Merge branch 'tracing/core' into tracing/hw-breakpoints

Conflicts:
	arch/Kconfig
	kernel/trace/trace.h

Merge reason: resolve the conflicts, plus adopt to the new
              ring-buffer APIs.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

40 files changed, 290 insertions, 433 deletions

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 4518dc500903..20d1465a2ab0 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -144,6 +144,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate)
 
 #else /* !CONFIG_ACPI */
 
+#define acpi_disabled 1
 #define acpi_lapic 0
 #define acpi_ioapic 0
 static inline void acpi_noirq_set(void) { }
diff --git a/arch/x86/include/asm/amd_iommu.h b/arch/x86/include/asm/amd_iommu.h
index 262e02820049..bdf96f119f06 100644
--- a/arch/x86/include/asm/amd_iommu.h
+++ b/arch/x86/include/asm/amd_iommu.h
@@ -29,9 +29,11 @@ extern void amd_iommu_detect(void);
 extern irqreturn_t amd_iommu_int_handler(int irq, void *data);
 extern void amd_iommu_flush_all_domains(void);
 extern void amd_iommu_flush_all_devices(void);
+extern void amd_iommu_shutdown(void);
 #else
 static inline int amd_iommu_init(void) { return -ENODEV; }
 static inline void amd_iommu_detect(void) { }
+static inline void amd_iommu_shutdown(void) { }
 #endif
 
 #endif /* _ASM_X86_AMD_IOMMU_H */
diff --git a/arch/x86/include/asm/atomic_32.h b/arch/x86/include/asm/atomic_32.h
index 8cb9c814e120..dc5a667ff791 100644
--- a/arch/x86/include/asm/atomic_32.h
+++ b/arch/x86/include/asm/atomic_32.h
@@ -19,7 +19,10 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)          ((v)->counter)
+static inline int atomic_read(const atomic_t *v)
+{
+        return v->counter;
+}
 
 /**
  * atomic_set - set atomic variable
@@ -28,7 +31,10 @@
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic_set(v, i)        (((v)->counter) = (i))
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
 
 /**
  * atomic_add - add integer to atomic variable
@@ -200,8 +206,15 @@ static inline int atomic_sub_return(int i, atomic_t *v)
         return atomic_add_return(-i, v);
 }
 
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+        return cmpxchg(&v->counter, old, new);
+}
+
+static inline int atomic_xchg(atomic_t *v, int new)
+{
+        return xchg(&v->counter, new);
+}
 
 /**
  * atomic_add_unless - add unless the number is already a given value
@@ -250,67 +263,22 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 /* An 64bit atomic type */
 
 typedef struct {
-        unsigned long long counter;
+        u64 __aligned(8) counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(val)      { (val) }
 
-/**
- * atomic64_read - read atomic64 variable
- * @v: pointer of type atomic64_t
- *
- * Atomically reads the value of @v.
- * Doesn't imply a read memory barrier.
- */
-#define __atomic64_read(ptr)            ((ptr)->counter)
-
-static inline unsigned long long
-cmpxchg8b(unsigned long long *ptr, unsigned long long old, unsigned long long new)
-{
-        asm volatile(
-
-                LOCK_PREFIX "cmpxchg8b (%[ptr])\n"
-
-                     :          "=A" (old)
-
-                     : [ptr]    "D" (ptr),
-                                "A" (old),
-                                "b" (ll_low(new)),
-                                "c" (ll_high(new))
-
-                     : "memory");
-
-        return old;
-}
-
-static inline unsigned long long
-atomic64_cmpxchg(atomic64_t *ptr, unsigned long long old_val,
-                 unsigned long long new_val)
-{
-        return cmpxchg8b(&ptr->counter, old_val, new_val);
-}
+extern u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old_val, u64 new_val);
 
 /**
  * atomic64_xchg - xchg atomic64 variable
  * @ptr:      pointer to type atomic64_t
  * @new_val:  value to assign
- * @old_val:  old value that was there
  *
  * Atomically xchgs the value of @ptr to @new_val and returns
  * the old value.
  */
-
-static inline unsigned long long
-atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
-{
-        unsigned long long old_val;
-
-        do {
-                old_val = atomic_read(ptr);
-        } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
-
-        return old_val;
-}
+extern u64 atomic64_xchg(atomic64_t *ptr, u64 new_val);
 
 /**
  * atomic64_set - set atomic64 variable
@@ -319,10 +287,7 @@ atomic64_xchg(atomic64_t *ptr, unsigned long long new_val)
  *
  * Atomically sets the value of @ptr to @new_val.
  */
-static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
-{
-        atomic64_xchg(ptr, new_val);
-}
+extern void atomic64_set(atomic64_t *ptr, u64 new_val);
 
 /**
  * atomic64_read - read atomic64 variable
@@ -330,17 +295,30 @@ static inline void atomic64_set(atomic64_t *ptr, unsigned long long new_val)
  *
  * Atomically reads the value of @ptr and returns it.
  */
-static inline unsigned long long atomic64_read(atomic64_t *ptr)
+static inline u64 atomic64_read(atomic64_t *ptr)
 {
-        unsigned long long curr_val;
-
-        do {
-                curr_val = __atomic64_read(ptr);
-        } while (atomic64_cmpxchg(ptr, curr_val, curr_val) != curr_val);
-
-        return curr_val;
+        u64 res;
+
+        /*
+         * Note, we inline this atomic64_t primitive because
+         * it only clobbers EAX/EDX and leaves the others
+         * untouched. We also (somewhat subtly) rely on the
+         * fact that cmpxchg8b returns the current 64-bit value
+         * of the memory location we are touching:
+         */
+        asm volatile(
+                "mov %%ebx, %%eax\n\t"
+                "mov %%ecx, %%edx\n\t"
+                LOCK_PREFIX "cmpxchg8b %1\n"
+                        : "=&A" (res)
+                        : "m" (*ptr)
+                );
+
+        return res;
 }
 
+extern u64 atomic64_read(atomic64_t *ptr);
+
 /**
  * atomic64_add_return - add and return
  * @delta: integer value to add
@@ -348,34 +326,14 @@ static inline unsigned long long atomic64_read(atomic64_t *ptr)
  *
  * Atomically adds @delta to @ptr and returns @delta + *@ptr
  */
-static inline unsigned long long
-atomic64_add_return(unsigned long long delta, atomic64_t *ptr)
-{
-        unsigned long long old_val, new_val;
-
-        do {
-                old_val = atomic_read(ptr);
-                new_val = old_val + delta;
-
-        } while (atomic64_cmpxchg(ptr, old_val, new_val) != old_val);
-
-        return new_val;
-}
-
-static inline long atomic64_sub_return(unsigned long long delta, atomic64_t *ptr)
-{
-        return atomic64_add_return(-delta, ptr);
-}
+extern u64 atomic64_add_return(u64 delta, atomic64_t *ptr);
 
