Merge commit 'v2.6.35' into kbuild/kbuild

Conflicts:
	arch/powerpc/Makefile

13 files changed, 1007 insertions, 502 deletions

diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index 5acfb1eb4df..1dfab540151 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -65,6 +65,10 @@
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+/* Make all open coded DECLARE_TRACE nops */
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)
+
 #ifdef CONFIG_EVENT_TRACING
 #include <trace/ftrace.h>
 #endif
@@ -75,6 +79,7 @@
 #undef DEFINE_EVENT
 #undef DEFINE_EVENT_PRINT
 #undef TRACE_HEADER_MULTI_READ
+#undef DECLARE_TRACE
 
 /* Only undef what we defined in this file */
 #ifdef UNDEF_TRACE_INCLUDE_FILE
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 5fb72733331..d870a918559 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -40,6 +40,16 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
 		  __entry->nr_sector, __entry->errors)
 );
 
+/**
+ * block_rq_abort - abort block operation request
+ * @q: queue containing the block operation request
+ * @rq: block IO operation request
+ *
+ * Called immediately after pending block IO operation request @rq in
+ * queue @q is aborted. The fields in the operation request @rq
+ * can be examined to determine which device and sectors the pending
+ * operation would access.
+ */
 DEFINE_EVENT(block_rq_with_error, block_rq_abort,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
@@ -47,6 +57,15 @@ DEFINE_EVENT(block_rq_with_error, block_rq_abort,
 	TP_ARGS(q, rq)
 );
 
+/**
+ * block_rq_requeue - place block IO request back on a queue
+ * @q: queue holding operation
+ * @rq: block IO operation request
+ *
+ * The block operation request @rq is being placed back into queue
+ * @q.  For some reason the request was not completed and needs to be
+ * put back in the queue.
+ */
 DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
@@ -54,6 +73,17 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
 	TP_ARGS(q, rq)
 );
 
+/**
+ * block_rq_complete - block IO operation completed by device driver
+ * @q: queue containing the block operation request
+ * @rq: block operations request
+ *
+ * The block_rq_complete tracepoint event indicates that some portion
+ * of operation request has been completed by the device driver.  If
+ * the @rq->bio is %NULL, then there is absolutely no additional work to
+ * do for the request. If @rq->bio is non-NULL then there is
+ * additional work required to complete the request.
+ */
 DEFINE_EVENT(block_rq_with_error, block_rq_complete,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
@@ -95,6 +125,16 @@ DECLARE_EVENT_CLASS(block_rq,
 		  __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_rq_insert - insert block operation request into queue
+ * @q: target queue
+ * @rq: block IO operation request
+ *
+ * Called immediately before block operation request @rq is inserted
+ * into queue @q.  The fields in the operation request @rq struct can
+ * be examined to determine which device and sectors the pending
+ * operation would access.
+ */
 DEFINE_EVENT(block_rq, block_rq_insert,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
@@ -102,6 +142,14 @@ DEFINE_EVENT(block_rq, block_rq_insert,
 	TP_ARGS(q, rq)
 );
 
+/**
+ * block_rq_issue - issue pending block IO request operation to device driver
+ * @q: queue holding operation
+ * @rq: block IO operation operation request
+ *
+ * Called when block operation request @rq from queue @q is sent to a
+ * device driver for processing.
+ */
 DEFINE_EVENT(block_rq, block_rq_issue,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
@@ -109,6 +157,17 @@ DEFINE_EVENT(block_rq, block_rq_issue,
 	TP_ARGS(q, rq)
 );
 
+/**
+ * block_bio_bounce - used bounce buffer when processing block operation
+ * @q: queue holding the block operation
+ * @bio: block operation
+ *
+ * A bounce buffer was used to handle the block operation @bio in @q.
+ * This occurs when hardware limitations prevent a direct transfer of
+ * data between the @bio data memory area and the IO device.  Use of a
+ * bounce buffer requires extra copying of data and decreases
+ * performance.
+ */
 TRACE_EVENT(block_bio_bounce,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -138,6 +197,14 @@ TRACE_EVENT(block_bio_bounce,
 		  __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_bio_complete - completed all work on the block operation
+ * @q: queue holding the block operation
+ * @bio: block operation completed
+ *
+ * This tracepoint indicates there is no further work to do on this
+ * block IO operation @bio.
+ */
 TRACE_EVENT(block_bio_complete,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -193,6 +260,14 @@ DECLARE_EVENT_CLASS(block_bio,
 		  __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_bio_backmerge - merging block operation to the end of an existing operation
+ * @q: queue holding operation
+ * @bio: new block operation to merge
+ *
+ * Merging block request @bio to the end of an existing block request
+ * in queue @q.
+ */
 DEFINE_EVENT(block_bio, block_bio_backmerge,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -200,6 +275,14 @@ DEFINE_EVENT(block_bio, block_bio_backmerge,
 	TP_ARGS(q, bio)
 );
 
+/**
+ * block_bio_frontmerge - merging block operation to the beginning of an existing operation
+ * @q: queue holding operation
+ * @bio: new block operation to merge
+ *
+ * Merging block IO operation @bio to the beginning of an existing block
+ * operation in queue @q.
+ */
 DEFINE_EVENT(block_bio, block_bio_frontmerge,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -207,6 +290,13 @@ DEFINE_EVENT(block_bio, block_bio_frontmerge,
 	TP_ARGS(q, bio)
 );
 
+/**
+ * block_bio_queue - putting new block IO operation in queue
+ * @q: queue holding operation
+ * @bio: new block operation
+ *
+ * About to place the block IO operation @bio into queue @q.
+ */
 DEFINE_EVENT(block_bio, block_bio_queue,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -243,6 +333,15 @@ DECLARE_EVENT_CLASS(block_get_rq,
 		  __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_getrq - get a free request entry in queue for block IO operations
+ * @q: queue for operations
+ * @bio: pending block IO operation
+ * @rw: low bit indicates a read (%0) or a write (%1)
+ *
+ * A request struct for queue @q has been allocated to handle the
+ * block IO operation @bio.
+ */
 DEFINE_EVENT(block_get_rq, block_getrq,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
@@ -250,6 +349,17 @@ DEFINE_EVENT(block_get_rq, block_getrq,
 	TP_ARGS(q, bio, rw)
 );
 
+/**
+ * block_sleeprq - waiting to get a free request entry in queue for block IO operation
+ * @q: queue for operation
+ * @bio: pending block IO operation
+ * @rw: low bit indicates a read (%0) or a write (%1)
+ *
+ * In the case where a request struct cannot be provided for queue @q
+ * the process needs to wait for an request struct to become
+ * available.  This tracepoint event is generated each time the
+ * process goes to sleep waiting for request struct become available.
+ */
 DEFINE_EVENT(block_get_rq, block_sleeprq,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
@@ -257,6 +367,14 @@ DEFINE_EVENT(block_get_rq, block_sleeprq,
 	TP_ARGS(q, bio, rw)
 );
 
+/**
+ * block_plug - keep operations requests in request queue
+ * @q: request queue to plug
+ *
+ * Plug the request queue @q.  Do not allow block operation requests
+ * to be sent to the device driver. Instead, accumulate requests in
+ * the queue to improve throughput performance of the block device.
+ */
 TRACE_EVENT(block_plug,
 
 	TP_PROTO(struct request_queue *q),
@@ -293,6 +411,13 @@ DECLARE_EVENT_CLASS(block_unplug,
 	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
 );
 
+/**
+ * block_unplug_timer - timed release of operations requests in queue to device driver
+ * @q: request queue to unplug
+ *
+ * Unplug the request queue @q because a timer expired and allow block
+ * operation requests to be sent to the device driver.
+ */
 DEFINE_EVENT(block_unplug, block_unplug_timer,
 
 	TP_PROTO(struct request_queue *q),
@@ -300,6 +425,13 @@ DEFINE_EVENT(block_unplug, block_unplug_timer,
 	TP_ARGS(q)
 );
 
+/**
+ * block_unplug_io - release of operations requests in request queue
+ * @q: request queue to unplug
+ *
+ * Unplug request queue @q because device driver is scheduled to work
+ * on elements in the request queue.
+ */
 DEFINE_EVENT(block_unplug, block_unplug_io,
 
 	TP_PROTO(struct request_queue *q),
@@ -307,6 +439,17 @@ DEFINE_EVENT(block_unplug, block_unplug_io,
 	TP_ARGS(q)
 );
 
+/**
+ * block_split - split a single bio struct into two bio structs
+ * @q: queue containing the bio
+ * @bio: block operation being split
+ * @new_sector: The starting sector for the new bio
+ *
+ * The bio request @bio in request queue @q needs to be split into two
+ * bio requests. The newly created @bio request starts at
+ * @new_sector. This split may be required due to hardware limitation
+ * such as operation crossing device boundaries in a RAID system.
+ */
 TRACE_EVENT(block_split,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio,
@@ -337,6 +480,16 @@ TRACE_EVENT(block_split,
 		  __entry->comm)
 );
 
