Merge branch 'next/cleanup-plat-s3c24xx' into next/cleanup-plat-s3c24xx-s5p

65 files changed, 739 insertions, 553 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 1d14cc6b79ad..c9866b0b77d8 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -81,7 +81,7 @@ config X86
 	select CLKEVT_I8253
 	select ARCH_HAVE_NMI_SAFE_CMPXCHG
 	select GENERIC_IOMAP
-	select DCACHE_WORD_ACCESS if !DEBUG_PAGEALLOC
+	select DCACHE_WORD_ACCESS
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 968dbe24a255..41a7237606a3 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -129,6 +129,7 @@ KBUILD_CFLAGS += -Wno-sign-compare
 KBUILD_CFLAGS += -fno-asynchronous-unwind-tables
 # prevent gcc from generating any FP code by mistake
 KBUILD_CFLAGS += $(call cc-option,-mno-sse -mno-mmx -mno-sse2 -mno-3dnow,)
+KBUILD_CFLAGS += $(call cc-option,-mno-avx,)
 
 KBUILD_CFLAGS += $(mflags-y)
 KBUILD_AFLAGS += $(mflags-y)
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 4be406abeefd..36b62bc52638 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -14,6 +14,9 @@ LINK-y			+= $(call cc-option,-m32)
 
 export LDFLAGS
 
+LDS_EXTRA		:= -Ui386
+export LDS_EXTRA
+
 # First of all, tune CFLAGS for the specific CPU. This actually sets cflags-y.
 include $(srctree)/arch/x86/Makefile_32.cpu
 
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index a0559930a180..c85e3ac99bba 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -33,6 +33,9 @@
 	__HEAD
 ENTRY(startup_32)
 #ifdef CONFIG_EFI_STUB
+	jmp	preferred_addr
+
+	.balign	0x10
 	/*
 	 * We don't need the return address, so set up the stack so
 	 * efi_main() can find its arugments.
@@ -41,12 +44,17 @@ ENTRY(startup_32)
 
 	call	efi_main
 	cmpl	$0, %eax
-	je	preferred_addr
 	movl	%eax, %esi
-	call	1f
+	jne	2f
 1:
+	/* EFI init failed, so hang. */
+	hlt
+	jmp	1b
+2:
+	call	3f
+3:
 	popl	%eax
-	subl	$1b, %eax
+	subl	$3b, %eax
 	subl	BP_pref_address(%esi), %eax
 	add	BP_code32_start(%esi), %eax
 	leal	preferred_addr(%eax), %eax
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 558d76ce23bc..87e03a13d8e3 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -200,18 +200,28 @@ ENTRY(startup_64)
 	 * entire text+data+bss and hopefully all of memory.
 	 */
 #ifdef CONFIG_EFI_STUB
-	pushq	%rsi
+	/*
+	 * The entry point for the PE/COFF executable is 0x210, so only
+	 * legacy boot loaders will execute this jmp.
+	 */
+	jmp	preferred_addr
+
+	.org 0x210
 	mov	%rcx, %rdi
 	mov	%rdx, %rsi
 	call	efi_main
-	popq	%rsi
-	cmpq	$0,%rax
-	je	preferred_addr
 	movq	%rax,%rsi
-	call	1f
+	cmpq	$0,%rax
+	jne	2f
 1:
+	/* EFI init failed, so hang. */
+	hlt
+	jmp	1b
+2:
+	call	3f
+3:
 	popq	%rax
-	subq	$1b, %rax
+	subq	$3b, %rax
 	subq	BP_pref_address(%rsi), %rax
 	add	BP_code32_start(%esi), %eax
 	leaq	preferred_addr(%rax), %rax
diff --git a/arch/x86/boot/compressed/relocs.c b/arch/x86/boot/compressed/relocs.c
index d3c0b0277666..fb7117a4ade1 100644
--- a/arch/x86/boot/compressed/relocs.c
+++ b/arch/x86/boot/compressed/relocs.c
@@ -403,13 +403,11 @@ static void print_absolute_symbols(void)
 	for (i = 0; i < ehdr.e_shnum; i++) {
 		struct section *sec = &secs[i];
 		char *sym_strtab;
-		Elf32_Sym *sh_symtab;
 		int j;
 
 		if (sec->shdr.sh_type != SHT_SYMTAB) {
 			continue;
 		}
-		sh_symtab = sec->symtab;
 		sym_strtab = sec->link->strtab;
 		for (j = 0; j < sec->shdr.sh_size/sizeof(Elf32_Sym); j++) {
 			Elf32_Sym *sym;
diff --git a/arch/x86/boot/tools/build.c b/arch/x86/boot/tools/build.c
index ed549767a231..24443a332083 100644
--- a/arch/x86/boot/tools/build.c
+++ b/arch/x86/boot/tools/build.c
@@ -205,8 +205,13 @@ int main(int argc, char ** argv)
 	put_unaligned_le32(file_sz, &buf[pe_header + 0x50]);
 
 #ifdef CONFIG_X86_32
-	/* Address of entry point */
-	put_unaligned_le32(i, &buf[pe_header + 0x28]);
+	/*
+	 * Address of entry point.
+	 *
+	 * The EFI stub entry point is +16 bytes from the start of
+	 * the .text section.
+	 */
+	put_unaligned_le32(i + 16, &buf[pe_header + 0x28]);
 
 	/* .text size */
 	put_unaligned_le32(file_sz, &buf[pe_header + 0xb0]);
@@ -217,9 +222,11 @@ int main(int argc, char ** argv)
 	/*
 	 * Address of entry point. startup_32 is at the beginning and
 	 * the 64-bit entry point (startup_64) is always 512 bytes
-	 * after.
+	 * after. The EFI stub entry point is 16 bytes after that, as
+	 * the first instruction allows legacy loaders to jump over
+	 * the EFI stub initialisation
 	 */
-	put_unaligned_le32(i + 512, &buf[pe_header + 0x28]);
+	put_unaligned_le32(i + 528, &buf[pe_header + 0x28]);
 
 	/* .text size */
 	put_unaligned_le32(file_sz, &buf[pe_header + 0xc0]);
diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c
index d511d951a052..07b3a68d2d29 100644
--- a/arch/x86/ia32/ia32_aout.c
+++ b/arch/x86/ia32/ia32_aout.c
@@ -119,9 +119,7 @@ static void set_brk(unsigned long start, unsigned long end)
 	end = PAGE_ALIGN(end);
 	if (end <= start)
 		return;
-	down_write(&current->mm->mmap_sem);
-	do_brk(start, end - start);
-	up_write(&current->mm->mmap_sem);
+	vm_brk(start, end - start);
 }
 
 #ifdef CORE_DUMP
@@ -296,8 +294,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 
 	/* OK, This is the point of no return */
 	set_personality(PER_LINUX);
-	set_thread_flag(TIF_IA32);
-	current->mm->context.ia32_compat = 1;
+	set_personality_ia32(false);
 
 	setup_new_exec(bprm);
 
@@ -332,9 +329,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		pos = 32;
 		map_size = ex.a_text+ex.a_data;
 
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(text_addr & PAGE_MASK, map_size);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(text_addr & PAGE_MASK, map_size);
 
 		if (error != (text_addr & PAGE_MASK)) {
 			send_sig(SIGKILL, current, 0);
@@ -373,9 +368,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		if (!bprm->file->f_op->mmap || (fd_offset & ~PAGE_MASK) != 0) {
 			loff_t pos = fd_offset;
 
-			down_write(&current->mm->mmap_sem);
-			do_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
-			up_write(&current->mm->mmap_sem);
+			vm_brk(N_TXTADDR(ex), ex.a_text+ex.a_data);
 			bprm->file->f_op->read(bprm->file,
 					(char __user *)N_TXTADDR(ex),
 					ex.a_text+ex.a_data, &pos);
@@ -385,26 +378,22 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			goto beyond_if;
 		}
 
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
+		error = vm_mmap(bprm->file, N_TXTADDR(ex), ex.a_text,
 				PROT_READ | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset);
-		up_write(&current->mm->mmap_sem);
 
 		if (error != N_TXTADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
 		}
 
-		down_write(&current->mm->mmap_sem);
-		error = do_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
+		error = vm_mmap(bprm->file, N_DATADDR(ex), ex.a_data,
 				PROT_READ | PROT_WRITE | PROT_EXEC,
 				MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE |
 				MAP_EXECUTABLE | MAP_32BIT,
 				fd_offset + ex.a_text);
-		up_write(&current->mm->mmap_sem);
 		if (error != N_DATADDR(ex)) {
 			send_sig(SIGKILL, current, 0);
 			return error;
@@ -476,9 +465,7 @@ static int load_aout_library(struct file *file)
 			error_time = jiffies;
 		}
 #endif
-		down_write(&current->mm->mmap_sem);
-		do_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
-		up_write(&current->mm->mmap_sem);
+		vm_brk(start_addr, ex.a_text + ex.a_data + ex.a_bss);
 
