X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=kernel%2Fsched.c;h=f04aa9664504025ad16e01f1c2c8c8da6a787545;hb=82af8ce84ed65d2fb6d8c017d3f2bbbf161061fb;hp=489e7d926408ebd8bded36ede64075f8ee9f6d8f;hpb=80dd99b368cf6501be88ab517bbbb5bf352b75b8;p=safe%2Fjmp%2Flinux-2.6 diff --git a/kernel/sched.c b/kernel/sched.c index 489e7d9..f04aa96 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -39,6 +39,7 @@ #include #include #include +#include #include #include #include @@ -68,17 +69,18 @@ #include #include #include -#include #include #include #include -#include #include #include #include "sched_cpupri.h" +#define CREATE_TRACE_POINTS +#include + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], @@ -118,12 +120,6 @@ */ #define RUNTIME_INF ((u64)~0ULL) -DEFINE_TRACE(sched_wait_task); -DEFINE_TRACE(sched_wakeup); -DEFINE_TRACE(sched_wakeup_new); -DEFINE_TRACE(sched_switch); -DEFINE_TRACE(sched_migrate_task); - #ifdef CONFIG_SMP static void double_rq_lock(struct rq *rq1, struct rq *rq2); @@ -231,13 +227,20 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) spin_lock(&rt_b->rt_runtime_lock); for (;;) { + unsigned long delta; + ktime_t soft, hard; + if (hrtimer_active(&rt_b->rt_period_timer)) break; now = hrtimer_cb_get_time(&rt_b->rt_period_timer); hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); - hrtimer_start_expires(&rt_b->rt_period_timer, - HRTIMER_MODE_ABS); + + soft = hrtimer_get_softexpires(&rt_b->rt_period_timer); + hard = hrtimer_get_expires(&rt_b->rt_period_timer); + delta = ktime_to_ns(ktime_sub(hard, soft)); + __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta, + HRTIMER_MODE_ABS, 0); } spin_unlock(&rt_b->rt_runtime_lock); } @@ -577,6 +580,7 @@ struct rq { struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; + u64 nr_migrations_in; struct cfs_rq cfs; struct rt_rq rt; @@ -623,6 +627,10 @@ struct rq { struct list_head migration_queue; #endif + /* calc_load related fields */ + unsigned long calc_load_update; + long calc_load_active; + #ifdef CONFIG_SCHED_HRTICK #ifdef CONFIG_SMP int hrtick_csd_pending; @@ -638,9 +646,6 @@ struct rq { /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ /* sys_sched_yield() stats */ - unsigned int yld_exp_empty; - unsigned int yld_act_empty; - unsigned int yld_both_empty; unsigned int yld_count; /* schedule() stats */ @@ -688,7 +693,7 @@ static inline int cpu_of(struct rq *rq) #define task_rq(p) cpu_rq(task_cpu(p)) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) -static inline void update_rq_clock(struct rq *rq) +inline void update_rq_clock(struct rq *rq) { rq->clock = sched_clock_cpu(cpu_of(rq)); } @@ -1113,7 +1118,7 @@ static void hrtick_start(struct rq *rq, u64 delay) if (rq == this_rq()) { hrtimer_restart(timer); } else if (!rq->hrtick_csd_pending) { - __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd); + __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0); rq->hrtick_csd_pending = 1; } } @@ -1149,7 +1154,8 @@ static __init void init_hrtick(void) */ static void hrtick_start(struct rq *rq, u64 delay) { - hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL); + __hrtimer_start_range_ns(&rq->hrtick_timer, ns_to_ktime(delay), 0, + HRTIMER_MODE_REL, 0); } static inline void init_hrtick(void) @@ -1413,10 +1419,22 @@ iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, struct rq_iterator *iterator); #endif +/* 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, +}; + #ifdef CONFIG_CGROUP_CPUACCT static void cpuacct_charge(struct task_struct *tsk, u64 cputime); +static void cpuacct_update_stats(struct task_struct *tsk, + enum cpuacct_stat_index idx, cputime_t val); #else static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} +static inline void cpuacct_update_stats(struct task_struct *tsk, + enum cpuacct_stat_index idx, cputime_t val) {} #endif static inline void inc_cpu_load(struct rq *rq, unsigned long load) @@ -1711,6 +1729,8 @@ static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) } #endif +static void calc_load_account_active(struct rq *this_rq); + #include "sched_stats.h" #include "sched_idletask.c" #include "sched_fair.c" @@ -1941,7 +1961,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) clock_offset = old_rq->clock - new_rq->clock; - trace_sched_migrate_task(p, task_cpu(p), new_cpu); + trace_sched_migrate_task(p, new_cpu); #ifdef CONFIG_SCHEDSTATS if (p->se.wait_start) @@ -1950,12 +1970,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) p->se.sleep_start -= clock_offset; if (p->se.block_start) p->se.block_start -= clock_offset; +#endif if (old_cpu != new_cpu) { - schedstat_inc(p, se.nr_migrations); + p->se.nr_migrations++; + new_rq->nr_migrations_in++; +#ifdef CONFIG_SCHEDSTATS if (task_hot(p, old_rq->clock, NULL)) schedstat_inc(p, se.nr_forced2_migrations); - } #endif + perf_counter_task_migration(p, new_cpu); + } p->se.vruntime -= old_cfsrq->min_vruntime - new_cfsrq->min_vruntime; @@ -1998,6 +2022,49 @@ migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) } /* + * wait_task_context_switch - wait for a thread to complete at least one + * context switch. + * + * @p must not be current. + */ +void wait_task_context_switch(struct task_struct *p) +{ + unsigned long nvcsw, nivcsw, flags; + int running; + struct rq *rq; + + nvcsw = p->nvcsw; + nivcsw = p->nivcsw; + for (;;) { + /* + * The runqueue is assigned before the actual context + * switch. We need to take the runqueue lock. + * + * We could check initially without the lock but it is + * very likely that we need to take the lock in every + * iteration. + */ + rq = task_rq_lock(p, &flags); + running = task_running(rq, p); + task_rq_unlock(rq, &flags); + + if (likely(!running)) + break; + /* + * The switch count is incremented before the actual + * context switch. We thus wait for two switches to be + * sure at least one completed. + */ + if ((p->nvcsw - nvcsw) > 1) + break; + if ((p->nivcsw - nivcsw) > 1) + break; + + cpu_relax(); + } +} + +/* * wait_task_inactive - wait for a thread to unschedule. * * If @match_state is nonzero, it's the @p->state value just checked and @@ -2307,6 +2374,27 @@ static int sched_balance_self(int cpu, int flag) #endif /* CONFIG_SMP */ +/** + * task_oncpu_function_call - call a function on the cpu on which a task runs + * @p: the task to evaluate + * @func: the function to be called + * @info: the function call argument + * + * Calls the function @func when the task is currently running. This might + * be on the current CPU, which just calls the function directly + */ +void task_oncpu_function_call(struct task_struct *p, + void (*func) (void *info), void *info) +{ + int cpu; + + preempt_disable(); + cpu = task_cpu(p); + if (task_curr(p)) + smp_call_function_single(cpu, func, info, 1); + preempt_enable(); +} + /*** * try_to_wake_up - wake up a thread * @p: the to-be-woken-up thread @@ -2441,6 +2529,17 @@ out: return success; } +/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * + * Attempt to wake up the nominated process and move it to the set of runnable + * processes. Returns 1 if the process was woken up, 0 if it was already + * running. