Messages in this thread Patch in this message | | | Date | Thu, 19 Nov 2020 09:55:05 -0000 | From | "tip-bot2 for Peter Zijlstra" <> | Subject | [tip: sched/urgent] sched: Fix data-race in wakeup |
| |
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@infradead.org> AuthorDate: Tue, 17 Nov 2020 09:08:41 +01:00 Committer: Peter Zijlstra <peterz@infradead.org> 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@techsingularity.net> Debugged-by: Will Deacon <will@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20201117083016.GK3121392@hirez.programming.kicks-ass.net --- 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;
| |