diff options
| author | Paul Mundt <lethal@linux-sh.org> | 2011-01-13 15:06:28 +0900 |
|---|---|---|
| committer | Paul Mundt <lethal@linux-sh.org> | 2011-01-13 15:06:28 +0900 |
| commit | f43dc23d5ea91fca257be02138a255f02d98e806 (patch) | |
| tree | b29722f6e965316e90ac97abf79923ced250dc21 /kernel/sched.c | |
| parent | f8e53553f452dcbf67cb89c8cba63a1cd6eb4cc0 (diff) | |
| parent | 4162cf64973df51fc885825bc9ca4d055891c49f (diff) | |
Merge branch 'master' of master.kernel.org:/pub/scm/linux/kernel/git/torvalds/linux-2.6 into common/serial-rework
Conflicts:
arch/sh/kernel/cpu/sh2/setup-sh7619.c
arch/sh/kernel/cpu/sh2a/setup-mxg.c
arch/sh/kernel/cpu/sh2a/setup-sh7201.c
arch/sh/kernel/cpu/sh2a/setup-sh7203.c
arch/sh/kernel/cpu/sh2a/setup-sh7206.c
arch/sh/kernel/cpu/sh3/setup-sh7705.c
arch/sh/kernel/cpu/sh3/setup-sh770x.c
arch/sh/kernel/cpu/sh3/setup-sh7710.c
arch/sh/kernel/cpu/sh3/setup-sh7720.c
arch/sh/kernel/cpu/sh4/setup-sh4-202.c
arch/sh/kernel/cpu/sh4/setup-sh7750.c
arch/sh/kernel/cpu/sh4/setup-sh7760.c
arch/sh/kernel/cpu/sh4a/setup-sh7343.c
arch/sh/kernel/cpu/sh4a/setup-sh7366.c
arch/sh/kernel/cpu/sh4a/setup-sh7722.c
arch/sh/kernel/cpu/sh4a/setup-sh7723.c
arch/sh/kernel/cpu/sh4a/setup-sh7724.c
arch/sh/kernel/cpu/sh4a/setup-sh7763.c
arch/sh/kernel/cpu/sh4a/setup-sh7770.c
arch/sh/kernel/cpu/sh4a/setup-sh7780.c
arch/sh/kernel/cpu/sh4a/setup-sh7785.c
arch/sh/kernel/cpu/sh4a/setup-sh7786.c
arch/sh/kernel/cpu/sh4a/setup-shx3.c
arch/sh/kernel/cpu/sh5/setup-sh5.c
drivers/serial/sh-sci.c
drivers/serial/sh-sci.h
include/linux/serial_sci.h
Diffstat (limited to 'kernel/sched.c')
| -rw-r--r-- | kernel/sched.c | 6016 |
1 files changed, 2350 insertions, 3666 deletions
diff --git a/kernel/sched.c b/kernel/sched.c index 7c9098d186e..a0eb0941fa8 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -39,7 +39,7 @@ #include <linux/completion.h> #include <linux/kernel_stat.h> #include <linux/debug_locks.h> -#include <linux/perf_counter.h> +#include <linux/perf_event.h> #include <linux/security.h> #include <linux/notifier.h> #include <linux/profile.h> @@ -55,16 +55,15 @@ #include <linux/cpu.h> #include <linux/cpuset.h> #include <linux/percpu.h> -#include <linux/kthread.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> +#include <linux/stop_machine.h> #include <linux/sysctl.h> #include <linux/syscalls.h> #include <linux/times.h> #include <linux/tsacct_kern.h> #include <linux/kprobes.h> #include <linux/delayacct.h> -#include <linux/reciprocal_div.h> #include <linux/unistd.h> #include <linux/pagemap.h> #include <linux/hrtimer.h> @@ -72,11 +71,15 @@ #include <linux/debugfs.h> #include <linux/ctype.h> #include <linux/ftrace.h> +#include <linux/slab.h> #include <asm/tlb.h> #include <asm/irq_regs.h> +#include <asm/mutex.h> #include "sched_cpupri.h" +#include "workqueue_sched.h" +#include "sched_autogroup.h" #define CREATE_TRACE_POINTS #include <trace/events/sched.h> @@ -120,30 +123,6 @@ */ #define RUNTIME_INF ((u64)~0ULL) -#ifdef CONFIG_SMP - -static void double_rq_lock(struct rq *rq1, struct rq *rq2); - -/* - * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) - * Since cpu_power is a 'constant', we can use a reciprocal divide. - */ -static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load) -{ - return reciprocal_divide(load, sg->reciprocal_cpu_power); -} - -/* - * Each time a sched group cpu_power is changed, - * we must compute its reciprocal value - */ -static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val) -{ - sg->__cpu_power += val; - sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power); -} -#endif - static inline int rt_policy(int policy) { if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) @@ -166,7 +145,7 @@ struct rt_prio_array { struct rt_bandwidth { /* nests inside the rq lock: */ - spinlock_t rt_runtime_lock; + raw_spinlock_t rt_runtime_lock; ktime_t rt_period; u64 rt_runtime; struct hrtimer rt_period_timer; @@ -203,7 +182,7 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) rt_b->rt_period = ns_to_ktime(period); rt_b->rt_runtime = runtime; - spin_lock_init(&rt_b->rt_runtime_lock); + raw_spin_lock_init(&rt_b->rt_runtime_lock); hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); @@ -225,7 +204,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) if (hrtimer_active(&rt_b->rt_period_timer)) return; - spin_lock(&rt_b->rt_runtime_lock); + raw_spin_lock(&rt_b->rt_runtime_lock); for (;;) { unsigned long delta; ktime_t soft, hard; @@ -242,7 +221,7 @@ static void start_rt_bandwidth(struct rt_bandwidth *rt_b) __hrtimer_start_range_ns(&rt_b->rt_period_timer, soft, delta, HRTIMER_MODE_ABS_PINNED, 0); } - spin_unlock(&rt_b->rt_runtime_lock); + raw_spin_unlock(&rt_b->rt_runtime_lock); } #ifdef CONFIG_RT_GROUP_SCHED @@ -258,7 +237,7 @@ static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) */ static DEFINE_MUTEX(sched_domains_mutex); -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED #include <linux/cgroup.h> @@ -268,13 +247,7 @@ static LIST_HEAD(task_groups); /* task group related information */ struct task_group { -#ifdef CONFIG_CGROUP_SCHED struct cgroup_subsys_state css; -#endif - -#ifdef CONFIG_USER_SCHED - uid_t uid; -#endif #ifdef CONFIG_FAIR_GROUP_SCHED /* schedulable entities of this group on each cpu */ @@ -282,6 +255,8 @@ struct task_group { /* runqueue "owned" by this group on each cpu */ struct cfs_rq **cfs_rq; unsigned long shares; + + atomic_t load_weight; #endif #ifdef CONFIG_RT_GROUP_SCHED @@ -297,56 +272,18 @@ struct task_group { struct task_group *parent; struct list_head siblings; struct list_head children; -}; - -#ifdef CONFIG_USER_SCHED - -/* Helper function to pass uid information to create_sched_user() */ -void set_tg_uid(struct user_struct *user) -{ - user->tg->uid = user->uid; -} -/* - * Root task group. - * Every UID task group (including init_task_group aka UID-0) will - * be a child to this group. - */ -struct task_group root_task_group; - -#ifdef CONFIG_FAIR_GROUP_SCHED -/* Default task group's sched entity on each cpu */ -static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); -/* Default task group's cfs_rq on each cpu */ -static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp; -#endif /* CONFIG_FAIR_GROUP_SCHED */ - -#ifdef CONFIG_RT_GROUP_SCHED -static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); -static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp; -#endif /* CONFIG_RT_GROUP_SCHED */ -#else /* !CONFIG_USER_SCHED */ -#define root_task_group init_task_group -#endif /* CONFIG_USER_SCHED */ +#ifdef CONFIG_SCHED_AUTOGROUP + struct autogroup *autogroup; +#endif +}; -/* task_group_lock serializes add/remove of task groups and also changes to - * a task group's cpu shares. - */ +/* task_group_lock serializes the addition/removal of task groups */ static DEFINE_SPINLOCK(task_group_lock); -#ifdef CONFIG_SMP -static int root_task_group_empty(void) -{ - return list_empty(&root_task_group.children); -} -#endif - #ifdef CONFIG_FAIR_GROUP_SCHED -#ifdef CONFIG_USER_SCHED -# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) -#else /* !CONFIG_USER_SCHED */ -# define INIT_TASK_GROUP_LOAD NICE_0_LOAD -#endif /* CONFIG_USER_SCHED */ + +# define ROOT_TASK_GROUP_LOAD NICE_0_LOAD /* * A weight of 0 or 1 can cause arithmetics problems. @@ -359,62 +296,15 @@ static int root_task_group_empty(void) #define MIN_SHARES 2 #define MAX_SHARES (1UL << 18) -static int init_task_group_load = INIT_TASK_GROUP_LOAD; +static int root_task_group_load = ROOT_TASK_GROUP_LOAD; #endif /* Default task group. * Every task in system belong to this group at bootup. */ -struct task_group init_task_group; - -/* return group to which a task belongs */ -static inline struct task_group *task_group(struct task_struct *p) -{ - struct task_group *tg; - -#ifdef CONFIG_USER_SCHED - rcu_read_lock(); - tg = __task_cred(p)->user->tg; - rcu_read_unlock(); -#elif defined(CONFIG_CGROUP_SCHED) - tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), - struct task_group, css); -#else - tg = &init_task_group; -#endif - return tg; -} - -/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ -static inline void set_task_rq(struct task_struct *p, unsigned int cpu) -{ -#ifdef CONFIG_FAIR_GROUP_SCHED - p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; - p->se.parent = task_group(p)->se[cpu]; -#endif - -#ifdef CONFIG_RT_GROUP_SCHED - p->rt.rt_rq = task_group(p)->rt_rq[cpu]; - p->rt.parent = task_group(p)->rt_se[cpu]; -#endif -} - -#else - -#ifdef CONFIG_SMP -static int root_task_group_empty(void) -{ - return 1; -} -#endif - -static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } -static inline struct task_group *task_group(struct task_struct *p) -{ - return NULL; -} +struct task_group root_task_group; -#endif /* CONFIG_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ /* CFS-related fields in a runqueue */ struct cfs_rq { @@ -449,6 +339,7 @@ struct cfs_rq { * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This * list is used during load balance. */ + int on_list; struct list_head leaf_cfs_rq_list; struct task_group *tg; /* group that "owns" this runqueue */ @@ -467,14 +358,17 @@ struct cfs_rq { unsigned long h_load; /* - * this cpu's part of tg->shares + * Maintaining per-cpu shares distribution for group scheduling + * + * load_stamp is the last time we updated the load average + * load_last is the last time we updated the load average and saw load + * load_unacc_exec_time is currently unaccounted execution time */ - unsigned long shares; + u64 load_avg; + u64 load_period; + u64 load_stamp, load_last, load_unacc_exec_time; - /* - * load.weight at the time we set shares - */ - unsigned long rq_weight; + unsigned long load_contribution; #endif #endif }; @@ -493,6 +387,7 @@ struct rt_rq { #endif #ifdef CONFIG_SMP unsigned long rt_nr_migratory; + unsigned long rt_nr_total; int overloaded; struct plist_head pushable_tasks; #endif @@ -500,7 +395,7 @@ struct rt_rq { u64 rt_time; u64 rt_runtime; /* Nests inside the rq lock: */ - spinlock_t rt_runtime_lock; + raw_spinlock_t rt_runtime_lock; #ifdef CONFIG_RT_GROUP_SCHED unsigned long rt_nr_boosted; @@ -508,7 +403,6 @@ struct rt_rq { struct rq *rq; struct list_head leaf_rt_rq_list; struct task_group *tg; - struct sched_rt_entity *rt_se; #endif }; @@ -533,17 +427,7 @@ struct root_domain { */ cpumask_var_t rto_mask; atomic_t rto_count; -#ifdef CONFIG_SMP struct cpupri cpupri; -#endif -#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) - /* - * Preferred wake up cpu nominated by sched_mc balance that will be - * used when most cpus are idle in the system indicating overall very - * low system utilisation. Triggered at POWERSAVINGS_BALANCE_WAKEUP(2) - */ - unsigned int sched_mc_preferred_wakeup_cpu; -#endif }; /* @@ -552,7 +436,7 @@ struct root_domain { */ static struct root_domain def_root_domain; -#endif +#endif /* CONFIG_SMP */ /* * This is the main, per-CPU runqueue data structure. @@ -563,7 +447,7 @@ static struct root_domain def_root_domain; */ struct rq { /* runqueue lock: */ - spinlock_t lock; + raw_spinlock_t lock; /* * nr_running and cpu_load should be in the same cacheline because @@ -572,15 +456,17 @@ struct rq { unsigned long nr_running; #define CPU_LOAD_IDX_MAX 5 unsigned long cpu_load[CPU_LOAD_IDX_MAX]; + unsigned long last_load_update_tick; #ifdef CONFIG_NO_HZ - unsigned long last_tick_seen; - unsigned char in_nohz_recently; + u64 nohz_stamp; + unsigned char nohz_balance_kick; #endif + unsigned int skip_clock_update; + /* capture load from *all* tasks on this cpu: */ struct load_weight load; unsigned long nr_load_updates; u64 nr_switches; - u64 nr_migrations_in; struct cfs_rq cfs; struct rt_rq rt; @@ -601,11 +487,12 @@ struct rq { */ unsigned long nr_uninterruptible; - struct task_struct *curr, *idle; + struct task_struct *curr, *idle, *stop; unsigned long next_balance; struct mm_struct *prev_mm; u64 clock; + u64 clock_task; atomic_t nr_iowait; @@ -613,18 +500,28 @@ struct rq { struct root_domain *rd; struct sched_domain *sd; + unsigned long cpu_power; + unsigned char idle_at_tick; /* For active balancing */ + int post_schedule; int active_balance; int push_cpu; + struct cpu_stop_work active_balance_work; /* cpu of this runqueue: */ int cpu; int online; unsigned long avg_load_per_task; - struct task_struct *migration_thread; - struct list_head migration_queue; + u64 rt_avg; + u64 age_stamp; + u64 idle_stamp; + u64 avg_idle; +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; #endif /* calc_load related fields */ @@ -664,10 +561,8 @@ struct rq { static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); -static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync) -{ - rq->curr->sched_class->check_preempt_curr(rq, p, sync); -} + +static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags); static inline int cpu_of(struct rq *rq) { @@ -678,6 +573,11 @@ static inline int cpu_of(struct rq *rq) #endif } +#define rcu_dereference_check_sched_domain(p) \ + rcu_dereference_check((p), \ + rcu_read_lock_sched_held() || \ + lockdep_is_held(&sched_domains_mutex)) + /* * The domain tree (rq->sd) is protected by RCU's quiescent state transition. * See detach_destroy_domains: synchronize_sched for details. @@ -686,16 +586,72 @@ static inline int cpu_of(struct rq *rq) * preempt-disabled sections. */ #define for_each_domain(cpu, __sd) \ - for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) + for (__sd = rcu_dereference_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) #define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) #define this_rq() (&__get_cpu_var(runqueues)) #define task_rq(p) cpu_rq(task_cpu(p)) #define cpu_curr(cpu) (cpu_rq(cpu)->curr) +#define raw_rq() (&__raw_get_cpu_var(runqueues)) + +#ifdef CONFIG_CGROUP_SCHED -inline void update_rq_clock(struct rq *rq) +/* + * Return the group to which this tasks belongs. + * + * We use task_subsys_state_check() and extend the RCU verification + * with lockdep_is_held(&task_rq(p)->lock) because