X-Git-Url: https://err.no/cgi-bin/gitweb.cgi?a=blobdiff_plain;f=kernel%2Fsched.c;h=b062856b946c4fbe4387763b0fdd61f9ac48625b;hb=db292ca302e83534f5f0f7139e13d7e6976e51f9;hp=afe76ec2e7feffb1f7a070d3f433b2838dca378a;hpb=804b908adfcffe3831621acb6c8a776585983d2a;p=linux-2.6 diff --git a/kernel/sched.c b/kernel/sched.c index afe76ec2e7..b062856b94 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -52,7 +52,6 @@ #include #include #include -#include #include #include #include @@ -66,6 +65,7 @@ #include #include +#include /* * Scheduler clock - returns current time in nanosec units. @@ -74,7 +74,7 @@ */ unsigned long long __attribute__((weak)) sched_clock(void) { - return (unsigned long long)jiffies * (1000000000 / HZ); + return (unsigned long long)jiffies * (NSEC_PER_SEC / HZ); } /* @@ -98,8 +98,8 @@ unsigned long long __attribute__((weak)) sched_clock(void) /* * Some helpers for converting nanosecond timing to jiffy resolution */ -#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (1000000000 / HZ)) -#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ)) +#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) +#define JIFFIES_TO_NS(TIME) ((TIME) * (NSEC_PER_SEC / HZ)) #define NICE_0_LOAD SCHED_LOAD_SCALE #define NICE_0_SHIFT SCHED_LOAD_SHIFT @@ -171,6 +171,7 @@ struct task_group { unsigned long shares; /* spinlock to serialize modification to shares */ spinlock_t lock; + struct rcu_head rcu; }; /* Default task group's sched entity on each cpu */ @@ -215,15 +216,15 @@ static inline struct task_group *task_group(struct task_struct *p) } /* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ -static inline void set_task_cfs_rq(struct task_struct *p) +static inline void set_task_cfs_rq(struct task_struct *p, unsigned int cpu) { - p->se.cfs_rq = task_group(p)->cfs_rq[task_cpu(p)]; - p->se.parent = task_group(p)->se[task_cpu(p)]; + p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; + p->se.parent = task_group(p)->se[cpu]; } #else -static inline void set_task_cfs_rq(struct task_struct *p) { } +static inline void set_task_cfs_rq(struct task_struct *p, unsigned int cpu) { } #endif /* CONFIG_FAIR_GROUP_SCHED */ @@ -257,7 +258,6 @@ struct cfs_rq { */ struct list_head leaf_cfs_rq_list; /* Better name : task_cfs_rq_list? */ struct task_group *tg; /* group that "owns" this runqueue */ - struct rcu_head rcu; #endif }; @@ -455,23 +455,27 @@ static void update_rq_clock(struct rq *rq) */ enum { SCHED_FEAT_NEW_FAIR_SLEEPERS = 1, - SCHED_FEAT_START_DEBIT = 2, - SCHED_FEAT_TREE_AVG = 4, - SCHED_FEAT_APPROX_AVG = 8, - SCHED_FEAT_WAKEUP_PREEMPT = 16, - SCHED_FEAT_PREEMPT_RESTRICT = 32, + SCHED_FEAT_WAKEUP_PREEMPT = 2, + SCHED_FEAT_START_DEBIT = 4, + SCHED_FEAT_TREE_AVG = 8, + SCHED_FEAT_APPROX_AVG = 16, }; const_debug unsigned int sysctl_sched_features = SCHED_FEAT_NEW_FAIR_SLEEPERS * 1 | + SCHED_FEAT_WAKEUP_PREEMPT * 1 | SCHED_FEAT_START_DEBIT * 1 | SCHED_FEAT_TREE_AVG * 0 | - SCHED_FEAT_APPROX_AVG * 0 | - SCHED_FEAT_WAKEUP_PREEMPT * 1 | - SCHED_FEAT_PREEMPT_RESTRICT * 1; + SCHED_FEAT_APPROX_AVG * 0; #define sched_feat(x) (sysctl_sched_features & SCHED_FEAT_##x) +/* + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ +const_debug unsigned int sysctl_sched_nr_migrate = 32; + /* * For kernel-internal use: high-speed (but slightly incorrect) per-cpu * clock constructed from sched_clock(): @@ -837,11 +841,24 @@ struct rq_iterator { struct task_struct *(*next)(void *); }; -static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, unsigned long *load_moved, - int *this_best_prio, struct rq_iterator *iterator); +#ifdef CONFIG_SMP +static unsigned long +balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, + int *this_best_prio, struct rq_iterator *iterator); + +static int +iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle, + struct rq_iterator *iterator); +#endif + +#ifdef CONFIG_CGROUP_CPUACCT +static void cpuacct_charge(struct task_struct *tsk, u64 cputime); +#else +static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} +#endif #include "sched_stats.h" #include "sched_idletask.c" @@ -1011,10 +1028,16 @@ unsigned long weighted_cpuload(const int cpu) static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) { + set_task_cfs_rq(p, cpu); #ifdef CONFIG_SMP + /* + * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be + * successfuly executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); task_thread_info(p)->cpu = cpu; #endif - set_task_cfs_rq(p); } #ifdef CONFIG_SMP @@ -2223,17 +2246,17 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, return 1; } -static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, unsigned long *load_moved, - int *this_best_prio, struct rq_iterator *iterator) +static unsigned long +balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, + int *this_best_prio, struct rq_iterator *iterator) { - int pulled = 0, pinned = 0, skip_for_load; + int loops = 0, pulled = 0, pinned = 0, skip_for_load; struct task_struct *p; long rem_load_move = max_load_move; - if (max_nr_move == 0 || max_load_move == 0) + if (max_load_move == 0) goto out; pinned = 1; @@ -2243,10 +2266,10 @@ static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, */ p = iterator->start(iterator->arg); next: - if (!p) + if (!p || loops++ > sysctl_sched_nr_migrate) goto out; /* - * To help distribute high priority tasks accross CPUs we don't + * 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 */ @@ -2263,10 +2286,9 @@ next: rem_load_move -= p->se.load.weight; /* - * We only want to steal up to the prescribed number of tasks - * and the prescribed amount of weighted load. + * We only want to steal up to the prescribed amount of weighted load. */ - if (pulled < max_nr_move && rem_load_move > 0) { + if (rem_load_move > 0) { if (p->prio < *this_best_prio) *this_best_prio = p->prio; p = iterator->next(iterator->arg); @@ -2274,7 +2296,7 @@ next: } out: /* - * Right now, this is the only place pull_task() is called, + * Right now, this is one of only two places pull_task() is called, * so we can safely collect pull_task() stats here rather than * inside pull_task(). */ @@ -2282,8 +2304,8 @@ out: if (all_pinned) *all_pinned = pinned; - *load_moved = max_load_move - rem_load_move; - return pulled; + + return max_load_move - rem_load_move; } /* @@ -2305,7 +2327,7 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, do { total_load_moved += class->load_balance(this_rq, this_cpu, busiest, - ULONG_MAX, max_load_move - total_load_moved, + max_load_move - total_load_moved, sd, idle, all_pinned, &this_best_prio); class = class->next; } while (class && max_load_move > total_load_moved); @@ -2313,6 +2335,32 @@ static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, return total_load_moved > 0; } +static int +iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle, + struct rq_iterator *iterator) +{ + struct task_struct *p = iterator->start(iterator->arg); + int pinned = 0; + + while (p) { + if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { + pull_task(busiest, p, this_rq, this_cpu); + /* + * Right now, this is only the second place pull_task() + * is called, so we can safely collect pull_task() + * stats here rather than inside pull_task(). + */ + schedstat_inc(sd, lb_gained[idle]); + + return 1; + } + p = iterator->next(iterator->arg); + } + + return 0; +} + /* * move_one_task tries to move exactly one task from busiest to this_rq, as * part of active balancing operations within "domain". @@ -2324,12 +2372,9 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, struct sched_domain *sd, enum cpu_idle_type idle) { const struct sched_class *class; - int this_best_prio = MAX_PRIO; for (class = sched_class_highest; class; class = class->next) - if (class->load_balance(this_rq, this_cpu, busiest, - 1, ULONG_MAX, sd, idle, NULL, - &this_best_prio)) + if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle)) return 1; return 0; @@ -3266,18 +3311,6 @@ static inline void idle_balance(int cpu, struct rq *rq) { } -/* Avoid "used but not defined" warning on UP */ -static int balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, - unsigned long max_nr_move, unsigned long max_load_move, - struct sched_domain *sd, enum cpu_idle_type idle, - int *all_pinned, unsigned long *load_moved, - int *this_best_prio, struct rq_iterator *iterator) -{ - *load_moved = 0; - - return 0; -} - #endif DEFINE_PER_CPU(struct kernel_stat, kstat); @@ -3310,20 +3343,15 @@ unsigned long long task_sched_runtime(struct task_struct *p) /* * Account user cpu time to a process. * @p: the process that the cpu time gets accounted to - * @hardirq_offset: the offset to subtract from hardirq_count() * @cputime: the cpu time spent in user space since the last update */ void account_user_time(struct task_struct *p, cputime_t cputime) { struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; cputime64_t tmp; - struct rq *rq = this_rq(); p->utime = cputime_add(p->utime, cputime); - if (p != rq->idle) - cpuacct_charge(p, cputime); - /* Add user time to cpustat. */ tmp = cputime_to_cputime64(cputime); if (TASK_NICE(p) > 0) @@ -3337,7 +3365,7 @@ void account_user_time(struct task_struct *p, cputime_t cputime) * @p: the process that the cpu time gets accounted to * @cputime: the cpu time spent in virtual machine since the last update */ -void account_guest_time(struct task_struct *p, cputime_t cputime) +static void account_guest_time(struct task_struct *p, cputime_t cputime) { cputime64_t tmp; struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; @@ -3374,11 +3402,8 @@ void account_system_time(struct task_struct *p, int hardirq_offset, struct rq *rq = this_rq(); cputime64_t tmp; - if (p->flags & PF_VCPU) { - account_guest_time(p, cputime); - p->flags &= ~PF_VCPU; - return; - } + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) + return account_guest_time(p, cputime); p->stime = cputime_add(p->stime, cputime); @@ -3388,10 +3413,9 @@ void account_system_time(struct task_struct *p, int hardirq_offset, cpustat->irq = cputime64_add(cpustat->irq, tmp); else if (softirq_count()) cpustat->softirq = cputime64_add(cpustat->softirq, tmp); - else if (p != rq->idle) { + else if (p != rq->idle) cpustat->system = cputime64_add(cpustat->system, tmp); - cpuacct_charge(p, cputime); - } else if (atomic_read(&rq->nr_iowait) > 0) + else if (atomic_read(&rq->nr_iowait) > 0) cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else cpustat->idle = cputime64_add(cpustat->idle, tmp); @@ -3427,10 +3451,8 @@ void account_steal_time(struct task_struct *p, cputime_t steal) cpustat->iowait = cputime64_add(cpustat->iowait, tmp); else cpustat->idle = cputime64_add(cpustat->idle, tmp); - } else { + } else cpustat->steal = cputime64_add(cpustat->steal, tmp); - cpuacct_charge(p, -tmp); - } } /* @@ -3509,12 +3531,19 @@ EXPORT_SYMBOL(sub_preempt_count); */ static noinline void __schedule_bug(struct task_struct *prev) { - printk(KERN_ERR "BUG: scheduling while atomic: %s/0x%08x/%d\n", - prev->comm, preempt_count(), task_pid_nr(prev)); + struct pt_regs *regs = get_irq_regs(); + + printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", + prev->comm, prev->pid, preempt_count()); + debug_show_held_locks(prev); if (irqs_disabled()) print_irqtrace_events(prev); - dump_stack(); + + if (regs) + show_regs(regs); + else + dump_stack(); } /* @@ -3822,7 +3851,7 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) } EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ -void fastcall complete(struct completion *x) +void complete(struct completion *x) { unsigned long flags; @@ -3834,7 +3863,7 @@ void fastcall complete(struct