9 files changed, 292 insertions, 144 deletions

diff --git a/include/trace/define_trace.h b/include/trace/define_trace.h
index 5acfb1eb4df9..1dfab5401511 100644
--- a/include/trace/define_trace.h
+++ b/include/trace/define_trace.h
@@ -65,6 +65,10 @@
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+/* Make all open coded DECLARE_TRACE nops */
+#undef DECLARE_TRACE
+#define DECLARE_TRACE(name, proto, args)
+
 #ifdef CONFIG_EVENT_TRACING
 #include <trace/ftrace.h>
 #endif
@@ -75,6 +79,7 @@
 #undef DEFINE_EVENT
 #undef DEFINE_EVENT_PRINT
 #undef TRACE_HEADER_MULTI_READ
+#undef DECLARE_TRACE
 
 /* Only undef what we defined in this file */
 #ifdef UNDEF_TRACE_INCLUDE_FILE
diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index 5fb72733331e..d870a918559c 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -40,6 +40,16 @@ DECLARE_EVENT_CLASS(block_rq_with_error,
                   __entry->nr_sector, __entry->errors)
 );
 
+/**
+ * block_rq_abort - abort block operation request
+ * @q: queue containing the block operation request
+ * @rq: block IO operation request
+ *
+ * Called immediately after pending block IO operation request @rq in
+ * queue @q is aborted. The fields in the operation request @rq
+ * can be examined to determine which device and sectors the pending
+ * operation would access.
+ */
 DEFINE_EVENT(block_rq_with_error, block_rq_abort,
 
         TP_PROTO(struct request_queue *q, struct request *rq),
@@ -47,6 +57,15 @@ DEFINE_EVENT(block_rq_with_error, block_rq_abort,
         TP_ARGS(q, rq)
 );
 
+/**
+ * block_rq_requeue - place block IO request back on a queue
+ * @q: queue holding operation
+ * @rq: block IO operation request
+ *
+ * The block operation request @rq is being placed back into queue
+ * @q.  For some reason the request was not completed and needs to be
+ * put back in the queue.
+ */
 DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
 
         TP_PROTO(struct request_queue *q, struct request *rq),
@@ -54,6 +73,17 @@ DEFINE_EVENT(block_rq_with_error, block_rq_requeue,
         TP_ARGS(q, rq)
 );
 
+/**
+ * block_rq_complete - block IO operation completed by device driver
+ * @q: queue containing the block operation request
+ * @rq: block operations request
+ *
+ * The block_rq_complete tracepoint event indicates that some portion
+ * of operation request has been completed by the device driver.  If
+ * the @rq->bio is %NULL, then there is absolutely no additional work to
+ * do for the request. If @rq->bio is non-NULL then there is
+ * additional work required to complete the request.
+ */
 DEFINE_EVENT(block_rq_with_error, block_rq_complete,
 
         TP_PROTO(struct request_queue *q, struct request *rq),
@@ -95,6 +125,16 @@ DECLARE_EVENT_CLASS(block_rq,
                   __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_rq_insert - insert block operation request into queue
+ * @q: target queue
+ * @rq: block IO operation request
+ *
+ * Called immediately before block operation request @rq is inserted
+ * into queue @q.  The fields in the operation request @rq struct can
+ * be examined to determine which device and sectors the pending
+ * operation would access.
+ */
 DEFINE_EVENT(block_rq, block_rq_insert,
 
         TP_PROTO(struct request_queue *q, struct request *rq),
@@ -102,6 +142,14 @@ DEFINE_EVENT(block_rq, block_rq_insert,
         TP_ARGS(q, rq)
 );
 
+/**
+ * block_rq_issue - issue pending block IO request operation to device driver
+ * @q: queue holding operation
+ * @rq: block IO operation operation request
+ *
+ * Called when block operation request @rq from queue @q is sent to a
+ * device driver for processing.
+ */
 DEFINE_EVENT(block_rq, block_rq_issue,
 
         TP_PROTO(struct request_queue *q, struct request *rq),
@@ -109,6 +157,17 @@ DEFINE_EVENT(block_rq, block_rq_issue,
         TP_ARGS(q, rq)
 );
 