-static inline long atomic64_inc_return(atomic64_t *ptr)
-{
-        return atomic64_add_return(1, ptr);
-}
-
-static inline long atomic64_dec_return(atomic64_t *ptr)
-{
-        return atomic64_sub_return(1, ptr);
-}
+/*
+ * Other variants with different arithmetic operators:
+ */
+extern u64 atomic64_sub_return(u64 delta, atomic64_t *ptr);
+extern u64 atomic64_inc_return(atomic64_t *ptr);
+extern u64 atomic64_dec_return(atomic64_t *ptr);
 
 /**
  * atomic64_add - add integer to atomic64 variable
@@ -384,10 +342,7 @@ static inline long atomic64_dec_return(atomic64_t *ptr)
  *
  * Atomically adds @delta to @ptr.
  */
-static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
-{
-        atomic64_add_return(delta, ptr);
-}
+extern void atomic64_add(u64 delta, atomic64_t *ptr);
 
 /**
  * atomic64_sub - subtract the atomic64 variable
@@ -396,10 +351,7 @@ static inline void atomic64_add(unsigned long long delta, atomic64_t *ptr)
  *
  * Atomically subtracts @delta from @ptr.
  */
-static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
-{
-        atomic64_add(-delta, ptr);
-}
+extern void atomic64_sub(u64 delta, atomic64_t *ptr);
 
 /**
  * atomic64_sub_and_test - subtract value from variable and test result
@@ -410,13 +362,7 @@ static inline void atomic64_sub(unsigned long long delta, atomic64_t *ptr)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int
-atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
-{
-        unsigned long long old_val = atomic64_sub_return(delta, ptr);
-
-        return old_val == 0;
-}
+extern int atomic64_sub_and_test(u64 delta, atomic64_t *ptr);
 
 /**
  * atomic64_inc - increment atomic64 variable
@@ -424,10 +370,7 @@ atomic64_sub_and_test(unsigned long long delta, atomic64_t *ptr)
  *
  * Atomically increments @ptr by 1.
  */
-static inline void atomic64_inc(atomic64_t *ptr)
-{
-        atomic64_add(1, ptr);
-}
+extern void atomic64_inc(atomic64_t *ptr);
 
 /**
  * atomic64_dec - decrement atomic64 variable
@@ -435,10 +378,7 @@ static inline void atomic64_inc(atomic64_t *ptr)
  *
  * Atomically decrements @ptr by 1.
  */
-static inline void atomic64_dec(atomic64_t *ptr)
-{
-        atomic64_sub(1, ptr);
-}
+extern void atomic64_dec(atomic64_t *ptr);
 
 /**
  * atomic64_dec_and_test - decrement and test
@@ -448,10 +388,7 @@ static inline void atomic64_dec(atomic64_t *ptr)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic64_dec_and_test(atomic64_t *ptr)
-{
-        return atomic64_sub_and_test(1, ptr);
-}
+extern int atomic64_dec_and_test(atomic64_t *ptr);
 
 /**
  * atomic64_inc_and_test - increment and test
@@ -461,10 +398,7 @@ static inline int atomic64_dec_and_test(atomic64_t *ptr)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_inc_and_test(atomic64_t *ptr)
-{
-        return atomic64_sub_and_test(-1, ptr);
-}
+extern int atomic64_inc_and_test(atomic64_t *ptr);
 
 /**
  * atomic64_add_negative - add and test if negative
@@ -475,13 +409,7 @@ static inline int atomic64_inc_and_test(atomic64_t *ptr)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int
-atomic64_add_negative(unsigned long long delta, atomic64_t *ptr)
-{
-        long long old_val = atomic64_add_return(delta, ptr);
-
-        return old_val < 0;
-}
+extern int atomic64_add_negative(u64 delta, atomic64_t *ptr);
 
 #include <asm-generic/atomic-long.h>
 #endif /* _ASM_X86_ATOMIC_32_H */
diff --git a/arch/x86/include/asm/atomic_64.h b/arch/x86/include/asm/atomic_64.h
index 0d6360220007..d605dc268e79 100644
--- a/arch/x86/include/asm/atomic_64.h
+++ b/arch/x86/include/asm/atomic_64.h
@@ -18,7 +18,10 @@
  *
  * Atomically reads the value of @v.
  */
-#define atomic_read(v)          ((v)->counter)
+static inline int atomic_read(const atomic_t *v)
+{
+        return v->counter;
+}
 
 /**
  * atomic_set - set atomic variable
@@ -27,7 +30,10 @@
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic_set(v, i)                (((v)->counter) = (i))
+static inline void atomic_set(atomic_t *v, int i)
+{
+        v->counter = i;
+}
 
 /**
  * atomic_add - add integer to atomic variable
@@ -192,7 +198,10 @@ static inline int atomic_sub_return(int i, atomic_t *v)
  * Atomically reads the value of @v.
  * Doesn't imply a read memory barrier.
  */
-#define atomic64_read(v)                ((v)->counter)
+static inline long atomic64_read(const atomic64_t *v)
+{
+        return v->counter;
+}
 
 /**
  * atomic64_set - set atomic64 variable
@@ -201,7 +210,10 @@ static inline int atomic_sub_return(int i, atomic_t *v)
  *
  * Atomically sets the value of @v to @i.
  */
-#define atomic64_set(v, i)              (((v)->counter) = (i))
+static inline void atomic64_set(atomic64_t *v, long i)
+{
+        v->counter = i;
+}
 
 /**
  * atomic64_add - add integer to atomic64 variable
@@ -355,11 +367,25 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 #define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
 #define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
 
-#define atomic64_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic64_xchg(v, new) (xchg(&((v)->counter), new))
+static inline long atomic64_cmpxchg(atomic64_t *v, long old, long new)
+{
+        return cmpxchg(&v->counter, old, new);
+}
+
+static inline long atomic64_xchg(atomic64_t *v, long new)
+{
+        return xchg(&v->counter, new);
+}
 
