From 41acab8851a0408c1d5ad6c21a07456f88b54d40 Mon Sep 17 00:00:00 2001 From: Lucas De Marchi Date: Wed, 10 Mar 2010 23:37:45 -0300 Subject: sched: Implement group scheduler statistics in one struct Put all statistic fields of sched_entity in one struct, sched_statistics, and embed it into sched_entity. This change allows to memset the sched_statistics to 0 when needed (for instance when forking), avoiding bugs of non initialized fields. Signed-off-by: Lucas De Marchi Signed-off-by: Peter Zijlstra LKML-Reference: <1268275065-18542-1-git-send-email-lucas.de.marchi@gmail.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 47 +++++++++-------------------------------------- 1 file changed, 9 insertions(+), 38 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 2c1db81f80eb..a4aa071f08f3 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2437,15 +2437,15 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, out_activate: #endif /* CONFIG_SMP */ - schedstat_inc(p, se.nr_wakeups); + schedstat_inc(p, se.statistics.nr_wakeups); if (wake_flags & WF_SYNC) - schedstat_inc(p, se.nr_wakeups_sync); + schedstat_inc(p, se.statistics.nr_wakeups_sync); if (orig_cpu != cpu) - schedstat_inc(p, se.nr_wakeups_migrate); + schedstat_inc(p, se.statistics.nr_wakeups_migrate); if (cpu == this_cpu) - schedstat_inc(p, se.nr_wakeups_local); + schedstat_inc(p, se.statistics.nr_wakeups_local); else - schedstat_inc(p, se.nr_wakeups_remote); + schedstat_inc(p, se.statistics.nr_wakeups_remote); activate_task(rq, p, 1); success = 1; @@ -2532,36 +2532,7 @@ static void __sched_fork(struct task_struct *p) p->se.avg_wakeup = sysctl_sched_wakeup_granularity; #ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.wait_max = 0; - p->se.wait_count = 0; - p->se.wait_sum = 0; - - p->se.sleep_start = 0; - p->se.sleep_max = 0; - p->se.sum_sleep_runtime = 0; - - p->se.block_start = 0; - p->se.block_max = 0; - p->se.exec_max = 0; - p->se.slice_max = 0; - - p->se.nr_migrations_cold = 0; - p->se.nr_failed_migrations_affine = 0; - p->se.nr_failed_migrations_running = 0; - p->se.nr_failed_migrations_hot = 0; - p->se.nr_forced_migrations = 0; - - p->se.nr_wakeups = 0; - p->se.nr_wakeups_sync = 0; - p->se.nr_wakeups_migrate = 0; - p->se.nr_wakeups_local = 0; - p->se.nr_wakeups_remote = 0; - p->se.nr_wakeups_affine = 0; - p->se.nr_wakeups_affine_attempts = 0; - p->se.nr_wakeups_passive = 0; - p->se.nr_wakeups_idle = 0; - + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); @@ -7910,9 +7881,9 @@ void normalize_rt_tasks(void) p->se.exec_start = 0; #ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.sleep_start = 0; - p->se.block_start = 0; + p->se.statistics.wait_start = 0; + p->se.statistics.sleep_start = 0; + p->se.statistics.block_start = 0; #endif if (!rt_task(p)) { -- cgit v1.2.3-70-g09d2 From 39c0cbe2150cbd848a25ba6cdb271d1ad46818ad Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:17:13 +0100 Subject: sched: Rate-limit nohz Entering nohz code on every micro-idle is costing ~10% throughput for netperf TCP_RR when scheduling cross-cpu. Rate limiting entry fixes this, but raises ticks a bit. On my Q6600, an idle box goes from ~85 interrupts/sec to 128. The higher the context switch rate, the more nohz entry costs. With this patch and some cycle recovery patches in my tree, max cross cpu context switch rate is improved by ~16%, a large portion of which of which is this ratelimiting. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301003.6785.28.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 6 ++++++ kernel/sched.c | 12 ++++++++++++ kernel/time/tick-sched.c | 3 +++ 3 files changed, 21 insertions(+) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8cc863d66477..13efe7dac5fa 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -271,11 +271,17 @@ extern cpumask_var_t nohz_cpu_mask; #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ) extern int select_nohz_load_balancer(int cpu); extern int get_nohz_load_balancer(void); +extern int nohz_ratelimit(int cpu); #else static inline int select_nohz_load_balancer(int cpu) { return 0; } + +static inline int nohz_ratelimit(int cpu) +{ + return 0; +} #endif /* diff --git a/kernel/sched.c b/kernel/sched.c index a4aa071f08f3..60b1bbe2ad1b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -492,6 +492,7 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; #ifdef CONFIG_NO_HZ + u64 nohz_stamp; unsigned char in_nohz_recently; #endif /* capture load from *all* tasks on this cpu: */ @@ -1228,6 +1229,17 @@ void wake_up_idle_cpu(int cpu) if (!tsk_is_polling(rq->idle)) smp_send_reschedule(cpu); } + +int nohz_ratelimit(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + u64 diff = rq->clock - rq->nohz_stamp; + + rq->nohz_stamp = rq->clock; + + return diff < (NSEC_PER_SEC / HZ) >> 1; +} + #endif /* CONFIG_NO_HZ */ static u64 sched_avg_period(void) diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index f992762d7f51..f25735a767af 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -262,6 +262,9 @@ void tick_nohz_stop_sched_tick(int inidle) goto end; } + if (nohz_ratelimit(cpu)) + goto end; + ts->idle_calls++; /* Read jiffies and the time when jiffies were updated last */ do { -- cgit v1.2.3-70-g09d2 From b42e0c41a422a212ddea0666d5a3a0e3c35206db Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:15:38 +0100 Subject: sched: Remove avg_wakeup Testing the load which led to this heuristic (nfs4 kbuild) shows that it has outlived it's usefullness. With intervening load balancing changes, I cannot see any difference with/without, so recover there fastpath cycles. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301062.6785.29.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 --- kernel/sched.c | 26 ++++---------------------- kernel/sched_debug.c | 1 - kernel/sched_fair.c | 31 ------------------------------- kernel/sched_features.h | 6 ------ 5 files changed, 4 insertions(+), 63 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 13efe7dac5fa..70c560f5ada0 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1185,9 +1185,6 @@ struct sched_entity { u64 nr_migrations; - u64 start_runtime; - u64 avg_wakeup; - #ifdef CONFIG_SCHEDSTATS struct sched_statistics statistics; #endif diff --git a/kernel/sched.c b/kernel/sched.c index 60b1bbe2ad1b..35a8626ace7d 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1880,9 +1880,6 @@ static void update_avg(u64 *avg, u64 sample) static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) { - if (wakeup) - p->se.start_runtime = p->se.sum_exec_runtime; - sched_info_queued(p); p->sched_class->enqueue_task(rq, p, wakeup, head); p->se.on_rq = 1; @@ -1890,17 +1887,11 @@ enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { - if (sleep) { - if (p->se.last_wakeup) { - update_avg(&p->se.avg_overlap, - p->se.sum_exec_runtime - p->se.last_wakeup); - p->se.last_wakeup = 0; - } else { - update_avg(&p->se.avg_wakeup, - sysctl_sched_wakeup_granularity); - } + if (sleep && p->se.last_wakeup) { + update_avg(&p->se.avg_overlap, + p->se.sum_exec_runtime - p->se.last_wakeup); + p->se.last_wakeup = 0; } - sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; @@ -2466,13 +2457,6 @@ out_activate: */ if (!in_interrupt()) { struct sched_entity *se = ¤t->se; - u64 sample = se->sum_exec_runtime; - - if (se->last_wakeup) - sample -= se->last_wakeup; - else - sample -= se->start_runtime; - update_avg(&se->avg_wakeup, sample); se->last_wakeup = se->sum_exec_runtime; } @@ -2540,8 +2524,6 @@ static void __sched_fork(struct task_struct *p) p->se.nr_migrations = 0; p->se.last_wakeup = 0; p->se.avg_overlap = 0; - p->se.start_runtime = 0; - p->se.avg_wakeup = sysctl_sched_wakeup_granularity; #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index ad9df4422763..20b95a420fec 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -408,7 +408,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.vruntime); PN(se.sum_exec_runtime); PN(se.avg_overlap); - PN(se.avg_wakeup); nr_switches = p->nvcsw + p->nivcsw; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 8ad164bbdac1..6fc62854422c 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1592,42 +1592,11 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag } #endif /* CONFIG_SMP */ -/* - * Adaptive granularity - * - * se->avg_wakeup gives the average time a task runs until it does a wakeup, - * with the limit of wakeup_gran -- when it never does a wakeup. - * - * So the smaller avg_wakeup is the faster we want this task to preempt, - * but we don't want to treat the preemptee unfairly and therefore allow it - * to run for at least the amount of time we'd like to run. - * - * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one - * - * NOTE: we use *nr_running to scale with load, this nicely matches the - * degrading latency on load. - */ -static unsigned long -adaptive_gran(struct sched_entity *curr, struct sched_entity *se) -{ - u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime; - u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running; - u64 gran = 0; - - if (this_run < expected_wakeup) - gran = expected_wakeup - this_run; - - return min_t(s64, gran, sysctl_sched_wakeup_granularity); -} - static unsigned long wakeup_gran(struct sched_entity *curr, struct sched_entity *se) { unsigned long gran = sysctl_sched_wakeup_granularity; - if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN)) - gran = adaptive_gran(curr, se); - /* * Since its curr running now, convert the gran from real-time * to virtual-time in his units. diff --git a/kernel/sched_features.h b/kernel/sched_features.h index d5059fd761d9..96ef5dbc66e1 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -30,12 +30,6 @@ SCHED_FEAT(START_DEBIT, 1) */ SCHED_FEAT(WAKEUP_PREEMPT, 1) -/* - * Compute wakeup_gran based on task behaviour, clipped to - * [0, sched_wakeup_gran_ns] - */ -SCHED_FEAT(ADAPTIVE_GRAN, 1) - /* * When converting the wakeup granularity to virtual time, do it such * that heavier tasks preempting a lighter task have an edge. -- cgit v1.2.3-70-g09d2 From e12f31d3e5d36328c7fbd0fce40a95e70b59152c Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:15:51 +0100 Subject: sched: Remove avg_overlap Both avg_overlap and avg_wakeup had an inherent problem in that their accuracy was detrimentally affected by cross-cpu wakeups, this because we are missing the necessary call to update_curr(). This can't be fixed without increasing overhead in our already too fat fastpath. Additionally, with recent load balancing changes making us prefer to place tasks in an idle cache domain (which is good for compute bound loads), communicating tasks suffer when a sync wakeup, which would enable affine placement, is turned into a non-sync wakeup by SYNC_LESS. With one task on the runqueue, wake_affine() rejects the affine wakeup request, leaving the unfortunate where placed, taking frequent cache misses. Remove it, and recover some fastpath cycles. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301121.6785.30.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 --- kernel/sched.c | 33 --------------------------------- kernel/sched_debug.c | 1 - kernel/sched_fair.c | 18 ------------------ kernel/sched_features.h | 16 ---------------- 5 files changed, 71 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 70c560f5ada0..8604884cee87 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1180,9 +1180,6 @@ struct sched_entity { u64 vruntime; u64 prev_sum_exec_runtime; - u64 last_wakeup; - u64 avg_overlap; - u64 nr_migrations; #ifdef CONFIG_SCHEDSTATS diff --git a/kernel/sched.c b/kernel/sched.c index 35a8626ace7d..68ed6f4f3c13 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1887,11 +1887,6 @@ enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { - if (sleep && p->se.last_wakeup) { - update_avg(&p->se.avg_overlap, - p->se.sum_exec_runtime - p->se.last_wakeup); - p->se.last_wakeup = 0; - } sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; @@ -2452,15 +2447,6 @@ out_activate: activate_task(rq, p, 1); success = 1; - /* - * Only attribute actual wakeups done by this task. - */ - if (!in_interrupt()) { - struct sched_entity *se = ¤t->se; - - se->last_wakeup = se->sum_exec_runtime; - } - out_running: trace_sched_wakeup(rq, p, success); check_preempt_curr(rq, p, wake_flags); @@ -2522,8 +2508,6 @@ static void __sched_fork(struct task_struct *p) p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; p->se.nr_migrations = 0; - p->se.last_wakeup = 0; - p->se.avg_overlap = 0; #ifdef CONFIG_SCHEDSTATS memset(&p->se.statistics, 0, sizeof(p->se.statistics)); @@ -3594,23 +3578,6 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->state == TASK_RUNNING) { - u64 runtime = prev->se.sum_exec_runtime; - - runtime -= prev->se.prev_sum_exec_runtime; - runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); - - /* - * In order to avoid avg_overlap growing stale when we are - * indeed overlapping and hence not getting put to sleep, grow - * the avg_overlap on preemption. - * - * We use the average preemption runtime because that - * correlates to the amount of cache footprint a task can - * build up. - */ - update_avg(&prev->se.avg_overlap, runtime); - } prev->sched_class->put_prev_task(rq, prev); } diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c index 20b95a420fec..8a46a719f367 100644 --- a/kernel/sched_debug.c +++ b/kernel/sched_debug.c @@ -407,7 +407,6 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) PN(se.exec_start); PN(se.vruntime); PN(se.sum_exec_runtime); - PN(se.avg_overlap); nr_switches = p->nvcsw + p->nivcsw; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 6fc62854422c..c3b69d4b5d65 