 		file->f_op->read(file, (char __user *)start_addr,
 			ex.a_text + ex.a_data, &pos);
@@ -490,12 +477,10 @@ static int load_aout_library(struct file *file)
 		goto out;
 	}
 	/* Now use mmap to map the library into memory. */
-	down_write(&current->mm->mmap_sem);
-	error = do_mmap(file, start_addr, ex.a_text + ex.a_data,
+	error = vm_mmap(file, start_addr, ex.a_text + ex.a_data,
 			PROT_READ | PROT_WRITE | PROT_EXEC,
 			MAP_FIXED | MAP_PRIVATE | MAP_DENYWRITE | MAP_32BIT,
 			N_TXTOFF(ex));
-	up_write(&current->mm->mmap_sem);
 	retval = error;
 	if (error != start_addr)
 		goto out;
@@ -503,9 +488,7 @@ static int load_aout_library(struct file *file)
 	len = PAGE_ALIGN(ex.a_text + ex.a_data);
 	bss = ex.a_text + ex.a_data + ex.a_bss;
 	if (bss > len) {
-		down_write(&current->mm->mmap_sem);
-		error = do_brk(start_addr + len, bss - len);
-		up_write(&current->mm->mmap_sem);
+		error = vm_brk(start_addr + len, bss - len);
 		retval = error;
 		if (error != start_addr + len)
 			goto out;
diff --git a/arch/x86/include/asm/cmpxchg.h b/arch/x86/include/asm/cmpxchg.h
index b3b733262909..99480e55973d 100644
--- a/arch/x86/include/asm/cmpxchg.h
+++ b/arch/x86/include/asm/cmpxchg.h
@@ -43,7 +43,7 @@ extern void __add_wrong_size(void)
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
 			asm volatile (lock #op "b %b0, %1\n"		\
-				      : "+r" (__ret), "+m" (*(ptr))	\
+				      : "+q" (__ret), "+m" (*(ptr))	\
 				      : : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
@@ -173,7 +173,7 @@ extern void __add_wrong_size(void)
 		switch (sizeof(*(ptr))) {				\
 		case __X86_CASE_B:					\
 			asm volatile (lock "addb %b1, %0\n"		\
-				      : "+m" (*(ptr)) : "ri" (inc)	\
+				      : "+m" (*(ptr)) : "qi" (inc)	\
 				      : "memory", "cc");		\
 			break;						\
 		case __X86_CASE_W:					\
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index ed3065fd6314..4b4331d71935 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -59,7 +59,8 @@ extern int dma_supported(struct device *hwdev, u64 mask);
 extern int dma_set_mask(struct device *dev, u64 mask);
 
 extern void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-					dma_addr_t *dma_addr, gfp_t flag);
+					dma_addr_t *dma_addr, gfp_t flag,
+					struct dma_attrs *attrs);
 
 static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size)
 {
@@ -111,9 +112,11 @@ static inline gfp_t dma_alloc_coherent_gfp_flags(struct device *dev, gfp_t gfp)
        return gfp;
 }
 
+#define dma_alloc_coherent(d,s,h,f)	dma_alloc_attrs(d,s,h,f,NULL)
+
 static inline void *
-dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
-		gfp_t gfp)
+dma_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+		gfp_t gfp, struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 	void *memory;
@@ -129,18 +132,21 @@ dma_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_handle,
 	if (!is_device_dma_capable(dev))
 		return NULL;
 
-	if (!ops->alloc_coherent)
+	if (!ops->alloc)
 		return NULL;
 
-	memory = ops->alloc_coherent(dev, size, dma_handle,
-				     dma_alloc_coherent_gfp_flags(dev, gfp));
+	memory = ops->alloc(dev, size, dma_handle,
+			    dma_alloc_coherent_gfp_flags(dev, gfp), attrs);
 	debug_dma_alloc_coherent(dev, size, *dma_handle, memory);
 
 	return memory;
 }
 
-static inline void dma_free_coherent(struct device *dev, size_t size,
-				     void *vaddr, dma_addr_t bus)
+#define dma_free_coherent(d,s,c,h) dma_free_attrs(d,s,c,h,NULL)
+
+static inline void dma_free_attrs(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t bus,
+				  struct dma_attrs *attrs)
 {
 	struct dma_map_ops *ops = get_dma_ops(dev);
 
@@ -150,8 +156,8 @@ static inline void dma_free_coherent(struct device *dev, size_t size,
 		return;
 
 	debug_dma_free_coherent(dev, size, vaddr, bus);
-	if (ops->free_coherent)
-		ops->free_coherent(dev, size, vaddr, bus);
+	if (ops->free)
+		ops->free(dev, size, vaddr, bus, attrs);
 }
 
 #endif
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
index 3427b7798dbc..7ef7c3020e5c 100644
--- a/arch/x86/include/asm/posix_types.h
+++ b/arch/x86/include/asm/posix_types.h
@@ -7,9 +7,9 @@
 #else
 # ifdef __i386__
 #  include "posix_types_32.h"
-# elif defined(__LP64__)
-#  include "posix_types_64.h"
-# else
+# elif defined(__ILP32__)
 #  include "posix_types_x32.h"
+# else
+#  include "posix_types_64.h"
 # endif
 #endif
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 7284c9a6a0b5..4fa7dcceb6c0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -974,16 +974,6 @@ extern bool cpu_has_amd_erratum(const int *);
 #define cpu_has_amd_erratum(x)	(false)
 #endif /* CONFIG_CPU_SUP_AMD */
 
-#ifdef CONFIG_X86_32
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#endif
-
-void disable_hlt(void);
-void enable_hlt(void);
-
 void cpu_idle_wait(void);
 
 extern unsigned long arch_align_stack(unsigned long sp);
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 4a085383af27..5ca71c065eef 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -257,7 +257,7 @@ struct sigcontext {
 	__u64 oldmask;
 	__u64 cr2;
 	struct _fpstate __user *fpstate;	/* zero when no FPU context */
-#ifndef __LP64__
+#ifdef __ILP32__
 	__u32 __fpstate_pad;
 #endif
 	__u64 reserved1[8];
diff --git a/arch/x86/include/asm/siginfo.h b/arch/x86/include/asm/siginfo.h
index fc1aa5535646..34c47b3341c0 100644
--- a/arch/x86/include/asm/siginfo.h
+++ b/arch/x86/include/asm/siginfo.h
@@ -2,7 +2,13 @@
 #define _ASM_X86_SIGINFO_H
 
 #ifdef __x86_64__
-# define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
+# ifdef __ILP32__ /* x32 */
+typedef long long __kernel_si_clock_t __attribute__((aligned(4)));
+#  define __ARCH_SI_CLOCK_T		__kernel_si_clock_t
+#  define __ARCH_SI_ATTRIBUTES		__attribute__((aligned(8)))
+# else /* x86-64 */
+#  define __ARCH_SI_PREAMBLE_SIZE	(4 * sizeof(int))
+# endif
 #endif
 
 #include <asm-generic/siginfo.h>
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 8be5f54d9360..e0544597cfe7 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -557,6 +557,8 @@ struct __large_struct { unsigned long buf[100]; };
 
 extern unsigned long
 copy_from_user_nmi(void *to, const void __user *from, unsigned long n);
+extern __must_check long
+strncpy_from_user(char *dst, const char __user *src, long count);
 
 /*
  * movsl can be slow when source and dest are not both 8-byte aligned
diff --git a/arch/x86/include/asm/uaccess_32.h b/arch/x86/include/asm/uaccess_32.h
index 566e803cc602..8084bc73b18c 100644
--- a/arch/x86/include/asm/uaccess_32.h
+++ b/arch/x86/include/asm/uaccess_32.h
@@ -213,11 +213,6 @@ static inline unsigned long __must_check copy_from_user(void *to,
 	return n;
 }
 
-long __must_check strncpy_from_user(char *dst, const char __user *src,
-				    long count);
-long __must_check __strncpy_from_user(char *dst,
-				      const char __user *src, long count);
-
 /**
  * strlen_user: - Get the size of a string in user space.
  * @str: The string to measure.
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 1c66d30971ad..fcd4b6f3ef02 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -208,10 +208,6 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
 	}
 }
 
-__must_check long
-strncpy_from_user(char *dst, const char __user *src, long count);
-__must_check long
-__strncpy_from_user(char *dst, const char __user *src, long count);
 __must_check long strnlen_user(const char __user *str, long n);
 __must_check long __strnlen_user(const char __user *str, long n);
 __must_check long strlen_user(const char __user *str);
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 37cdc9d99bb1..4437001d8e3d 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -63,10 +63,10 @@
 #else
 # ifdef __i386__
 #  include <asm/unistd_32.h>
-# elif defined(__LP64__)
-#  include <asm/unistd_64.h>
-# else
+# elif defined(__ILP32__)
 #  include <asm/unistd_x32.h>
+# else
+#  include <asm/unistd_64.h>
 # endif
 #endif
 
diff --git a/arch/x86/include/asm/word-at-a-time.h b/arch/x86/include/asm/word-at-a-time.h
new file mode 100644
index 000000000000..e58f03b206c3
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,79 @@
+#ifndef _ASM_WORD_AT_A_TIME_H
+#define _ASM_WORD_AT_A_TIME_H
+
+/*
+ * This is largely generic for little-endian machines, but the
+ * optimal byte mask counting is probably going to be something
+ * that is architecture-specific. If you have a reliably fast
+ * bit count instruction, that might be better than the multiply
+ * and shift, for example.
+ */
+
+#ifdef CONFIG_64BIT
+
+/*
+ * Jan Achrenius on G+: microoptimized version of
+ * the simpler "(mask & ONEBYTES) * ONEBYTES >> 56"
+ * that works for the bytemasks without having to
+ * mask them first.
+ */
+static inline long count_masked_bytes(unsigned long mask)
+{
+	return mask*0x0001020304050608ul >> 56;
+}
+
+#else	/* 32-bit case */
+
+/* Carl Chatfield / Jan Achrenius G+ version for 32-bit */
+static inline long count_masked_bytes(long mask)
+{
+	/* (000000 0000ff 00ffff ffffff) -> ( 1 1 2 3 ) */
+	long a = (0x0ff0001+mask) >> 23;
+	/* Fix the 1 for 00 case */
+	return a & mask;
+}
+
+#endif
+
+#define REPEAT_BYTE(x)	((~0ul / 0xff) * (x))
+
+/* Return the high bit set in the first byte that is a zero */
+static inline unsigned long has_zero(unsigned long a)
+{
+	return ((a - REPEAT_BYTE(0x01)) & ~a) & REPEAT_BYTE(0x80);
+}
+
+/*
+ * Load an unaligned word from kernel space.
+ *
+ * In the (very unlikely) case of the word being a page-crosser
+ * and the next page not being mapped, take the exception and
+ * return zeroes in the non-existing part.
+ */
+static inline unsigned long load_unaligned_zeropad(const void *addr)
+{
+	unsigned long ret, dummy;
+
+	asm(
+		"1:\tmov %2,%0\n"
+		"2:\n"
+		".section .fixup,\"ax\"\n"
+		"3:\t"
+		"lea %2,%1\n\t"
+		"and %3,%1\n\t"
+		"mov (%1),%0\n\t"
+		"leal %2,%%ecx\n\t"
+		"andl %4,%%ecx\n\t"
+		"shll $3,%%ecx\n\t"
+		"shr %%cl,%0\n\t"
+		"jmp 2b\n"
+		".previous\n"
+		_ASM_EXTABLE(1b, 3b)
+		:"=&r" (ret),"=&c" (dummy)
+		:"m" (*(unsigned long *)addr),
+		 "i" (-sizeof(unsigned long)),
+		 "i" (sizeof(unsigned long)-1));
+	return ret;
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index baaca8defec8..764b66a4cf89 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -195,6 +195,5 @@ extern struct x86_msi_ops x86_msi;
 
 extern void x86_init_noop(void);
 extern void x86_init_uint_noop(unsigned int unused);
-extern void x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node);
 
