From e0b257c3b71bd98a4866c3daecf000998aaa4927 Mon Sep 17 00:00:00 2001 From: Anna-Maria Behnsen Date: Tue, 15 Dec 2020 11:44:00 +0100 Subject: sched: Prevent raising SCHED_SOFTIRQ when CPU is !active SCHED_SOFTIRQ is raised to trigger periodic load balancing. When CPU is not active, CPU should not participate in load balancing. The scheduler uses nohz.idle_cpus_mask to keep track of the CPUs which can do idle load balancing. When bringing a CPU up the CPU is added to the mask when it reaches the active state, but on teardown the CPU stays in the mask until it goes offline and invokes sched_cpu_dying(). When SCHED_SOFTIRQ is raised on a !active CPU, there might be a pending softirq when stopping the tick which triggers a warning in NOHZ code. The SCHED_SOFTIRQ can also be raised by the scheduler tick which has the same issue. Therefore remove the CPU from nohz.idle_cpus_mask when it is marked inactive and also prevent the scheduler_tick() from raising SCHED_SOFTIRQ after this point. Signed-off-by: Anna-Maria Behnsen Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt (VMware) Link: https://lkml.kernel.org/r/20201215104400.9435-1-anna-maria@linutronix.de --- kernel/sched/core.c | 7 ++++++- kernel/sched/fair.c | 7 +++++-- 2 files changed, 11 insertions(+), 3 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 4fe4cbf0bf08..06b449942adf 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7596,6 +7596,12 @@ int sched_cpu_deactivate(unsigned int cpu) struct rq_flags rf; int ret; + /* + * Remove CPU from nohz.idle_cpus_mask to prevent participating in + * load balancing when not active + */ + nohz_balance_exit_idle(rq); + set_cpu_active(cpu, false); /* * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU @@ -7702,7 +7708,6 @@ int sched_cpu_dying(unsigned int cpu) calc_load_migrate(rq); update_max_interval(); - nohz_balance_exit_idle(rq); hrtick_clear(rq); return 0; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 39c5bda90bd4..389cb58655c0 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -10700,8 +10700,11 @@ static __latent_entropy void run_rebalance_domains(struct softirq_action *h) */ void trigger_load_balance(struct rq *rq) { - /* Don't need to rebalance while attached to NULL domain */ - if (unlikely(on_null_domain(rq))) + /* + * Don't need to rebalance while attached to NULL domain or + * runqueue CPU is not active + */ + if (unlikely(on_null_domain(rq) || !cpu_active(cpu_of(rq)))) return; if (time_after_eq(jiffies, rq->next_balance)) -- cgit v1.2.3