+/**
+ * block_remap - map request for a partition to the raw device
+ * @q: queue holding the operation
+ * @bio: revised operation
+ * @dev: device for the operation
+ * @from: original sector for the operation
+ *
+ * An operation for a partition on a block device has been mapped to the
+ * raw block device.
+ */
 TRACE_EVENT(block_remap,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
@@ -370,6 +523,17 @@ TRACE_EVENT(block_remap,
 		  (unsigned long long)__entry->old_sector)
 );
 
+/**
+ * block_rq_remap - map request for a block operation request
+ * @q: queue holding the operation
+ * @rq: block IO operation request
+ * @dev: device for the operation
+ * @from: original sector for the operation
+ *
+ * The block operation request @rq in @q has been remapped.  The block
+ * operation request @rq holds the current information and @from hold
+ * the original sector.
+ */
 TRACE_EVENT(block_rq_remap,
 
 	TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev,
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index d0b6cd3afb2..f3865c7b416 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -306,7 +306,6 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__field(	int,	pages_written		)
 		__field(	long,	pages_skipped		)
 		__field(	char,	more_io			)	
-		__field(	char,	no_nrwrite_index_update )
 		__field(       pgoff_t,	writeback_index		)
 	),
 
@@ -317,16 +316,14 @@ TRACE_EVENT(ext4_da_writepages_result,
 		__entry->pages_written	= pages_written;
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->more_io	= wbc->more_io;
-		__entry->no_nrwrite_index_update = wbc->no_nrwrite_index_update;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
-	TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld more_io %d no_nrwrite_index_update %d writeback_index %lu",
+	TP_printk("dev %s ino %lu ret %d pages_written %d pages_skipped %ld more_io %d writeback_index %lu",
 		  jbd2_dev_to_name(__entry->dev),
 		  (unsigned long) __entry->ino, __entry->ret,
 		  __entry->pages_written, __entry->pages_skipped,
 		  __entry->more_io,
-		  __entry->no_nrwrite_index_update,
 		  (unsigned long) __entry->writeback_index)
 );
 
@@ -353,7 +350,7 @@ TRACE_EVENT(ext4_discard_blocks,
 		  jbd2_dev_to_name(__entry->dev), __entry->blk, __entry->count)
 );
 
-TRACE_EVENT(ext4_mb_new_inode_pa,
+DECLARE_EVENT_CLASS(ext4__mb_new_pa,
 	TP_PROTO(struct ext4_allocation_context *ac,
 		 struct ext4_prealloc_space *pa),
 
@@ -381,32 +378,20 @@ TRACE_EVENT(ext4_mb_new_inode_pa,
 		  __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart)
 );
 
-TRACE_EVENT(ext4_mb_new_group_pa,
+DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_inode_pa,
+
 	TP_PROTO(struct ext4_allocation_context *ac,
 		 struct ext4_prealloc_space *pa),
 
-	TP_ARGS(ac, pa),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	__u64,	pa_pstart		)
-		__field(	__u32,	pa_len			)
-		__field(	__u64,	pa_lstart		)
+	TP_ARGS(ac, pa)
+);
 
-	),
+DEFINE_EVENT(ext4__mb_new_pa, ext4_mb_new_group_pa,
 
-	TP_fast_assign(
-		__entry->dev		= ac->ac_sb->s_dev;
-		__entry->ino		= ac->ac_inode->i_ino;
-		__entry->pa_pstart	= pa->pa_pstart;
-		__entry->pa_len		= pa->pa_len;
-		__entry->pa_lstart	= pa->pa_lstart;
-	),
+	TP_PROTO(struct ext4_allocation_context *ac,
+		 struct ext4_prealloc_space *pa),
 
-	TP_printk("dev %s ino %lu pstart %llu len %u lstart %llu",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->pa_pstart, __entry->pa_len, __entry->pa_lstart)
+	TP_ARGS(ac, pa)
 );
 
 TRACE_EVENT(ext4_mb_release_inode_pa,
@@ -618,9 +603,9 @@ TRACE_EVENT(ext4_free_blocks,
 );
 
 TRACE_EVENT(ext4_sync_file,
-	TP_PROTO(struct file *file, struct dentry *dentry, int datasync),
+	TP_PROTO(struct file *file, int datasync),
 
-	TP_ARGS(file, dentry, datasync),
+	TP_ARGS(file, datasync),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
@@ -630,6 +615,8 @@ TRACE_EVENT(ext4_sync_file,
 	),
 
 	TP_fast_assign(
+		struct dentry *dentry = file->f_path.dentry;
+
 		__entry->dev		= dentry->d_inode->i_sb->s_dev;
 		__entry->ino		= dentry->d_inode->i_ino;
 		__entry->datasync	= datasync;
@@ -790,7 +777,7 @@ TRACE_EVENT(ext4_mballoc_prealloc,
 		  __entry->result_len, __entry->result_logical)
 );
 
-TRACE_EVENT(ext4_mballoc_discard,
+DECLARE_EVENT_CLASS(ext4__mballoc,
 	TP_PROTO(struct ext4_allocation_context *ac),
 
 	TP_ARGS(ac),
@@ -819,33 +806,18 @@ TRACE_EVENT(ext4_mballoc_discard,
 		  __entry->result_len, __entry->result_logical)
 );
 
-TRACE_EVENT(ext4_mballoc_free,
+DEFINE_EVENT(ext4__mballoc, ext4_mballoc_discard,
+
 	TP_PROTO(struct ext4_allocation_context *ac),
 
-	TP_ARGS(ac),
+	TP_ARGS(ac)
+);
 
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	__u32, 	result_logical		)
-		__field(	  int,	result_start		)
-		__field(	__u32, 	result_group		)
-		__field(	  int,	result_len		)
-	),
+DEFINE_EVENT(ext4__mballoc, ext4_mballoc_free,
 
-	TP_fast_assign(
-		__entry->dev		= ac->ac_inode->i_sb->s_dev;
-		__entry->ino		= ac->ac_inode->i_ino;
-		__entry->result_logical	= ac->ac_b_ex.fe_logical;
-		__entry->result_start	= ac->ac_b_ex.fe_start;
-		__entry->result_group	= ac->ac_b_ex.fe_group;
-		__entry->result_len	= ac->ac_b_ex.fe_len;
-	),
+	TP_PROTO(struct ext4_allocation_context *ac),
 
-	TP_printk("dev %s inode %lu extent %u/%d/%u@%u ",
-		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
-		  __entry->result_group, __entry->result_start,
-		  __entry->result_len, __entry->result_logical)
+	TP_ARGS(ac)
 );
 
 TRACE_EVENT(ext4_forget,
@@ -874,6 +846,140 @@ TRACE_EVENT(ext4_forget,
 		  __entry->mode, __entry->is_metadata, __entry->block)
 );
 
+TRACE_EVENT(ext4_da_update_reserve_space,
+	TP_PROTO(struct inode *inode, int used_blocks),
+
+	TP_ARGS(inode, used_blocks),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	umode_t, mode			)
+		__field(	__u64,	i_blocks		)
+		__field(	int,	used_blocks		)
+		__field(	int,	reserved_data_blocks	)
+		__field(	int,	reserved_meta_blocks	)
+		__field(	int,	allocated_meta_blocks	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->mode	= inode->i_mode;
+		__entry->i_blocks = inode->i_blocks;
+		__entry->used_blocks = used_blocks;
+		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
+		__entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
+	),
+
+	TP_printk("dev %s ino %lu mode 0%o i_blocks %llu used_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->mode,  (unsigned long long) __entry->i_blocks,
+		  __entry->used_blocks, __entry->reserved_data_blocks,
+		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
+);
+
+TRACE_EVENT(ext4_da_reserve_space,
+	TP_PROTO(struct inode *inode, int md_needed),
+
+	TP_ARGS(inode, md_needed),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	umode_t, mode			)
+		__field(	__u64,	i_blocks		)
+		__field(	int,	md_needed		)
+		__field(	int,	reserved_data_blocks	)
+		__field(	int,	reserved_meta_blocks	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->mode	= inode->i_mode;
+		__entry->i_blocks = inode->i_blocks;
+		__entry->md_needed = md_needed;
+		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
+	),
+
+	TP_printk("dev %s ino %lu mode 0%o i_blocks %llu md_needed %d reserved_data_blocks %d reserved_meta_blocks %d",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->mode, (unsigned long long) __entry->i_blocks,
+		  __entry->md_needed, __entry->reserved_data_blocks,
+		  __entry->reserved_meta_blocks)
+);
+
+TRACE_EVENT(ext4_da_release_space,
+	TP_PROTO(struct inode *inode, int freed_blocks),
+
+	TP_ARGS(inode, freed_blocks),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	ino_t,	ino			)
+		__field(	umode_t, mode			)
+		__field(	__u64,	i_blocks		)
+		__field(	int,	freed_blocks		)
+		__field(	int,	reserved_data_blocks	)
+		__field(	int,	reserved_meta_blocks	)
+		__field(	int,	allocated_meta_blocks	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	= inode->i_sb->s_dev;
+		__entry->ino	= inode->i_ino;
+		__entry->mode	= inode->i_mode;
+		__entry->i_blocks = inode->i_blocks;
+		__entry->freed_blocks = freed_blocks;
+		__entry->reserved_data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+		__entry->reserved_meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
+		__entry->allocated_meta_blocks = EXT4_I(inode)->i_allocated_meta_blocks;
+	),
+
+	TP_printk("dev %s ino %lu mode 0%o i_blocks %llu freed_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d",
+		  jbd2_dev_to_name(__entry->dev), (unsigned long) __entry->ino,
+		  __entry->mode, (unsigned long long) __entry->i_blocks,
+		  __entry->freed_blocks, __entry->reserved_data_blocks,
+		  __entry->reserved_meta_blocks, __entry->allocated_meta_blocks)
+);
+
+DECLARE_EVENT_CLASS(ext4__bitmap_load,
+	TP_PROTO(struct super_block *sb, unsigned long group),
+
+	TP_ARGS(sb, group),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	__u32,	group			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev	= sb->s_dev;
+		__entry->group	= group;
+	),
+
+	TP_printk("dev %s group %u",
+		  jbd2_dev_to_name(__entry->dev), __entry->group)
+);
+
+DEFINE_EVENT(ext4__bitmap_load, ext4_mb_bitmap_load,
+
+	TP_PROTO(struct super_block *sb, unsigned long group),
+
+	TP_ARGS(sb, group)
+);
+
+DEFINE_EVENT(ext4__bitmap_load, ext4_mb_buddy_bitmap_load,
+
+	TP_PROTO(struct super_block *sb, unsigned long group),
+
+	TP_ARGS(sb, group)
+);
+
 #endif /* _TRACE_EXT4_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 96b370a050d..bf16545cc97 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -199,6 +199,34 @@ TRACE_EVENT(jbd2_checkpoint_stats,
 		  __entry->forced_to_close, __entry->written, __entry->dropped)
 );
 