cpu_cgroup_attach() + * holds that lock for each task it moves into the cgroup. Therefore + * by holding that lock, we pin the task to the current cgroup. + */ +static inline struct task_group *task_group(struct task_struct *p) { - rq->clock = sched_clock_cpu(cpu_of(rq)); + struct task_group *tg; + struct cgroup_subsys_state *css; + + css = task_subsys_state_check(p, cpu_cgroup_subsys_id, + lockdep_is_held(&task_rq(p)->lock)); + tg = container_of(css, struct task_group, css); + + return autogroup_task_group(p, tg); +} + +/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; + p->se.parent = task_group(p)->se[cpu]; +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + p->rt.rt_rq = task_group(p)->rt_rq[cpu]; + p->rt.parent = task_group(p)->rt_se[cpu]; +#endif +} + +#else /* CONFIG_CGROUP_SCHED */ + +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} + +#endif /* CONFIG_CGROUP_SCHED */ + +static void update_rq_clock_task(struct rq *rq, s64 delta); + +static void update_rq_clock(struct rq *rq) +{ + s64 delta; + + if (rq->skip_clock_update) + return; + + delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + rq->clock += delta; + update_rq_clock_task(rq, delta); } /* @@ -709,20 +665,15 @@ inline void update_rq_clock(struct rq *rq) /** * runqueue_is_locked + * @cpu: the processor in question. * * Returns true if the current cpu runqueue is locked. * This interface allows printk to be called with the runqueue lock * held and know whether or not it is OK to wake up the klogd. */ -int runqueue_is_locked(void) +int runqueue_is_locked(int cpu) { - int cpu = get_cpu(); - struct rq *rq = cpu_rq(cpu); - int ret; - - ret = spin_is_locked(&rq->lock); - put_cpu(); - return ret; + return raw_spin_is_locked(&cpu_rq(cpu)->lock); } /* @@ -777,7 +728,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, size_t cnt, loff_t *ppos) { char buf[64]; - char *cmp = buf; + char *cmp; int neg = 0; int i; @@ -788,16 +739,15 @@ sched_feat_write(struct file *filp, const char __user *ubuf, return -EFAULT; buf[cnt] = 0; + cmp = strstrip(buf); - if (strncmp(buf, "NO_", 3) == 0) { + if (strncmp(cmp, "NO_", 3) == 0) { neg = 1; cmp += 3; } for (i = 0; sched_feat_names[i]; i++) { - int len = strlen(sched_feat_names[i]); - - if (strncmp(cmp, sched_feat_names[i], len) == 0) { + if (strcmp(cmp, sched_feat_names[i]) == 0) { if (neg) sysctl_sched_features &= ~(1UL << i); else @@ -809,7 +759,7 @@ sched_feat_write(struct file *filp, const char __user *ubuf, if (!sched_feat_names[i]) return -EINVAL; - filp->f_pos += cnt; + *ppos += cnt; return cnt; } @@ -819,7 +769,7 @@ static int sched_feat_open(struct inode *inode, struct file *filp) return single_open(filp, sched_feat_show, NULL); } -static struct file_operations sched_feat_fops = { +static const struct file_operations sched_feat_fops = { .open = sched_feat_open, .write = sched_feat_write, .read = seq_read, @@ -847,17 +797,12 @@ late_initcall(sched_init_debug); const_debug unsigned int sysctl_sched_nr_migrate = 32; /* - * ratelimit for updating the group shares. - * default: 0.25ms - */ -unsigned int sysctl_sched_shares_ratelimit = 250000; - -/* - * Inject some fuzzyness into changing the per-cpu group shares - * this avoids remote rq-locks at the expense of fairness. - * default: 4 + * period over which we average the RT time consumption, measured + * in ms. + * + * default: 1s */ -unsigned int sysctl_sched_shares_thresh = 4; +const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC; /* * period over which we measure -rt task cpu usage in us. @@ -921,7 +866,7 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) */ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); } #else /* __ARCH_WANT_UNLOCKED_CTXSW */ @@ -945,9 +890,9 @@ static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) next->oncpu = 1; #endif #ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); #else - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); #endif } @@ -969,18 +914,29 @@ static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) #endif /* __ARCH_WANT_UNLOCKED_CTXSW */ /* + * Check whether the task is waking, we use this to synchronize ->cpus_allowed + * against ttwu(). + */ +static inline int task_is_waking(struct task_struct *p) +{ + return unlikely(p->state == TASK_WAKING); +} + +/* * __task_rq_lock - lock the runqueue a given task resides on. * Must be called interrupts disabled. */ static inline struct rq *__task_rq_lock(struct task_struct *p) __acquires(rq->lock) { + struct rq *rq; + for (;;) { - struct rq *rq = task_rq(p); - spin_lock(&rq->lock); + rq = task_rq(p); + raw_spin_lock(&rq->lock); if (likely(rq == task_rq(p))) return rq; - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); } } @@ -997,31 +953,23 @@ static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) for (;;) { local_irq_save(*flags); rq = task_rq(p); - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); if (likely(rq == task_rq(p))) return rq; - spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock_irqrestore(&rq->lock, *flags); } } -void task_rq_unlock_wait(struct task_struct *p) -{ - struct rq *rq = task_rq(p); - - smp_mb(); /* spin-unlock-wait is not a full memory barrier */ - spin_unlock_wait(&rq->lock); -} - static void __task_rq_unlock(struct rq *rq) __releases(rq->lock) { - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); } static inline void task_rq_unlock(struct rq *rq, unsigned long *flags) __releases(rq->lock) { - spin_unlock_irqrestore(&rq->lock, *flags); + raw_spin_unlock_irqrestore(&rq->lock, *flags); } /* @@ -1034,7 +982,7 @@ static struct rq *this_rq_lock(void) local_irq_disable(); rq = this_rq(); - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); return rq; } @@ -1081,10 +1029,10 @@ static enum hrtimer_restart hrtick(struct hrtimer *timer) WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); update_rq_clock(rq); rq->curr->sched_class->task_tick(rq, rq->curr, 1); - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); return HRTIMER_NORESTART; } @@ -1097,10 +1045,10 @@ static void __hrtick_start(void *arg) { struct rq *rq = arg; - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); hrtimer_restart(&rq->hrtick_timer); rq->hrtick_csd_pending = 0; - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); } /* @@ -1207,7 +1155,7 @@ static void resched_task(struct task_struct *p) { int cpu; - assert_spin_locked(&task_rq(p)->lock); + assert_raw_spin_locked(&task_rq(p)->lock); if (test_tsk_need_resched(p)) return; @@ -1229,14 +1177,35 @@ static void resched_cpu(int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - if (!spin_trylock_irqsave(&rq->lock, flags)) + if (!raw_spin_trylock_irqsave(&rq->lock, flags)) return; resched_task(cpu_curr(cpu)); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); } #ifdef CONFIG_NO_HZ /* + * In the semi idle case, use the nearest busy cpu for migrating timers + * from an idle cpu. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle cpu will add more delays to the timers than intended + * (as that cpu's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(void) +{ + int cpu = smp_processor_id(); + int i; + struct sched_domain *sd; + + for_each_domain(cpu, sd) { + for_each_cpu(i, sched_domain_span(sd)) + if (!idle_cpu(i)) + return i; + } + return cpu; +} +/* * When add_timer_on() enqueues a timer into the timer wheel of an * idle CPU then this timer might expire before the next timer event * which is scheduled to wake up that CPU. In case of a completely @@ -1275,14 +1244,50 @@ void wake_up_idle_cpu(int cpu) if (!tsk_is_polling(rq->idle)) smp_send_reschedule(cpu); } + #endif /* CONFIG_NO_HZ */ +static u64 sched_avg_period(void) +{ + return (u64)sysctl_sched_time_avg * NSEC_PER_MSEC / 2; +} + +static void sched_avg_update(struct rq *rq) +{ + s64 period = sched_avg_period(); + + while ((s64)(rq->clock - rq->age_stamp) > period) { + /* + * Inline assembly required to prevent the compiler + * optimising this loop into a divmod call. + * See __iter_div_u64_rem() for another example of this. + */ + asm("" : "+rm" (rq->age_stamp)); + rq->age_stamp += period; + rq->rt_avg /= 2; + } +} + +static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) +{ + rq->rt_avg += rt_delta; + sched_avg_update(rq); +} + #else /* !CONFIG_SMP */ static void resched_task(struct task_struct *p) { - assert_spin_locked(&task_rq(p)->lock); + assert_raw_spin_locked(&task_rq(p)->lock); set_tsk_need_resched(p); } + +static void sched_rt_avg_update(struct rq *rq, u64 rt_delta) +{ +} + +static void sched_avg_update(struct rq *rq) +{ +} #endif /* CONFIG_SMP */ #if BITS_PER_LONG == 32 @@ -1340,6 +1345,12 @@ static inline void update_load_sub(struct load_weight *lw, unsigned long dec) lw->inv_weight = 0; } +static inline void update_load_set(struct load_weight *lw, unsigned long w) +{ + lw->weight = w; + lw->inv_weight = 0; +} + /* * To aid in avoiding the subversion of "niceness" due to uneven distribution * of tasks with abnormal "nice" values across CPUs the contribution that @@ -1393,32 +1404,6 @@ static const u32 prio_to_wmult[40] = { /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, }; -static void activate_task(struct rq *rq, struct task_struct *p, int wakeup); - -/* - * runqueue iterator, to support SMP load-balancing between different - * scheduling classes, without having to expose their internal data - * structures to the load-balancing proper: - */ -struct rq_iterator { - void *arg; - struct task_struct *(*start)(void *); - struct task_struct *(*next)(void *); -}; - -#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 - /* Time spent by the tasks of the cpu accounting group executing in ... */ enum cpuacct_stat_index { CPUACCT_STAT_USER, /* ... user mode */ @@ -1493,103 +1478,67 @@ static int tg_nop(struct task_group *tg, void *data) #endif #ifdef CONFIG_SMP -static unsigned long source_load(int cpu, int type); -static unsigned long target_load(int cpu, int type); -static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); - -static unsigned long cpu_avg_load_per_task(int cpu) +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) { - struct rq *rq = cpu_rq(cpu); - unsigned long nr_running = ACCESS_ONCE(rq->nr_running); - - if (nr_running) - rq->avg_load_per_task = rq->load.weight / nr_running; - else - rq->avg_load_per_task = 0; - - return rq->avg_load_per_task; + return cpu_rq(cpu)->load.weight; } -#ifdef CONFIG_FAIR_GROUP_SCHED - -static void __set_se_shares(struct sched_entity *se, unsigned long shares); - /* - * Calculate and set the cpu's group shares. + * Return a low guess at the load of a migration-source cpu weighted + * according to the scheduling class and "nice" value. + * + * We want to under-estimate the load of migration sources, to + * balance conservatively. */ -static void -update_group_shares_cpu(struct task_group *tg, int cpu, - unsigned long sd_shares, unsigned long sd_rq_weight) +static unsigned long source_load(int cpu, int type) { - unsigned long shares; - unsigned long rq_weight; - - if (!tg->se[cpu]) - return; - - rq_weight = tg->cfs_rq[cpu]->rq_weight; - - /* - * \Sum shares * rq_weight - * shares = ----------------------- - * \Sum rq_weight - * - */ - shares = (sd_shares * rq_weight) / sd_rq_weight; - shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES); - - if (abs(shares - tg->se[cpu]->load.weight) > - sysctl_sched_shares_thresh) { - struct rq *rq = cpu_rq(cpu); - unsigned long flags; + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); - spin_lock_irqsave(&rq->lock, flags); - tg->cfs_rq[cpu]->shares = shares; + if (type == 0 || !sched_feat(LB_BIAS)) + return total; - __set_se_shares(tg->se[cpu], shares); - spin_unlock_irqrestore(&rq->lock, flags); - } + return min(rq->cpu_load[type-1], total); } /* - * Re-compute the task group their per cpu shares over the given domain. - * This needs to be done in a bottom-up fashion because the rq weight of a - * parent group depends on the shares of its child groups. + * Return a high guess at the load of a migration-target cpu weighted + * according to the scheduling class and "nice" value. */ -static int tg_shares_up(struct task_group *tg, void *data) +static unsigned long target_load(int cpu, int type) { - unsigned long weight, rq_weight = 0; - unsigned long shares = 0; - struct sched_domain *sd = data; - int i; + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); - for_each_cpu(i, sched_domain_span(sd)) { - /* - * If there are currently no tasks on the cpu pretend there - * is one of average load so that when a new task gets to - * run here it will not get delayed by group starvation. - */ - weight = tg->cfs_rq[i]->load.weight; - if (!weight) - weight = NICE_0_LOAD; + if (type == 0 || !sched_feat(LB_BIAS)) + return total; - tg->cfs_rq[i]->rq_weight = weight; - rq_weight += weight; - shares += tg->cfs_rq[i]->shares; - } + return max(rq->cpu_load[type-1], total); +} - if ((!shares && rq_weight) || shares > tg->shares) - shares = tg->shares; +static unsigned long power_of(int cpu) +{ + return cpu_rq(cpu)->cpu_power; +} - if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) - shares = tg->shares; +static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); - for_each_cpu(i, sched_domain_span(sd)) - update_group_shares_cpu(tg, i, shares, rq_weight); +static unsigned long cpu_avg_load_per_task(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long nr_running = ACCESS_ONCE(rq->nr_running); - return 0; + if (nr_running) + rq->avg_load_per_task = rq->load.weight / nr_running; + else + rq->avg_load_per_task = 0; + + return rq->avg_load_per_task; } +#ifdef CONFIG_FAIR_GROUP_SCHED + /* * Compute the cpu's hierarchical load factor for each task group. * This needs to be done in a top-down fashion because the load of a child @@ -1604,7 +1553,7 @@ static int tg_load_down(struct task_group *tg, void *data) load = cpu_rq(cpu)->load.weight; } else { load = tg->parent->cfs_rq[cpu]->h_load; - load *= tg->cfs_rq[cpu]->shares; + load *= tg->se[cpu]->load.weight; load /= tg->parent->cfs_rq[cpu]->load.weight + 1; } @@ -1613,43 +1562,17 @@ static int tg_load_down(struct task_group *tg, void *data) return 0; } -static void update_shares(struct sched_domain *sd) -{ - u64 now = cpu_clock(raw_smp_processor_id()); - s64 elapsed = now - sd->last_update; - - if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { - sd->last_update = now; - walk_tg_tree(tg_nop, tg_shares_up, sd); - } -} - -static void update_shares_locked(struct rq *rq, struct sched_domain *sd) -{ - spin_unlock(&rq->lock); - update_shares(sd); - spin_lock(&rq->lock); -} - static void update_h_load(long cpu) { walk_tg_tree(tg_load_down, tg_nop, (void *)cpu); } -#else - -static inline void update_shares(struct sched_domain *sd) -{ -} - -static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) -{ -} - #endif #ifdef CONFIG_PREEMPT +static void double_rq_lock(struct rq *rq1, struct rq *rq2); + /* * fair double_lock_balance: Safely acquires both rq->locks in a fair * way at the expense of forcing extra atomic operations in all @@ -1663,7 +1586,7 @@ static inline int _double_lock_balance(struct rq *this_rq, struct rq *busiest) __acquires(busiest->lock) __acquires(this_rq->lock) { - spin_unlock(&this_rq->lock); + raw_spin_unlock(&this_rq->lock); double_rq_lock(this_rq, busiest); return 1; @@ -1684,14 +1607,16 @@ static int _double_lock_balance(struct rq *this_rq, struct rq *busiest) { int ret = 0; - if (unlikely(!spin_trylock(&busiest->lock))) { + if (unlikely(!raw_spin_trylock(&busiest->lock))) { if (busiest < this_rq) { - spin_unlock(&this_rq->lock); - spin_lock(&busiest->lock); - spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); + raw_spin_unlock(&this_rq->lock); + raw_spin_lock(&busiest->lock); + raw_spin_lock_nested(&this_rq->lock, + SINGLE_DEPTH_NESTING); ret = 1; } else - spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); + raw_spin_lock_nested(&busiest->lock, + SINGLE_DEPTH_NESTING); } return ret; } @@ -1705,7 +1630,7 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) { if (unlikely(!irqs_disabled())) { /* printk() doesn't work good under rq->lock */ - spin_unlock(&this_rq->lock); + raw_spin_unlock(&this_rq->lock); BUG_ON(1); } @@ -1715,34 +1640,81 @@ static int double_lock_balance(struct rq *this_rq, struct rq *busiest) static inline void double_unlock_balance(struct rq *this_rq, struct rq *busiest) __releases(busiest->lock) { - spin_unlock(&busiest->lock); + raw_spin_unlock(&busiest->lock); lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); } -#endif -#ifdef CONFIG_FAIR_GROUP_SCHED -static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) +/* + * double_rq_lock - safely lock two runqueues + * + * Note this does not disable interrupts like task_rq_lock, + * you need to do so manually before calling. + */ +static void double_rq_lock(struct rq *rq1, struct rq *rq2) + __acquires(rq1->lock) + __acquires(rq2->lock) { -#ifdef CONFIG_SMP - cfs_rq->shares = shares; -#endif + BUG_ON(!irqs_disabled()); + if (rq1 == rq2) { + raw_spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ + } else { + if (rq1 < rq2) { + raw_spin_lock(&rq1->lock); + raw_spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); + } else { + raw_spin_lock(&rq2->lock); + raw_spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); + } + } +} + +/* + * double_rq_unlock - safely unlock two runqueues + * + * Note this does not restore interrupts like task_rq_unlock, + * you need to do so manually after calling. + */ +static void double_rq_unlock(struct rq *rq1, struct rq *rq2) + __releases(rq1->lock) + __releases(rq2->lock) +{ + raw_spin_unlock(&rq1->lock); + if (rq1 != rq2) + raw_spin_unlock(&rq2->lock); + else + __release(rq2->lock); } + #endif -static void calc_load_account_active(struct rq *this_rq); +static void calc_load_account_idle(struct rq *this_rq); +static void update_sysctl(void); +static int get_update_sysctl_factor(void); +static void update_cpu_load(struct rq *this_rq); -#include "sched_stats.h" -#include "sched_idletask.c" -#include "sched_fair.c" -#include "sched_rt.c" -#ifdef CONFIG_SCHED_DEBUG -# include "sched_debug.c" +static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) +{ + set_task_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 +} -#define sched_class_highest (&rt_sched_class) +static const struct sched_class rt_sched_class; + +#define sched_class_highest (&stop_sched_class) #define for_each_class(class) \ for (class = sched_class_highest; class; class = class->next) +#include "sched_stats.h" + static void inc_nr_running(struct rq *rq) { rq->nr_running++; @@ -1755,12 +1727,6 @@ static void dec_nr_running(struct rq *rq) static void set_load_weight(struct task_struct *p) { - if (task_has_rt_policy(p)) { - p->se.load.weight = prio_to_weight[0] * 2; - p->se.load.inv_weight = prio_to_wmult[0] >> 1; - return; - } - /* * SCHED_IDLE tasks get minimal weight: */ @@ -1774,38 +1740,232 @@ static void set_load_weight(struct task_struct *p) p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; } -static void update_avg(u64 *avg, u64 sample) +static void enqueue_task(struct rq *rq, struct task_struct *p, int flags) { - s64 diff = sample - *avg; - *avg += diff >> 3; + update_rq_clock(rq); + sched_info_queued(p); + p->sched_class->enqueue_task(rq, p, flags); + p->se.on_rq = 1; } -static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) +static void dequeue_task(struct rq *rq, struct task_struct *p, int flags) { - if (wakeup) - p->se.start_runtime = p->se.sum_exec_runtime; + update_rq_clock(rq); + sched_info_dequeued(p); + p->sched_class->dequeue_task(rq, p, flags); + p->se.on_rq = 0; +} - sched_info_queued(p); - p->sched_class->enqueue_task(rq, p, wakeup); - p->se.on_rq = 1; +/* + * activate_task - move a task to the runqueue. + */ +static void activate_task(struct rq *rq, struct task_struct *p, int flags) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible--; + + enqueue_task(rq, p, flags); + inc_nr_running(rq); } -static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) +/* + * deactivate_task - remove a task from the runqueue. + */ +static void deactivate_task(struct rq *rq, struct task_struct *p, int flags) { - if (sleep) { - if (p->se.last_wakeup) { - update_avg(&p->se.avg_overlap, - p->se.sum_exec_runtime - p->se.last_wakeup); - p->se.last_wakeup = 0; - } else { - update_avg(&p->se.avg_wakeup, - sysctl_sched_wakeup_granularity); - } + if (task_contributes_to_load(p)) + rq->nr_uninterruptible++; + + dequeue_task(rq, p, flags); + dec_nr_running(rq); +} + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in account_system_vtime, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/account_system_vtime on this CPU. We would either get old + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. + */ +static DEFINE_PER_CPU(u64, cpu_hardirq_time); +static DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +#ifndef CONFIG_64BIT +static DEFINE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) +{ + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} +#endif /* CONFIG_64BIT */ + +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ +void account_system_vtime(struct task_struct *curr) +{ + unsigned long flags; + s64 delta; + int cpu; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + + irq_time_write_begin(); + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + __this_cpu_add(cpu_hardirq_time, delta); + else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD)) + __this_cpu_add(cpu_softirq_time, delta); + + irq_time_write_end(); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(account_system_vtime); + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ + s64 irq_delta; + + irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; + rq->clock_task += delta; + + if (irq_delta && sched_feat(NONIRQ_POWER)) + sched_rt_avg_update(rq, irq_delta); +} + +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ + rq->clock_task += delta; +} + +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#include "sched_idletask.c" +#include "sched_fair.c" +#include "sched_rt.c" +#include "sched_autogroup.c" +#include "sched_stoptask.c" +#ifdef CONFIG_SCHED_DEBUG +# include "sched_debug.c" +#endif + +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); + + stop->sched_class = &stop_sched_class; } - sched_info_dequeued(p); - p->sched_class->dequeue_task(rq, p, sleep); - p->se.on_rq = 0; + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling class so that + * it can die in pieces. + */ + old_stop->sched_class = &rt_sched_class; + } } /* @@ -1854,30 +2014,6 @@ static int effective_prio(struct task_struct *p) return p->prio; } -/* - * activate_task - move a task to the runqueue. - */ -static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) -{ - if (task_contributes_to_load(p)) - rq->nr_uninterruptible--; - - enqueue_task(rq, p, wakeup); - inc_nr_running(rq); -} - -/* - * deactivate_task - remove a task from the runqueue. - */ -static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) -{ - if (task_contributes_to_load(p)) - rq->nr_uninterruptible++; - - dequeue_task(rq, p, sleep); - dec_nr_running(rq); -} - /** * task_curr - is this task currently executing on a CPU? * @p: the task in question. @@ -1887,20 +2023,6 @@ inline int task_curr(const struct task_struct *p) return cpu_curr(task_cpu(p)) == p; } -static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) -{ - set_task_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 -} - static inline void check_class_changed(struct rq *rq, struct task_struct *p, const struct sched_class *prev_class, int oldprio, int running) @@ -1913,14 +2035,32 @@ static inline void check_class_changed(struct rq *rq, struct task_struct *p, p->sched_class->prio_changed(rq, p, oldprio, running); } -#ifdef CONFIG_SMP - -/* Used instead of source_load when we know the type == 0 */ -static unsigned long weighted_cpuload(const int cpu) +static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) { - return cpu_rq(cpu)->load.weight; + const struct sched_class *class; + + if (p->sched_class == rq->curr->sched_class) { + rq->curr->sched_class->check_preempt_curr(rq, p, flags); + } else { + for_each_class(class) { + if (class == rq->curr->sched_class) + break; + if (class == p->sched_class) { + resched_task(rq->curr); + break; + } + } + } + + /* + * A queue event has occurred, and we're going to schedule. In + * this case, we can save a useless back to back clock update. + */ + if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr)) + rq->skip_clock_update = 1; } +#ifdef CONFIG_SMP /* * Is this task likely cache-hot: */ @@ -1929,17 +2069,20 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) { s64 delta; + if (p->sched_class != &fair_sched_class) + return 0; + + if (unlikely(p->policy == SCHED_IDLE)) + return 0; + /* * Buddy candidates are cache hot: */ - if (sched_feat(CACHE_HOT_BUDDY) && + if (sched_feat(CACHE_HOT_BUDDY) && this_rq()->nr_running && (&p->se == cfs_rq_of(&p->se)->next || &p->se == cfs_rq_of(&p->se)->last)) return 1; - if (p->sched_class != &fair_sched_class) - return 0; - if (sysctl_sched_migration_cost == -1) return 1; if (sysctl_sched_migration_cost == 0) @@ -1950,119 +2093,45 @@ task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) return delta < (s64)sysctl_sched_migration_cost; } - void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { - int old_cpu = task_cpu(p); - struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu); - struct cfs_rq *old_cfsrq = task_cfs_rq(p), - *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu); - u64 clock_offset; - - clock_offset = old_rq->clock - new_rq->clock; +#ifdef CONFIG_SCHED_DEBUG + /* + * We should never call set_task_cpu() on a blocked task, + * ttwu() will sort out the placement. + */ + WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING && + !(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE)); +#endif trace_sched_migrate_task(p, new_cpu); -#ifdef CONFIG_SCHEDSTATS - if (p->se.wait_start) - p->se.wait_start -= clock_offset; - if (p->se.sleep_start) - p->se.sleep_start -= clock_offset; - if (p->se.block_start) - p->se.block_start -= clock_offset; -#endif - if (old_cpu != new_cpu) { + if (task_cpu(p) != new_cpu) { 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_swcounter_event(PERF_COUNT_SW_CPU_MIGRATIONS, - 1, 1, NULL, 0); + perf_sw_event(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 1, NULL, 0); } - p->se.vruntime -= old_cfsrq->min_vruntime - - new_cfsrq->min_vruntime; __set_task_cpu(p, new_cpu); } -struct migration_req { - struct list_head list; - +struct migration_arg { struct task_struct *task; int dest_cpu; - - struct completion done; }; +static int migration_cpu_stop(void *data); + /* * The task's runqueue lock must be held. * Returns true if you have to wait for migration thread. */ -static int -migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) +static bool migrate_task(struct task_struct *p, struct rq *rq) { - struct rq *rq = task_rq(p); - /* * If the task is not on a runqueue (and not running), then - * it is sufficient to simply update the task's cpu field. + * the next wake-up will properly place the task. */ - if (!p->se.on_rq && !task_running(rq, p)) { - set_task_cpu(p, dest_cpu); - return 0; - } - - init_completion(&req->done); - req->task = p; - req->dest_cpu = dest_cpu; - list_add(&req->list, &rq->migration_queue); - - return 1; -} - -/* - * 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(); - } + return p->se.on_rq || task_running(rq, p); } /* @@ -2120,7 +2189,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state) * just go back and repeat. */ rq = task_rq_lock(p, &flags); - trace_sched_wait_task(rq, p); + trace_sched_wait_task(p); running = task_running(rq, p); on_rq = p->se.on_rq; ncsw = 0; @@ -2194,214 +2263,144 @@ void kick_process(struct task_struct *p) preempt_enable(); } EXPORT_SYMBOL_GPL(kick_process); +#endif /* CONFIG_SMP */ -/* - * Return a low guess at the load of a migration-source cpu weighted - * according to the scheduling class and "nice" value. +/** + * 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 * - * We want to under-estimate the load of migration sources, to - * balance conservatively. - */ -static unsigned long source_load(int cpu, int type) -{ - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; - - return min(rq->cpu_load[type-1], total); -} - -/* - * Return a high guess at the load of a migration-target cpu weighted - * according to the scheduling class and "nice" value. + * Calls the function @func when the task is currently running. This might + * be on the current CPU, which just calls the function directly */ -static unsigned long target_load(int cpu, int type) +void task_oncpu_function_call(struct task_struct *p, + void (*func) (void *info), void *info) { - struct rq *rq = cpu_rq(cpu); - unsigned long total = weighted_cpuload(cpu); - - if (type == 0 || !sched_feat(LB_BIAS)) - return total; + int cpu; - return max(rq->cpu_load[type-1], total); + preempt_disable(); + cpu = task_cpu(p); + if (task_curr(p)) + smp_call_function_single(cpu, func, info, 1); + preempt_enable(); } +#ifdef CONFIG_SMP /* - * find_idlest_group finds and returns the least busy CPU group within the - * domain. + * ->cpus_allowed is protected by either TASK_WAKING or rq->lock held. */ -static struct sched_group * -find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) +static int select_fallback_rq(int cpu, struct task_struct *p) { - struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups; - unsigned long min_load = ULONG_MAX, this_load = 0; - int load_idx = sd->forkexec_idx; - int imbalance = 100 + (sd->imbalance_pct-100)/2; - - do { - unsigned long load, avg_load; - int local_group; - int i; - - /* Skip over this group if it has no CPUs allowed */ - if (!cpumask_intersects(sched_group_cpus(group), - &p->cpus_allowed)) - continue; - - local_group = cpumask_test_cpu(this_cpu, - sched_group_cpus(group)); - - /* Tally up the load of all CPUs in the group */ - avg_load = 0; - - for_each_cpu(i, sched_group_cpus(group)) { - /* Bias balancing toward cpus of our domain */ - if (local_group) - load = source_load(i, load_idx); - else - load = target_load(i, load_idx); + int dest_cpu; + const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu)); - avg_load += load; - } + /* Look for allowed, online CPU in same node. */ + for_each_cpu_and(dest_cpu, nodemask, cpu_active_mask) + if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) + return dest_cpu; - /* Adjust by relative CPU power of the group */ - avg_load = sg_div_cpu_power(group, - avg_load * SCHED_LOAD_SCALE); + /* Any allowed, online CPU? */ + dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask); + if (dest_cpu < nr_cpu_ids) + return dest_cpu; - if (local_group) { - this_load = avg_load; - this = group; - } else if (avg_load < min_load) { - min_load = avg_load; - idlest = group; - } - } while (group = group->next, group != sd->groups); + /* No more Mr. Nice Guy. */ + dest_cpu = cpuset_cpus_allowed_fallback(p); + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk(KERN_INFO "process %d (%s) no longer affine to cpu%d\n", + task_pid_nr(p), p->comm, cpu); + } - if (!idlest || 100*this_load < imbalance*min_load) - return NULL; - return idlest; + return dest_cpu; } /* - * find_idlest_cpu - find the idlest cpu among the cpus in group. + * The caller (fork, wakeup) owns TASK_WAKING, ->cpus_allowed is stable. */ -static int -find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu) +static inline +int select_task_rq(struct rq *rq, struct task_struct *p, int sd_flags, int wake_flags) { - unsigned long load, min_load = ULONG_MAX; - int idlest = -1; - int i; - - /* Traverse only the allowed CPUs */ - for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) { - load = weighted_cpuload(i); + int cpu = p->sched_class->select_task_rq(rq, p, sd_flags, wake_flags); - if (load < min_load || (load == min_load && i == this_cpu)) { - min_load = load; - idlest = i; - } - } + /* + * In order not to call set_task_cpu() on a blocking task we need + * to rely on ttwu() to place the task on a valid ->cpus_allowed + * cpu. + * + * Since this is common to all placement strategies, this lives here. + * + * [ this allows ->select_task() to simply return task_cpu(p) and + * not worry about this generic constraint ] + */ + if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed) || + !cpu_online(cpu))) + cpu = select_fallback_rq(task_cpu(p), p); - return idlest; + return cpu; } -/* - * sched_balance_self: balance the current task (running on cpu) in domains - * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and - * SD_BALANCE_EXEC. - * - * Balance, ie. select the least loaded group. - * - * Returns the target CPU number, or the same CPU if no balancing is needed. - * - * preempt must be disabled. - */ -static int sched_balance_self(int cpu, int flag) +static void update_avg(u64 *avg, u64 sample) { - struct task_struct *t = current; - struct sched_domain *tmp, *sd = NULL; - - for_each_domain(cpu, tmp) { - /* - * If power savings logic is enabled for a domain, stop there. - */ - if (tmp->flags & SD_POWERSAVINGS_BALANCE) - break; - if (tmp->flags & flag) - sd = tmp; - } + s64 diff = sample - *avg; + *avg += diff >> 3; +} +#endif - if (sd) - update_shares(sd); +static inline void ttwu_activate(struct task_struct *p, struct rq *rq, + bool is_sync, bool is_migrate, bool is_local, + unsigned long en_flags) +{ + schedstat_inc(p, se.statistics.nr_wakeups); + if (is_sync) + schedstat_inc(p, se.statistics.nr_wakeups_sync); + if (is_migrate) + schedstat_inc(p, se.statistics.nr_wakeups_migrate); + if (is_local) + schedstat_inc(p, se.statistics.nr_wakeups_local); + else + schedstat_inc(p, se.statistics.nr_wakeups_remote); - while (sd) { - struct sched_group *group; - int new_cpu, weight; + activate_task(rq, p, en_flags); +} - if (!(sd->flags & flag)) { - sd = sd->child; - continue; - } +static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, + int wake_flags, bool success) +{ + trace_sched_wakeup(p, success); + check_preempt_curr(rq, p, wake_flags); - group = find_idlest_group(sd, t, cpu); - if (!group) { - sd = sd->child; - continue; - } + p->state = TASK_RUNNING; +#ifdef CONFIG_SMP + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); - new_cpu = find_idlest_cpu(group, t, cpu); - if (new_cpu == -1 || new_cpu == cpu) { - /* Now try balancing at a lower domain level of cpu */ - sd = sd->child; - continue; - } + if (unlikely(rq->idle_stamp)) { + u64 delta = rq->clock - rq->idle_stamp; + u64 max = 2*sysctl_sched_migration_cost; - /* Now try balancing at a lower domain level of new_cpu */ - cpu = new_cpu; - weight = cpumask_weight(sched_domain_span(sd)); - sd = NULL; - for_each_domain(cpu, tmp) { - if (weight <= cpumask_weight(sched_domain_span(tmp))) - break; - if (tmp->flags & flag) - sd = tmp; - } - /* while loop will break here if sd == NULL */ + if (delta > max) + rq->avg_idle = max; + else + update_avg(&rq->avg_idle, delta); + rq->idle_stamp = 0; } - - return cpu; +#endif + /* if a worker is waking up, notify workqueue */ + if ((p->flags & PF_WQ_WORKER) && success) + wq_worker_waking_up(p, cpu_of(rq)); } -#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 + * @p: the thread to be awakened * @state: the mask of task states that can be woken - * @sync: do a synchronous wakeup? + * @wake_flags: wake modifier flags (WF_*) * * Put it on the run-queue if it's not already there. The "current" * thread is always on the run-queue (except when the actual @@ -2409,39 +2408,22 @@ void task_oncpu_function_call(struct task_struct *p, * the simpler "current->state = TASK_RUNNING" to mark yourself * runnable without the overhead of this. * - * returns failure only if the task is already active. + * Returns %true if @p was woken up, %false if it was already running + * or @state didn't match @p's state. */ -static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) +static int try_to_wake_up(struct task_struct *p, unsigned int state, + int wake_flags) { int cpu, orig_cpu, this_cpu, success = 0; unsigned long flags; - long old_state; + unsigned long en_flags = ENQUEUE_WAKEUP; struct rq *rq; - if (!sched_feat(SYNC_WAKEUPS)) - sync = 0; - -#ifdef CONFIG_SMP - if (sched_feat(LB_WAKEUP_UPDATE) && !root_task_group_empty()) { - struct sched_domain *sd; - - this_cpu = raw_smp_processor_id(); - cpu = task_cpu(p); - - for_each_domain(this_cpu, sd) { - if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { - update_shares(sd); - break; - } - } - } -#endif + this_cpu = get_cpu(); smp_wmb(); rq = task_rq_lock(p, &flags); - update_rq_clock(rq); - old_state = p->state; - if (!(old_state & state)) + if (!(p->state & state)) goto out; if (p->se.on_rq) @@ -2449,28 +2431,47 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) cpu = task_cpu(p); orig_cpu = cpu; - this_cpu = smp_processor_id(); #ifdef CONFIG_SMP if (unlikely(task_running(rq, p))) goto out_activate; - cpu = p->sched_class->select_task_rq(p, sync); - if (cpu != orig_cpu) { - set_task_cpu(p, cpu); - task_rq_unlock(rq, &flags); - /* might preempt at this point */ - rq = task_rq_lock(p, &flags); - old_state = p->state; - if (!(old_state & state)) - goto out; - if (p->se.on_rq) - goto out_running; + /* + * In order to handle concurrent wakeups and release the rq->lock + * we put the task in TASK_WAKING state. + * + * First fix up the nr_uninterruptible count: + */ + if (task_contributes_to_load(p)) { + if (likely(cpu_online(orig_cpu))) + rq->nr_uninterruptible--; + else + this_rq()->nr_uninterruptible--; + } + p->state = TASK_WAKING; - this_cpu = smp_processor_id(); - cpu = task_cpu(p); + if (p->sched_class->task_waking) { + p->sched_class->task_waking(rq, p); + en_flags |= ENQUEUE_WAKING; } + cpu = select_task_rq(rq, p, SD_BALANCE_WAKE, wake_flags); + if (cpu != orig_cpu) + set_task_cpu(p, cpu); + __task_rq_unlock(rq); + + rq = cpu_rq(cpu); + raw_spin_lock(&rq->lock); + + /* + * We migrated the task without holding either rq->lock, however + * since the task is not on the task list itself, nobody else + * will try and migrate the task, hence the rq should match the + * cpu we just moved it to. + */ + WARN_ON(task_cpu(p) != cpu); + WARN_ON(p->state != TASK_WAKING); + #ifdef CONFIG_SCHEDSTATS schedstat_inc(rq, ttwu_count); if (cpu == this_cpu) @@ -2488,50 +2489,50 @@ static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) out_activate: #endif /* CONFIG_SMP */ - schedstat_inc(p, se.nr_wakeups); - if (sync) - schedstat_inc(p, se.nr_wakeups_sync); - if (orig_cpu != cpu) - schedstat_inc(p, se.nr_wakeups_migrate); - if (cpu == this_cpu) - schedstat_inc(p, se.nr_wakeups_local); - else - schedstat_inc(p, se.nr_wakeups_remote); - activate_task(rq, p, 1); + ttwu_activate(p, rq, wake_flags & WF_SYNC, orig_cpu != cpu, + cpu == this_cpu, en_flags); success = 1; - - /* - * Only attribute actual wakeups done by this task. - */ - if (!in_interrupt()) { - struct sched_entity *se = ¤t->se; - u64 sample = se->sum_exec_runtime; - - if (se->last_wakeup) - sample -= se->last_wakeup; - else - sample -= se->start_runtime; - update_avg(&se->avg_wakeup, sample); - - se->last_wakeup = se->sum_exec_runtime; - } - out_running: - trace_sched_wakeup(rq, p, success); - check_preempt_curr(rq, p, sync); - - p->state = TASK_RUNNING; -#ifdef CONFIG_SMP - if (p->sched_class->task_wake_up) - p->sched_class->task_wake_up(rq, p); -#endif + ttwu_post_activation(p, rq, wake_flags, success); out: task_rq_unlock(rq, &flags); + put_cpu(); return success; } /** + * try_to_wake_up_local - try to wake up a local task with rq lock held + * @p: the thread to be awakened + * + * Put @p on the run-queue if it's not alredy there. The caller must + * ensure that this_rq() is locked, @p is bound to this_rq() and not + * the current task. this_rq() stays locked over invocation. + */ +static void try_to_wake_up_local(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + bool success = false; + + BUG_ON(rq != this_rq()); + BUG_ON(p == current); + lockdep_assert_held(&rq->lock); + + if (!