diff options
Diffstat (limited to 'kernel')
40 files changed, 1204 insertions, 839 deletions
diff --git a/kernel/audit.c b/kernel/audit.c index 7c28936..47845c5 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -643,13 +643,13 @@ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) if ((task_active_pid_ns(current) != &init_pid_ns)) return -EPERM; - if (!capable(CAP_AUDIT_CONTROL)) + if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: - if (!capable(CAP_AUDIT_WRITE)) + if (!netlink_capable(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 9fcdaa7..3f1ca93 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -348,7 +348,7 @@ struct cgrp_cset_link { * reference-counted, to improve performance when child cgroups * haven't been created. */ -static struct css_set init_css_set = { +struct css_set init_css_set = { .refcount = ATOMIC_INIT(1), .cgrp_links = LIST_HEAD_INIT(init_css_set.cgrp_links), .tasks = LIST_HEAD_INIT(init_css_set.tasks), @@ -1495,7 +1495,7 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type, */ if (!use_task_css_set_links) cgroup_enable_task_cg_lists(); -retry: + mutex_lock(&cgroup_tree_mutex); mutex_lock(&cgroup_mutex); @@ -1503,7 +1503,7 @@ retry: ret = parse_cgroupfs_options(data, &opts); if (ret) goto out_unlock; - +retry: /* look for a matching existing root */ if (!opts.subsys_mask && !opts.none && !opts.name) { cgrp_dfl_root_visible = true; @@ -1562,9 +1562,9 @@ retry: if (!atomic_inc_not_zero(&root->cgrp.refcnt)) { mutex_unlock(&cgroup_mutex); mutex_unlock(&cgroup_tree_mutex); - kfree(opts.release_agent); - kfree(opts.name); msleep(10); + mutex_lock(&cgroup_tree_mutex); + mutex_lock(&cgroup_mutex); goto retry; } diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c index 2bc4a22..345628c 100644 --- a/kernel/cgroup_freezer.c +++ b/kernel/cgroup_freezer.c @@ -21,6 +21,7 @@ #include <linux/uaccess.h> #include <linux/freezer.h> #include <linux/seq_file.h> +#include <linux/mutex.h> /* * A cgroup is freezing if any FREEZING flags are set. FREEZING_SELF is @@ -42,9 +43,10 @@ enum freezer_state_flags { struct freezer { struct cgroup_subsys_state css; unsigned int state; - spinlock_t lock; }; +static DEFINE_MUTEX(freezer_mutex); + static inline struct freezer *css_freezer(struct cgroup_subsys_state *css) { return css ? container_of(css, struct freezer, css) : NULL; @@ -93,7 +95,6 @@ freezer_css_alloc(struct cgroup_subsys_state *parent_css) if (!freezer) return ERR_PTR(-ENOMEM); - spin_lock_init(&freezer->lock); return &freezer->css; } @@ -110,14 +111,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css) struct freezer *freezer = css_freezer(css); struct freezer *parent = parent_freezer(freezer); - /* - * The following double locking and freezing state inheritance - * guarantee that @cgroup can never escape ancestors' freezing - * states. See css_for_each_descendant_pre() for details. - */ - if (parent) - spin_lock_irq(&parent->lock); - spin_lock_nested(&freezer->lock, SINGLE_DEPTH_NESTING); + mutex_lock(&freezer_mutex); freezer->state |= CGROUP_FREEZER_ONLINE; @@ -126,10 +120,7 @@ static int freezer_css_online(struct cgroup_subsys_state *css) atomic_inc(&system_freezing_cnt); } - spin_unlock(&freezer->lock); - if (parent) - spin_unlock_irq(&parent->lock); - + mutex_unlock(&freezer_mutex); return 0; } @@ -144,14 +135,14 @@ static void freezer_css_offline(struct cgroup_subsys_state *css) { struct freezer *freezer = css_freezer(css); - spin_lock_irq(&freezer->lock); + mutex_lock(&freezer_mutex); if (freezer->state & CGROUP_FREEZING) atomic_dec(&system_freezing_cnt); freezer->state = 0; - spin_unlock_irq(&freezer->lock); + mutex_unlock(&freezer_mutex); } static void freezer_css_free(struct cgroup_subsys_state *css) @@ -175,7 +166,7 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, struct task_struct *task; bool clear_frozen = false; - spin_lock_irq(&freezer->lock); + mutex_lock(&freezer_mutex); /* * Make the new tasks conform to the current state of @new_css. @@ -197,21 +188,13 @@ static void freezer_attach(struct cgroup_subsys_state *new_css, } } - spin_unlock_irq(&freezer->lock); - - /* - * Propagate FROZEN clearing upwards. We may race with - * update_if_frozen(), but as long as both work bottom-up, either - * update_if_frozen() sees child's FROZEN cleared or we clear the - * parent's FROZEN later. No parent w/ !FROZEN children can be - * left FROZEN. - */ + /* propagate FROZEN clearing upwards */ while (clear_frozen && (freezer = parent_freezer(freezer))) { - spin_lock_irq(&freezer->lock); freezer->state &= ~CGROUP_FROZEN; clear_frozen = freezer->state & CGROUP_FREEZING; - spin_unlock_irq(&freezer->lock); } + + mutex_unlock(&freezer_mutex); } /** @@ -228,9 +211,6 @@ static void freezer_fork(struct task_struct *task) { struct freezer *freezer; - rcu_read_lock(); - freezer = task_freezer(task); - /* * The root cgroup is non-freezable, so we can skip locking the * freezer. This is safe regardless of race with task migration. @@ -238,24 +218,18 @@ static void freezer_fork(struct task_struct *task) * to do. If we lost and root is the new cgroup, noop is still the * right thing to do. */ - if (!parent_freezer(freezer)) - goto out; + if (task_css_is_root(task, freezer_cgrp_id)) + return; - /* - * Grab @freezer->lock and freeze @task after verifying @task still - * belongs to @freezer and it's freezing. The former is for the - * case where we have raced against task migration and lost and - * @task is already in a different cgroup which may not be frozen. - * This isn't strictly necessary as freeze_task() is allowed to be - * called spuriously but let's do it anyway for, if nothing else, - * documentation. - */ - spin_lock_irq(&freezer->lock); - if (freezer == task_freezer(task) && (freezer->state & CGROUP_FREEZING)) + mutex_lock(&freezer_mutex); + rcu_read_lock(); + + freezer = task_freezer(task); + if (freezer->state & CGROUP_FREEZING) freeze_task(task); - spin_unlock_irq(&freezer->lock); -out: + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); } /** @@ -281,22 +255,24 @@ static void update_if_frozen(struct cgroup_subsys_state *css) struct css_task_iter it; struct task_struct *task; - WARN_ON_ONCE(!rcu_read_lock_held()); - - spin_lock_irq(&freezer->lock); + lockdep_assert_held(&freezer_mutex); if (!(freezer->state & CGROUP_FREEZING) || (freezer->state & CGROUP_FROZEN)) - goto out_unlock; + return; /* are all (live) children frozen? */ + rcu_read_lock(); css_for_each_child(pos, css) { struct freezer *child = css_freezer(pos); if ((child->state & CGROUP_FREEZER_ONLINE) && - !(child->state & CGROUP_FROZEN)) - goto out_unlock; + !(child->state & CGROUP_FROZEN)) { + rcu_read_unlock(); + return; + } } + rcu_read_unlock(); /* are all tasks frozen? */ css_task_iter_start(css, &it); @@ -317,21 +293,29 @@ static void update_if_frozen(struct cgroup_subsys_state *css) freezer->state |= CGROUP_FROZEN; out_iter_end: css_task_iter_end(&it); -out_unlock: - spin_unlock_irq(&freezer->lock); } static int freezer_read(struct seq_file *m, void *v) { struct cgroup_subsys_state *css = seq_css(m), *pos; + mutex_lock(&freezer_mutex); rcu_read_lock(); /* update states bottom-up */ - css_for_each_descendant_post(pos, css) + css_for_each_descendant_post(pos, css) { + if (!css_tryget(pos)) + continue; + rcu_read_unlock(); + update_if_frozen(pos); + rcu_read_lock(); + css_put(pos); + } + rcu_read_unlock(); + mutex_unlock(&freezer_mutex); seq_puts(m, freezer_state_strs(css_freezer(css)->state)); seq_putc(m, '\n'); @@ -373,7 +357,7 @@ static void freezer_apply_state(struct freezer *freezer, bool freeze, unsigned int state) { /* also synchronizes against task migration, see freezer_attach() */ - lockdep_assert_held(&freezer->lock); + lockdep_assert_held(&freezer_mutex); if (!(freezer->state & CGROUP_FREEZER_ONLINE)) return; @@ -414,31 +398,29 @@ static void freezer_change_state(struct freezer *freezer, bool freeze) * descendant will try to inherit its parent's FREEZING state as * CGROUP_FREEZING_PARENT. */ + mutex_lock(&freezer_mutex); rcu_read_lock(); css_for_each_descendant_pre(pos, &freezer->css) { struct freezer *pos_f = css_freezer(pos); struct freezer *parent = parent_freezer(pos_f); - spin_lock_irq(&pos_f->lock); + if (!css_tryget(pos)) + continue; + rcu_read_unlock(); - if (pos_f == freezer) { + if (pos_f == freezer) freezer_apply_state(pos_f, freeze, CGROUP_FREEZING_SELF); - } else { - /* - * Our update to @parent->state is already visible - * which is all we need. No need to lock @parent. - * For more info on synchronization, see - * freezer_post_create(). - */ + else freezer_apply_state(pos_f, parent->state & CGROUP_FREEZING, CGROUP_FREEZING_PARENT); - } - spin_unlock_irq(&pos_f->lock); + rcu_read_lock(); + css_put(pos); } rcu_read_unlock(); + mutex_unlock(&freezer_mutex); } static int freezer_write(struct cgroup_subsys_state *css, struct cftype *cft, diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c index 6cb20d2..019d450 100644 --- a/kernel/context_tracking.c +++ b/kernel/context_tracking.c @@ -120,7 +120,7 @@ void context_tracking_user_enter(void) * instead of preempt_schedule() to exit user context if needed before * calling the scheduler. */ -asmlinkage void __sched notrace preempt_schedule_context(void) +asmlinkage __visible void __sched notrace preempt_schedule_context(void) { enum ctx_state prev_ctx; diff --git a/kernel/cpu.c b/kernel/cpu.c index a9e710e..247979a 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -726,10 +726,12 @@ void set_cpu_present(unsigned int cpu, bool present) void set_cpu_online(unsigned int cpu, bool online) { - if (online) + if (online) { cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits)); - else + cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits)); + } else { cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits)); + } } void set_cpu_active(unsigned int cpu, bool active) diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index d55092c..e0501fe 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -234,6 +234,11 @@ again: goto again; } timer->base = new_base; + } else { + if (cpu != this_cpu && hrtimer_check_target(timer, new_base)) { + cpu = this_cpu; + goto again; + } } return new_base; } @@ -569,6 +574,23 @@ hrtimer_force_reprogram(struct hrtimer_cpu_base *cpu_base, int skip_equal) cpu_base->expires_next.tv64 = expires_next.tv64; + /* + * If a hang was detected in the last timer interrupt then we + * leave the hang delay active in the hardware. We want the + * system to make progress. That also prevents the following + * scenario: + * T1 expires 50ms from now + * T2 expires 5s from now + * + * T1 is removed, so this code is called and would reprogram + * the hardware to 5s from now. Any hrtimer_start after that + * will not reprogram the hardware due to hang_detected being + * set. So we'd effectivly block all timers until the T2 event + * fires. + */ + if (cpu_base->hang_detected) + return; + if (cpu_base->expires_next.tv64 != KTIME_MAX) tick_program_event(cpu_base->expires_next, 1); } @@ -968,11 +990,8 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, /* Remove an active timer from the queue: */ ret = remove_hrtimer(timer, base); - /* Switch the timer base, if necessary: */ - new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); - if (mode & HRTIMER_MODE_REL) { - tim = ktime_add_safe(tim, new_base->get_time()); + tim = ktime_add_safe(tim, base->get_time()); /* * CONFIG_TIME_LOW_RES is a temporary way for architectures * to signal that they simply return xtime in @@ -987,6 +1006,9 @@ int __hrtimer_start_range_ns(struct hrtimer *timer, ktime_t tim, hrtimer_set_expires_range_ns(timer, tim, delta_ns); + /* Switch the timer base, if necessary: */ + new_base = switch_hrtimer_base(timer, base, mode & HRTIMER_MODE_PINNED); + timer_stats_hrtimer_set_start_info(timer); leftmost = enqueue_hrtimer(timer, new_base); diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index a7174617..bb07f29 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -363,6 +363,13 @@ __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, if (from > irq) return -EINVAL; from = irq; + } else { + /* + * For interrupts which are freely allocated the + * architecture can force a lower bound to the @from + * argument. x86 uses this to exclude the GSI space. + */ + from = arch_dynirq_lower_bound(from); } mutex_lock(&sparse_irq_lock); diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 2486a4c..d34131c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -180,7 +180,7 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, struct irq_chip *chip = irq_data_get_irq_chip(data); int ret; - ret = chip->irq_set_affinity(data, mask, false); + ret = chip->irq_set_affinity(data, mask, force); switch (ret) { case IRQ_SET_MASK_OK: cpumask_copy(data->affinity, mask); @@ -192,7 +192,8 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask, return ret; } -int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) +int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask, + bool force) { struct irq_chip *chip = irq_data_get_irq_chip(data); struct irq_desc *desc = irq_data_to_desc(data); @@ -202,7 +203,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) return -EINVAL; if (irq_can_move_pcntxt(data)) { - ret = irq_do_set_affinity(data, mask, false); + ret = irq_do_set_affinity(data, mask, force); } else { irqd_set_move_pending(data); irq_copy_pending(desc, mask); @@ -217,13 +218,7 @@ int __irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask) return ret; } -/** - * irq_set_affinity - Set the irq affinity of a given irq - * @irq: Interrupt to set affinity - * @mask: cpumask - * - */ -int irq_set_affinity(unsigned int irq, const struct cpumask *mask) +int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; @@ -233,7 +228,7 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *mask) return -EINVAL; raw_spin_lock_irqsave(&desc->lock, flags); - ret = __irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask); + ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force); raw_spin_unlock_irqrestore(&desc->lock, flags); return ret; } diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index b0e9467..d24e433 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -4188,7 +4188,7 @@ void debug_show_held_locks(struct task_struct *task) } EXPORT_SYMBOL_GPL(debug_show_held_locks); -asmlinkage void lockdep_sys_exit(void) +asmlinkage __visible void lockdep_sys_exit(void) { struct task_struct *curr = current; diff --git a/kernel/locking/locktorture.c b/kernel/locking/locktorture.c index f26b1a1..23343be 100644 --- a/kernel/locking/locktorture.c +++ b/kernel/locking/locktorture.c @@ -216,7 +216,7 @@ static int lock_torture_writer(void *arg) static DEFINE_TORTURE_RANDOM(rand); VERBOSE_TOROUT_STRING("lock_torture_writer task started"); - set_user_nice(current, 19); + set_user_nice(current, MAX_NICE); do { schedule_timeout_uninterruptible(1); diff --git a/kernel/module.c b/kernel/module.c index 1186940..079c461 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -815,9 +815,6 @@ SYSCALL_DEFINE2(delete_module, const char __user *, name_user, return -EFAULT; name[MODULE_NAME_LEN-1] = '\0'; - if (!(flags & O_NONBLOCK)) - pr_warn("waiting module removal not supported: please upgrade\n"); - if (mutex_lock_interruptible(&module_mutex) != 0) return -EINTR; @@ -3271,6 +3268,9 @@ static int load_module(struct load_info *info, const char __user *uargs, dynamic_debug_setup(info->debug, info->num_debug); + /* Ftrace init must be called in the MODULE_STATE_UNFORMED state */ + ftrace_module_init(mod); + /* Finally it's fully formed, ready to start executing. */ err = complete_formation(mod, info); if (err) diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 18fb7a2..1ea328a 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -1586,7 +1586,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm, return -ENOMEM; } -asmlinkage int swsusp_save(void) +asmlinkage __visible int swsusp_save(void) { unsigned int nr_pages, nr_highmem; diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c index c3ad9ca..155721f 100644 --- a/kernel/power/suspend.c +++ b/kernel/power/suspend.