diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/Makefile | 4 | ||||
| -rw-r--r-- | kernel/sched/autogroup.c (renamed from kernel/sched/auto_group.c) | 0 | ||||
| -rw-r--r-- | kernel/sched/autogroup.h (renamed from kernel/sched/auto_group.h) | 1 | ||||
| -rw-r--r-- | kernel/sched/clock.c | 176 | ||||
| -rw-r--r-- | kernel/sched/completion.c | 13 | ||||
| -rw-r--r-- | kernel/sched/core.c | 2392 | ||||
| -rw-r--r-- | kernel/sched/cpuacct.c | 2 | ||||
| -rw-r--r-- | kernel/sched/cpudeadline.c | 4 | ||||
| -rw-r--r-- | kernel/sched/cpufreq_schedutil.c | 159 | ||||
| -rw-r--r-- | kernel/sched/cpupri.c | 4 | ||||
| -rw-r--r-- | kernel/sched/cputime.c | 280 | ||||
| -rw-r--r-- | kernel/sched/deadline.c | 115 | ||||
| -rw-r--r-- | kernel/sched/debug.c | 7 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 790 | ||||
| -rw-r--r-- | kernel/sched/features.h | 5 | ||||
| -rw-r--r-- | kernel/sched/idle.c | 176 | ||||
| -rw-r--r-- | kernel/sched/idle_task.c | 2 | ||||
| -rw-r--r-- | kernel/sched/loadavg.c | 21 | ||||
| -rw-r--r-- | kernel/sched/rt.c | 43 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 172 | ||||
| -rw-r--r-- | kernel/sched/stats.h | 103 | ||||
| -rw-r--r-- | kernel/sched/stop_task.c | 2 | ||||
| -rw-r--r-- | kernel/sched/swait.c | 2 | ||||
| -rw-r--r-- | kernel/sched/topology.c | 1658 | ||||
| -rw-r--r-- | kernel/sched/wait.c | 42 |
25 files changed, 3449 insertions, 2724 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 5e59b832ae2b..89ab6758667b 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -18,8 +18,8 @@ endif obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o obj-y += wait.o swait.o completion.o idle.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o -obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o +obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o +obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o diff --git a/kernel/sched/auto_group.c b/kernel/sched/autogroup.c index da39489d2d80..da39489d2d80 100644 --- a/kernel/sched/auto_group.c +++ b/kernel/sched/autogroup.c diff --git a/kernel/sched/auto_group.h b/kernel/sched/autogroup.h index 890c95f2587a..ce40c810cd5c 100644 --- a/kernel/sched/auto_group.h +++ b/kernel/sched/autogroup.h @@ -2,6 +2,7 @@ #include <linux/kref.h> #include <linux/rwsem.h> +#include <linux/sched/autogroup.h> struct autogroup { /* diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index e85a725e5c34..00a45c45beca 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -58,6 +58,8 @@ #include <linux/percpu.h> #include <linux/ktime.h> #include <linux/sched.h> +#include <linux/nmi.h> +#include <linux/sched/clock.h> #include <linux/static_key.h> #include <linux/workqueue.h> #include <linux/compiler.h> @@ -77,91 +79,113 @@ EXPORT_SYMBOL_GPL(sched_clock); __read_mostly int sched_clock_running; +void sched_clock_init(void) +{ + sched_clock_running = 1; +} + #ifdef CONFIG_HAVE_UNSTABLE_SCHED_CLOCK -static struct static_key __sched_clock_stable = STATIC_KEY_INIT; -static int __sched_clock_stable_early; +/* + * We must start with !__sched_clock_stable because the unstable -> stable + * transition is accurate, while the stable -> unstable transition is not. + * + * Similarly we start with __sched_clock_stable_early, thereby assuming we + * will become stable, such that there's only a single 1 -> 0 transition. + */ +static DEFINE_STATIC_KEY_FALSE(__sched_clock_stable); +static int __sched_clock_stable_early = 1; -int sched_clock_stable(void) +/* + * We want: ktime_get_ns() + __gtod_offset == sched_clock() + __sched_clock_offset + */ +__read_mostly u64 __sched_clock_offset; +static __read_mostly u64 __gtod_offset; + +struct sched_clock_data { + u64 tick_raw; + u64 tick_gtod; + u64 clock; +}; + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); + +static inline struct sched_clock_data *this_scd(void) { - return static_key_false(&__sched_clock_stable); + return this_cpu_ptr(&sched_clock_data); } -static void __set_sched_clock_stable(void) +static inline struct sched_clock_data *cpu_sdc(int cpu) { - if (!sched_clock_stable()) - static_key_slow_inc(&__sched_clock_stable); + return &per_cpu(sched_clock_data, cpu); +} - tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); +int sched_clock_stable(void) +{ + return static_branch_likely(&__sched_clock_stable); } -void set_sched_clock_stable(void) +static void __set_sched_clock_stable(void) { - __sched_clock_stable_early = 1; + struct sched_clock_data *scd = this_scd(); - smp_mb(); /* matches sched_clock_init() */ + /* + * Attempt to make the (initial) unstable->stable transition continuous. + */ + __sched_clock_offset = (scd->tick_gtod + __gtod_offset) - (scd->tick_raw); - if (!sched_clock_running) - return; + printk(KERN_INFO "sched_clock: Marking stable (%lld, %lld)->(%lld, %lld)\n", + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); - __set_sched_clock_stable(); + static_branch_enable(&__sched_clock_stable); + tick_dep_clear(TICK_DEP_BIT_CLOCK_UNSTABLE); } -static void __clear_sched_clock_stable(struct work_struct *work) +static void __sched_clock_work(struct work_struct *work) { - /* XXX worry about clock continuity */ - if (sched_clock_stable()) - static_key_slow_dec(&__sched_clock_stable); - - tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); + static_branch_disable(&__sched_clock_stable); } -static DECLARE_WORK(sched_clock_work, __clear_sched_clock_stable); +static DECLARE_WORK(sched_clock_work, __sched_clock_work); -void clear_sched_clock_stable(void) +static void __clear_sched_clock_stable(void) { - __sched_clock_stable_early = 0; - - smp_mb(); /* matches sched_clock_init() */ - - if (!sched_clock_running) - return; - - schedule_work(&sched_clock_work); -} + struct sched_clock_data *scd = this_scd(); -struct sched_clock_data { - u64 tick_raw; - u64 tick_gtod; - u64 clock; -}; + /* + * Attempt to make the stable->unstable transition continuous. + * + * Trouble is, this is typically called from the TSC watchdog + * timer, which is late per definition. This means the tick + * values can already be screwy. + * + * Still do what we can. + */ + __gtod_offset = (scd->tick_raw + __sched_clock_offset) - (scd->tick_gtod); -static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data); + printk(KERN_INFO "sched_clock: Marking unstable (%lld, %lld)<-(%lld, %lld)\n", + scd->tick_gtod, __gtod_offset, + scd->tick_raw, __sched_clock_offset); -static inline struct sched_clock_data *this_scd(void) -{ - return this_cpu_ptr(&sched_clock_data); -} + tick_dep_set(TICK_DEP_BIT_CLOCK_UNSTABLE); -static inline struct sched_clock_data *cpu_sdc(int cpu) -{ - return &per_cpu(sched_clock_data, cpu); + if (sched_clock_stable()) + schedule_work(&sched_clock_work); } -void sched_clock_init(void) +void clear_sched_clock_stable(void) { - u64 ktime_now = ktime_to_ns(ktime_get()); - int cpu; - - for_each_possible_cpu(cpu) { - struct sched_clock_data *scd = cpu_sdc(cpu); + __sched_clock_stable_early = 0; - scd->tick_raw = 0; - scd->tick_gtod = ktime_now; - scd->clock = ktime_now; - } + smp_mb(); /* matches sched_clock_init_late() */ - sched_clock_running = 1; + if (sched_clock_running == 2) + __clear_sched_clock_stable(); +} +void sched_clock_init_late(void) +{ + sched_clock_running = 2; /* * Ensure that it is impossible to not do a static_key update. * @@ -173,8 +197,6 @@ void sched_clock_init(void) if (__sched_clock_stable_early) __set_sched_clock_stable(); - else - __clear_sched_clock_stable(NULL); } /* @@ -199,7 +221,7 @@ static inline u64 wrap_max(u64 x, u64 y) */ static u64 sched_clock_local(struct sched_clock_data *scd) { - u64 now, clock, old_clock, min_clock, max_clock; + u64 now, clock, old_clock, min_clock, max_clock, gtod; s64 delta; again: @@ -216,9 +238,10 @@ again: * scd->tick_gtod + TICK_NSEC); */ - clock = scd->tick_gtod + delta; - min_clock = wrap_max(scd->tick_gtod, old_clock); - max_clock = wrap_max(old_clock, scd->tick_gtod + TICK_NSEC); + gtod = scd->tick_gtod + __gtod_offset; + clock = gtod + delta; + min_clock = wrap_max(gtod, old_clock); + max_clock = wrap_max(old_clock, gtod + TICK_NSEC); clock = wrap_max(clock, min_clock); clock = wrap_min(clock, max_clock); @@ -302,7 +325,7 @@ u64 sched_clock_cpu(int cpu) u64 clock; if (sched_clock_stable()) - return sched_clock(); + return sched_clock() + __sched_clock_offset; if (unlikely(!sched_clock_running)) return 0ull; @@ -323,23 +346,22 @@ EXPORT_SYMBOL_GPL(sched_clock_cpu); void sched_clock_tick(void) { struct sched_clock_data *scd; - u64 now, now_gtod; - - if (sched_clock_stable()) - return; - - if (unlikely(!sched_clock_running)) - return; WARN_ON_ONCE(!irqs_disabled()); + /* + * Update these values even if sched_clock_stable(), because it can + * become unstable at any point in time at which point we need some + * values to fall back on. + * + * XXX arguably we can skip this if we expose tsc_clocksource_reliable + */ scd = this_scd(); - now_gtod = ktime_to_ns(ktime_get()); - now = sched_clock(); + scd->tick_raw = sched_clock(); + scd->tick_gtod = ktime_get_ns(); - scd->tick_raw = now; - scd->tick_gtod = now_gtod; - sched_clock_local(scd); + if (!sched_clock_stable() && likely(sched_clock_running)) + sched_clock_local(scd); } /* @@ -366,11 +388,6 @@ EXPORT_SYMBOL_GPL(sched_clock_idle_wakeup_event); #else /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ -void sched_clock_init(void) -{ - sched_clock_running = 1; -} - u64 sched_clock_cpu(int cpu) { if (unlikely(!sched_clock_running)) @@ -378,6 +395,7 @@ u64 sched_clock_cpu(int cpu) return sched_clock(); } + #endif /* CONFIG_HAVE_UNSTABLE_SCHED_CLOCK */ /* diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c index 8d0f35debf35..53f9558fa925 100644 --- a/kernel/sched/completion.c +++ b/kernel/sched/completion.c @@ -11,7 +11,8 @@ * Waiting for completion is a typically sync point, but not an exclusion point. */ -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/debug.h> #include <linux/completion.h> /** @@ -31,7 +32,8 @@ void complete(struct completion *x) unsigned long flags; spin_lock_irqsave(&x->wait.lock, flags); - x->done++; + if (x->done != UINT_MAX) + x->done++; __wake_up_locked(&x->wait, TASK_NORMAL, 1); spin_unlock_irqrestore(&x->wait.lock, flags); } @@ -51,7 +53,7 @@ void complete_all(struct completion *x) unsigned long flags; spin_lock_irqsave(&x->wait.lock, flags); - x->done += UINT_MAX/2; + x->done = UINT_MAX; __wake_up_locked(&x->wait, TASK_NORMAL, 0); spin_unlock_irqrestore(&x->wait.lock, flags); } @@ -79,7 +81,8 @@ do_wait_for_common(struct completion *x, if (!x->done) return timeout; } - x->done--; + if (x->done != UINT_MAX) + x->done--; return timeout ?: 1; } @@ -280,7 +283,7 @@ bool try_wait_for_completion(struct completion *x) spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; - else + else if (x->done != UINT_MAX) x->done--; spin_unlock_irqrestore(&x->wait.lock, flags); return ret; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 154fd689fe02..3b31fc05a0f1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1,85 +1,33 @@ /* * kernel/sched/core.c * - * Kernel scheduler and related syscalls + * Core kernel scheduler code and related syscalls * * Copyright (C) 1991-2002 Linus Torvalds - * - * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and - * make semaphores SMP safe - * 1998-11-19 Implemented schedule_timeout() and related stuff - * by Andrea Arcangeli - * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: - * hybrid priority-list and round-robin design with - * an array-switch method of distributing timeslices - * and per-CPU runqueues. Cleanups and useful suggestions - * by Davide Libenzi, preemptible kernel bits by Robert Love. - * 2003-09-03 Interactivity tuning by Con Kolivas. - * 2004-04-02 Scheduler domains code by Nick Piggin - * 2007-04-15 Work begun on replacing all interactivity tuning with a - * fair scheduling design by Con Kolivas. - * 2007-05-05 Load balancing (smp-nice) and other improvements - * by Peter Williams - * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith - * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri - * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, - * Thomas Gleixner, Mike Kravetz */ - -#include <linux/kasan.h> -#include <linux/mm.h> -#include <linux/module.h> -#include <linux/nmi.h> -#include <linux/init.h> -#include <linux/uaccess.h> -#include <linux/highmem.h> -#include <linux/mmu_context.h> -#include <linux/interrupt.h> -#include <linux/capability.h> -#include <linux/completion.h> -#include <linux/kernel_stat.h> -#include <linux/debug_locks.h> -#include <linux/perf_event.h> -#include <linux/security.h> -#include <linux/notifier.h> -#include <linux/profile.h> -#include <linux/freezer.h> -#include <linux/vmalloc.h> -#include <linux/blkdev.h> -#include <linux/delay.h> -#include <linux/pid_namespace.h> -#include <linux/smp.h> -#include <linux/threads.h> -#include <linux/timer.h> -#include <linux/rcupdate.h> -#include <linux/cpu.h> +#include <linux/sched.h> +#include <linux/sched/clock.h> +#include <uapi/linux/sched/types.h> +#include <linux/sched/loadavg.h> +#include <linux/sched/hotplug.h> #include <linux/cpuset.h> -#include <linux/percpu.h> -#include <linux/proc_fs.h> -#include <linux/seq_file.h> -#include <linux/sysctl.h> -#include <linux/syscalls.h> -#include <linux/times.h> -#include <linux/tsacct_kern.h> -#include <linux/kprobes.h> #include <linux/delayacct.h> -#include <linux/unistd.h> -#include <linux/pagemap.h> -#include <linux/hrtimer.h> -#include <linux/tick.h> -#include <linux/ctype.h> -#include <linux/ftrace.h> -#include <linux/slab.h> #include <linux/init_task.h> #include <linux/context_tracking.h> -#include <linux/compiler.h> -#include <linux/frame.h> +#include <linux/rcupdate_wait.h> + +#include <linux/blkdev.h> +#include <linux/kprobes.h> +#include <linux/mmu_context.h> +#include <linux/module.h> +#include <linux/nmi.h> #include <linux/prefetch.h> +#include <linux/profile.h> +#include <linux/security.h> +#include <linux/syscalls.h> #include <asm/switch_to.h> #include <asm/tlb.h> -#include <asm/irq_regs.h> -#include <asm/mutex.h> #ifdef CONFIG_PARAVIRT #include <asm/paravirt.h> #endif @@ -91,27 +39,8 @@ #define CREATE_TRACE_POINTS #include <trace/events/sched.h> -DEFINE_MUTEX(sched_domains_mutex); DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static void update_rq_clock_task(struct rq *rq, s64 delta); - -void update_rq_clock(struct rq *rq) -{ - s64 delta; - - lockdep_assert_held(&rq->lock); - - if (rq->clock_skip_update & RQCF_ACT_SKIP) - return; - - delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; - if (delta < 0) - return; - rq->clock += delta; - update_rq_clock_task(rq, delta); -} - /* * Debugging: various feature bits */ @@ -140,7 +69,7 @@ const_debug unsigned int sysctl_sched_nr_migrate = 32; const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; /* - * period over which we measure -rt task cpu usage in us. + * period over which we measure -rt task CPU usage in us. * default: 1s */ unsigned int sysctl_sched_rt_period = 1000000; @@ -153,7 +82,7 @@ __read_mostly int scheduler_running; */ int sysctl_sched_rt_runtime = 950000; -/* cpus with isolated domains */ +/* CPUs with isolated domains */ cpumask_var_t cpu_isolated_map; /* @@ -185,7 +114,7 @@ struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) rq = task_rq(p); raw_spin_lock(&rq->lock); if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { - rf->cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, rf); return rq; } raw_spin_unlock(&rq->lock); @@ -221,11 +150,11 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) * If we observe the old cpu in task_rq_lock, the acquire of * the old rq->lock will fully serialize against the stores. * - * If we observe the new cpu in task_rq_lock, the acquire will + * If we observe the new CPU in task_rq_lock, the acquire will * pair with the WMB to ensure we must then also see migrating. */ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) { - rf->cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, rf); return rq; } raw_spin_unlock(&rq->lock); @@ -236,6 +165,84 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) } } +/* + * RQ-clock updating methods: + */ + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + s64 steal = 0, irq_delta = 0; +#endif +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_key_false((¶virt_steal_rq_enabled))) { + steal = paravirt_steal_clock(cpu_of(rq)); + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + rq->prev_steal_time_rq += steal; + delta -= steal; + } +#endif + + rq->clock_task += delta; + +#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) + if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) + sched_rt_avg_update(rq, irq_delta + steal); +#endif +} + +void update_rq_clock(struct rq *rq) +{ + s64 delta; + + lockdep_assert_held(&rq->lock); + + if (rq->clock_update_flags & RQCF_ACT_SKIP) + return; + +#ifdef CONFIG_SCHED_DEBUG + rq->clock_update_flags |= RQCF_UPDATED; +#endif + delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + if (delta < 0) + return; + rq->clock += delta; + update_rq_clock_task(rq, delta); +} + + #ifdef CONFIG_SCHED_HRTICK /* * Use HR-timers to deliver accurate preemption points. @@ -458,7 +465,7 @@ void wake_up_q(struct wake_q_head *head) task = container_of(node, struct task_struct, wake_q); BUG_ON(!task); - /* task can safely be re-inserted now */ + /* Task can safely be re-inserted now: */ node = node->next; task->wake_q.next = NULL; @@ -516,12 +523,12 @@ void resched_cpu(int cpu) #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ_COMMON /* - * In the semi idle case, use the nearest busy cpu for migrating timers - * from an idle cpu. This is good for power-savings. + * In the semi idle case, use the nearest busy CPU for migrating timers + * from an idle CPU. This is good for power-savings. * * We don't do similar optimization for completely idle system, as - * selecting an idle cpu will add more delays to the timers than intended - * (as that cpu's timer base may not be uptodate wrt jiffies etc). + * selecting an idle CPU will add more delays to the timers than intended + * (as that CPU's timer base may not be uptodate wrt jiffies etc). */ int get_nohz_timer_target(void) { @@ -550,6 +557,7 @@ unlock: rcu_read_unlock(); return cpu; } + /* * When add_timer_on() enqueues a timer into the timer wheel of an * idle CPU then this timer might expire before the next timer event @@ -784,60 +792,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); } -static void update_rq_clock_task(struct rq *rq, s64 delta) -{ -/* - * In theory, the compile should just see 0 here, and optimize out the call - * to sched_rt_avg_update. But I don't trust it... - */ -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - s64 steal = 0, irq_delta = 0; -#endif -#ifdef CONFIG_IRQ_TIME_ACCOUNTING - irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; - - /* - * Since irq_time is only updated on {soft,}irq_exit, we might run into - * this case when a previous update_rq_clock() happened inside a - * {soft,}irq region. - * - * When this happens, we stop ->clock_task and only update the - * prev_irq_time stamp to account for the part that fit, so that a next - * update will consume the rest. This ensures ->clock_task is - * monotonic. - * - * It does however cause some slight miss-attribution of {soft,}irq - * time, a more accurate solution would be to update the irq_time using - * the current rq->clock timestamp, except that would require using - * atomic ops. - */ - if (irq_delta > delta) - irq_delta = delta; - - rq->prev_irq_time += irq_delta; - delta -= irq_delta; -#endif -#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING - if (static_key_false((¶virt_steal_rq_enabled))) { - steal = paravirt_steal_clock(cpu_of(rq)); - steal -= rq->prev_steal_time_rq; - - if (unlikely(steal > delta)) - steal = delta; - - rq->prev_steal_time_rq += steal; - delta -= steal; - } -#endif - - rq->clock_task += delta; - -#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING) - if ((irq_delta + steal) && sched_feat(NONTASK_CAPACITY)) - sched_rt_avg_update(rq, irq_delta + steal); -#endif -} - void sched_set_stop_task(int cpu, struct task_struct *stop) { struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; @@ -1018,7 +972,7 @@ struct migration_arg { }; /* - * Move (not current) task off this cpu, onto dest cpu. We're doing + * Move (not current) task off this CPU, onto the destination CPU. We're doing * this because either it can't run here any more (set_cpus_allowed() * away from this CPU, or CPU going down), or because we're * attempting to rebalance this task on exec (sched_exec). @@ -1032,7 +986,7 @@ static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_ return rq; /* Affinity changed (again). */ - if (!cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) return rq; rq = move_queued_task(rq, p, dest_cpu); @@ -1052,8 +1006,8 @@ static int migration_cpu_stop(void *data) struct rq *rq = this_rq(); /* - * The original target cpu might have gone down and we might - * be on another cpu but it doesn't matter. + * The original target CPU might have gone down and we might + * be on another CPU but it doesn't matter. */ local_irq_disable(); /* @@ -1141,6 +1095,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, int ret = 0; rq = task_rq_lock(p, &rf); + update_rq_clock(rq); if (p->flags & PF_KTHREAD) { /* @@ -1171,7 +1126,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, if (p->flags & PF_KTHREAD) { /* * For kernel threads that do indeed end up on online && - * !active we want to ensure they are strict per-cpu threads. + * !active we want to ensure they are strict per-CPU threads. */ WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && !cpumask_intersects(new_mask, cpu_active_mask) && @@ -1195,9 +1150,9 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, * OK, since we're going to drop the lock immediately * afterwards anyway. */ - lockdep_unpin_lock(&rq->lock, rf.cookie); + rq_unpin_lock(rq, &rf); rq = move_queued_task(rq, p, dest_cpu); - lockdep_repin_lock(&rq->lock, rf.cookie); + rq_repin_lock(rq, &rf); } out: task_rq_unlock(rq, p, &rf); @@ -1276,7 +1231,7 @@ static void __migrate_swap_task(struct task_struct *p, int cpu) /* * Task isn't running anymore; make it appear like we migrated * it before it went to sleep. This means on wakeup we make the - * previous cpu our target instead of where it really is. + * previous CPU our target instead of where it really is. */ p->wake_cpu = cpu; } @@ -1309,10 +1264,10 @@ static int migrate_swap_stop(void *data) if (task_cpu(arg->src_task) != arg->src_cpu) goto unlock; - if (!cpumask_test_cpu(arg->dst_cpu, tsk_cpus_allowed(arg->src_task))) + if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed)) goto unlock; - if (!cpumask_test_cpu(arg->src_cpu, tsk_cpus_allowed(arg->dst_task))) + if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed)) goto unlock; __migrate_swap_task(arg->src_task, arg->dst_cpu); @@ -1353,10 +1308,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p) if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu)) goto out; - if (!cpumask_test_cpu(arg.dst_cpu, tsk_cpus_allowed(arg.src_task))) + if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed)) goto out; - if (!cpumask_test_cpu(arg.src_cpu, tsk_cpus_allowed(arg.dst_task))) + if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed)) goto out; trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu); @@ -1456,7 +1411,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * yield - it could be a while. */ if (unlikely(queued)) { - ktime_t to = ktime_set(0, NSEC_PER_SEC/HZ); + ktime_t to = NSEC_PER_SEC / HZ; set_current_state(TASK_UNINTERRUPTIBLE); schedule_hrtimeout(&to, HRTIMER_MODE_REL); @@ -1508,12 +1463,12 @@ EXPORT_SYMBOL_GPL(kick_process); * * - on cpu-up we allow per-cpu kthreads on the online && !active cpu, * see __set_cpus_allowed_ptr(). At this point the newly online - * cpu isn't yet part of the sched domains, and balancing will not + * CPU isn't yet part of the sched domains, and balancing will not * see it. * - * - on cpu-down we clear cpu_active() to mask the sched domains and + * - on CPU-down we clear cpu_active() to mask the sched domains and * avoid the load balancer to place new tasks on the to be removed - * cpu. Existing tasks will remain running there and will be taken + * CPU. Existing tasks will remain running there and will be taken * off. * * This means that fallback selection must not select !active CPUs. @@ -1529,9 +1484,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) int dest_cpu; /* - * If the node that the cpu is on has been offlined, cpu_to_node() - * will return -1. There is no cpu on the node, and we should - * select the cpu on the other node. + * If the node that the CPU is on has been offlined, cpu_to_node() + * will return -1. There is no CPU on the node, and we should + * select the CPU on the other node. */ if (nid != -1) { nodemask = cpumask_of_node(nid); @@ -1540,14 +1495,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p) for_each_cpu(dest_cpu, nodemask) { if (!cpu_active(dest_cpu)) continue; - if (cpumask_test_cpu(dest_cpu, tsk_cpus_allowed(p))) + if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) return dest_cpu; } } for (;;) { /* Any allowed, online CPU? */ - for_each_cpu(dest_cpu, tsk_cpus_allowed(p)) { + for_each_cpu(dest_cpu, &p->cpus_allowed) { if (!(p->flags & PF_KTHREAD) && !cpu_active(dest_cpu)) continue; if (!cpu_online(dest_cpu)) @@ -1563,7 +1518,7 @@ static int select_fallback_rq(int cpu, struct task_struct *p) state = possible; break; } - /* fall-through */ + /* Fall-through */ case possible: do_set_cpus_allowed(p, cpu_possible_mask); state = fail; @@ -1599,22 +1554,22 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) { lockdep_assert_held(&p->pi_lock); - if (tsk_nr_cpus_allowed(p) > 1) + if (p->nr_cpus_allowed > 1) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); else - cpu = cpumask_any(tsk_cpus_allowed(p)); + cpu = cpumask_any(&p->cpus_allowed); /* * In order not to call set_task_cpu() on a blocking task we need * to rely on ttwu() to place the task on a valid ->cpus_allowed - * cpu. + * CPU. * * Since this is common to all placement strategies, this lives here. * * [ this allows ->select_task() to simply return task_cpu(p) and * not worry about this generic constraint ] */ - if (unlikely(!cpumask_test_cpu(cpu, tsk_cpus_allowed(p)) || + if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) || !cpu_online(cpu))) cpu = select_fallback_rq(task_cpu(p), p); @@ -1681,7 +1636,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl activate_task(rq, p, en_flags); p->on_rq = TASK_ON_RQ_QUEUED; - /* if a worker is waking up, notify workqueue */ + /* If a worker is waking up, notify the workqueue: */ if (p->flags & PF_WQ_WORKER) wq_worker_waking_up(p, cpu_of(rq)); } @@ -1690,7 +1645,7 @@ static inline void ttwu_activate(struct rq *rq, struct task_struct *p, int en_fl * Mark the task runnable and perform wakeup-preemption. */ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, - struct pin_cookie cookie) + struct rq_flags *rf) { check_preempt_curr(rq, p, wake_flags); p->state = TASK_RUNNING; @@ -1702,9 +1657,9 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, * Our task @p is fully woken up and running; so its safe to * drop the rq->lock, hereafter rq is only used for statistics. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); p->sched_class->task_woken(rq, p); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); } if (rq->idle_stamp) { @@ -1723,7 +1678,7 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags, static void ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, - struct pin_cookie cookie) + struct rq_flags *rf) { int en_flags = ENQUEUE_WAKEUP; @@ -1738,7 +1693,7 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags, #endif ttwu_activate(rq, p, en_flags); - ttwu_do_wakeup(rq, p, wake_flags, cookie); + ttwu_do_wakeup(rq, p, wake_flags, rf); } /* @@ -1757,7 +1712,7 @@ static int ttwu_remote(struct task_struct *p, int wake_flags) if (task_on_rq_queued(p)) { /* check_preempt_curr() may use rq clock */ update_rq_clock(rq); - ttwu_do_wakeup(rq, p, wake_flags, rf.cookie); + ttwu_do_wakeup(rq, p, wake_flags, &rf); ret = 1; } __task_rq_unlock(rq, &rf); @@ -1770,15 +1725,15 @@ void sched_ttwu_pending(void) { struct rq *rq = this_rq(); struct llist_node *llist = llist_del_all(&rq->wake_list); - struct pin_cookie cookie; struct task_struct *p; unsigned long flags; + struct rq_flags rf; if (!llist) return; raw_spin_lock_irqsave(&rq->lock, flags); - cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, &rf); while (llist) { int wake_flags = 0; @@ -1789,10 +1744,10 @@ void sched_ttwu_pending(void) if (p->sched_remote_wakeup) wake_flags = WF_MIGRATED; - ttwu_do_activate(rq, p, wake_flags, cookie); + ttwu_do_activate(rq, p, wake_flags, &rf); } - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, &rf); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -1864,7 +1819,7 @@ void wake_up_if_idle(int cpu) raw_spin_lock_irqsave(&rq->lock, flags); if (is_idle_task(rq->curr)) smp_send_reschedule(cpu); - /* Else cpu is not in idle, do nothing here */ + /* Else CPU is not idle, do nothing here: */ raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -1881,20 +1836,20 @@ bool cpus_share_cache(int this_cpu, int that_cpu) static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) { struct rq *rq = cpu_rq(cpu); - struct pin_cookie cookie; + struct rq_flags rf; #if defined(CONFIG_SMP) if (sched_feat(TTWU_QUEUE) && !cpus_share_cache(smp_processor_id(), cpu)) { - sched_clock_cpu(cpu); /* sync clocks x-cpu */ + sched_clock_cpu(cpu); /* Sync clocks across CPUs */ ttwu_queue_remote(p, cpu, wake_flags); return; } #endif raw_spin_lock(&rq->lock); - cookie = lockdep_pin_lock(&rq->lock); - ttwu_do_activate(rq, p, wake_flags, cookie); - lockdep_unpin_lock(&rq->lock, cookie); + rq_pin_lock(rq, &rf); + ttwu_do_activate(rq, p, wake_flags, &rf); + rq_unpin_lock(rq, &rf); raw_spin_unlock(&rq->lock); } @@ -1904,8 +1859,8 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * MIGRATION * * The basic program-order guarantee on SMP systems is that when a task [t] - * migrates, all its activity on its old cpu [c0] happens-before any subsequent - * execution on its new cpu [c1]. + * migrates, all its activity on its old CPU [c0] happens-before any subsequent + * execution on its new CPU [c1]. * * For migration (of runnable tasks) this is provided by the following means: * @@ -1916,7 +1871,7 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * * Transitivity guarantees that B happens after A and C after B. * Note: we only require RCpc transitivity. - * Note: the cpu doing B need not be c0 or c1 + * Note: the CPU doing B need not be c0 or c1 * * Example: * @@ -1995,14 +1950,15 @@ static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags) * @state: the mask of task states that can be woken * @wake_flags: wake modifier flags (WF_*) * - * Put it on the run-queue if it's not already there. The "current" - * thread is always on the run-queue (except when the actual - * re-schedule is in progress), and as such you're allowed to do - * the simpler "current->state = TASK_RUNNING" to mark yourself - * runnable without the overhead of this. + * If (@state & @p->state) @p->state = TASK_RUNNING. + * + * If the task was not queued/runnable, also place it back on a runqueue. + * + * Atomic against schedule() which would dequeue a task, also see + * set_current_state(). * - * Return: %true if @p was woken up, %false if it was already running. - * or @state didn't match @p's state. + * Return: %true if @p->state changes (an actual wakeup was done), + * %false otherwise. */ static int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) @@ -2023,7 +1979,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) trace_sched_waking(p); - success = 1; /* we're going to change ->state */ + /* We're going to change ->state: */ + success = 1; cpu = task_cpu(p); /* @@ -2072,7 +2029,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) smp_rmb(); /* - * If the owning (remote) cpu is still in the middle of schedule() with + * If the owning (remote) CPU is still in the middle of schedule() with * this task as prev, wait until its done referencing the task. * * Pairs with the smp_store_release() in finish_lock_switch(). @@ -2085,11 +2042,24 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) p->sched_contributes_to_load = !!task_contributes_to_load(p); p->state = TASK_WAKING; + if (p->in_iowait) { + delayacct_blkio_end(); + atomic_dec(&task_rq(p)->nr_iowait); + } + cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; set_task_cpu(p, cpu); } + +#else /* CONFIG_SMP */ + + if (p->in_iowait) { + delayacct_blkio_end(); + atomic_dec(&task_rq(p)->nr_iowait); + } + #endif /* CONFIG_SMP */ ttwu_queue(p, cpu, wake_flags); @@ -2110,7 +2080,7 @@ out: * ensure that this_rq() is locked, @p is bound to this_rq() and not * the current task. */ -static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie) +static void try_to_wake_up_local(struct task_struct *p, struct rq_flags *rf) { struct rq *rq = task_rq(p); @@ -2127,11 +2097,11 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie * disabled avoiding further scheduler activity on it and we've * not yet picked a replacement task. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); raw_spin_lock(&p->pi_lock); raw_spin_lock(&rq->lock); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); } if (!(p->state & TASK_NORMAL)) @@ -2139,10 +2109,15 @@ static void try_to_wake_up_local(struct task_struct *p, struct pin_cookie cookie trace_sched_waking(p); - if (!task_on_rq_queued(p)) + if (!task_on_rq_queued(p)) { + if (p->in_iowait) { + delayacct_blkio_end(); + atomic_dec(&rq->nr_iowait); + } ttwu_activate(rq, p, ENQUEUE_WAKEUP); + } - ttwu_do_wakeup(rq, p, 0, cookie); + ttwu_do_wakeup(rq, p, 0, rf); ttwu_stat(p, smp_processor_id(), 0); out: raw_spin_unlock(&p->pi_lock); @@ -2426,7 +2401,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) */ raw_spin_lock_irqsave(&p->pi_lock, flags); /* - * We're setting the cpu for the first time, we don't migrate, + * We're setting the CPU for the first time, we don't migrate, * so use __set_task_cpu(). */ __set_task_cpu(p, cpu); @@ -2569,7 +2544,7 @@ void wake_up_new_task(struct task_struct *p) /* * Fork balancing, do it here and not earlier because: * - cpus_allowed can change in the fork path - * - any previously selected cpu might disappear through hotplug + * - any previously selected CPU might disappear through hotplug * * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq, * as we're not fully set-up yet. @@ -2577,6 +2552,7 @@ void wake_up_new_task(struct task_struct *p) __set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0)); #endif rq = __task_rq_lock(p, &rf); + update_rq_clock(rq); post_init_entity_util_avg(&p->se); activate_task(rq, p, 0); @@ -2589,9 +2565,9 @@ void wake_up_new_task(struct task_struct *p) * Nothing relies on rq->lock after this, so its fine to * drop it. */ - lockdep_unpin_lock(&rq->lock, rf.cookie); + rq_unpin_lock(rq, &rf); p->sched_class->task_woken(rq, p); - lockdep_repin_lock(&rq->lock, rf.cookie); + rq_repin_lock(rq, &rf); } #endif task_rq_unlock(rq, p, &rf); @@ -2860,7 +2836,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) */ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, - struct task_struct *next, struct pin_cookie cookie) + struct task_struct *next, struct rq_flags *rf) { struct mm_struct *mm, *oldmm; @@ -2877,7 +2853,7 @@ context_switch(struct rq *rq, struct task_struct *prev, if (!mm) { next->active_mm = oldmm; - atomic_inc(&oldmm->mm_count); + mmgrab(oldmm); enter_lazy_tlb(oldmm, next); } else switch_mm_irqs_off(oldmm, mm, next); @@ -2886,13 +2862,16 @@ context_switch(struct rq *rq, struct task_struct *prev, prev->active_mm = NULL; rq->prev_mm = oldmm; } + + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); + /* * Since the runqueue lock will be released by the next * task (which is an invalid locking op but in the case * of the scheduler it's an obvious special-case), so we * do an early lockdep release here: */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); /* Here we just switch the register state and the stack. */ @@ -2919,7 +2898,7 @@ unsigned long nr_running(void) } /* - * Check if only the current task is running on the cpu. + * Check if only the current task is running on the CPU. * * Caution: this function does not check that the caller has disabled * preemption, thus the result might have a time-of-check-to-time-of-use @@ -2948,6 +2927,36 @@ unsigned long long nr_context_switches(void) return sum; } +/* + * IO-wait accounting, and how its mostly bollocks (on SMP). + * + * The idea behind IO-wait account is to account the idle time that we could + * have spend running if it were not for IO. That is, if we were to improve the + * storage performance, we'd have a proportional reduction in IO-wait time. + * + * This all works nicely on UP, where, when a task blocks on IO, we account + * idle time as IO-wait, because if the storage were faster, it could've been + * running and we'd not be idle. + * + * This has been extended to SMP, by doing the same for each CPU. This however + * is broken. + * + * Imagine for instance the case where two tasks block on one CPU, only the one + * CPU will have IO-wait accounted, while the other has regular idle. Even + * though, if the storage were faster, both could've ran at the same time, + * utilising both CPUs. + * + * This means, that when looking globally, the current IO-wait accounting on + * SMP is a lower bound, by reason of under accounting. + * + * Worse, since the numbers are provided per CPU, they are sometimes + * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly + * associated with any one particular CPU, it can wake to another CPU than it + * blocked on. This means the per CPU IO-wait number is meaningless. + * + * Task CPU affinities can make all that even more 'interesting'. + */ + unsigned long nr_iowait(void) { unsigned long i, sum = 0; @@ -2958,6 +2967,13 @@ unsigned long nr_iowait(void) return sum; } +/* + * Consumers of these two interfaces, like for example the cpufreq menu + * governor are using nonsensical data. Boosting frequency for a CPU that has + * IO-wait which might not even end up running the task when it does become + * runnable. + */ + unsigned long nr_iowait_cpu(int cpu) { struct rq *this = cpu_rq(cpu); @@ -3041,8 +3057,8 @@ unsigned long long task_sched_runtime(struct task_struct *p) * So we have a optimization chance when the task's delta_exec is 0. * Reading ->on_cpu is racy, but this is ok. * - * If we race with it leaving cpu, we'll take a lock. So we're correct. - * If we race with it entering cpu, unaccounted time is 0. This is + * If we race with it leaving CPU, we'll take a lock. So we're correct. + * If we race with it entering CPU, unaccounted time is 0. This is * indistinguishable from the read occurring a few cycles earlier. * If we see ->on_cpu without ->on_rq, the task is leaving, and has * been accounted, so we're correct here as well. @@ -3200,6 +3216,15 @@ static inline void preempt_latency_start(int val) { } static inline void preempt_latency_stop(int val) { } #endif +static inline unsigned long get_preempt_disable_ip(struct task_struct *p) +{ +#ifdef CONFIG_DEBUG_PREEMPT + return p->preempt_disable_ip; +#else + return 0; +#endif +} + /* * Print scheduling while atomic bug: */ @@ -3256,31 +3281,35 @@ static inline void schedule_debug(struct task_struct *prev) * Pick up the highest-prio task: */ static inline struct task_struct * -pick_next_task(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { - const struct sched_class *class = &fair_sched_class; + const struct sched_class *class; struct task_struct *p; /* - * Optimization: we know that if all tasks are in - * the fair class we can call that function directly: + * Optimization: we know that if all tasks are in the fair class we can + * call that function directly, but only if the @prev task wasn't of a + * higher scheduling class, because otherwise those loose the + * opportunity to pull in more work from other CPUs. */ - if (likely(prev->sched_class == class && + if (likely((prev->sched_class == &idle_sched_class || + prev->sched_class == &fair_sched_class) && rq->nr_running == rq->cfs.h_nr_running)) { - p = fair_sched_class.pick_next_task(rq, prev, cookie); + + p = fair_sched_class.pick_next_task(rq, prev, rf); if (unlikely(p == RETRY_TASK)) goto again; - /* assumes fair_sched_class->next == idle_sched_class */ + /* Assumes fair_sched_class->next == idle_sched_class */ if (unlikely(!p)) - p = idle_sched_class.pick_next_task(rq, prev, cookie); + p = idle_sched_class.pick_next_task(rq, prev, rf); return p; } again: for_each_class(class) { - p = class->pick_next_task(rq, prev, cookie); + p = class->pick_next_task(rq, prev, rf); if (p) { if (unlikely(p == RETRY_TASK)) goto again; @@ -3288,7 +3317,8 @@ again: } } - BUG(); /* the idle class will always have a runnable task */ + /* The idle class should always have a runnable task: */ + BUG(); } /* @@ -3334,7 +3364,7 @@ static void __sched notrace __schedule(bool preempt) { struct task_struct *prev, *next; unsigned long *switch_count; - struct pin_cookie cookie; + struct rq_flags rf; struct rq *rq; int cpu; @@ -3357,9 +3387,10 @@ static void __sched notrace __schedule(bool preempt) */ smp_mb__before_spinlock(); raw_spin_lock(&rq->lock); - cookie = lockdep_pin_lock(&rq->lock); + rq_pin_lock(rq, &rf); - rq->clock_skip_update <<= 1; /* promote REQ to ACT */ + /* Promote REQ to ACT */ + rq->clock_update_flags <<= 1; switch_count = &prev->nivcsw; if (!preempt && prev->state) { @@ -3369,6 +3400,11 @@ static void __sched notrace __schedule(bool preempt) deactivate_task(rq, prev, DEQUEUE_SLEEP); prev->on_rq = 0; + if (prev->in_iowait) { + atomic_inc(&rq->nr_iowait); + delayacct_blkio_start(); + } + /* * If a worker went to sleep, notify and ask workqueue * whether it wants to wake up a task to maintain @@ -3379,7 +3415,7 @@ static void __sched notrace __schedule(bool preempt) to_wakeup = wq_worker_sleeping(prev); if (to_wakeup) - try_to_wake_up_local(to_wakeup, cookie); + try_to_wake_up_local(to_wakeup, &rf); } } switch_count = &prev->nvcsw; @@ -3388,10 +3424,9 @@ static void __sched notrace __schedule(bool preempt) if (task_on_rq_queued(prev)) update_rq_clock(rq); - next = pick_next_task(rq, prev, cookie); + next = pick_next_task(rq, prev, &rf); clear_tsk_need_resched(prev); clear_preempt_need_resched(); - rq->clock_skip_update = 0; if (likely(prev != next)) { rq->nr_switches++; @@ -3399,9 +3434,12 @@ static void __sched notrace __schedule(bool preempt) ++*switch_count; trace_sched_switch(preempt, prev, next); - rq = context_switch(rq, prev, next, cookie); /* unlocks the rq */ + + /* Also unlocks the rq: */ + rq = context_switch(rq, prev, next, &rf); } else { - lockdep_unpin_lock(&rq->lock, cookie); + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); + rq_unpin_lock(rq, &rf); raw_spin_unlock_irq(&rq->lock); } @@ -3425,14 +3463,18 @@ void __noreturn do_task_dead(void) smp_mb(); raw_spin_unlock_wait(¤t->pi_lock); - /* causes final put_task_struct in finish_task_switch(). */ + /* Causes final put_task_struct in finish_task_switch(): */ __set_current_state(TASK_DEAD); - current->flags |= PF_NOFREEZE; /* tell freezer to ignore us */ + + /* Tell freezer to ignore us: */ + current->flags |= PF_NOFREEZE; + __schedule(false); BUG(); - /* Avoid "noreturn function does return". */ + + /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */ for (;;) - cpu_relax(); /* For when BUG is null */ + cpu_relax(); } static inline void sched_submit_work(struct task_struct *tsk) @@ -3650,6 +3692,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) BUG_ON(prio > MAX_PRIO); rq = __task_rq_lock(p, &rf); + update_rq_clock(rq); /* * Idle task boosting is a nono in general. There is one @@ -3724,7 +3767,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) check_class_changed(rq, p, prev_class, oldprio); out_unlock: - preempt_disable(); /* avoid rq from going away on us */ + /* Avoid rq from going away on us: */ + preempt_disable(); __task_rq_unlock(rq, &rf); balance_callback(rq); @@ -3746,6 +3790,8 @@ void set_user_nice(struct task_struct *p, long nice) * the task might be in the middle of scheduling on another CPU. */ rq = task_rq_lock(p, &rf); + update_rq_clock(rq); + /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected @@ -3792,7 +3838,7 @@ 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] */ + /* Convert nice value [19,-20] to rlimit style value [1,40]: */ int nice_rlim = nice_to_rlimit(nice); return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || @@ -3848,7 +3894,7 @@ int task_prio(const struct task_struct *p) } /** - * idle_cpu - is a given cpu idle currently? + * idle_cpu - is a given CPU idle currently? * @cpu: the processor in question. * * Return: 1 if the CPU is currently idle. 0 otherwise. @@ -3872,10 +3918,10 @@ int idle_cpu(int cpu) } /** - * idle_task - return the idle task for a given cpu. + * idle_task - return the idle task for a given CPU. * @cpu: the processor in question. * - * Return: The idle task for the cpu @cpu. + * Return: The idle task for the CPU @cpu. */ struct task_struct *idle_task(int cpu) { @@ -4041,7 +4087,7 @@ __checkparam_dl(const struct sched_attr *attr) } /* - * check the target process has a UID that matches the current process's + * Check the target process has a UID that matches the current process's: */ static bool check_same_owner(struct task_struct *p) { @@ -4056,8 +4102,7 @@ static bool check_same_owner(struct task_struct *p) return match; } -static bool dl_param_changed(struct task_struct *p, - const struct sched_attr *attr) +static bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr) { struct sched_dl_entity *dl_se = &p->dl; @@ -4084,10 +4129,10 @@ static int __sched_setscheduler(struct task_struct *p, int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE; struct rq *rq; - /* may grab non-irq protected spin_locks */ + /* May grab non-irq protected spin_locks: */ BUG_ON(in_interrupt()); recheck: - /* double check policy once rq lock held */ + /* Double check policy once rq lock held: */ if (policy < 0) { reset_on_fork = p->sched_reset_on_fork; policy = oldpolicy = p->policy; @@ -4127,11 +4172,11 @@ recheck: unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); - /* can't set/change the rt policy */ + /* Can't set/change the rt policy: */ if (policy != p->policy && !rlim_rtprio) return -EPERM; - /* can't increase priority */ + /* Can't increase priority: */ if (attr->sched_priority > p->rt_priority && attr->sched_priority > rlim_rtprio) return -EPERM; @@ -4155,11 +4200,11 @@ recheck: return -EPERM; } - /* can't change other user's priorities */ + /* Can't change other user's priorities: */ if (!check_same_owner(p)) return -EPERM; - /* Normal users shall not reset the sched_reset_on_fork flag */ + /* Normal users shall not reset the sched_reset_on_fork flag: */ if (p->sched_reset_on_fork && !reset_on_fork) return -EPERM; } @@ -4171,16 +4216,17 @@ recheck: } /* - * make sure no PI-waiters arrive (or leave) while we are + * Make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: * * To be able to change p->policy safely, the appropriate * runqueue lock must be held. */ rq = task_rq_lock(p, &rf); + update_rq_clock(rq); /* - * Changing the policy of the stop threads its a very bad idea + * Changing the policy of the stop threads its a very bad idea: */ if (p == rq->stop) { task_rq_unlock(rq, p, &rf); @@ -4236,7 +4282,7 @@ change: #endif } - /* recheck policy now with rq lock held */ + /* Re-check policy now with rq lock held: */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; task_rq_unlock(rq, p, &rf); @@ -4293,15 +4339,15 @@ change: set_curr_task(rq, p); check_class_changed(rq, p, prev_class, oldprio); - preempt_disable(); /* avoid rq from going away on us */ + + /* Avoid rq from going away on us: */ + preempt_disable(); task_rq_unlock(rq, p, &rf); if (pi) rt_mutex_adjust_pi(p); - /* - * Run balance callbacks after we've adjusted the PI chain. - */ + /* Run balance callbacks after we've adjusted the PI chain: */ balance_callback(rq); preempt_enable(); @@ -4394,8 +4440,7 @@ do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) /* * Mimics kernel/events/core.c perf_copy_attr(). */ -static int sched_copy_attr(struct sched_attr __user *uattr, - struct sched_attr *attr) +static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr) { u32 size; int ret; @@ -4403,19 +4448,19 @@ static int sched_copy_attr(struct sched_attr __user *uattr, if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) return -EFAULT; - /* - * zero the full structure, so that a short copy will be nice. - */ + /* Zero the full structure, so that a short copy will be nice: */ memset(attr, 0, sizeof(*attr)); ret = get_user(size, &uattr->size); if (ret) return ret; - if (size > PAGE_SIZE) /* silly large */ + /* Bail out on silly large: */ + if (size > PAGE_SIZE) goto err_size; - if (!size) /* abi compat */ + /* ABI compatibility quirk: */ + if (!size) size = SCHED_ATTR_SIZE_VER0; if (size < SCHED_ATTR_SIZE_VER0) @@ -4450,7 +4495,7 @@ static int sched_copy_attr(struct sched_attr __user *uattr, return -EFAULT; /* - * XXX: do we want to be lenient like existing syscalls; or do we want + * XXX: Do we want to be lenient like existing syscalls; or do we want * to be strict and return an error on out-of-bounds values? */ attr->sched_nice = clamp(attr->sched_nice, MIN_NICE, MAX_NICE); @@ -4470,10 +4515,8 @@ err_size: * * Return: 0 on success. An error code otherwise. */ -SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, - struct sched_param __user *, param) +SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param) { - /* negative values for policy are not valid */ if (policy < 0) return -EINVAL; @@ -4783,10 +4826,10 @@ static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, } /** - * sys_sched_setaffinity - set the cpu affinity of a process + * sys_sched_setaffinity - set the CPU affinity of a process * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to the new cpu mask + * @user_mask_ptr: user-space pointer to the new CPU mask * * Return: 0 on success. An error code otherwise. */ @@ -4834,10 +4877,10 @@ out_unlock: } /** - * sys_sched_getaffinity - get the cpu affinity of a process + * sys_sched_getaffinity - get the CPU affinity of a process * @pid: pid of the process * @len: length in bytes of the bitmask pointed to by user_mask_ptr - * @user_mask_ptr: user-space pointer to hold the current cpu mask + * @user_mask_ptr: user-space pointer to hold the current CPU mask * * Return: size of CPU mask copied to user_mask_ptr on success. An * error code otherwise. @@ -4965,7 +5008,7 @@ EXPORT_SYMBOL(__cond_resched_softirq); * Typical broken usage is: * * while (!event) - * yield(); + * yield(); * * where one assumes that yield() will let 'the other' process run that will * make event true. If the current task is a SCHED_FIFO task that will never @@ -5056,31 +5099,48 @@ out_irq: } EXPORT_SYMBOL_GPL(yield_to); +int io_schedule_prepare(void) +{ + int old_iowait = current->in_iowait; + + current->in_iowait = 1; + blk_schedule_flush_plug(current); + + return old_iowait; +} + +void io_schedule_finish(int token) +{ + current->in_iowait = token; +} + /* * This task is about to go to sleep on IO. Increment rq->nr_iowait so * that process accounting knows that this is a task in IO wait state. */ long __sched io_schedule_timeout(long timeout) { - int old_iowait = current->in_iowait; - struct rq *rq; + int token; long ret; - current->in_iowait = 1; - blk_schedule_flush_plug(current); - - delayacct_blkio_start(); - rq = raw_rq(); - atomic_inc(&rq->nr_iowait); + token = io_schedule_prepare(); ret = schedule_timeout(timeout); - current->in_iowait = old_iowait; - atomic_dec(&rq->nr_iowait); - delayacct_blkio_end(); + io_schedule_finish(token); return ret; } EXPORT_SYMBOL(io_schedule_timeout); +void io_schedule(void) +{ + int token; + + token = io_schedule_prepare(); + schedule(); + io_schedule_finish(token); +} +EXPORT_SYMBOL(io_schedule); + /** * sys_sched_get_priority_max - return maximum RT priority. * @policy: scheduling class. @@ -5192,6 +5252,9 @@ void sched_show_task(struct task_struct *p) int ppid; unsigned long state = p->state; + /* Make sure the string lines up properly with the number of task states: */ + BUILD_BUG_ON(sizeof(TASK_STATE_TO_CHAR_STR)-1 != ilog2(TASK_STATE_MAX)+1); + if (!try_get_task_stack(p)) return; if (state) @@ -5263,7 +5326,7 @@ void init_idle_bootup_task(struct task_struct *idle) /** * init_idle - set up an idle thread for a given CPU * @idle: task in question - * @cpu: cpu the idle task belongs to + * @cpu: CPU the idle task belongs to * * NOTE: this function does not set the idle thread's NEED_RESCHED * flag, to make booting more robust. @@ -5279,6 +5342,7 @@ void init_idle(struct task_struct *idle, int cpu) __sched_fork(0, idle); idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); + idle->flags |= PF_IDLE; kasan_unpoison_task_stack(idle); @@ -5293,7 +5357,7 @@ void init_idle(struct task_struct *idle, int cpu) #endif /* * We're having a chicken and egg problem, even though we are - * holding rq->lock, the cpu isn't yet set to this cpu so the + * holding rq->lock, the CPU isn't yet set to this CPU so the * lockdep check in task_group() will fail. * * Similar case to sched_fork(). / Alternatively we could @@ -5358,7 +5422,7 @@ int task_can_attach(struct task_struct *p, /* * Kthreads which disallow setaffinity shouldn't be moved - * to a new cpuset; we don't want to change their cpu + * to a new cpuset; we don't want to change their CPU * affinity and isolating such threads by their set of * allowed nodes is unnecessary. Thus, cpusets are not * applicable for such threads. This prevents checking for @@ -5407,7 +5471,7 @@ out: #ifdef CONFIG_SMP -static bool sched_smp_initialized __read_mostly; +bool sched_smp_initialized __read_mostly; #ifdef CONFIG_NUMA_BALANCING /* Migrate current task p to target_cpu */ @@ -5419,7 +5483,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu) if (curr_cpu == target_cpu) return 0; - if (!cpumask_test_cpu(target_cpu, tsk_cpus_allowed(p))) + if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed)) return -EINVAL; /* TODO: This is not properly updating schedstats */ @@ -5459,7 +5523,7 @@ void sched_setnuma(struct task_struct *p, int nid) #ifdef CONFIG_HOTPLUG_CPU /* - * Ensures that the idle task is using init_mm right before its cpu goes + * Ensure that the idle task is using init_mm right before its CPU goes * offline. */ void idle_task_exit(void) @@ -5519,7 +5583,7 @@ static void migrate_tasks(struct rq *dead_rq) { struct rq *rq = dead_rq; struct task_struct *next, *stop = rq->stop; - struct pin_cookie cookie; + struct rq_flags rf; int dest_cpu; /* @@ -5538,21 +5602,23 @@ static void migrate_tasks(struct rq *dead_rq) * class method both need to have an up-to-date * value of rq->clock[_task] */ + rq_pin_lock(rq, &rf); update_rq_clock(rq); + rq_unpin_lock(rq, &rf); for (;;) { /* * There's this thread running, bail when that's the only - * remaining thread. + * remaining thread: */ if (rq->nr_running == 1) break; /* - * pick_next_task assumes pinned rq->lock. + * pick_next_task() assumes pinned rq->lock: */ - cookie = lockdep_pin_lock(&rq->lock); - next = pick_next_task(rq, &fake_task, cookie); + rq_repin_lock(rq, &rf); + next = pick_next_task(rq, &fake_task, &rf); BUG_ON(!next); next->sched_class->put_prev_task(rq, next); @@ -5565,7 +5631,7 @@ static void migrate_tasks(struct rq *dead_rq) * because !cpu_active at this point, which means load-balance * will not interfere. Also, stop-machine. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, &rf); raw_spin_unlock(&rq->lock); raw_spin_lock(&next->pi_lock); raw_spin_lock(&rq->lock); @@ -5596,7 +5662,7 @@ static void migrate_tasks(struct rq *dead_rq) } #endif /* CONFIG_HOTPLUG_CPU */ -static void set_rq_online(struct rq *rq) +void set_rq_online(struct rq *rq) { if (!rq->online) { const struct sched_class *class; @@ -5611,7 +5677,7 @@ static void set_rq_online(struct rq *rq) } } -static void set_rq_offline(struct rq *rq) +void set_rq_offline(struct rq *rq) { if (rq->online) { const struct sched_class *class; @@ -5633,1631 +5699,10 @@ static void set_cpu_rq_start_time(unsigned int cpu) rq->age_stamp = sched_clock_cpu(cpu); } -static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ - -#ifdef CONFIG_SCHED_DEBUG - -static __read_mostly int sched_debug_enabled; - -static int __init sched_debug_setup(char *str) -{ - sched_debug_enabled = 1; - - return 0; -} -early_param("sched_debug", sched_debug_setup); - -static inline bool sched_debug(void) -{ - return sched_debug_enabled; -} - -static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, - struct cpumask *groupmask) -{ - struct sched_group *group = sd->groups; - - cpumask_clear(groupmask); - - printk(KERN_DEBUG "%*s domain %d: ", level, "", level); - - if (!(sd->flags & SD_LOAD_BALANCE)) { - printk("does not load-balance\n"); - if (sd->parent) - printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" - " has parent"); - return -1; - } - - printk(KERN_CONT "span %*pbl level %s\n", - cpumask_pr_args(sched_domain_span(sd)), sd->name); - - if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { - printk(KERN_ERR "ERROR: domain->span does not contain " - "CPU%d\n", cpu); - } - if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { - printk(KERN_ERR "ERROR: domain->groups does not contain" - " CPU%d\n", cpu); - } - - printk(KERN_DEBUG "%*s groups:", level + 1, ""); - do { - if (!group) { - printk("\n"); - printk(KERN_ERR "ERROR: group is NULL\n"); - break; - } - - if (!cpumask_weight(sched_group_cpus(group))) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: empty group\n"); - break; - } - - if (!