diff options
Diffstat (limited to 'kernel/sched/core.c')
| -rw-r--r-- | kernel/sched/core.c | 370 |
1 files changed, 301 insertions, 69 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 17c667b427b4..75554f366fd3 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -16,6 +16,7 @@ #include <linux/init_task.h> #include <linux/context_tracking.h> #include <linux/rcupdate_wait.h> +#include <linux/compat.h> #include <linux/blkdev.h> #include <linux/kprobes.h> @@ -26,6 +27,7 @@ #include <linux/profile.h> #include <linux/security.h> #include <linux/syscalls.h> +#include <linux/sched/isolation.h> #include <asm/switch_to.h> #include <asm/tlb.h> @@ -42,18 +44,21 @@ DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL) /* * Debugging: various feature bits + * + * If SCHED_DEBUG is disabled, each compilation unit has its own copy of + * sysctl_sched_features, defined in sched.h, to allow constants propagation + * at compile time and compiler optimization based on features default. */ - #define SCHED_FEAT(name, enabled) \ (1UL << __SCHED_FEAT_##name) * enabled | - const_debug unsigned int sysctl_sched_features = #include "features.h" 0; - #undef SCHED_FEAT +#endif /* * Number of tasks to iterate in a single balance run. @@ -83,9 +88,6 @@ __read_mostly int scheduler_running; */ int sysctl_sched_rt_runtime = 950000; -/* CPUs with isolated domains */ -cpumask_var_t cpu_isolated_map; - /* * __task_rq_lock - lock the rq @p resides on. */ @@ -505,8 +507,7 @@ void resched_cpu(int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - if (!raw_spin_trylock_irqsave(&rq->lock, flags)) - return; + raw_spin_lock_irqsave(&rq->lock, flags); resched_curr(rq); raw_spin_unlock_irqrestore(&rq->lock, flags); } @@ -526,7 +527,7 @@ int get_nohz_timer_target(void) int i, cpu = smp_processor_id(); struct sched_domain *sd; - if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu)) + if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER)) return cpu; rcu_read_lock(); @@ -535,15 +536,15 @@ int get_nohz_timer_target(void) if (cpu == i) continue; - if (!idle_cpu(i) && is_housekeeping_cpu(i)) { + if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) { cpu = i; goto unlock; } } } - if (!is_housekeeping_cpu(cpu)) - cpu = housekeeping_any_cpu(); + if (!housekeeping_cpu(cpu, HK_FLAG_TIMER)) + cpu = housekeeping_any_cpu(HK_FLAG_TIMER); unlock: rcu_read_unlock(); return cpu; @@ -733,7 +734,7 @@ int tg_nop(struct task_group *tg, void *data) } #endif -static void set_load_weight(struct task_struct *p) +static void set_load_weight(struct task_struct *p, bool update_load) { int prio = p->static_prio - MAX_RT_PRIO; struct load_weight *load = &p->se.load; @@ -747,8 +748,16 @@ static void set_load_weight(struct task_struct *p) return; } - load->weight = scale_load(sched_prio_to_weight[prio]); - load->inv_weight = sched_prio_to_wmult[prio]; + /* + * SCHED_OTHER tasks have to update their load when changing their + * weight + */ + if (update_load && p->sched_class == &fair_sched_class) { + reweight_task(p, prio); + } else { + load->weight = scale_load(sched_prio_to_weight[prio]); + load->inv_weight = sched_prio_to_wmult[prio]; + } } static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) @@ -951,8 +960,13 @@ struct migration_arg { static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf, struct task_struct *p, int dest_cpu) { - if (unlikely(!cpu_active(dest_cpu))) - return rq; + if (p->flags & PF_KTHREAD) { + if (unlikely(!cpu_online(dest_cpu))) + return rq; + } else { + if (unlikely(!cpu_active(dest_cpu))) + return rq; + } /* Affinity changed (again). */ if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) @@ -1168,6 +1182,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) || lockdep_is_held(&task_rq(p)->lock))); #endif + /* + * Clearly, migrating tasks to offline CPUs is a fairly daft thing. + */ + WARN_ON_ONCE(!cpu_online(new_cpu)); #endif trace_sched_migrate_task(p, new_cpu); @@ -1967,8 +1985,8 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) * reordered with p->state check below. This pairs with mb() in * set_current_state() the waiting thread does. */ - smp_mb__before_spinlock(); raw_spin_lock_irqsave(&p->pi_lock, flags); + smp_mb__after_spinlock(); if (!(p->state & state)) goto out; @@ -2069,7 +2087,7 @@ out: /** * try_to_wake_up_local - try to wake up a local task with rq lock held * @p: the thread to be awakened - * @cookie: context's cookie for pinning + * @rf: request-queue flags for pinning * * Put @p on the run-queue if it's not already there. The caller must * ensure that this_rq() is locked, @p is bound to this_rq() and not @@ -2349,7 +2367,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) p->static_prio = NICE_TO_PRIO(0); p->prio = p->normal_prio = __normal_prio(p); - set_load_weight(p); + set_load_weight(p, false); /* * We don't need the reset flag anymore after the fork. It has @@ -2635,6 +2653,16 @@ static struct rq *finish_task_switch(struct task_struct *prev) prev_state = prev->state; vtime_task_switch(prev); perf_event_task_sched_in(prev, current); + /* + * The membarrier system call requires a full memory barrier + * after storing to rq->curr, before going back to user-space. + * + * TODO: This smp_mb__after_unlock_lock can go away if PPC end + * up adding a full barrier to switch_mm(), or we should figure + * out if a smp_mb__after_unlock_lock is really the proper API + * to use. + */ + smp_mb__after_unlock_lock(); finish_lock_switch(rq, prev); finish_arch_post_lock_switch(); @@ -3281,8 +3309,8 @@ static void __sched notrace __schedule(bool preempt) * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) * done by the caller to avoid the race with signal_wake_up(). */ - smp_mb__before_spinlock(); rq_lock(rq, &rf); + smp_mb__after_spinlock(); /* Promote REQ to ACT */ rq->clock_update_flags <<= 1; @@ -3324,6 +3352,21 @@ static void __sched notrace __schedule(bool preempt) if (likely(prev != next)) { rq->nr_switches++; rq->curr = next; + /* + * The membarrier system call requires each architecture + * to have a full memory barrier after updating + * rq->curr, before returning to user-space. For TSO + * (e.g. x86), the architecture must provide its own + * barrier in switch_mm(). For weakly ordered machines + * for which spin_unlock() acts as a full memory + * barrier, finish_lock_switch() in common code takes + * care of this barrier. For weakly ordered machines for + * which spin_unlock() acts as a RELEASE barrier (only + * arm64 and PowerPC), arm64 has a full barrier in + * switch_to(), and PowerPC has + * smp_mb__after_unlock_lock() before + * finish_lock_switch(). + */ ++*switch_count; trace_sched_switch(preempt, prev, next); @@ -3352,8 +3395,8 @@ void __noreturn do_task_dead(void) * To avoid it, we have to wait for releasing tsk->pi_lock which * is held by try_to_wake_up() */ - smp_mb(); - raw_spin_unlock_wait(¤t->pi_lock); + raw_spin_lock_irq(¤t->pi_lock); + raw_spin_unlock_irq(¤t->pi_lock); /* Causes final put_task_struct in finish_task_switch(): */ __set_current_state(TASK_DEAD); @@ -3771,7 +3814,7 @@ void set_user_nice(struct task_struct *p, long nice) put_prev_task(rq, p); p->static_prio = NICE_TO_PRIO(nice); - set_load_weight(p); + set_load_weight(p, true); old_prio = p->prio; p->prio = effective_prio(p); delta = p->prio - old_prio; @@ -3928,7 +3971,7 @@ static void __setscheduler_params(struct task_struct *p, */ p->rt_priority = attr->sched_priority; p->normal_prio = normal_prio(p); - set_load_weight(p); + set_load_weight(p, true); } /* Actually do priority change: must hold pi & rq lock. */ @@ -4808,6 +4851,7 @@ int __sched _cond_resched(void) preempt_schedule_common(); return 1; } + rcu_all_qs(); return 0; } EXPORT_SYMBOL(_cond_resched); @@ -5064,13 +5108,11 @@ SYSCALL_DEFINE1(sched_get_priority_min, int, policy) * Return: On success, 0 and the timeslice is in @interval. Otherwise, * an error code. */ -SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, - struct timespec __user *, interval) +static int sched_rr_get_interval(pid_t pid, struct timespec64 *t) { struct task_struct *p; unsigned int time_slice; struct rq_flags rf; - struct timespec t; struct rq *rq; int retval; @@ -5094,33 +5136,51 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, task_rq_unlock(rq, p, &rf); rcu_read_unlock(); - jiffies_to_timespec(time_slice, &t); - retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; - return retval; + jiffies_to_timespec64(time_slice, t); + return 0; out_unlock: rcu_read_unlock(); return retval; } -static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct timespec __user *, interval) +{ + struct timespec64 t; + int retval = sched_rr_get_interval(pid, &t); + + if (retval == 0) + retval = put_timespec64(&t, interval); + + return retval; +} + +#ifdef CONFIG_COMPAT +COMPAT_SYSCALL_DEFINE2(sched_rr_get_interval, + compat_pid_t, pid, + struct compat_timespec __user *, interval) +{ + struct timespec64 t; + int retval = sched_rr_get_interval(pid, &t); + + if (retval == 0) + retval = compat_put_timespec64(&t, interval); + return retval; +} +#endif void sched_show_task(struct task_struct *p) { unsigned long free = 0; 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) - state = __ffs(state) + 1; - printk(KERN_INFO "%-15.15s %c", p->comm, - state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); - if (state == TASK_RUNNING) + + printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p)); + + if (p->state == TASK_RUNNING) printk(KERN_CONT " running task "); #ifdef CONFIG_DEBUG_STACK_USAGE free = stack_not_used(p); @@ -5138,6 +5198,29 @@ void sched_show_task(struct task_struct *p) show_stack(p, NULL); put_task_stack(p); } +EXPORT_SYMBOL_GPL(sched_show_task); + +static inline bool +state_filter_match(unsigned long state_filter, struct task_struct *p) +{ + /* no filter, everything matches */ + if (!state_filter) + return true; + + /* filter, but doesn't match */ + if (!(p->state & state_filter)) + return false; + + /* + * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows + * TASK_KILLABLE). + */ + if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE) + return false; + + return true; +} + void show_state_filter(unsigned long state_filter) { @@ -5161,7 +5244,7 @@ void show_state_filter(unsigned long state_filter) */ touch_nmi_watchdog(); touch_all_softlockup_watchdogs(); - if (!state_filter || (p->state & state_filter)) + if (state_filter_match(state_filter, p)) sched_show_task(p); } @@ -5177,11 +5260,6 @@ void show_state_filter(unsigned long state_filter) debug_show_all_locks(); } -void init_idle_bootup_task(struct task_struct *idle) -{ - idle->sched_class = &idle_sched_class; -} - /** * init_idle - set up an idle thread for a given CPU * @idle: task in question @@ -5438,7 +5516,7 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf) */ next = pick_next_task(rq, &fake_task, rf); BUG_ON(!next); - next->sched_class->put_prev_task(rq, next); + put_prev_task(rq, next); /* * Rules for changing task_struct::cpus_allowed are holding @@ -5538,16 +5616,15 @@ static void cpuset_cpu_active(void) * operation in the resume sequence, just build a single sched * domain, ignoring cpusets. */ - num_cpus_frozen--; - if (likely(num_cpus_frozen)) { - partition_sched_domains(1, NULL, NULL); + partition_sched_domains(1, NULL, NULL); + if (--num_cpus_frozen) return; - } /* * This is the last CPU online operation. So fall through and * restore the original sched domains by considering the * cpuset configurations. */ + cpuset_force_rebuild(); } cpuset_update_active_cpus(); } @@ -5683,10 +5760,6 @@ static inline void sched_init_smt(void) { } void __init sched_init_smp(void) { - cpumask_var_t non_isolated_cpus; - - alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); - sched_init_numa(); /* @@ -5696,16 +5769,12 @@ void __init sched_init_smp(void) */ mutex_lock(&sched_domains_mutex); sched_init_domains(cpu_active_mask); - cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); - if (cpumask_empty(non_isolated_cpus)) - cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); mutex_unlock(&sched_domains_mutex); /* Move init over to a non-isolated CPU */ - if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) + if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0) BUG(); sched_init_granularity(); - free_cpumask_var(non_isolated_cpus); init_sched_rt_class(); init_sched_dl_class(); @@ -5890,7 +5959,7 @@ void __init sched_init(void) atomic_set(&rq->nr_iowait, 0); } - set_load_weight(&init_task); + set_load_weight(&init_task, false); /* * The boot idle thread does lazy MMU switching as well: @@ -5909,9 +5978,6 @@ void __init sched_init(void) calc_load_update = jiffies + LOAD_FREQ; #ifdef CONFIG_SMP - /* May be allocated at isolcpus cmdline parse time */ - if (cpu_isolated_map == NULL) - zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); idle_thread_set_boot_cpu(); set_cpu_rq_start_time(smp_processor_id()); #endif @@ -6578,7 +6644,7 @@ static int __cfs_schedulable(struct task_group *tg, u64 period, u64 quota) return ret; } -static int cpu_stats_show(struct seq_file *sf, void *v) +static int cpu_cfs_stat_show(struct seq_file *sf, void *v) { struct task_group *tg = css_tg(seq_css(sf)); struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; @@ -6618,7 +6684,7 @@ static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css, } #endif /* CONFIG_RT_GROUP_SCHED */ -static struct cftype cpu_files[] = { +static struct cftype cpu_legacy_files[] = { #ifdef CONFIG_FAIR_GROUP_SCHED { .name = "shares", @@ -6639,7 +6705,7 @@ static struct cftype cpu_files[] = { }, { .name = "stat", - .seq_show = cpu_stats_show, + .seq_show = cpu_cfs_stat_show, }, #endif #ifdef CONFIG_RT_GROUP_SCHED @@ -6657,16 +6723,182 @@ static struct cftype cpu_files[] = { { } /* Terminate */ }; +static int cpu_extra_stat_show(struct seq_file *sf, + struct cgroup_subsys_state *css) +{ +#ifdef CONFIG_CFS_BANDWIDTH + { + struct task_group *tg = css_tg(css); + struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth; + u64 throttled_usec; + + throttled_usec = cfs_b->throttled_time; + do_div(throttled_usec, NSEC_PER_USEC); + + seq_printf(sf, "nr_periods %d\n" + "nr_throttled %d\n" + "throttled_usec %llu\n", + cfs_b->nr_periods, cfs_b->nr_throttled, + throttled_usec); + } +#endif + return 0; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct task_group *tg = css_tg(css); + u64 weight = scale_load_down(tg->shares); + + return DIV_ROUND_CLOSEST_ULL(weight * CGROUP_WEIGHT_DFL, 1024); +} + +static int cpu_weight_write_u64(struct cgroup_subsys_state *css, + struct cftype *cft, u64 weight) +{ + /* + * cgroup weight knobs should use the common MIN, DFL and MAX + * values which are 1, 100 and 10000 respectively. While it loses + * a bit of range on both ends, it maps pretty well onto the shares + * value used by scheduler and the round-trip conversions preserve + * the original value over the entire range. + */ + if (weight < CGROUP_WEIGHT_MIN || weight > CGROUP_WEIGHT_MAX) + return -ERANGE; + + weight = DIV_ROUND_CLOSEST_ULL(weight * 1024, CGROUP_WEIGHT_DFL); + + return sched_group_set_shares(css_tg(css), scale_load(weight)); +} + +static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + unsigned long weight = scale_load_down(css_tg(css)->shares); + int last_delta = INT_MAX; + int prio, delta; + + /* find the closest nice value to the current weight */ + for (prio = 0; prio < ARRAY_SIZE(sched_prio_to_weight); prio++) { + delta = abs(sched_prio_to_weight[prio] - weight); + if (delta >= last_delta) + break; + last_delta = delta; + } + + return PRIO_TO_NICE(prio - 1 + MAX_RT_PRIO); +} + +static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css, + struct cftype *cft, s64 nice) +{ + unsigned long weight; + + if (nice < MIN_NICE || nice > MAX_NICE) + return -ERANGE; + + weight = sched_prio_to_weight[NICE_TO_PRIO(nice) - MAX_RT_PRIO]; + return sched_group_set_shares(css_tg(css), scale_load(weight)); +} +#endif + +static void __maybe_unused cpu_period_quota_print(struct seq_file *sf, + long period, long quota) +{ + if (quota < 0) + seq_puts(sf, "max"); + else + seq_printf(sf, "%ld", quota); + + seq_printf(sf, " %ld\n", period); +} + +/* caller should put the current value in *@periodp before calling */ +static int __maybe_unused cpu_period_quota_parse(char *buf, + u64 *periodp, u64 *quotap) +{ + char tok[21]; /* U64_MAX */ + + if (!sscanf(buf, "%s %llu", tok, periodp)) + return -EINVAL; + + *periodp *= NSEC_PER_USEC; + + if (sscanf(tok, "%llu", quotap)) + *quotap *= NSEC_PER_USEC; + else if (!strcmp(tok, "max")) + *quotap = RUNTIME_INF; + else + return -EINVAL; + + return 0; +} + +#ifdef CONFIG_CFS_BANDWIDTH +static int cpu_max_show(struct seq_file *sf, void *v) +{ + struct task_group *tg = css_tg(seq_css(sf)); + + cpu_period_quota_print(sf, tg_get_cfs_period(tg), tg_get_cfs_quota(tg)); + return 0; +} + +static ssize_t cpu_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct task_group *tg = css_tg(of_css(of)); + u64 period = tg_get_cfs_period(tg); + u64 quota; + int ret; + + ret = cpu_period_quota_parse(buf, &period, "a); + if (!ret) + ret = tg_set_cfs_bandwidth(tg, period, quota); + return ret ?: nbytes; +} +#endif + +static struct cftype cpu_files[] = { +#ifdef CONFIG_FAIR_GROUP_SCHED + { + .name = "weight", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = cpu_weight_read_u64, + .write_u64 = cpu_weight_write_u64, + }, + { + .name = "weight.nice", + .flags = CFTYPE_NOT_ON_ROOT, + .read_s64 = cpu_weight_nice_read_s64, + .write_s64 = cpu_weight_nice_write_s64, + }, +#endif +#ifdef CONFIG_CFS_BANDWIDTH + { + .name = "max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = cpu_max_show, + .write = cpu_max_write, + }, +#endif + { } /* 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, + .css_extra_stat_show = cpu_extra_stat_show, .fork = cpu_cgroup_fork, .can_attach = cpu_cgroup_can_attach, .attach = cpu_cgroup_attach, - .legacy_cftypes = cpu_files, + .legacy_cftypes = cpu_legacy_files, + .dfl_cftypes = cpu_files, .early_init = true, + .threaded = true, }; #endif /* CONFIG_CGROUP_SCHED */ |