diff options
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/Makefile | 1 | ||||
| -rw-r--r-- | kernel/sched/clock.c | 26 | ||||
| -rw-r--r-- | kernel/sched/core.c | 414 | ||||
| -rw-r--r-- | kernel/sched/cpuacct.c | 296 | ||||
| -rw-r--r-- | kernel/sched/cpuacct.h | 17 | ||||
| -rw-r--r-- | kernel/sched/cputime.c | 240 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 158 | ||||
| -rw-r--r-- | kernel/sched/features.h | 7 | ||||
| -rw-r--r-- | kernel/sched/idle_task.c | 17 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 244 | ||||
| -rw-r--r-- | kernel/sched/stats.c | 7 |
11 files changed, 889 insertions, 538 deletions
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index f06d249e103b..deaf90e4a1de 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -16,3 +16,4 @@ obj-$(CONFIG_SMP) += cpupri.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o +obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c index c685e31492df..c3ae1446461c 100644 --- a/kernel/sched/clock.c +++ b/kernel/sched/clock.c @@ -176,10 +176,36 @@ static u64 sched_clock_remote(struct sched_clock_data *scd) u64 this_clock, remote_clock; u64 *ptr, old_val, val; +#if BITS_PER_LONG != 64 +again: + /* + * Careful here: The local and the remote clock values need to + * be read out atomic as we need to compare the values and + * then update either the local or the remote side. So the + * cmpxchg64 below only protects one readout. + * + * We must reread via sched_clock_local() in the retry case on + * 32bit as an NMI could use sched_clock_local() via the + * tracer and hit between the readout of + * the low32bit and the high 32bit portion. + */ + this_clock = sched_clock_local(my_scd); + /* + * We must enforce atomic readout on 32bit, otherwise the + * update on the remote cpu can hit inbetween the readout of + * the low32bit and the high 32bit portion. + */ + remote_clock = cmpxchg64(&scd->clock, 0, 0); +#else + /* + * On 64bit the read of [my]scd->clock is atomic versus the + * update, so we can avoid the above 32bit dance. + */ sched_clock_local(my_scd); again: this_clock = my_scd->clock; remote_clock = scd->clock; +#endif /* * Use the opportunity that we have both locks diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 7f12624a393c..58453b8272fd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -512,11 +512,6 @@ static inline void init_hrtick(void) * the target CPU. */ #ifdef CONFIG_SMP - -#ifndef tsk_is_polling -#define tsk_is_polling(t) 0 -#endif - void resched_task(struct task_struct *p) { int cpu; @@ -549,7 +544,7 @@ void resched_cpu(int cpu) raw_spin_unlock_irqrestore(&rq->lock, flags); } -#ifdef CONFIG_NO_HZ +#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. @@ -587,7 +582,7 @@ unlock: * account when the CPU goes back to idle and evaluates the timer * wheel for the next timer event. */ -void wake_up_idle_cpu(int cpu) +static void wake_up_idle_cpu(int cpu) { struct rq *rq = cpu_rq(cpu); @@ -617,20 +612,56 @@ void wake_up_idle_cpu(int cpu) smp_send_reschedule(cpu); } +static bool wake_up_full_nohz_cpu(int cpu) +{ + if (tick_nohz_full_cpu(cpu)) { + if (cpu != smp_processor_id() || + tick_nohz_tick_stopped()) + smp_send_reschedule(cpu); + return true; + } + + return false; +} + +void wake_up_nohz_cpu(int cpu) +{ + if (!wake_up_full_nohz_cpu(cpu)) + wake_up_idle_cpu(cpu); +} + static inline bool got_nohz_idle_kick(void) { int cpu = smp_processor_id(); return idle_cpu(cpu) && test_bit(NOHZ_BALANCE_KICK, nohz_flags(cpu)); } -#else /* CONFIG_NO_HZ */ +#else /* CONFIG_NO_HZ_COMMON */ static inline bool got_nohz_idle_kick(void) { return false; } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ + +#ifdef CONFIG_NO_HZ_FULL +bool sched_can_stop_tick(void) +{ + struct rq *rq; + + rq = this_rq(); + + /* Make sure rq->nr_running update is visible after the IPI */ + smp_rmb(); + + /* More than one running task need preemption */ + if (rq->nr_running > 1) + return false; + + return true; +} +#endif /* CONFIG_NO_HZ_FULL */ void sched_avg_update(struct rq *rq) { @@ -1288,8 +1319,8 @@ static void ttwu_activate(struct rq *rq, struct task_struct *p, int en_flags) static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags) { - trace_sched_wakeup(p, true); check_preempt_curr(rq, p, wake_flags); + trace_sched_wakeup(p, true); p->state = TASK_RUNNING; #ifdef CONFIG_SMP @@ -1362,7 +1393,8 @@ static void sched_ttwu_pending(void) void scheduler_ipi(void) { - if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) + if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick() + && !tick_nohz_full_cpu(smp_processor_id())) return; /* @@ -1379,6 +1411,7 @@ void scheduler_ipi(void) * somewhat pessimize the simple resched case. */ irq_enter(); + tick_nohz_full_check(); sched_ttwu_pending(); /* @@ -1498,8 +1531,10 @@ static void try_to_wake_up_local(struct task_struct *p) { struct rq *rq = task_rq(p); - BUG_ON(rq != this_rq()); - BUG_ON(p == current); + if (WARN_ON_ONCE(rq != this_rq()) || + WARN_ON_ONCE(p == current)) + return; + lockdep_assert_held(&rq->lock); if (!raw_spin_trylock(&p->pi_lock)) { @@ -1858,6 +1893,8 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) kprobe_flush_task(prev); put_task_struct(prev); } + + tick_nohz_task_switch(current); } #ifdef CONFIG_SMP @@ -2121,7 +2158,7 @@ calc_load(unsigned long load, unsigned long exp, unsigned long active) return load >> FSHIFT; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * Handle NO_HZ for the global load-average. * @@ -2347,12 +2384,12 @@ static void calc_global_nohz(void) smp_wmb(); calc_load_idx++; } -#else /* !CONFIG_NO_HZ */ +#else /* !CONFIG_NO_HZ_COMMON */ static inline long calc_load_fold_idle(void) { return 0; } static inline void calc_global_nohz(void) { } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ /* * calc_load - update the avenrun load estimates 10 ticks after the @@ -2512,7 +2549,7 @@ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load, sched_avg_update(this_rq); } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * There is no sane way to deal with nohz on smp when using jiffies because the * cpu doing the jiffies update might drift wrt the cpu doing the jiffy reading @@ -2572,7 +2609,7 @@ void update_cpu_load_nohz(void) } raw_spin_unlock(&this_rq->lock); } -#endif /* CONFIG_NO_HZ */ +#endif /* CONFIG_NO_HZ_COMMON */ /* * Called from scheduler_tick() @@ -2699,8 +2736,35 @@ void scheduler_tick(void) rq->idle_balance = idle_cpu(cpu); trigger_load_balance(rq, cpu); #endif + rq_last_tick_reset(rq); } +#ifdef CONFIG_NO_HZ_FULL +/** + * scheduler_tick_max_deferment + * + * Keep at least one tick per second when a single + * active task is running because the scheduler doesn't + * yet completely support full dynticks environment. + * + * This makes sure that uptime, CFS vruntime, load + * balancing, etc... continue to move forward, even + * with a very low granularity. + */ +u64 scheduler_tick_max_deferment(void) +{ + struct rq *rq = this_rq(); + unsigned long next, now = ACCESS_ONCE(jiffies); + + next = rq->last_sched_tick + HZ; + + if (time_before_eq(next, now)) + return 0; + + return