1 files changed, 62 insertions, 4 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index f6334782a59..6ba596b07a7 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -100,7 +100,7 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
 	 * For all intents and purposes a preempted task is a running task.
 	 */
 	if (task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)
-		state = TASK_RUNNING;
+		state = TASK_RUNNING | TASK_STATE_MAX;
 #endif
 
 	return state;
@@ -137,13 +137,14 @@ TRACE_EVENT(sched_switch,
 		__entry->next_prio	= next->prio;
 	),
 
-	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s ==> next_comm=%s next_pid=%d next_prio=%d",
+	TP_printk("prev_comm=%s prev_pid=%d prev_prio=%d prev_state=%s%s ==> next_comm=%s next_pid=%d next_prio=%d",
 		__entry->prev_comm, __entry->prev_pid, __entry->prev_prio,
-		__entry->prev_state ?
-		  __print_flags(__entry->prev_state, "|",
+		__entry->prev_state & (TASK_STATE_MAX-1) ?
+		  __print_flags(__entry->prev_state & (TASK_STATE_MAX-1), "|",
 				{ 1, "S"} , { 2, "D" }, { 4, "T" }, { 8, "t" },
 				{ 16, "Z" }, { 32, "X" }, { 64, "x" },
 				{ 128, "W" }) : "R",
+		__entry->prev_state & TASK_STATE_MAX ? "+" : "",
 		__entry->next_comm, __entry->next_pid, __entry->next_prio)
 );
 
@@ -330,6 +331,13 @@ DEFINE_EVENT(sched_stat_template, sched_stat_iowait,
 	     TP_ARGS(tsk, delay));
 
 /*
+ * Tracepoint for accounting blocked time (time the task is in uninterruptible).
+ */
+DEFINE_EVENT(sched_stat_template, sched_stat_blocked,
+	     TP_PROTO(struct task_struct *tsk, u64 delay),
+	     TP_ARGS(tsk, delay));
+
+/*
  * Tracepoint for accounting runtime (time the task is executing
  * on a CPU).
  */
@@ -362,6 +370,56 @@ TRACE_EVENT(sched_stat_runtime,
 			(unsigned long long)__entry->vruntime)
 );
 
+#ifdef CREATE_TRACE_POINTS
+static inline u64 trace_get_sleeptime(struct task_struct *tsk)
+{
+#ifdef CONFIG_SCHEDSTATS
+	u64 block, sleep;
+
+	block = tsk->se.statistics.block_start;
+	sleep = tsk->se.statistics.sleep_start;
+	tsk->se.statistics.block_start = 0;
+	tsk->se.statistics.sleep_start = 0;
+
+	return block ? block : sleep ? sleep : 0;
+#else
+	return 0;
+#endif
+}
+#endif
+
+/*
+ * Tracepoint for accounting sleeptime (time the task is sleeping
+ * or waiting for I/O).
+ */
+TRACE_EVENT(sched_stat_sleeptime,
+
+	TP_PROTO(struct task_struct *tsk, u64 now),
+
+	TP_ARGS(tsk, now),
+
+	TP_STRUCT__entry(
+		__array( char,	comm,	TASK_COMM_LEN	)
+		__field( pid_t,	pid			)
+		__field( u64,	sleeptime		)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		= tsk->pid;
+		__entry->sleeptime = trace_get_sleeptime(tsk);
+		__entry->sleeptime = __entry->sleeptime ?
+				now - __entry->sleeptime : 0;
+	)
+	TP_perf_assign(
+		__perf_count(__entry->sleeptime);
+	),
+
+	TP_printk("comm=%s pid=%d sleeptime=%Lu [ns]",
+			__entry->comm, __entry->pid,
+			(unsigned long long)__entry->sleeptime)
+);
+
 /*
  * Tracepoint for showing priority inheritance modifying a tasks
  * priority.