Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux-2.6-cpumask into merge-rr-cpumask

Conflicts:
	arch/x86/kernel/io_apic.c
	kernel/rcuclassic.c
	kernel/sched.c
	kernel/time/tick-sched.c

Signed-off-by: Mike Travis <travis@sgi.com>
[ mingo@elte.hu: backmerged typo fix for io_apic.c ]
Signed-off-by: Ingo Molnar <mingo@elte.hu>

54 files changed, 877 insertions, 447 deletions

diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 360010322711..9fa9dcdf344b 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -168,7 +168,15 @@ static inline void __change_bit(int nr, volatile unsigned long *addr)
  */
 static inline void change_bit(int nr, volatile unsigned long *addr)
 {
-        asm volatile(LOCK_PREFIX "btc %1,%0" : ADDR : "Ir" (nr));
+        if (IS_IMMEDIATE(nr)) {
+                asm volatile(LOCK_PREFIX "xorb %1,%0"
+                        : CONST_MASK_ADDR(nr, addr)
+                        : "iq" ((u8)CONST_MASK(nr)));
+        } else {
+                asm volatile(LOCK_PREFIX "btc %1,%0"
+                        : BITOP_ADDR(addr)
+                        : "Ir" (nr));
+        }
 }
 
 /**
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index 3def2065fcea..d9cf1cd156d2 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -9,7 +9,7 @@
 #ifdef CONFIG_X86_32
 # define __BUG_C0       "2:\t.long 1b, %c0\n"
 #else
-# define __BUG_C0       "2:\t.quad 1b, %c0\n"
+# define __BUG_C0       "2:\t.long 1b - 2b, %c0 - 2b\n"
 #endif
 
 #define BUG()                                                   \
diff --git a/arch/x86/include/asm/byteorder.h b/arch/x86/include/asm/byteorder.h
index e02ae2d89acf..f110ad417df3 100644
--- a/arch/x86/include/asm/byteorder.h
+++ b/arch/x86/include/asm/byteorder.h
@@ -4,26 +4,33 @@
 #include <asm/types.h>
 #include <linux/compiler.h>
 
-#ifdef __GNUC__
+#define __LITTLE_ENDIAN
 
-#ifdef __i386__
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
+static inline __attribute_const__ __u32 __arch_swab32(__u32 val)
 {
-#ifdef CONFIG_X86_BSWAP
-        asm("bswap %0" : "=r" (x) : "0" (x));
-#else
+#ifdef __i386__
+# ifdef CONFIG_X86_BSWAP
+        asm("bswap %0" : "=r" (val) : "0" (val));
+# else
         asm("xchgb %b0,%h0\n\t" /* swap lower bytes     */
             "rorl $16,%0\n\t"   /* swap words           */
             "xchgb %b0,%h0"     /* swap higher bytes    */
-            : "=q" (x)
-            : "0" (x));
+            : "=q" (val)
+            : "0" (val));
+# endif
+
+#else /* __i386__ */
+        asm("bswapl %0"
+            : "=r" (val)
+            : "0" (val));
 #endif
-        return x;
+        return val;
 }
+#define __arch_swab32 __arch_swab32
 
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
+static inline __attribute_const__ __u64 __arch_swab64(__u64 val)
 {
+#ifdef __i386__
         union {
                 struct {
                         __u32 a;
@@ -32,50 +39,27 @@ static inline __attribute_const__ __u64 ___arch__swab64(__u64 val)
                 __u64 u;
         } v;
         v.u = val;
-#ifdef CONFIG_X86_BSWAP
+# ifdef CONFIG_X86_BSWAP
         asm("bswapl %0 ; bswapl %1 ; xchgl %0,%1"
             : "=r" (v.s.a), "=r" (v.s.b)
             : "0" (v.s.a), "1" (v.s.b));
-#else
-        v.s.a = ___arch__swab32(v.s.a);
-        v.s.b = ___arch__swab32(v.s.b);
+# else
+        v.s.a = __arch_swab32(v.s.a);
+        v.s.b = __arch_swab32(v.s.b);
         asm("xchgl %0,%1"
             : "=r" (v.s.a), "=r" (v.s.b)
             : "0" (v.s.a), "1" (v.s.b));
-#endif
+# endif
         return v.u;
-}
-
 #else /* __i386__ */
-
-static inline __attribute_const__ __u64 ___arch__swab64(__u64 x)
-{
         asm("bswapq %0"
-            : "=r" (x)
-            : "0" (x));
-        return x;
-}
-
-static inline __attribute_const__ __u32 ___arch__swab32(__u32 x)
-{
-        asm("bswapl %0"
-            : "=r" (x)
-            : "0" (x));
-        return x;
-}
-
+            : "=r" (val)
+            : "0" (val));
+        return val;
 #endif
+}
+#define __arch_swab64 __arch_swab64
 
-/* Do not define swab16.  Gcc is smart enough to recognize "C" version and
-   convert it into rotation or exhange.  */
-
-#define __arch__swab64(x) ___arch__swab64(x)
-#define __arch__swab32(x) ___arch__swab32(x)
-
-#define __BYTEORDER_HAS_U64__
-
-#endif /* __GNUC__ */
-
-#include <linux/byteorder/little_endian.h>
+#include <linux/byteorder.h>
 
 #endif /* _ASM_X86_BYTEORDER_H */
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index cfdf8c2c5c31..ea408dcba513 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -80,7 +80,6 @@
 #define X86_FEATURE_UP          (3*32+ 9) /* smp kernel running on up */
 #define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
-#define X86_FEATURE_NOPL        (3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_PEBS        (3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS         (3*32+13) /* Branch Trace Store */
 #define X86_FEATURE_SYSCALL32   (3*32+14) /* "" syscall in ia32 userspace */
@@ -92,6 +91,8 @@
 #define X86_FEATURE_NOPL        (3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_AMDC1E      (3*32+21) /* AMD C1E detected */
 #define X86_FEATURE_XTOPOLOGY   (3*32+22) /* cpu topology enum extensions */
+#define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */
+#define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
 #define X86_FEATURE_XMM3        (4*32+ 0) /* "pni" SSE-3 */
@@ -117,6 +118,7 @@
 #define X86_FEATURE_XSAVE       (4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
 #define X86_FEATURE_OSXSAVE     (4*32+27) /* "" XSAVE enabled in the OS */
 #define X86_FEATURE_AVX         (4*32+28) /* Advanced Vector Extensions */
+#define X86_FEATURE_HYPERVISOR  (4*32+31) /* Running on a hypervisor */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
 #define X86_FEATURE_XSTORE      (5*32+ 2) /* "rng" RNG present (xstore) */
@@ -237,6 +239,7 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_xmm4_2          boot_cpu_has(X86_FEATURE_XMM4_2)
 #define cpu_has_x2apic          boot_cpu_has(X86_FEATURE_X2APIC)
 #define cpu_has_xsave           boot_cpu_has(X86_FEATURE_XSAVE)
+#define cpu_has_hypervisor      boot_cpu_has(X86_FEATURE_HYPERVISOR)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg         1
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index 097794ff6b79..4035357f5b9d 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -65,18 +65,16 @@ static inline struct dma_mapping_ops *get_dma_ops(struct device *dev)
                 return dma_ops;
         else
                 return dev->archdata.dma_ops;
-#endif /* _ASM_X86_DMA_MAPPING_H */
+#endif
 }
 
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
-#ifdef CONFIG_X86_64
         struct dma_mapping_ops *ops = get_dma_ops(dev);
         if (ops->mapping_error)
                 return ops->mapping_error(dev, dma_addr);
 
-#endif
         return (dma_addr == bad_dma_address);
 }
 
diff --git a/arch/x86/include/asm/ds.h b/arch/x86/include/asm/ds.h
index 99b6c39774a4..a8f672ba100c 100644
--- a/arch/x86/include/asm/ds.h
+++ b/arch/x86/include/asm/ds.h
@@ -6,13 +6,13 @@
  * precise-event based sampling (PEBS).
  *
  * It manages:
- * - per-thread and per-cpu allocation of BTS and PEBS
+ * - DS and BTS hardware configuration
  * - buffer overflow handling (to be done)
  * - buffer access
  *
- * It assumes:
- * - get_task_struct on all traced tasks
- * - current is allowed to trace tasks
+ * It does not do:
+ * - security checking (is the caller allowed to trace the task)
+ * - buffer allocation (memory accounting)
  *
  *
  * Copyright (C) 2007-2008 Intel Corporation.
@@ -31,6 +31,7 @@
 #ifdef CONFIG_X86_DS
 
 struct task_struct;
+struct ds_context;
 struct ds_tracer;
 struct bts_tracer;
 struct pebs_tracer;
@@ -38,6 +39,38 @@ struct pebs_tracer;
 typedef void (*bts_ovfl_callback_t)(struct bts_tracer *);
 typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *);
 
+
+/*
+ * A list of features plus corresponding macros to talk about them in
+ * the ds_request function's flags parameter.
+ *
+ * We use the enum to index an array of corresponding control bits;
+ * we use the macro to index a flags bit-vector.
+ */
+enum ds_feature {
+        dsf_bts = 0,
+        dsf_bts_kernel,
+#define BTS_KERNEL (1 << dsf_bts_kernel)
+        /* trace kernel-mode branches */
+
+        dsf_bts_user,
+#define BTS_USER (1 << dsf_bts_user)
+        /* trace user-mode branches */
+
+        dsf_bts_overflow,
+        dsf_bts_max,
+        dsf_pebs = dsf_bts_max,
+
+        dsf_pebs_max,
+        dsf_ctl_max = dsf_pebs_max,
+        dsf_bts_timestamps = dsf_ctl_max,
+#define BTS_TIMESTAMPS (1 << dsf_bts_timestamps)
+        /* add timestamps into BTS trace */
+
+#define BTS_USER_FLAGS (BTS_KERNEL | BTS_USER | BTS_TIMESTAMPS)
+};
+
+
 /*
  * Request BTS or PEBS
  *
@@ -58,92 +91,135 @@ typedef void (*pebs_ovfl_callback_t)(struct pebs_tracer *);
  *       NULL if cyclic buffer requested
  * th: the interrupt threshold in records from the end of the buffer;
  *     -1 if no interrupt threshold is requested.
+ * flags: a bit-mask of the above flags
  */
 extern struct bts_tracer *ds_request_bts(struct task_struct *task,
                                          void *base, size_t size,
-                                         bts_ovfl_callback_t ovfl, size_t th);
+                                         bts_ovfl_callback_t ovfl,
+                                         size_t th, unsigned int flags);
 extern struct pebs_tracer *ds_request_pebs(struct task_struct *task,
                                            void *base, size_t size,
                                            pebs_ovfl_callback_t ovfl,
-                                           size_t th);
+                                           size_t th, unsigned int flags);
 
