Merge branch 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'tracing-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (244 commits)
  Revert "x86, bts: reenable ptrace branch trace support"
  tracing: do not translate event helper macros in print format
  ftrace/documentation: fix typo in function grapher name
  tracing/events: convert block trace points to TRACE_EVENT(), fix !CONFIG_BLOCK
  tracing: add protection around module events unload
  tracing: add trace_seq_vprint interface
  tracing: fix the block trace points print size
  tracing/events: convert block trace points to TRACE_EVENT()
  ring-buffer: fix ret in rb_add_time_stamp
  ring-buffer: pass in lockdep class key for reader_lock
  tracing: add annotation to what type of stack trace is recorded
  tracing: fix multiple use of __print_flags and __print_symbolic
  tracing/events: fix output format of user stack
  tracing/events: fix output format of kernel stack
  tracing/trace_stack: fix the number of entries in the header
  ring-buffer: discard timestamps that are at the start of the buffer
  ring-buffer: try to discard unneeded timestamps
  ring-buffer: fix bug in ring_buffer_discard_commit
  ftrace: do not profile functions when disabled
  tracing: make trace pipe recognize latency format flag
  ...

36 files changed, 2213 insertions, 379 deletions

diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 89853bcd27a6..f1736ca7922c 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -63,7 +63,7 @@
 #define BRANCH_PROFILE()
 #endif
 
-#ifdef CONFIG_EVENT_TRACER
+#ifdef CONFIG_EVENT_TRACING
 #define FTRACE_EVENTS()	VMLINUX_SYMBOL(__start_ftrace_events) = .;	\
 			*(_ftrace_events)				\
 			VMLINUX_SYMBOL(__stop_ftrace_events) = .;
diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h
index d960889e92ef..7e4350ece0f8 100644
--- a/include/linux/blktrace_api.h
+++ b/include/linux/blktrace_api.h
@@ -116,9 +116,9 @@ struct blk_io_trace {
  * The remap event
  */
 struct blk_io_trace_remap {
-	__be32 device;
 	__be32 device_from;
-	__be64 sector;
+	__be32 device_to;
+	__be64 sector_from;
 };
 
 enum {
@@ -165,8 +165,9 @@ struct blk_trace {
 
 extern int blk_trace_ioctl(struct block_device *, unsigned, char __user *);
 extern void blk_trace_shutdown(struct request_queue *);
-extern int do_blk_trace_setup(struct request_queue *q,
-	char *name, dev_t dev, struct blk_user_trace_setup *buts);
+extern int do_blk_trace_setup(struct request_queue *q, char *name,
+			      dev_t dev, struct block_device *bdev,
+			      struct blk_user_trace_setup *buts);
 extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 
 /**
@@ -193,22 +194,42 @@ extern void __trace_note_message(struct blk_trace *, const char *fmt, ...);
 extern void blk_add_driver_data(struct request_queue *q, struct request *rq,
 				void *data, size_t len);
 extern int blk_trace_setup(struct request_queue *q, char *name, dev_t dev,
+			   struct block_device *bdev,
 			   char __user *arg);
 extern int blk_trace_startstop(struct request_queue *q, int start);
 extern int blk_trace_remove(struct request_queue *q);
+extern int blk_trace_init_sysfs(struct device *dev);
 
 extern struct attribute_group blk_trace_attr_group;
 
 #else /* !CONFIG_BLK_DEV_IO_TRACE */
-#define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
-#define blk_trace_shutdown(q)			do { } while (0)
-#define do_blk_trace_setup(q, name, dev, buts)	(-ENOTTY)
-#define blk_add_driver_data(q, rq, data, len)	do {} while (0)
-#define blk_trace_setup(q, name, dev, arg)	(-ENOTTY)
-#define blk_trace_startstop(q, start)		(-ENOTTY)
-#define blk_trace_remove(q)			(-ENOTTY)
-#define blk_add_trace_msg(q, fmt, ...)		do { } while (0)
+# define blk_trace_ioctl(bdev, cmd, arg)		(-ENOTTY)
+# define blk_trace_shutdown(q)				do { } while (0)
+# define do_blk_trace_setup(q, name, dev, bdev, buts)	(-ENOTTY)
+# define blk_add_driver_data(q, rq, data, len)		do {} while (0)
+# define blk_trace_setup(q, name, dev, bdev, arg)	(-ENOTTY)
+# define blk_trace_startstop(q, start)			(-ENOTTY)
+# define blk_trace_remove(q)				(-ENOTTY)
+# define blk_add_trace_msg(q, fmt, ...)			do { } while (0)
+static inline int blk_trace_init_sysfs(struct device *dev)
+{
+	return 0;
+}
 
 #endif /* CONFIG_BLK_DEV_IO_TRACE */
+
+#if defined(CONFIG_EVENT_TRACING) && defined(CONFIG_BLOCK)
+
+static inline int blk_cmd_buf_len(struct request *rq)
+{
+	return blk_pc_request(rq) ? rq->cmd_len * 3 : 1;
+}
+
+extern void blk_dump_cmd(char *buf, struct request *rq);
+extern void blk_fill_rwbs(char *rwbs, u32 rw, int bytes);
+extern void blk_fill_rwbs_rq(char *rwbs, struct request *rq);
+
+#endif /* CONFIG_EVENT_TRACING && CONFIG_BLOCK */
+
 #endif /* __KERNEL__ */
 #endif
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 8a0c2f221e6b..39b95c56587e 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -233,8 +233,6 @@ extern int ftrace_arch_read_dyn_info(char *buf, int size);
 
 extern int skip_trace(unsigned long ip);
 
-extern void ftrace_release(void *start, unsigned long size);
-
 extern void ftrace_disable_daemon(void);
 extern void ftrace_enable_daemon(void);
 #else
@@ -325,13 +323,8 @@ static inline void __ftrace_enabled_restore(int enabled)
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
 extern void ftrace_init(void);
-extern void ftrace_init_module(struct module *mod,
-			       unsigned long *start, unsigned long *end);
 #else
 static inline void ftrace_init(void) { }
-static inline void
-ftrace_init_module(struct module *mod,
-		   unsigned long *start, unsigned long *end) { }
 #endif
 
 /*
@@ -368,6 +361,7 @@ struct ftrace_ret_stack {
 	unsigned long ret;
 	unsigned long func;
 	unsigned long long calltime;
+	unsigned long long subtime;
 };
 
 /*
@@ -379,8 +373,6 @@ extern void return_to_handler(void);
 
 extern int
 ftrace_push_return_trace(unsigned long ret, unsigned long func, int *depth);
-extern void
-ftrace_pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret);
 
 /*
  * Sometimes we don't want to trace a function with the function
@@ -496,8 +488,15 @@ static inline int test_tsk_trace_graph(struct task_struct *tsk)
 
 extern int ftrace_dump_on_oops;
 
+#ifdef CONFIG_PREEMPT
+#define INIT_TRACE_RECURSION		.trace_recursion = 0,
+#endif
+
 #endif /* CONFIG_TRACING */
 