jiffies_to_usecs(next - now) * NSEC_PER_USEC; +} +#endif + notrace unsigned long get_parent_ip(unsigned long addr) { if (in_lock_functions(addr)) { @@ -2997,51 +3061,6 @@ void __sched schedule_preempt_disabled(void) preempt_disable(); } -#ifdef CONFIG_MUTEX_SPIN_ON_OWNER - -static inline bool owner_running(struct mutex *lock, struct task_struct *owner) -{ - if (lock->owner != owner) - return false; - - /* - * Ensure we emit the owner->on_cpu, dereference _after_ checking - * lock->owner still matches owner, if that fails, owner might - * point to free()d memory, if it still matches, the rcu_read_lock() - * ensures the memory stays valid. - */ - barrier(); - - return owner->on_cpu; -} - -/* - * Look out! "owner" is an entirely speculative pointer - * access and not reliable. - */ -int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner) -{ - if (!sched_feat(OWNER_SPIN)) - return 0; - - rcu_read_lock(); - while (owner_running(lock, owner)) { - if (need_resched()) - break; - - arch_mutex_cpu_relax(); - } - rcu_read_unlock(); - - /* - * We break out the loop above on need_resched() and when the - * owner changed, which is a sign for heavy contention. Return - * success only when lock->owner is NULL. - */ - return lock->owner == NULL; -} -#endif - #ifdef CONFIG_PREEMPT /* * this is the entry point to schedule() from in-kernel preemption @@ -3082,11 +3101,13 @@ EXPORT_SYMBOL(preempt_schedule); asmlinkage void __sched preempt_schedule_irq(void) { struct thread_info *ti = current_thread_info(); + enum ctx_state prev_state; /* Catch callers which need to be fixed */ BUG_ON(ti->preempt_count || !irqs_disabled()); - user_exit(); + prev_state = exception_enter(); + do { add_preempt_count(PREEMPT_ACTIVE); local_irq_enable(); @@ -3100,6 +3121,8 @@ asmlinkage void __sched preempt_schedule_irq(void) */ barrier(); } while (need_resched()); + + exception_exit(prev_state); } #endif /* CONFIG_PREEMPT */ @@ -4126,6 +4149,10 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) get_task_struct(p); rcu_read_unlock(); + if (p->flags & PF_NO_SETAFFINITY) { + retval = -EINVAL; + goto out_put_task; + } if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { retval = -ENOMEM; goto out_put_task; @@ -4626,6 +4653,7 @@ void sched_show_task(struct task_struct *p) task_pid_nr(p), ppid, (unsigned long)task_thread_info(p)->flags); + print_worker_info(KERN_INFO, p); show_stack(p, NULL); } @@ -4773,11 +4801,6 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) goto out; } - if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) { - ret = -EINVAL; - goto out; - } - do_set_cpus_allowed(p, new_mask); /* Can the task run on the task's current CPU? If so, we're done */ @@ -4999,7 +5022,7 @@ static void sd_free_ctl_entry(struct ctl_table **tablep) } static int min_load_idx = 0; -static int max_load_idx = CPU_LOAD_IDX_MAX; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; static void set_table_entry(struct ctl_table *entry, @@ -6248,7 +6271,7 @@ static void sched_init_numa(void) * 'level' contains the number of unique distances, excluding the * identity distance node_distance(i,i). * - * The sched_domains_nume_distance[] array includes the actual distance + * The sched_domains_numa_distance[] array includes the actual distance * numbers. */ @@ -6861,11 +6884,15 @@ int in_sched_functions(unsigned long addr) } #ifdef CONFIG_CGROUP_SCHED +/* + * Default task group. + * Every task in system belongs to this group at bootup. + */ struct task_group root_task_group; LIST_HEAD(task_groups); #endif -DECLARE_PER_CPU(cpumask_var_t, load_balance_tmpmask); +DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); void __init sched_init(void) { @@ -6902,7 +6929,7 @@ void __init sched_init(void) #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CPUMASK_OFFSTACK for_each_possible_cpu(i) { - per_cpu(load_balance_tmpmask, i) = (void *)ptr; + per_cpu(load_balance_mask, i) = (void *)ptr; ptr += cpumask_size(); } #endif /* CONFIG_CPUMASK_OFFSTACK */ @@ -6928,12 +6955,6 @@ void __init sched_init(void) #endif /* CONFIG_CGROUP_SCHED */ -#ifdef CONFIG_CGROUP_CPUACCT - root_cpuacct.cpustat = &kernel_cpustat; - root_cpuacct.cpuusage = alloc_percpu(u64); - /* Too early, not expected to fail */ - BUG_ON(!root_cpuacct.cpuusage); -#endif for_each_possible_cpu(i) { struct rq *rq; @@ -6997,9 +7018,12 @@ void __init sched_init(void) INIT_LIST_HEAD(&rq->cfs_tasks); rq_attach_root(rq, &def_root_domain); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON rq->nohz_flags = 0; #endif +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = 0; +#endif #endif init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); @@ -7455,7 +7479,7 @@ unlock: return err; } -int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +static int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) { u64 rt_runtime, rt_period; @@ -7467,7 +7491,7 @@ int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } -long sched_group_rt_runtime(struct task_group *tg) +static long sched_group_rt_runtime(struct task_group *tg) { u64 rt_runtime_us; @@ -7479,7 +7503,7 @@ long sched_group_rt_runtime(struct task_group *tg) return rt_runtime_us; } -int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) +static int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) { u64 rt_runtime, rt_period; @@ -7492,7 +7516,7 @@ int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) return tg_set_rt_bandwidth(tg, rt_period, rt_runtime); } -long sched_group_rt_period(struct task_group *tg) +static long sched_group_rt_period(struct task_group *tg) { u64 rt_period_us; @@ -7527,7 +7551,7 @@ static int sched_rt_global_constraints(void) return ret; } -int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) +static int sched_rt_can_attach(struct task_group *tg, struct task_struct *tsk) { /* Don't accept realtime tasks when there is no way for them to run */ if (rt_task(tsk) && tg->rt_bandwidth.rt_runtime == 0) @@ -8035,226 +8059,6 @@ struct cgroup_subsys cpu_cgroup_subsys = { #endif /* CONFIG_CGROUP_SCHED */ -#ifdef CONFIG_CGROUP_CPUACCT - -/* - * CPU accounting code for task groups. - * - * Based on the work by Paul Menage (menage@google.com) and Balbir Singh - * (balbir@in.ibm.com). - */ - -struct cpuacct root_cpuacct; - -/* create a new cpu accounting group */ -static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) -{ - struct cpuacct *ca; - - if (!cgrp->parent) - return &root_cpuacct.css; - - ca = kzalloc(sizeof(*ca), GFP_KERNEL); - if (!ca) - goto out; - - ca->cpuusage = alloc_percpu(u64); - if (!ca->cpuusage) - goto out_free_ca; - - ca->cpustat = alloc_percpu(struct kernel_cpustat); - if (!ca->cpustat) - goto out_free_cpuusage; - - return &ca->css; - -out_free_cpuusage: - free_percpu(ca->cpuusage); -out_free_ca: - kfree(ca); -out: - return ERR_PTR(-ENOMEM); -} - -/* destroy an existing cpu accounting group */ -static void cpuacct_css_free(struct cgroup *cgrp) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - - free_percpu(ca->cpustat); - free_percpu(ca->cpuusage); - kfree(ca); -} - -static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - u64 data; - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit read safe on 32-bit platforms. - */ - raw_spin_lock_irq(&cpu_rq(cpu)->lock); - data = *cpuusage; - raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - data = *cpuusage; -#endif - - return data; -} - -static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) -{ - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - -#ifndef CONFIG_64BIT - /* - * Take rq->lock to make 64-bit write safe on 32-bit platforms. - */ - raw_spin_lock_irq(&cpu_rq(cpu)->lock); - *cpuusage = val; - raw_spin_unlock_irq(&cpu_rq(cpu)->lock); -#else - *cpuusage = val; -#endif -} - -/* return total cpu usage (in nanoseconds) of a group */ -static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - u64 totalcpuusage = 0; - int i; - - for_each_present_cpu(i) - totalcpuusage += cpuacct_cpuusage_read(ca, i); - - return totalcpuusage; -} - -static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, - u64 reset) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int err = 0; - int i; - - if (reset) { - err = -EINVAL; - goto out; - } - - for_each_present_cpu(i) - cpuacct_cpuusage_write(ca, i, 0); - -out: - return err; -} - -static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, - struct seq_file *m) -{ - struct cpuacct *ca = cgroup_ca(cgroup); - u64 percpu; - int i; - - for_each_present_cpu(i) { - percpu = cpuacct_cpuusage_read(ca, i); - seq_printf(m, "%llu ", (unsigned long long) percpu); - } - seq_printf(m, "\n"); - return 0; -} - -static const char *cpuacct_stat_desc[] = { - [CPUACCT_STAT_USER] = "user", - [CPUACCT_STAT_SYSTEM] = "system", -}; - -static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, - struct cgroup_map_cb *cb) -{ - struct cpuacct *ca = cgroup_ca(cgrp); - int cpu; - s64 val = 0; - - for_each_online_cpu(cpu) { - struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); - val += kcpustat->cpustat[CPUTIME_USER]; - val += kcpustat->cpustat[CPUTIME_NICE]; - } - val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val); - - val = 0; - for_each_online_cpu(cpu) { - struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); - val += kcpustat->cpustat[CPUTIME_SYSTEM]; - val += kcpustat->cpustat[CPUTIME_IRQ]; - val += kcpustat->cpustat[CPUTIME_SOFTIRQ]; - } - - val = cputime64_to_clock_t(val); - cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); - - return 0; -} - -static struct cftype files[] = { - { - .name = "usage", - .read_u64 = cpuusage_read, - .write_u64 = cpuusage_write, - }, - { - .name = "usage_percpu", - .read_seq_string = cpuacct_percpu_seq_read, - }, - { - .name = "stat", - .read_map = cpuacct_stats_show, - }, - { } /* terminate */ -}; - -/* - * charge this task's execution time to its accounting group. - * - * called with rq->lock held. - */ -void cpuacct_charge(struct task_struct *tsk, u64 cputime) -{ - struct cpuacct *ca; - int cpu; - - if (unlikely(!cpuacct_subsys.active)) - return; - - cpu = task_cpu(tsk); - - rcu_read_lock(); - - ca = task_ca(tsk); - - for (; ca; ca = parent_ca(ca)) { - u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); - *cpuusage += cputime; - } - - rcu_read_unlock(); -} - -struct cgroup_subsys cpuacct_subsys = { - .name = "cpuacct", - .css_alloc = cpuacct_css_alloc, - .css_free = cpuacct_css_free, - .subsys_id = cpuacct_subsys_id, - .base_cftypes = files, -}; -#endif /* CONFIG_CGROUP_CPUACCT */ - void dump_cpu_task(int cpu) { pr_info("Task dump for CPU %d:\n", cpu); diff --git a/kernel/sched/cpuacct.c b/kernel/sched/cpuacct.c new file mode 100644 index 000000000000..dbb7e2cd95eb --- /dev/null +++ b/kernel/sched/cpuacct.c @@ -0,0 +1,296 @@ +#include <linux/cgroup.h> +#include <linux/slab.h> +#include <linux/percpu.h> +#include <linux/spinlock.h> +#include <linux/cpumask.h> +#include <linux/seq_file.h> +#include <linux/rcupdate.h> +#include <linux/kernel_stat.h> +#include <linux/err.h> + +#include "sched.h" + +/* + * CPU accounting code for task groups. + * + * Based on the work by Paul Menage (menage@google.com) and Balbir Singh + * (balbir@in.ibm.com). + */ + +/* Time spent by the tasks of the cpu accounting group executing in ... */ +enum cpuacct_stat_index { + CPUACCT_STAT_USER, /* ... user mode */ + CPUACCT_STAT_SYSTEM, /* ... kernel mode */ + + CPUACCT_STAT_NSTATS, +}; + +/* track cpu usage of a group of tasks and its child groups */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 __percpu *cpuusage; + struct kernel_cpustat __percpu *cpustat; +}; + +/* return cpu accounting group corresponding to this container */ +static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), + struct cpuacct, css); +} + +/* return cpu accounting group to which this task belongs */ +static inline struct cpuacct *task_ca(struct task_struct *tsk) +{ + return container_of(task_subsys_state(tsk, cpuacct_subsys_id), + struct cpuacct, css); +} + +static inline struct cpuacct *__parent_ca(struct cpuacct *ca) +{ + return cgroup_ca(ca->css.cgroup->parent); +} + +static inline struct cpuacct *parent_ca(struct cpuacct *ca) +{ + if (!ca->css.cgroup->parent) + return NULL; + return cgroup_ca(ca->css.cgroup->parent); +} + +static DEFINE_PER_CPU(u64, root_cpuacct_cpuusage); +static struct cpuacct root_cpuacct = { + .cpustat = &kernel_cpustat, + .cpuusage = &root_cpuacct_cpuusage, +}; + +/* create a new cpu accounting group */ +static struct cgroup_subsys_state *cpuacct_css_alloc(struct cgroup *cgrp) +{ + struct cpuacct *ca; + + if (!cgrp->parent) + return &root_cpuacct.css; + + ca = kzalloc(sizeof(*ca), GFP_KERNEL); + if (!ca) + goto out; + + ca->cpuusage = alloc_percpu(u64); + if (!ca->cpuusage) + goto out_free_ca; + + ca->cpustat = alloc_percpu(struct kernel_cpustat); + if (!ca->cpustat) + goto out_free_cpuusage; + + return &ca->css; + +out_free_cpuusage: + free_percpu(ca->cpuusage); +out_free_ca: + kfree(ca); +out: + return ERR_PTR(-ENOMEM); +} + +/* destroy an existing cpu accounting group */ +static void cpuacct_css_free(struct cgroup *cgrp) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + + free_percpu(ca->cpustat); + free_percpu(ca->cpuusage); + kfree(ca); +} + +static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + u64 data; + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit read safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + data = *cpuusage; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + data = *cpuusage; +#endif + + return data; +} + +static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) +{ + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + +#ifndef CONFIG_64BIT + /* + * Take rq->lock to make 64-bit write safe on 32-bit platforms. + */ + raw_spin_lock_irq(&cpu_rq(cpu)->lock); + *cpuusage = val; + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); +#else + *cpuusage = val; +#endif +} + +/* return total cpu usage (in nanoseconds) of a group */ +static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + u64 totalcpuusage = 0; + int i; + + for_each_present_cpu(i) + totalcpuusage += cpuacct_cpuusage_read(ca, i); + + return totalcpuusage; +} + +static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, + u64 