(p->state & TASK_NORMAL)) + return; + + if (!p->se.on_rq) { + if (likely(!task_running(rq, p))) { + schedstat_inc(rq, ttwu_count); + schedstat_inc(rq, ttwu_local); + } + ttwu_activate(p, rq, false, false, true, ENQUEUE_WAKEUP); + success = true; + } + ttwu_post_activation(p, rq, 0, success); +} + +/** * wake_up_process - Wake up a specific process * @p: The process to be woken up. * @@ -2565,21 +2566,9 @@ static void __sched_fork(struct task_struct *p) 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; - p->se.avg_wakeup = sysctl_sched_wakeup_granularity; #ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.sum_sleep_runtime = 0; - p->se.sleep_start = 0; - p->se.block_start = 0; - p->se.sleep_max = 0; - p->se.block_max = 0; - p->se.exec_max = 0; - p->se.slice_max = 0; - p->se.wait_max = 0; + memset(&p->se.statistics, 0, sizeof(p->se.statistics)); #endif INIT_LIST_HEAD(&p->rt.run_list); @@ -2589,14 +2578,6 @@ static void __sched_fork(struct task_struct *p) #ifdef CONFIG_PREEMPT_NOTIFIERS INIT_HLIST_HEAD(&p->preempt_notifiers); #endif - - /* - * We mark the process as running here, but have not actually - * inserted it onto the runqueue yet. This guarantees that - * nobody will actually run it, and a signal or other external - * event cannot wake it up and insert it on the runqueue either. - */ - p->state = TASK_RUNNING; } /* @@ -2607,19 +2588,57 @@ void sched_fork(struct task_struct *p, int clone_flags) int cpu = get_cpu(); __sched_fork(p); + /* + * We mark the process as running here. This guarantees that + * nobody will actually run it, and a signal or other external + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_RUNNING; -#ifdef CONFIG_SMP - cpu = sched_balance_self(cpu, SD_BALANCE_FORK); -#endif - set_task_cpu(p, cpu); + /* + * Revert to default priority/policy on fork if requested. + */ + if (unlikely(p->sched_reset_on_fork)) { + if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { + p->policy = SCHED_NORMAL; + p->normal_prio = p->static_prio; + } + + if (PRIO_TO_NICE(p->static_prio) < 0) { + p->static_prio = NICE_TO_PRIO(0); + p->normal_prio = p->static_prio; + set_load_weight(p); + } + + /* + * We don't need the reset flag anymore after the fork. It has + * fulfilled its duty: + */ + p->sched_reset_on_fork = 0; + } /* - * Make sure we do not leak PI boosting priority to the child: + * Make sure we do not leak PI boosting priority to the child. */ p->prio = current->normal_prio; + if (!rt_prio(p->prio)) p->sched_class = &fair_sched_class; + if (p->sched_class->task_fork) + p->sched_class->task_fork(p); + + /* + * The child is not yet in the pid-hash so no cgroup attach races, + * and the cgroup is pinned to this child due to cgroup_fork() + * is ran before sched_fork(). + * + * Silence PROVE_RCU. + */ + rcu_read_lock(); + set_task_cpu(p, cpu); + rcu_read_unlock(); + #if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) if (likely(sched_info_on())) memset(&p->sched_info, 0, sizeof(p->sched_info)); @@ -2631,7 +2650,9 @@ void sched_fork(struct task_struct *p, int clone_flags) /* Want to start with kernel preemption disabled. */ task_thread_info(p)->preempt_count = 1; #endif +#ifdef CONFIG_SMP plist_node_init(&p->pushable_tasks, MAX_PRIO); +#endif put_cpu(); } @@ -2647,30 +2668,37 @@ void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) { unsigned long flags; struct rq *rq; + int cpu __maybe_unused = get_cpu(); +#ifdef CONFIG_SMP rq = task_rq_lock(p, &flags); - BUG_ON(p->state != TASK_RUNNING); - update_rq_clock(rq); + p->state = TASK_WAKING; - p->prio = effective_prio(p); + /* + * Fork balancing, do it here and not earlier because: + * - cpus_allowed can change in the fork path + * - any previously selected cpu might disappear through hotplug + * + * We set TASK_WAKING so that select_task_rq() can drop rq->lock + * without people poking at ->cpus_allowed. + */ + cpu = select_task_rq(rq, p, SD_BALANCE_FORK, 0); + set_task_cpu(p, cpu); - if (!p->sched_class->task_new || !current->se.on_rq) { - activate_task(rq, p, 0); - } else { - /* - * Let the scheduling class do new task startup - * management (if any): - */ - p->sched_class->task_new(rq, p); - inc_nr_running(rq); - } - trace_sched_wakeup_new(rq, p, 1); - check_preempt_curr(rq, p, 0); + p->state = TASK_RUNNING; + task_rq_unlock(rq, &flags); +#endif + + rq = task_rq_lock(p, &flags); + activate_task(rq, p, 0); + trace_sched_wakeup_new(p, 1); + check_preempt_curr(rq, p, WF_FORK); #ifdef CONFIG_SMP - if (p->sched_class->task_wake_up) - p->sched_class->task_wake_up(rq, p); + if (p->sched_class->task_woken) + p->sched_class->task_woken(rq, p); #endif task_rq_unlock(rq, &flags); + put_cpu(); } #ifdef CONFIG_PREEMPT_NOTIFIERS @@ -2773,12 +2801,6 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) { struct mm_struct *mm = rq->prev_mm; long prev_state; -#ifdef CONFIG_SMP - int post_schedule = 0; - - if (current->sched_class->needs_post_schedule) - post_schedule = current->sched_class->needs_post_schedule(rq); -#endif rq->prev_mm = NULL; @@ -2795,12 +2817,14 @@ 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)); +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + local_irq_disable(); +#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ + perf_event_task_sched_in(current); +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + local_irq_enable(); +#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */ finish_lock_switch(rq, prev); -#ifdef CONFIG_SMP - if (post_schedule) - current->sched_class->post_schedule(rq); -#endif fire_sched_in_preempt_notifiers(current); if (mm) @@ -2815,6 +2839,42 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev) } } +#ifdef CONFIG_SMP + +/* assumes rq->lock is held */ +static inline void pre_schedule(struct rq *rq, struct task_struct *prev) +{ + if (prev->sched_class->pre_schedule) + prev->sched_class->pre_schedule(rq, prev); +} + +/* rq->lock is NOT held, but preemption is disabled */ +static inline void post_schedule(struct rq *rq) +{ + if (rq->post_schedule) { + unsigned long flags; + + raw_spin_lock_irqsave(&rq->lock, flags); + if (rq->curr->sched_class->post_schedule) + rq->curr->sched_class->post_schedule(rq); + raw_spin_unlock_irqrestore(&rq->lock, flags); + + rq->post_schedule = 0; + } +} + +#else + +static inline void pre_schedule(struct rq *rq, struct task_struct *p) +{ +} + +static inline void post_schedule(struct rq *rq) +{ +} + +#endif + /** * schedule_tail - first thing a freshly forked thread must call. * @prev: the thread we just switched away from. @@ -2825,6 +2885,13 @@ asmlinkage void schedule_tail(struct task_struct *prev) struct rq *rq = this_rq(); finish_task_switch(rq, prev); + + /* + * FIXME: do we need to worry about rq being invalidated by the + * task_switch? + */ + post_schedule(rq); + #ifdef __ARCH_WANT_UNLOCKED_CTXSW /* In this case, finish_task_switch does not reenable preemption */ preempt_enable(); @@ -2844,7 +2911,7 @@ context_switch(struct rq *rq, struct task_struct *prev, struct mm_struct *mm, *oldmm; prepare_task_switch(rq, prev, next); - trace_sched_switch(rq, prev, next); + trace_sched_switch(prev, next); mm = next->mm; oldmm = prev->active_mm; /* @@ -2854,14 +2921,14 @@ context_switch(struct rq *rq, struct task_struct *prev, */ arch_start_context_switch(prev); - if (unlikely(!mm)) { + if (!mm) { next->active_mm = oldmm; atomic_inc(&oldmm->mm_count); enter_lazy_tlb(oldmm, next); } else switch_mm(oldmm, mm, next); - if (unlikely(!prev->mm)) { + if (!prev->mm) { prev->active_mm = NULL; rq->prev_mm = oldmm; } @@ -2942,63 +3009,28 @@ unsigned long nr_iowait(void) return sum; } -/* 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 nr_iowait_cpu(int cpu) { - loads[0] = (avenrun[0] + offset) << shift; - loads[1] = (avenrun[1] + offset) << shift; - loads[2] = (avenrun[2] + offset) << shift; + struct rq *this = cpu_rq(cpu); + return atomic_read(&this->nr_iowait); } -static unsigned long -calc_load(unsigned long load, unsigned long exp, unsigned long active) +unsigned long this_cpu_load(void) { - load *= exp; - load += active * (FIXED_1 - exp); - return load >> FSHIFT; + struct rq *this = this_rq(); + return this->cpu_load[0]; } -/* - * 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; - - active = atomic_long_read(&calc_load_tasks); - active = active > 0 ? active * FIXED_1 : 0; - - 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; -} +/* 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); -/* - * Either called from update_cpu_load() or from a cpu going idle - */ -static void calc_load_account_active(struct rq *this_rq) +static long calc_load_fold_active(struct rq *this_rq) { - long nr_active, delta; + long nr_active, delta = 0; nr_active = this_rq->nr_running; nr_active += (long) this_rq->nr_uninterruptible; @@ -3006,1796 +3038,393 @@ static void calc_load_account_active(struct rq *this_rq) 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; -} - -/* - * Update rq->cpu_load[] statistics. This function is usually called every - * scheduler tick (TICK_NSEC). - */ -static void update_cpu_load(struct rq *this_rq) -{ - unsigned long this_load = this_rq->load.weight; - int i, scale; - - this_rq->nr_load_updates++; - - /* Update our load: */ - for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { - unsigned long old_load, new_load; - - /* scale is effectively 1 << i now, and >> i divides by scale */ - - old_load = this_rq->cpu_load[i]; - new_load = this_load; - /* - * Round up the averaging division if load is increasing. This - * prevents us from getting stuck on 9 if the load is 10, for - * example. - */ - if (new_load > old_load) - 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); - } + return delta; } -#ifdef CONFIG_SMP - -/* - * double_rq_lock - safely lock two runqueues - * - * Note this does not disable interrupts like task_rq_lock, - * you need to do so manually before calling. - */ -static void double_rq_lock(struct rq *rq1, struct rq *rq2) - __acquires(rq1->lock) - __acquires(rq2->lock) +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) { - BUG_ON(!irqs_disabled()); - if (rq1 == rq2) { - spin_lock(&rq1->lock); - __acquire(rq2->lock); /* Fake it out ;) */ - } else { - if (rq1 < rq2) { - spin_lock(&rq1->lock); - spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); - } else { - spin_lock(&rq2->lock); - spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); - } - } - update_rq_clock(rq1); - update_rq_clock(rq2); + load *= exp; + load += active * (FIXED_1 - exp); + load += 1UL << (FSHIFT - 1); + return load >> FSHIFT; } +#ifdef CONFIG_NO_HZ /* - * double_rq_unlock - safely unlock two runqueues + * For NO_HZ we delay the active fold to the next LOAD_FREQ update. * - * Note this does not restore interrupts like task_rq_unlock, - * you need to do so manually after calling. + * When making the ILB scale, we should try to pull this in as well. */ -static void double_rq_unlock(struct rq *rq1, struct rq *rq2) - __releases(rq1->lock) - __releases(rq2->lock) -{ - spin_unlock(&rq1->lock); - if (rq1 != rq2) - spin_unlock(&rq2->lock); - else - __release(rq2->lock); -} +static atomic_long_t calc_load_tasks_idle; -/* - * If dest_cpu is allowed for this process, migrate the task to it. - * This is accomplished by forcing the cpu_allowed mask to only - * allow dest_cpu, which will force the cpu onto dest_cpu. Then - * the cpu_allowed mask is restored. - */ -static void sched_migrate_task(struct task_struct *p, int dest_cpu) +static void calc_load_account_idle(struct rq *this_rq) { - struct migration_req req; - unsigned long flags; - struct rq *rq; - - rq = task_rq_lock(p, &flags); - if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed) - || unlikely(!cpu_active(dest_cpu))) - goto out; + long delta; - /* force the process onto the specified CPU */ - if (migrate_task(p, dest_cpu, &req)) { - /* Need to wait for migration thread (might exit: take ref). */ - struct task_struct *mt = rq->migration_thread; - - get_task_struct(mt); - task_rq_unlock(rq, &flags); - wake_up_process(mt); - put_task_struct(mt); - wait_for_completion(&req.done); - - return; - } -out: - task_rq_unlock(rq, &flags); + delta = calc_load_fold_active(this_rq); + if (delta) + atomic_long_add(delta, &calc_load_tasks_idle); } -/* - * sched_exec - execve() is a valuable balancing opportunity, because at - * this point the task has the smallest effective memory and cache footprint. - */ -void sched_exec(void) +static long calc_load_fold_idle(void) { - int new_cpu, this_cpu = get_cpu(); - new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC); - put_cpu(); - if (new_cpu != this_cpu) - sched_migrate_task(current, new_cpu); -} + long delta = 0; -/* - * pull_task - move a task from a remote runqueue to the local runqueue. - * Both runqueues must be locked. - */ -static void pull_task(struct rq *src_rq, struct task_struct *p, - struct rq *this_rq, int this_cpu) -{ - deactivate_task(src_rq, p, 0); - set_task_cpu(p, this_cpu); - activate_task(this_rq, p, 0); /* - * Note that idle threads have a prio of MAX_PRIO, for this test - * to be always true for them. + * Its got a race, we don't care... */ - check_preempt_curr(this_rq, p, 0); -} + if (atomic_long_read(&calc_load_tasks_idle)) + delta = atomic_long_xchg(&calc_load_tasks_idle, 0); -/* - * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? - */ -static -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 - * 2) cannot be migrated to this CPU due to cpus_allowed, or - * 3) are cache-hot on their current CPU. - */ - if (!cpumask_test_cpu(this_cpu, &p->cpus_allowed)) { - schedstat_inc(p, se.nr_failed_migrations_affine); - return 0; - } - *all_pinned = 0; - - if (task_running(rq, p)) { - schedstat_inc(p, se.nr_failed_migrations_running); - return 0; - } - - /* - * Aggressive migration if: - * 1) task is cache cold, or - * 2) too many balance attempts have failed. - */ - - 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 (tsk_cache_hot) { - schedstat_inc(sd, lb_hot_gained[idle]); - schedstat_inc(p, se.nr_forced_migrations); - } -#endif - return 1; - } - - if (tsk_cache_hot) { - schedstat_inc(p, se.nr_failed_migrations_hot); - return 0; - } - return 1; + return delta; } -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 loops = 0, pulled = 0, pinned = 0; - struct task_struct *p; - long rem_load_move = max_load_move; - - if (max_load_move == 0) - goto out; - - pinned = 1; - - /* - * Start the load-balancing iterator: - */ - p = iterator->start(iterator->arg); -next: - if (!p || loops++ > sysctl_sched_nr_migrate) - goto out; - - if ((p->se.load.weight >> 1) > rem_load_move || - !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { - p = iterator->next(iterator->arg); - goto next; - } - - pull_task(busiest, p, this_rq, this_cpu); - pulled++; - rem_load_move -= p->se.load.weight; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible kernels - * will stop after the first task is pulled to minimize the critical - * section. - */ - if (idle == CPU_NEWLY_IDLE) - goto out; -#endif - - /* - * We only want to steal up to the prescribed amount of weighted load. - */ - if (rem_load_move > 0) { - if (p->prio < *this_best_prio) - *this_best_prio = p->prio; - p = iterator->next(iterator->arg); - goto next; - } -out: - /* - * 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(). - */ - schedstat_add(sd, lb_gained[idle], pulled); - - if (all_pinned) - *all_pinned = pinned; - - return max_load_move - rem_load_move; -} - -/* - * move_tasks tries to move up to max_load_move weighted load from busiest to - * this_rq, as part of a balancing operation within domain "sd". - * Returns 1 if successful and 0 otherwise. +/** + * fixed_power_int - compute: x^n, in O(log n) time + * + * @x: base of the power + * @frac_bits: fractional bits of @x + * @n: power to raise @x to. * - * Called with both runqueues locked. + * By exploiting the relation between the definition of the natural power + * function: x^n := x*x*...