-#define atomic_cmpxchg(v, old, new) (cmpxchg(&((v)->counter), (old), (new)))
-#define atomic_xchg(v, new) (xchg(&((v)->counter), (new)))
+static inline long atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+        return cmpxchg(&v->counter, old, new);
+}
+
+static inline long atomic_xchg(atomic_t *v, int new)
+{
+        return xchg(&v->counter, new);
+}
 
 /**
  * atomic_add_unless - add unless the number is a given value
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 418e632d4a80..7a1065958ba9 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -8,7 +8,7 @@
 
 #ifdef __KERNEL__
 
-#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
 
 /* Physical address where kernel should be loaded. */
 #define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
@@ -16,10 +16,10 @@
                                 & ~(CONFIG_PHYSICAL_ALIGN - 1))
 
 /* Minimum kernel alignment, as a power of two */
-#ifdef CONFIG_x86_64
+#ifdef CONFIG_X86_64
 #define MIN_KERNEL_ALIGN_LG2    PMD_SHIFT
 #else
-#define MIN_KERNEL_ALIGN_LG2    (PAGE_SHIFT+1)
+#define MIN_KERNEL_ALIGN_LG2    (PAGE_SHIFT + THREAD_ORDER)
 #endif
 #define MIN_KERNEL_ALIGN        (_AC(1, UL) << MIN_KERNEL_ALIGN_LG2)
 
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index c45f415ce315..c993e9e0fed4 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -1,7 +1,6 @@
 #ifndef _ASM_X86_DESC_H
 #define _ASM_X86_DESC_H
 
-#ifndef __ASSEMBLY__
 #include <asm/desc_defs.h>
 #include <asm/ldt.h>
 #include <asm/mmu.h>
@@ -380,29 +379,4 @@ static inline void set_system_intr_gate_ist(int n, void *addr, unsigned ist)
         _set_gate(n, GATE_INTERRUPT, addr, 0x3, ist, __KERNEL_CS);
 }
 
-#else
-/*
- * GET_DESC_BASE reads the descriptor base of the specified segment.
- *
- * Args:
- *    idx - descriptor index
- *    gdt - GDT pointer
- *    base - 32bit register to which the base will be written
- *    lo_w - lo word of the "base" register
- *    lo_b - lo byte of the "base" register
- *    hi_b - hi byte of the low word of the "base" register
- *
- * Example:
- *    GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah)
- *    Will read the base address of GDT_ENTRY_ESPFIX_SS and put it into %eax.
- */
-#define GET_DESC_BASE(idx, gdt, base, lo_w, lo_b, hi_b) \
-        movb idx * 8 + 4(gdt), lo_b;                    \
-        movb idx * 8 + 7(gdt), hi_b;                    \
-        shll $16, base;                                 \
-        movw idx * 8 + 2(gdt), lo_w;
-
-
-#endif /* __ASSEMBLY__ */
-
 #endif /* _ASM_X86_DESC_H */
diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h
index b93405b228b4..1c3f9435f1c9 100644
--- a/arch/x86/include/asm/dma-mapping.h
+++ b/arch/x86/include/asm/dma-mapping.h
@@ -33,6 +33,8 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 #endif
 }
 
+#include <asm-generic/dma-mapping-common.h>
+
 /* Make sure we keep the same behaviour */
 static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
 {
@@ -53,177 +55,6 @@ 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);
 
-static inline dma_addr_t
-dma_map_single(struct device *hwdev, void *ptr, size_t size,
-               enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-        dma_addr_t addr;
-
-        BUG_ON(!valid_dma_direction(dir));
-        kmemcheck_mark_initialized(ptr, size);
-        addr = ops->map_page(hwdev, virt_to_page(ptr),
-                             (unsigned long)ptr & ~PAGE_MASK, size,
-                             dir, NULL);
-        debug_dma_map_page(hwdev, virt_to_page(ptr),
-                           (unsigned long)ptr & ~PAGE_MASK, size,
-                           dir, addr, true);
-        return addr;
-}
-
-static inline void
-dma_unmap_single(struct device *dev, dma_addr_t addr, size_t size,
-                 enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(dev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->unmap_page)
-                ops->unmap_page(dev, addr, size, dir, NULL);
-        debug_dma_unmap_page(dev, addr, size, dir, true);
-}
-
-static inline int
-dma_map_sg(struct device *hwdev, struct scatterlist *sg,
-           int nents, enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-        int ents;
-        struct scatterlist *s;
-        int i;
-
-        BUG_ON(!valid_dma_direction(dir));
-        for_each_sg(sg, s, nents, i)
-                kmemcheck_mark_initialized(sg_virt(s), s->length);
-        ents = ops->map_sg(hwdev, sg, nents, dir, NULL);
-        debug_dma_map_sg(hwdev, sg, nents, ents, dir);
-
-        return ents;
-}
-
-static inline void
-dma_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nents,
-             enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        debug_dma_unmap_sg(hwdev, sg, nents, dir);
-        if (ops->unmap_sg)
-                ops->unmap_sg(hwdev, sg, nents, dir, NULL);
-}
-
-static inline void
-dma_sync_single_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-                        size_t size, enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_single_for_cpu)
-                ops->sync_single_for_cpu(hwdev, dma_handle, size, dir);
-        debug_dma_sync_single_for_cpu(hwdev, dma_handle, size, dir);
-        flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_for_device(struct device *hwdev, dma_addr_t dma_handle,
-                           size_t size, enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_single_for_device)
-                ops->sync_single_for_device(hwdev, dma_handle, size, dir);
-        debug_dma_sync_single_for_device(hwdev, dma_handle, size, dir);
-        flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dma_handle,
-                              unsigned long offset, size_t size,
-                              enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_single_range_for_cpu)
-                ops->sync_single_range_for_cpu(hwdev, dma_handle, offset,
-                                               size, dir);
-        debug_dma_sync_single_range_for_cpu(hwdev, dma_handle,
-                                            offset, size, dir);
-        flush_write_buffers();
-}
-
-static inline void
-dma_sync_single_range_for_device(struct device *hwdev, dma_addr_t dma_handle,
-                                 unsigned long offset, size_t size,
-                                 enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_single_range_for_device)
-                ops->sync_single_range_for_device(hwdev, dma_handle,
-                                                  offset, size, dir);
-        debug_dma_sync_single_range_for_device(hwdev, dma_handle,
-                                               offset, size, dir);
-        flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-                    int nelems, enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_sg_for_cpu)
-                ops->sync_sg_for_cpu(hwdev, sg, nelems, dir);
-        debug_dma_sync_sg_for_cpu(hwdev, sg, nelems, dir);
-        flush_write_buffers();
-}
-
-static inline void
-dma_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
-                       int nelems, enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(hwdev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_sg_for_device)
-                ops->sync_sg_for_device(hwdev, sg, nelems, dir);
-        debug_dma_sync_sg_for_device(hwdev, sg, nelems, dir);
-
-        flush_write_buffers();
-}
-
-static inline dma_addr_t dma_map_page(struct device *dev, struct page *page,
-                                      size_t offset, size_t size,
-                                      enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(dev);
-        dma_addr_t addr;
-
-        BUG_ON(!valid_dma_direction(dir));
-        kmemcheck_mark_initialized(page_address(page) + offset, size);
-        addr = ops->map_page(dev, page, offset, size, dir, NULL);
-        debug_dma_map_page(dev, page, offset, size, dir, addr, false);
-
-        return addr;
-}
-
-static inline void dma_unmap_page(struct device *dev, dma_addr_t addr,
-                                  size_t size, enum dma_data_direction dir)
-{
-        struct dma_map_ops *ops = get_dma_ops(dev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->unmap_page)
-                ops->unmap_page(dev, addr, size, dir, NULL);
-        debug_dma_unmap_page(dev, addr, size, dir, false);
-}
-
 static inline void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
         enum dma_data_direction dir)
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index edc90f23e708..8406ed7f9926 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -33,7 +33,7 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 #define efi_call_virt6(f, a1, a2, a3, a4, a5, a6)       \
         efi_call_virt(f, a1, a2, a3, a4, a5, a6)
 