reset) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + int err = 0; + int i; + + if (reset) { + err = -EINVAL; + goto out; + } + + for_each_present_cpu(i) + cpuacct_cpuusage_write(ca, i, 0); + +out: + return err; +} + +static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, + struct seq_file *m) +{ + struct cpuacct *ca = cgroup_ca(cgroup); + u64 percpu; + int i; + + for_each_present_cpu(i) { + percpu = cpuacct_cpuusage_read(ca, i); + seq_printf(m, "%llu ", (unsigned long long) percpu); + } + seq_printf(m, "\n"); + return 0; +} + +static const char * const cpuacct_stat_desc[] = { + [CPUACCT_STAT_USER] = "user", + [CPUACCT_STAT_SYSTEM] = "system", +}; + +static int cpuacct_stats_show(struct cgroup *cgrp, struct cftype *cft, + struct cgroup_map_cb *cb) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + int cpu; + s64 val = 0; + + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_USER]; + val += kcpustat->cpustat[CPUTIME_NICE]; + } + val = cputime64_to_clock_t(val); + cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_USER], val); + + val = 0; + for_each_online_cpu(cpu) { + struct kernel_cpustat *kcpustat = per_cpu_ptr(ca->cpustat, cpu); + val += kcpustat->cpustat[CPUTIME_SYSTEM]; + val += kcpustat->cpustat[CPUTIME_IRQ]; + val += kcpustat->cpustat[CPUTIME_SOFTIRQ]; + } + + val = cputime64_to_clock_t(val); + cb->fill(cb, cpuacct_stat_desc[CPUACCT_STAT_SYSTEM], val); + + return 0; +} + +static struct cftype files[] = { + { + .name = "usage", + .read_u64 = cpuusage_read, + .write_u64 = cpuusage_write, + }, + { + .name = "usage_percpu", + .read_seq_string = cpuacct_percpu_seq_read, + }, + { + .name = "stat", + .read_map = cpuacct_stats_show, + }, + { } /* terminate */ +}; + +/* + * charge this task's execution time to its accounting group. + * + * called with rq->lock held. + */ +void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ + struct cpuacct *ca; + int cpu; + + cpu = task_cpu(tsk); + + rcu_read_lock(); + + ca = task_ca(tsk); + + while (true) { + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); + *cpuusage += cputime; + + ca = parent_ca(ca); + if (!ca) + break; + } + + rcu_read_unlock(); +} + +/* + * Add user/system time to cpuacct. + * + * Note: it's the caller that updates the account of the root cgroup. + */ +void cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ + struct kernel_cpustat *kcpustat; + struct cpuacct *ca; + + rcu_read_lock(); + ca = task_ca(p); + while (ca != &root_cpuacct) { + kcpustat = this_cpu_ptr(ca->cpustat); + kcpustat->cpustat[index] += val; + ca = __parent_ca(ca); + } + rcu_read_unlock(); +} + +struct cgroup_subsys cpuacct_subsys = { + .name = "cpuacct", + .css_alloc = cpuacct_css_alloc, + .css_free = cpuacct_css_free, + .subsys_id = cpuacct_subsys_id, + .base_cftypes = files, + .early_init = 1, +}; diff --git a/kernel/sched/cpuacct.h b/kernel/sched/cpuacct.h new file mode 100644 index 000000000000..ed605624a5e7 --- /dev/null +++ b/kernel/sched/cpuacct.h @@ -0,0 +1,17 @@ +#ifdef CONFIG_CGROUP_CPUACCT + +extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); +extern void cpuacct_account_field(struct task_struct *p, int index, u64 val); + +#else + +static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ +} + +static inline void +cpuacct_account_field(struct task_struct *p, int index, u64 val) +{ +} + +#endif diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index ed12cbb135f4..cc2dc3eea8a3 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -115,10 +115,6 @@ static int irqtime_account_si_update(void) static inline void task_group_account_field(struct task_struct *p, int index, u64 tmp) { -#ifdef CONFIG_CGROUP_CPUACCT - struct kernel_cpustat *kcpustat; - struct cpuacct *ca; -#endif /* * Since all updates are sure to touch the root cgroup, we * get ourselves ahead and touch it first. If the root cgroup @@ -127,19 +123,7 @@ static inline void task_group_account_field(struct task_struct *p, int index, */ __get_cpu_var(kernel_cpustat).cpustat[index] += tmp; -#ifdef CONFIG_CGROUP_CPUACCT - if (unlikely(!cpuacct_subsys.active)) - return; - - rcu_read_lock(); - ca = task_ca(p); - while (ca && (ca != &root_cpuacct)) { - kcpustat = this_cpu_ptr(ca->cpustat); - kcpustat->cpustat[index] += tmp; - ca = parent_ca(ca); - } - rcu_read_unlock(); -#endif + cpuacct_account_field(p, index, tmp); } /* @@ -310,7 +294,7 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) t = tsk; do { - task_cputime(tsk, &utime, &stime); + task_cputime(t, &utime, &stime); times->utime += utime; times->stime += stime; times->sum_exec_runtime += task_sched_runtime(t); @@ -388,7 +372,84 @@ static inline void irqtime_account_process_tick(struct task_struct *p, int user_ struct rq *rq) {} #endif /* CONFIG_IRQ_TIME_ACCOUNTING */ -#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING + +#ifndef __ARCH_HAS_VTIME_TASK_SWITCH +void vtime_task_switch(struct task_struct *prev) +{ + if (!vtime_accounting_enabled()) + return; + + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + vtime_account_system(prev); + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + vtime_account_user(prev); +#endif + arch_vtime_task_switch(prev); +} +#endif + +/* + * Archs that account the whole time spent in the idle task + * (outside irq) as idle time can rely on this and just implement + * vtime_account_system() and vtime_account_idle(). Archs that + * have other meaning of the idle time (s390 only includes the + * time spent by the CPU when it's in low power mode) must override + * vtime_account(). + */ +#ifndef __ARCH_HAS_VTIME_ACCOUNT +void vtime_account_irq_enter(struct task_struct *tsk) +{ + if (!vtime_accounting_enabled()) + return; + + if (!in_interrupt()) { + /* + * If we interrupted user, context_tracking_in_user() + * is 1 because the context tracking don't hook + * on irq entry/exit. This way we know if + * we need to flush user time on kernel entry. + */ + if (context_tracking_in_user()) { + vtime_account_user(tsk); + return; + } + + if (is_idle_task(tsk)) { + vtime_account_idle(tsk); + return; + } + } + vtime_account_system(tsk); +} +EXPORT_SYMBOL_GPL(vtime_account_irq_enter); +#endif /* __ARCH_HAS_VTIME_ACCOUNT */ +#endif /* CONFIG_VIRT_CPU_ACCOUNTING */ + + +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} + +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} +#else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ /* * Account a single tick of cpu time. * @p: the process that the cpu time gets accounted to @@ -443,96 +504,50 @@ void account_idle_ticks(unsigned long ticks) account_idle_time(jiffies_to_cputime(ticks)); } -#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ - -/* - * Use precise platform statistics if available: - */ -#ifdef CONFIG_VIRT_CPU_ACCOUNTING -void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - *ut = p->utime; - *st = p->stime; -} - -void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) -{ - struct task_cputime cputime; - - thread_group_cputime(p, &cputime); - - *ut = cputime.utime; - *st = cputime.stime; -} - -#ifndef __ARCH_HAS_VTIME_TASK_SWITCH -void vtime_task_switch(struct task_struct *prev) -{ - if (!vtime_accounting_enabled()) - return; - - if (is_idle_task(prev)) - vtime_account_idle(prev); - else - vtime_account_system(prev); - -#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE - vtime_account_user(prev); -#endif - arch_vtime_task_switch(prev); -} -#endif /* - * Archs that account the whole time spent in the idle task - * (outside irq) as idle time can rely on this and just implement - * vtime_account_system() and vtime_account_idle(). Archs that - * have other meaning of the idle time (s390 only includes the - * time spent by the CPU when it's in low power mode) must override - * vtime_account(). + * Perform (stime * rtime) / total, but avoid multiplication overflow by + * loosing precision when the numbers are big. */ -#ifndef __ARCH_HAS_VTIME_ACCOUNT -void vtime_account_irq_enter(struct task_struct *tsk) +static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) { - if (!vtime_accounting_enabled()) - return; + u64 scaled; - if (!in_interrupt()) { - /* - * If we interrupted user, context_tracking_in_user() - * is 1 because the context tracking don't hook - * on irq entry/exit. This way we know if - * we need to flush user time on kernel entry. - */ - if (context_tracking_in_user()) { - vtime_account_user(tsk); - return; + for (;;) { + /* Make sure "rtime" is the bigger of stime/rtime */ + if (stime > rtime) { + u64 tmp = rtime; rtime = stime; stime = tmp; } - if (is_idle_task(tsk)) { - vtime_account_idle(tsk); - return; - } - } - vtime_account_system(tsk); -} -EXPORT_SYMBOL_GPL(vtime_account_irq_enter); -#endif /* __ARCH_HAS_VTIME_ACCOUNT */ + /* Make sure 'total' fits in 32 bits */ + if (total >> 32) + goto drop_precision; -#else /* !CONFIG_VIRT_CPU_ACCOUNTING */ + /* Does rtime (and thus stime) fit in 32 bits? */ + if (!(rtime >> 32)) + break; -static cputime_t scale_stime(cputime_t stime, cputime_t rtime, cputime_t total) -{ - u64 temp = (__force u64) rtime; + /* Can we just balance rtime/stime rather than dropping bits? */ + if (stime >> 31) + goto drop_precision; - temp *= (__force u64) stime; + /* We can grow stime and shrink rtime and try to make them both fit */ + stime <<= 1; + rtime >>= 1; + continue; - if (sizeof(cputime_t) == 4) - temp = div_u64(temp, (__force u32) total); - else - temp = div64_u64(temp, (__force u64) total); +drop_precision: + /* We drop from rtime, it has more bits than stime */ + rtime >>= 1; + total >>= 1; + } - return (__force cputime_t) temp; + /* + * Make sure gcc understands that this is a 32x32->64 multiply, + * followed by a 64/32->64 divide. + */ + scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total); + return (__force cputime_t) scaled; } /* @@ -543,7 +558,13 @@ static void cputime_adjust(struct task_cputime *curr, struct cputime *prev, cputime_t *ut, cputime_t *st) { - cputime_t rtime, stime, total; + cputime_t rtime, stime, utime, total; + + if (vtime_accounting_enabled()) { + *ut = curr->utime; + *st = curr->stime; + return; + } stime = curr->stime; total = stime + curr->utime; @@ -560,10 +581,22 @@ static void cputime_adjust(struct task_cputime *curr, */ rtime = nsecs_to_cputime(curr->sum_exec_runtime); - if (total) - stime = scale_stime(stime, rtime, total); - else + /* + * Update userspace visible utime/stime values only if actual execution + * time is bigger than already exported. Note that can happen, that we + * provided bigger values due to scaling inaccuracy on big numbers. + */ + if (prev->stime + prev->utime >= rtime) + goto out; + + if (total) { + stime = scale_stime((__force u64)stime, + (__force u64)rtime, (__force u64)total); + utime = rtime - stime; + } else { stime = rtime; + utime = 0; + } /* * If the tick based count grows faster than the scheduler one, @@ -571,8 +604,9 @@ static void cputime_adjust(struct task_cputime *curr, * Let's enforce monotonicity. */ prev->stime = max(prev->stime, stime); - prev->utime = max(prev->utime, rtime - prev->stime); + prev->utime = max(prev->utime, utime); +out: *ut = prev->utime; *st = prev->stime; } @@ -597,7 +631,7 @@ void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime thread_group_cputime(p, &cputime); cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); } -#endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ +#endif /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN static unsigned long long vtime_delta(struct task_struct *tsk) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7a33e5986fc5..c61a614465c8 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -431,13 +431,13 @@ void account_cfs_rq_runtime(struct cfs_rq *cfs_rq, unsigned long delta_exec); * Scheduling class tree data structure manipulation methods: */ -static inline u64 max_vruntime(u64 min_vruntime, u64 vruntime) +static inline u64 max_vruntime(u64 max_vruntime, u64 vruntime) { - s64 delta = (s64)(vruntime - min_vruntime); + s64 delta = (s64)(vruntime - max_vruntime); if (delta > 0) - min_vruntime = vruntime; + max_vruntime = vruntime; - return min_vruntime; + return max_vruntime; } static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime) @@ -473,6 +473,7 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq) vruntime = min_vruntime(vruntime, se->vruntime); } + /* ensure we never gain time by being placed backwards. */ cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime); #ifndef CONFIG_64BIT smp_wmb(); @@ -652,7 +653,7 @@ static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se) } /* - * We calculate the vruntime slice of a to be inserted task + * We calculate the vruntime slice of a to-be-inserted task. * * vs = s/w */ @@ -1562,6 +1563,27 @@ static inline void dequeue_entity_load_avg(struct cfs_rq *cfs_rq, se->avg.decay_count = atomic64_read(&cfs_rq->decay_counter); } /* migrations, e.g. sleep=0 leave decay_count == 0 */ } + +/* + * Update the rq's load with the elapsed running time before entering + * idle. if the last scheduled task is not a CFS task, idle_enter will + * be the only way to update the runnable statistic. + */ +void idle_enter_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 1); +} + +/* + * Update the rq's load with the elapsed idle time before a task is + * scheduled. if the newly scheduled task is not a CFS task, idle_exit will + * be the only way to update the runnable statistic. + */ +void idle_exit_fair(struct rq *this_rq) +{ + update_rq_runnable_avg(this_rq, 0); +} + #else static inline void update_entity_load_avg(struct sched_entity *se, int update_cfs_rq) {} @@ -3874,12 +3896,16 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) int tsk_cache_hot = 0; /* * We do not migrate tasks that are: - * 1) running (obviously), or + * 1) throttled_lb_pair, or * 2) cannot be migrated to this CPU due to cpus_allowed, or - * 3) are cache-hot on their current CPU. + * 3) running (obviously), or + * 4) are cache-hot on their current CPU. */ + 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))) { - int new_dst_cpu; + int cpu; schedstat_inc(p, se.statistics.nr_failed_migrations_affine); @@ -3894,12 +3920,15 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) if (!env->dst_grpmask || (env->flags & LBF_SOME_PINNED)) return 