Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

49 files changed, 955 insertions, 802 deletions

diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index b57e6a43a37a..f9c0d3ba9e84 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -14,6 +14,7 @@ header-y += msr.h
 header-y += mtrr.h
 header-y += posix_types_32.h
 header-y += posix_types_64.h
+header-y += posix_types_x32.h
 header-y += prctl.h
 header-y += processor-flags.h
 header-y += ptrace-abi.h
@@ -24,3 +25,4 @@ header-y += vsyscall.h
 
 genhdr-y += unistd_32.h
 genhdr-y += unistd_64.h
+genhdr-y += unistd_x32.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index a9371c91718c..d85410171260 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -11,7 +11,6 @@
 #include <linux/atomic.h>
 #include <asm/fixmap.h>
 #include <asm/mpspec.h>
-#include <asm/system.h>
 #include <asm/msr.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
@@ -535,7 +534,7 @@ static inline unsigned int read_apic_id(void)
 
 static inline int default_apic_id_valid(int apicid)
 {
-	return x2apic_mode || (apicid < 255);
+	return (apicid < 255);
 }
 
 extern void default_setup_apic_routing(void);
diff --git a/arch/x86/include/asm/auxvec.h b/arch/x86/include/asm/auxvec.h
index 1316b4c35425..77203ac352de 100644
--- a/arch/x86/include/asm/auxvec.h
+++ b/arch/x86/include/asm/auxvec.h
@@ -9,4 +9,11 @@
 #endif
 #define AT_SYSINFO_EHDR		33
 
+/* entries in ARCH_DLINFO: */
+#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
+# define AT_VECTOR_SIZE_ARCH 2
+#else /* else it's non-compat x86-64 */
+# define AT_VECTOR_SIZE_ARCH 1
+#endif
+
 #endif /* _ASM_X86_AUXVEC_H */
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
new file mode 100644
index 000000000000..c6cd358a1eec
--- /dev/null
+++ b/arch/x86/include/asm/barrier.h
@@ -0,0 +1,116 @@
+#ifndef _ASM_X86_BARRIER_H
+#define _ASM_X86_BARRIER_H
+
+#include <asm/alternative.h>
+#include <asm/nops.h>
+
+/*
+ * 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 __always_inline void rdtsc_barrier(void)
+{
+	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
+	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
+}
+
+#endif /* _ASM_X86_BARRIER_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index f654d1bb17fb..11e1152222d0 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -36,4 +36,8 @@ do {								\
 #endif /* !CONFIG_BUG */
 
 #include <asm-generic/bug.h>
+
+
+extern void show_regs_common(void);
+
 #endif /* _ASM_X86_BUG_H */
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 4e12668711e5..9863ee3747da 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -3,6 +3,7 @@
 
 /* Caches aren't brain-dead on the intel. */
 #include <asm-generic/cacheflush.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_X86_PAT
 /*
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 30d737ef2a42..d6805798d6fc 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -6,7 +6,9 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <asm/processor.h>
 #include <asm/user32.h>
+#include <asm/unistd.h>
 
 #define COMPAT_USER_HZ		100
 #define COMPAT_UTS_MACHINE	"i686\0\0"
@@ -186,7 +188,20 @@ struct compat_shmid64_ds {
 /*
  * The type of struct elf_prstatus.pr_reg in compatible core dumps.
  */
+#ifdef CONFIG_X86_X32_ABI
+typedef struct user_regs_struct compat_elf_gregset_t;
+
+#define PR_REG_SIZE(S) (test_thread_flag(TIF_IA32) ? 68 : 216)
+#define PRSTATUS_SIZE(S) (test_thread_flag(TIF_IA32) ? 144 : 296)
+#define SET_PR_FPVALID(S,V) \
+  do { *(int *) (((void *) &((S)->pr_reg)) + PR_REG_SIZE(0)) = (V); } \
+  while (0)
+
+#define COMPAT_USE_64BIT_TIME \
+	(!!(task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT))
+#else
 typedef struct user_regs_struct32 compat_elf_gregset_t;
+#endif
 
 /*
  * A pointer passed in from user mode. This should not
@@ -208,13 +223,30 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {
-	struct pt_regs *regs = task_pt_regs(current);
-	return (void __user *)regs->sp - len;
+	compat_uptr_t sp;
+
+	if (test_thread_flag(TIF_IA32)) {
+		sp = task_pt_regs(current)->sp;
+	} else {
+		/* -128 for the x32 ABI redzone */
+		sp = percpu_read(old_rsp) - 128;
+	}
+
+	return (void __user *)round_down(sp - len, 16);
+}
+
+static inline bool is_x32_task(void)
+{
+#ifdef CONFIG_X86_X32_ABI
+	if (task_pt_regs(current)->orig_ax & __X32_SYSCALL_BIT)
+		return true;
+#endif
+	return false;
 }
 
-static inline int is_compat_task(void)
+static inline bool is_compat_task(void)
 {
-	return current_thread_info()->status & TS_COMPAT;
+	return is_ia32_task() || is_x32_task();
 }
 
 #endif /* _ASM_X86_COMPAT_H */
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/elf.h b/arch/x86/include/asm/elf.h
index 5f962df30d0f..5939f44fe0c0 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -84,7 +84,6 @@ extern unsigned int vdso_enabled;
 	(((x)->e_machine == EM_386) || ((x)->e_machine == EM_486))
 
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #ifdef CONFIG_X86_32
 #include <asm/desc.h>
@@ -156,7 +155,12 @@ do {						\
 #define elf_check_arch(x)			\
 	((x)->e_machine == EM_X86_64)
 
-#define compat_elf_check_arch(x)	elf_check_arch_ia32(x)
+#define compat_elf_check_arch(x)		\
+	(elf_check_arch_ia32(x) || (x)->e_machine == EM_X86_64)
+
+#if __USER32_DS != __USER_DS
+# error "The following code assumes __USER32_DS == __USER_DS"
+#endif
 
 static inline void elf_common_init(struct thread_struct *t,
 				   struct pt_regs *regs, const u16 ds)
@@ -179,8 +183,9 @@ static inline void elf_common_init(struct thread_struct *t,
 void start_thread_ia32(struct pt_regs *regs, u32 new_ip, u32 new_sp);
 #define compat_start_thread start_thread_ia32
 
-void set_personality_ia32(void);
-#define COMPAT_SET_PERSONALITY(ex) set_personality_ia32()
+void set_personality_ia32(bool);
+#define COMPAT_SET_PERSONALITY(ex)			\
+	set_personality_ia32((ex).e_machine == EM_X86_64)
 
 #define COMPAT_ELF_PLATFORM			("i686")
 
@@ -287,7 +292,7 @@ do {									\
 #define VDSO_HIGH_BASE		0xffffe000U /* CONFIG_COMPAT_VDSO address */
 
 /* 1GB for 64bit, 8MB for 32bit */
-#define STACK_RND_MASK (test_thread_flag(TIF_IA32) ? 0x7ff : 0x3fffff)
+#define STACK_RND_MASK (test_thread_flag(TIF_ADDR32) ? 0x7ff : 0x3fffff)
 
 #define ARCH_DLINFO							\
 do {									\
@@ -296,9 +301,20 @@ do {									\
 			    (unsigned long)current->mm->context.vdso);	\
 } while (0)
 
+#define ARCH_DLINFO_X32							\
+do {									\
+	if (vdso_enabled)						\
+		NEW_AUX_ENT(AT_SYSINFO_EHDR,				\
+			    (unsigned long)current->mm->context.vdso);	\
+} while (0)
+
 #define AT_SYSINFO		32
 
-#define COMPAT_ARCH_DLINFO	ARCH_DLINFO_IA32(sysctl_vsyscall32)
+#define COMPAT_ARCH_DLINFO						\
+if (test_thread_flag(TIF_X32))						\
+	ARCH_DLINFO_X32;						\
+else									\
+	ARCH_DLINFO_IA32(sysctl_vsyscall32)
 
 #define COMPAT_ELF_ET_DYN_BASE	(TASK_UNMAPPED_BASE + 0x1000000)
 
@@ -314,6 +330,8 @@ struct linux_binprm;
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
 				       int uses_interp);
+extern int x32_setup_additional_pages(struct linux_binprm *bprm,
+				      int uses_interp);
 
 extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
 #define compat_arch_setup_additional_pages	syscall32_setup_pages
@@ -330,7 +348,7 @@ static inline int mmap_is_ia32(void)
 	return 1;
 #endif
 #ifdef CONFIG_IA32_EMULATION
-	if (test_thread_flag(TIF_IA32))
+	if (test_thread_flag(TIF_ADDR32))
 		return 1;
 #endif
 	return 0;
diff --git a/arch/x86/include/asm/exec.h b/arch/x86/include/asm/exec.h
new file mode 100644
index 000000000000..54c2e1db274a
--- /dev/null
+++ b/arch/x86/include/asm/exec.h
@@ -0,0 +1 @@
+/* define arch_align_stack() here */
diff --git a/arch/x86/include/asm/futex.h b/arch/x86/include/asm/futex.h
index d09bb03653f0..71ecbcba1a4e 100644
--- a/arch/x86/include/asm/futex.h
+++ b/arch/x86/include/asm/futex.h
@@ -9,7 +9,6 @@
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #define __futex_atomic_op1(insn, ret, oldval, uaddr, oparg)	\
 	asm volatile("1:\t" insn "\n"				\
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 7ce0798b1b26..257d9cca214f 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -14,7 +14,6 @@
 