(sd->flags & SD_OVERLAP) && - cpumask_intersects(groupmask, sched_group_cpus(group))) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: repeated CPUs\n"); - break; - } - - cpumask_or(groupmask, groupmask, sched_group_cpus(group)); - - printk(KERN_CONT " %*pbl", - cpumask_pr_args(sched_group_cpus(group))); - if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { - printk(KERN_CONT " (cpu_capacity = %d)", - group->sgc->capacity); - } - - group = group->next; - } while (group != sd->groups); - printk(KERN_CONT "\n"); - - if (!cpumask_equal(sched_domain_span(sd), groupmask)) - printk(KERN_ERR "ERROR: groups don't span domain->span\n"); - - if (sd->parent && - !cpumask_subset(groupmask, sched_domain_span(sd->parent))) - printk(KERN_ERR "ERROR: parent span is not a superset " - "of domain->span\n"); - return 0; -} - -static void sched_domain_debug(struct sched_domain *sd, int cpu) -{ - int level = 0; - - if (!sched_debug_enabled) - return; - - if (!sd) { - printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); - return; - } - - printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); - - for (;;) { - if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) - break; - level++; - sd = sd->parent; - if (!sd) - break; - } -} -#else /* !CONFIG_SCHED_DEBUG */ - -# define sched_debug_enabled 0 -# define sched_domain_debug(sd, cpu) do { } while (0) -static inline bool sched_debug(void) -{ - return false; -} -#endif /* CONFIG_SCHED_DEBUG */ - -static int sd_degenerate(struct sched_domain *sd) -{ - if (cpumask_weight(sched_domain_span(sd)) == 1) - return 1; - - /* Following flags need at least 2 groups */ - if (sd->flags & (SD_LOAD_BALANCE | - SD_BALANCE_NEWIDLE | - SD_BALANCE_FORK | - SD_BALANCE_EXEC | - SD_SHARE_CPUCAPACITY | - SD_ASYM_CPUCAPACITY | - SD_SHARE_PKG_RESOURCES | - SD_SHARE_POWERDOMAIN)) { - if (sd->groups != sd->groups->next) - return 0; - } - - /* Following flags don't use groups */ - if (sd->flags & (SD_WAKE_AFFINE)) - return 0; - - return 1; -} - -static int -sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) -{ - unsigned long cflags = sd->flags, pflags = parent->flags; - - if (sd_degenerate(parent)) - return 1; - - if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) - return 0; - - /* Flags needing groups don't count if only 1 group in parent */ - if (parent->groups == parent->groups->next) { - pflags &= ~(SD_LOAD_BALANCE | - SD_BALANCE_NEWIDLE | - SD_BALANCE_FORK | - SD_BALANCE_EXEC | - SD_ASYM_CPUCAPACITY | - SD_SHARE_CPUCAPACITY | - SD_SHARE_PKG_RESOURCES | - SD_PREFER_SIBLING | - SD_SHARE_POWERDOMAIN); - if (nr_node_ids == 1) - pflags &= ~SD_SERIALIZE; - } - if (~cflags & pflags) - return 0; - - return 1; -} - -static void free_rootdomain(struct rcu_head *rcu) -{ - struct root_domain *rd = container_of(rcu, struct root_domain, rcu); - - cpupri_cleanup(&rd->cpupri); - cpudl_cleanup(&rd->cpudl); - free_cpumask_var(rd->dlo_mask); - free_cpumask_var(rd->rto_mask); - free_cpumask_var(rd->online); - free_cpumask_var(rd->span); - kfree(rd); -} - -static void rq_attach_root(struct rq *rq, struct root_domain *rd) -{ - struct root_domain *old_rd = NULL; - unsigned long flags; - - raw_spin_lock_irqsave(&rq->lock, flags); - - if (rq->rd) { - old_rd = rq->rd; - - if (cpumask_test_cpu(rq->cpu, old_rd->online)) - set_rq_offline(rq); - - cpumask_clear_cpu(rq->cpu, old_rd->span); - - /* - * If we dont want to free the old_rd yet then - * set old_rd to NULL to skip the freeing later - * in this function: - */ - if (!atomic_dec_and_test(&old_rd->refcount)) - old_rd = NULL; - } - - atomic_inc(&rd->refcount); - rq->rd = rd; - - cpumask_set_cpu(rq->cpu, rd->span); - if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) - set_rq_online(rq); - - raw_spin_unlock_irqrestore(&rq->lock, flags); - - if (old_rd) - call_rcu_sched(&old_rd->rcu, free_rootdomain); -} - -static int init_rootdomain(struct root_domain *rd) -{ - memset(rd, 0, sizeof(*rd)); - - if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) - goto out; - if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) - goto free_span; - if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) - goto free_online; - if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) - goto free_dlo_mask; - - init_dl_bw(&rd->dl_bw); - if (cpudl_init(&rd->cpudl) != 0) - goto free_dlo_mask; - - if (cpupri_init(&rd->cpupri) != 0) - goto free_rto_mask; - return 0; - -free_rto_mask: - free_cpumask_var(rd->rto_mask); -free_dlo_mask: - free_cpumask_var(rd->dlo_mask); -free_online: - free_cpumask_var(rd->online); -free_span: - free_cpumask_var(rd->span); -out: - return -ENOMEM; -} - -/* - * By default the system creates a single root-domain with all cpus as - * members (mimicking the global state we have today). - */ -struct root_domain def_root_domain; - -static void init_defrootdomain(void) -{ - init_rootdomain(&def_root_domain); - - atomic_set(&def_root_domain.refcount, 1); -} - -static struct root_domain *alloc_rootdomain(void) -{ - struct root_domain *rd; - - rd = kmalloc(sizeof(*rd), GFP_KERNEL); - if (!rd) - return NULL; - - if (init_rootdomain(rd) != 0) { - kfree(rd); - return NULL; - } - - return rd; -} - -static void free_sched_groups(struct sched_group *sg, int free_sgc) -{ - struct sched_group *tmp, *first; - - if (!sg) - return; - - first = sg; - do { - tmp = sg->next; - - if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) - kfree(sg->sgc); - - kfree(sg); - sg = tmp; - } while (sg != first); -} - -static void destroy_sched_domain(struct sched_domain *sd) -{ - /* - * If its an overlapping domain it has private groups, iterate and - * nuke them all. - */ - if (sd->flags & SD_OVERLAP) { - free_sched_groups(sd->groups, 1); - } else if (atomic_dec_and_test(&sd->groups->ref)) { - kfree(sd->groups->sgc); - kfree(sd->groups); - } - if (sd->shared && atomic_dec_and_test(&sd->shared->ref)) - kfree(sd->shared); - kfree(sd); -} - -static void destroy_sched_domains_rcu(struct rcu_head *rcu) -{ - struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); - - while (sd) { - struct sched_domain *parent = sd->parent; - destroy_sched_domain(sd); - sd = parent; - } -} - -static void destroy_sched_domains(struct sched_domain *sd) -{ - if (sd) - call_rcu(&sd->rcu, destroy_sched_domains_rcu); -} - -/* - * Keep a special pointer to the highest sched_domain that has - * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this - * allows us to avoid some pointer chasing select_idle_sibling(). - * - * Also keep a unique ID per domain (we use the first cpu number in - * the cpumask of the domain), this allows us to quickly tell if - * two cpus are in the same cache domain, see cpus_share_cache(). - */ -DEFINE_PER_CPU(struct sched_domain *, sd_llc); -DEFINE_PER_CPU(int, sd_llc_size); -DEFINE_PER_CPU(int, sd_llc_id); -DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); -DEFINE_PER_CPU(struct sched_domain *, sd_numa); -DEFINE_PER_CPU(struct sched_domain *, sd_asym); - -static void update_top_cache_domain(int cpu) -{ - struct sched_domain_shared *sds = NULL; - struct sched_domain *sd; - int id = cpu; - int size = 1; - - sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); - if (sd) { - id = cpumask_first(sched_domain_span(sd)); - size = cpumask_weight(sched_domain_span(sd)); - sds = sd->shared; - } - - rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); - per_cpu(sd_llc_size, cpu) = size; - per_cpu(sd_llc_id, cpu) = id; - rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds); - - sd = lowest_flag_domain(cpu, SD_NUMA); - rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); - - sd = highest_flag_domain(cpu, SD_ASYM_PACKING); - rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); -} - -/* - * Attach the domain 'sd' to 'cpu' as its base domain. Callers must - * hold the hotplug lock. - */ -static void -cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) -{ - struct rq *rq = cpu_rq(cpu); - struct sched_domain *tmp; - - /* Remove the sched domains which do not contribute to scheduling. */ - for (tmp = sd; tmp; ) { - struct sched_domain *parent = tmp->parent; - if (!parent) - break; - - if (sd_parent_degenerate(tmp, parent)) { - tmp->parent = parent->parent; - if (parent->parent) - parent->parent->child = tmp; - /* - * Transfer SD_PREFER_SIBLING down in case of a - * degenerate parent; the spans match for this - * so the property transfers. - */ - if (parent->flags & SD_PREFER_SIBLING) - tmp->flags |= SD_PREFER_SIBLING; - destroy_sched_domain(parent); - } else - tmp = tmp->parent; - } - - if (sd && sd_degenerate(sd)) { - tmp = sd; - sd = sd->parent; - destroy_sched_domain(tmp); - if (sd) - sd->child = NULL; - } - - sched_domain_debug(sd, cpu); - - rq_attach_root(rq, rd); - tmp = rq->sd; - rcu_assign_pointer(rq->sd, sd); - destroy_sched_domains(tmp); - - update_top_cache_domain(cpu); -} - -/* Setup the mask of cpus configured for isolated domains */ -static int __init isolated_cpu_setup(char *str) -{ - int ret; - - alloc_bootmem_cpumask_var(&cpu_isolated_map); - ret = cpulist_parse(str, cpu_isolated_map); - if (ret) { - pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); - return 0; - } - return 1; -} -__setup("isolcpus=", isolated_cpu_setup); - -struct s_data { - struct sched_domain ** __percpu sd; - struct root_domain *rd; -}; - -enum s_alloc { - sa_rootdomain, - sa_sd, - sa_sd_storage, - sa_none, -}; - -/* - * Build an iteration mask that can exclude certain CPUs from the upwards - * domain traversal. - * - * Asymmetric node setups can result in situations where the domain tree is of - * unequal depth, make sure to skip domains that already cover the entire - * range. - * - * In that case build_sched_domains() will have terminated the iteration early - * and our sibling sd spans will be empty. Domains should always include the - * cpu they're built on, so check that. - * - */ -static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) -{ - const struct cpumask *span = sched_domain_span(sd); - struct sd_data *sdd = sd->private; - struct sched_domain *sibling; - int i; - - for_each_cpu(i, span) { - sibling = *per_cpu_ptr(sdd->sd, i); - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) - continue; - - cpumask_set_cpu(i, sched_group_mask(sg)); - } -} - -/* - * Return the canonical balance cpu for this group, this is the first cpu - * of this group that's also in the iteration mask. - */ -int group_balance_cpu(struct sched_group *sg) -{ - return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); -} - -static int -build_overlap_sched_groups(struct sched_domain *sd, int cpu) -{ - struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; - const struct cpumask *span = sched_domain_span(sd); - struct cpumask *covered = sched_domains_tmpmask; - struct sd_data *sdd = sd->private; - struct sched_domain *sibling; - int i; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct cpumask *sg_span; - - if (cpumask_test_cpu(i, covered)) - continue; - - sibling = *per_cpu_ptr(sdd->sd, i); - - /* See the comment near build_group_mask(). */ - if (!cpumask_test_cpu(i, sched_domain_span(sibling))) - continue; - - sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, cpu_to_node(cpu)); - - if (!sg) - goto fail; - - sg_span = sched_group_cpus(sg); - if (sibling->child) - cpumask_copy(sg_span, sched_domain_span(sibling->child)); - else - cpumask_set_cpu(i, sg_span); - - cpumask_or(covered, covered, sg_span); - - sg->sgc = *per_cpu_ptr(sdd->sgc, i); - if (atomic_inc_return(&sg->sgc->ref) == 1) - build_group_mask(sd, sg); - - /* - * 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->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); - - /* - * Make sure the first group of this domain contains the - * canonical balance cpu. Otherwise the sched_domain iteration - * breaks. See update_sg_lb_stats(). - */ - if ((!groups && cpumask_test_cpu(cpu, sg_span)) || - group_balance_cpu(sg) == cpu) - groups = sg; - - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - last->next = first; - } - sd->groups = groups; - - return 0; - -fail: - free_sched_groups(first, 0); - - return -ENOMEM; -} - -static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) -{ - struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); - struct sched_domain *child = sd->child; - - if (child) - cpu = cpumask_first(sched_domain_span(child)); - - if (sg) { - *sg = *per_cpu_ptr(sdd->sg, cpu); - (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); - atomic_set(&(*sg)->sgc->ref, 1); /* for claim_allocations */ - } - - return cpu; -} - -/* - * 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_capacity to 0. - * - * Assumes the sched_domain tree is fully constructed - */ -static int -build_sched_groups(struct sched_domain *sd, int cpu) -{ - struct sched_group *first = NULL, *last = NULL; - struct sd_data *sdd = sd->private; - const struct cpumask *span = sched_domain_span(sd); - struct cpumask *covered; - int i; - - get_group(cpu, sdd, &sd->groups); - atomic_inc(&sd->groups->ref); - - if (cpu != cpumask_first(span)) - return 0; - - lockdep_assert_held(&sched_domains_mutex); - covered = sched_domains_tmpmask; - - cpumask_clear(covered); - - for_each_cpu(i, span) { - struct sched_group *sg; - int group, j; - - if (cpumask_test_cpu(i, covered)) - continue; - - group = get_group(i, sdd, &sg); - cpumask_setall(sched_group_mask(sg)); - - for_each_cpu(j, span) { - if (get_group(j, sdd, NULL) != group) - continue; - - cpumask_set_cpu(j, covered); - cpumask_set_cpu(j, sched_group_cpus(sg)); - } - - if (!first) - first = sg; - if (last) - last->next = sg; - last = sg; - } - last->next = first; - - return 0; -} - -/* - * Initialize sched groups cpu_capacity. - * - * 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_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_capacity(int cpu, struct sched_domain *sd) -{ - struct sched_group *sg = sd->groups; - - WARN_ON(!sg); - - do { - sg->group_weight = cpumask_weight(sched_group_cpus(sg)); - sg = sg->next; - } while (sg != sd->groups); - - if (cpu != group_balance_cpu(sg)) - return; - - update_group_capacity(sd, cpu); -} - -/* - * Initializers for schedule domains - * Non-inlined to reduce accumulated stack pressure in build_sched_domains() - */ - -static int default_relax_domain_level = -1; -int sched_domain_level_max; - -static int __init setup_relax_domain_level(char *str) -{ - if (kstrtoint(str, 0, &default_relax_domain_level)) - pr_warn("Unable to set relax_domain_level\n"); - - return 1; -} -__setup("relax_domain_level=", setup_relax_domain_level); - -static void set_domain_attribute(struct sched_domain *sd, - struct sched_domain_attr *attr) -{ - int request; - - if (!attr || attr->relax_domain_level < 0) { - if (default_relax_domain_level < 0) - return; - else - request = default_relax_domain_level; - } else - request = attr->relax_domain_level; - if (request < sd->level) { - /* turn off idle balance on this domain */ - sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); - } else { - /* turn on idle balance on this domain */ - sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); - } -} - -static void __sdt_free(const struct cpumask *cpu_map); -static int __sdt_alloc(const struct cpumask *cpu_map); - -static void __free_domain_allocs(struct s_data *d, enum s_alloc what, - const struct cpumask *cpu_map) -{ - switch (what) { - case sa_rootdomain: - if (!atomic_read(&d->rd->refcount)) - free_rootdomain(&d->rd->rcu); /* fall through */ - case sa_sd: - free_percpu(d->sd); /* fall through */ - case sa_sd_storage: - __sdt_free(cpu_map); /* fall through */ - case sa_none: - break; - } -} - -static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, - const struct cpumask *cpu_map) -{ - memset(d, 0, sizeof(*d)); - - if (__sdt_alloc(cpu_map)) - return sa_sd_storage; - d->sd = alloc_percpu(struct sched_domain *); - if (!d->sd) - return sa_sd_storage; - d->rd = alloc_rootdomain(); - if (!d->rd) - return sa_sd; - return sa_rootdomain; -} - -/* - * NULL the sd_data elements we've used to build the sched_domain and - * sched_group structure so that the subsequent __free_domain_allocs() - * will not free the data we're using. - */ -static void claim_allocations(int cpu, struct sched_domain *sd) -{ - struct sd_data *sdd = sd->private; - - WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); - *per_cpu_ptr(sdd->sd, cpu) = NULL; - - if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref)) - *per_cpu_ptr(sdd->sds, cpu) = NULL; - - if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) - *per_cpu_ptr(sdd->sg, cpu) = NULL; - - if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) - *per_cpu_ptr(sdd->sgc, cpu) = NULL; -} - -#ifdef CONFIG_NUMA -static int sched_domains_numa_levels; -enum numa_topology_type sched_numa_topology_type; -static int *sched_domains_numa_distance; -int sched_max_numa_distance; -static struct cpumask ***sched_domains_numa_masks; -static int sched_domains_curr_level; -#endif - -/* - * SD_flags allowed in topology descriptions. - * - * These flags are purely descriptive of the topology and do not prescribe - * behaviour. Behaviour is artificial and mapped in the below sd_init() - * function: - * - * 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 - * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies - * - * Odd one out, which beside describing the topology has a quirk also - * prescribes the desired behaviour that goes along with it: - * - * SD_ASYM_PACKING - describes SMT quirks - */ -#define TOPOLOGY_SD_FLAGS \ - (SD_SHARE_CPUCAPACITY | \ - SD_SHARE_PKG_RESOURCES | \ - SD_NUMA | \ - SD_ASYM_PACKING | \ - SD_ASYM_CPUCAPACITY | \ - SD_SHARE_POWERDOMAIN) - -static struct sched_domain * -sd_init(struct sched_domain_topology_level *tl, - const struct cpumask *cpu_map, - struct sched_domain *child, int cpu) -{ - struct sd_data *sdd = &tl->data; - struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); - int sd_id, 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 = 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 - | 1*SD_BALANCE_EXEC - | 1*SD_BALANCE_FORK - | 0*SD_BALANCE_WAKE - | 1*SD_WAKE_AFFINE - | 0*SD_SHARE_CPUCAPACITY - | 0*SD_SHARE_PKG_RESOURCES - | 0*SD_SERIALIZE - | 0*SD_PREFER_SIBLING - | 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, - .child = child, -#ifdef CONFIG_SCHED_DEBUG - .name = tl->name, -#endif - }; - - cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); - sd_id = cpumask_first(sched_domain_span(sd)); - - /* - * Convert topological properties into behaviour. - */ - - if (sd->flags & SD_ASYM_CPUCAPACITY) { - struct sched_domain *t = sd; - - for_each_lower_domain(t) - t->flags |= SD_BALANCE_WAKE; - } - - if (sd->flags & SD_SHARE_CPUCAPACITY) { - sd->flags |= SD_PREFER_SIBLING; - 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; - } - - /* - * For all levels sharing cache; connect a sched_domain_shared - * instance. - */ - if (sd->flags & SD_SHARE_PKG_RESOURCES) { - sd->shared = *per_cpu_ptr(sdd->sds, sd_id); - atomic_inc(&sd->shared->ref); - atomic_set(&sd->shared->nr_busy_cpus, sd_weight); - } - - sd->private = sdd; - - 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, }, -}; - -static 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) -{ - if (WARN_ON_ONCE(sched_smp_initialized)) - return; - - 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)]; -} - -static void sched_numa_warn(const char *str) -{ - static int done = false; - int i,j; - - if (done) - return; - - done = true; - - printk(KERN_WARNING "ERROR: %s\n\n", str); - - for (i = 0; i < nr_node_ids; i++) { - printk(KERN_WARNING " "); - for (j = 0; j < nr_node_ids; j++) - printk(KERN_CONT "%02d ", node_distance(i,j)); - printk(KERN_CONT "\n"); - } - printk(KERN_WARNING "\n"); -} - -bool find_numa_distance(int distance) -{ - int i; - - if (distance == node_distance(0, 0)) - return true; - - for (i = 0; i < sched_domains_numa_levels; i++) { - if (sched_domains_numa_distance[i] == distance) - return true; - } - - return false; -} - -/* - * A system can have three types of NUMA topology: - * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system - * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes - * NUMA_BACKPLANE: nodes can reach other nodes through a backplane - * - * The difference between a glueless mesh topology and a backplane - * topology lies in whether communication between not directly - * connected nodes goes through intermediary nodes (where programs - * could run), or through backplane controllers. This affects - * placement of programs. - * - * The type of topology can be discerned with the following tests: - * - If the maximum distance between any nodes is 1 hop, the system - * is directly connected. - * - If for two nodes A and B, located N > 1 hops away from each other, - * there is an intermediary node C, which is < N hops away from both - * nodes A and B, the system is a glueless mesh. - */ -static void init_numa_topology_type(void) -{ - int a, b, c, n; - - n = sched_max_numa_distance; - - if (sched_domains_numa_levels <= 1) { - sched_numa_topology_type = NUMA_DIRECT; - return; - } - - for_each_online_node(a) { - for_each_online_node(b) { - /* Find two nodes furthest removed from each other. */ - if (node_distance(a, b) < n) - continue; - - /* Is there an intermediary node between a and b? */ - for_each_online_node(c) { - if (node_distance(a, c) < n && - node_distance(b, c) < n) { - sched_numa_topology_type = - NUMA_GLUELESS_MESH; - return; - } - } - - sched_numa_topology_type = NUMA_BACKPLANE; - return; - } - } -} - -static void sched_init_numa(void) -{ - int next_distance, curr_distance = node_distance(0, 0); - struct sched_domain_topology_level *tl; - int level = 0; - int i, j, k; - - sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); - if (!sched_domains_numa_distance) - return; - - /* - * O(nr_nodes^2) deduplicating selection sort -- in order to find the - * unique distances in the node_distance() table. - * - * Assumes node_distance(0,j) includes all distances in - * node_distance(i,j) in order to avoid cubic time. - */ - next_distance = curr_distance; - for (i = 0; i < nr_node_ids; i++) { - for (j = 0; j < nr_node_ids; j++) { - for (k = 0; k < nr_node_ids; k++) { - int distance = node_distance(i, k); - - if (distance > curr_distance && - (distance < next_distance || - next_distance == curr_distance)) - next_distance = distance; - - /* - * While not a strong assumption it would be nice to know - * about cases where if node A is connected to B, B is not - * equally connected to A. - */ - if (sched_debug() && node_distance(k, i) != distance) - sched_numa_warn("Node-distance not symmetric"); - - if (sched_debug() && i && !find_numa_distance(distance)) - sched_numa_warn("Node-0 not representative"); - } - if (next_distance != curr_distance) { - sched_domains_numa_distance[level++] = next_distance; - sched_domains_numa_levels = level; - curr_distance = next_distance; - } else break; - } - - /* - * In case of sched_debug() we verify the above assumption. - */ - if (!sched_debug()) - break; - } - - if (!level) - return; - - /* - * 'level' contains the number of unique distances, excluding the - * identity distance node_distance(i,i). - * - * The sched_domains_numa_distance[] array includes the actual distance - * numbers. - */ - - /* - * Here, we should temporarily reset sched_domains_numa_levels to 0. - * If it fails to allocate memory for array sched_domains_numa_masks[][], - * the array will contain less then 'level' members. This could be - * dangerous when we use it to iterate array sched_domains_numa_masks[][] - * in other functions. - * - * We reset it to 'level' at the end of this function. - */ - sched_domains_numa_levels = 0; - - sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); - if (!sched_domains_numa_masks) - return; - - /* - * Now for each level, construct a mask per node which contains all - * cpus of nodes that are that many hops away from us. - */ - for (i = 0; i < level; i++) { - sched_domains_numa_masks[i] = - kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); - if (!sched_domains_numa_masks[i]) - return; - - for (j = 0; j < nr_node_ids; j++) { - struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); - if (!mask) - return; - - sched_domains_numa_masks[i][j] = mask; - - for_each_node(k) { - if (node_distance(j, k) > sched_domains_numa_distance[i]) - continue; - - cpumask_or(mask, mask, cpumask_of_node(k)); - } - } - } - - /* 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; - - /* - * Copy the default topology bits.. - */ - 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){ - .mask = sd_numa_mask, - .sd_flags = cpu_numa_flags, - .flags = SDTL_OVERLAP, - .numa_level = j, - SD_INIT_NAME(NUMA) - }; - } - - sched_domain_topology = tl; - - sched_domains_numa_levels = level; - sched_max_numa_distance = sched_domains_numa_distance[level - 1]; - - init_numa_topology_type(); -} - -static void sched_domains_numa_masks_set(unsigned int cpu) -{ - int node = cpu_to_node(cpu); - int i, j; - - for (i = 0; i < sched_domains_numa_levels; i++) { - for (j = 0; j < nr_node_ids; j++) { - if (node_distance(j, node) <= sched_domains_numa_distance[i]) - cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); - } - } -} - -static void sched_domains_numa_masks_clear(unsigned int cpu) -{ - int i, j; - - for (i = 0; i < sched_domains_numa_levels; i++) { - for (j = 0; j < nr_node_ids; j++) - cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); - } -} - -#else -static inline void sched_init_numa(void) { } -static void sched_domains_numa_masks_set(unsigned int cpu) { } -static void sched_domains_numa_masks_clear(unsigned int cpu) { } -#endif /* CONFIG_NUMA */ - -static int __sdt_alloc(const struct cpumask *cpu_map) -{ - struct sched_domain_topology_level *tl; - int j; - - for_each_sd_topology(tl) { - struct sd_data *sdd = &tl->data; - - sdd->sd = alloc_percpu(struct sched_domain *); - if (!sdd->sd) - return -ENOMEM; - - sdd->sds = alloc_percpu(struct sched_domain_shared *); - if (!sdd->sds) - return -ENOMEM; - - sdd->sg = alloc_percpu(struct sched_group *); - if (!sdd->sg) - return -ENOMEM; - - 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_domain_shared *sds; - struct sched_group *sg; - struct sched_group_capacity *sgc; - - sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), - GFP_KERNEL, cpu_to_node(j)); - if (!sd) - return -ENOMEM; - - *per_cpu_ptr(sdd->sd, j) = sd; - - sds = kzalloc_node(sizeof(struct sched_domain_shared), - GFP_KERNEL, cpu_to_node(j)); - if (!sds) - return -ENOMEM; - - *per_cpu_ptr(sdd->sds, j) = sds; - - sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, cpu_to_node(j)); - if (!sg) - return -ENOMEM; - - sg->next = sg; - - *per_cpu_ptr(sdd->sg, j) = sg; - - sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), - GFP_KERNEL, cpu_to_node(j)); - if (!sgc) - return -ENOMEM; - - *per_cpu_ptr(sdd->sgc, j) = sgc; - } - } - - return 0; -} - -static void __sdt_free(const struct cpumask *cpu_map) -{ - struct sched_domain_topology_level *tl; - int j; - - for_each_sd_topology(tl) { - struct sd_data *sdd = &tl->data; - - for_each_cpu(j, cpu_map) { - struct sched_domain *sd; - - if (sdd->sd) { - sd = *per_cpu_ptr(sdd->sd, j); - if (sd && (sd->flags & SD_OVERLAP)) - free_sched_groups(sd->groups, 0); - kfree(*per_cpu_ptr(sdd->sd, j)); - } - - if (sdd->sds) - kfree(*per_cpu_ptr(sdd->sds, j)); - if (sdd->sg) - kfree(*per_cpu_ptr(sdd->sg, j)); - if (sdd->sgc) - kfree(*per_cpu_ptr(sdd->sgc, j)); - } - free_percpu(sdd->sd); - sdd->sd = NULL; - free_percpu(sdd->sds); - sdd->sds = NULL; - free_percpu(sdd->sg); - sdd->sg = NULL; - free_percpu(sdd->sgc); - sdd->sgc = NULL; - } -} - -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 = sd_init(tl, cpu_map, child, cpu); - - if (child) { - sd->level = child->level + 1; - sched_domain_level_max = max(sched_domain_level_max, sd->level); - child->parent = sd; - - if (!cpumask_subset(sched_domain_span(child), - sched_domain_span(sd))) { - pr_err("BUG: arch topology borken\n"); -#ifdef CONFIG_SCHED_DEBUG - pr_err(" the %s domain not a subset of the %s domain\n", - child->name, sd->name); -#endif - /* Fixup, ensure @sd has at least @child cpus. */ - cpumask_or(sched_domain_span(sd), - sched_domain_span(sd), - sched_domain_span(child)); - } - - } - set_domain_attribute(sd, attr); - - return sd; -} - /* - * Build sched domains for a given set of cpus and attach the sched domains - * to the individual cpus + * used to mark begin/end of suspend/resume: */ -static int build_sched_domains(const struct cpumask *cpu_map, - struct sched_domain_attr *attr) -{ - enum s_alloc alloc_state; - struct sched_domain *sd; - struct s_data d; - struct rq *rq = NULL; - int i, ret = -ENOMEM; - - alloc_state = __visit_domain_allocation_hell(&d, cpu_map); - if (alloc_state != sa_rootdomain) - goto error; - - /* Set up domains for cpus specified by the cpu_map. */ - for_each_cpu(i, cpu_map) { - struct sched_domain_topology_level *tl; - - sd = NULL; - for_each_sd_topology(tl) { - sd = build_sched_domain(tl, cpu_map, attr, sd, i); - if (tl == sched_domain_topology) - *per_cpu_ptr(d.sd, i) = sd; - if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) - sd->flags |= SD_OVERLAP; - if (cpumask_equal(cpu_map, sched_domain_span(sd))) - break; - } - } - - /* Build the groups for the domains */ - for_each_cpu(i, cpu_map) { - for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { - sd->span_weight = cpumask_weight(sched_domain_span(sd)); - if (sd->flags & SD_OVERLAP) { - if (build_overlap_sched_groups(sd, i)) - goto error; - } else { - if (build_sched_groups(sd, i)) - goto error; - } - } - } - - /* 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_capacity(i, sd); - } - } - - /* Attach the domains */ - rcu_read_lock(); - for_each_cpu(i, cpu_map) { - rq = cpu_rq(i); - sd = *per_cpu_ptr(d.sd, i); - - /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */ - if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity)) - WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig); - - cpu_attach_domain(sd, d.rd, i); - } - rcu_read_unlock(); - - if (rq && sched_debug_enabled) { - pr_info("span: %*pbl (max cpu_capacity = %lu)\n", - cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); - } - - ret = 0; -error: - __free_domain_allocs(&d, alloc_state, cpu_map); - return ret; -} - -static cpumask_var_t *doms_cur; /* current sched domains */ -static int ndoms_cur; /* number of sched domains in 'doms_cur' */ -static struct sched_domain_attr *dattr_cur; - /* attribues of custom domains in 'doms_cur' */ - -/* - * Special case: If a kmalloc of a doms_cur partition (array of - * cpumask) fails, then fallback to a single sched domain, - * as determined by the single cpumask fallback_doms. - */ -static cpumask_var_t fallback_doms; - -/* - * arch_update_cpu_topology lets virtualized architectures update the - * cpu core maps. It is supposed to return 1 if the topology changed - * or 0 if it stayed the same. - */ -int __weak arch_update_cpu_topology(void) -{ - return 0; -} - -cpumask_var_t *alloc_sched_domains(unsigned int ndoms) -{ - int i; - cpumask_var_t *doms; - - doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); - if (!doms) - return NULL; - for (i = 0; i < ndoms; i++) { - if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { - free_sched_domains(doms, i); - return NULL; - } - } - return doms; -} - -void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) -{ - unsigned int i; - for (i = 0; i < ndoms; i++) - free_cpumask_var(doms[i]); - kfree(doms); -} - -/* - * Set up scheduler domains and groups. Callers must hold the hotplug lock. - * For now this just excludes isolated cpus, but could be used to - * exclude other special cases in the future. - */ -static int init_sched_domains(const struct cpumask *cpu_map) -{ - int err; - - arch_update_cpu_topology(); - ndoms_cur = 1; - doms_cur = alloc_sched_domains(ndoms_cur); - if (!doms_cur) - doms_cur = &fallback_doms; - cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); - err = build_sched_domains(doms_cur[0], NULL); - register_sched_domain_sysctl(); - - return err; -} - -/* - * Detach sched domains from a group of cpus specified in cpu_map - * These cpus will now be attached to the NULL domain - */ -static void detach_destroy_domains(const struct cpumask *cpu_map) -{ - int i; - - rcu_read_lock(); - for_each_cpu(i, cpu_map) - cpu_attach_domain(NULL, &def_root_domain, i); - rcu_read_unlock(); -} - -/* handle null as "default" */ -static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, - struct sched_domain_attr *new, int idx_new) -{ - struct sched_domain_attr tmp; - - /* fast path */ - if (!new && !cur) - return 1; - - tmp = SD_ATTR_INIT; - return !memcmp(cur ? (cur + idx_cur) : &tmp, - new ? (new + idx_new) : &tmp, - sizeof(struct sched_domain_attr)); -} - -/* - * Partition sched domains as specified by the 'ndoms_new' - * cpumasks in the array doms_new[] of cpumasks. This compares - * doms_new[] to the current sched domain partitioning, doms_cur[]. - * It destroys each deleted domain and builds each new domain. - * - * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. - * The masks don't intersect (don't overlap.) We should setup one - * sched domain for each mask. CPUs not in any of the cpumasks will - * not be load balanced. If the same cpumask appears both in the - * current 'doms_cur' domains and in the new 'doms_new', we can leave - * it as it is. - * - * The passed in 'doms_new' should be allocated using - * alloc_sched_domains. This routine takes ownership of it and will - * free_sched_domains it when done with it. If the caller failed the - * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, - * and partition_sched_domains() will fallback to the single partition - * 'fallback_doms', it also forces the domains to be rebuilt. - * - * If doms_new == NULL it will be replaced with cpu_online_mask. - * ndoms_new == 0 is a special case for destroying existing domains, - * and it will not create the default domain. - * - * Call with hotplug lock held - */ -void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], - struct sched_domain_attr *dattr_new) -{ - int i, j, n; - int new_topology; - - mutex_lock(&sched_domains_mutex); - - /* always unregister in case we don't destroy any domains */ - unregister_sched_domain_sysctl(); - - /* Let architecture update cpu core mappings. */ - new_topology = arch_update_cpu_topology(); - - n = doms_new ? ndoms_new : 0; - - /* Destroy deleted domains */ - for (i = 0; i < ndoms_cur; i++) { - for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_cur[i], doms_new[j]) - && dattrs_equal(dattr_cur, i, dattr_new, j)) - goto match1; - } - /* no match - a current sched domain not in new doms_new[] */ - detach_destroy_domains(doms_cur[i]); -match1: - ; - } - - n = ndoms_cur; - if (doms_new == NULL) { - n = 0; - doms_new = &fallback_doms; - cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); - WARN_ON_ONCE(dattr_new); - } - - /* Build new domains */ - for (i = 0; i < ndoms_new; i++) { - for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(doms_new[i], doms_cur[j]) - && dattrs_equal(dattr_new, i, dattr_cur, j)) - goto match2; - } - /* no match - add a new doms_new */ - build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); -match2: - ; - } - - /* Remember the new sched domains */ - if (doms_cur != &fallback_doms) - free_sched_domains(doms_cur, ndoms_cur); - kfree(dattr_cur); /* kfree(NULL) is safe */ - doms_cur = doms_new; - dattr_cur = dattr_new; - ndoms_cur = ndoms_new; - - register_sched_domain_sysctl(); - - mutex_unlock(&sched_domains_mutex); -} - -static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ +static int num_cpus_frozen; /* * Update cpusets according to cpu_active mask. If cpusets are @@ -7334,7 +5779,7 @@ int sched_cpu_activate(unsigned int cpu) * Put the rq online, if not already. This happens: * * 1) In the early boot process, because we build the real domains - * after all cpus have been brought up. + * after all CPUs have been brought up. * * 2) At runtime, if cpuset_cpu_active() fails to rebuild the * domains. @@ -7449,7 +5894,7 @@ void __init sched_init_smp(void) /* * There's no userspace yet to cause hotplug operations; hence all the - * cpu masks are stable and all blatant races in the below code cannot + * CPU masks are stable and all blatant races in the below code cannot * happen. */ mutex_lock(&sched_domains_mutex); @@ -7469,6 +5914,7 @@ void __init sched_init_smp(void) init_sched_dl_class(); sched_init_smt(); + sched_clock_init_late(); sched_smp_initialized = true; } @@ -7484,6 +5930,7 @@ early_initcall(migration_init); void __init sched_init_smp(void) { sched_init_granularity(); + sched_clock_init_late(); } #endif /* CONFIG_SMP */ @@ -7527,6 +5974,8 @@ void __init sched_init(void) int i, j; unsigned long alloc_size = 0, ptr; + sched_clock_init(); + for (i = 0; i < WAIT_TABLE_SIZE; i++) init_waitqueue_head(bit_wait_table + i); @@ -7565,10 +6014,8 @@ void __init sched_init(void) } #endif /* CONFIG_CPUMASK_OFFSTACK */ - init_rt_bandwidth(&def_rt_bandwidth, - global_rt_period(), global_rt_runtime()); - init_dl_bandwidth(&def_dl_bandwidth, - global_rt_period(), global_rt_runtime()); + init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime()); + init_dl_bandwidth(&def_dl_bandwidth, global_rt_period(), global_rt_runtime()); #ifdef CONFIG_SMP init_defrootdomain(); @@ -7602,19 +6049,20 @@ void __init sched_init(void) #ifdef CONFIG_FAIR_GROUP_SCHED root_task_group.shares = ROOT_TASK_GROUP_LOAD; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; /* - * How much cpu bandwidth does root_task_group get? + * How much CPU bandwidth does root_task_group get? * * In case of task-groups formed thr' the cgroup filesystem, it - * gets 100% of the cpu resources in the system. This overall - * system cpu resource is divided among the tasks of + * gets 100% of the CPU resources in the system. This overall + * system CPU resource is divided among the tasks of * root_task_group and its child task-groups in a fair manner, * based on each entity's (task or task-group's) weight * (se->load.weight). * * In other words, if root_task_group has 10 tasks of weight * 1024) and two child groups A0 and A1 (of weight 1024 each), - * then A0's share of the cpu resource is: + * then A0's share of the CPU resource is: * * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% * @@ -7667,7 +6115,7 @@ void __init sched_init(void) /* * The boot idle thread does lazy MMU switching as well: */ - atomic_inc(&init_mm.mm_count); + mmgrab(&init_mm); enter_lazy_tlb(&init_mm, current); /* @@ -7723,10 +6171,14 @@ EXPORT_SYMBOL(__might_sleep); void ___might_sleep(const char *file, int line, int preempt_offset) { - static unsigned long prev_jiffy; /* ratelimiting */ + /* Ratelimiting timestamp: */ + static unsigned long prev_jiffy; + unsigned long preempt_disable_ip; - rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ + /* WARN_ON_ONCE() by default, no rate limit required: */ + rcu_sleep_check(); + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && !is_idle_task(current)) || system_state != SYSTEM_RUNNING || oops_in_progress) @@ -7735,7 +6187,7 @@ void ___might_sleep(const char *file, int line, int preempt_offset) return; prev_jiffy = jiffies; - /* Save this before calling printk(), since that will clobber it */ + /* Save this before calling printk(), since that will clobber it: */ preempt_disable_ip = get_preempt_disable_ip(current); printk(KERN_ERR @@ -7814,7 +6266,7 @@ void normalize_rt_tasks(void) */ /** - * curr_task - return the current task for a given cpu. + * curr_task - return the current task for a given CPU. * @cpu: the processor in question. * * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! @@ -7830,13 +6282,13 @@ struct task_struct *curr_task(int cpu) #ifdef CONFIG_IA64 /** - * set_curr_task - set the current task for a given cpu. + * set_curr_task - set the current task for a given CPU. * @cpu: the processor in question. * @p: the task pointer to set. * * Description: This function must only be used when non-maskable interrupts * are serviced on a separate stack. It allows the architecture to switch the - * notion of the current task on a cpu in a non-blocking manner. This function + * notion of the current task on a CPU in a non-blocking manner. This function * must be called with all CPU's synchronized, and interrupts disabled, the * and caller must save the original value of the current task (see * curr_task() above) and restore that value before reenabling interrupts and @@ -7892,7 +6344,8 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) spin_lock_irqsave(&task_group_lock, flags); list_add_rcu(&tg->list, &task_groups); - WARN_ON(!parent); /* root should already exist */ + /* Root should already exist: */ + WARN_ON(!parent); tg->parent = parent; INIT_LIST_HEAD(&tg->children); @@ -7905,13 +6358,13 @@ void sched_online_group(struct task_group *tg, struct task_group *parent) /* rcu callback to free various structures associated with a task group */ static void sched_free_group_rcu(struct rcu_head *rhp) { - /* now it should be safe to free those cfs_rqs */ + /* Now it should be safe to free those cfs_rqs: */ sched_free_group(container_of(rhp, struct task_group, rcu)); } void sched_destroy_group(struct task_group *tg) { - /* wait for possible concurrent references to cfs_rqs complete */ + /* Wait for possible concurrent references to cfs_rqs complete: */ call_rcu(&tg->rcu, sched_free_group_rcu); } @@ -7919,7 +6372,7 @@ void sched_offline_group(struct task_group *tg) { unsigned long flags; - /* end participation in shares distribution */ + /* End participation in shares distribution: */ unregister_fair_sched_group(tg); spin_lock_irqsave(&task_group_lock, flags); @@ -7964,20 +6417,21 @@ void sched_move_task(struct task_struct *tsk) struct rq *rq; rq = task_rq_lock(tsk, &rf); + update_rq_clock(rq); running = task_current(rq, tsk); queued = task_on_rq_queued(tsk); if (queued) dequeue_task(rq, tsk, DEQUEUE_SAVE | DEQUEUE_MOVE); - if (unlikely(running)) + if (running) put_prev_task(rq, tsk); sched_change_group(tsk, TASK_MOVE_GROUP); if (queued) enqueue_task(rq, tsk, ENQUEUE_RESTORE | ENQUEUE_MOVE); - if (unlikely(running)) + if (running) set_curr_task(rq, tsk); task_rq_unlock(rq, tsk, &rf); @@ -8347,11 +6801,14 @@ int sched_rr_handler(struct ctl_table *table, int write, mutex_lock(&mutex); ret = proc_dointvec(table, write, buffer, lenp, ppos); - /* make sure that internally we keep jiffies */ - /* also, writing zero resets timeslice to default */ + /* + * Make sure that internally we keep jiffies. + * Also, writing zero resets the timeslice to default: + */ if (!ret && write) { - sched_rr_timeslice = sched_rr_timeslice <= 0 ? - RR_TIMESLICE : msecs_to_jiffies(sched_rr_timeslice); + sched_rr_timeslice = + sysctl_sched_rr_timeslice <= 0 ? RR_TIMESLICE : + msecs_to_jiffies(sysctl_sched_rr_timeslice); } mutex_unlock(&mutex); return ret; @@ -8379,11 +6836,20 @@ cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (IS_ERR(tg)) return ERR_PTR(-ENOMEM); - sched_online_group(tg, parent); - return &tg->css; } +/* Expose task group only after completing cgroup initialization */ +static int cpu_cgroup_css_online(struct cgroup_subsys_state *css) +{ + struct task_group *tg = css_tg(css); + struct task_group *parent = css_tg(css->parent); + + if (parent) + sched_online_group(tg, parent); + return 0; +} + static void cpu_cgroup_css_released(struct cgroup_subsys_state *css) { struct task_group *tg = css_tg(css); @@ -8412,6 +6878,7 @@ static void cpu_cgroup_fork(struct task_struct *task) rq = task_rq_lock(task, &rf); + update_rq_clock(rq); sched_change_group(task, TASK_SET_GROUP); task_rq_unlock(rq, task, &rf); @@ -8531,9 +6998,11 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota) cfs_b->quota = quota; __refill_cfs_bandwidth_runtime(cfs_b); - /* restart the period timer (if active) to handle new period expiry */ + + /* Restart the period timer (if active) to handle new period expiry: */ if (runtime_enabled) start_cfs_bandwidth(cfs_b); + raw_spin_unlock_irq(&cfs_b->lock); for_each_online_cpu(i) { @@ -8671,8 +7140,8 @@ static int tg_cfs_schedulable_down(struct task_group *tg, void *data) parent_quota = parent_b->hierarchical_quota; /* - * ensure max(child_quota) <= parent_quota, inherit when no - * limit is set + * Ensure max(child_quota) <= parent_quota, inherit when no + * limit is set: */ if (quota == RUNTIME_INF) quota = parent_quota; @@ -8781,11 +7250,12 @@ static struct cftype cpu_files[] = { .write_u64 = cpu_rt_period_write_uint, }, #endif - { } /* terminate */ + { } /* Terminate */ }; struct cgroup_subsys cpu_cgrp_subsys = { .css_alloc = cpu_cgroup_css_alloc, + .css_online = cpu_cgroup_css_online, .css_released = cpu_cgroup_css_released, .css_free = cpu_cgroup_css_free, .fork = cpu_cgroup_fork, diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c index bc0b309c3f19..f95ab29a45d0 100644 --- a/kernel/sched/cpuacct.c +++ b/kernel/sched/cpuacct.c @@ -297,7 +297,7 @@ static int cpuacct_stats_show(struct seq_file *sf, void *v) for (stat = 0; stat < CPUACCT_STAT_NSTATS; stat++) { seq_printf(sf, "%s %lld\n", cpuacct_stat_desc[stat], - cputime64_to_clock_t(val[stat])); + (long long)nsec_to_clock_t(val[stat])); } return 0; diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index e73119013c53..fba235c7d026 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -128,10 +128,10 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, const struct sched_dl_entity *dl_se = &p->dl; if (later_mask && - cpumask_and(later_mask, cp->free_cpus, tsk_cpus_allowed(p))) { + cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) { best_cpu = cpumask_any(later_mask); goto out; - } else if (cpumask_test_cpu(cpudl_maximum(cp), tsk_cpus_allowed(p)) && + } else if (cpumask_test_cpu(cpudl_maximum(cp), &p->cpus_allowed) && dl_time_before(dl_se->deadline, cp->elements[0].dl)) { best_cpu = cpudl_maximum(cp); if (later_mask) diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c index 69e06898997d..54c577578da6 100644 --- a/kernel/sched/cpufreq_schedutil.c +++ b/kernel/sched/cpufreq_schedutil.c @@ -12,11 +12,15 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/cpufreq.h> +#include <linux/kthread.h> +#include <uapi/linux/sched/types.h> #include <linux/slab.h> #include <trace/events/power.h> #include "sched.h" +#define SUGOV_KTHREAD_PRIORITY 50 + struct sugov_tunables { struct gov_attr_set attr_set; unsigned int rate_limit_us; @@ -32,11 +36,14 @@ struct sugov_policy { u64 last_freq_update_time; s64 freq_update_delay_ns; unsigned int next_freq; + unsigned int cached_raw_freq; /* The next fields are only needed if fast switch cannot be used. */ struct irq_work irq_work; - struct work_struct work; + struct kthread_work work; struct mutex work_lock; + struct kthread_worker worker; + struct task_struct *thread; bool work_in_progress; bool need_freq_update; @@ -46,7 +53,6 @@ struct sugov_cpu { struct update_util_data update_util; struct sugov_policy *sg_policy; - unsigned int cached_raw_freq; unsigned long iowait_boost; unsigned long iowait_boost_max; u64 last_update; @@ -110,7 +116,7 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, /** * get_next_freq - Compute a new frequency for a given cpufreq policy. - * @sg_cpu: schedutil cpu object to compute the new frequency for. + * @sg_policy: schedutil policy object to compute the new frequency for. * @util: Current CPU utilization. * @max: CPU capacity. * @@ -130,19 +136,18 @@ static void sugov_update_commit(struct sugov_policy *sg_policy, u64 time, * next_freq (as calculated above) is returned, subject to policy min/max and * cpufreq driver limitations. */ -static unsigned int get_next_freq(struct sugov_cpu *sg_cpu, unsigned long util, - unsigned long max) +static unsigned int get_next_freq(struct sugov_policy *sg_policy, + unsigned long util, unsigned long max) { - struct sugov_policy *sg_policy = sg_cpu->sg_policy; struct cpufreq_policy *policy = sg_policy->policy; unsigned int freq = arch_scale_freq_invariant() ? policy->cpuinfo.max_freq : policy->cur; freq = (freq + (freq >> 2)) * util / max; - if (freq == sg_cpu->cached_raw_freq && sg_policy->next_freq != UINT_MAX) + if (freq == sg_policy->cached_raw_freq && sg_policy->next_freq != UINT_MAX) return sg_policy->next_freq; - sg_cpu->cached_raw_freq = freq; + sg_policy->cached_raw_freq = freq; return cpufreq_driver_resolve_freq(policy, freq); } @@ -207,7 +212,7 @@ static void sugov_update_single(struct update_util_data *hook, u64 time, } else { sugov_get_util(&util, &max); sugov_iowait_boost(sg_cpu, &util, &max); - next_f = get_next_freq(sg_cpu, util, max); + next_f = get_next_freq(sg_policy, util, max); } sugov_update_commit(sg_policy, time, next_f); } @@ -261,7 +266,7 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, sugov_iowait_boost(j_sg_cpu, &util, &max); } - return get_next_freq(sg_cpu, util, max); + return get_next_freq(sg_policy, util, max); } static void sugov_update_shared(struct update_util_data *hook, u64 time, @@ -291,7 +296,7 @@ static void sugov_update_shared(struct update_util_data *hook, u64 time, raw_spin_unlock(&sg_policy->update_lock); } -static void sugov_work(struct work_struct *work) +static void sugov_work(struct kthread_work *work) { struct sugov_policy *sg_policy = container_of(work, struct sugov_policy, work); @@ -308,7 +313,21 @@ static void sugov_irq_work(struct irq_work *irq_work) struct sugov_policy *sg_policy; sg_policy = container_of(irq_work, struct sugov_policy, irq_work); - schedule_work_on(smp_processor_id(), &sg_policy->work); + + /* + * For RT and deadline tasks, the schedutil governor shoots the + * frequency to maximum. Special care must be taken to ensure that this + * kthread doesn't result in the same behavior. + * + * This is (mostly) guaranteed by the work_in_progress flag. The flag is + * updated only at the end of the sugov_work() function and before that + * the schedutil governor rejects all other frequency scaling requests. + * + * There is a very rare case though, where the RT thread yields right + * after the work_in_progress flag is cleared. The effects of that are + * neglected for now. + */ + kthread_queue_work(&sg_policy->worker, &sg_policy->work); } /************************** sysfs interface ************************/ @@ -371,19 +390,64 @@ static struct sugov_policy *sugov_policy_alloc(struct cpufreq_policy *policy) return NULL; sg_policy->policy = policy; - init_irq_work(&sg_policy->irq_work, sugov_irq_work); - INIT_WORK(&sg_policy->work, sugov_work); - mutex_init(&sg_policy->work_lock); raw_spin_lock_init(&sg_policy->update_lock); return sg_policy; } static void sugov_policy_free(struct sugov_policy *sg_policy) { - mutex_destroy(&sg_policy->work_lock); kfree(sg_policy); } +static int sugov_kthread_create(struct sugov_policy *sg_policy) +{ + struct task_struct *thread; + struct sched_param param = { .sched_priority = MAX_USER_RT_PRIO / 2 }; + struct cpufreq_policy *policy = sg_policy->policy; + int ret; + + /* kthread only required for slow path */ + if (policy->fast_switch_enabled) + return 0; + + kthread_init_work(&sg_policy->work, sugov_work); + kthread_init_worker(&sg_policy->worker); + thread = kthread_create(kthread_worker_fn, &sg_policy->worker, + "sugov:%d", + cpumask_first(policy->related_cpus)); + if (IS_ERR(thread)) { + pr_err("failed to create sugov thread: %ld\n", PTR_ERR(thread)); + return PTR_ERR(thread); + } + + ret = sched_setscheduler_nocheck(thread, SCHED_FIFO, ¶m); + if (ret) { + kthread_stop(thread); + pr_warn("%s: failed to set SCHED_FIFO\n", __func__); + return ret; + } + + sg_policy->thread = thread; + kthread_bind_mask(thread, policy->related_cpus); + init_irq_work(&sg_policy->irq_work, sugov_irq_work); + mutex_init(&sg_policy->work_lock); + + wake_up_process(thread); + + return 0; +} + +static void sugov_kthread_stop(struct sugov_policy *sg_policy) +{ + /* kthread only required for slow path */ + if (sg_policy->policy->fast_switch_enabled) + return; + + kthread_flush_worker(&sg_policy->worker); + kthread_stop(sg_policy->thread); + mutex_destroy(&sg_policy->work_lock); +} + static struct sugov_tunables *sugov_tunables_alloc(struct sugov_policy *sg_policy) { struct sugov_tunables *tunables; @@ -416,16 +480,24 @@ static int sugov_init(struct cpufreq_policy *policy) if (policy->governor_data) return -EBUSY; + cpufreq_enable_fast_switch(policy); + sg_policy = sugov_policy_alloc(policy); - if (!sg_policy) - return -ENOMEM; + if (!sg_policy) { + ret = -ENOMEM; + goto disable_fast_switch; + } + + ret = sugov_kthread_create(sg_policy); + if (ret) + goto free_sg_policy; mutex_lock(&global_tunables_lock); if (global_tunables) { if (WARN_ON(have_governor_per_policy())) { ret = -EINVAL; - goto free_sg_policy; + goto stop_kthread; } policy->governor_data = sg_policy; sg_policy->tunables = global_tunables; @@ -437,7 +509,7 @@ static int sugov_init(struct cpufreq_policy *policy) tunables = sugov_tunables_alloc(sg_policy); if (!tunables) { ret = -ENOMEM; - goto free_sg_policy; + goto stop_kthread; } tunables->rate_limit_us = LATENCY_MULTIPLIER; @@ -454,20 +526,25 @@ static int sugov_init(struct cpufreq_policy *policy) if (ret) goto fail; - out: +out: mutex_unlock(&global_tunables_lock); - - cpufreq_enable_fast_switch(policy); return 0; - fail: +fail: policy->governor_data = NULL; sugov_tunables_free(tunables); - free_sg_policy: +stop_kthread: + sugov_kthread_stop(sg_policy); + +free_sg_policy: mutex_unlock(&global_tunables_lock); sugov_policy_free(sg_policy); + +disable_fast_switch: + cpufreq_disable_fast_switch(policy); + pr_err("initialization failed (error %d)\n", ret); return ret; } @@ -478,8 +555,6 @@ static void sugov_exit(struct cpufreq_policy *policy) struct sugov_tunables *tunables = sg_policy->tunables; unsigned int count; - cpufreq_disable_fast_switch(policy); - mutex_lock(&global_tunables_lock); count = gov_attr_set_put(&tunables->attr_set, &sg_policy->tunables_hook); @@ -489,7 +564,9 @@ static void sugov_exit(struct cpufreq_policy *policy) mutex_unlock(&global_tunables_lock); + sugov_kthread_stop(sg_policy); sugov_policy_free(sg_policy); + cpufreq_disable_fast_switch(policy); } static int sugov_start(struct cpufreq_policy *policy) @@ -502,25 +579,19 @@ static int sugov_start(struct cpufreq_policy *policy) sg_policy->next_freq = UINT_MAX; sg_policy->work_in_progress = false; sg_policy->need_freq_update = false; + sg_policy->cached_raw_freq = 0; for_each_cpu(cpu, policy->cpus) { struct sugov_cpu *sg_cpu = &per_cpu(sugov_cpu, cpu); + memset(sg_cpu, 0, sizeof(*sg_cpu)); sg_cpu->sg_policy = sg_policy; - if (policy_is_shared(policy)) { - sg_cpu->util = 0; - sg_cpu->max = 0; - sg_cpu->flags = SCHED_CPUFREQ_RT; - sg_cpu->last_update = 0; - sg_cpu->cached_raw_freq = 0; - sg_cpu->iowait_boost = 0; - sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - sugov_update_shared); - } else { - cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, - sugov_update_single); - } + sg_cpu->flags = SCHED_CPUFREQ_RT; + sg_cpu->iowait_boost_max = policy->cpuinfo.max_freq; + cpufreq_add_update_util_hook(cpu, &sg_cpu->update_util, + policy_is_shared(policy) ? + sugov_update_shared : + sugov_update_single); } return 0; } @@ -535,8 +606,10 @@ static void sugov_stop(struct cpufreq_policy *policy) synchronize_sched(); - irq_work_sync(&sg_policy->irq_work); - cancel_work_sync(&sg_policy->work); + if (!policy->fast_switch_enabled) { + irq_work_sync(&sg_policy->irq_work); + kthread_cancel_work_sync(&sg_policy->work); + } } static void sugov_limits(struct cpufreq_policy *policy) diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 11e9705bf937..981fcd7dc394 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -103,11 +103,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p, if (skip) continue; - if (cpumask_any_and(tsk_cpus_allowed(p), vec->mask) >= nr_cpu_ids) + if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids) continue; if (lowest_mask) { - cpumask_and(lowest_mask, tsk_cpus_allowed(p), vec->mask); + cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask); /* * We have to ensure that we have at least one bit diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 5ebee3164e64..f3778e2b46c8 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -4,11 +4,8 @@ #include <linux/kernel_stat.h> #include <linux/static_key.h> #include <linux/context_tracking.h> +#include <linux/sched/cputime.h> #include "sched.h" -#ifdef CONFIG_PARAVIRT -#include <asm/paravirt.h> -#endif - #ifdef CONFIG_IRQ_TIME_ACCOUNTING @@ -44,6 +41,7 @@ void disable_sched_clock_irqtime(void) void irqtime_account_irq(struct task_struct *curr) { struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime); + u64 *cpustat = kcpustat_this_cpu->cpustat; s64 delta; int cpu; @@ -61,49 +59,34 @@ void irqtime_account_irq(struct task_struct *curr) * in that case, so as not to confuse scheduler with a special task * that do not consume any time, but still wants to run. */ - if (hardirq_count()) - irqtime->hardirq_time += delta; - else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) - irqtime->softirq_time += delta; + if (hardirq_count()) { + cpustat[CPUTIME_IRQ] += delta; + irqtime->tick_delta += delta; + } else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) { + cpustat[CPUTIME_SOFTIRQ] += delta; + irqtime->tick_delta += delta; + } u64_stats_update_end(&irqtime->sync); } EXPORT_SYMBOL_GPL(irqtime_account_irq); -static cputime_t irqtime_account_update(u64 irqtime, int idx, cputime_t maxtime) +static u64 irqtime_tick_accounted(u64 maxtime) { - u64 *cpustat = kcpustat_this_cpu->cpustat; - cputime_t irq_cputime; - - irq_cputime = nsecs_to_cputime64(irqtime) - cpustat[idx]; - irq_cputime = min(irq_cputime, maxtime); - cpustat[idx] += irq_cputime; - - return irq_cputime; -} + struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime); + u64 delta; -static cputime_t irqtime_account_hi_update(cputime_t maxtime) -{ - return irqtime_account_update(__this_cpu_read(cpu_irqtime.hardirq_time), - CPUTIME_IRQ, maxtime); -} + delta = min(irqtime->tick_delta, maxtime); + irqtime->tick_delta -= delta; -static cputime_t irqtime_account_si_update(cputime_t maxtime) -{ - return irqtime_account_update(__this_cpu_read(cpu_irqtime.softirq_time), - CPUTIME_SOFTIRQ, maxtime); + return delta; } #else /* CONFIG_IRQ_TIME_ACCOUNTING */ #define sched_clock_irqtime (0) -static cputime_t irqtime_account_hi_update(cputime_t dummy) -{ - return 0; -} - -static cputime_t irqtime_account_si_update(cputime_t dummy) +static u64 irqtime_tick_accounted(u64 dummy) { return 0; } @@ -128,22 +111,19 @@ static inline void task_group_account_field(struct task_struct *p, int index, * Account user cpu time to a process. * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in user space since the last update - * @cputime_scaled: cputime scaled by cpu frequency */ -void account_user_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) +void account_user_time(struct task_struct *p, u64 cputime) { int index; /* Add user time to process. */ p->utime += cputime; - p->utimescaled += cputime_scaled; account_group_user_time(p, cputime); index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER; /* Add user time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); + task_group_account_field(p, index, cputime); /* Account for user time used */ acct_account_cputime(p); @@ -153,26 +133,23 @@ void account_user_time(struct task_struct *p, cputime_t cputime, * Account guest cpu time to a process. * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in virtual machine since the last update - * @cputime_scaled: cputime scaled by cpu frequency */ -static void account_guest_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled) +void account_guest_time(struct task_struct *p, u64 cputime) { u64 *cpustat = kcpustat_this_cpu->cpustat; /* Add guest time to process. */ p->utime += cputime; - p->utimescaled += cputime_scaled; account_group_user_time(p, cputime); p->gtime += cputime; /* Add guest time to cpustat. */ if (task_nice(p) > 0) { - cpustat[CPUTIME_NICE] += (__force u64) cputime; - cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime; + cpustat[CPUTIME_NICE] += cputime; + cpustat[CPUTIME_GUEST_NICE] += cputime; } else { - cpustat[CPUTIME_USER] += (__force u64) cputime; - cpustat[CPUTIME_GUEST] += (__force u64) cputime; + cpustat[CPUTIME_USER] += cputime; + cpustat[CPUTIME_GUEST] += cputime; } } @@ -180,20 +157,17 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, * Account system cpu time to a process and desired cpustat field * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency - * @target_cputime64: pointer to cpustat field that has to be updated + * @index: pointer to cpustat field that has to be updated */ -static inline -void __account_system_time(struct task_struct *p, cputime_t cputime, - cputime_t cputime_scaled, int index) +void account_system_index_time(struct task_struct *p, + u64 cputime, enum cpu_usage_stat index) { /* Add system time to process. */ p->stime += cputime; - p->stimescaled += cputime_scaled; account_group_system_time(p, cputime); /* Add system time to cpustat. */ - task_group_account_field(p, index, (__force u64) cputime); + task_group_account_field(p, index, cputime); /* Account for system time used */ acct_account_cputime(p); @@ -204,15 +178,13 @@ void __account_system_time(struct task_struct *p, cputime_t cputime, * @p: the process that the cpu time gets accounted to * @hardirq_offset: the offset to subtract from hardirq_count() * @cputime: the cpu time spent in kernel space since the last update - * @cputime_scaled: cputime scaled by cpu frequency */ -void account_system_time(struct task_struct *p, int hardirq_offset, - cputime_t cputime, cputime_t cputime_scaled) +void account_system_time(struct task_struct *p, int hardirq_offset, u64 cputime) { int index; if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { - account_guest_time(p, cputime, cputime_scaled); + account_guest_time(p, cputime); return; } @@ -223,33 +195,33 @@ void account_system_time(struct task_struct *p, int hardirq_offset, else index = CPUTIME_SYSTEM; - __account_system_time(p, cputime, cputime_scaled, index); + account_system_index_time(p, cputime, index); } /* * Account for involuntary wait time. * @cputime: the cpu time spent in involuntary wait */ -void account_steal_time(cputime_t cputime) +void account_steal_time(u64 cputime) { u64 *cpustat = kcpustat_this_cpu->cpustat; - cpustat[CPUTIME_STEAL] += (__force u64) cputime; + cpustat[CPUTIME_STEAL] += cputime; } /* * Account for idle time. * @cputime: the cpu time spent in idle wait */ -void account_idle_time(cputime_t cputime) +void account_idle_time(u64 cputime) { u64 *cpustat = kcpustat_this_cpu->cpustat; struct rq *rq = this_rq(); if (atomic_read(&rq->nr_iowait) > 0) - cpustat[CPUTIME_IOWAIT] += (__force u64) cputime; + cpustat[CPUTIME_IOWAIT] += cputime; else - cpustat[CPUTIME_IDLE] += (__force u64) cputime; + cpustat[CPUTIME_IDLE] += cputime; } /* @@ -257,21 +229,19 @@ void account_idle_time(cputime_t cputime) * ticks are not redelivered later. Due to that, this function may on * occasion account more time than the calling functions think elapsed. */ -static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) +static __always_inline u64 steal_account_process_time(u64 maxtime) { #ifdef CONFIG_PARAVIRT if (static_key_false(¶virt_steal_enabled)) { - cputime_t steal_cputime; u64 steal; steal = paravirt_steal_clock(smp_processor_id()); steal -= this_rq()->prev_steal_time; + steal = min(steal, maxtime); + account_steal_time(steal); + this_rq()->prev_steal_time += steal; - steal_cputime = min(nsecs_to_cputime(steal), maxtime); - account_steal_time(steal_cputime); - this_rq()->prev_steal_time += cputime_to_nsecs(steal_cputime); - - return steal_cputime; + return steal; } #endif return 0; @@ -280,9 +250,9 @@ static __always_inline cputime_t steal_account_process_time(cputime_t maxtime) /* * Account how much elapsed time was spent in steal, irq, or softirq time. */ -static inline cputime_t account_other_time(cputime_t max) +static inline u64 account_other_time(u64 max) { - cputime_t accounted; + u64 accounted; /* Shall be converted to a lockdep-enabled lightweight check */ WARN_ON_ONCE(!irqs_disabled()); @@ -290,10 +260,7 @@ static inline cputime_t account_other_time(cputime_t max) accounted = steal_account_process_time(max); if (accounted < max) - accounted += irqtime_account_hi_update(max - accounted); - - if (accounted < max) - accounted += irqtime_account_si_update(max - accounted); + accounted += irqtime_tick_accounted(max - accounted); return accounted; } @@ -325,7 +292,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t) void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) { struct signal_struct *sig = tsk->signal; - cputime_t utime, stime; + u64 utime, stime; struct task_struct *t; unsigned int seq, nextseq; unsigned long flags; @@ -389,8 +356,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) static void irqtime_account_process_tick(struct task_struct *p, int user_tick, struct rq *rq, int ticks) { - u64 cputime = (__force u64) cputime_one_jiffy * ticks; - cputime_t scaled, other; + u64 other, cputime = TICK_NSEC * ticks; /* * When returning from idle, many ticks can get accounted at @@ -402,8 +368,8 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, other = account_other_time(ULONG_MAX); if (other >= cputime) return; + cputime -= other; - scaled = cputime_to_scaled(cputime); if (this_cpu_ksoftirqd() == p) { /* @@ -411,15 +377,15 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick, * So, we have to handle it separately here. * Also, p->stime needs to be updated for ksoftirqd. */ - __account_system_time(p, cputime, scaled, CPUTIME_SOFTIRQ); + account_system_index_time(p, cputime, CPUTIME_SOFTIRQ); } else if (user_tick) { - account_user_time(p, cputime, scaled); + account_user_time(p, cputime); } else if (p == rq->idle) { account_idle_time(cputime); } else if (p->flags & PF_VCPU) { /* System time or guest time */ - account_guest_time(p, cputime, scaled); + account_guest_time(p, cputime); } else { - __account_system_time(p, cputime, scaled, CPUTIME_SYSTEM); + account_system_index_time(p, cputime, CPUTIME_SYSTEM); } } @@ -448,9 +414,7 @@ void vtime_common_task_switch(struct task_struct *prev) else vtime_account_system(prev); -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - vtime_account_user(prev); -#endif + vtime_flush(prev); arch_vtime_task_switch(prev); } #endif @@ -478,14 +442,14 @@ void vtime_account_irq_enter(struct task_struct *tsk) EXPORT_SYMBOL_GPL(vtime_account_irq_enter); #endif /* __ARCH_HAS_VTIME_ACCOUNT */ -void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { *ut = p->utime; *st = p->stime; } EXPORT_SYMBOL_GPL(task_cputime_adjusted); -void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { struct task_cputime cputime; @@ -502,7 +466,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime */ void account_process_tick(struct task_struct *p, int user_tick) { - cputime_t cputime, scaled, steal; + u64 cputime, steal; struct rq *rq = this_rq(); if (vtime_accounting_cpu_enabled()) @@ -513,19 +477,18 @@ void account_process_tick(struct task_struct *p, int user_tick) return; } - cputime = cputime_one_jiffy; + cputime = TICK_NSEC; steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) return; cputime -= steal; - scaled = cputime_to_scaled(cputime); if (user_tick) - account_user_time(p, cputime, scaled); + account_user_time(p, cputime); else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, cputime, scaled); + account_system_time(p, HARDIRQ_OFFSET, cputime); else account_idle_time(cputime); } @@ -536,14 +499,14 @@ void account_process_tick(struct task_struct *p, int user_tick) */ void account_idle_ticks(unsigned long ticks) { - cputime_t cputime, steal; + u64 cputime, steal; if (sched_clock_irqtime) { irqtime_account_idle_ticks(ticks); return; } - cputime = jiffies_to_cputime(ticks); + cputime = ticks * TICK_NSEC; steal = steal_account_process_time(ULONG_MAX); if (steal >= cputime) @@ -557,7 +520,7 @@ void account_idle_ticks(unsigned long ticks) * Perform (stime * rtime) / total, but avoid multiplication overflow by * loosing precision when the numbers are big. */ -static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) +static u64 scale_stime(u64 stime, u64 rtime, u64 total) { u64 scaled; @@ -594,7 +557,7 @@ drop_precision: * followed by a 64/32->64 divide. */ scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total); - return (__force cputime_t) scaled; + return scaled; } /* @@ -619,14 +582,14 @@ drop_precision: */ static void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev, - cputime_t *ut, cputime_t *st) + u64 *ut, u64 *st) { - cputime_t rtime, stime, utime; + u64 rtime, stime, utime; unsigned long flags; /* Serialize concurrent callers such that we can honour our guarantees */ raw_spin_lock_irqsave(&prev->lock, flags); - rtime = nsecs_to_cputime(curr->sum_exec_runtime); + rtime = curr->sum_exec_runtime; /* * This is possible under two circumstances: @@ -657,8 +620,7 @@ static void cputime_adjust(struct task_cputime *curr, goto update; } - stime = scale_stime((__force u64)stime, (__force u64)rtime, - (__force u64)(stime + utime)); + stime = scale_stime(stime, rtime, stime + utime); update: /* @@ -691,7 +653,7 @@ out: raw_spin_unlock_irqrestore(&prev->lock, flags); } -void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { struct task_cputime cputime = { .sum_exec_runtime = p->se.sum_exec_runtime, @@ -702,7 +664,7 @@ void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) } EXPORT_SYMBOL_GPL(task_cputime_adjusted); -void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st) { struct task_cputime cputime; @@ -712,20 +674,20 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime #endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN -static cputime_t vtime_delta(struct task_struct *tsk) +static u64 vtime_delta(struct task_struct *tsk) { unsigned long now = READ_ONCE(jiffies); if (time_before(now, (unsigned long)tsk->vtime_snap)) return 0; - return jiffies_to_cputime(now - tsk->vtime_snap); + return jiffies_to_nsecs(now - tsk->vtime_snap); } -static cputime_t get_vtime_delta(struct task_struct *tsk) +static u64 get_vtime_delta(struct task_struct *tsk) { unsigned long now = READ_ONCE(jiffies); - cputime_t delta, other; + u64 delta, other; /* * Unlike tick based timing, vtime based timing never has lost @@ -734,7 +696,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) * elapsed time. Limit account_other_time to prevent rounding * errors from causing elapsed vtime to go negative. */ - delta = jiffies_to_cputime(now - tsk->vtime_snap); + delta = jiffies_to_nsecs(now - tsk->vtime_snap); other = account_other_time(delta); WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE); tsk->vtime_snap = now; @@ -744,9 +706,7 @@ static cputime_t get_vtime_delta(struct task_struct *tsk) static void __vtime_account_system(struct task_struct *tsk) { - cputime_t delta_cpu = get_vtime_delta(tsk); - - account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu)); + account_system_time(tsk, irq_count(), get_vtime_delta(tsk)); } void vtime_account_system(struct task_struct *tsk) @@ -761,14 +721,10 @@ void vtime_account_system(struct task_struct *tsk) void vtime_account_user(struct task_struct *tsk) { - cputime_t delta_cpu; - write_seqcount_begin(&tsk->vtime_seqcount); tsk->vtime_snap_whence = VTIME_SYS; - if (vtime_delta(tsk)) { - delta_cpu = get_vtime_delta(tsk); - account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu)); - } + if (vtime_delta(tsk)) + account_user_time(tsk, get_vtime_delta(tsk)); write_seqcount_end(&tsk->vtime_seqcount); } @@ -809,9 +765,7 @@ EXPORT_SYMBOL_GPL(vtime_guest_exit); void vtime_account_idle(struct task_struct *tsk) { - cputime_t delta_cpu = get_vtime_delta(tsk); - - account_idle_time(delta_cpu); + account_idle_time(get_vtime_delta(tsk)); } void arch_vtime_task_switch(struct task_struct *prev) @@ -838,10 +792,10 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_restore(flags); } -cputime_t task_gtime(struct task_struct *t) +u64 task_gtime(struct task_struct *t) { unsigned int seq; - cputime_t gtime; + u64 gtime; if (!vtime_accounting_enabled()) return t->gtime; @@ -863,29 +817,25 @@ cputime_t task_gtime(struct task_struct *t) * add up the pending nohz execution time since the last * cputime snapshot. */ -static void -fetch_task_cputime(struct task_struct *t, - cputime_t *u_dst, cputime_t *s_dst, - cputime_t *u_src, cputime_t *s_src, - cputime_t *udelta, cputime_t *sdelta) +void task_cputime(struct task_struct *t, u64 *utime, u64 *stime) { + u64 delta; unsigned int seq; - unsigned long long delta; - do { - *udelta = 0; - *sdelta = 0; + if (!vtime_accounting_enabled()) { + *utime = t->utime; + *stime = t->stime; + return; + } + do { seq = read_seqcount_begin(&t->vtime_seqcount); - if (u_dst) - *u_dst = *u_src; - if (s_dst) - *s_dst = *s_src; + *utime = t->utime; + *stime = t->stime; /* Task is sleeping, nothing to add */ - if (t->vtime_snap_whence == VTIME_INACTIVE || - is_idle_task(t)) + if (t->vtime_snap_whence == VTIME_INACTIVE || is_idle_task(t)) continue; delta = vtime_delta(t); @@ -894,54 +844,10 @@ fetch_task_cputime(struct task_struct *t, * Task runs either in user or kernel space, add pending nohz time to * the right place. */ - if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) { - *udelta = delta; - } else { - if (t->vtime_snap_whence == VTIME_SYS) - *sdelta = delta; - } + if (t->vtime_snap_whence == VTIME_USER || t->flags & PF_VCPU) + *utime += delta; + else if (t->vtime_snap_whence == VTIME_SYS) + *stime += delta; } while (read_seqcount_retry(&t->vtime_seqcount, seq)); } - - -void task_cputime(struct task_struct *t, cputime_t *utime, cputime_t *stime) -{ - cputime_t udelta, sdelta; - - if (!vtime_accounting_enabled()) { - if (utime) - *utime = t->utime; - if (stime) - *stime = t->stime; - return; - } - - fetch_task_cputime(t, utime, stime, &t->utime, - &t->stime, &udelta, &sdelta); - if (utime) - *utime += udelta; - if (stime) - *stime += sdelta; -} - -void task_cputime_scaled(struct task_struct *t, - cputime_t *utimescaled, cputime_t *stimescaled) -{ - cputime_t udelta, sdelta; - - if (!vtime_accounting_enabled()) { - if (utimescaled) - *utimescaled = t->utimescaled; - if (stimescaled) - *stimescaled = t->stimescaled; - return; - } - - fetch_task_cputime(t, utimescaled, stimescaled, - &t->utimescaled, &t->stimescaled, &udelta, &sdelta); - if (utimescaled) - *utimescaled += cputime_to_scaled(udelta); - if (stimescaled) - *stimescaled += cputime_to_scaled(sdelta); -} #endif /* CONFIG_VIRT_CPU_ACCOUNTING_GEN */ diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 37e2449186c4..a2ce59015642 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -134,7 +134,7 @@ static void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - if (tsk_nr_cpus_allowed(p) > 1) + if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory++; update_dl_migration(dl_rq); @@ -144,7 +144,7 @@ static void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq) { struct task_struct *p = dl_task_of(dl_se); - if (tsk_nr_cpus_allowed(p) > 1) + if (p->nr_cpus_allowed > 1) dl_rq->dl_nr_migratory--; update_dl_migration(dl_rq); @@ -252,7 +252,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p * If we cannot preempt any rq, fall back to pick any * online cpu. */ - cpu = cpumask_any_and(cpu_active_mask, tsk_cpus_allowed(p)); + cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed); if (cpu >= nr_cpu_ids) { /* * Fail to find any suitable cpu. @@ -445,13 +445,13 @@ static void replenish_dl_entity(struct sched_dl_entity *dl_se, * * This function returns true if: * - * runtime / (deadline - t) > dl_runtime / dl_period , + * runtime / (deadline - t) > dl_runtime / dl_deadline , * * IOW we can't recycle current parameters. * - * Notice that the bandwidth check is done against the period. For + * Notice that the bandwidth check is done against the deadline. For * task with deadline equal to period this is the same of using - * dl_deadline instead of dl_period in the equation above. + * dl_period instead of dl_deadline in the equation above. */ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, struct sched_dl_entity *pi_se, u64 t) @@ -476,7 +476,7 @@ static bool dl_entity_overflow(struct sched_dl_entity *dl_se, * of anything below microseconds resolution is actually fiction * (but still we want to give the user that illusion >;). */ - left = (pi_se->dl_period >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); + left = (pi_se->dl_deadline >> DL_SCALE) * (dl_se->runtime >> DL_SCALE); right = ((dl_se->deadline - t) >> DL_SCALE) * (pi_se->dl_runtime >> DL_SCALE); @@ -505,10 +505,15 @@ static void update_dl_entity(struct sched_dl_entity *dl_se, } } +static inline u64 dl_next_period(struct sched_dl_entity *dl_se) +{ + return dl_se->deadline - dl_se->dl_deadline + dl_se->dl_period; +} + /* * If the entity depleted all its runtime, and if we want it to sleep * while waiting for some new execution time to become available, we - * set the bandwidth enforcement timer to the replenishment instant + * set the bandwidth replenishment timer to the replenishment instant * and try to activate it. * * Notice that it is important for the caller to know if the timer @@ -530,7 +535,7 @@ static int start_dl_timer(struct task_struct *p) * that it is actually coming from rq->clock and not from * hrtimer's time base reading. */ - act = ns_to_ktime(dl_se->deadline); + act = ns_to_ktime(dl_next_period(dl_se)); now = hrtimer_cb_get_time(timer); delta = ktime_to_ns(now) - rq_clock(rq); act = ktime_add_ns(act, delta); @@ -586,7 +591,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) /* * The task might have changed its scheduling policy to something - * different than SCHED_DEADLINE (through switched_fromd_dl()). + * different than SCHED_DEADLINE (through switched_from_dl()). */ if (!dl_task(p)) { __dl_clear_params(p); @@ -638,6 +643,7 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) lockdep_unpin_lock(&rq->lock, rf.cookie); rq = dl_task_offline_migration(rq, p); rf.cookie = lockdep_pin_lock(&rq->lock); + update_rq_clock(rq); /* * Now that the task has been migrated to the new RQ and we @@ -663,9 +669,9 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer) * Nothing relies on rq->lock after this, so its safe to drop * rq->lock. */ - lockdep_unpin_lock(&rq->lock, rf.cookie); + rq_unpin_lock(rq, &rf); push_dl_task(rq); - lockdep_repin_lock(&rq->lock, rf.cookie); + rq_repin_lock(rq, &rf); } #endif @@ -689,6 +695,37 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se) timer->function = dl_task_timer; } +/* + * During the activation, CBS checks if it can reuse the current task's + * runtime and period. If the deadline of the task is in the past, CBS + * cannot use the runtime, and so it replenishes the task. This rule + * works fine for implicit deadline tasks (deadline == period), and the + * CBS was designed for implicit deadline tasks. However, a task with + * constrained deadline (deadine < period) might be awakened after the + * deadline, but before the next period. In this case, replenishing the + * task would allow it to run for runtime / deadline. As in this case + * deadline < period, CBS enables a task to run for more than the + * runtime / period. In a very loaded system, this can cause a domino + * effect, making other tasks miss their deadlines. + * + * To avoid this problem, in the activation of a constrained deadline + * task after the deadline but before the next period, throttle the + * task and set the replenishing timer to the begin of the next period, + * unless it is boosted. + */ +static inline void dl_check_constrained_dl(struct sched_dl_entity *dl_se) +{ + struct task_struct *p = dl_task_of(dl_se); + struct rq *rq = rq_of_dl_rq(dl_rq_of_se(dl_se)); + + if (dl_time_before(dl_se->deadline, rq_clock(rq)) && + dl_time_before(rq_clock(rq), dl_next_period(dl_se))) { + if (unlikely(dl_se->dl_boosted || !start_dl_timer(p))) + return; + dl_se->dl_throttled = 1; + } +} + static int dl_runtime_exceeded(struct sched_dl_entity *dl_se) { @@ -922,6 +959,11 @@ static void dequeue_dl_entity(struct sched_dl_entity *dl_se) __dequeue_dl_entity(dl_se); } +static inline bool dl_is_constrained(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline < dl_se->dl_period; +} + static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) { struct task_struct *pi_task = rt_mutex_get_top_task(p); @@ -948,6 +990,15 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) } /* + * Check if a constrained deadline task was activated + * after the deadline but before the next period. + * If that is the case, the task will be throttled and + * the replenishment timer will be set to the next period. + */ + if (!p->dl.dl_throttled && dl_is_constrained(&p->dl)) + dl_check_constrained_dl(&p->dl); + + /* * If p is throttled, we do nothing. In fact, if it exhausted * its budget it needs a replenishment and, since it now is on * its rq, the bandwidth timer callback (which clearly has not @@ -958,7 +1009,7 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) enqueue_dl_entity(&p->dl, pi_se, flags); - if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1032,9 +1083,9 @@ select_task_rq_dl(struct task_struct *p, int cpu, int sd_flag, int flags) * try to make it stay here, it might be important. */ if (unlikely(dl_task(curr)) && - (tsk_nr_cpus_allowed(curr) < 2 || + (curr->nr_cpus_allowed < 2 || !dl_entity_preempt(&p->dl, &curr->dl)) && - (tsk_nr_cpus_allowed(p) > 1)) { + (p->nr_cpus_allowed > 1)) { int target = find_later_rq(p); if (target != -1 && @@ -1055,7 +1106,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) * Current can't be migrated, useless to reschedule, * let's hope p can move out. */ - if (tsk_nr_cpus_allowed(rq->curr) == 1 || + if (rq->curr->nr_cpus_allowed == 1 || cpudl_find(&rq->rd->cpudl, rq->curr, NULL) == -1) return; @@ -1063,7 +1114,7 @@ static void check_preempt_equal_dl(struct rq *rq, struct task_struct *p) * p is migratable, so let's not schedule it and * see if it is pushed or pulled somewhere else. */ - if (tsk_nr_cpus_allowed(p) != 1 && + if (p->nr_cpus_allowed != 1 && cpudl_find(&rq->rd->cpudl, p, NULL) != -1) return; @@ -1118,7 +1169,7 @@ static struct sched_dl_entity *pick_next_dl_entity(struct rq *rq, } struct task_struct * -pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct sched_dl_entity *dl_se; struct task_struct *p; @@ -1133,11 +1184,11 @@ pick_next_task_dl(struct rq *rq, struct task_struct *prev, struct pin_cookie coo * disabled avoiding further scheduler activity on it and we're * being very careful to re-start the picking loop. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); pull_dl_task(rq); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); /* - * pull_rt_task() can drop (and re-acquire) rq->lock; this + * pull_dl_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. */ @@ -1178,7 +1229,7 @@ static void put_prev_task_dl(struct rq *rq, struct task_struct *p) { update_curr_dl(rq); - if (on_dl_rq(&p->dl) && tsk_nr_cpus_allowed(p) > 1) + if (on_dl_rq(&p->dl) && p->nr_cpus_allowed > 1) enqueue_pushable_dl_task(rq, p); } @@ -1235,7 +1286,7 @@ static void set_curr_task_dl(struct rq *rq) static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + cpumask_test_cpu(cpu, &p->cpus_allowed)) return 1; return 0; } @@ -1279,7 +1330,7 @@ static int find_later_rq(struct task_struct *task) if (unlikely(!later_mask)) return -1; - if (tsk_nr_cpus_allowed(task) == 1) + if (task->nr_cpus_allowed == 1) return -1; /* @@ -1384,8 +1435,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) /* Retry if something changed. */ if (double_lock_balance(rq, later_rq)) { if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(later_rq->cpu, - tsk_cpus_allowed(task)) || + !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || !dl_task(task) || !task_on_rq_queued(task))) { @@ -1425,7 +1475,7 @@ static struct task_struct *pick_next_pushable_dl_task(struct rq *rq) BUG_ON(rq->cpu != task_cpu(p)); BUG_ON(task_current(rq, p)); - BUG_ON(tsk_nr_cpus_allowed(p) <= 1); + BUG_ON(p->nr_cpus_allowed <= 1); BUG_ON(!task_on_rq_queued(p)); BUG_ON(!dl_task(p)); @@ -1464,7 +1514,7 @@ retry: */ if (dl_task(rq->curr) && dl_time_before(next_task->dl.deadline, rq->curr->dl.deadline) && - tsk_nr_cpus_allowed(rq->curr) > 1) { + rq->curr->nr_cpus_allowed > 1) { resched_curr(rq); return 0; } @@ -1611,9 +1661,9 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p) { if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && - tsk_nr_cpus_allowed(p) > 1 && + p->nr_cpus_allowed > 1 && dl_task(rq->curr) && - (tsk_nr_cpus_allowed(rq->curr) < 2 || + (rq->curr->nr_cpus_allowed < 2 || !dl_entity_preempt(&p->dl, &rq->curr->dl))) { push_dl_tasks(rq); } @@ -1727,14 +1777,13 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p) if (rq->curr != p) { #ifdef CONFIG_SMP - if (tsk_nr_cpus_allowed(p) > 1 && rq->dl.overloaded) + if (p->nr_cpus_allowed > 1 && rq->dl.overloaded) queue_push_tasks(rq); -#else +#endif if (dl_task(rq->curr)) check_preempt_curr_dl(rq, p, 0); else resched_curr(rq); -#endif } } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index fa178b62ea79..38f019324f1a 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -11,7 +11,8 @@ */ #include <linux/proc_fs.h> -#include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/task.h> #include <linux/seq_file.h> #include <linux/kallsyms.h> #include <linux/utsname.h> @@ -953,6 +954,10 @@ void proc_sched_show_task(struct task_struct *p, struct seq_file *m) #endif P(policy); P(prio); + if (p->policy == SCHED_DEADLINE) { + P(dl.runtime); + P(dl.deadline); + } #undef PN_SCHEDSTAT #undef PN #undef __PN diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index c242944f5cbd..dea138964b91 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -20,7 +20,9 @@ * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra */ -#include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/sched/topology.h> + #include <linux/latencytop.h> #include <linux/cpumask.h> #include <linux/cpuidle.h> @@ -37,7 +39,6 @@ /* * Targeted preemption latency for CPU-bound tasks: - * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) * * NOTE: this latency value is not the same as the concept of * 'timeslice length' - timeslices in CFS are of variable length @@ -46,31 +47,35 @@ * * (to see the precise effective timeslice length of your workload, * run vmstat and monitor the context-switches (cs) field) + * + * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_latency = 6000000ULL; -unsigned int normalized_sysctl_sched_latency = 6000000ULL; +unsigned int sysctl_sched_latency = 6000000ULL; +unsigned int normalized_sysctl_sched_latency = 6000000ULL; /* * The initial- and re-scaling of tunables is configurable - * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus)) * * Options are: - * SCHED_TUNABLESCALING_NONE - unscaled, always *1 - * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus) - * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus + * + * SCHED_TUNABLESCALING_NONE - unscaled, always *1 + * SCHED_TUNABLESCALING_LOG - scaled logarithmical, *1+ilog(ncpus) + * SCHED_TUNABLESCALING_LINEAR - scaled linear, *ncpus + * + * (default SCHED_TUNABLESCALING_LOG = *(1+ilog(ncpus)) */ -enum sched_tunable_scaling sysctl_sched_tunable_scaling - = SCHED_TUNABLESCALING_LOG; +enum sched_tunable_scaling sysctl_sched_tunable_scaling = SCHED_TUNABLESCALING_LOG; /* * Minimal preemption granularity for CPU-bound tasks: + * * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_min_granularity = 750000ULL; -unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; +unsigned int sysctl_sched_min_granularity = 750000ULL; +unsigned int normalized_sysctl_sched_min_granularity = 750000ULL; /* - * is kept at sysctl_sched_latency / sysctl_sched_min_granularity + * This value is kept at sysctl_sched_latency/sysctl_sched_min_granularity */ static unsigned int sched_nr_latency = 8; @@ -82,23 +87,27 @@ unsigned int sysctl_sched_child_runs_first __read_mostly; /* * SCHED_OTHER wake-up granularity. - * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) * * This option delays the preemption effects of decoupled workloads * and reduces their over-scheduling. Synchronous workloads will still * have immediate wakeup/sleep latencies. + * + * (default: 1 msec * (1 + ilog(ncpus)), units: nanoseconds) */ -unsigned int sysctl_sched_wakeup_granularity = 1000000UL; -unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int sysctl_sched_wakeup_granularity = 1000000UL; +unsigned int normalized_sysctl_sched_wakeup_granularity = 1000000UL; -const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +const_debug unsigned int sysctl_sched_migration_cost = 500000UL; +#ifdef CONFIG_SMP /* - * The exponential sliding window over which load is averaged for shares - * distribution. - * (default: 10msec) + * For asym packing, by default the lower numbered cpu has higher priority. */ -unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; +int __weak arch_asym_cpu_priority(int cpu) +{ + return -cpu; +} +#endif #ifdef CONFIG_CFS_BANDWIDTH /* @@ -109,16 +118,18 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL; * to consumption or the quota being specified to be smaller than the slice) * we will always only issue the remaining available time. * - * default: 5 msec, units: microseconds - */ -unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; + * (default: 5 msec, units: microseconds) + */ +unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL; #endif /* * The margin used when comparing utilization with CPU capacity: - * util * 1024 < capacity * margin + * util * margin < capacity * 1024 + * + * (default: ~20%) */ -unsigned int capacity_margin = 1280; /* ~20% */ +unsigned int capacity_margin = 1280; static inline void update_load_add(struct load_weight *lw, unsigned long inc) { @@ -290,19 +301,59 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp) static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq) { if (!cfs_rq->on_list) { + struct rq *rq = rq_of(cfs_rq); + int cpu = cpu_of(rq); /* * Ensure we either appear before our parent (if already * enqueued) or force our parent to appear after us when it is - * enqueued. The fact that we always enqueue bottom-up - * reduces this to two cases. + * enqueued. The fact that we always enqueue bottom-up + * reduces this to two cases and a special case for the root + * cfs_rq. Furthermore, it also means that we will always reset + * tmp_alone_branch either when the branch is connected + * to a tree or when we reach the beg of the tree */ if (cfs_rq->tg->parent && - cfs_rq->tg->parent->cfs_rq[cpu_of(rq_of(cfs_rq))]->on_list) { - list_add_rcu(&cfs_rq->leaf_cfs_rq_list, - &rq_of(cfs_rq)->leaf_cfs_rq_list); - } else { + cfs_rq->tg->parent->cfs_rq[cpu]->on_list) { + /* + * If parent is already on the list, we add the child + * just before. Thanks to circular linked property of + * the list, this means to put the child at the tail + * of the list that starts by parent. + */ + list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, + &(cfs_rq->tg->parent->cfs_rq[cpu]->leaf_cfs_rq_list)); + /* + * The branch is now connected to its tree so we can + * reset tmp_alone_branch to the beginning of the + * list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + } else if (!cfs_rq->tg->parent) { + /* + * cfs rq without parent should be put + * at the tail of the list. + */ list_add_tail_rcu(&cfs_rq->leaf_cfs_rq_list, - &rq_of(cfs_rq)->leaf_cfs_rq_list); + &rq->leaf_cfs_rq_list); + /* + * We have reach the beg of a tree so we can reset + * tmp_alone_branch to the beginning of the list. + */ + rq->tmp_alone_branch = &rq->leaf_cfs_rq_list; + } else { + /* + * The parent has not already been added so we want to + * make sure that it will be put after us. + * tmp_alone_branch points to the beg of the branch + * where we will add parent. + */ + list_add_rcu(&cfs_rq->leaf_cfs_rq_list, + rq->tmp_alone_branch); + /* + * update tmp_alone_branch to points to the new beg + * of the branch + */ + rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list; } cfs_rq->on_list = 1; @@ -708,9 +759,7 @@ void init_entity_runnable_average(struct sched_entity *se) } static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq); -static int update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq); -static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force); -static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se); +static void attach_entity_cfs_rq(struct sched_entity *se); /* * With new tasks being created, their initial util_avgs are extrapolated @@ -742,7 +791,6 @@ void post_init_entity_util_avg(struct sched_entity *se) struct cfs_rq *cfs_rq = cfs_rq_of(se); struct sched_avg *sa = &se->avg; long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2; - u64 now = cfs_rq_clock_task(cfs_rq); if (cap > 0) { if (cfs_rq->avg.util_avg != 0) { @@ -770,14 +818,12 @@ void post_init_entity_util_avg(struct sched_entity *se) * such that the next switched_to_fair() has the * expected state. */ - se->avg.last_update_time = now; + se->avg.last_update_time = cfs_rq_clock_task(cfs_rq); return; } } - update_cfs_rq_load_avg(now, cfs_rq, false); - attach_entity_load_avg(cfs_rq, se); - update_tg_load_avg(cfs_rq, false); + attach_entity_cfs_rq(se); } #else /* !CONFIG_SMP */ @@ -1507,7 +1553,7 @@ static void task_numa_compare(struct task_numa_env *env, */ if (cur) { /* Skip this swap candidate if cannot move to the source cpu */ - if (!cpumask_test_cpu(env->src_cpu, tsk_cpus_allowed(cur))) + if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed)) goto unlock; /* @@ -1617,7 +1663,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) { /* Skip this CPU if the source task cannot migrate */ - if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(env->p))) + if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed)) continue; env->dst_cpu = cpu; @@ -2613,6 +2659,18 @@ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg) if (tg_weight) shares /= tg_weight; + /* + * MIN_SHARES has to be unscaled here to support per-CPU partitioning + * of a group with small tg->shares value. It is a floor value which is + * assigned as a minimum load.weight to the sched_entity representing + * the group on a CPU. + * + * E.g. on 64-bit for a group with tg->shares of scale_load(15)=15*1024 + * on an 8-core system with 8 tasks each runnable on one CPU shares has + * to be 15*1024*1/8=1920 instead of scale_load(MIN_SHARES)=2*1024. In + * case no task is runnable on a CPU MIN_SHARES=2 should be returned + * instead of 0. + */ if (shares < MIN_SHARES) shares = MIN_SHARES; if (shares > tg->shares) @@ -2645,16 +2703,20 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, static inline int throttled_hierarchy(struct cfs_rq *cfs_rq); -static void update_cfs_shares(struct cfs_rq *cfs_rq) +static void