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ int wake_up_process(struct task_struct *p) { return try_to_wake_up(p, TASK_ALL, 0); @@ -2463,6 +2562,7 @@ static void __sched_fork(struct task_struct *p) p->se.exec_start = 0; p->se.sum_exec_runtime = 0; p->se.prev_sum_exec_runtime = 0; + p->se.nr_migrations = 0; p->se.last_wakeup = 0; p->se.avg_overlap = 0; p->se.start_runtime = 0; @@ -2693,6 +2793,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) */ prev_state = prev->state; finish_arch_switch(prev); + perf_counter_task_sched_in(current, cpu_of(rq)); finish_lock_switch(rq, prev); #ifdef CONFIG_SMP if (post_schedule) @@ -2749,7 +2850,7 @@ context_switch(struct rq *rq, struct task_struct *prev, * combine the page table reload and the switch backend into * one hypercall. */ - arch_enter_lazy_cpu_mode(); + arch_start_context_switch(prev); if (unlikely(!mm)) { next->active_mm = oldmm; @@ -2839,19 +2940,81 @@ unsigned long nr_iowait(void) return sum; } -unsigned long nr_active(void) +/* Variables and functions for calc_load */ +static atomic_long_t calc_load_tasks; +static unsigned long calc_load_update; +unsigned long avenrun[3]; +EXPORT_SYMBOL(avenrun); + +/** + * get_avenrun - get the load average array + * @loads: pointer to dest load array + * @offset: offset to add + * @shift: shift count to shift the result left + * + * These values are estimates at best, so no need for locking. + */ +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) { - unsigned long i, running = 0, uninterruptible = 0; + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; +} - for_each_online_cpu(i) { - running += cpu_rq(i)->nr_running; - uninterruptible += cpu_rq(i)->nr_uninterruptible; - } +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + load *= exp; + load += active * (FIXED_1 - exp); + return load >> FSHIFT; +} + +/* + * calc_load - update the avenrun load estimates 10 ticks after the + * CPUs have updated calc_load_tasks. + */ +void calc_global_load(void) +{ + unsigned long upd = calc_load_update + 10; + long active; + + if (time_before(jiffies, upd)) + return; - if (unlikely((long)uninterruptible < 0)) - uninterruptible = 0; + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; - return running + uninterruptible; + avenrun[0] = calc_load(avenrun[0], EXP_1, active); + avenrun[1] = calc_load(avenrun[1], EXP_5, active); + avenrun[2] = calc_load(avenrun[2], EXP_15, active); + + calc_load_update += LOAD_FREQ; +} + +/* + * Either called from update_cpu_load() or from a cpu going idle + */ +static void calc_load_account_active(struct rq *this_rq) +{ + long nr_active, delta; + + nr_active = this_rq->nr_running; + nr_active += (long) this_rq->nr_uninterruptible; + + if (nr_active != this_rq->calc_load_active) { + delta = nr_active - this_rq->calc_load_active; + this_rq->calc_load_active = nr_active; + atomic_long_add(delta, &calc_load_tasks); + } +} + +/* + * Externally visible per-cpu scheduler statistics: + * cpu_nr_migrations(cpu) - number of migrations into that cpu + */ +u64 cpu_nr_migrations(int cpu) +{ + return cpu_rq(cpu)->nr_migrations_in; } /* @@ -2882,6 +3045,11 @@ static void update_cpu_load(struct rq *this_rq) new_load += scale-1; this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; } + + if (time_after_eq(jiffies, this_rq->calc_load_update)) { + this_rq->calc_load_update += LOAD_FREQ; + calc_load_account_active(this_rq); + } } #ifdef CONFIG_SMP @@ -3002,6 +3170,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, struct sched_domain *sd, enum cpu_idle_type idle, int *all_pinned) { + int tsk_cache_hot = 0; /* * We do not migrate tasks that are: * 1) running (obviously), or @@ -3025,10 +3194,11 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, * 2) too many balance attempts have failed. */ - if (!task_hot(p, rq->clock, sd) || - sd->nr_balance_failed > sd->cache_nice_tries) { + tsk_cache_hot = task_hot(p, rq->clock, sd); + if (!tsk_cache_hot || + sd->nr_balance_failed > sd->cache_nice_tries) { #ifdef CONFIG_SCHEDSTATS - if (task_hot(p, rq->clock, sd)) { + if (tsk_cache_hot) { schedstat_inc(sd, lb_hot_gained[idle]); schedstat_inc(p, se.nr_forced_migrations); } @@ -3036,7 +3206,7 @@ int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, return 1; } - if (task_hot(p, rq->clock, sd)) { + if (tsk_cache_hot) { schedstat_inc(p, se.nr_failed_migrations_hot); return 0; } @@ -3190,246 +3360,480 @@ static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, return 0; } - +/********** Helpers for find_busiest_group ************************/ /* - * find_busiest_group finds and returns the busiest CPU group within the - * domain. It calculates and returns the amount of weighted load which - * should be moved to restore balance via the imbalance parameter. + * sd_lb_stats - Structure to store the statistics of a sched_domain + * during load balancing. */ -static struct sched_group * -find_busiest_group(struct sched_domain *sd, int this_cpu, - unsigned long *imbalance, enum cpu_idle_type idle, - int *sd_idle, const struct cpumask *cpus, int *balance) -{ - struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups; - unsigned long max_load, avg_load, total_load, this_load, total_pwr; - unsigned long max_pull; - unsigned long busiest_load_per_task, busiest_nr_running; - unsigned long this_load_per_task, this_nr_running; - int load_idx, group_imb = 0; +struct sd_lb_stats { + struct sched_group *busiest; /* Busiest group in this sd */ + struct sched_group *this; /* Local group in this sd */ + unsigned long total_load; /* Total load of all groups in sd */ + unsigned long total_pwr; /* Total power of all groups in sd */ + unsigned long avg_load; /* Average load across all groups in sd */ + + /** Statistics of this group */ + unsigned long this_load; + unsigned long this_load_per_task; + unsigned long this_nr_running; + + /* Statistics of the busiest group */ + unsigned long max_load; + unsigned long busiest_load_per_task; + unsigned long busiest_nr_running; + + int group_imb; /* Is there imbalance in this sd */ #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - int power_savings_balance = 1; - unsigned long leader_nr_running = 0, min_load_per_task = 0; - unsigned long min_nr_running = ULONG_MAX; - struct sched_group *group_min = NULL, *group_leader = NULL; + int power_savings_balance; /* Is powersave balance needed for this sd */ + struct sched_group *group_min; /* Least loaded group in sd */ + struct sched_group *group_leader; /* Group which relieves group_min */ + unsigned long min_load_per_task; /* load_per_task in group_min */ + unsigned long leader_nr_running; /* Nr running of group_leader */ + unsigned long min_nr_running; /* Nr running of group_min */ #endif +}; + +/* + * sg_lb_stats - stats of a sched_group required for load_balancing + */ +struct sg_lb_stats { + unsigned long avg_load; /*Avg load across the CPUs of the group */ + unsigned long group_load; /* Total load over the CPUs of the group */ + unsigned long sum_nr_running; /* Nr tasks running in the group */ + unsigned long sum_weighted_load; /* Weighted load of group's tasks */ + unsigned long group_capacity; + int group_imb; /* Is there an imbalance in the group ? */ +}; - 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; +/** + * 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)); +} - if (idle == CPU_NOT_IDLE) +/** + * get_sd_load_idx - Obtain the load index for a given sched domain. + * @sd: The sched_domain whose load_idx is to be obtained. + * @idle: The Idle status of the CPU for whose sd load_icx is obtained. + */ +static inline int get_sd_load_idx(struct sched_domain *sd, + enum cpu_idle_type idle) +{ + int load_idx; + + switch (idle) { + case CPU_NOT_IDLE: load_idx = sd->busy_idx; - else if (idle == CPU_NEWLY_IDLE) + break; + + case CPU_NEWLY_IDLE: load_idx = sd->newidle_idx; - else + break; + default: load_idx = sd->idle_idx; + break; + } - do { - unsigned long load, group_capacity, max_cpu_load, min_cpu_load; - int local_group; - int i; - 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; + return load_idx; +} - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); - if (local_group) - balance_cpu = cpumask_first(sched_group_cpus(group)); +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +/** + * init_sd_power_savings_stats - Initialize power savings statistics for + * the given sched_domain, during load balancing. + * + * @sd: Sched domain whose power-savings statistics are to be initialized. + * @sds: Variable containing the statistics for sd. + * @idle: Idle status of the CPU at which we're performing load-balancing. + */ +static inline void init_sd_power_savings_stats(struct sched_domain *sd, + struct sd_lb_stats *sds, enum cpu_idle_type idle) +{ + /* + * Busy processors will not participate in power savings + * balance. + */ + if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) + sds->power_savings_balance = 0; + else { + sds->power_savings_balance = 1; + sds->min_nr_running = ULONG_MAX; + sds->leader_nr_running = 0; + } +} - /* 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; +/** + * update_sd_power_savings_stats - Update the power saving stats for a + * sched_domain