 #endif
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 103b6ab368d3..146a49c763a4 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -24,6 +24,10 @@ unsigned long acpi_realmode_flags;
 static char temp_stack[4096];
 #endif
 
+asmlinkage void acpi_enter_s3(void)
+{
+	acpi_enter_sleep_state(3, wake_sleep_flags);
+}
 /**
  * acpi_suspend_lowlevel - save kernel state
  *
diff --git a/arch/x86/kernel/acpi/sleep.h b/arch/x86/kernel/acpi/sleep.h
index 416d4be13fef..d68677a2a010 100644
--- a/arch/x86/kernel/acpi/sleep.h
+++ b/arch/x86/kernel/acpi/sleep.h
@@ -3,12 +3,16 @@
  */
 
 #include <asm/trampoline.h>
+#include <linux/linkage.h>
 
 extern unsigned long saved_video_mode;
 extern long saved_magic;
 
 extern int wakeup_pmode_return;
 
+extern u8 wake_sleep_flags;
+extern asmlinkage void acpi_enter_s3(void);
+
 extern unsigned long acpi_copy_wakeup_routine(unsigned long);
 extern void wakeup_long64(void);
 
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index 13ab720573e3..72610839f03b 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -74,9 +74,7 @@ restore_registers:
 ENTRY(do_suspend_lowlevel)
 	call	save_processor_state
 	call	save_registers
-	pushl	$3
-	call	acpi_enter_sleep_state
-	addl	$4, %esp
+	call	acpi_enter_s3
 
 #	In case of S3 failure, we'll emerge here.  Jump
 # 	to ret_point to recover
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 8ea5164cbd04..014d1d28c397 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -71,9 +71,7 @@ ENTRY(do_suspend_lowlevel)
 	movq	%rsi, saved_rsi
 
 	addq	$8, %rsp
-	movl	$3, %edi
-	xorl	%eax, %eax
-	call	acpi_enter_sleep_state
+	call	acpi_enter_s3
 	/* in case something went wrong, restore the machine status and go on */
 	jmp	resume_point
 
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index b1e7c7f7a0af..e66311200cbd 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -477,7 +477,7 @@ error:
 /* allocate and map a coherent mapping */
 static void *
 gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
-		    gfp_t flag)
+		    gfp_t flag, struct dma_attrs *attrs)
 {
 	dma_addr_t paddr;
 	unsigned long align_mask;
@@ -500,7 +500,8 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 		}
 		__free_pages(page, get_order(size));
 	} else
-		return dma_generic_alloc_coherent(dev, size, dma_addr, flag);
+		return dma_generic_alloc_coherent(dev, size, dma_addr, flag,
+						  attrs);
 
 	return NULL;
 }
@@ -508,7 +509,7 @@ gart_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr,
 /* free a coherent mapping */
 static void
 gart_free_coherent(struct device *dev, size_t size, void *vaddr,
-		   dma_addr_t dma_addr)
+		   dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL);
 	free_pages((unsigned long)vaddr, get_order(size));
@@ -700,8 +701,8 @@ static struct dma_map_ops gart_dma_ops = {
 	.unmap_sg			= gart_unmap_sg,
 	.map_page			= gart_map_page,
 	.unmap_page			= gart_unmap_page,
-	.alloc_coherent			= gart_alloc_coherent,
-	.free_coherent			= gart_free_coherent,
+	.alloc				= gart_alloc_coherent,
+	.free				= gart_free_coherent,
 	.mapping_error			= gart_mapping_error,
 };
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 11544d8f1e97..edc24480469f 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1637,9 +1637,11 @@ static int __init apic_verify(void)
 	mp_lapic_addr = APIC_DEFAULT_PHYS_BASE;
 
 	/* The BIOS may have set up the APIC at some other address */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (l & MSR_IA32_APICBASE_ENABLE)
-		mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (l & MSR_IA32_APICBASE_ENABLE)
+			mp_lapic_addr = l & MSR_IA32_APICBASE_BASE;
+	}
 
 	pr_info("Found and enabled local APIC!\n");
 	return 0;
@@ -1657,13 +1659,15 @@ int __init apic_force_enable(unsigned long addr)
 	 * MSR. This can only be done in software for Intel P6 or later
 	 * and AMD K7 (Model > 1) or later.
 	 */
-	rdmsr(MSR_IA32_APICBASE, l, h);
-	if (!(l & MSR_IA32_APICBASE_ENABLE)) {
-		pr_info("Local APIC disabled by BIOS -- reenabling.\n");
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
-		enabled_via_apicbase = 1;
+	if (boot_cpu_data.x86 >= 6) {
+		rdmsr(MSR_IA32_APICBASE, l, h);
+		if (!(l & MSR_IA32_APICBASE_ENABLE)) {
+			pr_info("Local APIC disabled by BIOS -- reenabling.\n");
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+			enabled_via_apicbase = 1;
+		}
 	}
 	return apic_verify();
 }
@@ -2209,10 +2213,12 @@ static void lapic_resume(void)
 		 * FIXME! This will be wrong if we ever support suspend on
 		 * SMP! We'll need to do this as part of the CPU restore!
 		 */
-		rdmsr(MSR_IA32_APICBASE, l, h);
-		l &= ~MSR_IA32_APICBASE_BASE;
-		l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
-		wrmsr(MSR_IA32_APICBASE, l, h);
+		if (boot_cpu_data.x86 >= 6) {
+			rdmsr(MSR_IA32_APICBASE, l, h);
+			l &= ~MSR_IA32_APICBASE_BASE;
+			l |= MSR_IA32_APICBASE_ENABLE | mp_lapic_addr;
+			wrmsr(MSR_IA32_APICBASE, l, h);
+		}
 	}
 
 	maxlvt = lapic_get_maxlvt();
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 899803e03214..23e75422e013 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -207,8 +207,11 @@ static void __init map_csrs(void)
 
 static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
 {
-	c->phys_proc_id = node;
-	per_cpu(cpu_llc_id, smp_processor_id()) = node;
+
+	if (c->phys_proc_id != node) {
+		c->phys_proc_id = node;
+		per_cpu(cpu_llc_id, smp_processor_id()) = node;
+	}
 }
 
 static int __init numachip_system_init(void)
diff --git a/arch/x86/kernel/apic/x2apic_phys.c b/arch/x86/kernel/apic/x2apic_phys.c
index 8a778db45e3a..991e315f4227 100644
--- a/arch/x86/kernel/apic/x2apic_phys.c
+++ b/arch/x86/kernel/apic/x2apic_phys.c
@@ -24,6 +24,12 @@ static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
 	if (x2apic_phys)
 		return x2apic_enabled();
+	else if ((acpi_gbl_FADT.header.revision >= FADT2_REVISION_ID) &&
+		(acpi_gbl_FADT.flags & ACPI_FADT_APIC_PHYSICAL) &&
+		x2apic_enabled()) {
+		printk(KERN_DEBUG "System requires x2apic physical mode\n");
+		return 1;
+	}
 	else
 		return 0;
 }
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 0a44b90602b0..146bb6218eec 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -26,7 +26,8 @@
  *	contact AMD for precise details and a CPU swap.
  *
  *	See	http://www.multimania.com/poulot/k6bug.html
- *		http://www.amd.com/K6/k6docs/revgd.html
+ *	and	section 2.6.2 of "AMD-K6 Processor Revision Guide - Model 6"
+ *		(Publication # 21266  Issue Date: August 1998)
  *
  *	The following test is erm.. interesting. AMD neglected to up
  *	the chip setting when fixing the bug but they also tweaked some
@@ -94,7 +95,6 @@ static void __cpuinit init_amd_k6(struct cpuinfo_x86 *c)
 				"system stability may be impaired when more than 32 MB are used.\n");
 		else
 			printk(KERN_CONT "probably OK (after B9730xxxx).\n");
-		printk(KERN_INFO "Please see http://membres.lycos.fr/poulot/k6bug.html\n");
 	}
 
 	/* K6 with old style WHCR */
@@ -353,10 +353,11 @@ static void __cpuinit srat_detect_node(struct cpuinfo_x86 *c)
 		node = per_cpu(cpu_llc_id, cpu);
 
 	/*
-	 * If core numbers are inconsistent, it's likely a multi-fabric platform,
-	 * so invoke platform-specific handler
+	 * On multi-fabric platform (e.g. Numascale NumaChip) a
+	 * platform-specific handler needs to be called to fixup some
+	 * IDs of the CPU.
 	 */
-	if (c->phys_proc_id != node)
+	if (x86_cpuinit.fixup_cpu_id)
 		x86_cpuinit.fixup_cpu_id(c, node);
 
 	if (!node_online(node)) {
@@ -579,6 +580,24 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c)
 		}
 	}
 
+	/* re-enable TopologyExtensions if switched off by BIOS */
+	if ((c->x86 == 0x15) &&
+	    (c->x86_model >= 0x10) && (c->x86_model <= 0x1f) &&
+	    !cpu_has(c, X86_FEATURE_TOPOEXT)) {
+		u64 val;
+
+		if (!rdmsrl_amd_safe(0xc0011005, &val)) {
+			val |= 1ULL << 54;
+			wrmsrl_amd_safe(0xc0011005, val);
+			rdmsrl(0xc0011005, val);
+			if (val & (1ULL << 54)) {
+				set_cpu_cap(c, X86_FEATURE_TOPOEXT);
+				printk(KERN_INFO FW_INFO "CPU: Re-enabling "
+				  "disabled Topology Extensions Support\n");
+			}
+		}
+	}
+
 	cpu_detect_cache_sizes(c);
 
 	/* Multi core CPU? */
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 67e258362a3d..cf79302198a6 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1163,15 +1163,6 @@ static void dbg_restore_debug_regs(void)
 #endif /* ! CONFIG_KGDB */
 
