
-static int __init try_to_enable_IR(void)
-{
-#ifdef CONFIG_X86_IO_APIC
-	if (!x2apic_enabled() && skip_ioapic_setup) {
-		pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
-		return -1;
-	}
-#endif
-	return irq_remapping_enable();
-}
-
 void __init enable_IR_x2apic(void)
 {
 	unsigned long flags;
 	int ret, ir_stat;
 
-	if (skip_ioapic_setup)
+	if (skip_ioapic_setup) {
+		pr_info("Not enabling interrupt remapping due to skipped IO-APIC setup\n");
 		return;
+	}
 
 	ir_stat = irq_remapping_prepare();
 	if (ir_stat < 0 && !x2apic_supported())
@@ -1645,7 +1636,7 @@ void __init enable_IR_x2apic(void)
 
 	/* If irq_remapping_prepare() succeeded, try to enable it */
 	if (ir_stat >= 0)
-		ir_stat = try_to_enable_IR();
+		ir_stat = irq_remapping_enable();
 	/* ir_stat contains the remap mode or an error code */
 	try_to_enable_x2apic(ir_stat);
 
@@ -2062,10 +2053,10 @@ static int allocate_logical_cpuid(int apicid)
 
 	/* Allocate a new cpuid. */
 	if (nr_logical_cpuids >= nr_cpu_ids) {
-		WARN_ONCE(1, "Only %d processors supported."
+		WARN_ONCE(1, "APIC: NR_CPUS/possible_cpus limit of %i reached. "
 			     "Processor %d/0x%x and the rest are ignored.\n",
-			     nr_cpu_ids - 1, nr_logical_cpuids, apicid);
-		return -1;
+			     nr_cpu_ids, nr_logical_cpuids, apicid);
+		return -EINVAL;
 	}
 
 	cpuid_to_apicid[nr_logical_cpuids] = apicid;
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 35a5d5d..c36140d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -556,10 +556,6 @@ static void early_init_amd(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (check_tsc_unstable())
-			clear_sched_clock_stable();
-	} else {
-		clear_sched_clock_stable();
 	}
 
 	/* Bit 12 of 8000_0007 edx is accumulated power mechanism. */
diff --git a/arch/x86/kernel/cpu/centaur.c b/arch/x86/kernel/cpu/centaur.c
index adc0ebd..43955ee 100644
--- a/arch/x86/kernel/cpu/centaur.c
+++ b/arch/x86/kernel/cpu/centaur.c
@@ -105,8 +105,6 @@ static void early_init_centaur(struct cpuinfo_x86 *c)
 #ifdef CONFIG_X86_64
 	set_cpu_cap(c, X86_FEATURE_SYSENTER32);
 #endif
-
-	clear_sched_clock_stable();
 }
 
 static void init_centaur(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b11b38c..58094a1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -88,7 +88,6 @@ static void default_init(struct cpuinfo_x86 *c)
 			strcpy(c->x86_model_id, "386");
 	}
 #endif
-	clear_sched_clock_stable();
 }
 
 static const struct cpu_dev default_cpu = {
@@ -1077,8 +1076,6 @@ static void identify_cpu(struct cpuinfo_x86 *c)
 	 */
 	if (this_cpu->c_init)
 		this_cpu->c_init(c);
-	else
-		clear_sched_clock_stable();
 
 	/* Disable the PN if appropriate */
 	squash_the_stupid_serial_number(c);
diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c
index 0a3bc19..a70fd61 100644
--- a/arch/x86/kernel/cpu/cyrix.c
+++ b/arch/x86/kernel/cpu/cyrix.c
@@ -185,7 +185,6 @@ static void early_init_cyrix(struct cpuinfo_x86 *c)
 		set_cpu_cap(c, X86_FEATURE_CYRIX_ARR);
 		break;
 	}
-	clear_sched_clock_stable();
 }
 
 static void init_cyrix(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index fe0a615..0631977 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -162,10 +162,6 @@ static void early_init_intel(struct cpuinfo_x86 *c)
 	if (c->x86_power & (1 << 8)) {
 		set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
 		set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC);
-		if (check_tsc_unstable())
-			clear_sched_clock_stable();
-	} else {
-		clear_sched_clock_stable();
 	}
 
 	/* Penwell and Cloverview have the TSC which doesn't sleep on S3 */
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 0bbe0f3..c05509d 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -28,7 +28,6 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/task.h>
 #include <linux/slab.h>
-#include <linux/cpu.h>
 #include <linux/task_work.h>
 
 #include <uapi/linux/magic.h>
diff --git a/arch/x86/kernel/cpu/transmeta.c b/arch/x86/kernel/cpu/transmeta.c
index 8457b49..d77d07a 100644
--- a/arch/x86/kernel/cpu/transmeta.c
+++ b/arch/x86/kernel/cpu/transmeta.c
@@ -16,8 +16,6 @@ static void early_init_transmeta(struct cpuinfo_x86 *c)
 		if (xlvl >= 0x80860001)
 			c->x86_capability[CPUID_8086_0001_EDX] = cpuid_edx(0x80860001);
 	}
-
-	clear_sched_clock_stable();
 }
 
 static void init_transmeta(struct cpuinfo_x86 *c)
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 891f4da..22403a2 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -30,7 +30,6 @@
 #include <asm/hypervisor.h>
 #include <asm/timer.h>
 #include <asm/apic.h>
-#include <asm/timer.h>
 
 #undef pr_fmt
 #define pr_fmt(fmt)	"vmware: " fmt
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index dc6ba5b..89ff7af 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -354,7 +354,7 @@ static int hpet_resume(struct clock_event_device *evt, int timer)
 
 		irq_domain_deactivate_irq(irq_get_irq_data(hdev->irq));
 		irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
-		disable_irq(hdev->irq);
+		disable_hardirq(hdev->irq);
 		irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
 		enable_irq(hdev->irq);
 	}
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index bdb83e4..38b6458 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -167,7 +167,7 @@ static int __init boot_params_kdebugfs_init(void)
 	struct dentry *dbp, *version, *data;
 	int error = -ENOMEM;
 
-	dbp = debugfs_create_dir("boot_params", NULL);
+	dbp = debugfs_create_dir("boot_params", arch_debugfs_dir);
 	if (!dbp)
 		return -ENOMEM;
 
diff --git a/arch/x86/kernel/kprobes/common.h b/arch/x86/kernel/kprobes/common.h
index c6ee63f..d688826 100644
--- a/arch/x86/kernel/kprobes/common.h
+++ b/arch/x86/kernel/kprobes/common.h
@@ -67,7 +67,7 @@
 #endif
 
 /* Ensure if the instruction can be boostable */
-extern int can_boost(kprobe_opcode_t *instruction);
+extern int can_boost(kprobe_opcode_t *instruction, void *addr);
 /* Recover instruction if given address is probed */
 extern unsigned long recover_probed_instruction(kprobe_opcode_t *buf,
 					 unsigned long addr);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 6384eb7..993fa4f 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -167,12 +167,12 @@ NOKPROBE_SYMBOL(skip_prefixes);
  * Returns non-zero if opcode is boostable.
  * RIP relative instructions are adjusted at copying time in 64 bits mode
  */
-int can_boost(kprobe_opcode_t *opcodes)
+int can_boost(kprobe_opcode_t *opcodes, void *addr)
 {
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
 