-#define efi_ioremap(addr, size)                 ioremap_cache(addr, size)
+#define efi_ioremap(addr, size, type)           ioremap_cache(addr, size)
 
 #else /* !CONFIG_X86_32 */
 
@@ -84,7 +84,8 @@ extern u64 efi_call6(void *fp, u64 arg1, u64 arg2, u64 arg3,
         efi_call6((void *)(efi.systab->runtime->f), (u64)(a1), (u64)(a2), \
                   (u64)(a3), (u64)(a4), (u64)(a5), (u64)(a6))
 
-extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size);
+extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
+                                 u32 type);
 
 #endif /* CONFIG_X86_32 */
 
diff --git a/arch/x86/include/asm/fixmap.h b/arch/x86/include/asm/fixmap.h
index 2d81af3974a0..7b2d71df39a6 100644
--- a/arch/x86/include/asm/fixmap.h
+++ b/arch/x86/include/asm/fixmap.h
@@ -111,12 +111,9 @@ enum fixed_addresses {
 #ifdef CONFIG_PARAVIRT
         FIX_PARAVIRT_BOOTMAP,
 #endif
-        FIX_TEXT_POKE0, /* reserve 2 pages for text_poke() */
-        FIX_TEXT_POKE1,
+        FIX_TEXT_POKE1, /* reserve 2 pages for text_poke() */
+        FIX_TEXT_POKE0, /* first page is last, because allocation is backward */
         __end_of_permanent_fixed_addresses,
-#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
-        FIX_OHCI1394_BASE,
-#endif
         /*
          * 256 temporary boot-time mappings, used by early_ioremap(),
          * before ioremap() is functional.
@@ -129,6 +126,9 @@ enum fixed_addresses {
         FIX_BTMAP_END = __end_of_permanent_fixed_addresses + 256 -
                         (__end_of_permanent_fixed_addresses & 255),
         FIX_BTMAP_BEGIN = FIX_BTMAP_END + NR_FIX_BTMAPS*FIX_BTMAPS_SLOTS - 1,
+#ifdef CONFIG_PROVIDE_OHCI1394_DMA_INIT
+        FIX_OHCI1394_BASE,
+#endif
 #ifdef CONFIG_X86_32
         FIX_WP_TEST,
 #endif
diff --git a/arch/x86/include/asm/ftrace.h b/arch/x86/include/asm/ftrace.h
index bd2c6511c887..db24c2278be0 100644
--- a/arch/x86/include/asm/ftrace.h
+++ b/arch/x86/include/asm/ftrace.h
@@ -28,13 +28,6 @@
 
 #endif
 
-/* FIXME: I don't want to stay hardcoded */
-#ifdef CONFIG_X86_64
-# define FTRACE_SYSCALL_MAX     296
-#else
-# define FTRACE_SYSCALL_MAX     333
-#endif
-
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR             ((long)(mcount))
 #define MCOUNT_INSN_SIZE        5 /* sizeof mcount call */
diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h
index daf866ed0612..330ee807f89e 100644
--- a/arch/x86/include/asm/io_apic.h
+++ b/arch/x86/include/asm/io_apic.h
@@ -161,6 +161,7 @@ extern int io_apic_set_pci_routing(struct device *dev, int irq,
                  struct io_apic_irq_attr *irq_attr);
 extern int (*ioapic_renumber_irq)(int ioapic, int irq);
 extern void ioapic_init_mappings(void);
+extern void ioapic_insert_resources(void);
 
 extern struct IO_APIC_route_entry **alloc_ioapic_entries(void);
 extern void free_ioapic_entries(struct IO_APIC_route_entry **ioapic_entries);
@@ -180,6 +181,7 @@ extern void ioapic_write_entry(int apic, int pin,
 #define io_apic_assign_pci_irqs 0
 static const int timer_through_8259 = 0;
 static inline void ioapic_init_mappings(void)   { }
+static inline void ioapic_insert_resources(void) { }
 
 static inline void probe_nr_irqs_gsi(void)      { }
 #endif
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index af326a2975b5..fd6d21bbee6c 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -6,6 +6,7 @@ extern void no_iommu_init(void);
 extern struct dma_map_ops nommu_dma_ops;
 extern int force_iommu, no_iommu;
 extern int iommu_detected;
+extern int iommu_pass_through;
 
 /* 10 seconds */
 #define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 2bdab21f0898..c6ccbe7e81ad 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -12,9 +12,15 @@ static inline unsigned long native_save_fl(void)
 {
         unsigned long flags;
 
