sched/core: Fix trace_sched_switch()

__trace_sched_switch_state() is the last remaining PREEMPT_ACTIVE
user, move trace_sched_switch() from prepare_task_switch() to
__schedule() and propagate the @preempt argument.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 9 insertions, 13 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 539d6bc3216a..9b90c57517a9 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -104,22 +104,17 @@ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new,
              TP_ARGS(p));
 
 #ifdef CREATE_TRACE_POINTS
-static inline long __trace_sched_switch_state(struct task_struct *p)
+static inline long __trace_sched_switch_state(bool preempt, struct task_struct *p)
 {
-        long state = p->state;
-
-#ifdef CONFIG_PREEMPT
 #ifdef CONFIG_SCHED_DEBUG
         BUG_ON(p != current);
 #endif /* CONFIG_SCHED_DEBUG */
+
         /*
-         * For all intents and purposes a preempted task is a running task.
+         * Preemption ignores task state, therefore preempted tasks are always
+         * RUNNING (we will not have dequeued if state != RUNNING).
          */
-        if (preempt_count() & PREEMPT_ACTIVE)
-                state = TASK_RUNNING | TASK_STATE_MAX;
-#endif /* CONFIG_PREEMPT */
-
-        return state;
+        return preempt ? TASK_RUNNING | TASK_STATE_MAX : p->state;
 }
 #endif /* CREATE_TRACE_POINTS */
 
@@ -128,10 +123,11 @@ static inline long __trace_sched_switch_state(struct task_struct *p)
  */
 TRACE_EVENT(sched_switch,
 
-        TP_PROTO(struct task_struct *prev,
+        TP_PROTO(bool preempt,
+                 struct task_struct *prev,
                  struct task_struct *next),
 
-        TP_ARGS(prev, next),
+        TP_ARGS(preempt, prev, next),
 
         TP_STRUCT__entry(
                 __array(        char,   prev_comm,      TASK_COMM_LEN   )
@@ -147,7 +143,7 @@ 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     = __trace_sched_switch_state(prev);
+                __entry->prev_state     = __trace_sched_switch_state(preempt, prev);
                 memcpy(__entry->prev_comm, prev->comm, TASK_COMM_LEN);
                 __entry->next_pid       = next->pid;
                 __entry->next_prio      = next->prio;