diff --git a/include/linux/cpu.h b/include/linux/cpu.h index e287863ac053..de6b1722cdca 100644 --- a/include/linux/cpu.h +++ b/include/linux/cpu.h @@ -48,6 +48,31 @@ extern ssize_t arch_cpu_release(const char *, size_t); #endif struct notifier_block; +/* + * CPU notifier priorities. + */ +enum { + /* + * SCHED_ACTIVE marks a cpu which is coming up active during + * CPU_ONLINE and CPU_DOWN_FAILED and must be the first + * notifier. CPUSET_ACTIVE adjusts cpuset according to + * cpu_active mask right after SCHED_ACTIVE. During + * CPU_DOWN_PREPARE, SCHED_INACTIVE and CPUSET_INACTIVE are + * ordered in the similar way. + * + * This ordering guarantees consistent cpu_active mask and + * migration behavior to all cpu notifiers. + */ + CPU_PRI_SCHED_ACTIVE = INT_MAX, + CPU_PRI_CPUSET_ACTIVE = INT_MAX - 1, + CPU_PRI_SCHED_INACTIVE = INT_MIN + 1, + CPU_PRI_CPUSET_INACTIVE = INT_MIN, + + /* migration should happen before other stuff but after perf */ + CPU_PRI_PERF = 20, + CPU_PRI_MIGRATION = 10, +}; + #ifdef CONFIG_SMP /* Need to know about CPUs going up/down? */ #if defined(CONFIG_HOTPLUG_CPU) || !defined(MODULE) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 457ed765a116..f20eb8f16025 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -20,6 +20,7 @@ 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_update_active_cpus(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); @@ -132,6 +133,11 @@ static inline void set_mems_allowed(nodemask_t nodemask) static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {} +static inline void cpuset_update_active_cpus(void) +{ + partition_sched_domains(1, NULL, NULL); +} + static inline void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask) { diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index 5d0266d94985..469e03e96fe7 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1068,7 +1068,7 @@ static inline void perf_event_disable(struct perf_event *event) { } #define perf_cpu_notifier(fn) \ do { \ static struct notifier_block fn##_nb __cpuinitdata = \ - { .notifier_call = fn, .priority = 20 }; \ + { .notifier_call = fn, .priority = CPU_PRI_PERF }; \ fn(&fn##_nb, (unsigned long)CPU_UP_PREPARE, \ (void *)(unsigned long)smp_processor_id()); \ fn(&fn##_nb, (unsigned long)CPU_STARTING, \ diff --git a/include/linux/sched.h b/include/linux/sched.h index f118809c953f..edc3dd168d87 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1696,6 +1696,7 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t * #define PF_EXITING 0x00000004 /* getting shut down */ #define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */ #define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +#define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */ #define PF_SUPERPRIV 0x00000100 /* used super-user privileges */ diff --git a/kernel/cpu.c b/kernel/cpu.c index 97d1b426a4ac..f6e726f18491 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -235,11 +235,8 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) return -EINVAL; cpu_hotplug_begin(); - set_cpu_active(cpu, false); err = __cpu_notify(CPU_DOWN_PREPARE | mod, hcpu, -1, &nr_calls); if (err) { - set_cpu_active(cpu, true); - nr_calls--; __cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL); printk("%s: attempt to take down CPU %u failed\n", @@ -249,7 +246,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen) err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu)); if (err) { - set_cpu_active(cpu, true); /* CPU didn't die: tell everyone. Can't complain. */ cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu); @@ -321,8 +317,6 @@ static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen) goto out_notify; BUG_ON(!cpu_online(cpu)); - set_cpu_active(cpu, true); - /* Now call notifier in preparation. */ cpu_notify(CPU_ONLINE | mod, hcpu); diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 02b9611eadde..05727dcaa80d 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -2113,31 +2113,17 @@ static void scan_for_empty_cpusets(struct cpuset *root) * but making no active use of cpusets. * * This routine ensures that top_cpuset.cpus_allowed tracks - * cpu_online_map on each CPU hotplug (cpuhp) event. + * cpu_active_mask on each CPU hotplug (cpuhp) event. * * Called within get_online_cpus(). Needs to call cgroup_lock() * before calling generate_sched_domains(). */ -static int cpuset_track_online_cpus(struct notifier_block *unused_nb, - unsigned long phase, void *unused_cpu) +void __cpuexit cpuset_update_active_cpus(void) { struct sched_domain_attr *attr; cpumask_var_t *doms; int ndoms; - switch (phase) { - case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: - case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - break; - - default: - return NOTIFY_DONE; - } - cgroup_lock(); mutex_lock(&callback_mutex); cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); @@ -2148,8 +2134,6 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb, /* Have scheduler rebuild the domains */ partition_sched_domains(ndoms, doms, attr); - - return NOTIFY_OK; } #ifdef CONFIG_MEMORY_HOTPLUG @@ -2203,7 +2187,6 @@ void __init cpuset_init_smp(void) cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask); top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY]; - hotcpu_notifier(cpuset_track_online_cpus, 0); hotplug_memory_notifier(cpuset_track_online_nodes, 10); cpuset_wq = create_singlethread_workqueue("cpuset"); diff --git a/kernel/fork.c b/kernel/fork.c index b6cce14ba047..a82a65cef741 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -907,7 +907,7 @@ static void copy_flags(unsigned long clone_flags, struct task_struct *p) { unsigned long new_flags = p->flags; - new_flags &= ~PF_SUPERPRIV; + new_flags &= ~(PF_SUPERPRIV | PF_WQ_WORKER); new_flags |= PF_FORKNOEXEC; new_flags |= PF_STARTING; p->flags = new_flags; diff --git a/kernel/sched.c b/kernel/sched.c index f8b8996228dd..edd5a54b95da 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -77,6 +77,7 @@ #include #include "sched_cpupri.h" +#include "workqueue_sched.h" #define CREATE_TRACE_POINTS #include @@ -2267,11 +2268,55 @@ static void update_avg(u64 *avg, u64 sample) } #endif -/*** +static inline void ttwu_activate(struct task_struct *p, struct rq *rq, + bool is_sync, bool is_migrate, bool is_local, + unsigned long en_flags) +{ + schedstat_inc(p, se.statistics.nr_wakeups); + if (is_sync) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + if (is_migrate) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + if (is_local) + schedstat_inc(p, se.statistics.nr_wakeups_local); + else + schedstat_inc(p, se.statistics.nr_wakeups_remote); + + activate_task(rq, p, en_flags); +} + +static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, + int wake_flags, bool success) +{ + trace_sched_wakeup(p, success); + check_preempt_curr(rq, p, wake_flags); + + p->state = TASK_RUNNING; +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); + + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; + + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; + } +#endif + /* if a worker is waking up, notify workqueue */ + if ((p->flags & PF_WQ_WORKER) && success) + wq_worker_waking_up(p, cpu_of(rq)); +} + +/** * try_to_wake_up - wake up a thread - * @p: the to-be-woken-up thread + * @p: the thread to be awakened * @state: the mask of task states that can be woken - * @sync: do a synchronous wakeup? + * @wake_flags: wake modifier flags (WF_*) * * Put it on the run-queue if it's not already there. The "current" * thread is always on the run-queue (except when the actual @@ -2279,7 +2324,8 @@ static void update_avg(u64 *avg, u64 sample) * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * returns failure only if the task is already active. + * Returns %true if @p was woken up, %false if it was already running + * or @state didn't match @p's state. */ static int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) @@ -2359,38 +2405,11 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, out_activate: #endif /* CONFIG_SMP */ - schedstat_inc(p, se.statistics.nr_wakeups); - if (wake_flags & WF_SYNC) - schedstat_inc(p, se.statistics.nr_wakeups_sync); - if (orig_cpu != cpu) - schedstat_inc(p, se.statistics.nr_wakeups_migrate); - if (cpu == this_cpu) - schedstat_inc(p, se.statistics.nr_wakeups_local); - else - schedstat_inc(p, se.statistics.nr_wakeups_remote); - activate_task(rq, p, en_flags); + ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, + cpu == this_cpu, en_flags); success = 1; - out_running: - trace_sched_wakeup(p, success); - check_preempt_curr(rq, p, wake_flags); - - p->state = TASK_RUNNING; -#ifdef CONFIG_SMP - if (p->sched_class->task_woken) - p->sched_class->task_woken(rq, p); - - if (unlikely(rq->idle_stamp)) { - u64 delta = rq->clock - rq->idle_stamp; - u64 max = 2*sysctl_sched_migration_cost; - - if (delta > max) - rq->avg_idle = max; - else - update_avg(&rq->avg_idle, delta); - rq->idle_stamp = 0; - } -#endif + ttwu_post_activation(p, rq, wake_flags, success); out: task_rq_unlock(rq, &flags); put_cpu(); @@ -2398,6 +2417,37 @@ out: return success; } +/** + * try_to_wake_up_local - try to wake up a local task with rq lock held + * @p: the thread to be awakened + * + * Put @p on the run-queue if it's not alredy there. The caller must + * ensure that this_rq() is locked, @p is bound to this_rq() and not + * the current task. this_rq() stays locked over invocation. + */ +static void try_to_wake_up_local(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + bool success = false; + + BUG_ON(rq != this_rq()); + BUG_ON(p == current); + lockdep_assert_held(&rq->lock); + + if (!