[SCSI] Merge branch 'linus'

Conflicts:
	drivers/message/fusion/mptsas.c

fixed up conflict between req->data_len accessors and mptsas driver updates.

Signed-off-by: James Bottomley <James.Bottomley@HansenPartnership.com>

131 files changed, 4576 insertions, 1117 deletions

diff --git a/include/Kbuild b/include/Kbuild
index d8c3e3cbf416..fe36accd4328 100644
--- a/include/Kbuild
+++ b/include/Kbuild
@@ -8,3 +8,4 @@ header-y += mtd/
 header-y += rdma/
 header-y += video/
 header-y += drm/
+header-y += xen/
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 3673a13b6703..81d3be459efb 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -134,7 +134,7 @@ static inline long atomic_long_add_unless(atomic_long_t *l, long a, long u)
 #define atomic_long_cmpxchg(l, old, new) \
         (atomic64_cmpxchg((atomic64_t *)(l), (old), (new)))
 #define atomic_long_xchg(v, new) \
-        (atomic64_xchg((atomic64_t *)(l), (new)))
+        (atomic64_xchg((atomic64_t *)(v), (new)))
 
 #else  /*  BITS_PER_LONG == 64  */
 
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 8e6d0ca70aba..e410f602cab1 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -280,17 +280,18 @@ static inline void ptep_modify_prot_commit(struct mm_struct *mm,
 #endif
 
 /*
- * A facility to provide batching of the reload of page tables with the
- * actual context switch code for paravirtualized guests.  By convention,
- * only one of the lazy modes (CPU, MMU) should be active at any given
- * time, entry should never be nested, and entry and exits should always
- * be paired.  This is for sanity of maintaining and reasoning about the
- * kernel code.
+ * A facility to provide batching of the reload of page tables and
+ * other process state with the actual context switch code for
+ * paravirtualized guests.  By convention, only one of the batched
+ * update (lazy) modes (CPU, MMU) should be active at any given time,
+ * entry should never be nested, and entry and exits should always be
+ * paired.  This is for sanity of maintaining and reasoning about the
+ * kernel code.  In this case, the exit (end of the context switch) is
+ * in architecture-specific code, and so doesn't need a generic
+ * definition.
  */
-#ifndef __HAVE_ARCH_ENTER_LAZY_CPU_MODE
-#define arch_enter_lazy_cpu_mode()      do {} while (0)
-#define arch_leave_lazy_cpu_mode()      do {} while (0)
-#define arch_flush_lazy_cpu_mode()      do {} while (0)
+#ifndef __HAVE_ARCH_START_CONTEXT_SWITCH
+#define arch_start_context_switch(prev) do {} while (0)
 #endif
 
 #ifndef __HAVE_PFNMAP_TRACKING
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 89853bcd27a6..f1736ca7922c 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -63,7 +63,7 @@
 #define BRANCH_PROFILE()
 #endif
 
-#ifdef CONFIG_EVENT_TRACER
+#ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS() VMLINUX_SYMBOL(__start_ftrace_events) = .;      \
                         *(_ftrace_events)                               \
                         VMLINUX_SYMBOL(__stop_ftrace_events) = .;
diff --git a/include/drm/drmP.h b/include/drm/drmP.h
index c8c422151431..b84d8ae35e6f 100644
--- a/include/drm/drmP.h
+++ b/include/drm/drmP.h
@@ -1519,6 +1519,30 @@ static __inline__ void *drm_calloc(size_t nmemb, size_t size, int area)
 {
         return kcalloc(nmemb, size, GFP_KERNEL);
 }
+
+static __inline__ void *drm_calloc_large(size_t nmemb, size_t size)
+{
+        u8 *addr;
+
+        if (size <= PAGE_SIZE)
+            return kcalloc(nmemb, size, GFP_KERNEL);
+
+        addr = vmalloc(nmemb * size);
+        if (!addr)
+                return NULL;
+
+        memset(addr, 0, nmemb * size);
+
+        return addr;
+}
+
+static __inline void drm_free_large(void *ptr)
+{
+        if (!is_vmalloc_addr(ptr))
+                return kfree(ptr);
+
+        vfree(ptr);
+}
 #else
 extern void *drm_alloc(size_t size, int area);
 extern void drm_free(void *pt, size_t size, int area);
diff --git a/include/drm/drm_crtc.h b/include/drm/drm_crtc.h
index 3c1924c010e8..7300fb866767 100644
--- a/include/drm/drm_crtc.h
+++ b/include/drm/drm_crtc.h
@@ -471,6 +471,9 @@ struct drm_connector {
         u32 property_ids[DRM_CONNECTOR_MAX_PROPERTY];
         uint64_t property_values[DRM_CONNECTOR_MAX_PROPERTY];
 
+        /* requested DPMS state */
+        int dpms;
+
         void *helper_private;
 
         uint32_t encoder_ids[DRM_CONNECTOR_MAX_ENCODER];
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index ec073d8288d9..6769ff6c1bc0 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -99,6 +99,8 @@ extern bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
                                      struct drm_framebuffer *old_fb);
 extern bool drm_helper_crtc_in_use(struct drm_crtc *crtc);
 
+extern void drm_helper_connector_dpms(struct drm_connector *connector, int mode);
+
 extern int drm_helper_mode_fill_fb_struct(struct drm_framebuffer *fb,
                                           struct drm_mode_fb_cmd *mode_cmd);
 
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 3f0eaa397ef5..b3afd2219ad2 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -135,6 +135,7 @@ header-y += posix_types.h
 header-y += ppdev.h
 header-y += prctl.h
 header-y += qnxtypes.h
+header-y += qnx4_fs.h
 header-y += radeonfb.h
 header-y += raw.h
 header-y += resource.h
@@ -308,7 +309,6 @@ unifdef-y += poll.h
 unifdef-y += ppp_defs.h
 unifdef-y += ppp-comp.h
 unifdef-y += ptrace.h
-unifdef-y += qnx4_fs.h
 unifdef-y += quota.h
 unifdef-y += random.h
 unifdef-y += irqnr.h
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 88be890ee3c7..51b4b0a5ce8c 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -119,7 +119,7 @@ extern int pci_mmcfg_config_num;
 extern int sbf_port;
 extern unsigned long acpi_realmode_flags;
 
-int acpi_register_gsi (u32 gsi, int triggering, int polarity);
+int acpi_register_gsi (struct device *dev, u32 gsi, int triggering, int polarity);
 int acpi_gsi_to_irq (u32 gsi, unsigned int *irq);
 
 #ifdef CONFIG_X86_IO_APIC
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 51e6e54b2aa1..9b93cafa82a0 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -28,7 +28,7 @@ struct amba_id {
 
 struct amba_driver {
         struct device_driver    drv;
-        int                     (*probe)(struct amba_device *, void *);
+        int                     (*probe)(struct amba_device *, struct amba_id *);
         int                     (*remove)(struct amba_device *);
         void                    (*shutdown)(struct amba_device *);
         int                     (*suspend)(struct amba_device *, pm_message_t);
diff --git a/include/linux/amba/serial.h b/include/linux/amba/serial.h
index 48ee32a18ac5..64a982ea5d5f 100644
--- a/include/linux/amba/serial.h
+++ b/include/linux/amba/serial.h
@@ -159,6 +159,7 @@
 #define UART01x_FR_MODEM_ANY    (UART01x_FR_DCD|UART01x_FR_DSR|UART01x_FR_CTS)
 
 #ifndef __ASSEMBLY__
+struct amba_device; /* in uncompress this is included but amba/bus.h is not */
 struct amba_pl010_data {
         void (*set_mctrl)(struct amba_device *dev, void __iomem *base, unsigned int mctrl);
 };
diff --git a/include/linux/auto_fs.h b/include/linux/auto_fs.h
index 63265852b7d1..7b09c8348fd3 100644
--- a/include/linux/auto_fs.h
+++ b/include/linux/auto_fs.h
@@ -14,13 +14,12 @@
 #ifndef _LINUX_AUTO_FS_H
 #define _LINUX_AUTO_FS_H
 
+#include <linux/types.h>
 #ifdef __KERNEL__
 #include <linux/fs.h>
 #include <linux/limits.h>
-#include <linux/types.h>
 #include <linux/ioctl.h>
 #else
-#include <asm/types.h>
 #include <sys/ioctl.h>
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/bio.h b/include/linux/bio.h
index 7b214fd672a2..12737be58601 100644
--- a/include/linux/bio.h
+++ b/include/linux/bio.h
@@ -218,12 +218,12 @@ struct bio {
 #define bio_sectors(bio)        ((bio)->bi_size >> 9)
 #define bio_empty_barrier(bio)  (bio_barrier(bio) && !bio_has_data(bio) && !bio_discard(bio))
 
-static inline unsigned int bio_cur_sectors(struct bio *bio)
+static inline unsigned int bio_cur_bytes(struct bio *bio)
 {
         if (bio->bi_vcnt)
-                return bio_iovec(bio)->bv_len >> 9;
+                return bio_iovec(bio)->bv_len;
         else /* dataless requests such as discard */
-                return bio->bi_size >> 9;
+                return bio->bi_size;
 }
 
 static inline void *bio_data(struct bio *bio)
@@ -279,7 +279,7 @@ static inline int bio_has_allocated_vec(struct bio *bio)
 #define __BIO_SEG_BOUNDARY(addr1, addr2, mask) \
         (((addr1) | (mask)) == (((addr2) - 1) | (mask)))
 #define BIOVEC_SEG_BOUNDARY(q, b1, b2) \
-        __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, (q)->seg_boundary_mask)
+        __BIO_SEG_BOUNDARY(bvec_to_phys((b1)), bvec_to_phys((b2)) + (b2)->bv_len, queue_segment_boundary((q)))
 #define BIO_SEG_BOUNDARY(q, b1, b2) \
         BIOVEC_SEG_BOUNDARY((q), __BVEC_END((b1)), __BVEC_START((b2)))
 
@@ -506,7 +506,7 @@ static inline int bio_has_data(struct bio *bio)
 }
 
 /*
- * BIO list managment for use by remapping drivers (e.g. DM or MD).
+ * BIO list management for use by remapping drivers (e.g. DM or MD) and loop.
  *
  * A bio_list anchors a singly-linked list of bios chained through the bi_next
  * member of the bio.  The bio_list also caches the last list member to allow
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index b4f71f1a4af7..ebdfde8fe556 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -166,19 +166,9 @@ struct request {
         enum rq_cmd_type_bits cmd_type;
         unsigned long atomic_flags;
 
-        /* Maintain bio traversal state for part by part I/O submission.
-         * hard_* are block layer internals, no driver should touch them!
-         */
-
-        sector_t sector;                /* next sector to submit */
-        sector_t hard_sector;           /* next sector to complete */
-        unsigned long nr_sectors;       /* no. of sectors left to submit */
-        unsigned long hard_nr_sectors;  /* no. of sectors left to complete */
-        /* no. of sectors left to submit in the current segment */
-        unsigned int current_nr_sectors;
-
-        /* no. of sectors left to complete in the current segment */
-        unsigned int hard_cur_sectors;
+        /* the following two fields are internal, NEVER access directly */
+        sector_t __sector;              /* sector cursor */
+        unsigned int __data_len;        /* total data len */
 
         struct bio *bio;
         struct bio *biotail;
@@ -211,8 +201,8 @@ struct request {
 
         unsigned short ioprio;
 
-        void *special;
-        char *buffer;
+        void *special;          /* opaque pointer available for LLD use */
+        char *buffer;           /* kaddr of the current segment if available */
 
         int tag;
         int errors;
@@ -226,10 +216,9 @@ struct request {
         unsigned char __cmd[BLK_MAX_CDB];
         unsigned char *cmd;
 
-        unsigned int data_len;
         unsigned int extra_len; /* length of alignment and padding */
         unsigned int sense_len;
-        void *data;
+        unsigned int resid_len; /* residual count */
         void *sense;
 
         unsigned long deadline;
@@ -318,6 +307,26 @@ struct blk_cmd_filter {
         struct kobject kobj;
 };
 
+struct queue_limits {
+        unsigned long           bounce_pfn;
+        unsigned long           seg_boundary_mask;
+
+        unsigned int            max_hw_sectors;
+        unsigned int            max_sectors;
+        unsigned int            max_segment_size;
+        unsigned int            physical_block_size;
+        unsigned int            alignment_offset;
+        unsigned int            io_min;
+        unsigned int            io_opt;
+
+        unsigned short          logical_block_size;
+        unsigned short          max_hw_segments;
+        unsigned short          max_phys_segments;
+
+        unsigned char           misaligned;
+        unsigned char           no_cluster;
+};
+
 struct request_queue
 {
         /*
@@ -369,7 +378,6 @@ struct request_queue
         /*
          * queue needs bounce pages for pages above this limit
          */
-        unsigned long           bounce_pfn;
         gfp_t                   bounce_gfp;
 
         /*
@@ -398,14 +406,6 @@ struct request_queue
         unsigned int            nr_congestion_off;
         unsigned int            nr_batching;
 
-        unsigned int            max_sectors;
-        unsigned int            max_hw_sectors;
-        unsigned short          max_phys_segments;
-        unsigned short          max_hw_segments;
-        unsigned short          hardsect_size;
-        unsigned int            max_segment_size;
-
-        unsigned long           seg_boundary_mask;
         void                    *dma_drain_buffer;
         unsigned int            dma_drain_size;
         unsigned int            dma_pad_mask;
@@ -415,12 +415,14 @@ struct request_queue
         struct list_head        tag_busy_list;
 
         unsigned int            nr_sorted;
-        unsigned int            in_flight;
+        unsigned int            in_flight[2];
 
         unsigned int            rq_timeout;
         struct timer_list       timeout;
         struct list_head        timeout_list;
 
+        struct queue_limits     limits;
+
         /*
          * sg stuff
          */
@@ -522,6 +524,11 @@ static inline void queue_flag_clear_unlocked(unsigned int flag,
         __clear_bit(flag, &q->queue_flags);
 }
 
+static inline int queue_in_flight(struct request_queue *q)
+{
+        return q->in_flight[0] + q->in_flight[1];
+}
+
 static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 {
         WARN_ON_ONCE(!queue_is_locked(q));
@@ -752,10 +759,17 @@ extern void blk_rq_init(struct request_queue *q, struct request *rq);
 extern void blk_put_request(struct request *);
 extern void __blk_put_request(struct request_queue *, struct request *);
 extern struct request *blk_get_request(struct request_queue *, int, gfp_t);
+extern struct request *blk_make_request(struct request_queue *, struct bio *,
+                                        gfp_t);
 extern void blk_insert_request(struct request_queue *, struct request *, int, void *);
 extern void blk_requeue_request(struct request_queue *, struct request *);
 extern int blk_rq_check_limits(struct request_queue *q, struct request *rq);
 extern int blk_lld_busy(struct request_queue *q);
+extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src,
+                             struct bio_set *bs, gfp_t gfp_mask,
+                             int (*bio_ctr)(struct bio *, struct bio *, void *),
+                             void *data);
+extern void blk_rq_unprep_clone(struct request *rq);
 extern int blk_insert_cloned_request(struct request_queue *q,
                                      struct request *rq);
 extern void blk_plug_device(struct request_queue *);
@@ -768,12 +782,6 @@ extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t,
                          struct scsi_ioctl_command __user *);
 
 /*
- * Temporary export, until SCSI gets fixed up.
- */
-extern int blk_rq_append_bio(struct request_queue *q, struct request *rq,
-                             struct bio *bio);
-
-/*
  * A queue has just exitted congestion.  Note this in the global counter of
  * congested queues, and wake up anyone who was waiting for requests to be
  * put back.
@@ -798,7 +806,6 @@ extern void blk_sync_queue(struct request_queue *q);
 extern void __blk_stop_queue(struct request_queue *q);
 extern void __blk_run_queue(struct request_queue *);
 extern void blk_run_queue(struct request_queue *);
-extern void blk_start_queueing(struct request_queue *);
 extern int blk_rq_map_user(struct request_queue *, struct request *,
                            struct rq_map_data *, void __user *, unsigned long,
                            gfp_t);
@@ -831,41 +838,73 @@ static inline void blk_run_address_space(struct address_space *mapping)
                 blk_run_backing_dev(mapping->backing_dev_info, NULL);
 }
 
-extern void blkdev_dequeue_request(struct request *req);
+/*
+ * blk_rq_pos()         : the current sector
+ * blk_rq_bytes()       : bytes left in the entire request
+ * blk_rq_cur_bytes()   : bytes left in the current segment
+ * blk_rq_sectors()     : sectors left in the entire request
+ * blk_rq_cur_sectors() : sectors left in the current segment
+ */
+static inline sector_t blk_rq_pos(const struct request *rq)
+{
+        return rq->__sector;
+}
+
+static inline unsigned int blk_rq_bytes(const struct request *rq)
+{
+        return rq->__data_len;
+}
+
+static inline int blk_rq_cur_bytes(const struct request *rq)
+{
+        return rq->bio ? bio_cur_bytes(rq->bio) : 0;
+}
+
+static inline unsigned int blk_rq_sectors(const struct request *rq)
+{
+        return blk_rq_bytes(rq) >> 9;
+}
+
+static inline unsigned int blk_rq_cur_sectors(const struct request *rq)
+{
+        return blk_rq_cur_bytes(rq) >> 9;
+}
+
+/*
+ * Request issue related functions.
+ */
+extern struct request *blk_peek_request(struct request_queue *q);
+extern void blk_start_request(struct request *rq);
+extern struct request *blk_fetch_request(struct request_queue *q);
 
 /*
- * blk_end_request() and friends.
- * __blk_end_request() and end_request() must be called with
- * the request queue spinlock acquired.
+ * Request completion related functions.
+ *
+ * blk_update_request() completes given number of bytes and updates
+ * the request without completing it.
+ *
+ * blk_end_request() and friends.  __blk_end_request() must be called
+ * with the request queue spinlock acquired.
  *
  * Several drivers define their own end_request and call
  * blk_end_request() for parts of the original function.
  * This prevents code duplication in drivers.
  */
-extern int blk_end_request(struct request *rq, int error,
-                                unsigned int nr_bytes);
-extern int __blk_end_request(struct request *rq, int error,
-                                unsigned int nr_bytes);
-extern int blk_end_bidi_request(struct request *rq, int error,
-                                unsigned int nr_bytes, unsigned int bidi_bytes);
-extern void end_request(struct request *, int);
-extern int blk_end_request_callback(struct request *rq, int error,
-                                unsigned int nr_bytes,
-                                int (drv_callback)(struct request *));
+extern bool blk_update_request(struct request *rq, int error,
+                               unsigned int nr_bytes);
+extern bool blk_end_request(struct request *rq, int error,
+                            unsigned int nr_bytes);
+extern void blk_end_request_all(struct request *rq, int error);
+extern bool blk_end_request_cur(struct request *rq, int error);
+extern bool __blk_end_request(struct request *rq, int error,
+                              unsigned int nr_bytes);
+extern void __blk_end_request_all(struct request *rq, int error);
+extern bool __blk_end_request_cur(struct request *rq, int error);
+
 extern void blk_complete_request(struct request *);
 extern void __blk_complete_request(struct request *);
 extern void blk_abort_request(struct request *);
 extern void blk_abort_queue(struct request_queue *);
-extern void blk_update_request(struct request *rq, int error,
-                               unsigned int nr_bytes);
-
-/*
- * blk_end_request() takes bytes instead of sectors as a complete size.
- * blk_rq_bytes() returns bytes left to complete in the entire request.
- * blk_rq_cur_bytes() returns bytes left to complete in the current segment.
- */
-extern unsigned int blk_rq_bytes(struct request *rq);
-extern unsigned int blk_rq_cur_bytes(struct request *rq);
 
 /*
  * Access functions for manipulating queue properties
@@ -877,10 +916,20 @@ extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
 extern void blk_queue_max_sectors(struct request_queue *, unsigned int);
+extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_phys_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_hw_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
-extern void blk_queue_hardsect_size(struct request_queue *, unsigned short);
+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_queue_io_min(struct request_queue *q, unsigned int min);
+extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt);
+extern int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
+                            sector_t offset);
+extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
+                              sector_t offset);
 extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b);
 extern void blk_queue_dma_pad(struct request_queue *, unsigned int);
 extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int);
@@ -967,19 +1016,87 @@ extern void blk_set_cmd_filter_defaults(struct blk_cmd_filter *filter);
 
 #define blkdev_entry_to_request(entry) list_entry((entry), struct request, queuelist)
 
-static inline int queue_hardsect_size(struct request_queue *q)
+static inline unsigned long queue_bounce_pfn(struct request_queue *q)
+{
+        return q->limits.bounce_pfn;
+}
+
+static inline unsigned long queue_segment_boundary(struct request_queue *q)
+{
+        return q->limits.seg_boundary_mask;
+}
+
+static inline unsigned int queue_max_sectors(struct request_queue *q)
+{
+        return q->limits.max_sectors;
+}
+
+static inline unsigned int queue_max_hw_sectors(struct request_queue *q)
+{
+        return q->limits.max_hw_sectors;
+}
+
+static inline unsigned short queue_max_hw_segments(struct request_queue *q)
+{
+        return q->limits.max_hw_segments;
+}
+
+static inline unsigned short queue_max_phys_segments(struct request_queue *q)
+{
+        return q->limits.max_phys_segments;
+}
+
+static inline unsigned int queue_max_segment_size(struct request_queue *q)
+{
+        return q->limits.max_segment_size;
+}
+
+static inline unsigned short queue_logical_block_size(struct request_queue *q)
 {
         int retval = 512;
 
-        if (q && q->hardsect_size)
-                retval = q->hardsect_size;
+        if (q && q->limits.logical_block_size)
+                retval = q->limits.logical_block_size;
 
         return retval;
 }
 
-static inline int bdev_hardsect_size(struct block_device *bdev)
+static inline unsigned short bdev_logical_block_size(struct block_device *bdev)
+{
+        return queue_logical_block_size(bdev_get_queue(bdev));
+}
+
+static inline unsigned int queue_physical_block_size(struct request_queue *q)
+{
+        return q->limits.physical_block_size;
+}
+
+static inline unsigned int queue_io_min(struct request_queue *q)
+{
+        return q->limits.io_min;
+}
+
+static inline unsigned int queue_io_opt(struct request_queue *q)
+{
+        return q->limits.io_opt;
+}
+
+static inline int queue_alignment_offset(struct request_queue *q)
+{
+        if (q && q->limits.misaligned)
+                return -1;
+
+        if (q && q->limits.alignment_offset)
+                return q->limits.alignment_offset;
+
+        return 0;
+}
+
+static inline int queue_sector_alignment_offset(struct request_queue *q,
+                                                sector_t sector)
 {
-        return queue_hardsect_size(bdev_get_queue(bdev));
+        return ((sector << 9) - q->limits.alignment_offset)
+                & (q->limits.io_min - 1);
 }
 
 static inline int queue_dma_alignment(struct request_queue *q)
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index d960889e92ef..7e4350ece0f8 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -116,9 +116,9 @@ struct blk_io_trace {
  * The remap event
  */
 struct blk_io_trace_remap {
-        __be32 device;
         __be32 device_from;
-        __be64 sector;
+        __be32 device_to;
+        __be64 sector_from;
 };
 
 enum {
@@ -165,8 +165,9 @@ struct blk_trace {
 
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern int do_blk_trace_setup(struct request_queue *q,
-        char *name, dev_t dev, struct blk_user_trace_setup *buts);
+extern int do_blk_trace_setup(struct request_queue *q, char *name,
+                              dev_t dev, struct block_device *bdev,
+                              struct blk_user_trace_setup *buts);
 extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 
 /**
@@ -193,22 +194,42 @@ extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
                                 void *data, size_t len);
 extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+                           struct block_device *bdev,
                            char __user *arg);
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
+extern int blk_trace_init_sysfs(struct device *dev);
 
 extern struct attribute_group blk_trace_attr_group;
 
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
-#define blk_trace_ioctl(bdev, cmd, arg)         (-ENOTTY)
-#define blk_trace_shutdown(q)                   do { } while (0)
-#define do_blk_trace_setup(q, name, dev, buts)  (-ENOTTY)
-#define blk_add_driver_data(q, rq, data, len)   do {} while (0)
-#define blk_trace_setup(q, name, dev, arg)      (-ENOTTY)
-#define blk_trace_startstop(q, start)           (-ENOTTY)
-#define blk_trace_remove(q)                     (-ENOTTY)
-#define blk_add_trace_msg(q, fmt, ...)          do { } while (0)
+# define blk_trace_ioctl(bdev, cmd, arg)                (-ENOTTY)
+# define blk_trace_shutdown(q)                          do { } while (0)
+# define do_blk_trace_setup(q, name, dev, bdev, buts)   (-ENOTTY)
+# define blk_add_driver_data(q, rq, data, len)          do {} while (0)
+# define blk_trace_setup(q, name, dev, bdev, arg)       (-ENOTTY)
+# define blk_trace_startstop(q, start)                  (-ENOTTY)
+# define blk_trace_remove(q)                            (-ENOTTY)
+# define blk_add_trace_msg(q, fmt, ...)                 do { } while (0)
+static inline int blk_trace_init_sysfs(struct device *dev)
+{
+        return 0;
+}
 
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+
+static inline int blk_cmd_buf_len(struct request *rq)
+{
+        return blk_pc_request(rq) ? rq->cmd_len * 3 : 1;
+}
+
+extern void blk_dump_cmd(char *buf, struct request *rq);
+extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
+extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
+
+#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
+
 #endif /* __KERNEL__ */
 #endif
diff --git a/include/linux/cdev.h b/include/linux/cdev.h
index fb4591977b03..f389e319a454 100644
--- a/include/linux/cdev.h
+++ b/include/linux/cdev.h
@@ -28,6 +28,8 @@ int cdev_add(struct cdev *, dev_t, unsigned);
 
 void cdev_del(struct cdev *);
 
+int cdev_index(struct inode *inode);
+
 void cd_forget(struct inode *);
 
 extern struct backing_dev_info directly_mappable_cdev_bdi;
diff --git a/include/linux/clocksource.h b/include/linux/clocksource.h
index 5a40d14daa9f..c56457c8334e 100644
--- a/include/linux/clocksource.h
+++ b/include/linux/clocksource.h
@@ -288,7 +288,15 @@ static inline cycle_t clocksource_read(struct clocksource *cs)
  */
 static inline int clocksource_enable(struct clocksource *cs)
 {
-        return cs->enable ? cs->enable(cs) : 0;
+        int ret = 0;
+
+        if (cs->enable)
+                ret = cs->enable(cs);
+
+        /* save mult_orig on enable */
+        cs->mult_orig = cs->mult;
+
+        return ret;
 }
 
 /**
diff --git a/include/linux/compat.h b/include/linux/compat.h
index f2ded21f9a3c..af931ee43dd8 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -222,6 +222,8 @@ int copy_siginfo_from_user32(siginfo_t *to, struct compat_siginfo __user *from);
 int copy_siginfo_to_user32(struct compat_siginfo __user *to, siginfo_t *from);
 int get_compat_sigevent(struct sigevent *event,
                 const struct compat_sigevent __user *u_event);
+long compat_sys_rt_tgsigqueueinfo(compat_pid_t tgid, compat_pid_t pid, int sig,
+                                  struct compat_siginfo __user *uinfo);
 
 static inline int compat_timeval_compare(struct compat_timeval *lhs,
                                         struct compat_timeval *rhs)
diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 9f315382610b..c5ac87ca7bc6 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -1022,6 +1022,8 @@ typedef struct cpumask *cpumask_var_t;
 
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
+bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node);
+bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags);
 void alloc_bootmem_cpumask_var(cpumask_var_t *mask);
 void free_cpumask_var(cpumask_var_t mask);
 void free_bootmem_cpumask_var(cpumask_var_t mask);
@@ -1040,6 +1042,19 @@ static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
         return true;
 }
 
+static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+        cpumask_clear(*mask);
+        return true;
+}
+
+static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags,
+                                          int node)
+{
+        cpumask_clear(*mask);
+        return true;
+}
+
 static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
 }
diff --git a/include/linux/cramfs_fs.h b/include/linux/cramfs_fs.h
index 3be4e5a27d82..6fc2bed368b8 100644
--- a/include/linux/cramfs_fs.h
+++ b/include/linux/cramfs_fs.h
@@ -2,9 +2,8 @@
 #define __CRAMFS_H
 
 #include <linux/types.h>
+#include <linux/magic.h>
 
-#define CRAMFS_MAGIC            0x28cd3d45      /* some random number */
-#define CRAMFS_MAGIC_WEND       0x453dcd28      /* magic number with the wrong endianess */
 #define CRAMFS_SIGNATURE        "Compressed ROMFS"
 
 /*
diff --git a/include/linux/cred.h b/include/linux/cred.h
index 3282ee4318e7..4fa999696310 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -13,6 +13,7 @@
 #define _LINUX_CRED_H
 
 #include <linux/capability.h>
+#include <linux/init.h>
 #include <linux/key.h>
 #include <asm/atomic.h>
 
diff --git a/include/linux/cyclades.h b/include/linux/cyclades.h
index 788850ba4e75..1fbdea4f08eb 100644
--- a/include/linux/cyclades.h
+++ b/include/linux/cyclades.h
@@ -142,19 +142,6 @@ struct CYZ_BOOT_CTRL {
 
 
 #ifndef DP_WINDOW_SIZE
-/* #include "cyclomz.h" */
-/****************** ****************** *******************/
-/*
- *      The data types defined below are used in all ZFIRM interface
- *      data structures. They accomodate differences between HW
- *      architectures and compilers.
- */
-
-typedef __u64  ucdouble;                /* 64 bits, unsigned */
-typedef __u32  uclong;                  /* 32 bits, unsigned */
-typedef __u16  ucshort;         /* 16 bits, unsigned */
-typedef __u8   ucchar;                  /* 8 bits, unsigned */
-
 /*
  *      Memory Window Sizes
  */
@@ -507,16 +494,20 @@ struct ZFW_CTRL {
 
 /* Per card data structure */
 struct cyclades_card {
-    void __iomem *base_addr;
-    void __iomem *ctl_addr;
-    int irq;
-    unsigned int num_chips;     /* 0 if card absent, -1 if Z/PCI, else Y */
-    unsigned int first_line;    /* minor number of first channel on card */
-    unsigned int nports;        /* Number of ports in the card */
-    int bus_index;              /* address shift - 0 for ISA, 1 for PCI */
-    int intr_enabled;           /* FW Interrupt flag - 0 disabled, 1 enabled */
-    spinlock_t card_lock;
-    struct cyclades_port *ports;
+        void __iomem *base_addr;
+        union {
+                void __iomem *p9050;
+                struct RUNTIME_9060 __iomem *p9060;
+        } ctl_addr;
+        int irq;
+        unsigned int num_chips; /* 0 if card absent, -1 if Z/PCI, else Y */
+        unsigned int first_line;        /* minor number of first channel on card */
+        unsigned int nports;    /* Number of ports in the card */
+        int bus_index;          /* address shift - 0 for ISA, 1 for PCI */
+        int intr_enabled;               /* FW Interrupt flag - 0 disabled, 1 enabled */
+        u32 hw_ver;
+        spinlock_t card_lock;
+        struct cyclades_port *ports;
 };
 
 /***************************************
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 15156364d196..30b93b2a01a4 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -180,10 +180,12 @@ d_iput:		no		no		no       yes
 #define DCACHE_REFERENCED       0x0008  /* Recently used, don't discard. */
 #define DCACHE_UNHASHED         0x0010  
 
-#define DCACHE_INOTIFY_PARENT_WATCHED   0x0020 /* Parent inode is watched */
+#define DCACHE_INOTIFY_PARENT_WATCHED   0x0020 /* Parent inode is watched by inotify */
 
 #define DCACHE_COOKIE           0x0040  /* For use by dcookie subsystem */
 
+#define DCACHE_FSNOTIFY_PARENT_WATCHED  0x0080 /* Parent inode is watched by some fsnotify listener */
+
 extern spinlock_t dcache_lock;
 extern seqlock_t rename_lock;
 
@@ -351,6 +353,11 @@ static inline int d_unhashed(struct dentry *dentry)
         return (dentry->d_flags & DCACHE_UNHASHED);
 }
 
+static inline int d_unlinked(struct dentry *dentry)
+{
+        return d_unhashed(dentry) && !IS_ROOT(dentry);
+}
+
 static inline struct dentry *dget_parent(struct dentry *dentry)
 {
         struct dentry *ret;
@@ -368,7 +375,7 @@ static inline int d_mountpoint(struct dentry *dentry)
         return dentry->d_mounted;
 }
 
-extern struct vfsmount *lookup_mnt(struct vfsmount *, struct dentry *);
+extern struct vfsmount *lookup_mnt(struct path *);
 extern struct dentry *lookup_create(struct nameidata *nd, int is_dir);
 
 extern int sysctl_vfs_cache_pressure;
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index ded2d7c42668..49c2362977fd 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -149,7 +149,7 @@ struct io_restrictions {
         unsigned max_hw_sectors;
         unsigned max_sectors;
         unsigned max_segment_size;
-        unsigned short hardsect_size;
+        unsigned short logical_block_size;
         unsigned short max_hw_segments;
         unsigned short max_phys_segments;
         unsigned char no_cluster; /* inverted so that 0 is default */
diff --git a/include/linux/dma-debug.h b/include/linux/dma-debug.h
index 28d53cb7b5a2..171ad8aedc83 100644
--- a/include/linux/dma-debug.h
+++ b/include/linux/dma-debug.h
@@ -32,6 +32,8 @@ extern void dma_debug_add_bus(struct bus_type *bus);
 
 extern void dma_debug_init(u32 num_entries);
 
+extern int dma_debug_resize_entries(u32 num_entries);
+
 extern void debug_dma_map_page(struct device *dev, struct page *page,
                                size_t offset, size_t size,
                                int direction, dma_addr_t dma_addr,
@@ -91,6 +93,11 @@ static inline void dma_debug_init(u32 num_entries)
 {
 }
 