+TRACE_EVENT(jbd2_cleanup_journal_tail,
+
+	TP_PROTO(journal_t *journal, tid_t first_tid,
+		 unsigned long block_nr, unsigned long freed),
+
+	TP_ARGS(journal, first_tid, block_nr, freed),
+
+	TP_STRUCT__entry(
+		__field(	dev_t,	dev			)
+		__field(	tid_t,	tail_sequence		)
+		__field(	tid_t,	first_tid		)
+		__field(unsigned long,	block_nr		)
+		__field(unsigned long,	freed			)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->tail_sequence	= journal->j_tail_sequence;
+		__entry->first_tid	= first_tid;
+		__entry->block_nr	= block_nr;
+		__entry->freed		= freed;
+	),
+
+	TP_printk("dev %s from %u to %u offset %lu freed %lu",
+		  jbd2_dev_to_name(__entry->dev), __entry->tail_sequence,
+		  __entry->first_tid, __entry->block_nr, __entry->freed)
+);
+
 #endif /* _TRACE_JBD2_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index dbe10845527..6dd3a51ab1c 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -5,7 +5,6 @@
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM kvm
-#define TRACE_INCLUDE_FILE kvm
 
 #if defined(__KVM_HAVE_IOAPIC)
 TRACE_EVENT(kvm_set_irq,
@@ -145,6 +144,47 @@ TRACE_EVENT(kvm_mmio,
 		  __entry->len, __entry->gpa, __entry->val)
 );
 
+#define kvm_fpu_load_symbol	\
+	{0, "unload"},		\
+	{1, "load"}
+
+TRACE_EVENT(kvm_fpu,
+	TP_PROTO(int load),
+	TP_ARGS(load),
+
+	TP_STRUCT__entry(
+		__field(	u32,	        load		)
+	),
+
+	TP_fast_assign(
+		__entry->load		= load;
+	),
+
+	TP_printk("%s", __print_symbolic(__entry->load, kvm_fpu_load_symbol))
+);
+
+TRACE_EVENT(kvm_age_page,
+	TP_PROTO(ulong hva, struct kvm_memory_slot *slot, int ref),
+	TP_ARGS(hva, slot, ref),
+
+	TP_STRUCT__entry(
+		__field(	u64,	hva		)
+		__field(	u64,	gfn		)
+		__field(	u8,	referenced	)
+	),
+
+	TP_fast_assign(
+		__entry->hva		= hva;
+		__entry->gfn		=
+		  slot->base_gfn + ((hva - slot->userspace_addr) >> PAGE_SHIFT);
+		__entry->referenced	= ref;
+	),
+
+	TP_printk("hva %llx gfn %llx %s",
+		  __entry->hva, __entry->gfn,
+		  __entry->referenced ? "YOUNG" : "OLD")
+);
+
 #endif /* _TRACE_KVM_MAIN_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index a870ba125aa..2821b86de63 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -20,71 +20,61 @@ TRACE_EVENT(lock_acquire,
 	TP_STRUCT__entry(
 		__field(unsigned int, flags)
 		__string(name, lock->name)
+		__field(void *, lockdep_addr)
 	),
 
 	TP_fast_assign(
 		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+	TP_printk("%p %s%s%s", __entry->lockdep_addr,
+		  (__entry->flags & 1) ? "try " : "",
 		  (__entry->flags & 2) ? "read " : "",
 		  __get_str(name))
 );
 
-TRACE_EVENT(lock_release,
+DECLARE_EVENT_CLASS(lock,
 
-	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_ARGS(lock, nested, ip),
+	TP_ARGS(lock, ip),
 
 	TP_STRUCT__entry(
-		__string(name, lock->name)
+		__string(	name, 	lock->name	)
+		__field(	void *, lockdep_addr	)
 	),
 
 	TP_fast_assign(
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s", __get_str(name))
+	TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
 );
 
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_EVENT(lock_contended,
+DEFINE_EVENT(lock, lock_release,
 
 	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_ARGS(lock, ip),
+	TP_ARGS(lock, ip)
+);
 
-	TP_STRUCT__entry(
-		__string(name, lock->name)
-	),
+#ifdef CONFIG_LOCK_STAT
 
-	TP_fast_assign(
-		__assign_str(name, lock->name);
-	),
+DEFINE_EVENT(lock, lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_printk("%s", __get_str(name))
+	TP_ARGS(lock, ip)
 );
 
-TRACE_EVENT(lock_acquired,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+DEFINE_EVENT(lock, lock_acquired,
 
-	TP_ARGS(lock, ip, waittime),
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	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)
+	TP_ARGS(lock, ip)
 );
 
 #endif
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 4b0f48ba16a..c7bb2f0482f 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -51,11 +51,14 @@ TRACE_EVENT(module_free,
 	TP_printk("%s", __get_str(name))
 );
 
+#ifdef CONFIG_MODULE_UNLOAD
+/* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */
+
 DECLARE_EVENT_CLASS(module_refcnt,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt),
+	TP_ARGS(mod, ip),
 
 	TP_STRUCT__entry(
 		__field(	unsigned long,	ip		)
@@ -65,7 +68,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 	TP_fast_assign(
 		__entry->ip	= ip;
-		__entry->refcnt	= refcnt;
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
 		__assign_str(name, mod->name);
 	),
 
@@ -75,17 +78,18 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 DEFINE_EVENT(module_refcnt, module_get,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
 
 DEFINE_EVENT(module_refcnt, module_put,
 
-	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+	TP_PROTO(struct module *mod, unsigned long ip),
 
-	TP_ARGS(mod, ip, refcnt)
+	TP_ARGS(mod, ip)
 );
+#endif /* CONFIG_MODULE_UNLOAD */
 
 TRACE_EVENT(module_request,
 
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index a8989c4547e..188deca2f3c 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -1,4 +1,7 @@
-#ifndef _TRACE_NAPI_H_
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM napi
+
+#if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_NAPI_H_
 
 #include <linux/netdevice.h>
@@ -8,4 +11,7 @@ DECLARE_TRACE(napi_poll,
 	TP_PROTO(struct napi_struct *napi),
 	TP_ARGS(napi));
 
-#endif
+#endif /* _TRACE_NAPI_H_ */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index cfceb0b73e2..b9e1dd6c620 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -51,15 +51,12 @@ TRACE_EVENT(sched_kthread_stop_ret,
 
 /*
  * Tracepoint for waiting on task to unschedule:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 TRACE_EVENT(sched_wait_task,
 
-	TP_PROTO(struct rq *rq, struct task_struct *p),
+	TP_PROTO(struct task_struct *p),
 
-	TP_ARGS(rq, p),
+	TP_ARGS(p),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -79,15 +76,12 @@ TRACE_EVENT(sched_wait_task,
 
 /*
  * Tracepoint for waking up a task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-	TP_PROTO(struct rq *rq, struct task_struct *p, int success),
+	TP_PROTO(struct task_struct *p, int success),
 