*x (x multiplied by itself for n times), and + * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i, + * (where: n_i \elem {0, 1}, the binary vector representing n), + * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is + * of course trivially computable in O(log_2 n), the length of our binary + * vector. */ -static int move_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) -{ - const struct sched_class *class = sched_class_highest; - unsigned long total_load_moved = 0; - int this_best_prio = this_rq->curr->prio; - - do { - total_load_moved += - class->load_balance(this_rq, this_cpu, busiest, - max_load_move - total_load_moved, - sd, idle, all_pinned, &this_best_prio); - class = class->next; - -#ifdef CONFIG_PREEMPT - /* - * NEWIDLE balancing is a source of latency, so preemptible - * kernels will stop after the first task is pulled to minimize - * the critical section. - */ - if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) - break; -#endif - } while (class && max_load_move > total_load_moved); - - 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) +static unsigned long +fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n) { - struct task_struct *p = iterator->start(iterator->arg); - int pinned = 0; + unsigned long result = 1UL << frac_bits; - 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; + if (n) for (;;) { + if (n & 1) { + result *= x; + result += 1UL << (frac_bits - 1); + result >>= frac_bits; } - p = iterator->next(iterator->arg); + n >>= 1; + if (!n) + break; + x *= x; + x += 1UL << (frac_bits - 1); + x >>= frac_bits; } - return 0; + return result; } /* - * move_one_task tries to move exactly one task from busiest to this_rq, as - * part of active balancing operations within "domain". - * Returns 1 if successful and 0 otherwise. + * a1 = a0 * e + a * (1 - e) + * + * a2 = a1 * e + a * (1 - e) + * = (a0 * e + a * (1 - e)) * e + a * (1 - e) + * = a0 * e^2 + a * (1 - e) * (1 + e) + * + * a3 = a2 * e + a * (1 - e) + * = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e) + * = a0 * e^3 + a * (1 - e) * (1 + e + e^2) + * + * ... + * + * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1] + * = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e) + * = a0 * e^n + a * (1 - e^n) * - * Called with both runqueues locked. + * [1] application of the geometric series: + * + * n 1 - x^(n+1) + * S_n := \Sum x^i = ------------- + * i=0 1 - x */ -static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, - struct sched_domain *sd, enum cpu_idle_type idle) +static unsigned long +calc_load_n(unsigned long load, unsigned long exp, + unsigned long active, unsigned int n) { - const struct sched_class *class; - - for (class = sched_class_highest; class; class = class->next) - if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle)) - return 1; - return 0; + return calc_load(load, fixed_power_int(exp, FSHIFT, n), active); } -/********** Helpers for find_busiest_group ************************/ -/* - * sd_lb_stats - Structure to store the statistics of a sched_domain - * during load balancing. - */ -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; /* 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 ? */ -}; - -/** - * 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)); -} - -/** - * 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; - break; - - case CPU_NEWLY_IDLE: - load_idx = sd->newidle_idx; - break; - default: - load_idx = sd->idle_idx; - break; - } - - return load_idx; -} - - -#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. + * NO_HZ can leave us missing all per-cpu ticks calling + * calc_load_account_active(), but since an idle CPU folds its delta into + * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold + * in the pending idle delta if our idle period crossed a load cycle boundary. * - * @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. + * Once we've updated the global active value, we need to apply the exponential + * weights adjusted to the number of cycles missed. */ -static inline void init_sd_power_savings_stats(struct sched_domain *sd, - struct sd_lb_stats *sds, enum cpu_idle_type idle) +static void calc_global_nohz(unsigned long ticks) { - /* - * 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; - } -} - -/** - * 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) -{ - - if (!sds->power_savings_balance) - return; - - /* - * 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; + long delta, active, n; - /* - * 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) + if (time_before(jiffies, calc_load_update)) 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 we crossed a calc_load_update boundary, make sure to fold + * any pending idle changes, the respective CPUs might have + * missed the tick driven calc_load_account_active() update + * due to NO_HZ. */ - 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; - } + delta = calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); /* - * 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 we were idle for multiple load cycles, apply them. */ - if (sgs->sum_nr_running > sgs->group_capacity - 1) - return; + if (ticks >= LOAD_FREQ) { + n = ticks / LOAD_FREQ; - 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; - } -} + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; -/** - * 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; + avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n); + avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n); + avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n); - if (sds->this != sds->group_leader || - sds->group_leader == sds->group_min) - return 0; - - *imbalance = sds->min_load_per_task; - sds->busiest = sds->group_min; - - if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP) { - cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu = - group_first_cpu(sds->group_leader); + calc_load_update += n * LOAD_FREQ; } - 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; -} - -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 (local_group) - balance_cpu = group_first_cpu(group); - - /* 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) { - 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; - } - - sgs->group_load += load; - sgs->sum_nr_running += rq->nr_running; - sgs->sum_weighted_load += weighted_cpuload(i); - - sum_avg_load_per_task += cpu_avg_load_per_task(i); - } - - /* - * 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; - } - - /* Adjust by relative CPU power of the group */ - sgs->avg_load = sg_div_cpu_power(group, - sgs->group_load * SCHED_LOAD_SCALE); - - /* - * Consider the group unbalanced when the imbalance is larger - * than the average weight of two tasks. + * Its possible the remainder of the above division also crosses + * a LOAD_FREQ period, the regular check in calc_global_load() + * which comes after this will take care of that. * - * 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? + * Consider us being 11 ticks before a cycle completion, and us + * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will + * age us 4 cycles, and the test in calc_global_load() will + * pick up the final one. */ - 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) +#else +static void calc_load_account_idle(struct rq *this_rq) { - 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; - } - - update_sd_power_savings_stats(group, sds, local_group, &sgs); - group = group->next; - } while (group != sd->groups); - } -/** - * 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); - - 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; - } - - /* - * 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. - */ - - 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; +static inline long calc_load_fold_idle(void) +{ + return 0; } -/** - * 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) +static void calc_global_nohz(unsigned long ticks) { - 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 (sds->max_load < sds->avg_load) { - *imbalance = 0; - 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(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 * sds->busiest->__cpu_power, - (sds->avg_load - sds->this_load) * sds->this->__cpu_power) - / SCHED_LOAD_SCALE; - - /* - * if *imbalance is less than the average load per runnable task - * there is no gaurantee that any tasks will be moved so we'll have - * a think about bumping its value to force at least one task to be - * moved - */ - if (*imbalance < sds->busiest_load_per_task) - return fix_small_imbalance(sds, this_cpu, imbalance); - } -/******* find_busiest_group() helpers end here *********************/ +#endif /** - * 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. + * 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 * - * 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; - - memset(&sds, 0, sizeof(sds)); - - /* - * 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; - - /* Looks like there is an imbalance. Compute it */ - calculate_imbalance(&sds, this_cpu, imbalance); - return sds.busiest; - -out_balanced: - /* - * 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; -} - -/* - * find_busiest_queue - find the busiest runqueue among the cpus in group. - */ -static struct rq * -find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, - unsigned long imbalance, const struct cpumask *cpus) -{ - struct rq *busiest = NULL, *rq; - unsigned long max_load = 0; - int i; - - for_each_cpu(i, sched_group_cpus(group)) { - unsigned long wl; - - if (!cpumask_test_cpu(i, cpus)) - continue; - - rq = cpu_rq(i); - wl = weighted_cpuload(i); - - if (rq->nr_running == 1 && wl > imbalance) - continue; - - if (wl > max_load) { - max_load = wl; - busiest = rq; - } - } - - return busiest; -} - -/* - * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but - * so long as it is large enough. - */ -#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. + * These values are estimates at best, so no need for locking. */ -static int load_balance(int this_cpu, struct rq *this_rq, - struct sched_domain *sd, enum cpu_idle_type idle, - int *balance) +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) { - 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); - - /* - * When power savings policy is enabled for the parent domain, idle - * sibling can pick up load irrespective of busy siblings. In this case, - * let the state of idle sibling percolate up as CPU_IDLE, instead of - * portraying it as CPU_NOT_IDLE. - */ - if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - sd_idle = 1; - - schedstat_inc(sd, lb_count[idle]); - -redo: - update_shares(sd); - group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, - cpus, balance); - - if (*balance == 0) - goto out_balanced; - - if (!group) { - schedstat_inc(sd, lb_nobusyg[idle]); - goto out_balanced; - } - - busiest = find_busiest_queue(group, idle, imbalance, cpus); - if (!busiest) { - schedstat_inc(sd, lb_nobusyq[idle]); - goto out_balanced; - } - - BUG_ON(busiest == this_rq); - - schedstat_add(sd, lb_imbalance[idle], imbalance); - - ld_moved = 0; - if (busiest->nr_running > 1) { - /* - * Attempt to move tasks. If find_busiest_group has found - * an imbalance but busiest->nr_running <= 1, the group is - * still unbalanced. ld_moved simply stays zero, so it is - * correctly treated as an imbalance. - */ - local_irq_save(flags); - double_rq_lock(this_rq, busiest); - ld_moved = move_tasks(this_rq, this_cpu, busiest, - imbalance, sd, idle, &all_pinned); - double_rq_unlock(this_rq, busiest); - local_irq_restore(flags); - - /* - * some other cpu did the load balance for us. - */ - if (ld_moved && this_cpu != smp_processor_id()) - resched_cpu(this_cpu); - - /* All tasks on this runqueue were pinned by CPU affinity */ - if (unlikely(all_pinned)) { - cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_empty(cpus)) - goto redo; - goto out_balanced; - } - } - - if (!ld_moved) { - schedstat_inc(sd, lb_failed[idle]); - sd->nr_balance_failed++; - - if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) { - - spin_lock_irqsave(&busiest->lock, flags); - - /* don't kick the migration_thread, if the curr - * task on busiest cpu can't be moved to this_cpu - */ - if (!cpumask_test_cpu(this_cpu, - &busiest->curr->cpus_allowed)) { - spin_unlock_irqrestore(&busiest->lock, flags); - all_pinned = 1; - goto out_one_pinned; - } - - if (!busiest->active_balance) { - busiest->active_balance = 1; - busiest->push_cpu = this_cpu; - active_balance = 1; - } - spin_unlock_irqrestore(&busiest->lock, flags); - if (active_balance) - wake_up_process(busiest->migration_thread); - - /* - * We've kicked active balancing, reset the failure - * counter. - */ - sd->nr_balance_failed = sd->cache_nice_tries+1; - } - } else - sd->nr_balance_failed = 0; - - if (likely(!active_balance)) { - /* We were unbalanced, so reset the balancing interval */ - sd->balance_interval = sd->min_interval; - } else { - /* - * If we've begun active balancing, start to back off. This - * case may not be covered by the all_pinned logic if there - * is only 1 task on the busy runqueue (because we don't call - * move_tasks). - */ - if (sd->balance_interval < sd->max_interval) - sd->balance_interval *= 2; - } - - if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - - goto out; - -out_balanced: - schedstat_inc(sd, lb_balanced[idle]); - - sd->nr_balance_failed = 0; - -out_one_pinned: - /* tune up the balancing interval */ - if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) || - (sd->balance_interval < sd->max_interval)) - sd->balance_interval *= 2; - - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - ld_moved = -1; - else - ld_moved = 0; -out: - if (ld_moved) - update_shares(sd); - return