+/**
+ * block_bio_bounce - used bounce buffer when processing block operation
+ * @q: queue holding the block operation
+ * @bio: block operation
+ *
+ * A bounce buffer was used to handle the block operation @bio in @q.
+ * This occurs when hardware limitations prevent a direct transfer of
+ * data between the @bio data memory area and the IO device.  Use of a
+ * bounce buffer requires extra copying of data and decreases
+ * performance.
+ */
 TRACE_EVENT(block_bio_bounce,
 
         TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -138,6 +197,14 @@ TRACE_EVENT(block_bio_bounce,
                   __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_bio_complete - completed all work on the block operation
+ * @q: queue holding the block operation
+ * @bio: block operation completed
+ *
+ * This tracepoint indicates there is no further work to do on this
+ * block IO operation @bio.
+ */
 TRACE_EVENT(block_bio_complete,
 
         TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -193,6 +260,14 @@ DECLARE_EVENT_CLASS(block_bio,
                   __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_bio_backmerge - merging block operation to the end of an existing operation
+ * @q: queue holding operation
+ * @bio: new block operation to merge
+ *
+ * Merging block request @bio to the end of an existing block request
+ * in queue @q.
+ */
 DEFINE_EVENT(block_bio, block_bio_backmerge,
 
         TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -200,6 +275,14 @@ DEFINE_EVENT(block_bio, block_bio_backmerge,
         TP_ARGS(q, bio)
 );
 
+/**
+ * block_bio_frontmerge - merging block operation to the beginning of an existing operation
+ * @q: queue holding operation
+ * @bio: new block operation to merge
+ *
+ * Merging block IO operation @bio to the beginning of an existing block
+ * operation in queue @q.
+ */
 DEFINE_EVENT(block_bio, block_bio_frontmerge,
 
         TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -207,6 +290,13 @@ DEFINE_EVENT(block_bio, block_bio_frontmerge,
         TP_ARGS(q, bio)
 );
 
+/**
+ * block_bio_queue - putting new block IO operation in queue
+ * @q: queue holding operation
+ * @bio: new block operation
+ *
+ * About to place the block IO operation @bio into queue @q.
+ */
 DEFINE_EVENT(block_bio, block_bio_queue,
 
         TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -243,6 +333,15 @@ DECLARE_EVENT_CLASS(block_get_rq,
                   __entry->nr_sector, __entry->comm)
 );
 
+/**
+ * block_getrq - get a free request entry in queue for block IO operations
+ * @q: queue for operations
+ * @bio: pending block IO operation
+ * @rw: low bit indicates a read (%0) or a write (%1)
+ *
+ * A request struct for queue @q has been allocated to handle the
+ * block IO operation @bio.
+ */
 DEFINE_EVENT(block_get_rq, block_getrq,
 
         TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
@@ -250,6 +349,17 @@ DEFINE_EVENT(block_get_rq, block_getrq,
         TP_ARGS(q, bio, rw)
 );
 
+/**
+ * block_sleeprq - waiting to get a free request entry in queue for block IO operation
+ * @q: queue for operation
+ * @bio: pending block IO operation
+ * @rw: low bit indicates a read (%0) or a write (%1)
+ *
+ * In the case where a request struct cannot be provided for queue @q
+ * the process needs to wait for an request struct to become
+ * available.  This tracepoint event is generated each time the
+ * process goes to sleep waiting for request struct become available.
+ */
 DEFINE_EVENT(block_get_rq, block_sleeprq,
 
         TP_PROTO(struct request_queue *q, struct bio *bio, int rw),
@@ -257,6 +367,14 @@ DEFINE_EVENT(block_get_rq, block_sleeprq,
         TP_ARGS(q, bio, rw)
 );
 
+/**
+ * block_plug - keep operations requests in request queue
+ * @q: request queue to plug
+ *
+ * Plug the request queue @q.  Do not allow block operation requests
+ * to be sent to the device driver. Instead, accumulate requests in
+ * the queue to improve throughput performance of the block device.
+ */
 TRACE_EVENT(block_plug,
 
         TP_PROTO(struct request_queue *q),
@@ -293,6 +411,13 @@ DECLARE_EVENT_CLASS(block_unplug,
         TP_printk("[%s] %d", __entry->comm, __entry->nr_rq)
 );
 