 #include <linux/sched.h>
 #include <linux/hardirq.h>
-#include <asm/system.h>
 
 struct pt_regs;
 struct user_i387_struct;
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 1f7e62517284..ee52760549f0 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -43,6 +43,15 @@ struct ucontext_ia32 {
 	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
 };
 
+struct ucontext_x32 {
+	unsigned int	  uc_flags;
+	unsigned int 	  uc_link;
+	stack_ia32_t	  uc_stack;
+	unsigned int	  uc__pad0;     /* needed for alignment */
+	struct sigcontext uc_mcontext;  /* the 64-bit sigcontext type */
+	compat_sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
 /* This matches struct stat64 in glibc2.2, hence the absolutely
  * insane amounts of padding around dev_t's.
  */
@@ -116,6 +125,15 @@ typedef struct compat_siginfo {
 			compat_clock_t _stime;
 		} _sigchld;
 
+		/* SIGCHLD (x32 version) */
+		struct {
+			unsigned int _pid;	/* which child */
+			unsigned int _uid;	/* sender's uid */
+			int _status;		/* exit code */
+			compat_s64 _utime;
+			compat_s64 _stime;
+		} _sigchld_x32;
+
 		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 		struct {
 			unsigned int _addr;	/* faulting insn/memory ref. */
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index f49253d75710..c5d1785373ed 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -14,6 +14,7 @@ void exit_idle(void);
 #else /* !CONFIG_X86_64 */
 static inline void enter_idle(void) { }
 static inline void exit_idle(void) { }
+static inline void __exit_idle(void) { }
 #endif /* CONFIG_X86_64 */
 
 void amd_e400_remove_cpu(int cpu);
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 690d1cc9a877..2c4943de5150 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -21,6 +21,15 @@
 #define IO_APIC_REDIR_LEVEL_TRIGGER	(1 << 15)
 #define IO_APIC_REDIR_MASKED		(1 << 16)
 
+struct io_apic_ops {
+	void		(*init)  (void);
+	unsigned int	(*read)  (unsigned int apic, unsigned int reg);
+	void		(*write) (unsigned int apic, unsigned int reg, unsigned int value);
+	void		(*modify)(unsigned int apic, unsigned int reg, unsigned int value);
+};
+
+void __init set_io_apic_ops(const struct io_apic_ops *);
+
 /*
  * The structure of the IO-APIC:
  */
diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h
index 4d8dcbdfc120..e7d1c194d272 100644
--- a/arch/x86/include/asm/kvm.h
+++ b/arch/x86/include/asm/kvm.h
@@ -321,4 +321,8 @@ struct kvm_xcrs {
 	__u64 padding[16];
 };
 
+/* definition of registers in kvm_run */
+struct kvm_sync_regs {
+};
+
 #endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 7b9cfc4878af..c222e1a1b12a 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -176,6 +176,7 @@ struct x86_emulate_ops {
 	void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt);
 	ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr);
 	int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val);
+	void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val);
 	int (*cpl)(struct x86_emulate_ctxt *ctxt);
 	int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest);
 	int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value);
@@ -388,7 +389,7 @@ bool x86_page_table_writing_insn(struct x86_emulate_ctxt *ctxt);
 #define EMULATION_INTERCEPTED 2
 int x86_emulate_insn(struct x86_emulate_ctxt *ctxt);
 int emulator_task_switch(struct x86_emulate_ctxt *ctxt,
-			 u16 tss_selector, int reason,
+			 u16 tss_selector, int idt_index, int reason,
 			 bool has_error_code, u32 error_code);
 int emulate_int_real(struct x86_emulate_ctxt *ctxt, int irq);
 #endif /* _ASM_X86_KVM_X86_EMULATE_H */
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 52d6640a5ca1..e216ba066e79 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -29,7 +29,7 @@
 #include <asm/msr-index.h>
 
 #define KVM_MAX_VCPUS 254
-#define KVM_SOFT_MAX_VCPUS 64
+#define KVM_SOFT_MAX_VCPUS 160
 #define KVM_MEMORY_SLOTS 32
 /* memory slots that does not exposed to userspace */
 #define KVM_PRIVATE_MEM_SLOTS 4
@@ -181,13 +181,6 @@ struct kvm_mmu_memory_cache {
 	void *objects[KVM_NR_MEM_OBJS];
 };
 
-#define NR_PTE_CHAIN_ENTRIES 5
-
-struct kvm_pte_chain {
-	u64 *parent_ptes[NR_PTE_CHAIN_ENTRIES];
-	struct hlist_node link;
-};
-
 /*
  * kvm_mmu_page_role, below, is defined as:
  *
@@ -427,12 +420,16 @@ struct kvm_vcpu_arch {
 
 	u64 last_guest_tsc;
 	u64 last_kernel_ns;
-	u64 last_tsc_nsec;
-	u64 last_tsc_write;
-	u32 virtual_tsc_khz;
+	u64 last_host_tsc;
+	u64 tsc_offset_adjustment;
+	u64 this_tsc_nsec;
+	u64 this_tsc_write;
+	u8  this_tsc_generation;
 	bool tsc_catchup;
-	u32  tsc_catchup_mult;
-	s8   tsc_catchup_shift;
+	bool tsc_always_catchup;
+	s8 virtual_tsc_shift;
+	u32 virtual_tsc_mult;
+	u32 virtual_tsc_khz;
 
 	atomic_t nmi_queued;  /* unprocessed asynchronous NMIs */
 	unsigned nmi_pending; /* NMI queued after currently running handler */
@@ -478,6 +475,21 @@ struct kvm_vcpu_arch {
 		u32 id;
 		bool send_user_only;
 	} apf;
+
+	/* OSVW MSRs (AMD only) */
+	struct {
+		u64 length;
+		u64 status;
+	} osvw;
+};
+
+struct kvm_lpage_info {
+	unsigned long rmap_pde;
+	int write_count;
+};
+
+struct kvm_arch_memory_slot {
+	struct kvm_lpage_info *lpage_info[KVM_NR_PAGE_SIZES - 1];
 };
 
 struct kvm_arch {
@@ -511,8 +523,12 @@ struct kvm_arch {
 	s64 kvmclock_offset;
 	raw_spinlock_t tsc_write_lock;
 	u64 last_tsc_nsec;
-	u64 last_tsc_offset;
 	u64 last_tsc_write;
+	u32 last_tsc_khz;
+	u64 cur_tsc_nsec;
+	u64 cur_tsc_write;
+	u64 cur_tsc_offset;
+	u8  cur_tsc_generation;
 
 	struct kvm_xen_hvm_config xen_hvm_config;
 
@@ -644,7 +660,7 @@ struct kvm_x86_ops {
 	u64 (*get_mt_mask)(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio);
 	int (*get_lpage_level)(void);
 	bool (*rdtscp_supported)(void);
-	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment);
+	void (*adjust_tsc_offset)(struct kvm_vcpu *vcpu, s64 adjustment, bool host);
 
 	void (*set_tdp_cr3)(struct kvm_vcpu *vcpu, unsigned long cr3);
 
@@ -652,7 +668,7 @@ struct kvm_x86_ops {
 
 	bool (*has_wbinvd_exit)(void);
 
-	void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz);
+	void (*set_tsc_khz)(struct kvm_vcpu *vcpu, u32 user_tsc_khz, bool scale);
 	void (*write_tsc_offset)(struct kvm_vcpu *vcpu, u64 offset);
 
 	u64 (*compute_tsc_offset)(struct kvm_vcpu *vcpu, u64 target_tsc);
@@ -674,6 +690,17 @@ struct kvm_arch_async_pf {
 
 extern struct kvm_x86_ops *kvm_x86_ops;
 
+static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
+					   s64 adjustment)
+{
+	kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, false);
+}
+
+static inline void adjust_tsc_offset_host(struct kvm_vcpu *vcpu, s64 adjustment)
+{
+	kvm_x86_ops->adjust_tsc_offset(vcpu, adjustment, true);
+}
+
 int kvm_mmu_module_init(void);
 void kvm_mmu_module_exit(void);
 
@@ -741,8 +768,8 @@ int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu);
 void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
 int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg);
 
-int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason,
-		    bool has_error_code, u32 error_code);
+int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int idt_index,
+		    int reason, bool has_error_code, u32 error_code);
 
 int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0);
 int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3);
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 9cdae5d47e8f..c8bed0da434a 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -3,7 +3,6 @@
 
 #include <linux/percpu.h>
 
-#include <asm/system.h>
 #include <linux/atomic.h>
 #include <asm/asm.h>
 
diff --git a/arch/x86/include/asm/mc146818rtc.h b/arch/x86/include/asm/mc146818rtc.h
index 0e8e85bb7c51..d354fb781c57 100644
--- a/arch/x86/include/asm/mc146818rtc.h
+++ b/arch/x86/include/asm/mc146818rtc.h
@@ -5,7 +5,6 @@
 #define _ASM_X86_MC146818RTC_H
 