 /*
  * Release BTS or PEBS resources
- *
- * Returns 0 on success; -Eerrno otherwise
+ * Suspend and resume BTS or PEBS tracing
  *
  * tracer: the tracer handle returned from ds_request_~()
  */
-extern int ds_release_bts(struct bts_tracer *tracer);
-extern int ds_release_pebs(struct pebs_tracer *tracer);
+extern void ds_release_bts(struct bts_tracer *tracer);
+extern void ds_suspend_bts(struct bts_tracer *tracer);
+extern void ds_resume_bts(struct bts_tracer *tracer);
+extern void ds_release_pebs(struct pebs_tracer *tracer);
+extern void ds_suspend_pebs(struct pebs_tracer *tracer);
+extern void ds_resume_pebs(struct pebs_tracer *tracer);
+
 
 /*
- * Get the (array) index of the write pointer.
- * (assuming an array of BTS/PEBS records)
- *
- * Returns 0 on success; -Eerrno on error
+ * The raw DS buffer state as it is used for BTS and PEBS recording.
  *
- * tracer: the tracer handle returned from ds_request_~()
- * pos (out): will hold the result
+ * This is the low-level, arch-dependent interface for working
+ * directly on the raw trace data.
  */
-extern int ds_get_bts_index(struct bts_tracer *tracer, size_t *pos);
-extern int ds_get_pebs_index(struct pebs_tracer *tracer, size_t *pos);
+struct ds_trace {
+        /* the number of bts/pebs records */
+        size_t n;
+        /* the size of a bts/pebs record in bytes */
+        size_t size;
+        /* pointers into the raw buffer:
+           - to the first entry */
+        void *begin;
+        /* - one beyond the last entry */
+        void *end;
+        /* - one beyond the newest entry */
+        void *top;
+        /* - the interrupt threshold */
+        void *ith;
+        /* flags given on ds_request() */
+        unsigned int flags;
+};
 
 /*
- * Get the (array) index one record beyond the end of the array.
- * (assuming an array of BTS/PEBS records)
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- * pos (out): will hold the result
+ * An arch-independent view on branch trace data.
  */
-extern int ds_get_bts_end(struct bts_tracer *tracer, size_t *pos);
-extern int ds_get_pebs_end(struct pebs_tracer *tracer, size_t *pos);
+enum bts_qualifier {
+        bts_invalid,
+#define BTS_INVALID bts_invalid
+
+        bts_branch,
+#define BTS_BRANCH bts_branch
+
+        bts_task_arrives,
+#define BTS_TASK_ARRIVES bts_task_arrives
+
+        bts_task_departs,
+#define BTS_TASK_DEPARTS bts_task_departs
+
+        bts_qual_bit_size = 4,
+        bts_qual_max = (1 << bts_qual_bit_size),
+};
+
+struct bts_struct {
+        __u64 qualifier;
+        union {
+                /* BTS_BRANCH */
+                struct {
+                        __u64 from;
+                        __u64 to;
+                } lbr;
+                /* BTS_TASK_ARRIVES or BTS_TASK_DEPARTS */
+                struct {
+                        __u64 jiffies;
+                        pid_t pid;
+                } timestamp;
+        } variant;
+};
+
 
 /*
- * Provide a pointer to the BTS/PEBS record at parameter index.
- * (assuming an array of BTS/PEBS records)
- *
- * The pointer points directly into the buffer. The user is
- * responsible for copying the record.
+ * The BTS state.
  *
- * Returns the size of a single record on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- * index: the index of the requested record
- * record (out): pointer to the requested record
+ * This gives access to the raw DS state and adds functions to provide
+ * an arch-independent view of the BTS data.
  */
-extern int ds_access_bts(struct bts_tracer *tracer,
-                         size_t index, const void **record);
-extern int ds_access_pebs(struct pebs_tracer *tracer,
-                          size_t index, const void **record);
+struct bts_trace {
+        struct ds_trace ds;
+
+        int (*read)(struct bts_tracer *tracer, const void *at,
+                    struct bts_struct *out);
+        int (*write)(struct bts_tracer *tracer, const struct bts_struct *in);
+};
+
 
 /*
- * Write one or more BTS/PEBS records at the write pointer index and
- * advance the write pointer.
- *
- * If size is not a multiple of the record size, trailing bytes are
- * zeroed out.
+ * The PEBS state.
  *
- * May result in one or more overflow notifications.
- *
- * If called during overflow handling, that is, with index >=
- * interrupt threshold, the write will wrap around.
+ * This gives access to the raw DS state and the PEBS-specific counter
+ * reset value.
+ */
+struct pebs_trace {
+        struct ds_trace ds;
+
+        /* the PEBS reset value */
+        unsigned long long reset_value;
+};
+
+
+/*
+ * Read the BTS or PEBS trace.
  *
- * An overflow notification is given if and when the interrupt
- * threshold is reached during or after the write.
+ * Returns a view on the trace collected for the parameter tracer.
  *
- * Returns the number of bytes written or -Eerrno.
+ * The view remains valid as long as the traced task is not running or
+ * the tracer is suspended.
+ * Writes into the trace buffer are not reflected.
  *
  * tracer: the tracer handle returned from ds_request_~()
- * buffer: the buffer to write
- * size: the size of the buffer
  */
-extern int ds_write_bts(struct bts_tracer *tracer,
-                        const void *buffer, size_t size);
-extern int ds_write_pebs(struct pebs_tracer *tracer,
-                         const void *buffer, size_t size);
+extern const struct bts_trace *ds_read_bts(struct bts_tracer *tracer);
+extern const struct pebs_trace *ds_read_pebs(struct pebs_tracer *tracer);
+
 
 /*
  * Reset the write pointer of the BTS/PEBS buffer.
@@ -156,27 +232,6 @@ extern int ds_reset_bts(struct bts_tracer *tracer);
 extern int ds_reset_pebs(struct pebs_tracer *tracer);
 
 /*
- * Clear the BTS/PEBS buffer and reset the write pointer.
- * The entire buffer will be zeroed out.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_~()
- */
-extern int ds_clear_bts(struct bts_tracer *tracer);
-extern int ds_clear_pebs(struct pebs_tracer *tracer);
-
-/*
- * Provide the PEBS counter reset value.
- *
- * Returns 0 on success; -Eerrno on error
- *
- * tracer: the tracer handle returned from ds_request_pebs()
- * value (out): the counter reset value
- */
-extern int ds_get_pebs_reset(struct pebs_tracer *tracer, u64 *value);
-
-/*
  * Set the PEBS counter reset value.
  *
  * Returns 0 on success; -Eerrno on error
@@ -192,35 +247,26 @@ extern int ds_set_pebs_reset(struct pebs_tracer *tracer, u64 value);
 struct cpuinfo_x86;
 extern void __cpuinit ds_init_intel(struct cpuinfo_x86 *);
 
-
-
 /*
- * The DS context - part of struct thread_struct.
+ * Context switch work
  */
-#define MAX_SIZEOF_DS (12 * 8)
-
-struct ds_context {
-        /* pointer to the DS configuration; goes into MSR_IA32_DS_AREA */
-        unsigned char ds[MAX_SIZEOF_DS];
-        /* the owner of the BTS and PEBS configuration, respectively */
-        struct ds_tracer  *owner[2];
-        /* use count */
-        unsigned long count;
-        /* a pointer to the context location inside the thread_struct
-         * or the per_cpu context array */
-        struct ds_context **this;
-        /* a pointer to the task owning this context, or NULL, if the
-         * context is owned by a cpu */
-        struct task_struct *task;
-};
+extern void ds_switch_to(struct task_struct *prev, struct task_struct *next);
 
-/* called by exit_thread() to free leftover contexts */
-extern void ds_free(struct ds_context *context);
+/*
+ * Task clone/init and cleanup work
+ */
+extern void ds_copy_thread(struct task_struct *tsk, struct task_struct *father);
+extern void ds_exit_thread(struct task_struct *tsk);
 
 #else /* CONFIG_X86_DS */
 
 struct cpuinfo_x86;
 static inline void __cpuinit ds_init_intel(struct cpuinfo_x86 *ignored) {}
+static inline void ds_switch_to(struct task_struct *prev,
+                                struct task_struct *next) {}
+static inline void ds_copy_thread(struct task_struct *tsk,
+                                  struct task_struct *father) {}
+static inline void ds_exit_thread(struct task_struct *tsk) {}
 
 #endif /* CONFIG_X86_DS */
 #endif /* _ASM_X86_DS_H */
diff --git a/arch/x86/include/asm/dwarf2.h b/arch/x86/include/asm/dwarf2.h
index 804b6e6be929..3afc5e87cfdd 100644
--- a/arch/x86/include/asm/dwarf2.h
+++ b/arch/x86/include/asm/dwarf2.h
@@ -6,56 +6,91 @@
 #endif
 
 /*
-   Macros for dwarf2 CFI unwind table entries.
-   See "as.info" for details on these pseudo ops. Unfortunately
-   they are only supported in very new binutils, so define them
-   away for older version.
+ * Macros for dwarf2 CFI unwind table entries.
+ * See "as.info" for details on these pseudo ops. Unfortunately
+ * they are only supported in very new binutils, so define them
+ * away for older version.
  */
 
 #ifdef CONFIG_AS_CFI
 
-#define CFI_STARTPROC .cfi_startproc
-#define CFI_ENDPROC .cfi_endproc
-#define CFI_DEF_CFA .cfi_def_cfa
-#define CFI_DEF_CFA_REGISTER .cfi_def_cfa_register
-#define CFI_DEF_CFA_OFFSET .cfi_def_cfa_offset
-#define CFI_ADJUST_CFA_OFFSET .cfi_adjust_cfa_offset
-#define CFI_OFFSET .cfi_offset
-#define CFI_REL_OFFSET .cfi_rel_offset
-#define CFI_REGISTER .cfi_register
-#define CFI_RESTORE .cfi_restore
-#define CFI_REMEMBER_STATE .cfi_remember_state
-#define CFI_RESTORE_STATE .cfi_restore_state
-#define CFI_UNDEFINED .cfi_undefined
+#define CFI_STARTPROC           .cfi_startproc
+#define CFI_ENDPROC             .cfi_endproc
+#define CFI_DEF_CFA             .cfi_def_cfa
+#define CFI_DEF_CFA_REGISTER    .cfi_def_cfa_register
+#define CFI_DEF_CFA_OFFSET      .cfi_def_cfa_offset
+#define CFI_ADJUST_CFA_OFFSET   .cfi_adjust_cfa_offset
+#define CFI_OFFSET              .cfi_offset
+#define CFI_REL_OFFSET          .cfi_rel_offset
+#define CFI_REGISTER            .cfi_register
+#define CFI_RESTORE             .cfi_restore
+#define CFI_REMEMBER_STATE      .cfi_remember_state
+#define CFI_RESTORE_STATE       .cfi_restore_state
+#define CFI_UNDEFINED           .cfi_undefined
 
 #ifdef CONFIG_AS_CFI_SIGNAL_FRAME
-#define CFI_SIGNAL_FRAME .cfi_signal_frame
+#define CFI_SIGNAL_FRAME        .cfi_signal_frame
 #else
 #define CFI_SIGNAL_FRAME
 #endif
 