+#ifndef INIT_TRACE_RECURSION
+#define INIT_TRACE_RECURSION
+#endif
 
 #ifdef CONFIG_HW_BRANCH_TRACER
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
new file mode 100644
index 000000000000..5c093ffc655b
--- /dev/null
+++ b/include/linux/ftrace_event.h
@@ -0,0 +1,172 @@
+#ifndef _LINUX_FTRACE_EVENT_H
+#define _LINUX_FTRACE_EVENT_H
+
+#include <linux/trace_seq.h>
+#include <linux/ring_buffer.h>
+#include <linux/percpu.h>
+
+struct trace_array;
+struct tracer;
+struct dentry;
+
+DECLARE_PER_CPU(struct trace_seq, ftrace_event_seq);
+
+struct trace_print_flags {
+	unsigned long		mask;
+	const char		*name;
+};
+
+const char *ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
+				   unsigned long flags,
+				   const struct trace_print_flags *flag_array);
+
+const char *ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
+				     const struct trace_print_flags *symbol_array);
+
+/*
+ * The trace entry - the most basic unit of tracing. This is what
+ * is printed in the end as a single line in the trace output, such as:
+ *
+ *     bash-15816 [01]   235.197585: idle_cpu <- irq_enter
+ */
+struct trace_entry {
+	unsigned short		type;
+	unsigned char		flags;
+	unsigned char		preempt_count;
+	int			pid;
+	int			tgid;
+};
+
+#define FTRACE_MAX_EVENT						\
+	((1 << (sizeof(((struct trace_entry *)0)->type) * 8)) - 1)
+
+/*
+ * Trace iterator - used by printout routines who present trace
+ * results to users and which routines might sleep, etc:
+ */
+struct trace_iterator {
+	struct trace_array	*tr;
+	struct tracer		*trace;
+	void			*private;
+	int			cpu_file;
+	struct mutex		mutex;
+	struct ring_buffer_iter	*buffer_iter[NR_CPUS];
+	unsigned long		iter_flags;
+
+	/* The below is zeroed out in pipe_read */
+	struct trace_seq	seq;
+	struct trace_entry	*ent;
+	int			cpu;
+	u64			ts;
+
+	loff_t			pos;
+	long			idx;
+
+	cpumask_var_t		started;
+};
+
+
+typedef enum print_line_t (*trace_print_func)(struct trace_iterator *iter,
+					      int flags);
+struct trace_event {
+	struct hlist_node	node;
+	struct list_head	list;
+	int			type;
+	trace_print_func	trace;
+	trace_print_func	raw;
+	trace_print_func	hex;
+	trace_print_func	binary;
+};
+
+extern int register_ftrace_event(struct trace_event *event);
+extern int unregister_ftrace_event(struct trace_event *event);
+
+/* Return values for print_line callback */
+enum print_line_t {
+	TRACE_TYPE_PARTIAL_LINE	= 0,	/* Retry after flushing the seq */
+	TRACE_TYPE_HANDLED	= 1,
+	TRACE_TYPE_UNHANDLED	= 2,	/* Relay to other output functions */
+	TRACE_TYPE_NO_CONSUME	= 3	/* Handled but ask to not consume */
+};
+
+
+struct ring_buffer_event *
+trace_current_buffer_lock_reserve(int type, unsigned long len,
+				  unsigned long flags, int pc);
+void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+					unsigned long flags, int pc);
+void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+
+void tracing_record_cmdline(struct task_struct *tsk);
+
+struct ftrace_event_call {
+	struct list_head	list;
+	char			*name;
+	char			*system;
+	struct dentry		*dir;
+	struct trace_event	*event;
+	int			enabled;
+	int			(*regfunc)(void);
+	void			(*unregfunc)(void);
+	int			id;
+	int			(*raw_init)(void);
+	int			(*show_format)(struct trace_seq *s);
+	int			(*define_fields)(void);
+	struct list_head	fields;
+	int			filter_active;
+	void			*filter;
+	void			*mod;
+
+#ifdef CONFIG_EVENT_PROFILE
+	atomic_t	profile_count;
+	int		(*profile_enable)(struct ftrace_event_call *);
+	void		(*profile_disable)(struct ftrace_event_call *);
+#endif
+};
+
+#define MAX_FILTER_PRED		32
+#define MAX_FILTER_STR_VAL	128
+
+extern int init_preds(struct ftrace_event_call *call);
+extern void destroy_preds(struct ftrace_event_call *call);
+extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
+extern int filter_current_check_discard(struct ftrace_event_call *call,
+					void *rec,
+					struct ring_buffer_event *event);
+
+extern int trace_define_field(struct ftrace_event_call *call, char *type,
+			      char *name, int offset, int size, int is_signed);
+
+#define is_signed_type(type)	(((type)(-1)) < 0)
+
+int trace_set_clr_event(const char *system, const char *event, int set);
+
+/*
+ * The double __builtin_constant_p is because gcc will give us an error
+ * if we try to allocate the static variable to fmt if it is not a
+ * constant. Even with the outer if statement optimizing out.
+ */
+#define event_trace_printk(ip, fmt, args...)				\
+do {									\
+	__trace_printk_check_format(fmt, ##args);			\
+	tracing_record_cmdline(current);				\
+	if (__builtin_constant_p(fmt)) {				\
+		static const char *trace_printk_fmt			\
+		  __attribute__((section("__trace_printk_fmt"))) =	\
+			__builtin_constant_p(fmt) ? fmt : NULL;		\
+									\
+		__trace_bprintk(ip, trace_printk_fmt, ##args);		\
+	} else								\
+		__trace_printk(ip, fmt, ##args);			\
+} while (0)
+
+#define __common_field(type, item, is_signed)				\
+	ret = trace_define_field(event_call, #type, "common_" #item,	\
+				 offsetof(typeof(field.ent), item),	\
+				 sizeof(field.ent.item), is_signed);	\
+	if (ret)							\
+		return ret;
+
+#endif /* _LINUX_FTRACE_EVENT_H */
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index d87247d2641f..889bf99eca6d 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -174,6 +174,7 @@ extern struct cred init_cred;
 	INIT_TRACE_IRQFLAGS						\
 	INIT_LOCKDEP							\
 	INIT_FTRACE_GRAPH						\
+	INIT_TRACE_RECURSION						\
 }
 
 
diff --git a/include/linux/kmemtrace.h b/include/linux/kmemtrace.h
new file mode 100644
index 000000000000..b616d3930c3b
--- /dev/null
+++ b/include/linux/kmemtrace.h
@@ -0,0 +1,25 @@
+/*
+ * Copyright (C) 2008 Eduard - Gabriel Munteanu
+ *
+ * This file is released under GPL version 2.
+ */
+
+#ifndef _LINUX_KMEMTRACE_H
+#define _LINUX_KMEMTRACE_H
+
+#ifdef __KERNEL__
+
+#include <trace/events/kmem.h>
+
+#ifdef CONFIG_KMEMTRACE
+extern void kmemtrace_init(void);
+#else
+static inline void kmemtrace_init(void)
+{
+}
+#endif
+
+#endif /* __KERNEL__ */
+
+#endif /* _LINUX_KMEMTRACE_H */
+
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 511b09867096..9772d6cbfc82 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,6 +19,7 @@ struct anon_vma;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
+struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -1317,8 +1318,8 @@ int vmemmap_populate_basepages(struct page *start_page,
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern void *alloc_locked_buffer(size_t size);
-extern void free_locked_buffer(void *buffer, size_t size);
-extern void release_locked_buffer(void *buffer, size_t size);
+extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
+				 size_t size);
+extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 #endif /* __KERNEL__ */
 #endif /* _LINUX_MM_H */
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 3d1b7bde1283..97491f78b08c 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -30,6 +30,8 @@ extern unsigned int kmmio_count;
 
 extern int register_kmmio_probe(struct kmmio_probe *p);
 extern void unregister_kmmio_probe(struct kmmio_probe *p);
+extern int kmmio_init(void);
+extern void kmmio_cleanup(void);
 
 #ifdef CONFIG_MMIOTRACE
 /* kmmio is active by some kmmio_probes? */
diff --git a/include/linux/module.h b/include/linux/module.h
index 627ac082e2a6..a8f2c0aa4c32 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -337,6 +337,14 @@ struct module
 	const char **trace_bprintk_fmt_start;
 	unsigned int num_trace_bprintk_fmt;
 #endif
+#ifdef CONFIG_EVENT_TRACING
+	struct ftrace_event_call *trace_events;
+	unsigned int num_trace_events;
+#endif
+#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+	unsigned long *ftrace_callsites;
+	unsigned int num_ftrace_callsites;
+#endif
 
 #ifdef CONFIG_MODULE_UNLOAD
 	/* What modules depend on me? */
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 67c15653fc23..59e133d39d50 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -95,7 +95,6 @@ extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
 extern void exit_ptrace(struct task_struct *tracer);
-extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags);
 #define PTRACE_MODE_READ   1
 #define PTRACE_MODE_ATTACH 2
 /* Returns 0 on success, -errno on denial. */
@@ -327,15 +326,6 @@ static inline void user_enable_block_step(struct task_struct *task)
 #define arch_ptrace_untrace(task)		do { } while (0)
 #endif
 
-#ifndef arch_ptrace_fork
-/*
- * Do machine-specific work to initialize a new task.
- *
- * This is called from copy_process().
- */
-#define arch_ptrace_fork(child, clone_flags)	do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index e1b7b2173885..8670f1575fe1 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -11,7 +11,7 @@ struct ring_buffer_iter;
  * Don't refer to this struct directly, use functions below.
  */
 struct ring_buffer_event {
-	u32		type:2, len:3, time_delta:27;
+	u32		type_len:5, time_delta:27;
 	u32		array[];
 };
 
@@ -24,7 +24,8 @@ struct ring_buffer_event {
  *				  size is variable depending on how much
  *				  padding is needed
  *				 If time_delta is non zero:
- *				  everything else same as RINGBUF_TYPE_DATA
+ *				  array[0] holds the actual length
+ *				  size = 4 + length (bytes)
  *
  * @RINGBUF_TYPE_TIME_EXTEND:	Extend the time delta
  *				 array[0] = time delta (28 .. 59)
@@ -35,22 +36,23 @@ struct ring_buffer_event {
  *				 array[1..2] = tv_sec
  *				 size = 16 bytes
  *
- * @RINGBUF_TYPE_DATA:		Data record
- *				 If len is zero:
+ * <= @RINGBUF_TYPE_DATA_TYPE_LEN_MAX:
+ *				Data record
+ *				 If type_len is zero:
  *				  array[0] holds the actual length
  *				  array[1..(length+3)/4] holds data
- *				  size = 4 + 4 + length (bytes)
+ *				  size = 4 + length (bytes)
  *				 else
- *				  length = len << 2
+ *				  length = type_len << 2
  *				  array[0..(length+3)/4-1] holds data
  *				  size = 4 + length (bytes)
  */
 enum ring_buffer_type {
+	RINGBUF_TYPE_DATA_TYPE_LEN_MAX = 28,
 	RINGBUF_TYPE_PADDING,
 	RINGBUF_TYPE_TIME_EXTEND,
 	/* FIXME: RINGBUF_TYPE_TIME_STAMP not implemented */
 	RINGBUF_TYPE_TIME_STAMP,
-	RINGBUF_TYPE_DATA,
 };
 
 unsigned ring_buffer_event_length(struct ring_buffer_event *event);
@@ -68,13 +70,54 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
+/*
+ * ring_buffer_event_discard can discard any event in the ring buffer.
+ *   it is up to the caller to protect against a reader from
+ *   consuming it or a writer from wrapping and replacing it.
+ *
+ * No external protection is needed if this is called before
+ * the event is commited. But in that case it would be better to
+ * use ring_buffer_discard_commit.
+ *
+ * Note, if an event that has not been committed is discarded
+ * with ring_buffer_event_discard, it must still be committed.
+ */
 void ring_buffer_event_discard(struct ring_buffer_event *event);
 
