68 files changed, 672 insertions, 247 deletions

diff --git a/include/acpi/acpiosxf.h b/include/acpi/acpiosxf.h
index 3e798593b17b..ab0b85cf21f3 100644
--- a/include/acpi/acpiosxf.h
+++ b/include/acpi/acpiosxf.h
@@ -242,6 +242,10 @@ acpi_os_derive_pci_id(acpi_handle rhandle,
 acpi_status acpi_os_validate_interface(char *interface);
 acpi_status acpi_osi_invalidate(char* interface);
 
+acpi_status
+acpi_os_validate_address(u8 space_id, acpi_physical_address address,
+                         acpi_size length, char *name);
+
 u64 acpi_os_get_timer(void);
 
 acpi_status acpi_os_signal(u32 function, void *info);
diff --git a/include/acpi/processor.h b/include/acpi/processor.h
index baf1e0a9a7ee..740ac3ad8fd0 100644
--- a/include/acpi/processor.h
+++ b/include/acpi/processor.h
@@ -174,7 +174,7 @@ struct acpi_processor_throttling {
         cpumask_var_t shared_cpu_map;
         int (*acpi_processor_get_throttling) (struct acpi_processor * pr);
         int (*acpi_processor_set_throttling) (struct acpi_processor * pr,
-                                              int state);
+                                              int state, bool force);
 
         u32 address;
         u8 duty_offset;
@@ -321,7 +321,8 @@ static inline int acpi_processor_ppc_has_changed(struct acpi_processor *pr)
 /* in processor_throttling.c */
 int acpi_processor_tstate_has_changed(struct acpi_processor *pr);
 int acpi_processor_get_throttling_info(struct acpi_processor *pr);
-extern int acpi_processor_set_throttling(struct acpi_processor *pr, int state);
+extern int acpi_processor_set_throttling(struct acpi_processor *pr,
+                                         int state, bool force);
 extern const struct file_operations acpi_processor_throttling_fops;
 extern void acpi_processor_throttling_init(void);
 /* in processor_idle.c */
diff --git a/include/asm-generic/4level-fixup.h b/include/asm-generic/4level-fixup.h
index 9d40e879f99e..77ff547730af 100644
--- a/include/asm-generic/4level-fixup.h
+++ b/include/asm-generic/4level-fixup.h
@@ -27,9 +27,9 @@
 #define pud_page_vaddr(pud)             pgd_page_vaddr(pud)
 
 #undef pud_free_tlb
-#define pud_free_tlb(tlb, x)            do { } while (0)
+#define pud_free_tlb(tlb, x, addr)      do { } while (0)
 #define pud_free(mm, x)                 do { } while (0)
-#define __pud_free_tlb(tlb, x)          do { } while (0)
+#define __pud_free_tlb(tlb, x, addr)    do { } while (0)
 
 #undef  pud_addr_end
 #define pud_addr_end(addr, end)         (end)
diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h
index a7cdc48e8b78..725612b793ce 100644
--- a/include/asm-generic/pgtable-nopmd.h
+++ b/include/asm-generic/pgtable-nopmd.h
@@ -59,7 +59,7 @@ static inline pmd_t * pmd_offset(pud_t * pud, unsigned long address)
 static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd)
 {
 }
-#define __pmd_free_tlb(tlb, x)                  do { } while (0)
+#define __pmd_free_tlb(tlb, x, a)               do { } while (0)
 
 #undef  pmd_addr_end
 #define pmd_addr_end(addr, end)                 (end)
diff --git a/include/asm-generic/pgtable-nopud.h b/include/asm-generic/pgtable-nopud.h
index 87cf449a6df3..810431d8351b 100644
--- a/include/asm-generic/pgtable-nopud.h
+++ b/include/asm-generic/pgtable-nopud.h
@@ -52,7 +52,7 @@ static inline pud_t * pud_offset(pgd_t * pgd, unsigned long address)
  */
 #define pud_alloc_one(mm, address)              NULL
 #define pud_free(mm, x)                         do { } while (0)
-#define __pud_free_tlb(tlb, x)                  do { } while (0)
+#define __pud_free_tlb(tlb, x, a)               do { } while (0)
 
 #undef  pud_addr_end
 #define pud_addr_end(addr, end)                 (end)
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index f490e43a90b9..e43f9766259f 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -123,24 +123,24 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
                 __tlb_remove_tlb_entry(tlb, ptep, address);     \
         } while (0)
 
-#define pte_free_tlb(tlb, ptep)                                 \
+#define pte_free_tlb(tlb, ptep, address)                        \
         do {                                                    \
                 tlb->need_flush = 1;                            \
-                __pte_free_tlb(tlb, ptep);                      \
+                __pte_free_tlb(tlb, ptep, address);             \
         } while (0)
 
 #ifndef __ARCH_HAS_4LEVEL_HACK
-#define pud_free_tlb(tlb, pudp)                                 \
+#define pud_free_tlb(tlb, pudp, address)                        \
         do {                                                    \
                 tlb->need_flush = 1;                            \
-                __pud_free_tlb(tlb, pudp);                      \
+                __pud_free_tlb(tlb, pudp, address);             \
         } while (0)
 #endif
 
-#define pmd_free_tlb(tlb, pmdp)                                 \
+#define pmd_free_tlb(tlb, pmdp, address)                        \
         do {                                                    \
                 tlb->need_flush = 1;                            \
-                __pmd_free_tlb(tlb, pmdp);                      \
+                __pmd_free_tlb(tlb, pmdp, address);             \
         } while (0)
 
 #define tlb_migrate_finish(mm) do {} while (0)
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index 7174818c2c13..853508499d20 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -257,9 +257,12 @@
         {0x1002, 0x940F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_R600|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x94A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x94A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+        {0x1002, 0x94A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x94B1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x94B3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
+        {0x1002, 0x94B4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x94B5, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_NEW_MEMMAP}, \
+        {0x1002, 0x94B9, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV740|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9440, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9441, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9442, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV770|RADEON_NEW_MEMMAP}, \
@@ -288,6 +291,7 @@
         {0x1002, 0x948F, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9490, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9491, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+        {0x1002, 0x9495, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9498, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x949C, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x949E, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV730|RADEON_NEW_MEMMAP}, \
@@ -325,6 +329,7 @@
         {0x1002, 0x9552, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9553, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9555, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
+        {0x1002, 0x9557, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV710|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9580, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9581, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
         {0x1002, 0x9583, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RV630|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP}, \
@@ -365,6 +370,11 @@
         {0x1002, 0x9614, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
         {0x1002, 0x9615, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
         {0x1002, 0x9616, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+        {0x1002, 0x9710, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+        {0x1002, 0x9711, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+        {0x1002, 0x9712, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+        {0x1002, 0x9713, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+        {0x1002, 0x9714, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
         {0, 0, 0}
 
 #define r128_PCI_IDS \
diff --git a/include/drm/radeon_drm.h b/include/drm/radeon_drm.h
index 41862e9a4c20..2ba61e18fc8b 100644
--- a/include/drm/radeon_drm.h
+++ b/include/drm/radeon_drm.h
@@ -506,6 +506,9 @@ typedef struct {
 #define DRM_RADEON_GEM_WAIT_IDLE        0x24
 #define DRM_RADEON_CS                   0x26
 #define DRM_RADEON_INFO                 0x27
+#define DRM_RADEON_GEM_SET_TILING       0x28
+#define DRM_RADEON_GEM_GET_TILING       0x29
+#define DRM_RADEON_GEM_BUSY             0x2a
 
 #define DRM_IOCTL_RADEON_CP_INIT    DRM_IOW( DRM_COMMAND_BASE + DRM_RADEON_CP_INIT, drm_radeon_init_t)
 #define DRM_IOCTL_RADEON_CP_START   DRM_IO(  DRM_COMMAND_BASE + DRM_RADEON_CP_START)
@@ -544,7 +547,9 @@ typedef struct {
 #define DRM_IOCTL_RADEON_GEM_WAIT_IDLE  DRM_IOW(DRM_COMMAND_BASE + DRM_RADEON_GEM_WAIT_IDLE, struct drm_radeon_gem_wait_idle)
 #define DRM_IOCTL_RADEON_CS             DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_CS, struct drm_radeon_cs)
 #define DRM_IOCTL_RADEON_INFO           DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_INFO, struct drm_radeon_info)
-
+#define DRM_IOCTL_RADEON_SET_TILING     DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_SET_TILING, struct drm_radeon_gem_set_tiling)
+#define DRM_IOCTL_RADEON_GET_TILING     DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_GET_TILING, struct drm_radeon_gem_get_tiling)
+#define DRM_IOCTL_RADEON_GEM_BUSY       DRM_IOWR(DRM_COMMAND_BASE + DRM_RADEON_GEM_BUSY, struct drm_radeon_gem_busy)
 
 typedef struct drm_radeon_init {
         enum {
@@ -704,6 +709,7 @@ typedef struct drm_radeon_indirect {
 #define RADEON_PARAM_FB_LOCATION           14   /* FB location */
 #define RADEON_PARAM_NUM_GB_PIPES          15   /* num GB pipes */
 #define RADEON_PARAM_DEVICE_ID             16
+#define RADEON_PARAM_NUM_Z_PIPES           17   /* num Z pipes */
 
 typedef struct drm_radeon_getparam {
         int param;
@@ -796,6 +802,24 @@ struct drm_radeon_gem_create {
         uint32_t        flags;
 };
 
+#define RADEON_TILING_MACRO 0x1
+#define RADEON_TILING_MICRO 0x2
+#define RADEON_TILING_SWAP  0x4
+#define RADEON_TILING_SURFACE  0x8 /* this object requires a surface
+                                    * when mapped - i.e. front buffer */
+
+struct drm_radeon_gem_set_tiling {
+        uint32_t        handle;
+        uint32_t        tiling_flags;
+        uint32_t        pitch;
+};
+
+struct drm_radeon_gem_get_tiling {
+        uint32_t        handle;
+        uint32_t        tiling_flags;
+        uint32_t        pitch;
+};
+
 struct drm_radeon_gem_mmap {
         uint32_t        handle;
         uint32_t        pad;
@@ -817,7 +841,7 @@ struct drm_radeon_gem_wait_idle {
 
 struct drm_radeon_gem_busy {
         uint32_t        handle;
-        uint32_t        busy;
+        uint32_t        domain;
 };
 
 struct drm_radeon_gem_pread {
@@ -874,6 +898,7 @@ struct drm_radeon_cs {
 
 #define RADEON_INFO_DEVICE_ID           0x00
 #define RADEON_INFO_NUM_GB_PIPES        0x01
+#define RADEON_INFO_NUM_Z_PIPES         0x02
 
 struct drm_radeon_info {
         uint32_t                request;
diff --git a/include/drm/ttm/ttm_bo_driver.h b/include/drm/ttm/ttm_bo_driver.h
index 62ed733c52a2..a68829db381a 100644
--- a/include/drm/ttm/ttm_bo_driver.h
+++ b/include/drm/ttm/ttm_bo_driver.h
@@ -121,6 +121,7 @@ struct ttm_backend {
 #define TTM_PAGE_FLAG_SWAPPED         (1 << 4)
 #define TTM_PAGE_FLAG_PERSISTANT_SWAP (1 << 5)
 #define TTM_PAGE_FLAG_ZERO_ALLOC      (1 << 6)
+#define TTM_PAGE_FLAG_DMA32           (1 << 7)
 
 enum ttm_caching_state {
         tt_uncached,
@@ -353,6 +354,14 @@ struct ttm_bo_driver {
         int (*sync_obj_flush) (void *sync_obj, void *sync_arg);
         void (*sync_obj_unref) (void **sync_obj);
         void *(*sync_obj_ref) (void *sync_obj);
+
+        /* hook to notify driver about a driver move so it
+         * can do tiling things */
+        void (*move_notify)(struct ttm_buffer_object *bo,
+                            struct ttm_mem_reg *new_mem);
+        /* notify the driver we are taking a fault on this BO
+         * and have reserved it */
+        void (*fault_reserve_notify)(struct ttm_buffer_object *bo);
 };
 