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1241,7 +1241,6 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu, static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) { - struct task_struct *curr = current; unsigned long this_load, load; int idx, this_cpu, prev_cpu; unsigned long tl_per_task; @@ -1256,18 +1255,6 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) load = source_load(prev_cpu, idx); this_load = target_load(this_cpu, idx); - if (sync) { - if (sched_feat(SYNC_LESS) && - (curr->se.avg_overlap > sysctl_sched_migration_cost || - p->se.avg_overlap > sysctl_sched_migration_cost)) - sync = 0; - } else { - if (sched_feat(SYNC_MORE) && - (curr->se.avg_overlap < sysctl_sched_migration_cost && - p->se.avg_overlap < sysctl_sched_migration_cost)) - sync = 1; - } - /* * If sync wakeup then subtract the (maximum possible) * effect of the currently running task from the load @@ -1711,11 +1698,6 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_ if (sched_feat(WAKEUP_SYNC) && sync) goto preempt; - if (sched_feat(WAKEUP_OVERLAP) && - se->avg_overlap < sysctl_sched_migration_cost && - pse->avg_overlap < sysctl_sched_migration_cost) - goto preempt; - if (!sched_feat(WAKEUP_PREEMPT)) return; diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 96ef5dbc66e1..c545e048dfed 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -41,12 +41,6 @@ SCHED_FEAT(ASYM_GRAN, 1) */ SCHED_FEAT(WAKEUP_SYNC, 0) -/* - * Wakeup preempt based on task behaviour. Tasks that do not overlap - * don't get preempted. - */ -SCHED_FEAT(WAKEUP_OVERLAP, 0) - /* * Use the SYNC wakeup hint, pipes and the likes use this to indicate * the remote end is likely to consume the data we just wrote, and @@ -63,16 +57,6 @@ SCHED_FEAT(SYNC_WAKEUPS, 1) */ SCHED_FEAT(AFFINE_WAKEUPS, 1) -/* - * Weaken SYNC hint based on overlap - */ -SCHED_FEAT(SYNC_LESS, 1) - -/* - * Add SYNC hint based on overlap - */ -SCHED_FEAT(SYNC_MORE, 0) - /* * Prefer to schedule the task we woke last (assuming it failed * wakeup-preemption), since its likely going to consume data we -- cgit v1.2.3-70-g09d2 From a64692a3afd85fe048551ab89142fd5ca99a0dbd Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:16:20 +0100 Subject: sched: Cleanup/optimize clock updates Now that we no longer depend on the clock being updated prior to enqueueing on migratory wakeup, we can clean up a bit, placing calls to update_rq_clock() exactly where they are needed, ie on enqueue, dequeue and schedule events. In the case of a freshly enqueued task immediately preempting, we can skip the update during preemption, as the clock was just updated by the enqueue event. We also save an unneeded call during a migratory wakeup by not updating the previous runqueue, where update_curr() won't be invoked. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301199.6785.32.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 32 ++++++++++++++++---------------- kernel/sched_fair.c | 2 -- 2 files changed, 16 insertions(+), 18 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 68ed6f4f3c13..16559de4edea 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -495,6 +495,8 @@ struct rq { u64 nohz_stamp; unsigned char in_nohz_recently; #endif + unsigned int skip_clock_update; + /* capture load from *all* tasks on this cpu: */ struct load_weight load; unsigned long nr_load_updates; @@ -592,6 +594,13 @@ static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) { rq->curr->sched_class->check_preempt_curr(rq, p, flags); + + /* + * A queue event has occurred, and we're going to schedule. In + * this case, we can save a useless back to back clock update. + */ + if (test_tsk_need_resched(p)) + rq->skip_clock_update = 1; } static inline int cpu_of(struct rq *rq) @@ -626,7 +635,8 @@ static inline int cpu_of(struct rq *rq) inline void update_rq_clock(struct rq *rq) { - rq->clock = sched_clock_cpu(cpu_of(rq)); + if (!rq->skip_clock_update) + rq->clock = sched_clock_cpu(cpu_of(rq)); } /* @@ -1782,8 +1792,6 @@ static void double_rq_lock(struct rq *rq1, struct rq *rq2) raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); } } - update_rq_clock(rq1); - update_rq_clock(rq2); } /* @@ -1880,6 +1888,7 @@ static void update_avg(u64 *avg, u64 sample) static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) { + update_rq_clock(rq); sched_info_queued(p); p->sched_class->enqueue_task(rq, p, wakeup, head); p->se.on_rq = 1; @@ -1887,6 +1896,7 @@ enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { + update_rq_clock(rq); sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; @@ -2366,7 +2376,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, smp_wmb(); rq = task_rq_lock(p, &flags); - update_rq_clock(rq); if (!(p->state & state)) goto out; @@ -2407,7 +2416,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, rq = cpu_rq(cpu); raw_spin_lock(&rq->lock); - update_rq_clock(rq); /* * We migrated the task without holding either rq->lock, however @@ -2624,7 +2632,6 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) BUG_ON(p->state != TASK_WAKING); p->state = TASK_RUNNING; - update_rq_clock(rq); activate_task(rq, p, 0); trace_sched_wakeup_new(rq, p, 1); check_preempt_curr(rq, p, WF_FORK); @@ -3578,6 +3585,9 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { + if (prev->se.on_rq) + update_rq_clock(rq); + rq->skip_clock_update = 0; prev->sched_class->put_prev_task(rq, prev); } @@ -3640,7 +3650,6 @@ need_resched_nonpreemptible: hrtick_clear(rq); raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { @@ -4197,7 +4206,6 @@ void rt_mutex_setprio(struct task_struct *p, int prio) BUG_ON(prio < 0 || prio > MAX_PRIO); rq = task_rq_lock(p, &flags); - update_rq_clock(rq); oldprio = p->prio; prev_class = p->sched_class; @@ -4240,7 +4248,6 @@ void set_user_nice(struct task_struct *p, long nice) * the task might be in the middle of scheduling on another CPU. */ rq = task_rq_lock(p, &flags); - update_rq_clock(rq); /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected @@ -4523,7 +4530,6 @@ recheck: raw_spin_unlock_irqrestore(&p->pi_lock, flags); goto recheck; } - update_rq_clock(rq); on_rq = p->se.on_rq; running = task_current(rq, p); if (on_rq) @@ -5530,7 +5536,6 @@ void sched_idle_next(void) __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - update_rq_clock(rq); activate_task(rq, p, 0); raw_spin_unlock_irqrestore(&rq->lock, flags); @@ -5585,7 +5590,6 @@ static void migrate_dead_tasks(unsigned int dead_cpu) for ( ; ; ) { if (!rq->nr_running) break; - update_rq_clock(rq); next = pick_next_task(rq); if (!next) break; @@ -5869,7 +5873,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) rq->migration_thread = NULL; /* Idle task back to normal (off runqueue, low prio) */ raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); deactivate_task(rq, rq->idle, 0); __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); rq->idle->sched_class = &idle_sched_class; @@ -7815,7 +7818,6 @@ static void normalize_task(struct rq *rq, struct task_struct *p) { int on_rq; - update_rq_clock(rq); on_rq = p->se.on_rq; if (on_rq) deactivate_task(rq, p, 0); @@ -8177,8 +8179,6 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); - update_rq_clock(rq); - running = task_current(rq, tsk); on_rq = tsk->se.on_rq; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index c3b69d4b5d65..69e582020ff8 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -3064,8 +3064,6 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) /* move a task from busiest_rq to target_rq */ double_lock_balance(busiest_rq, target_rq); - update_rq_clock(busiest_rq); - update_rq_clock(target_rq); /* Search for an sd spanning us and the target CPU. */ for_each_domain(target_cpu, sd) { -- cgit v1.2.3-70-g09d2 From c6ee36c423c3ed1fb86bb3eabba9fc256a300d16 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 11 Mar 2010 17:16:43 +0100 Subject: sched: Remove SYNC_WAKEUPS feature Sync wakeups are critical functionality with a long history. Remove it, we don't need the branch or icache footprint. Signed-off-by: Mike Galbraith Signed-off-by: Peter Zijlstra LKML-Reference: <1268301817.6785.47.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 3 --- kernel/sched_features.h | 8 -------- 2 files changed, 11 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 16559de4edea..cc6dc8caa380 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2369,9 +2369,6 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, unsigned long flags; struct rq *rq; - if (!sched_feat(SYNC_WAKEUPS)) - wake_flags &= ~WF_SYNC; - this_cpu = get_cpu(); smp_wmb(); diff --git a/kernel/sched_features.h b/kernel/sched_features.h index 1cb7c4701bf3..f54b6f9cc3dd 100644 --- a/kernel/sched_features.h +++ b/kernel/sched_features.h @@ -22,14 +22,6 @@ SCHED_FEAT(WAKEUP_PREEMPT, 1) */ SCHED_FEAT(ASYM_GRAN, 1) -/* - * Use the SYNC wakeup hint, pipes and the likes use this to indicate - * the remote end is likely to consume the data we just wrote, and - * therefore has cache benefit from being placed on the same cpu, see - * also AFFINE_WAKEUPS. - */ -SCHED_FEAT(SYNC_WAKEUPS, 1) - /* * Based on load and program behaviour, see if it makes sense to place * a newly woken task on the same cpu as the task that woke it -- -- cgit v1.2.3-70-g09d2 From 897f0b3c3ff40b443c84e271bef19bd6ae885195 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 15 Mar 2010 10:10:03 +0100 Subject: sched: Kill the broken and deadlockable cpuset_lock/cpuset_cpus_allowed_locked code This patch just states the fact the cpusets/cpuhotplug interaction is broken and removes the deadlockable code which only pretends to work. - cpuset_lock() doesn't really work. It is needed for cpuset_cpus_allowed_locked() but we can't take this lock in try_to_wake_up()->select_fallback_rq() path. - cpuset_lock() is deadlockable. Suppose that a task T bound to CPU takes callback_mutex. If cpu_down(CPU) happens before T drops callback_mutex stop_machine() preempts T, then migration_call(CPU_DEAD) tries to take cpuset_lock() and hangs forever because CPU is already dead and thus T can't be scheduled. - cpuset_cpus_allowed_locked() is deadlockable too. It takes task_lock() which is not irq-safe, but try_to_wake_up() can be called from irq. Kill them, and change select_fallback_rq() to use cpu_possible_mask, like we currently do without CONFIG_CPUSETS. Also, with or without this patch, with or without CONFIG_CPUSETS, the callers of select_fallback_rq() can race with each other or with set_cpus_allowed() pathes. The subsequent patches try to to fix these problems. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100315091003.GA9123@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 13 ------------- kernel/cpuset.c | 27 +-------------------------- kernel/sched.c | 10 +++------- 3 files changed, 4 insertions(+), 46 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index a5740fc4d04b..eeaaee746bee 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -21,8 +21,6 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); -extern void cpuset_cpus_allowed_locked(struct task_struct *p, - struct cpumask *mask); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -69,9 +67,6 @@ struct seq_file; extern void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task); -extern void cpuset_lock(void); -extern void cpuset_unlock(void); - extern int cpuset_mem_spread_node(void); static inline int cpuset_do_page_mem_spread(void) @@ -105,11 +100,6 @@ static inline void cpuset_cpus_allowed(struct task_struct *p, { cpumask_copy(mask, cpu_possible_mask); } -static inline void cpuset_cpus_allowed_locked(struct task_struct *p, - struct cpumask *mask) -{ - cpumask_copy(mask, cpu_possible_mask); -} static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { @@ -157,9 +147,6 @@ static inline void cpuset_task_status_allowed(struct seq_file *m, { } -static inline void cpuset_lock(void) {} -static inline void cpuset_unlock(void) {} - static inline int cpuset_mem_spread_node(void) { return 0; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index d10946748ec2..9a747f56d58c 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2182,19 +2182,10 @@ void __init cpuset_init_smp(void) void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { mutex_lock(&callback_mutex); - cpuset_cpus_allowed_locked(tsk, pmask); - mutex_unlock(&callback_mutex); -} - -/** - * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset. - * Must be called with callback_mutex held. - **/ -void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask) -{ task_lock(tsk); guarantee_online_cpus(task_cs(tsk), pmask); task_unlock(tsk); + mutex_unlock(&callback_mutex); } void cpuset_init_current_mems_allowed(void) @@ -2382,22 +2373,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) return 0; } -/** - * cpuset_lock - lock out any changes to cpuset structures - * - * The out of memory (oom) code needs to mutex_lock cpusets - * from being changed while it scans the tasklist looking for a - * task in an overlapping cpuset. Expose callback_mutex via this - * cpuset_lock() routine, so the oom code can lock it, before - * locking the task list. The tasklist_lock is a spinlock, so - * must be taken inside callback_mutex. - */ - -void cpuset_lock(void) -{ - mutex_lock(&callback_mutex); -} - /** * cpuset_unlock - release lock on cpuset changes * diff --git a/kernel/sched.c b/kernel/sched.c index 52b7efd27416..c0b3ebc16317 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2296,11 +2296,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) return dest_cpu; /* No more Mr. Nice Guy. */ - if (dest_cpu >= nr_cpu_ids) { - rcu_read_lock(); - cpuset_cpus_allowed_locked(p, &p->cpus_allowed); - rcu_read_unlock(); - dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); + if (unlikely(dest_cpu >= nr_cpu_ids)) { + cpumask_copy(&p->cpus_allowed, cpu_possible_mask); + dest_cpu = cpumask_any(cpu_active_mask); /* * Don't tell them about moving exiting tasks or @@ -5866,7 +5864,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_DEAD: case CPU_DEAD_FROZEN: - cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */ migrate_live_tasks(cpu); rq = cpu_rq(cpu); kthread_stop(rq->migration_thread); @@ -5879,7 +5876,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) rq->idle->sched_class = &idle_sched_class; migrate_dead_tasks(cpu); raw_spin_unlock_irq(&rq->lock); - cpuset_unlock(); migrate_nr_uninterruptible(rq); BUG_ON(rq->nr_running != 0); calc_global_load_remove(rq); -- cgit v1.2.3-70-g09d2 From 1445c08d06c5594895b4fae952ef8a457e89c390 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 15 Mar 2010 10:10:10 +0100 Subject: sched: move_task_off_dead_cpu(): Take rq->lock around select_fallback_rq() move_task_off_dead_cpu()->select_fallback_rq() reads/updates ->cpus_allowed lockless. We can race with set_cpus_allowed() running in parallel. Change it to take rq->lock around select_fallback_rq(). Note that it is not trivial to move this spin_lock() into select_fallback_rq(), we must recheck the task was not migrated after we take the lock and other callers do not need this lock. To avoid the races with other callers of select_fallback_rq() which rely on TASK_WAKING, we also check p->state != TASK_WAKING and do nothing otherwise. The owner of TASK_WAKING must update ->cpus_allowed and choose the correct CPU anyway, and the subsequent __migrate_task() is just meaningless because p->se.on_rq must be false. Alternatively, we could change select_task_rq() to take rq->lock right after it calls sched_class->select_task_rq(), but this looks a bit ugly. Also, change it to not assume irqs are disabled and absorb __migrate_task_irq(). Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100315091010.GA9131@redhat.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index c0b3ebc16317..27774b5aeb61 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5448,29 +5448,29 @@ static int migration_thread(void *data) } #ifdef CONFIG_HOTPLUG_CPU - -static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) -{ - int ret; - - local_irq_disable(); - ret = __migrate_task(p, src_cpu, dest_cpu); - local_irq_enable(); - return ret; -} - /* * Figure out where task on dead CPU should go, use force if necessary. */ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) { - int dest_cpu; - + struct rq *rq = cpu_rq(dead_cpu); + int needs_cpu, uninitialized_var(dest_cpu); + unsigned long flags; again: - dest_cpu = select_fallback_rq(dead_cpu, p); + local_irq_save(flags); + + raw_spin_lock(&rq->lock); + needs_cpu = (task_cpu(p) == dead_cpu) && (p->state != TASK_WAKING); + if (needs_cpu) + dest_cpu = select_fallback_rq(dead_cpu, p); + raw_spin_unlock(&rq->lock); /* It can have affinity changed while we were choosing. */ - if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu))) + if (needs_cpu) + needs_cpu = !__migrate_task(p, dead_cpu, dest_cpu); + local_irq_restore(flags); + + if (unlikely(needs_cpu)) goto again; } -- cgit v1.2.3-70-g09d2 From c1804d547dc098363443667609c272d1e4d15ee8 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 15 Mar 2010 10:10:14 +0100 Subject: sched: move_task_off_dead_cpu(): Remove retry logic The previous patch preserved the retry logic, but it looks unneeded. __migrate_task() can only fail if we raced with migration after we dropped the lock, but in this case the caller of set_cpus_allowed/etc must initiate migration itself if ->on_rq == T. We already fixed p->cpus_allowed, the changes in active/online masks must be visible to racer, it should migrate the task to online cpu correctly. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100315091014.GA9138@redhat.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 13 ++++++------- 1 file changed, 6 insertions(+), 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 27774b5aeb61..f475c608b073 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5456,7 +5456,7 @@ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) struct rq *rq = cpu_rq(dead_cpu); int needs_cpu, uninitialized_var(dest_cpu); unsigned long flags; -again: + local_irq_save(flags); raw_spin_lock(&rq->lock); @@ -5464,14 +5464,13 @@ again: if (needs_cpu) dest_cpu = select_fallback_rq(dead_cpu, p); raw_spin_unlock(&rq->lock); - - /* It can have affinity changed while we were choosing. */ + /* + * It can only fail if we race with set_cpus_allowed(), + * in the racer should migrate the task anyway. + */ if (needs_cpu) - needs_cpu = !__migrate_task(p, dead_cpu, dest_cpu); + __migrate_task(p, dead_cpu, dest_cpu); local_irq_restore(flags); - - if (unlikely(needs_cpu)) - goto again; } /* -- cgit v1.2.3-70-g09d2 From 30da688ef6b76e01969b00608202fff1eed2accc Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 15 Mar 2010 10:10:19 +0100 Subject: sched: sched_exec(): Remove the select_fallback_rq() logic sched_exec()->select_task_rq() reads/updates ->cpus_allowed lockless. This can race with other CPUs updating our ->cpus_allowed, and this looks meaningless to me. The task is current and running, it must have online cpus in ->cpus_allowed, the fallback mode is bogus. And, if ->sched_class returns the "wrong" cpu, this likely means we raced with set_cpus_allowed() which was called for reason, why should sched_exec() retry and call ->select_task_rq() again? Change the code to call sched_class->select_task_rq() directly and do nothing if the returned cpu is wrong after re-checking under rq->lock. From now task_struct->cpus_allowed is always stable under TASK_WAKING, select_fallback_rq() is always called under rq-lock or the caller or the caller owns TASK_WAKING (select_task_rq). Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100315091019.GA9141@redhat.com> Signed-off-by: Ingo Molnar --- kernel/sched.c | 25 ++++++++----------------- 1 file changed, 8 insertions(+), 17 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index f475c608b073..165b532dd8c2 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2280,6 +2280,9 @@ void task_oncpu_function_call(struct task_struct *p, } #ifdef CONFIG_SMP +/* + * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. + */ static int select_fallback_rq(int cpu, struct task_struct *p) { int dest_cpu; @@ -2316,12 +2319,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) } /* - * Gets called from 3 sites (exec, fork, wakeup), since it is called without - * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done - * by: - * - * exec: is unstable, retry loop - * fork & wake-up: serialize ->cpus_allowed against TASK_WAKING + * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. */ static inline int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) @@ -3076,9 +3074,8 @@ void sched_exec(void) unsigned long flags; struct rq *rq; -again: this_cpu = get_cpu(); - dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0); + dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); if (dest_cpu == this_cpu) { put_cpu(); return; @@ -3086,18 +3083,12 @@ again: rq = task_rq_lock(p, &flags); put_cpu(); - /* * select_task_rq() can race against ->cpus_allowed */ - if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed) - || unlikely(!cpu_active(dest_cpu))) { - task_rq_unlock(rq, &flags); - goto again; - } - - /* force the process onto the specified CPU */ - if (migrate_task(p, dest_cpu, &req)) { + if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && + likely(cpu_active(dest_cpu)) && + migrate_task(p, dest_cpu, &req)) { /* Need to wait for migration thread (might exit: take ref). */ struct task_struct *mt = rq->migration_thread; -- cgit v1.2.3-70-g09d2 From 6a1bdc1b577ebcb65f6603c57f8347309bc4ab13 Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 15 Mar 2010 10:10:23 +0100 Subject: sched: _cpu_down(): Don't play with current->cpus_allowed _cpu_down() changes the current task's affinity and then recovers it at the end. The problems are well known: we can't restore old_allowed if it was bound to the now-dead-cpu, and we can race with the userspace which can change cpu-affinity during unplug. _cpu_down() should not play with current->cpus_allowed at all. Instead, take_cpu_down() can migrate the caller of _cpu_down() after __cpu_disable() removes the dying cpu from cpu_online_mask. Signed-off-by: Oleg Nesterov Acked-by: Rafael J. Wysocki Signed-off-by: Peter Zijlstra LKML-Reference: <20100315091023.GA9148@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/cpu.c | 18 ++++++------------ kernel/sched.c | 2 +- 3 files changed, 8 insertions(+), 13 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 43c945152732..8bea40725c76 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1843,6 +1843,7 @@ extern void sched_clock_idle_sleep_event(void); extern void sched_clock_idle_wakeup_event(u64 delta_ns); #ifdef CONFIG_HOTPLUG_CPU +extern void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p); extern void idle_task_exit(void); #else static inline void idle_task_exit(void) {} diff --git a/kernel/cpu.c b/kernel/cpu.c index f8cced2692b3..8d340faac380 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -163,6 +163,7 @@ static inline void check_for_tasks(int cpu) } struct take_cpu_down_param { + struct task_struct *caller; unsigned long mod; void *hcpu; }; @@ -171,6 +172,7 @@ struct take_cpu_down_param { static int __ref take_cpu_down(void *_param) { struct take_cpu_down_param *param = _param; + unsigned int cpu = (unsigned long)param->hcpu; int err; /* Ensure this CPU doesn't handle any more interrupts. */ @@ -181,6 +183,8 @@ static int __ref take_cpu_down(void *_param) raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod, param->hcpu); + if (task_cpu(param->caller) == cpu) + move_task_off_dead_cpu(cpu, param->caller); /* Force idle task to run as soon as we yield: it should immediately notice cpu is offline and die quickly. */ sched_idle_next(); @@ -191,10 +195,10 @@ static int __ref take_cpu_down(void *_param) static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) { int err, nr_calls = 0; - cpumask_var_t old_allowed; void *hcpu = (void *)(long)cpu; unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0; struct take_cpu_down_param tcd_param = { + .caller = current, .mod = mod, .hcpu = hcpu, }; @@ -205,9 +209,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) if (!cpu_online(cpu)) return -EINVAL; - if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL)) - return -ENOMEM; - cpu_hotplug_begin(); set_cpu_active(cpu, false); err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod, @@ -224,10 +225,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) goto out_release; } - /* Ensure that we are not runnable on dying cpu */ - cpumask_copy(old_allowed, ¤t->cpus_allowed); - set_cpus_allowed_ptr(current, cpu_active_mask); - err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { set_cpu_active(cpu, true); @@ -236,7 +233,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) hcpu) == NOTIFY_BAD) BUG(); - goto out_allowed; + goto out_release; } BUG_ON(cpu_online(cpu)); @@ -254,8 +251,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) check_for_tasks(cpu); -out_allowed: - set_cpus_allowed_ptr(current, old_allowed); out_release: cpu_hotplug_done(); if (!err) { @@ -263,7 +258,6 @@ out_release: hcpu) == NOTIFY_BAD) BUG(); } - free_cpumask_var(old_allowed); return err; } diff --git a/kernel/sched.c b/kernel/sched.c index 165b532dd8c2..11119deffa48 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5442,7 +5442,7 @@ static int migration_thread(void *data) /* * Figure out where task on dead CPU should go, use force if necessary. */ -static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) +void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) { struct rq *rq = cpu_rq(dead_cpu); int needs_cpu, uninitialized_var(dest_cpu); -- cgit v1.2.3-70-g09d2 From 9084bb8246ea935b98320554229e2f371f7f52fa Mon Sep 17 00:00:00 2001 From: Oleg Nesterov Date: Mon, 15 Mar 2010 10:10:27 +0100 Subject: sched: Make select_fallback_rq() cpuset friendly Introduce cpuset_cpus_allowed_fallback() helper to fix the cpuset problems with select_fallback_rq(). It can be called from any context and can't use any cpuset locks including task_lock(). It is called when the task doesn't have online cpus in ->cpus_allowed but ttwu/etc must be able to find a suitable cpu. I am not proud of this patch. Everything which needs such a fat comment can't be good even if correct. But I'd prefer to not change the locking rules in the code I hardly understand, and in any case I believe this simple change make the code much more correct compared to deadlocks we currently have. Signed-off-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: <20100315091027.GA9155@redhat.com> Signed-off-by: Ingo Molnar --- include/linux/cpuset.h | 7 +++++++ kernel/cpuset.c | 42 ++++++++++++++++++++++++++++++++++++++++++ kernel/sched.c | 4 +--- 3 files changed, 50 insertions(+), 3 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index eeaaee746bee..a73454aec333 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -21,6 +21,7 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ extern int cpuset_init(void); extern void cpuset_init_smp(void); extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask); +extern int cpuset_cpus_allowed_fallback(struct task_struct *p); extern nodemask_t cpuset_mems_allowed(struct task_struct *p); #define cpuset_current_mems_allowed (current->mems_allowed) void cpuset_init_current_mems_allowed(void); @@ -101,6 +102,12 @@ static inline void cpuset_cpus_allowed(struct task_struct *p, cpumask_copy(mask, cpu_possible_mask); } +static inline int cpuset_cpus_allowed_fallback(struct task_struct *p) +{ + cpumask_copy(&p->cpus_allowed, cpu_possible_mask); + return cpumask_any(cpu_active_mask); +} + static inline nodemask_t cpuset_mems_allowed(struct task_struct *p) { return node_possible_map; diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 9a747f56d58c..9a50c5f6e727 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2188,6 +2188,48 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) mutex_unlock(&callback_mutex); } +int cpuset_cpus_allowed_fallback(struct task_struct *tsk) +{ + const struct cpuset *cs; + int cpu; + + rcu_read_lock(); + cs = task_cs(tsk); + if (cs) + cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed); + rcu_read_unlock(); + + /* + * We own tsk->cpus_allowed, nobody can change it under us. + * + * But we used cs && cs->cpus_allowed lockless and thus can + * race with cgroup_attach_task() or update_cpumask() and get + * the wrong tsk->cpus_allowed. However, both cases imply the + * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() + * which takes task_rq_lock(). + * + * If we are called after it dropped the lock we must see all + * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary + * set any mask even if it is not right from task_cs() pov, + * the pending set_cpus_allowed_ptr() will fix things. + */ + + cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask); + if (cpu >= nr_cpu_ids) { + /* + * Either tsk->cpus_allowed is wrong (see above) or it + * is actually empty. The latter case is only possible + * if we are racing with remove_tasks_in_empty_cpuset(). + * Like above we can temporary set any mask and rely on + * set_cpus_allowed_ptr() as synchronization point. + */ + cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask); + cpu = cpumask_any(cpu_active_mask); + } + + return cpu; +} + void cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); diff --git a/kernel/sched.c b/kernel/sched.c index 11119deffa48..9a38c7a24ed7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2300,9 +2300,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) /* No more Mr. Nice Guy. */ if (unlikely(dest_cpu >= nr_cpu_ids)) { - cpumask_copy(&p->cpus_allowed, cpu_possible_mask); - dest_cpu = cpumask_any(cpu_active_mask); - + dest_cpu = cpuset_cpus_allowed_fallback(p); /* * Don't tell them about moving exiting tasks or * kernel threads (both mm NULL), since they never -- cgit v1.2.3-70-g09d2 From 0017d735092844118bef006696a750a0e4ef6ebd Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Mar 2010 18:34:10 +0100 Subject: sched: Fix TASK_WAKING vs fork deadlock Oleg noticed a few races with the TASK_WAKING usage on fork. - since TASK_WAKING is basically a spinlock, it should be IRQ safe - since we set TASK_WAKING (*) without holding rq->lock it could be there still is a rq->lock holder, thereby not actually providing full serialization. (*) in fact we clear PF_STARTING, which in effect enables TASK_WAKING. Cure the second issue by not setting TASK_WAKING in sched_fork(), but only temporarily in wake_up_new_task() while calling select_task_rq(). Cure the first by holding rq->lock around the select_task_rq() call, this will disable IRQs, this however requires that we push down the rq->lock release into select_task_rq_fair()'s cgroup stuff. Because select_task_rq_fair() still needs to drop the rq->lock we cannot fully get rid of TASK_WAKING. Reported-by: Oleg Nesterov Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 ++- kernel/sched.c | 65 ++++++++++++++++++------------------------------- kernel/sched_fair.c | 8 ++++-- kernel/sched_idletask.c | 3 ++- kernel/sched_rt.c | 5 ++-- 5 files changed, 36 insertions(+), 48 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index 8bea40725c76..fb6c18843ee8 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1046,7 +1046,8 @@ struct sched_class { void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP - int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); + int (*select_task_rq)(struct rq *rq, struct task_struct *p, + int sd_flag, int flags); void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); void (*post_schedule) (struct rq *this_rq); diff --git a/kernel/sched.c b/kernel/sched.c index 9a38c7a24ed7..dcd17736dae1 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -916,14 +916,10 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) /* * Check whether the task is waking, we use this to synchronize against * ttwu() so that task_cpu() reports a stable number. - * - * We need to make an exception for PF_STARTING tasks because the fork - * path might require task_rq_lock() to work, eg. it can call - * set_cpus_allowed_ptr() from the cpuset clone_ns code. */ static inline int task_is_waking(struct task_struct *p) { - return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING)); + return unlikely(p->state == TASK_WAKING); } /* @@ -2320,9 +2316,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. */ static inline -int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags) +int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) { - int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags); + int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags); /* * In order not to call set_task_cpu() on a blocking task we need @@ -2393,17 +2389,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, if (p->sched_class->task_waking) p->sched_class->task_waking(rq, p); - __task_rq_unlock(rq); - - cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags); - if (cpu != orig_cpu) { - /* - * Since we migrate the task without holding any rq->lock, - * we need to be careful with task_rq_lock(), since that - * might end up locking an invalid rq. - */ + cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); + if (cpu != orig_cpu) set_task_cpu(p, cpu); - } + __task_rq_unlock(rq); rq = cpu_rq(cpu); raw_spin_lock(&rq->lock); @@ -2530,11 +2519,11 @@ void sched_fork(struct task_struct *p, int clone_flags) __sched_fork(p); /* - * We mark the process as waking here. This guarantees that + * We mark the process as running here. This guarantees that * nobody will actually run it, and a signal or other external * event cannot wake it up and insert it on the runqueue either. */ - p->state = TASK_WAKING; + p->state = TASK_RUNNING; /* * Revert to default priority/policy on fork if requested. @@ -2601,28 +2590,25 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) int cpu __maybe_unused = get_cpu(); #ifdef CONFIG_SMP + rq = task_rq_lock(p, &flags); + p->state = TASK_WAKING; + /* * Fork balancing, do it here and not earlier because: * - cpus_allowed can change in the fork path * - any previously selected cpu might disappear through hotplug * - * We still have TASK_WAKING but PF_STARTING is gone now, meaning - * ->cpus_allowed is stable, we have preemption disabled, meaning - * cpu_online_mask is stable. + * We set TASK_WAKING so that select_task_rq() can drop rq->lock + * without people poking at ->cpus_allowed. */ - cpu = select_task_rq(p, SD_BALANCE_FORK, 0); + cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0); set_task_cpu(p, cpu); -#endif - - /* - * Since the task is not on the rq and we still have TASK_WAKING set - * nobody else will migrate this task. - */ - rq = cpu_rq(cpu); - raw_spin_lock_irqsave(&rq->lock, flags); - BUG_ON(p->state != TASK_WAKING); p->state = TASK_RUNNING; + task_rq_unlock(rq, &flags); +#endif + + rq = task_rq_lock(p, &flags); activate_task(rq, p, 0); trace_sched_wakeup_new(rq, p, 1); check_preempt_curr(rq, p, WF_FORK); @@ -3068,19 +3054,15 @@ void sched_exec(void) { struct task_struct *p = current; struct migration_req req; - int dest_cpu, this_cpu; unsigned long flags; struct rq *rq; - - this_cpu = get_cpu(); - dest_cpu = p->sched_class->select_task_rq(p, SD_BALANCE_EXEC, 0); - if (dest_cpu == this_cpu) { - put_cpu(); - return; - } + int dest_cpu; rq = task_rq_lock(p, &flags); - put_cpu(); + dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0); + if (dest_cpu == smp_processor_id()) + goto unlock; + /* * select_task_rq() can race against ->cpus_allowed */ @@ -3098,6 +3080,7 @@ void sched_exec(void) return; } +unlock: task_rq_unlock(rq, &flags); } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 49ad99378f82..8a5e7632d09b 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1423,7 +1423,8 @@ select_idle_sibling(struct task_struct *p, struct sched_domain *sd, int target) * * preempt must be disabled. */ -static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flags) +static int +select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_flags) { struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL; int cpu = smp_processor_id(); @@ -1521,8 +1522,11 @@ static int select_task_rq_fair(struct task_struct *p, int sd_flag, int wake_flag cpumask_weight(sched_domain_span(sd)))) tmp = affine_sd; - if (tmp) + if (tmp) { + raw_spin_unlock(&rq->lock); update_shares(tmp); + raw_spin_lock(&rq->lock); + } } #endif diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index a8a6d8a50947..5af709f503b0 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -6,7 +6,8 @@ */ #ifdef CONFIG_SMP -static int select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) +static int +select_task_rq_idle(struct rq *rq, struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index 012d69bb67c7..fde895f8044d 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -948,10 +948,9 @@ static void yield_task_rt(struct rq *rq) #ifdef CONFIG_SMP static int find_lowest_rq(struct task_struct *task); -static int select_task_rq_rt(struct task_struct *p, int sd_flag, int flags) +static int +select_task_rq_rt(struct rq *rq, struct task_struct *p, int sd_flag, int flags) { - struct rq *rq = task_rq(p); - if (sd_flag != SD_BALANCE_WAKE) return smp_processor_id(); -- cgit v1.2.3-70-g09d2 From 65cc8e4859ff29a9ddc989c88557d6059834c2a2 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 25 Mar 2010 21:05:16 +0100 Subject: sched: Optimize task_rq_lock() Now that we hold the rq->lock over set_task_cpu() again, we can do away with most of the TASK_WAKING checks and reduce them again to set_cpus_allowed_ptr(). Removes some conditionals from scheduling hot-paths. Signed-off-by: Peter Zijlstra Cc: Oleg Nesterov LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index dcd17736dae1..51d336e08a92 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -914,8 +914,8 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ /* - * Check whether the task is waking, we use this to synchronize against - * ttwu() so that task_cpu() reports a stable number. + * Check whether the task is waking, we use this to synchronize ->cpus_allowed + * against ttwu(). */ static inline int task_is_waking(struct task_struct *p) { @@ -932,11 +932,9 @@ static inline struct rq *__task_rq_lock(struct task_struct *p) struct rq *rq; for (;;) { - while (task_is_waking(p)) - cpu_relax(); rq = task_rq(p); raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p) && !task_is_waking(p))) + if (likely(rq == task_rq(p))) return rq; raw_spin_unlock(&rq->lock); } @@ -953,12 +951,10 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) struct rq *rq; for (;;) { - while (task_is_waking(p)) - cpu_relax(); local_irq_save(*flags); rq = task_rq(p); raw_spin_lock(&rq->lock); - if (likely(rq == task_rq(p) && !task_is_waking(p))) + if (likely(rq == task_rq(p))) return rq; raw_spin_unlock_irqrestore(&rq->lock, *flags); } @@ -5262,7 +5258,18 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) struct rq *rq; int ret = 0; + /* + * Serialize against TASK_WAKING so that ttwu() and wunt() can + * drop the rq->lock and still rely on ->cpus_allowed. + */ +again: + while (task_is_waking(p)) + cpu_relax(); rq = task_rq_lock(p, &flags); + if (task_is_waking(p)) { + task_rq_unlock(rq, &flags); + goto again; + } if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; -- cgit v1.2.3-70-g09d2 From cc87f76a601d2d256118f7bab15e35254356ae21 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 26 Mar 2010 12:22:14 +0100 Subject: sched: Fix nr_uninterruptible count The cpuload calculation in calc_load_account_active() assumes rq->nr_uninterruptible will not change on an offline cpu after migrate_nr_uninterruptible(). However the recent migrate on wakeup changes broke that and would result in decrementing the offline cpu's rq->nr_uninterruptible. Fix this by accounting the nr_uninterruptible on the waking cpu. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- kernel/sched.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 51d336e08a92..14c8d2a1b38a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2378,8 +2378,12 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, * * First fix up the nr_uninterruptible count: */ - if (task_contributes_to_load(p)) - rq->nr_uninterruptible--; + if (task_contributes_to_load(p)) { + if (likely(cpu_online(orig_cpu))) + rq->nr_uninterruptible--; + else + this_rq()->nr_uninterruptible--; + } p->state = TASK_WAKING; if (p->sched_class->task_waking) -- cgit v1.2.3-70-g09d2 From 371fd7e7a56a5c136d31aa980011bd2f131c3ef5 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Wed, 24 Mar 2010 16:38:48 +0100 Subject: sched: Add enqueue/dequeue flags In order to reduce the dependency on TASK_WAKING rework the enqueue interface to support a proper flags field. Replace the int wakeup, bool head arguments with an int flags argument and create the following flags: ENQUEUE_WAKEUP - the enqueue is a wakeup of a sleeping task, ENQUEUE_WAKING - the enqueue has relative vruntime due to having sched_class::task_waking() called, ENQUEUE_HEAD - the waking task should be places on the head of the priority queue (where appropriate). For symmetry also convert sched_class::dequeue() to a flags scheme. Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 11 ++++++++--- kernel/sched.c | 32 +++++++++++++++++--------------- kernel/sched_fair.c | 25 ++++++++----------------- kernel/sched_idletask.c | 2 +- kernel/sched_rt.c | 8 ++++---- 5 files changed, 38 insertions(+), 40 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index fb6c18843ee8..e3e900f318d7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1032,12 +1032,17 @@ struct sched_domain; #define WF_SYNC 0x01 /* waker goes to sleep after wakup */ #define WF_FORK 0x02 /* child wakeup after fork */ +#define ENQUEUE_WAKEUP 1 +#define ENQUEUE_WAKING 2 +#define ENQUEUE_HEAD 4 + +#define DEQUEUE_SLEEP 1 + struct sched_class { const struct sched_class *next; - void (*enqueue_task) (struct rq *rq, struct task_struct *p, int wakeup, - bool head); - void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep); + void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); void (*yield_task) (struct rq *rq); void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); diff --git a/kernel/sched.c b/kernel/sched.c index 14c8d2a1b38a..4a57e96dd6c7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1877,44 +1877,43 @@ static void update_avg(u64 *avg, u64 sample) *avg += diff >> 3; } -static void -enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head) +static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { update_rq_clock(rq); sched_info_queued(p); - p->sched_class->enqueue_task(rq, p, wakeup, head); + p->sched_class->enqueue_task(rq, p, flags); p->se.on_rq = 1; } -static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) +static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) { update_rq_clock(rq); sched_info_dequeued(p); - p->sched_class->dequeue_task(rq, p, sleep); + p->sched_class->dequeue_task(rq, p, flags); p->se.on_rq = 0; } /* * activate_task - move a task to the runqueue. */ -static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) +static void activate_task(struct rq *rq, struct task_struct *p, int flags) { if (task_contributes_to_load(p)) rq->nr_uninterruptible--; - enqueue_task(rq, p, wakeup, false); + enqueue_task(rq, p, flags); inc_nr_running(rq); } /* * deactivate_task - remove a task from the runqueue. */ -static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) +static void deactivate_task(struct rq *rq, struct task_struct *p, int flags) { if (task_contributes_to_load(p)) rq->nr_uninterruptible++; - dequeue_task(rq, p, sleep); + dequeue_task(rq, p, flags); dec_nr_running(rq); } @@ -2353,6 +2352,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, { int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; + unsigned long en_flags = ENQUEUE_WAKEUP; struct rq *rq; this_cpu = get_cpu(); @@ -2386,8 +2386,10 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, } p->state = TASK_WAKING; - if (p->sched_class->task_waking) + if (p->sched_class->task_waking) { p->sched_class->task_waking(rq, p); + en_flags |= ENQUEUE_WAKING; + } cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); if (cpu != orig_cpu) @@ -2432,7 +2434,7 @@ out_activate: schedstat_inc(p, se.statistics.nr_wakeups_local); else schedstat_inc(p, se.statistics.nr_wakeups_remote); - activate_task(rq, p, 1); + activate_task(rq, p, en_flags); success = 1; out_running: @@ -3623,7 +3625,7 @@ need_resched_nonpreemptible: if (unlikely(signal_pending_state(prev->state, prev))) prev->state = TASK_RUNNING; else - deactivate_task(rq, prev, 1); + deactivate_task(rq, prev, DEQUEUE_SLEEP); switch_count = &prev->nvcsw; } @@ -4193,7 +4195,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); if (on_rq) { - enqueue_task(rq, p, 0, oldprio < prio); + enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio, running); } @@ -4236,7 +4238,7 @@ void set_user_nice(struct task_struct *p, long nice) delta = p->prio - old_prio; if (on_rq) { - enqueue_task(rq, p, 0, false); + enqueue_task(rq, p, 0); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: @@ -8180,7 +8182,7 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->set_curr_task(rq); if (on_rq) - enqueue_task(rq, tsk, 0, false); + enqueue_task(rq, tsk, 0); task_rq_unlock(rq, &flags); } diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 8a5e7632d09b..88d3053ac7c2 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -757,9 +757,6 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial) se->vruntime = vruntime; } -#define ENQUEUE_WAKEUP 1 -#define ENQUEUE_MIGRATE 2 - static void enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { @@ -767,7 +764,7 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update the normalized vruntime before updating min_vruntime * through callig update_curr(). */ - if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_MIGRATE)) + if (!(flags & ENQUEUE_WAKEUP) || (flags & ENQUEUE_WAKING)) se->vruntime += cfs_rq->min_vruntime; /* @@ -803,7 +800,7 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se) } static void -dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) +dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) { /* * Update run-time statistics of the 'current'. @@ -811,7 +808,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) update_curr(cfs_rq); update_stats_dequeue(cfs_rq, se); - if (sleep) { + if (flags & DEQUEUE_SLEEP) { #ifdef CONFIG_SCHEDSTATS if (entity_is_task(se)) { struct task_struct *tsk = task_of(se); @@ -836,7 +833,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep) * update can refer to the ->curr item and we need to reflect this * movement in our normalized position. */ - if (!sleep) + if (!(flags & DEQUEUE_SLEEP)) se->vruntime -= cfs_rq->min_vruntime; } @@ -1045,16 +1042,10 @@ static inline void hrtick_update(struct rq *rq) * then put the task into the rbtree: */ static void -enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head) +enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; - int flags = 0; - - if (wakeup) - flags |= ENQUEUE_WAKEUP; - if (p->state == TASK_WAKING) - flags |= ENQUEUE_MIGRATE; for_each_sched_entity(se) { if (se->on_rq) @@ -1072,18 +1063,18 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int wakeup, bool head) * decreased. We remove the task from the rbtree and * update the fair scheduling stats: */ -static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int sleep) +static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) { struct cfs_rq *cfs_rq; struct sched_entity *se = &p->se; for_each_sched_entity(se) { cfs_rq = cfs_rq_of(se); - dequeue_entity(cfs_rq, se, sleep); + dequeue_entity(cfs_rq, se, flags); /* Don't dequeue parent if it has other entities besides us */ if (cfs_rq->load.weight) break; - sleep = 1; + flags |= DEQUEUE_SLEEP; } hrtick_update(rq); diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index 5af709f503b0..bea2b8f12024 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -33,7 +33,7 @@ static struct task_struct *pick_next_task_idle(struct rq *rq) * message if some code attempts to do it: */ static void -dequeue_task_idle(struct rq *rq, struct task_struct *p, int sleep) +dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags) { raw_spin_unlock_irq(&rq->lock); printk(KERN_ERR "bad: scheduling from the idle thread!\n"); diff --git a/kernel/sched_rt.c b/kernel/sched_rt.c index fde895f8044d..8afb953e31c6 100644 --- a/kernel/sched_rt.c +++ b/kernel/sched_rt.c @@ -888,20 +888,20 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se) * Adding/removing a task to/from a priority array: */ static void -enqueue_task_rt(struct rq *rq, struct task_struct *p, int wakeup, bool head) +enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) { struct sched_rt_entity *rt_se = &p->rt; - if (wakeup) + if (flags & ENQUEUE_WAKEUP) rt_se->timeout = 0; - enqueue_rt_entity(rt_se, head); + enqueue_rt_entity(rt_se, flags & ENQUEUE_HEAD); if (!task_current(rq, p) && p->rt.nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } -static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int sleep) +static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) { struct sched_rt_entity *rt_se = &p->rt; -- cgit v1.2.3-70-g09d2 From 09a40af5240de02d848247ab82440ad75b31ab11 Mon Sep 17 00:00:00 2001 From: Mike Galbraith Date: Thu, 15 Apr 2010 07:29:59 +0200 Subject: sched: Fix UP update_avg() build warning update_avg() is only used for SMP builds, move it to the nearest SMP block. Reported-by: Stephen Rothwell Signed-off-by: Mike Galbraith Cc: Peter Zijlstra LKML-Reference: <1271309399.14779.17.camel@marge.simson.net> Signed-off-by: Ingo Molnar --- kernel/sched.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index ab562ae4007c..de0da71daf77 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1872,12 +1872,6 @@ static void set_load_weight(struct task_struct *p) p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; } -static void update_avg(u64 *avg, u64 sample) -{ - s64 diff = sample - *avg; - *avg += diff >> 3; -} - static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { update_rq_clock(rq); @@ -2332,6 +2326,12 @@ int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_ return cpu; } + +static void update_avg(u64 *avg, u64 sample) +{ + s64 diff = sample - *avg; + *avg += diff >> 3; +} #endif /*** -- cgit v1.2.3-70-g09d2 From 74f5187ac873042f502227701ed1727e7c5fbfa9 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 22 Apr 2010 21:50:19 +0200 Subject: sched: Cure load average vs NO_HZ woes Chase reported that due to us decrementing calc_load_task prematurely (before the next LOAD_FREQ sample), the load average could be scewed by as much as the number of CPUs in the machine. This patch, based on Chase's patch, cures the problem by keeping the delta of the CPU going into NO_HZ idle separately and folding that in on the next LOAD_FREQ update. This restores the balance and we get strict LOAD_FREQ period samples. Signed-off-by: Peter Zijlstra Acked-by: Chase Douglas LKML-Reference: <1271934490.1776.343.camel@laptop> Signed-off-by: Ingo Molnar --- kernel/sched.c | 80 +++++++++++++++++++++++++++++++++++++++++-------- kernel/sched_idletask.c | 3 +- 2 files changed, 68 insertions(+), 15 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index de0da71daf77..0cc913a8554f 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -1815,7 +1815,7 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) } #endif -static void calc_load_account_active(struct rq *this_rq); +static void calc_load_account_idle(struct rq *this_rq); static void update_sysctl(void); static int get_update_sysctl_factor(void); @@ -2950,6 +2950,61 @@ static unsigned long calc_load_update; unsigned long avenrun[3]; EXPORT_SYMBOL(avenrun); +static long calc_load_fold_active(struct rq *this_rq) +{ + long nr_active, delta = 0; + + nr_active = this_rq->nr_running; + nr_active += (long) this_rq->nr_uninterruptible; + + if (nr_active != this_rq->calc_load_active) { + delta = nr_active - this_rq->calc_load_active; + this_rq->calc_load_active = nr_active; + } + + return delta; +} + +#ifdef CONFIG_NO_HZ +/* + * For NO_HZ we delay the active fold to the next LOAD_FREQ update. + * + * When making the ILB scale, we should try to pull this in as well. + */ +static atomic_long_t calc_load_tasks_idle; + +static void calc_load_account_idle(struct rq *this_rq) +{ + long delta; + + delta = calc_load_fold_active(this_rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks_idle); +} + +static long calc_load_fold_idle(void) +{ + long delta = 0; + + /* + * Its got a race, we don't care... + */ + if (atomic_long_read(&calc_load_tasks_idle)) + delta = atomic_long_xchg(&calc_load_tasks_idle, 0); + + return delta; +} +#else +static void calc_load_account_idle(struct rq *this_rq) +{ +} + +static inline long calc_load_fold_idle(void) +{ + return 0; +} +#endif + /** * get_avenrun - get the load average array * @loads: pointer to dest load array @@ -2996,20 +3051,22 @@ void calc_global_load(void) } /* - * Either called from update_cpu_load() or from a cpu going idle + * Called from update_cpu_load() to periodically update this CPU's + * active count. */ static void calc_load_account_active(struct rq *this_rq) { - long nr_active, delta; + long delta; - nr_active = this_rq->nr_running; - nr_active += (long) this_rq->nr_uninterruptible; + if (time_before(jiffies, this_rq->calc_load_update)) + return; - if (nr_active != this_rq->calc_load_active) { - delta = nr_active - this_rq->calc_load_active; - this_rq->calc_load_active = nr_active; + delta = calc_load_fold_active(this_rq); + delta += calc_load_fold_idle(); + if (delta) atomic_long_add(delta, &calc_load_tasks); - } + + this_rq->calc_load_update += LOAD_FREQ; } /* @@ -3041,10 +3098,7 @@ static void update_cpu_load(struct rq *this_rq) this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; } - if (time_after_eq(jiffies, this_rq->calc_load_update)) { - this_rq->calc_load_update += LOAD_FREQ; - calc_load_account_active(this_rq); - } + calc_load_account_active(this_rq); } #ifdef CONFIG_SMP diff --git a/kernel/sched_idletask.c b/kernel/sched_idletask.c index bea2b8f12024..9fa0f402c87c 100644 --- a/kernel/sched_idletask.c +++ b/kernel/sched_idletask.c @@ -23,8 +23,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static struct task_struct *pick_next_task_idle(struct rq *rq) { schedstat_inc(rq, sched_goidle); - /* adjust the active tasks