From 9642d18eee2cd169b60c6ac0f20bda745b5a3d1e Mon Sep 17 00:00:00 2001 From: Vatika Harlalka Date: Tue, 1 Sep 2015 16:50:59 +0200 Subject: [PATCH 1/3] nohz: Affine unpinned timers to housekeepers The problem addressed in this patch is about affining unpinned timers. Adaptive or Full Dynticks CPUs are currently disturbed by unnecessary jitter due to firing of such timers on them. This patch will affine timers to online CPUs which are not full dynticks in NOHZ_FULL configured systems. It should not introduce overhead in nohz full off case due to static keys. Signed-off-by: Vatika Harlalka Signed-off-by: Frederic Weisbecker Reviewed-by: Preeti U Murthy Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1441119060-2230-2-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- include/linux/tick.h | 9 +++++++++ kernel/sched/core.c | 7 +++++-- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/include/linux/tick.h b/include/linux/tick.h index 48d901f83f92..e312219ff823 100644 --- a/include/linux/tick.h +++ b/include/linux/tick.h @@ -147,11 +147,20 @@ static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) cpumask_or(mask, mask, tick_nohz_full_mask); } +static inline int housekeeping_any_cpu(void) +{ + return cpumask_any_and(housekeeping_mask, cpu_online_mask); +} + extern void tick_nohz_full_kick(void); extern void tick_nohz_full_kick_cpu(int cpu); extern void tick_nohz_full_kick_all(void); extern void __tick_nohz_task_switch(void); #else +static inline int housekeeping_any_cpu(void) +{ + return smp_processor_id(); +} static inline bool tick_nohz_full_enabled(void) { return false; } static inline bool tick_nohz_full_cpu(int cpu) { return false; } static inline void tick_nohz_full_add_cpus_to(struct cpumask *mask) { } diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8b864ecee0e1..0902e4d72671 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -623,18 +623,21 @@ int get_nohz_timer_target(void) int i, cpu = smp_processor_id(); struct sched_domain *sd; - if (!idle_cpu(cpu)) + if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu)) return cpu; rcu_read_lock(); for_each_domain(cpu, sd) { for_each_cpu(i, sched_domain_span(sd)) { - if (!idle_cpu(i)) { + if (!idle_cpu(i) && is_housekeeping_cpu(cpu)) { cpu = i; goto unlock; } } } + + if (!is_housekeeping_cpu(cpu)) + cpu = housekeeping_any_cpu(); unlock: rcu_read_unlock(); return cpu; From 7c8bb6cb95061b3143759459ed6c6b0c73bcfecb Mon Sep 17 00:00:00 2001 From: Frederic Weisbecker Date: Tue, 1 Sep 2015 16:51:00 +0200 Subject: [PATCH 2/3] nohz: Assert existing housekeepers when nohz full enabled The code ensures that when nohz full is running, at least the boot CPU serves as a housekeeper and it can't be later offlined. Let's assert this assumption to make sure that we have CPUs to handle unbound jobs like workqueues and timers while nohz full CPUs run undisturbed. Also improve the comments on housekeeper offlining prevention. Signed-off-by: Frederic Weisbecker Acked-by: Thomas Gleixner Cc: Chris Metcalf Cc: Christoph Lameter Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Preeti U Murthy Cc: Vatika Harlalka Link: http://lkml.kernel.org/r/1441119060-2230-3-git-send-email-fweisbec@gmail.com Signed-off-by: Ingo Molnar --- kernel/time/tick-sched.c | 15 +++++++++++---- 1 file changed, 11 insertions(+), 4 deletions(-) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 3319e16f31e5..7c7ec4515983 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -290,16 +290,17 @@ static int __init tick_nohz_full_setup(char *str) __setup("nohz_full=", tick_nohz_full_setup); static int tick_nohz_cpu_down_callback(struct notifier_block *nfb, - unsigned long action, - void *hcpu) + unsigned long action, + void *hcpu) { unsigned int cpu = (unsigned long)hcpu; switch (action & ~CPU_TASKS_FROZEN) { case CPU_DOWN_PREPARE: /* - * If we handle the timekeeping duty for full dynticks CPUs, - * we can't safely shutdown that CPU. + * The boot CPU handles housekeeping duty (unbound timers, + * workqueues, timekeeping, ...) on behalf of full dynticks + * CPUs. It must remain online when nohz full is enabled. */ if (tick_nohz_full_running && tick_do_timer_cpu == cpu) return NOTIFY_BAD; @@ -370,6 +371,12 @@ void __init tick_nohz_init(void) cpu_notifier(tick_nohz_cpu_down_callback, 0); pr_info("NO_HZ: Full dynticks CPUs: %*pbl.