completion *x) } EXPORT_SYMBOL(complete); -void fastcall complete_all(struct completion *x) +void complete_all(struct completion *x) { unsigned long flags; @@ -3886,13 +3915,13 @@ wait_for_common(struct completion *x, long timeout, int state) return timeout; } -void fastcall __sched wait_for_completion(struct completion *x) +void __sched wait_for_completion(struct completion *x) { wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); } EXPORT_SYMBOL(wait_for_completion); -unsigned long fastcall __sched +unsigned long __sched wait_for_completion_timeout(struct completion *x, unsigned long timeout) { return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); @@ -3908,7 +3937,7 @@ int __sched wait_for_completion_interruptible(struct completion *x) } EXPORT_SYMBOL(wait_for_completion_interruptible); -unsigned long fastcall __sched +unsigned long __sched wait_for_completion_interruptible_timeout(struct completion *x, unsigned long timeout) { @@ -4821,17 +4850,21 @@ long sys_sched_rr_get_interval(pid_t pid, struct timespec __user *interval) if (retval) goto out_unlock; - if (p->policy == SCHED_FIFO) - time_slice = 0; - else if (p->policy == SCHED_RR) + /* + * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER + * tasks that are on an otherwise idle runqueue: + */ + time_slice = 0; + if (p->policy == SCHED_RR) { time_slice = DEF_TIMESLICE; - else { + } else { struct sched_entity *se = &p->se; unsigned long flags; struct rq *rq; rq = task_rq_lock(p, &flags); - time_slice = NS_TO_JIFFIES(sched_slice(cfs_rq_of(se), se)); + if (rq->cfs.load.weight) + time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); task_rq_unlock(rq, &flags); } read_unlock(&tasklist_lock); @@ -4968,6 +5001,32 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) */ cpumask_t nohz_cpu_mask = CPU_MASK_NONE; +/* + * Increase the granularity value when there are more CPUs, + * because with more CPUs the 'effective latency' as visible + * to users decreases. But the relationship is not linear, + * so pick a second-best guess by going with the log2 of the + * number of CPUs. + * + * This idea comes from the SD scheduler of Con Kolivas: + */ +static inline void sched_init_granularity(void) +{ + unsigned int factor = 1 + ilog2(num_online_cpus()); + const unsigned long limit = 200000000; + + sysctl_sched_min_granularity *= factor; + if (sysctl_sched_min_granularity > limit) + sysctl_sched_min_granularity = limit; + + sysctl_sched_latency *= factor; + if (sysctl_sched_latency > limit) + sysctl_sched_latency = limit; + + sysctl_sched_wakeup_granularity *= factor; + sysctl_sched_batch_wakeup_granularity *= factor; +} + #ifdef CONFIG_SMP /* * This is how migration works: @@ -5146,7 +5205,7 @@ static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) } /* - * Figure out where task on dead CPU should go, use force if neccessary. + * Figure out where task on dead CPU should go, use force if necessary. * NOTE: interrupts should be disabled by the caller */ static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) @@ -5232,24 +5291,10 @@ static void migrate_live_tasks(int src_cpu) read_unlock(&tasklist_lock); } -/* - * activate_idle_task - move idle task to the _front_ of runqueue. - */ -static void activate_idle_task(struct task_struct *p, struct rq *rq) -{ - update_rq_clock(rq); - - if (p->state == TASK_UNINTERRUPTIBLE) - rq->nr_uninterruptible--; - - enqueue_task(rq, p, 0); - inc_nr_running(p, rq); -} - /* * Schedules idle task to be the next runnable task on current CPU. - * It does so by boosting its priority to highest possible and adding it to - * the _front_ of the runqueue. Used by CPU offline code. + * It does so by boosting its priority to highest possible. + * Used by CPU offline code. */ void sched_idle_next(void) { @@ -5269,8 +5314,8 @@ void sched_idle_next(void) __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - /* Add