-	TP_ARGS(rq, p, success),
+	TP_ARGS(p, success),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -111,31 +105,42 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 );
 
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-	     TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-	     TP_ARGS(rq, p, success));
+	     TP_PROTO(struct task_struct *p, int success),
+	     TP_ARGS(p, success));
 
 /*
  * Tracepoint for waking up a new task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-	     TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-	     TP_ARGS(rq, p, success));
+	     TP_PROTO(struct task_struct *p, int success),
+	     TP_ARGS(p, success));
+
+#ifdef CREATE_TRACE_POINTS
+static inline long __trace_sched_switch_state(struct task_struct *p)
+{
+	long state = p->state;
+
+#ifdef CONFIG_PREEMPT
+	/*
+	 * For all intents and purposes a preempted task is a running task.
+	 */
+	if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)
+		state = TASK_RUNNING;
+#endif
+
+	return state;
+}
+#endif
 
 /*
  * Tracepoint for task switches, performed by the scheduler:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 TRACE_EVENT(sched_switch,
 
-	TP_PROTO(struct rq *rq, struct task_struct *prev,
+	TP_PROTO(struct task_struct *prev,
 		 struct task_struct *next),
 
-	TP_ARGS(rq, prev, next),
+	TP_ARGS(prev, next),
 
 	TP_STRUCT__entry(
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
@@ -151,7 +156,7 @@ 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;
+		__entry->prev_state	= __trace_sched_switch_state(prev);
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
diff --git a/include/trace/events/scsi.h b/include/trace/events/scsi.h
new file mode 100644
index 00000000000..25fbefdf2f2
--- /dev/null
+++ b/include/trace/events/scsi.h
@@ -0,0 +1,345 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM scsi
+
+#if !defined(_TRACE_SCSI_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCSI_H
+
+#include <scsi/scsi_cmnd.h>
+#include <scsi/scsi_host.h>
+#include <linux/tracepoint.h>
+#include <linux/trace_seq.h>
+
+#define scsi_opcode_name(opcode)	{ opcode, #opcode }
+#define show_opcode_name(val)					\
+	__print_symbolic(val,					\
+		scsi_opcode_name(TEST_UNIT_READY),		\
+		scsi_opcode_name(REZERO_UNIT),			\
+		scsi_opcode_name(REQUEST_SENSE),		\
+		scsi_opcode_name(FORMAT_UNIT),			\
+		scsi_opcode_name(READ_BLOCK_LIMITS),		\
+		scsi_opcode_name(REASSIGN_BLOCKS),		\
+		scsi_opcode_name(INITIALIZE_ELEMENT_STATUS),	\
+		scsi_opcode_name(READ_6),			\
+		scsi_opcode_name(WRITE_6),			\
+		scsi_opcode_name(SEEK_6),			\
+		scsi_opcode_name(READ_REVERSE),			\
+		scsi_opcode_name(WRITE_FILEMARKS),		\
+		scsi_opcode_name(SPACE),			\
+		scsi_opcode_name(INQUIRY),			\
+		scsi_opcode_name(RECOVER_BUFFERED_DATA),	\
+		scsi_opcode_name(MODE_SELECT),			\
+		scsi_opcode_name(RESERVE),			\
+		scsi_opcode_name(RELEASE),			\
+		scsi_opcode_name(COPY),				\
+		scsi_opcode_name(ERASE),			\
+		scsi_opcode_name(MODE_SENSE),			\
+		scsi_opcode_name(START_STOP),			\
+		scsi_opcode_name(RECEIVE_DIAGNOSTIC),		\
+		scsi_opcode_name(SEND_DIAGNOSTIC),		\
+		scsi_opcode_name(ALLOW_MEDIUM_REMOVAL),		\
+		scsi_opcode_name(SET_WINDOW),			\
+		scsi_opcode_name(READ_CAPACITY),		\
+		scsi_opcode_name(READ_10),			\
+		scsi_opcode_name(WRITE_10),			\
+		scsi_opcode_name(SEEK_10),			\
+		scsi_opcode_name(POSITION_TO_ELEMENT),		\
+		scsi_opcode_name(WRITE_VERIFY),			\
+		scsi_opcode_name(VERIFY),			\
+		scsi_opcode_name(SEARCH_HIGH),			\
+		scsi_opcode_name(SEARCH_EQUAL),			\
+		scsi_opcode_name(SEARCH_LOW),			\
+		scsi_opcode_name(SET_LIMITS),			\
+		scsi_opcode_name(PRE_FETCH),			\
+		scsi_opcode_name(READ_POSITION),		\
+		scsi_opcode_name(SYNCHRONIZE_CACHE),		\
+		scsi_opcode_name(LOCK_UNLOCK_CACHE),		\
+		scsi_opcode_name(READ_DEFECT_DATA),		\
+		scsi_opcode_name(MEDIUM_SCAN),			\
+		scsi_opcode_name(COMPARE),			\
+		scsi_opcode_name(COPY_VERIFY),			\
+		scsi_opcode_name(WRITE_BUFFER),			\
+		scsi_opcode_name(READ_BUFFER),			\
+		scsi_opcode_name(UPDATE_BLOCK),			\
+		scsi_opcode_name(READ_LONG),			\
+		scsi_opcode_name(WRITE_LONG),			\
+		scsi_opcode_name(CHANGE_DEFINITION),		\
+		scsi_opcode_name(WRITE_SAME),			\
+		scsi_opcode_name(UNMAP),			\
+		scsi_opcode_name(READ_TOC),			\
+		scsi_opcode_name(LOG_SELECT),			\
+		scsi_opcode_name(LOG_SENSE),			\
+		scsi_opcode_name(XDWRITEREAD_10),		\
+		scsi_opcode_name(MODE_SELECT_10),		\
+		scsi_opcode_name(RESERVE_10),			\
+		scsi_opcode_name(RELEASE_10),			\
+		scsi_opcode_name(MODE_SENSE_10),		\
+		scsi_opcode_name(PERSISTENT_RESERVE_IN),	\
+		scsi_opcode_name(PERSISTENT_RESERVE_OUT),	\
+		scsi_opcode_name(VARIABLE_LENGTH_CMD),		\
+		scsi_opcode_name(REPORT_LUNS),			\
+		scsi_opcode_name(MAINTENANCE_IN),		\
+		scsi_opcode_name(MAINTENANCE_OUT),		\
+		scsi_opcode_name(MOVE_MEDIUM),			\
+		scsi_opcode_name(EXCHANGE_MEDIUM),		\
+		scsi_opcode_name(READ_12),			\
+		scsi_opcode_name(WRITE_12),			\
+		scsi_opcode_name(WRITE_VERIFY_12),		\
+		scsi_opcode_name(SEARCH_HIGH_12),		\
+		scsi_opcode_name(SEARCH_EQUAL_12),		\
+		scsi_opcode_name(SEARCH_LOW_12),		\
+		scsi_opcode_name(READ_ELEMENT_STATUS),		\
+		scsi_opcode_name(SEND_VOLUME_TAG),		\
+		scsi_opcode_name(WRITE_LONG_2),			\
+		scsi_opcode_name(READ_16),			\
+		scsi_opcode_name(WRITE_16),			\
+		scsi_opcode_name(VERIFY_16),			\
+		scsi_opcode_name(WRITE_SAME_16),		\
+		scsi_opcode_name(SERVICE_ACTION_IN),		\
+		scsi_opcode_name(SAI_READ_CAPACITY_16),		\
+		scsi_opcode_name(SAI_GET_LBA_STATUS),		\
+		scsi_opcode_name(MI_REPORT_TARGET_PGS),		\
+		scsi_opcode_name(MO_SET_TARGET_PGS),		\
+		scsi_opcode_name(READ_32),			\
+		scsi_opcode_name(WRITE_32),			\
+		scsi_opcode_name(WRITE_SAME_32),		\
+		scsi_opcode_name(ATA_16),			\
+		scsi_opcode_name(ATA_12))
+
+#define scsi_hostbyte_name(result)	{ result, #result }
+#define show_hostbyte_name(val)					\
+	__print_symbolic(val,					\
+		scsi_hostbyte_name(DID_OK),			\
+		scsi_hostbyte_name(DID_NO_CONNECT),		\
+		scsi_hostbyte_name(DID_BUS_BUSY),		\
+		scsi_hostbyte_name(DID_TIME_OUT),		\
+		scsi_hostbyte_name(DID_BAD_TARGET),		\
+		scsi_hostbyte_name(DID_ABORT),			\
+		scsi_hostbyte_name(DID_PARITY),			\
+		scsi_hostbyte_name(DID_ERROR),			\
+		scsi_hostbyte_name(DID_RESET),			\
+		scsi_hostbyte_name(DID_BAD_INTR),		\
+		scsi_hostbyte_name(DID_PASSTHROUGH),		\
+		scsi_hostbyte_name(DID_SOFT_ERROR),		\
+		scsi_hostbyte_name(DID_IMM_RETRY),		\
+		scsi_hostbyte_name(DID_REQUEUE),		\
+		scsi_hostbyte_name(DID_TRANSPORT_DISRUPTED),	\
+		scsi_hostbyte_name(DID_TRANSPORT_FAILFAST))
+
+#define scsi_driverbyte_name(result)	{ result, #result }
+#define show_driverbyte_name(val)				\
+	__print_symbolic(val,					\
+		scsi_driverbyte_name(DRIVER_OK),		\
+		scsi_driverbyte_name(DRIVER_BUSY),		\
+		scsi_driverbyte_name(DRIVER_SOFT),		\
+		scsi_driverbyte_name(DRIVER_MEDIA),		\
+		scsi_driverbyte_name(DRIVER_ERROR),		\
+		scsi_driverbyte_name(DRIVER_INVALID),		\
+		scsi_driverbyte_name(DRIVER_TIMEOUT),		\
+		scsi_driverbyte_name(DRIVER_HARD),		\
+		scsi_driverbyte_name(DRIVER_SENSE))
+
