From 02ad2dc7b3e7455fff589d535860a01158187c44 Mon Sep 17 00:00:00 2001 Message-Id: <02ad2dc7b3e7455fff589d535860a01158187c44.1601675151.git.zanussi@kernel.org> In-Reply-To: <5b5a156f9808b1acf1205606e03da117214549ea.1601675151.git.zanussi@kernel.org> References: <5b5a156f9808b1acf1205606e03da117214549ea.1601675151.git.zanussi@kernel.org> From: Peter Zijlstra Date: Mon, 7 Jan 2019 13:52:31 +0100 Subject: [PATCH 011/333] sched/fair: Robustify CFS-bandwidth timer locking Origin: https://www.kernel.org/pub/linux/kernel/projects/rt/4.19/older/patches-4.19.148-rt64.tar.xz Traditionally hrtimer callbacks were run with IRQs disabled, but with the introduction of HRTIMER_MODE_SOFT it is possible they run from SoftIRQ context, which does _NOT_ have IRQs disabled. Allow for the CFS bandwidth timers (period_timer and slack_timer) to be ran from SoftIRQ context; this entails removing the assumption that IRQs are already disabled from the locking. While mainline doesn't strictly need this, -RT forces all timers not explicitly marked with MODE_HARD into MODE_SOFT and trips over this. And marking these timers as MODE_HARD doesn't make sense as they're not required for RT operation and can potentially be quite expensive. Cc: Ingo Molnar Cc: Thomas Gleixner Cc: Sebastian Andrzej Siewior Reported-by: Tom Putzeys Tested-by: Mike Galbraith Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/20190107125231.GE14122@hirez.programming.kicks-ass.net Signed-off-by: Sebastian Andrzej Siewior --- kernel/sched/fair.c | 30 ++++++++++++++++-------------- 1 file changed, 16 insertions(+), 14 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 696d08a4593e..63a630f8dd1e 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -4597,7 +4597,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) struct rq *rq = rq_of(cfs_rq); struct rq_flags rf; - rq_lock(rq, &rf); + rq_lock_irqsave(rq, &rf); if (!cfs_rq_throttled(cfs_rq)) goto next; @@ -4616,7 +4616,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) unthrottle_cfs_rq(cfs_rq); next: - rq_unlock(rq, &rf); + rq_unlock_irqrestore(rq, &rf); if (!remaining) break; @@ -4632,7 +4632,7 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining) * period the timer is deactivated until scheduling resumes; cfs_b->idle is * used to track this state. */ -static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) +static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags) { u64 runtime; int throttled; @@ -4672,10 +4672,10 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) { runtime = cfs_b->runtime; cfs_b->distribute_running = 1; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); /* we can't nest cfs_b->lock while distributing bandwidth */ runtime = distribute_cfs_runtime(cfs_b, runtime); - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->distribute_running = 0; throttled = !list_empty(&cfs_b->throttled_cfs_rq); @@ -4783,16 +4783,17 @@ 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(); + unsigned long flags; /* confirm we're still not at a refresh boundary */ - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); if (cfs_b->distribute_running) { - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return; } if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) { - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return; } @@ -4802,17 +4803,17 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b) if (runtime) cfs_b->distribute_running = 1; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); if (!runtime) return; runtime = distribute_cfs_runtime(cfs_b, runtime); - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); cfs_b->runtime -= min(runtime, cfs_b->runtime); cfs_b->distribute_running = 0; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); } /* @@ -4892,11 +4893,12 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) { struct cfs_bandwidth *cfs_b = container_of(timer, struct cfs_bandwidth, period_timer); + unsigned long flags; int overrun; int idle = 0; int count = 0; - raw_spin_lock(&cfs_b->lock); + raw_spin_lock_irqsave(&cfs_b->lock, flags); for (;;) { overrun = hrtimer_forward_now(timer, cfs_b->period); if (!overrun) @@ -4932,11 +4934,11 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) count = 0; } - idle = do_sched_cfs_period_timer(cfs_b, overrun); + idle = do_sched_cfs_period_timer(cfs_b, overrun, flags); } if (idle) cfs_b->period_active = 0; - raw_spin_unlock(&cfs_b->lock); + raw_spin_unlock_irqrestore(&cfs_b->lock, flags); return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; } -- 2.17.1