+/**
+ * block_unplug_timer - timed release of operations requests in queue to device driver
+ * @q: request queue to unplug
+ *
+ * Unplug the request queue @q because a timer expired and allow block
+ * operation requests to be sent to the device driver.
+ */
 DEFINE_EVENT(block_unplug, block_unplug_timer,
 
         TP_PROTO(struct request_queue *q),
@@ -300,6 +425,13 @@ DEFINE_EVENT(block_unplug, block_unplug_timer,
         TP_ARGS(q)
 );
 
+/**
+ * block_unplug_io - release of operations requests in request queue
+ * @q: request queue to unplug
+ *
+ * Unplug request queue @q because device driver is scheduled to work
+ * on elements in the request queue.
+ */
 DEFINE_EVENT(block_unplug, block_unplug_io,
 
         TP_PROTO(struct request_queue *q),
@@ -307,6 +439,17 @@ DEFINE_EVENT(block_unplug, block_unplug_io,
         TP_ARGS(q)
 );
 
+/**
+ * block_split - split a single bio struct into two bio structs
+ * @q: queue containing the bio
+ * @bio: block operation being split
+ * @new_sector: The starting sector for the new bio
+ *
+ * The bio request @bio in request queue @q needs to be split into two
+ * bio requests. The newly created @bio request starts at
+ * @new_sector. This split may be required due to hardware limitation
+ * such as operation crossing device boundaries in a RAID system.
+ */
 TRACE_EVENT(block_split,
 
         TP_PROTO(struct request_queue *q, struct bio *bio,
@@ -337,6 +480,16 @@ TRACE_EVENT(block_split,
                   __entry->comm)
 );
 
+/**
+ * block_remap - map request for a partition to the raw device
+ * @q: queue holding the operation
+ * @bio: revised operation
+ * @dev: device for the operation
+ * @from: original sector for the operation
+ *
+ * An operation for a partition on a block device has been mapped to the
+ * raw block device.
+ */
 TRACE_EVENT(block_remap,
 
         TP_PROTO(struct request_queue *q, struct bio *bio, dev_t dev,
@@ -370,6 +523,17 @@ TRACE_EVENT(block_remap,
                   (unsigned long long)__entry->old_sector)
 );
 
+/**
+ * block_rq_remap - map request for a block operation request
+ * @q: queue holding the operation
+ * @rq: block IO operation request
+ * @dev: device for the operation
+ * @from: original sector for the operation
+ *
+ * The block operation request @rq in @q has been remapped.  The block
+ * operation request @rq holds the current information and @from hold
+ * the original sector.
+ */
 TRACE_EVENT(block_rq_remap,
 
         TP_PROTO(struct request_queue *q, struct request *rq, dev_t dev,
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index 5c1dcfc16c60..2821b86de63b 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -35,15 +35,15 @@ TRACE_EVENT(lock_acquire,
                   __get_str(name))
 );
 
-TRACE_EVENT(lock_release,
+DECLARE_EVENT_CLASS(lock,
 
-        TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+        TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-        TP_ARGS(lock, nested, ip),
+        TP_ARGS(lock, ip),
 
         TP_STRUCT__entry(
-                __string(name, lock->name)
-                __field(void *, lockdep_addr)
+                __string(       name,   lock->name      )
+                __field(        void *, lockdep_addr    )
         ),
 
         TP_fast_assign(
@@ -51,51 +51,30 @@ TRACE_EVENT(lock_release,
                 __entry->lockdep_addr = lock;
         ),
 
-        TP_printk("%p %s",
-                  __entry->lockdep_addr, __get_str(name))
+        TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
 );
 
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_EVENT(lock_contended,
+DEFINE_EVENT(lock, lock_release,
 
         TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-        TP_ARGS(lock, ip),
+        TP_ARGS(lock, ip)
+);
 
-        TP_STRUCT__entry(
-                __string(name, lock->name)
-                __field(void *, lockdep_addr)
-        ),
+#ifdef CONFIG_LOCK_STAT
 
-        TP_fast_assign(
-                __assign_str(name, lock->name);
-                __entry->lockdep_addr = lock;
-        ),
+DEFINE_EVENT(lock, lock_contended,
 
-        TP_printk("%p %s",
-                  __entry->lockdep_addr, __get_str(name))
-);
+        TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-TRACE_EVENT(lock_acquired,
-        TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+        TP_ARGS(lock, ip)
+);
 