+#define scsi_msgbyte_name(result)	{ result, #result }
+#define show_msgbyte_name(val)					\
+	__print_symbolic(val,					\
+		scsi_msgbyte_name(COMMAND_COMPLETE),		\
+		scsi_msgbyte_name(EXTENDED_MESSAGE),		\
+		scsi_msgbyte_name(SAVE_POINTERS),		\
+		scsi_msgbyte_name(RESTORE_POINTERS),		\
+		scsi_msgbyte_name(DISCONNECT),			\
+		scsi_msgbyte_name(INITIATOR_ERROR),		\
+		scsi_msgbyte_name(ABORT_TASK_SET),		\
+		scsi_msgbyte_name(MESSAGE_REJECT),		\
+		scsi_msgbyte_name(NOP),				\
+		scsi_msgbyte_name(MSG_PARITY_ERROR),		\
+		scsi_msgbyte_name(LINKED_CMD_COMPLETE),		\
+		scsi_msgbyte_name(LINKED_FLG_CMD_COMPLETE),	\
+		scsi_msgbyte_name(TARGET_RESET),		\
+		scsi_msgbyte_name(ABORT_TASK),			\
+		scsi_msgbyte_name(CLEAR_TASK_SET),		\
+		scsi_msgbyte_name(INITIATE_RECOVERY),		\
+		scsi_msgbyte_name(RELEASE_RECOVERY),		\
+		scsi_msgbyte_name(CLEAR_ACA),			\
+		scsi_msgbyte_name(LOGICAL_UNIT_RESET),		\
+		scsi_msgbyte_name(SIMPLE_QUEUE_TAG),		\
+		scsi_msgbyte_name(HEAD_OF_QUEUE_TAG),		\
+		scsi_msgbyte_name(ORDERED_QUEUE_TAG),		\
+		scsi_msgbyte_name(IGNORE_WIDE_RESIDUE),		\
+		scsi_msgbyte_name(ACA),				\
+		scsi_msgbyte_name(QAS_REQUEST),			\
+		scsi_msgbyte_name(BUS_DEVICE_RESET),		\
+		scsi_msgbyte_name(ABORT))
+
+#define scsi_statusbyte_name(result)	{ result, #result }
+#define show_statusbyte_name(val)				\
+	__print_symbolic(val,					\
+		scsi_statusbyte_name(SAM_STAT_GOOD),		\
+		scsi_statusbyte_name(SAM_STAT_CHECK_CONDITION),	\
+		scsi_statusbyte_name(SAM_STAT_CONDITION_MET),	\
+		scsi_statusbyte_name(SAM_STAT_BUSY),		\
+		scsi_statusbyte_name(SAM_STAT_INTERMEDIATE),	\
+		scsi_statusbyte_name(SAM_STAT_INTERMEDIATE_CONDITION_MET), \
+		scsi_statusbyte_name(SAM_STAT_RESERVATION_CONFLICT),	\
+		scsi_statusbyte_name(SAM_STAT_COMMAND_TERMINATED),	\
+		scsi_statusbyte_name(SAM_STAT_TASK_SET_FULL),	\
+		scsi_statusbyte_name(SAM_STAT_ACA_ACTIVE),	\
+		scsi_statusbyte_name(SAM_STAT_TASK_ABORTED))
+
+const char *scsi_trace_parse_cdb(struct trace_seq*, unsigned char*, int);
+#define __parse_cdb(cdb, len) scsi_trace_parse_cdb(p, cdb, len)
+
+TRACE_EVENT(scsi_dispatch_cmd_start,
+
+	TP_PROTO(struct scsi_cmnd *cmd),
+
+	TP_ARGS(cmd),
+
+	TP_STRUCT__entry(
+		__field( unsigned int,	host_no	)
+		__field( unsigned int,	channel	)
+		__field( unsigned int,	id	)
+		__field( unsigned int,	lun	)
+		__field( unsigned int,	opcode	)
+		__field( unsigned int,	cmd_len )
+		__field( unsigned int,	data_sglen )
+		__field( unsigned int,	prot_sglen )
+		__dynamic_array(unsigned char,	cmnd, cmd->cmd_len)
+	),
+
+	TP_fast_assign(
+		__entry->host_no	= cmd->device->host->host_no;
+		__entry->channel	= cmd->device->channel;
+		__entry->id		= cmd->device->id;
+		__entry->lun		= cmd->device->lun;
+		__entry->opcode		= cmd->cmnd[0];
+		__entry->cmd_len	= cmd->cmd_len;
+		__entry->data_sglen	= scsi_sg_count(cmd);
+		__entry->prot_sglen	= scsi_prot_sg_count(cmd);
+		memcpy(__get_dynamic_array(cmnd), cmd->cmnd, cmd->cmd_len);
+	),
+
+	TP_printk("host_no=%u channel=%u id=%u lun=%u data_sgl=%u prot_sgl=%u" \
+		  " cmnd=(%s %s raw=%s)",
+		  __entry->host_no, __entry->channel, __entry->id,
+		  __entry->lun, __entry->data_sglen, __entry->prot_sglen,
+		  show_opcode_name(__entry->opcode),
+		  __parse_cdb(__get_dynamic_array(cmnd), __entry->cmd_len),
+		  __print_hex(__get_dynamic_array(cmnd), __entry->cmd_len))
+);
+
+TRACE_EVENT(scsi_dispatch_cmd_error,
+
+	TP_PROTO(struct scsi_cmnd *cmd, int rtn),
+
+	TP_ARGS(cmd, rtn),
+
+	TP_STRUCT__entry(
+		__field( unsigned int,	host_no	)
+		__field( unsigned int,	channel	)
+		__field( unsigned int,	id	)
+		__field( unsigned int,	lun	)
+		__field( int,		rtn	)
+		__field( unsigned int,	opcode	)
+		__field( unsigned int,	cmd_len )
+		__field( unsigned int,	data_sglen )
+		__field( unsigned int,	prot_sglen )
+		__dynamic_array(unsigned char,	cmnd, cmd->cmd_len)
+	),
+
+	TP_fast_assign(
+		__entry->host_no	= cmd->device->host->host_no;
+		__entry->channel	= cmd->device->channel;
+		__entry->id		= cmd->device->id;
+		__entry->lun		= cmd->device->lun;
+		__entry->rtn		= rtn;
+		__entry->opcode		= cmd->cmnd[0];
+		__entry->cmd_len	= cmd->cmd_len;
+		__entry->data_sglen	= scsi_sg_count(cmd);
+		__entry->prot_sglen	= scsi_prot_sg_count(cmd);
+		memcpy(__get_dynamic_array(cmnd), cmd->cmnd, cmd->cmd_len);
+	),
+
+	TP_printk("host_no=%u channel=%u id=%u lun=%u data_sgl=%u prot_sgl=%u" \
+		  " cmnd=(%s %s raw=%s) rtn=%d",
+		  __entry->host_no, __entry->channel, __entry->id,
+		  __entry->lun, __entry->data_sglen, __entry->prot_sglen,
+		  show_opcode_name(__entry->opcode),
+		  __parse_cdb(__get_dynamic_array(cmnd), __entry->cmd_len),
+		  __print_hex(__get_dynamic_array(cmnd), __entry->cmd_len),
+		  __entry->rtn)
+);
+
+DECLARE_EVENT_CLASS(scsi_cmd_done_timeout_template,
+
+	TP_PROTO(struct scsi_cmnd *cmd),
+
+	TP_ARGS(cmd),
+
+	TP_STRUCT__entry(
+		__field( unsigned int,	host_no	)
+		__field( unsigned int,	channel	)
+		__field( unsigned int,	id	)
+		__field( unsigned int,	lun	)
+		__field( int,		result	)
+		__field( unsigned int,	opcode	)
+		__field( unsigned int,	cmd_len )
+		__field( unsigned int,	data_sglen )
+		__field( unsigned int,	prot_sglen )
+		__dynamic_array(unsigned char,	cmnd, cmd->cmd_len)
+	),
+
+	TP_fast_assign(
+		__entry->host_no	= cmd->device->host->host_no;
+		__entry->channel	= cmd->device->channel;
+		__entry->id		= cmd->device->id;
+		__entry->lun		= cmd->device->lun;
+		__entry->result		= cmd->result;
+		__entry->opcode		= cmd->cmnd[0];
+		__entry->cmd_len	= cmd->cmd_len;
+		__entry->data_sglen	= scsi_sg_count(cmd);
+		__entry->prot_sglen	= scsi_prot_sg_count(cmd);
+		memcpy(__get_dynamic_array(cmnd), cmd->cmnd, cmd->cmd_len);
+	),
+
+	TP_printk("host_no=%u channel=%u id=%u lun=%u data_sgl=%u " \
+		  "prot_sgl=%u cmnd=(%s %s raw=%s) result=(driver=%s host=%s " \
+		  "message=%s status=%s)",
+		  __entry->host_no, __entry->channel, __entry->id,
+		  __entry->lun, __entry->data_sglen, __entry->prot_sglen,
+		  show_opcode_name(__entry->opcode),
+		  __parse_cdb(__get_dynamic_array(cmnd), __entry->cmd_len),
+		  __print_hex(__get_dynamic_array(cmnd), __entry->cmd_len),
+		  show_driverbyte_name(((__entry->result) >> 24) & 0xff),
+		  show_hostbyte_name(((__entry->result) >> 16) & 0xff),
+		  show_msgbyte_name(((__entry->result) >> 8) & 0xff),
+		  show_statusbyte_name(__entry->result & 0xff))
+);
+
+DEFINE_EVENT(scsi_cmd_done_timeout_template, scsi_dispatch_cmd_done,
+	     TP_PROTO(struct scsi_cmnd *cmd),
+	     TP_ARGS(cmd));
+
+DEFINE_EVENT(scsi_cmd_done_timeout_template, scsi_dispatch_cmd_timeout,
+	     TP_PROTO(struct scsi_cmnd *cmd),
+	     TP_ARGS(cmd));
+
+TRACE_EVENT(scsi_eh_wakeup,
+
+	TP_PROTO(struct Scsi_Host *shost),
+
+	TP_ARGS(shost),
+
+	TP_STRUCT__entry(
+		__field( unsigned int,	host_no	)
+	),
+
+	TP_fast_assign(
+		__entry->host_no	= shost->host_no;
+	),
+
+	TP_printk("host_no=%u", __entry->host_no)
+);
+
+#endif /*  _TRACE_SCSI_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h
index a510b75ac30..17df43464df 100644
--- a/include/trace/events/signal.h
+++ b/include/trace/events/signal.h
@@ -10,7 +10,8 @@
 