 #define TTM_NUM_MEM_TYPES 8
@@ -429,6 +438,8 @@ struct ttm_bo_device {
          */
 
         struct delayed_work wq;
+
+        bool need_dma32;
 };
 
 /**
@@ -648,7 +659,14 @@ extern int ttm_bo_device_release(struct ttm_bo_device *bdev);
 extern int ttm_bo_device_init(struct ttm_bo_device *bdev,
                               struct ttm_mem_global *mem_glob,
                               struct ttm_bo_driver *driver,
-                              uint64_t file_page_offset);
+                              uint64_t file_page_offset, bool need_dma32);
+
+/**
+ * ttm_bo_unmap_virtual
+ *
+ * @bo: tear down the virtual mappings for this BO
+ */
+extern void ttm_bo_unmap_virtual(struct ttm_buffer_object *bo);
 
 /**
  * ttm_bo_reserve:
diff --git a/include/drm/ttm/ttm_module.h b/include/drm/ttm/ttm_module.h
index 889a4c7958ae..d1d433834e4f 100644
--- a/include/drm/ttm/ttm_module.h
+++ b/include/drm/ttm/ttm_module.h
@@ -33,7 +33,7 @@
 
 #include <linux/kernel.h>
 
-#define TTM_PFX "[TTM]"
+#define TTM_PFX "[TTM] "
 
 enum ttm_global_types {
         TTM_GLOBAL_TTM_MEM = 0,
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
index 2878811c6134..756d78b8c1c5 100644
--- a/include/linux/bitmap.h
+++ b/include/linux/bitmap.h
@@ -94,13 +94,13 @@ extern void __bitmap_shift_right(unsigned long *dst,
                         const unsigned long *src, int shift, int bits);
 extern void __bitmap_shift_left(unsigned long *dst,
                         const unsigned long *src, int shift, int bits);
-extern void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
                         const unsigned long *bitmap2, int bits);
 extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
                         const unsigned long *bitmap2, int bits);
 extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
                         const unsigned long *bitmap2, int bits);
-extern void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
                         const unsigned long *bitmap2, int bits);
 extern int __bitmap_intersects(const unsigned long *bitmap1,
                         const unsigned long *bitmap2, int bits);
@@ -171,13 +171,12 @@ static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
         }
 }
 
-static inline void bitmap_and(unsigned long *dst, const unsigned long *src1,
+static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
         if (small_const_nbits(nbits))
-                *dst = *src1 & *src2;
-        else
-                __bitmap_and(dst, src1, src2, nbits);
+                return (*dst = *src1 & *src2) != 0;
+        return __bitmap_and(dst, src1, src2, nbits);
 }
 
 static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
@@ -198,13 +197,12 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
                 __bitmap_xor(dst, src1, src2, nbits);
 }
 
-static inline void bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1,
                         const unsigned long *src2, int nbits)
 {
         if (small_const_nbits(nbits))
-                *dst = *src1 & ~(*src2);
-        else
-                __bitmap_andnot(dst, src1, src2, nbits);
+                return (*dst = *src1 & ~(*src2)) != 0;
+        return __bitmap_andnot(dst, src1, src2, nbits);
 }
 
 static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index e7cb5dbf6c26..69103e053c92 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -913,6 +913,7 @@ extern void blk_queue_logical_block_size(struct request_queue *, unsigned short)
 extern void blk_queue_physical_block_size(struct request_queue *, unsigned short);
 extern void blk_queue_alignment_offset(struct request_queue *q,
                                        unsigned int alignment);
+extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min);
 extern void blk_queue_io_min(struct request_queue *q, unsigned int min);
 extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
 extern void blk_set_default_limits(struct queue_limits *lim);
diff --git a/include/linux/cb710.h b/include/linux/cb710.h
index 63bc9a4d2926..8cc10411bab2 100644
--- a/include/linux/cb710.h
+++ b/include/linux/cb710.h
@@ -140,29 +140,6 @@ void cb710_dump_regs(struct cb710_chip *chip, unsigned dump);
 #include <linux/highmem.h>
 #include <linux/scatterlist.h>
 
-/**
- * cb710_sg_miter_stop_writing - stop mapping iteration after writing
- * @miter: sg mapping iter to be stopped
- *
- * Description:
- *   Stops mapping iterator @miter.  @miter should have been started
- *   started using sg_miter_start().  A stopped iteration can be
- *   resumed by calling sg_miter_next() on it.  This is useful when
- *   resources (kmap) need to be released during iteration.
- *
- *   This is a convenience wrapper that will be optimized out for arches
- *   that don't need flush_kernel_dcache_page().
- *
- * Context:
- *   IRQ disabled if the SG_MITER_ATOMIC is set.  Don't care otherwise.
- */
-static inline void cb710_sg_miter_stop_writing(struct sg_mapping_iter *miter)
-{
-        if (miter->page)
-                flush_kernel_dcache_page(miter->page);
-        sg_miter_stop(miter);
-}
-
 /*
  * 32-bit PIO mapping sg iterator
  *
@@ -171,12 +148,12 @@ static inline void cb710_sg_miter_stop_writing(struct sg_mapping_iter *miter)
  * without DMA support).
  *
  * Best-case reading (transfer from device):
- *   sg_miter_start();
+ *   sg_miter_start(, SG_MITER_TO_SG);
  *   cb710_sg_dwiter_write_from_io();
- *   cb710_sg_miter_stop_writing();
+ *   sg_miter_stop();
  *
  * Best-case writing (transfer to device):
- *   sg_miter_start();
+ *   sg_miter_start(, SG_MITER_FROM_SG);
  *   cb710_sg_dwiter_read_to_io();
  *   sg_miter_stop();
  */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 665fa70e4094..90bba9e62286 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -179,14 +179,11 @@ struct cgroup {
          */
         struct list_head release_list;
 
-        /* pids_mutex protects the fields below */
+        /* pids_mutex protects pids_list and cached pid arrays. */
         struct rw_semaphore pids_mutex;
-        /* Array of process ids in the cgroup */
-        pid_t *tasks_pids;
-        /* How many files are using the current tasks_pids array */
-        int pids_use_count;
-        /* Length of the current tasks_pids array */
-        int pids_length;
+
+        /* Linked list of struct cgroup_pids */
+        struct list_head pids_list;
 
         /* For RCU-protected deletion */
         struct rcu_head rcu_head;
@@ -366,6 +363,23 @@ int cgroup_task_count(const struct cgroup *cgrp);
 int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task);
 
 /*
+ * When the subsys has to access css and may add permanent refcnt to css,
+ * it should take care of racy conditions with rmdir(). Following set of
+ * functions, is for stop/restart rmdir if necessary.
+ * Because these will call css_get/put, "css" should be alive css.
+ *
+ *  cgroup_exclude_rmdir();
+ *  ...do some jobs which may access arbitrary empty cgroup
+ *  cgroup_release_and_wakeup_rmdir();
+ *
+ *  When someone removes a cgroup while cgroup_exclude_rmdir() holds it,
+ *  it sleeps and cgroup_release_and_wakeup_rmdir() will wake him up.
+ */
+
+void cgroup_exclude_rmdir(struct cgroup_subsys_state *css);
+void cgroup_release_and_wakeup_rmdir(struct cgroup_subsys_state *css);
+
+/*
  * Control Group subsystem type.
  * See Documentation/cgroups/cgroups.txt for details
  */
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index c56457c8334e..1219be4fb42e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -293,7 +293,12 @@ static inline int clocksource_enable(struct clocksource *cs)
         if (cs->enable)
                 ret = cs->enable(cs);
 
-        /* save mult_orig on enable */
+        /*
+         * The frequency may have changed while the clocksource
+         * was disabled. If so the code in ->enable() must update
+         * the mult value to reflect the new frequency. Make sure
+         * mult_orig follows this change.
+         */
         cs->mult_orig = cs->mult;
 
         return ret;
@@ -309,6 +314,13 @@ static inline int clocksource_enable(struct clocksource *cs)
  */
 static inline void clocksource_disable(struct clocksource *cs)
 {
+        /*
+         * Save mult_orig in mult so clocksource_enable() can
+         * restore the value regardless if ->enable() updates
+         * the value of mult or not.
+         */
+        cs->mult = cs->mult_orig;
+
         if (cs->disable)
                 cs->disable(cs);
 }
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index c5ac87ca7bc6..796df12091b7 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -43,10 +43,10 @@
  * int cpu_isset(cpu, mask)             true iff bit 'cpu' set in mask
  * int cpu_test_and_set(cpu, mask)      test and set bit 'cpu' in mask
  *
- * void cpus_and(dst, src1, src2)       dst = src1 & src2  [intersection]
+ * int cpus_and(dst, src1, src2)        dst = src1 & src2  [intersection]
  * void cpus_or(dst, src1, src2)        dst = src1 | src2  [union]
  * void cpus_xor(dst, src1, src2)       dst = src1 ^ src2
- * void cpus_andnot(dst, src1, src2)    dst = src1 & ~src2
+ * int cpus_andnot(dst, src1, src2)     dst = src1 & ~src2
  * void cpus_complement(dst, src)       dst = ~src
  *
  * int cpus_equal(mask1, mask2)         Does mask1 == mask2?
@@ -179,10 +179,10 @@ static inline int __cpu_test_and_set(int cpu, cpumask_t *addr)
 }
 
 #define cpus_and(dst, src1, src2) __cpus_and(&(dst), &(src1), &(src2), NR_CPUS)
-static inline void __cpus_and(cpumask_t *dstp, const cpumask_t *src1p,
+static inline int __cpus_and(cpumask_t *dstp, const cpumask_t *src1p,
                                         const cpumask_t *src2p, int nbits)
 {
-        bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
+        return bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_or(dst, src1, src2) __cpus_or(&(dst), &(src1), &(src2), NR_CPUS)
@@ -201,10 +201,10 @@ static inline void __cpus_xor(cpumask_t *dstp, const cpumask_t *src1p,
 
 #define cpus_andnot(dst, src1, src2) \
                                 __cpus_andnot(&(dst), &(src1), &(src2), NR_CPUS)
-static inline void __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p,
+static inline int __cpus_andnot(cpumask_t *dstp, const cpumask_t *src1p,
                                         const cpumask_t *src2p, int nbits)
 {
-        bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
+        return bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits);
 }
 
 #define cpus_complement(dst, src) __cpus_complement(&(dst), &(src), NR_CPUS)
@@ -738,11 +738,11 @@ static inline void cpumask_clear(struct cpumask *dstp)
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_and(struct cpumask *dstp,
+static inline int cpumask_and(struct cpumask *dstp,
                                const struct cpumask *src1p,
                                const struct cpumask *src2p)
 {
-        bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
+        return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p),
                                        cpumask_bits(src2p), nr_cpumask_bits);
 }
 
