Re: [PATCH 3/3] sched: Use cpu_dying() to fix balance_push vs hotplug-rollback

[Peter Zijlstra]

On Tue, Apr 20, 2021 at 04:39:04PM +0200, Peter Zijlstra wrote:
> On Tue, Apr 20, 2021 at 04:20:56PM +0200, Peter Zijlstra wrote:
> > On Tue, Apr 20, 2021 at 10:46:33AM +0100, Vincent Donnefort wrote:
> > 
> > > Found the issue:
> > > 
> > > $ cat hotplug/states:
> > > 219: sched:active
> > > 220: online
> > > 
> > > CPU0: 
> > > 
> > > $ echo 219 > hotplug/fail
> > > $ echo 0 > online
> > > 
> > > => cpu_active = 1 cpu_dying = 1
> > > 
> > > which means that later on, for another CPU hotunplug, in
> > > __balance_push_cpu_stop(), the fallback rq for a kthread can select that
> > > CPU0, but __migrate_task() would fail and we end-up in an infinite loop,
> > > trying to migrate that task to CPU0.
> > > 
> > > The problem is that for a failure in sched:active, as "online" has no callback,
> > > there will be no call to cpuhp_invoke_callback(). Hence, the cpu_dying bit would
> > > not be reset.
> > 
> > Urgh! Good find.

> I seem to have triggered the BUG() in select_fallback_rq() with your recipie.
> Have cpu0 fail on sched:active, then offline all other CPUs.
> 
> Now lemme add that patch.

(which obviously didn't actually build) seems to fix it.

---
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 838dcf238f92..e538518556f4 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -63,6 +63,7 @@ struct cpuhp_cpu_state {
 	bool			rollback;
 	bool			single;
 	bool			bringup;
+	int			cpu;
 	struct hlist_node	*node;
 	struct hlist_node	*last;
 	enum cpuhp_state	cb_state;
@@ -160,9 +161,6 @@ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
 	int (*cb)(unsigned int cpu);
 	int ret, cnt;
 
-	if (cpu_dying(cpu) != !bringup)
-		set_cpu_dying(cpu, !bringup);
-
 	if (st->fail == state) {
 		st->fail = CPUHP_INVALID;
 		return -EAGAIN;
@@ -467,13 +465,16 @@ static inline enum cpuhp_state
 cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 {
 	enum cpuhp_state prev_state = st->state;
+	bool bringup = st->state < target;
 
 	st->rollback = false;
 	st->last = NULL;
 
 	st->target = target;
 	st->single = false;
-	st->bringup = st->state < target;
+	st->bringup = bringup;
+	if (cpu_dying(st->cpu) != !bringup)
+		set_cpu_dying(st->cpu, !bringup);
 
 	return prev_state;
 }
@@ -481,6 +482,8 @@ cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target)
 static inline void
 cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
 {
+	bool bringup = !st->bringup;
+
 	st->target = prev_state;
 
 	/*
@@ -503,7 +506,9 @@ cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state)
 			st->state++;
 	}
 
-	st->bringup = !st->bringup;
+	st->bringup = bringup;
+	if (cpu_dying(st->cpu) != !bringup)
+		set_cpu_dying(st->cpu, !bringup);
 }
 
 /* Regular hotplug invocation of the AP hotplug thread */
@@ -693,6 +698,7 @@ static void cpuhp_create(unsigned int cpu)
 
 	init_completion(&st->done_up);
 	init_completion(&st->done_down);
+	st->cpu = cpu;
 }
 
 static int cpuhp_should_run(unsigned int cpu)