perf/trace: Add ability to set a target task for events

A few events are interesting not only for a current task.
For example, sched_stat_* events are interesting for a task
which wakes up. For this reason, it will be good if such
events will be delivered to a target task too.

Now a target task can be set by using __perf_task().

The original idea and a draft patch belongs to Peter Zijlstra.

I need these events for profiling sleep times. sched_switch is used for
getting callchains and sched_stat_* is used for getting time periods.
These events are combined in user space, then it can be analyzed by
perf tools.

Inspired-by: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Arun Sharma <asharma@fb.com>
Signed-off-by: Andrew Vagin <avagin@openvz.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1342016098-213063-1-git-send-email-avagin@openvz.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index af961d6..642928c 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -306,9 +306,10 @@
 
 static inline void
 perf_trace_buf_submit(void *raw_data, int size, int rctx, u64 addr,
-		       u64 count, struct pt_regs *regs, void *head)
+		       u64 count, struct pt_regs *regs, void *head,
+		       struct task_struct *task)
 {
-	perf_tp_event(addr, count, raw_data, size, regs, head, rctx);
+	perf_tp_event(addr, count, raw_data, size, regs, head, rctx, task);
 }
 #endif
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 76c5c8b..7602ccb 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1272,7 +1272,8 @@
 extern void perf_event_init(void);
 extern void perf_tp_event(u64 addr, u64 count, void *record,
 			  int entry_size, struct pt_regs *regs,
-			  struct hlist_head *head, int rctx);
+			  struct hlist_head *head, int rctx,
+			  struct task_struct *task);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index ea7a203..5a8671e 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -73,6 +73,9 @@
 		__entry->prio		= p->prio;
 		__entry->success	= success;
 		__entry->target_cpu	= task_cpu(p);
+	)
+	TP_perf_assign(
+		__perf_task(p);
 	),
 
 	TP_printk("comm=%s pid=%d prio=%d success=%d target_cpu=%03d",
@@ -325,6 +328,7 @@
 	)
 	TP_perf_assign(
 		__perf_count(delay);
+		__perf_task(tsk);
 	),
 
 	TP_printk("comm=%s pid=%d delay=%Lu [ns]",
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index c6bc2fa..a763888 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -712,6 +712,9 @@
 #undef __perf_count
 #define __perf_count(c) __count = (c)
 
+#undef __perf_task
+#define __perf_task(t) __task = (t)
+
 #undef TP_perf_assign
 #define TP_perf_assign(args...) args
 
@@ -725,6 +728,7 @@
 	struct ftrace_raw_##call *entry;				\
 	struct pt_regs __regs;						\
 	u64 __addr = 0, __count = 1;					\
+	struct task_struct *__task = NULL;				\
 	struct hlist_head *head;					\
 	int __entry_size;						\
 	int __data_size;						\
@@ -752,7 +756,7 @@
 									\
 	head = this_cpu_ptr(event_call->perf_events);			\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
-		__count, &__regs, head);				\
+		__count, &__regs, head, __task);			\
 }
 
 /*