 #include <asm/io.h>
-#include <asm/system.h>
 #include <asm/processor.h>
 #include <linux/mc146818rtc.h>
 
diff --git a/arch/x86/include/asm/mtrr.h b/arch/x86/include/asm/mtrr.h
index 4365ffdb461f..7e3f17f92c66 100644
--- a/arch/x86/include/asm/mtrr.h
+++ b/arch/x86/include/asm/mtrr.h
@@ -29,18 +29,18 @@
 
 #define	MTRR_IOCTL_BASE	'M'
 
-struct mtrr_sentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int type;     /*  Type of region   */
-};
-
 /* Warning: this structure has a different order from i386
    on x86-64. The 32bit emulation code takes care of that.
    But you need to use this for 64bit, otherwise your X server
    will break. */
 
 #ifdef __i386__
+struct mtrr_sentry {
+    unsigned long base;    /*  Base address     */
+    unsigned int size;    /*  Size of region   */
+    unsigned int type;     /*  Type of region   */
+};
+
 struct mtrr_gentry {
     unsigned int regnum;   /*  Register number  */
     unsigned long base;    /*  Base address     */
@@ -50,12 +50,20 @@ struct mtrr_gentry {
 
 #else /* __i386__ */
 
+struct mtrr_sentry {
+	__u64 base;		/*  Base address     */
+	__u32 size;		/*  Size of region   */
+	__u32 type;		/*  Type of region   */
+};
+
 struct mtrr_gentry {
-    unsigned long base;    /*  Base address     */
-    unsigned int size;    /*  Size of region   */
-    unsigned int regnum;   /*  Register number  */
-    unsigned int type;     /*  Type of region   */
+	__u64 base;		/*  Base address     */
+	__u32 size;		/*  Size of region   */
+	__u32 regnum;		/*  Register number  */
+	__u32 type;		/*  Type of region   */
+	__u32 _pad;		/*  Unused	     */
 };
+
 #endif /* !__i386__ */
 
 struct mtrr_var_range {
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index bce688d54c12..e21fdd10479f 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -55,7 +55,6 @@ extern unsigned long init_memory_mapping(unsigned long start,
 					 unsigned long end);
 
 extern void initmem_init(void);
-extern void free_initmem(void);
 
 #endif	/* !__ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index e8fb2c7a5f4f..2291895b1836 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -23,6 +23,7 @@
 #define ARCH_PERFMON_EVENTSEL_USR			(1ULL << 16)
 #define ARCH_PERFMON_EVENTSEL_OS			(1ULL << 17)
 #define ARCH_PERFMON_EVENTSEL_EDGE			(1ULL << 18)
+#define ARCH_PERFMON_EVENTSEL_PIN_CONTROL		(1ULL << 19)
 #define ARCH_PERFMON_EVENTSEL_INT			(1ULL << 20)
 #define ARCH_PERFMON_EVENTSEL_ANY			(1ULL << 21)
 #define ARCH_PERFMON_EVENTSEL_ENABLE			(1ULL << 22)
diff --git a/arch/x86/include/asm/posix_types.h b/arch/x86/include/asm/posix_types.h
index bb7133dc155d..3427b7798dbc 100644
--- a/arch/x86/include/asm/posix_types.h
+++ b/arch/x86/include/asm/posix_types.h
@@ -7,7 +7,9 @@
 #else
 # ifdef __i386__
 #  include "posix_types_32.h"
-# else
+# elif defined(__LP64__)
 #  include "posix_types_64.h"
+# else
+#  include "posix_types_x32.h"
 # endif
 #endif
diff --git a/arch/x86/include/asm/posix_types_32.h b/arch/x86/include/asm/posix_types_32.h
index f7d9adf82e53..99f262e04b91 100644
--- a/arch/x86/include/asm/posix_types_32.h
+++ b/arch/x86/include/asm/posix_types_32.h
@@ -7,79 +7,22 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
 typedef unsigned short	__kernel_mode_t;
+#define __kernel_mode_t __kernel_mode_t
+
 typedef unsigned short	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
+#define __kernel_nlink_t __kernel_nlink_t
+
 typedef unsigned short	__kernel_ipc_pid_t;
+#define __kernel_ipc_pid_t __kernel_ipc_pid_t
+
 typedef unsigned short	__kernel_uid_t;
 typedef unsigned short	__kernel_gid_t;
-typedef unsigned int	__kernel_size_t;
-typedef int		__kernel_ssize_t;
-typedef int		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-typedef unsigned int	__kernel_uid32_t;
-typedef unsigned int	__kernel_gid32_t;
+#define __kernel_uid_t __kernel_uid_t
 
-typedef unsigned short	__kernel_old_uid_t;
-typedef unsigned short	__kernel_old_gid_t;
 typedef unsigned short	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
-#if defined(__KERNEL__)
-
-#undef	__FD_SET
-#define __FD_SET(fd,fdsetp)					\
-	asm volatile("btsl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int)(fd)))
-
-#undef	__FD_CLR
-#define __FD_CLR(fd,fdsetp)					\
-	asm volatile("btrl %1,%0":				\
-		     "+m" (*(__kernel_fd_set *)(fdsetp))	\
-		     : "r" ((int) (fd)))
-
-#undef	__FD_ISSET
-#define __FD_ISSET(fd,fdsetp)					\
-	(__extension__						\
-	 ({							\
-	 unsigned char __result;				\
-	 asm volatile("btl %1,%2 ; setb %0"			\
-		      : "=q" (__result)				\
-		      : "r" ((int)(fd)),			\
-			"m" (*(__kernel_fd_set *)(fdsetp)));	\
-	 __result;						\
-}))
-
-#undef	__FD_ZERO
-#define __FD_ZERO(fdsetp)					\
-do {								\
-	int __d0, __d1;						\
-	asm volatile("cld ; rep ; stosl"			\
-		     : "=m" (*(__kernel_fd_set *)(fdsetp)),	\
-		       "=&c" (__d0), "=&D" (__d1)		\
-		     : "a" (0), "1" (__FDSET_LONGS),		\
-		       "2" ((__kernel_fd_set *)(fdsetp))	\
-		     : "memory");				\
-} while (0)
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_X86_POSIX_TYPES_32_H */
diff --git a/arch/x86/include/asm/posix_types_64.h b/arch/x86/include/asm/posix_types_64.h
index eb8d2d92b63e..cba0c1ead162 100644
--- a/arch/x86/include/asm/posix_types_64.h
+++ b/arch/x86/include/asm/posix_types_64.h
@@ -7,113 +7,13 @@
  * assume GCC is being used.
  */
 
-typedef unsigned long	__kernel_ino_t;
-typedef unsigned int	__kernel_mode_t;
-typedef unsigned long	__kernel_nlink_t;
-typedef long		__kernel_off_t;
-typedef int		__kernel_pid_t;
-typedef int		__kernel_ipc_pid_t;
-typedef unsigned int	__kernel_uid_t;
-typedef unsigned int	__kernel_gid_t;
-typedef unsigned long	__kernel_size_t;
-typedef long		__kernel_ssize_t;
-typedef long		__kernel_ptrdiff_t;
-typedef long		__kernel_time_t;
-typedef long		__kernel_suseconds_t;
-typedef long		__kernel_clock_t;
-typedef int		__kernel_timer_t;
-typedef int		__kernel_clockid_t;
-typedef int		__kernel_daddr_t;
-typedef char *		__kernel_caddr_t;
-typedef unsigned short	__kernel_uid16_t;
-typedef unsigned short	__kernel_gid16_t;
-
-#ifdef __GNUC__
-typedef long long	__kernel_loff_t;
-#endif
-
-typedef struct {
-	int	val[2];
-} __kernel_fsid_t;
-
 typedef unsigned short __kernel_old_uid_t;
 typedef unsigned short __kernel_old_gid_t;
-typedef __kernel_uid_t __kernel_uid32_t;
-typedef __kernel_gid_t __kernel_gid32_t;
+#define __kernel_old_uid_t __kernel_old_uid_t
 
 typedef unsigned long	__kernel_old_dev_t;
+#define __kernel_old_dev_t __kernel_old_dev_t
 
