On Sun, Jan 17, 2021 at 04:57:27PM +0000, Valentin Schneider wrote:
> On 16/01/21 12:30, Peter Zijlstra wrote:
> > @@ -1796,13 +1796,28 @@ static inline bool rq_has_pinned_tasks(s
> > */
> > static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
> > {
> > + /* When not in the task's cpumask, no point in looking further. */
> > if (!cpumask_test_cpu(cpu, p->cpus_ptr))
> > return false;
> >
> > + /* migrate_disabled() must be allowed to finish. */
> > + if (is_migration_disabled(p))
> > return cpu_online(cpu);
> >
> > + /* Non kernel threads are not allowed during either online or offline.
> > */
> > + if (!(p->flags & PF_KTHREAD))
> > + return cpu_active(cpu);
> > +
> > + /* KTHREAD_IS_PER_CPU is always allowed. */
> > + if (kthread_is_per_cpu(p))
> > + return cpu_online(cpu);
> > +
> > + /* Regular kernel threads don't get to stay during offline. */
> > + if (cpu_rq(cpu)->balance_callback == &balance_push_callback)
> > + return cpu_active(cpu);
>
> is_cpu_allowed(, cpu) isn't guaranteed to have cpu_rq(cpu)'s rq_lock
> held, so this can race with balance_push_set(, true). This shouldn't
> matter under normal circumstances as we'll have sched_cpu_wait_empty()
> further down the line.
>
> This might get ugly with the rollback faff - this is jumping the gun a
> bit, but that's something we'll have to address, and I think what I'm
> concerned about is close to what you mentioned in
>
> http://lore.kernel.org/r/yam1t2qzr7rib...@hirez.programming.kicks-ass.net
>
> Here's what I'm thinking of:
>
> _cpu_up() ttwu()
> select_task_rq()
> is_cpu_allowed()
> rq->balance_callback !=
> balance_push_callback
> smpboot_unpark_threads() // FAIL
> (now going down, set push here)
> sched_cpu_wait_empty()
> ... ttwu_queue()
> sched_cpu_dying()
> *ARGH*
>
Let me try this then...
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5057054b1cff..9b045296d646 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7495,6 +7495,8 @@ int sched_cpu_activate(unsigned int cpu)
return 0;
}
+unsigned long sched_cpu_rcu_state;
+
int sched_cpu_deactivate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -7519,6 +7521,11 @@ int sched_cpu_deactivate(unsigned int cpu)
*/
balance_push_set(cpu, true);
+ /*
+ * See sched_cpu_wait_empty().
+ */
+ sched_cpu_rcu_state = get_state_synchronize_rcu();
+
rq_lock_irqsave(rq, &rf);
if (rq->rd) {
update_rq_clock(rq);
@@ -7578,6 +7585,12 @@ int sched_cpu_starting(unsigned int cpu)
*/
int sched_cpu_wait_empty(unsigned int cpu)
{
+ /*
+ * Guarantee that TTWU will observe balance_push_set(true),
+ * such that all wakeups will refuse this CPU.
+ */
+ cond_synchronize_rcu(sched_cpu_rcu_state);
+
balance_hotplug_wait();
return 0;
}