idle task to the _front_ of its priority queue: */ - activate_idle_task(p, rq); + update_rq_clock(rq); + activate_task(rq, p, 0); spin_unlock_irqrestore(&rq->lock, flags); } @@ -5341,7 +5386,7 @@ static struct ctl_table sd_ctl_dir[] = { .procname = "sched_domain", .mode = 0555, }, - {0,}, + {0, }, }; static struct ctl_table sd_ctl_root[] = { @@ -5351,7 +5396,7 @@ static struct ctl_table sd_ctl_root[] = { .mode = 0555, .child = sd_ctl_dir, }, - {0,}, + {0, }, }; static struct ctl_table *sd_alloc_ctl_entry(int n) @@ -5431,7 +5476,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) return table; } -static ctl_table * sd_alloc_ctl_cpu_table(int cpu) +static ctl_table *sd_alloc_ctl_cpu_table(int cpu) { struct ctl_table *entry, *table; struct sched_domain *sd; @@ -5463,11 +5508,12 @@ static void register_sched_domain_sysctl(void) struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); char buf[32]; + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + if (entry == NULL) return; - sd_ctl_dir[0].child = entry; - for_each_online_cpu(i) { snprintf(buf, 32, "cpu%d", i); entry->procname = kstrdup(buf, GFP_KERNEL); @@ -5475,14 +5521,19 @@ static void register_sched_domain_sysctl(void) entry->child = sd_alloc_ctl_cpu_table(i); entry++; } + + WARN_ON(sd_sysctl_header); sd_sysctl_header = register_sysctl_table(sd_ctl_root); } +/* may be called multiple times per register */ static void unregister_sched_domain_sysctl(void) { - unregister_sysctl_table(sd_sysctl_header); + if (sd_sysctl_header) + unregister_sysctl_table(sd_sysctl_header); sd_sysctl_header = NULL; - sd_free_ctl_entry(&sd_ctl_dir[0].child); + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); } #else static void register_sched_domain_sysctl(void) @@ -5525,7 +5576,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) case CPU_ONLINE: case CPU_ONLINE_FROZEN: - /* Strictly unneccessary, as first user will wake it. */ + /* Strictly unnecessary, as first user will wake it. */ wake_up_process(cpu_rq(cpu)->migration_thread); break; @@ -5591,7 +5642,7 @@ static struct notifier_block __cpuinitdata migration_notifier = { .priority = 10 }; -int __init migration_init(void) +void __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; @@ -5601,8 +5652,6 @@ int __init migration_init(void) BUG_ON(err == NOTIFY_BAD); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); - - return 0; } #endif @@ -5613,101 +5662,101 @@ int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); #ifdef CONFIG_SCHED_DEBUG -static void sched_domain_debug(struct sched_domain *sd, int cpu) + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level) { - int level = 0; + struct sched_group *group = sd->groups; + cpumask_t groupmask; + char str[NR_CPUS]; - if (!sd) { - printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); - return; + cpumask_scnprintf(str, NR_CPUS, sd->span); + cpus_clear(groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; } - printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + printk(KERN_CONT "span %s\n", str); + + if (!cpu_isset(cpu, sd->span)) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + if (!cpu_isset(cpu, group->cpumask)) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + printk(KERN_DEBUG "%*s groups:", level + 1, ""); do { - int i; - char str[NR_CPUS]; - struct sched_group *group = sd->groups; - cpumask_t groupmask; - - cpumask_scnprintf(str, NR_CPUS, sd->span); - cpus_clear(groupmask); - - printk(KERN_DEBUG); - for (i = 0; i < level + 1; i++) - printk(" "); - printk("domain %d: ", level); - - if (!