 /*
+ * ring_buffer_discard_commit will remove an event that has not
+ *   ben committed yet. If this is used, then ring_buffer_unlock_commit
+ *   must not be called on the discarded event. This function
+ *   will try to remove the event from the ring buffer completely
+ *   if another event has not been written after it.
+ *
+ * Example use:
+ *
+ *  if (some_condition)
+ *    ring_buffer_discard_commit(buffer, event);
+ *  else
+ *    ring_buffer_unlock_commit(buffer, event);
+ */
+void ring_buffer_discard_commit(struct ring_buffer *buffer,
+				struct ring_buffer_event *event);
+
+/*
  * size is in bytes for each per CPU buffer.
  */
 struct ring_buffer *
-ring_buffer_alloc(unsigned long size, unsigned flags);
+__ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *key);
+
+/*
+ * Because the ring buffer is generic, if other users of the ring buffer get
+ * traced by ftrace, it can produce lockdep warnings. We need to keep each
+ * ring buffer's lock class separate.
+ */
+#define ring_buffer_alloc(size, flags)			\
+({							\
+	static struct lock_class_key __key;		\
+	__ring_buffer_alloc((size), (flags), &__key);	\
+})
+
 void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
@@ -122,6 +165,8 @@ unsigned long ring_buffer_entries(struct ring_buffer *buffer);
 unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
+unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,
@@ -137,6 +182,11 @@ void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
 int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
 			  size_t len, int cpu, int full);
 
+struct trace_seq;
+
+int ring_buffer_print_entry_header(struct trace_seq *s);
+int ring_buffer_print_page_header(struct trace_seq *s);
+
 enum ring_buffer_flags {
 	RB_FL_OVERWRITE		= 1 << 0,
 };
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d4646ae300f0..d1399660b776 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -97,8 +97,8 @@ struct exec_domain;
 struct futex_pi_state;
 struct robust_list_head;
 struct bio;
-struct bts_tracer;
 struct fs_struct;
+struct bts_context;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -1230,18 +1230,11 @@ struct task_struct {
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-#ifdef CONFIG_X86_PTRACE_BTS
 	/*
 	 * This is the tracer handle for the ptrace BTS extension.
 	 * This field actually belongs to the ptracer task.
 	 */
-	struct bts_tracer *bts;
-	/*
-	 * The buffer to hold the BTS data.
-	 */
-	void *bts_buffer;
-	size_t bts_size;
-#endif /* CONFIG_X86_PTRACE_BTS */
+	struct bts_context *bts;
 
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
@@ -1449,7 +1442,9 @@ struct task_struct {
 #ifdef CONFIG_TRACING
 	/* state flags for use by tracers */
 	unsigned long trace;
-#endif
+	/* bitmask of trace recursion */
+	unsigned long trace_recursion;
+#endif /* CONFIG_TRACING */
 };
 
 /* Future-safe accessor for struct task_struct's cpus_allowed. */
@@ -2022,8 +2017,10 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
+extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
+static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
diff --git a/include/linux/slab_def.h b/include/linux/slab_def.h
index 5ac9b0bcaf9a..713f841ecaa9 100644
--- a/include/linux/slab_def.h
+++ b/include/linux/slab_def.h
@@ -14,7 +14,7 @@
 #include <asm/page.h>		/* kmalloc_sizes.h needs PAGE_SIZE */
 #include <asm/cache.h>		/* kmalloc_sizes.h needs L1_CACHE_BYTES */
 #include <linux/compiler.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 /* Size description struct for general caches. */
 struct cache_sizes {
diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h
index 5046f90c1171..be5d40c43bd2 100644
--- a/include/linux/slub_def.h
+++ b/include/linux/slub_def.h
@@ -10,7 +10,7 @@
 #include <linux/gfp.h>
 #include <linux/workqueue.h>
 #include <linux/kobject.h>
-#include <trace/kmemtrace.h>
+#include <linux/kmemtrace.h>
 
 enum stat_item {
 	ALLOC_FASTPATH,		/* Allocation from cpu slab */
diff --git a/include/linux/trace_seq.h b/include/linux/trace_seq.h
new file mode 100644
index 000000000000..c68bccba2074
--- /dev/null
+++ b/include/linux/trace_seq.h
@@ -0,0 +1,92 @@
+#ifndef _LINUX_TRACE_SEQ_H
+#define _LINUX_TRACE_SEQ_H
+
+#include <linux/fs.h>
+
+/*
+ * Trace sequences are used to allow a function to call several other functions
+ * to create a string of data to use (up to a max of PAGE_SIZE.
+ */
+
+struct trace_seq {
+	unsigned char		buffer[PAGE_SIZE];
+	unsigned int		len;
+	unsigned int		readpos;
+};
+
+static inline void
+trace_seq_init(struct trace_seq *s)
+{
+	s->len = 0;
+	s->readpos = 0;
+}
+
+/*
+ * Currently only defined when tracing is enabled.
+ */
+#ifdef CONFIG_TRACING
+extern int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+	__attribute__ ((format (printf, 2, 3)));
+extern int trace_seq_vprintf(struct trace_seq *s, const char *fmt, va_list args)
+	__attribute__ ((format (printf, 2, 0)));
+extern int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary);
+extern void trace_print_seq(struct seq_file *m, struct trace_seq *s);
+extern ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+				 size_t cnt);
+extern int trace_seq_puts(struct trace_seq *s, const char *str);
+extern int trace_seq_putc(struct trace_seq *s, unsigned char c);
+extern int trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len);
+extern int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				size_t len);
+extern void *trace_seq_reserve(struct trace_seq *s, size_t len);
+extern int trace_seq_path(struct trace_seq *s, struct path *path);
+
+#else /* CONFIG_TRACING */
+static inline int trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
+{
+	return 0;
+}
+static inline int
+trace_seq_bprintf(struct trace_seq *s, const char *fmt, const u32 *binary)
+{
+	return 0;
+}
+
+static inline void trace_print_seq(struct seq_file *m, struct trace_seq *s)
+{
+}
+static inline ssize_t trace_seq_to_user(struct trace_seq *s, char __user *ubuf,
+				 size_t cnt)
+{
+	return 0;
+}
+static inline int trace_seq_puts(struct trace_seq *s, const char *str)
+{
+	return 0;
+}
+static inline int trace_seq_putc(struct trace_seq *s, unsigned char c)
+{
+	return 0;
+}
+static inline int
+trace_seq_putmem(struct trace_seq *s, const void *mem, size_t len)
+{
+	return 0;
+}
+static inline int trace_seq_putmem_hex(struct trace_seq *s, const void *mem,
+				       size_t len)
+{
+	return 0;
+}
+static inline void *trace_seq_reserve(struct trace_seq *s, size_t len)
+{
+	return NULL;
+}
+static inline int trace_seq_path(struct trace_seq *s, struct path *path)
+{
+	return 0;
+}
+#endif /* CONFIG_TRACING */
+
+#endif /* _LINUX_TRACE_SEQ_H */
diff --git a/include/linux/tracepoint.h b/include/linux/tracepoint.h
index d35a7ee7611f..14df7e635d43 100644
--- a/include/linux/tracepoint.h
+++ b/include/linux/tracepoint.h
@@ -31,6 +31,8 @@ struct tracepoint {
 					 * Keep in sync with vmlinux.lds.h.
 					 */
 
+#ifndef DECLARE_TRACE
+
 #define TP_PROTO(args...)	args
 #define TP_ARGS(args...)		args
 
@@ -114,6 +116,7 @@ static inline void tracepoint_update_probe_range(struct tracepoint *begin,
 	struct tracepoint *end)
 { }
 #endif /* CONFIG_TRACEPOINTS */
+#endif /* DECLARE_TRACE */
 
 /*
  * Connect a probe to a tracepoint.
@@ -154,10 +157,8 @@ static inline void tracepoint_synchronize_unregister(void)
 }
 
 #define PARAMS(args...) args
-#define TRACE_FORMAT(name, proto, args, fmt)		\
-	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-
 
+#ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro:
  *
@@ -262,5 +263,6 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define TRACE_EVENT(name, proto, args, struct, assign, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
+#endif
 