@@ -779,11 +779,11 @@ static inline void cpumask_xor(struct cpumask *dstp,
  * @src1p: the first input
  * @src2p: the second input
  */
-static inline void cpumask_andnot(struct cpumask *dstp,
+static inline int cpumask_andnot(struct cpumask *dstp,
                                   const struct cpumask *src1p,
                                   const struct cpumask *src2p)
 {
-        bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
+        return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p),
                                           cpumask_bits(src2p), nr_cpumask_bits);
 }
 
diff --git a/include/linux/decompress/generic.h b/include/linux/decompress/generic.h
index 6dfb856327bb..0c7111a55a1a 100644
--- a/include/linux/decompress/generic.h
+++ b/include/linux/decompress/generic.h
@@ -1,31 +1,37 @@
 #ifndef DECOMPRESS_GENERIC_H
 #define DECOMPRESS_GENERIC_H
 
-/* Minimal chunksize to be read.
- *Bzip2 prefers at least 4096
- *Lzma prefers 0x10000 */
-#define COMPR_IOBUF_SIZE        4096
-
 typedef int (*decompress_fn) (unsigned char *inbuf, int len,
                               int(*fill)(void*, unsigned int),
-                              int(*writebb)(void*, unsigned int),
-                              unsigned char *output,
+                              int(*flush)(void*, unsigned int),
+                              unsigned char *outbuf,
                               int *posp,
                               void(*error)(char *x));
 
 /* inbuf   - input buffer
  *len     - len of pre-read data in inbuf
- *fill    - function to fill inbuf if empty
- *writebb - function to write out outbug
+ *fill    - function to fill inbuf when empty
+ *flush   - function to write out outbuf
+ *outbuf  - output buffer
  *posp    - if non-null, input position (number of bytes read) will be
  *        returned here
  *
- *If len != 0, the inbuf is initialized (with as much data), and fill
- *should not be called
- *If len = 0, the inbuf is allocated, but empty. Its size is IOBUF_SIZE
- *fill should be called (repeatedly...) to read data, at most IOBUF_SIZE
+ *If len != 0, inbuf should contain all the necessary input data, and fill
+ *should be NULL
+ *If len = 0, inbuf can be NULL, in which case the decompressor will allocate
+ *the input buffer.  If inbuf != NULL it must be at least XXX_IOBUF_SIZE bytes.
+ *fill will be called (repeatedly...) to read data, at most XXX_IOBUF_SIZE
+ *bytes should be read per call.  Replace XXX with the appropriate decompressor
+ *name, i.e. LZMA_IOBUF_SIZE.
+ *
+ *If flush = NULL, outbuf must be large enough to buffer all the expected
+ *output.  If flush != NULL, the output buffer will be allocated by the
+ *decompressor (outbuf = NULL), and the flush function will be called to
+ *flush the output buffer at the appropriate time (decompressor and stream
+ *dependent).
  */
 
+
 /* Utility routine to detect the decompression method */
 decompress_fn decompress_method(const unsigned char *inbuf, int len,
                                 const char **name);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 0d6310657f32..655e7721580a 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -84,7 +84,7 @@ typedef int (*dm_merge_fn) (struct dm_target *ti, struct bvec_merge_data *bvm,
 
 typedef int (*iterate_devices_callout_fn) (struct dm_target *ti,
                                            struct dm_dev *dev,
-                                           sector_t physical_start,
+                                           sector_t start, sector_t len,
                                            void *data);
 
 typedef int (*dm_iterate_devices_fn) (struct dm_target *ti,
@@ -104,7 +104,7 @@ void dm_error(const char *message);
  * Combine device limits.
  */
 int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
-                         sector_t start, void *data);
+                         sector_t start, sector_t len, void *data);
 
 struct dm_dev {
         struct block_device *bdev;
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index 634a5e5aba3e..7499b3667798 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -874,7 +874,7 @@ struct buffer_head * ext3_getblk (handle_t *, struct inode *, long, int, int *);
 struct buffer_head * ext3_bread (handle_t *, struct inode *, int, int, int *);
 int ext3_get_blocks_handle(handle_t *handle, struct inode *inode,
         sector_t iblock, unsigned long maxblocks, struct buffer_head *bh_result,
-        int create, int extend_disksize);
+        int create);
 
 extern struct inode *ext3_iget(struct super_block *, unsigned long);
 extern int  ext3_write_inode (struct inode *, int);
diff --git a/include/linux/flex_array.h b/include/linux/flex_array.h
new file mode 100644
index 000000000000..45ff18491514
--- /dev/null
+++ b/include/linux/flex_array.h
@@ -0,0 +1,49 @@
+#ifndef _FLEX_ARRAY_H
+#define _FLEX_ARRAY_H
+
+#include <linux/types.h>
+#include <asm/page.h>
+
+#define FLEX_ARRAY_PART_SIZE PAGE_SIZE
+#define FLEX_ARRAY_BASE_SIZE PAGE_SIZE
+
+struct flex_array_part;
+
+/*
+ * This is meant to replace cases where an array-like
+ * structure has gotten too big to fit into kmalloc()
+ * and the developer is getting tempted to use
+ * vmalloc().
+ */
+
+struct flex_array {
+        union {
+                struct {
+                        int element_size;
+                        int total_nr_elements;
+                        struct flex_array_part *parts[];
+                };
+                /*
+                 * This little trick makes sure that
+                 * sizeof(flex_array) == PAGE_SIZE
+                 */
+                char padding[FLEX_ARRAY_BASE_SIZE];
+        };
+};
+
+#define FLEX_ARRAY_INIT(size, total) { { {\
+        .element_size = (size),         \
+        .total_nr_elements = (total),   \
+} } }
+
+struct flex_array *flex_array_alloc(int element_size, unsigned int total,
+                gfp_t flags);
+int flex_array_prealloc(struct flex_array *fa, unsigned int start,
+                unsigned int end, gfp_t flags);
+void flex_array_free(struct flex_array *fa);
+void flex_array_free_parts(struct flex_array *fa);
+int flex_array_put(struct flex_array *fa, unsigned int element_nr, void *src,
+                gfp_t flags);
+void *flex_array_get(struct flex_array *fa, unsigned int element_nr);
+
+#endif /* _FLEX_ARRAY_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 0872372184fe..73e9b643e455 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1946,6 +1946,7 @@ extern void putname(const char *name);
 extern int register_blkdev(unsigned int, const char *);
 extern void unregister_blkdev(unsigned int, const char *);
 extern struct block_device *bdget(dev_t);
+extern struct block_device *bdgrab(struct block_device *bdev);
 extern void bd_set_size(struct block_device *, loff_t size);
 extern void bd_forget(struct inode *inode);
 extern void bdput(struct block_device *);
@@ -2122,7 +2123,7 @@ extern struct file *do_filp_open(int dfd, const char *pathname,
                 int open_flag, int mode, int acc_mode);
 extern int may_open(struct path *, int, int);
 
-extern int kernel_read(struct file *, unsigned long, char *, unsigned long);
+extern int kernel_read(struct file *, loff_t, char *, unsigned long);
 extern struct file * open_exec(const char *);
  
 /* fs/dcache.c -- generic fs support functions */
@@ -2136,7 +2137,7 @@ extern loff_t default_llseek(struct file *file, loff_t offset, int origin);
 
 extern loff_t vfs_llseek(struct file *file, loff_t offset, int origin);
 
-extern struct inode * inode_init_always(struct super_block *, struct inode *);
+extern int inode_init_always(struct super_block *, struct inode *);
 extern void inode_init_once(struct inode *);
 extern void inode_add_to_lists(struct super_block *, struct inode *);
 extern void iput(struct inode *);
@@ -2163,6 +2164,7 @@ extern void __iget(struct inode * inode);
 extern void iget_failed(struct inode *);
 extern void clear_inode(struct inode *);
 extern void destroy_inode(struct inode *);
+extern void __destroy_inode(struct inode *);
 extern struct inode *new_inode(struct super_block *);
 extern int should_remove_suid(struct dentry *);
 extern int file_remove_suid(struct file *);
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 6c3de999fb34..4d6f47b51189 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -352,7 +352,7 @@ extern void fsnotify_unmount_inodes(struct list_head *list);
 /* put here because inotify does some weird stuff when destroying watches */
 extern struct fsnotify_event *fsnotify_create_event(struct inode *to_tell, __u32 mask,
                                                     void *data, int data_is, const char *name,
-                                                    u32 cookie);
+                                                    u32 cookie, gfp_t gfp);
 
 #else
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 5c093ffc655b..a81170de7f6b 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -89,7 +89,9 @@ enum print_line_t {
         TRACE_TYPE_NO_CONSUME   = 3     /* Handled but ask to not consume */
 };
 
-
+void tracing_generic_entry_update(struct trace_entry *entry,
+                                  unsigned long flags,
+                                  int pc);
 struct ring_buffer_event *
 trace_current_buffer_lock_reserve(int type, unsigned long len,
                                   unsigned long flags, int pc);
@@ -119,11 +121,9 @@ struct ftrace_event_call {
         void                    *filter;
         void                    *mod;
 
-#ifdef CONFIG_EVENT_PROFILE
-        atomic_t        profile_count;
-        int             (*profile_enable)(struct ftrace_event_call *);
-        void            (*profile_disable)(struct ftrace_event_call *);
-#endif
+        atomic_t                profile_count;
+        int                     (*profile_enable)(struct ftrace_event_call *);
+        void                    (*profile_disable)(struct ftrace_event_call *);
 };
 
 #define MAX_FILTER_PRED         32
diff --git a/include/linux/gen_stats.h b/include/linux/gen_stats.h
index 0ffa41df0ee8..710e901085d0 100644
--- a/include/linux/gen_stats.h
+++ b/include/linux/gen_stats.h
@@ -22,6 +22,11 @@ struct gnet_stats_basic
 {
         __u64   bytes;
         __u32   packets;
+};
+struct gnet_stats_basic_packed
+{
+        __u64   bytes;
+        __u32   packets;
 } __attribute__ ((packed));
 
 /**
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 2723513a5651..5cbc620bdfe0 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -10,6 +10,7 @@
 #include <asm/tlbflush.h>
 
 struct ctl_table;
+struct user_struct;
 
 int PageHuge(struct page *page);
 
@@ -146,7 +147,8 @@ static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb)
 
 extern const struct file_operations hugetlbfs_file_operations;
 extern struct vm_operations_struct hugetlb_vm_ops;
-struct file *hugetlb_file_setup(const char *name, size_t, int);
+struct file *hugetlb_file_setup(const char *name, size_t size, int acct,
+                                                struct user_struct **user);
 int hugetlb_get_quota(struct address_space *mapping, long delta);
 void hugetlb_put_quota(struct address_space *mapping, long delta);
 
@@ -168,7 +170,7 @@ static inline void set_file_hugepages(struct file *file)
 
 #define is_file_hugepages(file)                 0
 #define set_file_hugepages(file)                BUG()
-#define hugetlb_file_setup(name,size,acctflag)  ERR_PTR(-ENOSYS)
+#define hugetlb_file_setup(name,size,acct,user) ERR_PTR(-ENOSYS)
 
