From 296b2ffe7fa9ed756c41415c6b1512bc4ad687b1 Mon Sep 17 00:00:00 2001 From: Vincent Guittot Date: Tue, 26 Jun 2018 15:53:22 +0200 Subject: sched/rt: Fix call to cpufreq_update_util() With commit: 8f111bc357aa ("cpufreq/schedutil: Rewrite CPUFREQ_RT support") the schedutil governor uses rq->rt.rt_nr_running to detect whether an RT task is currently running on the CPU and to set frequency to max if necessary. cpufreq_update_util() is called in enqueue/dequeue_top_rt_rq() but rq->rt.rt_nr_running has not been updated yet when dequeue_top_rt_rq() is called so schedutil still considers that an RT task is running when the last task is dequeued. The update of rq->rt.rt_nr_running happens later in dequeue_rt_stack(). In fact, we can take advantage of the sequence that the dequeue then re-enqueue rt entities when a rt task is enqueued or dequeued; As a result enqueue_top_rt_rq() is always called when a task is enqueued or dequeued and also when groups are throttled or unthrottled. The only place that not use enqueue_top_rt_rq() is when root rt_rq is throttled. Signed-off-by: Vincent Guittot Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: efault@gmx.de Cc: juri.lelli@redhat.com Cc: patrick.bellasi@arm.com Cc: viresh.kumar@linaro.org Fixes: 8f111bc357aa ('cpufreq/schedutil: Rewrite CPUFREQ_RT support') Link: http://lkml.kernel.org/r/1530021202-21695-1-git-send-email-vincent.guittot@linaro.org Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) (limited to 'kernel/sched/rt.c') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 47556b0c9a95..572567078b60 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -508,8 +508,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; - if (!rt_se) + if (!rt_se) { dequeue_top_rt_rq(rt_rq); + /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ + cpufreq_update_util(rq_of_rt_rq(rt_rq), 0); + } else if (on_rt_rq(rt_se)) dequeue_rt_entity(rt_se, 0); } @@ -1001,8 +1004,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq) sub_nr_running(rq, rt_rq->rt_nr_running); rt_rq->rt_queued = 0; - /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ - cpufreq_update_util(rq, 0); } static void @@ -1014,11 +1015,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq) if (rt_rq->rt_queued) return; - if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + + if (rt_rq_throttled(rt_rq)) return; - add_nr_running(rq, rt_rq->rt_nr_running); - rt_rq->rt_queued = 1; + if (rt_rq->rt_nr_running) { + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; + } /* Kick cpufreq (see the comment in kernel/sched/sched.h). */ cpufreq_update_util(rq, 0); -- cgit v1.2.3 From f3d133ee0a17d5694c6f21873eec9863e11fa423 Mon Sep 17 00:00:00 2001 From: Hailong Liu Date: Wed, 18 Jul 2018 08:46:55 +0800 Subject: sched/rt: Restore rt_runtime after disabling RT_RUNTIME_SHARE NO_RT_RUNTIME_SHARE feature is used to prevent a CPU borrow enough runtime with a spin-rt-task. However, if RT_RUNTIME_SHARE feature is enabled and rt_rq has borrowd enough rt_runtime at the beginning, rt_runtime can't be restored to its initial bandwidth rt_runtime after we disable RT_RUNTIME_SHARE. E.g. on my PC with 4 cores, procedure to reproduce: 1) Make sure RT_RUNTIME_SHARE is enabled cat /sys/kernel/debug/sched_features GENTLE_FAIR_SLEEPERS START_DEBIT NO_NEXT_BUDDY LAST_BUDDY CACHE_HOT_BUDDY WAKEUP_PREEMPTION NO_HRTICK NO_DOUBLE_TICK LB_BIAS NONTASK_CAPACITY TTWU_QUEUE NO_SIS_AVG_CPU SIS_PROP NO_WARN_DOUBLE_CLOCK RT_PUSH_IPI RT_RUNTIME_SHARE NO_LB_MIN ATTACH_AGE_LOAD WA_IDLE WA_WEIGHT WA_BIAS 2) Start a spin-rt-task ./loop_rr & 3) set affinity to the last cpu taskset -p 8 $pid_of_loop_rr 4) Observe that last cpu have borrowed enough runtime. cat /proc/sched_debug | grep rt_runtime .rt_runtime : 950.000000 .rt_runtime : 900.000000 .rt_runtime : 950.000000 .rt_runtime : 1000.000000 5) Disable RT_RUNTIME_SHARE echo NO_RT_RUNTIME_SHARE > /sys/kernel/debug/sched_features 6) Observe that rt_runtime can not been restored cat /proc/sched_debug | grep rt_runtime .rt_runtime : 950.000000 .rt_runtime : 900.000000 .rt_runtime : 950.000000 .rt_runtime : 1000.000000 This patch help to restore rt_runtime after we disable RT_RUNTIME_SHARE. Signed-off-by: Hailong Liu Signed-off-by: Jiang Biao Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: zhong.weidong@zte.com.cn Link: http://lkml.kernel.org/r/1531874815-39357-1-git-send-email-liu.hailong6@zte.com.cn Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/sched/rt.c') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 572567078b60..eaaec8364f96 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -836,6 +836,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun) * can be time-consuming. Try to avoid it when possible. */ raw_spin_lock(&rt_rq->rt_runtime_lock); + if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF) + rt_rq->rt_runtime = rt_b->rt_runtime; skip = !rt_rq->rt_time && !rt_rq->rt_nr_running; raw_spin_unlock(&rt_rq->rt_runtime_lock); if (skip) -- cgit v1.2.3