 /*
- * Prints an error where the NUMA and configured core-number mismatch and the
- * platform didn't override this to fix it up
- */
-void __cpuinit x86_default_fixup_cpu_id(struct cpuinfo_x86 *c, int node)
-{
-	pr_err("NUMA core number %d differs from configured core number %d\n", node, c->phys_proc_id);
-}
-
-/*
  * cpu_init() initializes state that is per-CPU. Some data is already
  * initialized (naturally) in the bootstrap process, such as the GDT
  * and IDT. We reload them nevertheless, this function acts as a
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 73d08ed98a64..b8f3653dddbc 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -433,14 +433,14 @@ int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot,
 	/*  check if @slot is already used or the index is already disabled */
 	ret = amd_get_l3_disable_slot(nb, slot);
 	if (ret >= 0)
-		return -EINVAL;
+		return -EEXIST;
 
 	if (index > nb->l3_cache.indices)
 		return -EINVAL;
 
 	/* check whether the other slot has disabled the same index already */
 	if (index == amd_get_l3_disable_slot(nb, !slot))
-		return -EINVAL;
+		return -EEXIST;
 
 	amd_l3_disable_index(nb, cpu, slot, index);
 
@@ -468,8 +468,8 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
 	err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val);
 	if (err) {
 		if (err == -EEXIST)
-			printk(KERN_WARNING "L3 disable slot %d in use!\n",
-					    slot);
+			pr_warning("L3 slot %d in use/index already disabled!\n",
+				   slot);
 		return err;
 	}
 	return count;
diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index ef484d9d0a25..a2dfacfd7103 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -1271,6 +1271,17 @@ done:
 	return num ? -EINVAL : 0;
 }
 
+PMU_FORMAT_ATTR(cccr, "config:0-31" );
+PMU_FORMAT_ATTR(escr, "config:32-62");
+PMU_FORMAT_ATTR(ht,   "config:63"   );
+
+static struct attribute *intel_p4_formats_attr[] = {
+	&format_attr_cccr.attr,
+	&format_attr_escr.attr,
+	&format_attr_ht.attr,
+	NULL,
+};
+
 static __initconst const struct x86_pmu p4_pmu = {
 	.name			= "Netburst P4/Xeon",
 	.handle_irq		= p4_pmu_handle_irq,
@@ -1305,6 +1316,8 @@ static __initconst const struct x86_pmu p4_pmu = {
 	 * the former idea is taken from OProfile code
 	 */
 	.perfctr_second_write	= 1,
+
+	.format_attrs		= intel_p4_formats_attr,
 };
 
 __init int p4_pmu_init(void)
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index 7734bcbb5a3a..2d6e6498c176 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -235,6 +235,7 @@ int init_fpu(struct task_struct *tsk)
 	if (tsk_used_math(tsk)) {
 		if (HAVE_HWFP && tsk == current)
 			unlazy_fpu(tsk);
+		tsk->thread.fpu.last_cpu = ~0;
 		return 0;
 	}
 
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 7943e0c21bde..3dafc6003b7c 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -282,8 +282,13 @@ void fixup_irqs(void)
 		else if (!(warned++))
 			set_affinity = 0;
 
+		/*
+		 * We unmask if the irq was not marked masked by the
+		 * core code. That respects the lazy irq disable
+		 * behaviour.
+		 */
 		if (!irqd_can_move_in_process_context(data) &&
-		    !irqd_irq_disabled(data) && chip->irq_unmask)
+		    !irqd_irq_masked(data) && chip->irq_unmask)
 			chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
diff --git a/arch/x86/kernel/kdebugfs.c b/arch/x86/kernel/kdebugfs.c
index 90fcf62854bb..1d5d31ea686b 100644
--- a/arch/x86/kernel/kdebugfs.c
+++ b/arch/x86/kernel/kdebugfs.c
@@ -68,16 +68,9 @@ static ssize_t setup_data_read(struct file *file, char __user *user_buf,
 	return count;
 }
 
-static int setup_data_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-
-	return 0;
-}
-
 static const struct file_operations fops_setup_data = {
 	.read		= setup_data_read,
-	.open		= setup_data_open,
+	.open		= simple_open,
 	.llseek		= default_llseek,
 };
 
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index db6720edfdd0..8bfb6146f753 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -43,6 +43,8 @@
 #include <linux/smp.h>
 #include <linux/nmi.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/uaccess.h>
+#include <linux/memory.h>
 
 #include <asm/debugreg.h>
 #include <asm/apicdef.h>
@@ -741,6 +743,64 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 	regs->ip = ip;
 }
 
+int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
+{
+	int err;
+	char opc[BREAK_INSTR_SIZE];
+
+	bpt->type = BP_BREAKPOINT;
+	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+				BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+	err = probe_kernel_write((char *)bpt->bpt_addr,
+				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
+#ifdef CONFIG_DEBUG_RODATA
+	if (!err)
+		return err;
+	/*
+	 * It is safe to call text_poke() because normal kernel execution
+	 * is stopped on all cores, so long as the text_mutex is not locked.
+	 */
+	if (mutex_is_locked(&text_mutex))
+		return -EBUSY;
+	text_poke((void *)bpt->bpt_addr, arch_kgdb_ops.gdb_bpt_instr,
+		  BREAK_INSTR_SIZE);
+	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+	if (err)
+		return err;
+	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
+		return -EINVAL;
+	bpt->type = BP_POKE_BREAKPOINT;
+#endif /* CONFIG_DEBUG_RODATA */
+	return err;
+}
+
+int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
+{
+#ifdef CONFIG_DEBUG_RODATA
+	int err;
+	char opc[BREAK_INSTR_SIZE];
+
+	if (bpt->type != BP_POKE_BREAKPOINT)
+		goto knl_write;
+	/*
+	 * It is safe to call text_poke() because normal kernel execution
+	 * is stopped on all cores, so long as the text_mutex is not locked.
+	 */
+	if (mutex_is_locked(&text_mutex))
+		goto knl_write;
+	text_poke((void *)bpt->bpt_addr, bpt->saved_instr, BREAK_INSTR_SIZE);
+	err = probe_kernel_read(opc, (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
+	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
+		goto knl_write;
+	return err;
+knl_write:
+#endif /* CONFIG_DEBUG_RODATA */
+	return probe_kernel_write((char *)bpt->bpt_addr,
+				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
+}
+
 struct kgdb_arch arch_kgdb_ops = {
 	/* Breakpoint instruction: */
 	.gdb_bpt_instr		= { 0xcc },
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 694d801bf606..b8ba6e4a27e4 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -38,6 +38,7 @@
 #include <asm/traps.h>
 #include <asm/desc.h>
 #include <asm/tlbflush.h>
+#include <asm/idle.h>
 
 static int kvmapf = 1;
 
@@ -253,7 +254,10 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code)
 		kvm_async_pf_task_wait((u32)read_cr2());
 		break;
 	case KVM_PV_REASON_PAGE_READY:
+		rcu_irq_enter();
+		exit_idle();
 		kvm_async_pf_task_wake((u32)read_cr2());
+		rcu_irq_exit();
 		break;
 	}
 }
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index 73465aab28f8..8a2ce8fd41c0 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -82,11 +82,6 @@ static int collect_cpu_info_amd(int cpu, struct cpu_signature *csig)
 {
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
-	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
-		pr_warning("CPU%d: family %d not supported\n", cpu, c->x86);
-		return -1;
-	}
-
 	csig->rev = c->microcode;
 	pr_info("CPU%d: patch_level=0x%08x\n", cpu, csig->rev);
 
@@ -380,6 +375,13 @@ static struct microcode_ops microcode_amd_ops = {
 
 struct microcode_ops * __init init_amd_microcode(void)
 {
+	struct cpuinfo_x86 *c = &cpu_data(0);
+
+	if (c->x86_vendor != X86_VENDOR_AMD || c->x86 < 0x10) {
+		pr_warning("AMD CPU family 0x%x not supported\n", c->x86);
+		return NULL;
+	}
+
 	patch = (void *)get_zeroed_page(GFP_KERNEL);
 	if (!patch)
 		return NULL;
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index 87a0f8688301..c9bda6d6035c 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -419,10 +419,8 @@ static int mc_device_add(struct device *dev, struct subsys_interface *sif)
 	if (err)
 		return err;
 
-	if (microcode_init_cpu(cpu) == UCODE_ERROR) {
-		sysfs_remove_group(&dev->kobj, &mc_attr_group);
+	if (microcode_init_cpu(cpu) == UCODE_ERROR)
 		return -EINVAL;
-	}
 
 	return err;
 }
@@ -528,11 +526,11 @@ static int __init microcode_init(void)
 		microcode_ops = init_intel_microcode();
 	else if (c->x86_vendor == X86_VENDOR_AMD)
 		microcode_ops = init_amd_microcode();
-
-	if (!microcode_ops) {
+	else
 		pr_err("no support for this CPU vendor\n");
+
+	if (!microcode_ops)
 		return -ENODEV;
-	}
 
 	microcode_pdev = platform_device_register_simple("microcode", -1,
 							 NULL, 0);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 6ac5782f4d6b..d0b2fb9ccbb1 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -430,7 +430,7 @@ static void calgary_unmap_page(struct device *dev, dma_addr_t dma_addr,
 }
 
 static void* calgary_alloc_coherent(struct device *dev, size_t size,
-	dma_addr_t *dma_handle, gfp_t flag)
+	dma_addr_t *dma_handle, gfp_t flag, struct dma_attrs *attrs)
 {
 	void *ret = NULL;
 	dma_addr_t mapping;
@@ -463,7 +463,8 @@ error:
 }
 
 static void calgary_free_coherent(struct device *dev, size_t size,
-				  void *vaddr, dma_addr_t dma_handle)
+				  void *vaddr, dma_addr_t dma_handle,
+				  struct dma_attrs *attrs)
 {
 	unsigned int npages;
 	struct iommu_table *tbl = find_iommu_table(dev);
@@ -476,8 +477,8 @@ static void calgary_free_coherent(struct device *dev, size_t size,
 }
 
