Each time we sync cfs_rq->runtime_expires with cfs_b->runtime_expires, we should sync its ->expires_seq too. However it is missing for distribute_cfs_runtime(), especially the slack timer call path.
Fixes: 512ac999d275 ("sched/fair: Fix bandwidth timer clock drift condition") Cc: Xunlei Pang <xlp...@linux.alibaba.com> Cc: Ben Segall <bseg...@google.com> Cc: Linus Torvalds <torva...@linux-foundation.org> Cc: Peter Zijlstra <pet...@infradead.org> Cc: Thomas Gleixner <t...@linutronix.de> Signed-off-by: Cong Wang <xiyou.wangc...@gmail.com> --- kernel/sched/fair.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 2f0a0be4d344..910c50db3d74 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4857,7 +4857,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) } static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, - u64 remaining, u64 expires) + u64 remaining, u64 expires, int expires_seq) { struct cfs_rq *cfs_rq; u64 runtime; @@ -4880,6 +4880,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, cfs_rq->runtime_remaining += runtime; cfs_rq->runtime_expires = expires; + cfs_rq->expires_seq = expires_seq; /* we check whether we're throttled above */ if (cfs_rq->runtime_remaining > 0) @@ -4905,7 +4906,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) { u64 runtime, runtime_expires; - int throttled; + int throttled, expires_seq; /* no need to continue the timer with no bandwidth constraint */ if (cfs_b->quota == RUNTIME_INF) @@ -4933,6 +4934,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) cfs_b->nr_throttled += overrun; runtime_expires = cfs_b->runtime_expires; + expires_seq = cfs_b->expires_seq; /* * This check is repeated as we are holding onto the new bandwidth while @@ -4946,7 +4948,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) raw_spin_unlock(&cfs_b->lock); /* we can't nest cfs_b->lock while distributing bandwidth */ runtime = distribute_cfs_runtime(cfs_b, runtime, - runtime_expires); + runtime_expires, expires_seq); raw_spin_lock(&cfs_b->lock); throttled = !list_empty(&cfs_b->throttled_cfs_rq); @@ -5055,6 +5057,7 @@ static __always_inline void return_cfs_rq_runtime(struct cfs_rq *cfs_rq) static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) { u64 runtime = 0, slice = sched_cfs_bandwidth_slice(); + int expires_seq; u64 expires; /* confirm we're still not at a refresh boundary */ @@ -5068,12 +5071,13 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) runtime = cfs_b->runtime; expires = cfs_b->runtime_expires; + expires_seq = cfs_b->expires_seq; raw_spin_unlock(&cfs_b->lock); if (!runtime) return; - runtime = distribute_cfs_runtime(cfs_b, runtime, expires); + runtime = distribute_cfs_runtime(cfs_b, runtime, expires, expires_seq); raw_spin_lock(&cfs_b->lock); if (expires == cfs_b->runtime_expires) -- 2.14.4