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/console.h> #include <linux/cpu.h> +#include <linux/cpuidle.h> #include <linux/syscalls.h> #include <linux/gfp.h> #include <linux/io.h> @@ -53,7 +54,11 @@ static void freeze_begin(void) static void freeze_enter(void) { + cpuidle_use_deepest_state(true); + cpuidle_resume(); wait_event(suspend_freeze_wait_head, suspend_freeze_wake); + cpuidle_pause(); + cpuidle_use_deepest_state(false); } void freeze_wake(void) diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index a45b509..7228258 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1674,7 +1674,7 @@ EXPORT_SYMBOL(printk_emit); * * See the vsnprintf() documentation for format string extensions over C99. */ -asmlinkage int printk(const char *fmt, ...) +asmlinkage __visible int printk(const char *fmt, ...) { va_list args; int r; @@ -1737,7 +1737,7 @@ void early_vprintk(const char *fmt, va_list ap) } } -asmlinkage void early_printk(const char *fmt, ...) +asmlinkage __visible void early_printk(const char *fmt, ...) { va_list ap; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 8a70ec0..54f5722 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -522,6 +522,71 @@ static inline void init_hrtick(void) #endif /* CONFIG_SCHED_HRTICK */ /* + * cmpxchg based fetch_or, macro so it works for different integer types + */ +#define fetch_or(ptr, val) \ +({ typeof(*(ptr)) __old, __val = *(ptr); \ + for (;;) { \ + __old = cmpxchg((ptr), __val, __val | (val)); \ + if (__old == __val) \ + break; \ + __val = __old; \ + } \ + __old; \ +}) + +#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG) +/* + * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG, + * this avoids any races wrt polling state changes and thereby avoids + * spurious IPIs. + */ +static bool set_nr_and_not_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG); +} + +/* + * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set. + * + * If this returns true, then the idle task promises to call + * sched_ttwu_pending() and reschedule soon. + */ +static bool set_nr_if_polling(struct task_struct *p) +{ + struct thread_info *ti = task_thread_info(p); + typeof(ti->flags) old, val = ACCESS_ONCE(ti->flags); + + for (;;) { + if (!(val & _TIF_POLLING_NRFLAG)) + return false; + if (val & _TIF_NEED_RESCHED) + return true; + old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED); + if (old == val) + break; + val = old; + } + return true; +} + +#else +static bool set_nr_and_not_polling(struct task_struct *p) +{ + set_tsk_need_resched(p); + return true; +} + +#ifdef CONFIG_SMP +static bool set_nr_if_polling(struct task_struct *p) +{ + return false; +} +#endif +#endif + +/* * resched_task - mark a task 'to be rescheduled now'. * * On UP this means the setting of the need_resched flag, on SMP it @@ -537,18 +602,18 @@ void resched_task(struct task_struct *p) if (test_tsk_need_resched(p)) return; - set_tsk_need_resched(p); - cpu = task_cpu(p); + if (cpu == smp_processor_id()) { + set_tsk_need_resched(p); set_preempt_need_resched(); return; } - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(p)) + if (set_nr_and_not_polling(p)) smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } void resched_cpu(int cpu) @@ -611,27 +676,10 @@ static void wake_up_idle_cpu(int cpu) if (cpu == smp_processor_id()) return; - /* - * This is safe, as this function is called with the timer - * wheel base lock of (cpu) held. When the CPU is on the way - * to idle and has not yet set rq->curr to idle then it will - * be serialized on the timer wheel base lock and take the new - * timer into account automatically. - */ - if (rq->curr != rq->idle) - return; - - /* - * We can set TIF_RESCHED on the idle task of the other CPU - * lockless. The worst case is that the other CPU runs the - * idle task through an additional NOOP schedule() - */ - set_tsk_need_resched(rq->idle); - - /* NEED_RESCHED must be visible before we test polling */ - smp_mb(); - if (!tsk_is_polling(rq->idle)) + if (set_nr_and_not_polling(rq->idle)) smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); } static bool wake_up_full_nohz_cpu(int cpu) @@ -857,7 +905,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta) rq->clock_task += delta; #if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - if ((irq_delta + steal) && sched_feat(NONTASK_POWER)) + if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) sched_rt_avg_update(rq, irq_delta + steal); #endif } @@ -1490,13 +1538,17 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) } #ifdef CONFIG_SMP -static void sched_ttwu_pending(void) +void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); struct task_struct *p; + unsigned long flags; - raw_spin_lock(&rq->lock); + if (!llist) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); while (llist) { p = llist_entry(llist, struct task_struct, wake_entry); @@ -1504,7 +1556,7 @@ static void sched_ttwu_pending(void) ttwu_do_activate(rq, p, 0); } - raw_spin_unlock(&rq->lock); + raw_spin_unlock_irqrestore(&rq->lock, flags); } void scheduler_ipi(void) @@ -1550,8 +1602,14 @@ void scheduler_ipi(void) static void ttwu_queue_remote(struct task_struct *p, int cpu) { - if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) - smp_send_reschedule(cpu); + struct rq *rq = cpu_rq(cpu); + + if (llist_add(&p->wake_entry, &cpu_rq(cpu)->wake_list)) { + if (!set_nr_if_polling(rq->idle)) + smp_send_reschedule(cpu); + else + trace_sched_wake_idle_without_ipi(cpu); + } } bool cpus_share_cache(int this_cpu, int that_cpu) @@ -2208,7 +2266,7 @@ static inline void post_schedule(struct rq *rq) * schedule_tail - first thing a freshly forked thread must call. * @prev: the thread we just switched away from. */ -asmlinkage void schedule_tail(struct task_struct *prev) +asmlinkage __visible void schedule_tail(struct task_struct *prev) __releases(rq->lock) { struct rq *rq = this_rq(); @@ -2608,8 +2666,14 @@ pick_next_task(struct rq *rq, struct task_struct *prev) if (likely(prev->sched_class == class && rq->nr_running == rq->cfs.h_nr_running)) { p = fair_sched_class.pick_next_task(rq, prev); - if (likely(p && p != RETRY_TASK)) - return p; + if (unlikely(p == RETRY_TASK)) + goto again; + + /* assumes fair_sched_class->next == idle_sched_class */ + if (unlikely(!p)) + p = idle_sched_class.pick_next_task(rq, prev); + + return p; } again: @@ -2757,7 +2821,7 @@ static inline void sched_submit_work(struct task_struct *tsk) blk_schedule_flush_plug(tsk); } -asmlinkage void __sched schedule(void) +asmlinkage __visible void __sched schedule(void) { struct task_struct *tsk = current; @@ -2767,7 +2831,7 @@ asmlinkage void __sched schedule(void) EXPORT_SYMBOL(schedule); #ifdef CONFIG_CONTEXT_TRACKING -asmlinkage void __sched schedule_user(void) +asmlinkage __visible void __sched schedule_user(void) { /* * If we come here after a random call to set_need_resched(), @@ -2799,7 +2863,7 @@ void __sched schedule_preempt_disabled(void) * off of preempt_enable. Kernel preemptions off return from interrupt * occur there and call schedule directly. */ -asmlinkage void __sched notrace preempt_schedule(void) +asmlinkage __visible void __sched notrace preempt_schedule(void) { /* * If there is a non-zero preempt_count or interrupts are disabled, @@ -2829,7 +2893,7 @@ EXPORT_SYMBOL(preempt_schedule); * Note, that this is called and return with irqs disabled. This will * protect us against recursive calling from irq. */ -asmlinkage void __sched preempt_schedule_irq(void) +asmlinkage __visible void __sched preempt_schedule_irq(void) { enum ctx_state prev_state; @@ -3012,7 +3076,7 @@ EXPORT_SYMBOL(set_user_nice); int can_nice(const struct task_struct *p, const int nice) { /* convert nice value [19,-20] to rlimit style value [1,40] */ - int nice_rlim = 20 - nice; + int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); @@ -3036,17 +3100,10 @@ SYSCALL_DEFINE1(nice, int, increment) * We don't have to worry. Conceptually one call occurs first * and we have a single winner. */ - if (increment < -40) - increment = -40; - if (increment > 40) - increment = 40; - + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); nice = task_nice(current) + increment; - if (nice < MIN_NICE) - nice = MIN_NICE; - if (nice > MAX_NICE) - nice = MAX_NICE; + nice = clamp_val(nice, MIN_NICE, MAX_NICE); if (increment < 0 && !can_nice(current, nice)) return -EPERM; @@ -3140,6 +3197,7 @@ __setparam_dl(struct task_struct *p, const struct sched_attr *attr) dl_se->dl_bw = to_ratio(dl_se->dl_period, dl_se->dl_runtime); dl_se->dl_throttled = 0; dl_se->dl_new = 1; + dl_se->dl_yielded = 0; } static void __setscheduler_params(struct task_struct *p, @@ -3204,17 +3262,40 @@ __getparam_dl(struct task_struct *p, struct sched_attr *attr) * We ask for the deadline not being zero, and greater or equal * than the runtime, as well as the period of being zero or * greater than deadline. Furthermore, we have to be sure that - * user parameters are above the internal resolution (1us); we - * check sched_runtime only since it is always the smaller one. + * user parameters are above the internal resolution of 1us (we + * check sched_runtime only since it is always the smaller one) and + * below 2^63 ns (we have to check both sched_deadline and + * sched_period, as the latter can be zero). */ static bool __checkparam_dl(const struct sched_attr *attr) { - return attr && attr->sched_deadline != 0 && - (attr->sched_period == 0 || - (s64)(attr->sched_period - attr->sched_deadline) >= 0) && - (s64)(attr->sched_deadline - attr->sched_runtime ) >= 0 && - attr->sched_runtime >= (2 << (DL_SCALE - 1)); + /* deadline != 0 */ + if (attr->sched_deadline == 0) + return false; + + /* + * Since we truncate DL_SCALE bits, make sure we're at least + * that big. + */ + if (attr->sched_runtime < (1ULL << DL_SCALE)) + return false; + + /* + * Since we use the MSB for wrap-around and sign issues, make + * sure it's not set (mind that period can be equal to zero). + */ + if (attr->sched_deadline & (1ULL << 63) || + attr->sched_period & (1ULL << 63)) + return false; + + /* runtime <= deadline <= period (if period != 0) */ + if ((attr->sched_period != 0 && + attr->sched_period < attr->sched_deadline) || + attr->sched_deadline < attr->sched_runtime) + return false; + + return true; } /* @@ -3612,13 +3693,11 @@ static int sched_copy_attr(struct sched_attr __user *uattr, */ attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); -out: - return ret; + return 0; err_size: put_user(sizeof(*attr), &uattr->size); - ret = -E2BIG; - goto out; + return -E2BIG; } /** @@ -3655,6 +3734,7 @@ SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) * sys_sched_setattr - same as above, but with extended sched_attr * @pid: the pid in question. * @uattr: structure containing the extended parameters. + * @flags: for future extension. */ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, unsigned int, flags) @@ -3666,8 +3746,12 @@ SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, if (!uattr || pid < 0 || flags) return -EINVAL; - if (sched_copy_attr(uattr, &attr)) - return -EFAULT; + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if (attr.sched_policy < 0) + return -EINVAL; rcu_read_lock(); retval = -ESRCH; @@ -3717,7 +3801,7 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) */ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) { - struct sched_param lp; + struct sched_param lp = { .sched_priority = 0 }; struct task_struct *p; int retval; @@ -3734,11 +3818,8 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) if (retval) goto out_unlock; - if (task_has_dl_policy(p)) { - retval = -EINVAL; - goto out_unlock; - } - lp.sched_priority = p->rt_priority; + if (task_has_rt_policy(p)) + lp.sched_priority = p->rt_priority; rcu_read_unlock(); /* @@ -3776,7 +3857,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, for (; addr < end; addr++) { if (*addr) - goto err_size; + return -EFBIG; } attr->size = usize; @@ -3786,12 +3867,7 @@ static int sched_read_attr(struct sched_attr __user *uattr, if (ret) return -EFAULT; -out: - return ret; - -err_size: - ret = -E2BIG; - goto out; + return 0; } /** @@ -3799,6 +3875,7 @@ err_size: * @pid: the pid in question. * @uattr: structure containing the extended parameters. * @size: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. */ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, unsigned int, size, unsigned int, flags) @@ -4161,7 +4238,7 @@ EXPORT_SYMBOL(yield); * false (0) if we failed to boost the target. * -ESRCH if there's no task to yield to. */ -bool __sched yield_to(struct task_struct *p, bool preempt) +int __sched yield_to(struct task_struct *p, bool preempt) { struct task_struct *curr = current; struct rq *rq, *p_rq; @@ -5055,11 +5132,20 @@ static struct notifier_block migration_notifier = { .priority = CPU_PRI_MIGRATION, }; +static void __cpuinit set_cpu_rq_start_time(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + rq->age_stamp = sched_clock_cpu(cpu); +} + static int sched_cpu_active(struct notifier_block *nfb, unsigned long action, void *hcpu) { switch (action & ~CPU_TASKS_FROZEN) { case CPU_STARTING: + set_cpu_rq_start_time(); + return NOTIFY_OK; case CPU_DOWN_FAILED: set_cpu_active((long)hcpu, true); return NOTIFY_OK; @@ -5178,14 +5264,13 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, } /* - * Even though we initialize ->power to something semi-sane, - * we leave power_orig unset. This allows us to detect if + * Even though we initialize ->capacity to something semi-sane, + * we leave capacity_orig unset. This allows us to detect if * domain iteration is still funny without causing /0 traps. */ - if (!group->sgp->power_orig) { + if (!group->sgc->capacity_orig) { printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_power not " - "set\n"); + printk(KERN_ERR "ERROR: domain->cpu_capacity not set\n"); break; } @@ -5207,9 +5292,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); printk(KERN_CONT " %s", str); - if (group->sgp->power != SCHED_POWER_SCALE) { - printk(KERN_CONT " (cpu_power = %d)", - group->sgp->power); + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { + printk(KERN_CONT " (cpu_capacity = %d)", + group->sgc->capacity); } group = group->next; @@ -5267,8 +5352,9 @@ static int sd_degenerate(struct sched_domain *sd) SD_BALANCE_NEWIDLE | SD_BALANCE_FORK | SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | - SD_SHARE_PKG_RESOURCES)) { + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { if (sd->groups != sd->groups->next) return 0; } @@ -5297,9 +5383,10 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) SD_BALANCE_NEWIDLE | SD_BALANCE_FORK | SD_BALANCE_EXEC | - SD_SHARE_CPUPOWER | + SD_SHARE_CPUCAPACITY | SD_SHARE_PKG_RESOURCES | - SD_PREFER_SIBLING); + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); if (nr_node_ids == 1) pflags &= ~SD_SERIALIZE; } @@ -5421,7 +5508,7 @@ static struct root_domain *alloc_rootdomain(void) return rd; } -static void free_sched_groups(struct sched_group *sg, int free_sgp) +static void free_sched_groups(struct sched_group *sg, int free_sgc) { struct sched_group *tmp, *first; @@ -5432,8 +5519,8 @@ static void free_sched_groups(struct sched_group *sg, int free_sgp) do { tmp = sg->next; - if (free_sgp && atomic_dec_and_test(&sg->sgp->ref)) - kfree(sg->sgp); + if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) + kfree(sg->sgc); kfree(sg); sg = tmp; @@ -5451,7 +5538,7 @@ static void free_sched_domain(struct rcu_head *rcu) if (sd->flags & SD_OVERLAP) { free_sched_groups(sd->groups, 1); } else if (atomic_dec_and_test(&sd->groups->ref)) { - kfree(sd->groups->sgp); + kfree(sd->groups->sgc); kfree(sd->groups); } kfree(sd); @@ -5573,17 +5660,6 @@ static int __init isolated_cpu_setup(char *str) __setup("isolcpus=", isolated_cpu_setup); -static const struct cpumask *cpu_cpu_mask(int cpu) -{ - return cpumask_of_node(cpu_to_node(cpu)); -} - -struct sd_data { - struct sched_domain **__percpu sd; - struct sched_group **__percpu sg; - struct sched_group_power **__percpu sgp; -}; - struct s_data { struct sched_domain ** __percpu sd; struct root_domain *rd; @@ -5596,21 +5672,6 @@ enum s_alloc { sa_none, }; -struct sched_domain_topology_level; - -typedef struct sched_domain *(*sched_domain_init_f)(struct sched_domain_topology_level *tl, int cpu); -typedef const struct cpumask *(*sched_domain_mask_f)(int cpu); - -#define SDTL_OVERLAP 0x01 - -struct sched_domain_topology_level { - sched_domain_init_f init; - sched_domain_mask_f mask; - int flags; - int numa_level; - struct sd_data data; -}; - /* * Build an iteration mask that can exclude certain CPUs from the upwards * domain traversal. @@ -5688,17 +5749,17 @@ build_overlap_sched_groups(struct sched_domain *sd, int cpu) cpumask_or(covered, covered, sg_span); - sg->sgp = *per_cpu_ptr(sdd->sgp, i); - if (atomic_inc_return(&sg->sgp->ref) == 1) + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) build_group_mask(sd, sg); /* - * Initialize sgp->power such that even if we mess up the + * Initialize sgc->capacity such that even if we mess up the * domains and no possible iteration will get us here, we won't * die on a /0 trap. */ - sg->sgp->power = SCHED_POWER_SCALE * cpumask_weight(sg_span); - sg->sgp->power_orig = sg->sgp->power; + sg->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + sg->sgc->capacity_orig = sg->sgc->capacity; /* * Make sure the first group of this domain contains the @@ -5736,8 +5797,8 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) if (sg) { *sg = *per_cpu_ptr(sdd->sg, cpu); - (*sg)->sgp = *per_cpu_ptr(sdd->sgp, cpu); - atomic_set(&(*sg)->sgp->ref, 1); /* for claim_allocations */ + (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */ } return cpu; @@ -5746,7 +5807,7 @@ static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) /* * build_sched_groups will build a circular linked list of the groups * covered by the given span, and will set each group's ->cpumask correctly, - * and ->cpu_power to 0. + * and ->cpu_capacity to 0. * * Assumes the sched_domain tree is fully constructed */ @@ -5778,8 +5839,6 @@ build_sched_groups(struct sched_domain *sd, int cpu) continue; group = get_group(i, sdd, &sg); - cpumask_clear(sched_group_cpus(sg)); - sg->sgp->power = 0; cpumask_setall(sched_group_mask(sg)); for_each_cpu(j, span) { @@ -5802,16 +5861,16 @@ build_sched_groups(struct sched_domain *sd, int cpu) } /* - * Initialize sched groups cpu_power. + * Initialize sched groups cpu_capacity. * - * cpu_power indicates the capacity of sched group, which is used while + * cpu_capacity indicates the capacity of sched group, which is used while * distributing the load between different sched groups in a sched domain. - * Typically cpu_power for all the groups in a sched domain will be same unless - * there are asymmetries in the topology. If there are asymmetries, group - * having more cpu_power will pickup more load compared to the group having - * less cpu_power. + * Typically cpu_capacity for all the groups in a sched domain will be same + * unless there are asymmetries in the topology. If there are asymmetries, + * group having more cpu_capacity will pickup more load compared to the + * group having less cpu_capacity. */ -static void init_sched_groups_power(int cpu, struct sched_domain *sd) +static void init_sched_groups_capacity(int cpu, struct sched_domain *sd) { struct sched_group *sg = sd->groups; @@ -5825,13 +5884,8 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) if (cpu != group_balance_cpu(sg)) return; - update_group_power(sd, cpu); - atomic_set(&sg->sgp->nr_busy_cpus, sg->group_weight); -} - -int __weak arch_sd_sibling_asym_packing(void) -{ - return 0*SD_ASYM_PACKING; + update_group_capacity(sd, cpu); + atomic_set(&sg->sgc->nr_busy_cpus, sg->group_weight); } /* @@ -5839,34 +5893,6 @@ int __weak arch_sd_sibling_asym_packing(void) * Non-inlined to reduce accumulated stack pressure in build_sched_domains() */ -#ifdef CONFIG_SCHED_DEBUG -# define SD_INIT_NAME(sd, type) sd->name = #type -#else -# define SD_INIT_NAME(sd, type) do { } while (0) -#endif - -#define SD_INIT_FUNC(type) \ -static noinline struct sched_domain * \ -sd_init_##type(struct sched_domain_topology_level *tl, int cpu) \ -{ \ - struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); \ - *sd = SD_##type##_INIT; \ - SD_INIT_NAME(sd, type); \ - sd->private = &tl->data; \ - return sd; \ -} - -SD_INIT_FUNC(CPU) -#ifdef CONFIG_SCHED_SMT - SD_INIT_FUNC(SIBLING) -#endif -#ifdef CONFIG_SCHED_MC - SD_INIT_FUNC(MC) -#endif -#ifdef CONFIG_SCHED_BOOK - SD_INIT_FUNC(BOOK) -#endif - static int default_relax_domain_level = -1; int sched_domain_level_max; @@ -5950,101 +5976,158 @@ static void claim_allocations(int cpu, struct sched_domain *sd) if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) *per_cpu_ptr(sdd->sg, cpu) = NULL; - if (atomic_read(&(*per_cpu_ptr(sdd->sgp, cpu))->ref)) - *per_cpu_ptr(sdd->sgp, cpu) = NULL; -} - -#ifdef CONFIG_SCHED_SMT -static const struct cpumask *cpu_smt_mask(int cpu) -{ - return topology_thread_cpumask(cpu); + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; } -#endif - -/* - * Topology list, bottom-up. - */ -static struct sched_domain_topology_level default_topology[] = { -#ifdef CONFIG_SCHED_SMT - { sd_init_SIBLING, cpu_smt_mask, }, -#endif -#ifdef CONFIG_SCHED_MC - { sd_init_MC, cpu_coregroup_mask, }, -#endif -#ifdef CONFIG_SCHED_BOOK - { sd_init_BOOK, cpu_book_mask, }, -#endif - { sd_init_CPU, cpu_cpu_mask, }, - { NULL, }, -}; - -static struct sched_domain_topology_level *sched_domain_topology = default_topology; - -#define for_each_sd_topology(tl) \ - for (tl = sched_domain_topology; tl->init; tl++) #ifdef CONFIG_NUMA - static int sched_domains_numa_levels; static int *sched_domains_numa_distance; static struct cpumask ***sched_domains_numa_masks; static int sched_domains_curr_level; +#endif -static inline int sd_local_flags(int level) -{ - if (sched_domains_numa_distance[level] > RECLAIM_DISTANCE) - return 0; - - return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE; -} +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUCAPACITY - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) static struct sched_domain * -sd_numa_init(struct sched_domain_topology_level *tl, int cpu) +sd_init(struct sched_domain_topology_level *tl, int cpu) { struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); - int level = tl->numa_level; - int sd_weight = cpumask_weight( - sched_domains_numa_masks[level][cpu_to_node(cpu)]); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; *sd = (struct sched_domain){ .min_interval = sd_weight, .max_interval = 2*sd_weight, .busy_factor = 32, .imbalance_pct = 125, - .cache_nice_tries = 2, - .busy_idx = 3, - .idle_idx = 2, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, .newidle_idx = 0, .wake_idx = 0, .forkexec_idx = 0, .flags = 1*SD_LOAD_BALANCE | 1*SD_BALANCE_NEWIDLE - | 0*SD_BALANCE_EXEC - | 0*SD_BALANCE_FORK + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK | 0*SD_BALANCE_WAKE - | 0*SD_WAKE_AFFINE - | 0*SD_SHARE_CPUPOWER + | 1*SD_WAKE_AFFINE + | 0*SD_SHARE_CPUCAPACITY | 0*SD_SHARE_PKG_RESOURCES - | 1*SD_SERIALIZE + | 0*SD_SERIALIZE | 0*SD_PREFER_SIBLING - | 1*SD_NUMA - | sd_local_flags(level) + | 0*SD_NUMA + | sd_flags , + .last_balance = jiffies, .balance_interval = sd_weight, + .smt_gain = 0, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif }; - SD_INIT_NAME(sd, NUMA); - sd->private = &tl->data; /* - * Ugly hack to pass state to sd_numa_mask()... + * Convert topological properties into behaviour. */ - sched_domains_curr_level = tl->numa_level; + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; return sd; } +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +struct sched_domain_topology_level *sched_domain_topology = default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + static const struct cpumask *sd_numa_mask(int cpu) { return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; @@ -6188,7 +6271,10 @@ static void sched_init_numa(void) } } - tl = kzalloc((ARRAY_SIZE(default_topology) + level) * + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * sizeof(struct sched_domain_topology_level), GFP_KERNEL); if (!tl) return; @@ -6196,18 +6282,19 @@ static void sched_init_numa(void) /* * Copy the default topology bits.. */ - for (i = 0; default_topology[i].init; i++) - tl[i] = default_topology[i]; + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; /* * .. and append 'j' levels of NUMA goodness. */ for (j = 0; j < level; i++, j++) { tl[i] = (struct sched_domain_topology_level){ - .init = sd_numa_init, .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, .flags = SDTL_OVERLAP, .numa_level = j, + SD_INIT_NAME(NUMA) }; } @@ -6292,14 +6379,14 @@ static int __sdt_alloc(const struct cpumask *cpu_map) if (!sdd->sg) return -ENOMEM; - sdd->sgp = alloc_percpu(struct sched_group_power *); - if (!sdd->sgp) + sdd->sgc = alloc_percpu(struct sched_group_capacity *); + if (!sdd->sgc) return -ENOMEM; for_each_cpu(j, cpu_map) { struct sched_domain *sd; struct sched_group *sg; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); @@ -6317,12 +6404,12 @@ static int __sdt_alloc(const struct cpumask *cpu_map) *per_cpu_ptr(sdd->sg, j) = sg; - sgp = kzalloc_node(sizeof(struct sched_group_power) + cpumask_size(), + sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), GFP_KERNEL, cpu_to_node(j)); - if (!sgp) + if (!sgc) return -ENOMEM; - *per_cpu_ptr(sdd->sgp, j) = sgp; + *per_cpu_ptr(sdd->sgc, j) = sgc; } } @@ -6349,15 +6436,15 @@ static void __sdt_free(const struct cpumask *cpu_map) if (sdd->sg) kfree(*per_cpu_ptr(sdd->sg, j)); - if (sdd->sgp) - kfree(*per_cpu_ptr(sdd->sgp, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); } free_percpu(sdd->sd); sdd->sd = NULL; free_percpu(sdd->sg); sdd->sg = NULL; - free_percpu(sdd->sgp); - sdd->sgp = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; } } @@ -6365,7 +6452,7 @@ struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, const struct cpumask *cpu_map, struct sched_domain_attr *attr, struct sched_domain *child, int cpu) { - struct sched_domain *sd = tl->init(tl, cpu); + struct sched_domain *sd = sd_init(tl, cpu); if (!sd) return child; @@ -6427,14 +6514,14 @@ static int build_sched_domains(const struct cpumask *cpu_map, } } - /* Calculate CPU power for physical packages and nodes */ + /* Calculate CPU capacity for physical packages and nodes */ for (i = nr_cpumask_bits-1; i >= 0; i--) { if (!cpumask_test_cpu(i, cpu_map)) continue; for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { claim_allocations(i, sd); - init_sched_groups_power(i, sd); + init_sched_groups_capacity(i, sd); } } @@ -6877,7 +6964,7 @@ void __init sched_init(void) #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; - rq->cpu_power = SCHED_POWER_SCALE; + rq->cpu_capacity = SCHED_CAPACITY_SCALE; rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; @@ -6935,6 +7022,7 @@ void __init sched_init(void) if (cpu_isolated_map == NULL) zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); idle_thread_set_boot_cpu(); + set_cpu_rq_start_time(); #endif init_sched_fair_class(); diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 5b9bb42..bd95963 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -13,6 +13,7 @@ #include <linux/gfp.h> #include <linux/kernel.h> +#include <linux/slab.h> #include "cpudeadline.h" static inline int parent(int i) @@ -39,8 +40,10 @@ static void cpudl_exchange(struct cpudl *cp, int a, int b) { int cpu_a = cp->elements[a].cpu, cpu_b = cp->elements[b].cpu; - swap(cp->elements[a], cp->elements[b]); - swap(cp->cpu_to_idx[cpu_a], cp->cpu_to_idx[cpu_b]); + swap(cp->elements[a].cpu, cp->elements[b].cpu); + swap(cp->elements[a].dl , cp->elements[b].dl ); + + swap(cp->elements[cpu_a].idx, cp->elements[cpu_b].idx); } static void cpudl_heapify(struct cpudl *cp, int idx) @@ -140,7 +143,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) WARN_ON(!cpu_present(cpu)); raw_spin_lock_irqsave(&cp->lock, flags); - old_idx = cp->cpu_to_idx[cpu]; + old_idx = cp->elements[cpu].idx; if (!is_valid) { /* remove item */ if (old_idx == IDX_INVALID) { @@ -155,8 +158,8 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) cp->elements[old_idx].dl = cp->elements[cp->size - 1].dl; cp->elements[old_idx].cpu = new_cpu; cp->size--; - cp->cpu_to_idx[new_cpu] = old_idx; - cp->cpu_to_idx[cpu] = IDX_INVALID; + cp->elements[new_cpu].idx = old_idx; + cp->elements[cpu].idx = IDX_INVALID; while (old_idx > 0 && dl_time_before( cp->elements[parent(old_idx)].dl, cp->elements[old_idx].dl)) { @@ -173,7 +176,7 @@ void cpudl_set(struct cpudl *cp, int cpu, u64 dl, int is_valid) cp->size++; cp->elements[cp->size - 1].dl = 0; cp->elements[cp->size - 1].cpu = cpu; - cp->cpu_to_idx[cpu] = cp->size - 1; + cp->elements[cpu].idx = cp->size - 1; cpudl_change_key(cp, cp->size - 1, dl); cpumask_clear_cpu(cpu, cp->free_cpus); } else { @@ -195,10 +198,21 @@ int cpudl_init(struct cpudl *cp) memset(cp, 0, sizeof(*cp)); raw_spin_lock_init(&cp->lock); cp->size = 0; - for (i = 0; i < NR_CPUS; i++) - cp->cpu_to_idx[i] = IDX_INVALID; - if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) + + cp->elements = kcalloc(nr_cpu_ids, + sizeof(struct cpudl_item), + GFP_KERNEL); + if (!cp->elements) + return -ENOMEM; + + if (!alloc_cpumask_var(&cp->free_cpus, GFP_KERNEL)) { + kfree(cp->elements); return -ENOMEM; + } + + for_each_possible_cpu(i) + cp->elements[i].idx = IDX_INVALID; + cpumask_setall(cp->free_cpus); return 0; @@ -210,7 +224,6 @@ int cpudl_init(struct cpudl *cp) */ void cpudl_cleanup(struct cpudl *cp) { - /* - * nothing to do for the moment - */ + free_cpumask_var(cp->free_cpus); + kfree(cp->elements); } diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h index a202789..538c979 100644 --- a/kernel/sched/cpudeadline.h +++ b/kernel/sched/cpudeadline.h @@ -5,17 +5,17 @@ #define IDX_INVALID -1 -struct array_item { +struct cpudl_item { u64 dl; int cpu; + int idx; }; struct cpudl { raw_spinlock_t lock; int size; - int cpu_to_idx[NR_CPUS]; - struct array_item elements[NR_CPUS]; cpumask_var_t free_cpus; + struct cpudl_item *elements; }; diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 746bc93..981fcd7 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -30,6 +30,7 @@ #include <linux/gfp.h> #include <linux/sched.h> #include <linux/sched/rt.h> +#include <linux/slab.h> #include "cpupri.h" /* Convert between a 140 based task->prio, and our 102 based cpupri */ @@ -70,8 +71,7 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, int idx = 0; int task_pri = convert_prio(p->prio); - if (task_pri >= MAX_RT_PRIO) - return 0; + BUG_ON(task_pri >= CPUPRI_NR_PRIORITIES); for (idx = 0; idx < task_pri; idx++) { struct cpupri_vec *vec = &cp->pri_to_cpu[idx]; @@ -219,8 +219,13 @@ int cpupri_init(struct cpupri *cp) goto cleanup; } + cp->cpu_to_pri = kcalloc(nr_cpu_ids, sizeof(int), GFP_KERNEL); + if (!cp->cpu_to_pri) + goto cleanup; + for_each_possible_cpu(i) cp->cpu_to_pri[i] = CPUPRI_INVALID; + return 0; cleanup: @@ -237,6 +242,7 @@ void cpupri_cleanup(struct cpupri *cp) { int i; + kfree(cp->cpu_to_pri); for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) free_cpumask_var(cp->pri_to_cpu[i].mask); } diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h index f6d7561..6b03334 100644 --- a/kernel/sched/cpupri.h +++ b/kernel/sched/cpupri.h @@ -17,7 +17,7 @@ struct cpupri_vec { struct cpupri { struct cpupri_vec pri_to_cpu[CPUPRI_NR_PRIORITIES]; - int cpu_to_pri[NR_CPUS]; + int *cpu_to_pri; }; #ifdef CONFIG_SMP diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index a95097c..72fdf06 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -332,50 +332,50 @@ out: * softirq