 #endif /* !CONFIG_HUGETLBFS */
 
diff --git a/include/linux/inetdevice.h b/include/linux/inetdevice.h
index acef2a770b6b..ad27c7da8798 100644
--- a/include/linux/inetdevice.h
+++ b/include/linux/inetdevice.h
@@ -82,7 +82,7 @@ static inline void ipv4_devconf_setall(struct in_device *in_dev)
 
 #define IN_DEV_FORWARD(in_dev)          IN_DEV_CONF_GET((in_dev), FORWARDING)
 #define IN_DEV_MFORWARD(in_dev)         IN_DEV_ANDCONF((in_dev), MC_FORWARDING)
-#define IN_DEV_RPFILTER(in_dev)         IN_DEV_ANDCONF((in_dev), RP_FILTER)
+#define IN_DEV_RPFILTER(in_dev)         IN_DEV_MAXCONF((in_dev), RP_FILTER)
 #define IN_DEV_SOURCE_ROUTE(in_dev)     IN_DEV_ANDCONF((in_dev), \
                                                        ACCEPT_SOURCE_ROUTE)
 #define IN_DEV_BOOTP_RELAY(in_dev)      IN_DEV_ANDCONF((in_dev), BOOTP_RELAY)
diff --git a/include/linux/input/matrix_keypad.h b/include/linux/input/matrix_keypad.h
index 7964516c6954..15d5903af2dd 100644
--- a/include/linux/input/matrix_keypad.h
+++ b/include/linux/input/matrix_keypad.h
@@ -15,12 +15,13 @@
 #define KEY_COL(k)              (((k) >> 16) & 0xff)
 #define KEY_VAL(k)              ((k) & 0xffff)
 
+#define MATRIX_SCAN_CODE(row, col, row_shift)   (((row) << (row_shift)) + (col))
+
 /**
  * struct matrix_keymap_data - keymap for matrix keyboards
  * @keymap: pointer to array of uint32 values encoded with KEY() macro
  *      representing keymap
  * @keymap_size: number of entries (initialized) in this keymap
- * @max_keymap_size: maximum size of keymap supported by the device
  *
  * This structure is supposed to be used by platform code to supply
  * keymaps to drivers that implement matrix-like keypads/keyboards.
@@ -28,14 +29,13 @@
 struct matrix_keymap_data {
         const uint32_t *keymap;
         unsigned int    keymap_size;
-        unsigned int    max_keymap_size;
 };
 
 /**
  * struct matrix_keypad_platform_data - platform-dependent keypad data
  * @keymap_data: pointer to &matrix_keymap_data
- * @row_gpios: array of gpio numbers reporesenting rows
- * @col_gpios: array of gpio numbers reporesenting colums
+ * @row_gpios: pointer to array of gpio numbers representing rows
+ * @col_gpios: pointer to array of gpio numbers reporesenting colums
  * @num_row_gpios: actual number of row gpios used by device
  * @num_col_gpios: actual number of col gpios used by device
  * @col_scan_delay_us: delay, measured in microseconds, that is
@@ -48,8 +48,9 @@ struct matrix_keymap_data {
 struct matrix_keypad_platform_data {
         const struct matrix_keymap_data *keymap_data;
 
-        unsigned int    row_gpios[MATRIX_MAX_ROWS];
-        unsigned int    col_gpios[MATRIX_MAX_COLS];
+        const unsigned int *row_gpios;
+        const unsigned int *col_gpios;
+
         unsigned int    num_row_gpios;
         unsigned int    num_col_gpios;
 
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 2721f07e9354..35e7df1e9f30 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -14,6 +14,7 @@
 #include <linux/irqflags.h>
 #include <linux/smp.h>
 #include <linux/percpu.h>
+#include <linux/hrtimer.h>
 
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
@@ -64,11 +65,13 @@
  * IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
  * IRQTF_DIED      - handler thread died
  * IRQTF_WARNED    - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
+ * IRQTF_AFFINITY  - irq thread is requested to adjust affinity
  */
 enum {
         IRQTF_RUNTHREAD,
         IRQTF_DIED,
         IRQTF_WARNED,
+        IRQTF_AFFINITY,
 };
 
 typedef irqreturn_t (*irq_handler_t)(int, void *);
@@ -517,6 +520,31 @@ extern void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu);
 extern void tasklet_init(struct tasklet_struct *t,
                          void (*func)(unsigned long), unsigned long data);
 
+struct tasklet_hrtimer {
+        struct hrtimer          timer;
+        struct tasklet_struct   tasklet;
+        enum hrtimer_restart    (*function)(struct hrtimer *);
+};
+
+extern void
+tasklet_hrtimer_init(struct tasklet_hrtimer *ttimer,
+                     enum hrtimer_restart (*function)(struct hrtimer *),
+                     clockid_t which_clock, enum hrtimer_mode mode);
+
+static inline
+int tasklet_hrtimer_start(struct tasklet_hrtimer *ttimer, ktime_t time,
+                          const enum hrtimer_mode mode)
+{
+        return hrtimer_start(&ttimer->timer, time, mode);
+}
+
+static inline
+void tasklet_hrtimer_cancel(struct tasklet_hrtimer *ttimer)
+{
+        hrtimer_cancel(&ttimer->timer);
+        tasklet_kill(&ttimer->tasklet);
+}
+
 /*
  * Autoprobing for irqs:
  *
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index dd05434fa45f..4da4a75c3f1e 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -92,7 +92,7 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc)
          * a race).
          */
         if (ioc && atomic_long_inc_not_zero(&ioc->refcount)) {
-                atomic_long_inc(&ioc->refcount);
+                atomic_inc(&ioc->nr_tasks);
                 return ioc;
         }
 
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 16713dc672e4..3060bdc35ffe 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -110,6 +110,7 @@ struct kvm_memory_slot {
 
 struct kvm_kernel_irq_routing_entry {
         u32 gsi;
+        u32 type;
         int (*set)(struct kvm_kernel_irq_routing_entry *e,
                     struct kvm *kvm, int level);
         union {
diff --git a/include/linux/lguest.h b/include/linux/lguest.h
index dbf2479e808e..2fb1dcbcb5aa 100644
--- a/include/linux/lguest.h
+++ b/include/linux/lguest.h
@@ -1,5 +1,7 @@
-/* Things the lguest guest needs to know.  Note: like all lguest interfaces,
- * this is subject to wild and random change between versions. */
+/*
+ * Things the lguest guest needs to know.  Note: like all lguest interfaces,
+ * this is subject to wild and random change between versions.
+ */
 #ifndef _LINUX_LGUEST_H
 #define _LINUX_LGUEST_H
 
@@ -11,32 +13,41 @@
 #define LG_CLOCK_MIN_DELTA      100UL
 #define LG_CLOCK_MAX_DELTA      ULONG_MAX
 
-/*G:031 The second method of communicating with the Host is to via "struct
+/*G:031
+ * The second method of communicating with the Host is to via "struct
  * lguest_data".  Once the Guest's initialization hypercall tells the Host where
- * this is, the Guest and Host both publish information in it. :*/
-struct lguest_data
-{
-        /* 512 == enabled (same as eflags in normal hardware).  The Guest
-         * changes interrupts so often that a hypercall is too slow. */
+ * this is, the Guest and Host both publish information in it.
+:*/
+struct lguest_data {
+        /*
+         * 512 == enabled (same as eflags in normal hardware).  The Guest
+         * changes interrupts so often that a hypercall is too slow.
+         */
         unsigned int irq_enabled;
         /* Fine-grained interrupt disabling by the Guest */
         DECLARE_BITMAP(blocked_interrupts, LGUEST_IRQS);
 
-        /* The Host writes the virtual address of the last page fault here,
+        /*
+         * The Host writes the virtual address of the last page fault here,
          * which saves the Guest a hypercall.  CR2 is the native register where
-         * this address would normally be found. */
+         * this address would normally be found.
+         */
         unsigned long cr2;
 
         /* Wallclock time set by the Host. */
         struct timespec time;
 
-        /* Interrupt pending set by the Host.  The Guest should do a hypercall
-         * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF). */
+        /*
+         * Interrupt pending set by the Host.  The Guest should do a hypercall
+         * if it re-enables interrupts and sees this set (to X86_EFLAGS_IF).
+         */
         int irq_pending;
 
-        /* Async hypercall ring.  Instead of directly making hypercalls, we can
+        /*
+         * Async hypercall ring.  Instead of directly making hypercalls, we can
          * place them in here for processing the next time the Host wants.
-         * This batching can be quite efficient. */
+         * This batching can be quite efficient.
+         */
 
         /* 0xFF == done (set by Host), 0 == pending (set by Guest). */
         u8 hcall_status[LHCALL_RING_SIZE];
diff --git a/include/linux/lguest_launcher.h b/include/linux/lguest_launcher.h
index bfefbdf7498a..495203ff221c 100644
--- a/include/linux/lguest_launcher.h
+++ b/include/linux/lguest_launcher.h
@@ -29,8 +29,10 @@ struct lguest_device_desc {
         __u8 type;
         /* The number of virtqueues (first in config array) */
         __u8 num_vq;
-        /* The number of bytes of feature bits.  Multiply by 2: one for host
-         * features and one for Guest acknowledgements. */
+        /*
+         * The number of bytes of feature bits.  Multiply by 2: one for host
+         * features and one for Guest acknowledgements.
+         */
         __u8 feature_len;
         /* The number of bytes of the config array after virtqueues. */
         __u8 config_len;
@@ -39,8 +41,10 @@ struct lguest_device_desc {
         __u8 config[0];
 };
 
-/*D:135 This is how we expect the device configuration field for a virtqueue
- * to be laid out in config space. */
+/*D:135
+ * This is how we expect the device configuration field for a virtqueue
+ * to be laid out in config space.
+ */
 struct lguest_vqconfig {
         /* The number of entries in the virtio_ring */
         __u16 num;
@@ -61,7 +65,9 @@ enum lguest_req
         LHREQ_EVENTFD, /* + address, fd. */
 };
 
-/* The alignment to use between consumer and producer parts of vring.
- * x86 pagesize for historical reasons. */
+/*
+ * The alignment to use between consumer and producer parts of vring.
+ * x86 pagesize for historical reasons.
+ */
 #define LGUEST_VRING_ALIGN      4096
 #endif /* _LINUX_LGUEST_LAUNCHER */
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 79b6d7fd4ac2..e5b6e33c6571 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -589,6 +589,7 @@ struct ata_device {
 #endif
         /* n_sector is CLEAR_BEGIN, read comment above CLEAR_BEGIN */
         u64                     n_sectors;      /* size of device, if ATA */
+        u64                     n_native_sectors; /* native size, if ATA */
         unsigned int            class;          /* ATA_DEV_xxx */
         unsigned long           unpark_deadline;
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ba3a7cb1eaa0..9a72cc78e6b8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -34,8 +34,6 @@ extern int sysctl_legacy_va_layout;
 #define sysctl_legacy_va_layout 0
 #endif
 
-extern unsigned long mmap_min_addr;
-
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -575,19 +573,6 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
 }
 