+static inline int dma_debug_resize_entries(u32 num_entries)
+{
+        return 0;
+}
+
 static inline void debug_dma_map_page(struct device *dev, struct page *page,
                                       size_t offset, size_t size,
                                       int direction, dma_addr_t dma_addr,
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index e397dc342cda..10ff5c498824 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -108,6 +108,7 @@ struct irte {
 };
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
+extern int intr_remapping_supported(void);
 extern int enable_intr_remapping(int);
 extern void disable_intr_remapping(void);
 extern int reenable_intr_remapping(int);
@@ -157,6 +158,8 @@ static inline struct intel_iommu *map_ioapic_to_ir(int apic)
 }
 #define irq_remapped(irq)               (0)
 #define enable_intr_remapping(mode)     (-1)
+#define disable_intr_remapping()        (0)
+#define reenable_intr_remapping(mode)   (0)
 #define intr_remapping_enabled          (0)
 #endif
 
diff --git a/include/linux/dnotify.h b/include/linux/dnotify.h
index 102a902b4396..ecc06286226d 100644
--- a/include/linux/dnotify.h
+++ b/include/linux/dnotify.h
@@ -10,7 +10,7 @@
 
 struct dnotify_struct {
         struct dnotify_struct * dn_next;
-        unsigned long           dn_mask;
+        __u32                   dn_mask;
         int                     dn_fd;
         struct file *           dn_filp;
         fl_owner_t              dn_owner;
@@ -21,23 +21,18 @@ struct dnotify_struct {
 
 #ifdef CONFIG_DNOTIFY
 
-extern void __inode_dir_notify(struct inode *, unsigned long);
+#define DNOTIFY_ALL_EVENTS (FS_DELETE | FS_DELETE_CHILD |\
+                            FS_MODIFY | FS_MODIFY_CHILD |\
+                            FS_ACCESS | FS_ACCESS_CHILD |\
+                            FS_ATTRIB | FS_ATTRIB_CHILD |\
+                            FS_CREATE | FS_DN_RENAME |\
+                            FS_MOVED_FROM | FS_MOVED_TO)
+
 extern void dnotify_flush(struct file *, fl_owner_t);
 extern int fcntl_dirnotify(int, struct file *, unsigned long);
-extern void dnotify_parent(struct dentry *, unsigned long);
-
-static inline void inode_dir_notify(struct inode *inode, unsigned long event)
-{
-        if (inode->i_dnotify_mask & (event))
-                __inode_dir_notify(inode, event);
-}
 
 #else
 
-static inline void __inode_dir_notify(struct inode *inode, unsigned long event)
-{
-}
-
 static inline void dnotify_flush(struct file *filp, fl_owner_t id)
 {
 }
@@ -47,14 +42,6 @@ static inline int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
         return -EINVAL;
 }
 
-static inline void dnotify_parent(struct dentry *dentry, unsigned long event)
-{
-}
-
-static inline void inode_dir_notify(struct inode *inode, unsigned long event)
-{
-}
-
 #endif /* CONFIG_DNOTIFY */
 
 #endif /* __KERNEL __ */
diff --git a/include/linux/elevator.h b/include/linux/elevator.h
index c59b769f62b0..1cb3372e65d8 100644
--- a/include/linux/elevator.h
+++ b/include/linux/elevator.h
@@ -103,10 +103,8 @@ extern int elv_merge(struct request_queue *, struct request **, struct bio *);
 extern void elv_merge_requests(struct request_queue *, struct request *,
                                struct request *);
 extern void elv_merged_request(struct request_queue *, struct request *, int);
-extern void elv_dequeue_request(struct request_queue *, struct request *);
 extern void elv_requeue_request(struct request_queue *, struct request *);
 extern int elv_queue_empty(struct request_queue *);
-extern struct request *elv_next_request(struct request_queue *q);
 extern struct request *elv_former_request(struct request_queue *, struct request *);
 extern struct request *elv_latter_request(struct request_queue *, struct request *);
 extern int elv_register_queue(struct request_queue *q);
@@ -171,7 +169,7 @@ enum {
         ELV_MQUEUE_MUST,
 };
 
-#define rq_end_sector(rq)       ((rq)->sector + (rq)->nr_sectors)
+#define rq_end_sector(rq)       (blk_rq_pos(rq) + blk_rq_sectors(rq))
 #define rb_entry_rq(node)       rb_entry((node), struct request, rb_node)
 
 /*
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 3b534e527e09..ede84fa7da5d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -729,8 +729,8 @@ struct inode {
         struct timespec         i_atime;
         struct timespec         i_mtime;
         struct timespec         i_ctime;
-        unsigned int            i_blkbits;
         blkcnt_t                i_blocks;
+        unsigned int            i_blkbits;
         unsigned short          i_bytes;
         umode_t                 i_mode;
         spinlock_t              i_lock; /* i_blocks, i_bytes, maybe i_size */
@@ -751,13 +751,12 @@ struct inode {
                 struct block_device     *i_bdev;
                 struct cdev             *i_cdev;
         };
-        int                     i_cindex;
 
         __u32                   i_generation;
 
-#ifdef CONFIG_DNOTIFY
-        unsigned long           i_dnotify_mask; /* Directory notify events */
-        struct dnotify_struct   *i_dnotify; /* for directory notifications */
+#ifdef CONFIG_FSNOTIFY
+        __u32                   i_fsnotify_mask; /* all events this inode cares about */
+        struct hlist_head       i_fsnotify_mark_entries; /* fsnotify mark entries */
 #endif
 
 #ifdef CONFIG_INOTIFY
@@ -1321,7 +1320,7 @@ struct super_block {
         struct rw_semaphore     s_umount;
         struct mutex            s_lock;
         int                     s_count;
-        int                     s_need_sync_fs;
+        int                     s_need_sync;
         atomic_t                s_active;
 #ifdef CONFIG_SECURITY
         void                    *s_security;
@@ -1372,11 +1371,6 @@ struct super_block {
          * generic_show_options()
          */
         char *s_options;
-
-        /*
-         * storage for asynchronous operations
-         */
-        struct list_head s_async_list;
 };
 
 extern struct timespec current_fs_time(struct super_block *sb);
@@ -1800,7 +1794,7 @@ extern struct vfsmount *kern_mount_data(struct file_system_type *, void *data);
 extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 extern long do_mount(char *, char *, char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(struct vfsmount *, struct dentry *);
+extern struct vfsmount *collect_mounts(struct path *);
 extern void drop_collected_mounts(struct vfsmount *);
 
 extern int vfs_statfs(struct dentry *, struct kstatfs *);
@@ -1947,8 +1941,6 @@ extern struct super_block *freeze_bdev(struct block_device *);
 extern void emergency_thaw_all(void);
 extern int thaw_bdev(struct block_device *bdev, struct super_block *sb);
 extern int fsync_bdev(struct block_device *);
-extern int fsync_super(struct super_block *);
-extern int fsync_no_super(struct block_device *);
 #else
 static inline void bd_forget(struct inode *inode) {}
 static inline int sync_blockdev(struct block_device *bdev) { return 0; }
@@ -1964,6 +1956,7 @@ static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
         return 0;
 }
 #endif
+extern int sync_filesystem(struct super_block *);
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
 extern const struct file_operations bad_sock_fops;
@@ -2082,12 +2075,8 @@ extern int filemap_fdatawrite_range(struct address_space *mapping,
 
 extern int vfs_fsync(struct file *file, struct dentry *dentry, int datasync);
 extern void sync_supers(void);
-extern void sync_filesystems(int wait);
-extern void __fsync_super(struct super_block *sb);
 extern void emergency_sync(void);
 extern void emergency_remount(void);
-extern int do_remount_sb(struct super_block *sb, int flags,
-                         void *data, int force);
 #ifdef CONFIG_BLOCK
 extern sector_t bmap(struct inode *, sector_t);
 #endif
@@ -2205,6 +2194,8 @@ extern int generic_segment_checks(const struct iovec *iov,
 /* fs/splice.c */
 extern ssize_t generic_file_splice_read(struct file *, loff_t *,
                 struct pipe_inode_info *, size_t, unsigned int);
+extern ssize_t default_file_splice_read(struct file *, loff_t *,
+                struct pipe_inode_info *, size_t, unsigned int);
 extern ssize_t generic_file_splice_write(struct pipe_inode_info *,
                 struct file *, loff_t *, size_t, unsigned int);
 extern ssize_t generic_splice_sendpage(struct pipe_inode_info *pipe,
@@ -2354,6 +2345,8 @@ extern void simple_release_fs(struct vfsmount **mount, int *count);
 extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
                         loff_t *ppos, const void *from, size_t available);
 
+extern int simple_fsync(struct file *, struct dentry *, int);
+
 #ifdef CONFIG_MIGRATION
 extern int buffer_migrate_page(struct address_space *,
                                 struct page *, struct page *);
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 00fbd5b245c9..936f9aa8bb97 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -13,6 +13,7 @@
 
 #include <linux/dnotify.h>
 #include <linux/inotify.h>
+#include <linux/fsnotify_backend.h>
 #include <linux/audit.h>
 
 /*
@@ -22,19 +23,45 @@
 static inline void fsnotify_d_instantiate(struct dentry *entry,
                                                 struct inode *inode)
 {
+        __fsnotify_d_instantiate(entry, inode);
+
         inotify_d_instantiate(entry, inode);
 }
 
+/* Notify this dentry's parent about a child's events. */
+static inline void fsnotify_parent(struct dentry *dentry, __u32 mask)
+{
+        __fsnotify_parent(dentry, mask);
+
+        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
+}
+
 /*
  * fsnotify_d_move - entry has been moved
  * Called with dcache_lock and entry->d_lock held.
  */
 static inline void fsnotify_d_move(struct dentry *entry)
 {
+        /*
+         * On move we need to update entry->d_flags to indicate if the new parent
+         * cares about events from this entry.
+         */
+        __fsnotify_update_dcache_flags(entry);
+
         inotify_d_move(entry);
 }
 
 /*
+ * fsnotify_link_count - inode's link count changed
+ */
+static inline void fsnotify_link_count(struct inode *inode)
+{
+        inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL);
+
+        fsnotify(inode, FS_ATTRIB, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+}
+
+/*
  * fsnotify_move - file old_name at old_dir was moved to new_name at new_dir
  */
 static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
@@ -42,42 +69,62 @@ static inline void fsnotify_move(struct inode *old_dir, struct inode *new_dir,
                                  int isdir, struct inode *target, struct dentry *moved)
 {
         struct inode *source = moved->d_inode;
-        u32 cookie = inotify_get_cookie();
+        u32 in_cookie = inotify_get_cookie();
+        u32 fs_cookie = fsnotify_get_cookie();
+        __u32 old_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_FROM);
+        __u32 new_dir_mask = (FS_EVENT_ON_CHILD | FS_MOVED_TO);
 
         if (old_dir == new_dir)
-                inode_dir_notify(old_dir, DN_RENAME);
-        else {
-                inode_dir_notify(old_dir, DN_DELETE);
-                inode_dir_notify(new_dir, DN_CREATE);
-        }
+                old_dir_mask |= FS_DN_RENAME;
 
-        if (isdir)
+        if (isdir) {
                 isdir = IN_ISDIR;
-        inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir,cookie,old_name,
+                old_dir_mask |= FS_IN_ISDIR;
+                new_dir_mask |= FS_IN_ISDIR;
+        }
+
+        inotify_inode_queue_event(old_dir, IN_MOVED_FROM|isdir, in_cookie, old_name,
                                   source);
-        inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, cookie, new_name,
+        inotify_inode_queue_event(new_dir, IN_MOVED_TO|isdir, in_cookie, new_name,
                                   source);
 
+        fsnotify(old_dir, old_dir_mask, old_dir, FSNOTIFY_EVENT_INODE, old_name, fs_cookie);
+        fsnotify(new_dir, new_dir_mask, new_dir, FSNOTIFY_EVENT_INODE, new_name, fs_cookie);
+
         if (target) {
                 inotify_inode_queue_event(target, IN_DELETE_SELF, 0, NULL, NULL);
                 inotify_inode_is_dead(target);
+
+                /* this is really a link_count change not a removal */
+                fsnotify_link_count(target);
         }
 
         if (source) {
                 inotify_inode_queue_event(source, IN_MOVE_SELF, 0, NULL, NULL);
+                fsnotify(source, FS_MOVE_SELF, moved->d_inode, FSNOTIFY_EVENT_INODE, NULL, 0);
         }
         audit_inode_child(new_name, moved, new_dir);
 }
 
 /*
+ * fsnotify_inode_delete - and inode is being evicted from cache, clean up is needed
+ */
+static inline void fsnotify_inode_delete(struct inode *inode)
+{
+        __fsnotify_inode_delete(inode);
+}
+
+/*
  * fsnotify_nameremove - a filename was removed from a directory
  */
 static inline void fsnotify_nameremove(struct dentry *dentry, int isdir)
 {
+        __u32 mask = FS_DELETE;
+
         if (isdir)
-                isdir = IN_ISDIR;
-        dnotify_parent(dentry, DN_DELETE);
-        inotify_dentry_parent_queue_event(dentry, IN_DELETE|isdir, 0, dentry->d_name.name);
+                mask |= FS_IN_ISDIR;
+
+        fsnotify_parent(dentry, mask);
 }
 
 /*
@@ -87,14 +134,9 @@ static inline void fsnotify_inoderemove(struct inode *inode)
 {
         inotify_inode_queue_event(inode, IN_DELETE_SELF, 0, NULL, NULL);
         inotify_inode_is_dead(inode);
-}
 
-/*
- * fsnotify_link_count - inode's link count changed
- */
-static inline void fsnotify_link_count(struct inode *inode)
-{
-        inotify_inode_queue_event(inode, IN_ATTRIB, 0, NULL, NULL);
+        fsnotify(inode, FS_DELETE_SELF, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+        __fsnotify_inode_delete(inode);
 }
 
 /*
@@ -102,10 +144,11 @@ static inline void fsnotify_link_count(struct inode *inode)
  */
 static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
 {
-        inode_dir_notify(inode, DN_CREATE);
         inotify_inode_queue_event(inode, IN_CREATE, 0, dentry->d_name.name,
                                   dentry->d_inode);
         audit_inode_child(dentry->d_name.name, dentry, inode);
+
+        fsnotify(inode, FS_CREATE, dentry->d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
 }
 
 /*
@@ -115,11 +158,12 @@ static inline void fsnotify_create(struct inode *inode, struct dentry *dentry)
  */
 static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct dentry *new_dentry)
 {
-        inode_dir_notify(dir, DN_CREATE);
         inotify_inode_queue_event(dir, IN_CREATE, 0, new_dentry->d_name.name,
                                   inode);
         fsnotify_link_count(inode);
         audit_inode_child(new_dentry->d_name.name, new_dentry, dir);
+
+        fsnotify(dir, FS_CREATE, inode, FSNOTIFY_EVENT_INODE, new_dentry->d_name.name, 0);
 }
 
 /*
@@ -127,10 +171,13 @@ static inline void fsnotify_link(struct inode *dir, struct inode *inode, struct
  */
 static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 {
-        inode_dir_notify(inode, DN_CREATE);
-        inotify_inode_queue_event(inode, IN_CREATE | IN_ISDIR, 0, 
-                                  dentry->d_name.name, dentry->d_inode);
+        __u32 mask = (FS_CREATE | FS_IN_ISDIR);
+        struct inode *d_inode = dentry->d_inode;
+
+        inotify_inode_queue_event(inode, mask, 0, dentry->d_name.name, d_inode);
         audit_inode_child(dentry->d_name.name, dentry, inode);
+
+        fsnotify(inode, mask, d_inode, FSNOTIFY_EVENT_INODE, dentry->d_name.name, 0);
 }
 
 /*
@@ -139,14 +186,15 @@ static inline void fsnotify_mkdir(struct inode *inode, struct dentry *dentry)
 static inline void fsnotify_access(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_ACCESS;
+        __u32 mask = FS_ACCESS;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        dnotify_parent(dentry, DN_ACCESS);
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -155,14 +203,15 @@ static inline void fsnotify_access(struct dentry *dentry)
 static inline void fsnotify_modify(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_MODIFY;
+        __u32 mask = FS_MODIFY;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        dnotify_parent(dentry, DN_MODIFY);
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -171,13 +220,15 @@ static inline void fsnotify_modify(struct dentry *dentry)
 static inline void fsnotify_open(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_OPEN;
+        __u32 mask = FS_OPEN;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -187,15 +238,16 @@ static inline void fsnotify_close(struct file *file)
 {
         struct dentry *dentry = file->f_path.dentry;
         struct inode *inode = dentry->d_inode;
-        const char *name = dentry->d_name.name;
         fmode_t mode = file->f_mode;
-        u32 mask = (mode & FMODE_WRITE) ? IN_CLOSE_WRITE : IN_CLOSE_NOWRITE;
+        __u32 mask = (mode & FMODE_WRITE) ? FS_CLOSE_WRITE : FS_CLOSE_NOWRITE;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        inotify_dentry_parent_queue_event(dentry, mask, 0, name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, file, FSNOTIFY_EVENT_FILE, NULL, 0);
 }
 
 /*
@@ -204,13 +256,15 @@ static inline void fsnotify_close(struct file *file)
 static inline void fsnotify_xattr(struct dentry *dentry)
 {
         struct inode *inode = dentry->d_inode;
-        u32 mask = IN_ATTRIB;
+        __u32 mask = FS_ATTRIB;
 
         if (S_ISDIR(inode->i_mode))
-                mask |= IN_ISDIR;
+                mask |= FS_IN_ISDIR;
 
-        inotify_dentry_parent_queue_event(dentry, mask, 0, dentry->d_name.name);
         inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+        fsnotify_parent(dentry, mask);
+        fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
 }
 
 /*
@@ -220,50 +274,37 @@ static inline void fsnotify_xattr(struct dentry *dentry)
 static inline void fsnotify_change(struct dentry *dentry, unsigned int ia_valid)
 {
         struct inode *inode = dentry->d_inode;
-        int dn_mask = 0;
-        u32 in_mask = 0;
+        __u32 mask = 0;
+
+        if (ia_valid & ATTR_UID)
+                mask |= FS_ATTRIB;
+        if (ia_valid & ATTR_GID)
+                mask |= FS_ATTRIB;
+        if (ia_valid & ATTR_SIZE)
+                mask |= FS_MODIFY;
 
-        if (ia_valid & ATTR_UID) {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        }
-        if (ia_valid & ATTR_GID) {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        }
-        if (ia_valid & ATTR_SIZE) {
-                in_mask |= IN_MODIFY;
-                dn_mask |= DN_MODIFY;
-        }
         /* both times implies a utime(s) call */
         if ((ia_valid & (ATTR_ATIME | ATTR_MTIME)) == (ATTR_ATIME | ATTR_MTIME))
-        {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        } else if (ia_valid & ATTR_ATIME) {
-                in_mask |= IN_ACCESS;
-                dn_mask |= DN_ACCESS;
-        } else if (ia_valid & ATTR_MTIME) {
-                in_mask |= IN_MODIFY;
-                dn_mask |= DN_MODIFY;
-        }
-        if (ia_valid & ATTR_MODE) {
-                in_mask |= IN_ATTRIB;
-                dn_mask |= DN_ATTRIB;
-        }
+                mask |= FS_ATTRIB;
+        else if (ia_valid & ATTR_ATIME)
+                mask |= FS_ACCESS;
+        else if (ia_valid & ATTR_MTIME)
+                mask |= FS_MODIFY;
+
+        if (ia_valid & ATTR_MODE)
+                mask |= FS_ATTRIB;
 
-        if (dn_mask)
-                dnotify_parent(dentry, dn_mask);
-        if (in_mask) {
+        if (mask) {
                 if (S_ISDIR(inode->i_mode))
-                        in_mask |= IN_ISDIR;
-                inotify_inode_queue_event(inode, in_mask, 0, NULL, NULL);
-                inotify_dentry_parent_queue_event(dentry, in_mask, 0,
-                                                  dentry->d_name.name);
+                        mask |= FS_IN_ISDIR;
+                inotify_inode_queue_event(inode, mask, 0, NULL, NULL);
+
+                fsnotify_parent(dentry, mask);
+                fsnotify(inode, mask, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
         }
 }
 
-#ifdef CONFIG_INOTIFY   /* inotify helpers */
+#if defined(CONFIG_INOTIFY) || defined(CONFIG_FSNOTIFY) /* notify helpers */
 
 /*
  * fsnotify_oldname_init - save off the old filename before we change it
@@ -281,7 +322,7 @@ static inline void fsnotify_oldname_free(const char *old_name)
         kfree(old_name);
 }
 
-#else   /* CONFIG_INOTIFY */
+#else   /* CONFIG_INOTIFY || CONFIG_FSNOTIFY */
 
 static inline const char *fsnotify_oldname_init(const char *name)
 {
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
new file mode 100644
index 000000000000..44848aa830dc
--- /dev/null
+++ b/include/linux/fsnotify_backend.h
@@ -0,0 +1,387 @@
+/*
+ * Filesystem access notification for Linux
+ *
+ *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
+ */
+
+#ifndef __LINUX_FSNOTIFY_BACKEND_H
+#define __LINUX_FSNOTIFY_BACKEND_H
+
+#ifdef __KERNEL__
+
+#include <linux/idr.h> /* inotify uses this */
+#include <linux/fs.h> /* struct inode */
+#include <linux/list.h>
+#include <linux/path.h> /* struct path */
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#include <asm/atomic.h>
+
+/*
+ * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily
+ * convert between them.  dnotify only needs conversion at watch creation
+ * so no perf loss there.  fanotify isn't defined yet, so it can use the
+ * wholes if it needs more events.
+ */
+#define FS_ACCESS               0x00000001      /* File was accessed */
+#define FS_MODIFY               0x00000002      /* File was modified */
+#define FS_ATTRIB               0x00000004      /* Metadata changed */
+#define FS_CLOSE_WRITE          0x00000008      /* Writtable file was closed */
+#define FS_CLOSE_NOWRITE        0x00000010      /* Unwrittable file closed */
+#define FS_OPEN                 0x00000020      /* File was opened */
+#define FS_MOVED_FROM           0x00000040      /* File was moved from X */
+#define FS_MOVED_TO             0x00000080      /* File was moved to Y */
+#define FS_CREATE               0x00000100      /* Subfile was created */
+#define FS_DELETE               0x00000200      /* Subfile was deleted */
+#define FS_DELETE_SELF          0x00000400      /* Self was deleted */
+#define FS_MOVE_SELF            0x00000800      /* Self was moved */
+
+#define FS_UNMOUNT              0x00002000      /* inode on umount fs */
+#define FS_Q_OVERFLOW           0x00004000      /* Event queued overflowed */
+#define FS_IN_IGNORED           0x00008000      /* last inotify event here */
+
+#define FS_IN_ISDIR             0x40000000      /* event occurred against dir */
+#define FS_IN_ONESHOT           0x80000000      /* only send event once */
+
+#define FS_DN_RENAME            0x10000000      /* file renamed */
+#define FS_DN_MULTISHOT         0x20000000      /* dnotify multishot */
+
+/* This inode cares about things that happen to its children.  Always set for
+ * dnotify and inotify. */
+#define FS_EVENT_ON_CHILD       0x08000000
+
+/* This is a list of all events that may get sent to a parernt based on fs event
+ * happening to inodes inside that directory */
+#define FS_EVENTS_POSS_ON_CHILD   (FS_ACCESS | FS_MODIFY | FS_ATTRIB |\
+                                   FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | FS_OPEN |\
+                                   FS_MOVED_FROM | FS_MOVED_TO | FS_CREATE |\
+                                   FS_DELETE)
+
+/* listeners that hard code group numbers near the top */
+#define DNOTIFY_GROUP_NUM       UINT_MAX
+#define INOTIFY_GROUP_NUM       (DNOTIFY_GROUP_NUM-1)
+
+struct fsnotify_group;
+struct fsnotify_event;
+struct fsnotify_mark_entry;
+struct fsnotify_event_private_data;
+
+/*
+ * Each group much define these ops.  The fsnotify infrastructure will call
+ * these operations for each relevant group.
+ *
+ * should_send_event - given a group, inode, and mask this function determines
+ *              if the group is interested in this event.
+ * handle_event - main call for a group to handle an fs event
+ * free_group_priv - called when a group refcnt hits 0 to clean up the private union
+ * freeing-mark - this means that a mark has been flagged to die when everything
+ *              finishes using it.  The function is supplied with what must be a
+ *              valid group and inode to use to clean up.
+ */
+struct fsnotify_ops {
+        bool (*should_send_event)(struct fsnotify_group *group, struct inode *inode, __u32 mask);
+        int (*handle_event)(struct fsnotify_group *group, struct fsnotify_event *event);
+        void (*free_group_priv)(struct fsnotify_group *group);
+        void (*freeing_mark)(struct fsnotify_mark_entry *entry, struct fsnotify_group *group);
+        void (*free_event_priv)(struct fsnotify_event_private_data *priv);
+};
+
+/*
+ * A group is a "thing" that wants to receive notification about filesystem
+ * events.  The mask holds the subset of event types this group cares about.
+ * refcnt on a group is up to the implementor and at any moment if it goes 0
+ * everything will be cleaned up.
+ */
+struct fsnotify_group {
+        /*
+         * global list of all groups receiving events from fsnotify.
+         * anchored by fsnotify_groups and protected by either fsnotify_grp_mutex
+         * or fsnotify_grp_srcu depending on write vs read.
+         */
+        struct list_head group_list;
+
+        /*
+         * Defines all of the event types in which this group is interested.
+         * This mask is a bitwise OR of the FS_* events from above.  Each time
+         * this mask changes for a group (if it changes) the correct functions
+         * must be called to update the global structures which indicate global
+         * interest in event types.
+         */
+        __u32 mask;
+
+        /*
+         * How the refcnt is used is up to each group.  When the refcnt hits 0
+         * fsnotify will clean up all of the resources associated with this group.
+         * As an example, the dnotify group will always have a refcnt=1 and that
+         * will never change.  Inotify, on the other hand, has a group per
+         * inotify_init() and the refcnt will hit 0 only when that fd has been
+         * closed.
+         */
+        atomic_t refcnt;                /* things with interest in this group */
+        unsigned int group_num;         /* simply prevents accidental group collision */
+
+        const struct fsnotify_ops *ops; /* how this group handles things */
+
+        /* needed to send notification to userspace */
+        struct mutex notification_mutex;        /* protect the notification_list */
+        struct list_head notification_list;     /* list of event_holder this group needs to send to userspace */
+        wait_queue_head_t notification_waitq;   /* read() on the notification file blocks on this waitq */
+        unsigned int q_len;                     /* events on the queue */
+        unsigned int max_events;                /* maximum events allowed on the list */
+
+        /* stores all fastapth entries assoc with this group so they can be cleaned on unregister */
+        spinlock_t mark_lock;           /* protect mark_entries list */
+        atomic_t num_marks;             /* 1 for each mark entry and 1 for not being
+                                         * past the point of no return when freeing
+                                         * a group */
+        struct list_head mark_entries;  /* all inode mark entries for this group */
+
+        /* prevents double list_del of group_list.  protected by global fsnotify_grp_mutex */
+        bool on_group_list;
+
+        /* groups can define private fields here or use the void *private */
+        union {
+                void *private;
+#ifdef CONFIG_INOTIFY_USER
+                struct inotify_group_private_data {
+                        spinlock_t      idr_lock;
+                        struct idr      idr;
+                        u32             last_wd;
+                        struct fasync_struct    *fa;    /* async notification */
+                        struct user_struct      *user;
+                } inotify_data;
+#endif
+        };
+};
+
+/*
+ * A single event can be queued in multiple group->notification_lists.
+ *
+ * each group->notification_list will point to an event_holder which in turns points
+ * to the actual event that needs to be sent to userspace.
+ *
+ * Seemed cheaper to create a refcnt'd event and a small holder for every group
+ * than create a different event for every group
+ *
+ */
+struct fsnotify_event_holder {
+        struct fsnotify_event *event;
+        struct list_head event_list;
+};
+
+/*
+ * Inotify needs to tack data onto an event.  This struct lets us later find the
+ * correct private data of the correct group.
+ */
+struct fsnotify_event_private_data {
+        struct fsnotify_group *group;
+        struct list_head event_list;
+};
+
+/*
+ * all of the information about the original object we want to now send to
+ * a group.  If you want to carry more info from the accessing task to the
+ * listener this structure is where you need to be adding fields.
+ */
+struct fsnotify_event {
+        /*
+         * If we create an event we are also likely going to need a holder
+         * to link to a group.  So embed one holder in the event.  Means only
+         * one allocation for the common case where we only have one group
+         */
+        struct fsnotify_event_holder holder;
+        spinlock_t lock;        /* protection for the associated event_holder and private_list */
+        /* to_tell may ONLY be dereferenced during handle_event(). */
+        struct inode *to_tell;  /* either the inode the event happened to or its parent */
+        /*
+         * depending on the event type we should have either a path or inode
+         * We hold a reference on path, but NOT on inode.  Since we have the ref on
+         * the path, it may be dereferenced at any point during this object's
+         * lifetime.  That reference is dropped when this object's refcnt hits
+         * 0.  If this event contains an inode instead of a path, the inode may
+         * ONLY be used during handle_event().
+         */
+        union {
+                struct path path;
+                struct inode *inode;
+        };
+/* when calling fsnotify tell it if the data is a path or inode */
+#define FSNOTIFY_EVENT_NONE     0
+#define FSNOTIFY_EVENT_PATH     1
+#define FSNOTIFY_EVENT_INODE    2
+#define FSNOTIFY_EVENT_FILE     3
+        int data_type;          /* which of the above union we have */
+        atomic_t refcnt;        /* how many groups still are using/need to send this event */
+        __u32 mask;             /* the type of access, bitwise OR for FS_* event types */
+
+        u32 sync_cookie;        /* used to corrolate events, namely inotify mv events */
+        char *file_name;
+        size_t name_len;
+
+        struct list_head private_data_list;     /* groups can store private data here */
+};
+
+/*
+ * a mark is simply an entry attached to an in core inode which allows an
+ * fsnotify listener to indicate they are either no longer interested in events
+ * of a type matching mask or only interested in those events.
+ *
+ * these are flushed when an inode is evicted from core and may be flushed
+ * when the inode is modified (as seen by fsnotify_access).  Some fsnotify users
+ * (such as dnotify) will flush these when the open fd is closed and not at
+ * inode eviction or modification.
+ */
+struct fsnotify_mark_entry {
+        __u32 mask;                     /* mask this mark entry is for */
+        /* we hold ref for each i_list and g_list.  also one ref for each 'thing'
+         * in kernel that found and may be using this mark. */
+        atomic_t refcnt;                /* active things looking at this mark */
+        struct inode *inode;            /* inode this entry is associated with */
+        struct fsnotify_group *group;   /* group this mark entry is for */
+        struct hlist_node i_list;       /* list of mark_entries by inode->i_fsnotify_mark_entries */
+        struct list_head g_list;        /* list of mark_entries by group->i_fsnotify_mark_entries */
+        spinlock_t lock;                /* protect group, inode, and killme */
+        struct list_head free_i_list;   /* tmp list used when freeing this mark */
+        struct list_head free_g_list;   /* tmp list used when freeing this mark */
+        void (*free_mark)(struct fsnotify_mark_entry *entry); /* called on final put+free */
+};
+
+#ifdef CONFIG_FSNOTIFY
+
+/* called from the vfs helpers */
+
+/* main fsnotify call to send events */
+extern void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
+                     const char *name, u32 cookie);
+extern void __fsnotify_parent(struct dentry *dentry, __u32 mask);
+extern void __fsnotify_inode_delete(struct inode *inode);
+extern u32 fsnotify_get_cookie(void);
+
+static inline int fsnotify_inode_watches_children(struct inode *inode)
+{
+        /* FS_EVENT_ON_CHILD is set if the inode may care */
+        if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD))
+                return 0;
+        /* this inode might care about child events, does it care about the
+         * specific set of events that can happen on a child? */
+        return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD;
+}
+
+/*
+ * Update the dentry with a flag indicating the interest of its parent to receive
+ * filesystem events when those events happens to this dentry->d_inode.
+ */
+static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
+{
+        struct dentry *parent;
+
+        assert_spin_locked(&dcache_lock);
+        assert_spin_locked(&dentry->d_lock);
+
+        parent = dentry->d_parent;
+        if (fsnotify_inode_watches_children(parent->d_inode))
+                dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+        else
+                dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
+}
+
+/*
+ * fsnotify_d_instantiate - instantiate a dentry for inode
+ * Called with dcache_lock held.
+ */
+static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode)
+{
+        if (!inode)
+                return;
+
+        assert_spin_locked(&dcache_lock);
+
+        spin_lock(&dentry->d_lock);
+        __fsnotify_update_dcache_flags(dentry);
+        spin_unlock(&dentry->d_lock);
+}
+
+/* called from fsnotify listeners, such as fanotify or dnotify */
+
+/* must call when a group changes its ->mask */
+extern void fsnotify_recalc_global_mask(void);
+/* get a reference to an existing or create a new group */
+extern struct fsnotify_group *fsnotify_obtain_group(unsigned int group_num,
+                                                    __u32 mask,
+                                                    const struct fsnotify_ops *ops);
+/* run all marks associated with this group and update group->mask */
+extern void fsnotify_recalc_group_mask(struct fsnotify_group *group);
+/* drop reference on a group from fsnotify_obtain_group */
+extern void fsnotify_put_group(struct fsnotify_group *group);
+
+/* take a reference to an event */
+extern void fsnotify_get_event(struct fsnotify_event *event);
+extern void fsnotify_put_event(struct fsnotify_event *event);
+/* find private data previously attached to an event and unlink it */
+extern struct fsnotify_event_private_data *fsnotify_remove_priv_from_event(struct fsnotify_group *group,
+                                                                           struct fsnotify_event *event);
+
+/* attach the event to the group notification queue */
+extern int fsnotify_add_notify_event(struct fsnotify_group *group, struct fsnotify_event *event,
+                                     struct fsnotify_event_private_data *priv);
+/* true if the group notification queue is empty */
+extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group);
+/* return, but do not dequeue the first event on the notification queue */
+extern struct fsnotify_event *fsnotify_peek_notify_event(struct fsnotify_group *group);
+/* return AND dequeue the first event on the notification queue */
+extern struct fsnotify_event *fsnotify_remove_notify_event(struct fsnotify_group *group);
+
+/* functions used to manipulate the marks attached to inodes */
+
+/* run all marks associated with an inode and update inode->i_fsnotify_mask */
+extern void fsnotify_recalc_inode_mask(struct inode *inode);
+extern void fsnotify_init_mark(struct fsnotify_mark_entry *entry, void (*free_mark)(struct fsnotify_mark_entry *entry));
+/* find (and take a reference) to a mark associated with group and inode */
+extern struct fsnotify_mark_entry *fsnotify_find_mark_entry(struct fsnotify_group *group, struct inode *inode);
+/* attach the mark to both the group and the inode */
+extern int fsnotify_add_mark(struct fsnotify_mark_entry *entry, struct fsnotify_group *group, struct inode *inode);
+/* given a mark, flag it to be freed when all references are dropped */
+extern void fsnotify_destroy_mark_by_entry(struct fsnotify_mark_entry *entry);
+/* run all the marks in a group, and flag them to be freed */
+extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group);
+extern void fsnotify_get_mark(struct fsnotify_mark_entry *entry);
+extern void fsnotify_put_mark(struct fsnotify_mark_entry *entry);
+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);
+
+#else
+
+static inline void fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is,
+                            const char *name, u32 cookie)
+{}
+
+static inline void __fsnotify_parent(struct dentry *dentry, __u32 mask)
+{}
+
+static inline void __fsnotify_inode_delete(struct inode *inode)
+{}
+
+static inline void __fsnotify_update_dcache_flags(struct dentry *dentry)
+{}
+
+static inline void __fsnotify_d_instantiate(struct dentry *dentry, struct inode *inode)
+{}
+
+static inline u32 fsnotify_get_cookie(void)
+{
+        return 0;
+}
+
+static inline void fsnotify_unmount_inodes(struct list_head *list)
+{}
+
+#endif  /* CONFIG_FSNOTIFY */
+
+#endif  /* __KERNEL __ */
+
+#endif  /* __LINUX_FSNOTIFY_BACKEND_H */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8a0c2f221e6b..39b95c56587e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -233,8 +233,6 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 
-extern void ftrace_release(void *start, unsigned long size);
-
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
 #else
@@ -325,13 +323,8 @@ static inline void __ftrace_enabled_restore(int enabled)
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
-extern void ftrace_init_module(struct module *mod,
-                               unsigned long *start, unsigned long *end);
 #else
 static inline void ftrace_init(void) { }
-static inline void
-ftrace_init_module(struct module *mod,
-                   unsigned long *start, unsigned long *end) { }
 #endif
 