as those do not count in task exec_runtime any more. */ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) + struct rq *rq, int ticks) { - cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + cputime_t scaled = cputime_to_scaled(cputime_one_jiffy); + u64 cputime = (__force u64) cputime_one_jiffy; u64 *cpustat = kcpustat_this_cpu->cpustat; if (steal_account_process_tick()) return; + cputime *= ticks; + scaled *= ticks; + if (irqtime_account_hi_update()) { - cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_IRQ] += cputime; } else if (irqtime_account_si_update()) { - cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy; + cpustat[CPUTIME_SOFTIRQ] += cputime; } else if (this_cpu_ksoftirqd() == p) { /* * ksoftirqd time do not get accounted in cpu_softirq_time. * So, we have to handle it separately here. * Also, p->stime needs to be updated for ksoftirqd. */ - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SOFTIRQ); + __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ); } else if (user_tick) { - account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_user_time(p, cputime, scaled); } else if (p == rq->idle) { - account_idle_time(cputime_one_jiffy); + account_idle_time(cputime); } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled); + account_guest_time(p, cputime, scaled); } else { - __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled, - CPUTIME_SYSTEM); + __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM); } } static void irqtime_account_idle_ticks(int ticks) { - int i; struct rq *rq = this_rq(); - for (i = 0; i < ticks; i++) - irqtime_account_process_tick(current, 0, rq); + irqtime_account_process_tick(current, 0, rq, ticks); } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ static inline void irqtime_account_idle_ticks(int ticks) {} static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick, - struct rq *rq) {} + struct rq *rq, int nr_ticks) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ /* @@ -464,7 +464,7 @@ void account_process_tick(struct task_struct *p, int user_tick) return; if (sched_clock_irqtime) { - irqtime_account_process_tick(p, user_tick, rq); + irqtime_account_process_tick(p, user_tick, rq, 1); return; } diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 27ef409..0d6b170 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -57,8 +57,6 @@ void init_dl_bandwidth(struct dl_bandwidth *dl_b, u64 period, u64 runtime) dl_b->dl_runtime = runtime; } -extern unsigned long to_ratio(u64 period, u64 runtime); - void init_dl_bw(struct dl_bw *dl_b) { raw_spin_lock_init(&dl_b->lock); @@ -520,7 +518,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * We need to take care of a possible races here. In fact, the * task might have changed its scheduling policy to something * different from SCHED_DEADLINE or changed its reservation - * parameters (through sched_setscheduler()). + * parameters (through sched_setattr()). */ if (!dl_task(p) || dl_se->dl_new) goto unlock; @@ -528,6 +526,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) sched_clock_tick(); update_rq_clock(rq); dl_se->dl_throttled = 0; + dl_se->dl_yielded = 0; if (p->on_rq) { enqueue_task_dl(rq, p, ENQUEUE_REPLENISH); if (task_has_dl_policy(rq->curr)) @@ -740,7 +739,7 @@ void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); dl_rq->dl_nr_running++; - inc_nr_running(rq_of_dl_rq(dl_rq)); + add_nr_running(rq_of_dl_rq(dl_rq), 1); inc_dl_deadline(dl_rq, deadline); inc_dl_migration(dl_se, dl_rq); @@ -754,7 +753,7 @@ void dec_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) WARN_ON(!dl_prio(prio)); WARN_ON(!dl_rq->dl_nr_running); dl_rq->dl_nr_running--; - dec_nr_running(rq_of_dl_rq(dl_rq)); + sub_nr_running(rq_of_dl_rq(dl_rq), 1); dec_dl_deadline(dl_rq, dl_se->deadline); dec_dl_migration(dl_se, dl_rq); @@ -893,10 +892,10 @@ static void yield_task_dl(struct rq *rq) * We make the task go to sleep until its current deadline by * forcing its runtime to zero. This way, update_curr_dl() stops * it and the bandwidth timer will wake it up and will give it - * new scheduling parameters (thanks to dl_new=1). + * new scheduling parameters (thanks to dl_yielded=1). */ if (p->dl.runtime > 0) { - rq->curr->dl.dl_new = 1; + rq->curr->dl.dl_yielded = 1; p->dl.runtime = 0; } update_curr_dl(rq); @@ -1021,8 +1020,17 @@ struct task_struct *pick_next_task_dl(struct rq *rq, struct task_struct *prev) dl_rq = &rq->dl; - if (need_pull_dl_task(rq, prev)) + if (need_pull_dl_task(rq, prev)) { pull_dl_task(rq); + /* + * pull_rt_task() can drop (and re-acquire) rq->lock; this + * means a stop task can slip in, in which case we need to + * re-start task selection. + */ + if (rq->stop && rq->stop->on_rq) + return RETRY_TASK; + } + /* * When prev is DL, we may throttle it in put_prev_task(). * So, we update time before we check for dl_nr_running. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7e9bd0b..d3c73122 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1017,7 +1017,7 @@ bool should_numa_migrate_memory(struct task_struct *p, struct page * page, static unsigned long weighted_cpuload(const int cpu); static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); -static unsigned long power_of(int cpu); +static unsigned long capacity_of(int cpu); static long effective_load(struct task_group *tg, int cpu, long wl, long wg); /* Cached statistics for all CPUs within a node */ @@ -1026,11 +1026,11 @@ struct numa_stats { unsigned long load; /* Total compute capacity of CPUs on a node */ - unsigned long power; + unsigned long compute_capacity; /* Approximate capacity in terms of runnable tasks on a node */ - unsigned long capacity; - int has_capacity; + unsigned long task_capacity; + int has_free_capacity; }; /* @@ -1046,7 +1046,7 @@ static void update_numa_stats(struct numa_stats *ns, int nid) ns->nr_running += rq->nr_running; ns->load += weighted_cpuload(cpu); - ns->power += power_of(cpu); + ns->compute_capacity += capacity_of(cpu); cpus++; } @@ -1056,15 +1056,16 @@ static void update_numa_stats(struct numa_stats *ns, int nid) * the @ns structure is NULL'ed and task_numa_compare() will * not find this node attractive. * - * We'll either bail at !has_capacity, or we'll detect a huge imbalance - * and bail there. + * We'll either bail at !has_free_capacity, or we'll detect a huge + * imbalance and bail there. */ if (!cpus) return; - ns->load = (ns->load * SCHED_POWER_SCALE) / ns->power; - ns->capacity = DIV_ROUND_CLOSEST(ns->power, SCHED_POWER_SCALE); - ns->has_capacity = (ns->nr_running < ns->capacity); + ns->load = (ns->load * SCHED_CAPACITY_SCALE) / ns->compute_capacity; + ns->task_capacity = + DIV_ROUND_CLOSEST(ns->compute_capacity, SCHED_CAPACITY_SCALE); + ns->has_free_capacity = (ns->nr_running < ns->task_capacity); } struct task_numa_env { @@ -1095,6 +1096,34 @@ static void task_numa_assign(struct task_numa_env *env, env->best_cpu = env->dst_cpu; } +static bool load_too_imbalanced(long orig_src_load, long orig_dst_load, + long src_load, long dst_load, + struct task_numa_env *env) +{ + long imb, old_imb; + + /* We care about the slope of the imbalance, not the direction. */ + if (dst_load < src_load) + swap(dst_load, src_load); + + /* Is the difference below the threshold? */ + imb = dst_load * 100 - src_load * env->imbalance_pct; + if (imb <= 0) + return false; + + /* + * The imbalance is above the allowed threshold. + * Compare it with the old imbalance. + */ + if (orig_dst_load < orig_src_load) + swap(orig_dst_load, orig_src_load); + + old_imb = orig_dst_load * 100 - orig_src_load * env->imbalance_pct; + + /* Would this change make things worse? */ + return (old_imb > imb); +} + /* * This checks if the overall compute and NUMA accesses of the system would * be improved if the source tasks was migrated to the target dst_cpu taking @@ -1107,7 +1136,8 @@ static void task_numa_compare(struct task_numa_env *env, struct rq *src_rq = cpu_rq(env->src_cpu); struct rq *dst_rq = cpu_rq(env->dst_cpu); struct task_struct *cur; - long dst_load, src_load; + long orig_src_load, src_load; + long orig_dst_load, dst_load; long load; long imp = (groupimp > 0) ? groupimp : taskimp; @@ -1166,8 +1196,8 @@ static void task_numa_compare(struct task_numa_env *env, if (!cur) { /* Is there capacity at our destination? */ - if (env->src_stats.has_capacity && - !env->dst_stats.has_capacity) + if (env->src_stats.has_free_capacity && + !env->dst_stats.has_free_capacity) goto unlock; goto balance; @@ -1181,13 +1211,13 @@ static void task_numa_compare(struct task_numa_env *env, * In the overloaded case, try and keep the load balanced. */ balance: - dst_load = env->dst_stats.load; - src_load = env->src_stats.load; + orig_dst_load = env->dst_stats.load; + orig_src_load = env->src_stats.load; - /* XXX missing power terms */ + /* XXX missing capacity terms */ load = task_h_load(env->p); - dst_load += load; - src_load -= load; + dst_load = orig_dst_load + load; + src_load = orig_src_load - load; if (cur) { load = task_h_load(cur); @@ -1195,11 +1225,8 @@ balance: src_load += load; } - /* make src_load the smaller */ - if (dst_load < src_load) - swap(dst_load, src_load); - - if (src_load * env->imbalance_pct < dst_load * 100) + if (load_too_imbalanced(orig_src_load, orig_dst_load, + src_load, dst_load, env)) goto unlock; assign: @@ -1275,8 +1302,8 @@ static int task_numa_migrate(struct task_struct *p) groupimp = group_weight(p, env.dst_nid) - groupweight; update_numa_stats(&env.dst_stats, env.dst_nid); - /* If the preferred nid has capacity, try to use it. */ - if (env.dst_stats.has_capacity) + /* If the preferred nid has free capacity, try to use it. */ + if (env.dst_stats.has_free_capacity) task_numa_find_cpu(&env, taskimp, groupimp); /* No space available on the preferred nid. Look elsewhere. */ @@ -1301,7 +1328,16 @@ static int task_numa_migrate(struct task_struct *p) if (env.best_cpu == -1) return -EAGAIN; - sched_setnuma(p, env.dst_nid); + /* + * If the task is part of a workload that spans multiple NUMA nodes, + * and is migrating into one of the workload's active nodes, remember + * this node as the task's preferred numa node, so the workload can + * settle down. + * A task that migrated to a second choice node will be better off + * trying for a better one later. Do not set the preferred node here. + */ + if (p->numa_group && node_isset(env.dst_nid, p->numa_group->active_nodes)) + sched_setnuma(p, env.dst_nid); /* * Reset the scan period if the task is being rescheduled on an @@ -1326,12 +1362,15 @@ static int task_numa_migrate(struct task_struct *p) /* Attempt to migrate a task to a CPU on the preferred node. */ static void numa_migrate_preferred(struct task_struct *p) { + unsigned long interval = HZ; + /* This task has no NUMA fault statistics yet */ if (unlikely(p->numa_preferred_nid == -1 || !p->numa_faults_memory)) return; /* Periodically retry migrating the task to the preferred node */ - p->numa_migrate_retry = jiffies + HZ; + interval = min(interval, msecs_to_jiffies(p->numa_scan_period) / 16); + p->numa_migrate_retry = jiffies + interval; /* Success if task is already running on preferred CPU */ if (task_node(p) == p->numa_preferred_nid) @@ -1497,7 +1536,7 @@ static void task_numa_placement(struct task_struct *p) /* If the task is part of a group prevent parallel updates to group stats */ if (p->numa_group) { group_lock = &p->numa_group->lock; - spin_lock(group_lock); + spin_lock_irq(group_lock); } /* Find the node with the highest number of faults */ @@ -1572,7 +1611,7 @@ static void task_numa_placement(struct task_struct *p) } } - spin_unlock(group_lock); + spin_unlock_irq(group_lock); } /* Preferred node as the node with the most faults */ @@ -1677,7 +1716,8 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, if (!join) return; - double_lock(&my_grp->lock, &grp->lock); + BUG_ON(irqs_disabled()); + double_lock_irq(&my_grp->lock, &grp->lock); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) { my_grp->faults[i] -= p->numa_faults_memory[i]; @@ -1691,7 +1731,7 @@ static void task_numa_group(struct task_struct *p, int cpupid, int flags, grp->nr_tasks++; spin_unlock(&my_grp->lock); - spin_unlock(&grp->lock); + spin_unlock_irq(&grp->lock); rcu_assign_pointer(p->numa_group, grp); @@ -1710,14 +1750,14 @@ void task_numa_free(struct task_struct *p) void *numa_faults = p->numa_faults_memory; if (grp) { - spin_lock(&grp->lock); + spin_lock_irq(&grp->lock); for (i = 0; i < NR_NUMA_HINT_FAULT_STATS * nr_node_ids; i++) grp->faults[i] -= p->numa_faults_memory[i]; grp->total_faults -= p->total_numa_faults; list_del(&p->numa_entry); grp->nr_tasks--; - spin_unlock(&grp->lock); + spin_unlock_irq(&grp->lock); rcu_assign_pointer(p->numa_group, NULL); put_numa_group(grp); } @@ -1737,6 +1777,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) struct task_struct *p = current; bool migrated = flags & TNF_MIGRATED; int cpu_node = task_node(current); + int local = !!(flags & TNF_FAULT_LOCAL); int priv; if (!numabalancing_enabled) @@ -1785,6 +1826,17 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) task_numa_group(p, last_cpupid, flags, &priv); } + /* + * If a workload spans multiple NUMA nodes, a shared fault that + * occurs wholly within the set of nodes that the workload is + * actively using should be counted as local. This allows the + * scan rate to slow down when a workload has settled down. + */ + if (!priv && !local && p->numa_group && + node_isset(cpu_node, p->numa_group->active_nodes) && + node_isset(mem_node, p->numa_group->active_nodes)) + local = 1; + task_numa_placement(p); /* @@ -1799,7 +1851,7 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) p->numa_faults_buffer_memory[task_faults_idx(mem_node, priv)] += pages; p->numa_faults_buffer_cpu[task_faults_idx(cpu_node, priv)] += pages; - p->numa_faults_locality[!!