 #endif
diff --git a/include/trace/block.h b/include/trace/block.h
deleted file mode 100644
index 25b7068b819e..000000000000
--- a/include/trace/block.h
+++ /dev/null
@@ -1,76 +0,0 @@
-#ifndef _TRACE_BLOCK_H
-#define _TRACE_BLOCK_H
-
-#include <linux/blkdev.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(block_rq_abort,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_insert,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_issue,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_requeue,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_rq_complete,
-	TP_PROTO(struct request_queue *q, struct request *rq),
-	      TP_ARGS(q, rq));
-
-DECLARE_TRACE(block_bio_bounce,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_complete,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_backmerge,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_frontmerge,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_bio_queue,
-	TP_PROTO(struct request_queue *q, struct bio *bio),
-	      TP_ARGS(q, bio));
-
-DECLARE_TRACE(block_getrq,
-	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-	      TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_sleeprq,
-	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
-	      TP_ARGS(q, bio, rw));
-
-DECLARE_TRACE(block_plug,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_timer,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_unplug_io,
-	TP_PROTO(struct request_queue *q),
-	      TP_ARGS(q));
-
-DECLARE_TRACE(block_split,
-	TP_PROTO(struct request_queue *q, struct bio *bio, unsigned int pdu),
-	      TP_ARGS(q, bio, pdu));
-
-DECLARE_TRACE(block_remap,
-	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
-		 sector_t from, sector_t to),
-	      TP_ARGS(q, bio, dev, from, to));
-
-#endif
diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
new file mode 100644
index 000000000000..f7a7ae1e8f90
--- /dev/null
+++ b/include/trace/define_trace.h
@@ -0,0 +1,75 @@
+/*
+ * Trace files that want to automate creationg of all tracepoints defined
+ * in their file should include this file. The following are macros that the
+ * trace file may define:
+ *
+ * TRACE_SYSTEM defines the system the tracepoint is for
+ *
+ * TRACE_INCLUDE_FILE if the file name is something other than TRACE_SYSTEM.h
+ *     This macro may be defined to tell define_trace.h what file to include.
+ *     Note, leave off the ".h".
+ *
+ * TRACE_INCLUDE_PATH if the path is something other than core kernel include/trace
+ *     then this macro can define the path to use. Note, the path is relative to
+ *     define_trace.h, not the file including it. Full path names for out of tree
+ *     modules must be used.
+ */
+
+#ifdef CREATE_TRACE_POINTS
+
+/* Prevent recursion */
+#undef CREATE_TRACE_POINTS
+
+#include <linux/stringify.h>
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
+	DEFINE_TRACE(name)
+
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)	\
+	DEFINE_TRACE(name)
+
+#undef TRACE_INCLUDE
+#undef __TRACE_INCLUDE
+
+#ifndef TRACE_INCLUDE_FILE
+# define TRACE_INCLUDE_FILE TRACE_SYSTEM
+# define UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifndef TRACE_INCLUDE_PATH
+# define __TRACE_INCLUDE(system) <trace/events/system.h>
+# define UNDEF_TRACE_INCLUDE_PATH
+#else
+# define __TRACE_INCLUDE(system) __stringify(TRACE_INCLUDE_PATH/system.h)
+#endif
+
+# define TRACE_INCLUDE(system) __TRACE_INCLUDE(system)
+
+/* Let the trace headers be reread */
+#define TRACE_HEADER_MULTI_READ
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#ifdef CONFIG_EVENT_TRACING
+#include <trace/ftrace.h>
+#endif
+
+#undef TRACE_HEADER_MULTI_READ
+
+/* Only undef what we defined in this file */
+#ifdef UNDEF_TRACE_INCLUDE_FILE
+# undef TRACE_INCLUDE_FILE
+# undef UNDEF_TRACE_INCLUDE_FILE
+#endif
+
+#ifdef UNDEF_TRACE_INCLUDE_PATH
+# undef TRACE_INCLUDE_PATH
+# undef UNDEF_TRACE_INCLUDE_PATH
+#endif
+
+/* We may be processing more files */
+#define CREATE_TRACE_POINTS
+
+#endif /* CREATE_TRACE_POINTS */
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
new file mode 100644
index 000000000000..53effd496a50
--- /dev/null
+++ b/include/trace/events/block.h
@@ -0,0 +1,498 @@
+#if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_BLOCK_H
+
+#include <linux/blktrace_api.h>
+#include <linux/blkdev.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
+TRACE_EVENT(block_rq_abort,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_insert,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned int,	bytes			)
+		__array(  char,		rwbs,	6		)
+		__array(  char,         comm,   TASK_COMM_LEN   )
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->bytes     = blk_pc_request(rq) ? rq->data_len : 0;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __entry->bytes, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_issue,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  unsigned int,	bytes			)
+		__array(  char,		rwbs,	6		)
+		__array(  char,		comm,   TASK_COMM_LEN   )
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->bytes     = blk_pc_request(rq) ? rq->data_len : 0;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %u (%s) %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __entry->bytes, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_rq_requeue,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->errors	   = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+
+TRACE_EVENT(block_rq_complete,
+
+	TP_PROTO(struct request_queue *q, struct request *rq),
+
+	TP_ARGS(q, rq),
+
+	TP_STRUCT__entry(
+		__field(  dev_t,	dev			)
+		__field(  sector_t,	sector			)
+		__field(  unsigned int,	nr_sector		)
+		__field(  int,		errors			)
+		__array(  char,		rwbs,	6		)
+		__dynamic_array( char,	cmd,	blk_cmd_buf_len(rq)	)
+	),
+
+	TP_fast_assign(
+		__entry->dev	   = rq->rq_disk ? disk_devt(rq->rq_disk) : 0;
+		__entry->sector    = blk_pc_request(rq) ? 0 : rq->hard_sector;
+		__entry->nr_sector = blk_pc_request(rq) ?
+						0 : rq->hard_nr_sectors;
+		__entry->errors    = rq->errors;
+
+		blk_fill_rwbs_rq(__entry->rwbs, rq);
+		blk_dump_cmd(__get_str(cmd), rq);
+	),
+
+	TP_printk("%d,%d %s (%s) %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->rwbs, __get_str(cmd),
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->errors)
+);
+TRACE_EVENT(block_bio_bounce,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_complete,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned,	nr_sector	)
+		__field( int,		error		)
+		__array( char,		rwbs,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%d]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->error)
+);
+
+TRACE_EVENT(block_bio_backmerge,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_frontmerge,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_bio_queue,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio),
+
+	TP_ARGS(q, bio),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_getrq,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+	TP_ARGS(q, bio, rw),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+        ),
+
+	TP_fast_assign(
+		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
+		__entry->sector		= bio ? bio->bi_sector : 0;
+		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		blk_fill_rwbs(__entry->rwbs,
+			      bio ? bio->bi_rw : 0, __entry->nr_sector);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+        ),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_sleeprq,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
+
+	TP_ARGS(q, bio, rw),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev			)
+		__field( sector_t,	sector			)
+		__field( unsigned int,	nr_sector		)
+		__array( char,		rwbs,	6		)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio ? bio->bi_bdev->bd_dev : 0;
+		__entry->sector		= bio ? bio->bi_sector : 0;
+		__entry->nr_sector	= bio ? bio->bi_size >> 9 : 0;
+		blk_fill_rwbs(__entry->rwbs,
+			    bio ? bio->bi_rw : 0, __entry->nr_sector);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu + %u [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector, __entry->comm)
+);
+
+TRACE_EVENT(block_plug,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s]", __entry->comm)
+);
+
+TRACE_EVENT(block_unplug_timer,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__field( int,		nr_rq			)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_unplug_io,
+
+	TP_PROTO(struct request_queue *q),
+
+	TP_ARGS(q),
+
+	TP_STRUCT__entry(
+		__field( int,		nr_rq			)
+		__array( char,		comm,	TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->nr_rq	= q->rq.count[READ] + q->rq.count[WRITE];
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
+);
+
+TRACE_EVENT(block_split,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio,
+		 unsigned int new_sector),
+
+	TP_ARGS(q, bio, new_sector),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev				)
+		__field( sector_t,	sector				)
+		__field( sector_t,	new_sector			)
+		__array( char,		rwbs,		6		)
+		__array( char,		comm,		TASK_COMM_LEN	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->new_sector	= new_sector;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+		memcpy(__entry->comm, current->comm, TASK_COMM_LEN);
+	),
+
+	TP_printk("%d,%d %s %llu / %llu [%s]",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  (unsigned long long)__entry->new_sector,
+		  __entry->comm)
+);
+
+TRACE_EVENT(block_remap,
+
+	TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
+		 sector_t from),
+
+	TP_ARGS(q, bio, dev, from),
+
+	TP_STRUCT__entry(
+		__field( dev_t,		dev		)
+		__field( sector_t,	sector		)
+		__field( unsigned int,	nr_sector	)
+		__field( dev_t,		old_dev		)
+		__field( sector_t,	old_sector	)
+		__array( char,		rwbs,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->sector		= bio->bi_sector;
+		__entry->nr_sector	= bio->bi_size >> 9;
+		__entry->old_dev	= dev;
+		__entry->old_sector	= from;
+		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);