as we might go into a long sleep */ - calc_load_account_active(rq); + calc_load_account_idle(rq); return rq->idle; } -- cgit v1.2.3-70-g09d2 From 669c55e9f99b90e46eaa0f98a67ec53d46dc969a Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 16 Apr 2010 14:59:29 +0200 Subject: sched: Pre-compute cpumask_weight(sched_domain_span(sd)) Dave reported that his large SPARC machines spend lots of time in hweight64(), try and optimize some of those needless cpumask_weight() invocations (esp. with the large offstack cpumasks these are very expensive indeed). Reported-by: David Miller Signed-off-by: Peter Zijlstra LKML-Reference: Signed-off-by: Ingo Molnar --- include/linux/sched.h | 1 + kernel/sched.c | 3 +++ kernel/sched_fair.c | 12 +++++------- 3 files changed, 9 insertions(+), 7 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/linux/sched.h b/include/linux/sched.h index e3e900f318d7..dfea40574b2a 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -960,6 +960,7 @@ struct sched_domain { char *name; #endif + unsigned int span_weight; /* * Span of all CPUs in this domain. * diff --git a/kernel/sched.c b/kernel/sched.c index 0cc913a8554f..4956ed092838 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -6271,6 +6271,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) struct rq *rq = cpu_rq(cpu); struct sched_domain *tmp; + for (tmp = sd; tmp; tmp = tmp->parent) + tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); + /* Remove the sched domains which do not contribute to scheduling. */ for (tmp = sd; tmp; ) { struct sched_domain *parent = tmp->parent; diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index 88d3053ac7c2..0a413c7e3ab8 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -1508,9 +1508,7 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ * Pick the largest domain to update shares over */ tmp = sd; - if (affine_sd && (!tmp || - cpumask_weight(sched_domain_span(affine_sd)) > - cpumask_weight(sched_domain_span(sd)))) + if (affine_sd && (!tmp || affine_sd->span_weight > sd->span_weight)) tmp = affine_sd; if (tmp) { @@ -1554,10 +1552,10 @@ select_task_rq_fair(struct rq *rq, struct task_struct *p, int sd_flag, int wake_ /* Now try balancing at a lower domain level of new_cpu */ cpu = new_cpu; - weight = cpumask_weight(sched_domain_span(sd)); + weight = sd->span_weight; sd = NULL; for_each_domain(cpu, tmp) { - if (weight <= cpumask_weight(sched_domain_span(tmp))) + if (weight <= tmp->span_weight) break; if (tmp->flags & sd_flag) sd = tmp; @@ -2243,7 +2241,7 @@ unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) { - unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long weight = sd->span_weight; unsigned long smt_gain = sd->smt_gain; smt_gain /= weight; @@ -2276,7 +2274,7 @@ unsigned long scale_rt_power(int cpu) static void update_cpu_power(struct sched_domain *sd, int cpu) { - unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long weight = sd->span_weight; unsigned long power = SCHED_LOAD_SCALE; struct sched_group *sdg = sd->groups; -- cgit v1.2.3-70-g09d2 From 969c79215a35b06e5e3efe69b9412f858df7856c Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 6 May 2010 18:49:21 +0200 Subject: sched: replace migration_thread with cpu_stop Currently migration_thread is serving three purposes - migration pusher, context to execute active_load_balance() and forced context switcher for expedited RCU synchronize_sched. All three roles are hardcoded into migration_thread() and determining which job is scheduled is slightly messy. This patch kills migration_thread and replaces all three uses with cpu_stop. The three different roles of migration_thread() are splitted into three separate cpu_stop callbacks - migration_cpu_stop(), active_load_balance_cpu_stop() and synchronize_sched_expedited_cpu_stop() - and each use case now simply asks cpu_stop to execute the callback as necessary. synchronize_sched_expedited() was implemented with private preallocated resources and custom multi-cpu queueing and waiting logic, both of which are provided by cpu_stop. synchronize_sched_expedited_count is made atomic and all other shared resources along with the mutex are dropped. synchronize_sched_expedited() also implemented a check to detect cases where not all the callback got executed on their assigned cpus and fall back to synchronize_sched(). If called with cpu hotplug blocked, cpu_stop already guarantees that and the condition cannot happen; otherwise, stop_machine() would break. However, this patch preserves the paranoid check using a cpumask to record on which cpus the stopper ran so that it can serve as a bisection point if something actually goes wrong theree. Because the internal execution state is no longer visible, rcu_expedited_torture_stats() is removed. This patch also renames cpu_stop threads to from "stopper/%d" to "migration/%d". The names of these threads ultimately don't matter and there's no reason to make unnecessary userland visible changes. With this patch applied, stop_machine() and sched now share the same resources. stop_machine() is faster without wasting any resources and sched migration users are much cleaner. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Ingo Molnar Cc: Dipankar Sarma Cc: Josh Triplett Cc: Paul E. McKenney Cc: Oleg Nesterov Cc: Dimitri Sivanich --- Documentation/RCU/torture.txt | 10 -- include/linux/rcutiny.h | 2 - include/linux/rcutree.h | 1 - kernel/rcutorture.c | 2 +- kernel/sched.c | 315 ++++++++++++------------------------------ kernel/sched_fair.c | 48 +++++-- kernel/stop_machine.c | 2 +- 7 files changed, 127 insertions(+), 253 deletions(-) (limited to 'kernel/sched.c') diff --git a/Documentation/RCU/torture.txt b/Documentation/RCU/torture.txt index 0e50bc2aa1e2..5d9016795fd8 100644 --- a/Documentation/RCU/torture.txt +++ b/Documentation/RCU/torture.txt @@ -182,16 +182,6 @@ Similarly, sched_expedited RCU provides the following: sched_expedited-torture: Reader Pipe: 12660320201 95875 0 0 0 0 0 0 0 0 0 sched_expedited-torture: Reader Batch: 12660424885 0 0 0 0 0 0 0 0 0 0 sched_expedited-torture: Free-Block Circulation: 1090795 1090795 1090794 1090793 1090792 1090791 1090790 1090789 1090788 1090787 0 - state: -1 / 0:0 3:0 4:0 - -As before, the first four lines are similar to those for RCU. -The last line shows the task-migration state. The first number is --1 if synchronize_sched_expedited() is idle, -2 if in the process of -posting wakeups to the migration kthreads, and N when waiting on CPU N. -Each of the colon-separated fields following the "/" is a CPU:state pair. -Valid states are "0" for idle, "1" for waiting for quiescent state, -"2" for passed through quiescent state, and "3" when a race with a -CPU-hotplug event forces use of the synchronize_sched() primitive. USAGE diff --git a/include/linux/rcutiny.h b/include/linux/rcutiny.h index a5195875480a..0006b2df00e1 100644 --- a/include/linux/rcutiny.h +++ b/include/linux/rcutiny.h @@ -60,8 +60,6 @@ static inline long rcu_batches_completed_bh(void) return 0; } -extern int rcu_expedited_torture_stats(char *page); - static inline void rcu_force_quiescent_state(void) { } diff --git a/include/linux/rcutree.h b/include/linux/rcutree.h index 42cc3a04779e..24e467e526b8 100644 --- a/include/linux/rcutree.h +++ b/include/linux/rcutree.h @@ -35,7 +35,6 @@ struct notifier_block; extern void rcu_sched_qs(int cpu); extern void rcu_bh_qs(int cpu); extern int rcu_needs_cpu(int cpu); -extern int rcu_expedited_torture_stats(char *page); #ifdef CONFIG_TREE_PREEMPT_RCU diff --git a/kernel/rcutorture.c b/kernel/rcutorture.c index 58df55bf83ed..2b676f3a0f26 100644 --- a/kernel/rcutorture.c +++ b/kernel/rcutorture.c @@ -669,7 +669,7 @@ static struct rcu_torture_ops sched_expedited_ops = { .sync = synchronize_sched_expedited, .cb_barrier = NULL, .fqs = rcu_sched_force_quiescent_state, - .stats = rcu_expedited_torture_stats, + .stats = NULL, .irq_capable = 1, .name = "sched_expedited" }; diff --git a/kernel/sched.c b/kernel/sched.c index 4956ed092838..f1d577a0a8ab 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -55,9 +55,9 @@ #include #include #include -#include #include #include +#include #include #include #include @@ -539,15 +539,13 @@ struct rq { int post_schedule; int active_balance; int push_cpu; + struct cpu_stop_work active_balance_work; /* cpu of this runqueue: */ int cpu; int online; unsigned long avg_load_per_task; - struct task_struct *migration_thread; - struct list_head migration_queue; - u64 rt_avg; u64 age_stamp; u64 idle_stamp; @@ -2037,21 +2035,18 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) __set_task_cpu(p, new_cpu); } -struct migration_req { - struct list_head list; - +struct migration_arg { struct task_struct *task; int dest_cpu; - - struct completion done; }; +static int migration_cpu_stop(void *data); + /* * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ -static int -migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) +static bool migrate_task(struct task_struct *p, int dest_cpu) { struct rq *rq = task_rq(p); @@ -2059,15 +2054,7 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) * If the task is not on a runqueue (and not running), then * the next wake-up will properly place the task. */ - if (!p->se.on_rq && !task_running(rq, p)) - return 0; - - init_completion(&req->done); - req->task = p; - req->dest_cpu = dest_cpu; - list_add(&req->list, &rq->migration_queue); - - return 1; + return p->se.on_rq || task_running(rq, p); } /* @@ -3110,7 +3097,6 @@ static void update_cpu_load(struct rq *this_rq) void sched_exec(void) { struct task_struct *p = current; - struct migration_req req; unsigned long flags; struct rq *rq; int dest_cpu; @@ -3124,17 +3110,11 @@ void sched_exec(void) * select_task_rq() can race against ->cpus_allowed */ if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && - likely(cpu_active(dest_cpu)) && - migrate_task(p, dest_cpu, &req)) { - /* Need to wait for migration thread (might exit: take ref). */ - struct task_struct *mt = rq->migration_thread; + likely(cpu_active(dest_cpu)) && migrate_task(p, dest_cpu)) { + struct migration_arg arg = { p, dest_cpu }; - get_task_struct(mt); task_rq_unlock(rq, &flags); - wake_up_process(mt); - put_task_struct(mt); - wait_for_completion(&req.done); - + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); return; } unlock: @@ -5290,17 +5270,15 @@ static inline void sched_init_granularity(void) /* * This is how migration works: * - * 1) we queue a struct migration_req structure in the source CPU's - * runqueue and wake up that CPU's migration thread. - * 2) we down() the locked semaphore => thread blocks. - * 3) migration thread wakes up (implicitly it forces the migrated - * thread off the CPU) - * 4) it gets the migration request and checks whether the migrated - * task is still in the wrong runqueue. - * 5) if it's in the wrong runqueue then the migration thread removes + * 1) we invoke migration_cpu_stop() on the target CPU using + * stop_one_cpu(). + * 2) stopper starts to run (implicitly forcing the migrated thread + * off the CPU) + * 3) it checks whether the migrated task is still in the wrong runqueue. + * 4) if it's in the wrong runqueue then the migration thread removes * it and puts it into the right queue. - * 6) migration thread up()s the semaphore. - * 7) we wake up and the migration is done. + * 5) stopper completes and stop_one_cpu() returns and the migration + * is done. */ /* @@ -5314,9 +5292,9 @@ static inline void sched_init_granularity(void) */ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { - struct migration_req req; unsigned long flags; struct rq *rq; + unsigned int dest_cpu; int ret = 0; /* @@ -5354,15 +5332,12 @@ again: if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out; - if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) { + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); + if (migrate_task(p, dest_cpu)) { + struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ - struct task_struct *mt = rq->migration_thread; - - get_task_struct(mt); task_rq_unlock(rq, &flags); - wake_up_process(mt); - put_task_struct(mt); - wait_for_completion(&req.done); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; } @@ -5420,70 +5395,22 @@ fail: return ret; } -#define RCU_MIGRATION_IDLE 0 -#define RCU_MIGRATION_NEED_QS 1 -#define RCU_MIGRATION_GOT_QS 2 -#define RCU_MIGRATION_MUST_SYNC 3 - /* - * migration_thread - this is a highprio system thread that performs - * thread migration by bumping thread off CPU then 'pushing' onto - * another runqueue. + * migration_cpu_stop - this will be executed by a highprio stopper thread + * and performs thread migration by bumping thread off CPU then + * 'pushing' onto another runqueue. */ -static int migration_thread(void *data) +static int migration_cpu_stop(void *data) { - int badcpu; - int cpu = (long)data; - struct rq *rq; - - rq = cpu_rq(cpu); - BUG_ON(rq->migration_thread != current); - - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - struct migration_req *req; - struct list_head *head; - - raw_spin_lock_irq(&rq->lock); - - if (cpu_is_offline(cpu)) { - raw_spin_unlock_irq(&rq->lock); - break; - } - - if (rq->active_balance) { - active_load_balance(rq, cpu); - rq->active_balance = 0; - } - - head = &rq->migration_queue; - - if (list_empty(head)) { - raw_spin_unlock_irq(&rq->lock); - schedule(); - set_current_state(TASK_INTERRUPTIBLE); - continue; - } - req = list_entry(head->next, struct migration_req, list); - list_del_init(head->next); - - if (req->task != NULL) { - raw_spin_unlock(&rq->lock); - __migrate_task(req->task, cpu, req->dest_cpu); - } else if (likely(cpu == (badcpu = smp_processor_id()))) { - req->dest_cpu = RCU_MIGRATION_GOT_QS; - raw_spin_unlock(&rq->lock); - } else { - req->dest_cpu = RCU_MIGRATION_MUST_SYNC; - raw_spin_unlock(&rq->lock); - WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu); - } - local_irq_enable(); - - complete(&req->done); - } - __set_current_state(TASK_RUNNING); + struct migration_arg *arg = data; + /* + * The original target cpu might have gone down and we might + * be on another cpu but it doesn't matter. + */ + local_irq_disable(); + __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); + local_irq_enable(); return 0; } @@ -5850,35 +5777,20 @@ static void set_rq_offline(struct rq *rq) static int __cpuinit migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { - struct task_struct *p; int cpu = (long)hcpu; unsigned long flags; - struct rq *rq; + struct rq *rq = cpu_rq(cpu); switch (action) { case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: - p = kthread_create(migration_thread, hcpu, "migration/%d", cpu); - if (IS_ERR(p)) - return NOTIFY_BAD; - kthread_bind(p, cpu); - /* Must be high prio: stop_machine expects to yield to it. */ - rq = task_rq_lock(p, &flags); - __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - task_rq_unlock(rq, &flags); - get_task_struct(p); - cpu_rq(cpu)->migration_thread = p; rq->calc_load_update = calc_load_update; break; case CPU_ONLINE: case CPU_ONLINE_FROZEN: - /* Strictly unnecessary, as first user will wake it. */ - wake_up_process(cpu_rq(cpu)->migration_thread); - /* Update our root-domain */ - rq = cpu_rq(cpu); raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); @@ -5889,25 +5801,9 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - if (!cpu_rq(cpu)->migration_thread) - break; - /* Unbind it from offline cpu so it can run. Fall thru. */ - kthread_bind(cpu_rq(cpu)->migration_thread, - cpumask_any(cpu_online_mask)); - kthread_stop(cpu_rq(cpu)->migration_thread); - put_task_struct(cpu_rq(cpu)->migration_thread); - cpu_rq(cpu)->migration_thread = NULL; - break; - case CPU_DEAD: case CPU_DEAD_FROZEN: migrate_live_tasks(cpu); - rq = cpu_rq(cpu); - kthread_stop(rq->migration_thread); - put_task_struct(rq->migration_thread); - rq->migration_thread = NULL; /* Idle task back to normal (off runqueue, low prio) */ raw_spin_lock_irq(&rq->lock); deactivate_task(rq, rq->idle, 0); @@ -5918,29 +5814,11 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) migrate_nr_uninterruptible(rq); BUG_ON(rq->nr_running != 0); calc_global_load_remove(rq); - /* - * No need to migrate the tasks: it was best-effort if - * they didn't take sched_hotcpu_mutex. Just wake up - * the requestors. - */ - raw_spin_lock_irq(&rq->lock); - while (!list_empty(&rq->migration_queue)) { - struct migration_req *req; - - req = list_entry(rq->migration_queue.next, - struct migration_req, list); - list_del_init(&req->list); - raw_spin_unlock_irq(&rq->lock); - complete(&req->done); - raw_spin_lock_irq(&rq->lock); - } - raw_spin_unlock_irq(&rq->lock); break; case CPU_DYING: case CPU_DYING_FROZEN: /* Update our root-domain */ - rq = cpu_rq(cpu); raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); @@ -7757,10 +7635,8 @@ void __init sched_init(void) rq->push_cpu = 0; rq->cpu = i; rq->online = 0; - rq->migration_thread = NULL; rq->idle_stamp = 0; rq->avg_idle = 2*sysctl_sched_migration_cost; - INIT_LIST_HEAD(&rq->migration_queue); rq_attach_root(rq, &def_root_domain); #endif init_rq_hrtick(rq); @@ -9054,43 +8930,39 @@ struct cgroup_subsys cpuacct_subsys = { #ifndef CONFIG_SMP -int rcu_expedited_torture_stats(char *page) -{ - return 0; -} -EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats); - void synchronize_sched_expedited(void) { + /* + * There must be a full memory barrier on each affected CPU + * between the time that try_stop_cpus() is called and the + * time that it returns. + * + * In the current initial implementation of cpu_stop, the + * above condition is already met when the control reaches + * this point and the following smp_mb() is not strictly + * necessary. Do smp_mb() anyway for documentation and + * robustness against future implementation changes. + */ + smp_mb(); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); #else /* #ifndef CONFIG_SMP */ -static DEFINE_PER_CPU(struct migration_req, rcu_migration_req); -static DEFINE_MUTEX(rcu_sched_expedited_mutex); - -#define RCU_EXPEDITED_STATE_POST -2 -#define RCU_EXPEDITED_STATE_IDLE -1 +static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); -static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE; - -int rcu_expedited_torture_stats(char *page) +static int synchronize_sched_expedited_cpu_stop(void *data) { - int cnt = 0; - int cpu; + static DEFINE_SPINLOCK(done_mask_lock); + struct cpumask *done_mask = data; - cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state); - for_each_online_cpu(cpu) { - cnt += sprintf(&page[cnt], " %d:%d", - cpu, per_cpu(rcu_migration_req, cpu).dest_cpu); + if (done_mask) { + spin_lock(&done_mask_lock); + cpumask_set_cpu(smp_processor_id(), done_mask); + spin_unlock(&done_mask_lock); } - cnt += sprintf(&page[cnt], "\n"); - return cnt; + return 0; } -EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats); - -static long synchronize_sched_expedited_count; /* * Wait for an rcu-sched grace period to elapse, but use "big hammer" @@ -9104,60 +8976,55 @@ static long synchronize_sched_expedited_count; */ void synchronize_sched_expedited(void) { - int cpu; - unsigned long flags; - bool need_full_sync = 0; - struct rq *rq; - struct migration_req *req; - long snap; - int trycount = 0; + cpumask_var_t done_mask_var; + struct cpumask *done_mask = NULL; + int snap, trycount = 0; + + /* + * done_mask is used to check that all cpus actually have + * finished running the stopper, which is guaranteed by + * stop_cpus() if it's called with cpu hotplug blocked. Keep + * the paranoia for now but it's best effort if cpumask is off + * stack. + */ + if (zalloc_cpumask_var(&done_mask_var, GFP_ATOMIC)) + done_mask = done_mask_var; smp_mb(); /* ensure prior mod happens before capturing snap. */ - snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1; + snap = atomic_read(&synchronize_sched_expedited_count) + 1; get_online_cpus(); - while (!mutex_trylock(&rcu_sched_expedited_mutex)) { + while (try_stop_cpus(cpu_online_mask, + synchronize_sched_expedited_cpu_stop, + done_mask) == -EAGAIN) { put_online_cpus(); if (trycount++ < 10) udelay(trycount * num_online_cpus()); else { synchronize_sched(); - return; + goto free_out; } - if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) { + if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) { smp_mb(); /* ensure test happens before caller kfree */ - return; + goto free_out; } get_online_cpus(); } - rcu_expedited_state = RCU_EXPEDITED_STATE_POST; - for_each_online_cpu(cpu) { - rq = cpu_rq(cpu); - req = &per_cpu(rcu_migration_req, cpu); - init_completion(&req->done); - req->task = NULL; - req->dest_cpu = RCU_MIGRATION_NEED_QS; - raw_spin_lock_irqsave(&rq->lock, flags); - list_add(&req->list, &rq->migration_queue); - raw_spin_unlock_irqrestore(&rq->lock, flags); - wake_up_process(rq->migration_thread); - } - for_each_online_cpu(cpu) { - rcu_expedited_state = cpu; - req = &per_cpu(rcu_migration_req, cpu); - rq = cpu_rq(cpu); - wait_for_completion(&req->done); - raw_spin_lock_irqsave(&rq->lock, flags); - if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC)) - need_full_sync = 1; - req->dest_cpu = RCU_MIGRATION_IDLE; - raw_spin_unlock_irqrestore(&rq->lock, flags); - } - rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE; - synchronize_sched_expedited_count++; - mutex_unlock(&rcu_sched_expedited_mutex); + atomic_inc(&synchronize_sched_expedited_count); + if (done_mask) + cpumask_xor(done_mask, done_mask, cpu_online_mask); put_online_cpus(); - if (need_full_sync) + + /* paranoia - this can't happen */ + if (done_mask && cpumask_weight(done_mask)) { + char buf[80]; + + cpulist_scnprintf(buf, sizeof(buf), done_mask); + WARN_ONCE(1, "synchronize_sched_expedited: cpu online and done masks disagree on %d cpus: %s\n", + cpumask_weight(done_mask), buf); synchronize_sched(); + } +free_out: + free_cpumask_var(done_mask_var); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c index cbd8b8a296d1..217e4a9393e4 100644 --- a/kernel/sched_fair.c +++ b/kernel/sched_fair.c @@ -2798,6 +2798,8 @@ static int need_active_balance(struct sched_domain *sd, int sd_idle, int idle) return unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2); } +static int active_load_balance_cpu_stop(void *data); + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. @@ -2887,8 +2889,9 @@ redo: if (need_active_balance(sd, sd_idle, idle)) { raw_spin_lock_irqsave(&busiest->lock, flags); - /* don't kick the migration_thread, if the curr - * task on busiest cpu can't be moved to this_cpu + /* don't kick the active_load_balance_cpu_stop, + * if the curr task on busiest cpu can't be + * moved to this_cpu */ if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { @@ -2898,14 +2901,22 @@ redo: goto out_one_pinned; } + /* + * ->active_balance synchronizes accesses to + * ->active_balance_work. Once set, it's cleared + * only after active load balance is finished. + */ if (!busiest->active_balance) { busiest->active_balance = 1; busiest->push_cpu = this_cpu; active_balance = 1; } raw_spin_unlock_irqrestore(&busiest->lock, flags); + if (active_balance) - wake_up_process(busiest->migration_thread); + stop_one_cpu_nowait(cpu_of(busiest), + active_load_balance_cpu_stop, busiest, + &busiest->active_balance_work); /* * We've kicked active balancing, reset the failure @@ -3012,24 +3023,29 @@ static void idle_balance(int this_cpu, struct rq *this_rq) } /* - * active_load_balance is run by migration threads. It pushes running tasks - * off the busiest CPU onto idle CPUs. It requires at least 1 task to be - * running on each physical CPU where possible, and avoids physical / - * logical imbalances. - * - * Called with busiest_rq locked. + * active_load_balance_cpu_stop is run by cpu stopper. It pushes + * running tasks off the busiest CPU onto idle CPUs. It requires at + * least 1 task to be running on each physical CPU where possible, and + * avoids physical / logical imbalances. */ -static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) +static int active_load_balance_cpu_stop(void *data) { + struct rq *busiest_rq = data; + int busiest_cpu = cpu_of(busiest_rq); int target_cpu = busiest_rq->push_cpu; + struct rq *target_rq = cpu_rq(target_cpu); struct sched_domain *sd; - struct rq *target_rq; + + raw_spin_lock_irq(&busiest_rq->lock); + + /* make sure the requested cpu hasn't gone down in the meantime */ + if (unlikely(busiest_cpu != smp_processor_id() || + !busiest_rq->active_balance)) + goto out_unlock; /* Is there any task to move? */ if (busiest_rq->nr_running <= 1) - return; - - target_rq = cpu_rq(target_cpu); + goto out_unlock; /* * This condition is "impossible", if it occurs @@ -3058,6 +3074,10 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) schedstat_inc(sd, alb_failed); } double_unlock_balance(busiest_rq, target_rq); +out_unlock: + busiest_rq->active_balance = 0; + raw_spin_unlock_irq(&busiest_rq->lock); + return 0; } #ifdef CONFIG_NO_HZ diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c index 884c7a1afeed..5b20141a5ec1 100644 --- a/kernel/stop_machine.c +++ b/kernel/stop_machine.c @@ -301,7 +301,7 @@ static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb, case CPU_UP_PREPARE: BUG_ON(stopper->thread || stopper->enabled || !list_empty(&stopper->works)); - p = kthread_create(cpu_stopper_thread, stopper, "stopper/%d", + p = kthread_create(cpu_stopper_thread, stopper, "migration/%d", cpu); if (IS_ERR(p)) return NOTIFY_BAD; -- cgit v1.2.3-70-g09d2 From 94458d5ecb3da844823cc191e73e5c5ead98a464 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 6 May 2010 18:49:21 +0200 Subject: sched: kill paranoia check in synchronize_sched_expedited() The paranoid check which verifies that the cpu_stop callback is actually called on all online cpus is completely superflous. It's guaranteed by cpu_stop facility and if it didn't work as advertised other things would go horribly wrong and trying to recover using synchronize_sched() wouldn't be very meaningful. Kill the paranoid check. Removal of this feature is done as a separate step so that it can serve as a bisection point if something actually goes wrong. Signed-off-by: Tejun Heo Acked-by: Peter Zijlstra Cc: Ingo Molnar Cc: Dipankar Sarma Cc: Josh Triplett Cc: Paul E. McKenney Cc: Oleg Nesterov Cc: Dimitri Sivanich --- kernel/sched.c | 40 +++------------------------------------- 1 file changed, 3 insertions(+), 37 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index f1d577a0a8ab..e9c6d798831a 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8953,14 +8953,6 @@ static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); static int synchronize_sched_expedited_cpu_stop(void *data) { - static DEFINE_SPINLOCK(done_mask_lock); - struct cpumask *done_mask = data; - - if (done_mask) { - spin_lock(&done_mask_lock); - cpumask_set_cpu(smp_processor_id(), done_mask); - spin_unlock(&done_mask_lock); - } return 0; } @@ -8976,55 +8968,29 @@ static int synchronize_sched_expedited_cpu_stop(void *data) */ void synchronize_sched_expedited(void) { - cpumask_var_t done_mask_var; - struct cpumask *done_mask = NULL; int snap, trycount = 0; - /* - * done_mask is used to check that all cpus actually have - * finished running the stopper, which is guaranteed by - * stop_cpus() if it's called with cpu hotplug blocked. Keep - * the paranoia for now but it's best effort if cpumask is off - * stack. - */ - if (zalloc_cpumask_var(&done_mask_var, GFP_ATOMIC)) - done_mask = done_mask_var; - smp_mb(); /* ensure prior mod happens before capturing snap. */ snap = atomic_read(&synchronize_sched_expedited_count) + 1; get_online_cpus(); while (try_stop_cpus(cpu_online_mask, synchronize_sched_expedited_cpu_stop, - done_mask) == -EAGAIN) { + NULL) == -EAGAIN) { put_online_cpus(); if (trycount++ < 10) udelay(trycount * num_online_cpus()); else { synchronize_sched(); - goto free_out; + return; } if (atomic_read(&synchronize_sched_expedited_count) - snap > 0) { smp_mb(); /* ensure test happens before caller kfree */ - goto free_out; + return; } get_online_cpus(); } atomic_inc(&synchronize_sched_expedited_count); - if (done_mask) - cpumask_xor(done_mask, done_mask, cpu_online_mask); put_online_cpus(); - - /* paranoia - this can't happen */ - if (done_mask && cpumask_weight(done_mask)) { - char buf[80]; - - cpulist_scnprintf(buf, sizeof(buf), done_mask); - WARN_ONCE(1, "synchronize_sched_expedited: cpu online and done masks disagree on %d cpus: %s\n", - cpumask_weight(done_mask), buf); - synchronize_sched(); - } -free_out: - free_cpumask_var(done_mask_var); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); -- cgit v1.2.3-70-g09d2 From cc631fb732b8ccd6a0cc45557475ea09b0c21a68 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 6 May 2010 18:49:21 +0200 Subject: sched: correctly place paranioa memory barriers in synchronize_sched_expedited() The memory barriers must be in the SMP case, not in the !SMP case. Also add a barrier after the atomic_inc() in order to ensure that other CPUs see post-synchronize_sched_expedited() actions as following the expedited grace period. Signed-off-by: Paul E. McKenney Signed-off-by: Tejun Heo --- kernel/sched.