-	if (search_exception_tables((unsigned long)opcodes))
+	if (search_exception_tables((unsigned long)addr))
 		return 0;	/* Page fault may occur on this address. */
 
 retry:
@@ -417,7 +417,7 @@ static int arch_copy_kprobe(struct kprobe *p)
 	 * __copy_instruction can modify the displacement of the instruction,
 	 * but it doesn't affect boostable check.
 	 */
-	if (can_boost(p->ainsn.insn))
+	if (can_boost(p->ainsn.insn, p->addr))
 		p->ainsn.boostable = 0;
 	else
 		p->ainsn.boostable = -1;
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 3d1bee9..3e7c6e5 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -178,7 +178,7 @@ static int copy_optimized_instructions(u8 *dest, u8 *src)
 
 	while (len < RELATIVEJUMP_SIZE) {
 		ret = __copy_instruction(dest + len, src + len);
-		if (!ret || !can_boost(dest + len))
+		if (!ret || !can_boost(dest + len, src + len))
 			return -EINVAL;
 		len += ret;
 	}
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index e244c19..4194d6f 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -223,6 +223,22 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_BOARD_NAME, "P4S800"),
 		},
 	},
+	{	/* Handle problems with rebooting on ASUS EeeBook X205TA */
+		.callback = set_acpi_reboot,
+		.ident = "ASUS EeeBook X205TA",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+		},
+	},
+	{	/* Handle problems with rebooting on ASUS EeeBook X205TAW */
+		.callback = set_acpi_reboot,
+		.ident = "ASUS EeeBook X205TAW",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "X205TAW"),
+		},
+	},
 
 	/* Certec */
 	{       /* Handle problems with rebooting on Certec BPC600 */
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 46bcda4..4f7a983 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -327,9 +327,16 @@ unsigned long long sched_clock(void)
 {
 	return paravirt_sched_clock();
 }
+
+static inline bool using_native_sched_clock(void)
+{
+	return pv_time_ops.sched_clock == native_sched_clock;
+}
 #else
 unsigned long long
 sched_clock(void) __attribute__((alias("native_sched_clock")));
+
+static inline bool using_native_sched_clock(void) { return true; }
 #endif
 
 int check_tsc_unstable(void)
@@ -1112,8 +1119,10 @@ static void tsc_cs_mark_unstable(struct clocksource *cs)
 {
 	if (tsc_unstable)
 		return;
+
 	tsc_unstable = 1;
-	clear_sched_clock_stable();
+	if (using_native_sched_clock())
+		clear_sched_clock_stable();
 	disable_sched_clock_irqtime();
 	pr_info("Marking TSC unstable due to clocksource watchdog\n");
 }
@@ -1135,18 +1144,20 @@ static struct clocksource clocksource_tsc = {
 
 void mark_tsc_unstable(char *reason)
 {
-	if (!tsc_unstable) {
-		tsc_unstable = 1;
+	if (tsc_unstable)
+		return;
+
+	tsc_unstable = 1;
+	if (using_native_sched_clock())
 		clear_sched_clock_stable();
-		disable_sched_clock_irqtime();
-		pr_info("Marking TSC unstable due to %s\n", reason);
-		/* Change only the rating, when not registered */
-		if (clocksource_tsc.mult)
-			clocksource_mark_unstable(&clocksource_tsc);
-		else {
-			clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
-			clocksource_tsc.rating = 0;
-		}
+	disable_sched_clock_irqtime();
+	pr_info("Marking TSC unstable due to %s\n", reason);
+	/* Change only the rating, when not registered */
+	if (clocksource_tsc.mult) {
+		clocksource_mark_unstable(&clocksource_tsc);
+	} else {
+		clocksource_tsc.flags |= CLOCK_SOURCE_UNSTABLE;
+		clocksource_tsc.rating = 0;
 	}
 }
 
diff --git a/arch/x86/pci/common.c b/arch/x86/pci/common.c
index 0cb52ae..190e718 100644
--- a/arch/x86/pci/common.c
+++ b/arch/x86/pci/common.c
@@ -735,6 +735,15 @@ void pcibios_disable_device (struct pci_dev *dev)
 		pcibios_disable_irq(dev);
 }
 
+#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC
+void pcibios_release_device(struct pci_dev *dev)
+{
+	if (atomic_dec_return(&dev->enable_cnt) >= 0)
+		pcibios_disable_device(dev);
+
+}
+#endif
+
 int pci_ext_cfg_avail(void)
 {
 	if (raw_pci_ext_ops)
diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 766d4d3..f25982c 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1847,7 +1847,6 @@ static void pq_init(int node, int pnode)
 
 	ops.write_payload_first(pnode, first);
 	ops.write_payload_last(pnode, last);
-	ops.write_g_sw_ack(pnode, 0xffffUL);
 
 	/* in effect, all msg_type's are set to MSG_NOOP */
 	memset(pqp, 0, sizeof(struct bau_pq_entry) * DEST_Q_SIZE);
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index 25e068b..b6d5c89 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -11,6 +11,7 @@
  */
 
 #include "sha256.h"
+#include "purgatory.h"
 #include "../boot/string.h"
 
 struct sha_region {
@@ -18,11 +19,11 @@ struct sha_region {
 	unsigned long len;
 };
 
-unsigned long backup_dest = 0;
-unsigned long backup_src = 0;
-unsigned long backup_sz = 0;
+static unsigned long backup_dest;
+static unsigned long backup_src;
+static unsigned long backup_sz;
 
-u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
+static u8 sha256_digest[SHA256_DIGEST_SIZE] = { 0 };
 
 struct sha_region sha_regions[16] = {};
 
@@ -39,7 +40,7 @@ static int copy_backup_region(void)
 	return 0;
 }
 
-int verify_sha256_digest(void)
+static int verify_sha256_digest(void)
 {
 	struct sha_region *ptr, *end;
 	u8 digest[SHA256_DIGEST_SIZE];
diff --git a/arch/x86/purgatory/purgatory.h b/arch/x86/purgatory/purgatory.h
new file mode 100644
index 0000000..e2e365a
--- /dev/null
+++ b/arch/x86/purgatory/purgatory.h
@@ -0,0 +1,8 @@
+#ifndef PURGATORY_H
+#define PURGATORY_H
+
+#ifndef __ASSEMBLY__
+extern void purgatory(void);
+#endif	/* __ASSEMBLY__ */
+
+#endif /* PURGATORY_H */
diff --git a/arch/x86/purgatory/setup-x86_64.S b/arch/x86/purgatory/setup-x86_64.S
index fe3c91b..f90e9df 100644
--- a/arch/x86/purgatory/setup-x86_64.S
+++ b/arch/x86/purgatory/setup-x86_64.S
@@ -9,6 +9,7 @@
  * This source code is licensed under the GNU General Public License,
  * Version 2.  See the file COPYING for more details.
  */
+#include "purgatory.h"
 
 	.text
 	.globl purgatory_start
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 219b90b..f159001 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -41,8 +41,10 @@ void acpi_gpe_apply_masked_gpes(void);
 void acpi_container_init(void);
 void acpi_memory_hotplug_init(void);
 #ifdef	CONFIG_ACPI_HOTPLUG_IOAPIC
+void pci_ioapic_remove(struct acpi_pci_root *root);
 int acpi_ioapic_remove(struct acpi_pci_root *root);
 #else
+static inline void pci_ioapic_remove(struct acpi_pci_root *root) { return; }
 static inline int acpi_ioapic_remove(struct acpi_pci_root *root) { return 0; }
 #endif
 #ifdef CONFIG_ACPI_DOCK
diff --git a/drivers/acpi/ioapic.c b/drivers/acpi/ioapic.c
index 6d7ce6e..1120dfd6 100644
--- a/drivers/acpi/ioapic.c
+++ b/drivers/acpi/ioapic.c
@@ -206,6 +206,23 @@ int acpi_ioapic_add(acpi_handle root_handle)
 	return ACPI_SUCCESS(status) && ACPI_SUCCESS(retval) ? 0 : -ENODEV;
 }
 
