Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework

Conflicts:
	arch/sh/kernel/cpu/sh2/setup-sh7619.c
	arch/sh/kernel/cpu/sh2a/setup-mxg.c
	arch/sh/kernel/cpu/sh2a/setup-sh7201.c
	arch/sh/kernel/cpu/sh2a/setup-sh7203.c
	arch/sh/kernel/cpu/sh2a/setup-sh7206.c
	arch/sh/kernel/cpu/sh3/setup-sh7705.c
	arch/sh/kernel/cpu/sh3/setup-sh770x.c
	arch/sh/kernel/cpu/sh3/setup-sh7710.c
	arch/sh/kernel/cpu/sh3/setup-sh7720.c
	arch/sh/kernel/cpu/sh4/setup-sh4-202.c
	arch/sh/kernel/cpu/sh4/setup-sh7750.c
	arch/sh/kernel/cpu/sh4/setup-sh7760.c
	arch/sh/kernel/cpu/sh4a/setup-sh7343.c
	arch/sh/kernel/cpu/sh4a/setup-sh7366.c
	arch/sh/kernel/cpu/sh4a/setup-sh7722.c
	arch/sh/kernel/cpu/sh4a/setup-sh7723.c
	arch/sh/kernel/cpu/sh4a/setup-sh7724.c
	arch/sh/kernel/cpu/sh4a/setup-sh7763.c
	arch/sh/kernel/cpu/sh4a/setup-sh7770.c
	arch/sh/kernel/cpu/sh4a/setup-sh7780.c
	arch/sh/kernel/cpu/sh4a/setup-sh7785.c
	arch/sh/kernel/cpu/sh4a/setup-sh7786.c
	arch/sh/kernel/cpu/sh4a/setup-shx3.c
	arch/sh/kernel/cpu/sh5/setup-sh5.c
	drivers/serial/sh-sci.c
	drivers/serial/sh-sci.h
	include/linux/serial_sci.h

29 files changed, 4521 insertions, 1322 deletions

diff --git a/include/trace/boot.h b/include/trace/boot.h
deleted file mode 100644
index 088ea089e31d..000000000000
--- a/include/trace/boot.h
+++ /dev/null
@@ -1,60 +0,0 @@
-#ifndef _LINUX_TRACE_BOOT_H
-#define _LINUX_TRACE_BOOT_H
-
-#include <linux/module.h>
-#include <linux/kallsyms.h>
-#include <linux/init.h>
-
-/*
- * Structure which defines the trace of an initcall
- * while it is called.
- * You don't have to fill the func field since it is
- * only used internally by the tracer.
- */
-struct boot_trace_call {
-	pid_t			caller;
-	char			func[KSYM_SYMBOL_LEN];
-};
-
-/*
- * Structure which defines the trace of an initcall
- * while it returns.
- */
-struct boot_trace_ret {
-	char			func[KSYM_SYMBOL_LEN];
-	int				result;
-	unsigned long long	duration;		/* nsecs */
-};
-
-#ifdef CONFIG_BOOT_TRACER
-/* Append the traces on the ring-buffer */
-extern void trace_boot_call(struct boot_trace_call *bt, initcall_t fn);
-extern void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn);
-
-/* Tells the tracer that smp_pre_initcall is finished.
- * So we can start the tracing
- */
-extern void start_boot_trace(void);
-
-/* Resume the tracing of other necessary events
- * such as sched switches
- */
-extern void enable_boot_trace(void);
-
-/* Suspend this tracing. Actually, only sched_switches tracing have
- * to be suspended. Initcalls doesn't need it.)
- */
-extern void disable_boot_trace(void);
-#else
-static inline
-void trace_boot_call(struct boot_trace_call *bt, initcall_t fn) { }
-
-static inline
-void trace_boot_ret(struct boot_trace_ret *bt, initcall_t fn) { }
-
-static inline void start_boot_trace(void) { }
-static inline void enable_boot_trace(void) { }
-static inline void disable_boot_trace(void) { }
-#endif /* CONFIG_BOOT_TRACER */
-
-#endif /* __LINUX_TRACE_BOOT_H */
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index f7a7ae1e8f90..da39b22636f7 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -21,11 +21,47 @@
 #undef CREATE_TRACE_POINTS
 
 #include <linux/stringify.h>
+/*
+ * module.h includes tracepoints, and because ftrace.h
+ * pulls in module.h:
+ *  trace/ftrace.h -> linux/ftrace_event.h -> linux/perf_event.h ->
+ *  linux/ftrace.h -> linux/module.h
+ * we must include module.h here before we play with any of
+ * the TRACE_EVENT() macros, otherwise the tracepoints included
+ * by module.h may break the build.
+ */
+#include <linux/module.h>
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
 	DEFINE_TRACE(name)
 
+#undef TRACE_EVENT_CONDITION
+#define TRACE_EVENT_CONDITION(name, proto, args, cond, tstruct, assign, print) \
+	TRACE_EVENT(name,						\
+		PARAMS(proto),						\
+		PARAMS(args),						\
+		PARAMS(tstruct),					\
+		PARAMS(assign),						\
+		PARAMS(print))
+
+#undef TRACE_EVENT_FN
+#define TRACE_EVENT_FN(name, proto, args, tstruct,		\
+		assign, print, reg, unreg)			\
+	DEFINE_TRACE_FN(name, reg, unreg)
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args) \
+	DEFINE_TRACE(name)
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_TRACE(name)
+
+#undef DEFINE_EVENT_CONDITION
+#define DEFINE_EVENT_CONDITION(template, name, proto, args, cond) \
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
 #undef DECLARE_TRACE
 #define DECLARE_TRACE(name, proto, args)	\
 	DEFINE_TRACE(name)
@@ -52,11 +88,23 @@
 
 #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
 
+#undef TRACE_EVENT
+#undef TRACE_EVENT_FN
+#undef TRACE_EVENT_CONDITION
+#undef DECLARE_EVENT_CLASS
+#undef DEFINE_EVENT
+#undef DEFINE_EVENT_PRINT
+#undef DEFINE_EVENT_CONDITION
 #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/bkl.h b/include/trace/events/bkl.h
new file mode 100644
index 000000000000..1af72dc24278
--- /dev/null
+++ b/include/trace/events/bkl.h
@@ -0,0 +1,61 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM bkl
+
+#if !defined(_TRACE_BKL_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BKL_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(lock_kernel,
+
+	TP_PROTO(const char *func, const char *file, int line),
+
+	TP_ARGS(func, file, line),
+
+	TP_STRUCT__entry(
+		__field(	int,		depth			)
+		__field_ext(	const char *,	func, FILTER_PTR_STRING	)
+		__field_ext(	const char *,	file, FILTER_PTR_STRING	)
+		__field(	int,		line			)
+	),
+
+	TP_fast_assign(
+		/* We want to record the lock_depth after lock is acquired */
+		__entry->depth = current->lock_depth + 1;
+		__entry->func = func;
+		__entry->file = file;
+		__entry->line = line;
+	),
+
+	TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth,
+		  __entry->file, __entry->line, __entry->func)
+);
+
+TRACE_EVENT(unlock_kernel,
+
+	TP_PROTO(const char *func, const char *file, int line),
+
+	TP_ARGS(func, file, line),
+
+	TP_STRUCT__entry(
+		__field(int,		depth		)
+		__field(const char *,	func		)
+		__field(const char *,	file		)
+		__field(int,		line		)
+	),
+
+	TP_fast_assign(
+		__entry->depth = current->lock_depth;
+		__entry->func = func;
+		__entry->file = file;
+		__entry->line = line;
+	),
+
+	TP_printk("depth=%d file:line=%s:%d func=%s()", __entry->depth,
+		  __entry->file, __entry->line, __entry->func)
+);
+
+#endif /* _TRACE_BKL_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index d6b05f42dd44..d8ce278515c3 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -1,3 +1,6 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
 #if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_BLOCK_H
 
@@ -5,10 +8,7 @@
 #include <linux/blkdev.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM block
-
-TRACE_EVENT(block_rq_abort,
+DECLARE_EVENT_CLASS(block_rq_with_error,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
@@ -25,8 +25,10 @@ TRACE_EVENT(block_rq_abort,
 
 	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->sector    = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_pos(rq);
+		__entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_sectors(rq);
 		__entry->errors    = rq->errors;
 
 		blk_fill_rwbs_rq(__entry->rwbs, rq);
@@ -40,41 +42,58 @@ TRACE_EVENT(block_rq_abort,
 		  __entry->nr_sector, __entry->errors)
 );
 
-TRACE_EVENT(block_rq_insert,
+/**
+ * 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),
 
-	TP_ARGS(q, 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)	)
-	),
+/**
+ * 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_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;
+	TP_PROTO(struct request_queue *q, struct request *rq),
 
-		blk_fill_rwbs_rq(__entry->rwbs, rq);
-		blk_dump_cmd(__get_str(cmd), rq);
-		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
-	),
+	TP_ARGS(q, rq)
+);
 
-	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)
+/**
+ * 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),
+
+	TP_ARGS(q, rq)
 );
 
-TRACE_EVENT(block_rq_issue,
+DECLARE_EVENT_CLASS(block_rq,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
 
@@ -86,15 +105,18 @@ TRACE_EVENT(block_rq_issue,
 		__field(  unsigned int,	nr_sector		)
 		__field(  unsigned int,	bytes			)
 		__array(  char,		rwbs,	6		)
-		__array(  char,		comm,   TASK_COMM_LEN   )
+		__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;
+		__entry->sector    = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_pos(rq);
+		__entry->nr_sector = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					0 : blk_rq_sectors(rq);
+		__entry->bytes     = (rq->cmd_type == REQ_TYPE_BLOCK_PC) ?
+					blk_rq_bytes(rq) : 0;
 
 		blk_fill_rwbs_rq(__entry->rwbs, rq);
 		blk_dump_cmd(__get_str(cmd), rq);
@@ -108,69 +130,49 @@ TRACE_EVENT(block_rq_issue,
 		  __entry->nr_sector, __entry->comm)
 );
 
-TRACE_EVENT(block_rq_requeue,
+/**
+ * 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),
 
-	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)
+	TP_ARGS(q, rq)
 );
 
-TRACE_EVENT(block_rq_complete,
+/**
+ * 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),
 
-	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)
+	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),
@@ -186,7 +188,8 @@ TRACE_EVENT(block_bio_bounce,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio->bi_bdev ?
+					  bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio->bi_sector;
 		__entry->nr_sector	= bio->bi_size >> 9;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
@@ -199,6 +202,14 @@ 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),
@@ -226,7 +237,7 @@ TRACE_EVENT(block_bio_complete,
 		  __entry->nr_sector, __entry->error)
 );
 
-TRACE_EVENT(block_bio_backmerge,
+DECLARE_EVENT_CLASS(block_bio,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
 
@@ -254,63 +265,51 @@ TRACE_EVENT(block_bio_backmerge,
 		  __entry->nr_sector, __entry->comm)
 );
 
-TRACE_EVENT(block_bio_frontmerge,
+/**
+ * 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),
 
-	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)
+	TP_ARGS(q, bio)
 );
 
-TRACE_EVENT(block_bio_queue,
+/**
+ * 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),
 
-	TP_ARGS(q, 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	)
-	),
+/**
+ * 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_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_PROTO(struct request_queue *q, struct bio *bio),
 
-	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)
+	TP_ARGS(q, bio)
 );
 
-TRACE_EVENT(block_getrq,
+DECLARE_EVENT_CLASS(block_get_rq,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
 
@@ -339,35 +338,48 @@ TRACE_EVENT(block_getrq,
 		  __entry->nr_sector, __entry->comm)
 );
 
-TRACE_EVENT(block_sleeprq,
+/**
+ * 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),
 
-	TP_ARGS(q, bio, 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	)
-	),
+/**
+ * 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_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_PROTO(struct request_queue *q, struct bio *bio, int rw),
 
-	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)
+	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),
@@ -385,7 +397,7 @@ TRACE_EVENT(block_plug,
 	TP_printk("[%s]", __entry->comm)
 );
 
-TRACE_EVENT(block_unplug_timer,
+DECLARE_EVENT_CLASS(block_unplug,
 
 	TP_PROTO(struct request_queue *q),
 
@@ -404,25 +416,45 @@ TRACE_EVENT(block_unplug_timer,
 	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
 );
 
-TRACE_EVENT(block_unplug_io,
+/**
+ * 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),
 
-	TP_ARGS(q),
+	TP_ARGS(q)
+);
 
-	TP_STRUCT__entry(
-		__field( int,		nr_rq			)
-		__array( char,		comm,	TASK_COMM_LEN	)
-	),
+/**
+ * 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_fast_assign(
-		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
-		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
-	),
+	TP_PROTO(struct request_queue *q),
 
-	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+	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,
@@ -453,6 +485,16 @@ 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,
@@ -486,6 +528,50 @@ 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,
+		 sector_t from),
+
+	TP_ARGS(q, rq, 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		= disk_devt(rq->rq_disk);
+		__entry->sector		= blk_rq_pos(rq);
+		__entry->nr_sector	= blk_rq_sectors(rq);
+		__entry->old_dev	= dev;
+		__entry->old_sector	= from;
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+	),
+
+	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 */
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index acf4cc9cd36d..e5e345fb2a5c 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1,21 +1,28 @@
-#if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_EXT4_H
-
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM ext4
 
+#if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EXT4_H
+
 #include <linux/writeback.h>
-#include "../../../fs/ext4/ext4.h"
-#include "../../../fs/ext4/mballoc.h"
 #include <linux/tracepoint.h>
 
+struct ext4_allocation_context;
+struct ext4_allocation_request;
+struct ext4_prealloc_space;
+struct ext4_inode_info;
+struct mpage_da_data;
+
+#define EXT4_I(inode) (container_of(inode, struct ext4_inode_info, vfs_inode))
+
 TRACE_EVENT(ext4_free_inode,
 	TP_PROTO(struct inode *inode),
 
 	TP_ARGS(inode),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	umode_t, mode			)
 		__field(	uid_t,	uid			)
@@ -24,7 +31,8 @@ TRACE_EVENT(ext4_free_inode,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
 		__entry->mode	= inode->i_mode;
 		__entry->uid	= inode->i_uid;
@@ -32,9 +40,11 @@ TRACE_EVENT(ext4_free_inode,
 		__entry->blocks	= inode->i_blocks;
 	),
 
-	TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode,
-		  __entry->uid, __entry->gid, __entry->blocks)
+	TP_printk("dev %d,%d ino %lu mode 0%o uid %u gid %u blocks %llu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->mode,
+		  __entry->uid, __entry->gid,
+		  (unsigned long long) __entry->blocks)
 );
 
 TRACE_EVENT(ext4_request_inode,
@@ -43,19 +53,22 @@ TRACE_EVENT(ext4_request_inode,
 	TP_ARGS(dir, mode),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	dir			)
 		__field(	umode_t, mode			)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= dir->i_sb->s_dev;
+		__entry->dev_major = MAJOR(dir->i_sb->s_dev);
+		__entry->dev_minor = MINOR(dir->i_sb->s_dev);
 		__entry->dir	= dir->i_ino;
 		__entry->mode	= mode;
 	),
 
-	TP_printk("dev %s dir %lu mode %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->dir, __entry->mode)
+	TP_printk("dev %d,%d dir %lu mode 0%o",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->dir, __entry->mode)
 );
 
 TRACE_EVENT(ext4_allocate_inode,
@@ -64,112 +77,180 @@ TRACE_EVENT(ext4_allocate_inode,
 	TP_ARGS(inode, dir, mode),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	ino_t,	dir			)
 		__field(	umode_t, mode			)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
 		__entry->dir	= dir->i_ino;
 		__entry->mode	= mode;
 	),
 
-	TP_printk("dev %s ino %lu dir %lu mode %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->dir, __entry->mode)
+	TP_printk("dev %d,%d ino %lu dir %lu mode 0%o",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  (unsigned long) __entry->dir, __entry->mode)
 );
 
-TRACE_EVENT(ext4_write_begin,
+TRACE_EVENT(ext4_evict_inode,
+	TP_PROTO(struct inode *inode),
 
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-		 unsigned int flags),
+	TP_ARGS(inode),
 
-	TP_ARGS(inode, pos, len, flags),
+	TP_STRUCT__entry(
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
+		__field(	int,	nlink			)
+	),
+
+	TP_fast_assign(
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
+		__entry->ino	= inode->i_ino;
+		__entry->nlink	= inode->i_nlink;
+	),
+
+	TP_printk("dev %d,%d ino %lu nlink %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->nlink)
+);
+
+TRACE_EVENT(ext4_drop_inode,
+	TP_PROTO(struct inode *inode, int drop),
+
+	TP_ARGS(inode, drop),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,	dev_major		)
+		__field(	int,	dev_minor		)
 		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, flags		)
+		__field(	int,	drop			)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->flags	= flags;
+		__entry->drop	= drop;
 	),
 
-	TP_printk("dev %s ino %lu pos %llu len %u flags %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
-		  __entry->flags)
+	TP_printk("dev %d,%d ino %lu drop %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->drop)
 );
 
-TRACE_EVENT(ext4_ordered_write_end,
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-			unsigned int copied),
+TRACE_EVENT(ext4_mark_inode_dirty,
+	TP_PROTO(struct inode *inode, unsigned long IP),
 
-	TP_ARGS(inode, pos, len, copied),
+	TP_ARGS(inode, IP),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,	dev_major		)
+		__field(	int,	dev_minor		)
 		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, copied		)
+		__field(unsigned long,	ip			)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->copied	= copied;
+		__entry->ip	= IP;
+	),
+
+	TP_printk("dev %d,%d ino %lu caller %pF",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, (void *)__entry->ip)
+);
+
+TRACE_EVENT(ext4_begin_ordered_truncate,
+	TP_PROTO(struct inode *inode, loff_t new_size),
+
+	TP_ARGS(inode, new_size),
+
+	TP_STRUCT__entry(
+		__field(	int,	dev_major		)
+		__field(	int,	dev_minor		)
+		__field(	ino_t,	ino			)
+		__field(	loff_t,	new_size		)
 	),
 
-	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
-		  __entry->copied)
+	TP_fast_assign(
+		__entry->dev_major	= MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(inode->i_sb->s_dev);
+		__entry->ino		= inode->i_ino;
+		__entry->new_size	= new_size;
+	),
+
+	TP_printk("dev %d,%d ino %lu new_size %lld",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  (long long) __entry->new_size)
 );
 
