diff options
author | Ingo Molnar <mingo@elte.hu> | 2008-07-14 16:11:02 +0200 |
---|---|---|
committer | Ingo Molnar <mingo@elte.hu> | 2008-07-14 16:11:02 +0200 |
commit | d14c8a680ccfdeb5e7b9be4d61162c2b373bd1e8 (patch) | |
tree | 38cead29b9b34b9d26b5cfe7b2c2673d6f7ac052 /kernel | |
parent | d59fdcf2ac501de99c3dfb452af5e254d4342886 (diff) | |
parent | 873a6ed6288b6c2c0d2cc84d3b2bf2fab9ba0181 (diff) |
Merge branch 'sched/for-linus' into tracing/for-linus
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/Makefile | 5 | ||||
-rw-r--r-- | kernel/cpu.c | 24 | ||||
-rw-r--r-- | kernel/cpuset.c | 14 | ||||
-rw-r--r-- | kernel/kthread.c | 1 | ||||
-rw-r--r-- | kernel/sched.c | 723 | ||||
-rw-r--r-- | kernel/sched_clock.c | 137 | ||||
-rw-r--r-- | kernel/sched_cpupri.c | 174 | ||||
-rw-r--r-- | kernel/sched_cpupri.h | 36 | ||||
-rw-r--r-- | kernel/sched_debug.c | 64 | ||||
-rw-r--r-- | kernel/sched_fair.c | 413 | ||||
-rw-r--r-- | kernel/sched_features.h | 7 | ||||
-rw-r--r-- | kernel/sched_rt.c | 405 | ||||
-rw-r--r-- | kernel/sched_stats.h | 42 | ||||
-rw-r--r-- | kernel/sysctl.c | 8 | ||||
-rw-r--r-- | kernel/time/tick-sched.c | 2 |
15 files changed, 1521 insertions, 534 deletions
diff --git a/kernel/Makefile b/kernel/Makefile index 1c9938addb9..6c55301112e 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -3,7 +3,7 @@ # obj-y = sched.o fork.o exec_domain.o panic.o printk.o profile.o \ - exit.o itimer.o time.o softirq.o resource.o \ + cpu.o exit.o itimer.o time.o softirq.o resource.o \ sysctl.o capability.o ptrace.o timer.o user.o \ signal.o sys.o kmod.o workqueue.o pid.o \ rcupdate.o extable.o params.o posix-timers.o \ @@ -27,7 +27,7 @@ obj-$(CONFIG_RT_MUTEXES) += rtmutex.o obj-$(CONFIG_DEBUG_RT_MUTEXES) += rtmutex-debug.o obj-$(CONFIG_RT_MUTEX_TESTER) += rtmutex-tester.o obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o -obj-$(CONFIG_SMP) += cpu.o spinlock.o +obj-$(CONFIG_SMP) += spinlock.o obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o obj-$(CONFIG_PROVE_LOCKING) += spinlock.o obj-$(CONFIG_UID16) += uid16.o @@ -69,6 +69,7 @@ obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o obj-$(CONFIG_MARKERS) += marker.o obj-$(CONFIG_LATENCYTOP) += latencytop.o +obj-$(CONFIG_SMP) += sched_cpupri.o ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y) # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is diff --git a/kernel/cpu.c b/kernel/cpu.c index c77bc3a1c72..b11f06dc149 100644 --- a/kernel/cpu.c +++ b/kernel/cpu.c @@ -15,6 +15,28 @@ #include <linux/stop_machine.h> #include <linux/mutex.h> +/* + * Represents all cpu's present in the system + * In systems capable of hotplug, this map could dynamically grow + * as new cpu's are detected in the system via any platform specific + * method, such as ACPI for e.g. + */ +cpumask_t cpu_present_map __read_mostly; +EXPORT_SYMBOL(cpu_present_map); + +#ifndef CONFIG_SMP + +/* + * Represents all cpu's that are currently online. + */ +cpumask_t cpu_online_map __read_mostly = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_online_map); + +cpumask_t cpu_possible_map __read_mostly = CPU_MASK_ALL; +EXPORT_SYMBOL(cpu_possible_map); + +#else /* CONFIG_SMP */ + /* Serializes the updates to cpu_online_map, cpu_present_map */ static DEFINE_MUTEX(cpu_add_remove_lock); @@ -403,3 +425,5 @@ out: cpu_maps_update_done(); } #endif /* CONFIG_PM_SLEEP_SMP */ + +#endif /* CONFIG_SMP */ diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 798b3ab054e..459d601947a 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -1194,6 +1194,15 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)) return -ENOSPC; + if (tsk->flags & PF_THREAD_BOUND) { + cpumask_t mask; + + mutex_lock(&callback_mutex); + mask = cs->cpus_allowed; + mutex_unlock(&callback_mutex); + if (!cpus_equal(tsk->cpus_allowed, mask)) + return -EINVAL; + } return security_task_setscheduler(tsk, 0, NULL); } @@ -1207,11 +1216,14 