+void pci_ioapic_remove(struct acpi_pci_root *root)
+{
+	struct acpi_pci_ioapic *ioapic, *tmp;
+
+	mutex_lock(&ioapic_list_lock);
+	list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
+		if (root->device->handle != ioapic->root_handle)
+			continue;
+		if (ioapic->pdev) {
+			pci_release_region(ioapic->pdev, 0);
+			pci_disable_device(ioapic->pdev);
+			pci_dev_put(ioapic->pdev);
+		}
+	}
+	mutex_unlock(&ioapic_list_lock);
+}
+
 int acpi_ioapic_remove(struct acpi_pci_root *root)
 {
 	int retval = 0;
@@ -215,15 +232,8 @@ int acpi_ioapic_remove(struct acpi_pci_root *root)
 	list_for_each_entry_safe(ioapic, tmp, &ioapic_list, list) {
 		if (root->device->handle != ioapic->root_handle)
 			continue;
-
 		if (acpi_unregister_ioapic(ioapic->handle, ioapic->gsi_base))
 			retval = -EBUSY;
-
-		if (ioapic->pdev) {
-			pci_release_region(ioapic->pdev, 0);
-			pci_disable_device(ioapic->pdev);
-			pci_dev_put(ioapic->pdev);
-		}
 		if (ioapic->res.flags && ioapic->res.parent)
 			release_resource(&ioapic->res);
 		list_del(&ioapic->list);
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index bf601d4..919be0a 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -648,12 +648,12 @@ static void acpi_pci_root_remove(struct acpi_device *device)
 
 	pci_stop_root_bus(root->bus);
 
-	WARN_ON(acpi_ioapic_remove(root));
-
+	pci_ioapic_remove(root);
 	device_set_run_wake(root->bus->bridge, false);
 	pci_acpi_remove_bus_pm_notifier(device);
 
 	pci_remove_root_bus(root->bus);
+	WARN_ON(acpi_ioapic_remove(root));
 
 	dmar_device_remove(device->handle);
 
diff --git a/drivers/char/nwbutton.c b/drivers/char/nwbutton.c
index a5b1eb2..e6d0d27 100644
--- a/drivers/char/nwbutton.c
+++ b/drivers/char/nwbutton.c
@@ -6,7 +6,7 @@
 
 #include <linux/module.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/interrupt.h>
 #include <linux/time.h>
 #include <linux/timer.h>
diff --git a/drivers/firmware/efi/arm-runtime.c b/drivers/firmware/efi/arm-runtime.c
index 349dc3e..974c5a3 100644
--- a/drivers/firmware/efi/arm-runtime.c
+++ b/drivers/firmware/efi/arm-runtime.c
@@ -65,6 +65,7 @@ static bool __init efi_virtmap_init(void)
 	bool systab_found;
 
 	efi_mm.pgd = pgd_alloc(&efi_mm);
+	mm_init_cpumask(&efi_mm);
 	init_new_context(NULL, &efi_mm);
 
 	systab_found = false;
diff --git a/drivers/firmware/efi/libstub/secureboot.c b/drivers/firmware/efi/libstub/secureboot.c
index 6def402..5da36e5 100644
--- a/drivers/firmware/efi/libstub/secureboot.c
+++ b/drivers/firmware/efi/libstub/secureboot.c
@@ -45,6 +45,8 @@ enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
 	size = sizeof(secboot);
 	status = get_efi_var(efi_SecureBoot_name, &efi_variable_guid,
 			     NULL, &size, &secboot);
+	if (status == EFI_NOT_FOUND)
+		return efi_secureboot_mode_disabled;
 	if (status != EFI_SUCCESS)
 		goto out_efi_err;
 
@@ -78,7 +80,5 @@ enum efi_secureboot_mode efi_get_secureboot(efi_system_table_t *sys_table_arg)
 
 out_efi_err:
 	pr_efi_err(sys_table_arg, "Could not determine UEFI Secure Boot status.\n");
-	if (status == EFI_NOT_FOUND)
-		return efi_secureboot_mode_disabled;
 	return efi_secureboot_mode_unknown;
 }
diff --git a/drivers/irqchip/irq-crossbar.c b/drivers/irqchip/irq-crossbar.c
index 1eef56a..05bbf17 100644
--- a/drivers/irqchip/irq-crossbar.c
+++ b/drivers/irqchip/irq-crossbar.c
@@ -198,7 +198,8 @@ static const struct irq_domain_ops crossbar_domain_ops = {
 
 static int __init crossbar_of_init(struct device_node *node)
 {
-	int i, size, max = 0, reserved = 0, entry;
+	int i, size, reserved = 0;
+	u32 max = 0, entry;
 	const __be32 *irqsr;
 	int ret = -ENOMEM;
 
diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
index f8afc6d..e8cef1a 100644
--- a/drivers/xen/swiotlb-xen.c
+++ b/drivers/xen/swiotlb-xen.c
@@ -681,3 +681,50 @@ xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask)
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xen_swiotlb_set_dma_mask);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+	if (__generic_dma_ops(dev)->mmap)
+		return __generic_dma_ops(dev)->mmap(dev, vma, cpu_addr,
+						    dma_addr, size, attrs);
+#endif
+	return dma_common_mmap(dev, vma, cpu_addr, dma_addr, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_dma_mmap);
+
+/*
+ * This function should be called with the pages from the current domain only,
+ * passing pages mapped from other domains would lead to memory corruption.
+ */
+int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t handle, size_t size,
+			unsigned long attrs)
+{
+#if defined(CONFIG_ARM) || defined(CONFIG_ARM64)
+	if (__generic_dma_ops(dev)->get_sgtable) {
+#if 0
+	/*
+	 * This check verifies that the page belongs to the current domain and
+	 * is not one mapped from another domain.
+	 * This check is for debug only, and should not go to production build
+	 */
+		unsigned long bfn = PHYS_PFN(dma_to_phys(dev, handle));
+		BUG_ON (!page_is_ram(bfn));
+#endif
+		return __generic_dma_ops(dev)->get_sgtable(dev, sgt, cpu_addr,
+							   handle, size, attrs);
+	}
+#endif
+	return dma_common_get_sgtable(dev, sgt, cpu_addr, handle, size);
+}
+EXPORT_SYMBOL_GPL(xen_swiotlb_get_sgtable);
diff --git a/fs/timerfd.c b/fs/timerfd.c
index 384fa75..c543cdb 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -400,9 +400,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 	     clockid != CLOCK_BOOTTIME_ALARM))
 		return -EINVAL;
 
-	if (!capable(CAP_WAKE_ALARM) &&
-	    (clockid == CLOCK_REALTIME_ALARM ||
-	     clockid == CLOCK_BOOTTIME_ALARM))
+	if ((clockid == CLOCK_REALTIME_ALARM ||
+	     clockid == CLOCK_BOOTTIME_ALARM) &&
+	    !capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -449,7 +449,7 @@ static int do_timerfd_settime(int ufd, int flags,
 		return ret;
 	ctx = f.file->private_data;
 
-	if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) {
+	if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) {
 		fdput(f);
 		return -EPERM;
 	}
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 8e06d75..2afd74b 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -90,6 +90,13 @@ extern bool static_key_initialized;
 struct static_key {
 	atomic_t enabled;
 /*
+ * Note:
+ *   To make anonymous unions work with old compilers, the static
+ *   initialization of them requires brackets. This creates a dependency
+ *   on the order of the struct with the initializers. If any fields
+ *   are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need
+ *   to be modified.
+ *
  * bit 0 => 1 if key is initially true
  *	    0 if initially false
  * bit 1 => 1 if points to struct static_key_mod
@@ -166,10 +173,10 @@ extern void static_key_disable(struct static_key *key);
  */
 #define STATIC_KEY_INIT_TRUE					\
 	{ .enabled = { 1 },					\
-	  .entries = (void *)JUMP_TYPE_TRUE }
+	  { .entries = (void *)JUMP_TYPE_TRUE } }
 #define STATIC_KEY_INIT_FALSE					\
 	{ .enabled = { 0 },					\
-	  .entries = (void *)JUMP_TYPE_FALSE }
+	  { .entries = (void *)JUMP_TYPE_FALSE } }
 