(flags & TNF_FAULT_LOCAL)] += pages; + p->numa_faults_locality[local] += pages; } static void reset_ptenuma_scan(struct task_struct *p) @@ -3173,10 +3225,12 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq) * has not truly expired. * * Fortunately we can check determine whether this the case by checking - * whether the global deadline has advanced. + * whether the global deadline has advanced. It is valid to compare + * cfs_b->runtime_expires without any locks since we only care about + * exact equality, so a partial write will still work. */ - if ((s64)(cfs_rq->runtime_expires - cfs_b->runtime_expires) >= 0) { + if (cfs_rq->runtime_expires != cfs_b->runtime_expires) { /* extend local deadline, drift is bounded above by 2 ticks */ cfs_rq->runtime_expires += TICK_NSEC; } else { @@ -3300,7 +3354,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq) } if (!se) - rq->nr_running -= task_delta; + sub_nr_running(rq, task_delta); cfs_rq->throttled = 1; cfs_rq->throttled_clock = rq_clock(rq); @@ -3351,7 +3405,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq) } if (!se) - rq->nr_running += task_delta; + add_nr_running(rq, task_delta); /* determine whether we need to wake up potentially idle cpu */ if (rq->curr == rq->idle && rq->cfs.nr_running) @@ -3405,21 +3459,21 @@ next: static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) { u64 runtime, runtime_expires; - int idle = 1, throttled; + int throttled; - raw_spin_lock(&cfs_b->lock); /* no need to continue the timer with no bandwidth constraint */ if (cfs_b->quota == RUNTIME_INF) - goto out_unlock; + goto out_deactivate; throttled = !list_empty(&cfs_b->throttled_cfs_rq); - /* idle depends on !throttled (for the case of a large deficit) */ - idle = cfs_b->idle && !throttled; cfs_b->nr_periods += overrun; - /* if we're going inactive then everything else can be deferred */ - if (idle) - goto out_unlock; + /* + * idle depends on !throttled (for the case of a large deficit), and if + * we're going inactive then everything else can be deferred + */ + if (cfs_b->idle && !throttled) + goto out_deactivate; /* * if we have relooped after returning idle once, we need to update our @@ -3433,7 +3487,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) if (!throttled) { /* mark as potentially idle for the upcoming period */ cfs_b->idle = 1; - goto out_unlock; + return 0; } /* account preceding periods in which throttling occurred */ @@ -3473,12 +3527,12 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun) * timer to remain active while there are any throttled entities.) */ cfs_b->idle = 0; -out_unlock: - if (idle) - cfs_b->timer_active = 0; - raw_spin_unlock(&cfs_b->lock); - return idle; + return 0; + +out_deactivate: + cfs_b->timer_active = 0; + return 1; } /* a cfs_rq won't donate quota below this amount */ @@ -3655,6 +3709,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) int overrun; int idle = 0; + raw_spin_lock(&cfs_b->lock); for (;;) { now = hrtimer_cb_get_time(timer); overrun = hrtimer_forward(timer, now, cfs_b->period); @@ -3664,6 +3719,7 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer) idle = do_sched_cfs_period_timer(cfs_b, overrun); } + raw_spin_unlock(&cfs_b->lock); return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; } @@ -3723,8 +3779,6 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) struct cfs_rq *cfs_rq; for_each_leaf_cfs_rq(rq, cfs_rq) { - struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg); - if (!cfs_rq->runtime_enabled) continue; @@ -3732,7 +3786,7 @@ static void __maybe_unused unthrottle_offline_cfs_rqs(struct rq *rq) * clock_task is not advancing so we just need to make sure * there's some valid quota amount */ - cfs_rq->runtime_remaining = cfs_b->quota; + cfs_rq->runtime_remaining = 1; if (cfs_rq_throttled(cfs_rq)) unthrottle_cfs_rq(cfs_rq); } @@ -3883,7 +3937,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (!se) { update_rq_runnable_avg(rq, rq->nr_running); - inc_nr_running(rq); + add_nr_running(rq, 1); } hrtick_update(rq); } @@ -3943,7 +3997,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) } if (!se) { - dec_nr_running(rq); + sub_nr_running(rq, 1); update_rq_runnable_avg(rq, 1); } hrtick_update(rq); @@ -3989,9 +4043,9 @@ static unsigned long target_load(int cpu, int type) return max(rq->cpu_load[type-1], total); } -static unsigned long power_of(int cpu) +static unsigned long capacity_of(int cpu) { - return cpu_rq(cpu)->cpu_power; + return cpu_rq(cpu)->cpu_capacity; } static unsigned long cpu_avg_load_per_task(int cpu) @@ -4013,8 +4067,8 @@ static void record_wakee(struct task_struct *p) * about the boundary, really active task won't care * about the loss. */ - if (jiffies > current->wakee_flip_decay_ts + HZ) { - current->wakee_flips = 0; + if (time_after(jiffies, current->wakee_flip_decay_ts + HZ)) { + current->wakee_flips >>= 1; current->wakee_flip_decay_ts = jiffies; } @@ -4234,12 +4288,12 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync) s64 this_eff_load, prev_eff_load; this_eff_load = 100; - this_eff_load *= power_of(prev_cpu); + this_eff_load *= capacity_of(prev_cpu); this_eff_load *= this_load + effective_load(tg, this_cpu, weight, weight); prev_eff_load = 100 + (sd->imbalance_pct - 100) / 2; - prev_eff_load *= power_of(this_cpu); + prev_eff_load *= capacity_of(this_cpu); prev_eff_load *= load + effective_load(tg, prev_cpu, 0, weight); balanced = this_eff_load <= prev_eff_load; @@ -4315,8 +4369,8 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, avg_load += load; } - /* Adjust by relative CPU power of the group */ - avg_load = (avg_load * SCHED_POWER_SCALE) / group->sgp->power; + /* Adjust by relative CPU capacity of the group */ + avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity; if (local_group) { this_load = avg_load; @@ -4448,10 +4502,10 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f sd = tmp; } - if (affine_sd) { - if (cpu != prev_cpu && wake_affine(affine_sd, p, sync)) - prev_cpu = cpu; + if (affine_sd && cpu != prev_cpu && wake_affine(affine_sd, p, sync)) + prev_cpu = cpu; + if (sd_flag & SD_BALANCE_WAKE) { new_cpu = select_idle_sibling(p, prev_cpu); goto unlock; } @@ -4519,6 +4573,9 @@ migrate_task_rq_fair(struct task_struct *p, int next_cpu) atomic_long_add(se->avg.load_avg_contrib, &cfs_rq->removed_load); } + + /* We have migrated, no longer consider this task hot */ + se->exec_start = 0; } #endif /* CONFIG_SMP */ @@ -4893,14 +4950,14 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p, bool preemp * * W'_i,n = (2^n - 1) / 2^n * W_i,n + 1 / 2^n * W_i,0 (3) * - * P_i is the cpu power (or compute capacity) of cpu i, typically it is the + * C_i is the compute capacity of cpu i, typically it is the * fraction of 'recent' time available for SCHED_OTHER task execution. But it * can also include other factors [XXX]. * * To achieve this balance we define a measure of imbalance which follows * directly from (1): * - * imb_i,j = max{ avg(W/P), W_i/P_i } - min{ avg(W/P), W_j/P_j } (4) + * imb_i,j = max{ avg(W/C), W_i/C_i } - min{ avg(W/C), W_j/C_j } (4) * * We them move tasks around to minimize the imbalance. In the continuous * function space it is obvious this converges, in the discrete case we get @@ -5069,6 +5126,7 @@ task_hot(struct task_struct *p, u64 now) /* Returns true if the destination node has incurred more faults */ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) { + struct numa_group *numa_group = rcu_dereference(p->numa_group); int src_nid, dst_nid; if (!sched_feat(NUMA_FAVOUR_HIGHER) || !p->numa_faults_memory || @@ -5082,21 +5140,29 @@ static bool migrate_improves_locality(struct task_struct *p, struct lb_env *env) if (src_nid == dst_nid) return false; - /* Always encourage migration to the preferred node. */ - if (dst_nid == p->numa_preferred_nid) - return true; + if (numa_group) { + /* Task is already in the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return false; + + /* Task is moving into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return true; - /* If both task and group weight improve, this move is a winner. */ - if (task_weight(p, dst_nid) > task_weight(p, src_nid) && - group_weight(p, dst_nid) > group_weight(p, src_nid)) + return group_faults(p, dst_nid) > group_faults(p, src_nid); + } + + /* Encourage migration to the preferred node. */ + if (dst_nid == p->numa_preferred_nid) return true; - return false; + return task_faults(p, dst_nid) > task_faults(p, src_nid); } static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) { + struct numa_group *numa_group = rcu_dereference(p->numa_group); int src_nid, dst_nid; if (!sched_feat(NUMA) || !sched_feat(NUMA_RESIST_LOWER)) @@ -5111,16 +5177,23 @@ static bool migrate_degrades_locality(struct task_struct *p, struct lb_env *env) if (src_nid == dst_nid) return false; + if (numa_group) { + /* Task is moving within/into the group's interleave set. */ + if (node_isset(dst_nid, numa_group->active_nodes)) + return false; + + /* Task is moving out of the group's interleave set. */ + if (node_isset(src_nid, numa_group->active_nodes)) + return true; + + return group_faults(p, dst_nid) < group_faults(p, src_nid); + } + /* Migrating away from the preferred node is always bad. */ if (src_nid == p->numa_preferred_nid) return true; - /* If either task or group weight get worse, don't do it. */ - if (task_weight(p, dst_nid) < task_weight(p, src_nid) || - group_weight(p, dst_nid) < group_weight(p, src_nid)) - return true; - - return false; + return task_faults(p, dst_nid) < task_faults(p, src_nid); } #else @@ -5459,13 +5532,13 @@ struct sg_lb_stats { unsigned long group_load; /* Total load over the CPUs of the group */ unsigned long sum_weighted_load; /* Weighted load of group's tasks */ unsigned long load_per_task; - unsigned long group_power; + unsigned long group_capacity; unsigned int sum_nr_running; /* Nr tasks running in the group */ - unsigned int group_capacity; + unsigned int group_capacity_factor; unsigned int idle_cpus; unsigned int group_weight; int group_imb; /* Is there an imbalance in the group ? */ - int group_has_capacity; /* Is there extra capacity in the group? */ + int group_has_free_capacity; #ifdef CONFIG_NUMA_BALANCING unsigned int nr_numa_running; unsigned int nr_preferred_running; @@ -5480,7 +5553,7 @@ struct sd_lb_stats { struct sched_group *busiest; /* Busiest group in this sd */ struct sched_group *local; /* Local group in this sd */ unsigned long total_load; /* Total load of all groups in sd */ - unsigned long total_pwr; /* Total power of all groups in sd */ + unsigned long total_capacity; /* Total capacity of all groups in sd */ unsigned long avg_load; /* Average load across all groups in sd */ struct sg_lb_stats busiest_stat;/* Statistics of the busiest group */ @@ -5499,7 +5572,7 @@ static inline void init_sd_lb_stats(struct sd_lb_stats *sds) .busiest = NULL, .local = NULL, .total_load = 0UL, - .total_pwr = 0UL, + .total_capacity = 0UL, .busiest_stat = { .avg_load = 0UL, }, @@ -5534,17 +5607,17 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_capacity(struct sched_domain *sd, int cpu) { - return SCHED_POWER_SCALE; + return SCHED_CAPACITY_SCALE; } -unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) +unsigned long __weak arch_scale_freq_capacity(struct sched_domain *sd, int cpu) { - return default_scale_freq_power(sd, cpu); + return default_scale_capacity(sd, cpu); } -static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_smt_capacity(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; unsigned long smt_gain = sd->smt_gain; @@ -5554,15 +5627,16 @@ static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) return smt_gain; } -unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) +unsigned long __weak arch_scale_smt_capacity(struct sched_domain *sd, int cpu) { - return default_scale_smt_power(sd, cpu); + return default_scale_smt_capacity(sd, cpu); } -static unsigned long scale_rt_power(int cpu) +static unsigned long scale_rt_capacity(int cpu) { struct rq *rq = cpu_rq(cpu); u64 total, available, age_stamp, avg; + s64 delta; /* * Since we're reading these variables without serialization make sure @@ -5571,74 +5645,78 @@ static unsigned long scale_rt_power(int cpu) age_stamp = ACCESS_ONCE(rq->age_stamp); avg = ACCESS_ONCE(rq->rt_avg); - total = sched_avg_period() + (rq_clock(rq) - age_stamp); + delta = rq_clock(rq) - age_stamp; + if (unlikely(delta < 0)) + delta = 0; + + total = sched_avg_period() + delta; if (unlikely(total < avg)) { - /* Ensures that power won't end up being negative */ + /* Ensures that capacity won't end up being negative */ available = 0; } else { available = total - avg; } - if (unlikely((s64)total < SCHED_POWER_SCALE)) - total = SCHED_POWER_SCALE; + if (unlikely((s64)total < SCHED_CAPACITY_SCALE)) + total = SCHED_CAPACITY_SCALE; - total >>= SCHED_POWER_SHIFT; + total >>= SCHED_CAPACITY_SHIFT; return div_u64(available, total); } -static void update_cpu_power(struct sched_domain *sd, int cpu) +static void update_cpu_capacity(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; - unsigned long power = SCHED_POWER_SCALE; + unsigned long capacity = SCHED_CAPACITY_SCALE; struct sched_group *sdg = sd->groups; - if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { - if (sched_feat(ARCH_POWER)) - power *= arch_scale_smt_power(sd, cpu); + if ((sd->flags & SD_SHARE_CPUCAPACITY) && weight > 1) { + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_smt_capacity(sd, cpu); else - power *= default_scale_smt_power(sd, cpu); + capacity *= default_scale_smt_capacity(sd, cpu); - power >>= SCHED_POWER_SHIFT; + capacity >>= SCHED_CAPACITY_SHIFT; } - sdg->sgp->power_orig = power; + sdg->sgc->capacity_orig = capacity; - if (sched_feat(ARCH_POWER)) - power *= arch_scale_freq_power(sd, cpu); + if (sched_feat(ARCH_CAPACITY)) + capacity *= arch_scale_freq_capacity(sd, cpu); else - power *= default_scale_freq_power(sd, cpu); + capacity *= default_scale_capacity(sd, cpu); - power >>= SCHED_POWER_SHIFT; + capacity >>= SCHED_CAPACITY_SHIFT; - power *= scale_rt_power(cpu); - power >>= SCHED_POWER_SHIFT; + capacity *= scale_rt_capacity(cpu); + capacity >>= SCHED_CAPACITY_SHIFT; - if (!power) - power = 1; + if (!capacity) + capacity = 1; - cpu_rq(cpu)->cpu_power = power; - sdg->sgp->power = power; + cpu_rq(cpu)->cpu_capacity = capacity; + sdg->sgc->capacity = capacity; } -void update_group_power(struct sched_domain *sd, int cpu) +void update_group_capacity(struct sched_domain *sd, int cpu) { struct sched_domain *child = sd->child; struct sched_group *group, *sdg = sd->groups; - unsigned long power, power_orig; + unsigned long capacity, capacity_orig; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); interval = clamp(interval, 1UL, max_load_balance_interval); - sdg->sgp->next_update = jiffies + interval; + sdg->sgc->next_update = jiffies + interval; if (!child) { - update_cpu_power(sd, cpu); + update_cpu_capacity(sd, cpu); return; } - power_orig = power = 0; + capacity_orig = capacity = 0; if (child->flags & SD_OVERLAP) { /* @@ -5647,31 +5725,31 @@ void update_group_power(struct sched_domain *sd, int cpu) */ for_each_cpu(cpu, sched_group_cpus(sdg)) { - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; struct rq *rq = cpu_rq(cpu); /* - * build_sched_domains() -> init_sched_groups_power() + * build_sched_domains() -> init_sched_groups_capacity() * gets here before we've attached the domains to the * runqueues. * - * Use power_of(), which is set irrespective of domains - * in update_cpu_power(). + * Use capacity_of(), which is set irrespective of domains + * in update_cpu_capacity(). * - * This avoids power/power_orig from being 0 and + * This avoids capacity/capacity_orig from being 0 and * causing divide-by-zero issues on boot. * - * Runtime updates will correct power_orig. + * Runtime updates will correct capacity_orig. */ if (unlikely(!rq->sd)) { - power_orig += power_of(cpu); - power += power_of(cpu); + capacity_orig += capacity_of(cpu); + capacity += capacity_of(cpu); continue; } - sgp = rq->sd->groups->sgp; - power_orig += sgp->power_orig; - power += sgp->power; + sgc = rq->sd->groups->sgc; + capacity_orig += sgc->capacity_orig; + capacity += sgc->capacity; } } else { /* @@ -5681,14 +5759,14 @@ void update_group_power(struct sched_domain *sd, int cpu) group = child->groups; do { - power_orig += group->sgp->power_orig; - power += group->sgp->power; + capacity_orig += group->sgc->capacity_orig; + capacity += group->sgc->capacity; group = group->next; } while (group != child->groups); } - sdg->sgp->power_orig = power_orig; - sdg->sgp->power = power; + sdg->sgc->capacity_orig = capacity_orig; + sdg->sgc->capacity = capacity; } /* @@ -5702,15 +5780,15 @@ static inline int fix_small_capacity(struct sched_domain *sd, struct sched_group *group) { /* - * Only siblings can have significantly less than SCHED_POWER_SCALE + * Only siblings can have significantly less than SCHED_CAPACITY_SCALE */ - if (!(sd->flags & SD_SHARE_CPUPOWER)) + if (!