update_cfs_shares(struct sched_entity *se) { + struct cfs_rq *cfs_rq = group_cfs_rq(se); struct task_group *tg; - struct sched_entity *se; long shares; - tg = cfs_rq->tg; - se = tg->se[cpu_of(rq_of(cfs_rq))]; - if (!se || throttled_hierarchy(cfs_rq)) + if (!cfs_rq) return; + + if (throttled_hierarchy(cfs_rq)) + return; + + tg = cfs_rq->tg; + #ifndef CONFIG_SMP if (likely(se->load.weight == tg->shares)) return; @@ -2663,8 +2725,9 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq) reweight_entity(cfs_rq_of(se), se, shares); } + #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void update_cfs_shares(struct cfs_rq *cfs_rq) +static inline void update_cfs_shares(struct sched_entity *se) { } #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -2890,6 +2953,26 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa, return decayed; } +/* + * Signed add and clamp on underflow. + * + * Explicitly do a load-store to ensure the intermediate value never hits + * memory. This allows lockless observations without ever seeing the negative + * values. + */ +#define add_positive(_ptr, _val) do { \ + typeof(_ptr) ptr = (_ptr); \ + typeof(_val) val = (_val); \ + typeof(*ptr) res, var = READ_ONCE(*ptr); \ + \ + res = var + val; \ + \ + if (val < 0 && res > var) \ + res = 0; \ + \ + WRITE_ONCE(*ptr, res); \ +} while (0) + #ifdef CONFIG_FAIR_GROUP_SCHED /** * update_tg_load_avg - update the tg's load avg @@ -2969,8 +3052,138 @@ void set_task_rq_fair(struct sched_entity *se, se->avg.last_update_time = n_last_update_time; } } + +/* Take into account change of utilization of a child task group */ +static inline void +update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct cfs_rq *gcfs_rq = group_cfs_rq(se); + long delta = gcfs_rq->avg.util_avg - se->avg.util_avg; + + /* Nothing to update */ + if (!delta) + return; + + /* Set new sched_entity's utilization */ + se->avg.util_avg = gcfs_rq->avg.util_avg; + se->avg.util_sum = se->avg.util_avg * LOAD_AVG_MAX; + + /* Update parent cfs_rq utilization */ + add_positive(&cfs_rq->avg.util_avg, delta); + cfs_rq->avg.util_sum = cfs_rq->avg.util_avg * LOAD_AVG_MAX; +} + +/* Take into account change of load of a child task group */ +static inline void +update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se) +{ + struct cfs_rq *gcfs_rq = group_cfs_rq(se); + long delta, load = gcfs_rq->avg.load_avg; + + /* + * If the load of group cfs_rq is null, the load of the + * sched_entity will also be null so we can skip the formula + */ + if (load) { + long tg_load; + + /* Get tg's load and ensure tg_load > 0 */ + tg_load = atomic_long_read(&gcfs_rq->tg->load_avg) + 1; + + /* Ensure tg_load >= load and updated with current load*/ + tg_load -= gcfs_rq->tg_load_avg_contrib; + tg_load += load; + + /* + * We need to compute a correction term in the case that the + * task group is consuming more CPU than a task of equal + * weight. A task with a weight equals to tg->shares will have + * a load less or equal to scale_load_down(tg->shares). + * Similarly, the sched_entities that represent the task group + * at parent level, can't have a load higher than + * scale_load_down(tg->shares). And the Sum of sched_entities' + * load must be <= scale_load_down(tg->shares). + */ + if (tg_load > scale_load_down(gcfs_rq->tg->shares)) { + /* scale gcfs_rq's load into tg's shares*/ + load *= scale_load_down(gcfs_rq->tg->shares); + load /= tg_load; + } + } + + delta = load - se->avg.load_avg; + + /* Nothing to update */ + if (!delta) + return; + + /* Set new sched_entity's load */ + se->avg.load_avg = load; + se->avg.load_sum = se->avg.load_avg * LOAD_AVG_MAX; + + /* Update parent cfs_rq load */ + add_positive(&cfs_rq->avg.load_avg, delta); + cfs_rq->avg.load_sum = cfs_rq->avg.load_avg * LOAD_AVG_MAX; + + /* + * If the sched_entity is already enqueued, we also have to update the + * runnable load avg. + */ + if (se->on_rq) { + /* Update parent cfs_rq runnable_load_avg */ + add_positive(&cfs_rq->runnable_load_avg, delta); + cfs_rq->runnable_load_sum = cfs_rq->runnable_load_avg * LOAD_AVG_MAX; + } +} + +static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) +{ + cfs_rq->propagate_avg = 1; +} + +static inline int test_and_clear_tg_cfs_propagate(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = group_cfs_rq(se); + + if (!cfs_rq->propagate_avg) + return 0; + + cfs_rq->propagate_avg = 0; + return 1; +} + +/* Update task and its cfs_rq load average */ +static inline int propagate_entity_load_avg(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq; + + if (entity_is_task(se)) + return 0; + + if (!test_and_clear_tg_cfs_propagate(se)) + return 0; + + cfs_rq = cfs_rq_of(se); + + set_tg_cfs_propagate(cfs_rq); + + update_tg_cfs_util(cfs_rq, se); + update_tg_cfs_load(cfs_rq, se); + + return 1; +} + #else /* CONFIG_FAIR_GROUP_SCHED */ + static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} + +static inline int propagate_entity_load_avg(struct sched_entity *se) +{ + return 0; +} + +static inline void set_tg_cfs_propagate(struct cfs_rq *cfs_rq) {} + #endif /* CONFIG_FAIR_GROUP_SCHED */ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq) @@ -3041,6 +3254,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) sub_positive(&sa->load_avg, r); sub_positive(&sa->load_sum, r * LOAD_AVG_MAX); removed_load = 1; + set_tg_cfs_propagate(cfs_rq); } if (atomic_long_read(&cfs_rq->removed_util_avg)) { @@ -3048,6 +3262,7 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) sub_positive(&sa->util_avg, r); sub_positive(&sa->util_sum, r * LOAD_AVG_MAX); removed_util = 1; + set_tg_cfs_propagate(cfs_rq); } decayed = __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa, @@ -3064,23 +3279,35 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) return decayed || removed_load; } +/* + * Optional action to be done while updating the load average + */ +#define UPDATE_TG 0x1 +#define SKIP_AGE_LOAD 0x2 + /* Update task and its cfs_rq load average */ -static inline void update_load_avg(struct sched_entity *se, int update_tg) +static inline void update_load_avg(struct sched_entity *se, int flags) { struct cfs_rq *cfs_rq = cfs_rq_of(se); u64 now = cfs_rq_clock_task(cfs_rq); struct rq *rq = rq_of(cfs_rq); int cpu = cpu_of(rq); + int decayed; /* * Track task load average for carrying it to new CPU after migrated, and * track group sched_entity load average for task_h_load calc in migration */ - __update_load_avg(now, cpu, &se->avg, + if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD)) { + __update_load_avg(now, cpu, &se->avg, se->on_rq * scale_load_down(se->load.weight), cfs_rq->curr == se, NULL); + } + + decayed = update_cfs_rq_load_avg(now, cfs_rq, true); + decayed |= propagate_entity_load_avg(se); - if (update_cfs_rq_load_avg(now, cfs_rq, true) && update_tg) + if (decayed && (flags & UPDATE_TG)) update_tg_load_avg(cfs_rq, 0); } @@ -3094,31 +3321,12 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) */ static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - if (!sched_feat(ATTACH_AGE_LOAD)) - goto skip_aging; - - /* - * If we got migrated (either between CPUs or between cgroups) we'll - * have aged the average right before clearing @last_update_time. - * - * Or we're fresh through post_init_entity_util_avg(). - */ - if (se->avg.last_update_time) { - __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)), - &se->avg, 0, 0, NULL); - - /* - * XXX: we could have just aged the entire load away if we've been - * absent from the fair class for too long. - */ - } - -skip_aging: se->avg.last_update_time = cfs_rq->avg.last_update_time; cfs_rq->avg.load_avg += se->avg.load_avg; cfs_rq->avg.load_sum += se->avg.load_sum; cfs_rq->avg.util_avg += se->avg.util_avg; cfs_rq->avg.util_sum += se->avg.util_sum; + set_tg_cfs_propagate(cfs_rq); cfs_rq_util_change(cfs_rq); } @@ -3133,14 +3341,12 @@ skip_aging: */ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)), - &se->avg, se->on_rq * scale_load_down(se->load.weight), - cfs_rq->curr == se, NULL); sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg); sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum); sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg); sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum); + set_tg_cfs_propagate(cfs_rq); cfs_rq_util_change(cfs_rq); } @@ -3150,34 +3356,20 @@ static inline void enqueue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { struct sched_avg *sa = &se->avg; - u64 now = cfs_rq_clock_task(cfs_rq); - int migrated, decayed; - - migrated = !sa->last_update_time; - if (!migrated) { - __update_load_avg(now, cpu_of(rq_of(cfs_rq)), sa, - se->on_rq * scale_load_down(se->load.weight), - cfs_rq->curr == se, NULL); - } - - decayed = update_cfs_rq_load_avg(now, cfs_rq, !migrated); cfs_rq->runnable_load_avg += sa->load_avg; cfs_rq->runnable_load_sum += sa->load_sum; - if (migrated) + if (!sa->last_update_time) { attach_entity_load_avg(cfs_rq, se); - - if (decayed || migrated) update_tg_load_avg(cfs_rq, 0); + } } /* Remove the runnable load generated by se from cfs_rq's runnable load average */ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { - update_load_avg(se, 1); - cfs_rq->runnable_load_avg = max_t(long, cfs_rq->runnable_load_avg - se->avg.load_avg, 0); cfs_rq->runnable_load_sum = @@ -3206,13 +3398,25 @@ static inline u64 cfs_rq_last_update_time(struct cfs_rq *cfs_rq) #endif /* + * Synchronize entity load avg of dequeued entity without locking + * the previous rq. + */ +void sync_entity_load_avg(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); + u64 last_update_time; + + last_update_time = cfs_rq_last_update_time(cfs_rq); + __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL); +} + +/* * Task first catches up with cfs_rq, and then subtract * itself from the cfs_rq (task must be off the queue now). */ void remove_entity_load_avg(struct sched_entity *se) { struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 last_update_time; /* * tasks cannot exit without having gone through wake_up_new_task() -> @@ -3224,9 +3428,7 @@ void remove_entity_load_avg(struct sched_entity *se) * calls this. */ - last_update_time = cfs_rq_last_update_time(cfs_rq); - - __update_load_avg(last_update_time, cpu_of(rq_of(cfs_rq)), &se->avg, 0, 0, NULL); + sync_entity_load_avg(se); atomic_long_add(se->avg.load_avg, &cfs_rq->removed_load_avg); atomic_long_add(se->avg.util_avg, &cfs_rq->removed_util_avg); } @@ -3241,7 +3443,7 @@ static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq) return cfs_rq->avg.load_avg; } -static int idle_balance(struct rq *this_rq); +static int idle_balance(struct rq *this_rq, struct rq_flags *rf); #else /* CONFIG_SMP */ @@ -3251,7 +3453,10 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq) return 0; } -static inline void update_load_avg(struct sched_entity *se, int not_used) +#define UPDATE_TG 0x0 +#define SKIP_AGE_LOAD 0x0 + +static inline void update_load_avg(struct sched_entity *se, int not_used1) { cpufreq_update_util(rq_of(cfs_rq_of(se)), 0); } @@ -3267,7 +3472,7 @@ attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} static inline void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {} -static inline int idle_balance(struct rq *rq) +static inline int idle_balance(struct rq *rq, struct rq_flags *rf) { return 0; } @@ -3396,9 +3601,18 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) if (renorm && !curr) se->vruntime += cfs_rq->min_vruntime; + /* + * When enqueuing a sched_entity, we must: + * - Update loads to have both entity and cfs_rq synced with now. + * - Add its load to cfs_rq->runnable_avg + * - For group_entity, update its weight to reflect the new share of + * its group cfs_rq + * - Add its new weight to cfs_rq->load.weight + */ + update_load_avg(se, UPDATE_TG); enqueue_entity_load_avg(cfs_rq, se); + update_cfs_shares(se); account_entity_enqueue(cfs_rq, se); - update_cfs_shares(cfs_rq); if (flags & ENQUEUE_WAKEUP) place_entity(cfs_rq, se, 0); @@ -3470,6 +3684,16 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) * Update run-time statistics of the 'current'. */ update_curr(cfs_rq); + + /* + * When dequeuing a sched_entity, we must: + * - Update loads to have both entity and cfs_rq synced with now. + * - Substract its load from the cfs_rq->runnable_avg. + * - Substract its previous weight from cfs_rq->load.weight. + * - For group entity, update its weight to reflect the new share + * of its group cfs_rq. + */ + update_load_avg(se, UPDATE_TG); dequeue_entity_load_avg(cfs_rq, se); update_stats_dequeue(cfs_rq, se, flags); @@ -3493,7 +3717,7 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags) /* return excess runtime on last dequeue */ return_cfs_rq_runtime(cfs_rq); - update_cfs_shares(cfs_rq); + update_cfs_shares(se); /* * Now advance min_vruntime if @se was the entity holding it back, @@ -3557,7 +3781,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se) */ update_stats_wait_end(cfs_rq, se); __dequeue_entity(cfs_rq, se); - update_load_avg(se, 1); + update_load_avg(se, UPDATE_TG); } update_stats_curr_start(cfs_rq, se); @@ -3675,8 +3899,8 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued) /* * Ensure that runnable average is periodically updated. */ - update_load_avg(curr, 1); - update_cfs_shares(cfs_rq); + update_load_avg(curr, UPDATE_TG); + update_cfs_shares(curr); #ifdef CONFIG_SCHED_HRTICK /* @@ -4572,8 +4796,8 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; - update_load_avg(se, 1); - update_cfs_shares(cfs_rq); + update_load_avg(se, UPDATE_TG); + update_cfs_shares(se); } if (!se) @@ -4631,8 +4855,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags) if (cfs_rq_throttled(cfs_rq)) break; - update_load_avg(se, 1); - update_cfs_shares(cfs_rq); + update_load_avg(se, UPDATE_TG); + update_cfs_shares(se); } if (!se) @@ -5199,6 +5423,14 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, return 1; } +static inline int task_util(struct task_struct *p); +static int cpu_util_wake(int cpu, struct task_struct *p); + +static unsigned long capacity_spare_wake(int cpu, struct task_struct *p) +{ + return capacity_orig_of(cpu) - cpu_util_wake(cpu, p); +} + /* * find_idlest_group finds and returns the least busy CPU group within the * domain. @@ -5208,28 +5440,39 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu, int sd_flag) { struct sched_group *idlest = NULL, *group = sd->groups; - unsigned long min_load = ULONG_MAX, this_load = 0; + struct sched_group *most_spare_sg = NULL; + unsigned long min_runnable_load = ULONG_MAX, this_runnable_load = 0; + unsigned long min_avg_load = ULONG_MAX, this_avg_load = 0; + unsigned long most_spare = 0, this_spare = 0; int load_idx = sd->forkexec_idx; - int imbalance = 100 + (sd->imbalance_pct-100)/2; + int imbalance_scale = 100 + (sd->imbalance_pct-100)/2; + unsigned long imbalance = scale_load_down(NICE_0_LOAD) * + (sd->imbalance_pct-100) / 100; if (sd_flag & SD_BALANCE_WAKE) load_idx = sd->wake_idx; do { - unsigned long load, avg_load; + unsigned long load, avg_load, runnable_load; + unsigned long spare_cap, max_spare_cap; int local_group; int i; /* Skip over this group if it has no CPUs allowed */ if (!cpumask_intersects(sched_group_cpus(group), - tsk_cpus_allowed(p))) + &p->cpus_allowed)) continue; local_group = cpumask_test_cpu(this_cpu, sched_group_cpus(group)); - /* Tally up the load of all CPUs in the group */ + /* + * Tally up the load of all CPUs in the group and find + * the group containing the CPU with most spare capacity. + */ avg_load = 0; + runnable_load = 0; + max_spare_cap = 0; for_each_cpu(i, sched_group_cpus(group)) { /* Bias balancing toward cpus of our domain */ @@ -5238,22 +5481,84 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p, else load = target_load(i, load_idx); - avg_load += load; + runnable_load += load; + + avg_load += cfs_rq_load_avg(&cpu_rq(i)->cfs); + + spare_cap = capacity_spare_wake(i, p); + + if (spare_cap > max_spare_cap) + max_spare_cap = spare_cap; } /* Adjust by relative CPU capacity of the group */ - avg_load = (avg_load * SCHED_CAPACITY_SCALE) / group->sgc->capacity; + avg_load = (avg_load * SCHED_CAPACITY_SCALE) / + group->sgc->capacity; + runnable_load = (runnable_load * SCHED_CAPACITY_SCALE) / + group->sgc->capacity; if (local_group) { - this_load = avg_load; - } else if (avg_load < min_load) { - min_load = avg_load; - idlest = group; + this_runnable_load = runnable_load; + this_avg_load = avg_load; + this_spare = max_spare_cap; + } else { + if (min_runnable_load > (runnable_load + imbalance)) { + /* + * The runnable load is significantly smaller + * so we can pick this new cpu + */ + min_runnable_load = runnable_load; + min_avg_load = avg_load; + idlest = group; + } else if ((runnable_load < (min_runnable_load + imbalance)) && + (100*min_avg_load > imbalance_scale*avg_load)) { + /* + * The runnable loads are close so take the + * blocked load into account through avg_load. + */ + min_avg_load = avg_load; + idlest = group; + } + + if (most_spare < max_spare_cap) { + most_spare = max_spare_cap; + most_spare_sg = group; + } } } while (group = group->next, group != sd->groups); - if (!idlest || 100*this_load < imbalance*min_load) + /* + * The cross-over point between using spare capacity or least load + * is too conservative for high utilization tasks on partially + * utilized systems if we require spare_capacity > task_util(p), + * so we allow for some task stuffing by using + * spare_capacity > task_util(p)/2. + * + * Spare capacity can't be used for fork because the utilization has + * not been set yet, we must first select a rq to compute the initial + * utilization. + */ + if (sd_flag & SD_BALANCE_FORK) + goto skip_spare; + + if (this_spare > task_util(p) / 2 && + imbalance_scale*this_spare > 100*most_spare) return NULL; + + if (most_spare > task_util(p) / 2) + return most_spare_sg; + +skip_spare: + if (!idlest) + return NULL; + + if (min_runnable_load > (this_runnable_load + imbalance)) + return NULL; + + if ((this_runnable_load < (min_runnable_load + imbalance)) && + (100*this_avg_load < imbalance_scale*min_avg_load)) + return NULL; + return idlest; } @@ -5275,7 +5580,7 @@ find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) return cpumask_first(sched_group_cpus(group)); /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_cpus(group), tsk_cpus_allowed(p)) { + for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { if (idle_cpu(i)) { struct rq *rq = cpu_rq(i); struct cpuidle_state *idle = idle_get_state(rq); @@ -5414,7 +5719,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int if (!test_idle_cores(target, false)) return -1; - cpumask_and(cpus, sched_domain_span(sd), tsk_cpus_allowed(p)); + cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed); for_each_cpu_wrap(core, cpus, target, wrap) { bool idle = true; @@ -5448,7 +5753,7 @@ static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int t return -1; for_each_cpu(cpu, cpu_smt_mask(target)) { - if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) continue; if (idle_cpu(cpu)) return cpu; @@ -5494,13 +5799,13 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t * Due to large variance we need a large fuzz factor; hackbench in * particularly is sensitive here. */ - if ((avg_idle / 512) < avg_cost) + if (sched_feat(SIS_AVG_CPU) && (avg_idle / 512) < avg_cost) return -1; time = local_clock(); for_each_cpu_wrap(cpu, sched_domain_span(sd), target, wrap) { - if (!cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + if (!cpumask_test_cpu(cpu, &p->cpus_allowed)) continue; if (idle_cpu(cpu)) break; @@ -5590,6 +5895,24 @@ static inline int task_util(struct task_struct *p) } /* + * cpu_util_wake: Compute cpu utilization with any contributions from + * the waking task p removed. + */ +static int cpu_util_wake(int cpu, struct task_struct *p) +{ + unsigned long util, capacity; + + /* Task has no contribution or is new */ + if (cpu != task_cpu(p) || !p->se.avg.last_update_time) + return cpu_util(cpu); + + capacity = capacity_orig_of(cpu); + util = max_t(long, cpu_rq(cpu)->cfs.avg.util_avg - task_util(p), 0); + + return (util >= capacity) ? capacity : util; +} + +/* * Disable WAKE_AFFINE in the case where task @p doesn't fit in the * capacity of either the waking CPU @cpu or the previous CPU @prev_cpu. * @@ -5607,6 +5930,9 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) if (max_cap - min_cap < max_cap >> 3) return 0; + /* Bring task utilization in sync with prev_cpu */ + sync_entity_load_avg(&p->se); + return min_cap * 1024 < task_util(p) * capacity_margin; } @@ -5634,7 +5960,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f if (sd_flag & SD_BALANCE_WAKE) { record_wakee(p); want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) - && cpumask_test_cpu(cpu, tsk_cpus_allowed(p)); + && cpumask_test_cpu(cpu, &p->cpus_allowed); } rcu_read_lock(); @@ -5923,7 +6249,7 @@ preempt: } static struct task_struct * -pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct cfs_rq *cfs_rq = &rq->cfs; struct sched_entity *se; @@ -6030,15 +6356,8 @@ simple: return p; idle: - /* - * This is OK, because current is on_cpu, which avoids it being picked - * for load-balance and preemption/IRQs are still disabled avoiding - * further scheduler activity on it and we're being very careful to - * re-start the picking loop. - */ - lockdep_unpin_lock(&rq->lock, cookie); - new_tasks = idle_balance(rq); - lockdep_repin_lock(&rq->lock, cookie); + new_tasks = idle_balance(rq, rf); + /* * Because idle_balance() releases (and re-acquires) rq->lock, it is * possible for any higher priority task to appear. In that case we @@ -6381,7 +6700,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) return 0; - if (!cpumask_test_cpu(env->dst_cpu, tsk_cpus_allowed(p))) { + if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) { int cpu; schedstat_inc(p->se.statistics.nr_failed_migrations_affine); @@ -6401,7 +6720,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) /* Prevent to re-select dst_cpu via env's cpus */ for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) { - if (cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) { + if (cpumask_test_cpu(cpu, &p->cpus_allowed)) { env->flags |= LBF_DST_PINNED; env->new_dst_cpu = cpu; break; @@ -6641,6 +6960,10 @@ static void update_blocked_averages(int cpu) if (update_cfs_rq_load_avg(cfs_rq_clock_task(cfs_rq), cfs_rq, true)) update_tg_load_avg(cfs_rq, 0); + + /* Propagate pending load changes to the parent */ + if (cfs_rq->tg->se[cpu]) + update_load_avg(cfs_rq->tg->se[cpu], 0); } raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -6845,13 +7168,14 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) cpu_rq(cpu)->cpu_capacity = capacity; sdg->sgc->capacity = capacity; + sdg->sgc->min_capacity = capacity; } 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 capacity; + unsigned long capacity, min_capacity; unsigned long interval; interval = msecs_to_jiffies(sd->balance_interval); @@ -6864,6 +7188,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu) } capacity = 0; + min_capacity = ULONG_MAX; if (child->flags & SD_OVERLAP) { /* @@ -6888,11 +7213,12 @@ void update_group_capacity(struct sched_domain *sd, int cpu) */ if (unlikely(!rq->sd)) { capacity += capacity_of(cpu); - continue; + } else { + sgc = rq->sd->groups->sgc; + capacity += sgc->capacity; } - sgc = rq->sd->groups->sgc; - capacity += sgc->capacity; + min_capacity = min(capacity, min_capacity); } } else { /* @@ -6902,12 +7228,16 @@ void update_group_capacity(struct sched_domain *sd, int cpu) group = child->groups; do { - capacity += group->sgc->capacity; + struct sched_group_capacity *sgc = group->sgc; + + capacity += sgc->capacity; + min_capacity = min(sgc->min_capacity, min_capacity); group = group->next; } while (group != child->groups); } sdg->sgc->capacity = capacity; + sdg->sgc->min_capacity = min_capacity; } /* @@ -6924,14 +7254,14 @@ check_cpu_capacity(struct rq *rq, struct sched_domain *sd) /* * Group imbalance indicates (and tries to solve) the problem where balancing - * groups is inadequate due to tsk_cpus_allowed() constraints. + * groups is inadequate due to ->cpus_allowed constraints. * * Imagine a situation of two groups of 4 cpus each and 4 tasks each with a * cpumask covering 1 cpu of the first group and 3 cpus of the second group. * Something like: * - * { 0 1 2 3 } { 4 5 6 7 } - * * * * * + * { 0 1 2 3 } { 4 5 6 7 } + * * * * * * * If we were to balance group-wise we'd place two tasks in the first group and * two tasks in the second group. Clearly this is undesired as it will overload @@ -7002,6 +7332,17 @@ group_is_overloaded(struct lb_env *env, struct sg_lb_stats *sgs) return false; } +/* + * group_smaller_cpu_capacity: Returns true if sched_group sg has smaller + * per-CPU capacity than sched_group ref. + */ +static inline bool +group_smaller_cpu_capacity(struct sched_group *sg, struct sched_group *ref) +{ + return sg->sgc->min_capacity * capacity_margin < + ref->sgc->min_capacity * 1024; +} + static inline enum group_type group_classify(struct sched_group *group, struct sg_lb_stats *sgs) @@ -7105,6 +7446,20 @@ static bool update_sd_pick_busiest(struct lb_env *env, if (sgs->avg_load <= busiest->avg_load) return false; + if (!(env->sd->flags & SD_ASYM_CPUCAPACITY)) + goto asym_packing; + + /* + * Candidate sg has no more than one task per CPU and + * has higher per-CPU capacity. Migrating tasks to less + * capable CPUs may harm throughput. Maximize throughput, + * power/energy consequences are not considered. + */ + if (sgs->sum_nr_running <= sgs->group_weight && + group_smaller_cpu_capacity(sds->local, sg)) + return false; + +asym_packing: /* This is the busiest node in its class. */ if (!(env->sd->flags & SD_ASYM_PACKING)) return true; @@ -7113,16 +7468,18 @@ static bool update_sd_pick_busiest(struct lb_env *env, if (env->idle == CPU_NOT_IDLE) return true; /* - * ASYM_PACKING needs to move all the work to the lowest - * numbered CPUs in the group, therefore mark all groups - * higher than ourself as busy. + * ASYM_PACKING needs to move all the work to the highest + * prority CPUs in the group, therefore mark all groups + * of lower priority than ourself as busy. */ - if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) { + if (sgs->sum_nr_running && + sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) { if (!sds->busiest) return true; - /* Prefer to move from highest possible cpu's work */ - if (group_first_cpu(sds->busiest) < group_first_cpu(sg)) + /* Prefer to move from lowest priority cpu's work */ + if (sched_asym_prefer(sds->busiest->asym_prefer_cpu, + sg->asym_prefer_cpu)) return true; } @@ -7274,8 +7631,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds) if (!sds->busiest) return 0; - busiest_cpu = group_first_cpu(sds->busiest); - if (env->dst_cpu > busiest_cpu) + busiest_cpu = sds->busiest->asym_prefer_cpu; + if (sched_asym_prefer(busiest_cpu, env->dst_cpu)) return 0; env->imbalance = DIV_ROUND_CLOSEST( @@ -7613,10 +7970,11 @@ static int need_active_balance(struct lb_env *env) /* * ASYM_PACKING needs to force migrate tasks from busy but - * higher numbered CPUs in order to pack all tasks in the - * lowest numbered CPUs. + * lower priority CPUs in order to pack all tasks in the + * highest priority CPUs. */ - if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu) + if ((sd->flags & SD_ASYM_PACKING) && + sched_asym_prefer(env->dst_cpu, env->src_cpu)) return 1; } @@ -7748,6 +8106,7 @@ redo: more_balance: raw_spin_lock_irqsave(&busiest->lock, flags); + update_rq_clock(busiest); /* * cur_ld_moved - load moved in current iteration @@ -7854,8 +8213,7 @@ more_balance: * if the curr task on busiest cpu can't be * moved to this_cpu */ - if (!cpumask_test_cpu(this_cpu, - tsk_cpus_allowed(busiest->curr))) { + if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { raw_spin_unlock_irqrestore(&busiest->lock, flags); env.flags |= LBF_ALL_PINNED; @@ -7968,7 +8326,7 @@ update_next_balance(struct sched_domain *sd, unsigned long *next_balance) * 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) +static int idle_balance(struct rq *this_rq, struct rq_flags *rf) { unsigned long next_balance = jiffies + HZ; int this_cpu = this_rq->cpu; @@ -7982,6 +8340,14 @@ static int idle_balance(struct rq *this_rq) */ this_rq->idle_stamp = rq_clock(this_rq); + /* + * This is OK, because current is on_cpu, which avoids it being picked + * for load-balance and preemption/IRQs are still disabled avoiding + * further scheduler activity on it and we're being very careful to + * re-start the picking loop. + */ + rq_unpin_lock(this_rq, rf); + if (this_rq->avg_idle < sysctl_sched_migration_cost || !this_rq->rd->overload) { rcu_read_lock(); @@ -8059,6 +8425,8 @@ out: if (pulled_task) this_rq->idle_stamp = 0; + rq_repin_lock(this_rq, rf); + return pulled_task; } @@ -8114,6 +8482,7 @@ static int active_load_balance_cpu_stop(void *data) }; schedstat_inc(sd->alb_count); + update_rq_clock(busiest_rq); p = detach_one_task(&env); if (p) { @@ -8465,7 +8834,7 @@ static inline bool nohz_kick_needed(struct rq *rq) unsigned long now = jiffies; struct sched_domain_shared *sds; struct sched_domain *sd; - int nr_busy, cpu = rq->cpu; + int nr_busy, i, cpu = rq->cpu; bool kick = false; if (unlikely(rq->idle_balance)) @@ -8516,12 +8885,18 @@ static inline bool nohz_kick_needed(struct rq *rq) } sd = rcu_dereference(per_cpu(sd_asym, cpu)); - if (sd && (cpumask_first_and(nohz.idle_cpus_mask, - sched_domain_span(sd)) < cpu)) { - kick = true; - goto unlock; - } + if (sd) { + for_each_cpu(i, sched_domain_span(sd)) { + if (i == cpu || + !cpumask_test_cpu(i, nohz.idle_cpus_mask)) + continue; + if (sched_asym_prefer(i, cpu)) { + kick = true; + goto unlock; + } + } + } unlock: rcu_read_unlock(); return kick; @@ -8687,32 +9062,45 @@ static inline bool vruntime_normalized(struct task_struct *p) return false; } -static void detach_task_cfs_rq(struct task_struct *p) +#ifdef CONFIG_FAIR_GROUP_SCHED +/* + * Propagate the changes of the sched_entity across the tg tree to make it + * visible to the root + */ +static void propagate_entity_cfs_rq(struct sched_entity *se) { - struct sched_entity *se = &p->se; - struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 now = cfs_rq_clock_task(cfs_rq); + struct cfs_rq *cfs_rq; - if (!vruntime_normalized(p)) { - /* - * Fix up our vruntime so that the current sleep doesn't - * cause 'unlimited' sleep bonus. - */ - place_entity(cfs_rq, se, 0); - se->vruntime -= cfs_rq->min_vruntime; + /* Start to propagate at parent */ + se = se->parent; + + for_each_sched_entity(se) { + cfs_rq = cfs_rq_of(se); + + if (cfs_rq_throttled(cfs_rq)) + break; + + update_load_avg(se, UPDATE_TG); } +} +#else +static void propagate_entity_cfs_rq(struct sched_entity *se) { } +#endif + +static void detach_entity_cfs_rq(struct sched_entity *se) +{ + struct cfs_rq *cfs_rq = cfs_rq_of(se); /* Catch up with the cfs_rq and remove our load when we leave */ - update_cfs_rq_load_avg(now, cfs_rq, false); + update_load_avg(se, 0); detach_entity_load_avg(cfs_rq, se); update_tg_load_avg(cfs_rq, false); + propagate_entity_cfs_rq(se); } -static void attach_task_cfs_rq(struct task_struct *p) +static void attach_entity_cfs_rq(struct sched_entity *se) { - struct sched_entity *se = &p->se; struct cfs_rq *cfs_rq = cfs_rq_of(se); - u64 now = cfs_rq_clock_task(cfs_rq); #ifdef CONFIG_FAIR_GROUP_SCHED /* @@ -8722,10 +9110,36 @@ static void attach_task_cfs_rq(struct task_struct *p) se->depth = se->parent ? se->parent->depth + 1 : 0; #endif - /* Synchronize task with its cfs_rq */ - update_cfs_rq_load_avg(now, cfs_rq, false); + /* Synchronize entity with its cfs_rq */ + update_load_avg(se, sched_feat(ATTACH_AGE_LOAD) ? 