ld_moved; + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; } /* - * Check this_cpu to ensure it is balanced within domain. Attempt to move - * tasks if there is an imbalance. - * - * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE). - * this_rq is locked. + * calc_load - update the avenrun load estimates 10 ticks after the + * CPUs have updated calc_load_tasks. */ -static int -load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd) +void calc_global_load(unsigned long ticks) { - struct sched_group *group; - struct rq *busiest = NULL; - unsigned long imbalance; - int ld_moved = 0; - int sd_idle = 0; - int all_pinned = 0; - struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask); - - cpumask_setall(cpus); - - /* - * When power savings policy is enabled for the parent domain, idle - * sibling can pick up load irrespective of busy siblings. In this case, - * let the state of idle sibling percolate up as IDLE, instead of - * portraying it as CPU_NOT_IDLE. - */ - if (sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - sd_idle = 1; - - schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); -redo: - update_shares_locked(this_rq, sd); - group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE, - &sd_idle, cpus, NULL); - if (!group) { - schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]); - goto out_balanced; - } - - busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus); - if (!busiest) { - schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]); - goto out_balanced; - } - - BUG_ON(busiest == this_rq); - - schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance); - - ld_moved = 0; - if (busiest->nr_running > 1) { - /* Attempt to move tasks */ - double_lock_balance(this_rq, busiest); - /* this_rq->clock is already updated */ - update_rq_clock(busiest); - ld_moved = move_tasks(this_rq, this_cpu, busiest, - imbalance, sd, CPU_NEWLY_IDLE, - &all_pinned); - double_unlock_balance(this_rq, busiest); - - if (unlikely(all_pinned)) { - cpumask_clear_cpu(cpu_of(busiest), cpus); - if (!cpumask_empty(cpus)) - goto redo; - } - } - - if (!ld_moved) { - int active_balance = 0; - - schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]); - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - - if (sched_mc_power_savings < POWERSAVINGS_BALANCE_WAKEUP) - return -1; - - if (sd->nr_balance_failed++ < 2) - return -1; - - /* - * The only task running in a non-idle cpu can be moved to this - * cpu in an attempt to completely freeup the other CPU - * package. The same method used to move task in load_balance() - * have been extended for load_balance_newidle() to speedup - * consolidation at sched_mc=POWERSAVINGS_BALANCE_WAKEUP (2) - * - * The package power saving logic comes from - * find_busiest_group(). If there are no imbalance, then - * f_b_g() will return NULL. However when sched_mc={1,2} then - * f_b_g() will select a group from which a running task may be - * pulled to this cpu in order to make the other package idle. - * If there is no opportunity to make a package idle and if - * there are no imbalance, then f_b_g() will return NULL and no - * action will be taken in load_balance_newidle(). - * - * Under normal task pull operation due to imbalance, there - * will be more than one task in the source run queue and - * move_tasks() will succeed. ld_moved will be true and this - * active balance code will not be triggered. - */ - - /* Lock busiest in correct order while this_rq is held */ - double_lock_balance(this_rq, busiest); - - /* - * don't kick the migration_thread, if the curr - * task on busiest cpu can't be moved to this_cpu - */ - if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) { - double_unlock_balance(this_rq, busiest); - all_pinned = 1; - return ld_moved; - } - - if (!busiest->active_balance) { - busiest->active_balance = 1; - busiest->push_cpu = this_cpu; - active_balance = 1; - } - - double_unlock_balance(this_rq, busiest); - /* - * Should not call ttwu while holding a rq->lock - */ - spin_unlock(&this_rq->lock); - if (active_balance) - wake_up_process(busiest->migration_thread); - spin_lock(&this_rq->lock); - - } else - sd->nr_balance_failed = 0; - - update_shares_locked(this_rq, sd); - return ld_moved; - -out_balanced: - schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]); - if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && - !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) - return -1; - sd->nr_balance_failed = 0; + long active; - return 0; -} + calc_global_nohz(ticks); -/* - * idle_balance is called by schedule() if this_cpu is about to become - * idle. Attempts to pull tasks from other CPUs. - */ -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; - - for_each_domain(this_cpu, sd) { - unsigned long interval; + if (time_before(jiffies, calc_load_update + 10)) + return; - if (!(sd->flags & SD_LOAD_BALANCE)) - continue; + active = atomic_long_read(&calc_load_tasks); + active = active > 0 ? active * FIXED_1 : 0; - if (sd->flags & SD_BALANCE_NEWIDLE) - /* If we've pulled tasks over stop searching: */ - pulled_task = load_balance_newidle(this_cpu, this_rq, - sd); + 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); - interval = msecs_to_jiffies(sd->balance_interval); - if (time_after(next_balance, sd->last_balance + interval)) - next_balance = sd->last_balance + interval; - if (pulled_task) - break; - } - if (pulled_task || time_after(jiffies, this_rq->next_balance)) { - /* - * We are going idle. next_balance may be set based on - * a busy processor. So reset next_balance. - */ - this_rq->next_balance = next_balance; - } + calc_load_update += LOAD_FREQ; } /* - * active_load_balance is run by migration threads. It pushes running tasks - * off the busiest CPU onto idle CPUs. It requires at least 1 task to be - * running on each physical CPU where possible, and avoids physical / - * logical imbalances. - * - * Called with busiest_rq locked. + * Called from update_cpu_load() to periodically update this CPU's + * active count. */ -static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) +static void calc_load_account_active(struct rq *this_rq) { - int target_cpu = busiest_rq->push_cpu; - struct sched_domain *sd; - struct rq *target_rq; + long delta; - /* Is there any task to move? */ - if (busiest_rq->nr_running <= 1) + if (time_before(jiffies, this_rq->calc_load_update)) return; - target_rq = cpu_rq(target_cpu); - - /* - * This condition is "impossible", if it occurs - * we need to fix it. Originally reported by - * Bjorn Helgaas on a 128-cpu setup. - */ - BUG_ON(busiest_rq == target_rq); - - /* move a task from busiest_rq to target_rq */ - double_lock_balance(busiest_rq, target_rq); - update_rq_clock(busiest_rq); - update_rq_clock(target_rq); - - /* Search for an sd spanning us and the target CPU. */ - for_each_domain(target_cpu, sd) { - if ((sd->flags & SD_LOAD_BALANCE) && - cpumask_test_cpu(busiest_cpu, sched_domain_span(sd))) - break; - } - - if (likely(sd)) { - schedstat_inc(sd, alb_count); - - if (move_one_task(target_rq, target_cpu, busiest_rq, - sd, CPU_IDLE)) - schedstat_inc(sd, alb_pushed); - else - schedstat_inc(sd, alb_failed); - } - double_unlock_balance(busiest_rq, target_rq); -} - -#ifdef CONFIG_NO_HZ -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), -}; + delta = calc_load_fold_active(this_rq); + delta += calc_load_fold_idle(); + if (delta) + atomic_long_add(delta, &calc_load_tasks); -int get_nohz_load_balancer(void) -{ - return atomic_read(&nohz.load_balancer); + this_rq->calc_load_update += LOAD_FREQ; } -#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. +/* + * The exact cpuload at various idx values, calculated at every tick would be + * load = (2^idx - 1) / 2^idx * load + 1 / 2^idx * cur_load * - * 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. + * If a cpu misses updates for n-1 ticks (as it was idle) and update gets called + * on nth tick when cpu may be busy, then we have: + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * load = (2^idx - 1) / 2^idx) * load + 1 / 2^idx * cur_load * - * 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 + * decay_load_missed() below does efficient calculation of + * load = ((2^idx - 1) / 2^idx)^(n-1) * load + * avoiding 0..n-1 loop doing load = ((2^idx - 1) / 2^idx) * load * - * Returns: 1 if the group is semi-idle. 0 otherwise. + * The calculation is approximated on a 128 point scale. + * degrade_zero_ticks is the number of ticks after which load at any + * particular idx is approximated to be zero. + * degrade_factor is a precomputed table, a row for each load idx. + * Each column corresponds to degradation factor for a power of two ticks, + * based on 128 point scale. + * Example: + * row 2, col 3 (=12) says that the degradation at load idx 2 after + * 8 ticks is 12/128 (which is an approximation of exact factor 3^8/4^8). * - * 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. + * With this power of 2 load factors, we can degrade the load n times + * by looking at 1 bits in n and doing as many mult/shift instead of + * n mult/shifts needed by the exact degradation. + */ +#define DEGRADE_SHIFT 7 +static const unsigned char + degrade_zero_ticks[CPU_LOAD_IDX_MAX] = {0, 8, 32, 64, 128}; +static const unsigned char + degrade_factor[CPU_LOAD_IDX_MAX][DEGRADE_SHIFT + 1] = { + {0, 0, 0, 0, 0, 0, 0, 0}, + {64, 32, 8, 0, 0, 0, 0, 0}, + {96, 72, 40, 12, 1, 0, 0}, + {112, 98, 75, 43, 15, 1, 0}, + {120, 112, 98, 76, 45, 16, 2} }; + +/* + * Update cpu_load for any missed ticks, due to tickless idle. The backlog + * would be when CPU is idle and so we just decay the old load without + * adding any new load. */ -static inline int is_semi_idle_group(struct sched_group *ilb_group) +static unsigned long +decay_load_missed(unsigned long load, unsigned long missed_updates, int idx) { - cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask, - sched_group_cpus(ilb_group)); + int j = 0; - /* - * 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 (!missed_updates) + return load; - if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group))) + if (missed_updates >= degrade_zero_ticks[idx]) 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 - * load balancing on behalf of all those cpus. If all the cpus in the system - * go into this tickless mode, then there will be no ilb owner (as there is - * no need for one) and all the cpus will sleep till the next wakeup event - * arrives... - * - * For the ilb owner, tick is not stopped. And this tick will be used - * for idle load balancing. ilb owner will still be part of - * nohz.cpu_mask.. - * - * While stopping the tick, this cpu will become the ilb owner if there - * is no other owner. And will be the owner till that cpu becomes busy - * or if all cpus in the system stop their ticks at which point - * there is no need for ilb owner. - * - * When the ilb owner becomes busy, it nominates another owner, during the - * next busy scheduler_tick() - */ -int select_nohz_load_balancer(int stop_tick) -{ - int cpu = smp_processor_id(); - - if (stop_tick) { - cpu_rq(cpu)->in_nohz_recently = 1; - - if (!cpu_active(cpu)) { - if (atomic_read(&nohz.load_balancer) != cpu) - return 0; - - /* - * If we are going offline and still the leader, - * give up! - */ - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) - BUG(); - - return 0; - } - - cpumask_set_cpu(cpu, nohz.cpu_mask); - - /* time for ilb owner also to sleep */ - if (cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { - if (atomic_read(&nohz.load_balancer) == cpu) - atomic_set(&nohz.load_balancer, -1); - return 0; - } - - if (atomic_read(&nohz.load_balancer) == -1) { - /* make me the ilb owner */ - if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) - return 1; - } 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; + if (idx == 1) + return load >> missed_updates; - cpumask_clear_cpu(cpu, nohz.cpu_mask); + while (missed_updates) { + if (missed_updates % 2) + load = (load * degrade_factor[idx][j]) >> DEGRADE_SHIFT; - if (atomic_read(&nohz.load_balancer) == cpu) - if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) - BUG(); + missed_updates >>= 1; + j++; } - return 0; + return load; } -#endif - -static DEFINE_SPINLOCK(balancing); /* - * It checks each scheduling domain to see if it is due to be balanced, - * and initiates a balancing operation if so. - * - * Balancing parameters are set up in arch_init_sched_domains. + * Update rq->cpu_load[] statistics. This function is usually called every + * scheduler tick (TICK_NSEC). With tickless idle this will not be called + * every tick. We fix it up based on jiffies. */ -static void rebalance_domains(int cpu, enum cpu_idle_type idle) +static void update_cpu_load(struct rq *this_rq) { - int balance = 1; - struct rq *rq = cpu_rq(cpu); - unsigned long interval; - struct sched_domain *sd; - /* Earliest time when we have to do rebalance again */ - unsigned long next_balance = jiffies + 60*HZ; - int update_next_balance = 0; - int need_serialize; - - for_each_domain(cpu, sd) { - if (!