-TRACE_EVENT(ext4_writeback_write_end,
+DECLARE_EVENT_CLASS(ext4__write_begin,
+
 	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-		 unsigned int copied),
+		 unsigned int flags),
 
-	TP_ARGS(inode, pos, len, copied),
+	TP_ARGS(inode, pos, len, flags),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	loff_t,	pos			)
 		__field(	unsigned int, len		)
-		__field(	unsigned int, copied		)
+		__field(	unsigned int, flags		)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
 		__entry->pos	= pos;
 		__entry->len	= len;
-		__entry->copied	= copied;
+		__entry->flags	= flags;
 	),
 
-	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
-		  __entry->copied)
+	TP_printk("dev %d,%d ino %lu pos %llu len %u flags %u",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->pos, __entry->len, __entry->flags)
 );
 
-TRACE_EVENT(ext4_journalled_write_end,
+DEFINE_EVENT(ext4__write_begin, ext4_write_begin,
+
 	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-		 unsigned int copied),
+		 unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags)
+);
+
+DEFINE_EVENT(ext4__write_begin, ext4_da_write_begin,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int flags),
+
+	TP_ARGS(inode, pos, len, flags)
+);
+
+DECLARE_EVENT_CLASS(ext4__write_end,
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+			unsigned int copied),
+
 	TP_ARGS(inode, pos, len, copied),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	loff_t,	pos			)
 		__field(	unsigned int, len		)
@@ -177,38 +258,75 @@ TRACE_EVENT(ext4_journalled_write_end,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
 		__entry->pos	= pos;
 		__entry->len	= len;
 		__entry->copied	= copied;
 	),
 
-	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
-		  __entry->copied)
+	TP_printk("dev %d,%d ino %lu pos %llu len %u copied %u",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->pos,
+		  __entry->len, __entry->copied)
+);
+
+DEFINE_EVENT(ext4__write_end, ext4_ordered_write_end,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied)
+);
+
+DEFINE_EVENT(ext4__write_end, ext4_writeback_write_end,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied)
 );
 
-TRACE_EVENT(ext4_da_writepage,
+DEFINE_EVENT(ext4__write_end, ext4_journalled_write_end,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied)
+);
+
+DEFINE_EVENT(ext4__write_end, ext4_da_write_end,
+
+	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
+		 unsigned int copied),
+
+	TP_ARGS(inode, pos, len, copied)
+);
+
+TRACE_EVENT(ext4_writepage,
 	TP_PROTO(struct inode *inode, struct page *page),
 
 	TP_ARGS(inode, page),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	pgoff_t, index			)
 
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
 		__entry->index	= page->index;
 	),
 
-	TP_printk("dev %s ino %lu page_index %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
+	TP_printk("dev %d,%d ino %lu page_index %lu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->index)
 );
 
 TRACE_EVENT(ext4_da_writepages,
@@ -217,39 +335,81 @@ TRACE_EVENT(ext4_da_writepages,
 	TP_ARGS(inode, wbc),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	long,	nr_to_write		)
 		__field(	long,	pages_skipped		)
 		__field(	loff_t,	range_start		)
 		__field(	loff_t,	range_end		)
-		__field(	char,	nonblocking		)
 		__field(	char,	for_kupdate		)
 		__field(	char,	for_reclaim		)
-		__field(	char,	for_writepages		)
 		__field(	char,	range_cyclic		)
+		__field(       pgoff_t,	writeback_index		)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
+		__entry->dev_major	= MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(inode->i_sb->s_dev);
 		__entry->ino		= inode->i_ino;
 		__entry->nr_to_write	= wbc->nr_to_write;
 		__entry->pages_skipped	= wbc->pages_skipped;
 		__entry->range_start	= wbc->range_start;
 		__entry->range_end	= wbc->range_end;
-		__entry->nonblocking	= wbc->nonblocking;
 		__entry->for_kupdate	= wbc->for_kupdate;
 		__entry->for_reclaim	= wbc->for_reclaim;
-		__entry->for_writepages	= wbc->for_writepages;
 		__entry->range_cyclic	= wbc->range_cyclic;
+		__entry->writeback_index = inode->i_mapping->writeback_index;
 	),
 
-	TP_printk("dev %s ino %lu nr_t_write %ld pages_skipped %ld range_start %llu range_end %llu nonblocking %d for_kupdate %d for_reclaim %d for_writepages %d range_cyclic %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->nr_to_write,
+	TP_printk("dev %d,%d ino %lu nr_to_write %ld pages_skipped %ld "
+		  "range_start %llu range_end %llu "
+		  "for_kupdate %d for_reclaim %d "
+		  "range_cyclic %d writeback_index %lu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->nr_to_write,
 		  __entry->pages_skipped, __entry->range_start,
-		  __entry->range_end, __entry->nonblocking,
+		  __entry->range_end,
 		  __entry->for_kupdate, __entry->for_reclaim,
-		  __entry->for_writepages, __entry->range_cyclic)
+		  __entry->range_cyclic,
+		  (unsigned long) __entry->writeback_index)
+);
+
+TRACE_EVENT(ext4_da_write_pages,
+	TP_PROTO(struct inode *inode, struct mpage_da_data *mpd),
+
+	TP_ARGS(inode, mpd),
+
+	TP_STRUCT__entry(
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
+		__field(	__u64,	b_blocknr		)
+		__field(	__u32,	b_size			)
+		__field(	__u32,	b_state			)
+		__field(	unsigned long,	first_page	)
+		__field(	int,	io_done			)
+		__field(	int,	pages_written		)
+	),
+
+	TP_fast_assign(
+		__entry->dev_major	= MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(inode->i_sb->s_dev);
+		__entry->ino		= inode->i_ino;
+		__entry->b_blocknr	= mpd->b_blocknr;
+		__entry->b_size		= mpd->b_size;
+		__entry->b_state	= mpd->b_state;
+		__entry->first_page	= mpd->first_page;
+		__entry->io_done	= mpd->io_done;
+		__entry->pages_written	= mpd->pages_written;
+	),
+
+	TP_printk("dev %d,%d ino %lu b_blocknr %llu b_size %u b_state 0x%04x first_page %lu io_done %d pages_written %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->b_blocknr, __entry->b_size,
+		  __entry->b_state, __entry->first_page,
+		  __entry->io_done, __entry->pages_written)
 );
 
 TRACE_EVENT(ext4_da_writepages_result,
@@ -259,129 +419,33 @@ TRACE_EVENT(ext4_da_writepages_result,
 	TP_ARGS(inode, wbc, ret, pages_written),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	int,	ret			)
 		__field(	int,	pages_written		)
 		__field(	long,	pages_skipped		)
-		__field(	char,	encountered_congestion	)
 		__field(	char,	more_io			)	
-		__field(	char,	no_nrwrite_index_update )
+		__field(       pgoff_t,	writeback_index		)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
+		__entry->dev_major	= MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(inode->i_sb->s_dev);
 		__entry->ino		= inode->i_ino;
 		__entry->ret		= ret;
 		__entry->pages_written	= pages_written;
 		__entry->pages_skipped	= wbc->pages_skipped;
-		__entry->encountered_congestion	= wbc->encountered_congestion;
 		__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 congestion %d more_io %d no_nrwrite_index_update %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->ret,
+	TP_printk("dev %d,%d ino %lu ret %d pages_written %d pages_skipped %ld more_io %d writeback_index %lu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->ret,
 		  __entry->pages_written, __entry->pages_skipped,
-		  __entry->encountered_congestion, __entry->more_io,
-		  __entry->no_nrwrite_index_update)
-);
-
-TRACE_EVENT(ext4_da_write_begin,
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-			unsigned int flags),
-
-	TP_ARGS(inode, pos, len, flags),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, flags		)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->flags	= flags;
-	),
-
-	TP_printk("dev %s ino %lu pos %llu len %u flags %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
-		  __entry->flags)
-);
-
-TRACE_EVENT(ext4_da_write_end,
-	TP_PROTO(struct inode *inode, loff_t pos, unsigned int len,
-			unsigned int copied),
-
-	TP_ARGS(inode, pos, len, copied),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	loff_t,	pos			)
-		__field(	unsigned int, len		)
-		__field(	unsigned int, copied		)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->pos	= pos;
-		__entry->len	= len;
-		__entry->copied	= copied;
-	),
-
-	TP_printk("dev %s ino %lu pos %llu len %u copied %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pos, __entry->len,
-		  __entry->copied)
-);
-
-TRACE_EVENT(ext4_normal_writepage,
-	TP_PROTO(struct inode *inode, struct page *page),
-
-	TP_ARGS(inode, page),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	pgoff_t, index			)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->index	= page->index;
-	),
-
-	TP_printk("dev %s ino %lu page_index %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
-);
-
-TRACE_EVENT(ext4_journalled_writepage,
-	TP_PROTO(struct inode *inode, struct page *page),
-
-	TP_ARGS(inode, page),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	pgoff_t, index			)
-
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->index	= page->index;
-	),
-
-	TP_printk("dev %s ino %lu page_index %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
+		  __entry->more_io,
+		  (unsigned long) __entry->writeback_index)
 );
 
 TRACE_EVENT(ext4_discard_blocks,
@@ -391,30 +455,34 @@ TRACE_EVENT(ext4_discard_blocks,
 	TP_ARGS(sb, blk, count),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	__u64,	blk			)
 		__field(	__u64,	count			)
 
 	),
 
 	TP_fast_assign(
-		__entry->dev	= sb->s_dev;
+		__entry->dev_major = MAJOR(sb->s_dev);
+		__entry->dev_minor = MINOR(sb->s_dev);
 		__entry->blk	= blk;
 		__entry->count	= count;
 	),
 
-	TP_printk("dev %s blk %llu count %llu",
-		  jbd2_dev_to_name(__entry->dev), __entry->blk, __entry->count)
+	TP_printk("dev %d,%d blk %llu count %llu",
+		  __entry->dev_major, __entry->dev_minor,
+		  __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),
 
 	TP_ARGS(ac, pa),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	__u64,	pa_pstart		)
 		__field(	__u32,	pa_len			)
@@ -423,55 +491,47 @@ TRACE_EVENT(ext4_mb_new_inode_pa,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= ac->ac_sb->s_dev;
+		__entry->dev_major	= MAJOR(ac->ac_sb->s_dev);
+		__entry->dev_minor	= MINOR(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_printk("dev %s ino %lu pstart %llu len %u lstart %llu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->pa_pstart,
+	TP_printk("dev %d,%d ino %lu pstart %llu len %u lstart %llu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __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), __entry->ino, __entry->pa_pstart,
-		  __entry->pa_len, __entry->pa_lstart)
+	TP_ARGS(ac, pa)
 );
 
 TRACE_EVENT(ext4_mb_release_inode_pa,
-	TP_PROTO(struct ext4_allocation_context *ac,
+	TP_PROTO(struct super_block *sb,
+		 struct inode *inode,
 		 struct ext4_prealloc_space *pa,
 		 unsigned long long block, unsigned int count),
 
-	TP_ARGS(ac, pa, block, count),
+	TP_ARGS(sb, inode, pa, block, count),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	__u64,	block			)
 		__field(	__u32,	count			)
@@ -479,40 +539,42 @@ TRACE_EVENT(ext4_mb_release_inode_pa,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= ac->ac_sb->s_dev;
-		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->dev_major	= MAJOR(sb->s_dev);
+		__entry->dev_minor	= MINOR(sb->s_dev);
+		__entry->ino		= inode->i_ino;
 		__entry->block		= block;
 		__entry->count		= count;
 	),
 
-	TP_printk("dev %s ino %lu block %llu count %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block,
-		  __entry->count)
+	TP_printk("dev %d,%d ino %lu block %llu count %u",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->block, __entry->count)
 );
 
 TRACE_EVENT(ext4_mb_release_group_pa,
-	TP_PROTO(struct ext4_allocation_context *ac,
+	TP_PROTO(struct super_block *sb,
 		 struct ext4_prealloc_space *pa),
 
-	TP_ARGS(ac, pa),
+	TP_ARGS(sb, pa),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	__u64,	pa_pstart		)
 		__field(	__u32,	pa_len			)
 
 	),
 
 	TP_fast_assign(
-		__entry->dev		= ac->ac_sb->s_dev;
-		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->dev_major	= MAJOR(sb->s_dev);
+		__entry->dev_minor	= MINOR(sb->s_dev);
 		__entry->pa_pstart	= pa->pa_pstart;
 		__entry->pa_len		= pa->pa_len;
 	),
 
-	TP_printk("dev %s pstart %llu len %u",
-		  jbd2_dev_to_name(__entry->dev), __entry->pa_pstart, __entry->pa_len)
+	TP_printk("dev %d,%d pstart %llu len %u",
+		  __entry->dev_major, __entry->dev_minor,
+		  __entry->pa_pstart, __entry->pa_len)
 );
 
 TRACE_EVENT(ext4_discard_preallocations,
@@ -521,18 +583,21 @@ TRACE_EVENT(ext4_discard_preallocations,
 	TP_ARGS(inode),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
 		__entry->ino	= inode->i_ino;
 	),
 
-	TP_printk("dev %s ino %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino)
+	TP_printk("dev %d,%d ino %lu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino)
 );
 
 TRACE_EVENT(ext4_mb_discard_preallocations,
@@ -541,18 +606,20 @@ TRACE_EVENT(ext4_mb_discard_preallocations,
 	TP_ARGS(sb, needed),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	int,	needed			)
 
 	),
 
 	TP_fast_assign(
-		__entry->dev	= sb->s_dev;
+		__entry->dev_major = MAJOR(sb->s_dev);
+		__entry->dev_minor = MINOR(sb->s_dev);
 		__entry->needed	= needed;
 	),
 
-	TP_printk("dev %s needed %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->needed)
+	TP_printk("dev %d,%d needed %d",
+		  __entry->dev_major, __entry->dev_minor, __entry->needed)
 );
 
 TRACE_EVENT(ext4_request_blocks,
@@ -561,7 +628,8 @@ TRACE_EVENT(ext4_request_blocks,
 	TP_ARGS(ar),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	unsigned int, flags		)
 		__field(	unsigned int, len		)
@@ -574,7 +642,8 @@ TRACE_EVENT(ext4_request_blocks,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= ar->inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(ar->inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(ar->inode->i_sb->s_dev);
 		__entry->ino	= ar->inode->i_ino;
 		__entry->flags	= ar->flags;
 		__entry->len	= ar->len;
@@ -586,9 +655,10 @@ TRACE_EVENT(ext4_request_blocks,
 		__entry->pright	= ar->pright;
 	),
 
-	TP_printk("dev %s ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags,
-		  __entry->len,
+	TP_printk("dev %d,%d ino %lu flags %u len %u lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->flags, __entry->len,
 		  (unsigned long long) __entry->logical,
 		  (unsigned long long) __entry->goal,
 		  (unsigned long long) __entry->lleft,
@@ -603,7 +673,8 @@ TRACE_EVENT(ext4_allocate_blocks,
 	TP_ARGS(ar, block),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	__u64,	block			)
 		__field(	unsigned int, flags		)
@@ -617,7 +688,8 @@ TRACE_EVENT(ext4_allocate_blocks,
 	),
 
 	TP_fast_assign(
-		__entry->dev	= ar->inode->i_sb->s_dev;
+		__entry->dev_major = MAJOR(ar->inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(ar->inode->i_sb->s_dev);
 		__entry->ino	= ar->inode->i_ino;
 		__entry->block	= block;
 		__entry->flags	= ar->flags;
@@ -630,8 +702,9 @@ TRACE_EVENT(ext4_allocate_blocks,
 		__entry->pright	= ar->pright;
 	),
 
-	TP_printk("dev %s ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->flags,
+	TP_printk("dev %d,%d ino %lu flags %u len %u block %llu lblk %llu goal %llu lleft %llu lright %llu pleft %llu pright %llu ",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __entry->flags,
 		  __entry->len, __entry->block,
 		  (unsigned long long) __entry->logical,
 		  (unsigned long long) __entry->goal,
@@ -643,54 +716,64 @@ TRACE_EVENT(ext4_allocate_blocks,
 
 TRACE_EVENT(ext4_free_blocks,
 	TP_PROTO(struct inode *inode, __u64 block, unsigned long count,
-			int metadata),
+		 int flags),
 
-	TP_ARGS(inode, block, count, metadata),
+	TP_ARGS(inode, block, count, flags),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
+		__field(      umode_t, mode			)
 		__field(	__u64,	block			)
 		__field(	unsigned long,	count		)
-		__field(	int,	metadata		)
-
+		__field(	 int,	flags			)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= inode->i_sb->s_dev;
+		__entry->dev_major	= MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(inode->i_sb->s_dev);
 		__entry->ino		= inode->i_ino;
+		__entry->mode		= inode->i_mode;
 		__entry->block		= block;
 		__entry->count		= count;
-		__entry->metadata	= metadata;
+		__entry->flags		= flags;
 	),
 
-	TP_printk("dev %s ino %lu block %llu count %lu metadata %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->block,
-		  __entry->count, __entry->metadata)
+	TP_printk("dev %d,%d ino %lu mode 0%o block %llu count %lu flags %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->mode, __entry->block, __entry->count,
+		  __entry->flags)
 );
 
 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			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	ino_t,	ino			)
 		__field(	ino_t,	parent			)
 		__field(	int,	datasync		)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= dentry->d_inode->i_sb->s_dev;
+		struct dentry *dentry = file->f_path.dentry;
+
+		__entry->dev_major	= MAJOR(dentry->d_inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(dentry->d_inode->i_sb->s_dev);
 		__entry->ino		= dentry->d_inode->i_ino;
 		__entry->datasync	= datasync;
 		__entry->parent		= dentry->d_parent->d_inode->i_ino;
 	),
 
-	TP_printk("dev %s ino %ld parent %ld datasync %d ",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->parent,
-		  __entry->datasync)
+	TP_printk("dev %d,%d ino %ld parent %ld datasync %d ",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  (unsigned long) __entry->parent, __entry->datasync)
 );
 
 TRACE_EVENT(ext4_sync_fs,
@@ -699,18 +782,388 @@ TRACE_EVENT(ext4_sync_fs,
 	TP_ARGS(sb, wait),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	int,	wait			)
 
 	),
 
 	TP_fast_assign(
-		__entry->dev	= sb->s_dev;
+		__entry->dev_major = MAJOR(sb->s_dev);
+		__entry->dev_minor = MINOR(sb->s_dev);
 		__entry->wait	= wait;
 	),
 