 /*
@@ -368,6 +361,7 @@ struct ftrace_ret_stack {
         unsigned long ret;
         unsigned long func;
         unsigned long long calltime;
+        unsigned long long subtime;
 };
 
 /*
@@ -379,8 +373,6 @@ extern void return_to_handler(void);
 
 extern int
 ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
-extern void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 
 /*
  * Sometimes we don't want to trace a function with the function
@@ -496,8 +488,15 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 
 extern int ftrace_dump_on_oops;
 
+#ifdef CONFIG_PREEMPT
+#define INIT_TRACE_RECURSION            .trace_recursion = 0,
+#endif
+
 #endif /* CONFIG_TRACING */
 
+#ifndef INIT_TRACE_RECURSION
+#define INIT_TRACE_RECURSION
+#endif
 
 #ifdef CONFIG_HW_BRANCH_TRACER
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
new file mode 100644
index 000000000000..5c093ffc655b
--- /dev/null
+++ b/include/linux/ftrace_event.h
@@ -0,0 +1,172 @@
+#ifndef _LINUX_FTRACE_EVENT_H
+#define _LINUX_FTRACE_EVENT_H
+
+#include <linux/trace_seq.h>
+#include <linux/ring_buffer.h>
+#include <linux/percpu.h>
+
+struct trace_array;
+struct tracer;
+struct dentry;
+
+DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq);
+
+struct trace_print_flags {
+        unsigned long           mask;
+        const char              *name;
+};
+
+const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+                                   unsigned long flags,
+                                   const struct trace_print_flags *flag_array);
+
+const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+                                     const struct trace_print_flags *symbol_array);
+
+/*
+ * The trace entry - the most basic unit of tracing. This is what
+ * is printed in the end as a single line in the trace output, such as:
+ *
+ *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
+ */
+struct trace_entry {
+        unsigned short          type;
+        unsigned char           flags;
+        unsigned char           preempt_count;
+        int                     pid;
+        int                     tgid;
+};
+
+#define FTRACE_MAX_EVENT                                                \
+        ((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1)
+
+/*
+ * Trace iterator - used by printout routines who present trace
+ * results to users and which routines might sleep, etc:
+ */
+struct trace_iterator {
+        struct trace_array      *tr;
+        struct tracer           *trace;
+        void                    *private;
+        int                     cpu_file;
+        struct mutex            mutex;
+        struct ring_buffer_iter *buffer_iter[NR_CPUS];
+        unsigned long           iter_flags;
+
+        /* The below is zeroed out in pipe_read */
+        struct trace_seq        seq;
+        struct trace_entry      *ent;
+        int                     cpu;
+        u64                     ts;
+
+        loff_t                  pos;
+        long                    idx;
+
+        cpumask_var_t           started;
+};
+
+
+typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
+                                              int flags);
+struct trace_event {
+        struct hlist_node       node;
+        struct list_head        list;
+        int                     type;
+        trace_print_func        trace;
+        trace_print_func        raw;
+        trace_print_func        hex;
+        trace_print_func        binary;
+};
+
+extern int register_ftrace_event(struct trace_event *event);
+extern int unregister_ftrace_event(struct trace_event *event);
+
+/* Return values for print_line callback */
+enum print_line_t {
+        TRACE_TYPE_PARTIAL_LINE = 0,    /* Retry after flushing the seq */
+        TRACE_TYPE_HANDLED      = 1,
+        TRACE_TYPE_UNHANDLED    = 2,    /* Relay to other output functions */
+        TRACE_TYPE_NO_CONSUME   = 3     /* Handled but ask to not consume */
+};
+
+
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(int type, unsigned long len,
+                                  unsigned long flags, int pc);
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+                                        unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+                                        unsigned long flags, int pc);
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+
+void tracing_record_cmdline(struct task_struct *tsk);
+
+struct ftrace_event_call {
+        struct list_head        list;
+        char                    *name;
+        char                    *system;
+        struct dentry           *dir;
+        struct trace_event      *event;
+        int                     enabled;
+        int                     (*regfunc)(void);
+        void                    (*unregfunc)(void);
+        int                     id;
+        int                     (*raw_init)(void);
+        int                     (*show_format)(struct trace_seq *s);
+        int                     (*define_fields)(void);
+        struct list_head        fields;
+        int                     filter_active;
+        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
+};
+
+#define MAX_FILTER_PRED         32
+#define MAX_FILTER_STR_VAL      128
+
+extern int init_preds(struct ftrace_event_call *call);
+extern void destroy_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern int filter_current_check_discard(struct ftrace_event_call *call,
+                                        void *rec,
+                                        struct ring_buffer_event *event);
+
+extern int trace_define_field(struct ftrace_event_call *call, char *type,
+                              char *name, int offset, int size, int is_signed);
+
+#define is_signed_type(type)    (((type)(-1)) < 0)
+
+int trace_set_clr_event(const char *system, const char *event, int set);
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement optimizing out.
+ */
+#define event_trace_printk(ip, fmt, args...)                            \
+do {                                                                    \
+        __trace_printk_check_format(fmt, ##args);                       \
+        tracing_record_cmdline(current);                                \
+        if (__builtin_constant_p(fmt)) {                                \
+                static const char *trace_printk_fmt                     \
+                  __attribute__((section("__trace_printk_fmt"))) =      \
+                        __builtin_constant_p(fmt) ? fmt : NULL;         \
+                                                                        \
+                __trace_bprintk(ip, trace_printk_fmt, ##args);          \
+        } else                                                          \
+                __trace_printk(ip, fmt, ##args);                        \
+} while (0)
+
+#define __common_field(type, item, is_signed)                           \
+        ret = trace_define_field(event_call, #type, "common_" #item,    \
+                                 offsetof(typeof(field.ent), item),     \
+                                 sizeof(field.ent.item), is_signed);    \
+        if (ret)                                                        \
+                return ret;
+
+#endif /* _LINUX_FTRACE_EVENT_H */
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 3bf5bb5a34f9..34956c8fdebf 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -23,6 +23,8 @@ union ktime;
 #define FUTEX_TRYLOCK_PI        8
 #define FUTEX_WAIT_BITSET       9
 #define FUTEX_WAKE_BITSET       10
+#define FUTEX_WAIT_REQUEUE_PI   11
+#define FUTEX_CMP_REQUEUE_PI    12
 
 #define FUTEX_PRIVATE_FLAG      128
 #define FUTEX_CLOCK_REALTIME    256
@@ -38,6 +40,10 @@ union ktime;
 #define FUTEX_TRYLOCK_PI_PRIVATE (FUTEX_TRYLOCK_PI | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAIT_BITSET_PRIVATE       (FUTEX_WAIT_BITS | FUTEX_PRIVATE_FLAG)
 #define FUTEX_WAKE_BITSET_PRIVATE       (FUTEX_WAKE_BITS | FUTEX_PRIVATE_FLAG)
+#define FUTEX_WAIT_REQUEUE_PI_PRIVATE   (FUTEX_WAIT_REQUEUE_PI | \
+                                         FUTEX_PRIVATE_FLAG)
+#define FUTEX_CMP_REQUEUE_PI_PRIVATE    (FUTEX_CMP_REQUEUE_PI | \
+                                         FUTEX_PRIVATE_FLAG)
 
 /*
  * Support for robust futexes: the kernel cleans up held futexes at
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index a1a28caed23d..149fda264c86 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -90,6 +90,7 @@ struct disk_stats {
 struct hd_struct {
         sector_t start_sect;
         sector_t nr_sects;
+        sector_t alignment_offset;
         struct device __dev;
         struct kobject *holder_dir;
         int policy, partno;
diff --git a/include/linux/i7300_idle.h b/include/linux/i7300_idle.h
index 05a80c44513c..1587b7dec505 100644
--- a/include/linux/i7300_idle.h
+++ b/include/linux/i7300_idle.h
@@ -16,35 +16,33 @@
 struct fbd_ioat {
         unsigned int vendor;
         unsigned int ioat_dev;
+        unsigned int enabled;
 };
 
 /*
  * The i5000 chip-set has the same hooks as the i7300
- * but support is disabled by default because this driver
- * has not been validated on that platform.
+ * but it is not enabled by default and must be manually
+ * manually enabled with "forceload=1" because it is
+ * only lightly validated.
  */
-#define SUPPORT_I5000 0
 
 static const struct fbd_ioat fbd_ioat_list[] = {
-        {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_CNB},
-#if SUPPORT_I5000
-        {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT},
-#endif
+        {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT_CNB, 1},
+        {PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_IOAT, 0},
         {0, 0}
 };
 
 /* table of devices that work with this driver */
 static const struct pci_device_id pci_tbl[] = {
         { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_FBD_CNB) },
-#if SUPPORT_I5000
         { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_5000_ERR) },
-#endif
         { } /* Terminating entry */
 };
 
 /* Check for known platforms with I/O-AT */
 static inline int i7300_idle_platform_probe(struct pci_dev **fbd_dev,
-                                                struct pci_dev **ioat_dev)
+                                                struct pci_dev **ioat_dev,
+                                                int enable_all)
 {
         int i;
         struct pci_dev *memdev, *dmadev;
@@ -69,6 +67,8 @@ static inline int i7300_idle_platform_probe(struct pci_dev **fbd_dev,
         for (i = 0; fbd_ioat_list[i].vendor != 0; i++) {
                 if (dmadev->vendor == fbd_ioat_list[i].vendor &&
                     dmadev->device == fbd_ioat_list[i].ioat_dev) {
+                        if (!(fbd_ioat_list[i].enabled || enable_all))
+                                continue;
                         if (fbd_dev)
                                 *fbd_dev = memdev;
                         if (ioat_dev)
diff --git a/include/linux/ide.h b/include/linux/ide.h
index ff65fffb078f..867cb68d8461 100644
--- a/include/linux/ide.h
+++ b/include/linux/ide.h
@@ -26,6 +26,9 @@
 #include <asm/io.h>
 #include <asm/mutex.h>
 
+/* for request_sense */
+#include <linux/cdrom.h>
+
 #if defined(CONFIG_CRIS) || defined(CONFIG_FRV) || defined(CONFIG_MN10300)
 # define SUPPORT_VLB_SYNC 0
 #else
@@ -324,7 +327,6 @@ struct ide_cmd {
         unsigned int            cursg_ofs;
 
         struct request          *rq;            /* copy of request */
-        void                    *special;       /* valid_t generally */
 };
 
 /* ATAPI packet command flags */
@@ -360,11 +362,7 @@ struct ide_atapi_pc {
 
         /* data buffer */
         u8 *buf;
-        /* current buffer position */
-        u8 *cur_pos;
         int buf_size;
-        /* missing/available data on the current buffer */
-        int b_count;
 
         /* the corresponding request */
         struct request *rq;
@@ -377,10 +375,6 @@ struct ide_atapi_pc {
          */
         u8 pc_buf[IDE_PC_BUFFER_SIZE];
 
-        /* idetape only */
-        struct idetape_bh *bh;
-        char *b_data;
-
         unsigned long timeout;
 };
 
@@ -593,16 +587,16 @@ struct ide_drive_s {
         /* callback for packet commands */
         int  (*pc_callback)(struct ide_drive_s *, int);
 
-        void (*pc_update_buffers)(struct ide_drive_s *, struct ide_atapi_pc *);
-        int  (*pc_io_buffers)(struct ide_drive_s *, struct ide_atapi_pc *,
-                              unsigned int, int);
-
         ide_startstop_t (*irq_handler)(struct ide_drive_s *);
 
         unsigned long atapi_flags;
 
         struct ide_atapi_pc request_sense_pc;
-        struct request request_sense_rq;
+
+        /* current sense rq and buffer */
+        bool sense_rq_armed;
+        struct request sense_rq;
+        struct request_sense sense_data;
 };
 
 typedef struct ide_drive_s ide_drive_t;
@@ -1109,7 +1103,7 @@ void ide_fix_driveid(u16 *);
 
 extern void ide_fixstring(u8 *, const int, const int);
 
-int ide_busy_sleep(ide_hwif_t *, unsigned long, int);
+int ide_busy_sleep(ide_drive_t *, unsigned long, int);
 
 int ide_wait_stat(ide_startstop_t *, ide_drive_t *, u8, u8, unsigned long);
 
@@ -1174,7 +1168,10 @@ int ide_do_test_unit_ready(ide_drive_t *, struct gendisk *);
 int ide_do_start_stop(ide_drive_t *, struct gendisk *, int);
 int ide_set_media_lock(ide_drive_t *, struct gendisk *, int);
 void ide_create_request_sense_cmd(ide_drive_t *, struct ide_atapi_pc *);
-void ide_retry_pc(ide_drive_t *, struct gendisk *);
+void ide_retry_pc(ide_drive_t *drive);
+
+void ide_prep_sense(ide_drive_t *drive, struct request *rq);
+int ide_queue_sense_rq(ide_drive_t *drive, void *special);
 
 int ide_cd_expiry(ide_drive_t *);
 
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 0e2aa45cb0ce..b1b827d091a9 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -13,14 +13,17 @@
 #include <linux/fs.h>
 struct linux_binprm;
 
+#define IMA_COUNT_UPDATE 1
+#define IMA_COUNT_LEAVE 0
+
 #ifdef CONFIG_IMA
 extern int ima_bprm_check(struct linux_binprm *bprm);
 extern int ima_inode_alloc(struct inode *inode);
 extern void ima_inode_free(struct inode *inode);
-extern int ima_path_check(struct path *path, int mask);
+extern int ima_path_check(struct path *path, int mask, int update_counts);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
-extern void ima_shm_check(struct file *file);
+extern void ima_counts_get(struct file *file);
 
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
@@ -38,7 +41,7 @@ static inline void ima_inode_free(struct inode *inode)
         return;
 }
 
-static inline int ima_path_check(struct path *path, int mask)
+static inline int ima_path_check(struct path *path, int mask, int update_counts)
 {
         return 0;
 }
@@ -53,7 +56,7 @@ static inline int ima_file_mmap(struct file *file, unsigned long prot)
         return 0;
 }
 
-static inline void ima_shm_check(struct file *file)
+static inline void ima_counts_get(struct file *file)
 {
         return;
 }
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index d87247d2641f..28b1f30601b5 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -108,6 +108,15 @@ extern struct group_info init_groups;
 
 extern struct cred init_cred;
 
+#ifdef CONFIG_PERF_COUNTERS
+# define INIT_PERF_COUNTERS(tsk)                                        \
+        .perf_counter_mutex =                                           \
+                 __MUTEX_INITIALIZER(tsk.perf_counter_mutex),           \
+        .perf_counter_list = LIST_HEAD_INIT(tsk.perf_counter_list),
+#else
+# define INIT_PERF_COUNTERS(tsk)
+#endif
+
 /*
  *  INIT_TASK is used to set up the first task table, touch at
  * your own risk!. Base=0, limit=0x1fffff (=2MB)
@@ -145,8 +154,8 @@ extern struct cred init_cred;
         .group_leader   = &tsk,                                         \
         .real_cred      = &init_cred,                                   \
         .cred           = &init_cred,                                   \
-        .cred_exec_mutex =                                              \
-                 __MUTEX_INITIALIZER(tsk.cred_exec_mutex),              \
+        .cred_guard_mutex =                                             \
+                 __MUTEX_INITIALIZER(tsk.cred_guard_mutex),             \
         .comm           = "swapper",                                    \
         .thread         = INIT_THREAD,                                  \
         .fs             = &init_fs,                                     \
@@ -171,9 +180,11 @@ extern struct cred init_cred;
         },                                                              \
         .dirties = INIT_PROP_LOCAL_SINGLE(dirties),                     \
         INIT_IDS                                                        \
+        INIT_PERF_COUNTERS(tsk)                                         \
         INIT_TRACE_IRQFLAGS                                             \
         INIT_LOCKDEP                                                    \
         INIT_FTRACE_GRAPH                                               \
+        INIT_TRACE_RECURSION                                            \
 }
 
 
diff --git a/include/linux/input.h b/include/linux/input.h
index 0e6ff5de3588..6fed4f6a9c9e 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -656,6 +656,7 @@ struct input_absinfo {
 #define ABS_MT_POSITION_Y       0x36    /* Center Y ellipse position */
 #define ABS_MT_TOOL_TYPE        0x37    /* Type of touching device */
 #define ABS_MT_BLOB_ID          0x38    /* Group a set of packets as a blob */
+#define ABS_MT_TRACKING_ID      0x39    /* Unique ID of initiated contact */
 
 #define ABS_MAX                 0x3f
 #define ABS_CNT                 (ABS_MAX+1)
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index 91bb76f44f14..ff374ceface0 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -566,6 +566,6 @@ struct irq_desc;
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
-extern int arch_init_chip_data(struct irq_desc *desc, int cpu);
+extern int arch_init_chip_data(struct irq_desc *desc, int node);
 
 #endif
diff --git a/include/linux/iocontext.h b/include/linux/iocontext.h
index 08b987bccf89..dd05434fa45f 100644
--- a/include/linux/iocontext.h
+++ b/include/linux/iocontext.h
@@ -64,7 +64,7 @@ struct cfq_io_context {
  * and kmalloc'ed. These could be shared between processes.
  */
 struct io_context {
-        atomic_t refcount;
+        atomic_long_t refcount;
         atomic_t nr_tasks;
 
         /* all the fields below are protected by this lock */
@@ -91,8 +91,8 @@ static inline struct io_context *ioc_task_link(struct io_context *ioc)
          * if ref count is zero, don't allow sharing (ioc is going away, it's
          * a race).
          */
-        if (ioc && atomic_inc_not_zero(&ioc->refcount)) {
-                atomic_inc(&ioc->nr_tasks);
+        if (ioc && atomic_long_inc_not_zero(&ioc->refcount)) {
+                atomic_long_inc(&ioc->refcount);
                 return ioc;
         }
 
diff --git a/include/linux/irq.h b/include/linux/irq.h
index b7cbeed972e4..1e50c34f0062 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -117,7 +117,7 @@ struct irq_chip {
         void            (*eoi)(unsigned int irq);
 
         void            (*end)(unsigned int irq);
-        void            (*set_affinity)(unsigned int irq,
+        int             (*set_affinity)(unsigned int irq,
                                         const struct cpumask *dest);
         int             (*retrigger)(unsigned int irq);
         int             (*set_type)(unsigned int irq, unsigned int flow_type);
@@ -187,7 +187,7 @@ struct irq_desc {
         spinlock_t              lock;
 #ifdef CONFIG_SMP
         cpumask_var_t           affinity;
-        unsigned int            cpu;
+        unsigned int            node;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
         cpumask_var_t           pending_mask;
 #endif
@@ -201,26 +201,23 @@ struct irq_desc {
 } ____cacheline_internodealigned_in_smp;
 
 extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
-                                        struct irq_desc *desc, int cpu);
+                                        struct irq_desc *desc, int node);
 extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
 
 #ifndef CONFIG_SPARSE_IRQ
 extern struct irq_desc irq_desc[NR_IRQS];
-#else /* CONFIG_SPARSE_IRQ */
-extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int cpu);
-#endif /* CONFIG_SPARSE_IRQ */
-
-extern struct irq_desc *irq_to_desc_alloc_cpu(unsigned int irq, int cpu);
+#endif
 
-static inline struct irq_desc *
-irq_remap_to_desc(unsigned int irq, struct irq_desc *desc)
-{
-#ifdef CONFIG_NUMA_MIGRATE_IRQ_DESC
-        return irq_to_desc(irq);
+#ifdef CONFIG_NUMA_IRQ_DESC
+extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
 #else
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
         return desc;
-#endif
 }
+#endif
+
+extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
 
 /*
  * Migration helpers for obsolete names, they will go away:
@@ -386,7 +383,7 @@ extern void set_irq_noprobe(unsigned int irq);
 extern void set_irq_probe(unsigned int irq);
 
 /* Handle dynamic irq creation and destruction */
-extern unsigned int create_irq_nr(unsigned int irq_want);
+extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
@@ -424,47 +421,44 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 
 #ifdef CONFIG_SMP
 /**
- * init_alloc_desc_masks - allocate cpumasks for irq_desc
+ * alloc_desc_masks - allocate cpumasks for irq_desc
  * @desc:       pointer to irq_desc struct
  * @cpu:        cpu which will be handling the cpumasks
  * @boot:       true if need bootmem
  *
  * Allocates affinity and pending_mask cpumask if required.
  * Returns true if successful (or not required).
- * Side effect: affinity has all bits set, pending_mask has all bits clear.
  */
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
-                                                                bool boot)
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
+                                                        bool boot)
 {
-        int node;
-
-        if (boot) {
-                alloc_bootmem_cpumask_var(&desc->affinity);
-                cpumask_setall(desc->affinity);
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-                alloc_bootmem_cpumask_var(&desc->pending_mask);
-                cpumask_clear(desc->pending_mask);
-#endif
-                return true;
-        }
+        gfp_t gfp = GFP_ATOMIC;
 
-        node = cpu_to_node(cpu);
+        if (boot)
+                gfp = GFP_NOWAIT;
 
-        if (!alloc_cpumask_var_node(&desc->affinity, GFP_ATOMIC, node))
+#ifdef CONFIG_CPUMASK_OFFSTACK
+        if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
                 return false;
-        cpumask_setall(desc->affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
-        if (!alloc_cpumask_var_node(&desc->pending_mask, GFP_ATOMIC, node)) {
+        if (!alloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
                 free_cpumask_var(desc->affinity);
                 return false;
         }
-        cpumask_clear(desc->pending_mask);
+#endif
 #endif
         return true;
 }
 
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+        cpumask_setall(desc->affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+        cpumask_clear(desc->pending_mask);
+#endif
+}
+
 /**
  * init_copy_desc_masks - copy cpumasks for irq_desc
  * @old_desc:   pointer to old irq_desc struct
@@ -478,7 +472,7 @@ static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
 static inline void init_copy_desc_masks(struct irq_desc *old_desc,
                                         struct irq_desc *new_desc)
 {
-#ifdef CONFIG_CPUMASKS_OFFSTACK
+#ifdef CONFIG_CPUMASK_OFFSTACK
         cpumask_copy(new_desc->affinity, old_desc->affinity);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -499,12 +493,16 @@ static inline void free_desc_masks(struct irq_desc *old_desc,
 
 #else /* !CONFIG_SMP */
 
-static inline bool init_alloc_desc_masks(struct irq_desc *desc, int cpu,
+static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
                                                                 bool boot)
 {
         return true;
 }
 
+static inline void init_desc_masks(struct irq_desc *desc)
+{
+}
+
 static inline void init_copy_desc_masks(struct irq_desc *old_desc,
                                         struct irq_desc *new_desc)
 {
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 0c8b89f28a95..a77c6007dc99 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -81,7 +81,12 @@ static inline unsigned int kstat_irqs(unsigned int irq)
         return sum;
 }
 
+
+/*
+ * Lock/unlock the current runqueue - to extract task statistics:
+ */
 extern unsigned long long task_delta_exec(struct task_struct *);
+
 extern void account_user_time(struct task_struct *, cputime_t, cputime_t);
 extern void account_system_time(struct task_struct *, int, cputime_t, cputime_t);
 extern void account_steal_time(cputime_t);
diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
new file mode 100644
index 000000000000..7796aed6cdd5
--- /dev/null
+++ b/include/linux/kmemleak.h
@@ -0,0 +1,96 @@
+/*
+ * include/linux/kmemleak.h
+ *
+ * Copyright (C) 2008 ARM Limited
+ * Written by Catalin Marinas <catalin.marinas@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef __KMEMLEAK_H
+#define __KMEMLEAK_H
+
+#ifdef CONFIG_DEBUG_KMEMLEAK
+
+extern void kmemleak_init(void);
+extern void kmemleak_alloc(const void *ptr, size_t size, int min_count,
+                           gfp_t gfp);
+extern void kmemleak_free(const void *ptr);
+extern void kmemleak_padding(const void *ptr, unsigned long offset,
+                             size_t size);
+extern void kmemleak_not_leak(const void *ptr);
+extern void kmemleak_ignore(const void *ptr);
+extern void kmemleak_scan_area(const void *ptr, unsigned long offset,
+                               size_t length, gfp_t gfp);
+extern void kmemleak_no_scan(const void *ptr);
+
+static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
+                                            int min_count, unsigned long flags,
+                                            gfp_t gfp)
+{
+        if (!(flags & SLAB_NOLEAKTRACE))
+                kmemleak_alloc(ptr, size, min_count, gfp);
+}
+
+static inline void kmemleak_free_recursive(const void *ptr, unsigned long flags)
+{
+        if (!(flags & SLAB_NOLEAKTRACE))
+                kmemleak_free(ptr);
+}
+
+static inline void kmemleak_erase(void **ptr)
+{
+        *ptr = NULL;
+}
+
+#else
+
+static inline void kmemleak_init(void)
+{
+}
+static inline void kmemleak_alloc(const void *ptr, size_t size, int min_count,
+                                  gfp_t gfp)
+{
+}
+static inline void kmemleak_alloc_recursive(const void *ptr, size_t size,
+                                            int min_count, unsigned long flags,
+                                            gfp_t gfp)
+{
+}
+static inline void kmemleak_free(const void *ptr)
+{
+}
+static inline void kmemleak_free_recursive(const void *ptr, unsigned long flags)
+{
+}
+static inline void kmemleak_not_leak(const void *ptr)
+{
+}
+static inline void kmemleak_ignore(const void *ptr)
+{
+}
+static inline void kmemleak_scan_area(const void *ptr, unsigned long offset,
+                                      size_t length, gfp_t gfp)
+{
+}
+static inline void kmemleak_erase(void **ptr)
+{
+}
+static inline void kmemleak_no_scan(const void *ptr)
+{
+}
+
+#endif  /* CONFIG_DEBUG_KMEMLEAK */
+
+#endif  /* __KMEMLEAK_H */
diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h
new file mode 100644
index 000000000000..b616d3930c3b
--- /dev/null
+++ b/include/linux/kmemtrace.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ *
+ * This file is released under GPL version 2.
+ */
+
+#ifndef _LINUX_KMEMTRACE_H
+#define _LINUX_KMEMTRACE_H
+
+#ifdef __KERNEL__
+
+#include <trace/events/kmem.h>
+
+#ifdef CONFIG_KMEMTRACE
+extern void kmemtrace_init(void);
+#else
+static inline void kmemtrace_init(void)
+{
+}
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_KMEMTRACE_H */
+
diff --git a/include/linux/kvm.h b/include/linux/kvm.h
index 8cc137911b34..3db5d8d37485 100644
--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -119,7 +119,7 @@ struct kvm_run {
                         __u32 error_code;
                 } ex;
                 /* KVM_EXIT_IO */
-                struct kvm_io {
+                struct {
 #define KVM_EXIT_IO_IN  0
 #define KVM_EXIT_IO_OUT 1
                         __u8 direction;
@@ -224,10 +224,10 @@ struct kvm_interrupt {
 /* for KVM_GET_DIRTY_LOG */
 struct kvm_dirty_log {
         __u32 slot;
-        __u32 padding;
+        __u32 padding1;
         union {
                 void __user *dirty_bitmap; /* one bit per page */
-                __u64 padding;
+                __u64 padding2;
         };
 };
 
@@ -409,6 +409,10 @@ struct kvm_trace_rec {
 #ifdef __KVM_HAVE_DEVICE_ASSIGNMENT
 #define KVM_CAP_DEVICE_DEASSIGNMENT 27
 #endif
+#ifdef __KVM_HAVE_MSIX
+#define KVM_CAP_DEVICE_MSIX 28
+#endif
+#define KVM_CAP_ASSIGN_DEV_IRQ 29
 /* Another bug in KVM_SET_USER_MEMORY_REGION fixed: */
 #define KVM_CAP_JOIN_MEMORY_REGIONS_WORKS 30
 
@@ -482,11 +486,18 @@ struct kvm_irq_routing {
 #define KVM_ASSIGN_PCI_DEVICE _IOR(KVMIO, 0x69, \
                                    struct kvm_assigned_pci_dev)
 #define KVM_SET_GSI_ROUTING       _IOW(KVMIO, 0x6a, struct kvm_irq_routing)
+/* deprecated, replaced by KVM_ASSIGN_DEV_IRQ */
 #define KVM_ASSIGN_IRQ _IOR(KVMIO, 0x70, \
                             struct kvm_assigned_irq)
+#define KVM_ASSIGN_DEV_IRQ        _IOW(KVMIO, 0x70, struct kvm_assigned_irq)
 #define KVM_REINJECT_CONTROL      _IO(KVMIO, 0x71)
 #define KVM_DEASSIGN_PCI_DEVICE _IOW(KVMIO, 0x72, \
                                      struct kvm_assigned_pci_dev)
+#define KVM_ASSIGN_SET_MSIX_NR \
+                        _IOW(KVMIO, 0x73, struct kvm_assigned_msix_nr)
+#define KVM_ASSIGN_SET_MSIX_ENTRY \
+                        _IOW(KVMIO, 0x74, struct kvm_assigned_msix_entry)
+#define KVM_DEASSIGN_DEV_IRQ       _IOW(KVMIO, 0x75, struct kvm_assigned_irq)
 
 /*
  * ioctls for vcpu fds
@@ -577,6 +588,8 @@ struct kvm_debug_guest {
 #define KVM_TRC_STLB_INVAL       (KVM_TRC_HANDLER + 0x18)
 #define KVM_TRC_PPC_INSTR        (KVM_TRC_HANDLER + 0x19)
 
+#define KVM_DEV_ASSIGN_ENABLE_IOMMU     (1 << 0)
+
 struct kvm_assigned_pci_dev {
         __u32 assigned_dev_id;
         __u32 busnr;
@@ -587,6 +600,17 @@ struct kvm_assigned_pci_dev {
         };
 };
 
+#define KVM_DEV_IRQ_HOST_INTX    (1 << 0)
+#define KVM_DEV_IRQ_HOST_MSI     (1 << 1)
+#define KVM_DEV_IRQ_HOST_MSIX    (1 << 2)
+
+#define KVM_DEV_IRQ_GUEST_INTX   (1 << 8)
+#define KVM_DEV_IRQ_GUEST_MSI    (1 << 9)
+#define KVM_DEV_IRQ_GUEST_MSIX   (1 << 10)
+
+#define KVM_DEV_IRQ_HOST_MASK    0x00ff
+#define KVM_DEV_IRQ_GUEST_MASK   0xff00
+
 struct kvm_assigned_irq {
         __u32 assigned_dev_id;
         __u32 host_irq;
@@ -602,9 +626,19 @@ struct kvm_assigned_irq {
         };
 };
 
-#define KVM_DEV_ASSIGN_ENABLE_IOMMU     (1 << 0)
 
-#define KVM_DEV_IRQ_ASSIGN_MSI_ACTION   KVM_DEV_IRQ_ASSIGN_ENABLE_MSI
-#define KVM_DEV_IRQ_ASSIGN_ENABLE_MSI   (1 << 0)
+struct kvm_assigned_msix_nr {
+        __u32 assigned_dev_id;
+        __u16 entry_nr;
+        __u16 padding;
+};
+
+#define KVM_MAX_MSIX_PER_DEV            512
+struct kvm_assigned_msix_entry {
+        __u32 assigned_dev_id;
+        __u32 gsi;
+        __u16 entry; /* The index of entry in the MSI-X table */
+        __u16 padding[3];
+};
 