while performing load balancing. + * + * @group: sched_group belonging to the sched_domain under consideration. + * @sds: Variable containing the statistics of the sched_domain + * @local_group: Does group contain the CPU for which we're performing + * load balancing ? + * @sgs: Variable containing the statistics of the group. + */ +static inline void update_sd_power_savings_stats(struct sched_group *group, + struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) +{ - max_cpu_load = 0; - min_cpu_load = ~0UL; + if (!sds->power_savings_balance) + return; - for_each_cpu_and(i, sched_group_cpus(group), cpus) { - struct rq *rq = cpu_rq(i); + /* + * If the local group is idle or completely loaded + * no need to do power savings balance at this domain + */ + if (local_group && (sds->this_nr_running >= sgs->group_capacity || + !sds->this_nr_running)) + sds->power_savings_balance = 0; - if (*sd_idle && rq->nr_running) - *sd_idle = 0; + /* + * If a group is already running at full capacity or idle, + * don't include that group in power savings calculations + */ + if (!sds->power_savings_balance || + sgs->sum_nr_running >= sgs->group_capacity || + !sgs->sum_nr_running) + return; - /* Bias balancing toward cpus of our domain */ - if (local_group) { - if (idle_cpu(i) && !first_idle_cpu) { - first_idle_cpu = 1; - balance_cpu = i; - } + /* + * Calculate the group which has the least non-idle load. + * This is the group from where we need to pick up the load + * for saving power + */ + if ((sgs->sum_nr_running < sds->min_nr_running) || + (sgs->sum_nr_running == sds->min_nr_running && + group_first_cpu(group) > group_first_cpu(sds->group_min))) { + sds->group_min = group; + sds->min_nr_running = sgs->sum_nr_running; + sds->min_load_per_task = sgs->sum_weighted_load / + sgs->sum_nr_running; + } - load = target_load(i, load_idx); - } else { - load = source_load(i, load_idx); - if (load > max_cpu_load) - max_cpu_load = load; - if (min_cpu_load > load) - min_cpu_load = load; - } + /* + * Calculate the group which is almost near its + * capacity but still has some space to pick up some load + * from other group and save more power + */ + if (sgs->sum_nr_running > sgs->group_capacity - 1) + return; - avg_load += load; - sum_nr_running += rq->nr_running; - sum_weighted_load += weighted_cpuload(i); + if (sgs->sum_nr_running > sds->leader_nr_running || + (sgs->sum_nr_running == sds->leader_nr_running && + group_first_cpu(group) < group_first_cpu(sds->group_leader))) { + sds->group_leader = group; + sds->leader_nr_running = sgs->sum_nr_running; + } +} - sum_avg_load_per_task += cpu_avg_load_per_task(i); - } +/** + * check_power_save_busiest_group - see if there is potential for some power-savings balance + * @sds: Variable containing the statistics of the sched_domain + * under consideration. + * @this_cpu: Cpu at which we're currently performing load-balancing. + * @imbalance: Variable to store the imbalance. + * + * Description: + * Check if we have potential to perform some power-savings balance. + * If yes, set the busiest group to be the least loaded group in the + * sched_domain, so that it's CPUs can be put to idle. + * + * Returns 1 if there is potential to perform power-savings balance. + * Else returns 0. + */ +static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + if (!sds->power_savings_balance) + return 0; - /* - * First idle cpu or the first cpu(busiest) in this sched group - * is eligible for doing load balancing at this and above - * domains. In the newly idle case, we will allow all the cpu's - * to do the newly idle load balance. - */ - if (idle != CPU_NEWLY_IDLE && local_group && - balance_cpu != this_cpu && balance) { - *balance = 0; - goto ret; - } + if (sds->this != sds->group_leader || + sds->group_leader == sds->group_min) + return 0; - total_load += avg_load; - total_pwr += group->__cpu_power; + *imbalance = sds->min_load_per_task; + sds->busiest = sds->group_min; - /* Adjust by relative CPU power of the group */ - avg_load = sg_div_cpu_power(group, - avg_load * SCHED_LOAD_SCALE); + if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { + cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = + group_first_cpu(sds->group_leader); + } + + return 1; +} +#else /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ +static inline void init_sd_power_savings_stats(struct sched_domain *sd, + struct sd_lb_stats *sds, enum cpu_idle_type idle) +{ + return; +} - /* - * 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); +static inline void update_sd_power_savings_stats(struct sched_group *group, + struct sd_lb_stats *sds, int local_group, struct sg_lb_stats *sgs) +{ + return; +} + +static inline int check_power_save_busiest_group(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + return 0; +} +#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ + + +/** + * update_sg_lb_stats - Update sched_group's statistics for load balancing. + * @group: sched_group whose statistics are to be updated. + * @this_cpu: Cpu for which load balance is currently performed. + * @idle: Idle status of this_cpu + * @load_idx: Load index of sched_domain of this_cpu for load calc. + * @sd_idle: Idle status of the sched_domain containing group. + * @local_group: Does group contain this_cpu. + * @cpus: Set of cpus considered for load balancing. + * @balance: Should we balance. + * @sgs: variable to hold the statistics for this group. + */ +static inline void update_sg_lb_stats(struct sched_group *group, int this_cpu, + enum cpu_idle_type idle, int load_idx, int *sd_idle, + int local_group, const struct cpumask *cpus, + int *balance, struct sg_lb_stats *sgs) +{ + unsigned long load, max_cpu_load, min_cpu_load; + int i; + unsigned int balance_cpu = -1, first_idle_cpu = 0; + unsigned long sum_avg_load_per_task; + unsigned long avg_load_per_task; - if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) - __group_imb = 1; + if (local_group) + balance_cpu = group_first_cpu(group); - group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; + /* Tally up the load of all CPUs in the group */ + sum_avg_load_per_task = avg_load_per_task = 0; + max_cpu_load = 0; + min_cpu_load = ~0UL; + for_each_cpu_and(i, sched_group_cpus(group), cpus) { + struct rq *rq = cpu_rq(i); + + if (*sd_idle && rq->nr_running) + *sd_idle = 0; + + /* Bias balancing toward cpus of our domain */ if (local_group) { - this_load = avg_load; - this = group; - this_nr_running = sum_nr_running; - this_load_per_task = sum_weighted_load; - } else if (avg_load > max_load && - (sum_nr_running > group_capacity || __group_imb)) { - max_load = avg_load; - busiest = group; - busiest_nr_running = sum_nr_running; - busiest_load_per_task = sum_weighted_load; - group_imb = __group_imb; + if (idle_cpu(i) && !first_idle_cpu) { + first_idle_cpu = 1; + balance_cpu = i; + } + + load = target_load(i, load_idx); + } else { + load = source_load(i, load_idx); + if (load > max_cpu_load) + max_cpu_load = load; + if (min_cpu_load > load) + min_cpu_load = load; } -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - /* - * Busy processors will not participate in power savings - * balance. - */ - if (idle == CPU_NOT_IDLE || - !