+        /*
+         * Note: this needs to be "=r" not "=rm", because we have the
+         * stack offset from what gcc expects at the time the "pop" is
+         * executed, and so a memory reference with respect to the stack
+         * would end up using the wrong address.
+         */
         asm volatile("# __raw_save_flags\n\t"
                      "pushf ; pop %0"
-                     : "=g" (flags)
+                     : "=r" (flags)
                      : /* no input */
                      : "memory");
 
diff --git a/arch/x86/include/asm/lguest.h b/arch/x86/include/asm/lguest.h
index 313389cd50d2..5136dad57cbb 100644
--- a/arch/x86/include/asm/lguest.h
+++ b/arch/x86/include/asm/lguest.h
@@ -17,8 +17,7 @@
 /* Pages for switcher itself, then two pages per cpu */
 #define TOTAL_SWITCHER_PAGES (SHARED_SWITCHER_PAGES + 2 * nr_cpu_ids)
 
-/* We map at -4M (-2M when PAE is activated) for ease of mapping
- * into the guest (one PTE page). */
+/* We map at -4M (-2M for PAE) for ease of mapping (one PTE page). */
 #ifdef CONFIG_X86_PAE
 #define SWITCHER_ADDR 0xFFE00000
 #else
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index d31c4a684078..ba0eed8aa1a6 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -30,27 +30,27 @@
 #include <asm/hw_irq.h>
 #include <asm/kvm_para.h>
 
-/*G:031 But first, how does our Guest contact the Host to ask for privileged
+/*G:030
+ * But first, how does our Guest contact the Host to ask for privileged
  * operations?  There are two ways: the direct way is to make a "hypercall",
  * to make requests of the Host Itself.
  *
- * We use the KVM hypercall mechanism. Seventeen hypercalls are
- * available: the hypercall number is put in the %eax register, and the
- * arguments (when required) are placed in %ebx, %ecx, %edx and %esi.
- * If a return value makes sense, it's returned in %eax.
+ * We use the KVM hypercall mechanism, though completely different hypercall
+ * numbers. Seventeen hypercalls are available: the hypercall number is put in
+ * the %eax register, and the arguments (when required) are placed in %ebx,
+ * %ecx, %edx and %esi.  If a return value makes sense, it's returned in %eax.
  *
  * Grossly invalid calls result in Sudden Death at the hands of the vengeful
  * Host, rather than returning failure.  This reflects Winston Churchill's
- * definition of a gentleman: "someone who is only rude intentionally". */
-/*:*/
+ * definition of a gentleman: "someone who is only rude intentionally".
+:*/
 
 /* Can't use our min() macro here: needs to be a constant */
 #define LGUEST_IRQS (NR_IRQS < 32 ? NR_IRQS: 32)
 
 #define LHCALL_RING_SIZE 64
 struct hcall_args {
-        /* These map directly onto eax, ebx, ecx, edx and esi
-         * in struct lguest_regs */
+        /* These map directly onto eax/ebx/ecx/edx/esi in struct lguest_regs */
         unsigned long arg0, arg1, arg2, arg3, arg4;
 };
 
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 540a466e50f5..5cdd8d100ec9 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -102,15 +102,39 @@ struct mce_log {
 
 #ifdef __KERNEL__
 
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <asm/atomic.h>
+
 extern int mce_disabled;
+extern int mce_p5_enabled;
 
-#include <asm/atomic.h>
-#include <linux/percpu.h>
+#ifdef CONFIG_X86_MCE
+void mcheck_init(struct cpuinfo_x86 *c);
+#else
+static inline void mcheck_init(struct cpuinfo_x86 *c) {}
+#endif
+
+#ifdef CONFIG_X86_OLD_MCE
+extern int nr_mce_banks;
+void amd_mcheck_init(struct cpuinfo_x86 *c);
+void intel_p4_mcheck_init(struct cpuinfo_x86 *c);
+void intel_p6_mcheck_init(struct cpuinfo_x86 *c);
+#endif
+
+#ifdef CONFIG_X86_ANCIENT_MCE
+void intel_p5_mcheck_init(struct cpuinfo_x86 *c);
+void winchip_mcheck_init(struct cpuinfo_x86 *c);
+static inline void enable_p5_mce(void) { mce_p5_enabled = 1; }
+#else
+static inline void intel_p5_mcheck_init(struct cpuinfo_x86 *c) {}
+static inline void winchip_mcheck_init(struct cpuinfo_x86 *c) {}
+static inline void enable_p5_mce(void) {}
+#endif
 
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
 DECLARE_PER_CPU(struct sys_device, mce_dev);
-extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
 
 /*
  * To support more than 128 would need to escape the predefined
@@ -145,12 +169,8 @@ int mce_available(struct cpuinfo_x86 *c);
 DECLARE_PER_CPU(unsigned, mce_exception_count);
 DECLARE_PER_CPU(unsigned, mce_poll_count);
 
-void mce_log_therm_throt_event(__u64 status);
-
 extern atomic_t mce_entry;
 
-void do_machine_check(struct pt_regs *, long);
-
 typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS);
 DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
 
@@ -167,13 +187,32 @@ void mce_notify_process(void);
 DECLARE_PER_CPU(struct mce, injectm);
 extern struct file_operations mce_chrdev_ops;
 
-#ifdef CONFIG_X86_MCE
-void mcheck_init(struct cpuinfo_x86 *c);
-#else
-#define mcheck_init(c) do { } while (0)
-#endif
+/*
+ * Exception handler
+ */
+
+/* Call the installed machine check handler for this CPU setup. */
+extern void (*machine_check_vector)(struct pt_regs *, long error_code);
+void do_machine_check(struct pt_regs *, long);
+
+/*
+ * Threshold handler
+ */
 
 extern void (*mce_threshold_vector)(void);
+extern void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
+
+/*
+ * Thermal handler
+ */
+
+void intel_init_thermal(struct cpuinfo_x86 *c);
+
+#ifdef CONFIG_X86_NEW_MCE
+void mce_log_therm_throt_event(__u64 status);
+#else
+static inline void mce_log_therm_throt_event(__u64 status) {}
+#endif
 
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_MCE_H */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 1692fb5050e3..6be7fc254b59 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -246,10 +246,6 @@
 #define MSR_IA32_MISC_ENABLE_TURBO_DISABLE      (1ULL << 38)
 #define MSR_IA32_MISC_ENABLE_IP_PREF_DISABLE    (1ULL << 39)
 
-/* Intel Model 6 */
-#define MSR_P6_EVNTSEL0                 0x00000186
-#define MSR_P6_EVNTSEL1                 0x00000187
-
 /* P4/Xeon+ specific */
 #define MSR_IA32_MCG_EAX                0x00000180
 #define MSR_IA32_MCG_EBX                0x00000181
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 22603764e7db..48ad9d29484a 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -3,13 +3,10 @@
 