-	TP_printk("dev %s wait %d", jbd2_dev_to_name(__entry->dev),
-		  __entry->wait)
+	TP_printk("dev %d,%d wait %d", __entry->dev_major,
+		  __entry->dev_minor, __entry->wait)
+);
+
+TRACE_EVENT(ext4_alloc_da_blocks,
+	TP_PROTO(struct inode *inode),
+
+	TP_ARGS(inode),
+
+	TP_STRUCT__entry(
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
+		__field( unsigned int,	data_blocks	)
+		__field( unsigned int,	meta_blocks	)
+	),
+
+	TP_fast_assign(
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
+		__entry->ino	= inode->i_ino;
+		__entry->data_blocks = EXT4_I(inode)->i_reserved_data_blocks;
+		__entry->meta_blocks = EXT4_I(inode)->i_reserved_meta_blocks;
+	),
+
+	TP_printk("dev %d,%d ino %lu data_blocks %u meta_blocks %u",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->data_blocks, __entry->meta_blocks)
+);
+
+TRACE_EVENT(ext4_mballoc_alloc,
+	TP_PROTO(struct ext4_allocation_context *ac),
+
+	TP_ARGS(ac),
+
+	TP_STRUCT__entry(
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
+		__field(	__u16,	found			)
+		__field(	__u16,	groups			)
+		__field(	__u16,	buddy			)
+		__field(	__u16,	flags			)
+		__field(	__u16,	tail			)
+		__field(	__u8,	cr			)
+		__field(	__u32, 	orig_logical		)
+		__field(	  int,	orig_start		)
+		__field(	__u32, 	orig_group		)
+		__field(	  int,	orig_len		)
+		__field(	__u32, 	goal_logical		)
+		__field(	  int,	goal_start		)
+		__field(	__u32, 	goal_group		)
+		__field(	  int,	goal_len		)
+		__field(	__u32, 	result_logical		)
+		__field(	  int,	result_start		)
+		__field(	__u32, 	result_group		)
+		__field(	  int,	result_len		)
+	),
+
+	TP_fast_assign(
+		__entry->dev_major	= MAJOR(ac->ac_inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(ac->ac_inode->i_sb->s_dev);
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->found		= ac->ac_found;
+		__entry->flags		= ac->ac_flags;
+		__entry->groups		= ac->ac_groups_scanned;
+		__entry->buddy		= ac->ac_buddy;
+		__entry->tail		= ac->ac_tail;
+		__entry->cr		= ac->ac_criteria;
+		__entry->orig_logical	= ac->ac_o_ex.fe_logical;
+		__entry->orig_start	= ac->ac_o_ex.fe_start;
+		__entry->orig_group	= ac->ac_o_ex.fe_group;
+		__entry->orig_len	= ac->ac_o_ex.fe_len;
+		__entry->goal_logical	= ac->ac_g_ex.fe_logical;
+		__entry->goal_start	= ac->ac_g_ex.fe_start;
+		__entry->goal_group	= ac->ac_g_ex.fe_group;
+		__entry->goal_len	= ac->ac_g_ex.fe_len;
+		__entry->result_logical	= ac->ac_f_ex.fe_logical;
+		__entry->result_start	= ac->ac_f_ex.fe_start;
+		__entry->result_group	= ac->ac_f_ex.fe_group;
+		__entry->result_len	= ac->ac_f_ex.fe_len;
+	),
+
+	TP_printk("dev %d,%d inode %lu orig %u/%d/%u@%u goal %u/%d/%u@%u "
+		  "result %u/%d/%u@%u blks %u grps %u cr %u flags 0x%04x "
+		  "tail %u broken %u",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->orig_group, __entry->orig_start,
+		  __entry->orig_len, __entry->orig_logical,
+		  __entry->goal_group, __entry->goal_start,
+		  __entry->goal_len, __entry->goal_logical,
+		  __entry->result_group, __entry->result_start,
+		  __entry->result_len, __entry->result_logical,
+		  __entry->found, __entry->groups, __entry->cr,
+		  __entry->flags, __entry->tail,
+		  __entry->buddy ? 1 << __entry->buddy : 0)
+);
+
+TRACE_EVENT(ext4_mballoc_prealloc,
+	TP_PROTO(struct ext4_allocation_context *ac),
+
+	TP_ARGS(ac),
+
+	TP_STRUCT__entry(
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
+		__field(	__u32, 	orig_logical		)
+		__field(	  int,	orig_start		)
+		__field(	__u32, 	orig_group		)
+		__field(	  int,	orig_len		)
+		__field(	__u32, 	result_logical		)
+		__field(	  int,	result_start		)
+		__field(	__u32, 	result_group		)
+		__field(	  int,	result_len		)
+	),
+
+	TP_fast_assign(
+		__entry->dev_major	= MAJOR(ac->ac_inode->i_sb->s_dev);
+		__entry->dev_minor	= MINOR(ac->ac_inode->i_sb->s_dev);
+		__entry->ino		= ac->ac_inode->i_ino;
+		__entry->orig_logical	= ac->ac_o_ex.fe_logical;
+		__entry->orig_start	= ac->ac_o_ex.fe_start;
+		__entry->orig_group	= ac->ac_o_ex.fe_group;
+		__entry->orig_len	= ac->ac_o_ex.fe_len;
+		__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_printk("dev %d,%d inode %lu orig %u/%d/%u@%u result %u/%d/%u@%u",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->orig_group, __entry->orig_start,
+		  __entry->orig_len, __entry->orig_logical,
+		  __entry->result_group, __entry->result_start,
+		  __entry->result_len, __entry->result_logical)
+);
+
+DECLARE_EVENT_CLASS(ext4__mballoc,
+	TP_PROTO(struct super_block *sb,
+		 struct inode *inode,
+		 ext4_group_t group,
+		 ext4_grpblk_t start,
+		 ext4_grpblk_t len),
+
+	TP_ARGS(sb, inode, group, start, len),
+
+	TP_STRUCT__entry(
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
+		__field(	  int,	result_start		)
+		__field(	__u32, 	result_group		)
+		__field(	  int,	result_len		)
+	),
+
+	TP_fast_assign(
+		__entry->dev_major	= MAJOR(sb->s_dev);
+		__entry->dev_minor	= MINOR(sb->s_dev);
+		__entry->ino		= inode ? inode->i_ino : 0;
+		__entry->result_start	= start;
+		__entry->result_group	= group;
+		__entry->result_len	= len;
+	),
+
+	TP_printk("dev %d,%d inode %lu extent %u/%d/%u ",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino,
+		  __entry->result_group, __entry->result_start,
+		  __entry->result_len)
+);
+
+DEFINE_EVENT(ext4__mballoc, ext4_mballoc_discard,
+
+	TP_PROTO(struct super_block *sb,
+		 struct inode *inode,
+		 ext4_group_t group,
+		 ext4_grpblk_t start,
+		 ext4_grpblk_t len),
+
+	TP_ARGS(sb, inode, group, start, len)
+);
+
+DEFINE_EVENT(ext4__mballoc, ext4_mballoc_free,
+
+	TP_PROTO(struct super_block *sb,
+		 struct inode *inode,
+		 ext4_group_t group,
+		 ext4_grpblk_t start,
+		 ext4_grpblk_t len),
+
+	TP_ARGS(sb, inode, group, start, len)
+);
+
+TRACE_EVENT(ext4_forget,
+	TP_PROTO(struct inode *inode, int is_metadata, __u64 block),
+
+	TP_ARGS(inode, is_metadata, block),
+
+	TP_STRUCT__entry(
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
+		__field(	umode_t, mode			)
+		__field(	int,	is_metadata		)
+		__field(	__u64,	block			)
+	),
+
+	TP_fast_assign(
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
+		__entry->ino	= inode->i_ino;
+		__entry->mode	= inode->i_mode;
+		__entry->is_metadata = is_metadata;
+		__entry->block	= block;
+	),
+
+	TP_printk("dev %d,%d ino %lu mode 0%o is_metadata %d block %llu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino, __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(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__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_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(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 %d,%d ino %lu mode 0%o i_blocks %llu used_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  (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(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__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_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(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 %d,%d ino %lu mode 0%o i_blocks %llu md_needed %d reserved_data_blocks %d reserved_meta_blocks %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  (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(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__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_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(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 %d,%d ino %lu mode 0%o i_blocks %llu freed_blocks %d reserved_data_blocks %d reserved_meta_blocks %d allocated_meta_blocks %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  (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(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	__u32,	group			)
+
+	),
+
+	TP_fast_assign(
+		__entry->dev_major = MAJOR(sb->s_dev);
+		__entry->dev_minor = MINOR(sb->s_dev);
+		__entry->group	= group;
+	),
+
+	TP_printk("dev %d,%d group %u",
+		  __entry->dev_major, __entry->dev_minor, __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 */
diff --git a/include/trace/events/gfpflags.h b/include/trace/events/gfpflags.h
new file mode 100644
index 000000000000..e3615c093741
--- /dev/null
+++ b/include/trace/events/gfpflags.h
@@ -0,0 +1,37 @@
+/*
+ * 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"
+
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index b0c7ede55eb1..1c09820df585 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -1,23 +1,26 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
 #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
+struct irqaction;
+struct softirq_action;
 
 #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),	\
+#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(BLOCK_IOPOLL),	\
+			 softirq_name(TASKLET),		\
+			 softirq_name(SCHED),		\
+			 softirq_name(HRTIMER),		\
 			 softirq_name(RCU))
 
 /**
@@ -47,7 +50,7 @@ TRACE_EVENT(irq_handler_entry,
 		__assign_str(name, action->name);
 	),
 
-	TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name))
+	TP_printk("irq=%d name=%s", __entry->irq, __get_str(name))
 );
 
 /**
@@ -77,66 +80,68 @@ TRACE_EVENT(irq_handler_exit,
 		__entry->ret	= ret;
 	),
 
-	TP_printk("irq=%d return=%s",
+	TP_printk("irq=%d ret=%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,
+DECLARE_EVENT_CLASS(softirq,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec),
+	TP_ARGS(vec_nr),
 
 	TP_STRUCT__entry(
-		__field(	int,	vec			)
+		__field(	unsigned int,	vec	)
 	),
 
 	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
+		__entry->vec = vec_nr;
 	),
 
-	TP_printk("softirq=%d action=%s", __entry->vec,
+	TP_printk("vec=%u [action=%s]", __entry->vec,
 		  show_softirq_name(__entry->vec))
 );
 
 /**
+ * softirq_entry - called immediately before the softirq handler
+ * @vec_nr:  softirq vector number
+ *
+ * When used in combination with the softirq_exit tracepoint
+ * we can determine the softirq handler runtine.
+ */
+DEFINE_EVENT(softirq, softirq_entry,
+
+	TP_PROTO(unsigned int vec_nr),
+
+	TP_ARGS(vec_nr)
+);
+
+/**
  * 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
+ * @vec_nr:  softirq vector number
  *
- * 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.
+ * When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq handler runtine.
  */
-TRACE_EVENT(softirq_exit,
+DEFINE_EVENT(softirq, softirq_exit,
 
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_ARGS(h, vec),
+	TP_ARGS(vec_nr)
+);
 
-	TP_STRUCT__entry(
-		__field(	int,	vec			)
-	),
+/**
+ * softirq_raise - called immediately when a softirq is raised
+ * @vec_nr:  softirq vector number
+ *
+ * When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq raise to run latency.
+ */
+DEFINE_EVENT(softirq, softirq_raise,
 
-	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
-	),
+	TP_PROTO(unsigned int vec_nr),
 
-	TP_printk("softirq=%d action=%s", __entry->vec,
-		  show_softirq_name(__entry->vec))
+	TP_ARGS(vec_nr)
 );
 
 #endif /*  _TRACE_IRQ_H */
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 845b0b4b48fd..7447ea9305b5 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -1,11 +1,14 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM jbd2
+
 #if !defined(_TRACE_JBD2_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_JBD2_H
 
 #include <linux/jbd2.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM jbd2
+struct transaction_chp_stats_s;
+struct transaction_run_stats_s;
 
 TRACE_EVENT(jbd2_checkpoint,
 
@@ -14,152 +17,230 @@ TRACE_EVENT(jbd2_checkpoint,
 	TP_ARGS(journal, result),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,	dev_major		)
+		__field(	int,	dev_minor		)
 		__field(	int,	result			)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
+		__entry->dev_minor	= MINOR(journal->j_fs_dev->bd_dev);
 		__entry->result		= result;
 	),
 
-	TP_printk("dev %s result %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->result)
+	TP_printk("dev %d,%d result %d",
+		  __entry->dev_major, __entry->dev_minor, __entry->result)
 );
 
-TRACE_EVENT(jbd2_start_commit,
+DECLARE_EVENT_CLASS(jbd2_commit,
 
 	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
 	TP_ARGS(journal, commit_transaction),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	char,	sync_commit		  )
 		__field(	int,	transaction		  )
 	),
 
 	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
+		__entry->dev_minor	= MINOR(journal->j_fs_dev->bd_dev);
 		__entry->sync_commit = commit_transaction->t_synchronous_commit;
 		__entry->transaction	= commit_transaction->t_tid;
 	),
 
-	TP_printk("dev %s transaction %d sync %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit)
+	TP_printk("dev %d,%d transaction %d sync %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  __entry->transaction, __entry->sync_commit)
+);
+
+DEFINE_EVENT(jbd2_commit, jbd2_start_commit,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction)
+);
+
+DEFINE_EVENT(jbd2_commit, jbd2_commit_locking,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction)
 );
 
-TRACE_EVENT(jbd2_commit_locking,
+DEFINE_EVENT(jbd2_commit, jbd2_commit_flushing,
 
 	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
 
+	TP_ARGS(journal, commit_transaction)
+);
+
+DEFINE_EVENT(jbd2_commit, jbd2_commit_logging,
+
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
+	TP_ARGS(journal, commit_transaction)
+);
+
+TRACE_EVENT(jbd2_end_commit,
+	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+
 	TP_ARGS(journal, commit_transaction),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
 		__field(	char,	sync_commit		  )
 		__field(	int,	transaction		  )
+		__field(	int,	head		  	  )
 	),
 
 	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
+		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
+		__entry->dev_minor	= MINOR(journal->j_fs_dev->bd_dev);
 		__entry->sync_commit = commit_transaction->t_synchronous_commit;
 		__entry->transaction	= commit_transaction->t_tid;
+		__entry->head		= journal->j_tail_sequence;
 	),
 
-	TP_printk("dev %s transaction %d sync %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit)
+	TP_printk("dev %d,%d transaction %d sync %d head %d",
+		  __entry->dev_major, __entry->dev_minor,
+		  __entry->transaction, __entry->sync_commit, __entry->head)
 );
 
-TRACE_EVENT(jbd2_commit_flushing,
-
-	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+TRACE_EVENT(jbd2_submit_inode_data,
+	TP_PROTO(struct inode *inode),
 
-	TP_ARGS(journal, commit_transaction),
+	TP_ARGS(inode),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	char,	sync_commit		  )
-		__field(	int,	transaction		  )
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	ino_t,	ino			)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->sync_commit = commit_transaction->t_synchronous_commit;
-		__entry->transaction	= commit_transaction->t_tid;
+		__entry->dev_major = MAJOR(inode->i_sb->s_dev);
+		__entry->dev_minor = MINOR(inode->i_sb->s_dev);
+		__entry->ino	= inode->i_ino;
 	),
 
-	TP_printk("dev %s transaction %d sync %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit)
+	TP_printk("dev %d,%d ino %lu",
+		  __entry->dev_major, __entry->dev_minor,
+		  (unsigned long) __entry->ino)
 );
 
-TRACE_EVENT(jbd2_commit_logging,
+TRACE_EVENT(jbd2_run_stats,
+	TP_PROTO(dev_t dev, unsigned long tid,
+		 struct transaction_run_stats_s *stats),
 
-	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
-
-	TP_ARGS(journal, commit_transaction),
+	TP_ARGS(dev, tid, stats),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	char,	sync_commit		  )
-		__field(	int,	transaction		  )
+		__field(		  int,	dev_major	)
+		__field(		  int,	dev_minor	)
+		__field(	unsigned long,	tid		)
+		__field(	unsigned long,	wait		)
+		__field(	unsigned long,	running		)
+		__field(	unsigned long,	locked		)
+		__field(	unsigned long,	flushing	)
+		__field(	unsigned long,	logging		)
+		__field(		__u32,	handle_count	)
+		__field(		__u32,	blocks		)
+		__field(		__u32,	blocks_logged	)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->sync_commit = commit_transaction->t_synchronous_commit;
-		__entry->transaction	= commit_transaction->t_tid;
+		__entry->dev_major	= MAJOR(dev);
+		__entry->dev_minor	= MINOR(dev);
+		__entry->tid		= tid;
+		__entry->wait		= stats->rs_wait;
+		__entry->running	= stats->rs_running;
+		__entry->locked		= stats->rs_locked;
+		__entry->flushing	= stats->rs_flushing;
+		__entry->logging	= stats->rs_logging;
+		__entry->handle_count	= stats->rs_handle_count;
+		__entry->blocks		= stats->rs_blocks;
+		__entry->blocks_logged	= stats->rs_blocks_logged;
 	),
 
-	TP_printk("dev %s transaction %d sync %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit)
+	TP_printk("dev %d,%d tid %lu wait %u running %u locked %u flushing %u "
+		  "logging %u handle_count %u blocks %u blocks_logged %u",
+		  __entry->dev_major, __entry->dev_minor, __entry->tid,
+		  jiffies_to_msecs(__entry->wait),
+		  jiffies_to_msecs(__entry->running),
+		  jiffies_to_msecs(__entry->locked),
+		  jiffies_to_msecs(__entry->flushing),
+		  jiffies_to_msecs(__entry->logging),
+		  __entry->handle_count, __entry->blocks,
+		  __entry->blocks_logged)
 );
 
-TRACE_EVENT(jbd2_end_commit,
-	TP_PROTO(journal_t *journal, transaction_t *commit_transaction),
+TRACE_EVENT(jbd2_checkpoint_stats,
+	TP_PROTO(dev_t dev, unsigned long tid,
+		 struct transaction_chp_stats_s *stats),
 