-#ifdef __KERNEL__
-
-#undef __FD_SET
-static inline void __FD_SET(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] |= (1UL<<_rem);
-}
-
-#undef __FD_CLR
-static inline void __FD_CLR(unsigned long fd, __kernel_fd_set *fdsetp)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	fdsetp->fds_bits[_tmp] &= ~(1UL<<_rem);
-}
-
-#undef __FD_ISSET
-static inline int __FD_ISSET(unsigned long fd, __const__ __kernel_fd_set *p)
-{
-	unsigned long _tmp = fd / __NFDBITS;
-	unsigned long _rem = fd % __NFDBITS;
-	return (p->fds_bits[_tmp] & (1UL<<_rem)) != 0;
-}
-
-/*
- * This will unroll the loop for the normal constant cases (8 or 32 longs,
- * for 256 and 1024-bit fd_sets respectively)
- */
-#undef __FD_ZERO
-static inline void __FD_ZERO(__kernel_fd_set *p)
-{
-	unsigned long *tmp = p->fds_bits;
-	int i;
-
-	if (__builtin_constant_p(__FDSET_LONGS)) {
-		switch (__FDSET_LONGS) {
-		case 32:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			tmp[16] = 0; tmp[17] = 0; tmp[18] = 0; tmp[19] = 0;
-			tmp[20] = 0; tmp[21] = 0; tmp[22] = 0; tmp[23] = 0;
-			tmp[24] = 0; tmp[25] = 0; tmp[26] = 0; tmp[27] = 0;
-			tmp[28] = 0; tmp[29] = 0; tmp[30] = 0; tmp[31] = 0;
-			return;
-		case 16:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			tmp[ 8] = 0; tmp[ 9] = 0; tmp[10] = 0; tmp[11] = 0;
-			tmp[12] = 0; tmp[13] = 0; tmp[14] = 0; tmp[15] = 0;
-			return;
-		case 8:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			tmp[ 4] = 0; tmp[ 5] = 0; tmp[ 6] = 0; tmp[ 7] = 0;
-			return;
-		case 4:
-			tmp[ 0] = 0; tmp[ 1] = 0; tmp[ 2] = 0; tmp[ 3] = 0;
-			return;
-		}
-	}
-	i = __FDSET_LONGS;
-	while (i) {
-		i--;
-		*tmp = 0;
-		tmp++;
-	}
-}
-
-#endif /* defined(__KERNEL__) */
+#include <asm-generic/posix_types.h>
 
 #endif /* _ASM_X86_POSIX_TYPES_64_H */
diff --git a/arch/x86/include/asm/posix_types_x32.h b/arch/x86/include/asm/posix_types_x32.h
new file mode 100644
index 000000000000..85f9bdafa93c
--- /dev/null
+++ b/arch/x86/include/asm/posix_types_x32.h
@@ -0,0 +1,19 @@
+#ifndef _ASM_X86_POSIX_TYPES_X32_H
+#define _ASM_X86_POSIX_TYPES_X32_H
+
+/*
+ * This file is only used by user-level software, so you need to
+ * be a little careful about namespace pollution etc.  Also, we cannot
+ * assume GCC is being used.
+ *
+ * These types should generally match the ones used by the 64-bit kernel,
+ *
+ */
+
+typedef long long __kernel_long_t;
+typedef unsigned long long __kernel_ulong_t;
+#define __kernel_long_t __kernel_long_t
+
+#include <asm/posix_types_64.h>
+
+#endif /* _ASM_X86_POSIX_TYPES_X32_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5533b30cac07..4fa7dcceb6c0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -14,13 +14,13 @@ struct mm_struct;
 #include <asm/sigcontext.h>
 #include <asm/current.h>
 #include <asm/cpufeature.h>
-#include <asm/system.h>
 #include <asm/page.h>
 #include <asm/pgtable_types.h>
 #include <asm/percpu.h>
 #include <asm/msr.h>
 #include <asm/desc_defs.h>
 #include <asm/nops.h>
+#include <asm/special_insns.h>
 
 #include <linux/personality.h>
 #include <linux/cpumask.h>
@@ -29,6 +29,15 @@ struct mm_struct;
 #include <linux/math64.h>
 #include <linux/init.h>
 #include <linux/err.h>
+#include <linux/irqflags.h>
+
+/*
+ * We handle most unaligned accesses in hardware.  On the other hand
+ * unaligned DMA can be quite expensive on some Nehalem processors.
+ *
+ * Based on this we disable the IP header alignment in network drivers.
+ */
+#define NET_IP_ALIGN	0
 
 #define HBP_NUM 4
 /*
@@ -454,7 +463,7 @@ struct thread_struct {
 	unsigned long           ptrace_dr7;
 	/* Fault info: */
 	unsigned long		cr2;
-	unsigned long		trap_no;
+	unsigned long		trap_nr;
 	unsigned long		error_code;
 	/* floating point and extended processor state */
 	struct fpu		fpu;
@@ -864,9 +873,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define IA32_PAGE_OFFSET	((current->personality & ADDR_LIMIT_3GB) ? \
 					0xc0000000 : 0xFFFFe000)
 
-#define TASK_SIZE		(test_thread_flag(TIF_IA32) ? \
+#define TASK_SIZE		(test_thread_flag(TIF_ADDR32) ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
-#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_IA32)) ? \
+#define TASK_SIZE_OF(child)	((test_tsk_thread_flag(child, TIF_ADDR32)) ? \
 					IA32_PAGE_OFFSET : TASK_SIZE_MAX)
 
 #define STACK_TOP		TASK_SIZE
@@ -888,6 +897,12 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.sp0 - 1)
 extern unsigned long KSTK_ESP(struct task_struct *task);
+
+/*
+ * User space RSP while inside the SYSCALL fast path
+ */
+DECLARE_PER_CPU(unsigned long, old_rsp);
+
 #endif /* CONFIG_X86_64 */
 
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
@@ -959,4 +974,14 @@ extern bool cpu_has_amd_erratum(const int *);
 #define cpu_has_amd_erratum(x)	(false)
 #endif /* CONFIG_CPU_SUP_AMD */
 
+void cpu_idle_wait(void);
+
+extern unsigned long arch_align_stack(unsigned long sp);
+extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
+
+void default_idle(void);
+bool set_pm_idle_to_default(void);
+
+void stop_this_cpu(void *dummy);
+
 #endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 35664547125b..dcfde52979c3 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -145,7 +145,6 @@ extern unsigned long
 convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs);
 extern void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 			 int error_code, int si_code);
-void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
 
 extern long syscall_trace_enter(struct pt_regs *);
 extern void syscall_trace_leave(struct pt_regs *);
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 5e641715c3fe..165466233ab0 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -212,7 +212,61 @@
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 extern const char early_idt_handlers[NUM_EXCEPTION_VECTORS][10];
-#endif
-#endif
+
+/*
+ * Load a segment. Fall back on loading the zero
+ * segment if something goes wrong..
+ */
+#define loadsegment(seg, value)						\
+do {									\
+	unsigned short __val = (value);					\
+									\
+	asm volatile("						\n"	\
+		     "1:	movl %k0,%%" #seg "		\n"	\
+									\
+		     ".section .fixup,\"ax\"			\n"	\
+		     "2:	xorl %k0,%k0			\n"	\
+		     "		jmp 1b				\n"	\
+		     ".previous					\n"	\
+									\
+		     _ASM_EXTABLE(1b, 2b)				\
+									\
+		     : "+r" (__val) : : "memory");			\
+} while (0)
+
+/*
+ * Save a segment register away
+ */
+#define savesegment(seg, value)				\
+	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
+
+/*
+ * x86_32 user gs accessors.
+ */
+#ifdef CONFIG_X86_32
+#ifdef CONFIG_X86_32_LAZY_GS
+#define get_user_gs(regs)	(u16)({unsigned long v; savesegment(gs, v); v;})
+#define set_user_gs(regs, v)	loadsegment(gs, (unsigned long)(v))
+#define task_user_gs(tsk)	((tsk)->thread.gs)
+#define lazy_save_gs(v)		savesegment(gs, (v))
+#define lazy_load_gs(v)		loadsegment(gs, (v))
+#else	/* X86_32_LAZY_GS */
+#define get_user_gs(regs)	(u16)((regs)->gs)
+#define set_user_gs(regs, v)	do { (regs)->gs = (v); } while (0)
+#define task_user_gs(tsk)	(task_pt_regs(tsk)->gs)
+#define lazy_save_gs(v)		do { } while (0)
+#define lazy_load_gs(v)		do { } while (0)
+#endif	/* X86_32_LAZY_GS */
+#endif	/* X86_32 */
+
+static inline unsigned long get_limit(unsigned long segment)
+{
+	unsigned long __limit;
+	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
+	return __limit + 1;
+}
+
+#endif /* !__ASSEMBLY__ */
+#endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_SEGMENT_H */
diff --git a/arch/x86/include/asm/sigcontext.h b/arch/x86/include/asm/sigcontext.h
index 04459d25e66e..4a085383af27 100644
--- a/arch/x86/include/asm/sigcontext.h
+++ b/arch/x86/include/asm/sigcontext.h
@@ -230,34 +230,37 @@ struct sigcontext {
  * User-space might still rely on the old definition:
  */
 struct sigcontext {
-	unsigned long r8;
-	unsigned long r9;
-	unsigned long r10;
-	unsigned long r11;
-	unsigned long r12;
-	unsigned long r13;
-	unsigned long r14;
-	unsigned long r15;
-	unsigned long rdi;
-	unsigned long rsi;
-	unsigned long rbp;
-	unsigned long rbx;
-	unsigned long rdx;
-	unsigned long rax;
-	unsigned long rcx;
-	unsigned long rsp;
-	unsigned long rip;
-	unsigned long eflags;		/* RFLAGS */
-	unsigned short cs;
-	unsigned short gs;
-	unsigned short fs;
-	unsigned short __pad0;
-	unsigned long err;
-	unsigned long trapno;
-	unsigned long oldmask;
-	unsigned long cr2;
+	__u64 r8;
+	__u64 r9;
+	__u64 r10;
+	__u64 r11;
+	__u64 r12;
+	__u64 r13;
+	__u64 r14;
+	__u64 r15;
+	__u64 rdi;
+	__u64 rsi;
+	__u64 rbp;
+	__u64 rbx;
+	__u64 rdx;
+	__u64 rax;
+	__u64 rcx;
+	__u64 rsp;
+	__u64 rip;
+	__u64 eflags;		/* RFLAGS */
+	__u16 cs;
+	__u16 gs;
+	__u16 fs;
+	__u16 __pad0;
+	__u64 err;
+	__u64 trapno;
+	__u64 oldmask;
+	__u64 cr2;
 	struct _fpstate __user *fpstate;	/* zero when no FPU context */
-	unsigned long reserved1[8];
+#ifndef __LP64__
+	__u32 __fpstate_pad;
+#endif
+	__u64 reserved1[8];
 };
 #endif /* !__KERNEL__ */
 