 #include <asm/msr-index.h>
 
-#ifndef __ASSEMBLY__
-# include <linux/types.h>
-#endif
-
 #ifdef __KERNEL__
 #ifndef __ASSEMBLY__
 
+#include <linux/types.h>
 #include <asm/asm.h>
 #include <asm/errno.h>
 #include <asm/cpumask.h>
@@ -264,6 +261,4 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
 #endif  /* CONFIG_SMP */
 #endif /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
-
-
 #endif /* _ASM_X86_MSR_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index c97264409934..c86e5ed4af51 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -72,7 +72,6 @@ void lapic_watchdog_stop(void);
 int lapic_watchdog_init(unsigned nmi_hz);
 int lapic_wd_event(unsigned nmi_hz);
 unsigned lapic_adjust_nmi_hz(unsigned hz);
-int lapic_watchdog_ok(void);
 void disable_lapic_nmi_watchdog(void);
 void enable_lapic_nmi_watchdog(void);
 void stop_nmi(void);
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 8d382d3abf38..7639dbf5d223 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -41,7 +41,7 @@
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
 #define __PHYSICAL_MASK_SHIFT   46
-#define __VIRTUAL_MASK_SHIFT    48
+#define __VIRTUAL_MASK_SHIFT    47
 
 /*
  * Kernel image size is limited to 512 MB (see level2_kernel_pgt in
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index b51a1e8b0baf..1ff685ca221c 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -91,7 +91,7 @@ extern void pci_iommu_alloc(void);
 
 #define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
 
-#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG)
+#if defined(CONFIG_X86_64) || defined(CONFIG_DMAR) || defined(CONFIG_DMA_API_DEBUG)
 
 #define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
                 dma_addr_t ADDR_NAME;
@@ -130,6 +130,7 @@ extern void pci_iommu_alloc(void);
 
 /* generic pci stuff */
 #include <asm-generic/pci.h>
+#define PCIBIOS_MAX_MEM_32 0xffffffff
 
 #ifdef CONFIG_NUMA
 /* Returns the node based on pci bus */
diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h
index e60fd3e14bdf..b399988eee3a 100644
--- a/arch/x86/include/asm/pci_x86.h
+++ b/arch/x86/include/asm/pci_x86.h
@@ -121,6 +121,9 @@ extern int __init pcibios_init(void);
 extern int __init pci_mmcfg_arch_init(void);
 extern void __init pci_mmcfg_arch_free(void);
 
+extern struct acpi_mcfg_allocation *pci_mmcfg_config;
+extern int pci_mmcfg_config_num;
+
 /*
  * AMD Fam10h CPUs are buggy, and cannot access MMIO config space
  * on their northbrige except through the * %eax register. As such, you MUST
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 02ecb30982a3..103f1ddb0d85 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -42,6 +42,7 @@
 
 #else /* ...!ASSEMBLY */
 
+#include <linux/kernel.h>
 #include <linux/stringify.h>
 
 #ifdef CONFIG_SMP
@@ -155,6 +156,15 @@ do {							\
 /* We can use this directly for local CPU (faster). */
 DECLARE_PER_CPU(unsigned long, this_cpu_off);
 
+#ifdef CONFIG_NEED_MULTIPLE_NODES
+void *pcpu_lpage_remapped(void *kaddr);
+#else
+static inline void *pcpu_lpage_remapped(void *kaddr)
+{
+        return NULL;
+}
+#endif
+
 #endif /* !__ASSEMBLY__ */
 
 #ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/perf_counter.h b/arch/x86/include/asm/perf_counter.h
index 876ed97147b3..fa64e401589d 100644
--- a/arch/x86/include/asm/perf_counter.h
+++ b/arch/x86/include/asm/perf_counter.h
@@ -84,14 +84,12 @@ union cpuid10_edx {
 #define MSR_ARCH_PERFMON_FIXED_CTR2                     0x30b
 #define X86_PMC_IDX_FIXED_BUS_CYCLES                    (X86_PMC_IDX_FIXED + 2)
 
-extern void set_perf_counter_pending(void);
-
-#define clear_perf_counter_pending()    do { } while (0)
-#define test_perf_counter_pending()     (0)
-
 #ifdef CONFIG_PERF_COUNTERS
 extern void init_hw_perf_counters(void);
 extern void perf_counters_lapic_init(void);
+
+#define PERF_COUNTER_INDEX_OFFSET                       0
+
 #else
 static inline void init_hw_perf_counters(void)          { }
 static inline void perf_counters_lapic_init(void)       { }
diff --git a/arch/x86/include/asm/pgalloc.h b/arch/x86/include/asm/pgalloc.h
index dd14c54ac718..0e8c2a0fd922 100644
--- a/arch/x86/include/asm/pgalloc.h
+++ b/arch/x86/include/asm/pgalloc.h
@@ -46,7 +46,13 @@ static inline void pte_free(struct mm_struct *mm, struct page *pte)
         __free_page(pte);
 }
 
-extern void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
+extern void ___pte_free_tlb(struct mmu_gather *tlb, struct page *pte);
+
+static inline void __pte_free_tlb(struct mmu_gather *tlb, struct page *pte,
+                                  unsigned long address)
+{
+        ___pte_free_tlb(tlb, pte);
+}
 
 static inline void pmd_populate_kernel(struct mm_struct *mm,
                                        pmd_t *pmd, pte_t *pte)
@@ -78,7 +84,13 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
         free_page((unsigned long)pmd);
 }
 
-extern void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
+extern void ___pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd);
+
+static inline void __pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
+                                  unsigned long adddress)
+{
+        ___pmd_free_tlb(tlb, pmd);
+}
 
 #ifdef CONFIG_X86_PAE
 extern void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd);
@@ -108,7 +120,14 @@ static inline void pud_free(struct mm_struct *mm, pud_t *pud)
         free_page((unsigned long)pud);
 }
 
-extern void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
+extern void ___pud_free_tlb(struct mmu_gather *tlb, pud_t *pud);
+
+static inline void __pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
+                                  unsigned long address)
+{
+        ___pud_free_tlb(tlb, pud);
+}
+
 #endif  /* PAGETABLE_LEVELS > 3 */
 #endif  /* PAGETABLE_LEVELS > 2 */
 
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 3cc06e3fceb8..16748077559a 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -2,6 +2,7 @@
 #define _ASM_X86_PGTABLE_H
 