 #endif
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 894a56e365e8..aacc5449f586 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -38,6 +38,7 @@
 #define KVM_REQ_UNHALT             6
 #define KVM_REQ_MMU_SYNC           7
 #define KVM_REQ_KVMCLOCK_UPDATE    8
+#define KVM_REQ_KICK               9
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID     0
 
@@ -72,7 +73,6 @@ struct kvm_vcpu {
         struct mutex mutex;
         int   cpu;
         struct kvm_run *run;
-        int guest_mode;
         unsigned long requests;
         unsigned long guest_debug;
         int fpu_active;
@@ -298,6 +298,7 @@ int kvm_arch_hardware_setup(void);
 void kvm_arch_hardware_unsetup(void);
 void kvm_arch_check_processor_compat(void *rtn);
 int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu);
+int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
 
 void kvm_free_physmem(struct kvm *kvm);
 
@@ -319,6 +320,13 @@ struct kvm_irq_ack_notifier {
         void (*irq_acked)(struct kvm_irq_ack_notifier *kian);
 };
 
+#define KVM_ASSIGNED_MSIX_PENDING               0x1
+struct kvm_guest_msix_entry {
+        u32 vector;
+        u16 entry;
+        u16 flags;
+};
+
 struct kvm_assigned_dev_kernel {
         struct kvm_irq_ack_notifier ack_notifier;
         struct work_struct interrupt_work;
@@ -326,18 +334,18 @@ struct kvm_assigned_dev_kernel {
         int assigned_dev_id;
         int host_busnr;
         int host_devfn;
+        unsigned int entries_nr;
         int host_irq;
         bool host_irq_disabled;
+        struct msix_entry *host_msix_entries;
         int guest_irq;
-#define KVM_ASSIGNED_DEV_GUEST_INTX     (1 << 0)
-#define KVM_ASSIGNED_DEV_GUEST_MSI      (1 << 1)
-#define KVM_ASSIGNED_DEV_HOST_INTX      (1 << 8)
-#define KVM_ASSIGNED_DEV_HOST_MSI       (1 << 9)
+        struct kvm_guest_msix_entry *guest_msix_entries;
         unsigned long irq_requested_type;
         int irq_source_id;
         int flags;
         struct pci_dev *dev;
         struct kvm *kvm;
+        spinlock_t assigned_dev_lock;
 };
 
 struct kvm_irq_mask_notifier {
@@ -360,6 +368,9 @@ void kvm_unregister_irq_ack_notifier(struct kvm_irq_ack_notifier *kian);
 int kvm_request_irq_source_id(struct kvm *kvm);
 void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 
+/* For vcpu->arch.iommu_flags */
+#define KVM_IOMMU_CACHE_COHERENCY       0x1
+
 #ifdef CONFIG_IOMMU_API
 int kvm_iommu_map_pages(struct kvm *kvm, gfn_t base_gfn,
                         unsigned long npages);
diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h
index 2b8318c83e53..fb46efbeabec 100644
--- a/include/linux/kvm_types.h
+++ b/include/linux/kvm_types.h
@@ -40,4 +40,31 @@ typedef unsigned long  hfn_t;
 
 typedef hfn_t pfn_t;
 
+union kvm_ioapic_redirect_entry {
+        u64 bits;
+        struct {
+                u8 vector;
+                u8 delivery_mode:3;
+                u8 dest_mode:1;
+                u8 delivery_status:1;
+                u8 polarity:1;
+                u8 remote_irr:1;
+                u8 trig_mode:1;
+                u8 mask:1;
+                u8 reserve:7;
+                u8 reserved[4];
+                u8 dest_id;
+        } fields;
+};
+
+struct kvm_lapic_irq {
+        u32 vector;
+        u32 delivery_mode;
+        u32 dest_mode;
+        u32 level;
+        u32 trig_mode;
+        u32 shorthand;
+        u32 dest_id;
+};
+
 #endif /* __KVM_TYPES_H__ */
diff --git a/include/linux/loop.h b/include/linux/loop.h
index 40725447f5e0..66c194e2d9b9 100644
--- a/include/linux/loop.h
+++ b/include/linux/loop.h
@@ -56,8 +56,7 @@ struct loop_device {
         gfp_t           old_gfp_mask;
 
         spinlock_t              lo_lock;
-        struct bio              *lo_bio;
-        struct bio              *lo_biotail;
+        struct bio_list         lo_bio_list;
         int                     lo_state;
         struct mutex            lo_ctl_mutex;
         struct task_struct      *lo_thread;
diff --git a/include/linux/lsm_audit.h b/include/linux/lsm_audit.h
new file mode 100644
index 000000000000..e461b2c3d711
--- /dev/null
+++ b/include/linux/lsm_audit.h
@@ -0,0 +1,111 @@
+/*
+ * Common LSM logging functions
+ * Heavily borrowed from selinux/avc.h
+ *
+ * Author : Etienne BASSET  <etienne.basset@ensta.org>
+ *
+ * All credits to : Stephen Smalley, <sds@epoch.ncsc.mil>
+ * All BUGS to : Etienne BASSET  <etienne.basset@ensta.org>
+ */
+#ifndef _LSM_COMMON_LOGGING_
+#define _LSM_COMMON_LOGGING_
+
+#include <linux/stddef.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/kdev_t.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/audit.h>
+#include <linux/in6.h>
+#include <linux/path.h>
+#include <linux/key.h>
+#include <linux/skbuff.h>
+#include <asm/system.h>
+
+
+/* Auxiliary data to use in generating the audit record. */
+struct common_audit_data {
+        char    type;
+#define LSM_AUDIT_DATA_FS      1
+#define LSM_AUDIT_DATA_NET     2
+#define LSM_AUDIT_DATA_CAP     3
+#define LSM_AUDIT_DATA_IPC     4
+#define LSM_AUDIT_DATA_TASK    5
+#define LSM_AUDIT_DATA_KEY     6
+        struct task_struct *tsk;
+        union   {
+                struct {
+                        struct path path;
+                        struct inode *inode;
+                } fs;
+                struct {
+                        int netif;
+                        struct sock *sk;
+                        u16 family;
+                        __be16 dport;
+                        __be16 sport;
+                        union {
+                                struct {
+                                        __be32 daddr;
+                                        __be32 saddr;
+                                } v4;
+                                struct {
+                                        struct in6_addr daddr;
+                                        struct in6_addr saddr;
+                                } v6;
+                        } fam;
+                } net;
+                int cap;
+                int ipc_id;
+                struct task_struct *tsk;
+#ifdef CONFIG_KEYS
+                struct {
+                        key_serial_t key;
+                        char *key_desc;
+                } key_struct;
+#endif
+        } u;
+        const char *function;
+        /* this union contains LSM specific data */
+        union {
+                /* SMACK data */
+                struct smack_audit_data {
+                        char *subject;
+                        char *object;
+                        char *request;
+                        int result;
+                } smack_audit_data;
+                /* SELinux data */
+                struct {
+                        u32 ssid;
+                        u32 tsid;
+                        u16 tclass;
+                        u32 requested;
+                        u32 audited;
+                        struct av_decision *avd;
+                        int result;
+                } selinux_audit_data;
+        } lsm_priv;
+        /* these callback will be implemented by a specific LSM */
+        void (*lsm_pre_audit)(struct audit_buffer *, void *);
+        void (*lsm_post_audit)(struct audit_buffer *, void *);
+};
+
+#define v4info fam.v4
+#define v6info fam.v6
+
+int ipv4_skb_to_auditdata(struct sk_buff *skb,
+                struct common_audit_data *ad, u8 *proto);
+
+int ipv6_skb_to_auditdata(struct sk_buff *skb,
+                struct common_audit_data *ad, u8 *proto);
+
+/* Initialize an LSM audit data structure. */
+#define COMMON_AUDIT_DATA_INIT(_d, _t) \
+        { memset((_d), 0, sizeof(struct common_audit_data)); \
+         (_d)->type = LSM_AUDIT_DATA_##_t; (_d)->function = __func__; }
+
+void common_lsm_audit(struct common_audit_data *a);
+
+#endif
diff --git a/include/linux/magic.h b/include/linux/magic.h
index 5b4e28bcb788..1923327b9869 100644
--- a/include/linux/magic.h
+++ b/include/linux/magic.h
@@ -6,9 +6,12 @@
 #define AFS_SUPER_MAGIC                0x5346414F
 #define AUTOFS_SUPER_MAGIC      0x0187
 #define CODA_SUPER_MAGIC        0x73757245
+#define CRAMFS_MAGIC            0x28cd3d45      /* some random number */
+#define CRAMFS_MAGIC_WEND       0x453dcd28      /* magic number with the wrong endianess */
 #define DEBUGFS_MAGIC          0x64626720
 #define SYSFS_MAGIC             0x62656572
 #define SECURITYFS_MAGIC        0x73636673
+#define SELINUX_MAGIC           0xf97cff8c
 #define TMPFS_MAGIC             0x01021994
 #define SQUASHFS_MAGIC          0x73717368
 #define EFS_SUPER_MAGIC         0x414A53
diff --git a/include/linux/mg_disk.h b/include/linux/mg_disk.h
deleted file mode 100644
index 1f76b1ebf627..000000000000
--- a/include/linux/mg_disk.h
+++ /dev/null
@@ -1,206 +0,0 @@
-/*
- *  include/linux/mg_disk.c
- *
- *  Support for the mGine m[g]flash IO mode.
- *  Based on legacy hd.c
- *
- * (c) 2008 mGine Co.,LTD
- * (c) 2008 unsik Kim <donari75@gmail.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2 as
- *  published by the Free Software Foundation.
- */
-
-#ifndef __MG_DISK_H__
-#define __MG_DISK_H__
-
-#include <linux/blkdev.h>
-#include <linux/ata.h>
-
-/* name for block device */
-#define MG_DISK_NAME "mgd"
-/* name for platform device */
-#define MG_DEV_NAME "mg_disk"
-
-#define MG_DISK_MAJ 0
-#define MG_DISK_MAX_PART 16
-#define MG_SECTOR_SIZE 512
-#define MG_MAX_SECTS 256
-
-/* Register offsets */
-#define MG_BUFF_OFFSET                  0x8000
-#define MG_STORAGE_BUFFER_SIZE          0x200
-#define MG_REG_OFFSET                   0xC000
-#define MG_REG_FEATURE                  (MG_REG_OFFSET + 2)     /* write case */
-#define MG_REG_ERROR                    (MG_REG_OFFSET + 2)     /* read case */
-#define MG_REG_SECT_CNT                 (MG_REG_OFFSET + 4)
-#define MG_REG_SECT_NUM                 (MG_REG_OFFSET + 6)
-#define MG_REG_CYL_LOW                  (MG_REG_OFFSET + 8)
-#define MG_REG_CYL_HIGH                 (MG_REG_OFFSET + 0xA)
-#define MG_REG_DRV_HEAD                 (MG_REG_OFFSET + 0xC)
-#define MG_REG_COMMAND                  (MG_REG_OFFSET + 0xE)   /* write case */
-#define MG_REG_STATUS                   (MG_REG_OFFSET + 0xE)   /* read  case */
-#define MG_REG_DRV_CTRL                 (MG_REG_OFFSET + 0x10)
-#define MG_REG_BURST_CTRL               (MG_REG_OFFSET + 0x12)
-
-/* "Drive Select/Head Register" bit values */
-#define MG_REG_HEAD_MUST_BE_ON          0xA0 /* These 2 bits are always on */
-#define MG_REG_HEAD_DRIVE_MASTER        (0x00 | MG_REG_HEAD_MUST_BE_ON)
-#define MG_REG_HEAD_DRIVE_SLAVE         (0x10 | MG_REG_HEAD_MUST_BE_ON)
-#define MG_REG_HEAD_LBA_MODE            (0x40 | MG_REG_HEAD_MUST_BE_ON)
-
-
-/* "Device Control Register" bit values */
-#define MG_REG_CTRL_INTR_ENABLE                 0x0
-#define MG_REG_CTRL_INTR_DISABLE                (0x1<<1)
-#define MG_REG_CTRL_RESET                       (0x1<<2)
-#define MG_REG_CTRL_INTR_POLA_ACTIVE_HIGH       0x0
-#define MG_REG_CTRL_INTR_POLA_ACTIVE_LOW        (0x1<<4)
-#define MG_REG_CTRL_DPD_POLA_ACTIVE_LOW         0x0
-#define MG_REG_CTRL_DPD_POLA_ACTIVE_HIGH        (0x1<<5)
-#define MG_REG_CTRL_DPD_DISABLE                 0x0
-#define MG_REG_CTRL_DPD_ENABLE                  (0x1<<6)
-
-/* Status register bit */
-/* error bit in status register */
-#define MG_REG_STATUS_BIT_ERROR                 0x01
-/* corrected error in status register */
-#define MG_REG_STATUS_BIT_CORRECTED_ERROR       0x04
-/* data request bit in status register */
-#define MG_REG_STATUS_BIT_DATA_REQ              0x08
-/* DSC - Drive Seek Complete */
-#define MG_REG_STATUS_BIT_SEEK_DONE             0x10
-/* DWF - Drive Write Fault */
-#define MG_REG_STATUS_BIT_WRITE_FAULT           0x20
-#define MG_REG_STATUS_BIT_READY                 0x40
-#define MG_REG_STATUS_BIT_BUSY                  0x80
-
-/* handy status */
-#define MG_STAT_READY   (MG_REG_STATUS_BIT_READY | MG_REG_STATUS_BIT_SEEK_DONE)
-#define MG_READY_OK(s)  (((s) & (MG_STAT_READY | \
-                                (MG_REG_STATUS_BIT_BUSY | \
-                                 MG_REG_STATUS_BIT_WRITE_FAULT | \
-                                 MG_REG_STATUS_BIT_ERROR))) == MG_STAT_READY)
-
-/* Error register */
-#define MG_REG_ERR_AMNF         0x01
-#define MG_REG_ERR_ABRT         0x04
-#define MG_REG_ERR_IDNF         0x10
-#define MG_REG_ERR_UNC          0x40
-#define MG_REG_ERR_BBK          0x80
-
-/* error code for others */
-#define MG_ERR_NONE             0
-#define MG_ERR_TIMEOUT          0x100
-#define MG_ERR_INIT_STAT        0x101
-#define MG_ERR_TRANSLATION      0x102
-#define MG_ERR_CTRL_RST         0x103
-#define MG_ERR_INV_STAT         0x104
-#define MG_ERR_RSTOUT           0x105
-
-#define MG_MAX_ERRORS   6       /* Max read/write errors */
-
-/* command */
-#define MG_CMD_RD 0x20
-#define MG_CMD_WR 0x30
-#define MG_CMD_SLEEP 0x99
-#define MG_CMD_WAKEUP 0xC3
-#define MG_CMD_ID 0xEC
-#define MG_CMD_WR_CONF 0x3C
-#define MG_CMD_RD_CONF 0x40
-
-/* operation mode */
-#define MG_OP_CASCADE (1 << 0)
-#define MG_OP_CASCADE_SYNC_RD (1 << 1)
-#define MG_OP_CASCADE_SYNC_WR (1 << 2)
-#define MG_OP_INTERLEAVE (1 << 3)
-
-/* synchronous */
-#define MG_BURST_LAT_4 (3 << 4)
-#define MG_BURST_LAT_5 (4 << 4)
-#define MG_BURST_LAT_6 (5 << 4)
-#define MG_BURST_LAT_7 (6 << 4)
-#define MG_BURST_LAT_8 (7 << 4)
-#define MG_BURST_LEN_4 (1 << 1)
-#define MG_BURST_LEN_8 (2 << 1)
-#define MG_BURST_LEN_16 (3 << 1)
-#define MG_BURST_LEN_32 (4 << 1)
-#define MG_BURST_LEN_CONT (0 << 1)
-
-/* timeout value (unit: ms) */
-#define MG_TMAX_CONF_TO_CMD     1
-#define MG_TMAX_WAIT_RD_DRQ     10
-#define MG_TMAX_WAIT_WR_DRQ     500
-#define MG_TMAX_RST_TO_BUSY     10
-#define MG_TMAX_HDRST_TO_RDY    500
-#define MG_TMAX_SWRST_TO_RDY    500
-#define MG_TMAX_RSTOUT          3000
-
-/* device attribution */
-/* use mflash as boot device */
-#define MG_BOOT_DEV             (1 << 0)
-/* use mflash as storage device */
-#define MG_STORAGE_DEV          (1 << 1)
-/* same as MG_STORAGE_DEV, but bootloader already done reset sequence */
-#define MG_STORAGE_DEV_SKIP_RST (1 << 2)
-
-#define MG_DEV_MASK (MG_BOOT_DEV | MG_STORAGE_DEV | MG_STORAGE_DEV_SKIP_RST)
-
-/* names of GPIO resource */
-#define MG_RST_PIN      "mg_rst"
-/* except MG_BOOT_DEV, reset-out pin should be assigned */
-#define MG_RSTOUT_PIN   "mg_rstout"
-
-/* private driver data */
-struct mg_drv_data {
-        /* disk resource */
-        u32 use_polling;
-
-        /* device attribution */
-        u32 dev_attr;
-
-        /* internally used */
-        struct mg_host *host;
-};
-
-/* main structure for mflash driver */
-struct mg_host {
-        struct device *dev;
-
-        struct request_queue *breq;
-        spinlock_t lock;
-        struct gendisk *gd;
-
-        struct timer_list timer;
-        void (*mg_do_intr) (struct mg_host *);
-
-        u16 id[ATA_ID_WORDS];
-
-        u16 cyls;
-        u16 heads;
-        u16 sectors;
-        u32 n_sectors;
-        u32 nres_sectors;
-
-        void __iomem *dev_base;
-        unsigned int irq;
-        unsigned int rst;
-        unsigned int rstout;
-
-        u32 major;
-        u32 error;
-};
-
-/*
- * Debugging macro and defines
- */
-#undef DO_MG_DEBUG
-#ifdef DO_MG_DEBUG
-#  define MG_DBG(fmt, args...) \
-        printk(KERN_DEBUG "%s:%d "fmt, __func__, __LINE__, ##args)
-#else /* CONFIG_MG_DEBUG */
-#  define MG_DBG(fmt, args...) do { } while (0)
-#endif /* CONFIG_MG_DEBUG */
-
-#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index bff1f0d475c7..ad613ed66ab0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,6 +19,7 @@ struct anon_vma;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
+struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -580,12 +581,10 @@ static inline void set_page_links(struct page *page, enum zone_type zone,
  */
 static inline unsigned long round_hint_to_min(unsigned long hint)
 {
-#ifdef CONFIG_SECURITY
         hint &= PAGE_MASK;
         if (((void *)hint != NULL) &&
             (hint < mmap_min_addr))
                 return PAGE_ALIGN(mmap_min_addr);
-#endif
         return hint;
 }
 
@@ -1031,8 +1030,6 @@ extern void add_active_range(unsigned int nid, unsigned long start_pfn,
                                         unsigned long end_pfn);
 extern void remove_active_range(unsigned int nid, unsigned long start_pfn,
                                         unsigned long end_pfn);
-extern void push_node_boundaries(unsigned int nid, unsigned long start_pfn,
-                                        unsigned long end_pfn);
 extern void remove_all_active_ranges(void);
 extern unsigned long absent_pages_in_range(unsigned long start_pfn,
                                                 unsigned long end_pfn);
@@ -1319,8 +1316,8 @@ int vmemmap_populate_basepages(struct page *start_page,
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern void *alloc_locked_buffer(size_t size);
-extern void free_locked_buffer(void *buffer, size_t size);
-extern void release_locked_buffer(void *buffer, size_t size);
+extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+                                 size_t size);
+extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 3d1b7bde1283..97491f78b08c 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -30,6 +30,8 @@ extern unsigned int kmmio_count;
 
 extern int register_kmmio_probe(struct kmmio_probe *p);
 extern void unregister_kmmio_probe(struct kmmio_probe *p);
+extern int kmmio_init(void);
+extern void kmmio_cleanup(void);
 
 #ifdef CONFIG_MMIOTRACE
 /* kmmio is active by some kmmio_probes? */
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 186ec6ab334d..a47c879e1304 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1097,6 +1097,32 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long);
 #define pfn_valid_within(pfn) (1)
 #endif
 
+#ifdef CONFIG_ARCH_HAS_HOLES_MEMORYMODEL
+/*
+ * pfn_valid() is meant to be able to tell if a given PFN has valid memmap
+ * associated with it or not. In FLATMEM, it is expected that holes always
+ * have valid memmap as long as there is valid PFNs either side of the hole.
+ * In SPARSEMEM, it is assumed that a valid section has a memmap for the
+ * entire section.
+ *
+ * However, an ARM, and maybe other embedded architectures in the future
+ * free memmap backing holes to save memory on the assumption the memmap is
+ * never used. The page_zone linkages are then broken even though pfn_valid()
+ * returns true. A walker of the full memmap must then do this additional
+ * check to ensure the memmap they are looking at is sane by making sure
+ * the zone and PFN linkages are still valid. This is expensive, but walkers
+ * of the full memmap are extremely rare.
+ */
+int memmap_valid_within(unsigned long pfn,
+                                        struct page *page, struct zone *zone);
+#else
+static inline int memmap_valid_within(unsigned long pfn,
+                                        struct page *page, struct zone *zone)
+{
+        return 1;
+}
+#endif /* CONFIG_ARCH_HAS_HOLES_MEMORYMODEL */
+
 #endif /* !__GENERATING_BOUNDS.H */
 #endif /* !__ASSEMBLY__ */
 #endif /* _LINUX_MMZONE_H */
diff --git a/include/linux/module.h b/include/linux/module.h
index 627ac082e2a6..a8f2c0aa4c32 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -337,6 +337,14 @@ struct module
         const char **trace_bprintk_fmt_start;
         unsigned int num_trace_bprintk_fmt;
 #endif
+#ifdef CONFIG_EVENT_TRACING
+        struct ftrace_event_call *trace_events;
+        unsigned int num_trace_events;
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+        unsigned long *ftrace_callsites;
+        unsigned int num_ftrace_callsites;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
         /* What modules depend on me? */
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 51f55f903aff..5d5275364867 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -30,7 +30,7 @@ struct mnt_namespace;
 #define MNT_STRICTATIME 0x80
 
 #define MNT_SHRINKABLE  0x100
-#define MNT_IMBALANCED_WRITE_COUNT      0x200 /* just for debugging */
+#define MNT_WRITE_HOLD  0x200
 
 #define MNT_SHARED      0x1000  /* if the vfsmount is a shared mount */
 #define MNT_UNBINDABLE  0x2000  /* if the vfsmount is a unbindable mount */
@@ -65,13 +65,22 @@ struct vfsmount {
         int mnt_expiry_mark;            /* true if marked for expiry */
         int mnt_pinned;
         int mnt_ghosts;
-        /*
-         * This value is not stable unless all of the mnt_writers[] spinlocks
-         * are held, and all mnt_writer[]s on this mount have 0 as their ->count
-         */
-        atomic_t __mnt_writers;
+#ifdef CONFIG_SMP
+        int *mnt_writers;
+#else
+        int mnt_writers;
+#endif
 };
 
+static inline int *get_mnt_writers_ptr(struct vfsmount *mnt)
+{
+#ifdef CONFIG_SMP
+        return mnt->mnt_writers;
+#else
+        return &mnt->mnt_writers;
+#endif
+}
+
 static inline struct vfsmount *mntget(struct vfsmount *mnt)
 {
         if (mnt)
@@ -79,7 +88,11 @@ static inline struct vfsmount *mntget(struct vfsmount *mnt)
         return mnt;
 }
 
+struct file; /* forward dec */
+
 extern int mnt_want_write(struct vfsmount *mnt);
+extern int mnt_want_write_file(struct file *file);
+extern int mnt_clone_write(struct vfsmount *mnt);
 extern void mnt_drop_write(struct vfsmount *mnt);
 extern void mntput_no_expire(struct vfsmount *mnt);
 extern void mnt_pin(struct vfsmount *mnt);
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 3069ec7e0ab8..878cab4f5fcc 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -150,5 +150,6 @@ extern int __must_check mutex_lock_killable(struct mutex *lock);
  */
 extern int mutex_trylock(struct mutex *lock);
 extern void mutex_unlock(struct mutex *lock);
+extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
 #endif
diff --git a/include/linux/namei.h b/include/linux/namei.h
index 518098fe63af..d870ae2faedc 100644
--- a/include/linux/namei.h
+++ b/include/linux/namei.h
@@ -18,6 +18,7 @@ enum { MAX_NESTED_LINKS = 8 };
 struct nameidata {
         struct path     path;
         struct qstr     last;
+        struct path     root;
         unsigned int    flags;
         int             last_type;
         unsigned        depth;
@@ -77,8 +78,8 @@ extern void release_open_intent(struct nameidata *);
 extern struct dentry *lookup_one_len(const char *, struct dentry *, int);
 extern struct dentry *lookup_one_noperm(const char *, struct dentry *);
 
-extern int follow_down(struct vfsmount **, struct dentry **);
-extern int follow_up(struct vfsmount **, struct dentry **);
+extern int follow_down(struct path *);
+extern int follow_up(struct path *);
 
 extern struct dentry *lock_rename(struct dentry *, struct dentry *);
 extern void unlock_rename(struct dentry *, struct dentry *);
diff --git a/include/linux/net_dropmon.h b/include/linux/net_dropmon.h
index 0217fb81a630..0e2e100c44a2 100644
--- a/include/linux/net_dropmon.h
+++ b/include/linux/net_dropmon.h
@@ -1,6 +1,7 @@
 #ifndef __NET_DROPMON_H
 #define __NET_DROPMON_H
 
+#include <linux/types.h>
 #include <linux/netlink.h>
 
 struct net_dm_drop_point {
diff --git a/include/linux/netfilter/nf_conntrack_tcp.h b/include/linux/netfilter/nf_conntrack_tcp.h
index 3066789b972a..b2f384d42611 100644
--- a/include/linux/netfilter/nf_conntrack_tcp.h
+++ b/include/linux/netfilter/nf_conntrack_tcp.h
@@ -35,6 +35,9 @@ enum tcp_conntrack {
 /* Has unacknowledged data */
 #define IP_CT_TCP_FLAG_DATA_UNACKNOWLEDGED      0x10
 
+/* The field td_maxack has been set */
+#define IP_CT_TCP_FLAG_MAXACK_SET               0x20
+
 struct nf_ct_tcp_flags {
         __u8 flags;
         __u8 mask;
@@ -46,6 +49,7 @@ struct ip_ct_tcp_state {
         u_int32_t       td_end;         /* max of seq + len */
         u_int32_t       td_maxend;      /* max of ack + max(win, 1) */
         u_int32_t       td_maxwin;      /* max(win) */
+        u_int32_t       td_maxack;      /* max of ack */
         u_int8_t        td_scale;       /* window scale factor */
         u_int8_t        flags;          /* per direction options */
 };
diff --git a/include/linux/nfsd/export.h b/include/linux/nfsd/export.h
index bcd0201589f8..a6d9ef2bb34a 100644
--- a/include/linux/nfsd/export.h
+++ b/include/linux/nfsd/export.h
@@ -125,11 +125,9 @@ void			nfsd_export_flush(void);
 void                    exp_readlock(void);
 void                    exp_readunlock(void);
 struct svc_export *     rqst_exp_get_by_name(struct svc_rqst *,
-                                             struct vfsmount *,
-                                             struct dentry *);
+                                             struct path *);
 struct svc_export *     rqst_exp_parent(struct svc_rqst *,
-                                        struct vfsmount *mnt,
-                                        struct dentry *dentry);
+                                        struct path *);
 int                     exp_rootfh(struct auth_domain *, 
                                         char *path, struct knfsd_fh *, int maxsize);
 __be32                  exp_pseudoroot(struct svc_rqst *, struct svc_fh *);
diff --git a/include/linux/parport.h b/include/linux/parport.h
index e1f83c5065c5..38a423ed3c01 100644
--- a/include/linux/parport.h
+++ b/include/linux/parport.h
@@ -324,6 +324,10 @@ struct parport {
         int spintime;
         atomic_t ref_count;
 
+        unsigned long devflags;
+#define PARPORT_DEVPROC_REGISTERED      0
+        struct pardevice *proc_device;  /* Currently register proc device */
+
         struct list_head full_list;
         struct parport *slaves[3];
 };
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index 06ba90c211a5..d7d1c41a0b17 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -1406,7 +1406,7 @@
 #define PCI_DEVICE_ID_VIA_82C598_1      0x8598
 #define PCI_DEVICE_ID_VIA_838X_1        0xB188
 #define PCI_DEVICE_ID_VIA_83_87XX_1     0xB198
-#define PCI_DEVICE_ID_VIA_C409_IDE      0XC409
+#define PCI_DEVICE_ID_VIA_VX855_IDE     0xC409
 #define PCI_DEVICE_ID_VIA_ANON          0xFFFF
 
 #define PCI_VENDOR_ID_SIEMENS           0x110A
@@ -1996,10 +1996,12 @@
 #define PCI_DEVICE_ID_OXSEMI_PCIe952_1_U        0xC118
 #define PCI_DEVICE_ID_OXSEMI_PCIe952_1_GU       0xC11C
 #define PCI_DEVICE_ID_OXSEMI_16PCI954   0x9501
+#define PCI_DEVICE_ID_OXSEMI_C950       0x950B
 #define PCI_DEVICE_ID_OXSEMI_16PCI95N   0x9511
 #define PCI_DEVICE_ID_OXSEMI_16PCI954PP 0x9513
 #define PCI_DEVICE_ID_OXSEMI_16PCI952   0x9521
 #define PCI_DEVICE_ID_OXSEMI_16PCI952PP 0x9523
+#define PCI_SUBDEVICE_ID_OXSEMI_C950    0x0001
 
 #define PCI_VENDOR_ID_CHELSIO           0x1425
 
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 1581ff235c7e..26fd9d12f050 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -86,7 +86,12 @@ struct percpu_data {
         void *ptrs[1];
 };
 
+/* pointer disguising messes up the kmemleak objects tracking */
+#ifndef CONFIG_DEBUG_KMEMLEAK
 #define __percpu_disguise(pdata) (struct percpu_data *)~(unsigned long)(pdata)
+#else
+#define __percpu_disguise(pdata) (struct percpu_data *)(pdata)
+#endif
 