 #else  /* !HAVE_JUMP_LABEL */
 
diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h
index be76523..32354b4 100644
--- a/include/linux/user_namespace.h
+++ b/include/linux/user_namespace.h
@@ -72,7 +72,7 @@ struct ucounts {
 	struct hlist_node node;
 	struct user_namespace *ns;
 	kuid_t uid;
-	atomic_t count;
+	int count;
 	atomic_t ucount[UCOUNT_COUNTS];
 };
 
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index 14e49c7..b35533b 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -1,5 +1,6 @@
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM raw_syscalls
+#undef TRACE_INCLUDE_FILE
 #define TRACE_INCLUDE_FILE syscalls
 
 #if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
diff --git a/include/xen/swiotlb-xen.h b/include/xen/swiotlb-xen.h
index a0083be..1f6d78f 100644
--- a/include/xen/swiotlb-xen.h
+++ b/include/xen/swiotlb-xen.h
@@ -2,6 +2,7 @@
 #define __LINUX_SWIOTLB_XEN_H
 
 #include <linux/dma-direction.h>
+#include <linux/scatterlist.h>
 #include <linux/swiotlb.h>
 
 extern int xen_swiotlb_init(int verbose, bool early);
@@ -55,4 +56,14 @@ xen_swiotlb_dma_supported(struct device *hwdev, u64 mask);
 
 extern int
 xen_swiotlb_set_dma_mask(struct device *dev, u64 dma_mask);
+
+extern int
+xen_swiotlb_dma_mmap(struct device *dev, struct vm_area_struct *vma,
+		     void *cpu_addr, dma_addr_t dma_addr, size_t size,
+		     unsigned long attrs);
+
+extern int
+xen_swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt,
+			void *cpu_addr, dma_addr_t handle, size_t size,
+			unsigned long attrs);
 #endif /* __LINUX_SWIOTLB_XEN_H */
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 12e38c2..a95e5d1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3262,10 +3262,17 @@ static int __lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	if (depth) {
 		hlock = curr->held_locks + depth - 1;
 		if (hlock->class_idx == class_idx && nest_lock) {
-			if (hlock->references)
+			if (hlock->references) {
+				/*
+				 * Check: unsigned int references:12, overflow.
+				 */
+				if (DEBUG_LOCKS_WARN_ON(hlock->references == (1 << 12)-1))
+					return 0;
+
 				hlock->references++;
-			else
+			} else {
 				hlock->references = 2;
+			}
 
 			return 1;
 		}
diff --git a/kernel/locking/test-ww_mutex.c b/kernel/locking/test-ww_mutex.c
index da6c9a3..6b7abb3 100644
--- a/kernel/locking/test-ww_mutex.c
+++ b/kernel/locking/test-ww_mutex.c
@@ -50,7 +50,7 @@ static void test_mutex_work(struct work_struct *work)
 
 	if (mtx->flags & TEST_MTX_TRY) {
 		while (!ww_mutex_trylock(&mtx->mutex))
-			cpu_relax();
+			cond_resched();
 	} else {
 		ww_mutex_lock(&mtx->mutex, NULL);
 	}
@@ -88,7 +88,7 @@ static int __test_mutex(unsigned int flags)
 				ret = -EINVAL;
 				break;
 			}
-			cpu_relax();
+			cond_resched();
 		} while (time_before(jiffies, timeout));
 	} else {
 		ret = wait_for_completion_timeout(&mtx.done, TIMEOUT);
@@ -627,7 +627,7 @@ static int __init test_ww_mutex_init(void)
 	if (ret)
 		return ret;
 
-	ret = stress(4096, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
+	ret = stress(4095, hweight32(STRESS_ALL)*ncpus, 1<<12, STRESS_ALL);
 	if (ret)
 		return ret;
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9563838..3b31fc0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3287,10 +3287,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 	struct task_struct *p;
 
 	/*
-	 * Optimization: we know that if all tasks are in
-	 * the fair class we can call that function directly:
+	 * Optimization: we know that if all tasks are in the fair class we can
+	 * call that function directly, but only if the @prev task wasn't of a
+	 * higher scheduling class, because otherwise those loose the
+	 * opportunity to pull in more work from other CPUs.
 	 */
-	if (likely(rq->nr_running == rq->cfs.h_nr_running)) {
+	if (likely((prev->sched_class == &idle_sched_class ||
+		    prev->sched_class == &fair_sched_class) &&
+		   rq->nr_running == rq->cfs.h_nr_running)) {
+
 		p = fair_sched_class.pick_next_task(rq, prev, rf);
 		if (unlikely(p == RETRY_TASK))
 			goto again;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 3e88b35..dea1389 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5799,7 +5799,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
 	 * Due to large variance we need a large fuzz factor; hackbench in
 	 * particularly is sensitive here.
 	 */
-	if ((avg_idle / 512) < avg_cost)
+	if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost)
 		return -1;
 
 	time = local_clock();
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 69631fa..1b3c818 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true)
  */
 SCHED_FEAT(TTWU_QUEUE, true)
 
+/*
+ * When doing wakeups, attempt to limit superfluous scans of the LLC domain.
+ */
+SCHED_FEAT(SIS_AVG_CPU, false)
+
 #ifdef HAVE_RT_PUSH_IPI
 /*
  * In order to avoid a thundering herd attack of CPUs that are
diff --git a/kernel/time/jiffies.c b/kernel/time/jiffies.c
index 7906b3f..4977191 100644
--- a/kernel/time/jiffies.c
+++ b/kernel/time/jiffies.c
@@ -125,7 +125,7 @@ int register_refined_jiffies(long cycles_per_second)
 	shift_hz += cycles_per_tick/2;
 	do_div(shift_hz, cycles_per_tick);
 	/* Calculate nsec_per_tick using shift_hz */
-	nsec_per_tick = (u64)TICK_NSEC << 8;
+	nsec_per_tick = (u64)NSEC_PER_SEC << 8;
 	nsec_per_tick += (u32)shift_hz/2;
 	do_div(nsec_per_tick, (u32)shift_hz);
 
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d503800..d4a06e7 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -429,7 +429,7 @@
 
 	  If unsure, say N.
 
-config KPROBE_EVENT
+config KPROBE_EVENTS
 	depends on KPROBES
 	depends on HAVE_REGS_AND_STACK_ACCESS_API
 	bool "Enable kprobes-based dynamic events"
@@ -447,7 +447,7 @@
 	  This option is also required by perf-probe subcommand of perf tools.
 	  If you want to use perf tools, this option is strongly recommended.
 