 #else
 
-/* Due to the structure of pre-exisiting code, don't use assembler line
-   comment character # to ignore the arguments. Instead, use a dummy macro. */
+/*
+ * Due to the structure of pre-exisiting code, don't use assembler line
+ * comment character # to ignore the arguments. Instead, use a dummy macro.
+ */
 .macro cfi_ignore a=0, b=0, c=0, d=0
 .endm
 
-#define CFI_STARTPROC   cfi_ignore
-#define CFI_ENDPROC     cfi_ignore
-#define CFI_DEF_CFA     cfi_ignore
+#define CFI_STARTPROC           cfi_ignore
+#define CFI_ENDPROC             cfi_ignore
+#define CFI_DEF_CFA             cfi_ignore
 #define CFI_DEF_CFA_REGISTER    cfi_ignore
 #define CFI_DEF_CFA_OFFSET      cfi_ignore
 #define CFI_ADJUST_CFA_OFFSET   cfi_ignore
-#define CFI_OFFSET      cfi_ignore
-#define CFI_REL_OFFSET  cfi_ignore
-#define CFI_REGISTER    cfi_ignore
-#define CFI_RESTORE     cfi_ignore
-#define CFI_REMEMBER_STATE cfi_ignore
-#define CFI_RESTORE_STATE cfi_ignore
-#define CFI_UNDEFINED cfi_ignore
-#define CFI_SIGNAL_FRAME cfi_ignore
+#define CFI_OFFSET              cfi_ignore
+#define CFI_REL_OFFSET          cfi_ignore
+#define CFI_REGISTER            cfi_ignore
+#define CFI_RESTORE             cfi_ignore
+#define CFI_REMEMBER_STATE      cfi_ignore
+#define CFI_RESTORE_STATE       cfi_ignore
+#define CFI_UNDEFINED           cfi_ignore
+#define CFI_SIGNAL_FRAME        cfi_ignore
 
 #endif
 
+/*
+ * An attempt to make CFI annotations more or less
+ * correct and shorter. It is implied that you know
+ * what you're doing if you use them.
+ */
+#ifdef __ASSEMBLY__
+#ifdef CONFIG_X86_64
+        .macro pushq_cfi reg
+        pushq \reg
+        CFI_ADJUST_CFA_OFFSET 8
+        .endm
+
+        .macro popq_cfi reg
+        popq \reg
+        CFI_ADJUST_CFA_OFFSET -8
+        .endm
+
+        .macro movq_cfi reg offset=0
+        movq %\reg, \offset(%rsp)
+        CFI_REL_OFFSET \reg, \offset
+        .endm
+
+        .macro movq_cfi_restore offset reg
+        movq \offset(%rsp), %\reg
+        CFI_RESTORE \reg
+        .endm
+#else /*!CONFIG_X86_64*/
+
+        /* 32bit defenitions are missed yet */
+
+#endif /*!CONFIG_X86_64*/
+#endif /*__ASSEMBLY__*/
+
 #endif /* _ASM_X86_DWARF2_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 40ca1bea7916..f51a3ddde01a 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -325,7 +325,7 @@ struct linux_binprm;
 
 #define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
 extern int arch_setup_additional_pages(struct linux_binprm *bprm,
-                                       int executable_stack);
+                                       int uses_interp);
 
 extern int syscall32_setup_pages(struct linux_binprm *, int exstack);
 #define compat_arch_setup_additional_pages      syscall32_setup_pages
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index 7e61b4ceb9a4..b55b4a7fbefd 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -1,6 +1,33 @@
 #ifndef _ASM_X86_FTRACE_H
 #define _ASM_X86_FTRACE_H
 
+#ifdef __ASSEMBLY__
+
+        .macro MCOUNT_SAVE_FRAME
+        /* taken from glibc */
+        subq $0x38, %rsp
+        movq %rax, (%rsp)
+        movq %rcx, 8(%rsp)
+        movq %rdx, 16(%rsp)
+        movq %rsi, 24(%rsp)
+        movq %rdi, 32(%rsp)
+        movq %r8, 40(%rsp)
+        movq %r9, 48(%rsp)
+        .endm
+
+        .macro MCOUNT_RESTORE_FRAME
+        movq 48(%rsp), %r9
+        movq 40(%rsp), %r8
+        movq 32(%rsp), %rdi
+        movq 24(%rsp), %rsi
+        movq 16(%rsp), %rdx
+        movq 8(%rsp), %rcx
+        movq (%rsp), %rax
+        addq $0x38, %rsp
+        .endm
+
+#endif
+
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR             ((long)(mcount))
 #define MCOUNT_INSN_SIZE        5 /* sizeof mcount call */
@@ -46,7 +73,7 @@ struct ftrace_ret_stack {
 /*
  * Primary handler of a function return.
  * It relays on ftrace_return_to_handler.
- * Defined in entry32.S
+ * Defined in entry_32/64.S
  */
 extern void return_to_handler(void);
 
diff --git a/arch/x86/include/asm/gart.h b/arch/x86/include/asm/gart.h
index 74252264433d..6cfdafa409d8 100644
--- a/arch/x86/include/asm/gart.h
+++ b/arch/x86/include/asm/gart.h
@@ -29,6 +29,39 @@ extern int fix_aperture;
 #define AMD64_GARTCACHECTL      0x9c
 #define AMD64_GARTEN            (1<<0)
 
+#ifdef CONFIG_GART_IOMMU
+extern int gart_iommu_aperture;
+extern int gart_iommu_aperture_allowed;
+extern int gart_iommu_aperture_disabled;
+
+extern void early_gart_iommu_check(void);
+extern void gart_iommu_init(void);
+extern void gart_iommu_shutdown(void);
+extern void __init gart_parse_options(char *);
+extern void gart_iommu_hole_init(void);
+
+#else
+#define gart_iommu_aperture            0
+#define gart_iommu_aperture_allowed    0
+#define gart_iommu_aperture_disabled   1
+
+static inline void early_gart_iommu_check(void)
+{
+}
+static inline void gart_iommu_init(void)
+{
+}
+static inline void gart_iommu_shutdown(void)
+{
+}
+static inline void gart_parse_options(char *options)
+{
+}
+static inline void gart_iommu_hole_init(void)
+{
+}
+#endif
+
 extern int agp_amd64_init(void);
 
 static inline void enable_gart_translation(struct pci_dev *dev, u64 addr)
diff --git a/arch/x86/include/asm/hardirq_32.h b/arch/x86/include/asm/hardirq_32.h
index 5ca135e72f2b..cf7954d1405f 100644
--- a/arch/x86/include/asm/hardirq_32.h
+++ b/arch/x86/include/asm/hardirq_32.h
@@ -22,6 +22,8 @@ DECLARE_PER_CPU(irq_cpustat_t, irq_stat);
 #define __ARCH_IRQ_STAT
 #define __IRQ_STAT(cpu, member) (per_cpu(irq_stat, cpu).member)
 
+#define inc_irq_stat(member)    (__get_cpu_var(irq_stat).member++)
+
 void ack_bad_irq(unsigned int irq);
 #include <linux/irq_cpustat.h>
 
diff --git a/arch/x86/include/asm/hardirq_64.h b/arch/x86/include/asm/hardirq_64.h
index 1ba381fc51d3..b5a6b5d56704 100644
--- a/arch/x86/include/asm/hardirq_64.h
+++ b/arch/x86/include/asm/hardirq_64.h
@@ -11,6 +11,8 @@
 
 #define __ARCH_IRQ_STAT 1
 
+#define inc_irq_stat(member)    add_pda(member, 1)
+
 #define local_softirq_pending() read_pda(__softirq_pending)
 
 #define __ARCH_SET_SOFTIRQ_PENDING 1
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b97aecb0b61d..8de644b6b959 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -109,9 +109,7 @@ extern asmlinkage void smp_invalidate_interrupt(struct pt_regs *);
 #endif
 #endif
 
-#ifdef CONFIG_X86_32
-extern void (*const interrupt[NR_VECTORS])(void);
-#endif
+extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void);
 
 typedef int vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h
new file mode 100644
index 000000000000..369f5c5d09a1
--- /dev/null
+++ b/arch/x86/include/asm/hypervisor.h
@@ -0,0 +1,26 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__HYPERVISOR_H
+#define ASM_X86__HYPERVISOR_H
+
+extern unsigned long get_hypervisor_tsc_freq(void);
+extern void init_hypervisor(struct cpuinfo_x86 *c);
+
+#endif
diff --git a/arch/x86/include/asm/ia32.h b/arch/x86/include/asm/ia32.h
index 97989c0e534c..50ca486fd88c 100644
--- a/arch/x86/include/asm/ia32.h
+++ b/arch/x86/include/asm/ia32.h
@@ -129,24 +129,6 @@ typedef struct compat_siginfo {
         } _sifields;
 } compat_siginfo_t;
 
-struct sigframe32 {
-        u32 pretcode;
-        int sig;
-        struct sigcontext_ia32 sc;
-        struct _fpstate_ia32 fpstate;
-        unsigned int extramask[_COMPAT_NSIG_WORDS-1];
-};
-
-struct rt_sigframe32 {
-        u32 pretcode;
-        int sig;
-        u32 pinfo;
-        u32 puc;
-        compat_siginfo_t info;
-        struct ucontext_ia32 uc;
-        struct _fpstate_ia32 fpstate;
-};
-
 struct ustat32 {
         __u32                   f_tfree;
         compat_ino_t            f_tinode;
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index 44c89c3a23e9..38d87379e270 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -8,8 +8,13 @@ struct notifier_block;
 void idle_notifier_register(struct notifier_block *n);
 void idle_notifier_unregister(struct notifier_block *n);
 
+#ifdef CONFIG_X86_64
 void enter_idle(void);
 void exit_idle(void);
+#else /* !CONFIG_X86_64 */
+static inline void enter_idle(void) { }
+static inline void exit_idle(void) { }
+#endif /* CONFIG_X86_64 */
 
 void c1e_remove_cpu(int cpu);
 
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index ac2abc88cd95..05cfed4485fa 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -4,6 +4,7 @@
 #define ARCH_HAS_IOREMAP_WC
 
 #include <linux/compiler.h>
+#include <asm-generic/int-ll64.h>
 
 #define build_mmio_read(name, size, type, reg, barrier) \
 static inline type name(const volatile void __iomem *addr) \
@@ -45,21 +46,39 @@ build_mmio_write(__writel, "l", unsigned int, "r", )
 #define mmiowb() barrier()
 
 #ifdef CONFIG_X86_64
+
 build_mmio_read(readq, "q", unsigned long, "=r", :"memory")
-build_mmio_read(__readq, "q", unsigned long, "=r", )
 build_mmio_write(writeq, "q", unsigned long, "r", :"memory")
-build_mmio_write(__writeq, "q", unsigned long, "r", )
 