 static struct dma_map_ops calgary_dma_ops = {
-	.alloc_coherent = calgary_alloc_coherent,
-	.free_coherent = calgary_free_coherent,
+	.alloc = calgary_alloc_coherent,
+	.free = calgary_free_coherent,
 	.map_sg = calgary_map_sg,
 	.unmap_sg = calgary_unmap_sg,
 	.map_page = calgary_map_page,
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 28e5e06fcba4..3003250ac51d 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -96,7 +96,8 @@ void __init pci_iommu_alloc(void)
 	}
 }
 void *dma_generic_alloc_coherent(struct device *dev, size_t size,
-				 dma_addr_t *dma_addr, gfp_t flag)
+				 dma_addr_t *dma_addr, gfp_t flag,
+				 struct dma_attrs *attrs)
 {
 	unsigned long dma_mask;
 	struct page *page;
diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c
index 3af4af810c07..f96050685b46 100644
--- a/arch/x86/kernel/pci-nommu.c
+++ b/arch/x86/kernel/pci-nommu.c
@@ -75,7 +75,7 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg,
 }
 
 static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr,
-				dma_addr_t dma_addr)
+				dma_addr_t dma_addr, struct dma_attrs *attrs)
 {
 	free_pages((unsigned long)vaddr, get_order(size));
 }
@@ -96,8 +96,8 @@ static void nommu_sync_sg_for_device(struct device *dev,
 }
 
 struct dma_map_ops nommu_dma_ops = {
-	.alloc_coherent		= dma_generic_alloc_coherent,
-	.free_coherent		= nommu_free_coherent,
+	.alloc			= dma_generic_alloc_coherent,
+	.free			= nommu_free_coherent,
 	.map_sg			= nommu_map_sg,
 	.map_page		= nommu_map_page,
 	.sync_single_for_device = nommu_sync_single_for_device,
diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c
index 8f972cbddef0..6c483ba98b9c 100644
--- a/arch/x86/kernel/pci-swiotlb.c
+++ b/arch/x86/kernel/pci-swiotlb.c
@@ -15,21 +15,30 @@
 int swiotlb __read_mostly;
 
 static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size,
-					dma_addr_t *dma_handle, gfp_t flags)
+					dma_addr_t *dma_handle, gfp_t flags,
+					struct dma_attrs *attrs)
 {
 	void *vaddr;
 
-	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags);
+	vaddr = dma_generic_alloc_coherent(hwdev, size, dma_handle, flags,
+					   attrs);
 	if (vaddr)
 		return vaddr;
 
 	return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags);
 }
 
+static void x86_swiotlb_free_coherent(struct device *dev, size_t size,
+				      void *vaddr, dma_addr_t dma_addr,
+				      struct dma_attrs *attrs)
+{
+	swiotlb_free_coherent(dev, size, vaddr, dma_addr);
+}
+
 static struct dma_map_ops swiotlb_dma_ops = {
 	.mapping_error = swiotlb_dma_mapping_error,
-	.alloc_coherent = x86_swiotlb_alloc_coherent,
-	.free_coherent = swiotlb_free_coherent,
+	.alloc = x86_swiotlb_alloc_coherent,
+	.free = x86_swiotlb_free_coherent,
 	.sync_single_for_cpu = swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index a33afaa5ddb7..1d92a5ab6e8b 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -362,34 +362,10 @@ void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
 #endif
 
-#ifdef CONFIG_X86_32
-/*
- * This halt magic was a workaround for ancient floppy DMA
- * wreckage. It should be safe to remove.
- */
-static int hlt_counter;
-void disable_hlt(void)
-{
-	hlt_counter++;
-}
-EXPORT_SYMBOL(disable_hlt);
-
-void enable_hlt(void)
-{
-	hlt_counter--;
-}
-EXPORT_SYMBOL(enable_hlt);
-
-static inline int hlt_use_halt(void)
-{
-	return (!hlt_counter && boot_cpu_data.hlt_works_ok);
-}
-#else
 static inline int hlt_use_halt(void)
 {
 	return 1;
 }
-#endif
 
 #ifndef CONFIG_SMP
 static inline void play_dead(void)
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index f386dc49f988..7515cf0e1805 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -216,9 +216,9 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 	current_thread_info()->sig_on_uaccess_error = 1;
 
 	/*
-	 * 0 is a valid user pointer (in the access_ok sense) on 32-bit and
+	 * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
 	 * 64-bit, so we don't need to special-case it here.  For all the
-	 * vsyscalls, 0 means "don't write anything" not "write it at
+	 * vsyscalls, NULL means "don't write anything" not "write it at
 	 * address 0".
 	 */
 	ret = -EFAULT;
@@ -247,7 +247,7 @@ bool emulate_vsyscall(struct pt_regs *regs, unsigned long address)
 
 		ret = sys_getcpu((unsigned __user *)regs->di,
 				 (unsigned __user *)regs->si,
-				 0);
+				 NULL);
 		break;
 	}
 
diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
index e9f265fd79ae..9cf71d0b2d37 100644
--- a/arch/x86/kernel/x86_init.c
+++ b/arch/x86/kernel/x86_init.c
@@ -93,7 +93,6 @@ struct x86_init_ops x86_init __initdata = {
 struct x86_cpuinit_ops x86_cpuinit __cpuinitdata = {
 	.early_percpu_clock_init	= x86_init_noop,
 	.setup_percpu_clockev		= setup_secondary_APIC_clock,
-	.fixup_cpu_id			= x86_default_fixup_cpu_id,
 };
 
 static void default_nmi_init(void) { };
diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c
index a73f0c104813..2e88438ffd83 100644
--- a/arch/x86/kvm/pmu.c
+++ b/arch/x86/kvm/pmu.c
@@ -369,7 +369,7 @@ int kvm_pmu_set_msr(struct kvm_vcpu *vcpu, u32 index, u64 data)
 	case MSR_CORE_PERF_FIXED_CTR_CTRL:
 		if (pmu->fixed_ctr_ctrl == data)
 			return 0;
-		if (!(data & 0xfffffffffffff444)) {
+		if (!(data & 0xfffffffffffff444ull)) {
 			reprogram_fixed_counters(pmu, data);
 			return 0;
 		}
@@ -459,17 +459,17 @@ void kvm_pmu_cpuid_update(struct kvm_vcpu *vcpu)
 	pmu->available_event_types = ~entry->ebx & ((1ull << bitmap_len) - 1);
 
 	if (pmu->version == 1) {
-		pmu->global_ctrl = (1 << pmu->nr_arch_gp_counters) - 1;
-		return;
+		pmu->nr_arch_fixed_counters = 0;
+	} else {
+		pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
+				X86_PMC_MAX_FIXED);
+		pmu->counter_bitmask[KVM_PMC_FIXED] =
+			((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
 	}
 
-	pmu->nr_arch_fixed_counters = min((int)(entry->edx & 0x1f),
-			X86_PMC_MAX_FIXED);
-	pmu->counter_bitmask[KVM_PMC_FIXED] =
-		((u64)1 << ((entry->edx >> 5) & 0xff)) - 1;
-	pmu->global_ctrl_mask = ~(((1 << pmu->nr_arch_gp_counters) - 1)
-			| (((1ull << pmu->nr_arch_fixed_counters) - 1)
-				<< X86_PMC_IDX_FIXED));
+	pmu->global_ctrl = ((1 << pmu->nr_arch_gp_counters) - 1) |
+		(((1ull << pmu->nr_arch_fixed_counters) - 1) << X86_PMC_IDX_FIXED);
+	pmu->global_ctrl_mask = ~pmu->global_ctrl;
 }
 
 void kvm_pmu_init(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 280751c84724..4ff0ab9bc3c8 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2210,9 +2210,12 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
 			msr->data = data;
-			if (msr - vmx->guest_msrs < vmx->save_nmsrs)
+			if (msr - vmx->guest_msrs < vmx->save_nmsrs) {
+				preempt_disable();
 				kvm_set_shared_msr(msr->index, msr->data,
 						   msr->mask);
+				preempt_enable();
+			}
 			break;
 		}
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
@@ -3906,7 +3909,9 @@ static int vmx_vcpu_reset(struct kvm_vcpu *vcpu)
 		vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
 
 	vmx->vcpu.arch.cr0 = X86_CR0_NW | X86_CR0_CD | X86_CR0_ET;
+	vcpu->srcu_idx = srcu_read_lock(&vcpu->kvm->srcu);
 	vmx_set_cr0(&vmx->vcpu, kvm_read_cr0(vcpu)); /* enter rmode */
+	srcu_read_unlock(&vcpu->kvm->srcu, vcpu->srcu_idx);
 	vmx_set_cr4(&vmx->vcpu, 0);
 	vmx_set_efer(&vmx->vcpu, 0);
 	vmx_fpu_activate(&vmx->vcpu);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4044ce0bf7c1..91a5e989abcf 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6336,13 +6336,11 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 		if (npages && !old.rmap) {
 			unsigned long userspace_addr;
 
-			down_write(&current->mm->mmap_sem);
-			userspace_addr = do_mmap(NULL, 0,
+			userspace_addr = vm_mmap(NULL, 0,
 						 npages * PAGE_SIZE,
 						 PROT_READ | PROT_WRITE,
 						 map_flags,
 						 0);
-			up_write(&current->mm->mmap_sem);
 
 			if (IS_ERR((void *)userspace_addr))
 				return PTR_ERR((void *)userspace_addr);
@@ -6366,10 +6364,8 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 	if (!user_alloc && !old.user_alloc && old.rmap && !npages) {
 		int ret;
 
-		down_write(&current->mm->mmap_sem);
-		ret = do_munmap(current->mm, old.userspace_addr,
+		ret = vm_munmap(old.userspace_addr,
 				old.npages * PAGE_SIZE);
-		up_write(&current->mm->mmap_sem);
 		if (ret < 0)
 			printk(KERN_WARNING
 			       "kvm_vm_ioctl_set_memory_region: "
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 25feb1ae71c5..b1e6c4b2e8eb 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -379,8 +379,8 @@ err_out:
 	return;
 }
 