-	TP_ARGS(journal, commit_transaction),
+	TP_ARGS(dev, tid, stats),
 
 	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	char,	sync_commit		  )
-		__field(	int,	transaction		  )
-		__field(	int,	head		  	  )
+		__field(		  int,	dev_major	)
+		__field(		  int,	dev_minor	)
+		__field(	unsigned long,	tid		)
+		__field(	unsigned long,	chp_time	)
+		__field(		__u32,	forced_to_close	)
+		__field(		__u32,	written		)
+		__field(		__u32,	dropped		)
 	),
 
 	TP_fast_assign(
-		__entry->dev		= journal->j_fs_dev->bd_dev;
-		__entry->sync_commit = commit_transaction->t_synchronous_commit;
-		__entry->transaction	= commit_transaction->t_tid;
-		__entry->head		= journal->j_tail_sequence;
+		__entry->dev_major	= MAJOR(dev);
+		__entry->dev_minor	= MINOR(dev);
+		__entry->tid		= tid;
+		__entry->chp_time	= stats->cs_chp_time;
+		__entry->forced_to_close= stats->cs_forced_to_close;
+		__entry->written	= stats->cs_written;
+		__entry->dropped	= stats->cs_dropped;
 	),
 
-	TP_printk("dev %s transaction %d sync %d head %d",
-		  jbd2_dev_to_name(__entry->dev), __entry->transaction,
-		  __entry->sync_commit, __entry->head)
+	TP_printk("dev %d,%d tid %lu chp_time %u forced_to_close %u "
+		  "written %u dropped %u",
+		  __entry->dev_major, __entry->dev_minor, __entry->tid,
+		  jiffies_to_msecs(__entry->chp_time),
+		  __entry->forced_to_close, __entry->written, __entry->dropped)
 );
 
-TRACE_EVENT(jbd2_submit_inode_data,
-	TP_PROTO(struct inode *inode),
+TRACE_EVENT(jbd2_cleanup_journal_tail,
 
-	TP_ARGS(inode),
+	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(	ino_t,	ino			)
+		__field(	int,   dev_major                )
+		__field(	int,   dev_minor                )
+		__field(	tid_t,	tail_sequence		)
+		__field(	tid_t,	first_tid		)
+		__field(unsigned long,	block_nr		)
+		__field(unsigned long,	freed			)
 	),
 
 	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
+		__entry->dev_major	= MAJOR(journal->j_fs_dev->bd_dev);
+		__entry->dev_minor	= MINOR(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 ino %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino)
+	TP_printk("dev %d,%d from %u to %u offset %lu freed %lu",
+		  __entry->dev_major, __entry->dev_minor,
+		  __entry->tail_sequence, __entry->first_tid,
+		  __entry->block_nr, __entry->freed)
 );
 
 #endif /* _TRACE_JBD2_H */
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 9baba50d6512..a9c87ad8331c 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -1,50 +1,14 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kmem
+
 #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_KMEM_H
 
 #include <linux/types.h>
 #include <linux/tracepoint.h>
+#include "gfpflags.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,
+DECLARE_EVENT_CLASS(kmem_alloc,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
@@ -78,41 +42,23 @@ TRACE_EVENT(kmalloc,
 		show_gfp_flags(__entry->gfp_flags))
 );
 
-TRACE_EVENT(kmem_cache_alloc,
+DEFINE_EVENT(kmem_alloc, kmalloc,
 
-	TP_PROTO(unsigned long call_site,
-		 const void *ptr,
-		 size_t bytes_req,
-		 size_t bytes_alloc,
-		 gfp_t gfp_flags),
+	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_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	)
-	),
+DEFINE_EVENT(kmem_alloc, kmem_cache_alloc,
 
-	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_PROTO(unsigned long call_site, const void *ptr,
+		 size_t bytes_req, size_t bytes_alloc, gfp_t 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))
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags)
 );
 
-TRACE_EVENT(kmalloc_node,
+DECLARE_EVENT_CLASS(kmem_alloc_node,
 
 	TP_PROTO(unsigned long call_site,
 		 const void *ptr,
@@ -150,81 +96,212 @@ TRACE_EVENT(kmalloc_node,
 		__entry->node)
 );
 
-TRACE_EVENT(kmem_cache_alloc_node,
+DEFINE_EVENT(kmem_alloc_node, 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_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_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node)
+);
+
+DEFINE_EVENT(kmem_alloc_node, 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_EVENT_CLASS(kmem_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		)
-		__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)
+	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
 );
 
-TRACE_EVENT(kfree,
+DEFINE_EVENT(kmem_free, kfree,
 
 	TP_PROTO(unsigned long call_site, const void *ptr),
 
-	TP_ARGS(call_site, ptr),
+	TP_ARGS(call_site, ptr)
+);
+
+DEFINE_EVENT(kmem_free, kmem_cache_free,
+
+	TP_PROTO(unsigned long call_site, const void *ptr),
+
+	TP_ARGS(call_site, ptr)
+);
+
+TRACE_EVENT(mm_page_free_direct,
+
+	TP_PROTO(struct page *page, unsigned int order),
+
+	TP_ARGS(page, order),
 
 	TP_STRUCT__entry(
-		__field(	unsigned long,	call_site	)
-		__field(	const void *,	ptr		)
+		__field(	struct page *,	page		)
+		__field(	unsigned int,	order		)
 	),
 
 	TP_fast_assign(
-		__entry->call_site	= call_site;
-		__entry->ptr		= ptr;
+		__entry->page		= page;
+		__entry->order		= order;
 	),
 
-	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+	TP_printk("page=%p pfn=%lu order=%d",
+			__entry->page,
+			page_to_pfn(__entry->page),
+			__entry->order)
 );
 
-TRACE_EVENT(kmem_cache_free,
+TRACE_EVENT(mm_pagevec_free,
 
-	TP_PROTO(unsigned long call_site, const void *ptr),
+	TP_PROTO(struct page *page, int cold),
 
-	TP_ARGS(call_site, ptr),
+	TP_ARGS(page, cold),
 
 	TP_STRUCT__entry(
-		__field(	unsigned long,	call_site	)
-		__field(	const void *,	ptr		)
+		__field(	struct page *,	page		)
+		__field(	int,		cold		)
 	),
 
 	TP_fast_assign(
-		__entry->call_site	= call_site;
-		__entry->ptr		= ptr;
+		__entry->page		= page;
+		__entry->cold		= cold;
 	),
 
-	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+	TP_printk("page=%p pfn=%lu order=0 cold=%d",
+			__entry->page,
+			page_to_pfn(__entry->page),
+			__entry->cold)
 );
+
+TRACE_EVENT(mm_page_alloc,
+
+	TP_PROTO(struct page *page, unsigned int order,
+			gfp_t gfp_flags, int migratetype),
+
+	TP_ARGS(page, order, gfp_flags, migratetype),
+
+	TP_STRUCT__entry(
+		__field(	struct page *,	page		)
+		__field(	unsigned int,	order		)
+		__field(	gfp_t,		gfp_flags	)
+		__field(	int,		migratetype	)
+	),
+
+	TP_fast_assign(
+		__entry->page		= page;
+		__entry->order		= order;
+		__entry->gfp_flags	= gfp_flags;
+		__entry->migratetype	= migratetype;
+	),
+
+	TP_printk("page=%p pfn=%lu order=%d migratetype=%d gfp_flags=%s",
+		__entry->page,
+		page_to_pfn(__entry->page),
+		__entry->order,
+		__entry->migratetype,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+DECLARE_EVENT_CLASS(mm_page,
+
+	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+
+	TP_ARGS(page, order, migratetype),
+
+	TP_STRUCT__entry(
+		__field(	struct page *,	page		)
+		__field(	unsigned int,	order		)
+		__field(	int,		migratetype	)
+	),
+
+	TP_fast_assign(
+		__entry->page		= page;
+		__entry->order		= order;
+		__entry->migratetype	= migratetype;
+	),
+
+	TP_printk("page=%p pfn=%lu order=%u migratetype=%d percpu_refill=%d",
+		__entry->page,
+		page_to_pfn(__entry->page),
+		__entry->order,
+		__entry->migratetype,
+		__entry->order == 0)
+);
+
+DEFINE_EVENT(mm_page, mm_page_alloc_zone_locked,
+
+	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+
+	TP_ARGS(page, order, migratetype)
+);
+
+DEFINE_EVENT_PRINT(mm_page, mm_page_pcpu_drain,
+
+	TP_PROTO(struct page *page, unsigned int order, int migratetype),
+
+	TP_ARGS(page, order, migratetype),
+
+	TP_printk("page=%p pfn=%lu order=%d migratetype=%d",
+		__entry->page, page_to_pfn(__entry->page),
+		__entry->order, __entry->migratetype)
+);
+
+TRACE_EVENT(mm_page_alloc_extfrag,
+
+	TP_PROTO(struct page *page,
+			int alloc_order, int fallback_order,
+			int alloc_migratetype, int fallback_migratetype),
+
+	TP_ARGS(page,
+		alloc_order, fallback_order,
+		alloc_migratetype, fallback_migratetype),
+
+	TP_STRUCT__entry(
+		__field(	struct page *,	page			)
+		__field(	int,		alloc_order		)
+		__field(	int,		fallback_order		)
+		__field(	int,		alloc_migratetype	)
+		__field(	int,		fallback_migratetype	)
+	),
+
+	TP_fast_assign(
+		__entry->page			= page;
+		__entry->alloc_order		= alloc_order;
+		__entry->fallback_order		= fallback_order;
+		__entry->alloc_migratetype	= alloc_migratetype;
+		__entry->fallback_migratetype	= fallback_migratetype;
+	),
+
+	TP_printk("page=%p pfn=%lu alloc_order=%d fallback_order=%d pageblock_order=%d alloc_migratetype=%d fallback_migratetype=%d fragmenting=%d change_ownership=%d",
+		__entry->page,
+		page_to_pfn(__entry->page),
+		__entry->alloc_order,
+		__entry->fallback_order,
+		pageblock_order,
+		__entry->alloc_migratetype,
+		__entry->fallback_migratetype,
+		__entry->fallback_order < pageblock_order,
+		__entry->alloc_migratetype == __entry->fallback_migratetype)
+);
+
 #endif /* _TRACE_KMEM_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
new file mode 100644
index 000000000000..6dd3a51ab1cb
--- /dev/null
+++ b/include/trace/events/kvm.h
@@ -0,0 +1,191 @@
+#if !defined(_TRACE_KVM_MAIN_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KVM_MAIN_H
+
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kvm
+
+#if defined(__KVM_HAVE_IOAPIC)
+TRACE_EVENT(kvm_set_irq,
+	TP_PROTO(unsigned int gsi, int level, int irq_source_id),
+	TP_ARGS(gsi, level, irq_source_id),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	gsi		)
+		__field(	int,		level		)
+		__field(	int,		irq_source_id	)
+	),
+
+	TP_fast_assign(
+		__entry->gsi		= gsi;
+		__entry->level		= level;
+		__entry->irq_source_id	= irq_source_id;
+	),
+
+	TP_printk("gsi %u level %d source %d",
+		  __entry->gsi, __entry->level, __entry->irq_source_id)
+);
+
+#define kvm_deliver_mode		\
+	{0x0, "Fixed"},			\
+	{0x1, "LowPrio"},		\
+	{0x2, "SMI"},			\
+	{0x3, "Res3"},			\
+	{0x4, "NMI"},			\
+	{0x5, "INIT"},			\
+	{0x6, "SIPI"},			\
+	{0x7, "ExtINT"}
+
+TRACE_EVENT(kvm_ioapic_set_irq,
+	    TP_PROTO(__u64 e, int pin, bool coalesced),
+	    TP_ARGS(e, pin, coalesced),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		e		)
+		__field(	int,		pin		)
+		__field(	bool,		coalesced	)
+	),
+
+	TP_fast_assign(
+		__entry->e		= e;
+		__entry->pin		= pin;
+		__entry->coalesced	= coalesced;
+	),
+
+	TP_printk("pin %u dst %x vec=%u (%s|%s|%s%s)%s",
+		  __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e,
+		  __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
+		  (__entry->e & (1<<11)) ? "logical" : "physical",
+		  (__entry->e & (1<<15)) ? "level" : "edge",
+		  (__entry->e & (1<<16)) ? "|masked" : "",
+		  __entry->coalesced ? " (coalesced)" : "")
+);
+
+TRACE_EVENT(kvm_msi_set_irq,
+	    TP_PROTO(__u64 address, __u64 data),
+	    TP_ARGS(address, data),
+
+	TP_STRUCT__entry(
+		__field(	__u64,		address		)
+		__field(	__u64,		data		)
+	),
+
+	TP_fast_assign(
+		__entry->address	= address;
+		__entry->data		= data;
+	),
+
+	TP_printk("dst %u vec %x (%s|%s|%s%s)",
+		  (u8)(__entry->address >> 12), (u8)__entry->data,
+		  __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
+		  (__entry->address & (1<<2)) ? "logical" : "physical",
+		  (__entry->data & (1<<15)) ? "level" : "edge",
+		  (__entry->address & (1<<3)) ? "|rh" : "")
+);
+
+#define kvm_irqchips						\
+	{KVM_IRQCHIP_PIC_MASTER,	"PIC master"},		\
+	{KVM_IRQCHIP_PIC_SLAVE,		"PIC slave"},		\
+	{KVM_IRQCHIP_IOAPIC,		"IOAPIC"}
+
+TRACE_EVENT(kvm_ack_irq,
+	TP_PROTO(unsigned int irqchip, unsigned int pin),
+	TP_ARGS(irqchip, pin),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	irqchip		)
+		__field(	unsigned int,	pin		)
+	),
+
+	TP_fast_assign(
+		__entry->irqchip	= irqchip;
+		__entry->pin		= pin;
+	),
+
+	TP_printk("irqchip %s pin %u",
+		  __print_symbolic(__entry->irqchip, kvm_irqchips),
+		 __entry->pin)
+);
+
+
+
+#endif /* defined(__KVM_HAVE_IOAPIC) */
+
+#define KVM_TRACE_MMIO_READ_UNSATISFIED 0
+#define KVM_TRACE_MMIO_READ 1
+#define KVM_TRACE_MMIO_WRITE 2
+
+#define kvm_trace_symbol_mmio \
+	{ KVM_TRACE_MMIO_READ_UNSATISFIED, "unsatisfied-read" }, \
+	{ KVM_TRACE_MMIO_READ, "read" }, \
+	{ KVM_TRACE_MMIO_WRITE, "write" }
+
+TRACE_EVENT(kvm_mmio,
+	TP_PROTO(int type, int len, u64 gpa, u64 val),
+	TP_ARGS(type, len, gpa, val),
+
+	TP_STRUCT__entry(
+		__field(	u32,	type		)
+		__field(	u32,	len		)
+		__field(	u64,	gpa		)
+		__field(	u64,	val		)
+	),
+
+	TP_fast_assign(
+		__entry->type		= type;
+		__entry->len		= len;
+		__entry->gpa		= gpa;
+		__entry->val		= val;
+	),
+
+	TP_printk("mmio %s len %u gpa 0x%llx val 0x%llx",
+		  __print_symbolic(__entry->type, kvm_trace_symbol_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 */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
new file mode 100644
index 000000000000..2821b86de63b
--- /dev/null
+++ b/include/trace/events/lock.h
@@ -0,0 +1,86 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lock
+
+#if !defined(_TRACE_LOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCK_H
+
+#include <linux/lockdep.h>
+#include <linux/tracepoint.h>
+
+#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)
+		__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("%p %s%s%s", __entry->lockdep_addr,
+		  (__entry->flags & 1) ? "try " : "",
+		  (__entry->flags & 2) ? "read " : "",
+		  __get_str(name))
+);
+
+DECLARE_EVENT_CLASS(lock,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip),
+
+	TP_STRUCT__entry(
+		__string(	name, 	lock->name	)
+		__field(	void *, lockdep_addr	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
+	),
+
+	TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
+);
+
+DEFINE_EVENT(lock, lock_release,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+DEFINE_EVENT(lock, lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+DEFINE_EVENT(lock, lock_acquired,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip)
+);
+
+#endif
+#endif
+
+#endif /* _TRACE_LOCK_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
deleted file mode 100644
index 0e956c9dfd7e..000000000000
--- a/include/trace/events/lockdep.h
+++ /dev/null
@@ -1,96 +0,0 @@
-#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/events/mce.h b/include/trace/events/mce.h
new file mode 100644
index 000000000000..7eee77895cb3
--- /dev/null
+++ b/include/trace/events/mce.h
@@ -0,0 +1,69 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM mce
+
+#if !defined(_TRACE_MCE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MCE_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+#include <asm/mce.h>
+
+TRACE_EVENT(mce_record,
+
+	TP_PROTO(struct mce *m),
+
+	TP_ARGS(m),
+
+	TP_STRUCT__entry(
+		__field(	u64,		mcgcap		)
+		__field(	u64,		mcgstatus	)
+		__field(	u8,		bank		)
+		__field(	u64,		status		)
+		__field(	u64,		addr		)
+		__field(	u64,		misc		)
+		__field(	u64,		ip		)
+		__field(	u8,		cs		)
+		__field(	u64,		tsc		)
+		__field(	u64,		walltime	)
+		__field(	u32,		cpu		)
+		__field(	u32,		cpuid		)
+		__field(	u32,		apicid		)
+		__field(	u32,		socketid	)
+		__field(	u8,		cpuvendor	)
+	),
+
+	TP_fast_assign(
+		__entry->mcgcap		= m->mcgcap;
+		__entry->mcgstatus	= m->mcgstatus;
+		__entry->bank		= m->bank;
+		__entry->status		= m->status;
+		__entry->addr		= m->addr;
+		__entry->misc		= m->misc;
+		__entry->ip		= m->ip;
+		__entry->cs		= m->cs;
+		__entry->tsc		= m->tsc;
+		__entry->walltime	= m->time;
+		__entry->cpu		= m->extcpu;
+		__entry->cpuid		= m->cpuid;
+		__entry->apicid		= m->apicid;
+		__entry->socketid	= m->socketid;
+		__entry->cpuvendor	= m->cpuvendor;
+	),
+
+	TP_printk("CPU: %d, MCGc/s: %llx/%llx, MC%d: %016Lx, ADDR/MISC: %016Lx/%016Lx, RIP: %02x:<%016Lx>, TSC: %llx, PROCESSOR: %u:%x, TIME: %llu, SOCKET: %u, APIC: %x",
+		__entry->cpu,
+		__entry->mcgcap, __entry->mcgstatus,
+		__entry->bank, __entry->status,
+		__entry->addr, __entry->misc,
+		__entry->cs, __entry->ip,
+		__entry->tsc,
+		__entry->cpuvendor, __entry->cpuid,
+		__entry->walltime,
+		__entry->socketid,
+		__entry->apicid)
+);
+
+#endif /* _TRACE_MCE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
new file mode 100644
index 000000000000..c7bb2f0482fe
--- /dev/null
+++ b/include/trace/events/module.h
@@ -0,0 +1,122 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM module
+
+#if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MODULE_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_MODULES
+
+struct module;
+
+#define show_module_flags(flags) __print_flags(flags, "",	\
+	{ (1UL << TAINT_PROPRIETARY_MODULE),	"P" },		\
+	{ (1UL << TAINT_FORCED_MODULE),		"F" },		\
+	{ (1UL << TAINT_CRAP),			"C" })
+
+TRACE_EVENT(module_load,
+
+	TP_PROTO(struct module *mod),
+
+	TP_ARGS(mod),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	taints		)
+		__string(	name,		mod->name	)
+	),
+
+	TP_fast_assign(
+		__entry->taints = mod->taints;
+		__assign_str(name, mod->name);
+	),
+
+	TP_printk("%s %s", __get_str(name), show_module_flags(__entry->taints))
+);
+
+TRACE_EVENT(module_free,
+
+	TP_PROTO(struct module *mod),
+
+	TP_ARGS(mod),
+
+	TP_STRUCT__entry(
+		__string(	name,		mod->name	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, mod->name);
+	),
+
+	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),
+
+	TP_ARGS(mod, ip),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	ip		)
+		__field(	int,		refcnt		)
+		__string(	name,		mod->name	)
+	),
+
+	TP_fast_assign(
+		__entry->ip	= ip;
+		__entry->refcnt	= __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
+		__assign_str(name, mod->name);
+	),
+
+	TP_printk("%s call_site=%pf refcnt=%d",
+		  __get_str(name), (void *)__entry->ip, __entry->refcnt)
+);
+
+DEFINE_EVENT(module_refcnt, module_get,
+
+	TP_PROTO(struct module *mod, unsigned long ip),
+
+	TP_ARGS(mod, ip)
+);
+
+DEFINE_EVENT(module_refcnt, module_put,
+
+	TP_PROTO(struct module *mod, unsigned long ip),
+
+	TP_ARGS(mod, ip)
+);
+#endif /* CONFIG_MODULE_UNLOAD */
+
+TRACE_EVENT(module_request,
+
+	TP_PROTO(char *name, bool wait, unsigned long ip),
+
+	TP_ARGS(name, wait, ip),
+
+	TP_STRUCT__entry(
+		__field(	bool,		wait		)
+		__field(	unsigned long,	ip		)
+		__string(	name,		name		)
+	),
+
+	TP_fast_assign(
+		__entry->wait	= wait;
+		__entry->ip	= ip;
+		__assign_str(name, name);
+	),
+
+	TP_printk("%s wait=%d call_site=%pf",
+		  __get_str(name), (int)__entry->wait, (void *)__entry->ip)
+);
+
+#endif /* CONFIG_MODULES */
+
+#endif /* _TRACE_MODULE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index a8989c4547e7..8fe1e93f531d 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -1,11 +1,38 @@
-#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>
 #include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
 