 /*
- * If a hint addr is less than mmap_min_addr change hint to be as
- * low as possible but still greater than mmap_min_addr
- */
-static inline unsigned long round_hint_to_min(unsigned long hint)
-{
-        hint &= PAGE_MASK;
-        if (((void *)hint != NULL) &&
-            (hint < mmap_min_addr))
-                return PAGE_ALIGN(mmap_min_addr);
-        return hint;
-}
-
-/*
  * Some inline functions in vmstat.h depend on page_zone()
  */
 #include <linux/vmstat.h>
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 7acc8439d9b3..0042090a4d70 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -240,8 +240,6 @@ struct mm_struct {
 
         unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
 
-        s8 oom_adj;     /* OOM kill score adjustment (bit shift) */
-
         cpumask_t cpu_vm_mask;
 
         /* Architecture-specific MM context */
diff --git a/include/linux/mtd/mtd.h b/include/linux/mtd/mtd.h
index 5675b63a0631..0f32a9b6ff55 100644
--- a/include/linux/mtd/mtd.h
+++ b/include/linux/mtd/mtd.h
@@ -251,7 +251,7 @@ struct mtd_info {
 
 static inline struct mtd_info *dev_to_mtd(struct device *dev)
 {
-        return dev ? container_of(dev, struct mtd_info, dev) : NULL;
+        return dev ? dev_get_drvdata(dev) : NULL;
 }
 
 static inline uint32_t mtd_div_by_eb(uint64_t sz, struct mtd_info *mtd)
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index af6dcb992bc3..b70313d33ff8 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -47,6 +47,8 @@ struct mtd_partition {
 #define MTDPART_SIZ_FULL        (0)
 
 
+struct mtd_info;
+
 int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int);
 int del_mtd_partitions(struct mtd_info *);
 
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index fdffb413b192..f6b90240dd41 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -473,7 +473,6 @@ extern int  nfs_writepages(struct address_space *, struct writeback_control *);
 extern int  nfs_flush_incompatible(struct file *file, struct page *page);
 extern int  nfs_updatepage(struct file *, struct page *, unsigned int, unsigned int);
 extern int nfs_writeback_done(struct rpc_task *, struct nfs_write_data *);
-extern void nfs_writedata_release(void *);
 
 /*
  * Try to write back everything synchronously (but check the
@@ -488,7 +487,6 @@ extern int nfs_wb_page_cancel(struct inode *inode, struct page* page);
 extern int  nfs_commit_inode(struct inode *, int);
 extern struct nfs_write_data *nfs_commitdata_alloc(void);
 extern void nfs_commit_free(struct nfs_write_data *wdata);
-extern void nfs_commitdata_release(void *wdata);
 #else
 static inline int
 nfs_commit_inode(struct inode *inode, int how)
@@ -507,6 +505,7 @@ nfs_have_writebacks(struct inode *inode)
  * Allocate nfs_write_data structures
  */
 extern struct nfs_write_data *nfs_writedata_alloc(unsigned int npages);
+extern void nfs_writedata_free(struct nfs_write_data *);
 
 /*
  * linux/fs/nfs/read.c
@@ -515,7 +514,6 @@ extern int  nfs_readpage(struct file *, struct page *);
 extern int  nfs_readpages(struct file *, struct address_space *,
                 struct list_head *, unsigned);
 extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
-extern void nfs_readdata_release(void *data);
 extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
                                struct page *);
 
@@ -523,6 +521,7 @@ extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
  * Allocate nfs_read_data structures
  */
 extern struct nfs_read_data *nfs_readdata_alloc(unsigned int npages);
+extern void nfs_readdata_free(struct nfs_read_data *);
 
 /*
  * linux/fs/nfs3proc.c
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index 829b94b156f2..b359c4a9ec9e 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -82,6 +82,12 @@
  *    to generate slightly worse code.  So use a simple one-line #define
  *    for node_isset(), instead of wrapping an inline inside a macro, the
  *    way we do the other calls.
+ *
+ * NODEMASK_SCRATCH
+ * When doing above logical AND, OR, XOR, Remap operations the callers tend to
+ * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large,
+ * nodemask_t's consume too much stack space.  NODEMASK_SCRATCH is a helper
+ * for such situations. See below and CPUMASK_ALLOC also.
  */
 
 #include <linux/kernel.h>
@@ -473,4 +479,26 @@ static inline int num_node_state(enum node_states state)
 #define for_each_node(node)        for_each_node_state(node, N_POSSIBLE)
 #define for_each_online_node(node) for_each_node_state(node, N_ONLINE)
 
+/*
+ * For nodemask scrach area.(See CPUMASK_ALLOC() in cpumask.h)
+ */
+
+#if NODES_SHIFT > 8 /* nodemask_t > 64 bytes */
+#define NODEMASK_ALLOC(x, m) struct x *m = kmalloc(sizeof(*m), GFP_KERNEL)
+#define NODEMASK_FREE(m) kfree(m)
+#else
+#define NODEMASK_ALLOC(x, m) struct x _m, *m = &_m
+#define NODEMASK_FREE(m)
+#endif
+
+/* A example struture for using NODEMASK_ALLOC, used in mempolicy. */
+struct nodemask_scratch {
+        nodemask_t      mask1;
+        nodemask_t      mask2;
+};
+
+#define NODEMASK_SCRATCH(x) NODEMASK_ALLOC(nodemask_scratch, x)
+#define NODEMASK_SCRATCH_FREE(x)  NODEMASK_FREE(x)
+
+
 #endif /* __LINUX_NODEMASK_H */
diff --git a/include/linux/of_mdio.h b/include/linux/of_mdio.h
index c9663c690303..53b94e025c7c 100644
--- a/include/linux/of_mdio.h
+++ b/include/linux/of_mdio.h
@@ -18,5 +18,8 @@ extern struct phy_device *of_phy_connect(struct net_device *dev,
                                          struct device_node *phy_np,
                                          void (*hndlr)(struct net_device *),
                                          u32 flags, phy_interface_t iface);
+extern struct phy_device *of_phy_connect_fixed_link(struct net_device *dev,
+                                         void (*hndlr)(struct net_device *),
+                                         phy_interface_t iface);
 
 #endif /* __LINUX_OF_MDIO_H */
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 5e970c7d3fd5..b53f7006cc4e 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -115,26 +115,44 @@ enum perf_counter_sample_format {
         PERF_SAMPLE_TID                         = 1U << 1,
         PERF_SAMPLE_TIME                        = 1U << 2,
         PERF_SAMPLE_ADDR                        = 1U << 3,
-        PERF_SAMPLE_GROUP                       = 1U << 4,
+        PERF_SAMPLE_READ                        = 1U << 4,
         PERF_SAMPLE_CALLCHAIN                   = 1U << 5,
         PERF_SAMPLE_ID                          = 1U << 6,
         PERF_SAMPLE_CPU                         = 1U << 7,
         PERF_SAMPLE_PERIOD                      = 1U << 8,
+        PERF_SAMPLE_STREAM_ID                   = 1U << 9,
+        PERF_SAMPLE_RAW                         = 1U << 10,
 
-        PERF_SAMPLE_MAX = 1U << 9,              /* non-ABI */
+        PERF_SAMPLE_MAX = 1U << 11,             /* non-ABI */
 };
 
 /*
- * Bits that can be set in attr.read_format to request that
- * reads on the counter should return the indicated quantities,
- * in increasing order of bit value, after the counter value.
+ * The format of the data returned by read() on a perf counter fd,
+ * as specified by attr.read_format:
+ *
+ * struct read_format {
+ *      { u64           value;
+ *        { u64         time_enabled; } && PERF_FORMAT_ENABLED
+ *        { u64         time_running; } && PERF_FORMAT_RUNNING
+ *        { u64         id;           } && PERF_FORMAT_ID
+ *      } && !PERF_FORMAT_GROUP
+ *
+ *      { u64           nr;
+ *        { u64         time_enabled; } && PERF_FORMAT_ENABLED
+ *        { u64         time_running; } && PERF_FORMAT_RUNNING
+ *        { u64         value;
+ *          { u64       id;           } && PERF_FORMAT_ID
+ *        }             cntr[nr];
+ *      } && PERF_FORMAT_GROUP
+ * };
  */
 enum perf_counter_read_format {
         PERF_FORMAT_TOTAL_TIME_ENABLED          = 1U << 0,
         PERF_FORMAT_TOTAL_TIME_RUNNING          = 1U << 1,
         PERF_FORMAT_ID                          = 1U << 2,
+        PERF_FORMAT_GROUP                       = 1U << 3,
 
-        PERF_FORMAT_MAX = 1U << 3,              /* non-ABI */
+        PERF_FORMAT_MAX = 1U << 4,              /* non-ABI */
 };
 
 #define PERF_ATTR_SIZE_VER0     64      /* sizeof first published struct */
@@ -180,8 +198,9 @@ struct perf_counter_attr {
                                 freq           :  1, /* use freq, not period  */
                                 inherit_stat   :  1, /* per task counts       */
                                 enable_on_exec :  1, /* next exec enables     */
+                                task           :  1, /* trace fork/exit       */
 
-                                __reserved_1   : 51;
+                                __reserved_1   : 50;
 
         __u32                   wakeup_events;  /* wakeup every n events */
         __u32                   __reserved_2;
@@ -310,18 +329,18 @@ enum perf_event_type {
         /*
          * struct {
          *      struct perf_event_header        header;
-         *      u64                             time;
-         *      u64                             id;
-         *      u64                             sample_period;
+         *      u32                             pid, ppid;
+         *      u32                             tid, ptid;
          * };
          */
-        PERF_EVENT_PERIOD               = 4,
+        PERF_EVENT_EXIT                 = 4,
 
         /*
          * struct {
          *      struct perf_event_header        header;
          *      u64                             time;
          *      u64                             id;
+         *      u64                             stream_id;
          * };
          */
         PERF_EVENT_THROTTLE             = 5,
@@ -331,6 +350,7 @@ enum perf_event_type {
          * struct {
          *      struct perf_event_header        header;
          *      u32                             pid, ppid;
+         *      u32                             tid, ptid;
          * };
          */
         PERF_EVENT_FORK                 = 7,
@@ -339,10 +359,8 @@ enum perf_event_type {
          * struct {
          *      struct perf_event_header        header;
          *      u32                             pid, tid;
-         *      u64                             value;
-         *      { u64           time_enabled;   } && PERF_FORMAT_ENABLED
-         *      { u64           time_running;   } && PERF_FORMAT_RUNNING
-         *      { u64           parent_id;      } && PERF_FORMAT_ID
+         *
+         *      struct read_format              values;
          * };
          */
         PERF_EVENT_READ                 = 8,
@@ -356,14 +374,28 @@ enum perf_event_type {
          *      { u64                   time;     } && PERF_SAMPLE_TIME
          *      { u64                   addr;     } && PERF_SAMPLE_ADDR
          *      { u64                   id;       } && PERF_SAMPLE_ID
+         *      { u64                   stream_id;} && PERF_SAMPLE_STREAM_ID
          *      { u32                   cpu, res; } && PERF_SAMPLE_CPU
          *      { u64                   period;   } && PERF_SAMPLE_PERIOD
          *
-         *      { u64                   nr;
-         *        { u64 id, val; }      cnt[nr];  } && PERF_SAMPLE_GROUP
+         *      { struct read_format    values;   } && PERF_SAMPLE_READ
          *
          *      { u64                   nr,
          *        u64                   ips[nr];  } && PERF_SAMPLE_CALLCHAIN
+         *
+         *      #
+         *      # The RAW record below is opaque data wrt the ABI
+         *      #
+         *      # That is, the ABI doesn't make any promises wrt to
+         *      # the stability of its content, it may vary depending
+         *      # on event, hardware, kernel version and phase of
+         *      # the moon.
+         *      #
+         *      # In other words, PERF_SAMPLE_RAW contents are not an ABI.
+         *      #
+         *
+         *      { u32                   size;
+         *        char                  data[size];}&& PERF_SAMPLE_RAW
          * };
          */
         PERF_EVENT_SAMPLE               = 9,
@@ -409,6 +441,11 @@ struct perf_callchain_entry {
         __u64                           ip[PERF_MAX_STACK_DEPTH];
 };
 