 #include <asm/page.h>
+#include <asm/e820.h>
 
 #include <asm/pgtable_types.h>
 
@@ -269,10 +270,17 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 
 #define canon_pgprot(p) __pgprot(massage_pgprot(p))
 
-static inline int is_new_memtype_allowed(unsigned long flags,
-                                                unsigned long new_flags)
+static inline int is_new_memtype_allowed(u64 paddr, unsigned long size,
+                                         unsigned long flags,
+                                         unsigned long new_flags)
 {
         /*
+         * PAT type is always WB for ISA. So no need to check.
+         */
+        if (is_ISA_range(paddr, paddr + size - 1))
+                return 1;
+
+        /*
          * Certain new memtypes are not allowed with certain
          * requested memtype:
          * - request is uncached, return cannot be write-back
diff --git a/arch/x86/include/asm/pgtable_32.h b/arch/x86/include/asm/pgtable_32.h
index 31bd120cf2a2..01fd9461d323 100644
--- a/arch/x86/include/asm/pgtable_32.h
+++ b/arch/x86/include/asm/pgtable_32.h
@@ -49,13 +49,17 @@ extern void set_pmd_pfn(unsigned long, unsigned long, pgprot_t);
 #endif
 
 #if defined(CONFIG_HIGHPTE)
+#define __KM_PTE                        \
+        (in_nmi() ? KM_NMI_PTE :        \
+         in_irq() ? KM_IRQ_PTE :        \
+         KM_PTE0)
 #define pte_offset_map(dir, address)                                    \
-        ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE0) +          \
+        ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), __KM_PTE) +         \
          pte_index((address)))
 #define pte_offset_map_nested(dir, address)                             \
         ((pte_t *)kmap_atomic_pte(pmd_page(*(dir)), KM_PTE1) +          \
          pte_index((address)))
-#define pte_unmap(pte) kunmap_atomic((pte), KM_PTE0)
+#define pte_unmap(pte) kunmap_atomic((pte), __KM_PTE)
 #define pte_unmap_nested(pte) kunmap_atomic((pte), KM_PTE1)
 #else
 #define pte_offset_map(dir, address)                                    \
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index abde308fdb0f..c57a30117149 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -165,10 +165,7 @@ extern void cleanup_highmap(void);
 
 /* fs/proc/kcore.c */
 #define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK)
-#define kc_offset_to_vaddr(o)                           \
-        (((o) & (1UL << (__VIRTUAL_MASK_SHIFT - 1)))    \
-         ? ((o) | ~__VIRTUAL_MASK)                      \
-         : (o))
+#define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK)
 
 #define __HAVE_ARCH_PTE_SAME
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/proto.h b/arch/x86/include/asm/proto.h
index 49fb3ecf3bb3..621f56d73121 100644
--- a/arch/x86/include/asm/proto.h
+++ b/arch/x86/include/asm/proto.h
@@ -22,7 +22,14 @@ extern int reboot_force;
 
 long do_arch_prctl(struct task_struct *task, int code, unsigned long addr);
 
-#define round_up(x, y) (((x) + (y) - 1) & ~((y) - 1))
-#define round_down(x, y) ((x) & ~((y) - 1))
+/*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ */
+#define __round_mask(x,y) ((__typeof__(x))((y)-1))
+#define round_up(x,y) ((((x)-1) | __round_mask(x,y))+1)
+#define round_down(x,y) ((x) & ~__round_mask(x,y))
 
 #endif /* _ASM_X86_PROTO_H */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index b7e5db876399..4e77853321db 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -302,4 +302,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 #define _raw_read_relax(lock)   cpu_relax()
 #define _raw_write_relax(lock)  cpu_relax()
 
+/* The {read|write|spin}_lock() on x86 are full memory barriers. */
+static inline void smp_mb__after_lock(void) { }
+#define ARCH_HAS_SMP_MB_AFTER_LOCK
+
 #endif /* _ASM_X86_SPINLOCK_H */
diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h
index f517944b2b17..cf86a5e73815 100644
--- a/arch/x86/include/asm/stacktrace.h
+++ b/arch/x86/include/asm/stacktrace.h
@@ -3,6 +3,8 @@
 
 extern int kstack_depth_to_print;
 
+int x86_is_stack_id(int id, char *name);
+
 /* Generic stack tracer with callbacks */
 
 struct stacktrace_ops {
diff --git a/arch/x86/include/asm/therm_throt.h b/arch/x86/include/asm/therm_throt.h
deleted file mode 100644
index c62349ee7860..000000000000
--- a/arch/x86/include/asm/therm_throt.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _ASM_X86_THERM_THROT_H
-#define _ASM_X86_THERM_THROT_H
-
-#include <asm/atomic.h>
-
-extern atomic_t therm_throt_en;
-int therm_throt_process(int curr);
-
-#endif /* _ASM_X86_THERM_THROT_H */
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index b0783520988b..6f7786aea4fc 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -49,7 +49,7 @@ struct thread_info {
         .exec_domain    = &default_exec_domain, \
         .flags          = 0,                    \
         .cpu            = 0,                    \
-        .preempt_count  = 1,                    \
+        .preempt_count  = INIT_PREEMPT_COUNT,   \
         .addr_limit     = KERNEL_DS,            \
         .restart_block = {                      \
                 .fn = do_no_restart_syscall,    \
@@ -95,7 +95,7 @@ struct thread_info {
 #define TIF_DEBUGCTLMSR         25      /* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR         26      /* uses thread_struct.ds_area_msr */
 #define TIF_LAZY_MMU_UPDATES    27      /* task is updating the mmu lazily */
-#define TIF_SYSCALL_FTRACE      28      /* for ftrace syscall instrumentation */
+#define TIF_SYSCALL_TRACEPOINT  28      /* syscall tracepoint instrumentation */
 
 #define _TIF_SYSCALL_TRACE      (1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME      (1 << TIF_NOTIFY_RESUME)
@@ -118,17 +118,17 @@ struct thread_info {
 #define _TIF_DEBUGCTLMSR        (1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR        (1 << TIF_DS_AREA_MSR)
 #define _TIF_LAZY_MMU_UPDATES   (1 << TIF_LAZY_MMU_UPDATES)
-#define _TIF_SYSCALL_FTRACE     (1 << TIF_SYSCALL_FTRACE)
+#define _TIF_SYSCALL_TRACEPOINT (1 << TIF_SYSCALL_TRACEPOINT)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY \
-        (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE |  \
-         _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
+        (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |   \
+         _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
 