-DECLARE_TRACE(napi_poll,
 	TP_PROTO(struct napi_struct *napi),
-	TP_ARGS(napi));
 
-#endif
+	TP_ARGS(napi),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV);
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s",
+		__entry->napi, __get_str(dev_name))
+);
+
+#undef NO_DEV
+
+#endif /* _TRACE_NAPI_H_ */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
new file mode 100644
index 000000000000..5f247f5ffc56
--- /dev/null
+++ b/include/trace/events/net.h
@@ -0,0 +1,82 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM net
+
+#if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NET_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(net_dev_xmit,
+
+	TP_PROTO(struct sk_buff *skb,
+		 int rc),
+
+	TP_ARGS(skb, rc),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__field(	int,		rc		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->rc = rc;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
+		__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
+);
+
+DECLARE_EVENT_CLASS(net_dev_template,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u",
+		__get_str(name), __entry->skbaddr, __entry->len)
+)
+
+DEFINE_EVENT(net_dev_template, net_dev_queue,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_receive_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_rx,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+#endif /* _TRACE_NET_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
new file mode 100644
index 000000000000..1bcc2a8c00e2
--- /dev/null
+++ b/include/trace/events/power.h
@@ -0,0 +1,240 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM power
+
+#if !defined(_TRACE_POWER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_POWER_H
+
+#include <linux/ktime.h>
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(cpu,
+
+	TP_PROTO(unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(state, cpu_id),
+
+	TP_STRUCT__entry(
+		__field(	u32,		state		)
+		__field(	u32,		cpu_id		)
+	),
+
+	TP_fast_assign(
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("state=%lu cpu_id=%lu", (unsigned long)__entry->state,
+		  (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(cpu, cpu_idle,
+
+	TP_PROTO(unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(state, cpu_id)
+);
+
+/* This file can get included multiple times, TRACE_HEADER_MULTI_READ at top */
+#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING
+#define _PWR_EVENT_AVOID_DOUBLE_DEFINING
+
+#define PWR_EVENT_EXIT -1
+#endif
+
+DEFINE_EVENT(cpu, cpu_frequency,
+
+	TP_PROTO(unsigned int frequency, unsigned int cpu_id),
+
+	TP_ARGS(frequency, cpu_id)
+);
+
+TRACE_EVENT(machine_suspend,
+
+	TP_PROTO(unsigned int state),
+
+	TP_ARGS(state),
+
+	TP_STRUCT__entry(
+		__field(	u32,		state		)
+	),
+
+	TP_fast_assign(
+		__entry->state = state;
+	),
+
+	TP_printk("state=%lu", (unsigned long)__entry->state)
+);
+
+/* This code will be removed after deprecation time exceeded (2.6.41) */
+#ifdef CONFIG_EVENT_POWER_TRACING_DEPRECATED
+
+/*
+ * The power events are used for cpuidle & suspend (power_start, power_end)
+ *  and for cpufreq (power_frequency)
+ */
+DECLARE_EVENT_CLASS(power,
+
+	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(type, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__field(	u64,		type		)
+		__field(	u64,		state		)
+		__field(	u64,		cpu_id		)
+	),
+
+	TP_fast_assign(
+		__entry->type = type;
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("type=%lu state=%lu cpu_id=%lu", (unsigned long)__entry->type,
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(power, power_start,
+
+	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(type, state, cpu_id)
+);
+
+DEFINE_EVENT(power, power_frequency,
+
+	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(type, state, cpu_id)
+);
+
+TRACE_EVENT(power_end,
+
+	TP_PROTO(unsigned int cpu_id),
+
+	TP_ARGS(cpu_id),
+
+	TP_STRUCT__entry(
+		__field(	u64,		cpu_id		)
+	),
+
+	TP_fast_assign(
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("cpu_id=%lu", (unsigned long)__entry->cpu_id)
+
+);
+
+/* Deprecated dummy functions must be protected against multi-declartion */
+#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+#define _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+
+enum {
+	POWER_NONE = 0,
+	POWER_CSTATE = 1,
+	POWER_PSTATE = 2,
+};
+#endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */
+
+#else /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */
+
+#ifndef _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+#define _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED
+enum {
+       POWER_NONE = 0,
+       POWER_CSTATE = 1,
+       POWER_PSTATE = 2,
+};
+
+/* These dummy declaration have to be ripped out when the deprecated
+   events get removed */
+static inline void trace_power_start(u64 type, u64 state, u64 cpuid) {};
+static inline void trace_power_end(u64 cpuid) {};
+static inline void trace_power_frequency(u64 type, u64 state, u64 cpuid) {};
+#endif /* _PWR_EVENT_AVOID_DOUBLE_DEFINING_DEPRECATED */
+
+#endif /* CONFIG_EVENT_POWER_TRACING_DEPRECATED */
+
+/*
+ * The clock events are used for clock enable/disable and for
+ *  clock rate change
+ */
+DECLARE_EVENT_CLASS(clock,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_enable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_disable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_set_rate,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+/*
+ * The power domain events are used for power domains transitions
+ */
+DECLARE_EVENT_CLASS(power_domain,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(power_domain, power_domain_target,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+#endif /* _TRACE_POWER_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 24ab5bcff7b2..f6334782a593 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -1,12 +1,12 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sched
+
 #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_SCHED_H
 
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM sched
-
 /*
  * Tracepoint for calling kthread_stop, performed to end a kthread:
  */
@@ -26,7 +26,7 @@ TRACE_EVENT(sched_kthread_stop,
 		__entry->pid	= t->pid;
 	),
 
-	TP_printk("task %s:%d", __entry->comm, __entry->pid)
+	TP_printk("comm=%s pid=%d", __entry->comm, __entry->pid)
 );
 
 /*
@@ -46,54 +46,24 @@ TRACE_EVENT(sched_kthread_stop_ret,
 		__entry->ret	= ret;
 	),
 
-	TP_printk("ret %d", __entry->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_ARGS(rq, p),
-
-	TP_STRUCT__entry(
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-		__field(	int,	prio			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid	= p->pid;
-		__entry->prio	= p->prio;
-	),
-
-	TP_printk("task %s:%d [%d]",
-		  __entry->comm, __entry->pid, __entry->prio)
+	TP_printk("ret=%d", __entry->ret)
 );
 
 /*
  * Tracepoint for waking up a task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
-TRACE_EVENT(sched_wakeup,
+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	)
 		__field(	pid_t,	pid			)
 		__field(	int,	prio			)
 		__field(	int,	success			)
+		__field(	int,	target_cpu		)
 	),
 
 	TP_fast_assign(
@@ -101,56 +71,51 @@ TRACE_EVENT(sched_wakeup,
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
 		__entry->success	= success;
+		__entry->target_cpu	= task_cpu(p);
 	),
 
-	TP_printk("task %s:%d [%d] success=%d",
+	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success)
+		  __entry->success, __entry->target_cpu)
 );
 
+DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
+	     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. )
  */
-TRACE_EVENT(sched_wakeup_new,
-
-	TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-
-	TP_ARGS(rq, p, success),
-
-	TP_STRUCT__entry(
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-		__field(	int,	prio			)
-		__field(	int,	success			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
-		__entry->success	= success;
-	),
-
-	TP_printk("task %s:%d [%d] success=%d",
-		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success)
-);
+DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
+	     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	)
@@ -166,13 +131,13 @@ 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;
 	),
 
-	TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
+	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s ==> next_comm=%s next_pid=%d next_prio=%d",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
 		__entry->prev_state ?
 		  __print_flags(__entry->prev_state, "|",
@@ -207,15 +172,12 @@ TRACE_EVENT(sched_migrate_task,
 		__entry->dest_cpu	= dest_cpu;
 	),
 
-	TP_printk("task %s:%d [%d] from: %d  to: %d",
+	TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d",
 		  __entry->comm, __entry->pid, __entry->prio,
 		  __entry->orig_cpu, __entry->dest_cpu)
 );
 
-/*
- * Tracepoint for freeing a task:
- */
-TRACE_EVENT(sched_process_free,
+DECLARE_EVENT_CLASS(sched_process_template,
 
 	TP_PROTO(struct task_struct *p),
 
@@ -233,34 +195,31 @@ TRACE_EVENT(sched_process_free,
 		__entry->prio		= p->prio;
 	),
 
-	TP_printk("task %s:%d [%d]",
+	TP_printk("comm=%s pid=%d prio=%d",
 		  __entry->comm, __entry->pid, __entry->prio)
 );
 
 /*
+ * Tracepoint for freeing a task:
+ */
+DEFINE_EVENT(sched_process_template, sched_process_free,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
+	     
+
+/*
  * Tracepoint for a task exiting:
  */
-TRACE_EVENT(sched_process_exit,
+DEFINE_EVENT(sched_process_template, sched_process_exit,
+	     TP_PROTO(struct task_struct *p),
+	     TP_ARGS(p));
 
+/*
+ * Tracepoint for waiting on task to unschedule:
+ */
+DEFINE_EVENT(sched_process_template, sched_wait_task,
 	TP_PROTO(struct task_struct *p),
-
-	TP_ARGS(p),
-
-	TP_STRUCT__entry(
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
-		__field(	int,	prio			)
-	),
-
-	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid		= p->pid;
-		__entry->prio		= p->prio;
-	),
-
-	TP_printk("task %s:%d [%d]",
-		  __entry->comm, __entry->pid, __entry->prio)
-);
+	TP_ARGS(p));
 
 /*
  * Tracepoint for a waiting task:
@@ -283,7 +242,7 @@ TRACE_EVENT(sched_process_wait,
 		__entry->prio		= current->prio;
 	),
 
-	TP_printk("task %s:%d [%d]",
+	TP_printk("comm=%s pid=%d prio=%d",
 		  __entry->comm, __entry->pid, __entry->prio)
 );
 
@@ -310,34 +269,126 @@ TRACE_EVENT(sched_process_fork,
 		__entry->child_pid	= child->pid;
 	),
 
-	TP_printk("parent %s:%d  child %s:%d",
+	TP_printk("comm=%s pid=%d child_comm=%s child_pid=%d",
 		__entry->parent_comm, __entry->parent_pid,
 		__entry->child_comm, __entry->child_pid)
 );
 
 /*
- * Tracepoint for sending a signal:
+ * XXX the below sched_stat tracepoints only apply to SCHED_OTHER/BATCH/IDLE
+ *     adding sched_stat support to SCHED_FIFO/RR would be welcome.
  */
-TRACE_EVENT(sched_signal_send,
+DECLARE_EVENT_CLASS(sched_stat_template,
 
-	TP_PROTO(int sig, struct task_struct *p),
+	TP_PROTO(struct task_struct *tsk, u64 delay),
 
-	TP_ARGS(sig, p),
+	TP_ARGS(tsk, delay),
 
 	TP_STRUCT__entry(
-		__field(	int,	sig			)
-		__array(	char,	comm,	TASK_COMM_LEN	)
-		__field(	pid_t,	pid			)
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( u64,	delay			)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
-		__entry->pid	= p->pid;
-		__entry->sig	= sig;
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid	= tsk->pid;
+		__entry->delay	= delay;
+	)
+	TP_perf_assign(
+		__perf_count(delay);
+	),
+
+	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
+			__entry->comm, __entry->pid,
+			(unsigned long long)__entry->delay)
+);
+
+
+/*
+ * Tracepoint for accounting wait time (time the task is runnable
+ * but not actually running due to scheduler contention).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_wait,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
+/*
+ * Tracepoint for accounting sleep time (time the task is not runnable,
+ * including iowait, see below).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_sleep,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
+/*
+ * Tracepoint for accounting iowait time (time the task is not runnable
+ * due to waiting on IO to complete).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
+/*
+ * Tracepoint for accounting runtime (time the task is executing
+ * on a CPU).
+ */
+TRACE_EVENT(sched_stat_runtime,
+
+	TP_PROTO(struct task_struct *tsk, u64 runtime, u64 vruntime),
+
+	TP_ARGS(tsk, runtime, vruntime),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( u64,	runtime			)
+		__field( u64,	vruntime			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		= tsk->pid;
+		__entry->runtime	= runtime;
+		__entry->vruntime	= vruntime;
+	)
+	TP_perf_assign(
+		__perf_count(runtime);
+	),
+
+	TP_printk("comm=%s pid=%d runtime=%Lu [ns] vruntime=%Lu [ns]",
+			__entry->comm, __entry->pid,
+			(unsigned long long)__entry->runtime,
+			(unsigned long long)__entry->vruntime)
+);
+
+/*
+ * Tracepoint for showing priority inheritance modifying a tasks
+ * priority.
+ */
+TRACE_EVENT(sched_pi_setprio,
+
+	TP_PROTO(struct task_struct *tsk, int newprio),
+
+	TP_ARGS(tsk, newprio),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( int,	oldprio			)
+		__field( int,	newprio			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		= tsk->pid;
+		__entry->oldprio	= tsk->prio;
+		__entry->newprio	= newprio;
 	),
 
-	TP_printk("sig: %d  task %s:%d",
-		  __entry->sig, __entry->comm, __entry->pid)
+	TP_printk("comm=%s pid=%d oldprio=%d newprio=%d",
+			__entry->comm, __entry->pid,
+			__entry->oldprio, __entry->newprio)
 );
 