-        TP_ARGS(lock, ip, waittime),
+DEFINE_EVENT(lock, lock_acquired,
 
-        TP_STRUCT__entry(
-                __string(name, lock->name)
-                __field(s64, wait_nsec)
-                __field(void *, lockdep_addr)
-        ),
+        TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-        TP_fast_assign(
-                __assign_str(name, lock->name);
-                __entry->wait_nsec = waittime;
-                __entry->lockdep_addr = lock;
-        ),
-        TP_printk("%p %s (%llu ns)", __entry->lockdep_addr,
-                  __get_str(name),
-                  __entry->wait_nsec)
+        TP_ARGS(lock, ip)
 );
 
 #endif
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index 4b0f48ba16a6..c7bb2f0482fe 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -51,11 +51,14 @@ TRACE_EVENT(module_free,
         TP_printk("%s", __get_str(name))
 );
 
+#ifdef CONFIG_MODULE_UNLOAD
+/* trace_module_get/put are only used if CONFIG_MODULE_UNLOAD is defined */
+
 DECLARE_EVENT_CLASS(module_refcnt,
 
-        TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+        TP_PROTO(struct module *mod, unsigned long ip),
 
-        TP_ARGS(mod, ip, refcnt),
+        TP_ARGS(mod, ip),
 
         TP_STRUCT__entry(
                 __field(        unsigned long,  ip              )
@@ -65,7 +68,7 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
         TP_fast_assign(
                 __entry->ip     = ip;
-                __entry->refcnt = refcnt;
+                __entry->refcnt = __this_cpu_read(mod->refptr->incs) + __this_cpu_read(mod->refptr->decs);
                 __assign_str(name, mod->name);
         ),
 
@@ -75,17 +78,18 @@ DECLARE_EVENT_CLASS(module_refcnt,
 
 DEFINE_EVENT(module_refcnt, module_get,
 
-        TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+        TP_PROTO(struct module *mod, unsigned long ip),
 
-        TP_ARGS(mod, ip, refcnt)
+        TP_ARGS(mod, ip)
 );
 
 DEFINE_EVENT(module_refcnt, module_put,
 
-        TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+        TP_PROTO(struct module *mod, unsigned long ip),
 
-        TP_ARGS(mod, ip, refcnt)
+        TP_ARGS(mod, ip)
 );
+#endif /* CONFIG_MODULE_UNLOAD */
 
 TRACE_EVENT(module_request,
 
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index a8989c4547e7..188deca2f3c7 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -1,4 +1,7 @@
-#ifndef _TRACE_NAPI_H_
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM napi
+
+#if !defined(_TRACE_NAPI_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_NAPI_H_
 
 #include <linux/netdevice.h>
@@ -8,4 +11,7 @@ DECLARE_TRACE(napi_poll,
         TP_PROTO(struct napi_struct *napi),
         TP_ARGS(napi));
 
-#endif
+#endif /* _TRACE_NAPI_H_ */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index cfceb0b73e20..4f733ecea46e 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -51,15 +51,12 @@ TRACE_EVENT(sched_kthread_stop_ret,
 
 /*
  * Tracepoint for waiting on task to unschedule:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 TRACE_EVENT(sched_wait_task,
 
-        TP_PROTO(struct rq *rq, struct task_struct *p),
+        TP_PROTO(struct task_struct *p),
 
-        TP_ARGS(rq, p),
+        TP_ARGS(p),
 
         TP_STRUCT__entry(
                 __array(        char,   comm,   TASK_COMM_LEN   )
@@ -79,15 +76,12 @@ TRACE_EVENT(sched_wait_task,
 
 /*
  * Tracepoint for waking up a task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 DECLARE_EVENT_CLASS(sched_wakeup_template,
 
-        TP_PROTO(struct rq *rq, struct task_struct *p, int success),
+        TP_PROTO(struct task_struct *p, int success),
 
-        TP_ARGS(rq, p, success),
+        TP_ARGS(p, success),
 
         TP_STRUCT__entry(
                 __array(        char,   comm,   TASK_COMM_LEN   )
@@ -111,31 +105,25 @@ DECLARE_EVENT_CLASS(sched_wakeup_template,
 );
 