+	),
+
+	TP_printk("%d,%d %s %llu + %u <- (%d,%d) %llu",
+		  MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rwbs,
+		  (unsigned long long)__entry->sector,
+		  __entry->nr_sector,
+		  MAJOR(__entry->old_dev), MINOR(__entry->old_dev),
+		  (unsigned long long)__entry->old_sector)
+);
+
+#endif /* _TRACE_BLOCK_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
new file mode 100644
index 000000000000..b0c7ede55eb1
--- /dev/null
+++ b/include/trace/events/irq.h
@@ -0,0 +1,145 @@
+#if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_IRQ_H
+
+#include <linux/tracepoint.h>
+#include <linux/interrupt.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
+#define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
+#define show_softirq_name(val)			\
+	__print_symbolic(val,			\
+			 softirq_name(HI),	\
+			 softirq_name(TIMER),	\
+			 softirq_name(NET_TX),	\
+			 softirq_name(NET_RX),	\
+			 softirq_name(BLOCK),	\
+			 softirq_name(TASKLET),	\
+			 softirq_name(SCHED),	\
+			 softirq_name(HRTIMER),	\
+			 softirq_name(RCU))
+
+/**
+ * irq_handler_entry - called immediately before the irq action handler
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ *
+ * The struct irqaction pointed to by @action contains various
+ * information about the handler, including the device name,
+ * @action->name, and the device id, @action->dev_id. When used in
+ * conjunction with the irq_handler_exit tracepoint, we can figure
+ * out irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_entry,
+
+	TP_PROTO(int irq, struct irqaction *action),
+
+	TP_ARGS(irq, action),
+
+	TP_STRUCT__entry(
+		__field(	int,	irq		)
+		__string(	name,	action->name	)
+	),
+
+	TP_fast_assign(
+		__entry->irq = irq;
+		__assign_str(name, action->name);
+	),
+
+	TP_printk("irq=%d handler=%s", __entry->irq, __get_str(name))
+);
+
+/**
+ * irq_handler_exit - called immediately after the irq action handler returns
+ * @irq: irq number
+ * @action: pointer to struct irqaction
+ * @ret: return value
+ *
+ * If the @ret value is set to IRQ_HANDLED, then we know that the corresponding
+ * @action->handler scuccessully handled this irq. Otherwise, the irq might be
+ * a shared irq line, or the irq was not handled successfully. Can be used in
+ * conjunction with the irq_handler_entry to understand irq handler latencies.
+ */
+TRACE_EVENT(irq_handler_exit,
+
+	TP_PROTO(int irq, struct irqaction *action, int ret),
+
+	TP_ARGS(irq, action, ret),
+
+	TP_STRUCT__entry(
+		__field(	int,	irq	)
+		__field(	int,	ret	)
+	),
+
+	TP_fast_assign(
+		__entry->irq	= irq;
+		__entry->ret	= ret;
+	),
+
+	TP_printk("irq=%d return=%s",
+		  __entry->irq, __entry->ret ? "handled" : "unhandled")
+);
+
+/**
+ * softirq_entry - called immediately before the softirq handler
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter, contains a pointer to the struct softirq_action
+ * which has a pointer to the action handler that is called. By subtracting
+ * the @vec pointer from the @h pointer, we can determine the softirq
+ * number. Also, when used in combination with the softirq_exit tracepoint
+ * we can determine the softirq latency.
+ */
+TRACE_EVENT(softirq_entry,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec),
+
+	TP_STRUCT__entry(
+		__field(	int,	vec			)
+	),
+
+	TP_fast_assign(
+		__entry->vec = (int)(h - vec);
+	),
+
+	TP_printk("softirq=%d action=%s", __entry->vec,
+		  show_softirq_name(__entry->vec))
+);
+
+/**
+ * softirq_exit - called immediately after the softirq handler returns
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the struct softirq_action
+ * that has handled the softirq. By subtracting the @vec pointer from
+ * the @h pointer, we can determine the softirq number. Also, when used in
+ * combination with the softirq_entry tracepoint we can determine the softirq
+ * latency.
+ */
+TRACE_EVENT(softirq_exit,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec),
+
+	TP_STRUCT__entry(
+		__field(	int,	vec			)
+	),
+
+	TP_fast_assign(
+		__entry->vec = (int)(h - vec);
+	),
+
+	TP_printk("softirq=%d action=%s", __entry->vec,
+		  show_softirq_name(__entry->vec))
+);
+
+#endif /*  _TRACE_IRQ_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
new file mode 100644
index 000000000000..9baba50d6512
--- /dev/null
+++ b/include/trace/events/kmem.h
@@ -0,0 +1,231 @@
+#if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_KMEM_H
+
+#include <linux/types.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kmem
+
+/*
+ * The order of these masks is important. Matching masks will be seen
+ * first and the left over flags will end up showing by themselves.
+ *
+ * For example, if we have GFP_KERNEL before GFP_USER we wil get:
+ *
+ *  GFP_KERNEL|GFP_HARDWALL
+ *
+ * Thus most bits set go first.
+ */
+#define show_gfp_flags(flags)						\
+	(flags) ? __print_flags(flags, "|",				\
+	{(unsigned long)GFP_HIGHUSER_MOVABLE,	"GFP_HIGHUSER_MOVABLE"}, \
+	{(unsigned long)GFP_HIGHUSER,		"GFP_HIGHUSER"},	\
+	{(unsigned long)GFP_USER,		"GFP_USER"},		\
+	{(unsigned long)GFP_TEMPORARY,		"GFP_TEMPORARY"},	\
+	{(unsigned long)GFP_KERNEL,		"GFP_KERNEL"},		\
+	{(unsigned long)GFP_NOFS,		"GFP_NOFS"},		\
+	{(unsigned long)GFP_ATOMIC,		"GFP_ATOMIC"},		\
+	{(unsigned long)GFP_NOIO,		"GFP_NOIO"},		\
+	{(unsigned long)__GFP_HIGH,		"GFP_HIGH"},		\
+	{(unsigned long)__GFP_WAIT,		"GFP_WAIT"},		\
+	{(unsigned long)__GFP_IO,		"GFP_IO"},		\
+	{(unsigned long)__GFP_COLD,		"GFP_COLD"},		\
+	{(unsigned long)__GFP_NOWARN,		"GFP_NOWARN"},		\
+	{(unsigned long)__GFP_REPEAT,		"GFP_REPEAT"},		\
+	{(unsigned long)__GFP_NOFAIL,		"GFP_NOFAIL"},		\
+	{(unsigned long)__GFP_NORETRY,		"GFP_NORETRY"},		\
+	{(unsigned long)__GFP_COMP,		"GFP_COMP"},		\
+	{(unsigned long)__GFP_ZERO,		"GFP_ZERO"},		\
+	{(unsigned long)__GFP_NOMEMALLOC,	"GFP_NOMEMALLOC"},	\
+	{(unsigned long)__GFP_HARDWALL,		"GFP_HARDWALL"},	\
+	{(unsigned long)__GFP_THISNODE,		"GFP_THISNODE"},	\
+	{(unsigned long)__GFP_RECLAIMABLE,	"GFP_RECLAIMABLE"},	\
+	{(unsigned long)__GFP_MOVABLE,		"GFP_MOVABLE"}		\
+	) : "GFP_NOWAIT"
+
+TRACE_EVENT(kmalloc,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmem_cache_alloc,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags))
+);
+
+TRACE_EVENT(kmalloc_node,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags,
+		 int node),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+		__field(	int,		node		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+		__entry->node		= node;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->node)
+);
+
+TRACE_EVENT(kmem_cache_alloc_node,
+
+	TP_PROTO(unsigned long call_site,
+		 const void *ptr,
+		 size_t bytes_req,
+		 size_t bytes_alloc,
+		 gfp_t gfp_flags,
+		 int node),
+
+	TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+		__field(	size_t,		bytes_req	)
+		__field(	size_t,		bytes_alloc	)
+		__field(	gfp_t,		gfp_flags	)
+		__field(	int,		node		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+		__entry->bytes_req	= bytes_req;
+		__entry->bytes_alloc	= bytes_alloc;
+		__entry->gfp_flags	= gfp_flags;
+		__entry->node		= node;
+	),
+
+	TP_printk("call_site=%lx ptr=%p bytes_req=%zu bytes_alloc=%zu gfp_flags=%s node=%d",
+		__entry->call_site,
+		__entry->ptr,
+		__entry->bytes_req,
+		__entry->bytes_alloc,
+		show_gfp_flags(__entry->gfp_flags),
+		__entry->node)
+);
+
+TRACE_EVENT(kfree,
+
+	TP_PROTO(unsigned long call_site, const void *ptr),
+
+	TP_ARGS(call_site, ptr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+
+TRACE_EVENT(kmem_cache_free,
+
+	TP_PROTO(unsigned long call_site, const void *ptr),
+
+	TP_ARGS(call_site, ptr),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	call_site	)
+		__field(	const void *,	ptr		)
+	),
+
+	TP_fast_assign(
+		__entry->call_site	= call_site;
+		__entry->ptr		= ptr;
+	),
+
+	TP_printk("call_site=%lx ptr=%p", __entry->call_site, __entry->ptr)
+);
+#endif /* _TRACE_KMEM_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/lockdep.h b/include/trace/events/lockdep.h
new file mode 100644
index 000000000000..0e956c9dfd7e
--- /dev/null
+++ b/include/trace/events/lockdep.h
@@ -0,0 +1,96 @@
+#if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_LOCKDEP_H
+
+#include <linux/lockdep.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lockdep
+
+#ifdef CONFIG_LOCKDEP
+
+TRACE_EVENT(lock_acquire,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
+		int trylock, int read, int check,
+		struct lockdep_map *next_lock, unsigned long ip),
+
+	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, flags)
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+		  (__entry->flags & 2) ? "read " : "",
+		  __get_str(name))
+);
+
+TRACE_EVENT(lock_release,
+
+	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+
+	TP_ARGS(lock, nested, ip),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s", __get_str(name))
+);
+
+#ifdef CONFIG_LOCK_STAT
+
+TRACE_EVENT(lock_contended,
+
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
+
+	TP_ARGS(lock, ip),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+	),
+
+	TP_printk("%s", __get_str(name))
+);
+
+TRACE_EVENT(lock_acquired,
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+
+	TP_ARGS(lock, ip, waittime),
+
+	TP_STRUCT__entry(
+		__string(name, lock->name)
+		__field(unsigned long, wait_usec)
+		__field(unsigned long, wait_nsec_rem)
+	),
+	TP_fast_assign(
+		__assign_str(name, lock->name);
+		__entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
+		__entry->wait_usec = (unsigned long) waittime;
+	),
+	TP_printk("%s (%lu.%03lu us)", __get_str(name), __entry->wait_usec,
+				       __entry->wait_nsec_rem)
+);
+
+#endif
+#endif
+
+#endif /* _TRACE_LOCKDEP_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/sched_event_types.h b/include/trace/events/sched.h
index 63547dc1125f..24ab5bcff7b2 100644
--- a/include/trace/sched_event_types.h
+++ b/include/trace/events/sched.h
@@ -1,9 +1,8 @@
+#if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SCHED_H
 