-#define readq_relaxed(a) __readq(a)
-#define __raw_readq __readq
-#define __raw_writeq writeq
+#else
+
+static inline __u64 readq(const volatile void __iomem *addr)
+{
+        const volatile u32 __iomem *p = addr;
+        u32 low, high;
+
+        low = readl(p);
+        high = readl(p + 1);
+
+        return low + ((u64)high << 32);
+}
+
+static inline void writeq(__u64 val, volatile void __iomem *addr)
+{
+        writel(val, addr);
+        writel(val >> 32, addr+4);
+}
 
-/* Let people know we have them */
-#define readq readq
-#define writeq writeq
 #endif
 
-extern int iommu_bio_merge;
+#define readq_relaxed(a)        readq(a)
+
+#define __raw_readq(a)          readq(a)
+#define __raw_writeq(val, addr) writeq(val, addr)
+
+/* Let people know that we have them */
+#define readq                   readq
+#define writeq                  writeq
 
 #ifdef CONFIG_X86_32
 # include "io_32.h"
diff --git a/arch/x86/include/asm/io_64.h b/arch/x86/include/asm/io_64.h
index fea325a1122f..563c16270ba6 100644
--- a/arch/x86/include/asm/io_64.h
+++ b/arch/x86/include/asm/io_64.h
@@ -232,8 +232,6 @@ void memset_io(volatile void __iomem *a, int b, size_t c);
 
 #define flush_write_buffers()
 
-#define BIO_VMERGE_BOUNDARY iommu_bio_merge
-
 /*
  * Convert a virtual cached pointer to an uncached pointer
  */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index 25d527ca1362..7a1f44ac1f17 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -156,11 +156,21 @@ extern int sis_apic_bug;
 /* 1 if "noapic" boot option passed */
 extern int skip_ioapic_setup;
 
+/* 1 if "noapic" boot option passed */
+extern int noioapicquirk;
+
+/* -1 if "noapic" boot option passed */
+extern int noioapicreroute;
+
 /* 1 if the timer IRQ uses the '8259A Virtual Wire' mode */
 extern int timer_through_8259;
 
 static inline void disable_ioapic_setup(void)
 {
+#ifdef CONFIG_PCI
+        noioapicquirk = 1;
+        noioapicreroute = -1;
+#endif
         skip_ioapic_setup = 1;
 }
 
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 0b500c5b6446..a6ee9e6f530f 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -7,42 +7,7 @@ extern struct dma_mapping_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
 
-extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
-
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
 
-#ifdef CONFIG_GART_IOMMU
-extern int gart_iommu_aperture;
-extern int gart_iommu_aperture_allowed;
-extern int gart_iommu_aperture_disabled;
-
-extern void early_gart_iommu_check(void);
-extern void gart_iommu_init(void);
-extern void gart_iommu_shutdown(void);
-extern void __init gart_parse_options(char *);
-extern void gart_iommu_hole_init(void);
-
-#else
-#define gart_iommu_aperture            0
-#define gart_iommu_aperture_allowed    0
-#define gart_iommu_aperture_disabled   1
-
-static inline void early_gart_iommu_check(void)
-{
-}
-static inline void gart_iommu_init(void)
-{
-}
-static inline void gart_iommu_shutdown(void)
-{
-}
-static inline void gart_parse_options(char *options)
-{
-}
-static inline void gart_iommu_hole_init(void)
-{
-}
-#endif
-
 #endif /* _ASM_X86_IOMMU_H */
diff --git a/arch/x86/include/asm/irq.h b/arch/x86/include/asm/irq.h
index 4bb732e45a85..592688ed04d3 100644
--- a/arch/x86/include/asm/irq.h
+++ b/arch/x86/include/asm/irq.h
@@ -31,10 +31,6 @@ static inline int irq_canonicalize(int irq)
 # endif
 #endif
 
-#ifdef CONFIG_IRQBALANCE
-extern int irqbalance_disable(char *str);
-#endif
-
 #ifdef CONFIG_HOTPLUG_CPU
 #include <linux/cpumask.h>
 extern void fixup_irqs(void);
diff --git a/arch/x86/include/asm/irq_regs_32.h b/arch/x86/include/asm/irq_regs_32.h
index af2f02d27fc7..86afd7473457 100644
--- a/arch/x86/include/asm/irq_regs_32.h
+++ b/arch/x86/include/asm/irq_regs_32.h
@@ -9,6 +9,8 @@
 
 #include <asm/percpu.h>
 
+#define ARCH_HAS_OWN_IRQ_REGS
+
 DECLARE_PER_CPU(struct pt_regs *, irq_regs);
 
 static inline struct pt_regs *get_irq_regs(void)
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index f61ee8f937e4..5d98d0b68ffc 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -57,5 +57,65 @@
 #define __ALIGN_STR ".align 16,0x90"
 #endif
 
+/*
+ * to check ENTRY_X86/END_X86 and
+ * KPROBE_ENTRY_X86/KPROBE_END_X86
+ * unbalanced-missed-mixed appearance
+ */
+#define __set_entry_x86         .set ENTRY_X86_IN, 0
+#define __unset_entry_x86       .set ENTRY_X86_IN, 1
+#define __set_kprobe_x86        .set KPROBE_X86_IN, 0
+#define __unset_kprobe_x86      .set KPROBE_X86_IN, 1
+
+#define __macro_err_x86 .error "ENTRY_X86/KPROBE_X86 unbalanced,missed,mixed"
+
+#define __check_entry_x86       \
+        .ifdef ENTRY_X86_IN;    \
+        .ifeq ENTRY_X86_IN;     \
+        __macro_err_x86;        \
+        .abort;                 \
+        .endif;                 \
+        .endif
+
+#define __check_kprobe_x86      \
+        .ifdef KPROBE_X86_IN;   \
+        .ifeq KPROBE_X86_IN;    \
+        __macro_err_x86;        \
+        .abort;                 \
+        .endif;                 \
+        .endif
+
+#define __check_entry_kprobe_x86        \
+        __check_entry_x86;              \
+        __check_kprobe_x86
+
+#define ENTRY_KPROBE_FINAL_X86 __check_entry_kprobe_x86
+
+#define ENTRY_X86(name)                 \
+        __check_entry_kprobe_x86;       \
+        __set_entry_x86;                \
+        .globl name;                    \
+        __ALIGN;                        \
+        name:
+
+#define END_X86(name)                   \
+        __unset_entry_x86;              \
+        __check_entry_kprobe_x86;       \
+        .size name, .-name
+
+#define KPROBE_ENTRY_X86(name)          \
+        __check_entry_kprobe_x86;       \
+        __set_kprobe_x86;               \
+        .pushsection .kprobes.text, "ax"; \
+        .globl name;                    \
+        __ALIGN;                        \
+        name:
+
+#define KPROBE_END_X86(name)            \
+        __unset_kprobe_x86;             \
+        __check_entry_kprobe_x86;       \
+        .size name, .-name;             \
+        .popsection
+
 #endif /* _ASM_X86_LINKAGE_H */
 
diff --git a/arch/x86/include/asm/mmu_context_32.h b/arch/x86/include/asm/mmu_context_32.h
index 8e10015781fb..7e98ce1d2c0e 100644
--- a/arch/x86/include/asm/mmu_context_32.h
+++ b/arch/x86/include/asm/mmu_context_32.h
@@ -4,9 +4,8 @@
 static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 #ifdef CONFIG_SMP
-        unsigned cpu = smp_processor_id();
-        if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK)
-                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_LAZY;
+        if (x86_read_percpu(cpu_tlbstate.state) == TLBSTATE_OK)
+                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_LAZY);
 #endif
 }
 
@@ -20,8 +19,8 @@ static inline void switch_mm(struct mm_struct *prev,
                 /* stop flush ipis for the previous mm */
                 cpu_clear(cpu, prev->cpu_vm_mask);
 #ifdef CONFIG_SMP
-                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
-                per_cpu(cpu_tlbstate, cpu).active_mm = next;
+                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
+                x86_write_percpu(cpu_tlbstate.active_mm, next);
 #endif
                 cpu_set(cpu, next->cpu_vm_mask);
 
@@ -36,8 +35,8 @@ static inline void switch_mm(struct mm_struct *prev,
         }
 #ifdef CONFIG_SMP
         else {
-                per_cpu(cpu_tlbstate, cpu).state = TLBSTATE_OK;
-                BUG_ON(per_cpu(cpu_tlbstate, cpu).active_mm != next);
+                x86_write_percpu(cpu_tlbstate.state, TLBSTATE_OK);
+                BUG_ON(x86_read_percpu(cpu_tlbstate.active_mm) != next);
 
                 if (!cpu_test_and_set(cpu, next->cpu_vm_mask)) {
                         /* We were in lazy tlb mode and leave_mm disabled
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e38859d577a1..cb58643947b9 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -85,7 +85,9 @@
 /* AMD64 MSRs. Not complete. See the architecture manual for a more
    complete list. */
 
+#define MSR_AMD64_PATCH_LEVEL           0x0000008b
 #define MSR_AMD64_NB_CFG                0xc001001f
+#define MSR_AMD64_PATCH_LOADER          0xc0010020
 #define MSR_AMD64_IBSFETCHCTL           0xc0011030
 #define MSR_AMD64_IBSFETCHLINAD         0xc0011031
 #define MSR_AMD64_IBSFETCHPHYSAD        0xc0011032
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index c2a812ebde89..638bf6241807 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -22,10 +22,10 @@ static inline unsigned long long native_read_tscp(unsigned int *aux)
 }
 
 /*
- * i386 calling convention returns 64-bit value in edx:eax, while
- * x86_64 returns at rax. Also, the "A" constraint does not really
- * mean rdx:rax in x86_64, so we need specialized behaviour for each
- * architecture
+ * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A"
+ * constraint has different meanings. For i386, "A" means exactly
+ * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead,
+ * it means rax *or* rdx.
  */
 #ifdef CONFIG_X86_64
 #define DECLARE_ARGS(val, low, high)    unsigned low, high
@@ -85,7 +85,8 @@ static inline void native_write_msr(unsigned int msr,
         asm volatile("wrmsr" : : "c" (msr), "a"(low), "d" (high) : "memory");
 }
 
-static inline int native_write_msr_safe(unsigned int msr,
+/* Can be uninlined because referenced by paravirt */
+notrace static inline int native_write_msr_safe(unsigned int msr,
                                         unsigned low, unsigned high)
 {
         int err;
@@ -181,10 +182,10 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
 }
 
 #define rdtscl(low)                                             \
-        ((low) = (u32)native_read_tsc())
+        ((low) = (u32)__native_read_tsc())
 
 #define rdtscll(val)                                            \
-        ((val) = native_read_tsc())
+        ((val) = __native_read_tsc())
 
 #define rdpmc(counter, low, high)                       \
 do {                                                    \
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index 875b38edf193..a977de23cb4d 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -19,6 +19,8 @@ struct pci_sysdata {
 };
 
 extern int pci_routeirq;
+extern int noioapicquirk;
+extern int noioapicreroute;
 
 /* scan a bus after allocating a pci_sysdata for it */
 extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
@@ -82,6 +84,8 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev,
 static inline void early_quirks(void) { }
 #endif
 