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index e9c6d798831a..155a16d52146 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8931,6 +8931,15 @@ struct cgroup_subsys cpuacct_subsys = { #ifndef CONFIG_SMP void synchronize_sched_expedited(void) +{ +} +EXPORT_SYMBOL_GPL(synchronize_sched_expedited); + +#else /* #ifndef CONFIG_SMP */ + +static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); + +static int synchronize_sched_expedited_cpu_stop(void *data) { /* * There must be a full memory barrier on each affected CPU @@ -8943,16 +8952,7 @@ void synchronize_sched_expedited(void) * necessary. Do smp_mb() anyway for documentation and * robustness against future implementation changes. */ - smp_mb(); -} -EXPORT_SYMBOL_GPL(synchronize_sched_expedited); - -#else /* #ifndef CONFIG_SMP */ - -static atomic_t synchronize_sched_expedited_count = ATOMIC_INIT(0); - -static int synchronize_sched_expedited_cpu_stop(void *data) -{ + smp_mb(); /* See above comment block. */ return 0; } @@ -8990,6 +8990,7 @@ void synchronize_sched_expedited(void) get_online_cpus(); } atomic_inc(&synchronize_sched_expedited_count); + smp_mb__after_atomic_inc(); /* ensure post-GP actions seen after GP. */ put_online_cpus(); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); -- cgit v1.2.3-70-g09d2 From fc390cde362309f6892bb719194f242c466a978b Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Thu, 6 May 2010 11:42:52 -0700 Subject: rcu: need barrier() in UP synchronize_sched_expedited() If synchronize_sched_expedited() is ever to be called from within kernel/sched.c in a !SMP PREEMPT kernel, the !SMP implementation needs a barrier(). Signed-off-by: Paul E. McKenney Signed-off-by: Tejun Heo --- kernel/sched.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel/sched.c') diff --git a/kernel/sched.c b/kernel/sched.c index 155a16d52146..fbaf3128d010 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -8932,6 +8932,7 @@ struct cgroup_subsys cpuacct_subsys = { void synchronize_sched_expedited(void) { + barrier(); } EXPORT_SYMBOL_GPL(synchronize_sched_expedited); -- cgit v1.2.3-70-g09d2 From 27a9da6538ee18046d7bff8e36a9f783542c54c3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Tue, 4 May 2010 20:36:56 +0200 Subject: sched: Remove rq argument to the tracepoints struct rq isn't visible outside of sched.o so its near useless to expose the pointer, also there are no users of it, so remove it. Acked-by: Steven Rostedt Signed-off-by: Peter Zijlstra LKML-Reference: <1272997616.1642.207.camel@laptop> Signed-off-by: Ingo Molnar --- include/trace/events/sched.h | 32 ++++++++++---------------------- kernel/sched.c | 8 ++++---- kernel/trace/ftrace.c | 3 +-- kernel/trace/trace_sched_switch.c | 5 ++--- kernel/trace/trace_sched_wakeup.c | 5 ++--- 5 files changed, 19 insertions(+), 34 deletions(-) (limited to 'kernel/sched.c') diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index cfceb0b73e20..4f733ecea46e 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -51,15 +51,12 @@ TRACE_EVENT(sched_kthread_stop_ret, /* * Tracepoint for waiting on task to unschedule: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) */ TRACE_EVENT(sched_wait_task, - TP_PROTO(struct rq *rq, struct task_struct *p), + TP_PROTO(struct task_struct *p), - TP_ARGS(rq, p), + TP_ARGS(p), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) @@ -79,15 +76,12 @@ TRACE_EVENT(sched_wait_task, /* * Tracepoint for waking up a task: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) */ DECLARE_EVENT_CLASS(sched_wakeup_template, - TP_PROTO(struct rq *rq, struct task_struct *p, int success), + TP_PROTO(struct task_struct *p, int success), - TP_ARGS(rq, p, success), + TP_ARGS(p, success), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) @@ -111,31 +105,25 @@ DECLARE_EVENT_CLASS(sched_wakeup_template, ); DEFINE_EVENT(sched_wakeup_template, sched_wakeup, - TP_PROTO(struct rq *rq, struct task_struct *p, int success), - TP_ARGS(rq, p, success)); + TP_PROTO(struct task_struct *p, int success), + TP_ARGS(p, success)); /* * Tracepoint for waking up a new task: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) */ DEFINE_EVENT(sched_wakeup_template, sched_wakeup_new, - TP_PROTO(struct rq *rq, struct task_struct *p, int success), - TP_ARGS(rq, p, success)); + TP_PROTO(struct task_struct *p, int success), + TP_ARGS(p, success)); /* * Tracepoint for task switches, performed by the scheduler: - * - * (NOTE: the 'rq' argument is not used by generic trace events, - * but used by the latency tracer plugin. ) */ TRACE_EVENT(sched_switch, - TP_PROTO(struct rq *rq, struct task_struct *prev, + TP_PROTO(struct task_struct *prev, struct task_struct *next), - TP_ARGS(rq, prev, next), + TP_ARGS(prev, next), TP_STRUCT__entry( __array( char, prev_comm, TASK_COMM_LEN ) diff --git a/kernel/sched.c b/kernel/sched.c index 4956ed092838..11ac0eb0bce7 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -2168,7 +2168,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * just go back and repeat. */ rq = task_rq_lock(p, &flags); - trace_sched_wait_task(rq, p); + trace_sched_wait_task(p); running = task_running(rq, p); on_rq = p->se.on_rq; ncsw = 0; @@ -2439,7 +2439,7 @@ out_activate: success = 1; out_running: - trace_sched_wakeup(rq, p, success); + trace_sched_wakeup(p, success); check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -2613,7 +2613,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) rq = task_rq_lock(p, &flags); activate_task(rq, p, 0); - trace_sched_wakeup_new(rq, p, 1); + trace_sched_wakeup_new(p, 1); check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP if (p->sched_class->task_woken) @@ -2833,7 +2833,7 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm, *oldmm; prepare_task_switch(rq, prev, next); - trace_sched_switch(rq, prev, next); + trace_sched_switch(prev, next); mm = next->mm; oldmm = prev->active_mm; /* diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2404b59b3097..aa3a92b511e2 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -3212,8 +3212,7 @@ free: } static void -ftrace_graph_probe_sched_switch(struct rq *__rq, struct task_struct *prev, - struct task_struct *next) +ftrace_graph_probe_sched_switch(struct task_struct *prev, struct task_struct *next) { unsigned long long timestamp; int index; diff --git a/kernel/trace/trace_sched_switch.c b/kernel/trace/trace_sched_switch.c index 5fca0f51fde4..a55fccfede5d 100644 --- a/kernel/trace/trace_sched_switch.c +++ b/kernel/trace/trace_sched_switch.c @@ -50,8 +50,7 @@ tracing_sched_switch_trace(struct trace_array *tr, } static void -probe_sched_switch(struct rq *__rq, struct task_struct *prev, - struct task_struct *next) +probe_sched_switch(struct task_struct *prev, struct task_struct *next) { struct trace_array_cpu *data; unsigned long flags; @@ -109,7 +108,7 @@ tracing_sched_wakeup_trace(struct trace_array *tr, } static void -probe_sched_wakeup(struct rq *__rq, struct task_struct *wakee, int success) +probe_sched_wakeup(struct task_struct *wakee, int success) { struct trace_array_cpu *data; unsigned long flags; diff --git a/kernel/trace/trace_sched_wakeup.c b/kernel/trace/trace_sched_wakeup.c index 0271742abb8d..8052446ceeaa 100644 --- a/kernel/trace/trace_sched_wakeup.c +++ b/kernel/trace/trace_sched_wakeup.c @@ -107,8 +107,7 @@ static void probe_wakeup_migrate_task(struct task_struct *task, int cpu) } static void notrace -probe_wakeup_sched_switch(struct rq *rq, struct task_struct *prev, - struct task_struct *next) +probe_wakeup_sched_switch(struct task_struct *prev, struct task_struct *next) { struct trace_array_cpu *data; cycle_t T0, T1, delta; @@ -200,7 +199,7 @@ static void wakeup_reset(struct trace_array *tr) } static void -probe_wakeup(struct rq *rq, struct task_struct *p, int success) +probe_wakeup(struct task_struct *p, int success) { struct trace_array_cpu *data; int cpu = smp_processor_id(); -- cgit v1.2.3-70-g09d2 From a93d2f1744206827ccf416e2cdc5018aa503314e Mon Sep 17 00:00:00 2001 From: Changli Gao Date: Fri, 7 May 2010 14:33:26 +0800 Subject: sched, wait: Use wrapper functions epoll should not touch flags in wait_queue_t. This patch introduces a new function __add_wait_queue_exclusive(), for the users, who use wait queue as a LIFO queue. __add_wait_queue_tail_exclusive() is introduced too instead of add_wait_queue_exclusive_locked(). remove_wait_queue_locked() is removed, as it is a duplicate of __remove_wait_queue(), disliked by users, and with less users. Signed-off-by: Changli Gao Signed-off-by: Peter Zijlstra Cc: Alexander Viro Cc: Paul Menage Cc: Li Zefan Cc: Davide Libenzi Cc: LKML-Reference: <1273214006-2979-1-git-send-email-xiaosuo@gmail.com> Signed-off-by: Ingo Molnar --- fs/eventpoll.c | 3 +-- include/linux/wait.h | 35 +++++++++++++++-------------------- kernel/cgroup.c | 2 +- kernel/sched.c | 3 +-- 4 files changed, 18 insertions(+), 25 deletions(-) (limited to 'kernel/sched.c') diff --git a/fs/eventpoll.c b/fs/eventpoll.c index bd056a5b4efc..3817149919cb 100644 --- a/fs/eventpoll.c +++ b/fs/eventpoll.c @@ -1140,8 +1140,7 @@ retry: * ep_poll_callback() when events will become available. */ init_waitqueue_entry(&wait, current); - wait.flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue(&ep->wq, &wait); + __add_wait_queue_exclusive(&ep->wq, &wait); for (;;) { /* diff --git a/include/linux/wait.h b/include/linux/wait.h index a48e16b77d5e..76d96d035ea0 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -127,12 +127,26 @@ static inline void __add_wait_queue(wait_queue_head_t *head, wait_queue_t *new) /* * Used for wake-one threads: */ +static inline void __add_wait_queue_exclusive(wait_queue_head_t *q, + wait_queue_t *wait) +{ + wait->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue(q, wait); +} + static inline void __add_wait_queue_tail(wait_queue_head_t *head, - wait_queue_t *new) + wait_queue_t *new) { list_add_tail(&new->task_list, &head->task_list); } +static inline void __add_wait_queue_tail_exclusive(wait_queue_head_t *q, + wait_queue_t *wait) +{ + wait->flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue_tail(q, wait); +} + static inline void __remove_wait_queue(wait_queue_head_t *head, wait_queue_t *old) { @@ -403,25 +417,6 @@ do { \ __ret; \ }) -/* - * Must be called with the spinlock in the wait_queue_head_t held. - */ -static inline void add_wait_queue_exclusive_locked(wait_queue_head_t *q, - wait_queue_t * wait) -{ - wait->flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(q, wait); -} - -/* - * Must be called with the spinlock in the wait_queue_head_t held. - */ -static inline void remove_wait_queue_locked(wait_queue_head_t *q, - wait_queue_t * wait) -{ - __remove_wait_queue(q, wait); -} - /* * These are the old interfaces to sleep waiting for an event. * They are racy. DO NOT use them, use the wait_event* interfaces above. diff --git a/kernel/cgroup.c b/kernel/cgroup.c index e2769e13980c..4a07d057a265 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -3010,7 +3010,7 @@ static int cgroup_event_wake(wait_queue_t *wait, unsigned mode, unsigned long flags = (unsigned long)key; if (flags & POLLHUP) { - remove_wait_queue_locked(event->wqh, &event->wait); + __remove_wait_queue(event->wqh, &event->wait); spin_lock(&cgrp->event_list_lock); list_del(&event->list); spin_unlock(&cgrp->event_list_lock); diff --git a/kernel/sched.c b/kernel/sched.c index 39aa9c7e22c0..b531d7934083 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -3983,8 +3983,7 @@ do_wait_for_common(struct completion *x, long timeout, int state) if (!x->done) { DECLARE_WAITQUEUE(wait, current); - wait.flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(&x->wait, &wait); + __add_wait_queue_tail_exclusive(&x->wait, &wait); do { if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; -- cgit v1.2.3-70-g09d2