 #define TP_STORE_SIGINFO(__entry, info)				\
 	do {							\
-		if (info == SEND_SIG_NOINFO) {			\
+		if (info == SEND_SIG_NOINFO ||			\
+		    info == SEND_SIG_FORCED) {			\
 			__entry->errno	= 0;			\
 			__entry->code	= SI_USER;		\
 		} else if (info == SEND_SIG_PRIV) {		\
@@ -100,18 +101,7 @@ TRACE_EVENT(signal_deliver,
 		  __entry->sa_handler, __entry->sa_flags)
 );
 
-/**
- * signal_overflow_fail - called when signal queue is overflow
- * @sig: signal number
- * @group: signal to process group or not (bool)
- * @info: pointer to struct siginfo
- *
- * Kernel fails to generate 'sig' signal with 'info' siginfo, because
- * siginfo queue is overflow, and the signal is dropped.
- * 'group' is not 0 if the signal will be sent to a process group.
- * 'sig' is always one of RT signals.
- */
-TRACE_EVENT(signal_overflow_fail,
+DECLARE_EVENT_CLASS(signal_queue_overflow,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
@@ -135,6 +125,24 @@ TRACE_EVENT(signal_overflow_fail,
 );
 
 /**
+ * signal_overflow_fail - called when signal queue is overflow
+ * @sig: signal number
+ * @group: signal to process group or not (bool)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel fails to generate 'sig' signal with 'info' siginfo, because
+ * siginfo queue is overflow, and the signal is dropped.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of RT signals.
+ */
+DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail,
+
+	TP_PROTO(int sig, int group, struct siginfo *info),
+
+	TP_ARGS(sig, group, info)
+);
+
+/**
  * signal_lose_info - called when siginfo is lost
  * @sig: signal number
  * @group: signal to process group or not (bool)
@@ -145,28 +153,13 @@ TRACE_EVENT(signal_overflow_fail,
  * 'group' is not 0 if the signal will be sent to a process group.
  * 'sig' is always one of non-RT signals.
  */
-TRACE_EVENT(signal_lose_info,
+DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
 
 	TP_PROTO(int sig, int group, struct siginfo *info),
 
-	TP_ARGS(sig, group, info),
-
-	TP_STRUCT__entry(
-		__field(	int,	sig	)
-		__field(	int,	group	)
-		__field(	int,	errno	)
-		__field(	int,	code	)
-	),
-
-	TP_fast_assign(
-		__entry->sig	= sig;
-		__entry->group	= group;
-		TP_STORE_SIGINFO(__entry, info);
-	),
-
-	TP_printk("sig=%d group=%d errno=%d code=%d",
-		  __entry->sig, __entry->group, __entry->errno, __entry->code)
+	TP_ARGS(sig, group, info)
 );
+
 #endif /* _TRACE_SIGNAL_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index c6fe03e902c..5a64905d727 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -62,10 +62,14 @@
 		struct trace_entry	ent;				\
 		tstruct							\
 		char			__data[0];			\
-	};
+	};								\
+									\
+	static struct ftrace_event_class event_class_##name;
+
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args)	\
-	static struct ftrace_event_call event_##name
+	static struct ftrace_event_call	__used		\
+	__attribute__((__aligned__(4))) event_##name
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
@@ -131,130 +135,6 @@
 #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;\tsigned:%u;\n",	\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item),	\
-			       (unsigned int)is_signed_type(type));	\
-	if (!ret)							\
-		return 0;
-
-#undef __field_ext
-#define __field_ext(type, item, filter_type)	__field(type, item)
-
-#undef __array
-#define __array(type, item, len)						\
-	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
-			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	\
-			       (unsigned int)offsetof(typeof(field), item), \
-			       (unsigned int)sizeof(field.item),	\
-			       (unsigned int)is_signed_type(type));	\
-	if (!ret)							\
-		return 0;
-
-#undef __dynamic_array
-#define __dynamic_array(type, item, len)				       \
-	ret = trace_seq_printf(s, "\tfield:__data_loc " #type "[] " #item ";\t"\
-			       "offset:%u;\tsize:%u;\tsigned:%u;\n",	       \
-			       (unsigned int)offsetof(typeof(field),	       \
-					__data_loc_##item),		       \
-			       (unsigned int)sizeof(field.__data_loc_##item), \
-			       (unsigned int)is_signed_type(type));	\
-	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 TP_perf_assign
-#define TP_perf_assign(args...)
-
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
-static int								\
-ftrace_format_setup_##call(struct ftrace_event_call *unused,		\
-			   struct trace_seq *s)				\
-{									\
-	struct ftrace_raw_##call field __attribute__((unused));		\
-	int ret = 0;							\
-									\
-	tstruct;							\
-									\
-	return ret;							\
-}									\
-									\
-static int								\
-ftrace_format_##call(struct ftrace_event_call *unused,			\
-		     struct trace_seq *s)				\
-{									\
-	int ret = 0;							\
-									\
-	ret = ftrace_format_setup_##call(unused, s);			\
-	if (!ret)							\
-		return ret;						\
-									\
-	ret = trace_seq_printf(s, "\nprint fmt: " print);		\
-									\
-	return ret;							\
-}
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args)
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)		\
-static int								\
-ftrace_format_##name(struct ftrace_event_call *unused,			\
-		      struct trace_seq *s)				\
-{									\
-	int ret = 0;							\
-									\
-	ret = ftrace_format_setup_##template(unused, s);		\
-	if (!ret)							\
-		return ret;						\
-									\
-	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:
@@ -270,16 +150,18 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
  *
  *	entry = iter->ent;
  *
- *	if (entry->type != event_<call>.id) {
+ *	if (entry->type != event_<call>->event.type) {
  *		WARN_ON_ONCE(1);
  *		return TRACE_TYPE_UNHANDLED;
  *	}
  *
  *	field = (typeof(field))entry;
  *
- *	p = get_cpu_var(ftrace_event_seq);
+ *	p = &get_cpu_var(ftrace_event_seq);
  *	trace_seq_init(p);
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	ret = trace_seq_printf(s, "%s: ", <call>);
+ *	if (ret)
+ *		ret = trace_seq_printf(s, <TP_printk> "\n");
  *	put_cpu();
  *	if (!ret)
  *		return TRACE_TYPE_PARTIAL_LINE;
@@ -321,21 +203,28 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
 		ftrace_print_symbols_seq(p, value, symbols);		\
 	})
 