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
index 4e0fe26d27d3..7c7c27c97daa 100644
--- a/arch/x86/include/asm/sigframe.h
+++ b/arch/x86/include/asm/sigframe.h
@@ -59,12 +59,25 @@ struct rt_sigframe_ia32 {
 #endif /* defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION) */
 
 #ifdef CONFIG_X86_64
+
 struct rt_sigframe {
 	char __user *pretcode;
 	struct ucontext uc;
 	struct siginfo info;
 	/* fp state follows here */
 };
+
+#ifdef CONFIG_X86_X32_ABI
+
+struct rt_sigframe_x32 {
+	u64 pretcode;
+	struct ucontext_x32 uc;
+	compat_siginfo_t info;
+	/* fp state follows here */
+};
+
+#endif /* CONFIG_X86_X32_ABI */
+
 #endif /* CONFIG_X86_64 */
 
 #endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
new file mode 100644
index 000000000000..ada93b3b8c66
--- /dev/null
+++ b/arch/x86/include/asm/sighandling.h
@@ -0,0 +1,24 @@
+#ifndef _ASM_X86_SIGHANDLING_H
+#define _ASM_X86_SIGHANDLING_H
+
+#include <linux/compiler.h>
+#include <linux/ptrace.h>
+#include <linux/signal.h>
+
+#include <asm/processor-flags.h>
+
+#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
+
+#define __FIX_EFLAGS	(X86_EFLAGS_AC | X86_EFLAGS_OF | \
+			 X86_EFLAGS_DF | X86_EFLAGS_TF | X86_EFLAGS_SF | \
+			 X86_EFLAGS_ZF | X86_EFLAGS_AF | X86_EFLAGS_PF | \
+			 X86_EFLAGS_CF)
+
+void signal_fault(struct pt_regs *regs, void __user *frame, char *where);
+
+int restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc,
+		       unsigned long *pax);
+int setup_sigcontext(struct sigcontext __user *sc, void __user *fpstate,
+		     struct pt_regs *regs, unsigned long mask);
+
+#endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
new file mode 100644
index 000000000000..41fc93a2e225
--- /dev/null
+++ b/arch/x86/include/asm/special_insns.h
@@ -0,0 +1,199 @@
+#ifndef _ASM_X86_SPECIAL_INSNS_H
+#define _ASM_X86_SPECIAL_INSNS_H
+
+
+#ifdef __KERNEL__
+
+static inline void native_clts(void)
+{
+	asm volatile("clts");
+}
+
+/*
+ * Volatile isn't enough to prevent the compiler from reordering the
+ * read/write functions for the control registers and messing everything up.
+ * A memory clobber would solve the problem, but would prevent reordering of
+ * all loads stores around it, which can hurt performance. Solution is to
+ * use a variable and mimic reads and writes to it to enforce serialization
+ */
+static unsigned long __force_order;
+
+static inline unsigned long native_read_cr0(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr0(unsigned long val)
+{
+	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr2(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr2(unsigned long val)
+{
+	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr3(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline void native_write_cr3(unsigned long val)
+{
+	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
+}
+
+static inline unsigned long native_read_cr4(void)
+{
+	unsigned long val;
+	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
+	return val;
+}
+
+static inline unsigned long native_read_cr4_safe(void)
+{
+	unsigned long val;
+	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
+	 * exists, so it will never fail. */
+#ifdef CONFIG_X86_32
+	asm volatile("1: mov %%cr4, %0\n"
+		     "2:\n"
+		     _ASM_EXTABLE(1b, 2b)
+		     : "=r" (val), "=m" (__force_order) : "0" (0));
+#else
+	val = native_read_cr4();
+#endif
+	return val;
+}
+
+static inline void native_write_cr4(unsigned long val)
+{
+	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
+}
+
+#ifdef CONFIG_X86_64
+static inline unsigned long native_read_cr8(void)
+{
+	unsigned long cr8;
+	asm volatile("movq %%cr8,%0" : "=r" (cr8));
+	return cr8;
+}
+
+static inline void native_write_cr8(unsigned long val)
+{
+	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
+}
+#endif
+
+static inline void native_wbinvd(void)
+{
+	asm volatile("wbinvd": : :"memory");
+}
+
+extern void native_load_gs_index(unsigned);
+
+#ifdef CONFIG_PARAVIRT
+#include <asm/paravirt.h>
+#else
+
+static inline unsigned long read_cr0(void)
+{
+	return native_read_cr0();
+}
+
+static inline void write_cr0(unsigned long x)
+{
+	native_write_cr0(x);
+}
+
+static inline unsigned long read_cr2(void)
+{
+	return native_read_cr2();
+}
+
+static inline void write_cr2(unsigned long x)
+{
+	native_write_cr2(x);
+}
+
+static inline unsigned long read_cr3(void)
+{
+	return native_read_cr3();
+}
+
+static inline void write_cr3(unsigned long x)
+{
+	native_write_cr3(x);
+}
+
+static inline unsigned long read_cr4(void)
+{
+	return native_read_cr4();
+}
+
+static inline unsigned long read_cr4_safe(void)
+{
+	return native_read_cr4_safe();
+}
+
+static inline void write_cr4(unsigned long x)
+{
+	native_write_cr4(x);
+}
+
+static inline void wbinvd(void)
+{
+	native_wbinvd();
+}
+
+#ifdef CONFIG_X86_64
+
+static inline unsigned long read_cr8(void)
+{
+	return native_read_cr8();
+}
+
+static inline void write_cr8(unsigned long x)
+{
+	native_write_cr8(x);
+}
+
+static inline void load_gs_index(unsigned selector)
+{
+	native_load_gs_index(selector);
+}
+
+#endif
+
+/* Clear the 'TS' bit */
+static inline void clts(void)
+{
+	native_clts();
+}
+
+#endif/* CONFIG_PARAVIRT */
+
+#define stts() write_cr0(read_cr0() | X86_CR0_TS)
+
+static inline void clflush(volatile void *__p)
+{
+	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
+}
+
+#define nop() asm volatile ("nop")
+
+
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_SPECIAL_INSNS_H */
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 157517763565..b5d9533d2c38 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -38,7 +38,6 @@
 #include <asm/tsc.h>
 #include <asm/processor.h>
 #include <asm/percpu.h>
-#include <asm/system.h>
 #include <asm/desc.h>
 #include <linux/random.h>
 