(sd->flags & SD_LOAD_BALANCE)) { - printk("does not load-balance\n"); - if (sd->parent) - printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" - " has parent"); + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); break; } - printk("span %s\n", str); + if (!group->__cpu_power) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: domain->cpu_power not " + "set\n"); + break; + } - if (!cpu_isset(cpu, sd->span)) - printk(KERN_ERR "ERROR: domain->span does not contain " - "CPU%d\n", cpu); - if (!cpu_isset(cpu, group->cpumask)) - printk(KERN_ERR "ERROR: domain->groups does not contain" - " CPU%d\n", cpu); + if (!cpus_weight(group->cpumask)) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } - printk(KERN_DEBUG); - for (i = 0; i < level + 2; i++) - printk(" "); - printk("groups:"); - do { - if (!group) { - printk("\n"); - printk(KERN_ERR "ERROR: group is NULL\n"); - break; - } + if (cpus_intersects(groupmask, group->cpumask)) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } - if (!group->__cpu_power) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: domain->cpu_power not " - "set\n"); - break; - } + cpus_or(groupmask, groupmask, group->cpumask); - if (!cpus_weight(group->cpumask)) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: empty group\n"); - break; - } + cpumask_scnprintf(str, NR_CPUS, group->cpumask); + printk(KERN_CONT " %s", str); - if (cpus_intersects(groupmask, group->cpumask)) { - printk(KERN_CONT "\n"); - printk(KERN_ERR "ERROR: repeated CPUs\n"); - break; - } + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); - cpus_or(groupmask, groupmask, group->cpumask); + if (!cpus_equal(sd->span, groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); - cpumask_scnprintf(str, NR_CPUS, group->cpumask); - printk(KERN_CONT " %s", str); + if (sd->parent && !cpus_subset(groupmask, sd->parent->span)) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} - group = group->next; - } while (group != sd->groups); - printk(KERN_CONT "\n"); +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + int level = 0; - if (!cpus_equal(sd->span, groupmask)) - printk(KERN_ERR "ERROR: groups don't span " - "domain->span\n"); + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + for (;;) { + if (sched_domain_debug_one(sd, cpu, level)) + break; level++; sd = sd->parent; if (!sd) - continue; - - if (!cpus_subset(groupmask, sd->span)) - printk(KERN_ERR "ERROR: parent span is not a superset " - "of domain->span\n"); - - } while (sd); + break; + } } #else # define sched_domain_debug(sd, cpu) do { } while (0) @@ -6426,13 +6475,17 @@ static cpumask_t fallback_doms; */ static int arch_init_sched_domains(const cpumask_t *cpu_map) { + int err; + ndoms_cur = 1; doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL); if (!doms_cur) doms_cur = &fallback_doms; cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur); register_sched_domain_sysctl(); - return build_sched_domains(doms_cur); + + return err; } static void arch_destroy_sched_domains(const cpumask_t *cpu_map) @@ -6481,6 +6534,9 @@ void partition_sched_domains(int ndoms_new, cpumask_t *doms_new) { int i, j; + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + if (doms_new == NULL) { ndoms_new = 1; doms_new = &fallback_doms; @@ -6516,6 +6572,8 @@ match2: kfree(doms_cur); doms_cur = doms_new; ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); } #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) @@ -6649,18 +6707,17 @@ void __init sched_init_smp(void) /* Move init over to a non-isolated CPU */ if (set_cpus_allowed(current, non_isolated_cpus) < 0) BUG(); + sched_init_granularity(); } #else void __init sched_init_smp(void) { + sched_init_granularity(); } #endif /* CONFIG_SMP */ int in_sched_functions(unsigned long addr) { - /* Linker adds these: start and end of __sched functions */ - extern char __sched_text_start[], __sched_text_end[]; - return in_lock_functions(addr) || (addr >= (unsigned long)__sched_text_start && addr < (unsigned long)__sched_text_end); @@ -6980,8 +7037,8 @@ err: /* rcu callback to free various structures associated with a task group */ static void free_sched_group(struct rcu_head *rhp) { - struct