-/* use <trace/sched.h> instead */
-#ifndef TRACE_EVENT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
 
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM sched
@@ -157,6 +156,7 @@ TRACE_EVENT(sched_switch,
 		__array(	char,	prev_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	prev_pid			)
 		__field(	int,	prev_prio			)
+		__field(	long,	prev_state			)
 		__array(	char,	next_comm,	TASK_COMM_LEN	)
 		__field(	pid_t,	next_pid			)
 		__field(	int,	next_prio			)
@@ -166,13 +166,19 @@ TRACE_EVENT(sched_switch,
 		memcpy(__entry->next_comm, next->comm, TASK_COMM_LEN);
 		__entry->prev_pid	= prev->pid;
 		__entry->prev_prio	= prev->prio;
+		__entry->prev_state	= prev->state;
 		memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
 		__entry->next_pid	= next->pid;
 		__entry->next_prio	= next->prio;
 	),
 
-	TP_printk("task %s:%d [%d] ==> %s:%d [%d]",
+	TP_printk("task %s:%d [%d] (%s) ==> %s:%d [%d]",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
+		__entry->prev_state ?
+		  __print_flags(__entry->prev_state, "|",
+				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
+				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
+				{ 128, "W" }) : "R",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
 
@@ -181,9 +187,9 @@ TRACE_EVENT(sched_switch,
  */
 TRACE_EVENT(sched_migrate_task,
 
-	TP_PROTO(struct task_struct *p, int orig_cpu, int dest_cpu),
+	TP_PROTO(struct task_struct *p, int dest_cpu),
 
-	TP_ARGS(p, orig_cpu, dest_cpu),
+	TP_ARGS(p, dest_cpu),
 
 	TP_STRUCT__entry(
 		__array(	char,	comm,	TASK_COMM_LEN	)
@@ -197,7 +203,7 @@ TRACE_EVENT(sched_migrate_task,
 		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
-		__entry->orig_cpu	= orig_cpu;
+		__entry->orig_cpu	= task_cpu(p);
 		__entry->dest_cpu	= dest_cpu;
 	),
 
@@ -334,4 +340,7 @@ TRACE_EVENT(sched_signal_send,
 		  __entry->sig, __entry->comm, __entry->pid)
 );
 