+struct perf_raw_record {
+        u32                             size;
+        void                            *data;
+};
+
 struct task_struct;
 
 /**
@@ -677,10 +714,13 @@ struct perf_sample_data {
         struct pt_regs                  *regs;
         u64                             addr;
         u64                             period;
+        struct perf_raw_record          *raw;
 };
 
 extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
                                  struct perf_sample_data *data);
+extern void perf_counter_output(struct perf_counter *counter, int nmi,
+                                struct perf_sample_data *data);
 
 /*
  * Return 1 for a software counter, 0 for a hardware counter
diff --git a/include/linux/pps.h b/include/linux/pps.h
index cfe5c7214ec6..0194ab06177b 100644
--- a/include/linux/pps.h
+++ b/include/linux/pps.h
@@ -22,6 +22,8 @@
 #ifndef _PPS_H_
 #define _PPS_H_
 
+#include <linux/types.h>
+
 #define PPS_VERSION             "5.3.6"
 #define PPS_MAX_SOURCES         16              /* should be enough... */
 
diff --git a/include/linux/rfkill.h b/include/linux/rfkill.h
index 2ce29831feb6..278777fa8a3a 100644
--- a/include/linux/rfkill.h
+++ b/include/linux/rfkill.h
@@ -224,7 +224,7 @@ void rfkill_destroy(struct rfkill *rfkill);
  * should be blocked) so that drivers need not keep track of the soft
  * block state -- which they might not be able to.
  */
-bool __must_check rfkill_set_hw_state(struct rfkill *rfkill, bool blocked);
+bool rfkill_set_hw_state(struct rfkill *rfkill, bool blocked);
 
 /**
  * rfkill_set_sw_state - Set the internal rfkill software block state
diff --git a/include/linux/scatterlist.h b/include/linux/scatterlist.h
index e5996984ddd0..9aaf5bfdad1a 100644
--- a/include/linux/scatterlist.h
+++ b/include/linux/scatterlist.h
@@ -242,6 +242,8 @@ size_t sg_copy_to_buffer(struct scatterlist *sgl, unsigned int nents,
  */
 
 #define SG_MITER_ATOMIC         (1 << 0)         /* use kmap_atomic */
+#define SG_MITER_TO_SG          (1 << 1)        /* flush back to phys on unmap */
+#define SG_MITER_FROM_SG        (1 << 2)        /* nop */
 
 struct sg_mapping_iter {
         /* the following three fields can be accessed directly */
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 16a982e389fb..0f1ea4a66957 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -209,7 +209,7 @@ extern unsigned long long time_sync_thresh;
                         ((task->state & (__TASK_STOPPED | __TASK_TRACED)) != 0)
 #define task_contributes_to_load(task)  \
                                 ((task->state & TASK_UNINTERRUPTIBLE) != 0 && \
-                                 (task->flags & PF_FROZEN) == 0)
+                                 (task->flags & PF_FREEZING) == 0)
 
 #define __set_task_state(tsk, state_value)              \
         do { (tsk)->state = (state_value); } while (0)
@@ -1198,6 +1198,7 @@ struct task_struct {
          * a short time
          */
         unsigned char fpu_counter;
+        s8 oomkilladj; /* OOM kill score adjustment (bit shift). */
 #ifdef CONFIG_BLK_DEV_IO_TRACE
         unsigned int btrace_seq;
 #endif
@@ -1680,6 +1681,7 @@ extern cputime_t task_gtime(struct task_struct *p);
 #define PF_MEMALLOC     0x00000800      /* Allocating memory */
 #define PF_FLUSHER      0x00001000      /* responsible for disk writeback */
 #define PF_USED_MATH    0x00002000      /* if unset the fpu must be initialized before use */
+#define PF_FREEZING     0x00004000      /* freeze in progress. do not account to load */
 #define PF_NOFREEZE     0x00008000      /* this thread should not be frozen */
 #define PF_FROZEN       0x00010000      /* frozen for system suspend */
 #define PF_FSTRANS      0x00020000      /* inside a filesystem transaction */
diff --git a/include/linux/security.h b/include/linux/security.h
index 5eff459b3833..1f16eea2017b 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -28,6 +28,7 @@
 #include <linux/resource.h>
 #include <linux/sem.h>
 #include <linux/shm.h>
+#include <linux/mm.h> /* PAGE_ALIGN */
 #include <linux/msg.h>
 #include <linux/sched.h>
 #include <linux/key.h>
@@ -66,6 +67,9 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name,
 extern int cap_inode_removexattr(struct dentry *dentry, const char *name);
 extern int cap_inode_need_killpriv(struct dentry *dentry);
 extern int cap_inode_killpriv(struct dentry *dentry);
+extern int cap_file_mmap(struct file *file, unsigned long reqprot,
+                         unsigned long prot, unsigned long flags,
+                         unsigned long addr, unsigned long addr_only);
 extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags);
 extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
                           unsigned long arg4, unsigned long arg5);
@@ -92,6 +96,7 @@ extern int cap_netlink_send(struct sock *sk, struct sk_buff *skb);
 extern int cap_netlink_recv(struct sk_buff *skb, int cap);
 
 extern unsigned long mmap_min_addr;
+extern unsigned long dac_mmap_min_addr;
 /*
  * Values used in the task_security_ops calls
  */
@@ -116,6 +121,21 @@ struct request_sock;
 #define LSM_UNSAFE_PTRACE       2
 #define LSM_UNSAFE_PTRACE_CAP   4
 
+/*
+ * If a hint addr is less than mmap_min_addr change hint to be as
+ * low as possible but still greater than mmap_min_addr
+ */
+static inline unsigned long round_hint_to_min(unsigned long hint)
+{
+        hint &= PAGE_MASK;
+        if (((void *)hint != NULL) &&
+            (hint < mmap_min_addr))
+                return PAGE_ALIGN(mmap_min_addr);
+        return hint;
+}
+extern int mmap_min_addr_handler(struct ctl_table *table, int write, struct file *filp,
+                                 void __user *buffer, size_t *lenp, loff_t *ppos);
+
 #ifdef CONFIG_SECURITY
 
 struct security_mnt_opts {
@@ -2197,9 +2217,7 @@ static inline int security_file_mmap(struct file *file, unsigned long reqprot,
                                      unsigned long addr,
                                      unsigned long addr_only)
 {
-        if ((addr < mmap_min_addr) && !capable(CAP_SYS_RAWIO))
-                return -EACCES;
-        return 0;
+        return cap_file_mmap(file, reqprot, prot, flags, addr, addr_only);
 }
 
 static inline int security_file_mprotect(struct vm_area_struct *vma,
diff --git a/include/linux/tty.h b/include/linux/tty.h
index 1488d8c81aac..e8c6c9136c97 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -394,6 +394,7 @@ extern void __do_SAK(struct tty_struct *tty);
 extern void disassociate_ctty(int priv);
 extern void no_tty(void);
 extern void tty_flip_buffer_push(struct tty_struct *tty);
+extern void tty_flush_to_ldisc(struct tty_struct *tty);
 extern void tty_buffer_free_all(struct tty_struct *tty);
 extern void tty_buffer_flush(struct tty_struct *tty);
 extern void tty_buffer_init(struct tty_struct *tty);
diff --git a/include/linux/tty_ldisc.h b/include/linux/tty_ldisc.h
index 40f38d896777..0c4ee9b88f85 100644
--- a/include/linux/tty_ldisc.h
+++ b/include/linux/tty_ldisc.h
@@ -144,7 +144,7 @@ struct tty_ldisc_ops {
 
 struct tty_ldisc {
         struct tty_ldisc_ops *ops;
-        int refcount;
+        atomic_t users;
 };
 
 #define TTY_LDISC_MAGIC 0x5403
diff --git a/include/linux/ucb1400.h b/include/linux/ucb1400.h
index ed889f4168f3..ae779bb8cc0f 100644
--- a/include/linux/ucb1400.h
+++ b/include/linux/ucb1400.h
@@ -73,6 +73,10 @@
 
 #define UCB_ADC_DATA            0x68
 #define UCB_ADC_DAT_VALID       (1 << 15)
+
+#define UCB_FCSR                0x6c
+#define UCB_FCSR_AVE            (1 << 12)
+
 #define UCB_ADC_DAT_MASK        0x3ff
 
 #define UCB_ID                  0x7e
diff --git a/include/linux/uio.h b/include/linux/uio.h
index b7fe13883bdb..98c114323a8b 100644
--- a/include/linux/uio.h
+++ b/include/linux/uio.h
@@ -19,15 +19,6 @@ struct iovec
         __kernel_size_t iov_len; /* Must be size_t (1003.1g) */
 };
 
-#ifdef __KERNEL__
-
-struct kvec {
-        void *iov_base; /* and that should *never* hold a userland pointer */
-        size_t iov_len;
-};
-
-#endif
-
 /*
  *      UIO_MAXIOV shall be at least 16 1003.1g (5.4.1.1)
  */
@@ -35,6 +26,13 @@ struct kvec {
 #define UIO_FASTIOV     8
 #define UIO_MAXIOV      1024
 
+#ifdef __KERNEL__
+
+struct kvec {
+        void *iov_base; /* and that should *never* hold a userland pointer */
+        size_t iov_len;
+};
+
 /*
  * Total number of bytes covered by an iovec.
  *
@@ -53,5 +51,6 @@ static inline size_t iov_length(const struct iovec *iov, unsigned long nr_segs)
 }
 
 unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to);
+#endif
 
 #endif
diff --git a/include/linux/videodev2.h b/include/linux/videodev2.h
index 95846d988011..74f16876f38d 100644
--- a/include/linux/videodev2.h
+++ b/include/linux/videodev2.h
@@ -338,6 +338,7 @@ struct v4l2_pix_format {
 /*  Vendor-specific formats   */
 #define V4L2_PIX_FMT_WNVA     v4l2_fourcc('W', 'N', 'V', 'A') /* Winnov hw compress */
 #define V4L2_PIX_FMT_SN9C10X  v4l2_fourcc('S', '9', '1', '0') /* SN9C10x compression */
+#define V4L2_PIX_FMT_SN9C20X_I420 v4l2_fourcc('S', '9', '2', '0') /* SN9C20x YUV 4:2:0 */
 #define V4L2_PIX_FMT_PWC1     v4l2_fourcc('P', 'W', 'C', '1') /* pwc older webcam */
 #define V4L2_PIX_FMT_PWC2     v4l2_fourcc('P', 'W', 'C', '2') /* pwc newer webcam */
 #define V4L2_PIX_FMT_ET61X251 v4l2_fourcc('E', '6', '2', '5') /* ET61X251 compression */
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
index be7d255fc7cf..8dab9f2b8832 100644
--- a/include/linux/virtio_blk.h
+++ b/include/linux/virtio_blk.h
@@ -20,8 +20,7 @@
 