cfs_rq *cfs_rq = container_of(rhp, struct cfs_rq, rcu); - struct task_group *tg = cfs_rq->tg; + struct task_group *tg = container_of(rhp, struct task_group, rcu); + struct cfs_rq *cfs_rq; struct sched_entity *se; int i; @@ -7002,7 +7059,7 @@ static void free_sched_group(struct rcu_head *rhp) /* Destroy runqueue etc associated with a task group */ void sched_destroy_group(struct task_group *tg) { - struct cfs_rq *cfs_rq; + struct cfs_rq *cfs_rq = NULL; int i; for_each_possible_cpu(i) { @@ -7010,10 +7067,10 @@ void sched_destroy_group(struct task_group *tg) list_del_rcu(&cfs_rq->leaf_cfs_rq_list); } - cfs_rq = tg->cfs_rq[0]; + BUG_ON(!cfs_rq); /* wait for possible concurrent references to cfs_rqs complete */ - call_rcu(&cfs_rq->rcu, free_sched_group); + call_rcu(&tg->rcu, free_sched_group); } /* change task's runqueue when it moves between groups. @@ -7029,8 +7086,10 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); - if (tsk->sched_class != &fair_sched_class) + if (tsk->sched_class != &fair_sched_class) { + set_task_cfs_rq(tsk, task_cpu(tsk)); goto done; + } update_rq_clock(rq); @@ -7043,7 +7102,7 @@ void sched_move_task(struct task_struct *tsk) tsk->sched_class->put_prev_task(rq, tsk); } - set_task_cfs_rq(tsk); + set_task_cfs_rq(tsk, task_cpu(tsk)); if (on_rq) { if (unlikely(running)) @@ -7103,25 +7162,25 @@ unsigned long sched_group_shares(struct task_group *tg) #ifdef CONFIG_FAIR_CGROUP_SCHED /* return corresponding task_group object of a cgroup */ -static inline struct task_group *cgroup_tg(struct cgroup *cont) +static inline struct task_group *cgroup_tg(struct cgroup *cgrp) { - return container_of(cgroup_subsys_state(cont, cpu_cgroup_subsys_id), - struct task_group, css); + return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id), + struct task_group, css); } static struct cgroup_subsys_state * -cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) +cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) { struct task_group *tg; - if (!cont->parent) { + if (!cgrp->parent) { /* This is early initialization for the top cgroup */ - init_task_group.css.cgroup = cont; + init_task_group.css.cgroup = cgrp; return &init_task_group.css; } /* we support only 1-level deep hierarchical scheduler atm */ - if (cont->parent->parent) + if (cgrp->parent->parent) return ERR_PTR(-EINVAL); tg = sched_create_group(); @@ -7129,21 +7188,21 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) return ERR_PTR(-ENOMEM); /* Bind the cgroup to task_group object we just created */ - tg->css.cgroup = cont; + tg->css.cgroup = cgrp; return &tg->css; } static void cpu_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) + struct cgroup *cgrp) { - struct task_group *tg = cgroup_tg(cont); + struct task_group *tg = cgroup_tg(cgrp); sched_destroy_group(tg); } static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *cont, struct task_struct *tsk) + struct cgroup *cgrp, struct task_struct *tsk) { /* We don't support RT-tasks being in separate groups */ if (tsk->sched_class != &fair_sched_class) @@ -7153,62 +7212,170 @@ static int cpu_cgroup_can_attach(struct cgroup_subsys *ss, } static void -cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cont, +cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, struct cgroup *old_cont, struct task_struct *tsk) { sched_move_task(tsk); } -static ssize_t cpu_shares_write(struct cgroup *cont, struct cftype *cftype, - struct file *file, const char __user *userbuf, - size_t nbytes, loff_t *ppos) +static int cpu_shares_write_uint(struct cgroup *cgrp, struct cftype *cftype, + u64 shareval) { - unsigned long shareval; - struct task_group *tg = cgroup_tg(cont); - char buffer[2*sizeof(unsigned long) + 1]; - int rc; - - if (nbytes > 2*sizeof(unsigned long)) /* safety check */ - return -E2BIG; - - if (copy_from_user(buffer, userbuf, nbytes)) - return -EFAULT; - - buffer[nbytes] = 