0 : SKIP_AGE_LOAD); attach_entity_load_avg(cfs_rq, se); update_tg_load_avg(cfs_rq, false); + propagate_entity_cfs_rq(se); +} + +static void detach_task_cfs_rq(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + if (!vruntime_normalized(p)) { + /* + * Fix up our vruntime so that the current sleep doesn't + * cause 'unlimited' sleep bonus. + */ + place_entity(cfs_rq, se, 0); + se->vruntime -= cfs_rq->min_vruntime; + } + + detach_entity_cfs_rq(se); +} + +static void attach_task_cfs_rq(struct task_struct *p) +{ + struct sched_entity *se = &p->se; + struct cfs_rq *cfs_rq = cfs_rq_of(se); + + attach_entity_cfs_rq(se); if (!vruntime_normalized(p)) se->vruntime += cfs_rq->min_vruntime; @@ -8779,6 +9193,9 @@ void init_cfs_rq(struct cfs_rq *cfs_rq) cfs_rq->min_vruntime_copy = cfs_rq->min_vruntime; #endif #ifdef CONFIG_SMP +#ifdef CONFIG_FAIR_GROUP_SCHED + cfs_rq->propagate_avg = 0; +#endif atomic_long_set(&cfs_rq->removed_load_avg, 0); atomic_long_set(&cfs_rq->removed_util_avg, 0); #endif @@ -8887,7 +9304,8 @@ void online_fair_sched_group(struct task_group *tg) se = tg->se[i]; raw_spin_lock_irq(&rq->lock); - post_init_entity_util_avg(se); + update_rq_clock(rq); + attach_entity_cfs_rq(se); sync_throttle(tg, i); raw_spin_unlock_irq(&rq->lock); } @@ -8979,8 +9397,10 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) /* Possible calls to update_curr() need rq clock */ update_rq_clock(rq); - for_each_sched_entity(se) - update_cfs_shares(group_cfs_rq(se)); + for_each_sched_entity(se) { + update_load_avg(se, UPDATE_TG); + update_cfs_shares(se); + } raw_spin_unlock_irqrestore(&rq->lock, flags); } diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 69631fa46c2f..1b3c8189b286 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -51,6 +51,11 @@ SCHED_FEAT(NONTASK_CAPACITY, true) */ SCHED_FEAT(TTWU_QUEUE, true) +/* + * When doing wakeups, attempt to limit superfluous scans of the LLC domain. + */ +SCHED_FEAT(SIS_AVG_CPU, false) + #ifdef HAVE_RT_PUSH_IPI /* * In order to avoid a thundering herd attack of CPUs that are diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c index 1d8718d5300d..ac6d5176463d 100644 --- a/kernel/sched/idle.c +++ b/kernel/sched/idle.c @@ -2,6 +2,7 @@ * Generic entry point for the idle threads */ #include <linux/sched.h> +#include <linux/sched/idle.h> #include <linux/cpu.h> #include <linux/cpuidle.h> #include <linux/cpuhotplug.h> @@ -164,11 +165,14 @@ static void cpuidle_idle_call(void) * timekeeping to prevent timer interrupts from kicking us out of idle * until a proper wakeup interrupt happens. */ - if (idle_should_freeze()) { - entered_state = cpuidle_enter_freeze(drv, dev); - if (entered_state > 0) { - local_irq_enable(); - goto exit_idle; + + if (idle_should_freeze() || dev->use_deepest_state) { + if (idle_should_freeze()) { + entered_state = cpuidle_enter_freeze(drv, dev); + if (entered_state > 0) { + local_irq_enable(); + goto exit_idle; + } } next_state = cpuidle_find_deepest_state(drv, dev); @@ -202,76 +206,65 @@ exit_idle: * * Called with polling cleared. */ -static void cpu_idle_loop(void) +static void do_idle(void) { - int cpu = smp_processor_id(); - - 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(); - quiet_vmstat(); - tick_nohz_idle_enter(); + /* + * 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. + */ - while (!need_resched()) { - check_pgt_cache(); - rmb(); + __current_set_polling(); + tick_nohz_idle_enter(); - if (cpu_is_offline(cpu)) { - cpuhp_report_idle_dead(); - arch_cpu_idle_dead(); - } + while (!need_resched()) { + check_pgt_cache(); + rmb(); - local_irq_disable(); - arch_cpu_idle_enter(); - - /* - * In poll mode we reenable interrupts and spin. - * - * Also if we detected in the wakeup from idle - * path that the tick broadcast device expired - * for us, we don't want to go deep idle as we - * know that the IPI is going to arrive right - * away - */ - if (cpu_idle_force_poll || tick_check_broadcast_expired()) - cpu_idle_poll(); - else - cpuidle_idle_call(); - - arch_cpu_idle_exit(); + if (cpu_is_offline(smp_processor_id())) { + cpuhp_report_idle_dead(); + arch_cpu_idle_dead(); } - /* - * Since we fell out of the loop above, we know - * TIF_NEED_RESCHED must be set, propagate it into - * PREEMPT_NEED_RESCHED. - * - * This is required because for polling idle loops we will - * not have had an IPI to fold the state for us. - */ - preempt_set_need_resched(); - tick_nohz_idle_exit(); - __current_clr_polling(); + local_irq_disable(); + arch_cpu_idle_enter(); /* - * 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. + * In poll mode we reenable interrupts and spin. Also if we + * detected in the wakeup from idle path that the tick + * broadcast device expired for us, we don't want to go deep + * idle as we know that the IPI is going to arrive right away. */ - smp_mb__after_atomic(); - - sched_ttwu_pending(); - schedule_preempt_disabled(); + if (cpu_idle_force_poll || tick_check_broadcast_expired()) + cpu_idle_poll(); + else + cpuidle_idle_call(); + arch_cpu_idle_exit(); } + + /* + * Since we fell out of the loop above, we know TIF_NEED_RESCHED must + * be set, propagate it into PREEMPT_NEED_RESCHED. + * + * This is required because for polling idle loops we will not have had + * an IPI to fold the state for us. + */ + 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(); } bool cpu_in_idle(unsigned long pc) @@ -280,6 +273,56 @@ bool cpu_in_idle(unsigned long pc) pc < (unsigned long)__cpuidle_text_end; } +struct idle_timer { + struct hrtimer timer; + int done; +}; + +static enum hrtimer_restart idle_inject_timer_fn(struct hrtimer *timer) +{ + struct idle_timer *it = container_of(timer, struct idle_timer, timer); + + WRITE_ONCE(it->done, 1); + set_tsk_need_resched(current); + + return HRTIMER_NORESTART; +} + +void play_idle(unsigned long duration_ms) +{ + struct idle_timer it; + + /* + * Only FIFO tasks can disable the tick since they don't need the forced + * preemption. + */ + WARN_ON_ONCE(current->policy != SCHED_FIFO); + WARN_ON_ONCE(current->nr_cpus_allowed != 1); + WARN_ON_ONCE(!(current->flags & PF_KTHREAD)); + WARN_ON_ONCE(!(current->flags & PF_NO_SETAFFINITY)); + WARN_ON_ONCE(!duration_ms); + + rcu_sleep_check(); + preempt_disable(); + current->flags |= PF_IDLE; + cpuidle_use_deepest_state(true); + + it.done = 0; + hrtimer_init_on_stack(&it.timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + it.timer.function = idle_inject_timer_fn; + hrtimer_start(&it.timer, ms_to_ktime(duration_ms), HRTIMER_MODE_REL_PINNED); + + while (!READ_ONCE(it.done)) + do_idle(); + + cpuidle_use_deepest_state(false); + current->flags &= ~PF_IDLE; + + preempt_fold_need_resched(); + preempt_enable(); +} +EXPORT_SYMBOL_GPL(play_idle); + void cpu_startup_entry(enum cpuhp_state state) { /* @@ -299,5 +342,6 @@ void cpu_startup_entry(enum cpuhp_state state) #endif arch_cpu_idle_prepare(); cpuhp_online_idle(state); - cpu_idle_loop(); + while (1) + do_idle(); } diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index 5405d3feb112..0c00172db63e 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -24,7 +24,7 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl } static struct task_struct * -pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { put_prev_task(rq, prev); update_idle_core(rq); diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c index a2d6eb71f06b..f15fb2bdbc0d 100644 --- a/kernel/sched/loadavg.c +++ b/kernel/sched/loadavg.c @@ -7,6 +7,7 @@ */ #include <linux/export.h> +#include <linux/sched/loadavg.h> #include "sched.h" @@ -168,7 +169,7 @@ static inline int calc_load_write_idx(void) * If the folding window started, make sure we start writing in the * next idle-delta. */ - if (!time_before(jiffies, calc_load_update)) + if (!time_before(jiffies, READ_ONCE(calc_load_update))) idx++; return idx & 1; @@ -201,8 +202,9 @@ void calc_load_exit_idle(void) struct rq *this_rq = this_rq(); /* - * If we're still before the sample window, we're done. + * If we're still before the pending sample window, we're done. */ + this_rq->calc_load_update = READ_ONCE(calc_load_update); if (time_before(jiffies, this_rq->calc_load_update)) return; @@ -211,7 +213,6 @@ void calc_load_exit_idle(void) * accounted through the nohz accounting, so skip the entire deal and * sync up for the next window. */ - this_rq->calc_load_update = calc_load_update; if (time_before(jiffies, this_rq->calc_load_update + 10)) this_rq->calc_load_update += LOAD_FREQ; } @@ -307,13 +308,15 @@ calc_load_n(unsigned long load, unsigned long exp, */ static void calc_global_nohz(void) { + unsigned long sample_window; long delta, active, n; - if (!time_before(jiffies, calc_load_update + 10)) { + sample_window = READ_ONCE(calc_load_update); + if (!time_before(jiffies, sample_window + 10)) { /* * Catch-up, fold however many we are behind still */ - delta = jiffies - calc_load_update - 10; + delta = jiffies - sample_window - 10; n = 1 + (delta / LOAD_FREQ); active = atomic_long_read(&calc_load_tasks); @@ -323,7 +326,7 @@ static void calc_global_nohz(void) avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - calc_load_update += n * LOAD_FREQ; + WRITE_ONCE(calc_load_update, sample_window + n * LOAD_FREQ); } /* @@ -351,9 +354,11 @@ static inline void calc_global_nohz(void) { } */ void calc_global_load(unsigned long ticks) { + unsigned long sample_window; long active, delta; - if (time_before(jiffies, calc_load_update + 10)) + sample_window = READ_ONCE(calc_load_update); + if (time_before(jiffies, sample_window + 10)) return; /* @@ -370,7 +375,7 @@ void calc_global_load(unsigned long ticks) avenrun[1] = calc_load(avenrun[1], EXP_5, active); avenrun[2] = calc_load(avenrun[2], EXP_15, active); - calc_load_update += LOAD_FREQ; + WRITE_ONCE(calc_load_update, sample_window + LOAD_FREQ); /* * In case we idled for multiple LOAD_FREQ intervals, catch up in bulk. diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 2516b8df6dbb..9f3e40226dec 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -9,6 +9,7 @@ #include <linux/irq_work.h> int sched_rr_timeslice = RR_TIMESLICE; +int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE; static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); @@ -334,7 +335,7 @@ static void inc_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) rt_rq = &rq_of_rt_rq(rt_rq)->rt; rt_rq->rt_nr_total++; - if (tsk_nr_cpus_allowed(p) > 1) + if (p->nr_cpus_allowed > 1) rt_rq->rt_nr_migratory++; update_rt_migration(rt_rq); @@ -351,7 +352,7 @@ static void dec_rt_migration(struct sched_rt_entity *rt_se, struct rt_rq *rt_rq) rt_rq = &rq_of_rt_rq(rt_rq)->rt; rt_rq->rt_nr_total--; - if (tsk_nr_cpus_allowed(p) > 1) + if (p->nr_cpus_allowed > 1) rt_rq->rt_nr_migratory--; update_rt_migration(rt_rq); @@ -1323,7 +1324,7 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags) enqueue_rt_entity(rt_se, flags); - if (!task_current(rq, p) && tsk_nr_cpus_allowed(p) > 1) + if (!task_current(rq, p) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1412,7 +1413,7 @@ select_task_rq_rt(struct task_struct *p, int cpu, int sd_flag, int flags) * will have to sort it out. */ if (curr && unlikely(rt_task(curr)) && - (tsk_nr_cpus_allowed(curr) < 2 || + (curr->nr_cpus_allowed < 2 || curr->prio <= p->prio)) { int target = find_lowest_rq(p); @@ -1436,7 +1437,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) * Current can't be migrated, useless to reschedule, * let's hope p can move out. */ - if (tsk_nr_cpus_allowed(rq->curr) == 1 || + if (rq->curr->nr_cpus_allowed == 1 || !cpupri_find(&rq->rd->cpupri, rq->curr, NULL)) return; @@ -1444,7 +1445,7 @@ static void check_preempt_equal_prio(struct rq *rq, struct task_struct *p) * p is migratable, so let's not schedule it and * see if it is pushed or pulled somewhere else. */ - if (tsk_nr_cpus_allowed(p) != 1 + if (p->nr_cpus_allowed != 1 && cpupri_find(&rq->rd->cpupri, p, NULL)) return; @@ -1523,7 +1524,7 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) } static struct task_struct * -pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *p; struct rt_rq *rt_rq = &rq->rt; @@ -1535,9 +1536,9 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev, struct pin_cookie coo * disabled avoiding further scheduler activity on it and we're * being very careful to re-start the picking loop. */ - lockdep_unpin_lock(&rq->lock, cookie); + rq_unpin_lock(rq, rf); pull_rt_task(rq); - lockdep_repin_lock(&rq->lock, cookie); + rq_repin_lock(rq, rf); /* * pull_rt_task() can drop (and re-acquire) rq->lock; this * means a dl or stop task can slip in, in which case we need @@ -1578,7 +1579,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) * The previous task needs to be made eligible for pushing * if it is still active */ - if (on_rt_rq(&p->rt) && tsk_nr_cpus_allowed(p) > 1) + if (on_rt_rq(&p->rt) && p->nr_cpus_allowed > 1) enqueue_pushable_task(rq, p); } @@ -1590,7 +1591,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, tsk_cpus_allowed(p))) + cpumask_test_cpu(cpu, &p->cpus_allowed)) return 1; return 0; } @@ -1628,7 +1629,7 @@ static int find_lowest_rq(struct task_struct *task) if (unlikely(!lowest_mask)) return -1; - if (tsk_nr_cpus_allowed(task) == 1) + if (task->nr_cpus_allowed == 1) return -1; /* No other targets possible */ if (!cpupri_find(&task_rq(task)->rd->cpupri, task, lowest_mask)) @@ -1725,8 +1726,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) * Also make sure that it wasn't scheduled on its rq. */ if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(lowest_rq->cpu, - tsk_cpus_allowed(task)) || + !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) || task_running(rq, task) || !rt_task(task) || !task_on_rq_queued(task))) { @@ -1761,7 +1761,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) BUG_ON(rq->cpu != task_cpu(p)); BUG_ON(task_current(rq, p)); - BUG_ON(tsk_nr_cpus_allowed(p) <= 1); + BUG_ON(p->nr_cpus_allowed <= 1); BUG_ON(!task_on_rq_queued(p)); BUG_ON(!rt_task(p)); @@ -2121,9 +2121,9 @@ static void task_woken_rt(struct rq *rq, struct task_struct *p) { if (!task_running(rq, p) && !test_tsk_need_resched(rq->curr) && - tsk_nr_cpus_allowed(p) > 1 && + p->nr_cpus_allowed > 1 && (dl_task(rq->curr) || rt_task(rq->curr)) && - (tsk_nr_cpus_allowed(rq->curr) < 2 || + (rq->curr->nr_cpus_allowed < 2 || rq->curr->prio <= p->prio)) push_rt_tasks(rq); } @@ -2196,12 +2196,11 @@ static void switched_to_rt(struct rq *rq, struct task_struct *p) */ if (task_on_rq_queued(p) && rq->curr != p) { #ifdef CONFIG_SMP - if (tsk_nr_cpus_allowed(p) > 1 && rq->rt.overloaded) + if (p->nr_cpus_allowed > 1 && rq->rt.overloaded) queue_push_tasks(rq); -#else +#endif /* CONFIG_SMP */ if (p->prio < rq->curr->prio) resched_curr(rq); -#endif /* CONFIG_SMP */ } } @@ -2246,6 +2245,7 @@ prio_changed_rt(struct rq *rq, struct task_struct *p, int oldprio) } } +#ifdef CONFIG_POSIX_TIMERS static void watchdog(struct rq *rq, struct task_struct *p) { unsigned long soft, hard; @@ -2267,6 +2267,9 @@ static void watchdog(struct rq *rq, struct task_struct *p) p->cputime_expires.sched_exp = p->se.sum_exec_runtime; } } +#else +static inline void watchdog(struct rq *rq, struct task_struct *p) { } +#endif static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued) { diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 055f935d4421..5cbf92214ad8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1,9 +1,27 @@ #include <linux/sched.h> +#include <linux/sched/autogroup.h> #include <linux/sched/sysctl.h> +#include <linux/sched/topology.h> #include <linux/sched/rt.h> -#include <linux/u64_stats_sync.h> #include <linux/sched/deadline.h> +#include <linux/sched/clock.h> +#include <linux/sched/wake_q.h> +#include <linux/sched/signal.h> +#include <linux/sched/numa_balancing.h> +#include <linux/sched/mm.h> +#include <linux/sched/cpufreq.h> +#include <linux/sched/stat.h> +#include <linux/sched/nohz.h> +#include <linux/sched/debug.h> +#include <linux/sched/hotplug.h> +#include <linux/sched/task.h> +#include <linux/sched/task_stack.h> +#include <linux/sched/cputime.h> +#include <linux/sched/init.h> + +#include <linux/u64_stats_sync.h> +#include <linux/kernel_stat.h> #include <linux/binfmts.h> #include <linux/mutex.h> #include <linux/spinlock.h> @@ -12,6 +30,10 @@ #include <linux/tick.h> #include <linux/slab.h> +#ifdef CONFIG_PARAVIRT +#include <asm/paravirt.h> +#endif + #include "cpupri.h" #include "cpudeadline.h" #include "cpuacct.h" @@ -222,7 +244,7 @@ bool __dl_overflow(struct dl_bw *dl_b, int cpus, u64 old_bw, u64 new_bw) dl_b->bw * cpus < dl_b->total_bw - old_bw + new_bw; } -extern struct mutex sched_domains_mutex; +extern void init_dl_bw(struct dl_bw *dl_b); #ifdef CONFIG_CGROUP_SCHED @@ -404,6 +426,7 @@ struct cfs_rq { unsigned long runnable_load_avg; #ifdef CONFIG_FAIR_GROUP_SCHED unsigned long tg_load_avg_contrib; + unsigned long propagate_avg; #endif atomic_long_t removed_load_avg, removed_util_avg; #ifndef CONFIG_64BIT @@ -539,6 +562,11 @@ struct dl_rq { #ifdef CONFIG_SMP +static inline bool sched_asym_prefer(int a, int b) +{ + return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b); +} + /* * We add the notion of a root-domain which will be used to define per-domain * variables. Each exclusive cpuset essentially defines an island domain by @@ -577,6 +605,13 @@ struct root_domain { }; extern struct root_domain def_root_domain; +extern struct mutex sched_domains_mutex; +extern cpumask_var_t fallback_doms; +extern cpumask_var_t sched_domains_tmpmask; + +extern void init_defrootdomain(void); +extern int init_sched_domains(const struct cpumask *cpu_map); +extern void rq_attach_root(struct rq *rq, struct root_domain *rd); #endif /* CONFIG_SMP */ @@ -623,6 +658,7 @@ struct rq { #ifdef CONFIG_FAIR_GROUP_SCHED /* list of leaf cfs_rq on this cpu: */ struct list_head leaf_cfs_rq_list; + struct list_head *tmp_alone_branch; #endif /* CONFIG_FAIR_GROUP_SCHED */ /* @@ -637,7 +673,7 @@ struct rq { unsigned long next_balance; struct mm_struct *prev_mm; - unsigned int clock_skip_update; + unsigned int clock_update_flags; u64 clock; u64 clock_task; @@ -761,28 +797,110 @@ static inline u64 __rq_clock_broken(struct rq *rq) return READ_ONCE(rq->clock); } +/* + * rq::clock_update_flags bits + * + * %RQCF_REQ_SKIP - will request skipping of clock update on the next + * call to __schedule(). This is an optimisation to avoid + * neighbouring rq clock updates. + * + * %RQCF_ACT_SKIP - is set from inside of __schedule() when skipping is + * in effect and calls to update_rq_clock() are being ignored. + * + * %RQCF_UPDATED - is a debug flag that indicates whether a call has been + * made to update_rq_clock() since the last time rq::lock was pinned. + * + * If inside of __schedule(), clock_update_flags will have been + * shifted left (a left shift is a cheap operation for the fast path + * to promote %RQCF_REQ_SKIP to %RQCF_ACT_SKIP), so you must use, + * + * if (rq-clock_update_flags >= RQCF_UPDATED) + * + * to check if %RQCF_UPADTED is set. It'll never be shifted more than + * one position though, because the next rq_unpin_lock() will shift it + * back. + */ +#define RQCF_REQ_SKIP 0x01 +#define RQCF_ACT_SKIP 0x02 +#define RQCF_UPDATED 0x04 + +static inline void assert_clock_updated(struct rq *rq) +{ + /* + * The only reason for not seeing a clock update since the + * last rq_pin_lock() is if we're currently skipping updates. + */ + SCHED_WARN_ON(rq->clock_update_flags < RQCF_ACT_SKIP); +} + static inline u64 rq_clock(struct rq *rq) { lockdep_assert_held(&rq->lock); + assert_clock_updated(rq); + return rq->clock; } static inline u64 rq_clock_task(struct rq *rq) { lockdep_assert_held(&rq->lock); + assert_clock_updated(rq); + return rq->clock_task; } -#define RQCF_REQ_SKIP 0x01 -#define RQCF_ACT_SKIP 0x02 - static inline void rq_clock_skip_update(struct rq *rq, bool skip) { lockdep_assert_held(&rq->lock); if (skip) - rq->clock_skip_update |= RQCF_REQ_SKIP; + rq->clock_update_flags |= RQCF_REQ_SKIP; else - rq->clock_skip_update &= ~RQCF_REQ_SKIP; + rq->clock_update_flags &= ~RQCF_REQ_SKIP; +} + +struct rq_flags { + unsigned long flags; + struct pin_cookie cookie; +#ifdef CONFIG_SCHED_DEBUG + /* + * A copy of (rq::clock_update_flags & RQCF_UPDATED) for the + * current pin context is stashed here in case it needs to be + * restored in rq_repin_lock(). + */ + unsigned int clock_update_flags; +#endif +}; + +static inline void rq_pin_lock(struct rq *rq, struct rq_flags *rf) +{ + rf->cookie = lockdep_pin_lock(&rq->lock); + +#ifdef CONFIG_SCHED_DEBUG + rq->clock_update_flags &= (RQCF_REQ_SKIP|RQCF_ACT_SKIP); + rf->clock_update_flags = 0; +#endif +} + +static inline void rq_unpin_lock(struct rq *rq, struct rq_flags *rf) +{ +#ifdef CONFIG_SCHED_DEBUG + if (rq->clock_update_flags > RQCF_ACT_SKIP) + rf->clock_update_flags = RQCF_UPDATED; +#endif + + lockdep_unpin_lock(&rq->lock, rf->cookie); +} + +static inline void rq_repin_lock(struct rq *rq, struct rq_flags *rf) +{ + lockdep_repin_lock(&rq->lock, rf->cookie); + +#ifdef CONFIG_SCHED_DEBUG + /* + * Restore the value we stashed in @rf for this pin context. + */ + rq->clock_update_flags |= rf->clock_update_flags; +#endif } #ifdef CONFIG_NUMA @@ -796,6 +914,16 @@ extern int sched_max_numa_distance; extern bool find_numa_distance(int distance); #endif +#ifdef CONFIG_NUMA +extern void sched_init_numa(void); +extern void sched_domains_numa_masks_set(unsigned int cpu); +extern void sched_domains_numa_masks_clear(unsigned int cpu); +#else +static inline void sched_init_numa(void) { } +static inline void sched_domains_numa_masks_set(unsigned int cpu) { } +static inline void sched_domains_numa_masks_clear(unsigned int cpu) { } +#endif + #ifdef CONFIG_NUMA_BALANCING /* The regions in numa_faults array from task_struct */ enum numa_faults_stats { @@ -892,7 +1020,8 @@ struct sched_group_capacity { * CPU capacity of this group, SCHED_CAPACITY_SCALE being max capacity * for a single CPU. */ - unsigned int capacity; + unsigned long capacity; + unsigned long min_capacity; /* Min per-CPU capacity in group */ unsigned long next_update; int imbalance; /* XXX unrelated to capacity but shared group state */ @@ -905,6 +1034,7 @@ struct sched_group { unsigned int group_weight; struct sched_group_capacity *sgc; + int asym_prefer_cpu; /* cpu of highest priority in group */ /* * The CPUs this group covers. @@ -960,7 +1090,7 @@ static inline void sched_ttwu_pending(void) { } #endif /* CONFIG_SMP */ #include "stats.h" -#include "auto_group.h" +#include "autogroup.h" #ifdef CONFIG_CGROUP_SCHED @@ -1236,7 +1366,7 @@ struct sched_class { */ struct task_struct * (*pick_next_task) (struct rq *rq, struct task_struct *prev, - struct pin_cookie cookie); + struct rq_flags *rf); void (*put_prev_task) (struct rq *rq, struct task_struct *p); #ifdef CONFIG_SMP @@ -1492,11 +1622,6 @@ static inline void sched_rt_avg_update(struct rq *rq, u64 rt_delta) { } static inline void sched_avg_update(struct rq *rq) { } #endif -struct rq_flags { - unsigned long flags; - struct pin_cookie cookie; -}; - struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf) __acquires(rq->lock); struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) @@ -1506,7 +1631,7 @@ struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf) static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf) __releases(rq->lock) { - lockdep_unpin_lock(&rq->lock, rf->cookie); + rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); } @@ -1515,7 +1640,7 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf) __releases(rq->lock) __releases(p->pi_lock) { - lockdep_unpin_lock(&rq->lock, rf->cookie); + rq_unpin_lock(rq, rf); raw_spin_unlock(&rq->lock); raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags); } @@ -1665,6 +1790,10 @@ static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2) __release(rq2->lock); } +extern void set_rq_online (struct rq *rq); +extern void set_rq_offline(struct rq *rq); +extern bool sched_smp_initialized; + #else /* CONFIG_SMP */ /* @@ -1709,7 +1838,6 @@ extern void print_rt_stats(struct seq_file *m, int cpu); extern void print_dl_stats(struct seq_file *m, int cpu); extern void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq); - #ifdef CONFIG_NUMA_BALANCING extern void show_numa_stats(struct task_struct *p, struct seq_file *m); @@ -1741,8 +1869,7 @@ static inline void nohz_balance_exit_idle(unsigned int cpu) { } #ifdef CONFIG_IRQ_TIME_ACCOUNTING struct irqtime { - u64 hardirq_time; - u64 softirq_time; + u64 tick_delta; u64 irq_start_time; struct u64_stats_sync sync; }; @@ -1752,12 +1879,13 @@ DECLARE_PER_CPU(struct irqtime, cpu_irqtime); static inline u64 irq_time_read(int cpu) { struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu); + u64 *cpustat = kcpustat_cpu(cpu).cpustat; unsigned int seq; u64 total; do { seq = __u64_stats_fetch_begin(&irqtime->sync); - total = irqtime->softirq_time + irqtime->hardirq_time; + total = cpustat[CPUTIME_SOFTIRQ] + cpustat[CPUTIME_IRQ]; } while (__u64_stats_fetch_retry(&irqtime->sync, seq)); return total; diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 34659a853505..d5710651043b 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -164,106 +164,3 @@ sched_info_switch(struct rq *rq, #define sched_info_arrive(rq, next) do { } while (0) #define sched_info_switch(rq, t, next) do { } while (0) #endif /* CONFIG_SCHED_INFO */ - -/* - * The following are functions that support scheduler-internal time accounting. - * These functions are generally called at the timer tick. None of this depends - * on CONFIG_SCHEDSTATS. - */ - -/** - * cputimer_running - return true if cputimer is running - * - * @tsk: Pointer to target task. - */ -static inline bool cputimer_running(struct task_struct *tsk) - -{ - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - - /* Check if cputimer isn't running. This is accessed without locking. */ - if (!READ_ONCE(cputimer->running)) - return false; - - /* - * After we flush the task's sum_exec_runtime to sig->sum_sched_runtime - * in __exit_signal(), we won't account to the signal struct further - * cputime consumed by that task, even though the task can still be - * ticking after __exit_signal(). - * - * In order to keep a consistent behaviour between thread group cputime - * and thread group cputimer accounting, lets also ignore the cputime - * elapsing after __exit_signal() in any thread group timer running. - * - * This makes sure that POSIX CPU clocks and timers are synchronized, so - * that a POSIX CPU timer won't expire while the corresponding POSIX CPU - * clock delta is behind the expiring timer value. - */ - if (unlikely(!tsk->sighand)) - return false; - - return true; -} - -/** - * account_group_user_time - Maintain utime for a thread group. - * - * @tsk: Pointer to task structure. - * @cputime: Time value by which to increment the utime field of the - * thread_group_cputime structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the utime field there. - */ -static inline void account_group_user_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - - if (!cputimer_running(tsk)) - return; - - atomic64_add(cputime, &cputimer->cputime_atomic.utime); -} - -/** - * account_group_system_time - Maintain stime for a thread group. - * - * @tsk: Pointer to task structure. - * @cputime: Time value by which to increment the stime field of the - * thread_group_cputime structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the stime field there. - */ -static inline void account_group_system_time(struct task_struct *tsk, - cputime_t cputime) -{ - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - - if (!cputimer_running(tsk)) - return; - - atomic64_add(cputime, &cputimer->cputime_atomic.stime); -} - -/** - * account_group_exec_runtime - Maintain exec runtime for a thread group. - * - * @tsk: Pointer to task structure. - * @ns: Time value by which to increment the sum_exec_runtime field - * of the thread_group_cputime structure. - * - * If thread group time is being maintained, get the structure for the - * running CPU and update the sum_exec_runtime field there. - */ -static inline void account_group_exec_runtime(struct task_struct *tsk, - unsigned long long ns) -{ - struct thread_group_cputimer *cputimer = &tsk->signal->cputimer; - - if (!cputimer_running(tsk)) - return; - - atomic64_add(ns, &cputimer->cputime_atomic.sum_exec_runtime); -} diff --git a/kernel/sched/stop_task.c b/kernel/sched/stop_task.c index 604297a08b3a..9f69fb630853 100644 --- a/kernel/sched/stop_task.c +++ b/kernel/sched/stop_task.c @@ -24,7 +24,7 @@ check_preempt_curr_stop(struct rq *rq, struct task_struct *p, int flags) } static struct task_struct * -pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct pin_cookie cookie) +pick_next_task_stop(struct rq *rq, struct task_struct *prev, struct rq_flags *rf) { struct task_struct *stop = rq->stop; diff --git a/kernel/sched/swait.c b/kernel/sched/swait.c index 82f0dff90030..3d5610dcce11 100644 --- a/kernel/sched/swait.c +++ b/kernel/sched/swait.c @@ -1,4 +1,4 @@ -#include <linux/sched.h> +#include <linux/sched/signal.h> #include <linux/swait.h> void __init_swait_queue_head(struct swait_queue_head *q, const char *name, diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c new file mode 100644 index 000000000000..1b0b4fb12837 --- /dev/null +++ b/kernel/sched/topology.c @@ -0,0 +1,1658 @@ +/* + * Scheduler topology setup/handling methods + */ +#include <linux/sched.h> +#include <linux/mutex.h> + +#include "sched.h" + +DEFINE_MUTEX(sched_domains_mutex); + +/* Protected by sched_domains_mutex: */ +cpumask_var_t sched_domains_tmpmask; + +#ifdef CONFIG_SCHED_DEBUG + +static __read_mostly int sched_debug_enabled; + +static int __init sched_debug_setup(char *str) +{ + sched_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + struct cpumask *groupmask) +{ + struct sched_group *group = sd->groups; + + cpumask_clear(groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; + } + + printk(KERN_CONT "span %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + if (!cpumask_test_cpu(cpu, sched_group_cpus(group))) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + + printk(KERN_DEBUG "%*s groups:", level + 1, ""); + do { + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); + break; + } + + if (!cpumask_weight(sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } + + if (!