sched: Fix trace_sched_switch(.prev_state)

Gabriele noted that in case of signal_pending_state(), the tracepoint
sees a stale task-state.

Fixes: fa2c3254d7cf ("sched/tracing: Don't re-read p->state when emitting sched_switch event")
Reported-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Valentin Schneider <vschneid@redhat.com>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index cfaca3040b2f88581e96d1bea0a71500dfa06c65..042c978f7c9bf3d70d371b5ac2773bdadc134311 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6571,12 +6571,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
  * Otherwise marks the task's __state as RUNNING
  */
 static bool try_to_block_task(struct rq *rq, struct task_struct *p,
-                             unsigned long task_state)
+                             unsigned long *task_state_p)
 {
+       unsigned long task_state = *task_state_p;
        int flags = DEQUEUE_NOCLOCK;
 
        if (signal_pending_state(task_state, p)) {
                WRITE_ONCE(p->__state, TASK_RUNNING);
+               *task_state_p = TASK_RUNNING;
                return false;
        }
 
@@ -6713,7 +6715,7 @@ static void __sched notrace __schedule(int sched_mode)
                        goto picked;
                }
        } else if (!preempt && prev_state) {
-               try_to_block_task(rq, prev, prev_state);
+               try_to_block_task(rq, prev, &prev_state);
                switch_count = &prev->nvcsw;
        }