+extern void pci_iommu_alloc(void);
+
 #endif  /* __KERNEL__ */
 
 #ifdef CONFIG_X86_32
@@ -98,9 +102,9 @@ static inline void early_quirks(void) { }
 
 #ifdef CONFIG_NUMA
 /* Returns the node based on pci bus */
-static inline int __pcibus_to_node(struct pci_bus *bus)
+static inline int __pcibus_to_node(const struct pci_bus *bus)
 {
-        struct pci_sysdata *sd = bus->sysdata;
+        const struct pci_sysdata *sd = bus->sysdata;
 
         return sd->node;
 }
@@ -109,6 +113,12 @@ static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus)
 {
         return node_to_cpumask(__pcibus_to_node(bus));
 }
+
+static inline const struct cpumask *
+cpumask_of_pcibus(const struct pci_bus *bus)
+{
+        return cpumask_of_node(__pcibus_to_node(bus));
+}
 #endif
 
 #endif /* _ASM_X86_PCI_H */
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index d02d936840a3..4da207982777 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -23,7 +23,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
                                int reg, int len, u32 value);
 
 extern void dma32_reserve_bootmem(void);
-extern void pci_iommu_alloc(void);
 
 /* The PCI address space does equal the physical memory
  * address space.  The networking and block device layers use
diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h
index b17edfd23628..e0d199fe1d83 100644
--- a/arch/x86/include/asm/pgtable-2level.h
+++ b/arch/x86/include/asm/pgtable-2level.h
@@ -56,23 +56,55 @@ static inline pte_t native_ptep_get_and_clear(pte_t *xp)
 #define pte_none(x)             (!(x).pte_low)
 
 /*
- * Bits 0, 6 and 7 are taken, split up the 29 bits of offset
- * into this range:
+ * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken,
+ * split up the 29 bits of offset into this range:
  */
 #define PTE_FILE_MAX_BITS       29
+#define PTE_FILE_SHIFT1         (_PAGE_BIT_PRESENT + 1)
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
+#define PTE_FILE_SHIFT2         (_PAGE_BIT_FILE + 1)
+#define PTE_FILE_SHIFT3         (_PAGE_BIT_PROTNONE + 1)
+#else
+#define PTE_FILE_SHIFT2         (_PAGE_BIT_PROTNONE + 1)
+#define PTE_FILE_SHIFT3         (_PAGE_BIT_FILE + 1)
+#endif
+#define PTE_FILE_BITS1          (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1)
+#define PTE_FILE_BITS2          (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1)
 
 #define pte_to_pgoff(pte)                                               \
-        ((((pte).pte_low >> 1) & 0x1f) + (((pte).pte_low >> 8) << 5))
+        ((((pte).pte_low >> PTE_FILE_SHIFT1)                            \
+          & ((1U << PTE_FILE_BITS1) - 1))                               \
+         + ((((pte).pte_low >> PTE_FILE_SHIFT2)                         \
+             & ((1U << PTE_FILE_BITS2) - 1)) << PTE_FILE_BITS1)         \
+         + (((pte).pte_low >> PTE_FILE_SHIFT3)                          \
+            << (PTE_FILE_BITS1 + PTE_FILE_BITS2)))
 
 #define pgoff_to_pte(off)                                               \
-        ((pte_t) { .pte_low = (((off) & 0x1f) << 1) +                   \
-                        (((off) >> 5) << 8) + _PAGE_FILE })
+        ((pte_t) { .pte_low =                                           \
+         (((off) & ((1U << PTE_FILE_BITS1) - 1)) << PTE_FILE_SHIFT1)    \
+         + ((((off) >> PTE_FILE_BITS1) & ((1U << PTE_FILE_BITS2) - 1))  \
+            << PTE_FILE_SHIFT2)                                         \
+         + (((off) >> (PTE_FILE_BITS1 + PTE_FILE_BITS2))                \
+            << PTE_FILE_SHIFT3)                                         \
+         + _PAGE_FILE })
 
 /* Encode and de-code a swap entry */
-#define __swp_type(x)                   (((x).val >> 1) & 0x1f)
-#define __swp_offset(x)                 ((x).val >> 8)
-#define __swp_entry(type, offset)                               \
-        ((swp_entry_t) { ((type) << 1) | ((offset) << 8) })
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
+#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+#else
+#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
+#endif
+
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
+
+#define __swp_type(x)                   (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
+                                         & ((1U << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)                 ((x).val >> SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset)       ((swp_entry_t) { \
+                                         ((type) << (_PAGE_BIT_PRESENT + 1)) \
+                                         | ((offset) << SWP_OFFSET_SHIFT) })
 #define __pte_to_swp_entry(pte)         ((swp_entry_t) { (pte).pte_low })
 #define __swp_entry_to_pte(x)           ((pte_t) { .pte = (x).val })
 
diff --git a/arch/x86/include/asm/pgtable-3level.h b/arch/x86/include/asm/pgtable-3level.h
index 52597aeadfff..447da43cddb3 100644
--- a/arch/x86/include/asm/pgtable-3level.h
+++ b/arch/x86/include/asm/pgtable-3level.h
@@ -166,6 +166,7 @@ static inline int pte_none(pte_t pte)
 #define PTE_FILE_MAX_BITS       32
 
 /* Encode and de-code a swap entry */
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > 5)
 #define __swp_type(x)                   (((x).val) & 0x1f)
 #define __swp_offset(x)                 ((x).val >> 5)
 #define __swp_entry(type, offset)       ((swp_entry_t){(type) | (offset) << 5})
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index c012f3b11671..83e69f4a37f0 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -10,7 +10,6 @@
 #define _PAGE_BIT_PCD           4       /* page cache disabled */
 #define _PAGE_BIT_ACCESSED      5       /* was accessed (raised by CPU) */
 #define _PAGE_BIT_DIRTY         6       /* was written to (raised by CPU) */
-#define _PAGE_BIT_FILE          6
 #define _PAGE_BIT_PSE           7       /* 4 MB (or 2MB) page */
 #define _PAGE_BIT_PAT           7       /* on 4KB pages */
 #define _PAGE_BIT_GLOBAL        8       /* Global TLB entry PPro+ */
@@ -22,6 +21,12 @@
 #define _PAGE_BIT_CPA_TEST      _PAGE_BIT_UNUSED1
 #define _PAGE_BIT_NX           63       /* No execute: only valid after cpuid check */
 
+/* If _PAGE_BIT_PRESENT is clear, we use these: */
+/* - if the user mapped it with PROT_NONE; pte_present gives true */
+#define _PAGE_BIT_PROTNONE      _PAGE_BIT_GLOBAL
+/* - set: nonlinear file mapping, saved PTE; unset:swap */
+#define _PAGE_BIT_FILE          _PAGE_BIT_DIRTY
+
 #define _PAGE_PRESENT   (_AT(pteval_t, 1) << _PAGE_BIT_PRESENT)
 #define _PAGE_RW        (_AT(pteval_t, 1) << _PAGE_BIT_RW)
 #define _PAGE_USER      (_AT(pteval_t, 1) << _PAGE_BIT_USER)
@@ -46,11 +51,8 @@
 #define _PAGE_NX        (_AT(pteval_t, 0))
 #endif
 
-/* If _PAGE_PRESENT is clear, we use these: */
-#define _PAGE_FILE      _PAGE_DIRTY     /* nonlinear file mapping,
-                                         * saved PTE; unset:swap */
-#define _PAGE_PROTNONE  _PAGE_PSE       /* if the user mapped it with PROT_NONE;
-                                           pte_present gives true */
+#define _PAGE_FILE      (_AT(pteval_t, 1) << _PAGE_BIT_FILE)
+#define _PAGE_PROTNONE  (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE)
 
 #define _PAGE_TABLE     (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |        \
                          _PAGE_ACCESSED | _PAGE_DIRTY)
@@ -158,8 +160,19 @@
 #define PGD_IDENT_ATTR   0x001          /* PRESENT (no other attributes) */
 #endif
 
+/*
+ * Macro to mark a page protection value as UC-
+ */
+#define pgprot_noncached(prot)                                  \
+        ((boot_cpu_data.x86 > 3)                                \
+         ? (__pgprot(pgprot_val(prot) | _PAGE_CACHE_UC_MINUS))  \
+         : (prot))
+
 #ifndef __ASSEMBLY__
 
+#define pgprot_writecombine     pgprot_writecombine
+extern pgprot_t pgprot_writecombine(pgprot_t prot);
+
 /*
  * ZERO_PAGE is a global shared page that is always zero: used
  * for zero-mapped memory areas etc..
@@ -329,6 +342,9 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 #define canon_pgprot(p) __pgprot(pgprot_val(p) & __supported_pte_mask)
 
 #ifndef __ASSEMBLY__
+/* Indicate that x86 has its own track and untrack pfn vma functions */
+#define __HAVE_PFNMAP_TRACKING
+
 #define __HAVE_PHYS_MEM_ACCESS_PROT
 struct file;
 pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index f9d5889b336b..72b020deb46b 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -101,15 +101,6 @@ extern unsigned long pg0[];
 #endif
 
 /*
- * Macro to mark a page protection value as "uncacheable".
- * On processors which do not support it, this is a no-op.
- */
-#define pgprot_noncached(prot)                                  \
-        ((boot_cpu_data.x86 > 3)                                \
-         ? (__pgprot(pgprot_val(prot) | _PAGE_PCD | _PAGE_PWT)) \
-         : (prot))
-
-/*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
  */
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 545a0e042bb2..ba09289accaa 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -146,7 +146,7 @@ static inline void native_pgd_clear(pgd_t *pgd)
 #define PGDIR_MASK      (~(PGDIR_SIZE - 1))
 
 
-#define MAXMEM           _AC(0x00003fffffffffff, UL)
+#define MAXMEM           _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
 #define VMALLOC_START    _AC(0xffffc20000000000, UL)
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
 #define VMEMMAP_START    _AC(0xffffe20000000000, UL)
@@ -177,12 +177,6 @@ static inline int pmd_bad(pmd_t pmd)
 #define pages_to_mb(x)  ((x) >> (20 - PAGE_SHIFT))   /* FIXME: is this right? */
 
 /*
- * Macro to mark a page protection value as "uncacheable".
- */
-#define pgprot_noncached(prot)                                  \
-        (__pgprot(pgprot_val((prot)) | _PAGE_PCD | _PAGE_PWT))
-
-/*
  * Conversion functions: convert a page and protection to a page entry,
  * and a page entry and page directory to the page they refer to.
  */
@@ -250,10 +244,22 @@ static inline int pud_large(pud_t pte)
 extern int direct_gbpages;
 