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct mm_struct *mm; struct cpuset *cs = cgroup_cs(cont); struct cpuset *oldcs = cgroup_cs(oldcont); + int err; mutex_lock(&callback_mutex); guarantee_online_cpus(cs, &cpus); - set_cpus_allowed_ptr(tsk, &cpus); + err = set_cpus_allowed_ptr(tsk, &cpus); mutex_unlock(&callback_mutex); + if (err) + return; from = oldcs->mems_allowed; to = cs->mems_allowed; diff --git a/kernel/kthread.c b/kernel/kthread.c index bd1b9ea024e..97747cdd37c 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -180,6 +180,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu) set_task_cpu(k, cpu); k->cpus_allowed = cpumask_of_cpu(cpu); k->rt.nr_cpus_allowed = 1; + k->flags |= PF_THREAD_BOUND; } EXPORT_SYMBOL(kthread_bind); diff --git a/kernel/sched.c b/kernel/sched.c index 8402944f715..591d5e7f757 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -74,6 +74,8 @@ #include <asm/tlb.h> #include <asm/irq_regs.h> +#include "sched_cpupri.h" + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], @@ -289,15 +291,15 @@ struct task_group root_task_group; static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); /* Default task group's cfs_rq on each cpu */ static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp; -#endif +#endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp; -#endif -#else +#endif /* CONFIG_RT_GROUP_SCHED */ +#else /* !CONFIG_FAIR_GROUP_SCHED */ #define root_task_group init_task_group -#endif +#endif /* CONFIG_FAIR_GROUP_SCHED */ /* task_group_lock serializes add/remove of task groups and also changes to * a task group's cpu shares. @@ -307,9 +309,9 @@ static DEFINE_SPINLOCK(task_group_lock); #ifdef CONFIG_FAIR_GROUP_SCHED #ifdef CONFIG_USER_SCHED # define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) -#else +#else /* !CONFIG_USER_SCHED */ # define INIT_TASK_GROUP_LOAD NICE_0_LOAD -#endif +#endif /* CONFIG_USER_SCHED */ /* * A weight of 0 or 1 can cause arithmetics problems. @@ -363,6 +365,10 @@ static inline void set_task_rq(struct task_struct *p, unsigned int cpu) #else static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} #endif /* CONFIG_GROUP_SCHED */ @@ -373,6 +379,7 @@ struct cfs_rq { u64 exec_clock; u64 min_vruntime; + u64 pair_start; struct rb_root tasks_timeline; struct rb_node *rb_leftmost; @@ -401,6 +408,31 @@ struct cfs_rq { */ struct list_head leaf_cfs_rq_list; struct task_group *tg; /* group that "owns" this runqueue */ + +#ifdef CONFIG_SMP + /* + * the part of load.weight contributed by tasks + */ + unsigned long task_weight; + + /* + * h_load = weight * f(tg) + * + * Where f(tg) is the recursive weight fraction assigned to + * this group. + */ + unsigned long h_load; + + /* + * this cpu's part of tg->shares + */ + unsigned long shares; + + /* + * load.weight at the time we set shares + */ + unsigned long rq_weight; +#endif #endif }; @@ -452,6 +484,9 @@ struct root_domain { */ cpumask_t rto_mask; atomic_t rto_count; +#ifdef CONFIG_SMP + struct cpupri cpupri; +#endif }; /* @@ -526,6 +561,9 @@ struct rq { int push_cpu; /* cpu of this runqueue: */ int cpu; + int online; + + unsigned long avg_load_per_task; struct task_struct *migration_thread; struct list_head migration_queue; @@ -749,6 +787,12 @@ late_initcall(sched_init_debug); const_debug unsigned int sysctl_sched_nr_migrate = 32; /* + * ratelimit for updating the group shares. + * default: 0.5ms + */ +const_debug unsigned int sysctl_sched_shares_ratelimit = 500000; + +/* * period over which we measure -rt task cpu usage in us. * default: 1s */ @@ -775,82 +819,6 @@ static inline u64 global_rt_runtime(void) return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; } -unsigned long long time_sync_thresh = 100000; - -static DEFINE_PER_CPU(unsigned long long, time_offset); -static DEFINE_PER_CPU(unsigned long long, prev_cpu_time); - -/* - * Global lock which we take every now and then to synchronize - * the CPUs time. This