 #define per_cpu_ptr(ptr, cpu)                                           \
 ({                                                                      \
diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
new file mode 100644
index 000000000000..6e133954e2e4
--- /dev/null
+++ b/include/linux/perf_counter.h
@@ -0,0 +1,697 @@
+/*
+ *  Performance counters:
+ *
+ *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2009, Red Hat, Inc., Ingo Molnar
+ *    Copyright (C) 2008-2009, Red Hat, Inc., Peter Zijlstra
+ *
+ *  Data type definitions, declarations, prototypes.
+ *
+ *    Started by: Thomas Gleixner and Ingo Molnar
+ *
+ *  For licencing details see kernel-base/COPYING
+ */
+#ifndef _LINUX_PERF_COUNTER_H
+#define _LINUX_PERF_COUNTER_H
+
+#include <linux/types.h>
+#include <linux/ioctl.h>
+#include <asm/byteorder.h>
+
+/*
+ * User-space ABI bits:
+ */
+
+/*
+ * attr.type
+ */
+enum perf_type_id {
+        PERF_TYPE_HARDWARE                      = 0,
+        PERF_TYPE_SOFTWARE                      = 1,
+        PERF_TYPE_TRACEPOINT                    = 2,
+        PERF_TYPE_HW_CACHE                      = 3,
+        PERF_TYPE_RAW                           = 4,
+
+        PERF_TYPE_MAX,                          /* non-ABI */
+};
+
+/*
+ * Generalized performance counter event types, used by the
+ * attr.event_id parameter of the sys_perf_counter_open()
+ * syscall:
+ */
+enum perf_hw_id {
+        /*
+         * Common hardware events, generalized by the kernel:
+         */
+        PERF_COUNT_HW_CPU_CYCLES                = 0,
+        PERF_COUNT_HW_INSTRUCTIONS              = 1,
+        PERF_COUNT_HW_CACHE_REFERENCES          = 2,
+        PERF_COUNT_HW_CACHE_MISSES              = 3,
+        PERF_COUNT_HW_BRANCH_INSTRUCTIONS       = 4,
+        PERF_COUNT_HW_BRANCH_MISSES             = 5,
+        PERF_COUNT_HW_BUS_CYCLES                = 6,
+
+        PERF_COUNT_HW_MAX,                      /* non-ABI */
+};
+
+/*
+ * Generalized hardware cache counters:
+ *
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x
+ *       { read, write, prefetch } x
+ *       { accesses, misses }
+ */
+enum perf_hw_cache_id {
+        PERF_COUNT_HW_CACHE_L1D                 = 0,
+        PERF_COUNT_HW_CACHE_L1I                 = 1,
+        PERF_COUNT_HW_CACHE_LL                  = 2,
+        PERF_COUNT_HW_CACHE_DTLB                = 3,
+        PERF_COUNT_HW_CACHE_ITLB                = 4,
+        PERF_COUNT_HW_CACHE_BPU                 = 5,
+
+        PERF_COUNT_HW_CACHE_MAX,                /* non-ABI */
+};
+
+enum perf_hw_cache_op_id {
+        PERF_COUNT_HW_CACHE_OP_READ             = 0,
+        PERF_COUNT_HW_CACHE_OP_WRITE            = 1,
+        PERF_COUNT_HW_CACHE_OP_PREFETCH         = 2,
+
+        PERF_COUNT_HW_CACHE_OP_MAX,             /* non-ABI */
+};
+
+enum perf_hw_cache_op_result_id {
+        PERF_COUNT_HW_CACHE_RESULT_ACCESS       = 0,
+        PERF_COUNT_HW_CACHE_RESULT_MISS         = 1,
+
+        PERF_COUNT_HW_CACHE_RESULT_MAX,         /* non-ABI */
+};
+
+/*
+ * Special "software" counters provided by the kernel, even if the hardware
+ * does not support performance counters. These counters measure various
+ * physical and sw events of the kernel (and allow the profiling of them as
+ * well):
+ */
+enum perf_sw_ids {
+        PERF_COUNT_SW_CPU_CLOCK                 = 0,
+        PERF_COUNT_SW_TASK_CLOCK                = 1,
+        PERF_COUNT_SW_PAGE_FAULTS               = 2,
+        PERF_COUNT_SW_CONTEXT_SWITCHES          = 3,
+        PERF_COUNT_SW_CPU_MIGRATIONS            = 4,
+        PERF_COUNT_SW_PAGE_FAULTS_MIN           = 5,
+        PERF_COUNT_SW_PAGE_FAULTS_MAJ           = 6,
+
+        PERF_COUNT_SW_MAX,                      /* non-ABI */
+};
+
+/*
+ * Bits that can be set in attr.sample_type to request information
+ * in the overflow packets.
+ */
+enum perf_counter_sample_format {
+        PERF_SAMPLE_IP                          = 1U << 0,
+        PERF_SAMPLE_TID                         = 1U << 1,
+        PERF_SAMPLE_TIME                        = 1U << 2,
+        PERF_SAMPLE_ADDR                        = 1U << 3,
+        PERF_SAMPLE_GROUP                       = 1U << 4,
+        PERF_SAMPLE_CALLCHAIN                   = 1U << 5,
+        PERF_SAMPLE_ID                          = 1U << 6,
+        PERF_SAMPLE_CPU                         = 1U << 7,
+        PERF_SAMPLE_PERIOD                      = 1U << 8,
+};
+
+/*
+ * 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.
+ */
+enum perf_counter_read_format {
+        PERF_FORMAT_TOTAL_TIME_ENABLED          = 1U << 0,
+        PERF_FORMAT_TOTAL_TIME_RUNNING          = 1U << 1,
+        PERF_FORMAT_ID                          = 1U << 2,
+};
+
+/*
+ * Hardware event to monitor via a performance monitoring counter:
+ */
+struct perf_counter_attr {
+        /*
+         * Major type: hardware/software/tracepoint/etc.
+         */
+        __u32                   type;
+        __u32                   __reserved_1;
+
+        /*
+         * Type specific configuration information.
+         */
+        __u64                   config;
+
+        union {
+                __u64           sample_period;
+                __u64           sample_freq;
+        };
+
+        __u64                   sample_type;
+        __u64                   read_format;
+
+        __u64                   disabled       :  1, /* off by default        */
+                                inherit        :  1, /* children inherit it   */
+                                pinned         :  1, /* must always be on PMU */
+                                exclusive      :  1, /* only group on PMU     */
+                                exclude_user   :  1, /* don't count user      */
+                                exclude_kernel :  1, /* ditto kernel          */
+                                exclude_hv     :  1, /* ditto hypervisor      */
+                                exclude_idle   :  1, /* don't count when idle */
+                                mmap           :  1, /* include mmap data     */
+                                comm           :  1, /* include comm data     */
+                                freq           :  1, /* use freq, not period  */
+
+                                __reserved_2   : 53;
+
+        __u32                   wakeup_events;  /* wakeup every n events */
+        __u32                   __reserved_3;
+
+        __u64                   __reserved_4;
+};
+
+/*
+ * Ioctls that can be done on a perf counter fd:
+ */
+#define PERF_COUNTER_IOC_ENABLE         _IO ('$', 0)
+#define PERF_COUNTER_IOC_DISABLE        _IO ('$', 1)
+#define PERF_COUNTER_IOC_REFRESH        _IO ('$', 2)
+#define PERF_COUNTER_IOC_RESET          _IO ('$', 3)
+#define PERF_COUNTER_IOC_PERIOD         _IOW('$', 4, u64)
+
+enum perf_counter_ioc_flags {
+        PERF_IOC_FLAG_GROUP             = 1U << 0,
+};
+
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_counter_mmap_page {
+        __u32   version;                /* version number of this structure */
+        __u32   compat_version;         /* lowest version this is compat with */
+
+        /*
+         * Bits needed to read the hw counters in user-space.
+         *
+         *   u32 seq;
+         *   s64 count;
+         *
+         *   do {
+         *     seq = pc->lock;
+         *
+         *     barrier()
+         *     if (pc->index) {
+         *       count = pmc_read(pc->index - 1);
+         *       count += pc->offset;
+         *     } else
+         *       goto regular_read;
+         *
+         *     barrier();
+         *   } while (pc->lock != seq);
+         *
+         * NOTE: for obvious reason this only works on self-monitoring
+         *       processes.
+         */
+        __u32   lock;                   /* seqlock for synchronization */
+        __u32   index;                  /* hardware counter identifier */
+        __s64   offset;                 /* add to hardware counter value */
+
+        /*
+         * Control data for the mmap() data buffer.
+         *
+         * User-space reading this value should issue an rmb(), on SMP capable
+         * platforms, after reading this value -- see perf_counter_wakeup().
+         */
+        __u64   data_head;              /* head in the data section */
+};
+
+#define PERF_EVENT_MISC_CPUMODE_MASK            (3 << 0)
+#define PERF_EVENT_MISC_CPUMODE_UNKNOWN         (0 << 0)
+#define PERF_EVENT_MISC_KERNEL                  (1 << 0)
+#define PERF_EVENT_MISC_USER                    (2 << 0)
+#define PERF_EVENT_MISC_HYPERVISOR              (3 << 0)
+#define PERF_EVENT_MISC_OVERFLOW                (1 << 2)
+
+struct perf_event_header {
+        __u32   type;
+        __u16   misc;
+        __u16   size;
+};
+
+enum perf_event_type {
+
+        /*
+         * The MMAP events record the PROT_EXEC mappings so that we can
+         * correlate userspace IPs to code. They have the following structure:
+         *
+         * struct {
+         *      struct perf_event_header        header;
+         *
+         *      u32                             pid, tid;
+         *      u64                             addr;
+         *      u64                             len;
+         *      u64                             pgoff;
+         *      char                            filename[];
+         * };
+         */
+        PERF_EVENT_MMAP                 = 1,
+
+        /*
+         * struct {
+         *      struct perf_event_header        header;
+         *
+         *      u32                             pid, tid;
+         *      char                            comm[];
+         * };
+         */
+        PERF_EVENT_COMM                 = 3,
+
+        /*
+         * struct {
+         *      struct perf_event_header        header;
+         *      u64                             time;
+         *      u64                             id;
+         *      u64                             sample_period;
+         * };
+         */
+        PERF_EVENT_PERIOD               = 4,
+
+        /*
+         * struct {
+         *      struct perf_event_header        header;
+         *      u64                             time;
+         *      u64                             id;
+         * };
+         */
+        PERF_EVENT_THROTTLE             = 5,
+        PERF_EVENT_UNTHROTTLE           = 6,
+
+        /*
+         * struct {
+         *      struct perf_event_header        header;
+         *      u32                             pid, ppid;
+         * };
+         */
+        PERF_EVENT_FORK                 = 7,
+
+        /*
+         * When header.misc & PERF_EVENT_MISC_OVERFLOW the event_type field
+         * will be PERF_RECORD_*
+         *
+         * struct {
+         *      struct perf_event_header        header;
+         *
+         *      { u64                   ip;       } && PERF_RECORD_IP
+         *      { u32                   pid, tid; } && PERF_RECORD_TID
+         *      { u64                   time;     } && PERF_RECORD_TIME
+         *      { u64                   addr;     } && PERF_RECORD_ADDR
+         *      { u64                   config;   } && PERF_RECORD_CONFIG
+         *      { u32                   cpu, res; } && PERF_RECORD_CPU
+         *
+         *      { u64                   nr;
+         *        { u64 id, val; }      cnt[nr];  } && PERF_RECORD_GROUP
+         *
+         *      { u16                   nr,
+         *                              hv,
+         *                              kernel,
+         *                              user;
+         *        u64                   ips[nr];  } && PERF_RECORD_CALLCHAIN
+         * };
+         */
+};
+
+#ifdef __KERNEL__
+/*
+ * Kernel-internal data types and definitions:
+ */
+
+#ifdef CONFIG_PERF_COUNTERS
+# include <asm/perf_counter.h>
+#endif
+
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/rculist.h>
+#include <linux/rcupdate.h>
+#include <linux/spinlock.h>
+#include <linux/hrtimer.h>
+#include <linux/fs.h>
+#include <linux/pid_namespace.h>
+#include <asm/atomic.h>
+
+struct task_struct;
+
+/**
+ * struct hw_perf_counter - performance counter hardware details:
+ */
+struct hw_perf_counter {
+#ifdef CONFIG_PERF_COUNTERS
+        union {
+                struct { /* hardware */
+                        u64             config;
+                        unsigned long   config_base;
+                        unsigned long   counter_base;
+                        int             idx;
+                };
+                union { /* software */
+                        atomic64_t      count;
+                        struct hrtimer  hrtimer;
+                };
+        };
+        atomic64_t                      prev_count;
+        u64                             sample_period;
+        u64                             last_period;
+        atomic64_t                      period_left;
+        u64                             interrupts;
+
+        u64                             freq_count;
+        u64                             freq_interrupts;
+        u64                             freq_stamp;
+#endif
+};
+
+struct perf_counter;
+
+/**
+ * struct pmu - generic performance monitoring unit
+ */
+struct pmu {
+        int (*enable)                   (struct perf_counter *counter);
+        void (*disable)                 (struct perf_counter *counter);
+        void (*read)                    (struct perf_counter *counter);
+        void (*unthrottle)              (struct perf_counter *counter);
+};
+
+/**
+ * enum perf_counter_active_state - the states of a counter
+ */
+enum perf_counter_active_state {
+        PERF_COUNTER_STATE_ERROR        = -2,
+        PERF_COUNTER_STATE_OFF          = -1,
+        PERF_COUNTER_STATE_INACTIVE     =  0,
+        PERF_COUNTER_STATE_ACTIVE       =  1,
+};
+
+struct file;
+
+struct perf_mmap_data {
+        struct rcu_head                 rcu_head;
+        int                             nr_pages;       /* nr of data pages  */
+        int                             nr_locked;      /* nr pages mlocked  */
+
+        atomic_t                        poll;           /* POLL_ for wakeups */
+        atomic_t                        events;         /* event limit       */
+
+        atomic_long_t                   head;           /* write position    */
+        atomic_long_t                   done_head;      /* completed head    */
+
+        atomic_t                        lock;           /* concurrent writes */
+
+        atomic_t                        wakeup;         /* needs a wakeup    */
+
+        struct perf_counter_mmap_page   *user_page;
+        void                            *data_pages[0];
+};
+
+struct perf_pending_entry {
+        struct perf_pending_entry *next;
+        void (*func)(struct perf_pending_entry *);
+};
+
+/**
+ * struct perf_counter - performance counter kernel representation:
+ */
+struct perf_counter {
+#ifdef CONFIG_PERF_COUNTERS
+        struct list_head                list_entry;
+        struct list_head                event_entry;
+        struct list_head                sibling_list;
+        int                             nr_siblings;
+        struct perf_counter             *group_leader;
+        const struct pmu                *pmu;
+
+        enum perf_counter_active_state  state;
+        atomic64_t                      count;
+
+        /*
+         * These are the total time in nanoseconds that the counter
+         * has been enabled (i.e. eligible to run, and the task has
+         * been scheduled in, if this is a per-task counter)
+         * and running (scheduled onto the CPU), respectively.
+         *
+         * They are computed from tstamp_enabled, tstamp_running and
+         * tstamp_stopped when the counter is in INACTIVE or ACTIVE state.
+         */
+        u64                             total_time_enabled;
+        u64                             total_time_running;
+
+        /*
+         * These are timestamps used for computing total_time_enabled
+         * and total_time_running when the counter is in INACTIVE or
+         * ACTIVE state, measured in nanoseconds from an arbitrary point
+         * in time.
+         * tstamp_enabled: the notional time when the counter was enabled
+         * tstamp_running: the notional time when the counter was scheduled on
+         * tstamp_stopped: in INACTIVE state, the notional time when the
+         *      counter was scheduled off.
+         */
+        u64                             tstamp_enabled;
+        u64                             tstamp_running;
+        u64                             tstamp_stopped;
+
+        struct perf_counter_attr        attr;
+        struct hw_perf_counter          hw;
+
+        struct perf_counter_context     *ctx;
+        struct file                     *filp;
+
+        /*
+         * These accumulate total time (in nanoseconds) that children
+         * counters have been enabled and running, respectively.
+         */
+        atomic64_t                      child_total_time_enabled;
+        atomic64_t                      child_total_time_running;
+
+        /*
+         * Protect attach/detach and child_list:
+         */
+        struct mutex                    child_mutex;
+        struct list_head                child_list;
+        struct perf_counter             *parent;
+
+        int                             oncpu;
+        int                             cpu;
+
+        struct list_head                owner_entry;
+        struct task_struct              *owner;
+
+        /* mmap bits */
+        struct mutex                    mmap_mutex;
+        atomic_t                        mmap_count;
+        struct perf_mmap_data           *data;
+
+        /* poll related */
+        wait_queue_head_t               waitq;
+        struct fasync_struct            *fasync;
+
+        /* delayed work for NMIs and such */
+        int                             pending_wakeup;
+        int                             pending_kill;
+        int                             pending_disable;
+        struct perf_pending_entry       pending;
+
+        atomic_t                        event_limit;
+
+        void (*destroy)(struct perf_counter *);
+        struct rcu_head                 rcu_head;
+
+        struct pid_namespace            *ns;
+        u64                             id;
+#endif
+};
+
+/**
+ * struct perf_counter_context - counter context structure
+ *
+ * Used as a container for task counters and CPU counters as well:
+ */
+struct perf_counter_context {
+        /*
+         * Protect the states of the counters in the list,
+         * nr_active, and the list:
+         */
+        spinlock_t                      lock;
+        /*
+         * Protect the list of counters.  Locking either mutex or lock
+         * is sufficient to ensure the list doesn't change; to change
+         * the list you need to lock both the mutex and the spinlock.
+         */
+        struct mutex                    mutex;
+
+        struct list_head                counter_list;
+        struct list_head                event_list;
+        int                             nr_counters;
+        int                             nr_active;
+        int                             is_active;
+        atomic_t                        refcount;
+        struct task_struct              *task;
+
+        /*
+         * Context clock, runs when context enabled.
+         */
+        u64                             time;
+        u64                             timestamp;
+
+        /*
+         * These fields let us detect when two contexts have both
+         * been cloned (inherited) from a common ancestor.
+         */
+        struct perf_counter_context     *parent_ctx;
+        u64                             parent_gen;
+        u64                             generation;
+        int                             pin_count;
+        struct rcu_head                 rcu_head;
+};
+
+/**
+ * struct perf_counter_cpu_context - per cpu counter context structure
+ */
+struct perf_cpu_context {
+        struct perf_counter_context     ctx;
+        struct perf_counter_context     *task_ctx;
+        int                             active_oncpu;
+        int                             max_pertask;
+        int                             exclusive;
+
+        /*
+         * Recursion avoidance:
+         *
+         * task, softirq, irq, nmi context
+         */
+        int                             recursion[4];
+};
+
+#ifdef CONFIG_PERF_COUNTERS
+
+/*
+ * Set by architecture code:
+ */
+extern int perf_max_counters;
+
+extern const struct pmu *hw_perf_counter_init(struct perf_counter *counter);
+
+extern void perf_counter_task_sched_in(struct task_struct *task, int cpu);
+extern void perf_counter_task_sched_out(struct task_struct *task,
+                                        struct task_struct *next, int cpu);
+extern void perf_counter_task_tick(struct task_struct *task, int cpu);
+extern int perf_counter_init_task(struct task_struct *child);
+extern void perf_counter_exit_task(struct task_struct *child);
+extern void perf_counter_free_task(struct task_struct *task);
+extern void perf_counter_do_pending(void);
+extern void perf_counter_print_debug(void);
+extern void __perf_disable(void);
+extern bool __perf_enable(void);
+extern void perf_disable(void);
+extern void perf_enable(void);
+extern int perf_counter_task_disable(void);
+extern int perf_counter_task_enable(void);
+extern int hw_perf_group_sched_in(struct perf_counter *group_leader,
+               struct perf_cpu_context *cpuctx,
+               struct perf_counter_context *ctx, int cpu);
+extern void perf_counter_update_userpage(struct perf_counter *counter);
+
+struct perf_sample_data {
+        struct pt_regs                  *regs;
+        u64                             addr;
+        u64                             period;
+};
+
+extern int perf_counter_overflow(struct perf_counter *counter, int nmi,
+                                 struct perf_sample_data *data);
+
+/*
+ * Return 1 for a software counter, 0 for a hardware counter
+ */
+static inline int is_software_counter(struct perf_counter *counter)
+{
+        return (counter->attr.type != PERF_TYPE_RAW) &&
+                (counter->attr.type != PERF_TYPE_HARDWARE);
+}
+
+extern void perf_swcounter_event(u32, u64, int, struct pt_regs *, u64);
+
+extern void __perf_counter_mmap(struct vm_area_struct *vma);
+
+static inline void perf_counter_mmap(struct vm_area_struct *vma)
+{
+        if (vma->vm_flags & VM_EXEC)
+                __perf_counter_mmap(vma);
+}
+
+extern void perf_counter_comm(struct task_struct *tsk);
+extern void perf_counter_fork(struct task_struct *tsk);
+
+extern void perf_counter_task_migration(struct task_struct *task, int cpu);
+
+#define MAX_STACK_DEPTH                 255
+
+struct perf_callchain_entry {
+        u16                             nr;
+        u16                             hv;
+        u16                             kernel;
+        u16                             user;
+        u64                             ip[MAX_STACK_DEPTH];
+};
+
+extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+
+extern int sysctl_perf_counter_paranoid;
+extern int sysctl_perf_counter_mlock;
+extern int sysctl_perf_counter_sample_rate;
+
+extern void perf_counter_init(void);
+
+#ifndef perf_misc_flags
+#define perf_misc_flags(regs)   (user_mode(regs) ? PERF_EVENT_MISC_USER : \
+                                 PERF_EVENT_MISC_KERNEL)
+#define perf_instruction_pointer(regs)  instruction_pointer(regs)
+#endif
+
+#else
+static inline void
+perf_counter_task_sched_in(struct task_struct *task, int cpu)           { }
+static inline void
+perf_counter_task_sched_out(struct task_struct *task,
+                            struct task_struct *next, int cpu)          { }
+static inline void
+perf_counter_task_tick(struct task_struct *task, int cpu)               { }
+static inline int perf_counter_init_task(struct task_struct *child)     { return 0; }
+static inline void perf_counter_exit_task(struct task_struct *child)    { }
+static inline void perf_counter_free_task(struct task_struct *task)     { }
+static inline void perf_counter_do_pending(void)                        { }
+static inline void perf_counter_print_debug(void)                       { }
+static inline void perf_disable(void)                                   { }
+static inline void perf_enable(void)                                    { }
+static inline int perf_counter_task_disable(void)       { return -EINVAL; }
+static inline int perf_counter_task_enable(void)        { return -EINVAL; }
+
+static inline void
+perf_swcounter_event(u32 event, u64 nr, int nmi,
+                     struct pt_regs *regs, u64 addr)                    { }
+
+static inline void perf_counter_mmap(struct vm_area_struct *vma)        { }
+static inline void perf_counter_comm(struct task_struct *tsk)           { }
+static inline void perf_counter_fork(struct task_struct *tsk)           { }
+static inline void perf_counter_init(void)                              { }
+static inline void perf_counter_task_migration(struct task_struct *task,
+                                               int cpu)                 { }
+#endif
+
+#endif /* __KERNEL__ */
+#endif /* _LINUX_PERF_COUNTER_H */
diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h
index c8f038554e80..b43a9e039059 100644
--- a/include/linux/pipe_fs_i.h
+++ b/include/linux/pipe_fs_i.h
@@ -152,5 +152,6 @@ void generic_pipe_buf_unmap(struct pipe_inode_info *, struct pipe_buffer *, void
 void generic_pipe_buf_get(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_confirm(struct pipe_inode_info *, struct pipe_buffer *);
 int generic_pipe_buf_steal(struct pipe_inode_info *, struct pipe_buffer *);
+void generic_pipe_buf_release(struct pipe_inode_info *, struct pipe_buffer *);
 
 #endif
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index 48d887e3c6e7..b00df4c79c63 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -85,4 +85,7 @@
 #define PR_SET_TIMERSLACK 29
 #define PR_GET_TIMERSLACK 30
 
+#define PR_TASK_PERF_COUNTERS_DISABLE           31
+#define PR_TASK_PERF_COUNTERS_ENABLE            32
+
 #endif /* _LINUX_PRCTL_H */
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index fbfa3d44d33d..e6e77d31c418 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -93,20 +93,9 @@ struct vmcore {
 
 #ifdef CONFIG_PROC_FS
 
-extern spinlock_t proc_subdir_lock;
-
 extern void proc_root_init(void);
 
 void proc_flush_task(struct task_struct *task);
-struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *);
-int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir);
-unsigned long task_vsize(struct mm_struct *);
-int task_statm(struct mm_struct *, int *, int *, int *, int *);
-void task_mem(struct seq_file *, struct mm_struct *);
-void clear_refs_smap(struct mm_struct *mm);
-
-struct proc_dir_entry *de_get(struct proc_dir_entry *de);
-void de_put(struct proc_dir_entry *de);
 
 extern struct proc_dir_entry *create_proc_entry(const char *name, mode_t mode,
                                                 struct proc_dir_entry *parent);
@@ -116,20 +105,7 @@ struct proc_dir_entry *proc_create_data(const char *name, mode_t mode,
                                 void *data);
 extern void remove_proc_entry(const char *name, struct proc_dir_entry *parent);
 
-extern struct vfsmount *proc_mnt;
 struct pid_namespace;
-extern int proc_fill_super(struct super_block *);
-extern struct inode *proc_get_inode(struct super_block *, unsigned int, struct proc_dir_entry *);
-
-/*
- * These are generic /proc routines that use the internal
- * "struct proc_dir_entry" tree to traverse the filesystem.
- *
- * The /proc root directory has extended versions to take care
- * of the /proc/<pid> subdirectories.
- */
-extern int proc_readdir(struct file *, void *, filldir_t);
-extern struct dentry *proc_lookup(struct inode *, struct dentry *, struct nameidata *);
 
 extern int pid_ns_prepare_proc(struct pid_namespace *ns);
 extern void pid_ns_release_proc(struct pid_namespace *ns);
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 67c15653fc23..59e133d39d50 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -95,7 +95,6 @@ extern void __ptrace_link(struct task_struct *child,
                           struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
 extern void exit_ptrace(struct task_struct *tracer);
-extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags);
 #define PTRACE_MODE_READ   1
 #define PTRACE_MODE_ATTACH 2
 /* Returns 0 on success, -errno on denial. */
@@ -327,15 +326,6 @@ static inline void user_enable_block_step(struct task_struct *task)
 #define arch_ptrace_untrace(task)               do { } while (0)
 #endif
 
-#ifndef arch_ptrace_fork
-/*
- * Do machine-specific work to initialize a new task.
- *
- * This is called from copy_process().
- */
-#define arch_ptrace_fork(child, clone_flags)    do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
                                 unsigned long args[6], unsigned int maxargs,
                                 unsigned long *sp, unsigned long *pc);
diff --git a/include/linux/qnx4_fs.h b/include/linux/qnx4_fs.h
index 787d19ea9f46..8b9aee1a9ce3 100644
--- a/include/linux/qnx4_fs.h
+++ b/include/linux/qnx4_fs.h
@@ -85,65 +85,4 @@ struct qnx4_super_block {
         struct qnx4_inode_entry AltBoot;
 };
 
-#ifdef __KERNEL__
-
-#define QNX4_DEBUG 0
-
-#if QNX4_DEBUG
-#define QNX4DEBUG(X) printk X
-#else
-#define QNX4DEBUG(X) (void) 0
-#endif
-
-struct qnx4_sb_info {
-        struct buffer_head      *sb_buf;        /* superblock buffer */
-        struct qnx4_super_block *sb;            /* our superblock */
-        unsigned int            Version;        /* may be useful */
-        struct qnx4_inode_entry *BitMap;        /* useful */
-};
-
-struct qnx4_inode_info {
-        struct qnx4_inode_entry raw;
-        loff_t mmu_private;
-        struct inode vfs_inode;
-};
-
-extern struct inode *qnx4_iget(struct super_block *, unsigned long);
-extern struct dentry *qnx4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd);
-extern unsigned long qnx4_count_free_blocks(struct super_block *sb);
-extern unsigned long qnx4_block_map(struct inode *inode, long iblock);
-
-extern struct buffer_head *qnx4_bread(struct inode *, int, int);
-
-extern const struct inode_operations qnx4_file_inode_operations;
-extern const struct inode_operations qnx4_dir_inode_operations;
-extern const struct file_operations qnx4_file_operations;
-extern const struct file_operations qnx4_dir_operations;
-extern int qnx4_is_free(struct super_block *sb, long block);
-extern int qnx4_set_bitmap(struct super_block *sb, long block, int busy);
-extern int qnx4_create(struct inode *inode, struct dentry *dentry, int mode, struct nameidata *nd);
-extern void qnx4_truncate(struct inode *inode);
-extern void qnx4_free_inode(struct inode *inode);
-extern int qnx4_unlink(struct inode *dir, struct dentry *dentry);
-extern int qnx4_rmdir(struct inode *dir, struct dentry *dentry);
-extern int qnx4_sync_file(struct file *file, struct dentry *dentry, int);
-extern int qnx4_sync_inode(struct inode *inode);
-
-static inline struct qnx4_sb_info *qnx4_sb(struct super_block *sb)
-{
-        return sb->s_fs_info;
-}
-
-static inline struct qnx4_inode_info *qnx4_i(struct inode *inode)
-{
-        return container_of(inode, struct qnx4_inode_info, vfs_inode);
-}
-
-static inline struct qnx4_inode_entry *qnx4_raw_inode(struct inode *inode)
-{
-        return &qnx4_i(inode)->raw;
-}
-
-#endif                          /* __KERNEL__ */
-
 #endif
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 36353d95c8db..7bc457593684 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -20,7 +20,12 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb)
 /*
  * declaration of quota_function calls in kernel.
  */
-void sync_dquots(struct super_block *sb, int type);
+void sync_quota_sb(struct super_block *sb, int type);
+static inline void writeout_quota_sb(struct super_block *sb, int type)
+{
+        if (sb->s_qcop->quota_sync)
+                sb->s_qcop->quota_sync(sb, type);
+}
 
 int dquot_initialize(struct inode *inode, int type);
 int dquot_drop(struct inode *inode);
@@ -253,12 +258,7 @@ static inline void vfs_dq_free_inode(struct inode *inode)
                 inode->i_sb->dq_op->free_inode(inode, 1);
 }
 
-/* The following two functions cannot be called inside a transaction */
-static inline void vfs_dq_sync(struct super_block *sb)
-{
-        sync_dquots(sb, -1);
-}
-
+/* Cannot be called inside a transaction */
 static inline int vfs_dq_off(struct super_block *sb, int remount)
 {
         int ret = -ENOSYS;
@@ -334,7 +334,11 @@ static inline void vfs_dq_free_inode(struct inode *inode)
 {
 }
 
-static inline void vfs_dq_sync(struct super_block *sb)
+static inline void sync_quota_sb(struct super_block *sb, int type)
+{
+}
+
+static inline void writeout_quota_sb(struct super_block *sb, int type)
 {
 }
 
diff --git a/include/linux/rational.h b/include/linux/rational.h
new file mode 100644
index 000000000000..4f532fcd9eea
--- /dev/null
+++ b/include/linux/rational.h
@@ -0,0 +1,19 @@
+/*
+ * rational fractions
+ *
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ *
+ * helper functions when coping with rational numbers,
+ * e.g. when calculating optimum numerator/denominator pairs for
+ * pll configuration taking into account restricted register size
+ */
+
+#ifndef _LINUX_RATIONAL_H
+#define _LINUX_RATIONAL_H
+
+void rational_best_approximation(
+        unsigned long given_numerator, unsigned long given_denominator,
+        unsigned long max_numerator, unsigned long max_denominator,
+        unsigned long *best_numerator, unsigned long *best_denominator);
+
+#endif /* _LINUX_RATIONAL_H */
diff --git a/include/linux/rculist.h b/include/linux/rculist.h
index e649bd3f2c97..5710f43bbc9e 100644
--- a/include/linux/rculist.h
+++ b/include/linux/rculist.h
@@ -198,6 +198,32 @@ static inline void list_splice_init_rcu(struct list_head *list,
         at->prev = last;
 }
 
+/**
+ * list_entry_rcu - get the struct for this entry
+ * @ptr:        the &struct list_head pointer.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_entry_rcu(ptr, type, member) \
+        container_of(rcu_dereference(ptr), type, member)
+
+/**
+ * list_first_entry_rcu - get the first element from a list
+ * @ptr:        the list head to take the element from.
+ * @type:       the type of the struct this is embedded in.
+ * @member:     the name of the list_struct within the struct.
+ *
+ * Note, that list is expected to be not empty.
+ *
+ * This primitive may safely run concurrently with the _rcu list-mutation
+ * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock().
+ */
+#define list_first_entry_rcu(ptr, type, member) \
+        list_entry_rcu((ptr)->next, type, member)
+
 #define __list_for_each_rcu(pos, head) \
         for (pos = rcu_dereference((head)->next); \
                 pos != (head); \
@@ -214,9 +240,9 @@ static inline void list_splice_init_rcu(struct list_head *list,
  * as long as the traversal is guarded by rcu_read_lock().
  */
 #define list_for_each_entry_rcu(pos, head, member) \
-        for (pos = list_entry(rcu_dereference((head)->next), typeof(*pos), member); \
+        for (pos = list_entry_rcu((head)->next, typeof(*pos), member); \
                 prefetch(pos->member.next), &pos->member != (head); \
-                pos = list_entry(rcu_dereference(pos->member.next), typeof(*pos), member))
+                pos = list_entry_rcu(pos->member.next, typeof(*pos), member))
 
 
 /**
diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h
index 58b2aa5312b9..5a5153806c42 100644
--- a/include/linux/rcutree.h
+++ b/include/linux/rcutree.h
@@ -161,8 +161,15 @@ struct rcu_data {
         unsigned long offline_fqs;      /* Kicked due to being offline. */
         unsigned long resched_ipi;      /* Sent a resched IPI. */
 
-        /* 5) For future __rcu_pending statistics. */
+        /* 5) __rcu_pending() statistics. */
         long n_rcu_pending;             /* rcu_pending() calls since boot. */
+        long n_rp_qs_pending;
+        long n_rp_cb_ready;
+        long n_rp_cpu_needs_gp;
+        long n_rp_gp_completed;
+        long n_rp_gp_started;
+        long n_rp_need_fqs;
+        long n_rp_need_nothing;
 
         int cpu;
 };
diff --git a/include/linux/reiserfs_fs_sb.h b/include/linux/reiserfs_fs_sb.h
index 6473650c28f1..dab68bbed675 100644
--- a/include/linux/reiserfs_fs_sb.h
+++ b/include/linux/reiserfs_fs_sb.h
@@ -453,6 +453,7 @@ enum reiserfs_mount_options {
         REISERFS_ATTRS,
         REISERFS_XATTRS_USER,
         REISERFS_POSIXACL,
+        REISERFS_EXPOSE_PRIVROOT,
         REISERFS_BARRIER_NONE,
         REISERFS_BARRIER_FLUSH,
 
@@ -490,6 +491,7 @@ enum reiserfs_mount_options {
 #define reiserfs_data_writeback(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_WRITEBACK))
 #define reiserfs_xattrs_user(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_XATTRS_USER))
 #define reiserfs_posixacl(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_POSIXACL))
+#define reiserfs_expose_privroot(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_EXPOSE_PRIVROOT))
 #define reiserfs_xattrs_optional(s) (reiserfs_xattrs_user(s) || reiserfs_posixacl(s))
 #define reiserfs_barrier_none(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_NONE))
 #define reiserfs_barrier_flush(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_FLUSH))
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index e1b7b2173885..8670f1575fe1 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -11,7 +11,7 @@ struct ring_buffer_iter;
  * Don't refer to this struct directly, use functions below.
  */
 struct ring_buffer_event {
-        u32             type:2, len:3, time_delta:27;
+        u32             type_len:5, time_delta:27;
         u32             array[];
 };
 
@@ -24,7 +24,8 @@ struct ring_buffer_event {
  *                                size is variable depending on how much
  *                                padding is needed
  *                               If time_delta is non zero:
- *                                everything else same as RINGBUF_TYPE_DATA
+ *                                array[0] holds the actual length
+ *                                size = 4 + length (bytes)
  *
  * @RINGBUF_TYPE_TIME_EXTEND:   Extend the time delta
  *                               array[0] = time delta (28 .. 59)
@@ -35,22 +36,23 @@ struct ring_buffer_event {
  *                               array[1..2] = tv_sec
  *                               size = 16 bytes
  *
- * @RINGBUF_TYPE_DATA:          Data record
- *                               If len is zero:
+ * <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
+ *                              Data record
+ *                               If type_len is zero:
  *                                array[0] holds the actual length
  *                                array[1..(length+3)/4] holds data
- *                                size = 4 + 4 + length (bytes)
+ *                                size = 4 + length (bytes)
  *                               else
- *                                length = len << 2
+ *                                length = type_len << 2
  *                                array[0..(length+3)/4-1] holds data
  *                                size = 4 + length (bytes)
  */
 enum ring_buffer_type {
+        RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
         RINGBUF_TYPE_PADDING,
         RINGBUF_TYPE_TIME_EXTEND,
         /* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
         RINGBUF_TYPE_TIME_STAMP,
-        RINGBUF_TYPE_DATA,
 };
 
 unsigned ring_buffer_event_length(struct ring_buffer_event *event);
@@ -68,13 +70,54 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
         return event->time_delta;
 }
 