-config UPROBE_EVENT
+config UPROBE_EVENTS
 	bool "Enable uprobes-based dynamic events"
 	depends on ARCH_SUPPORTS_UPROBES
 	depends on MMU
@@ -466,7 +466,7 @@
 
 config BPF_EVENTS
 	depends on BPF_SYSCALL
-	depends on (KPROBE_EVENT || UPROBE_EVENT) && PERF_EVENTS
+	depends on (KPROBE_EVENTS || UPROBE_EVENTS) && PERF_EVENTS
 	bool
 	default y
 	help
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index e579808..90f2701 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -57,7 +57,7 @@
 obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
 obj-$(CONFIG_HIST_TRIGGERS) += trace_events_hist.o
 obj-$(CONFIG_BPF_EVENTS) += bpf_trace.o
-obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
+obj-$(CONFIG_KPROBE_EVENTS) += trace_kprobe.o
 obj-$(CONFIG_TRACEPOINTS) += power-traces.o
 ifeq ($(CONFIG_PM),y)
 obj-$(CONFIG_TRACEPOINTS) += rpm-traces.o
@@ -66,7 +66,7 @@
 obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
 endif
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
-obj-$(CONFIG_UPROBE_EVENT) += trace_uprobe.o
+obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 0d1597c..b9691ee 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -4416,16 +4416,24 @@ static int __init set_graph_notrace_function(char *str)
 }
 __setup("ftrace_graph_notrace=", set_graph_notrace_function);
 
+static int __init set_graph_max_depth_function(char *str)
+{
+	if (!str)
+		return 0;
+	fgraph_max_depth = simple_strtoul(str, NULL, 0);
+	return 1;
+}
+__setup("ftrace_graph_max_depth=", set_graph_max_depth_function);
+
 static void __init set_ftrace_early_graph(char *buf, int enable)
 {
 	int ret;
 	char *func;
 	struct ftrace_hash *hash;
 
-	if (enable)
-		hash = ftrace_graph_hash;
-	else
-		hash = ftrace_graph_notrace_hash;
+	hash = alloc_ftrace_hash(FTRACE_HASH_DEFAULT_BITS);
+	if (WARN_ON(!hash))
+		return;
 
 	while (buf) {
 		func = strsep(&buf, ",");
@@ -4435,6 +4443,11 @@ static void __init set_ftrace_early_graph(char *buf, int enable)
 			printk(KERN_DEBUG "ftrace: function %s not "
 					  "traceable\n", func);
 	}
+
+	if (enable)
+		ftrace_graph_hash = hash;
+	else
+		ftrace_graph_notrace_hash = hash;
 }
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
@@ -5488,7 +5501,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
  * Normally the mcount trampoline will call the ops->func, but there
  * are times that it should not. For example, if the ops does not
  * have its own recursion protection, then it should call the
- * ftrace_ops_recurs_func() instead.
+ * ftrace_ops_assist_func() instead.
  *
  * Returns the function that the trampoline should call for @ops.
  */
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 707445c..f351095 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4341,22 +4341,22 @@ static const char readme_msg[] =
 	"\t\t\t  traces\n"
 #endif
 #endif /* CONFIG_STACK_TRACER */
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#if defined(CONFIG_KPROBE_EVENT) || defined(CONFIG_UPROBE_EVENT)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
 	"\t  accepts: event-definitions (one definition per line)\n"
 	"\t   Format: p|r[:[<group>/]<event>] <place> [<args>]\n"
 	"\t           -:[<group>/]<event>\n"
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 	"\t    place: [<module>:]<symbol>[+<offset>]|<memaddr>\n"
 #endif
-#ifdef CONFIG_UPROBE_EVENT
+#ifdef CONFIG_UPROBE_EVENTS
 	"\t    place: <path>:<offset>\n"
 #endif
 	"\t     args: <name>=fetcharg[:type]\n"
diff --git a/kernel/trace/trace_probe.h b/kernel/trace/trace_probe.h
index 0c0ae54..903273c 100644
--- a/kernel/trace/trace_probe.h
+++ b/kernel/trace/trace_probe.h
@@ -248,7 +248,7 @@ ASSIGN_FETCH_FUNC(file_offset, ftype),			\
 #define FETCH_TYPE_STRING	0
 #define FETCH_TYPE_STRSIZE	1
 
-#ifdef CONFIG_KPROBE_EVENT
+#ifdef CONFIG_KPROBE_EVENTS
 struct symbol_cache;
 unsigned long update_symbol_cache(struct symbol_cache *sc);
 void free_symbol_cache(struct symbol_cache *sc);
@@ -278,7 +278,7 @@ alloc_symbol_cache(const char *sym, long offset)
 {
 	return NULL;
 }
-#endif /* CONFIG_KPROBE_EVENT */
+#endif /* CONFIG_KPROBE_EVENTS */
 
 struct probe_arg {
 	struct fetch_param	fetch;
diff --git a/kernel/ucount.c b/kernel/ucount.c
index 62630a4..b4eeee0 100644
--- a/kernel/ucount.c
+++ b/kernel/ucount.c
@@ -144,7 +144,7 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 
 		new->ns = ns;
 		new->uid = uid;
-		atomic_set(&new->count, 0);
+		new->count = 0;
 
 		spin_lock_irq(&ucounts_lock);
 		ucounts = find_ucounts(ns, uid, hashent);
@@ -155,8 +155,10 @@ static struct ucounts *get_ucounts(struct user_namespace *ns, kuid_t uid)
 			ucounts = new;
 		}
 	}
-	if (!atomic_add_unless(&ucounts->count, 1, INT_MAX))
+	if (ucounts->count == INT_MAX)
 		ucounts = NULL;
+	else
+		ucounts->count += 1;
 	spin_unlock_irq(&ucounts_lock);
 	return ucounts;
 }
@@ -165,13 +167,15 @@ static void put_ucounts(struct ucounts *ucounts)
 {
 	unsigned long flags;
 
-	if (atomic_dec_and_test(&ucounts->count)) {
-		spin_lock_irqsave(&ucounts_lock, flags);
+	spin_lock_irqsave(&ucounts_lock, flags);
+	ucounts->count -= 1;
+	if (!ucounts->count)
 		hlist_del_init(&ucounts->node);
-		spin_unlock_irqrestore(&ucounts_lock, flags);
+	else
+		ucounts = NULL;
+	spin_unlock_irqrestore(&ucounts_lock, flags);
 
-		kfree(ucounts);
-	}
+	kfree(ucounts);
 }
 
 static inline bool atomic_inc_below(atomic_t *v, int u)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 5ed506d..691a9ad 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -2129,8 +2129,8 @@ int ida_pre_get(struct ida *ida, gfp_t gfp)
 		struct ida_bitmap *bitmap = kmalloc(sizeof(*bitmap), gfp);
 		if (!bitmap)
 			return 0;
-		bitmap = this_cpu_cmpxchg(ida_bitmap, NULL, bitmap);
-		kfree(bitmap);
+		if (this_cpu_cmpxchg(ida_bitmap, NULL, bitmap))
+			kfree(bitmap);
 	}
 
 	return 1;
diff --git a/lib/refcount.c b/lib/refcount.c
index 1d33366..aa09ad3 100644
--- a/lib/refcount.c
+++ b/lib/refcount.c
@@ -58,7 +58,7 @@ bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 		val = old;
 	}
 
-	WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
 
 	return true;
 }
@@ -66,7 +66,7 @@ EXPORT_SYMBOL_GPL(refcount_add_not_zero);
 
 void refcount_add(unsigned int i, refcount_t *r)
 {
-	WARN(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_add_not_zero(i, r), "refcount_t: addition on 0; use-after-free.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_add);
 
@@ -97,7 +97,7 @@ bool refcount_inc_not_zero(refcount_t *r)
 		val = old;
 	}
 
-	WARN(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
+	WARN_ONCE(new == UINT_MAX, "refcount_t: saturated; leaking memory.\n");
 
 	return true;
 }
@@ -111,7 +111,7 @@ EXPORT_SYMBOL_GPL(refcount_inc_not_zero);
  */
 void refcount_inc(refcount_t *r)
 {
-	WARN(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
+	WARN_ONCE(!refcount_inc_not_zero(r), "refcount_t: increment on 0; use-after-free.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_inc);
 