method is not warp-safe, but it's good - * enough to synchronize slowly diverging time sources and thus - * it's good enough for tracing: - */ -static DEFINE_SPINLOCK(time_sync_lock); -static unsigned long long prev_global_time; - -static unsigned long long __sync_cpu_clock(unsigned long long time, int cpu) -{ - /* - * We want this inlined, to not get tracer function calls - * in this critical section: - */ - spin_acquire(&time_sync_lock.dep_map, 0, 0, _THIS_IP_); - __raw_spin_lock(&time_sync_lock.raw_lock); - - if (time < prev_global_time) { - per_cpu(time_offset, cpu) += prev_global_time - time; - time = prev_global_time; - } else { - prev_global_time = time; - } - - __raw_spin_unlock(&time_sync_lock.raw_lock); - spin_release(&time_sync_lock.dep_map, 1, _THIS_IP_); - - return time; -} - -static unsigned long long __cpu_clock(int cpu) -{ - unsigned long long now; - - /* - * Only call sched_clock() if the scheduler has already been - * initialized (some code might call cpu_clock() very early): - */ - if (unlikely(!scheduler_running)) - return 0; - - now = sched_clock_cpu(cpu); - - return now; -} - -/* - * For kernel-internal use: high-speed (but slightly incorrect) per-cpu - * clock constructed from sched_clock(): - */ -unsigned long long cpu_clock(int cpu) -{ - unsigned long long prev_cpu_time, time, delta_time; - unsigned long flags; - - local_irq_save(flags); - prev_cpu_time = per_cpu(prev_cpu_time, cpu); - time = __cpu_clock(cpu) + per_cpu(time_offset, cpu); - delta_time = time-prev_cpu_time; - - if (unlikely(delta_time > time_sync_thresh)) { - time = __sync_cpu_clock(time, cpu); - per_cpu(prev_cpu_time, cpu) = time; - } - local_irq_restore(flags); - - return time; -} -EXPORT_SYMBOL_GPL(cpu_clock); - #ifndef prepare_arch_switch # define prepare_arch_switch(next) do { } while (0) #endif @@ -1313,15 +1281,15 @@ void wake_up_idle_cpu(int cpu) if (!tsk_is_polling(rq->idle)) smp_send_reschedule(cpu); } -#endif +#endif /* CONFIG_NO_HZ */ -#else +#else /* !CONFIG_SMP */ static void __resched_task(struct task_struct *p, int tif_bit) { assert_spin_locked(&task_rq(p)->lock); set_tsk_thread_flag(p, tif_bit); } -#endif +#endif /* CONFIG_SMP */ #if BITS_PER_LONG == 32 # define WMULT_CONST (~0UL) @@ -1336,6 +1304,9 @@ static void __resched_task(struct task_struct *p, int tif_bit) */ #define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) +/* + * delta *= weight / lw + */ static unsigned long calc_delta_mine(unsigned long delta_exec, unsigned long weight, struct load_weight *lw) @@ -1363,12 +1334,6 @@ calc_delta_mine(unsigned long delta_exec, unsigned long weight, return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); } -static inline unsigned long -calc_delta_fair(unsigned long delta_exec, struct load_weight *lw) -{ - return calc_delta_mine(delta_exec, NICE_0_LOAD, lw); -} - static inline void update_load_add(struct load_weight *lw, unsigned long inc) { lw->weight += inc; @@ -1479,17 +1444,211 @@ static inline void dec_cpu_load(struct rq *rq, unsigned long load) #ifdef CONFIG_SMP static unsigned long source_load(int cpu, int type); static unsigned long target_load(int cpu, int type); -static unsigned long cpu_avg_load_per_task(int cpu); static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); -#else /* CONFIG_SMP */ + +static unsigned long cpu_avg_load_per_task(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->nr_running) + rq->avg_load_per_task = rq->load.weight / rq->nr_running; + + return rq->avg_load_per_task; +} #ifdef CONFIG_FAIR_GROUP_SCHED -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) + +typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *); + +/* + * Iterate the full tree, calling @down when first entering a node and @up when + * leaving it for the final time. + */ +static void +walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd) +{ + struct task_group *parent, *child; + + rcu_read_lock(); + parent = &root_task_group; +down: + (*down)(parent, cpu, sd); + list_for_each_entry_rcu(child, &parent->children, siblings) { + parent = child; + goto down; + +up: + continue; + } + (*up)(parent, cpu, sd); + + child = parent; + parent = parent->parent; + if (parent) + goto up; + rcu_read_unlock(); +} + +static void __set_se_shares(struct sched_entity *se, unsigned long shares); + +/* + * Calculate and set the cpu's group shares. + */ +static void +__update_group_shares_cpu(struct task_group *tg, int cpu, + unsigned long sd_shares, unsigned long sd_rq_weight) { + int boost = 0; + unsigned long shares; + unsigned long rq_weight; + + if (!tg->se[cpu]) + return; + + rq_weight = tg->cfs_rq[cpu]->load.weight; + + /* + * If there are currently no tasks on the cpu pretend there is one of + * average load so that when a new task gets to run here it will not + * get delayed by group starvation. + */ + if (!rq_weight) { + boost = 1; + rq_weight = NICE_0_LOAD; + } + + if (unlikely(rq_weight > sd_rq_weight)) + rq_weight = sd_rq_weight; + + /* + * \Sum shares * rq_weight + * shares = ----------------------- + * \Sum rq_weight + * + */ + shares = (sd_shares * rq_weight) / (sd_rq_weight + 1); + + /* + * record the actual number of shares, not the boosted amount. + */ + tg->cfs_rq[cpu]->shares = boost ? 0 : shares; + tg->cfs_rq[cpu]->rq_weight = rq_weight; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + else if (shares > MAX_SHARES) + shares = MAX_SHARES; + + __set_se_shares(tg->se[cpu], shares); } + +/* + * Re-compute the task group their per cpu shares over the given domain. + * This needs to be done in a bottom-up fashion because the rq weight of a + * parent group depends on the shares of its child groups. + */ +static void +tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd) +{ + unsigned long rq_weight = 0; + unsigned long shares = 0; + int i; + + for_each_cpu_mask(i, sd->span) { + rq_weight += tg->cfs_rq[i]->load.weight; + shares += tg->cfs_rq[i]->shares; + } + + if ((!shares && rq_weight) || shares > tg->shares) + shares = tg->shares; + + if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) + shares = tg->shares; + + if (!rq_weight) + rq_weight = cpus_weight(sd->span) * NICE_0_LOAD; + + for_each_cpu_mask(i, sd->span) { + struct rq *rq = cpu_rq(i); + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __update_group_shares_cpu(tg, i, shares, rq_weight); + spin_unlock_irqrestore(&rq->lock, flags); + } +} + +/* + * Compute the cpu's hierarchical load factor for each task group. + * This needs to be done in a top-down fashion because the load of a child + * group is a fraction of its parents load. + */ +static void +tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd) +{ + unsigned long load; + + if (!tg->parent) { + load = cpu_rq(cpu)->load.weight; + } else { + load = tg->parent->cfs_rq[cpu]->h_load; + load *= tg->cfs_rq[cpu]->shares; + load /= tg->parent->cfs_rq[cpu]->load.weight + 1; + } + + tg->cfs_rq[cpu]->h_load = load; +} + +static void +tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd) +{ +} + +static void update_shares(struct sched_domain *sd) +{ + u64 now = cpu_clock(raw_smp_processor_id()); + s64 elapsed = now - sd->last_update; + + if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { + sd->last_update = now; + walk_tg_tree(tg_nop, tg_shares_up, 0, sd); + } +} + +static void update_shares_locked(struct rq *rq, struct sched_domain *sd) +{ + spin_unlock(&rq->lock); + update_shares(sd); + spin_lock(&rq->lock); +} + +static void update_h_load(int cpu) +{ + walk_tg_tree(tg_load_down, tg_nop, cpu, NULL); +} + +#else + +static inline void update_shares(struct sched_domain *sd) +{ +} + +static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) +{ +} + #endif -#endif /* CONFIG_SMP */ +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) +{ +#ifdef CONFIG_SMP + cfs_rq->shares = shares; +#endif +} +#endif #include "sched_stats.h" #include "sched_idletask.c" @@ -1500,27 +1659,17 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) #endif #define sched_class_highest (&rt_sched_class) +#define for_each_class(class) \ + for (class = sched_class_highest; class; class = class->next) -static inline void inc_load(struct rq *rq, const struct task_struct *p) -{ - update_load_add(&rq->load, p->se.load.weight); -} - -static inline void dec_load(struct rq *rq, const struct task_struct *p) -{ - update_load_sub(&rq->load, p->se.load.weight); -} - -static void inc_nr_running(struct task_struct *p, struct rq *rq) +static void inc_nr_running(struct rq *rq) { rq->nr_running++; - inc_load(rq, p); } -static void dec_nr_running(struct task_struct *p, struct rq *rq) +static void dec_nr_running(struct rq *rq) { rq->nr_running--; - dec_load(rq, p); } static void set_load_weight(struct task_struct *p) @@ -1544,6 +1693,12 @@ static void set_load_weight(struct task_struct *p) p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; } +static void update_avg(u64 *avg, u64 sample) +{ + s64 diff = sample - *avg; + *avg += diff >> 3; +} + static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) { sched_info_queued(p); @@ -1553,6 +1708,13 @@ static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) { + if (sleep && p->se.last_wakeup) { + update_avg(&p->se.avg_overlap, + p->se.sum_exec_runtime - p->se.last_wakeup); + p->se.last_wakeup = 0; + } + + sched_info_dequeued(p); p->sched_class->dequeue_task(rq, p, sleep); p->se.on_rq = 0; } @@ -1612,7 +1774,7 @@ static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) rq->nr_uninterruptible--; enqueue_task(rq, p, wakeup); - inc_nr_running(p, rq); + inc_nr_running(rq); } /* @@ -1624,7 +1786,7 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) rq->nr_uninterruptible++; dequeue_task(rq, p, sleep); - dec_nr_running(p, rq); + dec_nr_running(rq); } /** @@ -1636,12 +1798,6 @@ inline int task_curr(const struct task_struct *p) return cpu_curr(task_cpu(p)) == p; } -/* Used instead of source_load when we know the type == 0 */ -unsigned long weighted_cpuload(const int cpu) -{ - return cpu_rq(cpu)->load.weight; -} - static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { set_task_rq(p, cpu); @@ -1670,6 +1826,12 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, #ifdef CONFIG_SMP +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) +{ + return cpu_rq(cpu)->load.weight; +} + /* * Is this task likely cache-hot: */ @@ -1880,7 +2042,7 @@ static unsigned long source_load(int cpu, int type) struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); - if (type == 0) + if (type == 0 || !sched_feat(LB_BIAS)) return total; return min(rq->cpu_load[type-1], total); @@ -1895,25 +2057,13 @@ static unsigned long target_load(int cpu, int type) struct rq *rq = cpu_rq(cpu); unsigned long total = weighted_cpuload(cpu); - if (type == 0) + if (type == 0 || !sched_feat(LB_BIAS)) return total; return max(rq->cpu_load[type-1], total); } /* - * Return the average load per task on the cpu's run queue - */ -static unsigned long cpu_avg_load_per_task(int cpu) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - unsigned long n = rq->nr_running; - - return n ? total / n : SCHED_LOAD_SCALE; -} - -/* * find_idlest_group finds and returns the least busy CPU group within the * domain. */ @@ -2019,6 +2169,9 @@ static int sched_balance_self(int cpu, int flag) sd = tmp; } + if (sd) + update_shares(sd); + while (sd) { cpumask_t span, tmpmask; struct sched_group *group; @@ -2085,6 +2238,22 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) if (!sched_feat(SYNC_WAKEUPS)) sync = 0; +#ifdef CONFIG_SMP + if (sched_feat(LB_WAKEUP_UPDATE)) { + struct sched_domain *sd; + + this_cpu = raw_smp_processor_id(); + cpu = task_cpu(p); + + for_each_domain(this_cpu, sd) { + if (cpu_isset(cpu, sd->span)) { + update_shares(sd); + break; + } + } + } +#endif + smp_wmb(); rq = task_rq_lock(p, &flags); old_state = p->state; @@ -2131,7 +2300,7 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) } } } -#endif +#endif /* CONFIG_SCHEDSTATS */ out_activate: #endif /* CONFIG_SMP */ @@ -2157,6 +2326,8 @@ out_running: p->sched_class->task_wake_up(rq, p); #endif out: + current->se.last_wakeup = current->se.sum_exec_runtime; + task_rq_unlock(rq, &flags); return success; @@ -2277,7 +2448,7 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) * management (if any): */ p->sched_class->task_new(rq, p); - inc_nr_running(p, rq); + inc_nr_running(rq); } check_preempt_curr(rq, p); #ifdef CONFIG_SMP @@ -2331,7 +2502,7 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, notifier->ops->sched_out(notifier, next); } -#else +#else /* !CONFIG_PREEMPT_NOTIFIERS */ static void fire_sched_in_preempt_notifiers(struct task_struct *curr) { @@ -2343,7 +2514,7 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr, { } -#endif +#endif /* CONFIG_PREEMPT_NOTIFIERS */ /** * prepare_task_switch - prepare to switch tasks @@ -2785,7 +2956,7 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, enum cpu_idle_type idle, int *all_pinned, int *this_best_prio, struct rq_iterator *iterator) { - int loops = 0, pulled = 0, pinned = 0, skip_for_load; + int loops = 0, pulled = 0, pinned = 0; struct task_struct *p; long rem_load_move = max_load_move; @@ -2801,14 +2972,8 @@ balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, next: if (!p || loops++ > sysctl_sched_nr_migrate) goto out; - /* - * To help distribute high priority tasks across CPUs we don't - * skip a task if it will be the highest priority task (i.e. smallest - * prio value) on its new queue regardless of its load weight - */ - skip_for_load = (p->se.load.weight >> 1) > rem_load_move + - SCHED_LOAD_SCALE_FUZZ; - if ((skip_for_load && p->prio >= *this_best_prio) || + + if ((p->se.load.weight >> 1) > rem_load_move || !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { p = iterator->next(iterator->arg); goto next; @@ -2863,6 +3028,10 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, max_load_move - total_load_moved, sd, idle, all_pinned, &this_best_prio); class = class->next; + + if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) + break; + } while (class && max_load_move > total_load_moved); return total_load_moved > 0; @@ -2939,6 +3108,7 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, max_load = this_load = total_load = total_pwr = 0; busiest_load_per_task = busiest_nr_running = 0; this_load_per_task = this_nr_running = 0; + if (idle == CPU_NOT_IDLE) load_idx = sd->busy_idx; else if (idle == CPU_NEWLY_IDLE) @@ -2953,6 +3123,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, int __group_imb = 0; unsigned int balance_cpu = -1, first_idle_cpu = 0; unsigned long sum_nr_running, sum_weighted_load; + unsigned long sum_avg_load_per_task; + unsigned long avg_load_per_task; local_group = cpu_isset(this_cpu, group->cpumask); @@ -2961,6 +3133,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, /* Tally up the load of all CPUs in the group */ sum_weighted_load = sum_nr_running = avg_load = 0; + sum_avg_load_per_task = avg_load_per_task = 0; + max_cpu_load = 0; min_cpu_load = ~0UL; @@ -2994,6 +3168,8 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, avg_load += load; sum_nr_running += rq->nr_running; sum_weighted_load += weighted_cpuload(i); + + sum_avg_load_per_task += cpu_avg_load_per_task(i); } /* @@ -3015,7 +3191,20 @@ find_busiest_group(struct sched_domain *sd, int this_cpu, avg_load = sg_div_cpu_power(group, avg_load * SCHED_LOAD_SCALE); - if ((max_cpu_load - min_cpu_load) > SCHED_LOAD_SCALE) + + /* + * Consider the group unbalanced when the imbalance is larger + * than the average weight of two tasks. + * + * APZ: with cgroup the avg task weight can vary wildly and + * might not be a suitable number - should we keep a + * normalized nr_running number somewhere