(p->state & TASK_NORMAL)) + return; + + if (!p->se.on_rq) { + if (likely(!task_running(rq, p))) { + schedstat_inc(rq, ttwu_count); + schedstat_inc(rq, ttwu_local); + } + ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); + success = true; + } + ttwu_post_activation(p, rq, 0, success); +} + /** * wake_up_process - Wake up a specific process * @p: The process to be woken up. @@ -3603,10 +3653,24 @@ need_resched_nonpreemptible: clear_tsk_need_resched(prev); if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { - if (unlikely(signal_pending_state(prev->state, prev))) + if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; - else + } else { + /* + * If a worker is going to sleep, notify and + * ask workqueue whether it wants to wake up a + * task to maintain concurrency. If so, wake + * up the task. + */ + if (prev->flags & PF_WQ_WORKER) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev, cpu); + if (to_wakeup) + try_to_wake_up_local(to_wakeup); + } deactivate_task(rq, prev, DEQUEUE_SLEEP); + } switch_count = &prev->nvcsw; } @@ -5801,20 +5865,49 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) */ static struct notifier_block __cpuinitdata migration_notifier = { .notifier_call = migration_call, - .priority = 10 + .priority = CPU_PRI_MIGRATION, }; +static int __cpuinit sched_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + set_cpu_active((long)hcpu, true); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active((long)hcpu, false); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + static int __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; - /* Start one for the boot CPU: */ + /* Initialize migration for the boot CPU */ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); BUG_ON(err == NOTIFY_BAD); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); + /* Register cpu active notifiers */ + cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); + cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); + return 0; } early_initcall(migration_init); @@ -7273,29 +7366,35 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) } #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -#ifndef CONFIG_CPUSETS /* - * Add online and remove offline CPUs from the scheduler domains. - * When cpusets are enabled they take over this function. + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). */ -static int update_sched_domains(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int __cpuexit cpuset_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) { - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DOWN_PREPARE: - case CPU_DOWN_PREPARE_FROZEN: case CPU_DOWN_FAILED: - case CPU_DOWN_FAILED_FROZEN: - partition_sched_domains(1, NULL, NULL); + cpuset_update_active_cpus(); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int __cpuexit cpuset_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + cpuset_update_active_cpus(); return NOTIFY_OK; - default: return NOTIFY_DONE; } } -#endif static int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu) @@ -7341,10 +7440,8 @@ void __init sched_init_smp(void) mutex_unlock(&sched_domains_mutex); put_online_cpus(); -#ifndef CONFIG_CPUSETS - /* XXX: Theoretical race here - CPU may be hotplugged now */ - hotcpu_notifier(update_sched_domains, 0); -#endif + hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); + hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); /* RT runtime code needs to handle some hotplug events */ hotcpu_notifier(update_runtime, 0); diff --git a/kernel/workqueue_sched.h b/kernel/workqueue_sched.h new file mode 100644 index 000000000000..af040babb742 --- /dev/null +++ b/kernel/workqueue_sched.h @@ -0,0 +1,16 @@ +/* + * kernel/workqueue_sched.h + * + * Scheduler hooks for concurrency managed workqueue. Only to be + * included from sched.c and workqueue.c. + */ +static inline void wq_worker_waking_up(struct task_struct *task, + unsigned int cpu) +{ +} + +static inline struct task_struct *wq_worker_sleeping(struct task_struct *task, + unsigned int cpu) +{ + return NULL; +}