+/*
+ * ring_buffer_event_discard can discard any event in the ring buffer.
+ *   it is up to the caller to protect against a reader from
+ *   consuming it or a writer from wrapping and replacing it.
+ *
+ * No external protection is needed if this is called before
+ * the event is commited. But in that case it would be better to
+ * use ring_buffer_discard_commit.
+ *
+ * Note, if an event that has not been committed is discarded
+ * with ring_buffer_event_discard, it must still be committed.
+ */
 void ring_buffer_event_discard(struct ring_buffer_event *event);
 
 /*
+ * ring_buffer_discard_commit will remove an event that has not
+ *   ben committed yet. If this is used, then ring_buffer_unlock_commit
+ *   must not be called on the discarded event. This function
+ *   will try to remove the event from the ring buffer completely
+ *   if another event has not been written after it.
+ *
+ * Example use:
+ *
+ *  if (some_condition)
+ *    ring_buffer_discard_commit(buffer, event);
+ *  else
+ *    ring_buffer_unlock_commit(buffer, event);
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+                                struct ring_buffer_event *event);
+
+/*
  * size is in bytes for each per CPU buffer.
  */
 struct ring_buffer *
-ring_buffer_alloc(unsigned long size, unsigned flags);
+__ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key);
+
+/*
+ * Because the ring buffer is generic, if other users of the ring buffer get
+ * traced by ftrace, it can produce lockdep warnings. We need to keep each
+ * ring buffer's lock class separate.
+ */
+#define ring_buffer_alloc(size, flags)                  \
+({                                                      \
+        static struct lock_class_key __key;             \
+        __ring_buffer_alloc((size), (flags), &__key);   \
+})
+
 void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
@@ -122,6 +165,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer);
 unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
@@ -137,6 +182,11 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
 int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
                           size_t len, int cpu, int full);
 
+struct trace_seq;
+
+int ring_buffer_print_entry_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_seq *s);
+
 enum ring_buffer_flags {
         RB_FL_OVERWRITE         = 1 << 0,
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index b4c38bc8049c..4896fdfec913 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -77,6 +77,7 @@ struct sched_param {
 #include <linux/proportions.h>
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
+#include <linux/rculist.h>
 #include <linux/rtmutex.h>
 
 #include <linux/time.h>
@@ -96,8 +97,9 @@ struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
 struct bio;
-struct bts_tracer;
 struct fs_struct;
+struct bts_context;
+struct perf_counter_context;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -116,6 +118,7 @@ struct fs_struct;
  *    11 bit fractions.
  */
 extern unsigned long avenrun[];         /* Load averages */
+extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
 
 #define FSHIFT          11              /* nr of bits of precision */
 #define FIXED_1         (1<<FSHIFT)     /* 1.0 as fixed-point */
@@ -135,8 +138,9 @@ DECLARE_PER_CPU(unsigned long, process_counts);
 extern int nr_processes(void);
 extern unsigned long nr_running(void);
 extern unsigned long nr_uninterruptible(void);
-extern unsigned long nr_active(void);
 extern unsigned long nr_iowait(void);
+extern void calc_global_load(void);
+extern u64 cpu_nr_migrations(int cpu);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
@@ -672,6 +676,10 @@ struct user_struct {
         struct work_struct work;
 #endif
 #endif
+
+#ifdef CONFIG_PERF_COUNTERS
+        atomic_long_t locked_vm;
+#endif
 };
 
 extern int uids_sysfs_init(void);
@@ -838,7 +846,17 @@ struct sched_group {
          */
         u32 reciprocal_cpu_power;
 
-        unsigned long cpumask[];
+        /*
+         * The CPUs this group covers.
+         *
+         * NOTE: this field is variable length. (Allocated dynamically
+         * by attaching extra space to the end of the structure,
+         * depending on how many CPUs the kernel has booted up with)
+         *
+         * It is also be embedded into static data structures at build
+         * time. (See 'struct static_sched_group' in kernel/sched.c)
+         */
+        unsigned long cpumask[0];
 };
 
 static inline struct cpumask *sched_group_cpus(struct sched_group *sg)
@@ -924,8 +942,17 @@ struct sched_domain {
         char *name;
 #endif
 
-        /* span of all CPUs in this domain */
-        unsigned long span[];
+        /*
+         * Span of all CPUs in this domain.
+         *
+         * NOTE: this field is variable length. (Allocated dynamically
+         * by attaching extra space to the end of the structure,
+         * depending on how many CPUs the kernel has booted up with)
+         *
+         * It is also be embedded into static data structures at build
+         * time. (See 'struct static_sched_domain' in kernel/sched.c)
+         */
+        unsigned long span[0];
 };
 
 static inline struct cpumask *sched_domain_span(struct sched_domain *sd)
@@ -1052,9 +1079,10 @@ struct sched_entity {
         u64                     last_wakeup;
         u64                     avg_overlap;
 
+        u64                     nr_migrations;
+
         u64                     start_runtime;
         u64                     avg_wakeup;
-        u64                     nr_migrations;
 
 #ifdef CONFIG_SCHEDSTATS
         u64                     wait_start;
@@ -1209,18 +1237,11 @@ struct task_struct {
         struct list_head ptraced;
         struct list_head ptrace_entry;
 
-#ifdef CONFIG_X86_PTRACE_BTS
         /*
          * This is the tracer handle for the ptrace BTS extension.
          * This field actually belongs to the ptracer task.
          */
-        struct bts_tracer *bts;
-        /*
-         * The buffer to hold the BTS data.
-         */
-        void *bts_buffer;
-        size_t bts_size;
-#endif /* CONFIG_X86_PTRACE_BTS */
+        struct bts_context *bts;
 
         /* PID/PID hash table linkage. */
         struct pid_link pids[PIDTYPE_MAX];
@@ -1247,7 +1268,9 @@ struct task_struct {
                                          * credentials (COW) */
         const struct cred *cred;        /* effective (overridable) subjective task
                                          * credentials (COW) */
-        struct mutex cred_exec_mutex;   /* execve vs ptrace cred calculation mutex */
+        struct mutex cred_guard_mutex;  /* guard against foreign influences on
+                                         * credential calculations
+                                         * (notably. ptrace) */
 
         char comm[TASK_COMM_LEN]; /* executable name excluding path
                                      - access with [gs]et_task_comm (which lock
@@ -1380,6 +1403,11 @@ struct task_struct {
         struct list_head pi_state_list;
         struct futex_pi_state *pi_state_cache;
 #endif
+#ifdef CONFIG_PERF_COUNTERS
+        struct perf_counter_context *perf_counter_ctxp;
+        struct mutex perf_counter_mutex;
+        struct list_head perf_counter_list;
+#endif
 #ifdef CONFIG_NUMA
         struct mempolicy *mempolicy;
         short il_next;
@@ -1428,7 +1456,9 @@ struct task_struct {
 #ifdef CONFIG_TRACING
         /* state flags for use by tracers */
         unsigned long trace;
-#endif
+        /* bitmask of trace recursion */
+        unsigned long trace_recursion;
+#endif /* CONFIG_TRACING */
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -1885,6 +1915,7 @@ extern void sched_dead(struct task_struct *p);
 
 extern void proc_caches_init(void);
 extern void flush_signals(struct task_struct *);
+extern void __flush_signals(struct task_struct *);
 extern void ignore_signals(struct task_struct *);
 extern void flush_signal_handlers(struct task_struct *, int force_default);
 extern int dequeue_signal(struct task_struct *tsk, sigset_t *mask, siginfo_t *info);
@@ -2001,8 +2032,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
+extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
+static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
                                                long match_state)
 {
@@ -2010,7 +2043,8 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
-#define next_task(p)    list_entry(rcu_dereference((p)->tasks.next), struct task_struct, tasks)
+#define next_task(p) \
+        list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
 
 #define for_each_process(p) \
         for (p = &init_task ; (p = next_task(p)) != &init_task ; )
@@ -2049,8 +2083,8 @@ int same_thread_group(struct task_struct *p1, struct task_struct *p2)
 
 static inline struct task_struct *next_thread(const struct task_struct *p)
 {
-        return list_entry(rcu_dereference(p->thread_group.next),
-                          struct task_struct, thread_group);
+        return list_entry_rcu(p->thread_group.next,
+                              struct task_struct, thread_group);
 }
 
 static inline int thread_group_empty(struct task_struct *p)
@@ -2388,6 +2422,13 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)       TASK_SIZE
 #endif
 
+/*
+ * Call the function if the target task is executing on a CPU right now:
+ */
+extern void task_oncpu_function_call(struct task_struct *p,
+                                     void (*func) (void *info), void *info);
+
+
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/include/linux/security.h b/include/linux/security.h
index d5fd6163606f..5eff459b3833 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2197,6 +2197,8 @@ 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;
 }
 
diff --git a/include/linux/serial.h b/include/linux/serial.h
index 9136cc5608c3..e5bb75a63802 100644
--- a/include/linux/serial.h
+++ b/include/linux/serial.h
@@ -96,54 +96,76 @@ struct serial_uart_config {
 
 /*
  * Definitions for async_struct (and serial_struct) flags field
+ *
+ * Define ASYNCB_* for convenient use with {test,set,clear}_bit.
  */
-#define ASYNC_HUP_NOTIFY 0x0001 /* Notify getty on hangups and closes 
-                                   on the callout port */
-#define ASYNC_FOURPORT  0x0002  /* Set OU1, OUT2 per AST Fourport settings */
-#define ASYNC_SAK       0x0004  /* Secure Attention Key (Orange book) */
-#define ASYNC_SPLIT_TERMIOS 0x0008 /* Separate termios for dialin/callout */
-
-#define ASYNC_SPD_MASK  0x1030
-#define ASYNC_SPD_HI    0x0010  /* Use 56000 instead of 38400 bps */
-
-#define ASYNC_SPD_VHI   0x0020  /* Use 115200 instead of 38400 bps */
-#define ASYNC_SPD_CUST  0x0030  /* Use user-specified divisor */
-
-#define ASYNC_SKIP_TEST 0x0040 /* Skip UART test during autoconfiguration */
-#define ASYNC_AUTO_IRQ  0x0080 /* Do automatic IRQ during autoconfiguration */
-#define ASYNC_SESSION_LOCKOUT 0x0100 /* Lock out cua opens based on session */
-#define ASYNC_PGRP_LOCKOUT    0x0200 /* Lock out cua opens based on pgrp */
-#define ASYNC_CALLOUT_NOHUP   0x0400 /* Don't do hangups for cua device */
-
-#define ASYNC_HARDPPS_CD        0x0800  /* Call hardpps when CD goes high  */
-
-#define ASYNC_SPD_SHI   0x1000  /* Use 230400 instead of 38400 bps */
-#define ASYNC_SPD_WARP  0x1010  /* Use 460800 instead of 38400 bps */
-
-#define ASYNC_LOW_LATENCY 0x2000 /* Request low latency behaviour */
-
-#define ASYNC_BUGGY_UART  0x4000 /* This is a buggy UART, skip some safety
-                                  * checks.  Note: can be dangerous! */
-
-#define ASYNC_AUTOPROBE  0x8000 /* Port was autoprobed by PCI or PNP code */
-
-#define ASYNC_FLAGS     0x7FFF  /* Possible legal async flags */
-#define ASYNC_USR_MASK  0x3430  /* Legal flags that non-privileged
-                                 * users can set or reset */
-
-/* Internal flags used only by kernel/chr_drv/serial.c */
-#define ASYNC_INITIALIZED       0x80000000 /* Serial port was initialized */
-#define ASYNC_NORMAL_ACTIVE     0x20000000 /* Normal device is active */
-#define ASYNC_BOOT_AUTOCONF     0x10000000 /* Autoconfigure port on bootup */
-#define ASYNC_CLOSING           0x08000000 /* Serial port is closing */
-#define ASYNC_CTS_FLOW          0x04000000 /* Do CTS flow control */
-#define ASYNC_CHECK_CD          0x02000000 /* i.e., CLOCAL */
-#define ASYNC_SHARE_IRQ         0x01000000 /* for multifunction cards
-                                             --- no longer used */
-#define ASYNC_CONS_FLOW         0x00800000 /* flow control for console  */
-
-#define ASYNC_BOOT_ONLYMCA      0x00400000 /* Probe only if MCA bus */
-#define ASYNC_INTERNAL_FLAGS    0xFFC00000 /* Internal flags */
+#define ASYNCB_HUP_NOTIFY        0 /* Notify getty on hangups and closes
+                                    * on the callout port */
+#define ASYNCB_FOURPORT          1 /* Set OU1, OUT2 per AST Fourport settings */
+#define ASYNCB_SAK               2 /* Secure Attention Key (Orange book) */
+#define ASYNCB_SPLIT_TERMIOS     3 /* Separate termios for dialin/callout */
+#define ASYNCB_SPD_HI            4 /* Use 56000 instead of 38400 bps */
+#define ASYNCB_SPD_VHI           5 /* Use 115200 instead of 38400 bps */
+#define ASYNCB_SKIP_TEST         6 /* Skip UART test during autoconfiguration */
+#define ASYNCB_AUTO_IRQ          7 /* Do automatic IRQ during
+                                    * autoconfiguration */
+#define ASYNCB_SESSION_LOCKOUT   8 /* Lock out cua opens based on session */
+#define ASYNCB_PGRP_LOCKOUT      9 /* Lock out cua opens based on pgrp */
+#define ASYNCB_CALLOUT_NOHUP    10 /* Don't do hangups for cua device */
+#define ASYNCB_HARDPPS_CD       11 /* Call hardpps when CD goes high  */
+#define ASYNCB_SPD_SHI          12 /* Use 230400 instead of 38400 bps */
+#define ASYNCB_LOW_LATENCY      13 /* Request low latency behaviour */
+#define ASYNCB_BUGGY_UART       14 /* This is a buggy UART, skip some safety
+                                    * checks.  Note: can be dangerous! */
+#define ASYNCB_AUTOPROBE        15 /* Port was autoprobed by PCI or PNP code */
+#define ASYNCB_LAST_USER        15
+
+/* Internal flags used only by kernel */
+#define ASYNCB_INITIALIZED      31 /* Serial port was initialized */
+#define ASYNCB_NORMAL_ACTIVE    29 /* Normal device is active */
+#define ASYNCB_BOOT_AUTOCONF    28 /* Autoconfigure port on bootup */
+#define ASYNCB_CLOSING          27 /* Serial port is closing */
+#define ASYNCB_CTS_FLOW         26 /* Do CTS flow control */
+#define ASYNCB_CHECK_CD         25 /* i.e., CLOCAL */
+#define ASYNCB_SHARE_IRQ        24 /* for multifunction cards, no longer used */
+#define ASYNCB_CONS_FLOW        23 /* flow control for console  */
+#define ASYNCB_BOOT_ONLYMCA     22 /* Probe only if MCA bus */
+#define ASYNCB_FIRST_KERNEL     22
+
+#define ASYNC_HUP_NOTIFY        (1U << ASYNCB_HUP_NOTIFY)
+#define ASYNC_FOURPORT          (1U << ASYNCB_FOURPORT)
+#define ASYNC_SAK               (1U << ASYNCB_SAK)
+#define ASYNC_SPLIT_TERMIOS     (1U << ASYNCB_SPLIT_TERMIOS)
+#define ASYNC_SPD_HI            (1U << ASYNCB_SPD_HI)
+#define ASYNC_SPD_VHI           (1U << ASYNCB_SPD_VHI)
+#define ASYNC_SKIP_TEST         (1U << ASYNCB_SKIP_TEST)
+#define ASYNC_AUTO_IRQ          (1U << ASYNCB_AUTO_IRQ)
+#define ASYNC_SESSION_LOCKOUT   (1U << ASYNCB_SESSION_LOCKOUT)
+#define ASYNC_PGRP_LOCKOUT      (1U << ASYNCB_PGRP_LOCKOUT)
+#define ASYNC_CALLOUT_NOHUP     (1U << ASYNCB_CALLOUT_NOHUP)
+#define ASYNC_HARDPPS_CD        (1U << ASYNCB_HARDPPS_CD)
+#define ASYNC_SPD_SHI           (1U << ASYNCB_SPD_SHI)
+#define ASYNC_LOW_LATENCY       (1U << ASYNCB_LOW_LATENCY)
+#define ASYNC_BUGGY_UART        (1U << ASYNCB_BUGGY_UART)
+#define ASYNC_AUTOPROBE         (1U << ASYNCB_AUTOPROBE)
+
+#define ASYNC_FLAGS             ((1U << ASYNCB_LAST_USER) - 1)
+#define ASYNC_USR_MASK          (ASYNC_SPD_HI|ASYNC_SPD_VHI| \
+                ASYNC_CALLOUT_NOHUP|ASYNC_SPD_SHI|ASYNC_LOW_LATENCY)
+#define ASYNC_SPD_CUST          (ASYNC_SPD_HI|ASYNC_SPD_VHI)
+#define ASYNC_SPD_WARP          (ASYNC_SPD_HI|ASYNC_SPD_SHI)
+#define ASYNC_SPD_MASK          (ASYNC_SPD_HI|ASYNC_SPD_VHI|ASYNC_SPD_SHI)
+
+#define ASYNC_INITIALIZED       (1U << ASYNCB_INITIALIZED)
+#define ASYNC_NORMAL_ACTIVE     (1U << ASYNCB_NORMAL_ACTIVE)
+#define ASYNC_BOOT_AUTOCONF     (1U << ASYNCB_BOOT_AUTOCONF)
+#define ASYNC_CLOSING           (1U << ASYNCB_CLOSING)
+#define ASYNC_CTS_FLOW          (1U << ASYNCB_CTS_FLOW)
+#define ASYNC_CHECK_CD          (1U << ASYNCB_CHECK_CD)
+#define ASYNC_SHARE_IRQ         (1U << ASYNCB_SHARE_IRQ)
+#define ASYNC_CONS_FLOW         (1U << ASYNCB_CONS_FLOW)
+#define ASYNC_BOOT_ONLYMCA      (1U << ASYNCB_BOOT_ONLYMCA)
+#define ASYNC_INTERNAL_FLAGS    (~((1U << ASYNCB_FIRST_KERNEL) - 1))
 
 /*
  * Multiport serial configuration structure --- external structure
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 57a97e52e58d..6fd80c4243f1 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -41,7 +41,8 @@
 #define PORT_XSCALE     15
 #define PORT_RM9000     16      /* PMC-Sierra RM9xxx internal UART */
 #define PORT_OCTEON     17      /* Cavium OCTEON internal UART */
-#define PORT_MAX_8250   17      /* max port ID */
+#define PORT_AR7        18      /* Texas Instruments AR7 internal UART */
+#define PORT_MAX_8250   18      /* max port ID */
 
 /*
  * ARM specific type numbers.  These are not currently guaranteed
@@ -167,6 +168,9 @@
 /* MAX3100 */
 #define PORT_MAX3100    86
 
+/* Timberdale UART */
+#define PORT_TIMBUART   87
+
 #ifdef __KERNEL__
 
 #include <linux/compiler.h>
diff --git a/include/linux/serial_sci.h b/include/linux/serial_sci.h
index 893cc53486bc..1c297ddc9d5a 100644
--- a/include/linux/serial_sci.h
+++ b/include/linux/serial_sci.h
@@ -25,8 +25,7 @@ struct plat_sci_port {
         unsigned int    irqs[SCIx_NR_IRQS];     /* ERI, RXI, TXI, BRI */
         unsigned int    type;                   /* SCI / SCIF / IRDA */
         upf_t           flags;                  /* UPF_* flags */
+        char            *clk;                   /* clock string */
 };
 
-int early_sci_setup(struct uart_port *port);
-
 #endif /* __LINUX_SERIAL_SCI_H */
diff --git a/include/linux/sh_cmt.h b/include/linux/sh_cmt.h
deleted file mode 100644
index 68cacde5954f..000000000000
--- a/include/linux/sh_cmt.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef __SH_CMT_H__
-#define __SH_CMT_H__
-
-struct sh_cmt_config {
-        char *name;
-        unsigned long channel_offset;
-        int timer_bit;
-        char *clk;
-        unsigned long clockevent_rating;
-        unsigned long clocksource_rating;
-};
-
-#endif /* __SH_CMT_H__ */
diff --git a/include/linux/sh_timer.h b/include/linux/sh_timer.h
new file mode 100644
index 000000000000..864bd56bd3b0
--- /dev/null
+++ b/include/linux/sh_timer.h
@@ -0,0 +1,13 @@
+#ifndef __SH_TIMER_H__
+#define __SH_TIMER_H__
+
+struct sh_timer_config {
+        char *name;
+        long channel_offset;
+        int timer_bit;
+        char *clk;
+        unsigned long clockevent_rating;
+        unsigned long clocksource_rating;
+};
+
+#endif /* __SH_TIMER_H__ */
diff --git a/include/linux/signal.h b/include/linux/signal.h
index 84f997f8aa53..c7552836bd95 100644
--- a/include/linux/signal.h
+++ b/include/linux/signal.h
@@ -235,6 +235,8 @@ static inline int valid_signal(unsigned long sig)
 extern int next_signal(struct sigpending *pending, sigset_t *mask);
 extern int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p);
 extern int __group_send_sig_info(int, struct siginfo *, struct task_struct *);
+extern long do_rt_tgsigqueueinfo(pid_t tgid, pid_t pid, int sig,
+                                 siginfo_t *info);
 extern long do_sigpending(void __user *, unsigned long);
 extern int sigprocmask(int, sigset_t *, sigset_t *);
 extern int show_unhandled_signals;
diff --git a/include/linux/slab.h b/include/linux/slab.h
index 24c5602bee99..48803064cedf 100644
--- a/include/linux/slab.h
+++ b/include/linux/slab.h
@@ -62,6 +62,8 @@
 # define SLAB_DEBUG_OBJECTS     0x00000000UL
 #endif
 
+#define SLAB_NOLEAKTRACE        0x00800000UL    /* Avoid kmemleak tracing */
+
 /* The following flags affect the page allocator grouping pages by mobility */
 #define SLAB_RECLAIM_ACCOUNT    0x00020000UL            /* Objects are reclaimable */
 #define SLAB_TEMPORARY          SLAB_RECLAIM_ACCOUNT    /* Objects are short-lived */
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 5ac9b0bcaf9a..713f841ecaa9 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -14,7 +14,7 @@
 #include <asm/page.h>           /* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>          /* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 /* Size description struct for general caches. */
 struct cache_sizes {
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 5046f90c1171..be5d40c43bd2 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -10,7 +10,7 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 enum stat_item {
         ALLOC_FASTPATH,         /* Allocation from cpu slab */
diff --git a/include/linux/spinlock_up.h b/include/linux/spinlock_up.h
index 938234c4a996..d4841ed8215b 100644
--- a/include/linux/spinlock_up.h
+++ b/include/linux/spinlock_up.h
@@ -60,6 +60,7 @@ static inline void __raw_spin_unlock(raw_spinlock_t *lock)
 #define __raw_spin_is_locked(lock)      ((void)(lock), 0)
 /* for sched.c and kernel_lock.c: */
 # define __raw_spin_lock(lock)          do { (void)(lock); } while (0)
+# define __raw_spin_lock_flags(lock, flags)     do { (void)(lock); } while (0)
 # define __raw_spin_unlock(lock)        do { (void)(lock); } while (0)
 # define __raw_spin_trylock(lock)       ({ (void)(lock); 1; })
 #endif /* DEBUG_SPINLOCK */
diff --git a/include/linux/splice.h b/include/linux/splice.h
index 5f3faa9d15ae..18e7c7c0cae6 100644
--- a/include/linux/splice.h
+++ b/include/linux/splice.h
@@ -11,8 +11,7 @@
 #include <linux/pipe_fs_i.h>
 
 /*
- * splice is tied to pipes as a transport (at least for now), so we'll just
- * add the splice flags here.
+ * Flags passed in from splice/tee/vmsplice
  */
 #define SPLICE_F_MOVE   (0x01)  /* move pages instead of copying */
 #define SPLICE_F_NONBLOCK (0x02) /* don't block on the pipe splicing (but */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 62d81435347a..d476aad3ff57 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -437,6 +437,11 @@ static inline int mem_cgroup_cache_charge_swapin(struct page *page,
         return 0;
 }
 
+static inline void
+mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
+{
+}
+
 #endif /* CONFIG_SWAP */
 #endif /* __KERNEL__*/
 #endif /* _LINUX_SWAP_H */
diff --git a/include/linux/swiotlb.h b/include/linux/swiotlb.h
index ac9ff54f7cb3..cb1a6631b8f4 100644
--- a/include/linux/swiotlb.h
+++ b/include/linux/swiotlb.h
@@ -29,7 +29,8 @@ extern void *swiotlb_alloc(unsigned order, unsigned long nslabs);
 
 extern dma_addr_t swiotlb_phys_to_bus(struct device *hwdev,
                                       phys_addr_t address);
-extern phys_addr_t swiotlb_bus_to_phys(dma_addr_t address);
+extern phys_addr_t swiotlb_bus_to_phys(struct device *hwdev,
+                                       dma_addr_t address);
 
 extern int swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size);
 
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 30520844b8da..c6c84ad8bd71 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -55,6 +55,7 @@ struct compat_timeval;
 struct robust_list_head;
 struct getcpu_cache;
 struct old_linux_dirent;
+struct perf_counter_attr;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -755,4 +756,8 @@ asmlinkage long sys_pipe(int __user *);
 
 int kernel_execve(const char *filename, char *const argv[], char *const envp[]);
 
+
+asmlinkage long sys_perf_counter_open(
+                const struct perf_counter_attr __user *attr_uptr,
+                pid_t pid, int cpu, int group_fd, unsigned long flags);
 #endif
diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h
index e6b820f8b56b..a8cc4e13434c 100644
--- a/include/linux/thread_info.h
+++ b/include/linux/thread_info.h
@@ -21,13 +21,14 @@ struct restart_block {
                 struct {
                         unsigned long arg0, arg1, arg2, arg3;
                 };
-                /* For futex_wait */
+                /* For futex_wait and futex_wait_requeue_pi */
                 struct {
                         u32 *uaddr;
                         u32 val;
                         u32 flags;
                         u32 bitset;
                         u64 time;
+                        u32 *uaddr2;
                 } futex;
                 /* For nanosleep */
                 struct {
diff --git a/include/linux/time.h b/include/linux/time.h
index 242f62499bb7..ea16c1a01d51 100644
--- a/include/linux/time.h
+++ b/include/linux/time.h
@@ -113,6 +113,21 @@ struct timespec current_kernel_time(void);
 #define CURRENT_TIME            (current_kernel_time())
 #define CURRENT_TIME_SEC        ((struct timespec) { get_seconds(), 0 })
 
+/* Some architectures do not supply their own clocksource.
+ * This is mainly the case in architectures that get their
+ * inter-tick times by reading the counter on their interval
+ * timer. Since these timers wrap every tick, they're not really
+ * useful as clocksources. Wrapping them to act like one is possible
+ * but not very efficient. So we provide a callout these arches
+ * can implement for use with the jiffies clocksource to provide
+ * finer then tick granular time.
+ */
+#ifdef CONFIG_ARCH_USES_GETTIMEOFFSET
+extern u32 arch_gettimeoffset(void);
+#else
+static inline u32 arch_gettimeoffset(void) { return 0; }
+#endif
+
 extern void do_gettimeofday(struct timeval *tv);
 extern int do_settimeofday(struct timespec *tv);
 extern int do_sys_settimeofday(struct timespec *tv, struct timezone *tz);
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
new file mode 100644
index 000000000000..c68bccba2074
--- /dev/null
+++ b/include/linux/trace_seq.h
@@ -0,0 +1,92 @@
+#ifndef _LINUX_TRACE_SEQ_H
+#define _LINUX_TRACE_SEQ_H
+
+#include <linux/fs.h>
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE.
+ */
+
+struct trace_seq {
+        unsigned char           buffer[PAGE_SIZE];
+        unsigned int            len;
+        unsigned int            readpos;
+};
+
+static inline void
+trace_seq_init(struct trace_seq *s)
+{
+        s->len = 0;
+        s->readpos = 0;
+}
+
+/*
+ * Currently only defined when tracing is enabled.
+ */
+#ifdef CONFIG_TRACING
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+        __attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+        __attribute__ ((format (printf, 2, 0)));
+extern int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
+extern void trace_print_seq(struct seq_file *m, struct trace_seq *s);
+extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+                                 size_t cnt);
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+                                size_t len);
+extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+extern int trace_seq_path(struct trace_seq *s, struct path *path);
+
+#else /* CONFIG_TRACING */
+static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+        return 0;
+}
+static inline int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+        return 0;
+}
+
+static inline void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+}
+static inline ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+                                 size_t cnt)
+{
+        return 0;
+}
+static inline int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+        return 0;
+}
+static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+        return 0;
+}
+static inline int
+trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
+{
+        return 0;
+}
+static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+                                       size_t len)
+{
+        return 0;
+}
+static inline void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+        return NULL;
+}
+static inline int trace_seq_path(struct trace_seq *s, struct path *path)
+{
+        return 0;
+}
+#endif /* CONFIG_TRACING */
+
+#endif /* _LINUX_TRACE_SEQ_H */
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index c7aa154f4bfc..eb96603d92db 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -259,14 +259,12 @@ static inline void tracehook_finish_clone(struct task_struct *child,
 
 /**
  * tracehook_report_clone - in parent, new child is about to start running
- * @trace:              return value from tracehook_prepare_clone()
  * @regs:               parent's user register state
  * @clone_flags:        flags from parent's system call
  * @pid:                new child's PID in the parent's namespace
  * @child:              new child task
  *
- * Called after a child is set up, but before it has been started
- * running.  @trace is the value returned by tracehook_prepare_clone().
+ * Called after a child is set up, but before it has been started running.
  * This is not a good place to block, because the child has not started
  * yet.  Suspend the child here if desired, and then block in
  * tracehook_report_clone_complete().  This must prevent the child from
@@ -276,13 +274,14 @@ static inline void tracehook_finish_clone(struct task_struct *child,
  *
  * Called with no locks held, but the child cannot run until this returns.
  */
-static inline void tracehook_report_clone(int trace, struct pt_regs *regs,
+static inline void tracehook_report_clone(struct pt_regs *regs,
                                           unsigned long clone_flags,
                                           pid_t pid, struct task_struct *child)
 {
-        if (unlikely(trace) || unlikely(clone_flags & CLONE_PTRACE)) {
+        if (unlikely(task_ptrace(child))) {
                 /*
-                 * The child starts up with an immediate SIGSTOP.
+                 * It doesn't matter who attached/attaching to this
+                 * task, the pending SIGSTOP is right in any case.
                  */
                 sigaddset(&child->pending.signal, SIGSTOP);
                 set_tsk_thread_flag(child, TIF_SIGPENDING);
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index d35a7ee7611f..14df7e635d43 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -31,6 +31,8 @@ struct tracepoint {
                                          * Keep in sync with vmlinux.lds.h.
                                          */
 
+#ifndef DECLARE_TRACE
+
 #define TP_PROTO(args...)       args
 #define TP_ARGS(args...)                args
 
@@ -114,6 +116,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
         struct tracepoint *end)
 { }
 #endif /* CONFIG_TRACEPOINTS */
+#endif /* DECLARE_TRACE */
 
 /*
  * Connect a probe to a tracepoint.
@@ -154,10 +157,8 @@ static inline void tracepoint_synchronize_unregister(void)
 }
 
 #define PARAMS(args...) args
-#define TRACE_FORMAT(name, proto, args, fmt)            \
-        DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-
 
+#ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro:
  *
@@ -262,5 +263,6 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define TRACE_EVENT(name, proto, args, struct, assign, print)   \
         DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#endif
 
 #endif
diff --git a/include/linux/tty.h b/include/linux/tty.h
index fc39db95499f..1488d8c81aac 100644
--- a/include/linux/tty.h
+++ b/include/linux/tty.h
@@ -185,7 +185,7 @@ struct tty_port;
 struct tty_port_operations {
         /* Return 1 if the carrier is raised */
         int (*carrier_raised)(struct tty_port *port);
-        void (*raise_dtr_rts)(struct tty_port *port);
+        void (*dtr_rts)(struct tty_port *port, int raise);
 };
         
 struct tty_port {
@@ -201,6 +201,9 @@ struct tty_port {
         unsigned char           *xmit_buf;      /* Optional buffer */
         int                     close_delay;    /* Close port delay */
         int                     closing_wait;   /* Delay for output */
+        int                     drain_delay;    /* Set to zero if no pure time
+                                                   based drain is needed else
+                                                   set to size of fifo */
 };
 
 /*
@@ -223,8 +226,11 @@ struct tty_struct {
         struct tty_driver *driver;
         const struct tty_operations *ops;
         int index;
-        /* The ldisc objects are protected by tty_ldisc_lock at the moment */
-        struct tty_ldisc ldisc;
+
+        /* Protects ldisc changes: Lock tty not pty */
+        struct mutex ldisc_mutex;
+        struct tty_ldisc *ldisc;
+
         struct mutex termios_mutex;
         spinlock_t ctrl_lock;
         /* Termios values are protected by the termios mutex */
@@ -311,6 +317,7 @@ struct tty_struct {
 #define TTY_CLOSING             7       /* ->close() in progress */
 #define TTY_LDISC               9       /* Line discipline attached */
 #define TTY_LDISC_CHANGING      10      /* Line discipline changing */
+#define TTY_LDISC_OPEN          11      /* Line discipline is open */
 #define TTY_HW_COOK_OUT         14      /* Hardware can do output cooking */
 #define TTY_HW_COOK_IN          15      /* Hardware can do input cooking */
 #define TTY_PTY_LOCK            16      /* pty private */
@@ -403,6 +410,7 @@ extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b);
 extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *);
 extern void tty_ldisc_deref(struct tty_ldisc *);
 extern struct tty_ldisc *tty_ldisc_ref_wait(struct tty_struct *);
+extern void tty_ldisc_hangup(struct tty_struct *tty);
 extern const struct file_operations tty_ldiscs_proc_fops;
 
 extern void tty_wakeup(struct tty_struct *tty);
@@ -425,6 +433,9 @@ extern struct tty_struct *tty_init_dev(struct tty_driver *driver, int idx,
 extern void tty_release_dev(struct file *filp);
 extern int tty_init_termios(struct tty_struct *tty);
 