+#undef __print_hex
+#define __print_hex(buf, buf_len) ftrace_print_hex_seq(p, buf, buf_len)
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-static enum print_line_t						\
-ftrace_raw_output_id_##call(int event_id, const char *name,		\
-			    struct trace_iterator *iter, int flags)	\
+static notrace enum print_line_t					\
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
+			 struct trace_event *trace_event)		\
 {									\
+	struct ftrace_event_call *event;				\
 	struct trace_seq *s = &iter->seq;				\
 	struct ftrace_raw_##call *field;				\
 	struct trace_entry *entry;					\
 	struct trace_seq *p;						\
 	int ret;							\
 									\
+	event = container_of(trace_event, struct ftrace_event_call,	\
+			     event);					\
+									\
 	entry = iter->ent;						\
 									\
-	if (entry->type != event_id) {					\
+	if (entry->type != event->event.type) {				\
 		WARN_ON_ONCE(1);					\
 		return TRACE_TYPE_UNHANDLED;				\
 	}								\
@@ -344,7 +233,7 @@ ftrace_raw_output_id_##call(int event_id, const char *name,		\
 									\
 	p = &get_cpu_var(ftrace_event_seq);				\
 	trace_seq_init(p);						\
-	ret = trace_seq_printf(s, "%s: ", name);			\
+	ret = trace_seq_printf(s, "%s: ", event->name);			\
 	if (ret)							\
 		ret = trace_seq_printf(s, print);			\
 	put_cpu();							\
@@ -352,21 +241,16 @@ ftrace_raw_output_id_##call(int event_id, const char *name,		\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\
 	return TRACE_TYPE_HANDLED;					\
-}
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args)			\
-static enum print_line_t						\
-ftrace_raw_output_##name(struct trace_iterator *iter, int flags)	\
-{									\
-	return ftrace_raw_output_id_##template(event_##name.id,		\
-					       #name, iter, flags);	\
-}
+}									\
+static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
+	.trace			= ftrace_raw_output_##call,		\
+};
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
-static enum print_line_t						\
-ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
+static notrace enum print_line_t					\
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags,	\
+			 struct trace_event *event)			\
 {									\
 	struct trace_seq *s = &iter->seq;				\
 	struct ftrace_raw_##template *field;				\
@@ -376,7 +260,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 									\
 	entry = iter->ent;						\
 									\
-	if (entry->type != event_##call.id) {				\
+	if (entry->type != event_##call.event.type) {			\
 		WARN_ON_ONCE(1);					\
 		return TRACE_TYPE_UNHANDLED;				\
 	}								\
@@ -393,7 +277,10 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\
 	return TRACE_TYPE_HANDLED;					\
-}
+}									\
+static struct trace_event_functions ftrace_event_type_funcs_##call = {	\
+	.trace			= ftrace_raw_output_##call,		\
+};
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
@@ -431,7 +318,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
-static int								\
+static int notrace							\
 ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 {									\
 	struct ftrace_raw_##call field;					\
@@ -479,7 +366,7 @@ ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-static inline int ftrace_get_offsets_##call(				\
+static inline notrace int ftrace_get_offsets_##call(			\
 	struct ftrace_data_offsets_##call *__data_offsets, proto)       \
 {									\
 	int __data_size = 0;						\
@@ -499,143 +386,85 @@ static inline int ftrace_get_offsets_##call(				\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#ifdef CONFIG_EVENT_PROFILE
-
-/*
- * Generate the functions needed for tracepoint perf_event support.
- *
- * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later
- *
- * static int ftrace_profile_enable_<call>(void)
- * {
- * 	return register_trace_<call>(ftrace_profile_<call>);
- * }
- *
- * static void ftrace_profile_disable_<call>(void)
- * {
- * 	unregister_trace_<call>(ftrace_profile_<call>);
- * }
- *
- */
-
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)
-
-#undef DEFINE_EVENT
-#define DEFINE_EVENT(template, name, proto, args)			\
-									\
-static void ftrace_profile_##name(proto);				\
-									\
-static int ftrace_profile_enable_##name(struct ftrace_event_call *unused)\
-{									\
-	return register_trace_##name(ftrace_profile_##name);		\
-}									\
-									\
-static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
-{									\
-	unregister_trace_##name(ftrace_profile_##name);			\
-}
-
-#undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
-	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
-
-#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-
-#endif
-
 /*
  * 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>(struct ftrace_event_call *unused)
- * {
- *	return register_trace_<call>(ftrace_event_<call>);
- * }
- *
- * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
- * {
- *	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)
+ * static void ftrace_raw_event_<call>(void *__data, proto)
  * {
+ *	struct ftrace_event_call *event_call = __data;
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
  *	struct ring_buffer *buffer;
  *	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(&buffer,
- *				  event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
+ *				  event_<call>->event.type,
+ *				  sizeof(*entry) + __data_size,
  *				  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(buffer, event, irq_flags, pc);
- * }
- *
- * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
- * {
- *	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;
- * }
+ *	{ <assign>; }  <-- Here we assign the entries by the __field and
+ *			   __array macros.
  *
- * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
- * {
- *	unregister_trace_<call>(ftrace_raw_event_<call>);
+ *	if (!filter_current_check_discard(buffer, event_call, entry, event))
+ *		trace_current_buffer_unlock_commit(buffer,
+ *						   event, irq_flags, pc);
  * }
  *
  * static struct trace_event ftrace_event_type_<call> = {
  *	.trace			= ftrace_raw_output_<call>, <-- stage 2
  * };
  *
+ * static const char print_fmt_<call>[] = <TP_printk>;
+ *
+ * static struct ftrace_event_class __used event_class_<template> = {
+ *	.system			= "<system>",
+ *	.define_fields		= ftrace_define_fields_<call>,
+ *	.fields			= LIST_HEAD_INIT(event_class_##call.fields),
+ *	.raw_init		= trace_event_raw_init,
+ *	.probe			= ftrace_raw_event_##call,
+ * };
+ *
  * static struct ftrace_event_call __used
  * __attribute__((__aligned__(4)))
  * __attribute__((section("_ftrace_events"))) event_<call> = {
  *	.name			= "<call>",
- *	.system			= "<system>",
- *	.raw_init		= trace_event_raw_init,
- *	.regfunc		= ftrace_reg_event_<call>,
- *	.unregfunc		= ftrace_unreg_event_<call>,
- *	.show_format		= ftrace_format_<call>,
- * }
+ *	.class			= event_class_<template>,
+ *	.event			= &ftrace_event_type_<call>,
+ *	.print_fmt		= print_fmt_<call>,
+ * };
  *
  */
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
+
+#define _TRACE_PERF_PROTO(call, proto)					\
+	static notrace void						\
+	perf_trace_##call(void *__data, proto);
 
-#define _TRACE_PROFILE_INIT(call)					\
-	.profile_enable = ftrace_profile_enable_##call,			\
-	.profile_disable = ftrace_profile_disable_##call,
+#define _TRACE_PERF_INIT(call)						\
+	.perf_probe		= perf_trace_##call,
 
 #else
-#define _TRACE_PROFILE_INIT(call)
-#endif
+#define _TRACE_PERF_PROTO(call, proto)
+#define _TRACE_PERF_INIT(call)
+#endif /* CONFIG_PERF_EVENTS */
 
 #undef __entry
 #define __entry entry
@@ -657,12 +486,19 @@ static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
 #define __assign_str(dst, src)						\
 	strcpy(__get_str(dst), src);
 
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef TP_perf_assign
+#define TP_perf_assign(args...)
+
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 									\
-static void ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
-				       proto)				\
+static notrace void							\
+ftrace_raw_event_##call(void *__data, proto)				\
 {									\
+	struct ftrace_event_call *event_call = __data;			\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
@@ -677,14 +513,13 @@ static void ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
 	event = trace_current_buffer_lock_reserve(&buffer,		\
-				 event_call->id,			\
+				 event_call->event.type,		\
 				 sizeof(*entry) + __data_size,		\
 				 irq_flags, pc);			\
 	if (!event)							\
 		return;							\
 	entry	= ring_buffer_event_data(event);			\
 									\
-									\
 	tstruct								\
 									\
 	{ assign; }							\
@@ -693,37 +528,47 @@ static void ftrace_raw_event_id_##call(struct ftrace_event_call *event_call, \
 		trace_nowake_buffer_unlock_commit(buffer,		\
 						  event, irq_flags, pc); \
 }
+/*
+ * The ftrace_test_probe is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the ftrace probe will
+ * fail to compile unless it too is updated.
+ */
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)			\
-									\
-static void ftrace_raw_event_##call(proto)				\
+static inline void ftrace_test_probe_##call(void)			\
 {									\
-	ftrace_raw_event_id_##template(&event_##call, args);		\
-}									\
-									\
-static int ftrace_raw_reg_event_##call(struct ftrace_event_call *unused)\
-{									\
-	return register_trace_##call(ftrace_raw_event_##call);		\
-}									\
-									\
-static void ftrace_raw_unreg_event_##call(struct ftrace_event_call *unused)\
-{									\
-	unregister_trace_##call(ftrace_raw_event_##call);		\
-}									\
-									\
-static struct trace_event ftrace_event_type_##call = {			\
-	.trace			= ftrace_raw_output_##call,		\
-};
+	check_trace_callback_type_##call(ftrace_raw_event_##template);	\
+}
 