 /* Encode and de-code a swap entry */
-#define __swp_type(x)                   (((x).val >> 1) & 0x3f)
-#define __swp_offset(x)                 ((x).val >> 8)
-#define __swp_entry(type, offset)       ((swp_entry_t) { ((type) << 1) | \
-                                                         ((offset) << 8) })
+#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE
+#define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+#else
+#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1)
+#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1)
+#endif
+
+#define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
+
+#define __swp_type(x)                   (((x).val >> (_PAGE_BIT_PRESENT + 1)) \
+                                         & ((1U << SWP_TYPE_BITS) - 1))
+#define __swp_offset(x)                 ((x).val >> SWP_OFFSET_SHIFT)
+#define __swp_entry(type, offset)       ((swp_entry_t) { \
+                                         ((type) << (_PAGE_BIT_PRESENT + 1)) \
+                                         | ((offset) << SWP_OFFSET_SHIFT) })
 #define __pte_to_swp_entry(pte)         ((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)           ((pte_t) { .pte = (x).val })
 
diff --git a/arch/x86/include/asm/prctl.h b/arch/x86/include/asm/prctl.h
index fe681147a4f7..a8894647dd9a 100644
--- a/arch/x86/include/asm/prctl.h
+++ b/arch/x86/include/asm/prctl.h
@@ -6,5 +6,8 @@
 #define ARCH_GET_FS 0x1003
 #define ARCH_GET_GS 0x1004
 
+#ifdef CONFIG_X86_64
+extern long sys_arch_prctl(int, unsigned long);
+#endif /* CONFIG_X86_64 */
 
 #endif /* _ASM_X86_PRCTL_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5ca01e383269..091cd8855f2e 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -110,6 +110,7 @@ struct cpuinfo_x86 {
         /* Index into per_cpu list: */
         u16                     cpu_index;
 #endif
+        unsigned int            x86_hyper_vendor;
 } __attribute__((__aligned__(SMP_CACHE_BYTES)));
 
 #define X86_VENDOR_INTEL        0
@@ -123,6 +124,9 @@ struct cpuinfo_x86 {
 
 #define X86_VENDOR_UNKNOWN      0xff
 
+#define X86_HYPER_VENDOR_NONE  0
+#define X86_HYPER_VENDOR_VMWARE 1
+
 /*
  * capabilities of CPUs
  */
@@ -752,6 +756,19 @@ extern void switch_to_new_gdt(void);
 extern void cpu_init(void);
 extern void init_gdt(int cpu);
 
+static inline unsigned long get_debugctlmsr(void)
+{
+    unsigned long debugctlmsr = 0;
+
+#ifndef CONFIG_X86_DEBUGCTLMSR
+        if (boot_cpu_data.x86 < 6)
+                return 0;
+#endif
+        rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+
+    return debugctlmsr;
+}
+
 static inline void update_debugctlmsr(unsigned long debugctlmsr)
 {
 #ifndef CONFIG_X86_DEBUGCTLMSR
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index eefb0594b058..6d34d954c228 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -6,7 +6,6 @@
 #include <asm/processor-flags.h>
 
 #ifdef __KERNEL__
-#include <asm/ds.h>             /* the DS BTS struct is used for ptrace too */
 #include <asm/segment.h>
 #endif
 
@@ -128,34 +127,6 @@ struct pt_regs {
 #endif /* !__i386__ */
 
 
-#ifdef CONFIG_X86_PTRACE_BTS
-/* a branch trace record entry
- *
- * In order to unify the interface between various processor versions,
- * we use the below data structure for all processors.
- */
-enum bts_qualifier {
-        BTS_INVALID = 0,
-        BTS_BRANCH,
-        BTS_TASK_ARRIVES,
-        BTS_TASK_DEPARTS
-};
-
-struct bts_struct {
-        __u64 qualifier;
-        union {
-                /* BTS_BRANCH */
-                struct {
-                        __u64 from_ip;
-                        __u64 to_ip;
-                } lbr;
-                /* BTS_TASK_ARRIVES or
-                   BTS_TASK_DEPARTS */
-                __u64 jiffies;
-        } variant;
-};
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 #ifdef __KERNEL__
 
 #include <linux/init.h>
@@ -163,13 +134,6 @@ struct bts_struct {
 struct cpuinfo_x86;
 struct task_struct;
 
-#ifdef CONFIG_X86_PTRACE_BTS
-extern void __cpuinit ptrace_bts_init_intel(struct cpuinfo_x86 *);
-extern void ptrace_bts_take_timestamp(struct task_struct *, enum bts_qualifier);
-#else
-#define ptrace_bts_init_intel(config) do {} while (0)
-#endif /* CONFIG_X86_PTRACE_BTS */
-
 extern unsigned long profile_pc(struct pt_regs *regs);
 
 extern unsigned long
@@ -271,6 +235,13 @@ extern int do_get_thread_area(struct task_struct *p, int idx,
 extern int do_set_thread_area(struct task_struct *p, int idx,
                               struct user_desc __user *info, int can_allocate);
 
+extern void x86_ptrace_untrace(struct task_struct *);
+extern void x86_ptrace_fork(struct task_struct *child,
+                            unsigned long clone_flags);
+
+#define arch_ptrace_untrace(tsk) x86_ptrace_untrace(tsk)
+#define arch_ptrace_fork(child, flags) x86_ptrace_fork(child, flags)
+
 #endif /* __KERNEL__ */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 294daeb3a006..4fcd53fd5f43 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -8,6 +8,10 @@
 /* Interrupt control for vSMPowered x86_64 systems */
 void vsmp_init(void);
 
+
+void setup_bios_corruption_check(void);
+
+
 #ifdef CONFIG_X86_VISWS
 extern void visws_early_detect(void);
 extern int is_visws_box(void);
diff --git a/arch/x86/include/asm/sigframe.h b/arch/x86/include/asm/sigframe.h
new file mode 100644
index 000000000000..4e0fe26d27d3
--- /dev/null
+++ b/arch/x86/include/asm/sigframe.h
@@ -0,0 +1,70 @@
+#ifndef _ASM_X86_SIGFRAME_H
+#define _ASM_X86_SIGFRAME_H
+
+#include <asm/sigcontext.h>
+#include <asm/siginfo.h>
+#include <asm/ucontext.h>
+
+#ifdef CONFIG_X86_32
+#define sigframe_ia32           sigframe
+#define rt_sigframe_ia32        rt_sigframe
+#define sigcontext_ia32         sigcontext
+#define _fpstate_ia32           _fpstate
+#define ucontext_ia32           ucontext
+#else /* !CONFIG_X86_32 */
+
+#ifdef CONFIG_IA32_EMULATION
+#include <asm/ia32.h>
+#endif /* CONFIG_IA32_EMULATION */
+
+#endif /* CONFIG_X86_32 */
+
+#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
+struct sigframe_ia32 {
+        u32 pretcode;
+        int sig;
+        struct sigcontext_ia32 sc;
+        /*
+         * fpstate is unused. fpstate is moved/allocated after
+         * retcode[] below. This movement allows to have the FP state and the
+         * future state extensions (xsave) stay together.
+         * And at the same time retaining the unused fpstate, prevents changing
+         * the offset of extramask[] in the sigframe and thus prevent any
+         * legacy application accessing/modifying it.
+         */
+        struct _fpstate_ia32 fpstate_unused;
+#ifdef CONFIG_IA32_EMULATION
+        unsigned int extramask[_COMPAT_NSIG_WORDS-1];
+#else /* !CONFIG_IA32_EMULATION */
+        unsigned long extramask[_NSIG_WORDS-1];
+#endif /* CONFIG_IA32_EMULATION */
+        char retcode[8];
+        /* fp state follows here */
+};
+
+struct rt_sigframe_ia32 {
+        u32 pretcode;
+        int sig;
+        u32 pinfo;
+        u32 puc;
+#ifdef CONFIG_IA32_EMULATION
+        compat_siginfo_t info;
+#else /* !CONFIG_IA32_EMULATION */
+        struct siginfo info;
+#endif /* CONFIG_IA32_EMULATION */
+        struct ucontext_ia32 uc;
+        char retcode[8];
+        /* fp state follows here */
+};
+#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 */
+};
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_SIGFRAME_H */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 96ac44f275da..7761a5d554bb 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -121,6 +121,10 @@ typedef unsigned long sigset_t;
 
 #ifndef __ASSEMBLY__
 
+# ifdef __KERNEL__
+extern void do_notify_resume(struct pt_regs *, void *, __u32);
+# endif /* __KERNEL__ */
+
 #ifdef __i386__
 # ifdef __KERNEL__
 struct old_sigaction {
@@ -141,8 +145,6 @@ struct k_sigaction {
         struct sigaction sa;
 };
 
-extern void do_notify_resume(struct pt_regs *, void *, __u32);
-
 # else /* __KERNEL__ */
 /* Here we must cater to libcs that poke about in kernel headers.  */
 
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index be44f7dab395..e3cc3c063ec5 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -27,7 +27,7 @@
 #else /* CONFIG_X86_32 */
 # define SECTION_SIZE_BITS      27 /* matt - 128 is convenient right now */
 # define MAX_PHYSADDR_BITS      44
-# define MAX_PHYSMEM_BITS       44
+# define MAX_PHYSMEM_BITS       44 /* Can be max 45 bits */
 #endif
 
 #endif /* CONFIG_SPARSEMEM */
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 87803da44010..9c6797c3e56c 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -19,6 +19,13 @@
 /* kernel/ioport.c */
 asmlinkage long sys_ioperm(unsigned long, unsigned long, int);
 
+/* kernel/ldt.c */
+asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
+
+/* kernel/tls.c */
+asmlinkage int sys_set_thread_area(struct user_desc __user *);
+asmlinkage int sys_get_thread_area(struct user_desc __user *);
+
 /* X86_32 only */
 #ifdef CONFIG_X86_32
 /* kernel/process_32.c */
@@ -33,14 +40,11 @@ asmlinkage int sys_sigaction(int, const struct old_sigaction __user *,
                              struct old_sigaction __user *);
 asmlinkage int sys_sigaltstack(unsigned long);
 asmlinkage unsigned long sys_sigreturn(unsigned long);
-asmlinkage int sys_rt_sigreturn(unsigned long);
+asmlinkage int sys_rt_sigreturn(struct pt_regs);
 
 /* kernel/ioport.c */
 asmlinkage long sys_iopl(unsigned long);
 
-/* kernel/ldt.c */
-asmlinkage int sys_modify_ldt(int, void __user *, unsigned long);
-
 /* kernel/sys_i386_32.c */
 asmlinkage long sys_mmap2(unsigned long, unsigned long, unsigned long,
                           unsigned long, unsigned long, unsigned long);
@@ -54,10 +58,6 @@ asmlinkage int sys_uname(struct old_utsname __user *);
 struct oldold_utsname;
 asmlinkage int sys_olduname(struct oldold_utsname __user *);
 
-/* kernel/tls.c */
-asmlinkage int sys_set_thread_area(struct user_desc __user *);
-asmlinkage int sys_get_thread_area(struct user_desc __user *);
-
 /* kernel/vm86_32.c */
 asmlinkage int sys_vm86old(struct pt_regs);
 asmlinkage int sys_vm86(struct pt_regs);
diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h
index 07c3e4048991..8e626ea33a1a 100644
--- a/arch/x86/include/asm/system.h
+++ b/arch/x86/include/asm/system.h
@@ -17,12 +17,12 @@
 # define AT_VECTOR_SIZE_ARCH 1
 #endif
 