(sd->flags & SD_POWERSAVINGS_BALANCE)) - goto group_next; + sgs->group_load += load; + sgs->sum_nr_running += rq->nr_running; + sgs->sum_weighted_load += weighted_cpuload(i); - /* - * If the local group is idle or completely loaded - * no need to do power savings balance at this domain - */ - if (local_group && (this_nr_running >= group_capacity || - !this_nr_running)) - power_savings_balance = 0; + sum_avg_load_per_task += cpu_avg_load_per_task(i); + } - /* - * If a group is already running at full capacity or idle, - * don't include that group in power savings calculations - */ - if (!power_savings_balance || sum_nr_running >= group_capacity - || !sum_nr_running) - goto group_next; + /* + * First idle cpu or the first cpu(busiest) in this sched group + * is eligible for doing load balancing at this and above + * domains. In the newly idle case, we will allow all the cpu's + * to do the newly idle load balance. + */ + if (idle != CPU_NEWLY_IDLE && local_group && + balance_cpu != this_cpu && balance) { + *balance = 0; + return; + } - /* - * Calculate the group which has the least non-idle load. - * This is the group from where we need to pick up the load - * for saving power - */ - if ((sum_nr_running < min_nr_running) || - (sum_nr_running == min_nr_running && - cpumask_first(sched_group_cpus(group)) > - cpumask_first(sched_group_cpus(group_min)))) { - group_min = group; - min_nr_running = sum_nr_running; - min_load_per_task = sum_weighted_load / - sum_nr_running; - } + /* Adjust by relative CPU power of the group */ + sgs->avg_load = sg_div_cpu_power(group, + sgs->group_load * SCHED_LOAD_SCALE); - /* - * Calculate the group which is almost near its - * capacity but still has some space to pick up some load - * from other group and save more power - */ - if (sum_nr_running <= group_capacity - 1) { - if (sum_nr_running > leader_nr_running || - (sum_nr_running == leader_nr_running && - cpumask_first(sched_group_cpus(group)) < - cpumask_first(sched_group_cpus(group_leader)))) { - group_leader = group; - leader_nr_running = sum_nr_running; - } + + /* + * 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) + sgs->group_imb = 1; + + sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; + +} + +/** + * update_sd_lb_stats - Update sched_group's statistics for load balancing. + * @sd: sched_domain whose statistics are to be updated. + * @this_cpu: Cpu for which load balance is currently performed. + * @idle: Idle status of this_cpu + * @sd_idle: Idle status of the sched_domain containing group. + * @cpus: Set of cpus considered for load balancing. + * @balance: Should we balance. + * @sds: variable to hold the statistics for this sched_domain. + */ +static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu, + enum cpu_idle_type idle, int *sd_idle, + const struct cpumask *cpus, int *balance, + struct sd_lb_stats *sds) +{ + struct sched_group *group = sd->groups; + struct sg_lb_stats sgs; + int load_idx; + + init_sd_power_savings_stats(sd, sds, idle); + load_idx = get_sd_load_idx(sd, idle); + + do { + int local_group; + + local_group = cpumask_test_cpu(this_cpu, + sched_group_cpus(group)); + memset(&sgs, 0, sizeof(sgs)); + update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle, + local_group, cpus, balance, &sgs); + + if (local_group && balance && !(*balance)) + return; + + sds->total_load += sgs.group_load; + sds->total_pwr += group->__cpu_power; + + if (local_group) { + sds->this_load = sgs.avg_load; + sds->this = group; + sds->this_nr_running = sgs.sum_nr_running; + sds->this_load_per_task = sgs.sum_weighted_load; + } else if (sgs.avg_load > sds->max_load && + (sgs.sum_nr_running > sgs.group_capacity || + sgs.group_imb)) { + sds->max_load = sgs.avg_load; + sds->busiest = group; + sds->busiest_nr_running = sgs.sum_nr_running; + sds->busiest_load_per_task = sgs.sum_weighted_load; + sds->group_imb = sgs.group_imb; } -group_next: -#endif + + update_sd_power_savings_stats(group, sds, local_group, &sgs); group = group->next; } while (group != sd->groups); - if (!busiest || this_load >= max_load || busiest_nr_running == 0) - goto out_balanced; - - avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr; +} - if (this_load >= avg_load || - 100*max_load <= sd->imbalance_pct*this_load) - goto out_balanced; +/** + * fix_small_imbalance - Calculate the minor imbalance that exists + * amongst the groups of a sched_domain, during + * load balancing. + * @sds: Statistics of the sched_domain whose imbalance is to be calculated. + * @this_cpu: The cpu at whose sched_domain we're performing load-balance. + * @imbalance: Variable to store the imbalance. + */ +static inline void fix_small_imbalance(struct sd_lb_stats *sds, + int this_cpu, unsigned long *imbalance) +{ + unsigned long tmp, pwr_now = 0, pwr_move = 0; + unsigned int imbn = 2; + + if (sds->this_nr_running) { + sds->this_load_per_task /= sds->this_nr_running; + if (sds->busiest_load_per_task > + sds->this_load_per_task) + imbn = 1; + } else + sds->this_load_per_task = + cpu_avg_load_per_task(this_cpu); - busiest_load_per_task /= busiest_nr_running; - if (group_imb) - busiest_load_per_task = min(busiest_load_per_task, avg_load); + if (sds->max_load - sds->this_load + sds->busiest_load_per_task >= + sds->busiest_load_per_task * imbn) { + *imbalance = sds->busiest_load_per_task; + return; + } /* - * We're trying to get all the cpus to the average_load, so we don't - * want to push ourselves above the average load, nor do we wish to - * reduce the max loaded cpu below the average load, as either of these - * actions would just result in more rebalancing later, and ping-pong - * tasks around. Thus we look for the minimum possible imbalance. - * Negative imbalances (*we* are more loaded than anyone else) will - * be counted as no imbalance for these purposes -- we can't fix that - * by pulling tasks to us. Be careful of negative numbers as they'll - * appear as very large values with unsigned longs. + * OK, we don't have enough imbalance to justify moving tasks, + * however we may be able to increase total CPU power used by + * moving them. */ - if (max_load <= busiest_load_per_task) - goto out_balanced; + pwr_now += sds->busiest->__cpu_power * + min(sds->busiest_load_per_task, sds->max_load); + pwr_now += sds->this->__cpu_power * + min(sds->this_load_per_task, sds->this_load); + pwr_now /= SCHED_LOAD_SCALE; + + /* Amount of load we'd subtract */ + tmp = sg_div_cpu_power(sds->busiest, + sds->busiest_load_per_task * SCHED_LOAD_SCALE); + if (sds->max_load > tmp) + pwr_move += sds->busiest->__cpu_power * + min(sds->busiest_load_per_task, sds->max_load - tmp); + + /* Amount of load we'd add */ + if (sds->max_load * sds->busiest->__cpu_power < + sds->busiest_load_per_task * SCHED_LOAD_SCALE) + tmp = sg_div_cpu_power(sds->this, + sds->max_load * sds->busiest->__cpu_power); + else + tmp = sg_div_cpu_power(sds->this, + sds->busiest_load_per_task * SCHED_LOAD_SCALE); + pwr_move += sds->this->__cpu_power * + min(sds->this_load_per_task, sds->this_load + tmp); + pwr_move /= SCHED_LOAD_SCALE; + + /* Move if we gain throughput */ + if (pwr_move > pwr_now) + *imbalance = sds->busiest_load_per_task; +} + +/** + * calculate_imbalance - Calculate the amount of imbalance present within the + * groups of a given sched_domain during load balance. + * @sds: statistics of the sched_domain whose imbalance is to be calculated. + * @this_cpu: Cpu for which currently load balance is being performed. + * @imbalance: The variable to store the imbalance. + */ +static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu, + unsigned long *imbalance) +{ + unsigned long max_pull; /* * In the presence of smp nice balancing, certain scenarios can have * max load less than avg load(as we skip the groups at or below * its cpu_power, while calculating max_load..) */ - if (max_load < avg_load) { + if (sds->max_load < sds->avg_load) { *imbalance = 0; - goto small_imbalance; + return fix_small_imbalance(sds, this_cpu, imbalance); } /* Don't want to pull so many tasks that a group would go idle */ - max_pull = min(max_load - avg_load, max_load - busiest_load_per_task); + max_pull = min(sds->max_load - sds->avg_load, + sds->max_load - sds->busiest_load_per_task); /* How much load to actually move to equalise the imbalance */ - *imbalance = min(max_pull * busiest->__cpu_power, - (avg_load - this_load) * this->__cpu_power) + *imbalance = min(max_pull * sds->busiest->__cpu_power, + (sds->avg_load - sds->this_load) * sds->this->__cpu_power) / SCHED_LOAD_SCALE; /* @@ -3438,78 +3842,110 @@ group_next: * a think about bumping its value to force at least one task to be * moved */ - if (*imbalance < busiest_load_per_task) { - unsigned long tmp, pwr_now, pwr_move; - unsigned int imbn; - -small_imbalance: - pwr_move = pwr_now = 0; - imbn = 2; - if (this_nr_running) { - this_load_per_task /= this_nr_running; - if (busiest_load_per_task > this_load_per_task) - imbn = 1; - } else - this_load_per_task = cpu_avg_load_per_task(this_cpu); + if (*imbalance < sds->busiest_load_per_task) + return