-#undef TRACE_SYSTEM
+#endif /* _TRACE_SCHED_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
new file mode 100644
index 000000000000..1e8fabb57c06
--- /dev/null
+++ b/include/trace/events/skb.h
@@ -0,0 +1,40 @@
+#if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_SKB_H
+
+#include <linux/skbuff.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM skb
+
+/*
+ * Tracepoint for free an sk_buff:
+ */
+TRACE_EVENT(kfree_skb,
+
+	TP_PROTO(struct sk_buff *skb, void *location),
+
+	TP_ARGS(skb, location),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned short,	protocol	)
+		__field(	void *,		location	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		if (skb) {
+			__entry->protocol = ntohs(skb->protocol);
+		}
+		__entry->location = location;
+	),
+
+	TP_printk("skbaddr=%p protocol=%u location=%p",
+		__entry->skbaddr, __entry->protocol, __entry->location)
+);
+
+#endif /* _TRACE_SKB_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
new file mode 100644
index 000000000000..035f1bff288e
--- /dev/null
+++ b/include/trace/events/workqueue.h
@@ -0,0 +1,100 @@
+#if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_WORKQUEUE_H
+
+#include <linux/workqueue.h>
+#include <linux/sched.h>
+#include <linux/tracepoint.h>
+
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
+TRACE_EVENT(workqueue_insertion,
+
+	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+	TP_ARGS(wq_thread, work),
+
+	TP_STRUCT__entry(
+		__array(char,		thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,		thread_pid)
+		__field(work_func_t,	func)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->func		= work->func;
+	),
+
+	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+		__entry->thread_pid, __entry->func)
+);
+
+TRACE_EVENT(workqueue_execution,
+
+	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
+
+	TP_ARGS(wq_thread, work),
+
+	TP_STRUCT__entry(
+		__array(char,		thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,		thread_pid)
+		__field(work_func_t,	func)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->func		= work->func;
+	),
+
+	TP_printk("thread=%s:%d func=%pF", __entry->thread_comm,
+		__entry->thread_pid, __entry->func)
+);
+
+/* Trace the creation of one workqueue thread on a cpu */
+TRACE_EVENT(workqueue_creation,
+
+	TP_PROTO(struct task_struct *wq_thread, int cpu),
+
+	TP_ARGS(wq_thread, cpu),
+
+	TP_STRUCT__entry(
+		__array(char,	thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,	thread_pid)
+		__field(int,	cpu)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+		__entry->cpu		= cpu;
+	),
+
+	TP_printk("thread=%s:%d cpu=%d", __entry->thread_comm,
+		__entry->thread_pid, __entry->cpu)
+);
+
+TRACE_EVENT(workqueue_destruction,
+
+	TP_PROTO(struct task_struct *wq_thread),
+
+	TP_ARGS(wq_thread),
+
+	TP_STRUCT__entry(
+		__array(char,	thread_comm,	TASK_COMM_LEN)
+		__field(pid_t,	thread_pid)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->thread_comm, wq_thread->comm, TASK_COMM_LEN);
+		__entry->thread_pid	= wq_thread->pid;
+	),
+
+	TP_printk("thread=%s:%d", __entry->thread_comm, __entry->thread_pid)
+);
+
+#endif /* _TRACE_WORKQUEUE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
new file mode 100644
index 000000000000..1867553c61e5
--- /dev/null
+++ b/include/trace/ftrace.h
@@ -0,0 +1,591 @@
+/*
+ * Stage 1 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * struct ftrace_raw_<call> {
+ *	struct trace_entry		ent;
+ *	<type>				<item>;
+ *	<type2>				<item2>[<len>];
+ *	[...]
+ * };
+ *
+ * The <type> <item> is created by the __field(type, item) macro or
+ * the __array(type2, item2, len) macro.
+ * We simply do "type item;", and that will create the fields
+ * in the structure.
+ */
+
+#include <linux/ftrace_event.h>
+
+#undef __field
+#define __field(type, item)		type	item;
+
+#undef __array
+#define __array(type, item, len)	type	item[len];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len) unsigned short __data_loc_##item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
+	struct ftrace_raw_##name {				\
+		struct trace_entry	ent;			\
+		tstruct						\
+		char			__data[0];		\
+	};							\
+	static struct ftrace_event_call event_##name
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+
+/*
+ * Stage 2 of the trace events.
+ *
+ * Include the following:
+ *
+ * struct ftrace_data_offsets_<call> {
+ *	int				<item1>;
+ *	int				<item2>;
+ *	[...]
+ * };
+ *
+ * The __dynamic_array() macro will create each int <item>, this is
+ * to keep the offset of each array from the beginning of the event.
+ */
+
+#undef __field
+#define __field(type, item);
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)	int item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+	struct ftrace_data_offsets_##call {				\
+		tstruct;						\
+	};
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Setup the showing format of trace point.
+ *
+ * int
+ * ftrace_format_##call(struct trace_seq *s)
+ * {
+ *	struct ftrace_raw_##call field;
+ *	int ret;
+ *
+ *	ret = trace_seq_printf(s, #type " " #item ";"
+ *			       " offset:%u; size:%u;\n",
+ *			       offsetof(struct ftrace_raw_##call, item),
+ *			       sizeof(field.type));
+ *
+ * }
+ */
+
+#undef TP_STRUCT__entry
+#define TP_STRUCT__entry(args...) args
+
+#undef __field
+#define __field(type, item)					\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
+			       "offset:%u;\tsize:%u;\n",		\
+			       (unsigned int)offsetof(typeof(field), item), \
+			       (unsigned int)sizeof(field.item));	\
+	if (!ret)							\
+		return 0;
+
+#undef __array
+#define __array(type, item, len)						\
+	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
+			       "offset:%u;\tsize:%u;\n",		\
+			       (unsigned int)offsetof(typeof(field), item), \
+			       (unsigned int)sizeof(field.item));	\
+	if (!ret)							\
+		return 0;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				       \
+	ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t"	       \
+			       "offset:%u;\tsize:%u;\n",		       \
+			       (unsigned int)offsetof(typeof(field),	       \
+					__data_loc_##item),		       \
+			       (unsigned int)sizeof(field.__data_loc_##item)); \
+	if (!ret)							       \
+		return 0;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef __entry
+#define __entry REC
+
+#undef __print_symbolic
+#undef __get_dynamic_array
+#undef __get_str
+
+#undef TP_printk
+#define TP_printk(fmt, args...) "%s, %s\n", #fmt, __stringify(args)
+
+#undef TP_fast_assign
+#define TP_fast_assign(args...) args
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+static int								\
+ftrace_format_##call(struct trace_seq *s)				\
+{									\
+	struct ftrace_raw_##call field __attribute__((unused));		\
+	int ret = 0;							\
+									\
+	tstruct;							\
+									\
+	trace_seq_printf(s, "\nprint fmt: " print);			\
+									\
+	return ret;							\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 3 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * enum print_line_t
+ * ftrace_raw_output_<call>(struct trace_iterator *iter, int flags)
+ * {
+ *	struct trace_seq *s = &iter->seq;
+ *	struct ftrace_raw_<call> *field; <-- defined in stage 1
+ *	struct trace_entry *entry;
+ *	struct trace_seq *p;
+ *	int ret;
+ *
+ *	entry = iter->ent;
+ *
+ *	if (entry->type != event_<call>.id) {
+ *		WARN_ON_ONCE(1);
+ *		return TRACE_TYPE_UNHANDLED;
+ *	}
+ *
+ *	field = (typeof(field))entry;
+ *
+ *	p = get_cpu_var(ftrace_event_seq);
+ *	trace_seq_init(p);
+ *	ret = trace_seq_printf(s, <TP_printk> "\n");
+ *	put_cpu();
+ *	if (!ret)
+ *		return TRACE_TYPE_PARTIAL_LINE;
+ *
+ *	return TRACE_TYPE_HANDLED;
+ * }
+ *
+ * This is the method used to print the raw event to the trace
+ * output format. Note, this is not needed if the data is read
+ * in binary.
+ */
+
+#undef __entry
+#define __entry field
+
+#undef TP_printk
+#define TP_printk(fmt, args...) fmt "\n", args
+
+#undef __get_dynamic_array
+#define __get_dynamic_array(field)	\
+		((void *)__entry + __entry->__data_loc_##field)
+
+#undef __get_str
+#define __get_str(field) (char *)__get_dynamic_array(field)
+
+#undef __print_flags
+#define __print_flags(flag, delim, flag_array...)			\
+	({								\
+		static const struct trace_print_flags flags[] =		\
+			{ flag_array, { -1, NULL }};			\
+		ftrace_print_flags_seq(p, delim, flag, flags);		\
+	})
+
+#undef __print_symbolic
+#define __print_symbolic(value, symbol_array...)			\
+	({								\
+		static const struct trace_print_flags symbols[] =	\
+			{ symbol_array, { -1, NULL }};			\
+		ftrace_print_symbols_seq(p, value, symbols);		\
+	})
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+enum print_line_t							\
+ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
+{									\
+	struct trace_seq *s = &iter->seq;				\
+	struct ftrace_raw_##call *field;				\
+	struct trace_entry *entry;					\
+	struct trace_seq *p;						\
+	int ret;							\
+									\
+	entry = iter->ent;						\
+									\
+	if (entry->type != event_##call.id) {				\
+		WARN_ON_ONCE(1);					\
+		return TRACE_TYPE_UNHANDLED;				\
+	}								\
+									\
+	field = (typeof(field))entry;					\
+									\
+	p = &get_cpu_var(ftrace_event_seq);				\
+	trace_seq_init(p);						\
+	ret = trace_seq_printf(s, #call ": " print);			\
+	put_cpu();							\
+	if (!ret)							\
+		return TRACE_TYPE_PARTIAL_LINE;				\
+									\
+	return TRACE_TYPE_HANDLED;					\
+}
+	
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef __field
+#define __field(type, item)						\
+	ret = trace_define_field(event_call, #type, #item,		\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), is_signed_type(type));	\
+	if (ret)							\
+		return ret;
+
+#undef __array
+#define __array(type, item, len)					\
+	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
+	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
+				 offsetof(typeof(field), item),		\
+				 sizeof(field.item), 0);		\
+	if (ret)							\
+		return ret;
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				       \
+	ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\
+				offsetof(typeof(field), __data_loc_##item),    \
+				 sizeof(field.__data_loc_##item), 0);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
+int									\
+ftrace_define_fields_##call(void)					\
+{									\
+	struct ftrace_raw_##call field;					\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	int ret;							\
+									\
+	__common_field(int, type, 1);					\
+	__common_field(unsigned char, flags, 0);			\
+	__common_field(unsigned char, preempt_count, 0);		\
+	__common_field(int, pid, 1);					\
+	__common_field(int, tgid, 1);					\
+									\
+	tstruct;							\
+									\
+	return ret;							\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * remember the offset of each array from the beginning of the event.
+ */
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__data_offsets->item = __data_size +				\
+			       offsetof(typeof(*entry), __data);	\
+	__data_size += (len) * sizeof(type);
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, strlen(src) + 1)       \
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+static inline int ftrace_get_offsets_##call(				\
+	struct ftrace_data_offsets_##call *__data_offsets, proto)       \
+{									\
+	int __data_size = 0;						\
+	struct ftrace_raw_##call __maybe_unused *entry;			\
+									\
+	tstruct;							\
+									\
+	return __data_size;						\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+/*
+ * Stage 4 of the trace events.
+ *
+ * Override the macros in <trace/trace_events.h> to include the following:
+ *
+ * static void ftrace_event_<call>(proto)
+ * {
+ *	event_trace_printk(_RET_IP_, "<call>: " <fmt>);
+ * }
+ *
+ * static int ftrace_reg_event_<call>(void)
+ * {
+ *	int ret;
+ *
+ *	ret = register_trace_<call>(ftrace_event_<call>);
+ *	if (!ret)
+ *		pr_info("event trace: Could not activate trace point "
+ *			"probe to  <call>");
+ *	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *	unregister_trace_<call>(ftrace_event_<call>);
+ * }
+ *
+ *
+ * For those macros defined with TRACE_EVENT:
+ *
+ * static struct ftrace_event_call event_<call>;
+ *
+ * static void ftrace_raw_event_<call>(proto)
+ * {
+ *	struct ring_buffer_event *event;
+ *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ *	unsigned long irq_flags;
+ *	int pc;
+ *
+ *	local_save_flags(irq_flags);
+ *	pc = preempt_count();
+ *
+ *	event = trace_current_buffer_lock_reserve(event_<call>.id,
+ *				  sizeof(struct ftrace_raw_<call>),
