[tip: sched/urgent] sched: Fix data-race in wakeup

[tip-bot2 for Peter Zijlstra]

The following commit has been merged into the sched/urgent branch of tip:

Commit-ID:     f97bb5272d9e95d400d6c8643ebb146b3e3e7842
Gitweb:        https://git.kernel.org/tip/f97bb5272d9e95d400d6c8643ebb146b3e3e7842
Author:        Peter Zijlstra <peterz@xxxxxxxxxxxxx>
AuthorDate:    Tue, 17 Nov 2020 09:08:41 +01:00
Committer:     Peter Zijlstra <peterz@xxxxxxxxxxxxx>
CommitterDate: Tue, 17 Nov 2020 13:15:27 +01:00

sched: Fix data-race in wakeup

Mel reported that on some ARM64 platforms loadavg goes bananas and
Will tracked it down to the following race:

  CPU0					CPU1

  schedule()
    prev->sched_contributes_to_load = X;
    deactivate_task(prev);

					try_to_wake_up()
					  if (p->on_rq &&) // false
					  if (smp_load_acquire(&p->on_cpu) && // true
					      ttwu_queue_wakelist())
					        p->sched_remote_wakeup = Y;

    smp_store_release(prev->on_cpu, 0);

where both p->sched_contributes_to_load and p->sched_remote_wakeup are
in the same word, and thus the stores X and Y race (and can clobber
one another's data).

Whereas prior to commit c6e7bd7afaeb ("sched/core: Optimize ttwu()
spinning on p->on_cpu") the p->on_cpu handoff serialized access to
p->sched_remote_wakeup (just as it still does with
p->sched_contributes_to_load) that commit broke that by calling
ttwu_queue_wakelist() with p->on_cpu != 0.

However, due to

  p->XXX = X			ttwu()
  schedule()			  if (p->on_rq && ...) // false
    smp_mb__after_spinlock()	  if (smp_load_acquire(&p->on_cpu) &&
    deactivate_task()		      ttwu_queue_wakelist())
      p->on_rq = 0;		        p->sched_remote_wakeup = Y;

We can be sure any 'current' store is complete and 'current' is
guaranteed asleep. Therefore we can move p->sched_remote_wakeup into
the current flags word.

Note: while the observed failure was loadavg accounting gone wrong due
to ttwu() cobbering p->sched_contributes_to_load, the reverse problem
is also possible where schedule() clobbers p->sched_remote_wakeup,
this could result in enqueue_entity() wrecking ->vruntime and causing
scheduling artifacts.

Fixes: c6e7bd7afaeb ("sched/core: Optimize ttwu() spinning on p->on_cpu")
Reported-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Debugged-by: Will Deacon <will@xxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Link: https://lkml.kernel.org/r/20201117083016.GK3121392@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
---
 include/linux/sched.h | 16 +++++++++++++++-
 1 file changed, 15 insertions(+), 1 deletion(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d383cf0..0e91b45 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -769,7 +769,6 @@ struct task_struct {
 	unsigned			sched_reset_on_fork:1;
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
-	unsigned			sched_remote_wakeup:1;
 #ifdef CONFIG_PSI
 	unsigned			sched_psi_wake_requeue:1;
 #endif
@@ -779,6 +778,21 @@ struct task_struct {
 
 	/* Unserialized, strictly 'current' */
 
+	/*
+	 * This field must not be in the scheduler word above due to wakelist
+	 * queueing no longer being serialized by p->on_cpu. However:
+	 *
+	 * p->XXX = X;			ttwu()
+	 * schedule()			  if (p->on_rq && ..) // false
+	 *   smp_mb__after_spinlock();	  if (smp_load_acquire(&p->on_cpu) && //true
+	 *   deactivate_task()		      ttwu_queue_wakelist())
+	 *     p->on_rq = 0;			p->sched_remote_wakeup = Y;
+	 *
+	 * guarantees all stores of 'current' are visible before
+	 * ->sched_remote_wakeup gets used, so it can be in this word.
+	 */
+	unsigned			sched_remote_wakeup:1;
+
 	/* Bit to tell LSMs we're in execve(): */
 	unsigned			in_execve:1;
 	unsigned			in_iowait:1;