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup,
-             TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-             TP_ARGS(rq, p, success));
+             TP_PROTO(struct task_struct *p, int success),
+             TP_ARGS(p, success));
 
 /*
  * Tracepoint for waking up a new task:
- *
- * (NOTE: the 'rq' argument is not used by generic trace events,
- *        but used by the latency tracer plugin. )
  */
 DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
-             TP_PROTO(struct rq *rq, struct task_struct *p, int success),
-             TP_ARGS(rq, p, success));
+             TP_PROTO(struct task_struct *p, int success),
+             TP_ARGS(p, success));
 
 /*
  * 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   )
diff --git a/include/trace/events/signal.h b/include/trace/events/signal.h
index a510b75ac304..814566c99d29 100644
--- a/include/trace/events/signal.h
+++ b/include/trace/events/signal.h
@@ -100,18 +100,7 @@ TRACE_EVENT(signal_deliver,
                   __entry->sa_handler, __entry->sa_flags)
 );
 
-/**
- * signal_overflow_fail - called when signal queue is overflow
- * @sig: signal number
- * @group: signal to process group or not (bool)
- * @info: pointer to struct siginfo
- *
- * Kernel fails to generate 'sig' signal with 'info' siginfo, because
- * siginfo queue is overflow, and the signal is dropped.
- * 'group' is not 0 if the signal will be sent to a process group.
- * 'sig' is always one of RT signals.
- */
-TRACE_EVENT(signal_overflow_fail,
+DECLARE_EVENT_CLASS(signal_queue_overflow,
 
         TP_PROTO(int sig, int group, struct siginfo *info),
 
@@ -135,6 +124,24 @@ TRACE_EVENT(signal_overflow_fail,
 );
 
 /**
+ * signal_overflow_fail - called when signal queue is overflow
+ * @sig: signal number
+ * @group: signal to process group or not (bool)
+ * @info: pointer to struct siginfo
+ *
+ * Kernel fails to generate 'sig' signal with 'info' siginfo, because
+ * siginfo queue is overflow, and the signal is dropped.
+ * 'group' is not 0 if the signal will be sent to a process group.
+ * 'sig' is always one of RT signals.
+ */
+DEFINE_EVENT(signal_queue_overflow, signal_overflow_fail,
+
+        TP_PROTO(int sig, int group, struct siginfo *info),
+
+        TP_ARGS(sig, group, info)
+);
+
+/**
  * signal_lose_info - called when siginfo is lost
  * @sig: signal number
  * @group: signal to process group or not (bool)
@@ -145,28 +152,13 @@ TRACE_EVENT(signal_overflow_fail,
  * 'group' is not 0 if the signal will be sent to a process group.
  * 'sig' is always one of non-RT signals.
  */
-TRACE_EVENT(signal_lose_info,
+DEFINE_EVENT(signal_queue_overflow, signal_lose_info,
 