+extern struct tty_struct *tty_pair_get_tty(struct tty_struct *tty);
+extern struct tty_struct *tty_pair_get_pty(struct tty_struct *tty);
+
 extern struct mutex tty_mutex;
 
 extern void tty_write_unlock(struct tty_struct *tty);
@@ -438,6 +449,7 @@ extern struct tty_struct *tty_port_tty_get(struct tty_port *port);
 extern void tty_port_tty_set(struct tty_port *port, struct tty_struct *tty);
 extern int tty_port_carrier_raised(struct tty_port *port);
 extern void tty_port_raise_dtr_rts(struct tty_port *port);
+extern void tty_port_lower_dtr_rts(struct tty_port *port);
 extern void tty_port_hangup(struct tty_port *port);
 extern int tty_port_block_til_ready(struct tty_port *port,
                                 struct tty_struct *tty, struct file *filp);
diff --git a/include/linux/tty_driver.h b/include/linux/tty_driver.h
index bcba84ea2d86..3566129384a4 100644
--- a/include/linux/tty_driver.h
+++ b/include/linux/tty_driver.h
@@ -127,7 +127,8 @@
  *      the line discipline are close to full, and it should somehow
  *      signal that no more characters should be sent to the tty.
  *
- *      Optional: Always invoke via tty_throttle();
+ *      Optional: Always invoke via tty_throttle(), called under the
+ *      termios lock.
  * 
  * void (*unthrottle)(struct tty_struct * tty);
  *
@@ -135,7 +136,8 @@
  *      that characters can now be sent to the tty without fear of
  *      overrunning the input buffers of the line disciplines.
  * 
- *      Optional: Always invoke via tty_unthrottle();
+ *      Optional: Always invoke via tty_unthrottle(), called under the
+ *      termios lock.
  *
  * void (*stop)(struct tty_struct *tty);
  *
diff --git a/include/linux/usb/serial.h b/include/linux/usb/serial.h
index 625e9e4639c6..8cdfed738fe4 100644
--- a/include/linux/usb/serial.h
+++ b/include/linux/usb/serial.h
@@ -224,8 +224,7 @@ struct usb_serial_driver {
         /* Called by console with tty = NULL and by tty */
         int  (*open)(struct tty_struct *tty,
                         struct usb_serial_port *port, struct file *filp);
-        void (*close)(struct tty_struct *tty,
-                        struct usb_serial_port *port, struct file *filp);
+        void (*close)(struct usb_serial_port *port);
         int  (*write)(struct tty_struct *tty, struct usb_serial_port *port,
                         const unsigned char *buf, int count);
         /* Called only by the tty layer */
@@ -241,6 +240,10 @@ struct usb_serial_driver {
         int  (*tiocmget)(struct tty_struct *tty, struct file *file);
         int  (*tiocmset)(struct tty_struct *tty, struct file *file,
                          unsigned int set, unsigned int clear);
+        /* Called by the tty layer for port level work. There may or may not
+           be an attached tty at this point */
+        void (*dtr_rts)(struct usb_serial_port *port, int on);
+        int  (*carrier_raised)(struct usb_serial_port *port);
         /* USB events */
         void (*read_int_callback)(struct urb *urb);
         void (*write_int_callback)(struct urb *urb);
@@ -283,8 +286,7 @@ extern int usb_serial_generic_open(struct tty_struct *tty,
                 struct usb_serial_port *port, struct file *filp);
 extern int usb_serial_generic_write(struct tty_struct *tty,
         struct usb_serial_port *port, const unsigned char *buf, int count);
-extern void usb_serial_generic_close(struct tty_struct *tty,
-                        struct usb_serial_port *port, struct file *filp);
+extern void usb_serial_generic_close(struct usb_serial_port *port);
 extern int usb_serial_generic_resume(struct usb_serial *serial);
 extern int usb_serial_generic_write_room(struct tty_struct *tty);
 extern int usb_serial_generic_chars_in_buffer(struct tty_struct *tty);
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h
index 94c56d29869d..be7d255fc7cf 100644
--- a/include/linux/virtio_blk.h
+++ b/include/linux/virtio_blk.h
@@ -15,6 +15,10 @@
 #define VIRTIO_BLK_F_GEOMETRY   4       /* Legacy geometry available  */
 #define VIRTIO_BLK_F_RO         5       /* Disk is read-only */
 #define VIRTIO_BLK_F_BLK_SIZE   6       /* Block size of disk is available*/
+#define VIRTIO_BLK_F_SCSI       7       /* Supports scsi command passthru */
+#define VIRTIO_BLK_F_IDENTIFY   8       /* ATA IDENTIFY supported */
+
+#define VIRTIO_BLK_ID_BYTES     (sizeof(__u16[256]))    /* IDENTIFY DATA */
 
 struct virtio_blk_config
 {
@@ -32,6 +36,7 @@ struct virtio_blk_config
         } geometry;
         /* block size of device (if VIRTIO_BLK_F_BLK_SIZE) */
         __u32 blk_size;
+        __u8 identify[VIRTIO_BLK_ID_BYTES];
 } __attribute__((packed));
 
 /* These two define direction. */
@@ -55,6 +60,13 @@ struct virtio_blk_outhdr
         __u64 sector;
 };
 
+struct virtio_scsi_inhdr {
+        __u32 errors;
+        __u32 data_len;
+        __u32 sense_len;
+        __u32 residual;
+};
+
 /* And this is the final byte of the write scatter-gather list. */
 #define VIRTIO_BLK_S_OK         0
 #define VIRTIO_BLK_S_IOERR      1
diff --git a/include/linux/wait.h b/include/linux/wait.h
index bc024632f365..6788e1a4d4ca 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -132,8 +132,6 @@ static inline void __remove_wait_queue(wait_queue_head_t *head,
         list_del(&old->task_list);
 }
 
-void __wake_up_common(wait_queue_head_t *q, unsigned int mode,
-                        int nr_exclusive, int sync, void *key);
 void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr, void *key);
 void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key);
 void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 93445477f86a..3224820c8514 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -79,7 +79,6 @@ struct writeback_control {
 void writeback_inodes(struct writeback_control *wbc);
 int inode_wait(void *);
 void sync_inodes_sb(struct super_block *, int wait);
-void sync_inodes(int wait);
 
 /* writeback.h requires fs.h; it, too, is not included from here. */
 static inline void wait_on_inode(struct inode *inode)
diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
index 43b50d36925c..3878d1dc7f59 100644
--- a/include/scsi/scsi_cmnd.h
+++ b/include/scsi/scsi_cmnd.h
@@ -270,7 +270,7 @@ static inline unsigned char scsi_get_prot_type(struct scsi_cmnd *scmd)
 
 static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd)
 {
-        return scmd->request->sector;
+        return blk_rq_pos(scmd->request);
 }
 
 static inline unsigned scsi_prot_sg_count(struct scsi_cmnd *cmd)
diff --git a/include/trace/block.h b/include/trace/block.h
deleted file mode 100644
index 25b7068b819e..000000000000
--- a/include/trace/block.h
+++ /dev/null
@@ -1,76 +0,0 @@
-#ifndef _TRACE_BLOCK_H
-#define _TRACE_BLOCK_H
-
-#include <linux/blkdev.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(block_rq_abort,
-        TP_PROTO(struct request_queue *q, struct request *rq),
-              TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_insert,
-        TP_PROTO(struct request_queue *q, struct request *rq),
-              TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_issue,
-        TP_PROTO(struct request_queue *q, struct request *rq),
-              TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_requeue,
-        TP_PROTO(struct request_queue *q, struct request *rq),
-              TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_complete,
-        TP_PROTO(struct request_queue *q, struct request *rq),
-              TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_bio_bounce,
-        TP_PROTO(struct request_queue *q, struct bio *bio),
-              TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_complete,
-        TP_PROTO(struct request_queue *q, struct bio *bio),
-              TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_backmerge,
-        TP_PROTO(struct request_queue *q, struct bio *bio),
-              TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_frontmerge,
-        TP_PROTO(struct request_queue *q, struct bio *bio),
-              TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_queue,
-        TP_PROTO(struct request_queue *q, struct bio *bio),
-              TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_getrq,
-        TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-              TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_sleeprq,
-        TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-              TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_plug,
-        TP_PROTO(struct request_queue *q),
-              TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_timer,
-        TP_PROTO(struct request_queue *q),
-              TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_io,
-        TP_PROTO(struct request_queue *q),
-              TP_ARGS(q));
-
-DECLARE_TRACE(block_split,
-        TP_PROTO(struct request_queue *q, struct bio *bio, unsigned int pdu),
-              TP_ARGS(q, bio, pdu));
-
-DECLARE_TRACE(block_remap,
-        TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
-                 sector_t from, sector_t to),
-              TP_ARGS(q, bio, dev, from, to));
-
-#endif
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
new file mode 100644
index 000000000000..f7a7ae1e8f90
--- /dev/null
+++ b/include/trace/define_trace.h
@@ -0,0 +1,75 @@
+/*
+ * Trace files that want to automate creationg of all tracepoints defined
+ * in their file should include this file. The following are macros that the
+ * trace file may define:
+ *
+ * TRACE_SYSTEM defines the system the tracepoint is for
+ *
+ * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h
+ *     This macro may be defined to tell define_trace.h what file to include.
+ *     Note, leave off the ".h".
+ *
+ * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace
+ *     then this macro can define the path to use. Note, the path is relative to
+ *     define_trace.h, not the file including it. Full path names for out of tree
+ *     modules must be used.
+ */
+
+#ifdef CREATE_TRACE_POINTS
+
+/* Prevent recursion */
+#undef CREATE_TRACE_POINTS
+
+#include <linux/stringify.h>
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)  \
+        DEFINE_TRACE(name)
+
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)        \
+        DEFINE_TRACE(name)
+
+#undef TRACE_INCLUDE
+#undef __TRACE_INCLUDE
+
+#ifndef TRACE_INCLUDE_FILE
+# define TRACE_INCLUDE_FILE TRACE_SYSTEM
+# define UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifndef TRACE_INCLUDE_PATH
+# define __TRACE_INCLUDE(system) <trace/events/system.h>
+# define UNDEF_TRACE_INCLUDE_PATH
+#else
+# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h)
+#endif
+
+# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system)
+
+/* Let the trace headers be reread */
+#define TRACE_HEADER_MULTI_READ
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#ifdef CONFIG_EVENT_TRACING
+#include <trace/ftrace.h>
+#endif
+
+#undef TRACE_HEADER_MULTI_READ
+
+/* Only undef what we defined in this file */
+#ifdef UNDEF_TRACE_INCLUDE_FILE
+# undef TRACE_INCLUDE_FILE
+# undef UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifdef UNDEF_TRACE_INCLUDE_PATH
+# undef TRACE_INCLUDE_PATH
+# undef UNDEF_TRACE_INCLUDE_PATH
+#endif
+
+/* We may be processing more files */
+#define CREATE_TRACE_POINTS
+
+#endif /* CREATE_TRACE_POINTS */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
new file mode 100644
index 000000000000..d6b05f42dd44
--- /dev/null
+++ b/include/trace/events/block.h
@@ -0,0 +1,493 @@
+#if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLOCK_H
+
+#include <linux/blktrace_api.h>
+#include <linux/blkdev.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
+TRACE_EVENT(block_rq_abort,
+
+        TP_PROTO(struct request_queue *q, struct request *rq),
+
+        TP_ARGS(q, rq),
+
+        TP_STRUCT__entry(
+                __field(  dev_t,        dev                     )
+                __field(  sector_t,     sector                  )
+                __field(  unsigned int, nr_sector               )
+                __field(  int,          errors                  )
+                __array(  char,         rwbs,   6               )
+                __dynamic_array( char,  cmd,    blk_cmd_buf_len(rq)     )
+        ),
+
+        TP_fast_assign(
+                __entry->dev       = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+                __entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+                __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+                __entry->errors    = rq->errors;
+
+                blk_fill_rwbs_rq(__entry->rwbs, rq);
+                blk_dump_cmd(__get_str(cmd), rq);
+        ),
+
+        TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->rwbs, __get_str(cmd),
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_insert,
+
+        TP_PROTO(struct request_queue *q, struct request *rq),
+
+        TP_ARGS(q, rq),
+
+        TP_STRUCT__entry(
+                __field(  dev_t,        dev                     )
+                __field(  sector_t,     sector                  )
+                __field(  unsigned int, nr_sector               )
+                __field(  unsigned int, bytes                   )
+                __array(  char,         rwbs,   6               )
+                __array(  char,         comm,   TASK_COMM_LEN   )
+                __dynamic_array( char,  cmd,    blk_cmd_buf_len(rq)     )
+        ),
+
+        TP_fast_assign(
+                __entry->dev       = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+                __entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+                __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+                __entry->bytes     = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0;
+
+                blk_fill_rwbs_rq(__entry->rwbs, rq);
+                blk_dump_cmd(__get_str(cmd), rq);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->rwbs, __entry->bytes, __get_str(cmd),
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_issue,
+
+        TP_PROTO(struct request_queue *q, struct request *rq),
+
+        TP_ARGS(q, rq),
+
+        TP_STRUCT__entry(
+                __field(  dev_t,        dev                     )
+                __field(  sector_t,     sector                  )
+                __field(  unsigned int, nr_sector               )
+                __field(  unsigned int, bytes                   )
+                __array(  char,         rwbs,   6               )
+                __array(  char,         comm,   TASK_COMM_LEN   )
+                __dynamic_array( char,  cmd,    blk_cmd_buf_len(rq)     )
+        ),
+
+        TP_fast_assign(
+                __entry->dev       = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+                __entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+                __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+                __entry->bytes     = blk_pc_request(rq) ? blk_rq_bytes(rq) : 0;
+
+                blk_fill_rwbs_rq(__entry->rwbs, rq);
+                blk_dump_cmd(__get_str(cmd), rq);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->rwbs, __entry->bytes, __get_str(cmd),
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_requeue,
+
+        TP_PROTO(struct request_queue *q, struct request *rq),
+
+        TP_ARGS(q, rq),
+
+        TP_STRUCT__entry(
+                __field(  dev_t,        dev                     )
+                __field(  sector_t,     sector                  )
+                __field(  unsigned int, nr_sector               )
+                __field(  int,          errors                  )
+                __array(  char,         rwbs,   6               )
+                __dynamic_array( char,  cmd,    blk_cmd_buf_len(rq)     )
+        ),
+
+        TP_fast_assign(
+                __entry->dev       = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+                __entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+                __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+                __entry->errors    = rq->errors;
+
+                blk_fill_rwbs_rq(__entry->rwbs, rq);
+                blk_dump_cmd(__get_str(cmd), rq);
+        ),
+
+        TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->rwbs, __get_str(cmd),
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_complete,
+
+        TP_PROTO(struct request_queue *q, struct request *rq),
+
+        TP_ARGS(q, rq),
+
+        TP_STRUCT__entry(
+                __field(  dev_t,        dev                     )
+                __field(  sector_t,     sector                  )
+                __field(  unsigned int, nr_sector               )
+                __field(  int,          errors                  )
+                __array(  char,         rwbs,   6               )
+                __dynamic_array( char,  cmd,    blk_cmd_buf_len(rq)     )
+        ),
+
+        TP_fast_assign(
+                __entry->dev       = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+                __entry->sector    = blk_pc_request(rq) ? 0 : blk_rq_pos(rq);
+                __entry->nr_sector = blk_pc_request(rq) ? 0 : blk_rq_sectors(rq);
+                __entry->errors    = rq->errors;
+
+                blk_fill_rwbs_rq(__entry->rwbs, rq);
+                blk_dump_cmd(__get_str(cmd), rq);
+        ),
+
+        TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev),
+                  __entry->rwbs, __get_str(cmd),
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->errors)
+);
+TRACE_EVENT(block_bio_bounce,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio),
+
+        TP_ARGS(q, bio),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev                     )
+                __field( sector_t,      sector                  )
+                __field( unsigned int,  nr_sector               )
+                __array( char,          rwbs,   6               )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio->bi_bdev->bd_dev;
+                __entry->sector         = bio->bi_sector;
+                __entry->nr_sector      = bio->bi_size >> 9;
+                blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_complete,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio),
+
+        TP_ARGS(q, bio),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev             )
+                __field( sector_t,      sector          )
+                __field( unsigned,      nr_sector       )
+                __field( int,           error           )
+                __array( char,          rwbs,   6       )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio->bi_bdev->bd_dev;
+                __entry->sector         = bio->bi_sector;
+                __entry->nr_sector      = bio->bi_size >> 9;
+                blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u [%d]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->error)
+);
+
+TRACE_EVENT(block_bio_backmerge,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio),
+
+        TP_ARGS(q, bio),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev                     )
+                __field( sector_t,      sector                  )
+                __field( unsigned int,  nr_sector               )
+                __array( char,          rwbs,   6               )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio->bi_bdev->bd_dev;
+                __entry->sector         = bio->bi_sector;
+                __entry->nr_sector      = bio->bi_size >> 9;
+                blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_frontmerge,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio),
+
+        TP_ARGS(q, bio),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev                     )
+                __field( sector_t,      sector                  )
+                __field( unsigned,      nr_sector               )
+                __array( char,          rwbs,   6               )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio->bi_bdev->bd_dev;
+                __entry->sector         = bio->bi_sector;
+                __entry->nr_sector      = bio->bi_size >> 9;
+                blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_queue,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio),
+
+        TP_ARGS(q, bio),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev                     )
+                __field( sector_t,      sector                  )
+                __field( unsigned int,  nr_sector               )
+                __array( char,          rwbs,   6               )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio->bi_bdev->bd_dev;
+                __entry->sector         = bio->bi_sector;
+                __entry->nr_sector      = bio->bi_size >> 9;
+                blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_getrq,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+        TP_ARGS(q, bio, rw),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev                     )
+                __field( sector_t,      sector                  )
+                __field( unsigned int,  nr_sector               )
+                __array( char,          rwbs,   6               )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio ? bio->bi_bdev->bd_dev : 0;
+                __entry->sector         = bio ? bio->bi_sector : 0;
+                __entry->nr_sector      = bio ? bio->bi_size >> 9 : 0;
+                blk_fill_rwbs(__entry->rwbs,
+                              bio ? bio->bi_rw : 0, __entry->nr_sector);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_sleeprq,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+        TP_ARGS(q, bio, rw),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev                     )
+                __field( sector_t,      sector                  )
+                __field( unsigned int,  nr_sector               )
+                __array( char,          rwbs,   6               )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio ? bio->bi_bdev->bd_dev : 0;
+                __entry->sector         = bio ? bio->bi_sector : 0;
+                __entry->nr_sector      = bio ? bio->bi_size >> 9 : 0;
+                blk_fill_rwbs(__entry->rwbs,
+                            bio ? bio->bi_rw : 0, __entry->nr_sector);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_plug,
+
+        TP_PROTO(struct request_queue *q),
+
+        TP_ARGS(q),
+
+        TP_STRUCT__entry(
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("[%s]", __entry->comm)
+);
+
+TRACE_EVENT(block_unplug_timer,
+
+        TP_PROTO(struct request_queue *q),
+
+        TP_ARGS(q),
+
+        TP_STRUCT__entry(
+                __field( int,           nr_rq                   )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->nr_rq  = q->rq.count[READ] + q->rq.count[WRITE];
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_unplug_io,
+
+        TP_PROTO(struct request_queue *q),
+
+        TP_ARGS(q),
+
+        TP_STRUCT__entry(
+                __field( int,           nr_rq                   )
+                __array( char,          comm,   TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->nr_rq  = q->rq.count[READ] + q->rq.count[WRITE];
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_split,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio,
+                 unsigned int new_sector),
+
+        TP_ARGS(q, bio, new_sector),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev                             )
+                __field( sector_t,      sector                          )
+                __field( sector_t,      new_sector                      )
+                __array( char,          rwbs,           6               )
+                __array( char,          comm,           TASK_COMM_LEN   )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio->bi_bdev->bd_dev;
+                __entry->sector         = bio->bi_sector;
+                __entry->new_sector     = new_sector;
+                blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+                memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+        TP_printk("%d,%d %s %llu / %llu [%s]",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  (unsigned long long)__entry->new_sector,
+                  __entry->comm)
+);
+
+TRACE_EVENT(block_remap,
+
+        TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
+                 sector_t from),
+
+        TP_ARGS(q, bio, dev, from),
+
+        TP_STRUCT__entry(
+                __field( dev_t,         dev             )
+                __field( sector_t,      sector          )
+                __field( unsigned int,  nr_sector       )
+                __field( dev_t,         old_dev         )
+                __field( sector_t,      old_sector      )
+                __array( char,          rwbs,   6       )
+        ),
+
+        TP_fast_assign(
+                __entry->dev            = bio->bi_bdev->bd_dev;
+                __entry->sector         = bio->bi_sector;
+                __entry->nr_sector      = bio->bi_size >> 9;
+                __entry->old_dev        = dev;
+                __entry->old_sector     = from;
+                blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+        ),
+
+        TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
+                  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+                  (unsigned long long)__entry->sector,
+                  __entry->nr_sector,
+                  MAJOR(__entry->old_dev), MINOR(__entry->old_dev),
+                  (unsigned long long)__entry->old_sector)
+);
+
+#endif /* _TRACE_BLOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
new file mode 100644
index 000000000000..b0c7ede55eb1
--- /dev/null
+++ b/include/trace/events/irq.h
@@ -0,0 +1,145 @@
+#if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_H
+
+#include <linux/tracepoint.h>
+#include <linux/interrupt.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
+#define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
+#define show_softirq_name(val)                  \
+        __print_symbolic(val,                   \
+                         softirq_name(HI),      \
+                         softirq_name(TIMER),   \
+                         softirq_name(NET_TX),  \
+                         softirq_name(NET_RX),  \
+                         softirq_name(BLOCK),   \
+                         softirq_name(TASKLET), \
+                         softirq_name(SCHED),   \
+                         softirq_name(HRTIMER), \
+                         softirq_name(RCU))
+
+/**
+ * irq_handler_entry - called immediately before the irq action handler
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ *
+ * The struct irqaction pointed to by @action contains various
+ * information about the handler, including the device name,
+ * @action->name, and the device id, @action->dev_id. When used in
+ * conjunction with the irq_handler_exit tracepoint, we can figure
+ * out irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_entry,
+
+        TP_PROTO(int irq, struct irqaction *action),
+
+        TP_ARGS(irq, action),
+
+        TP_STRUCT__entry(
+                __field(        int,    irq             )
+                __string(       name,   action->name    )
+        ),
+
+        TP_fast_assign(
+                __entry->irq = irq;
+                __assign_str(name, action->name);
+        ),
+
+        TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name))
+);
+
+/**
+ * irq_handler_exit - called immediately after the irq action handler returns
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ * @ret: return value
+ *
+ * If the @ret value is set to IRQ_HANDLED, then we know that the corresponding
+ * @action->handler scuccessully handled this irq. Otherwise, the irq might be
+ * a shared irq line, or the irq was not handled successfully. Can be used in
+ * conjunction with the irq_handler_entry to understand irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_exit,
+
+        TP_PROTO(int irq, struct irqaction *action, int ret),
+
+        TP_ARGS(irq, action, ret),
+
+        TP_STRUCT__entry(
+                __field(        int,    irq     )
+                __field(        int,    ret     )
+        ),
+
+        TP_fast_assign(
+                __entry->irq    = irq;
+                __entry->ret    = ret;
+        ),
+
+        TP_printk("irq=%d return=%s",
+                  __entry->irq, __entry->ret ? "handled" : "unhandled")
+);
+
+/**
+ * softirq_entry - called immediately before the softirq handler
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter, contains a pointer to the struct softirq_action
+ * which has a pointer to the action handler that is called. By subtracting
+ * the @vec pointer from the @h pointer, we can determine the softirq
+ * number. Also, when used in combination with the softirq_exit tracepoint
+ * we can determine the softirq latency.
+ */
+TRACE_EVENT(softirq_entry,
+
+        TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+        TP_ARGS(h, vec),
+
+        TP_STRUCT__entry(
+                __field(        int,    vec                     )
+        ),
+
+        TP_fast_assign(
+                __entry->vec = (int)(h - vec);
+        ),
+
+        TP_printk("softirq=%d action=%s", __entry->vec,
+                  show_softirq_name(__entry->vec))
+);
+
+/**
+ * softirq_exit - called immediately after the softirq handler returns
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the struct softirq_action
+ * that has handled the softirq. By subtracting the @vec pointer from
+ * the @h pointer, we can determine the softirq number. Also, when used in
+ * combination with the softirq_entry tracepoint we can determine the softirq
+ * latency.
+ */
+TRACE_EVENT(softirq_exit,
+
+        TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+        TP_ARGS(h, vec),
+
+        TP_STRUCT__entry(
+                __field(        int,    vec                     )
+        ),
+
+        TP_fast_assign(
+                __entry->vec = (int)(h - vec);
+        ),
+
+        TP_printk("softirq=%d action=%s", __entry->vec,
+                  show_softirq_name(__entry->vec))
+);
+
+#endif /*  _TRACE_IRQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
new file mode 100644
index 000000000000..9baba50d6512
--- /dev/null
+++ b/include/trace/events/kmem.h
@@ -0,0 +1,231 @@
+#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KMEM_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kmem
+
+/*
+ * The order of these masks is important. Matching masks will be seen
+ * first and the left over flags will end up showing by themselves.
+ *
+ * For example, if we have GFP_KERNEL before GFP_USER we wil get:
+ *
+ *  GFP_KERNEL|GFP_HARDWALL
+ *
+ * Thus most bits set go first.
+ */
+#define show_gfp_flags(flags)                                           \
+        (flags) ? __print_flags(flags, "|",                             \
+        {(unsigned long)GFP_HIGHUSER_MOVABLE,   "GFP_HIGHUSER_MOVABLE"}, \
+        {(unsigned long)GFP_HIGHUSER,           "GFP_HIGHUSER"},        \
+        {(unsigned long)GFP_USER,               "GFP_USER"},            \
+        {(unsigned long)GFP_TEMPORARY,          "GFP_TEMPORARY"},       \
+        {(unsigned long)GFP_KERNEL,             "GFP_KERNEL"},          \
+        {(unsigned long)GFP_NOFS,               "GFP_NOFS"},            \
+        {(unsigned long)GFP_ATOMIC,             "GFP_ATOMIC"},          \
+        {(unsigned long)GFP_NOIO,               "GFP_NOIO"},            \
+        {(unsigned long)__GFP_HIGH,             "GFP_HIGH"},            \
+        {(unsigned long)__GFP_WAIT,             "GFP_WAIT"},            \
+        {(unsigned long)__GFP_IO,               "GFP_IO"},              \
+        {(unsigned long)__GFP_COLD,             "GFP_COLD"},            \
+        {(unsigned long)__GFP_NOWARN,           "GFP_NOWARN"},          \
+        {(unsigned long)__GFP_REPEAT,           "GFP_REPEAT"},          \
+        {(unsigned long)__GFP_NOFAIL,           "GFP_NOFAIL"},          \
+        {(unsigned long)__GFP_NORETRY,          "GFP_NORETRY"},         \
+        {(unsigned long)__GFP_COMP,             "GFP_COMP"},            \
+        {(unsigned long)__GFP_ZERO,             "GFP_ZERO"},            \
+        {(unsigned long)__GFP_NOMEMALLOC,       "GFP_NOMEMALLOC"},      \
+        {(unsigned long)__GFP_HARDWALL,         "GFP_HARDWALL"},        \
+        {(unsigned long)__GFP_THISNODE,         "GFP_THISNODE"},        \
+        {(unsigned long)__GFP_RECLAIMABLE,      "GFP_RECLAIMABLE"},     \
+        {(unsigned long)__GFP_MOVABLE,          "GFP_MOVABLE"}          \
+        ) : "GFP_NOWAIT"
+
+TRACE_EVENT(kmalloc,
+
+        TP_PROTO(unsigned long call_site,
+                 const void *ptr,
+                 size_t bytes_req,
+                 size_t bytes_alloc,
+                 gfp_t gfp_flags),
+
+        TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+        TP_STRUCT__entry(
+                __field(        unsigned long,  call_site       )
+                __field(        const void *,   ptr             )
+                __field(        size_t,         bytes_req       )
+                __field(        size_t,         bytes_alloc     )
+                __field(        gfp_t,          gfp_flags       )
+        ),
+
+        TP_fast_assign(
+                __entry->call_site      = call_site;
+                __entry->ptr            = ptr;
+                __entry->bytes_req      = bytes_req;
+                __entry->bytes_alloc    = bytes_alloc;
+                __entry->gfp_flags      = gfp_flags;
+        ),
+
+        TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+                __entry->call_site,
+                __entry->ptr,
+                __entry->bytes_req,
+                __entry->bytes_alloc,
+                show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmem_cache_alloc,
+
+        TP_PROTO(unsigned long call_site,
+                 const void *ptr,
+                 size_t bytes_req,
+                 size_t bytes_alloc,
+                 gfp_t gfp_flags),
+
+        TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+        TP_STRUCT__entry(
+                __field(        unsigned long,  call_site       )
+                __field(        const void *,   ptr             )
+                __field(        size_t,         bytes_req       )
+                __field(        size_t,         bytes_alloc     )
+                __field(        gfp_t,          gfp_flags       )
+        ),
+
+        TP_fast_assign(
+                __entry->call_site      = call_site;
+                __entry->ptr            = ptr;
+                __entry->bytes_req      = bytes_req;
+                __entry->bytes_alloc    = bytes_alloc;
+                __entry->gfp_flags      = gfp_flags;
+        ),
+
+        TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+                __entry->call_site,
+                __entry->ptr,
+                __entry->bytes_req,
+                __entry->bytes_alloc,
+                show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmalloc_node,
+
+        TP_PROTO(unsigned long call_site,
+                 const void *ptr,
+                 size_t bytes_req,
+                 size_t bytes_alloc,
+                 gfp_t gfp_flags,
+                 int node),
+
+        TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+        TP_STRUCT__entry(
+                __field(        unsigned long,  call_site       )
+                __field(        const void *,   ptr             )
+                __field(        size_t,         bytes_req       )
+                __field(        size_t,         bytes_alloc     )
+                __field(        gfp_t,          gfp_flags       )
+                __field(        int,            node            )
+        ),
+
+        TP_fast_assign(
+                __entry->call_site      = call_site;
+                __entry->ptr            = ptr;
+                __entry->bytes_req      = bytes_req;
+                __entry->bytes_alloc    = bytes_alloc;
+                __entry->gfp_flags      = gfp_flags;
+                __entry->node           = node;
+        ),
+
+        TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+                __entry->call_site,
+                __entry->ptr,
+                __entry->bytes_req,
+                __entry->bytes_alloc,
+                show_gfp_flags(__entry->gfp_flags),
+                __entry->node)
+);
+
+TRACE_EVENT(kmem_cache_alloc_node,
+
+        TP_PROTO(unsigned long call_site,
+                 const void *ptr,
+                 size_t bytes_req,
+                 size_t bytes_alloc,
+                 gfp_t gfp_flags,
+                 int node),
+
+        TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+        TP_STRUCT__entry(
+                __field(        unsigned long,  call_site       )
+                __field(        const void *,   ptr             )
+                __field(        size_t,         bytes_req       )
+                __field(        size_t,         bytes_alloc     )
+                __field(        gfp_t,          gfp_flags       )
+                __field(        int,            node            )
+        ),
+
+        TP_fast_assign(
+                __entry->call_site      = call_site;
+                __entry->ptr            = ptr;
+                __entry->bytes_req      = bytes_req;
+                __entry->bytes_alloc    = bytes_alloc;
+                __entry->gfp_flags      = gfp_flags;
+                __entry->node           = node;
+        ),
+
+        TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+                __entry->call_site,
+                __entry->ptr,
+                __entry->bytes_req,
+                __entry->bytes_alloc,
+                show_gfp_flags(__entry->gfp_flags),
+                __entry->node)
+);
+
+TRACE_EVENT(kfree,
+
+        TP_PROTO(unsigned long call_site, const void *ptr),
+
+        TP_ARGS(call_site, ptr),
+
+        TP_STRUCT__entry(
+                __field(        unsigned long,  call_site       )
+                __field(        const void *,   ptr             )
+        ),
+
+        TP_fast_assign(
+                __entry->call_site      = call_site;
+                __entry->ptr            = ptr;
+        ),
+
+        TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+
+TRACE_EVENT(kmem_cache_free,
+
+        TP_PROTO(unsigned long call_site, const void *ptr),
+
+        TP_ARGS(call_site, ptr),
+
+        TP_STRUCT__entry(
+                __field(        unsigned long,  call_site       )
+                __field(        const void *,   ptr             )
+        ),
+
+        TP_fast_assign(
+                __entry->call_site      = call_site;
+                __entry->ptr            = ptr;
+        ),
+
+        TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+#endif /* _TRACE_KMEM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/lockdep.h b/include/trace/events/lockdep.h
new file mode 100644
index 000000000000..0e956c9dfd7e
--- /dev/null
+++ b/include/trace/events/lockdep.h
@@ -0,0 +1,96 @@
+#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCKDEP_H
+
+#include <linux/lockdep.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lockdep
+
+#ifdef CONFIG_LOCKDEP
+
+TRACE_EVENT(lock_acquire,
+
+        TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
+                int trylock, int read, int check,
+                struct lockdep_map *next_lock, unsigned long ip),
+
+        TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
+
+        TP_STRUCT__entry(
+                __field(unsigned int, flags)
+                __string(name, lock->name)
+        ),
+
+        TP_fast_assign(
+                __entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
+                __assign_str(name, lock->name);
+        ),
+
+        TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+                  (__entry->flags & 2) ? "read " : "",
+                  __get_str(name))
+);
+
+TRACE_EVENT(lock_release,
+
+        TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+
+        TP_ARGS(lock, nested, ip),
+
+        TP_STRUCT__entry(
+                __string(name, lock->name)
+        ),
+
+        TP_fast_assign(
+                __assign_str(name, lock->name);
+        ),
+
+        TP_printk("%s", __get_str(name))
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+TRACE_EVENT(lock_contended,
+
+        TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+        TP_ARGS(lock, ip),
+
+        TP_STRUCT__entry(
+                __string(name, lock->name)
+        ),
+
+        TP_fast_assign(
+                __assign_str(name, lock->name);
+        ),
+
+        TP_printk("%s", __get_str(name))
+);
+
+TRACE_EVENT(lock_acquired,
+        TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+
+        TP_ARGS(lock, ip, waittime),
+
+        TP_STRUCT__entry(
+                __string(name, lock->name)
+                __field(unsigned long, wait_usec)
+                __field(unsigned long, wait_nsec_rem)
+        ),
+        TP_fast_assign(
+                __assign_str(name, lock->name);
+                __entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
+                __entry->wait_usec = (unsigned long) waittime;
+        ),
+        TP_printk("%s (%lu.%03lu us)", __get_str(name), __entry->wait_usec,
+                                       __entry->wait_nsec_rem)
+);
+
+#endif
+#endif
+
+#endif /* _TRACE_LOCKDEP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/sched_event_types.h b/include/trace/events/sched.h
index 63547dc1125f..24ab5bcff7b2 100644
--- a/include/trace/sched_event_types.h
+++ b/include/trace/events/sched.h
@@ -1,9 +1,8 @@
+#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCHED_H
 