-/* Decode moffset16/32/64 */
-static void __get_moffset(struct insn *insn)
+/* Decode moffset16/32/64. Return 0 if failed */
+static int __get_moffset(struct insn *insn)
 {
 	switch (insn->addr_bytes) {
 	case 2:
@@ -397,15 +397,19 @@ static void __get_moffset(struct insn *insn)
 		insn->moffset2.value = get_next(int, insn);
 		insn->moffset2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->moffset1.got = insn->moffset2.got = 1;
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v32(Iz) */
-static void __get_immv32(struct insn *insn)
+/* Decode imm v32(Iz). Return 0 if failed */
+static int __get_immv32(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -417,14 +421,18 @@ static void __get_immv32(struct insn *insn)
 		insn->immediate.value = get_next(int, insn);
 		insn->immediate.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 
+	return 1;
+
 err_out:
-	return;
+	return 0;
 }
 
-/* Decode imm v64(Iv/Ov) */
-static void __get_immv(struct insn *insn)
+/* Decode imm v64(Iv/Ov), Return 0 if failed */
+static int __get_immv(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -441,15 +449,18 @@ static void __get_immv(struct insn *insn)
 		insn->immediate2.value = get_next(int, insn);
 		insn->immediate2.nbytes = 4;
 		break;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /* Decode ptr16:16/32(Ap) */
-static void __get_immptr(struct insn *insn)
+static int __get_immptr(struct insn *insn)
 {
 	switch (insn->opnd_bytes) {
 	case 2:
@@ -462,14 +473,17 @@ static void __get_immptr(struct insn *insn)
 		break;
 	case 8:
 		/* ptr16:64 is not exist (no segment) */
-		return;
+		return 0;
+	default:	/* opnd_bytes must be modified manually */
+		goto err_out;
 	}
 	insn->immediate2.value = get_next(unsigned short, insn);
 	insn->immediate2.nbytes = 2;
 	insn->immediate1.got = insn->immediate2.got = 1;
 
+	return 1;
 err_out:
-	return;
+	return 0;
 }
 
 /**
@@ -489,7 +503,8 @@ void insn_get_immediate(struct insn *insn)
 		insn_get_displacement(insn);
 
 	if (inat_has_moffset(insn->attr)) {
-		__get_moffset(insn);
+		if (!__get_moffset(insn))
+			goto err_out;
 		goto done;
 	}
 
@@ -517,16 +532,20 @@ void insn_get_immediate(struct insn *insn)
 		insn->immediate2.nbytes = 4;
 		break;
 	case INAT_IMM_PTR:
-		__get_immptr(insn);
+		if (!__get_immptr(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD32:
-		__get_immv32(insn);
+		if (!__get_immv32(insn))
+			goto err_out;
 		break;
 	case INAT_IMM_VWORD:
-		__get_immv(insn);
+		if (!__get_immv(insn))
+			goto err_out;
 		break;
 	default:
-		break;
+		/* Here, insn must have an immediate, but failed */
+		goto err_out;
 	}
 	if (inat_has_second_immediate(insn->attr)) {
 		insn->immediate2.value = get_next(char, insn);
diff --git a/arch/x86/lib/usercopy.c b/arch/x86/lib/usercopy.c
index 97be9cb54483..d6ae30bbd7bb 100644
--- a/arch/x86/lib/usercopy.c
+++ b/arch/x86/lib/usercopy.c
@@ -7,6 +7,8 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
 
+#include <asm/word-at-a-time.h>
+
 /*
  * best effort, GUP based copy_from_user() that is NMI-safe
  */
@@ -41,3 +43,104 @@ copy_from_user_nmi(void *to, const void __user *from, unsigned long n)
 	return len;
 }
 EXPORT_SYMBOL_GPL(copy_from_user_nmi);
+
+static inline unsigned long count_bytes(unsigned long mask)
+{
+	mask = (mask - 1) & ~mask;
+	mask >>= 7;
+	return count_masked_bytes(mask);
+}
+
+/*
+ * Do a strncpy, return length of string without final '\0'.
+ * 'count' is the user-supplied count (return 'count' if we
+ * hit it), 'max' is the address space maximum (and we return
+ * -EFAULT if we hit it).
+ */
+static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+{
+	long res = 0;
+
+	/*
+	 * Truncate 'max' to the user-specified limit, so that
+	 * we only have one limit we need to check in the loop
+	 */
+	if (max > count)
+		max = count;
+
+	while (max >= sizeof(unsigned long)) {
+		unsigned long c;
+
+		/* Fall back to byte-at-a-time if we get a page fault */
+		if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+			break;
+		/* This can write a few bytes past the NUL character, but that's ok */
+		*(unsigned long *)(dst+res) = c;
+		c = has_zero(c);
+		if (c)
+			return res + count_bytes(c);
+		res += sizeof(unsigned long);
+		max -= sizeof(unsigned long);
+	}
+
+	while (max) {
+		char c;
+
+		if (unlikely(__get_user(c,src+res)))
+			return -EFAULT;
+		dst[res] = c;
+		if (!c)
+			return res;
+		res++;
+		max--;
+	}
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, that's ok - we got as much as the user asked for.
+	 */
+	if (res >= count)
+		return res;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's an EFAULT.
+	 */
+	return -EFAULT;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long
+strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	if (unlikely(count <= 0))
+		return 0;
+
+	max_addr = current_thread_info()->addr_limit.seg;
+	src_addr = (unsigned long)src;
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		return do_strncpy_from_user(dst, src, count, max);
+	}
+	return -EFAULT;
+}
+EXPORT_SYMBOL(strncpy_from_user);
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index d9b094ca7aaa..ef2a6a5d78e3 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -33,93 +33,6 @@ static inline int __movsl_is_ok(unsigned long a1, unsigned long a2, unsigned lon
 	__movsl_is_ok((unsigned long)(a1), (unsigned long)(a2), (n))
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst, src, count, res)			   \
-do {									   \
-	int __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testl %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decl %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subl %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movl %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&d"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-/**
- * __strncpy_from_user: - Copy a NUL terminated string from userspace, with less checking.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- * Caller must check the specified block with access_ok() before calling
- * this function.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-/**
- * strncpy_from_user: - Copy a NUL terminated string from userspace.
- * @dst:   Destination address, in kernel space.  This buffer must be at
- *         least @count bytes long.
- * @src:   Source address, in user space.
- * @count: Maximum number of bytes to copy, including the trailing NUL.
- *
- * Copies a NUL-terminated string from userspace to kernel space.
- *
- * On success, returns the length of the string (not including the trailing
- * NUL).
- *
- * If access to userspace fails, returns -EFAULT (some data may have been
- * copied).
- *
- * If @count is smaller than the length of the string, copies @count bytes
- * and returns @count.
- */
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/lib/usercopy_64.c b/arch/x86/lib/usercopy_64.c
index b7c2849ffb66..0d0326f388c0 100644
--- a/arch/x86/lib/usercopy_64.c
+++ b/arch/x86/lib/usercopy_64.c
@@ -9,55 +9,6 @@
 #include <asm/uaccess.h>
 
 /*
- * Copy a null terminated string from userspace.
- */
-
-#define __do_strncpy_from_user(dst,src,count,res)			   \
-do {									   \
-	long __d0, __d1, __d2;						   \
-	might_fault();							   \
-	__asm__ __volatile__(						   \
-		"	testq %1,%1\n"					   \
-		"	jz 2f\n"					   \
-		"0:	lodsb\n"					   \
-		"	stosb\n"					   \
-		"	testb %%al,%%al\n"				   \
-		"	jz 1f\n"					   \
-		"	decq %1\n"					   \
-		"	jnz 0b\n"					   \
-		"1:	subq %1,%0\n"					   \
-		"2:\n"							   \
-		".section .fixup,\"ax\"\n"				   \
-		"3:	movq %5,%0\n"					   \
-		"	jmp 2b\n"					   \
-		".previous\n"						   \
-		_ASM_EXTABLE(0b,3b)					   \
-		: "=&r"(res), "=&c"(count), "=&a" (__d0), "=&S" (__d1),	   \
-		  "=&D" (__d2)						   \
-		: "i"(-EFAULT), "0"(count), "1"(count), "3"(src), "4"(dst) \
-		: "memory");						   \
-} while (0)
-
-long
-__strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res;
-	__do_strncpy_from_user(dst, src, count, res);
-	return res;
-}
-EXPORT_SYMBOL(__strncpy_from_user);
-
-long
-strncpy_from_user(char *dst, const char __user *src, long count)
-{
-	long res = -EFAULT;
-	if (access_ok(VERIFY_READ, src, 1))
-		return __strncpy_from_user(dst, src, count);
-	return res;
-}
-EXPORT_SYMBOL(strncpy_from_user);
-
-/*
  * Zero Userspace
  */
 
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S
index 66870223f8c5..877b9a1b2152 100644
--- a/arch/x86/net/bpf_jit.S
+++ b/arch/x86/net/bpf_jit.S
@@ -18,17 +18,17 @@
  * r9d : hlen = skb->len - skb->data_len
  */
 #define SKBDATA	%r8
-
-sk_load_word_ind:
-	.globl	sk_load_word_ind
-
-	add	%ebx,%esi	/* offset += X */
-#	test    %esi,%esi	/* if (offset < 0) goto bpf_error; */
-	js	bpf_error
+#define SKF_MAX_NEG_OFF    $(-0x200000) /* SKF_LL_OFF from filter.h */
 
 sk_load_word:
 	.globl	sk_load_word
 
+	test	%esi,%esi
+	js	bpf_slow_path_word_neg
+
+sk_load_word_positive_offset:
+	.globl	sk_load_word_positive_offset
+
 	mov	%r9d,%eax		# hlen
 	sub	%esi,%eax		# hlen - offset
 	cmp	$3,%eax
@@ -37,16 +37,15 @@ sk_load_word:
 	bswap   %eax  			/* ntohl() */
 	ret
 
-
-sk_load_half_ind:
-	.globl sk_load_half_ind
-
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_half:
 	.globl	sk_load_half
 
+	test	%esi,%esi
+	js	bpf_slow_path_half_neg
+
+sk_load_half_positive_offset:
+	.globl	sk_load_half_positive_offset
+
 	mov	%r9d,%eax
 	sub	%esi,%eax		#	hlen - offset
 	cmp	$1,%eax
@@ -55,14 +54,15 @@ sk_load_half:
 	rol	$8,%ax			# ntohs()
 	ret
 