 #endif /* _TRACE_SCHED_H */
diff --git a/include/trace/events/scsi.h b/include/trace/events/scsi.h
new file mode 100644
index 000000000000..25fbefdf2f2e
--- /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
new file mode 100644
index 000000000000..17df43464df0
--- /dev/null
+++ b/include/trace/events/signal.h
@@ -0,0 +1,166 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM signal
+
+#if !defined(_TRACE_SIGNAL_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SIGNAL_H
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#define TP_STORE_SIGINFO(__entry, info)				\
+	do {							\
+		if (info == SEND_SIG_NOINFO ||			\
+		    info == SEND_SIG_FORCED) {			\
+			__entry->errno	= 0;			\
+			__entry->code	= SI_USER;		\
+		} else if (info == SEND_SIG_PRIV) {		\
+			__entry->errno	= 0;			\
+			__entry->code	= SI_KERNEL;		\
+		} else {					\
+			__entry->errno	= info->si_errno;	\
+			__entry->code	= info->si_code;	\
+		}						\
+	} while (0)
+
+/**
+ * signal_generate - called when a signal is generated
+ * @sig: signal number
+ * @info: pointer to struct siginfo
+ * @task: pointer to struct task_struct
+ *
+ * Current process sends a 'sig' signal to 'task' process with
+ * 'info' siginfo. If 'info' is SEND_SIG_NOINFO or SEND_SIG_PRIV,
+ * 'info' is not a pointer and you can't access its field. Instead,
+ * SEND_SIG_NOINFO means that si_code is SI_USER, and SEND_SIG_PRIV
+ * means that si_code is SI_KERNEL.
+ */
+TRACE_EVENT(signal_generate,
+
+	TP_PROTO(int sig, struct siginfo *info, struct task_struct *task),
+
+	TP_ARGS(sig, info, task),
+
+	TP_STRUCT__entry(
+		__field(	int,	sig			)
+		__field(	int,	errno			)
+		__field(	int,	code			)
+		__array(	char,	comm,	TASK_COMM_LEN	)
+		__field(	pid_t,	pid			)
+	),
+
+	TP_fast_assign(
+		__entry->sig	= sig;
+		TP_STORE_SIGINFO(__entry, info);
+		memcpy(__entry->comm, task->comm, TASK_COMM_LEN);
+		__entry->pid	= task->pid;
+	),
+
+	TP_printk("sig=%d errno=%d code=%d comm=%s pid=%d",
+		  __entry->sig, __entry->errno, __entry->code,
+		  __entry->comm, __entry->pid)
+);
+
+/**
+ * signal_deliver - called when a signal is delivered
+ * @sig: signal number
+ * @info: pointer to struct siginfo
+ * @ka: pointer to struct k_sigaction
+ *
+ * A 'sig' signal is delivered to current process with 'info' siginfo,
+ * and it will be handled by 'ka'. ka->sa.sa_handler can be SIG_IGN or
+ * SIG_DFL.
+ * Note that some signals reported by signal_generate tracepoint can be
+ * lost, ignored or modified (by debugger) before hitting this tracepoint.
+ * This means, this can show which signals are actually delivered, but
+ * matching generated signals and delivered signals may not be correct.
+ */
+TRACE_EVENT(signal_deliver,
+
+	TP_PROTO(int sig, struct siginfo *info, struct k_sigaction *ka),
+
+	TP_ARGS(sig, info, ka),
+
+	TP_STRUCT__entry(
+		__field(	int,		sig		)
+		__field(	int,		errno		)
+		__field(	int,		code		)
+		__field(	unsigned long,	sa_handler	)
+		__field(	unsigned long,	sa_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->sig	= sig;
+		TP_STORE_SIGINFO(__entry, info);
+		__entry->sa_handler	= (unsigned long)ka->sa.sa_handler;
+		__entry->sa_flags	= ka->sa.sa_flags;
+	),
+
+	TP_printk("sig=%d errno=%d code=%d sa_handler=%lx sa_flags=%lx",
+		  __entry->sig, __entry->errno, __entry->code,
+		  __entry->sa_handler, __entry->sa_flags)
+);
+
+DECLARE_EVENT_CLASS(signal_queue_overflow,
+
+	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)
+);
+
+/**
+ * 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)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel generates 'sig' signal but loses 'info' siginfo, because siginfo
+ * queue is overflow.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of non-RT signals.
+ */
+DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
+
+	TP_PROTO(int sig, int group, struct siginfo *info),
+
+	TP_ARGS(sig, group, info)
+);
+
+#endif /* _TRACE_SIGNAL_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
index 1e8fabb57c06..f10293c41b1e 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -1,12 +1,13 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM skb
+
 #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_SKB_H
 
 #include <linux/skbuff.h>
+#include <linux/netdevice.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM skb
-
 /*
  * Tracepoint for free an sk_buff:
  */
@@ -24,9 +25,7 @@ TRACE_EVENT(kfree_skb,
 
 	TP_fast_assign(
 		__entry->skbaddr = skb;
-		if (skb) {
-			__entry->protocol = ntohs(skb->protocol);
-		}
+		__entry->protocol = ntohs(skb->protocol);
 		__entry->location = location;
 	),
 
@@ -34,6 +33,42 @@ TRACE_EVENT(kfree_skb,
 		__entry->skbaddr, __entry->protocol, __entry->location)
 );
 
+TRACE_EVENT(consume_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,	skbaddr	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+	),
+
+	TP_printk("skbaddr=%p", __entry->skbaddr)
+);
+
+TRACE_EVENT(skb_copy_datagram_iovec,
+
+	TP_PROTO(const struct sk_buff *skb, int len),
+
+	TP_ARGS(skb, len),
+
+	TP_STRUCT__entry(
+		__field(	const void *,		skbaddr		)
+		__field(	int,			len		)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = len;
+	),
+
+	TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len)
+);
+
 #endif /* _TRACE_SKB_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
new file mode 100644
index 000000000000..5a4c04a75b3d
--- /dev/null
+++ b/include/trace/events/syscalls.h
@@ -0,0 +1,75 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM raw_syscalls
+#define TRACE_INCLUDE_FILE syscalls
+
+#if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EVENTS_SYSCALLS_H
+
+#include <linux/tracepoint.h>
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+
+extern void syscall_regfunc(void);
+extern void syscall_unregfunc(void);
+
+TRACE_EVENT_FN(sys_enter,
+
+	TP_PROTO(struct pt_regs *regs, long id),
+
+	TP_ARGS(regs, id),
+
+	TP_STRUCT__entry(
+		__field(	long,		id		)
+		__array(	unsigned long,	args,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->id	= id;
+		syscall_get_arguments(current, regs, 0, 6, __entry->args);
+	),
+
+	TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)",
+		  __entry->id,
+		  __entry->args[0], __entry->args[1], __entry->args[2],
+		  __entry->args[3], __entry->args[4], __entry->args[5]),
+
+	syscall_regfunc, syscall_unregfunc
+);
+
+TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY)
+
+TRACE_EVENT_FN(sys_exit,
+
+	TP_PROTO(struct pt_regs *regs, long ret),
+
+	TP_ARGS(regs, ret),
+
+	TP_STRUCT__entry(
+		__field(	long,	id	)
+		__field(	long,	ret	)
+	),
+
+	TP_fast_assign(
+		__entry->id	= syscall_get_nr(current, regs);
+		__entry->ret	= ret;
+	),
+
+	TP_printk("NR %ld = %ld",
+		  __entry->id, __entry->ret),
+
+	syscall_regfunc, syscall_unregfunc
+);
+
+TRACE_EVENT_FLAGS(sys_exit, TRACE_EVENT_FL_CAP_ANY)
+
+#endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
+
+#endif /* _TRACE_EVENTS_SYSCALLS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/timer.h b/include/trace/events/timer.h
new file mode 100644
index 000000000000..425bcfe56c62
--- /dev/null
+++ b/include/trace/events/timer.h
@@ -0,0 +1,329 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM timer
+
+#if !defined(_TRACE_TIMER_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_TIMER_H
+
+#include <linux/tracepoint.h>
+#include <linux/hrtimer.h>
+#include <linux/timer.h>
+
+DECLARE_EVENT_CLASS(timer_class,
+
+	TP_PROTO(struct timer_list *timer),
+
+	TP_ARGS(timer),
+
+	TP_STRUCT__entry(
+		__field( void *,	timer	)
+	),
+
+	TP_fast_assign(
+		__entry->timer	= timer;
+	),
+
+	TP_printk("timer=%p", __entry->timer)
+);
+
+/**
+ * timer_init - called when the timer is initialized
+ * @timer:	pointer to struct timer_list
+ */
+DEFINE_EVENT(timer_class, timer_init,
+
+	TP_PROTO(struct timer_list *timer),
+
+	TP_ARGS(timer)
+);
+
+/**
+ * timer_start - called when the timer is started
+ * @timer:	pointer to struct timer_list
+ * @expires:	the timers expiry time
+ */
+TRACE_EVENT(timer_start,
+
+	TP_PROTO(struct timer_list *timer, unsigned long expires),
+
+	TP_ARGS(timer, expires),
+
+	TP_STRUCT__entry(
+		__field( void *,	timer		)
+		__field( void *,	function	)
+		__field( unsigned long,	expires		)
+		__field( unsigned long,	now		)
+	),
+
+	TP_fast_assign(
+		__entry->timer		= timer;
+		__entry->function	= timer->function;
+		__entry->expires	= expires;
+		__entry->now		= jiffies;
+	),
+
+	TP_printk("timer=%p function=%pf expires=%lu [timeout=%ld]",
+		  __entry->timer, __entry->function, __entry->expires,
+		  (long)__entry->expires - __entry->now)
+);
+
+/**
+ * timer_expire_entry - called immediately before the timer callback
+ * @timer:	pointer to struct timer_list
+ *
+ * Allows to determine the timer latency.
+ */
+TRACE_EVENT(timer_expire_entry,
+
+	TP_PROTO(struct timer_list *timer),
+
+	TP_ARGS(timer),
+
+	TP_STRUCT__entry(
+		__field( void *,	timer	)
+		__field( unsigned long,	now	)
+		__field( void *,	function)
+	),
+
+	TP_fast_assign(
+		__entry->timer		= timer;
+		__entry->now		= jiffies;
+		__entry->function	= timer->function;
+	),
+
+	TP_printk("timer=%p function=%pf now=%lu", __entry->timer, __entry->function,__entry->now)
+);
+
+/**
+ * timer_expire_exit - called immediately after the timer callback returns
+ * @timer:	pointer to struct timer_list
+ *
+ * When used in combination with the timer_expire_entry tracepoint we can
+ * determine the runtime of the timer callback function.
+ *
+ * NOTE: Do NOT derefernce timer in TP_fast_assign. The pointer might
+ * be invalid. We solely track the pointer.
+ */
+DEFINE_EVENT(timer_class, timer_expire_exit,
+
+	TP_PROTO(struct timer_list *timer),
+
+	TP_ARGS(timer)
+);
+
+/**
+ * timer_cancel - called when the timer is canceled
+ * @timer:	pointer to struct timer_list
+ */
+DEFINE_EVENT(timer_class, timer_cancel,
+
+	TP_PROTO(struct timer_list *timer),
+
+	TP_ARGS(timer)
+);
+
+/**
+ * hrtimer_init - called when the hrtimer is initialized
+ * @timer:	pointer to struct hrtimer
+ * @clockid:	the hrtimers clock
+ * @mode:	the hrtimers mode
+ */
+TRACE_EVENT(hrtimer_init,
+
+	TP_PROTO(struct hrtimer *hrtimer, clockid_t clockid,
+		 enum hrtimer_mode mode),
+
+	TP_ARGS(hrtimer, clockid, mode),
+
+	TP_STRUCT__entry(
+		__field( void *,		hrtimer		)
+		__field( clockid_t,		clockid		)
+		__field( enum hrtimer_mode,	mode		)
+	),
+
+	TP_fast_assign(
+		__entry->hrtimer	= hrtimer;
+		__entry->clockid	= clockid;
+		__entry->mode		= mode;
+	),
+
+	TP_printk("hrtimer=%p clockid=%s mode=%s", __entry->hrtimer,
+		  __entry->clockid == CLOCK_REALTIME ?
+			"CLOCK_REALTIME" : "CLOCK_MONOTONIC",
+		  __entry->mode == HRTIMER_MODE_ABS ?
+			"HRTIMER_MODE_ABS" : "HRTIMER_MODE_REL")
+);
+
+/**
+ * hrtimer_start - called when the hrtimer is started
+ * @timer: pointer to struct hrtimer
+ */
+TRACE_EVENT(hrtimer_start,
+
+	TP_PROTO(struct hrtimer *hrtimer),
+
+	TP_ARGS(hrtimer),
+
+	TP_STRUCT__entry(
+		__field( void *,	hrtimer		)
+		__field( void *,	function	)
+		__field( s64,		expires		)
+		__field( s64,		softexpires	)
+	),
+
+	TP_fast_assign(
+		__entry->hrtimer	= hrtimer;
+		__entry->function	= hrtimer->function;
+		__entry->expires	= hrtimer_get_expires(hrtimer).tv64;
+		__entry->softexpires	= hrtimer_get_softexpires(hrtimer).tv64;
+	),
+
+	TP_printk("hrtimer=%p function=%pf expires=%llu softexpires=%llu",
+		  __entry->hrtimer, __entry->function,
+		  (unsigned long long)ktime_to_ns((ktime_t) {
+				  .tv64 = __entry->expires }),
+		  (unsigned long long)ktime_to_ns((ktime_t) {
+				  .tv64 = __entry->softexpires }))
+);
+
+/**
+ * htimmer_expire_entry - called immediately before the hrtimer callback
+ * @timer:	pointer to struct hrtimer
+ * @now:	pointer to variable which contains current time of the
+ *		timers base.
+ *
+ * Allows to determine the timer latency.
+ */
+TRACE_EVENT(hrtimer_expire_entry,
+
+	TP_PROTO(struct hrtimer *hrtimer, ktime_t *now),
+
+	TP_ARGS(hrtimer, now),
+
+	TP_STRUCT__entry(
+		__field( void *,	hrtimer	)
+		__field( s64,		now	)
+		__field( void *,	function)
+	),
+
+	TP_fast_assign(
+		__entry->hrtimer	= hrtimer;
+		__entry->now		= now->tv64;
+		__entry->function	= hrtimer->function;
+	),
+
+	TP_printk("hrtimer=%p function=%pf now=%llu", __entry->hrtimer, __entry->function,
+		  (unsigned long long)ktime_to_ns((ktime_t) { .tv64 = __entry->now }))
+ );
+
+DECLARE_EVENT_CLASS(hrtimer_class,
+
+	TP_PROTO(struct hrtimer *hrtimer),
+
+	TP_ARGS(hrtimer),
+
+	TP_STRUCT__entry(
+		__field( void *,	hrtimer	)
+	),
+
+	TP_fast_assign(
+		__entry->hrtimer	= hrtimer;
+	),
+
+	TP_printk("hrtimer=%p", __entry->hrtimer)
+);
+
+/**
+ * hrtimer_expire_exit - called immediately after the hrtimer callback returns
+ * @timer:	pointer to struct hrtimer
+ *
+ * When used in combination with the hrtimer_expire_entry tracepoint we can
+ * determine the runtime of the callback function.
+ */
+DEFINE_EVENT(hrtimer_class, hrtimer_expire_exit,
+
+	TP_PROTO(struct hrtimer *hrtimer),
+
+	TP_ARGS(hrtimer)
+);
+
+/**
+ * hrtimer_cancel - called when the hrtimer is canceled
+ * @hrtimer:	pointer to struct hrtimer
+ */
+DEFINE_EVENT(hrtimer_class, hrtimer_cancel,
+
+	TP_PROTO(struct hrtimer *hrtimer),
+
+	TP_ARGS(hrtimer)
+);
+
+/**
+ * itimer_state - called when itimer is started or canceled
+ * @which:	name of the interval timer
+ * @value:	the itimers value, itimer is canceled if value->it_value is
+ *		zero, otherwise it is started
+ * @expires:	the itimers expiry time
+ */
+TRACE_EVENT(itimer_state,
+
+	TP_PROTO(int which, const struct itimerval *const value,
+		 cputime_t expires),
+
+	TP_ARGS(which, value, expires),
+
+	TP_STRUCT__entry(
+		__field(	int,		which		)
+		__field(	cputime_t,	expires		)
+		__field(	long,		value_sec	)
+		__field(	long,		value_usec	)
+		__field(	long,		interval_sec	)
+		__field(	long,		interval_usec	)
+	),
+
+	TP_fast_assign(
+		__entry->which		= which;
+		__entry->expires	= expires;
+		__entry->value_sec	= value->it_value.tv_sec;
+		__entry->value_usec	= value->it_value.tv_usec;
+		__entry->interval_sec	= value->it_interval.tv_sec;
+		__entry->interval_usec	= value->it_interval.tv_usec;
+	),
+
+	TP_printk("which=%d expires=%llu it_value=%ld.%ld it_interval=%ld.%ld",
+		  __entry->which, (unsigned long long)__entry->expires,
+		  __entry->value_sec, __entry->value_usec,
+		  __entry->interval_sec, __entry->interval_usec)
+);
+
+/**
+ * itimer_expire - called when itimer expires
+ * @which:	type of the interval timer
+ * @pid:	pid of the process which owns the timer
+ * @now:	current time, used to calculate the latency of itimer
+ */
+TRACE_EVENT(itimer_expire,
+
+	TP_PROTO(int which, struct pid *pid, cputime_t now),
+
+	TP_ARGS(which, pid, now),
+
+	TP_STRUCT__entry(
+		__field( int ,		which	)
+		__field( pid_t,		pid	)
+		__field( cputime_t,	now	)
+	),
+
+	TP_fast_assign(
+		__entry->which	= which;
+		__entry->now	= now;
+		__entry->pid	= pid_nr(pid);
+	),
+
+	TP_printk("which=%d pid=%d now=%llu", __entry->which,
+		  (int) __entry->pid, (unsigned long long)__entry->now)
+);
+
+#endif /*  _TRACE_TIMER_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/vmscan.h b/include/trace/events/vmscan.h
new file mode 100644
index 000000000000..c255fcc587bf
--- /dev/null
+++ b/include/trace/events/vmscan.h
@@ -0,0 +1,317 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vmscan
+
+#if !defined(_TRACE_VMSCAN_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_VMSCAN_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+#include "gfpflags.h"
+
+#define RECLAIM_WB_ANON		0x0001u
+#define RECLAIM_WB_FILE		0x0002u
+#define RECLAIM_WB_MIXED	0x0010u
+#define RECLAIM_WB_SYNC		0x0004u
+#define RECLAIM_WB_ASYNC	0x0008u
+
+#define show_reclaim_flags(flags)				\
+	(flags) ? __print_flags(flags, "|",			\
+		{RECLAIM_WB_ANON,	"RECLAIM_WB_ANON"},	\
+		{RECLAIM_WB_FILE,	"RECLAIM_WB_FILE"},	\
+		{RECLAIM_WB_MIXED,	"RECLAIM_WB_MIXED"},	\
+		{RECLAIM_WB_SYNC,	"RECLAIM_WB_SYNC"},	\
+		{RECLAIM_WB_ASYNC,	"RECLAIM_WB_ASYNC"}	\
+		) : "RECLAIM_WB_NONE"
+
+#define trace_reclaim_flags(page, sync) ( \
+	(page_is_file_cache(page) ? RECLAIM_WB_FILE : RECLAIM_WB_ANON) | \
+	(sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC)   \
+	)
+
+#define trace_shrink_flags(file, sync) ( \
+	(sync == LUMPY_MODE_SYNC ? RECLAIM_WB_MIXED : \
+			(file ? RECLAIM_WB_FILE : RECLAIM_WB_ANON)) |  \
+	(sync == LUMPY_MODE_SYNC ? RECLAIM_WB_SYNC : RECLAIM_WB_ASYNC) \
+	)
+
+TRACE_EVENT(mm_vmscan_kswapd_sleep,
+
+	TP_PROTO(int nid),
+
+	TP_ARGS(nid),
+
+	TP_STRUCT__entry(
+		__field(	int,	nid	)
+	),
+
+	TP_fast_assign(
+		__entry->nid	= nid;
+	),
+
+	TP_printk("nid=%d", __entry->nid)
+);
+
+TRACE_EVENT(mm_vmscan_kswapd_wake,
+
+	TP_PROTO(int nid, int order),
+
+	TP_ARGS(nid, order),
+
+	TP_STRUCT__entry(
+		__field(	int,	nid	)
+		__field(	int,	order	)
+	),
+
+	TP_fast_assign(
+		__entry->nid	= nid;
+		__entry->order	= order;
+	),
+
+	TP_printk("nid=%d order=%d", __entry->nid, __entry->order)
+);
+
+TRACE_EVENT(mm_vmscan_wakeup_kswapd,
+
+	TP_PROTO(int nid, int zid, int order),
+
+	TP_ARGS(nid, zid, order),
+
+	TP_STRUCT__entry(
+		__field(	int,		nid	)
+		__field(	int,		zid	)
+		__field(	int,		order	)
+	),
+
+	TP_fast_assign(
+		__entry->nid		= nid;
+		__entry->zid		= zid;
+		__entry->order		= order;
+	),
+
+	TP_printk("nid=%d zid=%d order=%d",
+		__entry->nid,
+		__entry->zid,
+		__entry->order)
+);
+
+DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_begin_template,
+
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+
+	TP_ARGS(order, may_writepage, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	int,	order		)
+		__field(	int,	may_writepage	)
+		__field(	gfp_t,	gfp_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->order		= order;
+		__entry->may_writepage	= may_writepage;
+		__entry->gfp_flags	= gfp_flags;
+	),
+
+	TP_printk("order=%d may_writepage=%d gfp_flags=%s",
+		__entry->order,
+		__entry->may_writepage,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_direct_reclaim_begin,
+
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+
+	TP_ARGS(order, may_writepage, gfp_flags)
+);
+
+DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_reclaim_begin,
+
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+
+	TP_ARGS(order, may_writepage, gfp_flags)
+);
+
+DEFINE_EVENT(mm_vmscan_direct_reclaim_begin_template, mm_vmscan_memcg_softlimit_reclaim_begin,
+
+	TP_PROTO(int order, int may_writepage, gfp_t gfp_flags),
+
+	TP_ARGS(order, may_writepage, gfp_flags)
+);
+
+DECLARE_EVENT_CLASS(mm_vmscan_direct_reclaim_end_template,
+
+	TP_PROTO(unsigned long nr_reclaimed),
+
+	TP_ARGS(nr_reclaimed),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	nr_reclaimed	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_reclaimed	= nr_reclaimed;
+	),
+
+	TP_printk("nr_reclaimed=%lu", __entry->nr_reclaimed)
+);
+
+DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_direct_reclaim_end,
+
+	TP_PROTO(unsigned long nr_reclaimed),
+
+	TP_ARGS(nr_reclaimed)
+);
+
+DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_reclaim_end,
+
+	TP_PROTO(unsigned long nr_reclaimed),
+
+	TP_ARGS(nr_reclaimed)
+);
+
+DEFINE_EVENT(mm_vmscan_direct_reclaim_end_template, mm_vmscan_memcg_softlimit_reclaim_end,
+
+	TP_PROTO(unsigned long nr_reclaimed),
+
+	TP_ARGS(nr_reclaimed)
+);
+
+
+DECLARE_EVENT_CLASS(mm_vmscan_lru_isolate_template,
+
+	TP_PROTO(int order,
+		unsigned long nr_requested,
+		unsigned long nr_scanned,
+		unsigned long nr_taken,
+		unsigned long nr_lumpy_taken,
+		unsigned long nr_lumpy_dirty,
+		unsigned long nr_lumpy_failed,
+		int isolate_mode),
+
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode),
+
+	TP_STRUCT__entry(
+		__field(int, order)
+		__field(unsigned long, nr_requested)
+		__field(unsigned long, nr_scanned)
+		__field(unsigned long, nr_taken)
+		__field(unsigned long, nr_lumpy_taken)
+		__field(unsigned long, nr_lumpy_dirty)
+		__field(unsigned long, nr_lumpy_failed)
+		__field(int, isolate_mode)
+	),
+
+	TP_fast_assign(
+		__entry->order = order;
+		__entry->nr_requested = nr_requested;
+		__entry->nr_scanned = nr_scanned;
+		__entry->nr_taken = nr_taken;
+		__entry->nr_lumpy_taken = nr_lumpy_taken;
+		__entry->nr_lumpy_dirty = nr_lumpy_dirty;
+		__entry->nr_lumpy_failed = nr_lumpy_failed;
+		__entry->isolate_mode = isolate_mode;
+	),
+
+	TP_printk("isolate_mode=%d order=%d nr_requested=%lu nr_scanned=%lu nr_taken=%lu contig_taken=%lu contig_dirty=%lu contig_failed=%lu",
+		__entry->isolate_mode,
+		__entry->order,
+		__entry->nr_requested,
+		__entry->nr_scanned,
+		__entry->nr_taken,
+		__entry->nr_lumpy_taken,
+		__entry->nr_lumpy_dirty,
+		__entry->nr_lumpy_failed)
+);
+
+DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_lru_isolate,
+
+	TP_PROTO(int order,
+		unsigned long nr_requested,
+		unsigned long nr_scanned,
+		unsigned long nr_taken,
+		unsigned long nr_lumpy_taken,
+		unsigned long nr_lumpy_dirty,
+		unsigned long nr_lumpy_failed,
+		int isolate_mode),
+
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode)
+
+);
+
+DEFINE_EVENT(mm_vmscan_lru_isolate_template, mm_vmscan_memcg_isolate,
+
+	TP_PROTO(int order,
+		unsigned long nr_requested,
+		unsigned long nr_scanned,
+		unsigned long nr_taken,
+		unsigned long nr_lumpy_taken,
+		unsigned long nr_lumpy_dirty,
+		unsigned long nr_lumpy_failed,
+		int isolate_mode),
+
+	TP_ARGS(order, nr_requested, nr_scanned, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, isolate_mode)
+
+);
+
+TRACE_EVENT(mm_vmscan_writepage,
+
+	TP_PROTO(struct page *page,
+		int reclaim_flags),
+
+	TP_ARGS(page, reclaim_flags),
+
+	TP_STRUCT__entry(
+		__field(struct page *, page)
+		__field(int, reclaim_flags)
+	),
+
+	TP_fast_assign(
+		__entry->page = page;
+		__entry->reclaim_flags = reclaim_flags;
+	),
+
+	TP_printk("page=%p pfn=%lu flags=%s",
+		__entry->page,
+		page_to_pfn(__entry->page),
+		show_reclaim_flags(__entry->reclaim_flags))
+);
+
+TRACE_EVENT(mm_vmscan_lru_shrink_inactive,
+
+	TP_PROTO(int nid, int zid,
+			unsigned long nr_scanned, unsigned long nr_reclaimed,
+			int priority, int reclaim_flags),
+
+	TP_ARGS(nid, zid, nr_scanned, nr_reclaimed, priority, reclaim_flags),
+
+	TP_STRUCT__entry(
+		__field(int, nid)
+		__field(int, zid)
+		__field(unsigned long, nr_scanned)
+		__field(unsigned long, nr_reclaimed)
+		__field(int, priority)
+		__field(int, reclaim_flags)
+	),
+
+	TP_fast_assign(
+		__entry->nid = nid;
+		__entry->zid = zid;
+		__entry->nr_scanned = nr_scanned;
+		__entry->nr_reclaimed = nr_reclaimed;
+		__entry->priority = priority;
+		__entry->reclaim_flags = reclaim_flags;
+	),
+
+	TP_printk("nid=%d zid=%d nr_scanned=%ld nr_reclaimed=%ld priority=%d flags=%s",
+		__entry->nid, __entry->zid,
+		__entry->nr_scanned, __entry->nr_reclaimed,
+		__entry->priority,
+		show_reclaim_flags(__entry->reclaim_flags))
+);
+
+
+#endif /* _TRACE_VMSCAN_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
index 035f1bff288e..7d497291c85d 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -1,100 +1,121 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
 #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>
+#include <linux/workqueue.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM workqueue
-
-TRACE_EVENT(workqueue_insertion,
+DECLARE_EVENT_CLASS(workqueue_work,
 