-/* use <trace/sched.h> instead */
-#ifndef TRACE_EVENT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM sched
@@ -157,6 +156,7 @@ TRACE_EVENT(sched_switch,
                 __array(        char,   prev_comm,      TASK_COMM_LEN   )
                 __field(        pid_t,  prev_pid                        )
                 __field(        int,    prev_prio                       )
+                __field(        long,   prev_state                      )
                 __array(        char,   next_comm,      TASK_COMM_LEN   )
                 __field(        pid_t,  next_pid                        )
                 __field(        int,    next_prio                       )
@@ -166,13 +166,19 @@ TRACE_EVENT(sched_switch,
                 memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
                 __entry->prev_pid       = prev->pid;
                 __entry->prev_prio      = prev->prio;
+                __entry->prev_state     = prev->state;
                 memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
                 __entry->next_pid       = next->pid;
                 __entry->next_prio      = next->prio;
         ),
 
-        TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
+        TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
                 __entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+                __entry->prev_state ?
+                  __print_flags(__entry->prev_state, "|",
+                                { 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
+                                { 16, "Z" }, { 32, "X" }, { 64, "x" },
+                                { 128, "W" }) : "R",
                 __entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
 
@@ -181,9 +187,9 @@ TRACE_EVENT(sched_switch,
  */
 TRACE_EVENT(sched_migrate_task,
 
-        TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
+        TP_PROTO(struct task_struct *p, int dest_cpu),
 
-        TP_ARGS(p, orig_cpu, dest_cpu),
+        TP_ARGS(p, dest_cpu),
 
         TP_STRUCT__entry(
                 __array(        char,   comm,   TASK_COMM_LEN   )
@@ -197,7 +203,7 @@ TRACE_EVENT(sched_migrate_task,
                 memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
                 __entry->pid            = p->pid;
                 __entry->prio           = p->prio;
-                __entry->orig_cpu       = orig_cpu;
+                __entry->orig_cpu       = task_cpu(p);
                 __entry->dest_cpu       = dest_cpu;
         ),
 
@@ -334,4 +340,7 @@ TRACE_EVENT(sched_signal_send,
                   __entry->sig, __entry->comm, __entry->pid)
 );
 
-#undef TRACE_SYSTEM
+#endif /* _TRACE_SCHED_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
new file mode 100644
index 000000000000..1e8fabb57c06
--- /dev/null
+++ b/include/trace/events/skb.h
@@ -0,0 +1,40 @@
+#if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SKB_H
+
+#include <linux/skbuff.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM skb
+
+/*
+ * Tracepoint for free an sk_buff:
+ */
+TRACE_EVENT(kfree_skb,
+
+        TP_PROTO(struct sk_buff *skb, void *location),
+
+        TP_ARGS(skb, location),
+
+        TP_STRUCT__entry(
+                __field(        void *,         skbaddr         )
+                __field(        unsigned short, protocol        )
+                __field(        void *,         location        )
+        ),
+
+        TP_fast_assign(
+                __entry->skbaddr = skb;
+                if (skb) {
+                        __entry->protocol = ntohs(skb->protocol);
+                }
+                __entry->location = location;
+        ),
+
+        TP_printk("skbaddr=%p protocol=%u location=%p",
+                __entry->skbaddr, __entry->protocol, __entry->location)
+);
+
+#endif /* _TRACE_SKB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
new file mode 100644
index 000000000000..035f1bff288e
--- /dev/null
+++ b/include/trace/events/workqueue.h
@@ -0,0 +1,100 @@
+#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WORKQUEUE_H
+
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
+TRACE_EVENT(workqueue_insertion,
+
+        TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+        TP_ARGS(wq_thread, work),
+
+        TP_STRUCT__entry(
+                __array(char,           thread_comm,    TASK_COMM_LEN)
+                __field(pid_t,          thread_pid)
+                __field(work_func_t,    func)
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+                __entry->thread_pid     = wq_thread->pid;
+                __entry->func           = work->func;
+        ),
+
+        TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+                __entry->thread_pid, __entry->func)
+);
+
+TRACE_EVENT(workqueue_execution,
+
+        TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+        TP_ARGS(wq_thread, work),
+
+        TP_STRUCT__entry(
+                __array(char,           thread_comm,    TASK_COMM_LEN)
+                __field(pid_t,          thread_pid)
+                __field(work_func_t,    func)
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+                __entry->thread_pid     = wq_thread->pid;
+                __entry->func           = work->func;
+        ),
+
+        TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+                __entry->thread_pid, __entry->func)
+);
+
+/* Trace the creation of one workqueue thread on a cpu */
+TRACE_EVENT(workqueue_creation,
+
+        TP_PROTO(struct task_struct *wq_thread, int cpu),
+
+        TP_ARGS(wq_thread, cpu),
+
+        TP_STRUCT__entry(
+                __array(char,   thread_comm,    TASK_COMM_LEN)
+                __field(pid_t,  thread_pid)
+                __field(int,    cpu)
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+                __entry->thread_pid     = wq_thread->pid;
+                __entry->cpu            = cpu;
+        ),
+
+        TP_printk("thread=%s:%d cpu=%d", __entry->thread_comm,
+                __entry->thread_pid, __entry->cpu)
+);
+
+TRACE_EVENT(workqueue_destruction,
+
+        TP_PROTO(struct task_struct *wq_thread),
+
+        TP_ARGS(wq_thread),
+
+        TP_STRUCT__entry(
+                __array(char,   thread_comm,    TASK_COMM_LEN)
+                __field(pid_t,  thread_pid)
+        ),
+
+        TP_fast_assign(
+                memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+                __entry->thread_pid     = wq_thread->pid;
+        ),
+
+        TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid)
+);
+
+#endif /* _TRACE_WORKQUEUE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
new file mode 100644
index 000000000000..1867553c61e5
--- /dev/null
+++ b/include/trace/ftrace.h
@@ -0,0 +1,591 @@
+/*
+ * Stage 1 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * struct ftrace_raw_<call> {
+ *      struct trace_entry              ent;
+ *      <type>                          <item>;
+ *      <type2>                         <item2>[<len>];
+ *      [...]
+ * };
+ *
+ * The <type> <item> is created by the __field(type, item) macro or
+ * the __array(type2, item2, len) macro.
+ * We simply do "type item;", and that will create the fields
+ * in the structure.
+ */
+
+#include <linux/ftrace_event.h>
+
+#undef __field
+#define __field(type, item)             type    item;
+
+#undef __array
+#define __array(type, item, len)        type    item[len];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) unsigned short __data_loc_##item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)  \
+        struct ftrace_raw_##name {                              \
+                struct trace_entry      ent;                    \
+                tstruct                                         \
+                char                    __data[0];              \
+        };                                                      \
+        static struct ftrace_event_call event_##name
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+
+/*
+ * Stage 2 of the trace events.
+ *
+ * Include the following:
+ *
+ * struct ftrace_data_offsets_<call> {
+ *      int                             <item1>;
+ *      int                             <item2>;
+ *      [...]
+ * };
+ *
+ * The __dynamic_array() macro will create each int <item>, this is
+ * to keep the offset of each array from the beginning of the event.
+ */
+
+#undef __field
+#define __field(type, item);
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)        int item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)          \
+        struct ftrace_data_offsets_##call {                             \
+                tstruct;                                                \
+        };
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Setup the showing format of trace point.
+ *
+ * int
+ * ftrace_format_##call(struct trace_seq *s)
+ * {
+ *      struct ftrace_raw_##call field;
+ *      int ret;
+ *
+ *      ret = trace_seq_printf(s, #type " " #item ";"
+ *                             " offset:%u; size:%u;\n",
+ *                             offsetof(struct ftrace_raw_##call, item),
+ *                             sizeof(field.type));
+ *
+ * }
+ */
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef __field
+#define __field(type, item)                                     \
+        ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"      \
+                               "offset:%u;\tsize:%u;\n",                \
+                               (unsigned int)offsetof(typeof(field), item), \
+                               (unsigned int)sizeof(field.item));       \
+        if (!ret)                                                       \
+                return 0;
+
+#undef __array
+#define __array(type, item, len)                                                \
+        ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"    \
+                               "offset:%u;\tsize:%u;\n",                \
+                               (unsigned int)offsetof(typeof(field), item), \
+                               (unsigned int)sizeof(field.item));       \
+        if (!ret)                                                       \
+                return 0;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)                                       \
+        ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t"            \
+                               "offset:%u;\tsize:%u;\n",                       \
+                               (unsigned int)offsetof(typeof(field),           \
+                                        __data_loc_##item),                    \
+                               (unsigned int)sizeof(field.__data_loc_##item)); \
+        if (!ret)                                                              \
+                return 0;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __entry
+#define __entry REC
+
+#undef __print_symbolic
+#undef __get_dynamic_array
+#undef __get_str
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
+
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)            \
+static int                                                              \
+ftrace_format_##call(struct trace_seq *s)                               \
+{                                                                       \
+        struct ftrace_raw_##call field __attribute__((unused));         \
+        int ret = 0;                                                    \
+                                                                        \
+        tstruct;                                                        \
+                                                                        \
+        trace_seq_printf(s, "\nprint fmt: " print);                     \
+                                                                        \
+        return ret;                                                     \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 3 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * enum print_line_t
+ * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
+ * {
+ *      struct trace_seq *s = &iter->seq;
+ *      struct ftrace_raw_<call> *field; <-- defined in stage 1
+ *      struct trace_entry *entry;
+ *      struct trace_seq *p;
+ *      int ret;
+ *
+ *      entry = iter->ent;
+ *
+ *      if (entry->type != event_<call>.id) {
+ *              WARN_ON_ONCE(1);
+ *              return TRACE_TYPE_UNHANDLED;
+ *      }
+ *
+ *      field = (typeof(field))entry;
+ *
+ *      p = get_cpu_var(ftrace_event_seq);
+ *      trace_seq_init(p);
+ *      ret = trace_seq_printf(s, <TP_printk> "\n");
+ *      put_cpu();
+ *      if (!ret)
+ *              return TRACE_TYPE_PARTIAL_LINE;
+ *
+ *      return TRACE_TYPE_HANDLED;
+ * }
+ *
+ * This is the method used to print the raw event to the trace
+ * output format. Note, this is not needed if the data is read
+ * in binary.
+ */
+
+#undef __entry
+#define __entry field
+
+#undef TP_printk
+#define TP_printk(fmt, args...) fmt "\n", args
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)      \
+                ((void *)__entry + __entry->__data_loc_##field)
+
+#undef __get_str
+#define __get_str(field) (char *)__get_dynamic_array(field)
+
+#undef __print_flags
+#define __print_flags(flag, delim, flag_array...)                       \
+        ({                                                              \
+                static const struct trace_print_flags flags[] =         \
+                        { flag_array, { -1, NULL }};                    \
+                ftrace_print_flags_seq(p, delim, flag, flags);          \
+        })
+
+#undef __print_symbolic
+#define __print_symbolic(value, symbol_array...)                        \
+        ({                                                              \
+                static const struct trace_print_flags symbols[] =       \
+                        { symbol_array, { -1, NULL }};                  \
+                ftrace_print_symbols_seq(p, value, symbols);            \
+        })
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)          \
+enum print_line_t                                                       \
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags)        \
+{                                                                       \
+        struct trace_seq *s = &iter->seq;                               \
+        struct ftrace_raw_##call *field;                                \
+        struct trace_entry *entry;                                      \
+        struct trace_seq *p;                                            \
+        int ret;                                                        \
+                                                                        \
+        entry = iter->ent;                                              \
+                                                                        \
+        if (entry->type != event_##call.id) {                           \
+                WARN_ON_ONCE(1);                                        \
+                return TRACE_TYPE_UNHANDLED;                            \
+        }                                                               \
+                                                                        \
+        field = (typeof(field))entry;                                   \
+                                                                        \
+        p = &get_cpu_var(ftrace_event_seq);                             \
+        trace_seq_init(p);                                              \
+        ret = trace_seq_printf(s, #call ": " print);                    \
+        put_cpu();                                                      \
+        if (!ret)                                                       \
+                return TRACE_TYPE_PARTIAL_LINE;                         \
+                                                                        \
+        return TRACE_TYPE_HANDLED;                                      \
+}
+        
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef __field
+#define __field(type, item)                                             \
+        ret = trace_define_field(event_call, #type, #item,              \
+                                 offsetof(typeof(field), item),         \
+                                 sizeof(field.item), is_signed_type(type));     \
+        if (ret)                                                        \
+                return ret;
+
+#undef __array
+#define __array(type, item, len)                                        \
+        BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);                         \
+        ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+                                 offsetof(typeof(field), item),         \
+                                 sizeof(field.item), 0);                \
+        if (ret)                                                        \
+                return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)                                       \
+        ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\
+                                offsetof(typeof(field), __data_loc_##item),    \
+                                 sizeof(field.__data_loc_##item), 0);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)            \
+int                                                                     \
+ftrace_define_fields_##call(void)                                       \
+{                                                                       \
+        struct ftrace_raw_##call field;                                 \
+        struct ftrace_event_call *event_call = &event_##call;           \
+        int ret;                                                        \
+                                                                        \
+        __common_field(int, type, 1);                                   \
+        __common_field(unsigned char, flags, 0);                        \
+        __common_field(unsigned char, preempt_count, 0);                \
+        __common_field(int, pid, 1);                                    \
+        __common_field(int, tgid, 1);                                   \
+                                                                        \
+        tstruct;                                                        \
+                                                                        \
+        return ret;                                                     \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * remember the offset of each array from the beginning of the event.
+ */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)                                \
+        __data_offsets->item = __data_size +                            \
+                               offsetof(typeof(*entry), __data);        \
+        __data_size += (len) * sizeof(type);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)       \
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)          \
+static inline int ftrace_get_offsets_##call(                            \
+        struct ftrace_data_offsets_##call *__data_offsets, proto)       \
+{                                                                       \
+        int __data_size = 0;                                            \
+        struct ftrace_raw_##call __maybe_unused *entry;                 \
+                                                                        \
+        tstruct;                                                        \
+                                                                        \
+        return __data_size;                                             \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 4 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * static void ftrace_event_<call>(proto)
+ * {
+ *      event_trace_printk(_RET_IP_, "<call>: " <fmt>);
+ * }
+ *
+ * static int ftrace_reg_event_<call>(void)
+ * {
+ *      int ret;
+ *
+ *      ret = register_trace_<call>(ftrace_event_<call>);
+ *      if (!ret)
+ *              pr_info("event trace: Could not activate trace point "
+ *                      "probe to  <call>");
+ *      return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *      unregister_trace_<call>(ftrace_event_<call>);
+ * }
+ *
+ *
+ * For those macros defined with TRACE_EVENT:
+ *
+ * static struct ftrace_event_call event_<call>;
+ *
+ * static void ftrace_raw_event_<call>(proto)
+ * {
+ *      struct ring_buffer_event *event;
+ *      struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ *      unsigned long irq_flags;
+ *      int pc;
+ *
+ *      local_save_flags(irq_flags);
+ *      pc = preempt_count();
+ *
+ *      event = trace_current_buffer_lock_reserve(event_<call>.id,
+ *                                sizeof(struct ftrace_raw_<call>),
+ *                                irq_flags, pc);
+ *      if (!event)
+ *              return;
+ *      entry   = ring_buffer_event_data(event);
+ *
+ *      <assign>;  <-- Here we assign the entries by the __field and
+ *                      __array macros.
+ *
+ *      trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ * }
+ *
+ * static int ftrace_raw_reg_event_<call>(void)
+ * {
+ *      int ret;
+ *
+ *      ret = register_trace_<call>(ftrace_raw_event_<call>);
+ *      if (!ret)
+ *              pr_info("event trace: Could not activate trace point "
+ *                      "probe to <call>");
+ *      return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *      unregister_trace_<call>(ftrace_raw_event_<call>);
+ * }
+ *
+ * static struct trace_event ftrace_event_type_<call> = {
+ *      .trace                  = ftrace_raw_output_<call>, <-- stage 2
+ * };
+ *
+ * static int ftrace_raw_init_event_<call>(void)
+ * {
+ *      int id;
+ *
+ *      id = register_ftrace_event(&ftrace_event_type_<call>);
+ *      if (!id)
+ *              return -ENODEV;
+ *      event_<call>.id = id;
+ *      return 0;
+ * }
+ *
+ * static struct ftrace_event_call __used
+ * __attribute__((__aligned__(4)))
+ * __attribute__((section("_ftrace_events"))) event_<call> = {
+ *      .name                   = "<call>",
+ *      .system                 = "<system>",
+ *      .raw_init               = ftrace_raw_init_event_<call>,
+ *      .regfunc                = ftrace_reg_event_<call>,
+ *      .unregfunc              = ftrace_unreg_event_<call>,
+ *      .show_format            = ftrace_format_<call>,
+ * }
+ *
+ */
+
+#undef TP_FMT
+#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),                               \
+        .profile_enable = ftrace_profile_enable_##call,                 \
+        .profile_disable = ftrace_profile_disable_##call,
+
+#else
+#define _TRACE_PROFILE(call, proto, args)
+#define _TRACE_PROFILE_INIT(call)
+#endif
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)                                \
+        __entry->__data_loc_##item = __data_offsets.item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)             \
+
+#undef __assign_str
+#define __assign_str(dst, src)                                          \
+        strcpy(__get_str(dst), src);
+
+#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;                           \
+                                                                        \
+static void ftrace_raw_event_##call(proto)                              \
+{                                                                       \
+        struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+        struct ftrace_event_call *event_call = &event_##call;           \
+        struct ring_buffer_event *event;                                \
+        struct ftrace_raw_##call *entry;                                \
+        unsigned long irq_flags;                                        \
+        int __data_size;                                                \
+        int pc;                                                         \
+                                                                        \
+        local_save_flags(irq_flags);                                    \
+        pc = preempt_count();                                           \
+                                                                        \
+        __data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+                                                                        \
+        event = trace_current_buffer_lock_reserve(event_##call.id,      \
+                                 sizeof(*entry) + __data_size,          \
+                                 irq_flags, pc);                        \
+        if (!event)                                                     \
+                return;                                                 \
+        entry   = ring_buffer_event_data(event);                        \
+                                                                        \
+                                                                        \
+        tstruct                                                         \
+                                                                        \
+        { assign; }                                                     \
+                                                                        \
+        if (!filter_current_check_discard(event_call, entry, event))    \
+                trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+}                                                                       \
+                                                                        \
+static int ftrace_raw_reg_event_##call(void)                            \
+{                                                                       \
+        int ret;                                                        \
+                                                                        \
+        ret = register_trace_##call(ftrace_raw_event_##call);           \
+        if (ret)                                                        \
+                pr_info("event trace: Could not activate trace point "  \
+                        "probe to " #call "\n");                        \
+        return ret;                                                     \
+}                                                                       \
+                                                                        \
+static void ftrace_raw_unreg_event_##call(void)                         \
+{                                                                       \
+        unregister_trace_##call(ftrace_raw_event_##call);               \
+}                                                                       \
+                                                                        \
+static struct trace_event ftrace_event_type_##call = {                  \
+        .trace                  = ftrace_raw_output_##call,             \
+};                                                                      \
+                                                                        \
+static int ftrace_raw_init_event_##call(void)                           \
+{                                                                       \
+        int id;                                                         \
+                                                                        \
+        id = register_ftrace_event(&ftrace_event_type_##call);          \
+        if (!id)                                                        \
+                return -ENODEV;                                         \
+        event_##call.id = id;                                           \
+        INIT_LIST_HEAD(&event_##call.fields);                           \
+        init_preds(&event_##call);                                      \
+        return 0;                                                       \
+}                                                                       \
+                                                                        \
+static struct ftrace_event_call __used                                  \
+__attribute__((__aligned__(4)))                                         \
+__attribute__((section("_ftrace_events"))) event_##call = {             \
+        .name                   = #call,                                \
+        .system                 = __stringify(TRACE_SYSTEM),            \
+        .event                  = &ftrace_event_type_##call,            \
+        .raw_init               = ftrace_raw_init_event_##call,         \
+        .regfunc                = ftrace_raw_reg_event_##call,          \
+        .unregfunc              = ftrace_raw_unreg_event_##call,        \
+        .show_format            = ftrace_format_##call,                 \
+        .define_fields          = ftrace_define_fields_##call,          \
+        _TRACE_PROFILE_INIT(call)                                       \
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef _TRACE_PROFILE
+#undef _TRACE_PROFILE_INIT
+
diff --git a/include/trace/irq.h b/include/trace/irq.h
deleted file mode 100644
index ff5d4495dc37..000000000000
--- a/include/trace/irq.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_IRQ_H
-#define _TRACE_IRQ_H
-
-#include <linux/interrupt.h>
-#include <linux/tracepoint.h>
-
-#include <trace/irq_event_types.h>
-
-#endif
diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h
deleted file mode 100644
index 85964ebd47ec..000000000000
--- a/include/trace/irq_event_types.h
+++ /dev/null
@@ -1,55 +0,0 @@
-
-/* use <trace/irq.h> instead */
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM irq
-
-/*
- * Tracepoint for entry of interrupt handler:
- */
-TRACE_FORMAT(irq_handler_entry,
-        TP_PROTO(int irq, struct irqaction *action),
-        TP_ARGS(irq, action),
-        TP_FMT("irq=%d handler=%s", irq, action->name)
-        );
-
-/*
- * Tracepoint for return of an interrupt handler:
- */
-TRACE_EVENT(irq_handler_exit,
-
-        TP_PROTO(int irq, struct irqaction *action, int ret),
-
-        TP_ARGS(irq, action, ret),
-
-        TP_STRUCT__entry(
-                __field(        int,    irq     )
-                __field(        int,    ret     )
-        ),
-
-        TP_fast_assign(
-                __entry->irq    = irq;
-                __entry->ret    = ret;
-        ),
-
-        TP_printk("irq=%d return=%s",
-                  __entry->irq, __entry->ret ? "handled" : "unhandled")
-);
-
-TRACE_FORMAT(softirq_entry,
-        TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-        TP_ARGS(h, vec),
-        TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-        );
-
-TRACE_FORMAT(softirq_exit,
-        TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-        TP_ARGS(h, vec),
-        TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-        );
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/kmemtrace.h b/include/trace/kmemtrace.h
deleted file mode 100644
index 28ee69f9cd46..000000000000
--- a/include/trace/kmemtrace.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <linux/tracepoint.h>
-#include <linux/types.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-DECLARE_TRACE(kmalloc,
-              TP_PROTO(unsigned long call_site,
-                      const void *ptr,
-                      size_t bytes_req,
-                      size_t bytes_alloc,
-                      gfp_t gfp_flags),
-              TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmem_cache_alloc,
-              TP_PROTO(unsigned long call_site,
-                      const void *ptr,
-                      size_t bytes_req,
-                      size_t bytes_alloc,
-                      gfp_t gfp_flags),
-              TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmalloc_node,
-              TP_PROTO(unsigned long call_site,
-                      const void *ptr,
-                      size_t bytes_req,
-                      size_t bytes_alloc,
-                      gfp_t gfp_flags,
-                      int node),
-              TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kmem_cache_alloc_node,
-              TP_PROTO(unsigned long call_site,
-                      const void *ptr,
-                      size_t bytes_req,
-                      size_t bytes_alloc,
-                      gfp_t gfp_flags,
-                      int node),
-              TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kfree,
-              TP_PROTO(unsigned long call_site, const void *ptr),
-              TP_ARGS(call_site, ptr));
-DECLARE_TRACE(kmem_cache_free,
-              TP_PROTO(unsigned long call_site, const void *ptr),
-              TP_ARGS(call_site, ptr));
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
diff --git a/include/trace/lockdep.h b/include/trace/lockdep.h
deleted file mode 100644
index 5ca67df87f2a..000000000000
--- a/include/trace/lockdep.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_LOCKDEP_H
-#define _TRACE_LOCKDEP_H
-
-#include <linux/lockdep.h>
-#include <linux/tracepoint.h>
-
-#include <trace/lockdep_event_types.h>
-
-#endif
diff --git a/include/trace/lockdep_event_types.h b/include/trace/lockdep_event_types.h
deleted file mode 100644
index adccfcd2ec8f..000000000000
--- a/include/trace/lockdep_event_types.h
+++ /dev/null
@@ -1,44 +0,0 @@
-
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM lock
-
-#ifdef CONFIG_LOCKDEP
-
-TRACE_FORMAT(lock_acquire,
-        TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
-                int trylock, int read, int check,
-                struct lockdep_map *next_lock, unsigned long ip),
-        TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
-        TP_FMT("%s%s%s", trylock ? "try " : "",
-                read ? "read " : "", lock->name)
-        );
-
-TRACE_FORMAT(lock_release,
-        TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
-        TP_ARGS(lock, nested, ip),
-        TP_FMT("%s", lock->name)
-        );
-
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_FORMAT(lock_contended,
-        TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-        TP_ARGS(lock, ip),
-        TP_FMT("%s", lock->name)
-        );
-
-TRACE_FORMAT(lock_acquired,
-        TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-        TP_ARGS(lock, ip),
-        TP_FMT("%s", lock->name)
-        );
-
-#endif
-#endif
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/sched.h b/include/trace/sched.h
deleted file mode 100644
index 4e372a1a29bf..000000000000
--- a/include/trace/sched.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_SCHED_H
-#define _TRACE_SCHED_H
-
-#include <linux/sched.h>
-#include <linux/tracepoint.h>
-
-#include <trace/sched_event_types.h>
-
-#endif
diff --git a/include/trace/skb.h b/include/trace/skb.h
deleted file mode 100644
index b66206d9be72..000000000000
--- a/include/trace/skb.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _TRACE_SKB_H_
-#define _TRACE_SKB_H_
-
-#include <linux/skbuff.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(kfree_skb,
-        TP_PROTO(struct sk_buff *skb, void *location),
-        TP_ARGS(skb, location));
-
-#endif
diff --git a/include/trace/trace_event_types.h b/include/trace/trace_event_types.h
deleted file mode 100644
index df56f5694be6..000000000000
--- a/include/trace/trace_event_types.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>_event_types.h here */
-
-#include <trace/sched_event_types.h>
-#include <trace/irq_event_types.h>
-#include <trace/lockdep_event_types.h>
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
deleted file mode 100644
index fd13750ca4ba..000000000000
--- a/include/trace/trace_events.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>.h here */
-
-#include <trace/sched.h>
-#include <trace/irq.h>
-#include <trace/lockdep.h>
diff --git a/include/trace/workqueue.h b/include/trace/workqueue.h
deleted file mode 100644
index 7626523deeba..000000000000
--- a/include/trace/workqueue.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __TRACE_WORKQUEUE_H
-#define __TRACE_WORKQUEUE_H
-
-#include <linux/tracepoint.h>
-#include <linux/workqueue.h>
-#include <linux/sched.h>
-
-DECLARE_TRACE(workqueue_insertion,
-           TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-           TP_ARGS(wq_thread, work));
-
-DECLARE_TRACE(workqueue_execution,
-           TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-           TP_ARGS(wq_thread, work));
-
-/* Trace the creation of one workqueue thread on a cpu */
-DECLARE_TRACE(workqueue_creation,
-           TP_PROTO(struct task_struct *wq_thread, int cpu),
-           TP_ARGS(wq_thread, cpu));
-
-DECLARE_TRACE(workqueue_destruction,
-           TP_PROTO(struct task_struct *wq_thread),
-           TP_ARGS(wq_thread));
-
-#endif /* __TRACE_WORKQUEUE_H */
diff --git a/include/xen/Kbuild b/include/xen/Kbuild
new file mode 100644
index 000000000000..4e65c16a445b
--- /dev/null
+++ b/include/xen/Kbuild
@@ -0,0 +1 @@
+header-y += evtchn.h
diff --git a/include/xen/events.h b/include/xen/events.h
index 0d5f1adc0363..e68d59a90ca8 100644
--- a/include/xen/events.h
+++ b/include/xen/events.h
@@ -53,4 +53,7 @@ bool xen_test_irq_pending(int irq);
    irq will be disabled so it won't deliver an interrupt. */
 void xen_poll_irq(int irq);
 
+/* Determine the IRQ which is bound to an event channel */
+unsigned irq_from_evtchn(unsigned int evtchn);
+
 #endif  /* _XEN_EVENTS_H */
diff --git a/include/xen/evtchn.h b/include/xen/evtchn.h
new file mode 100644
index 000000000000..14e833ee4e0b
--- /dev/null
+++ b/include/xen/evtchn.h
@@ -0,0 +1,88 @@
+/******************************************************************************
+ * evtchn.h
+ *
+ * Interface to /dev/xen/evtchn.
+ *
+ * Copyright (c) 2003-2005, K A Fraser
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version 2
+ * as published by the Free Software Foundation; or, when distributed
+ * separately from the Linux kernel or incorporated into other
+ * software packages, subject to the following license:
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this source file (the "Software"), to deal in the Software without
+ * restriction, including without limitation the rights to use, copy, modify,
+ * merge, publish, distribute, sublicense, and/or sell copies of the Software,
+ * and to permit persons to whom the Software is furnished to do so, subject to
+ * the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
+ * IN THE SOFTWARE.
+ */
+
+#ifndef __LINUX_PUBLIC_EVTCHN_H__
+#define __LINUX_PUBLIC_EVTCHN_H__
+
+/*
+ * Bind a fresh port to VIRQ @virq.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_VIRQ                          \
+        _IOC(_IOC_NONE, 'E', 0, sizeof(struct ioctl_evtchn_bind_virq))
+struct ioctl_evtchn_bind_virq {
+        unsigned int virq;
+};
+
+/*
+ * Bind a fresh port to remote <@remote_domain, @remote_port>.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_INTERDOMAIN                   \
+        _IOC(_IOC_NONE, 'E', 1, sizeof(struct ioctl_evtchn_bind_interdomain))
+struct ioctl_evtchn_bind_interdomain {
+        unsigned int remote_domain, remote_port;
+};
+
+/*
+ * Allocate a fresh port for binding to @remote_domain.
+ * Return allocated port.
+ */
+#define IOCTL_EVTCHN_BIND_UNBOUND_PORT                  \
+        _IOC(_IOC_NONE, 'E', 2, sizeof(struct ioctl_evtchn_bind_unbound_port))
+struct ioctl_evtchn_bind_unbound_port {
+        unsigned int remote_domain;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_UNBIND                             \
+        _IOC(_IOC_NONE, 'E', 3, sizeof(struct ioctl_evtchn_unbind))
+struct ioctl_evtchn_unbind {
+        unsigned int port;
+};
+
+/*
+ * Unbind previously allocated @port.
+ */
+#define IOCTL_EVTCHN_NOTIFY                             \
+        _IOC(_IOC_NONE, 'E', 4, sizeof(struct ioctl_evtchn_notify))
+struct ioctl_evtchn_notify {
+        unsigned int port;
+};
+
+/* Clear and reinitialise the event buffer. Clear error condition. */
+#define IOCTL_EVTCHN_RESET                              \
+        _IOC(_IOC_NONE, 'E', 5, 0)
+
+#endif /* __LINUX_PUBLIC_EVTCHN_H__ */
diff --git a/include/xen/interface/version.h b/include/xen/interface/version.h
index 453235e923f0..e8b6519d47e9 100644
--- a/include/xen/interface/version.h
+++ b/include/xen/interface/version.h
@@ -57,4 +57,7 @@ struct xen_feature_info {
 /* Declares the features reported by XENVER_get_features. */
 #include "features.h"
 
+/* arg == NULL; returns host memory page size. */
+#define XENVER_pagesize 7
+
 #endif /* __XEN_PUBLIC_VERSION_H__ */
diff --git a/include/xen/xenbus.h b/include/xen/xenbus.h
index f87f9614844d..b9763badbd77 100644
--- a/include/xen/xenbus.h
+++ b/include/xen/xenbus.h
@@ -91,8 +91,7 @@ struct xenbus_driver {
         void (*otherend_changed)(struct xenbus_device *dev,
                                  enum xenbus_state backend_state);
         int (*remove)(struct xenbus_device *dev);
-        int (*suspend)(struct xenbus_device *dev);
-        int (*suspend_cancel)(struct xenbus_device *dev);
+        int (*suspend)(struct xenbus_device *dev, pm_message_t state);
         int (*resume)(struct xenbus_device *dev);
         int (*uevent)(struct xenbus_device *, char **, int, char *, int);
         struct device_driver driver;