@@ -125,7 +125,7 @@ bool refcount_sub_and_test(unsigned int i, refcount_t *r)
 
 		new = val - i;
 		if (new > val) {
-			WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
 			return false;
 		}
 
@@ -164,7 +164,7 @@ EXPORT_SYMBOL_GPL(refcount_dec_and_test);
 
 void refcount_dec(refcount_t *r)
 {
-	WARN(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
+	WARN_ONCE(refcount_dec_and_test(r), "refcount_t: decrement hit 0; leaking memory.\n");
 }
 EXPORT_SYMBOL_GPL(refcount_dec);
 
@@ -204,7 +204,7 @@ bool refcount_dec_not_one(refcount_t *r)
 
 		new = val - 1;
 		if (new > val) {
-			WARN(new > val, "refcount_t: underflow; use-after-free.\n");
+			WARN_ONCE(new > val, "refcount_t: underflow; use-after-free.\n");
 			return true;
 		}
 
diff --git a/scripts/module-common.lds b/scripts/module-common.lds
index cf7e52e..9b6e246 100644
--- a/scripts/module-common.lds
+++ b/scripts/module-common.lds
@@ -22,4 +22,6 @@
 
 	. = ALIGN(8);
 	.init_array		0 : { *(SORT(.init_array.*)) *(.init_array) }
+
+	__jump_table		0 : ALIGN(8) { KEEP(*(__jump_table)) }
 }
diff --git a/tools/objtool/builtin-check.c b/tools/objtool/builtin-check.c
index 4cfdbb5..066086d 100644
--- a/tools/objtool/builtin-check.c
+++ b/tools/objtool/builtin-check.c
@@ -805,11 +805,20 @@ static struct rela *find_switch_table(struct objtool_file *file,
 		     insn->jump_dest->offset > orig_insn->offset))
 		    break;
 
+		/* look for a relocation which references .rodata */
 		text_rela = find_rela_by_dest_range(insn->sec, insn->offset,
 						    insn->len);
-		if (text_rela && text_rela->sym == file->rodata->sym)
-			return find_rela_by_dest(file->rodata,
-						 text_rela->addend);
+		if (!text_rela || text_rela->sym != file->rodata->sym)
+			continue;
+
+		/*
+		 * Make sure the .rodata address isn't associated with a
+		 * symbol.  gcc jump tables are anonymous data.
+		 */
+		if (find_symbol_containing(file->rodata, text_rela->addend))
+			continue;
+
+		return find_rela_by_dest(file->rodata, text_rela->addend);
 	}
 
 	return NULL;
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index 0d7983a..d897702 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -85,6 +85,18 @@ struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset)
 	return NULL;
 }
 
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset)
+{
+	struct symbol *sym;
+
+	list_for_each_entry(sym, &sec->symbol_list, list)
+		if (sym->type != STT_SECTION &&
+		    offset >= sym->offset && offset < sym->offset + sym->len)
+			return sym;
+
+	return NULL;
+}
+
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
 				     unsigned int len)
 {
diff --git a/tools/objtool/elf.h b/tools/objtool/elf.h
index aa1ff65..731973e 100644
--- a/tools/objtool/elf.h
+++ b/tools/objtool/elf.h
@@ -79,6 +79,7 @@ struct elf {
 struct elf *elf_open(const char *name);
 struct section *find_section_by_name(struct elf *elf, const char *name);
 struct symbol *find_symbol_by_offset(struct section *sec, unsigned long offset);
+struct symbol *find_symbol_containing(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest(struct section *sec, unsigned long offset);
 struct rela *find_rela_by_dest_range(struct section *sec, unsigned long offset,
 				     unsigned int len);
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
index 7913363..4f3c758 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
@@ -31,7 +31,7 @@
 #error Instruction buffer size too small
 #endif
 
-/* Based on branch_type() from perf_event_intel_lbr.c */
+/* Based on branch_type() from arch/x86/events/intel/lbr.c */
 static void intel_pt_insn_decoder(struct insn *insn,
 				  struct intel_pt_insn *intel_pt_insn)
 {
diff --git a/tools/testing/radix-tree/Makefile b/tools/testing/radix-tree/Makefile
index f11315b..6a9480c 100644
--- a/tools/testing/radix-tree/Makefile
+++ b/tools/testing/radix-tree/Makefile
@@ -1,6 +1,7 @@
 
 CFLAGS += -I. -I../../include -g -O2 -Wall -D_LGPL_SOURCE -fsanitize=address
-LDFLAGS += -lpthread -lurcu
+LDFLAGS += -fsanitize=address
+LDLIBS+= -lpthread -lurcu
 TARGETS = main idr-test multiorder
 CORE_OFILES := radix-tree.o idr.o linux.o test.o find_bit.o
 OFILES = main.o $(CORE_OFILES) regression1.o regression2.o regression3.o \
@@ -10,23 +11,25 @@
 	SHIFT=3
 endif
 
+ifeq ($(BUILD), 32)
+	CFLAGS += -m32
+	LDFLAGS += -m32
+endif
+
 targets: mapshift $(TARGETS)
 
 main:	$(OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o main
 
 idr-test: idr-test.o $(CORE_OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o idr-test
 
 multiorder: multiorder.o $(CORE_OFILES)
-	$(CC) $(CFLAGS) $(LDFLAGS) $^ -o multiorder
 
 clean:
 	$(RM) $(TARGETS) *.o radix-tree.c idr.c generated/map-shift.h
 
 vpath %.c ../../lib
 
-$(OFILES): *.h */*.h generated/map-shift.h \
+$(OFILES): Makefile *.h */*.h generated/map-shift.h \
 	../../include/linux/*.h \
 	../../include/asm/*.h \
 	../../../include/linux/radix-tree.h \
@@ -41,7 +44,7 @@
 .PHONY: mapshift
 
 mapshift:
-	@if ! grep -qw $(SHIFT) generated/map-shift.h; then		\
+	@if ! grep -qws $(SHIFT) generated/map-shift.h; then		\
 		echo "#define RADIX_TREE_MAP_SHIFT $(SHIFT)" >		\
 				generated/map-shift.h;			\
 	fi
diff --git a/tools/testing/radix-tree/benchmark.c b/tools/testing/radix-tree/benchmark.c
index 9b09ddf..99c40f3 100644
--- a/tools/testing/radix-tree/benchmark.c
+++ b/tools/testing/radix-tree/benchmark.c
@@ -17,6 +17,9 @@
 #include <time.h>
 #include "test.h"
 
+#define for_each_index(i, base, order) \
+	        for (i = base; i < base + (1 << order); i++)
+
 #define NSEC_PER_SEC	1000000000L
 
 static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
@@ -57,27 +60,176 @@ static long long benchmark_iter(struct radix_tree_root *root, bool tagged)
 	return nsec;
 }
 
+static void benchmark_insert(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		item_insert_order(root, index, order);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, insertion: %15lld ns\n",
+		size, step, order, nsec);
+}
+
+static void benchmark_tagging(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		radix_tree_tag_set(root, index, 0);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, tagging: %17lld ns\n",
+		size, step, order, nsec);
+}
+
+static void benchmark_delete(struct radix_tree_root *root,
+			     unsigned long size, unsigned long step, int order)
+{
+	struct timespec start, finish;
+	unsigned long index, i;
+	long long nsec;
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+
+	for (index = 0 ; index < size ; index += step)
+		for_each_index(i, index, order)
+			item_delete(root, i);
+
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	printv(2, "Size: %8ld, step: %8ld, order: %d, deletion: %16lld ns\n",
+		size, step, order, nsec);
+}
+
 static void benchmark_size(unsigned long size, unsigned long step, int order)
 {
 	RADIX_TREE(tree, GFP_KERNEL);
 	long long normal, tagged;
-	unsigned long index;
 