\n", cpumask_pr_args(tick_nohz_full_mask)); + + /* + * We need at least one CPU to handle housekeeping work such + * as timekeeping, unbound timers, workqueues, ... + */ + WARN_ON_ONCE(cpumask_empty(housekeeping_mask)); } #endif From 5473e0cc37c03c576adbda7591a6cc8e37c1bb7f Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Fri, 28 Aug 2015 14:55:56 +0800 Subject: [PATCH 3/3] sched: 'Annotate' migrate_tasks() Kernel testing triggered this warning: | WARNING: CPU: 0 PID: 13 at kernel/sched/core.c:1156 do_set_cpus_allowed+0x7e/0x80() | Modules linked in: | CPU: 0 PID: 13 Comm: migration/0 Not tainted 4.2.0-rc1-00049-g25834c7 #2 | Call Trace: | dump_stack+0x4b/0x75 | warn_slowpath_common+0x8b/0xc0 | warn_slowpath_null+0x22/0x30 | do_set_cpus_allowed+0x7e/0x80 | cpuset_cpus_allowed_fallback+0x7c/0x170 | select_fallback_rq+0x221/0x280 | migration_call+0xe3/0x250 | notifier_call_chain+0x53/0x70 | __raw_notifier_call_chain+0x1e/0x30 | cpu_notify+0x28/0x50 | take_cpu_down+0x22/0x40 | multi_cpu_stop+0xd5/0x140 | cpu_stopper_thread+0xbc/0x170 | smpboot_thread_fn+0x174/0x2f0 | kthread+0xc4/0xe0 | ret_from_kernel_thread+0x21/0x30 As Peterz pointed out: | So the normal rules for changing task_struct::cpus_allowed are holding | both pi_lock and rq->lock, such that holding either stabilizes the mask. | | This is so that wakeup can happen without rq->lock and load-balance | without pi_lock. | | From this we already get the relaxation that we can omit acquiring | rq->lock if the task is not on the rq, because in that case | load-balancing will not apply to it. | | ** these are the rules currently tested in do_set_cpus_allowed() ** | | Now, since __set_cpus_allowed_ptr() uses task_rq_lock() which | unconditionally acquires both locks, we could get away with holding just | rq->lock when on_rq for modification because that'd still exclude | __set_cpus_allowed_ptr(), it would also work against | __kthread_bind_mask() because that assumes !on_rq. | | That said, this is all somewhat fragile. | | Now, I don't think dropping rq->lock is quite as disastrous as it | usually is because !cpu_active at this point, which means load-balance | will not interfere, but that too is somewhat fragile. | | So we end up with a choice of two fragile.. This patch fixes it by following the rules for changing task_struct::cpus_allowed with both pi_lock and rq->lock held. Reported-by: kernel test robot Reported-by: Sasha Levin Signed-off-by: Wanpeng Li [ Modified changelog and patch. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/BLU436-SMTP1660820490DE202E3934ED3806E0@phx.gbl Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 29 ++++++++++++++++++++++++++--- 1 file changed, 26 insertions(+), 3 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 0902e4d72671..9b786704d34b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5183,24 +5183,47 @@ static void migrate_tasks(struct rq *dead_rq) break; /* - * Ensure rq->lock covers the entire task selection - * until the migration. + * pick_next_task assumes pinned rq->lock. */ lockdep_pin_lock(&rq->lock); next = pick_next_task(rq, &fake_task); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); + /* + * Rules for changing task_struct::cpus_allowed are holding + * both pi_lock and rq->lock, such that holding either + * stabilizes the mask. + * + * Drop rq->lock is not quite as disastrous as it usually is + * because !cpu_active at this point, which means load-balance + * will not interfere. Also, stop-machine. + */ + lockdep_unpin_lock(&rq->lock); + raw_spin_unlock(&rq->lock); + raw_spin_lock(&next->pi_lock); + raw_spin_lock(&rq->lock); + + /* + * Since we're inside stop-machine, _nothing_ should have + * changed the task, WARN if weird stuff happened, because in + * that case the above rq->lock drop is a fail too. + */ + if (WARN_ON(task_rq(next) != rq || !task_on_rq_queued(next))) { + raw_spin_unlock(&next->pi_lock); + continue; + } + /* Find suitable destination for @next, with force if needed. */ dest_cpu = select_fallback_rq(dead_rq->cpu, next); - lockdep_unpin_lock(&rq->lock); rq = __migrate_task(rq, next, dest_cpu); if (rq != dead_rq) { raw_spin_unlock(&rq->lock); rq = dead_rq; raw_spin_lock(&rq->lock); } + raw_spin_unlock(&next->pi_lock); } rq->stop = stop;