fix_small_imbalance(sds, this_cpu, imbalance); - if (max_load - this_load + busiest_load_per_task >= - busiest_load_per_task * imbn) { - *imbalance = busiest_load_per_task; - return busiest; - } +} +/******* find_busiest_group() helpers end here *********************/ - /* - * OK, we don't have enough imbalance to justify moving tasks, - * however we may be able to increase total CPU power used by - * moving them. - */ +/** + * find_busiest_group - Returns the busiest group within the sched_domain + * if there is an imbalance. If there isn't an imbalance, and + * the user has opted for power-savings, it returns a group whose + * CPUs can be put to idle by rebalancing those tasks elsewhere, if + * such a group exists. + * + * Also calculates the amount of weighted load which should be moved + * to restore balance. + * + * @sd: The sched_domain whose busiest group is to be returned. + * @this_cpu: The cpu for which load balancing is currently being performed. + * @imbalance: Variable which stores amount of weighted load which should + * be moved to restore balance/put a group to idle. + * @idle: The idle status of this_cpu. + * @sd_idle: The idleness of sd + * @cpus: The set of CPUs under consideration for load-balancing. + * @balance: Pointer to a variable indicating if this_cpu + * is the appropriate cpu to perform load balancing at this_level. + * + * Returns: - the busiest group if imbalance exists. + * - If no imbalance and user has opted for power-savings balance, + * return the least loaded group whose CPUs can be + * put to idle by rebalancing its tasks onto our group. + */ +static struct sched_group * +find_busiest_group(struct sched_domain *sd, int this_cpu, + unsigned long *imbalance, enum cpu_idle_type idle, + int *sd_idle, const struct cpumask *cpus, int *balance) +{ + struct sd_lb_stats sds; - pwr_now += busiest->__cpu_power * - min(busiest_load_per_task, max_load); - pwr_now += this->__cpu_power * - min(this_load_per_task, this_load); - pwr_now /= SCHED_LOAD_SCALE; - - /* Amount of load we'd subtract */ - tmp = sg_div_cpu_power(busiest, - busiest_load_per_task * SCHED_LOAD_SCALE); - if (max_load > tmp) - pwr_move += busiest->__cpu_power * - min(busiest_load_per_task, max_load - tmp); - - /* Amount of load we'd add */ - if (max_load * busiest->__cpu_power < - busiest_load_per_task * SCHED_LOAD_SCALE) - tmp = sg_div_cpu_power(this, - max_load * busiest->__cpu_power); - else - tmp = sg_div_cpu_power(this, - busiest_load_per_task * SCHED_LOAD_SCALE); - pwr_move += this->__cpu_power * - min(this_load_per_task, this_load + tmp); - pwr_move /= SCHED_LOAD_SCALE; + memset(&sds, 0, sizeof(sds)); - /* Move if we gain throughput */ - if (pwr_move > pwr_now) - *imbalance = busiest_load_per_task; - } + /* + * Compute the various statistics relavent for load balancing at + * this level. + */ + update_sd_lb_stats(sd, this_cpu, idle, sd_idle, cpus, + balance, &sds); + + /* Cases where imbalance does not exist from POV of this_cpu */ + /* 1) this_cpu is not the appropriate cpu to perform load balancing + * at this level. + * 2) There is no busy sibling group to pull from. + * 3) This group is the busiest group. + * 4) This group is more busy than the avg busieness at this + * sched_domain. + * 5) The imbalance is within the specified limit. + * 6) Any rebalance would lead to ping-pong + */ + if (balance && !(*balance)) + goto ret; + + if (!sds.busiest || sds.busiest_nr_running == 0) + goto out_balanced; + + if (sds.this_load >= sds.max_load) + goto out_balanced; + + sds.avg_load = (SCHED_LOAD_SCALE * sds.total_load) / sds.total_pwr; + + if (sds.this_load >= sds.avg_load) + goto out_balanced; + + if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load) + goto out_balanced; + + sds.busiest_load_per_task /= sds.busiest_nr_running; + if (sds.group_imb) + sds.busiest_load_per_task = + min(sds.busiest_load_per_task, sds.avg_load); + + /* + * We're trying to get all the cpus to the average_load, so we don't + * want to push ourselves above the average load, nor do we wish to + * reduce the max loaded cpu below the average load, as either of these + * actions would just result in more rebalancing later, and ping-pong + * tasks around. Thus we look for the minimum possible imbalance. + * Negative imbalances (*we* are more loaded than anyone else) will + * be counted as no imbalance for these purposes -- we can't fix that + * by pulling tasks to us. Be careful of negative numbers as they'll + * appear as very large values with unsigned longs. + */ + if (sds.max_load <= sds.busiest_load_per_task) + goto out_balanced; - return busiest; + /* Looks like there is an imbalance. Compute it */ + calculate_imbalance(&sds, this_cpu, imbalance); + return sds.busiest; out_balanced: -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) - goto ret; - - if (this == group_leader && group_leader != group_min) { - *imbalance = min_load_per_task; - if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { - cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = - cpumask_first(sched_group_cpus(group_leader)); - } - return group_min; - } -#endif + /* + * There is no obvious imbalance. But check if we can do some balancing + * to save power. + */ + if (check_power_save_busiest_group(&sds, this_cpu, imbalance)) + return sds.busiest; ret: *imbalance = 0; return NULL; @@ -3553,19 +3989,23 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, */ #define MAX_PINNED_INTERVAL 512 +/* Working cpumask for load_balance and load_balance_newidle. */ +static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask); + /* * Check this_cpu to ensure it is balanced within domain. Attempt to move * tasks if there is an imbalance. */ static int load_balance(int this_cpu, struct rq *this_rq, struct sched_domain *sd, enum cpu_idle_type idle, - int *balance, struct cpumask *cpus) + int *balance) { int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; struct sched_group *group; unsigned long imbalance; struct rq *busiest; unsigned long flags; + struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); cpumask_setall(cpus); @@ -3720,8 +4160,7 @@ out: * this_rq is locked. */ static int -load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, - struct cpumask *cpus) +load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) { struct sched_group *group; struct rq *busiest = NULL; @@ -3729,6 +4168,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, int ld_moved = 0; int sd_idle = 0; int all_pinned = 0; + struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); cpumask_setall(cpus); @@ -3869,10 +4309,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq) struct sched_domain *sd; int pulled_task = 0; unsigned long next_balance = jiffies + HZ; - cpumask_var_t tmpmask; - - if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC)) - return; for_each_domain(this_cpu, sd) { unsigned long interval; @@ -3883,7 +4319,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq) if (sd->flags & SD_BALANCE_NEWIDLE) /* If we've pulled tasks over stop searching: */ pulled_task = load_balance_newidle(this_cpu, this_rq, - sd, tmpmask); + sd); interval = msecs_to_jiffies(sd->balance_interval); if (time_after(next_balance, sd->last_balance + interval)) @@ -3898,7 +4334,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq) */ this_rq->next_balance = next_balance; } - free_cpumask_var(tmpmask); } /* @@ -3956,10 +4391,126 @@ static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) static struct { atomic_t load_balancer; cpumask_var_t cpu_mask; + cpumask_var_t ilb_grp_nohz_mask; } nohz ____cacheline_aligned = { .load_balancer = ATOMIC_INIT(-1), }; +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +/** + * lowest_flag_domain - Return lowest sched_domain containing flag. + * @cpu: The cpu whose lowest level of sched domain is to + * be returned. + * @flag: The flag to check for the lowest sched_domain + * for the given cpu. + * + * Returns the lowest sched_domain of a cpu which contains the given flag. + */ +static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd; + + for_each_domain(cpu, sd) + if (sd && (sd->flags & flag)) + break; + + return