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
new file mode 100644
index 000000000000..4ec45b3abba1
--- /dev/null
+++ b/arch/x86/include/asm/switch_to.h
@@ -0,0 +1,129 @@
+#ifndef _ASM_X86_SWITCH_TO_H
+#define _ASM_X86_SWITCH_TO_H
+
+struct task_struct; /* one of the stranger aspects of C forward declarations */
+struct task_struct *__switch_to(struct task_struct *prev,
+				struct task_struct *next);
+struct tss_struct;
+void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
+		      struct tss_struct *tss);
+
+#ifdef CONFIG_X86_32
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary							\
+	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
+	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
+#define __switch_canary_oparam						\
+	, [stack_canary] "=m" (stack_canary.canary)
+#define __switch_canary_iparam						\
+	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else	/* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif	/* CC_STACKPROTECTOR */
+
+/*
+ * Saving eflags is important. It switches not only IOPL between tasks,
+ * it also protects other tasks from NT leaking through sysenter etc.
+ */
+#define switch_to(prev, next, last)					\
+do {									\
+	/*								\
+	 * Context-switching clobbers all registers, so we clobber	\
+	 * them explicitly, via unused output variables.		\
+	 * (EAX and EBP is not listed because EBP is saved/restored	\
+	 * explicitly for wchan access and EAX is the return value of	\
+	 * __switch_to())						\
+	 */								\
+	unsigned long ebx, ecx, edx, esi, edi;				\
+									\
+	asm volatile("pushfl\n\t"		/* save    flags */	\
+		     "pushl %%ebp\n\t"		/* save    EBP   */	\
+		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
+		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
+		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
+		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
+		     __switch_canary					\
+		     "jmp __switch_to\n"	/* regparm call  */	\
+		     "1:\t"						\
+		     "popl %%ebp\n\t"		/* restore EBP   */	\
+		     "popfl\n"			/* restore flags */	\
+									\
+		     /* output parameters */				\
+		     : [prev_sp] "=m" (prev->thread.sp),		\
+		       [prev_ip] "=m" (prev->thread.ip),		\
+		       "=a" (last),					\
+									\
+		       /* clobbered output registers: */		\
+		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
+		       "=S" (esi), "=D" (edi)				\
+		       							\
+		       __switch_canary_oparam				\
+									\
+		       /* input parameters: */				\
+		     : [next_sp]  "m" (next->thread.sp),		\
+		       [next_ip]  "m" (next->thread.ip),		\
+		       							\
+		       /* regparm parameters for __switch_to(): */	\
+		       [prev]     "a" (prev),				\
+		       [next]     "d" (next)				\
+									\
+		       __switch_canary_iparam				\
+									\
+		     : /* reloaded segment registers */			\
+			"memory");					\
+} while (0)
+
+#else /* CONFIG_X86_32 */
+
+/* frame pointer must be last for get_wchan */
+#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
+#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
+
+#define __EXTRA_CLOBBER  \
+	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
+	  "r12", "r13", "r14", "r15"
+
+#ifdef CONFIG_CC_STACKPROTECTOR
+#define __switch_canary							  \
+	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
+	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
+#define __switch_canary_oparam						  \
+	, [gs_canary] "=m" (irq_stack_union.stack_canary)
+#define __switch_canary_iparam						  \
+	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
+#else	/* CC_STACKPROTECTOR */
+#define __switch_canary
+#define __switch_canary_oparam
+#define __switch_canary_iparam
+#endif	/* CC_STACKPROTECTOR */
+
+/* Save restore flags to clear handle leaking NT */
+#define switch_to(prev, next, last) \
+	asm volatile(SAVE_CONTEXT					  \
+	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
+	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
+	     "call __switch_to\n\t"					  \
+	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
+	     __switch_canary						  \
+	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
+	     "movq %%rax,%%rdi\n\t" 					  \
+	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"		  \
+	     "jnz   ret_from_fork\n\t"					  \
+	     RESTORE_CONTEXT						  \
+	     : "=a" (last)					  	  \
+	       __switch_canary_oparam					  \
+	     : [next] "S" (next), [prev] "D" (prev),			  \
+	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
+	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
+	       [_tif_fork] "i" (_TIF_FORK),			  	  \
+	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
+	       [current_task] "m" (current_task)			  \
+	       __switch_canary_iparam					  \
+	     : "memory", "cc" __EXTRA_CLOBBER)
+
+#endif /* CONFIG_X86_32 */
+
+#endif /* _ASM_X86_SWITCH_TO_H */
diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h
index cb238526a9f1..3fda9db48819 100644
--- a/arch/x86/include/asm/sys_ia32.h
+++ b/arch/x86/include/asm/sys_ia32.h
@@ -10,6 +10,8 @@
 #ifndef _ASM_X86_SYS_IA32_H
 #define _ASM_X86_SYS_IA32_H
 
+#ifdef CONFIG_COMPAT
+
 #include <linux/compiler.h>
 #include <linux/linkage.h>
 #include <linux/types.h>
@@ -36,8 +38,6 @@ asmlinkage long sys32_rt_sigaction(int, struct sigaction32 __user *,
 				   struct sigaction32 __user *, unsigned int);
 asmlinkage long sys32_sigaction(int, struct old_sigaction32 __user *,
 				struct old_sigaction32 __user *);
-asmlinkage long sys32_rt_sigprocmask(int, compat_sigset_t __user *,
-				     compat_sigset_t __user *, unsigned int);
 asmlinkage long sys32_alarm(unsigned int);
 
 asmlinkage long sys32_waitpid(compat_pid_t, unsigned int *, int);
@@ -83,4 +83,7 @@ asmlinkage long sys32_ipc(u32, int, int, int, compat_uptr_t, u32);
 
 asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int,
 				    const char __user *);
+
+#endif /* CONFIG_COMPAT */
+
 #endif /* _ASM_X86_SYS_IA32_H */
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index d962e5652a73..386b78686c4d 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -16,6 +16,7 @@
 #include <linux/sched.h>
 #include <linux/err.h>
 #include <asm/asm-offsets.h>	/* For NR_syscalls */
+#include <asm/unistd.h>
 
 extern const unsigned long sys_call_table[];
 
@@ -26,13 +27,13 @@ extern const unsigned long sys_call_table[];
  */
 static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
 {
-	return regs->orig_ax;
+	return regs->orig_ax & __SYSCALL_MASK;
 }
 
 static inline void syscall_rollback(struct task_struct *task,
 				    struct pt_regs *regs)
 {
-	regs->ax = regs->orig_ax;
+	regs->ax = regs->orig_ax & __SYSCALL_MASK;
 }
 