-sk_load_byte_ind:
-	.globl sk_load_byte_ind
-	add	%ebx,%esi	/* offset += X */
-	js	bpf_error
-
 sk_load_byte:
 	.globl	sk_load_byte
 
+	test	%esi,%esi
+	js	bpf_slow_path_byte_neg
+
+sk_load_byte_positive_offset:
+	.globl	sk_load_byte_positive_offset
+
 	cmp	%esi,%r9d   /* if (offset >= hlen) goto bpf_slow_path_byte */
 	jle	bpf_slow_path_byte
 	movzbl	(SKBDATA,%rsi),%eax
@@ -73,25 +73,21 @@ sk_load_byte:
  *
  * Implements BPF_S_LDX_B_MSH : ldxb  4*([offset]&0xf)
  * Must preserve A accumulator (%eax)
- * Inputs : %esi is the offset value, already known positive
+ * Inputs : %esi is the offset value
  */
-ENTRY(sk_load_byte_msh)
-	CFI_STARTPROC
+sk_load_byte_msh:
+	.globl	sk_load_byte_msh
+	test	%esi,%esi
+	js	bpf_slow_path_byte_msh_neg
+
+sk_load_byte_msh_positive_offset:
+	.globl	sk_load_byte_msh_positive_offset
 	cmp	%esi,%r9d      /* if (offset >= hlen) goto bpf_slow_path_byte_msh */
 	jle	bpf_slow_path_byte_msh
 	movzbl	(SKBDATA,%rsi),%ebx
 	and	$15,%bl
 	shl	$2,%bl
 	ret
-	CFI_ENDPROC
-ENDPROC(sk_load_byte_msh)
-
-bpf_error:
-# force a return 0 from jit handler
-	xor		%eax,%eax
-	mov		-8(%rbp),%rbx
-	leaveq
-	ret
 
 /* rsi contains offset and can be scratched */
 #define bpf_slow_path_common(LEN)		\
@@ -138,3 +134,67 @@ bpf_slow_path_byte_msh:
 	shl	$2,%al
 	xchg	%eax,%ebx
 	ret
+
+#define sk_negative_common(SIZE)				\
+	push	%rdi;	/* save skb */				\
+	push	%r9;						\
+	push	SKBDATA;					\
+/* rsi already has offset */					\
+	mov	$SIZE,%ecx;	/* size */			\
+	call	bpf_internal_load_pointer_neg_helper;		\
+	test	%rax,%rax;					\
+	pop	SKBDATA;					\
+	pop	%r9;						\
+	pop	%rdi;						\
+	jz	bpf_error
+
+
+bpf_slow_path_word_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi	/* test range */
+	jl	bpf_error	/* offset lower -> error  */
+sk_load_word_negative_offset:
+	.globl	sk_load_word_negative_offset
+	sk_negative_common(4)
+	mov	(%rax), %eax
+	bswap	%eax
+	ret
+
+bpf_slow_path_half_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_half_negative_offset:
+	.globl	sk_load_half_negative_offset
+	sk_negative_common(2)
+	mov	(%rax),%ax
+	rol	$8,%ax
+	movzwl	%ax,%eax
+	ret
+
+bpf_slow_path_byte_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_negative_offset:
+	.globl	sk_load_byte_negative_offset
+	sk_negative_common(1)
+	movzbl	(%rax), %eax
+	ret
+
+bpf_slow_path_byte_msh_neg:
+	cmp	SKF_MAX_NEG_OFF, %esi
+	jl	bpf_error
+sk_load_byte_msh_negative_offset:
+	.globl	sk_load_byte_msh_negative_offset
+	xchg	%eax,%ebx /* dont lose A , X is about to be scratched */
+	sk_negative_common(1)
+	movzbl	(%rax),%eax
+	and	$15,%al
+	shl	$2,%al
+	xchg	%eax,%ebx
+	ret
+
+bpf_error:
+# force a return 0 from jit handler
+	xor		%eax,%eax
+	mov		-8(%rbp),%rbx
+	leaveq
+	ret
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 5671752f8d9c..0597f95b6da6 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -30,7 +30,10 @@ int bpf_jit_enable __read_mostly;
  * assembly code in arch/x86/net/bpf_jit.S
  */
 extern u8 sk_load_word[], sk_load_half[], sk_load_byte[], sk_load_byte_msh[];
-extern u8 sk_load_word_ind[], sk_load_half_ind[], sk_load_byte_ind[];
+extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[];
+extern u8 sk_load_byte_positive_offset[], sk_load_byte_msh_positive_offset[];
+extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[];
+extern u8 sk_load_byte_negative_offset[], sk_load_byte_msh_negative_offset[];
 
 static inline u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len)
 {
@@ -117,6 +120,8 @@ static inline void bpf_flush_icache(void *start, void *end)
 	set_fs(old_fs);
 }
 
+#define CHOOSE_LOAD_FUNC(K, func) \
+	((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset)
 
 void bpf_jit_compile(struct sk_filter *fp)
 {
@@ -289,7 +294,7 @@ void bpf_jit_compile(struct sk_filter *fp)
 					EMIT2(0x24, K & 0xFF); /* and imm8,%al */
 				} else if (K >= 0xFFFF0000) {
 					EMIT2(0x66, 0x25);	/* and imm16,%ax */
-					EMIT2(K, 2);
+					EMIT(K, 2);
 				} else {
 					EMIT1_off32(0x25, K);	/* and imm32,%eax */
 				}
@@ -473,44 +478,46 @@ void bpf_jit_compile(struct sk_filter *fp)
 #endif
 				break;
 			case BPF_S_LD_W_ABS:
-				func = sk_load_word;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_word);
 common_load:			seen |= SEEN_DATAREF;
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
 				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K); /* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call */
 				break;
 			case BPF_S_LD_H_ABS:
-				func = sk_load_half;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_half);
 				goto common_load;
 			case BPF_S_LD_B_ABS:
-				func = sk_load_byte;
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte);
 				goto common_load;
 			case BPF_S_LDX_B_MSH:
-				if ((int)K < 0) {
-					/* Abort the JIT because __load_pointer() is needed. */
-					goto out;
-				}
+				func = CHOOSE_LOAD_FUNC(K, sk_load_byte_msh);
 				seen |= SEEN_DATAREF | SEEN_XREG;
-				t_offset = sk_load_byte_msh - (image + addrs[i]);
+				t_offset = func - (image + addrs[i]);
 				EMIT1_off32(0xbe, K);	/* mov imm32,%esi */
 				EMIT1_off32(0xe8, t_offset); /* call sk_load_byte_msh */
 				break;
 			case BPF_S_LD_W_IND:
-				func = sk_load_word_ind;
+				func = sk_load_word;
 common_load_ind:		seen |= SEEN_DATAREF | SEEN_XREG;
 				t_offset = func - (image + addrs[i]);
-				EMIT1_off32(0xbe, K);	/* mov imm32,%esi   */
+				if (K) {
+					if (is_imm8(K)) {
+						EMIT3(0x8d, 0x73, K); /* lea imm8(%rbx), %esi */
+					} else {
+						EMIT2(0x8d, 0xb3); /* lea imm32(%rbx),%esi */
+						EMIT(K, 4);
+					}
+				} else {
+					EMIT2(0x89,0xde); /* mov %ebx,%esi */
+				}
 				EMIT1_off32(0xe8, t_offset);	/* call sk_load_xxx_ind */
 				break;
 			case BPF_S_LD_H_IND:
-				func = sk_load_half_ind;
+				func = sk_load_half;
 				goto common_load_ind;
 			case BPF_S_LD_B_IND:
-				func = sk_load_byte_ind;
+				func = sk_load_byte;
 				goto common_load_ind;
 			case BPF_S_JMP_JA:
 				t_offset = addrs[i + K] - addrs[i];
diff --git a/arch/x86/platform/geode/net5501.c b/arch/x86/platform/geode/net5501.c
index 66d377e334f7..646e3b5b4bb6 100644
--- a/arch/x86/platform/geode/net5501.c
+++ b/arch/x86/platform/geode/net5501.c
@@ -63,7 +63,7 @@ static struct gpio_led net5501_leds[] = {
 		.name = "net5501:1",
 		.gpio = 6,
 		.default_trigger = "default-on",
-		.active_low = 1,
+		.active_low = 0,
 	},
 };
 
diff --git a/arch/x86/platform/mrst/mrst.c b/arch/x86/platform/mrst/mrst.c
index e0a37233c0af..e31bcd8f2eee 100644
--- a/arch/x86/platform/mrst/mrst.c
+++ b/arch/x86/platform/mrst/mrst.c
@@ -805,7 +805,7 @@ void intel_scu_devices_create(void)
 		} else
 			i2c_register_board_info(i2c_bus[i], i2c_devs[i], 1);
 	}
-	intel_scu_notifier_post(SCU_AVAILABLE, 0L);
+	intel_scu_notifier_post(SCU_AVAILABLE, NULL);
 }
 EXPORT_SYMBOL_GPL(intel_scu_devices_create);
 
@@ -814,7 +814,7 @@ void intel_scu_devices_destroy(void)
 {
 	int i;
 
-	intel_scu_notifier_post(SCU_DOWN, 0L);
+	intel_scu_notifier_post(SCU_DOWN, NULL);
 
 	for (i = 0; i < ipc_next_dev; i++)
 		platform_device_del(ipc_devs[i]);
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 47936830968c..218cdb16163c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -225,13 +225,13 @@ static void __restore_processor_state(struct saved_context *ctxt)
 	fix_processor_context();
 
 	do_fpu_end();
+	x86_platform.restore_sched_clock_state();
 	mtrr_bp_restore();
 }
 