0; /* nul-terminate */ - shareval = simple_strtoul(buffer, NULL, 10); - - rc = sched_group_set_shares(tg, shareval); - - return (rc < 0 ? rc : nbytes); + return sched_group_set_shares(cgroup_tg(cgrp), shareval); } -static u64 cpu_shares_read_uint(struct cgroup *cont, struct cftype *cft) +static u64 cpu_shares_read_uint(struct cgroup *cgrp, struct cftype *cft) { - struct task_group *tg = cgroup_tg(cont); + struct task_group *tg = cgroup_tg(cgrp); return (u64) tg->shares; } -static struct cftype cpu_shares = { - .name = "shares", - .read_uint = cpu_shares_read_uint, - .write = cpu_shares_write, +static struct cftype cpu_files[] = { + { + .name = "shares", + .read_uint = cpu_shares_read_uint, + .write_uint = cpu_shares_write_uint, + }, }; static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont) { - return cgroup_add_file(cont, ss, &cpu_shares); + return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files)); } struct cgroup_subsys cpu_cgroup_subsys = { - .name = "cpu", - .create = cpu_cgroup_create, - .destroy = cpu_cgroup_destroy, - .can_attach = cpu_cgroup_can_attach, - .attach = cpu_cgroup_attach, - .populate = cpu_cgroup_populate, - .subsys_id = cpu_cgroup_subsys_id, + .name = "cpu", + .create = cpu_cgroup_create, + .destroy = cpu_cgroup_destroy, + .can_attach = cpu_cgroup_can_attach, + .attach = cpu_cgroup_attach, + .populate = cpu_cgroup_populate, + .subsys_id = cpu_cgroup_subsys_id, .early_init = 1, }; #endif /* CONFIG_FAIR_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). + */ + +/* track cpu usage of a group of tasks */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 *cpuusage; +}; + +struct cgroup_subsys cpuacct_subsys; + +/* return cpu accounting group corresponding to this container */ +static inline struct cpuacct *cgroup_ca(struct cgroup *cont) +{ + return container_of(cgroup_subsys_state(cont, 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); +} + +/* create a new cpu accounting group */ +static struct cgroup_subsys_state *cpuacct_create( + struct cgroup_subsys *ss, struct cgroup *cont) +{ + struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); + + if (!ca) + return ERR_PTR(-ENOMEM); + + ca->cpuusage = alloc_percpu(u64); + if (!ca->cpuusage) { + kfree(ca); + return ERR_PTR(-ENOMEM); + } + + return &ca->css; +} + +/* destroy an existing cpu accounting group */ +static void cpuacct_destroy(struct cgroup_subsys *ss, + struct cgroup *cont) +{ + struct cpuacct *ca = cgroup_ca(cont); + + free_percpu(ca->cpuusage); + kfree(ca); +} + +/* return total cpu usage (in nanoseconds) of a group */ +static u64 cpuusage_read(struct cgroup *cont, struct cftype *cft) +{ + struct cpuacct *ca = cgroup_ca(cont); + u64 totalcpuusage = 0; + int i; + + for_each_possible_cpu(i) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, i); + + /* + * Take rq->lock to make 64-bit addition safe on 32-bit + * platforms. + */ + spin_lock_irq(&cpu_rq(i)->lock); + totalcpuusage += *cpuusage; + spin_unlock_irq(&cpu_rq(i)->lock); + } + + return totalcpuusage; +} + +static struct cftype files[] = { + { + .name = "usage", + .read_uint = cpuusage_read, + }, +}; + +static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cont) +{ + return cgroup_add_files(cont, ss, files, ARRAY_SIZE(files)); +} + +/* + * charge this task's execution time to its accounting group. + * + * called with rq->lock held. + */ +static void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ + struct cpuacct *ca; + + if (!cpuacct_subsys.active) + return; + + ca = task_ca(tsk); + if (ca) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk)); + + *cpuusage += cputime; + } +} + +struct cgroup_subsys cpuacct_subsys = { + .name = "cpuacct", + .create = cpuacct_create, + .destroy = cpuacct_destroy, + .populate = cpuacct_populate, + .subsys_id = cpuacct_subsys_id, +}; +#endif /* CONFIG_CGROUP_CPUACCT */