 static inline long syscall_get_error(struct task_struct *task,
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
deleted file mode 100644
index 2d2f01ce6dcb..000000000000
--- a/arch/x86/include/asm/system.h
+++ /dev/null
@@ -1,523 +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: */
-#if defined(CONFIG_IA32_EMULATION) || !defined(CONFIG_X86_64)
-# define AT_VECTOR_SIZE_ARCH 2
-#else /* else it's non-compat x86-64 */
-# define AT_VECTOR_SIZE_ARCH 1
-#endif
-
-struct task_struct; /* one of the stranger aspects of C forward declarations */
-struct task_struct *__switch_to(struct task_struct *prev,
-				struct task_struct *next);
-struct tss_struct;
-void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
-		      struct tss_struct *tss);
-extern void show_regs_common(void);
-
-#ifdef CONFIG_X86_32
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							\
-	"movl %P[task_canary](%[next]), %%ebx\n\t"			\
-	"movl %%ebx, "__percpu_arg([stack_canary])"\n\t"
-#define __switch_canary_oparam						\
-	, [stack_canary] "=m" (stack_canary.canary)
-#define __switch_canary_iparam						\
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
-
-/*
- * Saving eflags is important. It switches not only IOPL between tasks,
- * it also protects other tasks from NT leaking through sysenter etc.
- */
-#define switch_to(prev, next, last)					\
-do {									\
-	/*								\
-	 * Context-switching clobbers all registers, so we clobber	\
-	 * them explicitly, via unused output variables.		\
-	 * (EAX and EBP is not listed because EBP is saved/restored	\
-	 * explicitly for wchan access and EAX is the return value of	\
-	 * __switch_to())						\
-	 */								\
-	unsigned long ebx, ecx, edx, esi, edi;				\
-									\
-	asm volatile("pushfl\n\t"		/* save    flags */	\
-		     "pushl %%ebp\n\t"		/* save    EBP   */	\
-		     "movl %%esp,%[prev_sp]\n\t"	/* save    ESP   */ \
-		     "movl %[next_sp],%%esp\n\t"	/* restore ESP   */ \
-		     "movl $1f,%[prev_ip]\n\t"	/* save    EIP   */	\
-		     "pushl %[next_ip]\n\t"	/* restore EIP   */	\
-		     __switch_canary					\
-		     "jmp __switch_to\n"	/* regparm call  */	\
-		     "1:\t"						\
-		     "popl %%ebp\n\t"		/* restore EBP   */	\
-		     "popfl\n"			/* restore flags */	\
-									\
-		     /* output parameters */				\
-		     : [prev_sp] "=m" (prev->thread.sp),		\
-		       [prev_ip] "=m" (prev->thread.ip),		\
-		       "=a" (last),					\
-									\
-		       /* clobbered output registers: */		\
-		       "=b" (ebx), "=c" (ecx), "=d" (edx),		\
-		       "=S" (esi), "=D" (edi)				\
-		       							\
-		       __switch_canary_oparam				\
-									\
-		       /* input parameters: */				\
-		     : [next_sp]  "m" (next->thread.sp),		\
-		       [next_ip]  "m" (next->thread.ip),		\
-		       							\
-		       /* regparm parameters for __switch_to(): */	\
-		       [prev]     "a" (prev),				\
-		       [next]     "d" (next)				\
-									\
-		       __switch_canary_iparam				\
-									\
-		     : /* reloaded segment registers */			\
-			"memory");					\
-} while (0)
-
-/*
- * disable hlt during certain critical i/o operations
- */
-#define HAVE_DISABLE_HLT
-#else
-
-/* frame pointer must be last for get_wchan */
-#define SAVE_CONTEXT    "pushf ; pushq %%rbp ; movq %%rsi,%%rbp\n\t"
-#define RESTORE_CONTEXT "movq %%rbp,%%rsi ; popq %%rbp ; popf\t"
-
-#define __EXTRA_CLOBBER  \
-	, "rcx", "rbx", "rdx", "r8", "r9", "r10", "r11", \
-	  "r12", "r13", "r14", "r15"
-
-#ifdef CONFIG_CC_STACKPROTECTOR
-#define __switch_canary							  \
-	"movq %P[task_canary](%%rsi),%%r8\n\t"				  \
-	"movq %%r8,"__percpu_arg([gs_canary])"\n\t"
-#define __switch_canary_oparam						  \
-	, [gs_canary] "=m" (irq_stack_union.stack_canary)
-#define __switch_canary_iparam						  \
-	, [task_canary] "i" (offsetof(struct task_struct, stack_canary))
-#else	/* CC_STACKPROTECTOR */
-#define __switch_canary
-#define __switch_canary_oparam
-#define __switch_canary_iparam
-#endif	/* CC_STACKPROTECTOR */
-
-/* Save restore flags to clear handle leaking NT */
-#define switch_to(prev, next, last) \
-	asm volatile(SAVE_CONTEXT					  \
-	     "movq %%rsp,%P[threadrsp](%[prev])\n\t" /* save RSP */	  \
-	     "movq %P[threadrsp](%[next]),%%rsp\n\t" /* restore RSP */	  \
-	     "call __switch_to\n\t"					  \
-	     "movq "__percpu_arg([current_task])",%%rsi\n\t"		  \
-	     __switch_canary						  \
-	     "movq %P[thread_info](%%rsi),%%r8\n\t"			  \
-	     "movq %%rax,%%rdi\n\t" 					  \
-	     "testl  %[_tif_fork],%P[ti_flags](%%r8)\n\t"		  \
-	     "jnz   ret_from_fork\n\t"					  \
-	     RESTORE_CONTEXT						  \
-	     : "=a" (last)					  	  \
-	       __switch_canary_oparam					  \
-	     : [next] "S" (next), [prev] "D" (prev),			  \
-	       [threadrsp] "i" (offsetof(struct task_struct, thread.sp)), \
-	       [ti_flags] "i" (offsetof(struct thread_info, flags)),	  \
-	       [_tif_fork] "i" (_TIF_FORK),			  	  \
-	       [thread_info] "i" (offsetof(struct task_struct, stack)),   \
-	       [current_task] "m" (current_task)			  \
-	       __switch_canary_iparam					  \
-	     : "memory", "cc" __EXTRA_CLOBBER)
-#endif
-
-#ifdef __KERNEL__
-
-extern void native_load_gs_index(unsigned);
-
-/*
- * Load a segment. Fall back on loading the zero
- * segment if something goes wrong..
- */
-#define loadsegment(seg, value)						\
-do {									\
-	unsigned short __val = (value);					\
-									\
-	asm volatile("						\n"	\
-		     "1:	movl %k0,%%" #seg "		\n"	\
-									\
-		     ".section .fixup,\"ax\"			\n"	\
-		     "2:	xorl %k0,%k0			\n"	\
-		     "		jmp 1b				\n"	\
-		     ".previous					\n"	\
-									\
-		     _ASM_EXTABLE(1b, 2b)				\
-									\
-		     : "+r" (__val) : : "memory");			\
-} while (0)
-
-/*
- * Save a segment register away
- */
-#define savesegment(seg, value)				\
-	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
-
-/*
- * x86_32 user gs accessors.
- */
-#ifdef CONFIG_X86_32
-#ifdef CONFIG_X86_32_LAZY_GS
-#define get_user_gs(regs)	(u16)({unsigned long v; savesegment(gs, v); v;})
-#define set_user_gs(regs, v)	loadsegment(gs, (unsigned long)(v))
-#define task_user_gs(tsk)	((tsk)->thread.gs)
-#define lazy_save_gs(v)		savesegment(gs, (v))
-#define lazy_load_gs(v)		loadsegment(gs, (v))
-#else	/* X86_32_LAZY_GS */
-#define get_user_gs(regs)	(u16)((regs)->gs)
-#define set_user_gs(regs, v)	do { (regs)->gs = (v); } while (0)
-#define task_user_gs(tsk)	(task_pt_regs(tsk)->gs)
-#define lazy_save_gs(v)		do { } while (0)
-#define lazy_load_gs(v)		do { } while (0)
-#endif	/* X86_32_LAZY_GS */
-#endif	/* X86_32 */
-
-static inline unsigned long get_limit(unsigned long segment)
-{
-	unsigned long __limit;
-	asm("lsll %1,%0" : "=r" (__limit) : "r" (segment));
-	return __limit + 1;
-}
-
-static inline void native_clts(void)
-{
-	asm volatile("clts");
-}
-
-/*
- * Volatile isn't enough to prevent the compiler from reordering the
- * read/write functions for the control registers and messing everything up.
- * A memory clobber would solve the problem, but would prevent reordering of
- * all loads stores around it, which can hurt performance. Solution is to
- * use a variable and mimic reads and writes to it to enforce serialization
- */
-static unsigned long __force_order;
-
-static inline unsigned long native_read_cr0(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr0,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr0(unsigned long val)
-{
-	asm volatile("mov %0,%%cr0": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr2(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr2,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr2(unsigned long val)
-{
-	asm volatile("mov %0,%%cr2": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr3(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr3,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline void native_write_cr3(unsigned long val)
-{
-	asm volatile("mov %0,%%cr3": : "r" (val), "m" (__force_order));
-}
-
-static inline unsigned long native_read_cr4(void)
-{
-	unsigned long val;
-	asm volatile("mov %%cr4,%0\n\t" : "=r" (val), "=m" (__force_order));
-	return val;
-}
-
-static inline unsigned long native_read_cr4_safe(void)
-{
-	unsigned long val;
-	/* This could fault if %cr4 does not exist. In x86_64, a cr4 always
-	 * exists, so it will never fail. */
-#ifdef CONFIG_X86_32
-	asm volatile("1: mov %%cr4, %0\n"
-		     "2:\n"
-		     _ASM_EXTABLE(1b, 2b)
-		     : "=r" (val), "=m" (__force_order) : "0" (0));
-#else
-	val = native_read_cr4();
-#endif
-	return val;
-}
-
-static inline void native_write_cr4(unsigned long val)
-{
-	asm volatile("mov %0,%%cr4": : "r" (val), "m" (__force_order));
-}
-
-#ifdef CONFIG_X86_64
-static inline unsigned long native_read_cr8(void)
-{
-	unsigned long cr8;
-	asm volatile("movq %%cr8,%0" : "=r" (cr8));
-	return cr8;
-}
-
-static inline void native_write_cr8(unsigned long val)
-{
-	asm volatile("movq %0,%%cr8" :: "r" (val) : "memory");
-}
-#endif
-
-static inline void native_wbinvd(void)
-{
-	asm volatile("wbinvd": : :"memory");
-}
-
-#ifdef CONFIG_PARAVIRT
-#include <asm/paravirt.h>
-#else
-
-static inline unsigned long read_cr0(void)
-{
-	return native_read_cr0();
-}
-
-static inline void write_cr0(unsigned long x)
-{
-	native_write_cr0(x);
-}
-
-static inline unsigned long read_cr2(void)
-{
-	return native_read_cr2();
-}
-
-static inline void write_cr2(unsigned long x)
-{
-	native_write_cr2(x);
-}
-
-static inline unsigned long read_cr3(void)
-{
-	return native_read_cr3();
-}
-
-static inline void write_cr3(unsigned long x)
-{
-	native_write_cr3(x);
-}
-
-static inline unsigned long read_cr4(void)
-{
-	return native_read_cr4();
-}
-
-static inline unsigned long read_cr4_safe(void)
-{
-	return native_read_cr4_safe();
-}
-
-static inline void write_cr4(unsigned long x)
-{
-	native_write_cr4(x);
-}
-
-static inline void wbinvd(void)
-{
-	native_wbinvd();
-}
-
-#ifdef CONFIG_X86_64
-
-static inline unsigned long read_cr8(void)
-{
-	return native_read_cr8();
-}
-
-static inline void write_cr8(unsigned long x)
-{
-	native_write_cr8(x);
-}
-
-static inline void load_gs_index(unsigned selector)
-{
-	native_load_gs_index(selector);
-}
-
-#endif
-
-/* Clear the 'TS' bit */
-static inline void clts(void)
-{
-	native_clts();
-}
-
-#endif/* CONFIG_PARAVIRT */
-
-#define stts() write_cr0(read_cr0() | X86_CR0_TS)
-
-#endif /* __KERNEL__ */
-
-static inline void clflush(volatile void *__p)
-{
-	asm volatile("clflush %0" : "+m" (*(volatile char __force *)__p));
-}
-
-#define nop() asm volatile ("nop")
-
-void disable_hlt(void);
-void enable_hlt(void);
-
-void cpu_idle_wait(void);
-
-extern unsigned long arch_align_stack(unsigned long sp);
-extern void free_init_pages(char *what, unsigned long begin, unsigned long end);
-
-void default_idle(void);
-bool set_pm_idle_to_default(void);
-
-void stop_this_cpu(void *dummy);
-
-/*
- * 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 __always_inline void rdtsc_barrier(void)
-{
-	alternative(ASM_NOP3, "mfence", X86_FEATURE_MFENCE_RDTSC);
-	alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC);
-}
-
-/*
- * We handle most unaligned accesses in hardware.  On the other hand
- * unaligned DMA can be quite expensive on some Nehalem processors.
- *
- * Based on this we disable the IP header alignment in network drivers.
- */
-#define NET_IP_ALIGN	0
-#endif /* _ASM_X86_SYSTEM_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index cfd8144d5527..ad6df8ccd715 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -86,7 +86,7 @@ struct thread_info {
 #define TIF_MCE_NOTIFY		10	/* notify userspace of an MCE */
 #define TIF_USER_RETURN_NOTIFY	11	/* notify kernel of userspace return */
 #define TIF_NOTSC		16	/* TSC is not accessible in userland */
-#define TIF_IA32		17	/* 32bit process */
+#define TIF_IA32		17	/* IA32 compatibility process */
 #define TIF_FORK		18	/* ret_from_fork */
 #define TIF_MEMDIE		20	/* is terminating due to OOM killer */
 #define TIF_DEBUG		21	/* uses debug registers */
@@ -95,6 +95,8 @@ struct thread_info {
 #define TIF_BLOCKSTEP		25	/* set when we want DEBUGCTLMSR_BTF */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
 #define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
+#define TIF_ADDR32		29	/* 32-bit address space on 64 bits */
+#define TIF_X32			30	/* 32-bit native x86-64 binary */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -116,6 +118,8 @@ struct thread_info {
 #define _TIF_BLOCKSTEP		(1 << TIF_BLOCKSTEP)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
+#define _TIF_ADDR32		(1 << TIF_ADDR32)
+#define _TIF_X32		(1 << TIF_X32)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
@@ -262,6 +266,18 @@ static inline void set_restore_sigmask(void)
 	ti->status |= TS_RESTORE_SIGMASK;
 	set_bit(TIF_SIGPENDING, (unsigned long *)&ti->flags);
 }
+
+static inline bool is_ia32_task(void)
+{
+#ifdef CONFIG_X86_32
+	return true;
+#endif
+#ifdef CONFIG_IA32_EMULATION
+	if (current_thread_info()->status & TS_COMPAT)
+		return true;
+#endif
+	return false;
+}
 #endif	/* !__ASSEMBLY__ */
 