sd; +} + +/** + * for_each_flag_domain - Iterates over sched_domains containing the flag. + * @cpu: The cpu whose domains we're iterating over. + * @sd: variable holding the value of the power_savings_sd + * for cpu. + * @flag: The flag to filter the sched_domains to be iterated. + * + * Iterates over all the scheduler domains for a given cpu that has the 'flag' + * set, starting from the lowest sched_domain to the highest. + */ +#define for_each_flag_domain(cpu, sd, flag) \ + for (sd = lowest_flag_domain(cpu, flag); \ + (sd && (sd->flags & flag)); sd = sd->parent) + +/** + * is_semi_idle_group - Checks if the given sched_group is semi-idle. + * @ilb_group: group to be checked for semi-idleness + * + * Returns: 1 if the group is semi-idle. 0 otherwise. + * + * We define a sched_group to be semi idle if it has atleast one idle-CPU + * and atleast one non-idle CPU. This helper function checks if the given + * sched_group is semi-idle or not. + */ +static inline int is_semi_idle_group(struct sched_group *ilb_group) +{ + cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask, + sched_group_cpus(ilb_group)); + + /* + * A sched_group is semi-idle when it has atleast one busy cpu + * and atleast one idle cpu. + */ + if (cpumask_empty(nohz.ilb_grp_nohz_mask)) + return 0; + + if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group))) + return 0; + + return 1; +} +/** + * find_new_ilb - Finds the optimum idle load balancer for nomination. + * @cpu: The cpu which is nominating a new idle_load_balancer. + * + * Returns: Returns the id of the idle load balancer if it exists, + * Else, returns >= nr_cpu_ids. + * + * This algorithm picks the idle load balancer such that it belongs to a + * semi-idle powersavings sched_domain. The idea is to try and avoid + * completely idle packages/cores just for the purpose of idle load balancing + * when there are other idle cpu's which are better suited for that job. + */ +static int find_new_ilb(int cpu) +{ + struct sched_domain *sd; + struct sched_group *ilb_group; + + /* + * Have idle load balancer selection from semi-idle packages only + * when power-aware load balancing is enabled + */ + if (!(sched_smt_power_savings || sched_mc_power_savings)) + goto out_done; + + /* + * Optimize for the case when we have no idle CPUs or only one + * idle CPU. Don't walk the sched_domain hierarchy in such cases + */ + if (cpumask_weight(nohz.cpu_mask) < 2) + goto out_done; + + for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) { + ilb_group = sd->groups; + + do { + if (is_semi_idle_group(ilb_group)) + return cpumask_first(nohz.ilb_grp_nohz_mask); + + ilb_group = ilb_group->next; + + } while (ilb_group != sd->groups); + } + +out_done: + return cpumask_first(nohz.cpu_mask); +} +#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ +static inline int find_new_ilb(int call_cpu) +{ + return cpumask_first(nohz.cpu_mask); +} +#endif + /* * This routine will try to nominate the ilb (idle load balancing) * owner among the cpus whose ticks are stopped. ilb owner will do the idle @@ -4014,8 +4565,24 @@ int select_nohz_load_balancer(int stop_tick) /* make me the ilb owner */ if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) return 1; - } else if (atomic_read(&nohz.load_balancer) == cpu) + } else if (atomic_read(&nohz.load_balancer) == cpu) { + int new_ilb; + + if (!(sched_smt_power_savings || + sched_mc_power_savings)) + return 1; + /* + * Check to see if there is a more power-efficient + * ilb. + */ + new_ilb = find_new_ilb(cpu); + if (new_ilb < nr_cpu_ids && new_ilb != cpu) { + atomic_set(&nohz.load_balancer, -1); + resched_cpu(new_ilb); + return 0; + } return 1; + } } else { if (!cpumask_test_cpu(cpu, nohz.cpu_mask)) return 0; @@ -4048,11 +4615,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle) unsigned long next_balance = jiffies + 60*HZ; int update_next_balance = 0; int need_serialize; - cpumask_var_t tmp; - - /* Fails alloc? Rebalancing probably not a priority right now. */ - if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) - return; for_each_domain(cpu, sd) { if (!(sd->flags & SD_LOAD_BALANCE)) @@ -4077,7 +4639,7 @@ 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, tmp)) { + if (load_balance(cpu, rq, sd, idle, &balance)) { /* * We've pulled tasks over so either we're no * longer idle, or one of our SMT siblings is @@ -4111,8 +4673,6 @@ out: */ if (likely(update_next_balance)) rq->next_balance = next_balance; - - free_cpumask_var(tmp); } /* @@ -4191,15 +4751,7 @@ static inline void trigger_load_balance(struct rq *rq, int cpu) } if (atomic_read(&nohz.load_balancer) == -1) { - /* - * simple selection for now: Nominate the - * first cpu in the nohz list to be the next - * ilb owner. - * - * TBD: Traverse the sched domains and nominate - * the nearest cpu in the nohz.cpu_mask. - */ - int ilb = cpumask_first(nohz.cpu_mask); + int ilb = find_new_ilb(cpu); if (ilb < nr_cpu_ids) resched_cpu(ilb); @@ -4246,9 +4798,25 @@ DEFINE_PER_CPU(struct kernel_stat, kstat); EXPORT_PER_CPU_SYMBOL(kstat); /* - * Return any ns on the sched_clock that have not yet been banked in + * Return any ns on the sched_clock that have not yet been accounted in * @p in case that task is currently running. + * + * Called with task_rq_lock() held on @rq. */ +static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) +{ + u64 ns = 0; + + if (task_current(rq, p)) { + update_rq_clock(rq); + ns = rq->clock - p->se.exec_start; + if ((s64)ns < 0) + ns = 0; + } + + return ns; +} + unsigned long long task_delta_exec(struct task_struct *p) { unsigned long flags; @@ -4256,16 +4824,49 @@ unsigned long long task_delta_exec(struct task_struct *p) u64 ns = 0; rq = task_rq_lock(p, &flags); + ns = do_task_delta_exec(p, rq); + task_rq_unlock(rq, &flags); - if (task_current(rq, p)) { - u64 delta_exec; + return ns; +} - update_rq_clock(rq); - delta_exec = rq->clock - p->se.exec_start; - if ((s64)delta_exec > 0) - ns = delta_exec; - } +/* + * Return accounted runtime for the task. + * In case the task is currently running, return the runtime plus current's + * pending runtime that have not been accounted yet. + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + u64 ns = 0; + rq = task_rq_lock(p, &flags); + ns = p->se.sum_exec_runtime + do_task_delta_exec(p, rq); + task_rq_unlock(rq, &flags); + + return ns; +} + +/* + * Return sum_exec_runtime for the thread group. + * In case the task is currently running, return the sum plus current's + * pending runtime that have not been accounted yet. + * + * Note that the thread group might have other running tasks as well, + * so the return value not includes other pending runtime that other + * running tasks might have. + */ +unsigned long long thread_group_sched_runtime(struct task_struct *p) +{ + struct task_cputime totals; + unsigned long flags; + struct rq *rq; + u64 ns; + + rq = task_rq_lock(p, &flags); + thread_group_cputime(p, &totals); + ns = totals.sum_exec_runtime + do_task_delta_exec(p, rq); task_rq_unlock(rq, &flags); return ns; @@ -4294,6 +4895,8 @@ void account_user_time(struct task_struct *p, cputime_t cputime, cpustat->nice = cputime64_add(cpustat->nice, tmp); else cpustat->user = cputime64_add(cpustat->user, tmp); + + cpuacct_update_stats(p, CPUACCT_STAT_USER, cputime); /* Account for user time used */ acct_update_integrals(p); } @@ -4355,6 +4958,8 @@ void account_system_time(struct task_struct *p, int hardirq_offset, else cpustat->system = cputime64_add(cpustat->system, tmp); + cpuacct_update_stats(p, CPUACCT_STAT_SYSTEM, cputime); + /* Account for system time used */ acct_update_integrals(p); } @@ -4402,7 +5007,7 @@ void account_process_tick(struct task_struct *p, int user_tick) if (user_tick) account_user_time(p, one_jiffy, one_jiffy_scaled); - else if (p != rq->idle) + else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) account_system_time(p, HARDIRQ_OFFSET, one_jiffy, one_jiffy_scaled); else @@ -4510,16 +5115,15 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); spin_unlock(&rq->lock); + perf_counter_task_tick(curr, cpu); + #ifdef CONFIG_SMP rq->idle_at_tick = idle_cpu(cpu); trigger_load_balance(rq, cpu); #endif } -#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ - defined(CONFIG_PREEMPT_TRACER)) - -static inline unsigned long get_parent_ip(unsigned long addr) +notrace unsigned long get_parent_ip(unsigned long addr) { if (in_lock_functions(addr)) { addr = CALLER_ADDR2; @@ -4529,6 +5133,9 @@ static inline unsigned long get_parent_ip(unsigned long addr) return addr; } +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + void __kprobes add_preempt_count(int val) { #ifdef CONFIG_DEBUG_PREEMPT @@ -4725,6 +5332,7 @@ need_resched_nonpreemptible: if (likely(prev != next)) { sched_info_switch(prev, next); + perf_counter_task_sched_out(prev, next, cpu); rq->nr_switches++; rq->curr = next; @@ -4744,11 +5352,72 @@ need_resched_nonpreemptible: goto need_resched_nonpreemptible; preempt_enable_no_resched(); - if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) + if (need_resched()) goto need_resched; } EXPORT_SYMBOL(schedule); +#ifdef CONFIG_SMP +/* + * Look out! "owner" is an entirely speculative pointer + * access and not reliable. + */ +int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) +{ + unsigned int cpu; + struct rq *rq; + + if (!sched_feat(OWNER_SPIN)) + return 0; + +#ifdef CONFIG_DEBUG_PAGEALLOC + /* + * Need to access the cpu field knowing that + * DEBUG_PAGEALLOC could have unmapped it if + * the mutex owner just released it and exited. + */ + if (probe_kernel_address(&owner->cpu, cpu)) + goto out; +#else + cpu = owner->cpu; +#endif + + /* + * Even if the access succeeded (likely case), + * the cpu field may no longer be valid. + */ + if (cpu >= nr_cpumask_bits) + goto out; + + /* + * We need to validate that we can do a + * get_cpu() and that we have the percpu area. + */ + if (!cpu_online(cpu)) + goto out; + + rq = cpu_rq(cpu); + + for (;;) { + /* + * Owner changed, break to re-assess state. + */ + if (lock->owner != owner) + break; + + /* + * Is that owner really running on that cpu? + */ + if (task_thread_info(rq->curr) != owner || need_resched()) + return 0; + + cpu_relax(); + } +out: + return 1; +} +#endif + #ifdef CONFIG_PREEMPT /* * this is the entry point to schedule() from in-kernel preemption @@ -4826,7 +5495,7 @@ EXPORT_SYMBOL(default_wake_function); * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns * zero in this (rare) case, and we handle it by continuing to scan the queue. */ -void __wake_up_common(wait_queue_head_t *q, unsigned int mode, +static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, int nr_exclusive, int sync, void *key) { wait_queue_t *curr, *next; @@ -4846,6 +5515,9 @@ void __wake_up_common(wait_queue_head_t *q, unsigned int mode, * @mode: which threads * @nr_exclusive: how many wake-one or wake-many threads to wake up * @key: is directly passed to the wakeup function + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. */ void __wake_up(wait_queue_head_t *q, unsigned int mode, int nr_exclusive, void *key) @@ -4866,11 +5538,17 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) __wake_up_common(q, mode, 1, 0, NULL); } +void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) +{ + __wake_up_common(q, mode, 1, 0, key); +} + /** - * __wake_up_sync - wake up threads blocked on a waitqueue. + * __wake_up_sync_key - wake up threads blocked on a waitqueue. * @q: the waitqueue * @mode: which threads * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: opaque value to be passed to wakeup targets * * The sync wakeup differs that the waker knows that it will schedule * away soon, so while the target thread will be woken up, it will not @@ -4878,9 +5556,12 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) * with each other. This can prevent needless bouncing between CPUs. * * On UP it can prevent extra preemption. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. */ -void -__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) { unsigned long flags; int sync = 1; @@ -4892,9 +5573,18 @@ __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) sync = 0; spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, sync, NULL); + __wake_up_common(q, mode, nr_exclusive, sync, key); spin_unlock_irqrestore(&q->lock, flags); } +EXPORT_SYMBOL_GPL(__wake_up_sync_key); + +/* + * __wake_up_sync - see __wake_up_sync_key() + */ +void __wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +{ + __wake_up_sync_key(q, mode, nr_exclusive, NULL); +} EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ /** @@ -4905,6 +5595,9 @@ EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ * awakened in the same order in which they were queued. * * See also complete_all(), wait_for_completion() and related routines. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. */ void complete(struct completion *x) { @@ -4922,6 +5615,9 @@ EXPORT_SYMBOL(complete); * @x: holds the state of this particular completion * * This will wake up all threads waiting on this particular completion event. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. */ void complete_all(struct completion *x) { @@ -6078,15 +6774,11 @@ void sched_show_task(struct task_struct *p) printk(KERN_CONT " %016lx ", thread_saved_pc(p)); #endif #ifdef CONFIG_DEBUG_STACK_USAGE - { - unsigned long *n = end_of_stack(p); - while (!*n) - n++; - free = (unsigned long)n - (unsigned long)end_of_stack(p); - } + free = stack_not_used(p); #endif - printk(KERN_CONT "%5lu %5d %6d\n", free, - task_pid_nr(p), task_pid_nr(p->real_parent)); + printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, + task_pid_nr(p), task_pid_nr(p->real_parent), + (unsigned long)task_thread_info(p)->flags); show_stack(p, NULL); } @@ -6565,6 +7257,14 @@ static void migrate_dead_tasks(unsigned int dead_cpu) } } + +/* + * remove the tasks which were accounted by rq from calc_load_tasks. + */ +static void calc_global_load_remove(struct rq *rq) +{ + atomic_long_sub(rq->calc_load_active, &calc_load_tasks); +} #endif /* CONFIG_HOTPLUG_CPU */ #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) @@ -6799,6 +7499,8 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) /* Update our root-domain */ rq = cpu_rq(cpu); spin_lock_irqsave(&rq->lock, flags); + rq->calc_load_update = calc_load_update; + rq->calc_load_active = 0; if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); @@ -6838,7 +7540,7 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) cpuset_unlock(); migrate_nr_uninterruptible(rq); BUG_ON(rq->nr_running != 0); - + calc_global_load_remove(rq); /* * No need to migrate the tasks: it was best-effort if * they didn't take sched_hotcpu_mutex. Just wake up @@ -6874,8 +7576,10 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) return NOTIFY_OK; } -/* Register at highest priority so that task migration (migrate_all_tasks) - * happens before everything else. +/* + * Register at high priority so that task migration (migrate_all_tasks) + * happens before everything else. This has to be lower priority than + * the notifier in the perf_counter subsystem, though. */ static struct notifier_block __cpuinitdata migration_notifier = { .notifier_call = migration_call, @@ -6962,7 +7666,12 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, cpumask_or(groupmask, groupmask, sched_group_cpus(group)); cpulist_scnprintf(str, sizeof(str), sched_group_cpus(group)); + printk(KERN_CONT " %s", str); + if (group->__cpu_power != SCHED_LOAD_SCALE) { + printk(KERN_CONT " (__cpu_power = %d)", + group->__cpu_power); + } group = group->next; } while (group != sd->groups); @@ -7115,24 +7824,21 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) static int __init_refok init_rootdomain(struct root_domain *rd, bool bootmem) { + gfp_t gfp = GFP_KERNEL; + memset(rd, 0, sizeof(*rd)); - if (bootmem) { - alloc_bootmem_cpumask_var(&def_root_domain.span); - alloc_bootmem_cpumask_var(&def_root_domain.online); - alloc_bootmem_cpumask_var(&def_root_domain.rto_mask); - cpupri_init(&rd->cpupri, true); - return 0; - } + if (bootmem) + gfp = GFP_NOWAIT; - if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) + if (!alloc_cpumask_var(&rd->span, gfp)) goto out; - if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) + if (!alloc_cpumask_var(&rd->online, gfp)) goto free_span; - if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + if (!alloc_cpumask_var(&rd->rto_mask, gfp)) goto free_online; - if (cpupri_init(&rd->cpupri, false) != 0) + if (cpupri_init(&rd->cpupri, bootmem) != 0) goto free_rto_mask; return 0; @@ -7343,8 +8049,9 @@ int sched_smt_power_savings = 0, sched_mc_power_savings = 0; /* * The cpus mask in sched_group and sched_domain hangs off the end. - * FIXME: use cpumask_var_t or dynamic percpu alloc to avoid wasting space - * for nr_cpu_ids < CONFIG_NR_CPUS. + * + * ( See the the comments in include/linux/sched.h:struct sched_group + * and struct sched_domain. ) */ struct static_sched_group { struct sched_group sg; @@ -7388,7 +8095,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map, { int group; - cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map); + cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); group = cpumask_first(mask); if (sg) *sg = &per_cpu(sched_group_core, group).sg; @@ -7417,7 +8124,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); group = cpumask_first(mask); #elif defined(CONFIG_SCHED_SMT) - cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map); + cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); group = cpumask_first(mask); #else group = cpu; @@ -7465,7 +8172,7 @@ static void init_numa_sched_groups_power(struct sched_group *group_head) struct sched_domain *sd; sd = &per_cpu(phys_domains, j).sd; - if (j != cpumask_first(sched_group_cpus(sd->groups))) { + if (j != group_first_cpu(sd->groups)) { /* * Only add "power" once for each * physical package. @@ -7543,7 +8250,7 @@ static void init_sched_groups_power(int cpu, struct sched_domain *sd) WARN_ON(!sd || !sd->groups); - if (cpu != cpumask_first(sched_group_cpus(sd->groups))) + if (cpu != group_first_cpu(sd->groups)) return; child = sd->child; @@ -7760,7 +8467,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map, SD_INIT(sd, SIBLING); set_domain_attribute(sd, attr); cpumask_and(sched_domain_span(sd), - &per_cpu(cpu_sibling_map, i), cpu_map); + topology_thread_cpumask(i), cpu_map); sd->parent = p; p->child = sd; cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask); @@ -7771,7 +8478,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map, /* Set up CPU (sibling) groups */ for_each_cpu(i, cpu_map) { cpumask_and(this_sibling_map, - &per_cpu(cpu_sibling_map, i), cpu_map); + topology_thread_cpumask(i), cpu_map); if (i != cpumask_first(this_sibling_map)) continue; @@ -8447,12 +9154,15 @@ void __init sched_init(void) #ifdef CONFIG_USER_SCHED alloc_size *= 2; #endif +#ifdef CONFIG_CPUMASK_OFFSTACK + alloc_size += num_possible_cpus() * cpumask_size(); +#endif /* * As sched_init() is called before page_alloc is setup, * we use alloc_bootmem(). */ if (alloc_size) { - ptr = (unsigned long)alloc_bootmem(alloc_size); + ptr = (unsigned long)kzalloc(alloc_size, GFP_NOWAIT); #ifdef CONFIG_FAIR_GROUP_SCHED init_task_group.se = (struct sched_entity **)ptr; @@ -8484,6 +9194,12 @@ void __init sched_init(void) ptr += nr_cpu_ids * sizeof(void **); #endif /* CONFIG_USER_SCHED */ #endif /* CONFIG_RT_GROUP_SCHED */ +#ifdef CONFIG_CPUMASK_OFFSTACK + for_each_possible_cpu(i) { + per_cpu(load_balance_tmpmask, i) = (void *)ptr; + ptr += cpumask_size(); + } +#endif /* CONFIG_CPUMASK_OFFSTACK */ } #ifdef CONFIG_SMP @@ -8519,6 +9235,8 @@ void __init sched_init(void) rq = cpu_rq(i); spin_lock_init(&rq->lock); rq->nr_running = 0; + rq->calc_load_active = 0; + rq->calc_load_update = jiffies + LOAD_FREQ; init_cfs_rq(&rq->cfs, rq); init_rt_rq(&rq->rt, rq); #ifdef CONFIG_FAIR_GROUP_SCHED @@ -8539,7 +9257,7 @@ void __init sched_init(void) * 1024) and two child groups A0 and A1 (of weight 1024 each), * then A0's share of the cpu resource is: * - * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% + * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% * * We achieve this by letting init_task_group's tasks sit * directly in rq->cfs (i.e init_task_group->se[] = NULL). @@ -8626,20 +9344,26 @@ void __init sched_init(void) * when this runqueue becomes "idle". */ init_idle(current, smp_processor_id()); + + calc_load_update = jiffies + LOAD_FREQ; + /* * During early bootup we pretend to be a normal task: */ current->sched_class = &fair_sched_class; /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ - alloc_bootmem_cpumask_var(&nohz_cpu_mask); + alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ - alloc_bootmem_cpumask_var(&nohz.cpu_mask); + alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); + alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); #endif - alloc_bootmem_cpumask_var(&cpu_isolated_map); + alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ + perf_counter_init(); + scheduler_running = 1; } @@ -9381,6 +10105,13 @@ static int sched_rt_global_constraints(void) if (sysctl_sched_rt_period <= 0) return -EINVAL; + /* + * There's always some RT tasks in the root group + * -- migration, kstopmachine etc.. + */ + if (sysctl_sched_rt_runtime == 0) + return -EBUSY; + spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); for_each_possible_cpu(i) { struct rt_rq *rt_rq = &cpu_rq(i)->rt; @@ -9576,6 +10307,7 @@ struct cpuacct { struct cgroup_subsys_state css; /* cpuusage holds pointer to a u64-type object on every cpu */ u64 *cpuusage; + struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; struct cpuacct *parent; }; @@ -9600,20 +10332,32 @@ static struct cgroup_subsys_state *cpuacct_create( struct cgroup_subsys *ss, struct cgroup *cgrp) { struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); + int i; if (!ca) - return ERR_PTR(-ENOMEM); + goto out; ca->cpuusage = alloc_percpu(u64); - if (!ca->cpuusage) { - kfree(ca); - return ERR_PTR(-ENOMEM); - } + if (!ca->cpuusage) + goto out_free_ca; + + for (i = 0; i < CPUACCT_STAT_NSTATS; i++) + if (percpu_counter_init(&ca->cpustat[i], 0)) + goto out_free_counters; if (cgrp->parent) ca->parent = cgroup_ca(cgrp->parent); return &ca->css; + +out_free_counters: + while (--i >= 0) + percpu_counter_destroy(&ca->cpustat[i]); + free_percpu(ca->cpuusage); +out_free_ca: + kfree(ca); +out: + return ERR_PTR(-ENOMEM); } /* destroy an existing cpu accounting group */ @@ -9621,14 +10365,17 @@ static void cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) { struct cpuacct *ca = cgroup_ca(cgrp); + int i; + for (i = 0; i < CPUACCT_STAT_NSTATS; i++) + percpu_counter_destroy(&ca->cpustat[i]); free_percpu(ca->cpuusage); kfree(ca); } static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); u64 data; #ifndef CONFIG_64BIT @@ -9647,7 +10394,7 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); #ifndef CONFIG_64BIT /* @@ -9708,6 +10455,25 @@ static int cpuacct_percpu_seq_read(struct cgroup *cgroup, struct cftype *cft, 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 i; + + for (i = 0; i < CPUACCT_STAT_NSTATS; i++) { + s64 val = percpu_counter_read(&ca->cpustat[i]); + val = cputime64_to_clock_t(val); + cb->fill(cb, cpuacct_stat_desc[i], val); + } + return 0; +} + static struct cftype files[] = { { .name = "usage", @@ -9718,7 +10484,10 @@ static struct cftype files[] = { .name = "usage_percpu", .read_seq_string = cpuacct_percpu_seq_read, }, - + { + .name = "stat", + .read_map = cpuacct_stats_show, + }, }; static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) @@ -9740,12 +10509,38 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime) return; cpu = task_cpu(tsk); + + rcu_read_lock(); + ca = task_ca(tsk); for (; ca; ca = ca->parent) { - u64 *cpuusage = percpu_ptr(ca->cpuusage, cpu); + u64 *cpuusage = per_cpu_ptr(ca->cpuusage, cpu); *cpuusage += cputime; } + + rcu_read_unlock(); +} + +/* + * Charge the system/user time to the task's accounting group. + */ +static void cpuacct_update_stats(struct task_struct *tsk, + enum cpuacct_stat_index idx, cputime_t val) +{ + struct cpuacct *ca; + + if (unlikely(!cpuacct_subsys.active)) + return; + + rcu_read_lock(); + ca = task_ca(tsk); + + do { + percpu_counter_add(&ca->cpustat[idx], val); + ca = ca->parent; + } while (ca); + rcu_read_unlock(); } struct cgroup_subsys cpuacct_subsys = {