-	for (index = 0 ; index < size ; index += step) {
-		item_insert_order(&tree, index, order);
-		radix_tree_tag_set(&tree, index, 0);
-	}
+	benchmark_insert(&tree, size, step, order);
+	benchmark_tagging(&tree, size, step, order);
 
 	tagged = benchmark_iter(&tree, true);
 	normal = benchmark_iter(&tree, false);
 
-	printv(2, "Size %ld, step %6ld, order %d tagged %10lld ns, normal %10lld ns\n",
-		size, step, order, tagged, normal);
+	printv(2, "Size: %8ld, step: %8ld, order: %d, tagged iteration: %8lld ns\n",
+		size, step, order, tagged);
+	printv(2, "Size: %8ld, step: %8ld, order: %d, normal iteration: %8lld ns\n",
+		size, step, order, normal);
+
+	benchmark_delete(&tree, size, step, order);
 
 	item_kill_tree(&tree);
 	rcu_barrier();
 }
 
+static long long  __benchmark_split(unsigned long index,
+				    int old_order, int new_order)
+{
+	struct timespec start, finish;
+	long long nsec;
+	RADIX_TREE(tree, GFP_ATOMIC);
+
+	item_insert_order(&tree, index, old_order);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	radix_tree_split(&tree, index, new_order);
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+	       (finish.tv_nsec - start.tv_nsec);
+
+	item_kill_tree(&tree);
+
+	return nsec;
+
+}
+
+static void benchmark_split(unsigned long size, unsigned long step)
+{
+	int i, j, idx;
+	long long nsec = 0;
+
+
+	for (idx = 0; idx < size; idx += step) {
+		for (i = 3; i < 11; i++) {
+			for (j = 0; j < i; j++) {
+				nsec += __benchmark_split(idx, i, j);
+			}
+		}
+	}
+
+	printv(2, "Size %8ld, step %8ld, split time %10lld ns\n",
+			size, step, nsec);
+
+}
+
+static long long  __benchmark_join(unsigned long index,
+			     unsigned order1, unsigned order2)
+{
+	unsigned long loc;
+	struct timespec start, finish;
+	long long nsec;
+	void *item, *item2 = item_create(index + 1, order1);
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert_order(&tree, index, order2);
+	item = radix_tree_lookup(&tree, index);
+
+	clock_gettime(CLOCK_MONOTONIC, &start);
+	radix_tree_join(&tree, index + 1, order1, item2);
+	clock_gettime(CLOCK_MONOTONIC, &finish);
+	nsec = (finish.tv_sec - start.tv_sec) * NSEC_PER_SEC +
+		(finish.tv_nsec - start.tv_nsec);
+
+	loc = find_item(&tree, item);
+	if (loc == -1)
+		free(item);
+
+	item_kill_tree(&tree);
+
+	return nsec;
+}
+
+static void benchmark_join(unsigned long step)
+{
+	int i, j, idx;
+	long long nsec = 0;
+
+	for (idx = 0; idx < 1 << 10; idx += step) {
+		for (i = 1; i < 15; i++) {
+			for (j = 0; j < i; j++) {
+				nsec += __benchmark_join(idx, i, j);
+			}
+		}
+	}
+
+	printv(2, "Size %8d, step %8ld, join time %10lld ns\n",
+			1 << 10, step, nsec);
+}
+
 void benchmark(void)
 {
 	unsigned long size[] = {1 << 10, 1 << 20, 0};
@@ -95,4 +247,11 @@ void benchmark(void)
 	for (c = 0; size[c]; c++)
 		for (s = 0; step[s]; s++)
 			benchmark_size(size[c], step[s] << 9, 9);
+
+	for (c = 0; size[c]; c++)
+		for (s = 0; step[s]; s++)
+			benchmark_split(size[c], step[s]);
+
+	for (s = 0; step[s]; s++)
+		benchmark_join(step[s]);
 }
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index a26098c..30cd0b2 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -153,6 +153,30 @@ void idr_nowait_test(void)
 	idr_destroy(&idr);
 }
 
+void idr_get_next_test(void)
+{
+	unsigned long i;
+	int nextid;
+	DEFINE_IDR(idr);
+
+	int indices[] = {4, 7, 9, 15, 65, 128, 1000, 99999, 0};
+
+	for(i = 0; indices[i]; i++) {
+		struct item *item = item_create(indices[i], 0);
+		assert(idr_alloc(&idr, item, indices[i], indices[i+1],
+				 GFP_KERNEL) == indices[i]);
+	}
+
+	for(i = 0, nextid = 0; indices[i]; i++) {
+		idr_get_next(&idr, &nextid);
+		assert(nextid == indices[i]);
+		nextid++;
+	}
+
+	idr_for_each(&idr, item_idr_free, &idr);
+	idr_destroy(&idr);
+}
+
 void idr_checks(void)
 {
 	unsigned long i;
@@ -202,6 +226,7 @@ void idr_checks(void)
 	idr_alloc_test();
 	idr_null_test();
 	idr_nowait_test();
+	idr_get_next_test();
 }
 
 /*
@@ -338,7 +363,7 @@ void ida_check_random(void)
 {
 	DEFINE_IDA(ida);
 	DECLARE_BITMAP(bitmap, 2048);
-	int id;
+	int id, err;
 	unsigned int i;
 	time_t s = time(NULL);
 
@@ -352,8 +377,11 @@ void ida_check_random(void)
 			ida_remove(&ida, bit);
 		} else {
 			__set_bit(bit, bitmap);
-			ida_pre_get(&ida, GFP_KERNEL);
-			assert(!ida_get_new_above(&ida, bit, &id));
+			do {
+				ida_pre_get(&ida, GFP_KERNEL);
+				err = ida_get_new_above(&ida, bit, &id);
+			} while (err == -ENOMEM);
+			assert(!err);
 			assert(id == bit);
 		}
 	}
@@ -362,6 +390,24 @@ void ida_check_random(void)
 		goto repeat;
 }
 
+void ida_simple_get_remove_test(void)
+{
+	DEFINE_IDA(ida);
+	unsigned long i;
+
+	for (i = 0; i < 10000; i++) {
+		assert(ida_simple_get(&ida, 0, 20000, GFP_KERNEL) == i);
+	}
+	assert(ida_simple_get(&ida, 5, 30, GFP_KERNEL) < 0);
+
+	for (i = 0; i < 10000; i++) {
+		ida_simple_remove(&ida, i);
+	}
+	assert(ida_is_empty(&ida));
+
+	ida_destroy(&ida);
+}
+
 void ida_checks(void)
 {
 	DEFINE_IDA(ida);
@@ -428,15 +474,41 @@ void ida_checks(void)
 	ida_check_max();
 	ida_check_conv();
 	ida_check_random();
+	ida_simple_get_remove_test();
 
 	radix_tree_cpu_dead(1);
 }
 
+static void *ida_random_fn(void *arg)
+{
+	rcu_register_thread();
+	ida_check_random();
+	rcu_unregister_thread();
+	return NULL;
+}
+
+void ida_thread_tests(void)
+{
+	pthread_t threads[10];
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(threads); i++)
+		if (pthread_create(&threads[i], NULL, ida_random_fn, NULL)) {
+			perror("creating ida thread");
+			exit(1);
+		}
+
+	while (i--)
+		pthread_join(threads[i], NULL);
+}
+
 int __weak main(void)
 {
 	radix_tree_init();
 	idr_checks();
 	ida_checks();
+	ida_thread_tests();
+	radix_tree_cpu_dead(1);
 	rcu_barrier();
 	if (nr_allocated)
 		printf("nr_allocated = %d\n", nr_allocated);
diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c
index b829127..bc9a784 100644
--- a/tools/testing/radix-tree/main.c
+++ b/tools/testing/radix-tree/main.c
@@ -368,6 +368,7 @@ int main(int argc, char **argv)
 	iteration_test(0, 10 + 90 * long_run);
 	iteration_test(7, 10 + 90 * long_run);
 	single_thread_tests(long_run);
+	ida_thread_tests();
 