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT  \
         (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP |    \
-         _TIF_SYSCALL_FTRACE)
+         _TIF_SYSCALL_TRACEPOINT)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK                                                  \
@@ -137,7 +137,8 @@ struct thread_info {
            _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
 
 /* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE)
+#define _TIF_ALLWORK_MASK                                               \
+        ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT)
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK                                             \
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index bd37ed444a21..20ca9c4d4686 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -45,12 +45,16 @@ extern int no_timer_check;
  */
 
 DECLARE_PER_CPU(unsigned long, cyc2ns);
+DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 #define CYC2NS_SCALE_FACTOR 10 /* 2^10, carefully chosen */
 
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
-        return cyc * per_cpu(cyc2ns, smp_processor_id()) >> CYC2NS_SCALE_FACTOR;
+        int cpu = smp_processor_id();
+        unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
+        ns += cyc * per_cpu(cyc2ns, cpu) >> CYC2NS_SCALE_FACTOR;
+        return ns;
 }
 
 static inline unsigned long long cycles_2_ns(unsigned long long cyc)
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index b685ece89d5c..d2c6c930b491 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -25,7 +25,7 @@
 #define MAKE_MM_SEG(s)  ((mm_segment_t) { (s) })
 
 #define KERNEL_DS       MAKE_MM_SEG(-1UL)
-#define USER_DS         MAKE_MM_SEG(PAGE_OFFSET)
+#define USER_DS         MAKE_MM_SEG(TASK_SIZE_MAX)
 
 #define get_ds()        (KERNEL_DS)
 #define get_fs()        (current_thread_info()->addr_limit)
@@ -212,9 +212,9 @@ extern int __get_user_bad(void);
                      : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx")
 #else
 #define __put_user_asm_u64(x, ptr, retval, errret) \
-        __put_user_asm(x, ptr, retval, "q", "", "Zr", errret)
+        __put_user_asm(x, ptr, retval, "q", "", "er", errret)
 #define __put_user_asm_ex_u64(x, addr)  \
-        __put_user_asm_ex(x, addr, "q", "", "Zr")
+        __put_user_asm_ex(x, addr, "q", "", "er")
 #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu)
 #endif
 
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 8cc687326eb8..db24b215fc50 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -88,11 +88,11 @@ int __copy_to_user(void __user *dst, const void *src, unsigned size)
                               ret, "l", "k", "ir", 4);
                 return ret;
         case 8:__put_user_asm(*(u64 *)src, (u64 __user *)dst,
-                              ret, "q", "", "ir", 8);
+                              ret, "q", "", "er", 8);
                 return ret;
         case 10:
                 __put_user_asm(*(u64 *)src, (u64 __user *)dst,
-                               ret, "q", "", "ir", 10);
+                               ret, "q", "", "er", 10);
                 if (unlikely(ret))
                         return ret;
                 asm("":::"memory");
@@ -101,12 +101,12 @@ int __copy_to_user(void __user *dst, const void *src, unsigned size)
                 return ret;
         case 16:
                 __put_user_asm(*(u64 *)src, (u64 __user *)dst,
-                               ret, "q", "", "ir", 16);
+                               ret, "q", "", "er", 16);
                 if (unlikely(ret))
                         return ret;
                 asm("":::"memory");
                 __put_user_asm(1[(u64 *)src], 1 + (u64 __user *)dst,
-                               ret, "q", "", "ir", 8);
+                               ret, "q", "", "er", 8);
                 return ret;
         default:
                 return copy_user_generic((__force void *)dst, src, size);
@@ -157,7 +157,7 @@ int __copy_in_user(void __user *dst, const void __user *src, unsigned size)
                                ret, "q", "", "=r", 8);
                 if (likely(!ret))
                         __put_user_asm(tmp, (u64 __user *)dst,
-                                       ret, "q", "", "ir", 8);
+                                       ret, "q", "", "er", 8);
                 return ret;
         }
         default:
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index 732a30706153..8deaada61bc8 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -345,6 +345,8 @@
 
 #ifdef __KERNEL__
 
+#define NR_syscalls 337
+
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index 900e1617e672..b9f3c60de5f7 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -688,6 +688,12 @@ __SYSCALL(__NR_perf_counter_open, sys_perf_counter_open)
 #endif  /* __NO_STUBS */
 
 #ifdef __KERNEL__
+
+#ifndef COMPILE_OFFSETS
+#include <asm/asm-offsets.h>
+#define NR_syscalls (__NR_syscall_max + 1)
+#endif
+
 /*
  * "Conditional" syscalls
  *
diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index bddd44f2f0ab..80e2984f521c 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -133,7 +133,7 @@ struct bau_msg_payload {
  * see table 4.2.3.0.1 in broacast_assist spec.
  */
 struct bau_msg_header {
-        unsigned int dest_subnodeid:6;  /* must be zero */
+        unsigned int dest_subnodeid:6;  /* must be 0x10, for the LB */
         /* bits 5:0 */
         unsigned int base_dest_nodeid:15; /* nasid>>1 (pnode) of */
         /* bits 20:6 */                   /* first bit in node_map */
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 341070f7ad5c..77a68505419a 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -175,7 +175,7 @@ DECLARE_PER_CPU(struct uv_hub_info_s, __uv_hub_info);
 #define UV_GLOBAL_MMR32_PNODE_BITS(p)   ((p) << (UV_GLOBAL_MMR32_PNODE_SHIFT))
 
 #define UV_GLOBAL_MMR64_PNODE_BITS(p)                                   \
-        ((unsigned long)(UV_PNODE_TO_GNODE(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
+        (((unsigned long)(p)) << UV_GLOBAL_MMR64_PNODE_SHIFT)
 
 #define UV_APIC_PNODE_SHIFT     6
 
@@ -327,6 +327,7 @@ struct uv_blade_info {
         unsigned short  nr_possible_cpus;
         unsigned short  nr_online_cpus;
         unsigned short  pnode;
+        short           memory_nid;
 };
 extern struct uv_blade_info *uv_blade_info;
 extern short *uv_node_to_blade;
@@ -363,6 +364,12 @@ static inline int uv_blade_to_pnode(int bid)
         return uv_blade_info[bid].pnode;
 }
 
+/* Nid of memory node on blade. -1 if no blade-local memory */
+static inline int uv_blade_to_memory_nid(int bid)
+{
+        return uv_blade_info[bid].memory_nid;
+}
+
 /* Determine the number of possible cpus on a blade */
 static inline int uv_blade_nr_possible_cpus(int bid)
 {