         TP_PROTO(int sig, int group, struct siginfo *info),
 
-        TP_ARGS(sig, group, info),
-
-        TP_STRUCT__entry(
-                __field(        int,    sig     )
-                __field(        int,    group   )
-                __field(        int,    errno   )
-                __field(        int,    code    )
-        ),
-
-        TP_fast_assign(
-                __entry->sig    = sig;
-                __entry->group  = group;
-                TP_STORE_SIGINFO(__entry, info);
-        ),
-
-        TP_printk("sig=%d group=%d errno=%d code=%d",
-                  __entry->sig, __entry->group, __entry->errno, __entry->code)
+        TP_ARGS(sig, group, info)
 );
+
 #endif /* _TRACE_SIGNAL_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 0804cd594803..16253db38d73 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -154,9 +154,11 @@
  *
  *      field = (typeof(field))entry;
  *
- *      p = get_cpu_var(ftrace_event_seq);
+ *      p = &get_cpu_var(ftrace_event_seq);
  *      trace_seq_init(p);
- *      ret = trace_seq_printf(s, <TP_printk> "\n");
+ *      ret = trace_seq_printf(s, "%s: ", <call>);
+ *      if (ret)
+ *              ret = trace_seq_printf(s, <TP_printk> "\n");
  *      put_cpu();
  *      if (!ret)
  *              return TRACE_TYPE_PARTIAL_LINE;
@@ -401,18 +403,18 @@ static inline notrace int ftrace_get_offsets_##call(			\
 #undef DEFINE_EVENT
 #define DEFINE_EVENT(template, name, proto, args)                       \
                                                                         \
-static void ftrace_profile_##name(proto);                               \
+static void perf_trace_##name(proto);                                   \
                                                                         \
 static notrace int                                                      \
-ftrace_profile_enable_##name(struct ftrace_event_call *unused)          \
+perf_trace_enable_##name(struct ftrace_event_call *unused)              \
 {                                                                       \
-        return register_trace_##name(ftrace_profile_##name);            \
+        return register_trace_##name(perf_trace_##name);                \
 }                                                                       \
                                                                         \
 static notrace void                                                     \
-ftrace_profile_disable_##name(struct ftrace_event_call *unused)         \
+perf_trace_disable_##name(struct ftrace_event_call *unused)             \
 {                                                                       \
-        unregister_trace_##name(ftrace_profile_##name);                 \
+        unregister_trace_##name(perf_trace_##name);                     \
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -450,38 +452,38 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
  *
  * static void ftrace_raw_event_<call>(proto)
  * {
+ *      struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *      struct ring_buffer_event *event;
  *      struct ftrace_raw_<call> *entry; <-- defined in stage 1
  *      struct ring_buffer *buffer;
  *      unsigned long irq_flags;
+ *      int __data_size;
  *      int pc;
  *
  *      local_save_flags(irq_flags);
  *      pc = preempt_count();
  *
+ *      __data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
  *      event = trace_current_buffer_lock_reserve(&buffer,
  *                                event_<call>.id,
- *                                sizeof(struct ftrace_raw_<call>),
+ *                                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.
+ *      { <assign>; }  <-- Here we assign the entries by the __field and
+ *                         __array macros.
  *
- *      trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
+ *      if (!filter_current_check_discard(buffer, event_call, entry, event))
+ *              trace_current_buffer_unlock_commit(buffer,
+ *                                                 event, irq_flags, pc);
  * }
  *
  * static int ftrace_raw_reg_event_<call>(struct ftrace_event_call *unused)
  * {
- *      int ret;
- *
- *      ret = register_trace_<call>(ftrace_raw_event_<call>);
- *      if (!ret)
- *              pr_info("event trace: Could not activate trace point "
- *                      "probe to <call>");
- *      return ret;
+ *      return register_trace_<call>(ftrace_raw_event_<call>);
  * }
  *
  * static void ftrace_unreg_event_<call>(struct ftrace_event_call *unused)
@@ -493,6 +495,8 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
  *      .trace                  = ftrace_raw_output_<call>, <-- stage 2
  * };
  *
+ * static const char print_fmt_<call>[] = <TP_printk>;
+ *
  * static struct ftrace_event_call __used
  * __attribute__((__aligned__(4)))
  * __attribute__((section("_ftrace_events"))) event_<call> = {
@@ -501,18 +505,20 @@ ftrace_profile_disable_##name(struct ftrace_event_call *unused)		\
  *      .raw_init               = trace_event_raw_init,
  *      .regfunc                = ftrace_reg_event_<call>,
  *      .unregfunc              = ftrace_unreg_event_<call>,
+ *      .print_fmt              = print_fmt_<call>,
+ *      .define_fields          = ftrace_define_fields_<call>,
  * }
  *
  */
 
 #ifdef CONFIG_PERF_EVENTS
 
-#define _TRACE_PROFILE_INIT(call)                                       \
-        .profile_enable = ftrace_profile_enable_##call,                 \
-        .profile_disable = ftrace_profile_disable_##call,
+#define _TRACE_PERF_INIT(call)                                          \
+        .perf_event_enable = perf_trace_enable_##call,                  \
+        .perf_event_disable = perf_trace_disable_##call,
 
 #else
-#define _TRACE_PROFILE_INIT(call)
+#define _TRACE_PERF_INIT(call)
 #endif /* CONFIG_PERF_EVENTS */
 
 #undef __entry
@@ -569,7 +575,6 @@ ftrace_raw_event_id_##call(struct ftrace_event_call *event_call,	\
                 return;                                                 \
         entry   = ring_buffer_event_data(event);                        \
                                                                         \
-                                                                        \
         tstruct                                                         \
                                                                         \
         { assign; }                                                     \
@@ -638,7 +643,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
         .unregfunc              = ftrace_raw_unreg_event_##call,        \
         .print_fmt              = print_fmt_##template,                 \
         .define_fields          = ftrace_define_fields_##template,      \
-        _TRACE_PROFILE_INIT(call)                                       \
+        _TRACE_PERF_INIT(call)                                  \
 }
 