-#ifdef CONFIG_X86_32
-
 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);
 
+#ifdef CONFIG_X86_32
+
 /*
  * Saving eflags is important. It switches not only IOPL between tasks,
  * it also protects other tasks from NT leaking through sysenter etc.
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 0921b4018c11..98789647baa9 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -26,7 +26,7 @@ struct exec_domain;
 struct thread_info {
         struct task_struct      *task;          /* main task structure */
         struct exec_domain      *exec_domain;   /* execution domain */
-        unsigned long           flags;          /* low level flags */
+        __u32                   flags;          /* low level flags */
         __u32                   status;         /* thread synchronous flags */
         __u32                   cpu;            /* current CPU */
         int                     preempt_count;  /* 0 => preemptable,
@@ -93,7 +93,6 @@ struct thread_info {
 #define TIF_FORCED_TF           24      /* true if TF in eflags artificially */
 #define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
-#define TIF_BTS_TRACE_TS        27      /* record scheduling event timestamps */
 
 #define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME      (1 << TIF_NOTIFY_RESUME)
@@ -115,7 +114,6 @@ struct thread_info {
 #define _TIF_FORCED_TF          (1 << TIF_FORCED_TF)
 #define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
-#define _TIF_BTS_TRACE_TS       (1 << TIF_BTS_TRACE_TS)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY \
@@ -141,8 +139,7 @@ struct thread_info {
 
 /* flags to check in __switch_to() */
 #define _TIF_WORK_CTXSW                                                 \
-        (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_BTS_TRACE_TS| \
-                                                                _TIF_NOTSC)
+        (_TIF_IO_BITMAP|_TIF_DEBUGCTLMSR|_TIF_DS_AREA_MSR|_TIF_NOTSC)
 
 #define _TIF_WORK_CTXSW_PREV _TIF_WORK_CTXSW
 #define _TIF_WORK_CTXSW_NEXT (_TIF_WORK_CTXSW|_TIF_DEBUG)
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 79e31e9dcdda..4e2f2e0aab27 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -61,13 +61,19 @@ static inline int cpu_to_node(int cpu)
  *
  * Side note: this function creates the returned cpumask on the stack
  * so with a high NR_CPUS count, excessive stack space is used.  The
- * node_to_cpumask_ptr function should be used whenever possible.
+ * cpumask_of_node function should be used whenever possible.
  */
 static inline cpumask_t node_to_cpumask(int node)
 {
         return node_to_cpumask_map[node];
 }
 
+/* Returns a bitmask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
+{
+        return &node_to_cpumask_map[node];
+}
+
 #else /* CONFIG_X86_64 */
 
 /* Mappings between node number and cpus on that node. */
@@ -82,7 +88,7 @@ DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 extern int cpu_to_node(int cpu);
 extern int early_cpu_to_node(int cpu);
-extern const cpumask_t *_node_to_cpumask_ptr(int node);
+extern const cpumask_t *cpumask_of_node(int node);
 extern cpumask_t node_to_cpumask(int node);
 
 #else   /* !CONFIG_DEBUG_PER_CPU_MAPS */
@@ -103,7 +109,7 @@ static inline int early_cpu_to_node(int cpu)
 }
 
 /* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+static inline const cpumask_t *cpumask_of_node(int node)
 {
         return &node_to_cpumask_map[node];
 }
@@ -116,12 +122,15 @@ static inline cpumask_t node_to_cpumask(int node)
 
 #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
 
-/* Replace default node_to_cpumask_ptr with optimized version */
+/*
+ * Replace default node_to_cpumask_ptr with optimized version
+ * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
+ */
 #define node_to_cpumask_ptr(v, node)            \
-                const cpumask_t *v = _node_to_cpumask_ptr(node)
+                const cpumask_t *v = cpumask_of_node(node)
 
 #define node_to_cpumask_ptr_next(v, node)       \
-                           v = _node_to_cpumask_ptr(node)
+                           v = cpumask_of_node(node)
 
 #endif /* CONFIG_X86_64 */
 
@@ -187,7 +196,7 @@ extern int __node_distance(int, int);
 #define cpu_to_node(cpu)        0
 #define early_cpu_to_node(cpu)  0
 
-static inline const cpumask_t *_node_to_cpumask_ptr(int node)
+static inline const cpumask_t *cpumask_of_node(int node)
 {
         return &cpu_online_map;
 }
@@ -200,12 +209,15 @@ static inline int node_to_first_cpu(int node)
         return first_cpu(cpu_online_map);
 }
 
-/* Replace default node_to_cpumask_ptr with optimized version */
+/*
+ * Replace default node_to_cpumask_ptr with optimized version
+ * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
+ */
 #define node_to_cpumask_ptr(v, node)            \
-                const cpumask_t *v = _node_to_cpumask_ptr(node)
+                const cpumask_t *v = cpumask_of_node(node)
 
 #define node_to_cpumask_ptr_next(v, node)       \
-                           v = _node_to_cpumask_ptr(node)
+                           v = cpumask_of_node(node)
 #endif
 
 #include <asm-generic/topology.h>
@@ -214,12 +226,12 @@ static inline int node_to_first_cpu(int node)
 /* Returns the number of the first CPU on Node 'node'. */
 static inline int node_to_first_cpu(int node)
 {
-        node_to_cpumask_ptr(mask, node);
-        return first_cpu(*mask);
+        return cpumask_first(cpumask_of_node(node));
 }
 #endif
 
 extern cpumask_t cpu_coregroup_map(int cpu);
+extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)       (cpu_data(cpu).phys_proc_id)
diff --git a/arch/x86/include/asm/trampoline.h b/arch/x86/include/asm/trampoline.h
index fa0d79facdbc..780ba0ab94f9 100644
--- a/arch/x86/include/asm/trampoline.h
+++ b/arch/x86/include/asm/trampoline.h
@@ -3,6 +3,7 @@
 
 #ifndef __ASSEMBLY__
 
+#ifdef CONFIG_X86_TRAMPOLINE
 /*
  * Trampoline 80x86 program as an array.
  */
@@ -13,8 +14,14 @@ extern unsigned char *trampoline_base;
 extern unsigned long init_rsp;
 extern unsigned long initial_code;
 
+#define TRAMPOLINE_SIZE roundup(trampoline_end - trampoline_data, PAGE_SIZE)
 #define TRAMPOLINE_BASE 0x6000
+
 extern unsigned long setup_trampoline(void);
+extern void __init reserve_trampoline_memory(void);
+#else
+static inline void reserve_trampoline_memory(void) {};
+#endif /* CONFIG_X86_TRAMPOLINE */
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h
index 45dee286e45c..2ee0a3bceedf 100644
--- a/arch/x86/include/asm/traps.h
+++ b/arch/x86/include/asm/traps.h
@@ -46,6 +46,10 @@ dotraplinkage void do_coprocessor_segment_overrun(struct pt_regs *, long);
 dotraplinkage void do_invalid_TSS(struct pt_regs *, long);
 dotraplinkage void do_segment_not_present(struct pt_regs *, long);
 dotraplinkage void do_stack_segment(struct pt_regs *, long);
+#ifdef CONFIG_X86_64
+dotraplinkage void do_double_fault(struct pt_regs *, long);
+asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *);
+#endif
 dotraplinkage void do_general_protection(struct pt_regs *, long);
 dotraplinkage void do_page_fault(struct pt_regs *, unsigned long);
 dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long);
@@ -72,10 +76,13 @@ static inline int get_si_code(unsigned long condition)
 extern int panic_on_unrecovered_nmi;
 extern int kstack_depth_to_print;
 
-#ifdef CONFIG_X86_32
 void math_error(void __user *);
-unsigned long patch_espfix_desc(unsigned long, unsigned long);
 asmlinkage void math_emulate(long);
+#ifdef CONFIG_X86_32
+unsigned long patch_espfix_desc(unsigned long, unsigned long);
+#else
+asmlinkage void smp_thermal_interrupt(void);
+asmlinkage void mce_threshold_interrupt(void);
 #endif
 
 #endif /* _ASM_X86_TRAPS_H */
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 9cd83a8e40d5..38ae163cc91b 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -34,8 +34,6 @@ static inline cycles_t get_cycles(void)
 
 static __always_inline cycles_t vget_cycles(void)
 {
-        cycles_t cycles;
-
         /*
          * We only do VDSOs on TSC capable CPUs, so this shouldnt
          * access boot_cpu_data (which is not VDSO-safe):
@@ -44,11 +42,7 @@ static __always_inline cycles_t vget_cycles(void)
         if (!cpu_has_tsc)
                 return 0;
 #endif
-        rdtsc_barrier();
-        cycles = (cycles_t)__native_read_tsc();
-        rdtsc_barrier();
-
-        return cycles;
+        return (cycles_t)__native_read_tsc();
 }
 
 extern void tsc_init(void);
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 99192bb55a53..4340055b7559 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -352,14 +352,14 @@ do {									\
 
 #define __put_user_nocheck(x, ptr, size)                        \
 ({                                                              \
-        long __pu_err;                                          \
+        int __pu_err;                                           \
         __put_user_size((x), (ptr), (size), __pu_err, -EFAULT); \
         __pu_err;                                               \
 })
 
 #define __get_user_nocheck(x, ptr, size)                                \
 ({                                                                      \
-        long __gu_err;                                                  \
+        int __gu_err;                                                   \
         unsigned long __gu_val;                                         \
         __get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);    \
         (x) = (__force __typeof__(*(ptr)))__gu_val;                     \
diff --git a/arch/x86/include/asm/uv/bios.h b/arch/x86/include/asm/uv/bios.h
index d931d3b7e6f7..7ed17ff502b9 100644
--- a/arch/x86/include/asm/uv/bios.h
+++ b/arch/x86/include/asm/uv/bios.h
@@ -32,13 +32,18 @@
 enum uv_bios_cmd {
         UV_BIOS_COMMON,
         UV_BIOS_GET_SN_INFO,
-        UV_BIOS_FREQ_BASE
+        UV_BIOS_FREQ_BASE,
+        UV_BIOS_WATCHLIST_ALLOC,
+        UV_BIOS_WATCHLIST_FREE,
+        UV_BIOS_MEMPROTECT,
+        UV_BIOS_GET_PARTITION_ADDR
 };
 
 /*
  * Status values returned from a BIOS call.
  */
 enum {
+        BIOS_STATUS_MORE_PASSES         =  1,
         BIOS_STATUS_SUCCESS             =  0,
         BIOS_STATUS_UNIMPLEMENTED       = -ENOSYS,
         BIOS_STATUS_EINVAL              = -EINVAL,
@@ -71,6 +76,21 @@ union partition_info_u {
         };
 };
 