(sd->flags & SD_SHARE_CPUCAPACITY)) return 0; /* - * If ~90% of the cpu_power is still there, we're good. + * If ~90% of the cpu_capacity is still there, we're good. */ - if (group->sgp->power * 32 > group->sgp->power_orig * 29) + if (group->sgc->capacity * 32 > group->sgc->capacity_orig * 29) return 1; return 0; @@ -5747,34 +5825,35 @@ fix_small_capacity(struct sched_domain *sd, struct sched_group *group) static inline int sg_imbalanced(struct sched_group *group) { - return group->sgp->imbalance; + return group->sgc->imbalance; } /* - * Compute the group capacity. + * Compute the group capacity factor. * - * Avoid the issue where N*frac(smt_power) >= 1 creates 'phantom' cores by + * Avoid the issue where N*frac(smt_capacity) >= 1 creates 'phantom' cores by * first dividing out the smt factor and computing the actual number of cores - * and limit power unit capacity with that. + * and limit unit capacity with that. */ -static inline int sg_capacity(struct lb_env *env, struct sched_group *group) +static inline int sg_capacity_factor(struct lb_env *env, struct sched_group *group) { - unsigned int capacity, smt, cpus; - unsigned int power, power_orig; + unsigned int capacity_factor, smt, cpus; + unsigned int capacity, capacity_orig; - power = group->sgp->power; - power_orig = group->sgp->power_orig; + capacity = group->sgc->capacity; + capacity_orig = group->sgc->capacity_orig; cpus = group->group_weight; - /* smt := ceil(cpus / power), assumes: 1 < smt_power < 2 */ - smt = DIV_ROUND_UP(SCHED_POWER_SCALE * cpus, power_orig); - capacity = cpus / smt; /* cores */ + /* smt := ceil(cpus / capacity), assumes: 1 < smt_capacity < 2 */ + smt = DIV_ROUND_UP(SCHED_CAPACITY_SCALE * cpus, capacity_orig); + capacity_factor = cpus / smt; /* cores */ - capacity = min_t(unsigned, capacity, DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE)); - if (!capacity) - capacity = fix_small_capacity(env->sd, group); + capacity_factor = min_t(unsigned, + capacity_factor, DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE)); + if (!capacity_factor) + capacity_factor = fix_small_capacity(env->sd, group); - return capacity; + return capacity_factor; } /** @@ -5814,9 +5893,9 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->idle_cpus++; } - /* Adjust by relative CPU power of the group */ - sgs->group_power = group->sgp->power; - sgs->avg_load = (sgs->group_load*SCHED_POWER_SCALE) / sgs->group_power; + /* Adjust by relative CPU capacity of the group */ + sgs->group_capacity = group->sgc->capacity; + sgs->avg_load = (sgs->group_load*SCHED_CAPACITY_SCALE) / sgs->group_capacity; if (sgs->sum_nr_running) sgs->load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running; @@ -5824,10 +5903,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_weight = group->group_weight; sgs->group_imb = sg_imbalanced(group); - sgs->group_capacity = sg_capacity(env, group); + sgs->group_capacity_factor = sg_capacity_factor(env, group); - if (sgs->group_capacity > sgs->sum_nr_running) - sgs->group_has_capacity = 1; + if (sgs->group_capacity_factor > sgs->sum_nr_running) + sgs->group_has_free_capacity = 1; } /** @@ -5851,7 +5930,7 @@ static bool update_sd_pick_busiest(struct lb_env *env, if (sgs->avg_load <= sds->busiest_stat.avg_load) return false; - if (sgs->sum_nr_running > sgs->group_capacity) + if (sgs->sum_nr_running > sgs->group_capacity_factor) return true; if (sgs->group_imb) @@ -5931,8 +6010,8 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd sgs = &sds->local_stat; if (env->idle != CPU_NEWLY_IDLE || - time_after_eq(jiffies, sg->sgp->next_update)) - update_group_power(env->sd, env->dst_cpu); + time_after_eq(jiffies, sg->sgc->next_update)) + update_group_capacity(env->sd, env->dst_cpu); } update_sg_lb_stats(env, sg, load_idx, local_group, sgs); @@ -5942,17 +6021,17 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd /* * In case the child domain prefers tasks go to siblings - * first, lower the sg capacity to one so that we'll try + * first, lower the sg capacity factor to one so that we'll try * and move all the excess tasks away. We lower the capacity * of a group only if the local group has the capacity to fit - * these excess tasks, i.e. nr_running < group_capacity. The + * these excess tasks, i.e. nr_running < group_capacity_factor. The * extra check prevents the case where you always pull from the * heaviest group when it is already under-utilized (possible * with a large weight task outweighs the tasks on the system). */ if (prefer_sibling && sds->local && - sds->local_stat.group_has_capacity) - sgs->group_capacity = min(sgs->group_capacity, 1U); + sds->local_stat.group_has_free_capacity) + sgs->group_capacity_factor = min(sgs->group_capacity_factor, 1U); if (update_sd_pick_busiest(env, sds, sg, sgs)) { sds->busiest = sg; @@ -5962,7 +6041,7 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd next_group: /* Now, start updating sd_lb_stats */ sds->total_load += sgs->group_load; - sds->total_pwr += sgs->group_power; + sds->total_capacity += sgs->group_capacity; sg = sg->next; } while (sg != env->sd->groups); @@ -6009,8 +6088,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) return 0; env->imbalance = DIV_ROUND_CLOSEST( - sds->busiest_stat.avg_load * sds->busiest_stat.group_power, - SCHED_POWER_SCALE); + sds->busiest_stat.avg_load * sds->busiest_stat.group_capacity, + SCHED_CAPACITY_SCALE); return 1; } @@ -6025,7 +6104,7 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) static inline void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) { - unsigned long tmp, pwr_now = 0, pwr_move = 0; + unsigned long tmp, capa_now = 0, capa_move = 0; unsigned int imbn = 2; unsigned long scaled_busy_load_per_task; struct sg_lb_stats *local, *busiest; @@ -6039,8 +6118,8 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) imbn = 1; scaled_busy_load_per_task = - (busiest->load_per_task * SCHED_POWER_SCALE) / - busiest->group_power; + (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + busiest->group_capacity; if (busiest->avg_load + scaled_busy_load_per_task >= local->avg_load + (scaled_busy_load_per_task * imbn)) { @@ -6050,38 +6129,38 @@ void fix_small_imbalance(struct lb_env *env, struct sd_lb_stats *sds) /* * OK, we don't have enough imbalance to justify moving tasks, - * however we may be able to increase total CPU power used by + * however we may be able to increase total CPU capacity used by * moving them. */ - pwr_now += busiest->group_power * + capa_now += busiest->group_capacity * min(busiest->load_per_task, busiest->avg_load); - pwr_now += local->group_power * + capa_now += local->group_capacity * min(local->load_per_task, local->avg_load); - pwr_now /= SCHED_POWER_SCALE; + capa_now /= SCHED_CAPACITY_SCALE; /* Amount of load we'd subtract */ if (busiest->avg_load > scaled_busy_load_per_task) { - pwr_move += busiest->group_power * + capa_move += busiest->group_capacity * min(busiest->load_per_task, busiest->avg_load - scaled_busy_load_per_task); } /* Amount of load we'd add */ - if (busiest->avg_load * busiest->group_power < - busiest->load_per_task * SCHED_POWER_SCALE) { - tmp = (busiest->avg_load * busiest->group_power) / - local->group_power; + if (busiest->avg_load * busiest->group_capacity < + busiest->load_per_task * SCHED_CAPACITY_SCALE) { + tmp = (busiest->avg_load * busiest->group_capacity) / + local->group_capacity; } else { - tmp = (busiest->load_per_task * SCHED_POWER_SCALE) / - local->group_power; + tmp = (busiest->load_per_task * SCHED_CAPACITY_SCALE) / + local->group_capacity; } - pwr_move += local->group_power * + capa_move += local->group_capacity * min(local->load_per_task, local->avg_load + tmp); - pwr_move /= SCHED_POWER_SCALE; + capa_move /= SCHED_CAPACITY_SCALE; /* Move if we gain throughput */ - if (pwr_move > pwr_now) + if (capa_move > capa_now) env->imbalance = busiest->load_per_task; } @@ -6111,7 +6190,7 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* * In the presence of smp nice balancing, certain scenarios can have * max load less than avg load(as we skip the groups at or below - * its cpu_power, while calculating max_load..) + * its cpu_capacity, while calculating max_load..) */ if (busiest->avg_load <= sds->avg_load || local->avg_load >= sds->avg_load) { @@ -6126,10 +6205,10 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s * have to drop below capacity to reach cpu-load equilibrium. */ load_above_capacity = - (busiest->sum_nr_running - busiest->group_capacity); + (busiest->sum_nr_running - busiest->group_capacity_factor); - load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_POWER_SCALE); - load_above_capacity /= busiest->group_power; + load_above_capacity *= (SCHED_LOAD_SCALE * SCHED_CAPACITY_SCALE); + load_above_capacity /= busiest->group_capacity; } /* @@ -6144,9 +6223,9 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s /* How much load to actually move to equalise the imbalance */ env->imbalance = min( - max_pull * busiest->group_power, - (sds->avg_load - local->avg_load) * local->group_power - ) / SCHED_POWER_SCALE; + max_pull * busiest->group_capacity, + (sds->avg_load - local->avg_load) * local->group_capacity + ) / SCHED_CAPACITY_SCALE; /* * if *imbalance is less than the average load per runnable task @@ -6200,7 +6279,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) if (!sds.busiest || busiest->sum_nr_running == 0) goto out_balanced; - sds.avg_load = (SCHED_POWER_SCALE * sds.total_load) / sds.total_pwr; + sds.avg_load = (SCHED_CAPACITY_SCALE * sds.total_load) + / sds.total_capacity; /* * If the busiest group is imbalanced the below checks don't @@ -6211,8 +6291,8 @@ static struct sched_group *find_busiest_group(struct lb_env *env) goto force_balance; /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */ - if (env->idle == CPU_NEWLY_IDLE && local->group_has_capacity && - !busiest->group_has_capacity) + if (env->idle == CPU_NEWLY_IDLE && local->group_has_free_capacity && + !busiest->group_has_free_capacity) goto force_balance; /* @@ -6266,11 +6346,11 @@ static struct rq *find_busiest_queue(struct lb_env *env, struct sched_group *group) { struct rq *busiest = NULL, *rq; - unsigned long busiest_load = 0, busiest_power = 1; + unsigned long busiest_load = 0, busiest_capacity = 1; int i; for_each_cpu_and(i, sched_group_cpus(group), env->cpus) { - unsigned long power, capacity, wl; + unsigned long capacity, capacity_factor, wl; enum fbq_type rt; rq = cpu_rq(i); @@ -6298,34 +6378,34 @@ static struct rq *find_busiest_queue(struct lb_env *env, if (rt > env->fbq_type) continue; - power = power_of(i); - capacity = DIV_ROUND_CLOSEST(power, SCHED_POWER_SCALE); - if (!capacity) - capacity = fix_small_capacity(env->sd, group); + capacity = capacity_of(i); + capacity_factor = DIV_ROUND_CLOSEST(capacity, SCHED_CAPACITY_SCALE); + if (!capacity_factor) + capacity_factor = fix_small_capacity(env->sd, group); wl = weighted_cpuload(i); /* * When comparing with imbalance, use weighted_cpuload() - * which is not scaled with the cpu power. + * which is not scaled with the cpu capacity. */ - if (capacity && rq->nr_running == 1 && wl > env->imbalance) + if (capacity_factor && rq->nr_running == 1 && wl > env->imbalance) continue; /* * For the load comparisons with the other cpu's, consider - * the weighted_cpuload() scaled with the cpu power, so that - * the load can be moved away from the cpu that is potentially - * running at a lower capacity. + * the weighted_cpuload() scaled with the cpu capacity, so + * that the load can be moved away from the cpu that is + * potentially running at a lower capacity. * - * Thus we're looking for max(wl_i / power_i), crosswise + * Thus we're looking for max(wl_i / capacity_i), crosswise * multiplication to rid ourselves of the division works out - * to: wl_i * power_j > wl_j * power_i; where j is our - * previous maximum. + * to: wl_i * capacity_j > wl_j * capacity_i; where j is + * our previous maximum. */ - if (wl * busiest_power > busiest_load * power) { + if (wl * busiest_capacity > busiest_load * capacity) { busiest_load = wl; - busiest_power = power; + busiest_capacity = capacity; busiest = rq; } } @@ -6533,7 +6613,7 @@ more_balance: * We failed to reach balance because of affinity. */ if (sd_parent) { - int *group_imbalance = &sd_parent->groups->sgp->imbalance; + int *group_imbalance = &sd_parent->groups->sgc->imbalance; if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) { *group_imbalance = 1; @@ -6639,27 +6719,62 @@ out: return ld_moved; } +static inline unsigned long +get_sd_balance_interval(struct sched_domain *sd, int cpu_busy) +{ + unsigned long interval = sd->balance_interval; + + if (cpu_busy) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + interval = clamp(interval, 1UL, max_load_balance_interval); + + return interval; +} + +static inline void +update_next_balance(struct sched_domain *sd, int cpu_busy, unsigned long *next_balance) +{ + unsigned long interval, next; + + interval = get_sd_balance_interval(sd, cpu_busy); + next = sd->last_balance + interval; + + if (time_after(*next_balance, next)) + *next_balance = next; +} + /* * idle_balance is called by schedule() if this_cpu is about to become * idle. Attempts to pull tasks from other CPUs. */ static int idle_balance(struct rq *this_rq) { + unsigned long next_balance = jiffies + HZ; + int this_cpu = this_rq->cpu; struct sched_domain *sd; int pulled_task = 0; - unsigned long next_balance = jiffies + HZ; u64 curr_cost = 0; - int this_cpu = this_rq->cpu; idle_enter_fair(this_rq); + /* * We must set idle_stamp _before_ calling idle_balance(), such that we * measure the duration of idle_balance() as idle time. */ this_rq->idle_stamp = rq_clock(this_rq); - if (this_rq->avg_idle < sysctl_sched_migration_cost) + if (this_rq->avg_idle < sysctl_sched_migration_cost) { + rcu_read_lock(); + sd = rcu_dereference_check_sched_domain(this_rq->sd); + if (sd) + update_next_balance(sd, 0, &next_balance); + rcu_read_unlock(); + goto out; + } /* * Drop the rq->lock, but keep IRQ/preempt disabled. @@ -6669,20 +6784,20 @@ static int idle_balance(struct rq *this_rq) update_blocked_averages(this_cpu); rcu_read_lock(); for_each_domain(this_cpu, sd) { - unsigned long interval; int continue_balancing = 1; u64 t0, domain_cost; if (!(sd->flags & SD_LOAD_BALANCE)) continue; - if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) + if (this_rq->avg_idle < curr_cost + sd->max_newidle_lb_cost) { + update_next_balance(sd, 0, &next_balance); break; + } if (sd->flags & SD_BALANCE_NEWIDLE) { t0 = sched_clock_cpu(this_cpu); - /* If we've pulled tasks over stop searching: */ pulled_task = load_balance(this_cpu, this_rq, sd, CPU_NEWLY_IDLE, &continue_balancing); @@ -6694,41 +6809,37 @@ static int idle_balance(struct rq *this_rq) curr_cost += domain_cost; } - interval = msecs_to_jiffies(sd->balance_interval); - if (time_after(next_balance, sd->last_balance + interval)) - next_balance = sd->last_balance + interval; - if (pulled_task) + update_next_balance(sd, 0, &next_balance); + + /* + * Stop searching for tasks to pull if there are + * now runnable tasks on this rq. + */ + if (pulled_task || this_rq->nr_running > 0) break; } rcu_read_unlock(); raw_spin_lock(&this_rq->lock); + if (curr_cost > this_rq->max_idle_balance_cost) + this_rq->max_idle_balance_cost = curr_cost; + /* - * While browsing the domains, we released the rq lock. - * A task could have be enqueued in the meantime + * While browsing the domains, we released the rq lock, a task could + * have been enqueued in the meantime. Since we're not going idle, + * pretend we pulled a task. */ - if (this_rq->cfs.h_nr_running && !pulled_task) { + if (this_rq->cfs.h_nr_running && !pulled_task) pulled_task = 1; - goto out; - } - if (pulled_task || time_after(jiffies, this_rq->next_balance)) { - /* - * We are going idle. next_balance may be set based on - * a busy processor. So reset next_balance. - */ +out: + /* Move the next balance forward */ + if (time_after(this_rq->next_balance, next_balance)) this_rq->next_balance = next_balance; - } - if (curr_cost > this_rq->max_idle_balance_cost) - this_rq->max_idle_balance_cost = curr_cost; - -out: /* Is there a task of a high priority class? */ - if (this_rq->nr_running != this_rq->cfs.h_nr_running && - (this_rq->dl.dl_nr_running || - (this_rq->rt.rt_nr_running && !rt_rq_throttled(&this_rq->rt)))) + if (this_rq->nr_running != this_rq->cfs.h_nr_running) pulled_task = -1; if (pulled_task) { @@ -6889,7 +7000,7 @@ static inline void set_cpu_sd_state_busy(void) goto unlock; sd->nohz_idle = 0; - atomic_inc(&sd->groups->sgp->nr_busy_cpus); + atomic_inc(&sd->groups->sgc->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -6906,7 +7017,7 @@ void set_cpu_sd_state_idle(void) goto unlock; sd->nohz_idle = 1; - atomic_dec(&sd->groups->sgp->nr_busy_cpus); + atomic_dec(&sd->groups->sgc->nr_busy_cpus); unlock: rcu_read_unlock(); } @@ -7009,16 +7120,9 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) break; } - interval = sd->balance_interval; - if (idle != CPU_IDLE) - interval *= sd->busy_factor; - - /* scale ms to jiffies */ - interval = msecs_to_jiffies(interval); - interval = clamp(interval, 1UL, max_load_balance_interval); + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); need_serialize = sd->flags & SD_SERIALIZE; - if (need_serialize) { if (!spin_trylock(&balancing)) goto out; @@ -7034,6 +7138,7 @@ static void rebalance_domains(struct rq *rq, enum cpu_idle_type idle) idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; } sd->last_balance = jiffies; + interval = get_sd_balance_interval(sd, idle != CPU_IDLE); } if (need_serialize) spin_unlock(&balancing); @@ -7091,12 +7196,17 @@ static void nohz_idle_balance(struct rq *this_rq, enum cpu_idle_type idle) rq = cpu_rq(balance_cpu); - raw_spin_lock_irq(&rq->lock); - update_rq_clock(rq); - update_idle_cpu_load(rq); - raw_spin_unlock_irq(&rq->lock); - - rebalance_domains(rq, CPU_IDLE); + /* + * If time for next balance is due, + * do the balance. + */ + if (time_after_eq(jiffies, rq->next_balance)) { + raw_spin_lock_irq(&rq->lock); + update_rq_clock(rq); + update_idle_cpu_load(rq); + raw_spin_unlock_irq(&rq->lock); + rebalance_domains(rq, CPU_IDLE); + } if (time_after(this_rq->next_balance, rq->next_balance)) this_rq->next_balance = rq->next_balance; @@ -7111,7 +7221,7 @@ end: * of an idle cpu is the system. * - This rq has more than one task. * - At any scheduler domain level, this cpu's scheduler group has multiple - * busy cpu's exceeding the group's power. + * busy cpu's exceeding the group's capacity. * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler * domain span are idle. */ @@ -7119,7 +7229,7 @@ static inline int nohz_kick_needed(struct rq *rq) { unsigned long now = jiffies; struct sched_domain *sd; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; int nr_busy, cpu = rq->cpu; if (unlikely(rq->idle_balance)) @@ -7149,8 +7259,8 @@ static inline int nohz_kick_needed(struct rq *rq) sd = rcu_dereference(per_cpu(sd_busy, cpu)); if (sd) { - sgp = sd->groups->sgp; - nr_busy = atomic_read(&sgp->nr_busy_cpus); + sgc = sd->groups->sgc; + nr_busy = atomic_read(&sgc->nr_busy_cpus); if (nr_busy > 1) goto need_kick_unlock; diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 5716929..90284d1 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -37,18 +37,18 @@ SCHED_FEAT(CACHE_HOT_BUDDY, true) SCHED_FEAT(WAKEUP_PREEMPTION, true) /* - * Use arch dependent cpu power functions + * Use arch dependent cpu capacity functions */ -SCHED_FEAT(ARCH_POWER, true) +SCHED_FEAT(ARCH_CAPACITY, true) SCHED_FEAT(HRTICK, false) SCHED_FEAT(DOUBLE_TICK, false) SCHED_FEAT(LB_BIAS, true) /* - * Decrement CPU power based on time not spent running tasks + * Decrement CPU capacity based on time not spent running tasks */ -SCHED_FEAT(NONTASK_POWER, true) +SCHED_FEAT(NONTASK_CAPACITY, true) /* * Queue remote wakeups on the target CPU and process them diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 8f4390a..cf009fb 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -12,6 +12,8 @@ #include <trace/events/power.h> +#include "sched.h" + static int __read_mostly cpu_idle_force_poll; void cpu_idle_poll_ctrl(bool enable) @@ -67,24 +69,25 @@ void __weak arch_cpu_idle(void) * cpuidle_idle_call - the main idle function * * NOTE: no locks or semaphores should be used here - * return non-zero on failure + * + * On archs that support TIF_POLLING_NRFLAG, is called with polling + * set, and it returns with polling set. If it ever stops polling, it + * must clear the polling bit. */ -static int cpuidle_idle_call(void) +static void cpuidle_idle_call(void) { struct cpuidle_device *dev = __this_cpu_read(cpuidle_devices); struct cpuidle_driver *drv = cpuidle_get_cpu_driver(dev); - int next_state, entered_state, ret; + int next_state, entered_state; bool broadcast; /* * Check if the idle task must be rescheduled. If it is the - * case, exit the function after re-enabling the local irq and - * set again the polling flag + * case, exit the function after re-enabling the local irq. */ - if (current_clr_polling_and_test()) { + if (need_resched()) { local_irq_enable(); - __current_set_polling(); - return 0; + return; } /* @@ -101,104 +104,99 @@ static int cpuidle_idle_call(void) rcu_idle_enter(); /* - * Check if the cpuidle framework is ready, otherwise fallback - * to the default arch specific idle method + * Ask the cpuidle framework to choose a convenient idle state. + * Fall back to the default arch idle method on errors. */ - ret = cpuidle_enabled(drv, dev); - - if (!ret) { + next_state = cpuidle_select(drv, dev); + if (next_state < 0) { +use_default: /* - * Ask the governor to choose an idle state it thinks - * it is convenient to go to. There is *always* a - * convenient idle state + * We can't use the cpuidle framework, let's use the default + * idle routine. */ - next_state = cpuidle_select(drv, dev); - - /* - * The idle task must be scheduled, it is pointless to - * go to idle, just update no idle residency and get - * out of this function - */ - if (current_clr_polling_and_test()) { - dev->last_residency = 0; - entered_state = next_state; + if (current_clr_polling_and_test()) local_irq_enable(); - } else { - broadcast = !!(drv->states[next_state].flags & - CPUIDLE_FLAG_TIMER_STOP); - - if (broadcast) - /* - * Tell the time framework to switch - * to a broadcast timer because our - * local timer will be shutdown. If a - * local timer is used from another - * cpu as a broadcast timer, this call - * may fail if it is not available - */ - ret = clockevents_notify( - CLOCK_EVT_NOTIFY_BROADCAST_ENTER, - &dev->cpu); - - if (!ret) { - trace_cpu_idle_rcuidle(next_state, dev->cpu); - - /* - * Enter the idle state previously - * returned by the governor - * decision. This function will block - * until an interrupt occurs and will - * take care of re-enabling the local - * interrupts - */ - entered_state = cpuidle_enter(drv, dev, - next_state); - - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, - dev->cpu); - - if (broadcast) - clockevents_notify( - CLOCK_EVT_NOTIFY_BROADCAST_EXIT, - &dev->cpu); - - /* - * Give the governor an opportunity to reflect on the - * outcome - */ - cpuidle_reflect(dev, entered_state); - } - } + else + arch_cpu_idle(); + + goto exit_idle; } + + /* + * The idle task must be scheduled, it is pointless to + * go to idle, just update no idle residency and get + * out of this function + */ + if (current_clr_polling_and_test()) { + dev->last_residency = 0; + entered_state = next_state; + local_irq_enable(); + goto exit_idle; + } + + broadcast = !!(drv->states[next_state].flags & CPUIDLE_FLAG_TIMER_STOP); + /* - * We can't use the cpuidle framework, let's use the default - * idle routine + * Tell the time framework to switch to a broadcast timer + * because our local timer will be shutdown. If a local timer + * is used from another cpu as a broadcast timer, this call may + * fail if it is not available */ - if (ret) - arch_cpu_idle(); + if (broadcast && + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, &dev->cpu)) + goto use_default; + trace_cpu_idle_rcuidle(next_state, dev->cpu); + + /* + * Enter the idle state previously returned by the governor decision. + * This function will block until an interrupt occurs and will take + * care of re-enabling the local interrupts + */ + entered_state = cpuidle_enter(drv, dev, next_state); + + trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, dev->cpu); + + if (broadcast) + clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_EXIT, &dev->cpu); + + /* + * Give the governor an opportunity to reflect on the outcome + */ + cpuidle_reflect(dev, entered_state); + +exit_idle: __current_set_polling(); /* - * It is up to the idle functions to enable back the local - * interrupt + * It is up to the idle functions to reenable local interrupts */ if (WARN_ON_ONCE(irqs_disabled())) local_irq_enable(); rcu_idle_exit(); start_critical_timings(); - - return 0; } /* * Generic idle loop implementation + * + * Called with polling cleared. */ static void cpu_idle_loop(void) { while (1) { + /* + * If the arch has a polling bit, we maintain an invariant: + * + * Our polling bit is clear if we're not scheduled (i.e. if + * rq->curr != rq->idle). This means that, if rq->idle has + * the polling bit set, then setting need_resched is + * guaranteed to cause the cpu to reschedule. + */ + + __current_set_polling(); tick_nohz_idle_enter(); while (!need_resched()) { @@ -238,6 +236,17 @@ static void cpu_idle_loop(void) */ preempt_set_need_resched(); tick_nohz_idle_exit(); + __current_clr_polling(); + + /* + * We promise to call sched_ttwu_pending and reschedule + * if need_resched is set while polling is set. That + * means that clearing polling needs to be visible + * before doing these things. + */ + smp_mb__after_atomic(); + + sched_ttwu_pending(); schedule_preempt_disabled(); } } @@ -259,7 +268,6 @@ void cpu_startup_entry(enum cpuhp_state state) */ boot_init_stack_canary(); #endif - __current_set_polling(); arch_cpu_idle_prepare(); cpu_idle_loop(); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index d8cdf16..43406db 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -79,6 +79,8 @@ void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) rt_rq->overloaded = 0; plist_head_init(&rt_rq->pushable_tasks); #endif + /* We start is dequeued state, because no RT tasks are queued */ + rt_rq->rt_queued = 0; rt_rq->rt_time = 0; rt_rq->rt_throttled = 0; @@ -112,6 +114,13 @@ static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) return rt_se->rt_rq; } +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) +{ + struct rt_rq *rt_rq = rt_se->rt_rq; + + return rt_rq->rq; +} + void free_rt_sched_group(struct task_group *tg) { int i; @@ -211,10 +220,16 @@ static inline struct rq *rq_of_rt_rq(struct rt_rq *rt_rq) return container_of(rt_rq, struct rq, rt); } -static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +static inline struct rq *rq_of_rt_se(struct sched_rt_entity *rt_se) { struct task_struct *p = rt_task_of(rt_se); - struct rq *rq = task_rq(p); + + return task_rq(p); +} + +static inline struct rt_rq *rt_rq_of_se(struct sched_rt_entity *rt_se) +{ + struct rq *rq = rq_of_rt_se(rt_se); return &rq->rt; } @@ -391,6 +406,9 @@ static inline void set_post_schedule(struct rq *rq) } #endif /* CONFIG_SMP */ +static void enqueue_top_rt_rq(struct rt_rq *rt_rq); +static void dequeue_top_rt_rq(struct rt_rq *rt_rq); + static inline int on_rt_rq(struct sched_rt_entity *rt_se) { return !list_empty(&rt_se->run_list); @@ -452,8 +470,11 @@ static void sched_rt_rq_enqueue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; if (rt_rq->rt_nr_running) { - if (rt_se && !on_rt_rq(rt_se)) + if (!rt_se) + enqueue_top_rt_rq(rt_rq); + else if (!on_rt_rq(rt_se)) enqueue_rt_entity(rt_se, false); + if (rt_rq->highest_prio.curr < curr->prio) resched_task(curr); } @@ -466,10 +487,17 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq) rt_se = rt_rq->tg->rt_se[cpu]; - if (rt_se && on_rt_rq(rt_se)) + if (!rt_se) + dequeue_top_rt_rq(rt_rq); + else if (on_rt_rq(rt_se)) dequeue_rt_entity(rt_se); } +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; +} + static int rt_se_boosted(struct sched_rt_entity *rt_se) { struct rt_rq *rt_rq = group_rt_rq(rt_se); @@ -532,12 +560,23 @@ static inline struct rt_rq *group_rt_rq(struct sched_rt_entity *rt_se) static inline void sched_rt_rq_enqueue(struct rt_rq *rt_rq) { - if (rt_rq->rt_nr_running) - resched_task(rq_of_rt_rq(rt_rq)->curr); + struct rq *rq = rq_of_rt_rq(rt_rq); + + if (!rt_rq->rt_nr_running) + return; + + enqueue_top_rt_rq(rt_rq); + resched_task(rq->curr); } static inline void sched_rt_rq_dequeue(struct rt_rq *rt_rq) { + dequeue_top_rt_rq(rt_rq); +} + +static inline int rt_rq_throttled(struct rt_rq *rt_rq) +{ + return rt_rq->rt_throttled; } static inline const struct cpumask *sched_rt_period_mask(void) @@ -885,7 +924,6 @@ static void update_curr_rt(struct rq *rq) { struct task_struct *curr = rq->curr; struct sched_rt_entity *rt_se = &curr->rt; - struct rt_rq *rt_rq = rt_rq_of_se(rt_se); u64 delta_exec; if (curr->sched_class != &rt_sched_class) @@ -910,7 +948,7 @@ static void update_curr_rt(struct rq *rq) return; for_each_sched_rt_entity(rt_se) { - rt_rq = rt_rq_of_se(rt_se); + struct rt_rq *rt_rq = rt_rq_of_se(rt_se); if (sched_rt_runtime(rt_rq) != RUNTIME_INF) { raw_spin_lock(&rt_rq->rt_runtime_lock); @@ -922,6 +960,38 @@ static void update_curr_rt(struct rq *rq) } } +static void +dequeue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (!rt_rq->rt_queued) + return; + + BUG_ON(!rq->nr_running); + + sub_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 0; +} + +static void +enqueue_top_rt_rq(struct rt_rq *rt_rq) +{ + struct rq *rq = rq_of_rt_rq(rt_rq); + + BUG_ON(&rq->rt != rt_rq); + + if (rt_rq->rt_queued) + return; + if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running) + return; + + add_nr_running(rq, rt_rq->rt_nr_running); + rt_rq->rt_queued = 1; +} + #if defined CONFIG_SMP static void @@ -1045,12 +1115,23 @@ void dec_rt_group(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) {} #endif /* CONFIG_RT_GROUP_SCHED */ static inline +unsigned int rt_se_nr_running(struct sched_rt_entity *rt_se) +{ + struct rt_rq *group_rq = group_rt_rq(rt_se); + + if (group_rq) + return group_rq->rt_nr_running; + else + return 1; +} + +static inline void inc_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { int prio = rt_se_prio(rt_se); WARN_ON(!rt_prio(prio)); - rt_rq->rt_nr_running++; + rt_rq->rt_nr_running += rt_se_nr_running(rt_se); inc_rt_prio(rt_rq, prio); inc_rt_migration(rt_se, rt_rq); @@ -1062,7 +1143,7 @@ void dec_rt_tasks(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) { WARN_ON(!rt_prio(rt_se_prio(rt_se))); WARN_ON(!rt_rq->rt_nr_running); - rt_rq->rt_nr_running--; + rt_rq->rt_nr_running -= rt_se_nr_running(rt_se); dec_rt_prio(rt_rq, rt_se_prio(rt_se)); dec_rt_migration(rt_se, rt_rq); @@ -1119,6 +1200,8 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) back = rt_se; } + dequeue_top_rt_rq(rt_rq_of_se(back)); + for (rt_se = back; rt_se; rt_se = rt_se->back) { if (on_rt_rq(rt_se)) __dequeue_rt_entity(rt_se); @@ -1127,13 +1210,18 @@ static void dequeue_rt_stack(struct sched_rt_entity *rt_se) static void enqueue_rt_entity(struct sched_rt_entity *rt_se, bool head) { + struct rq *rq = rq_of_rt_se(rt_se); + dequeue_rt_stack(rt_se); for_each_sched_rt_entity(rt_se) __enqueue_rt_entity(rt_se, head); + enqueue_top_rt_rq(&rq->rt); } static void dequeue_rt_entity(struct sched_rt_entity *rt_se) { + struct rq *rq = rq_of_rt_se(rt_se); + dequeue_rt_stack(rt_se); for_each_sched_rt_entity(rt_se) { @@ -1142,6 +1230,7 @@ static void dequeue_rt_entity(struct sched_rt_entity *rt_se) if (rt_rq && rt_rq->rt_nr_running) __enqueue_rt_entity(rt_se, false); } + enqueue_top_rt_rq(&rq->rt); } /* @@ -1159,8 +1248,6 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); - - inc_nr_running(rq); } static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) @@ -1171,8 +1258,6 @@ static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags) dequeue_rt_entity(rt_se); dequeue_pushable_task(rq, p); - - dec_nr_running(rq); } /* @@ -1362,10 +1447,11 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) pull_rt_task(rq); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this - * means a dl task can slip in, in which case we need to - * re-start task selection. + * means a dl or stop task can slip in, in which case we need + * to re-start task selection. */ - if (unlikely(rq->dl.dl_nr_running)) + if (unlikely((rq->stop && rq->stop->on_rq) || + rq->dl.dl_nr_running)) return RETRY_TASK; } @@ -1376,10 +1462,7 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev) if (prev->sched_class == &rt_sched_class) update_curr_rt(rq); - if (!rt_rq->rt_nr_running) - return NULL; - - if (rt_rq_throttled(rt_rq)) + if (!rt_rq->rt_queued) return NULL; put_prev_task(rq, prev); @@ -1891,9 +1974,9 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) */ if (p->on_rq && rq->curr != p) { #ifdef CONFIG_SMP - if (rq->rt.overloaded && push_rt_task(rq) && + if (p->nr_cpus_allowed > 1 && rq->rt.overloaded && /* Don't resched if we changed runqueues */ - rq != task_rq(p)) + push_rt_task(rq) && rq != task_rq(p)) check_resched = 0; #endif /* CONFIG_SMP */ if (check_resched && p->prio < rq->curr->prio) diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index c9007f2..2f86361 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -409,6 +409,8 @@ struct rt_rq { int overloaded; struct plist_head pushable_tasks; #endif + int rt_queued; + int rt_throttled; u64 rt_time; u64 rt_runtime; @@ -423,18 +425,6 @@ struct rt_rq { #endif }; -#ifdef CONFIG_RT_GROUP_SCHED -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled && !rt_rq->rt_nr_boosted; -} -#else -static inline int rt_rq_throttled(struct rt_rq *rt_rq) -{ - return rt_rq->rt_throttled; -} -#endif - /* Deadline class' related fields in a runqueue */ struct dl_rq { /* runqueue is an rbtree, ordered by deadline */ @@ -577,7 +567,7 @@ struct rq { struct root_domain *rd; struct sched_domain *sd; - unsigned long cpu_power; + unsigned long cpu_capacity; unsigned char idle_balance; /* For active balancing */ @@ -680,6 +670,8 @@ extern int migrate_swap(struct task_struct *, struct task_struct *); #ifdef CONFIG_SMP +extern void sched_ttwu_pending(void); + #define rcu_dereference_check_sched_domain(p) \ rcu_dereference_check((p), \ lockdep_is_held(&sched_domains_mutex)) @@ -738,15 +730,15 @@ DECLARE_PER_CPU(struct sched_domain *, sd_numa); DECLARE_PER_CPU(struct sched_domain *, sd_busy); DECLARE_PER_CPU(struct sched_domain *, sd_asym); -struct sched_group_power { +struct sched_group_capacity { atomic_t ref; /* - * CPU power of this group, SCHED_LOAD_SCALE being max power for a - * single CPU. + * CPU capacity of this group, SCHED_LOAD_SCALE being max capacity + * for a single CPU. */ - unsigned int power, power_orig; + unsigned int capacity, capacity_orig; unsigned long next_update; - int imbalance; /* XXX unrelated to power but shared group state */ + int imbalance; /* XXX unrelated to capacity but shared group state */ /* * Number of busy cpus in this group. */ @@ -760,7 +752,7 @@ struct sched_group { atomic_t ref; unsigned int group_weight; - struct sched_group_power *sgp; + struct sched_group_capacity *sgc; /* * The CPUs this group covers. @@ -783,7 +775,7 @@ static inline struct cpumask *sched_group_cpus(struct sched_group *sg) */ static inline struct cpumask *sched_group_mask(struct sched_group *sg) { - return to_cpumask(sg->sgp->cpumask); + return to_cpumask(sg->sgc->cpumask); } /** @@ -797,6 +789,10 @@ static inline unsigned int group_first_cpu(struct sched_group *group) extern int group_balance_cpu(struct sched_group *sg); +#else + +static inline void sched_ttwu_pending(void) { } + #endif /* CONFIG_SMP */ #include "stats.h" @@ -1177,7 +1173,7 @@ extern const struct sched_class idle_sched_class; #ifdef CONFIG_SMP -extern void update_group_power(struct sched_domain *sd, int cpu); +extern void update_group_capacity(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); @@ -1216,12 +1212,14 @@ extern void update_idle_cpu_load(struct rq *this_rq); extern void init_task_runnable_average(struct task_struct *p); -static inline void inc_nr_running(struct rq *rq) +static inline void add_nr_running(struct rq *rq, unsigned count) { - rq->nr_running++; + unsigned prev_nr = rq->nr_running; + + rq->nr_running = prev_nr + count; #ifdef CONFIG_NO_HZ_FULL - if (rq->nr_running == 2) { + if (prev_nr < 2 && rq->nr_running >= 2) { if (tick_nohz_full_cpu(rq->cpu)) { /* Order rq->nr_running write against the IPI */ smp_wmb(); @@ -1231,9 +1229,9 @@ static inline void inc_nr_running(struct rq *rq) #endif } -static inline void dec_nr_running(struct rq *rq) +static inline void sub_nr_running(struct rq *rq, unsigned count) { - rq->nr_running--; + rq->nr_running -= count; } static inline void rq_last_tick_reset(struct rq *rq) @@ -1385,6 +1383,15 @@ static inline void double_lock(spinlock_t *l1, spinlock_t *l2) spin_lock_nested(l2, SINGLE_DEPTH_NESTING); } +static inline void double_lock_irq(spinlock_t *l1, spinlock_t *l2) +{ + if (l1 > l2) + swap(l1, l2); + + spin_lock_irq(l1); + spin_lock_nested(l2, SINGLE_DEPTH_NESTING); +} + static inline void double_raw_lock(raw_spinlock_t *l1, raw_spinlock_t *l2) { if (l1 > l2) diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index d6ce65d..bfe0eda 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -41,13 +41,13 @@ pick_next_task_stop(struct rq *rq, struct task_struct *prev) static void enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags) { - inc_nr_running(rq); + add_nr_running(rq, 1); } static void dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags) { - dec_nr_running(rq); + sub_nr_running(rq, 1); } static void yield_task_stop(struct rq *rq) diff --git a/kernel/seccomp.c b/kernel/seccomp.c index 590c379..b35c215 100644 --- a/kernel/seccomp.c +++ b/kernel/seccomp.c @@ -255,6 +255,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) goto free_prog; /* Allocate a new seccomp_filter */ + ret = -ENOMEM; filter = kzalloc(sizeof(struct seccomp_filter) + sizeof(struct sock_filter_int) * new_len, GFP_KERNEL|__GFP_NOWARN); @@ -264,6 +265,7 @@ static long seccomp_attach_filter(struct sock_fprog *fprog) ret = sk_convert_filter(fp, fprog->len, filter->insnsi, &new_len); if (ret) goto free_filter; + kfree(fp); atomic_set(&filter->usage, 1); filter->len = new_len; diff --git a/kernel/softirq.c b/kernel/softirq.c index b50990a..92f24f5 100644 --- a/kernel/softirq.c +++ b/kernel/softirq.c @@ -223,7 +223,7 @@ static inline bool lockdep_softirq_start(void) { return false; } static inline void lockdep_softirq_end(bool in_hardirq) { } #endif -asmlinkage void __do_softirq(void) +asmlinkage __visible void __do_softirq(void) { unsigned long end = jiffies + MAX_SOFTIRQ_TIME; unsigned long old_flags = current->flags; @@ -299,7 +299,7 @@ restart: tsk_restore_flags(current, old_flags, PF_MEMALLOC); } -asmlinkage void do_softirq(void) +asmlinkage __visible void do_softirq(void) { __u32 pending; unsigned long flags; @@ -779,3 +779,8 @@ int __init __weak arch_early_irq_init(void) { return 0; } + +unsigned int __weak arch_dynirq_lower_bound(unsigned int from) +{ + return from; +} diff --git a/kernel/sys.c b/kernel/sys.c index fba0f29..66a751e 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -250,7 +250,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) else p = current; if (p) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } @@ -261,7 +261,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) else pgrp = task_pgrp(current); do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); @@ -277,7 +277,7 @@ SYSCALL_DEFINE2(getpriority, int, which, int, who) do_each_thread(g, p) { if (uid_eq(task_uid(p), uid)) { - niceval = 20 - task_nice(p); + niceval = nice_to_rlimit(task_nice(p)); if (niceval > retval) retval = niceval; } diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c index 0156612..0a0608e 100644 --- a/kernel/time/tick-common.c +++ b/kernel/time/tick-common.c @@ -276,7 +276,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev, bool tick_check_replacement(struct clock_event_device *curdev, struct clock_event_device *newdev) { - if (tick_check_percpu(curdev, newdev, smp_processor_id())) + if (!tick_check_percpu(curdev, newdev, smp_processor_id())) return false; return tick_check_preferred(curdev, newdev); diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c index 9f8af69..6558b7a 100644 --- a/kernel/time/tick-sched.c +++ b/kernel/time/tick-sched.c @@ -84,6 +84,9 @@ static void tick_do_update_jiffies64(ktime_t now) /* Keep the tick_next_period variable up to date */ tick_next_period = ktime_add(last_jiffies_update, tick_period); + } else { + write_sequnlock(&jiffies_lock); + return; } write_sequnlock(&jiffies_lock); update_wall_time(); @@ -967,7 +970,7 @@ static void tick_nohz_switch_to_nohz(void) struct tick_sched *ts = &__get_cpu_var(tick_cpu_sched); ktime_t next; - if (!tick_nohz_active) + if (!tick_nohz_enabled) return; local_irq_disable(); diff --git a/kernel/timer.c b/kernel/timer.c index 87bd529..3bb01a3 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -838,7 +838,7 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires) bit = find_last_bit(&mask, BITS_PER_LONG); - mask = (1 << bit) - 1; + mask = (1UL << bit) - 1; expires_limit = expires_limit & ~(mask); diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 1fd4b94..4a54a25 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -4330,16 +4330,11 @@ static void ftrace_init_module(struct module *mod, ftrace_process_locs(mod, start, end); } -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) +void ftrace_module_init(struct module *mod) { - struct module *mod = data; - - if (val == MODULE_STATE_COMING) - ftrace_init_module(mod, mod->ftrace_callsites, - mod->ftrace_callsites + - mod->num_ftrace_callsites); - return 0; + ftrace_init_module(mod, mod->ftrace_callsites, + mod->ftrace_callsites + + mod->num_ftrace_callsites); } static int ftrace_module_notify_exit(struct notifier_block *self, @@ -4353,11 +4348,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self, return 0; } #else -static int ftrace_module_notify_enter(struct notifier_block *self, - unsigned long val, void *data) -{ - return 0; -} static int ftrace_module_notify_exit(struct notifier_block *self, unsigned long val, void *data) { @@ -4365,11 +4355,6 @@ static int ftrace_module_notify_exit(struct notifier_block *self, } #endif /* CONFIG_MODULES */ -struct notifier_block ftrace_module_enter_nb = { - .notifier_call = ftrace_module_notify_enter, - .priority = INT_MAX, /* Run before anything that can use kprobes */ -}; - struct notifier_block ftrace_module_exit_nb = { .notifier_call = ftrace_module_notify_exit, .priority = INT_MIN, /* Run after anything that can remove kprobes */ @@ -4403,10 +4388,6 @@ void __init ftrace_init(void) __start_mcount_loc, __stop_mcount_loc); - ret = register_module_notifier(&ftrace_module_enter_nb); - if (ret) - pr_warning("Failed to register trace ftrace module enter notifier\n"); - ret = register_module_notifier(&ftrace_module_exit_nb); if (ret) pr_warning("Failed to register trace ftrace module exit notifier\n"); diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 925f537..4747b47 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -77,7 +77,7 @@ event_triggers_call(struct ftrace_event_file *file, void *rec) data->ops->func(data); continue; } - filter = rcu_dereference(data->filter); + filter = rcu_dereference_sched(data->filter); if (filter && !filter_match_preds(filter, rec)) continue; if (data->cmd_ops->post_trigger) { diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c index 5b781d2..ffd5635 100644 --- a/kernel/trace/trace_functions.c +++ b/kernel/trace/trace_functions.c @@ -58,12 +58,16 @@ int ftrace_create_function_files(struct trace_array *tr, { int ret; - /* The top level array uses the "global_ops". */ - if (!(tr->flags & TRACE_ARRAY_FL_GLOBAL)) { - ret = allocate_ftrace_ops(tr); - if (ret) - return ret; - } + /* + * The top level array uses the "global_ops", and the files are + * created on boot up. + */ + if (tr->flags & TRACE_ARRAY_FL_GLOBAL) + return 0; + + ret = allocate_ftrace_ops(tr); + if (ret) + return ret; ftrace_create_filter_files(tr->ops, parent); diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index 930e514..c082a74 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -732,9 +732,15 @@ static int uprobe_buffer_enable(void) static void uprobe_buffer_disable(void) { + int cpu; + BUG_ON(!mutex_is_locked(&event_mutex)); if (--uprobe_buffer_refcnt == 0) { + for_each_possible_cpu(cpu) + free_page((unsigned long)per_cpu_ptr(uprobe_cpu_buffer, + cpu)->buf); + free_percpu(uprobe_cpu_buffer); uprobe_cpu_buffer = NULL; } diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c index ac5b23c..6620e58 100644 --- a/kernel/tracepoint.c +++ b/kernel/tracepoint.c @@ -188,7 +188,6 @@ static int tracepoint_add_func(struct tracepoint *tp, WARN_ON_ONCE(1); return PTR_ERR(old); } - release_probes(old); /* * rcu_assign_pointer has a smp_wmb() which makes sure that the new @@ -200,6 +199,7 @@ static int tracepoint_add_func(struct tracepoint *tp, rcu_assign_pointer(tp->funcs, tp_funcs); if (!static_key_enabled(&tp->key)) static_key_slow_inc(&tp->key); + release_probes(old); return 0; } @@ -221,7 +221,6 @@ static int tracepoint_remove_func(struct tracepoint *tp, WARN_ON_ONCE(1); return PTR_ERR(old); } - release_probes(old); if (!tp_funcs) { /* Removed last function */ @@ -232,6 +231,7 @@ static int tracepoint_remove_func(struct tracepoint *tp, static_key_slow_dec(&tp->key); } rcu_assign_pointer(tp->funcs, tp_funcs); + release_probes(old); return 0; } diff --git a/kernel/watchdog.c b/kernel/watchdog.c index e90089f..516203e 100644 --- a/kernel/watchdog.c +++ b/kernel/watchdog.c @@ -138,7 +138,11 @@ static void __touch_watchdog(void) void touch_softlockup_watchdog(void) { - __this_cpu_write(watchdog_touch_ts, 0); + /* + * Preemption can be enabled. It doesn't matter which CPU's timestamp + * gets zeroed here, so use the raw_ operation. + */ + raw_cpu_write(watchdog_touch_ts, 0); } EXPORT_SYMBOL(touch_softlockup_watchdog); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index 0ee63af..a4bab46 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -100,10 +100,10 @@ enum { /* * Rescue workers are used only on emergencies and shared by - * all cpus. Give -20. + * all cpus. Give MIN_NICE. */ - RESCUER_NICE_LEVEL = -20, - HIGHPRI_NICE_LEVEL = -20, + RESCUER_NICE_LEVEL = MIN_NICE, + HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 24, }; @@ -1916,6 +1916,12 @@ static void send_mayday(struct work_struct *work) /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { + /* + * If @pwq is for an unbound wq, its base ref may be put at + * any time due to an attribute change. Pin @pwq until the + * rescuer is done with it. + */ + get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); } @@ -2398,6 +2404,7 @@ static int rescuer_thread(void *__rescuer) struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; struct list_head *scheduled = &rescuer->scheduled; + bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); @@ -2409,11 +2416,15 @@ static int rescuer_thread(void *__rescuer) repeat: set_current_state(TASK_INTERRUPTIBLE); - if (kthread_should_stop()) { - __set_current_state(TASK_RUNNING); - rescuer->task->flags &= ~PF_WQ_WORKER; - return 0; - } + /* + * By the time the rescuer is requested to stop, the workqueue + * shouldn't have any work pending, but @wq->maydays may still have + * pwq(s) queued. This can happen by non-rescuer workers consuming + * all the work items before the rescuer got to them. Go through + * @wq->maydays processing before acting on should_stop so that the + * list is always empty on exit. + */ + should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ spin_lock_irq(&wq_mayday_lock); @@ -2445,6 +2456,12 @@ repeat: process_scheduled_works(rescuer); /* + * Put the reference grabbed by send_mayday(). @pool won't + * go away while we're holding its lock. + */ + put_pwq(pwq); + + /* * Leave this pool. If keep_working() is %true, notify a * regular worker; otherwise, we end up with 0 concurrency * and stalling the execution. @@ -2459,6 +2476,12 @@ repeat: spin_unlock_irq(&wq_mayday_lock); + if (should_stop) { + __set_current_state(TASK_RUNNING); + rescuer->task->flags &= ~PF_WQ_WORKER; + return 0; + } + /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); @@ -4100,7 +4123,8 @@ static void wq_update_unbound_numa(struct workqueue_struct *wq, int cpu, if (!pwq) { pr_warning("workqueue: allocation failed while updating NUMA affinity of \"%s\"\n", wq->name); - goto out_unlock; + mutex_lock(&wq->mutex); + goto use_dfl_pwq; } /* |