 	/* Free any remaining preallocated nodes */
 	radix_tree_cpu_dead(0);
diff --git a/tools/testing/radix-tree/tag_check.c b/tools/testing/radix-tree/tag_check.c
index d4ff009..36dcf7d 100644
--- a/tools/testing/radix-tree/tag_check.c
+++ b/tools/testing/radix-tree/tag_check.c
@@ -330,6 +330,34 @@ static void single_check(void)
 	item_kill_tree(&tree);
 }
 
+void radix_tree_clear_tags_test(void)
+{
+	unsigned long index;
+	struct radix_tree_node *node;
+	struct radix_tree_iter iter;
+	void **slot;
+
+	RADIX_TREE(tree, GFP_KERNEL);
+
+	item_insert(&tree, 0);
+	item_tag_set(&tree, 0, 0);
+	__radix_tree_lookup(&tree, 0, &node, &slot);
+	radix_tree_clear_tags(&tree, node, slot);
+	assert(item_tag_get(&tree, 0, 0) == 0);
+
+	for (index = 0; index < 1000; index++) {
+		item_insert(&tree, index);
+		item_tag_set(&tree, index, 0);
+	}
+
+	radix_tree_for_each_slot(slot, &tree, &iter, 0) {
+		radix_tree_clear_tags(&tree, iter.node, slot);
+		assert(item_tag_get(&tree, iter.index, 0) == 0);
+	}
+
+	item_kill_tree(&tree);
+}
+
 void tag_check(void)
 {
 	single_check();
@@ -347,4 +375,5 @@ void tag_check(void)
 	thrash_tags();
 	rcu_barrier();
 	printv(2, "after thrash_tags: %d allocated\n", nr_allocated);
+	radix_tree_clear_tags_test();
 }
diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h
index b30e11d..0f8220c 100644
--- a/tools/testing/radix-tree/test.h
+++ b/tools/testing/radix-tree/test.h
@@ -36,6 +36,7 @@ void iteration_test(unsigned order, unsigned duration);
 void benchmark(void);
 void idr_checks(void);
 void ida_checks(void);
+void ida_thread_tests(void);
 
 struct item *
 item_tag_set(struct radix_tree_root *root, unsigned long index, int tag);
diff --git a/tools/testing/selftests/powerpc/harness.c b/tools/testing/selftests/powerpc/harness.c
index 248a820..66d31de 100644
--- a/tools/testing/selftests/powerpc/harness.c
+++ b/tools/testing/selftests/powerpc/harness.c
@@ -114,9 +114,11 @@ int test_harness(int (test_function)(void), char *name)
 
 	rc = run_test(test_function, name);
 
-	if (rc == MAGIC_SKIP_RETURN_VALUE)
+	if (rc == MAGIC_SKIP_RETURN_VALUE) {
 		test_skip(name);
-	else
+		/* so that skipped test is not marked as failed */
+		rc = 0;
+	} else
 		test_finish(name, rc);
 
 	return rc;
diff --git a/tools/testing/selftests/x86/fsgsbase.c b/tools/testing/selftests/x86/fsgsbase.c
index 5b2b4b3..b4967d8 100644
--- a/tools/testing/selftests/x86/fsgsbase.c
+++ b/tools/testing/selftests/x86/fsgsbase.c
@@ -245,7 +245,7 @@ void do_unexpected_base(void)
 		long ret;
 		asm volatile ("int $0x80"
 			      : "=a" (ret) : "a" (243), "b" (low_desc)
-			      : "flags");
+			      : "r8", "r9", "r10", "r11");
 		memcpy(&desc, low_desc, sizeof(desc));
 		munmap(low_desc, sizeof(desc));
 
diff --git a/tools/testing/selftests/x86/ldt_gdt.c b/tools/testing/selftests/x86/ldt_gdt.c
index 4af4707..f612161 100644
--- a/tools/testing/selftests/x86/ldt_gdt.c
+++ b/tools/testing/selftests/x86/ldt_gdt.c
@@ -45,6 +45,12 @@
 #define AR_DB			(1 << 22)
 #define AR_G			(1 << 23)
 
+#ifdef __x86_64__
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
+#else
+# define INT80_CLOBBERS
+#endif
+
 static int nerrs;
 
 /* Points to an array of 1024 ints, each holding its own index. */
@@ -588,7 +594,7 @@ static int invoke_set_thread_area(void)
 	asm volatile ("int $0x80"
 		      : "=a" (ret), "+m" (low_user_desc) :
 			"a" (243), "b" (low_user_desc)
-		      : "flags");
+		      : INT80_CLOBBERS);
 	return ret;
 }
 
@@ -657,7 +663,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 	if (sel != 0) {
 		result = "FAIL";
@@ -688,7 +694,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 	if (sel != 0) {
 		result = "FAIL";
@@ -721,7 +727,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
 	syscall(SYS_arch_prctl, ARCH_GET_FS, &new_base);
@@ -774,7 +780,7 @@ static void test_gdt_invalidation(void)
 			"+a" (eax)
 		      : "m" (low_user_desc_clear),
 			[arg1] "r" ((unsigned int)(unsigned long)low_user_desc_clear)
-		      : "flags");
+		      : INT80_CLOBBERS);
 
 #ifdef __x86_64__
 	syscall(SYS_arch_prctl, ARCH_GET_GS, &new_base);
diff --git a/tools/testing/selftests/x86/ptrace_syscall.c b/tools/testing/selftests/x86/ptrace_syscall.c
index b037ce9c..eaea924 100644
--- a/tools/testing/selftests/x86/ptrace_syscall.c
+++ b/tools/testing/selftests/x86/ptrace_syscall.c
@@ -58,7 +58,8 @@ static void do_full_int80(struct syscall_args32 *args)
 	asm volatile ("int $0x80"
 		      : "+a" (args->nr),
 			"+b" (args->arg0), "+c" (args->arg1), "+d" (args->arg2),
-			"+S" (args->arg3), "+D" (args->arg4), "+r" (bp));
+			"+S" (args->arg3), "+D" (args->arg4), "+r" (bp)
+			: : "r8", "r9", "r10", "r11");
 	args->arg5 = bp;
 #else
 	sys32_helper(args, int80_and_ret);
diff --git a/tools/testing/selftests/x86/single_step_syscall.c b/tools/testing/selftests/x86/single_step_syscall.c
index 50c2635..a48da95 100644
--- a/tools/testing/selftests/x86/single_step_syscall.c
+++ b/tools/testing/selftests/x86/single_step_syscall.c
@@ -56,9 +56,11 @@ static volatile sig_atomic_t sig_traps;
 #ifdef __x86_64__
 # define REG_IP REG_RIP
 # define WIDTH "q"
+# define INT80_CLOBBERS "r8", "r9", "r10", "r11"
 #else
 # define REG_IP REG_EIP
 # define WIDTH "l"
+# define INT80_CLOBBERS
 #endif
 
 static unsigned long get_eflags(void)
@@ -140,7 +142,8 @@ int main()
 
 	printf("[RUN]\tSet TF and check int80\n");
 	set_eflags(get_eflags() | X86_EFLAGS_TF);
-	asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid));
+	asm volatile ("int $0x80" : "=a" (tmp) : "a" (SYS_getpid)
+			: INT80_CLOBBERS);
 	check_result();
 
 	/*