 #ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 169be8938b96..c0e108e08079 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -5,7 +5,7 @@
 #include <linux/sched.h>
 
 #include <asm/processor.h>
-#include <asm/system.h>
+#include <asm/special_insns.h>
 
 #ifdef CONFIG_PARAVIRT
 #include <asm/paravirt.h>
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 0012d0902c5f..88eae2aec619 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -89,4 +89,29 @@ asmlinkage void smp_thermal_interrupt(void);
 asmlinkage void mce_threshold_interrupt(void);
 #endif
 
+/* Interrupts/Exceptions */
+enum {
+	X86_TRAP_DE = 0,	/*  0, Divide-by-zero */
+	X86_TRAP_DB,		/*  1, Debug */
+	X86_TRAP_NMI,		/*  2, Non-maskable Interrupt */
+	X86_TRAP_BP,		/*  3, Breakpoint */
+	X86_TRAP_OF,		/*  4, Overflow */
+	X86_TRAP_BR,		/*  5, Bound Range Exceeded */
+	X86_TRAP_UD,		/*  6, Invalid Opcode */
+	X86_TRAP_NM,		/*  7, Device Not Available */
+	X86_TRAP_DF,		/*  8, Double Fault */
+	X86_TRAP_OLD_MF,	/*  9, Coprocessor Segment Overrun */
+	X86_TRAP_TS,		/* 10, Invalid TSS */
+	X86_TRAP_NP,		/* 11, Segment Not Present */
+	X86_TRAP_SS,		/* 12, Stack Segment Fault */
+	X86_TRAP_GP,		/* 13, General Protection Fault */
+	X86_TRAP_PF,		/* 14, Page Fault */
+	X86_TRAP_SPURIOUS,	/* 15, Spurious Interrupt */
+	X86_TRAP_MF,		/* 16, x87 Floating-Point Exception */
+	X86_TRAP_AC,		/* 17, Alignment Check */
+	X86_TRAP_MC,		/* 18, Machine Check */
+	X86_TRAP_XF,		/* 19, SIMD Floating-Point Exception */
+	X86_TRAP_IRET = 32,	/* 32, IRET Exception */
+};
+
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 15d99153a96d..c91e8b9d588b 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -61,7 +61,7 @@ extern void check_tsc_sync_source(int cpu);
 extern void check_tsc_sync_target(void);
 
 extern int notsc_setup(char *);
-extern void save_sched_clock_state(void);
-extern void restore_sched_clock_state(void);
+extern void tsc_save_sched_clock_state(void);
+extern void tsc_restore_sched_clock_state(void);
 
 #endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 21f77b89e47a..37cdc9d99bb1 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -1,7 +1,17 @@
 #ifndef _ASM_X86_UNISTD_H
 #define _ASM_X86_UNISTD_H 1
 
+/* x32 syscall flag bit */
+#define __X32_SYSCALL_BIT	0x40000000
+
 #ifdef __KERNEL__
+
+# ifdef CONFIG_X86_X32_ABI
+#  define __SYSCALL_MASK (~(__X32_SYSCALL_BIT))
+# else
+#  define __SYSCALL_MASK (~0)
+# endif
+
 # ifdef CONFIG_X86_32
 
 #  include <asm/unistd_32.h>
@@ -14,6 +24,7 @@
 # else
 
 #  include <asm/unistd_64.h>
+#  include <asm/unistd_64_x32.h>
 #  define __ARCH_WANT_COMPAT_SYS_TIME
 
 # endif
@@ -52,8 +63,10 @@
 #else
 # ifdef __i386__
 #  include <asm/unistd_32.h>
-# else
+# elif defined(__LP64__)
 #  include <asm/unistd_64.h>
+# else
+#  include <asm/unistd_x32.h>
 # endif
 #endif
 
diff --git a/arch/x86/include/asm/vgtod.h b/arch/x86/include/asm/vgtod.h
index 815285bcaceb..8b38be2de9e1 100644
--- a/arch/x86/include/asm/vgtod.h
+++ b/arch/x86/include/asm/vgtod.h
@@ -5,13 +5,8 @@
 #include <linux/clocksource.h>
 
 struct vsyscall_gtod_data {
-	seqlock_t	lock;
+	seqcount_t	seq;
 
-	/* open coded 'struct timespec' */
-	time_t		wall_time_sec;
-	u32		wall_time_nsec;
-
-	struct timezone sys_tz;
 	struct { /* extract of a clocksource struct */
 		int vclock_mode;
 		cycle_t	cycle_last;
@@ -19,8 +14,16 @@ struct vsyscall_gtod_data {
 		u32	mult;
 		u32	shift;
 	} clock;
-	struct timespec wall_to_monotonic;
+
+	/* open coded 'struct timespec' */
+	time_t		wall_time_sec;
+	u32		wall_time_nsec;
+	u32		monotonic_time_nsec;
+	time_t		monotonic_time_sec;
+
+	struct timezone sys_tz;
 	struct timespec wall_time_coarse;
+	struct timespec monotonic_time_coarse;
 };
 extern struct vsyscall_gtod_data vsyscall_gtod_data;
 
diff --git a/arch/x86/include/asm/virtext.h b/arch/x86/include/asm/virtext.h
index e0f9aa16358b..5da71c27cc59 100644
--- a/arch/x86/include/asm/virtext.h
+++ b/arch/x86/include/asm/virtext.h
@@ -16,7 +16,6 @@
 #define _ASM_X86_VIRTEX_H
 
 #include <asm/processor.h>
-#include <asm/system.h>
 
 #include <asm/vmx.h>
 #include <asm/svm.h>
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..6fe6767b7124
--- /dev/null
+++ b/arch/x86/include/asm/word-at-a-time.h
@@ -0,0 +1,46 @@
+#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);
+}
+
+#endif /* _ASM_WORD_AT_A_TIME_H */
diff --git a/arch/x86/include/asm/x2apic.h b/arch/x86/include/asm/x2apic.h
index 6bf5b8e478c0..92e54abf89e0 100644
--- a/arch/x86/include/asm/x2apic.h
+++ b/arch/x86/include/asm/x2apic.h
@@ -18,6 +18,11 @@ static const struct cpumask *x2apic_target_cpus(void)
 	return cpu_online_mask;
 }
 
+static int x2apic_apic_id_valid(int apicid)
+{
+	return 1;
+}
+
 static int x2apic_apic_id_registered(void)
 {
 	return 1;
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 517d4767ffdd..baaca8defec8 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -145,9 +145,11 @@ struct x86_init_ops {
 /**
  * struct x86_cpuinit_ops - platform specific cpu hotplug setups
  * @setup_percpu_clockev:	set up the per cpu clock event device
+ * @early_percpu_clock_init:	early init of the per cpu clock event device
  */
 struct x86_cpuinit_ops {
 	void (*setup_percpu_clockev)(void);
+	void (*early_percpu_clock_init)(void);
 	void (*fixup_cpu_id)(struct cpuinfo_x86 *c, int node);
 };
 
@@ -160,6 +162,8 @@ struct x86_cpuinit_ops {
  * @is_untracked_pat_range	exclude from PAT logic
  * @nmi_init			enable NMI on cpus
  * @i8042_detect		pre-detect if i8042 controller exists
+ * @save_sched_clock_state:	save state for sched_clock() on suspend
+ * @restore_sched_clock_state:	restore state for sched_clock() on resume
  */
 struct x86_platform_ops {
 	unsigned long (*calibrate_tsc)(void);
@@ -171,6 +175,8 @@ struct x86_platform_ops {
 	void (*nmi_init)(void);
 	unsigned char (*get_nmi_reason)(void);
 	int (*i8042_detect)(void);
+	void (*save_sched_clock_state)(void);
+	void (*restore_sched_clock_state)(void);
 };
 
 struct pci_dev;