The following commit has been merged into the sched/core branch of tip:
Commit-ID: efe09385864f3441c71711f91e621992f9423c01
Gitweb: https://git.kernel.org/tip/efe09385864f3441c71711f91e621992f9423c01
Author: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
AuthorDate: Fri, 23 Dec 2022 18:32:56 +08:00
Committer: Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Sat, 07 Jan 2023 10:48:38 +01:00
sched/core: Micro-optimize ttwu_runnable()
ttwu_runnable() is used as a fast wakeup path when the wakee task
is running on CPU or runnable on RQ, in both cases we can just
set its state to TASK_RUNNING to prevent a sleep.
If the wakee task is on_cpu running, we don't need to update_rq_clock()
or check_preempt_curr().
But if the wakee task is on_rq && !on_cpu (e.g. an IRQ hit before
the task got to schedule() and the task been preempted), we should
check_preempt_curr() to see if it can preempt the current running.
This also removes the class->task_woken() callback from ttwu_runnable(),
which wasn't required per the RT/DL implementations: any required push
operation would have been queued during class->set_next_task() when p
got preempted.
ttwu_runnable() also loses the update to rq->idle_stamp, as by definition
the rq cannot be idle in this scenario.
Suggested-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: Chengming Zhou <zhouchengming@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Reviewed-by: Valentin Schneider <vschneid@xxxxxxxxxx>
Reviewed-by: Steven Rostedt (Google) <rostedt@xxxxxxxxxxx>
Link: https://lore.kernel.org/r/20221223103257.4962-1-zhouchengming@xxxxxxxxxxxxx
---
kernel/sched/core.c | 13 ++++++++++---
1 file changed, 10 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f99ee69..255a318 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3720,9 +3720,16 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
rq = __task_rq_lock(p, &rf);
if (task_on_rq_queued(p)) {
- /* check_preempt_curr() may use rq clock */
- update_rq_clock(rq);
- ttwu_do_wakeup(rq, p, wake_flags, &rf);
+ if (!task_on_cpu(rq, p)) {
+ /*
+ * When on_rq && !on_cpu the task is preempted, see if
+ * it should preempt the task that is current now.
+ */
+ update_rq_clock(rq);
+ check_preempt_curr(rq, p, wake_flags);
+ }
+ WRITE_ONCE(p->__state, TASK_RUNNING);
+ trace_sched_wakeup(p);
ret = 1;
}
__task_rq_unlock(rq, &rf);
|