signal: retarget_shared_pending: optimize while_each_thread() loop (fec9993d) · Commits · 戴 / test

retarget_shared_pending() blindly does recalc_sigpending_and_wake() for every sub-thread, this is suboptimal. We can check t->blocked and stop looping once every bit in shared_pending has the new target. Note: we do not take task_is_stopped_or_traced(t) into account, we are not trying to speed up the signal delivery or to avoid the unnecessary (but harmless) signal_wake_up(0) in this unlikely case. Signed-off-by:

Oleg Nesterov <oleg@redhat.com> Reviewed-by:

Matt Fleming <matt.fleming@linux.intel.com> Acked-by:

Tejun Heo <tj@kernel.org>

kernel/signal.c

+15 −4

Original line number	Diff line number	Diff line
		@@ -2200,8 +2200,8 @@ relock:

		/*
		* It could be that complete_signal() picked us to notify about the
		* group-wide signal. Another thread should be notified now to take
		* the signal since we will not.
		* group-wide signal. Other threads should be notified now to take
		* the shared signals in @which since we will not.
		*/
		static void retarget_shared_pending(struct task_struct tsk, sigset_t which)
		{
		@@ -2214,8 +2214,19 @@ static void retarget_shared_pending(struct task_struct tsk, sigset_t which)

		t = tsk;
		while_each_thread(tsk, t) {
		if (!signal_pending(t) && !(t->flags & PF_EXITING))
		recalc_sigpending_and_wake(t);
		if (t->flags & PF_EXITING)
		continue;

		if (!has_pending_signals(&retarget, &t->blocked))
		continue;
		/* Remove the signals this thread can handle. */
		sigandsets(&retarget, &retarget, &t->blocked);

		if (!signal_pending(t))
		signal_wake_up(t, 0);

		if (sigisemptyset(&retarget))
		break;
		}
		}

Admin message