Skip to contentSkip to conversation

Fix for 10-second delay bug for -stable

PATCH Paul E. McKenney 1 participant 1 message Oct 31, 2018 RCU

lore
Share & tools
lore
#0 lore raw

Hello!

I have lightly tested the following backport of 92aa39e9dc77 ("rcu:
Make need_resched() respond to urgent RCU-QS needs") on v4.12-v4.19. Does it look reasonable from your viewpoint?

If I don't hear otherwise, I will send it along to -stable at the end of this coming weekend, Pacific Time.

This patch does not apply to v4.11 and earlier. I will therefore ignore those releases unless someone reproduces the problem on them.

Thanx, Paul

------------------------------------------------------------------------

commit 0a555b6d58f80dcd93a116c5b197208aeaf9f7ef

Author: Paul E. McKenney <[email protected]>
Date:   Mon Jul 9 13:47:30 2018 -0700

rcu: Make need_resched() respond to urgent RCU-QS needs

commit 92aa39e9dc77 upstream.

The per-CPU rcu_dynticks.rcu_urgent_qs variable communicates an urgent need for an RCU quiescent state from the force-quiescent-state processing within the grace-period kthread to context switches and to cond_resched(). Unfortunately, such urgent needs are not communicated to need_resched(), which is sometimes used to decide when to invoke cond_resched(), for but one example, within the KVM vcpu_run() function. As of v4.15, this can result in synchronize_sched() being delayed by up to ten seconds, which can be problematic, to say nothing of annoying.

This commit therefore checks rcu_dynticks.rcu_urgent_qs from within rcu_check_callbacks(), which is invoked from the scheduling-clock interrupt handler. If the current task is not an idle task and is not executing in usermode, a context switch is forced, and either way, the rcu_dynticks.rcu_urgent_qs variable is set to false. If the current task is an idle task, then RCU's dyntick-idle code will detect the quiescent state, so no further action is required. Similarly, if the task is executing in usermode, other code in rcu_check_callbacks() and its called functions will report the corresponding quiescent state.

[ paulmck: Backported to make patch apply cleanly on older versions. ]
Cc <[email protected]> # 4.12.x - 4.19.x
kernel/rcu/tree.c +9 -0
index 0b760c1369f7..15301ed19da6 100644
@@ -2662,6 +2662,15 @@ void rcu_check_callbacks(int user)
 		rcu_bh_qs();
 	}
 	rcu_preempt_check_callbacks();
+	/* The load-acquire pairs with the store-release setting to true. */
+	if (smp_load_acquire(this_cpu_ptr(&rcu_dynticks.rcu_urgent_qs))) {
+		/* Idle and userspace execution already are quiescent states. */
+		if (!rcu_is_cpu_rrupt_from_idle() && !user) {
+			set_tsk_need_resched(current);
+			set_preempt_need_resched();
+		}
+		__this_cpu_write(rcu_dynticks.rcu_urgent_qs, false);
+	}
 	if (rcu_pending())
 		invoke_rcu_core();