 #define VIRTIO_BLK_ID_BYTES     (sizeof(__u16[256]))    /* IDENTIFY DATA */
 
-struct virtio_blk_config
-{
+struct virtio_blk_config {
         /* The capacity (in 512-byte sectors). */
         __u64 capacity;
         /* The maximum segment size (if VIRTIO_BLK_F_SIZE_MAX) */
@@ -50,8 +49,7 @@ struct virtio_blk_config
 #define VIRTIO_BLK_T_BARRIER    0x80000000
 
 /* This is the first element of the read scatter-gather list. */
-struct virtio_blk_outhdr
-{
+struct virtio_blk_outhdr {
         /* VIRTIO_BLK_T* */
         __u32 type;
         /* io priority. */
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index 99f514575f6a..e547e3c8ee9a 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -79,8 +79,7 @@
  *      the dev->feature bits if it wants.
  */
 typedef void vq_callback_t(struct virtqueue *);
-struct virtio_config_ops
-{
+struct virtio_config_ops {
         void (*get)(struct virtio_device *vdev, unsigned offset,
                     void *buf, unsigned len);
         void (*set)(struct virtio_device *vdev, unsigned offset,
diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 9c543d6ac535..d8dd539c9f48 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -31,8 +31,7 @@
 
 #define VIRTIO_NET_S_LINK_UP    1       /* Link is up */
 
-struct virtio_net_config
-{
+struct virtio_net_config {
         /* The config defining mac address (if VIRTIO_NET_F_MAC) */
         __u8 mac[6];
         /* See VIRTIO_NET_F_STATUS and VIRTIO_NET_S_* above */
@@ -41,8 +40,7 @@ struct virtio_net_config
 
 /* This is the first element of the scatter-gather list.  If you don't
  * specify GSO or CSUM features, you can simply ignore the header. */
-struct virtio_net_hdr
-{
+struct virtio_net_hdr {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM     1       // Use csum_start, csum_offset
         __u8 flags;
 #define VIRTIO_NET_HDR_GSO_NONE         0       // Not a GSO frame
diff --git a/include/linux/virtio_ring.h b/include/linux/virtio_ring.h
index 693e0ec5afa6..e4d144b132b5 100644
--- a/include/linux/virtio_ring.h
+++ b/include/linux/virtio_ring.h
@@ -30,8 +30,7 @@
 #define VIRTIO_RING_F_INDIRECT_DESC     28
 
 /* Virtio ring descriptors: 16 bytes.  These can chain together via "next". */
-struct vring_desc
-{
+struct vring_desc {
         /* Address (guest-physical). */
         __u64 addr;
         /* Length. */
@@ -42,24 +41,21 @@ struct vring_desc
         __u16 next;
 };
 
-struct vring_avail
-{
+struct vring_avail {
         __u16 flags;
         __u16 idx;
         __u16 ring[];
 };
 
 /* u32 is used here for ids for padding reasons. */
-struct vring_used_elem
-{
+struct vring_used_elem {
         /* Index of start of used descriptor chain. */
         __u32 id;
         /* Total length of the descriptor chain which was used (written to) */
         __u32 len;
 };
 
-struct vring_used
-{
+struct vring_used {
         __u16 flags;
         __u16 idx;
         struct vring_used_elem ring[];
diff --git a/include/linux/wait.h b/include/linux/wait.h
index 6788e1a4d4ca..cf3c2f5dba51 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -77,7 +77,14 @@ struct task_struct;
 #define __WAIT_BIT_KEY_INITIALIZER(word, bit)                           \
         { .flags = word, .bit_nr = bit, }
 
-extern void init_waitqueue_head(wait_queue_head_t *q);
+extern void __init_waitqueue_head(wait_queue_head_t *q, struct lock_class_key *);
+
+#define init_waitqueue_head(q)                          \
+        do {                                            \
+                static struct lock_class_key __key;     \
+                                                        \
+                __init_waitqueue_head((q), &__key);     \
+        } while (0)
 
 #ifdef CONFIG_LOCKDEP
 # define __WAIT_QUEUE_HEAD_INIT_ONSTACK(name) \
diff --git a/include/media/v4l2-chip-ident.h b/include/media/v4l2-chip-ident.h
index 11a4a2d3e364..94e908c0d7a0 100644
--- a/include/media/v4l2-chip-ident.h
+++ b/include/media/v4l2-chip-ident.h
@@ -60,6 +60,10 @@ enum {
         V4L2_IDENT_OV7670 = 250,
         V4L2_IDENT_OV7720 = 251,
         V4L2_IDENT_OV7725 = 252,
+        V4L2_IDENT_OV7660 = 253,
+        V4L2_IDENT_OV9650 = 254,
+        V4L2_IDENT_OV9655 = 255,
+        V4L2_IDENT_SOI968 = 256,
 
         /* module saa7146: reserved range 300-309 */
         V4L2_IDENT_SAA7146 = 300,
@@ -161,6 +165,9 @@ enum {
         /* module tw9910: just ident 9910 */
         V4L2_IDENT_TW9910 = 9910,
 
+        /* module sn9c20x: just ident 10000 */
+        V4L2_IDENT_SN9C20X = 10000,
+
         /* module msp3400: reserved range 34000-34999 and 44000-44999 */
         V4L2_IDENT_MSPX4XX  = 34000, /* generic MSPX4XX identifier, only
                                         use internally (tveeprom.c). */
@@ -237,6 +244,11 @@ enum {
         V4L2_IDENT_MT9V022IX7ATC        = 45010, /* No way to detect "normal" I77ATx */
         V4L2_IDENT_MT9V022IX7ATM        = 45015, /* and "lead free" IA7ATx chips */
         V4L2_IDENT_MT9T031              = 45020,
+        V4L2_IDENT_MT9V111              = 45031,
+        V4L2_IDENT_MT9V112              = 45032,
+
+        /* HV7131R CMOS sensor: just ident 46000 */
+        V4L2_IDENT_HV7131R              = 46000,
 
         /* module cs53132a: just ident 53132 */
         V4L2_IDENT_CS53l32A = 53132,
diff --git a/include/net/act_api.h b/include/net/act_api.h
index 565eed8fe496..c05fd717c588 100644
--- a/include/net/act_api.h
+++ b/include/net/act_api.h
@@ -16,7 +16,7 @@ struct tcf_common {
         u32                             tcfc_capab;
         int                             tcfc_action;
         struct tcf_t                    tcfc_tm;
-        struct gnet_stats_basic         tcfc_bstats;
+        struct gnet_stats_basic_packed  tcfc_bstats;
         struct gnet_stats_queue         tcfc_qstats;
         struct gnet_stats_rate_est      tcfc_rate_est;
         spinlock_t                      tcfc_lock;
diff --git a/include/net/bluetooth/rfcomm.h b/include/net/bluetooth/rfcomm.h
index 80072611d26a..c274993234e3 100644
--- a/include/net/bluetooth/rfcomm.h
+++ b/include/net/bluetooth/rfcomm.h
@@ -355,7 +355,17 @@ struct rfcomm_dev_list_req {
 };
 
 int  rfcomm_dev_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
+
+#ifdef CONFIG_BT_RFCOMM_TTY
 int  rfcomm_init_ttys(void);
 void rfcomm_cleanup_ttys(void);
-
+#else
+static inline int rfcomm_init_ttys(void)
+{
+        return 0;
+}
+static inline void rfcomm_cleanup_ttys(void)
+{
+}
+#endif
 #endif /* __RFCOMM_H */
diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h
index 1a21895b732b..d1892d66701a 100644
--- a/include/net/cfg80211.h
+++ b/include/net/cfg80211.h
@@ -979,6 +979,10 @@ struct cfg80211_ops {
  *      channels at a later time. This can be used for devices which do not
  *      have calibration information gauranteed for frequencies or settings
  *      outside of its regulatory domain.
+ * @disable_beacon_hints: enable this if your driver needs to ensure that
+ *      passive scan flags and beaconing flags may not be lifted by cfg80211
+ *      due to regulatory beacon hints. For more information on beacon
+ *      hints read the documenation for regulatory_hint_found_beacon()
  * @reg_notifier: the driver's regulatory notification callback
  * @regd: the driver's regulatory domain, if one was requested via
  *      the regulatory_hint() API. This can be used by the driver
@@ -1004,6 +1008,7 @@ struct wiphy {
 
         bool custom_regulatory;
         bool strict_regulatory;
+        bool disable_beacon_hints;
 
         enum cfg80211_signal_type signal_type;
 
diff --git a/include/net/gen_stats.h b/include/net/gen_stats.h
index d136b5240ef2..c1488553e349 100644
--- a/include/net/gen_stats.h
+++ b/include/net/gen_stats.h
@@ -28,7 +28,7 @@ extern int gnet_stats_start_copy_compat(struct sk_buff *skb, int type,
                                         spinlock_t *lock, struct gnet_dump *d);
 
 extern int gnet_stats_copy_basic(struct gnet_dump *d,
-                                 struct gnet_stats_basic *b);
+                                 struct gnet_stats_basic_packed *b);
 extern int gnet_stats_copy_rate_est(struct gnet_dump *d,
                                     struct gnet_stats_rate_est *r);
 extern int gnet_stats_copy_queue(struct gnet_dump *d,
@@ -37,14 +37,14 @@ extern int gnet_stats_copy_app(struct gnet_dump *d, void *st, int len);
 
 extern int gnet_stats_finish_copy(struct gnet_dump *d);
 
-extern int gen_new_estimator(struct gnet_stats_basic *bstats,
+extern int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
                              struct gnet_stats_rate_est *rate_est,
                              spinlock_t *stats_lock, struct nlattr *opt);
-extern void gen_kill_estimator(struct gnet_stats_basic *bstats,
+extern void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
                                struct gnet_stats_rate_est *rate_est);
-extern int gen_replace_estimator(struct gnet_stats_basic *bstats,
+extern int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
                                  struct gnet_stats_rate_est *rate_est,
                                  spinlock_t *stats_lock, struct nlattr *opt);
-extern bool gen_estimator_active(const struct gnet_stats_basic *bstats,
+extern bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
                                  const struct gnet_stats_rate_est *rate_est);
 #endif
diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h
index 65d594dffbff..ddbf37e19616 100644
--- a/include/net/netfilter/xt_rateest.h
+++ b/include/net/netfilter/xt_rateest.h
@@ -8,7 +8,7 @@ struct xt_rateest {
         spinlock_t                      lock;
         struct gnet_estimator           params;
         struct gnet_stats_rate_est      rstats;
-        struct gnet_stats_basic         bstats;
+        struct gnet_stats_basic_packed  bstats;
 };
 
 extern struct xt_rateest *xt_rateest_lookup(const char *name);
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 82a3191375f5..7eafb8d54470 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -61,8 +61,8 @@ psched_tdiff_bounded(psched_time_t tv1, psched_time_t tv2, psched_time_t bound)
 }
 
 struct qdisc_watchdog {
-        struct hrtimer  timer;
-        struct Qdisc    *qdisc;
+        struct tasklet_hrtimer  timer;
+        struct Qdisc            *qdisc;
 };
 
 extern void qdisc_watchdog_init(struct qdisc_watchdog *wd, struct Qdisc *qdisc);
diff --git a/include/net/rose.h b/include/net/rose.h
index cbd5364b2c8a..5ba9f02731eb 100644
--- a/include/net/rose.h
+++ b/include/net/rose.h
@@ -156,7 +156,7 @@ extern int  sysctl_rose_maximum_vcs;
 extern int  sysctl_rose_window_size;
 extern int  rosecmp(rose_address *, rose_address *);
 extern int  rosecmpm(rose_address *, rose_address *, unsigned short);
-extern const char *rose2asc(const rose_address *);
+extern char *rose2asc(char *buf, const rose_address *);
 extern struct sock *rose_find_socket(unsigned int, struct rose_neigh *);
 extern void rose_kill_by_neigh(struct rose_neigh *);
 extern unsigned int rose_new_lci(struct rose_neigh *);
diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index 964ffa0d8815..5482e9582f55 100644
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -72,7 +72,7 @@ struct Qdisc
          */
         unsigned long           state;
         struct sk_buff_head     q;
-        struct gnet_stats_basic bstats;
+        struct gnet_stats_basic_packed bstats;
         struct gnet_stats_queue qstats;
 };
 
diff --git a/include/net/sock.h b/include/net/sock.h
index 2c0da9239b95..950409dcec3d 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -104,15 +104,15 @@ struct net;
 
