The patch titled
wait_task_inactive(): don't consider task->nivcsw
has been removed from the -mm tree. Its filename was
wait_task_inactive-dont-consider-task-nivcsw.patch
This patch was dropped because an alternative patch was merged
The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/
------------------------------------------------------
Subject: wait_task_inactive(): don't consider task->nivcsw
From: Oleg Nesterov <oleg@xxxxxxxxxx>
If wait_task_inactive() returns success the task was deactivated. In that
case schedule() always increments ->nvcsw which alone can be used as a
"generation counter".
If the next call returns the same number, we can be sure that the task was
unscheduled. Otherwise, because we know that .on_rq == 0 again, ->nvcsw
should have been changed in between.
Q: perhaps it is better to do "ncsw = (p->nvcsw << 1) | 1" ? This
decreases the possibility of "was it unscheduled" false positive when
->nvcsw == 0.
Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
Cc: Roland McGrath <roland@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
kernel/sched.c | 7 ++-----
1 file changed, 2 insertions(+), 5 deletions(-)
diff -puN kernel/sched.c~wait_task_inactive-dont-consider-task-nivcsw kernel/sched.c
--- a/kernel/sched.c~wait_task_inactive-dont-consider-task-nivcsw
+++ a/kernel/sched.c
@@ -1925,11 +1925,8 @@ unsigned long wait_task_inactive(struct
running = task_running(rq, p);
on_rq = p->se.on_rq;
ncsw = 0;
- if (!match_state || p->state == match_state) {
- ncsw = p->nivcsw + p->nvcsw;
- if (unlikely(!ncsw))
- ncsw = 1;
- }
+ if (!match_state || p->state == match_state)
+ ncsw = p->nvcsw ?: 1;
task_rq_unlock(rq, &flags);
/*
_
Patches currently in -mm which might be from oleg@xxxxxxxxxx are
linux-next.patch
posix-timers-dont-switch-to-group_leader-if-it_process-dies.patch
posix-timers-always-do-get_task_structtimer-it_process.patch
posix-timers-sys_timer_create-remove-the-buggy-pf_exiting-check.patch
posix-timers-sys_timer_create-simplify-and-s-tasklist-rcu.patch
posix-timers-move-the-initialization-of-timer-sigq-from-send-to-create-path.patch
posix-timers-sys_timer_create-cleanup-the-error-handling.patch
posix-timers-kill-it_sigev_signo-and-it_sigev_value.patch
posix-timers-lock_timer-kill-the-bogus-it_id-check.patch
posix-timers-lock_timer-make-it-readable.patch
wait_task_inactive-dont-consider-task-nivcsw.patch
wait_task_inactive-improve-the-returned-value-for-nvcsw-==-0.patch
posix-timers-use-struct-pid-instead-of-struct-task_struct.patch
posix-timers-check-it_signal-instead-of-it_pid-to-validate-the-timer.patch
posix-timers-simplify-de_thread-exit_itimers-path.patch
make-ptrace_untrace-static.patch
coredump-format_corename-dont-append-%pid-if-multi-threaded.patch
kthread_bind-use-wait_task_inactivetask_uninterruptible.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