-	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+	TP_PROTO(struct work_struct *work),
 
-	TP_ARGS(wq_thread, work),
+	TP_ARGS(work),
 
 	TP_STRUCT__entry(
-		__array(char,		thread_comm,	TASK_COMM_LEN)
-		__field(pid_t,		thread_pid)
-		__field(work_func_t,	func)
+		__field( void *,	work	)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
-		__entry->thread_pid	= wq_thread->pid;
-		__entry->func		= work->func;
+		__entry->work		= work;
 	),
 
-	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
-		__entry->thread_pid, __entry->func)
+	TP_printk("work struct %p", __entry->work)
 );
 
-TRACE_EVENT(workqueue_execution,
+/**
+ * workqueue_queue_work - called when a work gets queued
+ * @req_cpu:	the requested cpu
+ * @cwq:	pointer to struct cpu_workqueue_struct
+ * @work:	pointer to struct work_struct
+ *
+ * This event occurs when a work is queued immediately or once a
+ * delayed work is actually queued on a workqueue (ie: once the delay
+ * has been reached).
+ */
+TRACE_EVENT(workqueue_queue_work,
 
-	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+	TP_PROTO(unsigned int req_cpu, struct cpu_workqueue_struct *cwq,
+		 struct work_struct *work),
 
-	TP_ARGS(wq_thread, work),
+	TP_ARGS(req_cpu, cwq, work),
 
 	TP_STRUCT__entry(
-		__array(char,		thread_comm,	TASK_COMM_LEN)
-		__field(pid_t,		thread_pid)
-		__field(work_func_t,	func)
+		__field( void *,	work	)
+		__field( void *,	function)
+		__field( void *,	workqueue)
+		__field( unsigned int,	req_cpu	)
+		__field( unsigned int,	cpu	)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
-		__entry->thread_pid	= wq_thread->pid;
-		__entry->func		= work->func;
+		__entry->work		= work;
+		__entry->function	= work->func;
+		__entry->workqueue	= cwq->wq;
+		__entry->req_cpu	= req_cpu;
+		__entry->cpu		= cwq->gcwq->cpu;
 	),
 
-	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
-		__entry->thread_pid, __entry->func)
+	TP_printk("work struct=%p function=%pf workqueue=%p req_cpu=%u cpu=%u",
+		  __entry->work, __entry->function, __entry->workqueue,
+		  __entry->req_cpu, __entry->cpu)
 );
 
-/* Trace the creation of one workqueue thread on a cpu */
-TRACE_EVENT(workqueue_creation,
+/**
+ * workqueue_activate_work - called when a work gets activated
+ * @work:	pointer to struct work_struct
+ *
+ * This event occurs when a queued work is put on the active queue,
+ * which happens immediately after queueing unless @max_active limit
+ * is reached.
+ */
+DEFINE_EVENT(workqueue_work, workqueue_activate_work,
 
-	TP_PROTO(struct task_struct *wq_thread, int cpu),
+	TP_PROTO(struct work_struct *work),
 
-	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)
+	TP_ARGS(work)
 );
 
-TRACE_EVENT(workqueue_destruction,
+/**
+ * workqueue_execute_start - called immediately before the workqueue callback
+ * @work:	pointer to struct work_struct
+ *
+ * Allows to track workqueue execution.
+ */
+TRACE_EVENT(workqueue_execute_start,
 
-	TP_PROTO(struct task_struct *wq_thread),
+	TP_PROTO(struct work_struct *work),
 
-	TP_ARGS(wq_thread),
+	TP_ARGS(work),
 
 	TP_STRUCT__entry(
-		__array(char,	thread_comm,	TASK_COMM_LEN)
-		__field(pid_t,	thread_pid)
+		__field( void *,	work	)
+		__field( void *,	function)
 	),
 
 	TP_fast_assign(
-		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
-		__entry->thread_pid	= wq_thread->pid;
+		__entry->work		= work;
+		__entry->function	= work->func;
 	),
 
-	TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid)
+	TP_printk("work struct %p: function %pf", __entry->work, __entry->function)
+);
+
+/**
+ * workqueue_execute_end - called immediately before the workqueue callback
+ * @work:	pointer to struct work_struct
+ *
+ * Allows to track workqueue execution.
+ */
+DEFINE_EVENT(workqueue_work, workqueue_execute_end,
+
+	TP_PROTO(struct work_struct *work),
+
+	TP_ARGS(work)
 );
 
-#endif /* _TRACE_WORKQUEUE_H */
+#endif /*  _TRACE_WORKQUEUE_H */
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
new file mode 100644
index 000000000000..89a2b2db4375
--- /dev/null
+++ b/include/trace/events/writeback.h
@@ -0,0 +1,192 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM writeback
+
+#if !defined(_TRACE_WRITEBACK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WRITEBACK_H
+
+#include <linux/backing-dev.h>
+#include <linux/device.h>
+#include <linux/writeback.h>
+
+struct wb_writeback_work;
+
+DECLARE_EVENT_CLASS(writeback_work_class,
+	TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work),
+	TP_ARGS(bdi, work),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(long, nr_pages)
+		__field(dev_t, sb_dev)
+		__field(int, sync_mode)
+		__field(int, for_kupdate)
+		__field(int, range_cyclic)
+		__field(int, for_background)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->nr_pages = work->nr_pages;
+		__entry->sb_dev = work->sb ? work->sb->s_dev : 0;
+		__entry->sync_mode = work->sync_mode;
+		__entry->for_kupdate = work->for_kupdate;
+		__entry->range_cyclic = work->range_cyclic;
+		__entry->for_background	= work->for_background;
+	),
+	TP_printk("bdi %s: sb_dev %d:%d nr_pages=%ld sync_mode=%d "
+		  "kupdate=%d range_cyclic=%d background=%d",
+		  __entry->name,
+		  MAJOR(__entry->sb_dev), MINOR(__entry->sb_dev),
+		  __entry->nr_pages,
+		  __entry->sync_mode,
+		  __entry->for_kupdate,
+		  __entry->range_cyclic,
+		  __entry->for_background
+	)
+);
+#define DEFINE_WRITEBACK_WORK_EVENT(name) \
+DEFINE_EVENT(writeback_work_class, name, \
+	TP_PROTO(struct backing_dev_info *bdi, struct wb_writeback_work *work), \
+	TP_ARGS(bdi, work))
+DEFINE_WRITEBACK_WORK_EVENT(writeback_nothread);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_queue);
+DEFINE_WRITEBACK_WORK_EVENT(writeback_exec);
+
+TRACE_EVENT(writeback_pages_written,
+	TP_PROTO(long pages_written),
+	TP_ARGS(pages_written),
+	TP_STRUCT__entry(
+		__field(long,		pages)
+	),
+	TP_fast_assign(
+		__entry->pages		= pages_written;
+	),
+	TP_printk("%ld", __entry->pages)
+);
+
+DECLARE_EVENT_CLASS(writeback_class,
+	TP_PROTO(struct backing_dev_info *bdi),
+	TP_ARGS(bdi),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+	),
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+	),
+	TP_printk("bdi %s",
+		  __entry->name
+	)
+);
+#define DEFINE_WRITEBACK_EVENT(name) \
+DEFINE_EVENT(writeback_class, name, \
+	TP_PROTO(struct backing_dev_info *bdi), \
+	TP_ARGS(bdi))
+
+DEFINE_WRITEBACK_EVENT(writeback_nowork);
+DEFINE_WRITEBACK_EVENT(writeback_wake_thread);
+DEFINE_WRITEBACK_EVENT(writeback_wake_forker_thread);
+DEFINE_WRITEBACK_EVENT(writeback_bdi_register);
+DEFINE_WRITEBACK_EVENT(writeback_bdi_unregister);
+DEFINE_WRITEBACK_EVENT(writeback_thread_start);
+DEFINE_WRITEBACK_EVENT(writeback_thread_stop);
+
+DECLARE_EVENT_CLASS(wbc_class,
+	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi),
+	TP_ARGS(wbc, bdi),
+	TP_STRUCT__entry(
+		__array(char, name, 32)
+		__field(long, nr_to_write)
+		__field(long, pages_skipped)
+		__field(int, sync_mode)
+		__field(int, for_kupdate)
+		__field(int, for_background)
+		__field(int, for_reclaim)
+		__field(int, range_cyclic)
+		__field(int, more_io)
+		__field(unsigned long, older_than_this)
+		__field(long, range_start)
+		__field(long, range_end)
+	),
+
+	TP_fast_assign(
+		strncpy(__entry->name, dev_name(bdi->dev), 32);
+		__entry->nr_to_write	= wbc->nr_to_write;
+		__entry->pages_skipped	= wbc->pages_skipped;
+		__entry->sync_mode	= wbc->sync_mode;
+		__entry->for_kupdate	= wbc->for_kupdate;
+		__entry->for_background	= wbc->for_background;
+		__entry->for_reclaim	= wbc->for_reclaim;
+		__entry->range_cyclic	= wbc->range_cyclic;
+		__entry->more_io	= wbc->more_io;
+		__entry->older_than_this = wbc->older_than_this ?
+						*wbc->older_than_this : 0;
+		__entry->range_start	= (long)wbc->range_start;
+		__entry->range_end	= (long)wbc->range_end;
+	),
+
+	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
+		"bgrd=%d reclm=%d cyclic=%d more=%d older=0x%lx "
+		"start=0x%lx end=0x%lx",
+		__entry->name,
+		__entry->nr_to_write,
+		__entry->pages_skipped,
+		__entry->sync_mode,
+		__entry->for_kupdate,
+		__entry->for_background,
+		__entry->for_reclaim,
+		__entry->range_cyclic,
+		__entry->more_io,
+		__entry->older_than_this,
+		__entry->range_start,
+		__entry->range_end)
+)
+
+#define DEFINE_WBC_EVENT(name) \
+DEFINE_EVENT(wbc_class, name, \
+	TP_PROTO(struct writeback_control *wbc, struct backing_dev_info *bdi), \
+	TP_ARGS(wbc, bdi))
+DEFINE_WBC_EVENT(wbc_writeback_start);
+DEFINE_WBC_EVENT(wbc_writeback_written);
+DEFINE_WBC_EVENT(wbc_writeback_wait);
+DEFINE_WBC_EVENT(wbc_balance_dirty_start);
+DEFINE_WBC_EVENT(wbc_balance_dirty_written);
+DEFINE_WBC_EVENT(wbc_balance_dirty_wait);
+DEFINE_WBC_EVENT(wbc_writepage);
+
+DECLARE_EVENT_CLASS(writeback_congest_waited_template,
+
+	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
+
+	TP_ARGS(usec_timeout, usec_delayed),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	usec_timeout	)
+		__field(	unsigned int,	usec_delayed	)
+	),
+
+	TP_fast_assign(
+		__entry->usec_timeout	= usec_timeout;
+		__entry->usec_delayed	= usec_delayed;
+	),
+
+	TP_printk("usec_timeout=%u usec_delayed=%u",
+			__entry->usec_timeout,
+			__entry->usec_delayed)
+);
+
+DEFINE_EVENT(writeback_congest_waited_template, writeback_congestion_wait,
+
+	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
+
+	TP_ARGS(usec_timeout, usec_delayed)
+);
+
+DEFINE_EVENT(writeback_congest_waited_template, writeback_wait_iff_congested,
+
+	TP_PROTO(unsigned int usec_timeout, unsigned int usec_delayed),
+
+	TP_ARGS(usec_timeout, usec_delayed)
+);
+
+#endif /* _TRACE_WRITEBACK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1867553c61e5..e16610c208c9 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -18,14 +18,37 @@
 