that negates + * the hierarchy? + */ + avg_load_per_task = sg_div_cpu_power(group, + sum_avg_load_per_task * SCHED_LOAD_SCALE); + + if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) __group_imb = 1; group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; @@ -3156,9 +3345,9 @@ small_imbalance: if (busiest_load_per_task > this_load_per_task) imbn = 1; } else - this_load_per_task = SCHED_LOAD_SCALE; + this_load_per_task = cpu_avg_load_per_task(this_cpu); - if (max_load - this_load + SCHED_LOAD_SCALE_FUZZ >= + if (max_load - this_load + 2*busiest_load_per_task >= busiest_load_per_task * imbn) { *imbalance = busiest_load_per_task; return busiest; @@ -3284,6 +3473,7 @@ static int load_balance(int this_cpu, struct rq *this_rq, schedstat_inc(sd, lb_count[idle]); redo: + update_shares(sd); group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, cpus, balance); @@ -3386,8 +3576,9 @@ redo: if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - return ld_moved; + ld_moved = -1; + + goto out; out_balanced: schedstat_inc(sd, lb_balanced[idle]); @@ -3402,8 +3593,13 @@ out_one_pinned: if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - return 0; + ld_moved = -1; + else + ld_moved = 0; +out: + if (ld_moved) + update_shares(sd); + return ld_moved; } /* @@ -3438,6 +3634,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); redo: + update_shares_locked(this_rq, sd); group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE, &sd_idle, cpus, NULL); if (!group) { @@ -3481,6 +3678,7 @@ redo: } else sd->nr_balance_failed = 0; + update_shares_locked(this_rq, sd); return ld_moved; out_balanced: @@ -3672,6 +3870,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) /* Earliest time when we have to do rebalance again */ unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; + int need_serialize; cpumask_t tmp; for_each_domain(cpu, sd) { @@ -3689,8 +3888,9 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) if (interval > HZ*NR_CPUS/10) interval = HZ*NR_CPUS/10; + need_serialize = sd->flags & SD_SERIALIZE; - if (sd->flags & SD_SERIALIZE) { + if (need_serialize) { if (!spin_trylock(&balancing)) goto out; } @@ -3706,7 +3906,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) } sd->last_balance = jiffies; } - if (sd->flags & SD_SERIALIZE) + if (need_serialize) spin_unlock(&balancing); out: if (time_after(next_balance, sd->last_balance + interval)) { @@ -4070,6 +4270,7 @@ static noinline void __schedule_bug(struct task_struct *prev) prev->comm, prev->pid, preempt_count()); debug_show_held_locks(prev); + print_modules(); if (irqs_disabled()) print_irqtrace_events(prev); @@ -4143,7 +4344,7 @@ asmlinkage void __sched schedule(void) struct task_struct *prev, *next; unsigned long *switch_count; struct rq *rq; - int cpu; + int cpu, hrtick = sched_feat(HRTICK); need_resched: preempt_disable(); @@ -4158,7 +4359,8 @@ need_resched_nonpreemptible: schedule_debug(prev); - hrtick_clear(rq); + if (hrtick) + hrtick_clear(rq); /* * Do the rq-clock update outside the rq lock: @@ -4204,7 +4406,8 @@ need_resched_nonpreemptible: } else spin_unlock_irq(&rq->lock); - hrtick_set(rq); + if (hrtick) + hrtick_set(rq); if (unlikely(reacquire_kernel_lock(current) < 0)) goto need_resched_nonpreemptible; @@ -4586,10 +4789,8 @@ void set_user_nice(struct task_struct *p, long nice) goto out_unlock; } on_rq = p->se.on_rq; - if (on_rq) { + if (on_rq) dequeue_task(rq, p, 0); - dec_load(rq, p); - } p->static_prio = NICE_TO_PRIO(nice); set_load_weight(p); @@ -4599,7 +4800,6 @@ void set_user_nice(struct task_struct *p, long nice) if (on_rq) { enqueue_task(rq, p, 0); - inc_load(rq, p); /* * If the task increased its priority or is running and * lowered its priority, then reschedule its CPU: @@ -5070,24 +5270,6 @@ asmlinkage long sys_sched_setaffinity(pid_t pid, unsigned int len, return sched_setaffinity(pid, &new_mask); } -/* - * Represents all cpu's present in the system |