+union uv_watchlist_u {
+        u64     val;
+        struct {
+                u64     blade   : 16,
+                        size    : 32,
+                        filler  : 16;
+        };
+};
+
+enum uv_memprotect {
+        UV_MEMPROT_RESTRICT_ACCESS,
+        UV_MEMPROT_ALLOW_AMO,
+        UV_MEMPROT_ALLOW_RW
+};
+
 /*
  * bios calls have 6 parameters
  */
@@ -80,14 +100,20 @@ extern s64 uv_bios_call_reentrant(enum uv_bios_cmd, u64, u64, u64, u64, u64);
 
 extern s64 uv_bios_get_sn_info(int, int *, long *, long *, long *);
 extern s64 uv_bios_freq_base(u64, u64 *);
+extern int uv_bios_mq_watchlist_alloc(int, unsigned long, unsigned int,
+                                        unsigned long *);
+extern int uv_bios_mq_watchlist_free(int, int);
+extern s64 uv_bios_change_memprotect(u64, u64, enum uv_memprotect);
+extern s64 uv_bios_reserved_page_pa(u64, u64 *, u64 *, u64 *);
 
 extern void uv_bios_init(void);
 
+extern unsigned long sn_rtc_cycles_per_second;
 extern int uv_type;
 extern long sn_partition_id;
-extern long uv_coherency_id;
-extern long uv_region_size;
-#define partition_coherence_id()        (uv_coherency_id)
+extern long sn_coherency_id;
+extern long sn_region_size;
+#define partition_coherence_id()        (sn_coherency_id)
 
 extern struct kobject *sgi_uv_kobj;     /* /sys/firmware/sgi_uv */
 
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 7a5782610b2b..777327ef05c1 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -113,25 +113,37 @@
  */
 #define UV_MAX_NASID_VALUE      (UV_MAX_NUMALINK_NODES * 2)
 
+struct uv_scir_s {
+        struct timer_list timer;
+        unsigned long   offset;
+        unsigned long   last;
+        unsigned long   idle_on;
+        unsigned long   idle_off;
+        unsigned char   state;
+        unsigned char   enabled;
+};
+
 /*
  * The following defines attributes of the HUB chip. These attributes are
  * frequently referenced and are kept in the per-cpu data areas of each cpu.
  * They are kept together in a struct to minimize cache misses.
  */
 struct uv_hub_info_s {
-        unsigned long   global_mmr_base;
-        unsigned long   gpa_mask;
-        unsigned long   gnode_upper;
-        unsigned long   lowmem_remap_top;
-        unsigned long   lowmem_remap_base;
-        unsigned short  pnode;
-        unsigned short  pnode_mask;
-        unsigned short  coherency_domain_number;
-        unsigned short  numa_blade_id;
-        unsigned char   blade_processor_id;
-        unsigned char   m_val;
-        unsigned char   n_val;
+        unsigned long           global_mmr_base;
+        unsigned long           gpa_mask;
+        unsigned long           gnode_upper;
+        unsigned long           lowmem_remap_top;
+        unsigned long           lowmem_remap_base;
+        unsigned short          pnode;
+        unsigned short          pnode_mask;
+        unsigned short          coherency_domain_number;
+        unsigned short          numa_blade_id;
+        unsigned char           blade_processor_id;
+        unsigned char           m_val;
+        unsigned char           n_val;
+        struct uv_scir_s        scir;
 };
+
 DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define uv_hub_info             (&__get_cpu_var(__uv_hub_info))
 #define uv_cpu_hub_info(cpu)    (&per_cpu(__uv_hub_info, cpu))
@@ -163,6 +175,30 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 
 #define UV_APIC_PNODE_SHIFT     6
 
+/* Local Bus from cpu's perspective */
+#define LOCAL_BUS_BASE          0x1c00000
+#define LOCAL_BUS_SIZE          (4 * 1024 * 1024)
+
+/*
+ * System Controller Interface Reg
+ *
+ * Note there are NO leds on a UV system.  This register is only
+ * used by the system controller to monitor system-wide operation.
+ * There are 64 regs per node.  With Nahelem cpus (2 cores per node,
+ * 8 cpus per core, 2 threads per cpu) there are 32 cpu threads on
+ * a node.
+ *
+ * The window is located at top of ACPI MMR space
+ */
+#define SCIR_WINDOW_COUNT       64
+#define SCIR_LOCAL_MMR_BASE     (LOCAL_BUS_BASE + \
+                                 LOCAL_BUS_SIZE - \
+                                 SCIR_WINDOW_COUNT)
+
+#define SCIR_CPU_HEARTBEAT      0x01    /* timer interrupt */
+#define SCIR_CPU_ACTIVITY       0x02    /* not idle */
+#define SCIR_CPU_HB_INTERVAL    (HZ)    /* once per second */
+
 /*
  * Macros for converting between kernel virtual addresses, socket local physical
  * addresses, and UV global physical addresses.
@@ -174,7 +210,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 {
         if (paddr < uv_hub_info->lowmem_remap_top)
-                paddr += uv_hub_info->lowmem_remap_base;
+                paddr |= uv_hub_info->lowmem_remap_base;
         return paddr | uv_hub_info->gnode_upper;
 }
 
@@ -182,19 +218,7 @@ static inline unsigned long uv_soc_phys_ram_to_gpa(unsigned long paddr)
 /* socket virtual --> UV global physical address */
 static inline unsigned long uv_gpa(void *v)
 {
-        return __pa(v) | uv_hub_info->gnode_upper;
-}
-
-/* socket virtual --> UV global physical address */
-static inline void *uv_vgpa(void *v)
-{
-        return (void *)uv_gpa(v);
-}
-
-/* UV global physical address --> socket virtual */
-static inline void *uv_va(unsigned long gpa)
-{
-        return __va(gpa & uv_hub_info->gpa_mask);
+        return uv_soc_phys_ram_to_gpa(__pa(v));
 }
 
 /* pnode, offset --> socket virtual */
@@ -277,6 +301,16 @@ static inline void uv_write_local_mmr(unsigned long offset, unsigned long val)
         *uv_local_mmr_address(offset) = val;
 }
 
+static inline unsigned char uv_read_local_mmr8(unsigned long offset)
+{
+        return *((unsigned char *)uv_local_mmr_address(offset));
+}
+
+static inline void uv_write_local_mmr8(unsigned long offset, unsigned char val)
+{
+        *((unsigned char *)uv_local_mmr_address(offset)) = val;
+}
+
 /*
  * Structures and definitions for converting between cpu, node, pnode, and blade
  * numbers.
@@ -351,5 +385,20 @@ static inline int uv_num_possible_blades(void)
         return uv_possible_blades;
 }
 
-#endif /* _ASM_X86_UV_UV_HUB_H */
+/* Update SCIR state */
+static inline void uv_set_scir_bits(unsigned char value)
+{
+        if (uv_hub_info->scir.state != value) {
+                uv_hub_info->scir.state = value;
+                uv_write_local_mmr8(uv_hub_info->scir.offset, value);
+        }
+}
+static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
+{
+        if (uv_cpu_hub_info(cpu)->scir.state != value) {
+                uv_cpu_hub_info(cpu)->scir.state = value;
+                uv_write_local_mmr8(uv_cpu_hub_info(cpu)->scir.offset, value);
+        }
+}
 
+#endif /* _ASM_X86_UV_UV_HUB_H */
diff --git a/arch/x86/include/asm/vmware.h b/arch/x86/include/asm/vmware.h
new file mode 100644
index 000000000000..c11b7e100d83
--- /dev/null
+++ b/arch/x86/include/asm/vmware.h
@@ -0,0 +1,27 @@
+/*
+ * Copyright (C) 2008, VMware, Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+ *
+ */
+#ifndef ASM_X86__VMWARE_H
+#define ASM_X86__VMWARE_H
+
+extern unsigned long vmware_get_tsc_khz(void);
+extern int vmware_platform(void);
+extern void vmware_set_feature_bits(struct cpuinfo_x86 *c);
+
+#endif
diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h
index 3f6000d95fe2..5e79ca694326 100644
--- a/arch/x86/include/asm/xen/hypercall.h
+++ b/arch/x86/include/asm/xen/hypercall.h
@@ -33,8 +33,14 @@
 #ifndef _ASM_X86_XEN_HYPERCALL_H
 #define _ASM_X86_XEN_HYPERCALL_H
 
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/types.h>
+
+#include <asm/page.h>
+#include <asm/pgtable.h>
 
 #include <xen/interface/xen.h>
 #include <xen/interface/sched.h>
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index a38d25ac87d2..81fbd735aec4 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -33,39 +33,10 @@
 #ifndef _ASM_X86_XEN_HYPERVISOR_H
 #define _ASM_X86_XEN_HYPERVISOR_H
 
-#include <linux/types.h>
-#include <linux/kernel.h>
-
-#include <xen/interface/xen.h>
-#include <xen/interface/version.h>
-
-#include <asm/ptrace.h>
-#include <asm/page.h>
-#include <asm/desc.h>
-#if defined(__i386__)
-#  ifdef CONFIG_X86_PAE
-#   include <asm-generic/pgtable-nopud.h>
-#  else
-#   include <asm-generic/pgtable-nopmd.h>
-#  endif
-#endif
-#include <asm/xen/hypercall.h>
-
 /* arch/i386/kernel/setup.c */
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
-/* arch/i386/mach-xen/evtchn.c */
-/* Force a proper event-channel callback from Xen. */
-extern void force_evtchn_callback(void);
-
-/* Turn jiffies into Xen system time. */
-u64 jiffies_to_st(unsigned long jiffies);
-
-
-#define MULTI_UVMFLAGS_INDEX 3
-#define MULTI_UVMDOMID_INDEX 4
-
 enum xen_domain_type {
         XEN_NATIVE,
         XEN_PV_DOMAIN,
@@ -74,9 +45,15 @@ enum xen_domain_type {
 
 extern enum xen_domain_type xen_domain_type;
 
+#ifdef CONFIG_XEN
 #define xen_domain()            (xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()         (xen_domain_type == XEN_PV_DOMAIN)
+#else
+#define xen_domain()            (0)
+#endif
+
+#define xen_pv_domain()         (xen_domain() && xen_domain_type == XEN_PV_DOMAIN)
+#define xen_hvm_domain()        (xen_domain() && xen_domain_type == XEN_HVM_DOMAIN)
+
 #define xen_initial_domain()    (xen_pv_domain() && xen_start_info->flags & SIF_INITDOMAIN)
-#define xen_hvm_domain()        (xen_domain_type == XEN_HVM_DOMAIN)
 
 #endif /* _ASM_X86_XEN_HYPERVISOR_H */
diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h
index bc628998a1b9..7ef617ef1df3 100644
--- a/arch/x86/include/asm/xen/page.h
+++ b/arch/x86/include/asm/xen/page.h
@@ -1,11 +1,16 @@
 #ifndef _ASM_X86_XEN_PAGE_H
 #define _ASM_X86_XEN_PAGE_H
 
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/spinlock.h>
 #include <linux/pfn.h>
 
 #include <asm/uaccess.h>
+#include <asm/page.h>
 #include <asm/pgtable.h>
 
+#include <xen/interface/xen.h>
 #include <xen/features.h>
 
 /* Xen machine address */