 #undef DEFINE_EVENT_PRINT
@@ -657,18 +662,18 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
         .unregfunc              = ftrace_raw_unreg_event_##call,        \
         .print_fmt              = print_fmt_##call,                     \
         .define_fields          = ftrace_define_fields_##template,      \
-        _TRACE_PROFILE_INIT(call)                                       \
+        _TRACE_PERF_INIT(call)                                  \
 }
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 /*
- * Define the insertion callback to profile events
+ * Define the insertion callback to perf events
  *
  * The job is very similar to ftrace_raw_event_<call> except that we don't
  * insert in the ring buffer but in a perf counter.
  *
- * static void ftrace_profile_<call>(proto)
+ * static void ftrace_perf_<call>(proto)
  * {
  *      struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
  *      struct ftrace_event_call *event_call = &event_<call>;
@@ -699,9 +704,9 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  *      __cpu = smp_processor_id();
  *
  *      if (in_nmi())
- *              trace_buf = rcu_dereference(perf_trace_buf_nmi);
+ *              trace_buf = rcu_dereference_sched(perf_trace_buf_nmi);
  *      else
- *              trace_buf = rcu_dereference(perf_trace_buf);
+ *              trace_buf = rcu_dereference_sched(perf_trace_buf);
  *
  *      if (!trace_buf)
  *              goto end;
@@ -757,8 +762,8 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 #undef DECLARE_EVENT_CLASS
 #define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)  \
 static notrace void                                                     \
-ftrace_profile_templ_##call(struct ftrace_event_call *event_call,       \
-                            proto)                                      \
+perf_trace_templ_##call(struct ftrace_event_call *event_call,           \
+                        struct pt_regs *__regs, proto)                  \
 {                                                                       \
         struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
         struct ftrace_raw_##call *entry;                                \
@@ -773,10 +778,10 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
                              sizeof(u64));                              \
         __entry_size -= sizeof(u32);                                    \
                                                                         \
-        if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE,           \
+        if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE,               \
                       "profile buffer not large enough"))               \
                 return;                                                 \
-        entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare(    \
+        entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(     \
                 __entry_size, event_call->id, &rctx, &irq_flags);       \
         if (!entry)                                                     \
                 return;                                                 \
@@ -784,17 +789,22 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
                                                                         \
         { assign; }                                                     \
                                                                         \
-        ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr,       \
-                               __count, irq_flags);                     \
+        perf_trace_buf_submit(entry, __entry_size, rctx, __addr,        \
+                               __count, irq_flags, __regs);             \
 }
 
 #undef DEFINE_EVENT
-#define DEFINE_EVENT(template, call, proto, args)               \
-static notrace void ftrace_profile_##call(proto)                \
-{                                                               \
-        struct ftrace_event_call *event_call = &event_##call;   \
-                                                                \
-        ftrace_profile_templ_##template(event_call, args);      \
+#define DEFINE_EVENT(template, call, proto, args)                       \
+static notrace void perf_trace_##call(proto)                            \
+{                                                                       \
+        struct ftrace_event_call *event_call = &event_##call;           \
+        struct pt_regs *__regs = &get_cpu_var(perf_trace_regs);         \
+                                                                        \
+        perf_fetch_caller_regs(__regs, 1);                              \
+                                                                        \
+        perf_trace_templ_##template(event_call, __regs, args);          \
+                                                                        \
+        put_cpu_var(perf_trace_regs);                                   \
 }
 
 #undef DEFINE_EVENT_PRINT
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 0387100752f0..e5e5f48dbfb3 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -47,10 +47,10 @@ enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
 #endif
 
 #ifdef CONFIG_PERF_EVENTS
-int prof_sysenter_enable(struct ftrace_event_call *call);
-void prof_sysenter_disable(struct ftrace_event_call *call);
-int prof_sysexit_enable(struct ftrace_event_call *call);
-void prof_sysexit_disable(struct ftrace_event_call *call);
+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 */