 /**
  *      struct sock_common - minimal network layer representation of sockets
+ *      @skc_node: main hash linkage for various protocol lookup tables
+ *      @skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
+ *      @skc_refcnt: reference count
+ *      @skc_hash: hash value used with various protocol lookup tables
  *      @skc_family: network address family
  *      @skc_state: Connection state
  *      @skc_reuse: %SO_REUSEADDR setting
  *      @skc_bound_dev_if: bound device index if != 0
- *      @skc_node: main hash linkage for various protocol lookup tables
- *      @skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
  *      @skc_bind_node: bind hash linkage for various protocol lookup tables
- *      @skc_refcnt: reference count
- *      @skc_hash: hash value used with various protocol lookup tables
  *      @skc_prot: protocol handlers inside a network family
  *      @skc_net: reference to the network namespace of this socket
  *
@@ -120,17 +120,21 @@ struct net;
  *      for struct sock and struct inet_timewait_sock.
  */
 struct sock_common {
-        unsigned short          skc_family;
-        volatile unsigned char  skc_state;
-        unsigned char           skc_reuse;
-        int                     skc_bound_dev_if;
+        /*
+         * first fields are not copied in sock_copy()
+         */
         union {
                 struct hlist_node       skc_node;
                 struct hlist_nulls_node skc_nulls_node;
         };
-        struct hlist_node       skc_bind_node;
         atomic_t                skc_refcnt;
+
         unsigned int            skc_hash;
+        unsigned short          skc_family;
+        volatile unsigned char  skc_state;
+        unsigned char           skc_reuse;
+        int                     skc_bound_dev_if;
+        struct hlist_node       skc_bind_node;
         struct proto            *skc_prot;
 #ifdef CONFIG_NET_NS
         struct net              *skc_net;
@@ -208,15 +212,17 @@ struct sock {
          * don't add nothing before this first member (__sk_common) --acme
          */
         struct sock_common      __sk_common;
+#define sk_node                 __sk_common.skc_node
+#define sk_nulls_node           __sk_common.skc_nulls_node
+#define sk_refcnt               __sk_common.skc_refcnt
+
+#define sk_copy_start           __sk_common.skc_hash
+#define sk_hash                 __sk_common.skc_hash
 #define sk_family               __sk_common.skc_family
 #define sk_state                __sk_common.skc_state
 #define sk_reuse                __sk_common.skc_reuse
 #define sk_bound_dev_if         __sk_common.skc_bound_dev_if
-#define sk_node                 __sk_common.skc_node
-#define sk_nulls_node           __sk_common.skc_nulls_node
 #define sk_bind_node            __sk_common.skc_bind_node
-#define sk_refcnt               __sk_common.skc_refcnt
-#define sk_hash                 __sk_common.skc_hash
 #define sk_prot                 __sk_common.skc_prot
 #define sk_net                  __sk_common.skc_net
         kmemcheck_bitfield_begin(flags);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 19f4150f4d4d..88af84306471 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1425,6 +1425,11 @@ struct tcp_request_sock_ops {
 #ifdef CONFIG_TCP_MD5SIG
         struct tcp_md5sig_key   *(*md5_lookup) (struct sock *sk,
                                                 struct request_sock *req);
+        int                     (*calc_md5_hash) (char *location,
+                                                  struct tcp_md5sig_key *md5,
+                                                  struct sock *sk,
+                                                  struct request_sock *req,
+                                                  struct sk_buff *skb);
 #endif
 };
 
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1867553c61e5..f64fbaae781a 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -144,6 +144,9 @@
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
 
+#undef TP_perf_assign
+#define TP_perf_assign(args...)
+
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, func, print)            \
 static int                                                              \
@@ -345,6 +348,56 @@ static inline int ftrace_get_offsets_##call(				\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#ifdef CONFIG_EVENT_PROFILE
+
+/*
+ * Generate the functions needed for tracepoint perf_counter support.
+ *
+ * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later
+ *
+ * static int ftrace_profile_enable_<call>(struct ftrace_event_call *event_call)
+ * {
+ *      int ret = 0;
+ *
+ *      if (!atomic_inc_return(&event_call->profile_count))
+ *              ret = register_trace_<call>(ftrace_profile_<call>);
+ *
+ *      return ret;
+ * }
+ *
+ * static void ftrace_profile_disable_<call>(struct ftrace_event_call *event_call)
+ * {
+ *      if (atomic_add_negative(-1, &event->call->profile_count))
+ *              unregister_trace_<call>(ftrace_profile_<call>);
+ * }
+ *
+ */
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)          \
+                                                                        \
+static void ftrace_profile_##call(proto);                               \
+                                                                        \
+static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
+{                                                                       \
+        int ret = 0;                                                    \
+                                                                        \
+        if (!atomic_inc_return(&event_call->profile_count))             \
+                ret = register_trace_##call(ftrace_profile_##call);     \
+                                                                        \
+        return ret;                                                     \
+}                                                                       \
+                                                                        \
+static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
+{                                                                       \
+        if (atomic_add_negative(-1, &event_call->profile_count))        \
+                unregister_trace_##call(ftrace_profile_##call);         \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#endif
+
 /*
  * Stage 4 of the trace events.
  *
@@ -447,28 +500,6 @@ static inline int ftrace_get_offsets_##call(				\
 #define TP_FMT(fmt, args...)    fmt "\n", ##args
 
 #ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args)                               \
-static void ftrace_profile_##call(proto)                                \
-{                                                                       \
-        extern void perf_tpcounter_event(int);                          \
-        perf_tpcounter_event(event_##call.id);                          \
-}                                                                       \
-                                                                        \
-static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
-{                                                                       \
-        int ret = 0;                                                    \
-                                                                        \
-        if (!atomic_inc_return(&event_call->profile_count))             \
-                ret = register_trace_##call(ftrace_profile_##call);     \
-                                                                        \
-        return ret;                                                     \
-}                                                                       \
-                                                                        \
-static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
-{                                                                       \
-        if (atomic_add_negative(-1, &event_call->profile_count))        \
-                unregister_trace_##call(ftrace_profile_##call);         \
-}
 
 #define _TRACE_PROFILE_INIT(call)                                       \
         .profile_count = ATOMIC_INIT(-1),                               \
@@ -476,7 +507,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
         .profile_disable = ftrace_profile_disable_##call,
 
 #else
-#define _TRACE_PROFILE(call, proto, args)
 #define _TRACE_PROFILE_INIT(call)
 #endif
 
@@ -502,7 +532,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, assign, print)          \
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))                       \
                                                                         \
 static struct ftrace_event_call event_##call;                           \
                                                                         \
@@ -586,6 +615,110 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef _TRACE_PROFILE
+/*
+ * Define the insertion callback to profile events
+ *
+ * The job is very similar to ftrace_raw_event_<call> except that we don't
+ * insert in the ring buffer but in a perf counter.
+ *
+ * static void ftrace_profile_<call>(proto)
+ * {
+ *      struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
+ *      struct ftrace_event_call *event_call = &event_<call>;
+ *      extern void perf_tpcounter_event(int, u64, u64, void *, int);
+ *      struct ftrace_raw_##call *entry;
+ *      u64 __addr = 0, __count = 1;
+ *      unsigned long irq_flags;
+ *      int __entry_size;
+ *      int __data_size;
+ *      int pc;
+ *
+ *      local_save_flags(irq_flags);
+ *      pc = preempt_count();
+ *
+ *      __data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
+ *      // Below we want to get the aligned size by taking into account
+ *      // the u32 field that will later store the buffer size
+ *      __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ *                           sizeof(u64));
+ *      __entry_size -= sizeof(u32);
+ *
+ *      do {
+ *              char raw_data[__entry_size]; <- allocate our sample in the stack
+ *              struct trace_entry *ent;
+ *
+ *              zero dead bytes from alignment to avoid stack leak to userspace:
+ *
+ *              *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
+ *              entry = (struct ftrace_raw_<call> *)raw_data;
+ *              ent = &entry->ent;
+ *              tracing_generic_entry_update(ent, irq_flags, pc);
+ *              ent->type = event_call->id;
+ *
+ *              <tstruct> <- do some jobs with dynamic arrays
+ *
+ *              <assign>  <- affect our values
+ *
+ *              perf_tpcounter_event(event_call->id, __addr, __count, entry,
+ *                           __entry_size);  <- submit them to perf counter
+ *      } while (0);
+ *
+ * }
+ */
+
+#ifdef CONFIG_EVENT_PROFILE
+
+#undef __perf_addr
+#define __perf_addr(a) __addr = (a)
+
+#undef __perf_count
+#define __perf_count(c) __count = (c)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)          \
+static void ftrace_profile_##call(proto)                                \
+{                                                                       \
+        struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+        struct ftrace_event_call *event_call = &event_##call;           \
+        extern void perf_tpcounter_event(int, u64, u64, void *, int);   \
+        struct ftrace_raw_##call *entry;                                \
+        u64 __addr = 0, __count = 1;                                    \
+        unsigned long irq_flags;                                        \
+        int __entry_size;                                               \
+        int __data_size;                                                \
+        int pc;                                                         \
+                                                                        \
+        local_save_flags(irq_flags);                                    \
+        pc = preempt_count();                                           \
+                                                                        \
+        __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+        __entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+                             sizeof(u64));                              \
+        __entry_size -= sizeof(u32);                                    \
+                                                                        \
+        do {                                                            \
+                char raw_data[__entry_size];                            \
+                struct trace_entry *ent;                                \
+                                                                        \
+                *(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL; \
+                entry = (struct ftrace_raw_##call *)raw_data;           \
+                ent = &entry->ent;                                      \
+                tracing_generic_entry_update(ent, irq_flags, pc);       \
+                ent->type = event_call->id;                             \
+                                                                        \
+                tstruct                                                 \
+                                                                        \
+                { assign; }                                             \
+                                                                        \
+                perf_tpcounter_event(event_call->id, __addr, __count, entry,\
+                             __entry_size);                             \
+        } while (0);                                                    \
+                                                                        \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#endif /* CONFIG_EVENT_PROFILE */
+
 #undef _TRACE_PROFILE_INIT