(sd->flags & SD_OVERLAP) && + cpumask_intersects(groupmask, sched_group_cpus(group))) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } + + cpumask_or(groupmask, groupmask, sched_group_cpus(group)); + + printk(KERN_CONT " %*pbl", + cpumask_pr_args(sched_group_cpus(group))); + if (group->sgc->capacity != SCHED_CAPACITY_SCALE) { + printk(KERN_CONT " (cpu_capacity = %lu)", + group->sgc->capacity); + } + + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); + + if (!cpumask_equal(sched_domain_span(sd), groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} + +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + int level = 0; + + if (!sched_debug_enabled) + return; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } +} +#else /* !CONFIG_SCHED_DEBUG */ + +# define sched_debug_enabled 0 +# define sched_domain_debug(sd, cpu) do { } while (0) +static inline bool sched_debug(void) +{ + return false; +} +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpumask_weight(sched_domain_span(sd)) == 1) + return 1; + + /* Following flags need at least 2 groups */ + if (sd->flags & (SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUCAPACITY | + SD_ASYM_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_SHARE_POWERDOMAIN)) { + if (sd->groups != sd->groups->next) + return 0; + } + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_AFFINE)) + return 0; + + return 1; +} + +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) +{ + unsigned long cflags = sd->flags, pflags = parent->flags; + + if (sd_degenerate(parent)) + return 1; + + if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) + return 0; + + /* Flags needing groups don't count if only 1 group in parent */ + if (parent->groups == parent->groups->next) { + pflags &= ~(SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_ASYM_CPUCAPACITY | + SD_SHARE_CPUCAPACITY | + SD_SHARE_PKG_RESOURCES | + SD_PREFER_SIBLING | + SD_SHARE_POWERDOMAIN); + if (nr_node_ids == 1) + pflags &= ~SD_SERIALIZE; + } + if (~cflags & pflags) + return 0; + + return 1; +} + +static void free_rootdomain(struct rcu_head *rcu) +{ + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); + + cpupri_cleanup(&rd->cpupri); + cpudl_cleanup(&rd->cpudl); + free_cpumask_var(rd->dlo_mask); + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + +void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + struct root_domain *old_rd = NULL; + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + + if (rq->rd) { + old_rd = rq->rd; + + if (cpumask_test_cpu(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpumask_clear_cpu(rq->cpu, old_rd->span); + + /* + * If we dont want to free the old_rd yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) + set_rq_online(rq); + + raw_spin_unlock_irqrestore(&rq->lock, flags); + + if (old_rd) + call_rcu_sched(&old_rd->rcu, free_rootdomain); +} + +static int init_rootdomain(struct root_domain *rd) +{ + memset(rd, 0, sizeof(*rd)); + + if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!zalloc_cpumask_var(&rd->dlo_mask, GFP_KERNEL)) + goto free_online; + if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_dlo_mask; + + init_dl_bw(&rd->dl_bw); + if (cpudl_init(&rd->cpudl) != 0) + goto free_rto_mask; + + if (cpupri_init(&rd->cpupri) != 0) + goto free_cpudl; + return 0; + +free_cpudl: + cpudl_cleanup(&rd->cpudl); +free_rto_mask: + free_cpumask_var(rd->rto_mask); +free_dlo_mask: + free_cpumask_var(rd->dlo_mask); +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; +} + +/* + * By default the system creates a single root-domain with all CPUs as + * members (mimicking the global state we have today). + */ +struct root_domain def_root_domain; + +void init_defrootdomain(void) +{ + init_rootdomain(&def_root_domain); + + atomic_set(&def_root_domain.refcount, 1); +} + +static struct root_domain *alloc_rootdomain(void) +{ + struct root_domain *rd; + + rd = kmalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return NULL; + + if (init_rootdomain(rd) != 0) { + kfree(rd); + return NULL; + } + + return rd; +} + +static void free_sched_groups(struct sched_group *sg, int free_sgc) +{ + struct sched_group *tmp, *first; + + if (!sg) + return; + + first = sg; + do { + tmp = sg->next; + + if (free_sgc && atomic_dec_and_test(&sg->sgc->ref)) + kfree(sg->sgc); + + kfree(sg); + sg = tmp; + } while (sg != first); +} + +static void destroy_sched_domain(struct sched_domain *sd) +{ + /* + * If its an overlapping domain it has private groups, iterate and + * nuke them all. + */ + if (sd->flags & SD_OVERLAP) { + free_sched_groups(sd->groups, 1); + } else if (atomic_dec_and_test(&sd->groups->ref)) { + kfree(sd->groups->sgc); + kfree(sd->groups); + } + if (sd->shared && atomic_dec_and_test(&sd->shared->ref)) + kfree(sd->shared); + kfree(sd); +} + +static void destroy_sched_domains_rcu(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + + while (sd) { + struct sched_domain *parent = sd->parent; + destroy_sched_domain(sd); + sd = parent; + } +} + +static void destroy_sched_domains(struct sched_domain *sd) +{ + if (sd) + call_rcu(&sd->rcu, destroy_sched_domains_rcu); +} + +/* + * Keep a special pointer to the highest sched_domain that has + * SD_SHARE_PKG_RESOURCE set (Last Level Cache Domain) for this + * allows us to avoid some pointer chasing select_idle_sibling(). + * + * Also keep a unique ID per domain (we use the first CPU number in + * the cpumask of the domain), this allows us to quickly tell if + * two CPUs are in the same cache domain, see cpus_share_cache(). + */ +DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(int, sd_llc_size); +DEFINE_PER_CPU(int, sd_llc_id); +DEFINE_PER_CPU(struct sched_domain_shared *, sd_llc_shared); +DEFINE_PER_CPU(struct sched_domain *, sd_numa); +DEFINE_PER_CPU(struct sched_domain *, sd_asym); + +static void update_top_cache_domain(int cpu) +{ + struct sched_domain_shared *sds = NULL; + struct sched_domain *sd; + int id = cpu; + int size = 1; + + sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); + if (sd) { + id = cpumask_first(sched_domain_span(sd)); + size = cpumask_weight(sched_domain_span(sd)); + sds = sd->shared; + } + + rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); + per_cpu(sd_llc_size, cpu) = size; + per_cpu(sd_llc_id, cpu) = id; + rcu_assign_pointer(per_cpu(sd_llc_shared, cpu), sds); + + sd = lowest_flag_domain(cpu, SD_NUMA); + rcu_assign_pointer(per_cpu(sd_numa, cpu), sd); + + sd = highest_flag_domain(cpu, SD_ASYM_PACKING); + rcu_assign_pointer(per_cpu(sd_asym, cpu), sd); +} + +/* + * Attach the domain 'sd' to 'cpu' as its base domain. Callers must + * hold the hotplug lock. + */ +static void +cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_domain *tmp; + + /* Remove the sched domains which do not contribute to scheduling. */ + for (tmp = sd; tmp; ) { + struct sched_domain *parent = tmp->parent; + if (!parent) + break; + + if (sd_parent_degenerate(tmp, parent)) { + tmp->parent = parent->parent; + if (parent->parent) + parent->parent->child = tmp; + /* + * Transfer SD_PREFER_SIBLING down in case of a + * degenerate parent; the spans match for this + * so the property transfers. + */ + if (parent->flags & SD_PREFER_SIBLING) + tmp->flags |= SD_PREFER_SIBLING; + destroy_sched_domain(parent); + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + tmp = sd; + sd = sd->parent; + destroy_sched_domain(tmp); + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + tmp = rq->sd; + rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp); + + update_top_cache_domain(cpu); +} + +/* Setup the mask of CPUs configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + int ret; + + alloc_bootmem_cpumask_var(&cpu_isolated_map); + ret = cpulist_parse(str, cpu_isolated_map); + if (ret) { + pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); + return 0; + } + return 1; +} +__setup("isolcpus=", isolated_cpu_setup); + +struct s_data { + struct sched_domain ** __percpu sd; + struct root_domain *rd; +}; + +enum s_alloc { + sa_rootdomain, + sa_sd, + sa_sd_storage, + sa_none, +}; + +/* + * Build an iteration mask that can exclude certain CPUs from the upwards + * domain traversal. + * + * Asymmetric node setups can result in situations where the domain tree is of + * unequal depth, make sure to skip domains that already cover the entire + * range. + * + * In that case build_sched_domains() will have terminated the iteration early + * and our sibling sd spans will be empty. Domains should always include the + * CPU they're built on, so check that. + */ +static void build_group_mask(struct sched_domain *sd, struct sched_group *sg) +{ + const struct cpumask *span = sched_domain_span(sd); + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + for_each_cpu(i, span) { + sibling = *per_cpu_ptr(sdd->sd, i); + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + cpumask_set_cpu(i, sched_group_mask(sg)); + } +} + +/* + * Return the canonical balance CPU for this group, this is the first CPU + * of this group that's also in the iteration mask. + */ +int group_balance_cpu(struct sched_group *sg) +{ + return cpumask_first_and(sched_group_cpus(sg), sched_group_mask(sg)); +} + +static int +build_overlap_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL, *groups = NULL, *sg; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered = sched_domains_tmpmask; + struct sd_data *sdd = sd->private; + struct sched_domain *sibling; + int i; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct cpumask *sg_span; + + if (cpumask_test_cpu(i, covered)) + continue; + + sibling = *per_cpu_ptr(sdd->sd, i); + + /* See the comment near build_group_mask(). */ + if (!cpumask_test_cpu(i, sched_domain_span(sibling))) + continue; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(cpu)); + + if (!sg) + goto fail; + + sg_span = sched_group_cpus(sg); + if (sibling->child) + cpumask_copy(sg_span, sched_domain_span(sibling->child)); + else + cpumask_set_cpu(i, sg_span); + + cpumask_or(covered, covered, sg_span); + + sg->sgc = *per_cpu_ptr(sdd->sgc, i); + if (atomic_inc_return(&sg->sgc->ref) == 1) + build_group_mask(sd, sg); + + /* + * 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->sgc->capacity = SCHED_CAPACITY_SCALE * cpumask_weight(sg_span); + sg->sgc->min_capacity = SCHED_CAPACITY_SCALE; + + /* + * Make sure the first group of this domain contains the + * canonical balance CPU. Otherwise the sched_domain iteration + * breaks. See update_sg_lb_stats(). + */ + if ((!groups && cpumask_test_cpu(cpu, sg_span)) || + group_balance_cpu(sg) == cpu) + groups = sg; + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + last->next = first; + } + sd->groups = groups; + + return 0; + +fail: + free_sched_groups(first, 0); + + return -ENOMEM; +} + +static int get_group(int cpu, struct sd_data *sdd, struct sched_group **sg) +{ + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + struct sched_domain *child = sd->child; + + if (child) + cpu = cpumask_first(sched_domain_span(child)); + + if (sg) { + *sg = *per_cpu_ptr(sdd->sg, cpu); + (*sg)->sgc = *per_cpu_ptr(sdd->sgc, cpu); + + /* For claim_allocations: */ + atomic_set(&(*sg)->sgc->ref, 1); + } + + return cpu; +} + +/* + * 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_capacity to 0. + * + * Assumes the sched_domain tree is fully constructed + */ +static int +build_sched_groups(struct sched_domain *sd, int cpu) +{ + struct sched_group *first = NULL, *last = NULL; + struct sd_data *sdd = sd->private; + const struct cpumask *span = sched_domain_span(sd); + struct cpumask *covered; + int i; + + get_group(cpu, sdd, &sd->groups); + atomic_inc(&sd->groups->ref); + + if (cpu != cpumask_first(span)) + return 0; + + lockdep_assert_held(&sched_domains_mutex); + covered = sched_domains_tmpmask; + + cpumask_clear(covered); + + for_each_cpu(i, span) { + struct sched_group *sg; + int group, j; + + if (cpumask_test_cpu(i, covered)) + continue; + + group = get_group(i, sdd, &sg); + cpumask_setall(sched_group_mask(sg)); + + for_each_cpu(j, span) { + if (get_group(j, sdd, NULL) != group) + continue; + + cpumask_set_cpu(j, covered); + cpumask_set_cpu(j, sched_group_cpus(sg)); + } + + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; + + return 0; +} + +/* + * Initialize sched groups cpu_capacity. + * + * 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_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_capacity(int cpu, struct sched_domain *sd) +{ + struct sched_group *sg = sd->groups; + + WARN_ON(!sg); + + do { + int cpu, max_cpu = -1; + + sg->group_weight = cpumask_weight(sched_group_cpus(sg)); + + if (!(sd->flags & SD_ASYM_PACKING)) + goto next; + + for_each_cpu(cpu, sched_group_cpus(sg)) { + if (max_cpu < 0) + max_cpu = cpu; + else if (sched_asym_prefer(cpu, max_cpu)) + max_cpu = cpu; + } + sg->asym_prefer_cpu = max_cpu; + +next: + sg = sg->next; + } while (sg != sd->groups); + + if (cpu != group_balance_cpu(sg)) + return; + + update_group_capacity(sd, cpu); +} + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +static int default_relax_domain_level = -1; +int sched_domain_level_max; + +static int __init setup_relax_domain_level(char *str) +{ + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); + + return 1; +} +__setup("relax_domain_level=", setup_relax_domain_level); + +static void set_domain_attribute(struct sched_domain *sd, + struct sched_domain_attr *attr) +{ + int request; + + if (!attr || attr->relax_domain_level < 0) { + if (default_relax_domain_level < 0) + return; + else + request = default_relax_domain_level; + } else + request = attr->relax_domain_level; + if (request < sd->level) { + /* Turn off idle balance on this domain: */ + sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } else { + /* Turn on idle balance on this domain: */ + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } +} + +static void __sdt_free(const struct cpumask *cpu_map); +static int __sdt_alloc(const struct cpumask *cpu_map); + +static void __free_domain_allocs(struct s_data *d, enum s_alloc what, + const struct cpumask *cpu_map) +{ + switch (what) { + case sa_rootdomain: + if (!atomic_read(&d->rd->refcount)) + free_rootdomain(&d->rd->rcu); + /* Fall through */ + case sa_sd: + free_percpu(d->sd); + /* Fall through */ + case sa_sd_storage: + __sdt_free(cpu_map); + /* Fall through */ + case sa_none: + break; + } +} + +static enum s_alloc +__visit_domain_allocation_hell(struct s_data *d, const struct cpumask *cpu_map) +{ + memset(d, 0, sizeof(*d)); + + if (__sdt_alloc(cpu_map)) + return sa_sd_storage; + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; + d->rd = alloc_rootdomain(); + if (!d->rd) + return sa_sd; + return sa_rootdomain; +} + +/* + * NULL the sd_data elements we've used to build the sched_domain and + * sched_group structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sds, cpu))->ref)) + *per_cpu_ptr(sdd->sds, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sg, cpu))->ref)) + *per_cpu_ptr(sdd->sg, cpu) = NULL; + + if (atomic_read(&(*per_cpu_ptr(sdd->sgc, cpu))->ref)) + *per_cpu_ptr(sdd->sgc, cpu) = NULL; +} + +#ifdef CONFIG_NUMA +static int sched_domains_numa_levels; +enum numa_topology_type sched_numa_topology_type; +static int *sched_domains_numa_distance; +int sched_max_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; +#endif + +/* + * SD_flags allowed in topology descriptions. + * + * These flags are purely descriptive of the topology and do not prescribe + * behaviour. Behaviour is artificial and mapped in the below sd_init() + * function: + * + * 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 + * SD_ASYM_CPUCAPACITY - describes mixed capacity topologies + * + * Odd one out, which beside describing the topology has a quirk also + * prescribes the desired behaviour that goes along with it: + * + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_ASYM_CPUCAPACITY | \ + SD_SHARE_POWERDOMAIN) + +static struct sched_domain * +sd_init(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, + struct sched_domain *child, int cpu) +{ + struct sd_data *sdd = &tl->data; + struct sched_domain *sd = *per_cpu_ptr(sdd->sd, cpu); + int sd_id, 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 = 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 + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK + | 0*SD_BALANCE_WAKE + | 1*SD_WAKE_AFFINE + | 0*SD_SHARE_CPUCAPACITY + | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | 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, + .child = child, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif + }; + + cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + sd_id = cpumask_first(sched_domain_span(sd)); + + /* + * Convert topological properties into behaviour. + */ + + if (sd->flags & SD_ASYM_CPUCAPACITY) { + struct sched_domain *t = sd; + + for_each_lower_domain(t) + t->flags |= SD_BALANCE_WAKE; + } + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; + 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; + } + + /* + * For all levels sharing cache; connect a sched_domain_shared + * instance. + */ + if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->shared = *per_cpu_ptr(sdd->sds, sd_id); + atomic_inc(&sd->shared->ref); + atomic_set(&sd->shared->nr_busy_cpus, sd_weight); + } + + sd->private = sdd; + + 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, }, +}; + +static 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) +{ + if (WARN_ON_ONCE(sched_smp_initialized)) + return; + + 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)]; +} + +static void sched_numa_warn(const char *str) +{ + static int done = false; + int i,j; + + if (done) + return; + + done = true; + + printk(KERN_WARNING "ERROR: %s\n\n", str); + + for (i = 0; i < nr_node_ids; i++) { + printk(KERN_WARNING " "); + for (j = 0; j < nr_node_ids; j++) + printk(KERN_CONT "%02d ", node_distance(i,j)); + printk(KERN_CONT "\n"); + } + printk(KERN_WARNING "\n"); +} + +bool find_numa_distance(int distance) +{ + int i; + + if (distance == node_distance(0, 0)) + return true; + + for (i = 0; i < sched_domains_numa_levels; i++) { + if (sched_domains_numa_distance[i] == distance) + return true; + } + + return false; +} + +/* + * A system can have three types of NUMA topology: + * NUMA_DIRECT: all nodes are directly connected, or not a NUMA system + * NUMA_GLUELESS_MESH: some nodes reachable through intermediary nodes + * NUMA_BACKPLANE: nodes can reach other nodes through a backplane + * + * The difference between a glueless mesh topology and a backplane + * topology lies in whether communication between not directly + * connected nodes goes through intermediary nodes (where programs + * could run), or through backplane controllers. This affects + * placement of programs. + * + * The type of topology can be discerned with the following tests: + * - If the maximum distance between any nodes is 1 hop, the system + * is directly connected. + * - If for two nodes A and B, located N > 1 hops away from each other, + * there is an intermediary node C, which is < N hops away from both + * nodes A and B, the system is a glueless mesh. + */ +static void init_numa_topology_type(void) +{ + int a, b, c, n; + + n = sched_max_numa_distance; + + if (sched_domains_numa_levels <= 1) { + sched_numa_topology_type = NUMA_DIRECT; + return; + } + + for_each_online_node(a) { + for_each_online_node(b) { + /* Find two nodes furthest removed from each other. */ + if (node_distance(a, b) < n) + continue; + + /* Is there an intermediary node between a and b? */ + for_each_online_node(c) { + if (node_distance(a, c) < n && + node_distance(b, c) < n) { + sched_numa_topology_type = + NUMA_GLUELESS_MESH; + return; + } + } + + sched_numa_topology_type = NUMA_BACKPLANE; + return; + } + } +} + +void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + for (k = 0; k < nr_node_ids; k++) { + int distance = node_distance(i, k); + + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + + /* + * While not a strong assumption it would be nice to know + * about cases where if node A is connected to B, B is not + * equally connected to A. + */ + if (sched_debug() && node_distance(k, i) != distance) + sched_numa_warn("Node-distance not symmetric"); + + if (sched_debug() && i && !find_numa_distance(distance)) + sched_numa_warn("Node-0 not representative"); + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + + /* + * In case of sched_debug() we verify the above assumption. + */ + if (!sched_debug()) + break; + } + + if (!level) + return; + + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_numa_distance[] array includes the actual distance + * numbers. + */ + + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * CPUs of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for_each_node(k) { + if (node_distance(j, k) > sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + /* 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; + + /* + * Copy the default topology bits.. + */ + 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){ + .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, + .flags = SDTL_OVERLAP, + .numa_level = j, + SD_INIT_NAME(NUMA) + }; + } + + sched_domain_topology = tl; + + sched_domains_numa_levels = level; + sched_max_numa_distance = sched_domains_numa_distance[level - 1]; + + init_numa_topology_type(); +} + +void sched_domains_numa_masks_set(unsigned int cpu) +{ + int node = cpu_to_node(cpu); + int i, j; + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +void sched_domains_numa_masks_clear(unsigned int cpu) +{ + int i, j; + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +#endif /* CONFIG_NUMA */ + +static int __sdt_alloc(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + sdd->sd = alloc_percpu(struct sched_domain *); + if (!sdd->sd) + return -ENOMEM; + + sdd->sds = alloc_percpu(struct sched_domain_shared *); + if (!sdd->sds) + return -ENOMEM; + + sdd->sg = alloc_percpu(struct sched_group *); + if (!sdd->sg) + return -ENOMEM; + + 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_domain_shared *sds; + struct sched_group *sg; + struct sched_group_capacity *sgc; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return -ENOMEM; + + *per_cpu_ptr(sdd->sd, j) = sd; + + sds = kzalloc_node(sizeof(struct sched_domain_shared), + GFP_KERNEL, cpu_to_node(j)); + if (!sds) + return -ENOMEM; + + *per_cpu_ptr(sdd->sds, j) = sds; + + sg = kzalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sg) + return -ENOMEM; + + sg->next = sg; + + *per_cpu_ptr(sdd->sg, j) = sg; + + sgc = kzalloc_node(sizeof(struct sched_group_capacity) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sgc) + return -ENOMEM; + + *per_cpu_ptr(sdd->sgc, j) = sgc; + } + } + + return 0; +} + +static void __sdt_free(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + if (sd && (sd->flags & SD_OVERLAP)) + free_sched_groups(sd->groups, 0); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + + if (sdd->sds) + kfree(*per_cpu_ptr(sdd->sds, j)); + if (sdd->sg) + kfree(*per_cpu_ptr(sdd->sg, j)); + if (sdd->sgc) + kfree(*per_cpu_ptr(sdd->sgc, j)); + } + free_percpu(sdd->sd); + sdd->sd = NULL; + free_percpu(sdd->sds); + sdd->sds = NULL; + free_percpu(sdd->sg); + sdd->sg = NULL; + free_percpu(sdd->sgc); + sdd->sgc = NULL; + } +} + +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 = sd_init(tl, cpu_map, child, cpu); + + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); + child->parent = sd; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + + } + set_domain_attribute(sd, attr); + + return sd; +} + +/* + * Build sched domains for a given set of CPUs and attach the sched domains + * to the individual CPUs + */ +static int +build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr) +{ + enum s_alloc alloc_state; + struct sched_domain *sd; + struct s_data d; + struct rq *rq = NULL; + int i, ret = -ENOMEM; + + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); + if (alloc_state != sa_rootdomain) + goto error; + + /* Set up domains for CPUs specified by the cpu_map: */ + for_each_cpu(i, cpu_map) { + struct sched_domain_topology_level *tl; + + sd = NULL; + for_each_sd_topology(tl) { + sd = build_sched_domain(tl, cpu_map, attr, sd, i); + if (tl == sched_domain_topology) + *per_cpu_ptr(d.sd, i) = sd; + if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP)) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } + } + + /* Build the groups for the domains */ + for_each_cpu(i, cpu_map) { + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + sd->span_weight = cpumask_weight(sched_domain_span(sd)); + if (sd->flags & SD_OVERLAP) { + if (build_overlap_sched_groups(sd, i)) + goto error; + } else { + if (build_sched_groups(sd, i)) + goto error; + } + } + } + + /* 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_capacity(i, sd); + } + } + + /* Attach the domains */ + rcu_read_lock(); + for_each_cpu(i, cpu_map) { + rq = cpu_rq(i); + sd = *per_cpu_ptr(d.sd, i); + + /* Use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing: */ + if (rq->cpu_capacity_orig > READ_ONCE(d.rd->max_cpu_capacity)) + WRITE_ONCE(d.rd->max_cpu_capacity, rq->cpu_capacity_orig); + + cpu_attach_domain(sd, d.rd, i); + } + rcu_read_unlock(); + + if (rq && sched_debug_enabled) { + pr_info("span: %*pbl (max cpu_capacity = %lu)\n", + cpumask_pr_args(cpu_map), rq->rd->max_cpu_capacity); + } + + ret = 0; +error: + __free_domain_allocs(&d, alloc_state, cpu_map); + return ret; +} + +/* Current sched domains: */ +static cpumask_var_t *doms_cur; + +/* Number of sched domains in 'doms_cur': */ +static int ndoms_cur; + +/* Attribues of custom domains in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + +/* + * Special case: If a kmalloc() of a doms_cur partition (array of + * cpumask) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. + */ +cpumask_var_t fallback_doms; + +/* + * arch_update_cpu_topology lets virtualized architectures update the + * CPU core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __weak arch_update_cpu_topology(void) +{ + return 0; +} + +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + +/* + * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * For now this just excludes isolated CPUs, but could be used to + * exclude other special cases in the future. + */ +int init_sched_domains(const struct cpumask *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = alloc_sched_domains(ndoms_cur); + if (!doms_cur) + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur[0], NULL); + register_sched_domain_sysctl(); + + return err; +} + +/* + * Detach sched domains from a group of CPUs specified in cpu_map + * These CPUs will now be attached to the NULL domain + */ +static void detach_destroy_domains(const struct cpumask *cpu_map) +{ + int i; + + rcu_read_lock(); + for_each_cpu(i, cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + rcu_read_unlock(); +} + +/* handle null as "default" */ +static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, + struct sched_domain_attr *new, int idx_new) +{ + struct sched_domain_attr tmp; + + /* Fast path: */ + if (!new && !cur) + return 1; + + tmp = SD_ATTR_INIT; + return !memcmp(cur ? (cur + idx_cur) : &tmp, + new ? (new + idx_new) : &tmp, + sizeof(struct sched_domain_attr)); +} + +/* + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_mask. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + int new_topology; + + mutex_lock(&sched_domains_mutex); + + /* Always unregister in case we don't destroy any domains: */ + unregister_sched_domain_sysctl(); + + /* Let the architecture update CPU core mappings: */ + new_topology = arch_update_cpu_topology(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains: */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_cur[i], doms_new[j]) + && dattrs_equal(dattr_cur, i, dattr_new, j)) + goto match1; + } + /* No match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur[i]); +match1: + ; + } + + n = ndoms_cur; + if (doms_new == NULL) { + n = 0; + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); + } + + /* Build new domains: */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_equal(doms_new[i], doms_cur[j]) + && dattrs_equal(dattr_new, i, dattr_cur, j)) + goto match2; + } + /* No match - add a new doms_new */ + build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); +match2: + ; + } + + /* Remember the new sched domains: */ + if (doms_cur != &fallback_doms) + free_sched_domains(doms_cur, ndoms_cur); + + kfree(dattr_cur); + doms_cur = doms_new; + dattr_cur = dattr_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + mutex_unlock(&sched_domains_mutex); +} + diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c index 9453efe9b25a..b8c84c6dee64 100644 --- a/kernel/sched/wait.c +++ b/kernel/sched/wait.c @@ -5,7 +5,8 @@ */ #include <linux/init.h> #include <linux/export.h> -#include <linux/sched.h> +#include <linux/sched/signal.h> +#include <linux/sched/debug.h> #include <linux/mm.h> #include <linux/wait.h> #include <linux/hash.h> @@ -241,6 +242,45 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state) } EXPORT_SYMBOL(prepare_to_wait_event); +/* + * Note! These two wait functions are entered with the + * wait-queue lock held (and interrupts off in the _irq + * case), so there is no race with testing the wakeup + * condition in the caller before they add the wait + * entry to the wake queue. + */ +int do_wait_intr(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock(&wq->lock); + schedule(); + spin_lock(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr); + +int do_wait_intr_irq(wait_queue_head_t *wq, wait_queue_t *wait) +{ + if (likely(list_empty(&wait->task_list))) + __add_wait_queue_tail(wq, wait); + + set_current_state(TASK_INTERRUPTIBLE); + if (signal_pending(current)) + return -ERESTARTSYS; + + spin_unlock_irq(&wq->lock); + schedule(); + spin_lock_irq(&wq->lock); + return 0; +} +EXPORT_SYMBOL(do_wait_intr_irq); + /** * finish_wait - clean up after waiting in a queue * @q: waitqueue waited on |