+ *				  irq_flags, pc);
+ *	if (!event)
+ *		return;
+ *	entry	= ring_buffer_event_data(event);
+ *
+ *	<assign>;  <-- Here we assign the entries by the __field and
+ *			__array macros.
+ *
+ *	trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ * }
+ *
+ * static int ftrace_raw_reg_event_<call>(void)
+ * {
+ *	int ret;
+ *
+ *	ret = register_trace_<call>(ftrace_raw_event_<call>);
+ *	if (!ret)
+ *		pr_info("event trace: Could not activate trace point "
+ *			"probe to <call>");
+ *	return ret;
+ * }
+ *
+ * static void ftrace_unreg_event_<call>(void)
+ * {
+ *	unregister_trace_<call>(ftrace_raw_event_<call>);
+ * }
+ *
+ * static struct trace_event ftrace_event_type_<call> = {
+ *	.trace			= ftrace_raw_output_<call>, <-- stage 2
+ * };
+ *
+ * static int ftrace_raw_init_event_<call>(void)
+ * {
+ *	int id;
+ *
+ *	id = register_ftrace_event(&ftrace_event_type_<call>);
+ *	if (!id)
+ *		return -ENODEV;
+ *	event_<call>.id = id;
+ *	return 0;
+ * }
+ *
+ * static struct ftrace_event_call __used
+ * __attribute__((__aligned__(4)))
+ * __attribute__((section("_ftrace_events"))) event_<call> = {
+ *	.name			= "<call>",
+ *	.system			= "<system>",
+ *	.raw_init		= ftrace_raw_init_event_<call>,
+ *	.regfunc		= ftrace_reg_event_<call>,
+ *	.unregfunc		= ftrace_unreg_event_<call>,
+ *	.show_format		= ftrace_format_<call>,
+ * }
+ *
+ */
+
+#undef TP_FMT
+#define TP_FMT(fmt, args...)	fmt "\n", ##args
+
+#ifdef CONFIG_EVENT_PROFILE
+#define _TRACE_PROFILE(call, proto, args)				\
+static void ftrace_profile_##call(proto)				\
+{									\
+	extern void perf_tpcounter_event(int);				\
+	perf_tpcounter_event(event_##call.id);				\
+}									\
+									\
+static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
+{									\
+	int ret = 0;							\
+									\
+	if (!atomic_inc_return(&event_call->profile_count))		\
+		ret = register_trace_##call(ftrace_profile_##call);	\
+									\
+	return ret;							\
+}									\
+									\
+static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
+{									\
+	if (atomic_add_negative(-1, &event_call->profile_count))	\
+		unregister_trace_##call(ftrace_profile_##call);		\
+}
+
+#define _TRACE_PROFILE_INIT(call)					\
+	.profile_count = ATOMIC_INIT(-1),				\
+	.profile_enable = ftrace_profile_enable_##call,			\
+	.profile_disable = ftrace_profile_disable_##call,
+
+#else
+#define _TRACE_PROFILE(call, proto, args)
+#define _TRACE_PROFILE_INIT(call)
+#endif
+
+#undef __entry
+#define __entry entry
+
+#undef __field
+#define __field(type, item)
+
+#undef __array
+#define __array(type, item, len)
+
+#undef __dynamic_array
+#define __dynamic_array(type, item, len)				\
+	__entry->__data_loc_##item = __data_offsets.item;
+
+#undef __string
+#define __string(item, src) __dynamic_array(char, item, -1)       	\
+
+#undef __assign_str
+#define __assign_str(dst, src)						\
+	strcpy(__get_str(dst), src);
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
+									\
+static struct ftrace_event_call event_##call;				\
+									\
+static void ftrace_raw_event_##call(proto)				\
+{									\
+	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	struct ring_buffer_event *event;				\
+	struct ftrace_raw_##call *entry;				\
+	unsigned long irq_flags;					\
+	int __data_size;						\
+	int pc;								\
+									\
+	local_save_flags(irq_flags);					\
+	pc = preempt_count();						\
+									\
+	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+									\
+	event = trace_current_buffer_lock_reserve(event_##call.id,	\
+				 sizeof(*entry) + __data_size,		\
+				 irq_flags, pc);			\
+	if (!event)							\
+		return;							\
+	entry	= ring_buffer_event_data(event);			\
+									\
+									\
+	tstruct								\
+									\
+	{ assign; }							\
+									\
+	if (!filter_current_check_discard(event_call, entry, event))	\
+		trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+}									\
+									\
+static int ftrace_raw_reg_event_##call(void)				\
+{									\
+	int ret;							\
+									\
+	ret = register_trace_##call(ftrace_raw_event_##call);		\
+	if (ret)							\
+		pr_info("event trace: Could not activate trace point "	\
+			"probe to " #call "\n");			\
+	return ret;							\
+}									\
+									\
+static void ftrace_raw_unreg_event_##call(void)				\
+{									\
+	unregister_trace_##call(ftrace_raw_event_##call);		\
+}									\
+									\
+static struct trace_event ftrace_event_type_##call = {			\
+	.trace			= ftrace_raw_output_##call,		\
+};									\
+									\
+static int ftrace_raw_init_event_##call(void)				\
+{									\
+	int id;								\
+									\
+	id = register_ftrace_event(&ftrace_event_type_##call);		\
+	if (!id)							\
+		return -ENODEV;						\
+	event_##call.id = id;						\
+	INIT_LIST_HEAD(&event_##call.fields);				\
+	init_preds(&event_##call);					\
+	return 0;							\
+}									\
+									\
+static struct ftrace_event_call __used					\
+__attribute__((__aligned__(4)))						\
+__attribute__((section("_ftrace_events"))) event_##call = {		\
+	.name			= #call,				\
+	.system			= __stringify(TRACE_SYSTEM),		\
+	.event			= &ftrace_event_type_##call,		\
+	.raw_init		= ftrace_raw_init_event_##call,		\
+	.regfunc		= ftrace_raw_reg_event_##call,		\
+	.unregfunc		= ftrace_raw_unreg_event_##call,	\
+	.show_format		= ftrace_format_##call,			\
+	.define_fields		= ftrace_define_fields_##call,		\
+	_TRACE_PROFILE_INIT(call)					\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#undef _TRACE_PROFILE
+#undef _TRACE_PROFILE_INIT
+
diff --git a/include/trace/irq.h b/include/trace/irq.h
deleted file mode 100644
index ff5d4495dc37..000000000000
--- a/include/trace/irq.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_IRQ_H
-#define _TRACE_IRQ_H
-
-#include <linux/interrupt.h>
-#include <linux/tracepoint.h>
-
-#include <trace/irq_event_types.h>
-
-#endif
diff --git a/include/trace/irq_event_types.h b/include/trace/irq_event_types.h
deleted file mode 100644
index 85964ebd47ec..000000000000
--- a/include/trace/irq_event_types.h
+++ /dev/null
@@ -1,55 +0,0 @@
-
-/* use <trace/irq.h> instead */
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM irq
-
-/*
- * Tracepoint for entry of interrupt handler:
- */
-TRACE_FORMAT(irq_handler_entry,
-	TP_PROTO(int irq, struct irqaction *action),
-	TP_ARGS(irq, action),
-	TP_FMT("irq=%d handler=%s", irq, action->name)
-	);
-
-/*
- * Tracepoint for return of an interrupt handler:
- */
-TRACE_EVENT(irq_handler_exit,
-
-	TP_PROTO(int irq, struct irqaction *action, int ret),
-
-	TP_ARGS(irq, action, ret),
-
-	TP_STRUCT__entry(
-		__field(	int,	irq	)
-		__field(	int,	ret	)
-	),
-
-	TP_fast_assign(
-		__entry->irq	= irq;
-		__entry->ret	= ret;
-	),
-
-	TP_printk("irq=%d return=%s",
-		  __entry->irq, __entry->ret ? "handled" : "unhandled")
-);
-
-TRACE_FORMAT(softirq_entry,
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-	TP_ARGS(h, vec),
-	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-	);
-
-TRACE_FORMAT(softirq_exit,
-	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
-	TP_ARGS(h, vec),
-	TP_FMT("softirq=%d action=%s", (int)(h - vec), softirq_to_name[h-vec])
-	);
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/kmemtrace.h b/include/trace/kmemtrace.h
deleted file mode 100644
index 28ee69f9cd46..000000000000
--- a/include/trace/kmemtrace.h
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (C) 2008 Eduard - Gabriel Munteanu
- *
- * This file is released under GPL version 2.
- */
-
-#ifndef _LINUX_KMEMTRACE_H
-#define _LINUX_KMEMTRACE_H
-
-#ifdef __KERNEL__
-
-#include <linux/tracepoint.h>
-#include <linux/types.h>
-
-#ifdef CONFIG_KMEMTRACE
-extern void kmemtrace_init(void);
-#else
-static inline void kmemtrace_init(void)
-{
-}
-#endif
-
-DECLARE_TRACE(kmalloc,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmem_cache_alloc,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags));
-DECLARE_TRACE(kmalloc_node,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags,
-		      int node),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kmem_cache_alloc_node,
-	      TP_PROTO(unsigned long call_site,
-		      const void *ptr,
-		      size_t bytes_req,
-		      size_t bytes_alloc,
-		      gfp_t gfp_flags,
-		      int node),
-	      TP_ARGS(call_site, ptr, bytes_req, bytes_alloc, gfp_flags, node));
-DECLARE_TRACE(kfree,
-	      TP_PROTO(unsigned long call_site, const void *ptr),
-	      TP_ARGS(call_site, ptr));
-DECLARE_TRACE(kmem_cache_free,
-	      TP_PROTO(unsigned long call_site, const void *ptr),
-	      TP_ARGS(call_site, ptr));
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_KMEMTRACE_H */
-
diff --git a/include/trace/lockdep.h b/include/trace/lockdep.h
deleted file mode 100644
index 5ca67df87f2a..000000000000
--- a/include/trace/lockdep.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_LOCKDEP_H
-#define _TRACE_LOCKDEP_H
-
-#include <linux/lockdep.h>
-#include <linux/tracepoint.h>
-
-#include <trace/lockdep_event_types.h>
-
-#endif
diff --git a/include/trace/lockdep_event_types.h b/include/trace/lockdep_event_types.h
deleted file mode 100644
index adccfcd2ec8f..000000000000
--- a/include/trace/lockdep_event_types.h
+++ /dev/null
@@ -1,44 +0,0 @@
-
-#ifndef TRACE_FORMAT
-# error Do not include this file directly.
-# error Unless you know what you are doing.
-#endif
-
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM lock
-
-#ifdef CONFIG_LOCKDEP
-
-TRACE_FORMAT(lock_acquire,
-	TP_PROTO(struct lockdep_map *lock, unsigned int subclass,
-		int trylock, int read, int check,
-		struct lockdep_map *next_lock, unsigned long ip),
-	TP_ARGS(lock, subclass, trylock, read, check, next_lock, ip),
-	TP_FMT("%s%s%s", trylock ? "try " : "",
-		read ? "read " : "", lock->name)
-	);
-
-TRACE_FORMAT(lock_release,
-	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
-	TP_ARGS(lock, nested, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_FORMAT(lock_contended,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-	TP_ARGS(lock, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-TRACE_FORMAT(lock_acquired,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
-	TP_ARGS(lock, ip),
-	TP_FMT("%s", lock->name)
-	);
-
-#endif
-#endif
-
-#undef TRACE_SYSTEM
diff --git a/include/trace/sched.h b/include/trace/sched.h
deleted file mode 100644
index 4e372a1a29bf..000000000000
--- a/include/trace/sched.h
+++ /dev/null
@@ -1,9 +0,0 @@
-#ifndef _TRACE_SCHED_H
-#define _TRACE_SCHED_H
-
-#include <linux/sched.h>
-#include <linux/tracepoint.h>
-
-#include <trace/sched_event_types.h>
-
-#endif
diff --git a/include/trace/skb.h b/include/trace/skb.h
deleted file mode 100644
index b66206d9be72..000000000000
--- a/include/trace/skb.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef _TRACE_SKB_H_
-#define _TRACE_SKB_H_
-
-#include <linux/skbuff.h>
-#include <linux/tracepoint.h>
-
-DECLARE_TRACE(kfree_skb,
-	TP_PROTO(struct sk_buff *skb, void *location),
-	TP_ARGS(skb, location));
-
-#endif
diff --git a/include/trace/trace_event_types.h b/include/trace/trace_event_types.h
deleted file mode 100644
index df56f5694be6..000000000000
--- a/include/trace/trace_event_types.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>_event_types.h here */
-
-#include <trace/sched_event_types.h>
-#include <trace/irq_event_types.h>
-#include <trace/lockdep_event_types.h>
diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
deleted file mode 100644
index fd13750ca4ba..000000000000
--- a/include/trace/trace_events.h
+++ /dev/null
@@ -1,5 +0,0 @@
-/* trace/<type>.h here */
-
-#include <trace/sched.h>
-#include <trace/irq.h>
-#include <trace/lockdep.h>
diff --git a/include/trace/workqueue.h b/include/trace/workqueue.h
deleted file mode 100644
index 7626523deeba..000000000000
--- a/include/trace/workqueue.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef __TRACE_WORKQUEUE_H
-#define __TRACE_WORKQUEUE_H
-
-#include <linux/tracepoint.h>
-#include <linux/workqueue.h>
-#include <linux/sched.h>
-
-DECLARE_TRACE(workqueue_insertion,
-	   TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-	   TP_ARGS(wq_thread, work));
-
-DECLARE_TRACE(workqueue_execution,
-	   TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
-	   TP_ARGS(wq_thread, work));
-
-/* Trace the creation of one workqueue thread on a cpu */
-DECLARE_TRACE(workqueue_creation,
-	   TP_PROTO(struct task_struct *wq_thread, int cpu),
-	   TP_ARGS(wq_thread, cpu));
-
-DECLARE_TRACE(workqueue_destruction,
-	   TP_PROTO(struct task_struct *wq_thread),
-	   TP_ARGS(wq_thread));
-
-#endif /* __TRACE_WORKQUEUE_H */