 /* Needed by apm.c */
 void restore_processor_state(void)
 {
-	x86_platform.restore_sched_clock_state();
 	__restore_processor_state(&saved_context);
 }
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/um/asm/barrier.h b/arch/x86/um/asm/barrier.h
new file mode 100644
index 000000000000..7d01b8c56c00
--- /dev/null
+++ b/arch/x86/um/asm/barrier.h
@@ -0,0 +1,75 @@
+#ifndef _ASM_UM_BARRIER_H_
+#define _ASM_UM_BARRIER_H_
+
+#include <asm/asm.h>
+#include <asm/segment.h>
+#include <asm/cpufeature.h>
+#include <asm/cmpxchg.h>
+#include <asm/nops.h>
+
+#include <linux/kernel.h>
+#include <linux/irqflags.h>
+
+/*
+ * Force strict CPU ordering.
+ * And yes, this is required on UP too when we're talking
+ * to devices.
+ */
+#ifdef CONFIG_X86_32
+
+#define mb()	alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
+#define rmb()	alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
+#define wmb()	alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+
+#else /* CONFIG_X86_32 */
+
+#define mb()	asm volatile("mfence" : : : "memory")
+#define rmb()	asm volatile("lfence" : : : "memory")
+#define wmb()	asm volatile("sfence" : : : "memory")
+
+#endif /* CONFIG_X86_32 */
+
+#define read_barrier_depends()	do { } while (0)
+
+#ifdef CONFIG_SMP
+
+#define smp_mb()	mb()
+#ifdef CONFIG_X86_PPRO_FENCE
+#define smp_rmb()	rmb()
+#else /* CONFIG_X86_PPRO_FENCE */
+#define smp_rmb()	barrier()
+#endif /* CONFIG_X86_PPRO_FENCE */
+
+#ifdef CONFIG_X86_OOSTORE
+#define smp_wmb()	wmb()
+#else /* CONFIG_X86_OOSTORE */
+#define smp_wmb()	barrier()
+#endif /* CONFIG_X86_OOSTORE */
+
+#define smp_read_barrier_depends()	read_barrier_depends()
+#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
+
+#else /* CONFIG_SMP */
+
+#define smp_mb()	barrier()
+#define smp_rmb()	barrier()
+#define smp_wmb()	barrier()
+#define smp_read_barrier_depends()	do { } while (0)
+#define set_mb(var, value) do { var = value; barrier(); } while (0)
+
+#endif /* CONFIG_SMP */
+
+/*
+ * Stop RDTSC speculation. This is needed when you need to use RDTSC
+ * (or get_cycles or vread that possibly accesses the TSC) in a defined
+ * code region.
+ *
+ * (Could use an alternative three way for this if there was one.)
+ */
+static inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif
diff --git a/arch/x86/um/asm/system.h b/arch/x86/um/asm/system.h
deleted file mode 100644
index a459fd9b7598..000000000000
--- a/arch/x86/um/asm/system.h
+++ /dev/null
@@ -1,135 +0,0 @@
-#ifndef _ASM_X86_SYSTEM_H_
-#define _ASM_X86_SYSTEM_H_
-
-#include <asm/asm.h>
-#include <asm/segment.h>
-#include <asm/cpufeature.h>
-#include <asm/cmpxchg.h>
-#include <asm/nops.h>
-
-#include <linux/kernel.h>
-#include <linux/irqflags.h>
-
-/* entries in ARCH_DLINFO: */
-#ifdef CONFIG_IA32_EMULATION
-# define AT_VECTOR_SIZE_ARCH 2
-#else
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-extern unsigned long arch_align_stack(unsigned long sp);
-
-void default_idle(void);
-
-/*
- * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
- * to devices.
- */
-#ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
-#else
-#define mb() 	asm volatile("mfence":::"memory")
-#define rmb()	asm volatile("lfence":::"memory")
-#define wmb()	asm volatile("sfence" ::: "memory")
-#endif
-
-/**
- * read_barrier_depends - Flush all pending reads that subsequents reads
- * depend on.
- *
- * No data-dependent reads from memory-like regions are ever reordered
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- **/
-
-#define read_barrier_depends()	do { } while (0)
-
-#ifdef CONFIG_SMP
-#define smp_mb()	mb()
-#ifdef CONFIG_X86_PPRO_FENCE
-# define smp_rmb()	rmb()
-#else
-# define smp_rmb()	barrier()
-#endif
-#ifdef CONFIG_X86_OOSTORE
-# define smp_wmb() 	wmb()
-#else
-# define smp_wmb()	barrier()
-#endif
-#define smp_read_barrier_depends()	read_barrier_depends()
-#define set_mb(var, value) do { (void)xchg(&var, value); } while (0)
-#else
-#define smp_mb()	barrier()
-#define smp_rmb()	barrier()
-#define smp_wmb()	barrier()
-#define smp_read_barrier_depends()	do { } while (0)
-#define set_mb(var, value) do { var = value; barrier(); } while (0)
-#endif
-
-/*
- * Stop RDTSC speculation. This is needed when you need to use RDTSC
- * (or get_cycles or vread that possibly accesses the TSC) in a defined
- * code region.
- *
- * (Could use an alternative three way for this if there was one.)
- */
-static inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-extern void *_switch_to(void *prev, void *next, void *last);
-#define switch_to(prev, next, last) prev = _switch_to(prev, next, last)
-
-#endif
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index b132ade26f77..a8f8844b8d32 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -261,7 +261,8 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx,
 
 static bool __init xen_check_mwait(void)
 {
-#ifdef CONFIG_ACPI
+#if defined(CONFIG_ACPI) && !defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR) && \
+	!defined(CONFIG_ACPI_PROCESSOR_AGGREGATOR_MODULE)
 	struct xen_platform_op op = {
 		.cmd			= XENPF_set_processor_pminfo,
 		.u.set_pminfo.id	= -1,
@@ -349,7 +350,6 @@ static void __init xen_init_cpuid_mask(void)
 	/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
 	if ((cx & xsave_mask) != xsave_mask)
 		cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
-
 	if (xen_check_mwait())
 		cpuid_leaf1_ecx_set_mask = (1 << (X86_FEATURE_MWAIT % 32));
 }
@@ -967,7 +967,7 @@ void xen_setup_shared_info(void)
 	xen_setup_mfn_list_list();
 }
 
-/* This is called once we have the cpu_possible_map */
+/* This is called once we have the cpu_possible_mask */
 void xen_setup_vcpu_info_placement(void)
 {
 	int cpu;
diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c
index 988828b479ed..b8e279479a6b 100644
--- a/arch/x86/xen/mmu.c
+++ b/arch/x86/xen/mmu.c
@@ -1859,6 +1859,7 @@ pgd_t * __init xen_setup_kernel_pagetable(pgd_t *pgd,
 #endif	/* CONFIG_X86_64 */
 
 static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+static unsigned char fake_ioapic_mapping[PAGE_SIZE] __page_aligned_bss;
 
 static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 {
@@ -1899,7 +1900,7 @@ static void xen_set_fixmap(unsigned idx, phys_addr_t phys, pgprot_t prot)
 		 * We just don't map the IO APIC - all access is via
 		 * hypercalls.  Keep the address in the pte for reference.
 		 */
-		pte = pfn_pte(PFN_DOWN(__pa(dummy_mapping)), PAGE_KERNEL);
+		pte = pfn_pte(PFN_DOWN(__pa(fake_ioapic_mapping)), PAGE_KERNEL);
 		break;
 #endif
 
@@ -2064,6 +2065,7 @@ void __init xen_init_mmu_ops(void)
 	pv_mmu_ops = xen_mmu_ops;
 
 	memset(dummy_mapping, 0xff, PAGE_SIZE);
+	memset(fake_ioapic_mapping, 0xfd, PAGE_SIZE);
 }
 
 /* Protected by xen_reservation_lock. */
diff --git a/arch/x86/xen/pci-swiotlb-xen.c b/arch/x86/xen/pci-swiotlb-xen.c
index b480d4207a4c..967633ad98c4 100644
--- a/arch/x86/xen/pci-swiotlb-xen.c
+++ b/arch/x86/xen/pci-swiotlb-xen.c
@@ -12,8 +12,8 @@ int xen_swiotlb __read_mostly;
 
 static struct dma_map_ops xen_swiotlb_dma_ops = {
 	.mapping_error = xen_swiotlb_dma_mapping_error,
-	.alloc_coherent = xen_swiotlb_alloc_coherent,
-	.free_coherent = xen_swiotlb_free_coherent,
+	.alloc = xen_swiotlb_alloc_coherent,
+	.free = xen_swiotlb_free_coherent,
 	.sync_single_for_cpu = xen_swiotlb_sync_single_for_cpu,
 	.sync_single_for_device = xen_swiotlb_sync_single_for_device,
 	.sync_sg_for_cpu = xen_swiotlb_sync_sg_for_cpu,
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 02900e8ce26c..0503c0c493a9 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -59,7 +59,7 @@ static irqreturn_t xen_reschedule_interrupt(int irq, void *dev_id)
 
 static void __cpuinit cpu_bringup(void)
 {
-	int cpu = smp_processor_id();
+	int cpu;
 
 	cpu_init();
 	touch_softlockup_watchdog();
@@ -178,6 +178,7 @@ static void __init xen_fill_possible_map(void)
 static void __init xen_filter_cpu_maps(void)
 {
 	int i, rc;
+	unsigned int subtract = 0;
 
 	if (!xen_initial_domain())
 		return;
@@ -192,8 +193,22 @@ static void __init xen_filter_cpu_maps(void)
 		} else {
 			set_cpu_possible(i, false);
 			set_cpu_present(i, false);
+			subtract++;
 		}
 	}
+#ifdef CONFIG_HOTPLUG_CPU
+	/* This is akin to using 'nr_cpus' on the Linux command line.
+	 * Which is OK as when we use 'dom0_max_vcpus=X' we can only
+	 * have up to X, while nr_cpu_ids is greater than X. This
+	 * normally is not a problem, except when CPU hotplugging
+	 * is involved and then there might be more than X CPUs
+	 * in the guest - which will not work as there is no
+	 * hypercall to expand the max number of VCPUs an already
+	 * running guest has. So cap it up to X. */
+	if (subtract)
+		nr_cpu_ids = nr_cpu_ids - subtract;
+#endif
+
 }
 
 static void __init xen_smp_prepare_boot_cpu(void)
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 79d7362ad6d1..3e45aa000718 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -96,7 +96,7 @@ ENTRY(xen_restore_fl_direct)
 
 	/* check for unmasked and pending */
 	cmpw $0x0001, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
-	jz 1f
+	jnz 1f
 2:	call check_events
 1:
 ENDPATCH(xen_restore_fl_direct)