 #undef DEFINE_EVENT_PRINT
-#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
-	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#undef __entry
+#define __entry REC
+
+#undef __print_flags
+#undef __print_symbolic
+#undef __get_dynamic_array
+#undef __get_str
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "\"" fmt "\", "  __stringify(args)
+
 #undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+_TRACE_PERF_PROTO(call, PARAMS(proto));					\
+static const char print_fmt_##call[] = print;				\
+static struct ftrace_event_class __used event_class_##call = {		\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.define_fields		= ftrace_define_fields_##call,		\
+	.fields			= LIST_HEAD_INIT(event_class_##call.fields),\
+	.raw_init		= trace_event_raw_init,			\
+	.probe			= ftrace_raw_event_##call,		\
+	_TRACE_PERF_INIT(call)						\
+};
 
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, call, proto, args)			\
@@ -732,42 +577,34 @@ 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		= trace_event_raw_init,			\
-	.regfunc		= ftrace_raw_reg_event_##call,		\
-	.unregfunc		= ftrace_raw_unreg_event_##call,	\
-	.show_format		= ftrace_format_##template,		\
-	.define_fields		= ftrace_define_fields_##template,	\
-	_TRACE_PROFILE_INIT(call)					\
-}
+	.class			= &event_class_##template,		\
+	.event.funcs		= &ftrace_event_type_funcs_##template,	\
+	.print_fmt		= print_fmt_##template,			\
+};
 
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, call, proto, args, print)		\
 									\
+static const char print_fmt_##call[] = print;				\
+									\
 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		= trace_event_raw_init,			\
-	.regfunc		= ftrace_raw_reg_event_##call,		\
-	.unregfunc		= ftrace_raw_unreg_event_##call,	\
-	.show_format		= ftrace_format_##call,			\
-	.define_fields		= ftrace_define_fields_##template,	\
-	_TRACE_PROFILE_INIT(call)					\
+	.class			= &event_class_##template,		\
+	.event.funcs		= &ftrace_event_type_funcs_##call,	\
+	.print_fmt		= print_fmt_##call,			\
 }
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
- * Define the insertion callback to profile events
+ * Define the insertion callback to perf events
  *
  * The job is very similar to ftrace_raw_event_<call> except that we don't
  * insert in the ring buffer but in a perf counter.
  *
- * static void ftrace_profile_<call>(proto)
+ * static void ftrace_perf_<call>(proto)
  * {
  *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *	struct ftrace_event_call *event_call = &event_<call>;
@@ -798,9 +635,9 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  *	__cpu = smp_processor_id();
  *
  *	if (in_nmi())
- *		trace_buf = rcu_dereference(perf_trace_buf_nmi);
+ *		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
  *	else
- *		trace_buf = rcu_dereference(perf_trace_buf);
+ *		trace_buf = rcu_dereference_sched(perf_trace_buf);
  *
  *	if (!trace_buf)
  *		goto end;
@@ -835,7 +672,17 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  * }
  */
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
+
+#undef __entry
+#define __entry entry
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)	\
+		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
+
+#undef __get_str
+#define __get_str(field) (char *)__get_dynamic_array(field)
 
 #undef __perf_addr
 #define __perf_addr(a) __addr = (a)
@@ -845,89 +692,63 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-static void								\
-ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
-			    proto)					\
+static notrace void							\
+perf_trace_##call(void *__data, proto)					\
 {									\
+	struct ftrace_event_call *event_call = __data;			\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
-	extern int perf_swevent_get_recursion_context(void);		\
-	extern void perf_swevent_put_recursion_context(int rctx);	\
-	extern void perf_tp_event(int, u64, u64, void *, int);		\
 	struct ftrace_raw_##call *entry;				\
+	struct pt_regs __regs;						\
 	u64 __addr = 0, __count = 1;					\
-	unsigned long irq_flags;					\
-	struct trace_entry *ent;					\
+	struct hlist_head *head;					\
 	int __entry_size;						\
 	int __data_size;						\
-	char *trace_buf;						\
-	char *raw_data;							\
-	int __cpu;							\
 	int rctx;							\
-	int pc;								\
 									\
-	pc = preempt_count();						\
+	perf_fetch_caller_regs(&__regs, 1);				\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
 			     sizeof(u64));				\
 	__entry_size -= sizeof(u32);					\
 									\
-	if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE,		\
+	if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE,		\
 		      "profile buffer not large enough"))		\
 		return;							\
 									\
-	local_irq_save(irq_flags);					\
-									\
-	rctx = perf_swevent_get_recursion_context();			\
-	if (rctx < 0)							\
-		goto end_recursion;					\
-									\
-	__cpu = smp_processor_id();					\
-									\
-	if (in_nmi())							\
-		trace_buf = rcu_dereference(perf_trace_buf_nmi);	\
-	else								\
-		trace_buf = rcu_dereference(perf_trace_buf);		\
-									\
-	if (!trace_buf)							\
-		goto end;						\
-									\
-	raw_data = per_cpu_ptr(trace_buf, __cpu);			\
-									\
-	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;		\
-	entry = (struct ftrace_raw_##call *)raw_data;			\
-	ent = &entry->ent;						\
-	tracing_generic_entry_update(ent, irq_flags, pc);		\
-	ent->type = event_call->id;					\
+	entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(	\
+		__entry_size, event_call->event.type, &__regs, &rctx);	\
+	if (!entry)							\
+		return;							\
 									\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
-	perf_tp_event(event_call->id, __addr, __count, entry,		\
-			     __entry_size);				\
-									\
-end:									\
-	perf_swevent_put_recursion_context(rctx);			\
-end_recursion:								\
-	local_irq_restore(irq_flags);					\
+	head = this_cpu_ptr(event_call->perf_events);			\
+	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
+		__count, &__regs, head);				\
 }
 
+/*
+ * This part is compiled out, it is only here as a build time check
+ * to make sure that if the tracepoint handling changes, the
+ * perf probe will fail to compile unless it too is updated.
+ */
 #undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)		\
-static void ftrace_profile_##call(proto)			\
-{								\
-	struct ftrace_event_call *event_call = &event_##call;	\
-								\
-	ftrace_profile_templ_##template(event_call, args);	\
+#define DEFINE_EVENT(template, call, proto, args)			\
+static inline void perf_test_probe_##call(void)				\
+{									\
+	check_trace_callback_type_##call(perf_trace_##template);	\
 }
 
+
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-#endif /* CONFIG_EVENT_PROFILE */
+#endif /* CONFIG_PERF_EVENTS */
 
 #undef _TRACE_PROFILE_INIT
 
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 961fda3556b..257e08960d7 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -25,6 +25,8 @@ struct syscall_metadata {
 	int		nb_args;
 	const char	**types;
 	const char	**args;
+	struct list_head enter_fields;
+	struct list_head exit_fields;
 
 	struct ftrace_event_call *enter_event;
 	struct ftrace_event_call *exit_event;
@@ -34,27 +36,23 @@ struct syscall_metadata {
 extern unsigned long arch_syscall_addr(int nr);
 extern int init_syscall_trace(struct ftrace_event_call *call);
 
-extern int syscall_enter_format(struct ftrace_event_call *call,
-				struct trace_seq *s);
-extern int syscall_exit_format(struct ftrace_event_call *call,
-				struct trace_seq *s);
-extern int syscall_enter_define_fields(struct ftrace_event_call *call);
-extern int syscall_exit_define_fields(struct ftrace_event_call *call);
 extern int reg_event_syscall_enter(struct ftrace_event_call *call);
 extern void unreg_event_syscall_enter(struct ftrace_event_call *call);
 extern int reg_event_syscall_exit(struct ftrace_event_call *call);
 extern void unreg_event_syscall_exit(struct ftrace_event_call *call);
 extern int
 ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
-enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
-enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
+enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags,
+				      struct trace_event *event);
+enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags,
+				     struct trace_event *event);
 #endif
-#ifdef CONFIG_EVENT_PROFILE
-int prof_sysenter_enable(struct ftrace_event_call *call);
-void prof_sysenter_disable(struct ftrace_event_call *call);
-int prof_sysexit_enable(struct ftrace_event_call *call);
-void prof_sysexit_disable(struct ftrace_event_call *call);
 
+#ifdef CONFIG_PERF_EVENTS
+int perf_sysenter_enable(struct ftrace_event_call *call);
+void perf_sysenter_disable(struct ftrace_event_call *call);
+int perf_sysexit_enable(struct ftrace_event_call *call);
+void perf_sysexit_disable(struct ftrace_event_call *call);
 #endif
 
 #endif /* _TRACE_SYSCALL_H */