 #include <linux/ftrace_event.h>
 
+/*
+ * DECLARE_EVENT_CLASS can be used to add a generic function
+ * handlers for events. That is, if all events have the same
+ * parameters and just have distinct trace points.
+ * Each tracepoint can be defined with DEFINE_EVENT and that
+ * will map the DECLARE_EVENT_CLASS to the tracepoint.
+ *
+ * TRACE_EVENT is a one to one mapping between tracepoint and template.
+ */
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
+	DECLARE_EVENT_CLASS(name,			       \
+			     PARAMS(proto),		       \
+			     PARAMS(args),		       \
+			     PARAMS(tstruct),		       \
+			     PARAMS(assign),		       \
+			     PARAMS(print));		       \
+	DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));
+
+
 #undef __field
 #define __field(type, item)		type	item;
 
+#undef __field_ext
+#define __field_ext(type, item, filter_type)	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;
+#define __dynamic_array(type, item, len) u32 __data_loc_##item;
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
@@ -33,14 +56,35 @@
 #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
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print)	\
+	struct ftrace_raw_##name {					\
+		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	__used		\
+	__attribute__((__aligned__(4))) event_##name
+
+#undef DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
+
+/* Callbacks are meaningless to ftrace. */
+#undef TRACE_EVENT_FN
+#define TRACE_EVENT_FN(name, proto, args, tstruct,			\
+		assign, print, reg, unreg)				\
+	TRACE_EVENT(name, PARAMS(proto), PARAMS(args),			\
+		PARAMS(tstruct), PARAMS(assign), PARAMS(print))		\
+
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(name, value)					\
+	__TRACE_EVENT_FLAGS(name, value)
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
@@ -51,113 +95,46 @@
  * Include the following:
  *
  * struct ftrace_data_offsets_<call> {
- *	int				<item1>;
- *	int				<item2>;
+ *	u32				<item1>;
+ *	u32				<item2>;
  *	[...]
  * };
  *
- * The __dynamic_array() macro will create each int <item>, this is
+ * The __dynamic_array() macro will create each u32 <item>, this is
  * to keep the offset of each array from the beginning of the event.
+ * The size of an array is also encoded, in the higher 16 bits of <item>.
  */
 
 #undef __field
-#define __field(type, item);
+#define __field(type, item)
+
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
 
 #undef __array
 #define __array(type, item, len)
 
 #undef __dynamic_array
-#define __dynamic_array(type, item, len)	int item;
+#define __dynamic_array(type, item, len)	u32 item;
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
 
-#undef TRACE_EVENT
-#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
 	struct ftrace_data_offsets_##call {				\
 		tstruct;						\
 	};
 
-#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)
 
-/*
- * 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 DEFINE_EVENT_PRINT
+#define DEFINE_EVENT_PRINT(template, name, proto, args, print)	\
+	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
-#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;							\
-}
+#undef TRACE_EVENT_FLAGS
+#define TRACE_EVENT_FLAGS(event, flag)
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
@@ -172,22 +149,22 @@ ftrace_format_##call(struct trace_seq *s)				\
  *	struct trace_seq *s = &iter->seq;
  *	struct ftrace_raw_<call> *field; <-- defined in stage 1
  *	struct trace_entry *entry;
- *	struct trace_seq *p;
+ *	struct trace_seq *p = &iter->tmp_seq;
  *	int ret;
  *
  *	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);
  *	trace_seq_init(p);
- *	ret = trace_seq_printf(s, <TP_printk> "\n");
- *	put_cpu();
+ *	ret = trace_seq_printf(s, "%s: ", <call>);
+ *	if (ret)
+ *		ret = trace_seq_printf(s, <TP_printk> "\n");
  *	if (!ret)
  *		return TRACE_TYPE_PARTIAL_LINE;
  *
@@ -207,7 +184,7 @@ ftrace_format_##call(struct trace_seq *s)				\
 
 #undef __get_dynamic_array
 #define __get_dynamic_array(field)	\
-		((void *)__entry + __entry->__data_loc_##field)
+		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
 
 #undef __get_str
 #define __get_str(field) (char *)__get_dynamic_array(field)
@@ -215,9 +192,9 @@ ftrace_format_##call(struct trace_seq *s)				\
 #undef __print_flags
 #define __print_flags(flag, delim, flag_array...)			\
 	({								\
-		static const struct trace_print_flags flags[] =		\
+		static const struct trace_print_flags __flags[] =	\
 			{ flag_array, { -1, NULL }};			\
-		ftrace_print_flags_seq(p, delim, flag, flags);		\
+		ftrace_print_flags_seq(p, delim, flag, __flags);	\
 	})
 
 #undef __print_symbolic
@@ -228,84 +205,141 @@ ftrace_format_##call(struct trace_seq *s)				\
 		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)	\
+#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 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;						\
+	struct trace_seq *p = &iter->tmp_seq;				\
 	int ret;							\
 									\
+	event = container_of(trace_event, struct ftrace_event_call,	\
+			     event);					\
+									\
 	entry = iter->ent;						\
 									\
-	if (entry->type != event_##call.id) {				\
+	if (entry->type != event->event.type) {				\
 		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();							\
+	ret = trace_seq_printf(s, "%s: ", event->name);			\
+	if (ret)							\
+		ret = trace_seq_printf(s, print);			\
 	if (!ret)							\
 		return TRACE_TYPE_PARTIAL_LINE;				\
 									\
 	return TRACE_TYPE_HANDLED;					\
-}
-	
+}									\
+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 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;				\
+	struct trace_entry *entry;					\
+	struct trace_seq *p = &iter->tmp_seq;				\
+	int ret;							\
+									\
+	entry = iter->ent;						\
+									\
+	if (entry->type != event_##call.event.type) {			\
+		WARN_ON_ONCE(1);					\
+		return TRACE_TYPE_UNHANDLED;				\
+	}								\
+									\
+	field = (typeof(field))entry;					\
+									\
+	trace_seq_init(p);						\
+	ret = trace_seq_printf(s, "%s: ", #call);			\
+	if (ret)							\
+		ret = trace_seq_printf(s, print);			\
+	if (!ret)							\
+		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)
 
-#undef __field
-#define __field(type, item)						\
+#undef __field_ext
+#define __field_ext(type, item, filter_type)				\
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), is_signed_type(type));	\
+				 sizeof(field.item),			\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
+#undef __field
+#define __field(type, item)	__field_ext(type, item, FILTER_OTHER)
+
 #undef __array
 #define __array(type, item, len)					\
-	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
-	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+	do {								\
+		mutex_lock(&event_storage_mutex);			\
+		BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);			\
+		snprintf(event_storage, sizeof(event_storage),		\
+			 "%s[%d]", #type, len);				\
+		ret = trace_define_field(event_call, event_storage, #item, \
 				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), 0);		\
-	if (ret)							\
-		return ret;
+				 sizeof(field.item),			\
+				 is_signed_type(type), FILTER_OTHER);	\
+		mutex_unlock(&event_storage_mutex);			\
+		if (ret)						\
+			return ret;					\
+	} while (0);
 
 #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);
+	ret = trace_define_field(event_call, "__data_loc " #type "[]", #item,  \
+				 offsetof(typeof(field), __data_loc_##item),   \
+				 sizeof(field.__data_loc_##item),	       \
+				 is_signed_type(type), FILTER_OTHER);
 
 #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)					\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print)	\
+static int notrace							\
+ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 {									\
 	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;							\
 }
 
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)
+
+#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)
 
 /*
@@ -318,6 +352,9 @@ ftrace_define_fields_##call(void)					\
 #undef __field
 #define __field(type, item)
 
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
+
 #undef __array
 #define __array(type, item, len)
 
@@ -325,14 +362,15 @@ ftrace_define_fields_##call(void)					\
 #define __dynamic_array(type, item, len)				\
 	__data_offsets->item = __data_size +				\
 			       offsetof(typeof(*entry), __data);	\
+	__data_offsets->item |= (len * sizeof(type)) << 16;		\
 	__data_size += (len) * sizeof(type);
 
 #undef __string
-#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)       \
+#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(				\
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+static inline notrace int ftrace_get_offsets_##call(			\
 	struct ftrace_data_offsets_##call *__data_offsets, proto)       \
 {									\
 	int __data_size = 0;						\
@@ -343,6 +381,13 @@ static inline int ftrace_get_offsets_##call(				\
 	return __data_size;						\
 }
 
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, name, proto, args)
+
+#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)
 
 /*
@@ -350,135 +395,81 @@ static inline int ftrace_get_offsets_##call(				\
  *
  * 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)
+ * 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();
  *
- *	event = trace_current_buffer_lock_reserve(event_<call>.id,
- *				  sizeof(struct ftrace_raw_<call>),
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
+ *	event = trace_current_buffer_lock_reserve(&buffer,
+ *				  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(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;
- * }
+ *	{ <assign>; }  <-- Here we assign the entries by the __field and
+ *			   __array macros.
  *
- * static void ftrace_unreg_event_<call>(void)
- * {
- *	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 int ftrace_raw_init_event_<call>(void)
- * {
- *	int id;
+ * static const char print_fmt_<call>[] = <TP_printk>;
  *
- *	id = register_ftrace_event(&ftrace_event_type_<call>);
- *	if (!id)
- *		return -ENODEV;
- *	event_<call>.id = id;
- *	return 0;
- * }
+ * 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,
+ *	.reg			= ftrace_event_reg,
+ * };
  *
  * 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>,
- * }
+ *	.class			= event_class_<template>,
+ *	.event			= &ftrace_event_type_<call>,
+ *	.print_fmt		= print_fmt_<call>,
+ * };
  *
  */
 
-#undef TP_FMT
-#define TP_FMT(fmt, args...)	fmt "\n", ##args
+#ifdef CONFIG_PERF_EVENTS
 
-#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_PERF_PROTO(call, proto)					\
+	static notrace void						\
+	perf_trace_##call(void *__data, proto);
 
-#define _TRACE_PROFILE_INIT(call)					\
-	.profile_count = ATOMIC_INIT(-1),				\
-	.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(call, proto, args)
-#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
@@ -500,18 +491,23 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 #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;				\
+#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_##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 ftrace_event_call *event_call = &event_##call;		\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
+	struct ring_buffer *buffer;					\
 	unsigned long irq_flags;					\
 	int __data_size;						\
 	int pc;								\
@@ -521,71 +517,244 @@ static void ftrace_raw_event_##call(proto)				\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
-	event = trace_current_buffer_lock_reserve(event_##call.id,	\
+	event = trace_current_buffer_lock_reserve(&buffer,		\
+				 event_call->event.type,		\
 				 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)				\
+	if (!filter_current_check_discard(buffer, event_call, entry, event)) \
+		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 inline void ftrace_test_probe_##call(void)			\
 {									\
-	unregister_trace_##call(ftrace_raw_event_##call);		\
-}									\
+	check_trace_callback_type_##call(ftrace_raw_event_##template);	\
+}
+
+#undef DEFINE_EVENT_PRINT
+#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)	\
+_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,		\
+	.reg			= ftrace_event_reg,			\
+	_TRACE_PERF_INIT(call)						\
+};
+
+#undef DEFINE_EVENT
+#define DEFINE_EVENT(template, call, proto, args)			\
 									\
-static struct trace_event ftrace_event_type_##call = {			\
-	.trace			= ftrace_raw_output_##call,		\
-};									\
+static struct ftrace_event_call __used					\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name			= #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 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 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		= 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)					\
+	.class			= &event_class_##template,		\
+	.event.funcs		= &ftrace_event_type_funcs_##call,	\
+	.print_fmt		= print_fmt_##call,			\
 }
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef _TRACE_PROFILE
+/*
+ * 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_perf_<call>(proto)
+ * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
+ *	struct ftrace_event_call *event_call = &event_<call>;
+ *	extern void perf_tp_event(int, u64, u64, void *, int);
+ *	struct ftrace_raw_##call *entry;
+ *	struct perf_trace_buf *trace_buf;
+ *	u64 __addr = 0, __count = 1;
+ *	unsigned long irq_flags;
+ *	struct trace_entry *ent;
+ *	int __entry_size;
+ *	int __data_size;
+ *	int __cpu
+ *	int pc;
+ *
+ *	pc = preempt_count();
+ *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
+ *	// Below we want to get the aligned size by taking into account
+ *	// the u32 field that will later store the buffer size
+ *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ *			     sizeof(u64));
+ *	__entry_size -= sizeof(u32);
+ *
+ *	// Protect the non nmi buffer
+ *	// This also protects the rcu read side
+ *	local_irq_save(irq_flags);
+ *	__cpu = smp_processor_id();
+ *
+ *	if (in_nmi())
+ *		trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
+ *	else
+ *		trace_buf = rcu_dereference_sched(perf_trace_buf);
+ *
+ *	if (!trace_buf)
+ *		goto end;
+ *
+ *	trace_buf = per_cpu_ptr(trace_buf, __cpu);
+ *
+ * 	// Avoid recursion from perf that could mess up the buffer
+ * 	if (trace_buf->recursion++)
+ *		goto end_recursion;
+ *
+ * 	raw_data = trace_buf->buf;
+ *
+ *	// Make recursion update visible before entering perf_tp_event
+ *	// so that we protect from perf recursions.
+ *
+ *	barrier();
+ *
+ *	//zero dead bytes from alignment to avoid stack leak to userspace:
+ *	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;
+ *	entry = (struct ftrace_raw_<call> *)raw_data;
+ *	ent = &entry->ent;
+ *	tracing_generic_entry_update(ent, irq_flags, pc);
+ *	ent->type = event_call->id;
+ *
+ *	<tstruct> <- do some jobs with dynamic arrays
+ *
+ *	<assign>  <- affect our values
+ *
+ *	perf_tp_event(event_call->id, __addr, __count, entry,
+ *		     __entry_size);  <- submit them to perf counter
+ *
+ * }
+ */
+
+#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)
+
+#undef __perf_count
+#define __perf_count(c) __count = (c)
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+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;\
+	struct ftrace_raw_##call *entry;				\
+	struct pt_regs __regs;						\
+	u64 __addr = 0, __count = 1;					\
+	struct hlist_head *head;					\
+	int __entry_size;						\
+	int __data_size;						\
+	int rctx;							\
+									\
+	perf_fetch_caller_regs(&__regs);				\
+									\
+	__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 > PERF_MAX_TRACE_SIZE,		\
+		      "profile buffer not large enough"))		\
+		return;							\
+									\
+	entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(	\
+		__entry_size, event_call->event.type, &__regs, &rctx);	\
+	if (!entry)							\
+		return;							\
+									\
+	tstruct								\
+									\
+	{ assign; }							\
+									\
+	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 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_PERF_EVENTS */
+
 #undef _TRACE_PROFILE_INIT
 
diff --git a/include/trace/power.h b/include/trace/power.h
deleted file mode 100644
index ef204666e983..000000000000
--- a/include/trace/power.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef _TRACE_POWER_H
-#define _TRACE_POWER_H
-
-#include <linux/ktime.h>
-#include <linux/tracepoint.h>
-
-enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
-};
-
-struct power_trace {
-	ktime_t			stamp;
-	ktime_t			end;
-	int			type;
-	int			state;
-};
-
-DECLARE_TRACE(power_start,
-	TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state),
-	      TP_ARGS(it, type, state));
-
-DECLARE_TRACE(power_mark,
-	TP_PROTO(struct power_trace *it, unsigned int type, unsigned int state),
-	      TP_ARGS(it, type, state));
-
-DECLARE_TRACE(power_end,
-	TP_PROTO(struct power_trace *it),
-	      TP_ARGS(it));
-
-#endif /* _TRACE_POWER_H */
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 8cfe515cbc47..31966a4fb8cc 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -1,35 +1,57 @@
 #ifndef _TRACE_SYSCALL_H
 #define _TRACE_SYSCALL_H
 
+#include <linux/tracepoint.h>
+#include <linux/unistd.h>
+#include <linux/ftrace_event.h>
+
 #include <asm/ptrace.h>
 
+
 /*
  * A syscall entry in the ftrace syscalls array.
  *
  * @name: name of the syscall
+ * @syscall_nr: number of the syscall
  * @nb_args: number of parameters it takes
  * @types: list of types as strings
  * @args: list of args as strings (args[i] matches types[i])
+ * @enter_event: associated syscall_enter trace event
+ * @exit_event: associated syscall_exit trace event
  */
 struct syscall_metadata {
 	const char	*name;
+	int		syscall_nr;
 	int		nb_args;
 	const char	**types;
 	const char	**args;
+	struct list_head enter_fields;
+
+	struct ftrace_event_call *enter_event;
+	struct ftrace_event_call *exit_event;
 };
 
 #ifdef CONFIG_FTRACE_SYSCALLS
-extern void arch_init_ftrace_syscalls(void);
-extern struct syscall_metadata *syscall_nr_to_meta(int nr);
-extern void start_ftrace_syscalls(void);
-extern void stop_ftrace_syscalls(void);
-extern void ftrace_syscall_enter(struct pt_regs *regs);
-extern void ftrace_syscall_exit(struct pt_regs *regs);
-#else
-static inline void start_ftrace_syscalls(void)			{ }
-static inline void stop_ftrace_syscalls(void)			{ }
-static inline void ftrace_syscall_enter(struct pt_regs *regs)	{ }
-static inline void ftrace_syscall_exit(struct pt_regs *regs)	{ }
+extern unsigned long arch_syscall_addr(int nr);
+extern int init_syscall_trace(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,
+				      struct trace_event *event);
+enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags,
+				     struct trace_event *event);
+#endif
+
+#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 */