0; - new_dst_cpu = cpumask_first_and(env->dst_grpmask, - tsk_cpus_allowed(p)); - if (new_dst_cpu < nr_cpu_ids) { - env->flags |= LBF_SOME_PINNED; - env->new_dst_cpu = new_dst_cpu; + /* 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))) { + env->flags |= LBF_SOME_PINNED; + env->new_dst_cpu = cpu; + break; + } } + return 0; } @@ -3920,20 +3949,17 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env) tsk_cache_hot = task_hot(p, env->src_rq->clock_task, env->sd); if (!tsk_cache_hot || env->sd->nr_balance_failed > env->sd->cache_nice_tries) { -#ifdef CONFIG_SCHEDSTATS + if (tsk_cache_hot) { schedstat_inc(env->sd, lb_hot_gained[env->idle]); schedstat_inc(p, se.statistics.nr_forced_migrations); } -#endif + return 1; } - if (tsk_cache_hot) { - schedstat_inc(p, se.statistics.nr_failed_migrations_hot); - return 0; - } - return 1; + schedstat_inc(p, se.statistics.nr_failed_migrations_hot); + return 0; } /* @@ -3948,9 +3974,6 @@ static int move_one_task(struct lb_env *env) struct task_struct *p, *n; list_for_each_entry_safe(p, n, &env->src_rq->cfs_tasks, se.group_node) { - if (throttled_lb_pair(task_group(p), env->src_rq->cpu, env->dst_cpu)) - continue; - if (!can_migrate_task(p, env)) continue; @@ -4002,7 +4025,7 @@ static int move_tasks(struct lb_env *env) break; } - if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu)) + if (!can_migrate_task(p, env)) goto next; load = task_h_load(p); @@ -4013,9 +4036,6 @@ static int move_tasks(struct lb_env *env) if ((load / 2) > env->imbalance) goto next; - if (!can_migrate_task(p, env)) - goto next; - move_task(p, env); pulled++; env->imbalance -= load; @@ -4245,7 +4265,7 @@ static inline int get_sd_load_idx(struct sched_domain *sd, return load_idx; } -unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) { return SCHED_POWER_SCALE; } @@ -4255,7 +4275,7 @@ unsigned long __weak arch_scale_freq_power(struct sched_domain *sd, int cpu) return default_scale_freq_power(sd, cpu); } -unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +static unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) { unsigned long weight = sd->span_weight; unsigned long smt_gain = sd->smt_gain; @@ -4270,7 +4290,7 @@ unsigned long __weak arch_scale_smt_power(struct sched_domain *sd, int cpu) return default_scale_smt_power(sd, cpu); } -unsigned long scale_rt_power(int cpu) +static unsigned long scale_rt_power(int cpu) { struct rq *rq = cpu_rq(cpu); u64 total, available, age_stamp, avg; @@ -4960,7 +4980,7 @@ static struct rq *find_busiest_queue(struct lb_env *env, #define MAX_PINNED_INTERVAL 512 /* Working cpumask for load_balance and load_balance_newidle. */ -DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); +DEFINE_PER_CPU(cpumask_var_t, load_balance_mask); static int need_active_balance(struct lb_env *env) { @@ -4991,11 +5011,10 @@ static int load_balance(int this_cpu, struct rq *this_rq, int *balance) { int ld_moved, cur_ld_moved, active_balance = 0; - int lb_iterations, max_lb_iterations; struct sched_group *group; struct rq *busiest; unsigned long flags; - struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); + struct cpumask *cpus = __get_cpu_var(load_balance_mask); struct lb_env env = { .sd = sd, @@ -5007,8 +5026,14 @@ static int load_balance(int this_cpu, struct rq *this_rq, .cpus = cpus, }; + /* + * For NEWLY_IDLE load_balancing, we don't need to consider + * other cpus in our group + */ + if (idle == CPU_NEWLY_IDLE) + env.dst_grpmask = NULL; + cpumask_copy(cpus, cpu_active_mask); - max_lb_iterations = cpumask_weight(env.dst_grpmask); schedstat_inc(sd, lb_count[idle]); @@ -5034,7 +5059,6 @@ redo: schedstat_add(sd, lb_imbalance[idle], env.imbalance); ld_moved = 0; - lb_iterations = 1; if (busiest->nr_running > 1) { /* * Attempt to move tasks. If find_busiest_group has found @@ -5061,17 +5085,17 @@ more_balance: double_rq_unlock(env.dst_rq, busiest); local_irq_restore(flags); - if (env.flags & LBF_NEED_BREAK) { - env.flags &= ~LBF_NEED_BREAK; - goto more_balance; - } - /* * some other cpu did the load balance for us. */ if (cur_ld_moved && env.dst_cpu != smp_processor_id()) resched_cpu(env.dst_cpu); + if (env.flags & LBF_NEED_BREAK) { + env.flags &= ~LBF_NEED_BREAK; + goto more_balance; + } + /* * Revisit (affine) tasks on src_cpu that couldn't be moved to * us and move them to an alternate dst_cpu in our sched_group @@ -5091,14 +5115,17 @@ more_balance: * moreover subsequent load balance cycles should correct the * excess load moved. */ - if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0 && - lb_iterations++ < max_lb_iterations) { + if ((env.flags & LBF_SOME_PINNED) && env.imbalance > 0) { env.dst_rq = cpu_rq(env.new_dst_cpu); env.dst_cpu = env.new_dst_cpu; env.flags &= ~LBF_SOME_PINNED; env.loop = 0; env.loop_break = sched_nr_migrate_break; + + /* Prevent to re-select dst_cpu via env's cpus */ + cpumask_clear_cpu(env.dst_cpu, env.cpus); + /* * Go back to "more_balance" rather than "redo" since we * need to continue with same src_cpu. @@ -5219,8 +5246,6 @@ void idle_balance(int this_cpu, struct rq *this_rq) if (this_rq->avg_idle < sysctl_sched_migration_cost) return; - update_rq_runnable_avg(this_rq, 1); - /* * Drop the rq->lock, but keep IRQ/preempt disabled. */ @@ -5330,7 +5355,7 @@ out_unlock: return 0; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* * idle load balancing details * - When one of the busy CPUs notice that there may be an idle rebalancing @@ -5395,13 +5420,16 @@ static inline void set_cpu_sd_state_busy(void) struct sched_domain *sd; int cpu = smp_processor_id(); - if (!test_bit(NOHZ_IDLE, nohz_flags(cpu))) - return; - clear_bit(NOHZ_IDLE, nohz_flags(cpu)); - rcu_read_lock(); - for_each_domain(cpu, sd) + sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); + + if (!sd || !sd->nohz_idle) + goto unlock; + sd->nohz_idle = 0; + + for (; sd; sd = sd->parent) atomic_inc(&sd->groups->sgp->nr_busy_cpus); +unlock: rcu_read_unlock(); } @@ -5410,13 +5438,16 @@ void set_cpu_sd_state_idle(void) struct sched_domain *sd; int cpu = smp_processor_id(); - if (test_bit(NOHZ_IDLE, nohz_flags(cpu))) - return; - set_bit(NOHZ_IDLE, nohz_flags(cpu)); - rcu_read_lock(); - for_each_domain(cpu, sd) + sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); + + if (!sd || sd->nohz_idle) + goto unlock; + sd->nohz_idle = 1; + + for (; sd; sd = sd->parent) atomic_dec(&sd->groups->sgp->nr_busy_cpus); +unlock: rcu_read_unlock(); } @@ -5468,7 +5499,7 @@ void update_max_interval(void) * It checks each scheduling domain to see if it is due to be balanced, * and initiates a balancing operation if so. * - * Balancing parameters are set up in arch_init_sched_domains. + * Balancing parameters are set up in init_sched_domains. */ static void rebalance_domains(int cpu, enum cpu_idle_type idle) { @@ -5506,10 +5537,11 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (time_after_eq(jiffies, sd->last_balance + interval)) { if (load_balance(cpu, rq, sd, idle, &balance)) { /* - * We've pulled tasks over so either we're no - * longer idle. + * The LBF_SOME_PINNED logic could have changed + * env->dst_cpu, so we can't know our idle + * state even if we migrated tasks. Update it. */ - idle = CPU_NOT_IDLE; + idle = idle_cpu(cpu) ? CPU_IDLE : CPU_NOT_IDLE; } sd->last_balance = jiffies; } @@ -5540,9 +5572,9 @@ out: rq->next_balance = next_balance; } -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON /* - * In CONFIG_NO_HZ case, the idle balance kickee will do the + * In CONFIG_NO_HZ_COMMON case, the idle balance kickee will do the * rebalancing for all the cpus for whom scheduler ticks are stopped. */ static void nohz_idle_balance(int this_cpu, enum cpu_idle_type idle) @@ -5685,7 +5717,7 @@ void trigger_load_balance(struct rq *rq, int cpu) if (time_after_eq(jiffies, rq->next_balance) && likely(!on_null_domain(cpu))) raise_softirq(SCHED_SOFTIRQ); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON if (nohz_kick_needed(rq, cpu) && likely(!on_null_domain(cpu))) nohz_balancer_kick(cpu); #endif @@ -6155,7 +6187,7 @@ __init void init_sched_fair_class(void) #ifdef CONFIG_SMP open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON nohz.next_balance = jiffies; zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); cpu_notifier(sched_ilb_notifier, 0); diff --git a/kernel/sched/features.h b/kernel/sched/features.h index 1ad1d2b5395f..99399f8e4799 100644 --- a/kernel/sched/features.h +++ b/kernel/sched/features.h @@ -46,13 +46,6 @@ SCHED_FEAT(DOUBLE_TICK, false) SCHED_FEAT(LB_BIAS, true) /* - * Spin-wait on mutex acquisition when the mutex owner is running on - * another cpu -- assumes that when the owner is running, it will soon - * release the lock. Decreases scheduling overhead. - */ -SCHED_FEAT(OWNER_SPIN, true) - -/* * Decrement CPU power based on time not spent running tasks */ SCHED_FEAT(NONTASK_POWER, true) diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c index b6baf370cae9..d8da01008d39 100644 --- a/kernel/sched/idle_task.c +++ b/kernel/sched/idle_task.c @@ -13,6 +13,17 @@ select_task_rq_idle(struct task_struct *p, int sd_flag, int flags) { return task_cpu(p); /* IDLE tasks as never migrated */ } + +static void pre_schedule_idle(struct rq *rq, struct task_struct *prev) +{ + idle_exit_fair(rq); + rq_last_tick_reset(rq); +} + +static void post_schedule_idle(struct rq *rq) +{ + idle_enter_fair(rq); +} #endif /* CONFIG_SMP */ /* * Idle tasks are unconditionally rescheduled: @@ -25,6 +36,10 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl static struct task_struct *pick_next_task_idle(struct rq *rq) { schedstat_inc(rq, sched_goidle); +#ifdef CONFIG_SMP + /* Trigger the post schedule to do an idle_enter for CFS */ + rq->post_schedule = 1; +#endif return rq->idle; } @@ -86,6 +101,8 @@ const struct sched_class idle_sched_class = { #ifdef CONFIG_SMP .select_task_rq = select_task_rq_idle, + .pre_schedule = pre_schedule_idle, + .post_schedule = post_schedule_idle, #endif .set_curr_task = set_curr_task_idle, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index cc03cfdf469f..ce39224d6155 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -5,8 +5,10 @@ #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/stop_machine.h> +#include <linux/tick.h> #include "cpupri.h" +#include "cpuacct.h" extern __read_mostly int scheduler_running; @@ -33,6 +35,31 @@ extern __read_mostly int scheduler_running; */ #define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) +/* + * Increase resolution of nice-level calculations for 64-bit architectures. + * The extra resolution improves shares distribution and load balancing of + * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup + * hierarchies, especially on larger systems. This is not a user-visible change + * and does not change the user-interface for setting shares/weights. + * + * We increase resolution only if we have enough bits to allow this increased + * resolution (i.e. BITS_PER_LONG > 32). The costs for increasing resolution + * when BITS_PER_LONG <= 32 are pretty high and the returns do not justify the + * increased costs. + */ +#if 0 /* BITS_PER_LONG > 32 -- currently broken: it increases power usage under light load */ +# define SCHED_LOAD_RESOLUTION 10 +# define scale_load(w) ((w) << SCHED_LOAD_RESOLUTION) +# define scale_load_down(w) ((w) >> SCHED_LOAD_RESOLUTION) +#else +# define SCHED_LOAD_RESOLUTION 0 +# define scale_load(w) (w) +# define scale_load_down(w) (w) +#endif + +#define SCHED_LOAD_SHIFT (10 + SCHED_LOAD_RESOLUTION) +#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) + #define NICE_0_LOAD SCHED_LOAD_SCALE #define NICE_0_SHIFT SCHED_LOAD_SHIFT @@ -154,11 +181,6 @@ struct task_group { #define MAX_SHARES (1UL << 18) #endif -/* Default task group. - * Every task in system belong to this group at bootup. - */ -extern struct task_group root_task_group; - typedef int (*tg_visitor)(struct task_group *, void *); extern int walk_tg_tree_from(struct task_group *from, @@ -196,6 +218,18 @@ extern void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, struct sched_rt_entity *rt_se, int cpu, struct sched_rt_entity *parent); +extern struct task_group *sched_create_group(struct task_group *parent); +extern void sched_online_group(struct task_group *tg, + struct task_group *parent); +extern void sched_destroy_group(struct task_group *tg); +extern void sched_offline_group(struct task_group *tg); + +extern void sched_move_task(struct task_struct *tsk); + +#ifdef CONFIG_FAIR_GROUP_SCHED +extern int sched_group_set_shares(struct task_group *tg, unsigned long shares); +#endif + #else /* CONFIG_CGROUP_SCHED */ struct cfs_bandwidth { }; @@ -372,10 +406,13 @@ struct rq { #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; unsigned long last_load_update_tick; -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON u64 nohz_stamp; unsigned long nohz_flags; #endif +#ifdef CONFIG_NO_HZ_FULL + unsigned long last_sched_tick; +#endif int skip_clock_update; /* capture load from *all* tasks on this cpu: */ @@ -547,6 +584,62 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag) DECLARE_PER_CPU(struct sched_domain *, sd_llc); DECLARE_PER_CPU(int, sd_llc_id); +struct sched_group_power { + atomic_t ref; + /* + * CPU power of this group, SCHED_LOAD_SCALE being max power for a + * single CPU. + */ + unsigned int power, power_orig; + unsigned long next_update; + /* + * Number of busy cpus in this group. + */ + atomic_t nr_busy_cpus; + + unsigned long cpumask[0]; /* iteration mask */ +}; + +struct sched_group { + struct sched_group *next; /* Must be a circular list */ + atomic_t ref; + + unsigned int group_weight; + struct sched_group_power *sgp; + + /* + * The CPUs this group covers. + * + * NOTE: this field is variable length. (Allocated dynamically + * by attaching extra space to the end of the structure, + * depending on how many CPUs the kernel has booted up with) + */ + unsigned long cpumask[0]; +}; + +static inline struct cpumask *sched_group_cpus(struct sched_group *sg) +{ + return to_cpumask(sg->cpumask); +} + +/* + * cpumask masking which cpus in the group are allowed to iterate up the domain + * tree. + */ +static inline struct cpumask *sched_group_mask(struct sched_group *sg) +{ + return to_cpumask(sg->sgp->cpumask); +} + +/** + * group_first_cpu - Returns the first cpu in the cpumask of a sched_group. + * @group: The group whose first cpu is to be returned. + */ +static inline unsigned int group_first_cpu(struct sched_group *group) +{ + return cpumask_first(sched_group_cpus(group)); +} + extern int group_balance_cpu(struct sched_group *sg); #endif /* CONFIG_SMP */ @@ -784,6 +877,12 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) } #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ +#define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x4 /* internal use, task got migrated */ static inline void update_load_add(struct load_weight *lw, unsigned long inc) { @@ -856,14 +955,61 @@ static const u32 prio_to_wmult[40] = { /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, }; -/* Time spent by the tasks of the cpu accounting group executing in ... */ -enum cpuacct_stat_index { - CPUACCT_STAT_USER, /* ... user mode */ - CPUACCT_STAT_SYSTEM, /* ... kernel mode */ +#define ENQUEUE_WAKEUP 1 +#define ENQUEUE_HEAD 2 +#ifdef CONFIG_SMP +#define ENQUEUE_WAKING 4 /* sched_class::task_waking was called */ +#else +#define ENQUEUE_WAKING 0 +#endif - CPUACCT_STAT_NSTATS, -}; +#define DEQUEUE_SLEEP 1 +struct sched_class { + const struct sched_class *next; + + void (*enqueue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*dequeue_task) (struct rq *rq, struct task_struct *p, int flags); + void (*yield_task) (struct rq *rq); + bool (*yield_to_task) (struct rq *rq, struct task_struct *p, bool preempt); + + void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags); + + struct task_struct * (*pick_next_task) (struct rq *rq); + void (*put_prev_task) (struct rq *rq, struct task_struct *p); + +#ifdef CONFIG_SMP + int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags); + void (*migrate_task_rq)(struct task_struct *p, int next_cpu); + + void (*pre_schedule) (struct rq *this_rq, struct task_struct *task); + void (*post_schedule) (struct rq *this_rq); + void (*task_waking) (struct task_struct *task); + void (*task_woken) (struct rq *this_rq, struct task_struct *task); + + void (*set_cpus_allowed)(struct task_struct *p, + const struct cpumask *newmask); + + void (*rq_online)(struct rq *rq); + void (*rq_offline)(struct rq *rq); +#endif + + void (*set_curr_task) (struct rq *rq); + void (*task_tick) (struct rq *rq, struct task_struct *p, int queued); + void (*task_fork) (struct task_struct *p); + + void (*switched_from) (struct rq *this_rq, struct task_struct *task); + void (*switched_to) (struct rq *this_rq, struct task_struct *task); + void (*prio_changed) (struct rq *this_rq, struct task_struct *task, + int oldprio); + + unsigned int (*get_rr_interval) (struct rq *rq, + struct task_struct *task); + +#ifdef CONFIG_FAIR_GROUP_SCHED + void (*task_move_group) (struct task_struct *p, int on_rq); +#endif +}; #define sched_class_highest (&stop_sched_class) #define for_each_class(class) \ @@ -877,9 +1023,23 @@ extern const struct sched_class idle_sched_class; #ifdef CONFIG_SMP +extern void update_group_power(struct sched_domain *sd, int cpu); + extern void trigger_load_balance(struct rq *rq, int cpu); extern void idle_balance(int this_cpu, struct rq *this_rq); +/* + * Only depends on SMP, FAIR_GROUP_SCHED may be removed when runnable_avg + * becomes useful in lb + */ +#if defined(CONFIG_FAIR_GROUP_SCHED) +extern void idle_enter_fair(struct rq *this_rq); +extern void idle_exit_fair(struct rq *this_rq); +#else +static inline void idle_enter_fair(struct rq *this_rq) {} +static inline void idle_exit_fair(struct rq *this_rq) {} +#endif + #else /* CONFIG_SMP */ static inline void idle_balance(int cpu, struct rq *rq) @@ -891,7 +1051,6 @@ static inline void idle_balance(int cpu, struct rq *rq) extern void sysrq_sched_debug_show(void); extern void sched_init_granularity(void); extern void update_max_interval(void); -extern void update_group_power(struct sched_domain *sd, int cpu); extern int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu); extern void init_sched_rt_class(void); extern void init_sched_fair_class(void); @@ -904,45 +1063,6 @@ extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime extern void update_idle_cpu_load(struct rq *this_rq); -#ifdef CONFIG_CGROUP_CPUACCT -#include <linux/cgroup.h> -/* track cpu usage of a group of tasks and its child groups */ -struct cpuacct { - struct cgroup_subsys_state css; - /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 __percpu *cpuusage; - struct kernel_cpustat __percpu *cpustat; -}; - -extern struct cgroup_subsys cpuacct_subsys; -extern struct cpuacct root_cpuacct; - -/* return cpu accounting group corresponding to this container */ -static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) -{ - return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), - struct cpuacct, css); -} - -/* return cpu accounting group to which this task belongs */ -static inline struct cpuacct *task_ca(struct task_struct *tsk) -{ - return container_of(task_subsys_state(tsk, cpuacct_subsys_id), - struct cpuacct, css); -} - -static inline struct cpuacct *parent_ca(struct cpuacct *ca) -{ - if (!ca || !ca->css.cgroup->parent) - return NULL; - return cgroup_ca(ca->css.cgroup->parent); -} - -extern void cpuacct_charge(struct task_struct *tsk, u64 cputime); -#else -static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} -#endif - #ifdef CONFIG_PARAVIRT static inline u64 steal_ticks(u64 steal) { @@ -956,6 +1076,16 @@ static inline u64 steal_ticks(u64 steal) static inline void inc_nr_running(struct rq *rq) { rq->nr_running++; + +#ifdef CONFIG_NO_HZ_FULL + if (rq->nr_running == 2) { + if (tick_nohz_full_cpu(rq->cpu)) { + /* Order rq->nr_running write against the IPI */ + smp_wmb(); + smp_send_reschedule(rq->cpu); + } + } +#endif } static inline void dec_nr_running(struct rq *rq) @@ -963,6 +1093,13 @@ static inline void dec_nr_running(struct rq *rq) rq->nr_running--; } +static inline void rq_last_tick_reset(struct rq *rq) +{ +#ifdef CONFIG_NO_HZ_FULL + rq->last_sched_tick = jiffies; +#endif +} + extern void update_rq_clock(struct rq *rq); extern void activate_task(struct rq *rq, struct task_struct *p, int flags); @@ -1183,11 +1320,10 @@ extern void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq); extern void account_cfs_bandwidth_used(int enabled, int was_enabled); -#ifdef CONFIG_NO_HZ +#ifdef CONFIG_NO_HZ_COMMON enum rq_nohz_flag_bits { NOHZ_TICK_STOPPED, NOHZ_BALANCE_KICK, - NOHZ_IDLE, }; #define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags) diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c index e036eda1a9c9..da98af347e8b 100644 --- a/kernel/sched/stats.c +++ b/kernel/sched/stats.c @@ -130,16 +130,11 @@ static int schedstat_open(struct inode *inode, struct file *file) return seq_open(file, &schedstat_sops); } -static int schedstat_release(struct inode *inode, struct file *file) -{ - return 0; -}; - static const struct file_operations proc_schedstat_operations = { .open = schedstat_open, .read = seq_read, .llseek = seq_lseek, - .release = schedstat_release, + .release = seq_release, }; static int __init proc_schedstat_init(void) |