(sd->flags & SD_LOAD_BALANCE)) - continue; + unsigned long this_load = this_rq->load.weight; + unsigned long curr_jiffies = jiffies; + unsigned long pending_updates; + int i, scale; - interval = sd->balance_interval; - if (idle != CPU_IDLE) - interval *= sd->busy_factor; + this_rq->nr_load_updates++; - /* scale ms to jiffies */ - interval = msecs_to_jiffies(interval); - if (unlikely(!interval)) - interval = 1; - if (interval > HZ*NR_CPUS/10) - interval = HZ*NR_CPUS/10; + /* Avoid repeated calls on same jiffy, when moving in and out of idle */ + if (curr_jiffies == this_rq->last_load_update_tick) + return; - need_serialize = sd->flags & SD_SERIALIZE; + pending_updates = curr_jiffies - this_rq->last_load_update_tick; + this_rq->last_load_update_tick = curr_jiffies; - if (need_serialize) { - if (!spin_trylock(&balancing)) - goto out; - } + /* Update our load: */ + this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */ + for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { + unsigned long old_load, new_load; - if (time_after_eq(jiffies, sd->last_balance + interval)) { - if (load_balance(cpu, rq, sd, idle, &balance)) { - /* - * We've pulled tasks over so either we're no - * longer idle, or one of our SMT siblings is - * not idle. - */ - idle = CPU_NOT_IDLE; - } - sd->last_balance = jiffies; - } - if (need_serialize) - spin_unlock(&balancing); -out: - if (time_after(next_balance, sd->last_balance + interval)) { - next_balance = sd->last_balance + interval; - update_next_balance = 1; - } + /* scale is effectively 1 << i now, and >> i divides by scale */ + old_load = this_rq->cpu_load[i]; + old_load = decay_load_missed(old_load, pending_updates - 1, i); + new_load = this_load; /* - * Stop the load balance at this level. There is another - * CPU in our sched group which is doing load balancing more - * actively. + * Round up the averaging division if load is increasing. This + * prevents us from getting stuck on 9 if the load is 10, for + * example. */ - if (!balance) - break; + if (new_load > old_load) + new_load += scale - 1; + + this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i; } - /* - * next_balance will be updated only when there is a need. - * When the cpu is attached to null domain for ex, it will not be - * updated. - */ - if (likely(update_next_balance)) - rq->next_balance = next_balance; + sched_avg_update(this_rq); } -/* - * run_rebalance_domains is triggered when needed from the scheduler tick. - * In CONFIG_NO_HZ case, the idle load balance owner will do the - * rebalancing for all the cpus for whom scheduler ticks are stopped. - */ -static void run_rebalance_domains(struct softirq_action *h) +static void update_cpu_load_active(struct rq *this_rq) { - int this_cpu = smp_processor_id(); - struct rq *this_rq = cpu_rq(this_cpu); - enum cpu_idle_type idle = this_rq->idle_at_tick ? - CPU_IDLE : CPU_NOT_IDLE; - - rebalance_domains(this_cpu, idle); - -#ifdef CONFIG_NO_HZ - /* - * If this cpu is the owner for idle load balancing, then do the - * balancing on behalf of the other idle cpus whose ticks are - * stopped. - */ - if (this_rq->idle_at_tick && - atomic_read(&nohz.load_balancer) == this_cpu) { - struct rq *rq; - int balance_cpu; + update_cpu_load(this_rq); - for_each_cpu(balance_cpu, nohz.cpu_mask) { - if (balance_cpu == this_cpu) - continue; - - /* - * If this cpu gets work to do, stop the load balancing - * work being done for other cpus. Next load - * balancing owner will pick it up. - */ - if (need_resched()) - break; - - rebalance_domains(balance_cpu, CPU_IDLE); - - rq = cpu_rq(balance_cpu); - if (time_after(this_rq->next_balance, rq->next_balance)) - this_rq->next_balance = rq->next_balance; - } - } -#endif + calc_load_account_active(this_rq); } -static inline int on_null_domain(int cpu) -{ - return !rcu_dereference(cpu_rq(cpu)->sd); -} +#ifdef CONFIG_SMP /* - * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. - * - * In case of CONFIG_NO_HZ, this is the place where we nominate a new - * idle load balancing owner or decide to stop the periodic load balancing, - * if the whole system is idle. + * sched_exec - execve() is a valuable balancing opportunity, because at + * this point the task has the smallest effective memory and cache footprint. */ -static inline void trigger_load_balance(struct rq *rq, int cpu) +void sched_exec(void) { -#ifdef CONFIG_NO_HZ - /* - * If we were in the nohz mode recently and busy at the current - * scheduler tick, then check if we need to nominate new idle - * load balancer. - */ - if (rq->in_nohz_recently && !rq->idle_at_tick) { - rq->in_nohz_recently = 0; - - if (atomic_read(&nohz.load_balancer) == cpu) { - cpumask_clear_cpu(cpu, nohz.cpu_mask); - atomic_set(&nohz.load_balancer, -1); - } - - if (atomic_read(&nohz.load_balancer) == -1) { - int ilb = find_new_ilb(cpu); + struct task_struct *p = current; + unsigned long flags; + struct rq *rq; + int dest_cpu; - if (ilb < nr_cpu_ids) - resched_cpu(ilb); - } - } + rq = task_rq_lock(p, &flags); + dest_cpu = p->sched_class->select_task_rq(rq, p, SD_BALANCE_EXEC, 0); + if (dest_cpu == smp_processor_id()) + goto unlock; /* - * If this cpu is idle and doing idle load balancing for all the - * cpus with ticks stopped, is it time for that to stop? + * select_task_rq() can race against ->cpus_allowed */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && - cpumask_weight(nohz.cpu_mask) == num_online_cpus()) { - resched_cpu(cpu); - return; - } + if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed) && + likely(cpu_active(dest_cpu)) && migrate_task(p, rq)) { + struct migration_arg arg = { p, dest_cpu }; - /* - * If this cpu is idle and the idle load balancing is done by - * someone else, then no need raise the SCHED_SOFTIRQ - */ - if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && - cpumask_test_cpu(cpu, nohz.cpu_mask)) + task_rq_unlock(rq, &flags); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); return; -#endif - /* Don't need to rebalance while attached to NULL domain */ - if (time_after_eq(jiffies, rq->next_balance) && - likely(!on_null_domain(cpu))) - raise_softirq(SCHED_SOFTIRQ); -} - -#else /* CONFIG_SMP */ - -/* - * on UP we do not need to balance between CPUs: - */ -static inline void idle_balance(int cpu, struct rq *rq) -{ + } +unlock: + task_rq_unlock(rq, &flags); } #endif @@ -4816,7 +3445,7 @@ static u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) if (task_current(rq, p)) { update_rq_clock(rq); - ns = rq->clock - p->se.exec_start; + ns = rq->clock_task - p->se.exec_start; if ((s64)ns < 0) ns = 0; } @@ -4929,8 +3558,13 @@ static void account_guest_time(struct task_struct *p, cputime_t cputime, p->gtime = cputime_add(p->gtime, cputime); /* Add guest time to cpustat. */ - cpustat->user = cputime64_add(cpustat->user, tmp); - cpustat->guest = cputime64_add(cpustat->guest, tmp); + if (TASK_NICE(p) > 0) { + cpustat->nice = cputime64_add(cpustat->nice, tmp); + cpustat->guest_nice = cputime64_add(cpustat->guest_nice, tmp); + } else { + cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->guest = cputime64_add(cpustat->guest, tmp); + } } /* @@ -4960,7 +3594,7 @@ void account_system_time(struct task_struct *p, int hardirq_offset, tmp = cputime_to_cputime64(cputime); if (hardirq_count() - hardirq_offset) cpustat->irq = cputime64_add(cpustat->irq, tmp); - else if (softirq_count()) + else if (in_serving_softirq()) cpustat->softirq = cputime64_add(cpustat->softirq, tmp); else cpustat->system = cputime64_add(cpustat->system, tmp); @@ -5008,17 +3642,16 @@ void account_idle_time(cputime_t cputime) */ void account_process_tick(struct task_struct *p, int user_tick) { - cputime_t one_jiffy = jiffies_to_cputime(1); - cputime_t one_jiffy_scaled = cputime_to_scaled(one_jiffy); + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); struct rq *rq = this_rq(); if (user_tick) - account_user_time(p, one_jiffy, one_jiffy_scaled); + account_user_time(p, cputime_one_jiffy, one_jiffy_scaled); else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET)) - account_system_time(p, HARDIRQ_OFFSET, one_jiffy, + account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy, one_jiffy_scaled); else - account_idle_time(one_jiffy); + account_idle_time(cputime_one_jiffy); } /* @@ -5046,60 +3679,86 @@ void account_idle_ticks(unsigned long ticks) * Use precise platform statistics if available: */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING -cputime_t task_utime(struct task_struct *p) +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->utime; + *ut = p->utime; + *st = p->stime; } -cputime_t task_stime(struct task_struct *p) +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - return p->stime; + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; } #else -cputime_t task_utime(struct task_struct *p) + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t utime = cputime_to_clock_t(p->utime), - total = utime + cputime_to_clock_t(p->stime); - u64 temp; + cputime_t rtime, utime = p->utime, total = cputime_add(utime, p->stime); /* * Use CFS's precise accounting: */ - temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); + rtime = nsecs_to_cputime(p->se.sum_exec_runtime); if (total) { + u64 temp = rtime; + temp *= utime; do_div(temp, total); - } - utime = (clock_t)temp; + utime = (cputime_t)temp; + } else + utime = rtime; - p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime)); - return p->prev_utime; + /* + * Compare with previous values, to keep monotonicity: + */ + p->prev_utime = max(p->prev_utime, utime); + p->prev_stime = max(p->prev_stime, cputime_sub(rtime, p->prev_utime)); + + *ut = p->prev_utime; + *st = p->prev_stime; } -cputime_t task_stime(struct task_struct *p) +/* + * Must be called with siglock held. + */ +void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st) { - clock_t stime; + struct signal_struct *sig = p->signal; + struct task_cputime cputime; + cputime_t rtime, utime, total; - /* - * Use CFS's precise accounting. (we subtract utime from - * the total, to make sure the total observed by userspace - * grows monotonically - apps rely on that): - */ - stime = nsec_to_clock_t(p->se.sum_exec_runtime) - - cputime_to_clock_t(task_utime(p)); + thread_group_cputime(p, &cputime); - if (stime >= 0) - p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + total = cputime_add(cputime.utime, cputime.stime); + rtime = nsecs_to_cputime(cputime.sum_exec_runtime); - return p->prev_stime; -} -#endif + if (total) { + u64 temp = rtime; -inline cputime_t task_gtime(struct task_struct *p) -{ - return p->gtime; + temp *= cputime.utime; + do_div(temp, total); + utime = (cputime_t)temp; + } else + utime = rtime; + + sig->prev_utime = max(sig->prev_utime, utime); + sig->prev_stime = max(sig->prev_stime, + cputime_sub(rtime, sig->prev_utime)); + + *ut = sig->prev_utime; + *st = sig->prev_stime; } +#endif /* * This function gets called by the timer code, with HZ frequency. @@ -5116,13 +3775,13 @@ void scheduler_tick(void) sched_clock_tick(); - spin_lock(&rq->lock); + raw_spin_lock(&rq->lock); update_rq_clock(rq); - update_cpu_load(rq); + update_cpu_load_active(rq); curr->sched_class->task_tick(rq, curr, 0); - spin_unlock(&rq->lock); + raw_spin_unlock(&rq->lock); - perf_counter_task_tick(curr, cpu); + perf_event_task_tick(); #ifdef CONFIG_SMP rq->idle_at_tick = idle_cpu(cpu); @@ -5236,23 +3895,8 @@ static inline void schedule_debug(struct task_struct *prev) static void put_prev_task(struct rq *rq, struct task_struct *prev) { - if (prev->state == TASK_RUNNING) { - u64 runtime = prev->se.sum_exec_runtime; - - runtime -= prev->se.prev_sum_exec_runtime; - runtime = min_t(u64, runtime, 2*sysctl_sched_migration_cost); - - /* - * In order to avoid avg_overlap growing stale when we are - * indeed overlapping and hence not getting put to sleep, grow - * the avg_overlap on preemption. - * - * We use the average preemption runtime because that - * correlates to the amount of cache footprint a task can - * build up. - */ - update_avg(&prev->se.avg_overlap, runtime); - } + if (prev->se.on_rq) + update_rq_clock(rq); prev->sched_class->put_prev_task(rq, prev); } @@ -5275,17 +3919,13 @@ pick_next_task(struct rq *rq) return p; } - class = sched_class_highest; - for ( ; ; ) { + for_each_class(class) { p = class->pick_next_task(rq); if (p) return p; - /* - * Will never be NULL as the idle class always - * returns a non-NULL p: - */ - class = class->next; } + + BUG(); /* the idle class will always have a runnable task */ } /* @@ -5302,9 +3942,8 @@ need_resched: preempt_disable(); cpu = smp_processor_id(); rq = cpu_rq(cpu); - rcu_qsctr_inc(cpu); + rcu_note_context_switch(cpu); prev = rq->curr; - switch_count = &prev->nivcsw; release_kernel_lock(prev); need_resched_nonpreemptible: @@ -5314,32 +3953,44 @@ need_resched_nonpreemptible: if (sched_feat(HRTICK)) hrtick_clear(rq); - spin_lock_irq(&rq->lock); - update_rq_clock(rq); - clear_tsk_need_resched(prev); + raw_spin_lock_irq(&rq->lock); + switch_count = &prev->nivcsw; if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { - if (unlikely(signal_pending_state(prev->state, prev))) + if (unlikely(signal_pending_state(prev->state, prev))) { prev->state = TASK_RUNNING; - else - deactivate_task(rq, prev, 1); + } else { + /* + * If a worker is going to sleep, notify and + * ask workqueue whether it wants to wake up a + * task to maintain concurrency. If so, wake + * up the task. + */ + if (prev->flags & PF_WQ_WORKER) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev, cpu); + if (to_wakeup) + try_to_wake_up_local(to_wakeup); + } + deactivate_task(rq, prev, DEQUEUE_SLEEP); + } switch_count = &prev->nvcsw; } -#ifdef CONFIG_SMP - if (prev->sched_class->pre_schedule) - prev->sched_class->pre_schedule(rq, prev); -#endif + pre_schedule(rq, prev); if (unlikely(!rq->nr_running)) idle_balance(cpu, rq); put_prev_task(rq, prev); next = pick_next_task(rq); + clear_tsk_need_resched(prev); + rq->skip_clock_update = 0; if (likely(prev != next)) { sched_info_switch(prev, next); - perf_counter_task_sched_out(prev, next, cpu); + perf_event_task_sched_out(prev, next); rq->nr_switches++; rq->curr = next; @@ -5347,15 +3998,19 @@ need_resched_nonpreemptible: context_switch(rq, prev, next); /* unlocks the rq */ /* - * the context switch might have flipped the stack from under - * us, hence refresh the local variables. + * The context switch have flipped the stack from under us + * and restored the local variables which were saved when + * this task called schedule() in the past. prev == current + * is still correct, but it can be moved to another cpu/rq. */ cpu = smp_processor_id(); rq = cpu_rq(cpu); } else - spin_unlock_irq(&rq->lock); + raw_spin_unlock_irq(&rq->lock); + + post_schedule(rq); - if (unlikely(reacquire_kernel_lock(current) < 0)) + if (unlikely(reacquire_kernel_lock(prev))) goto need_resched_nonpreemptible; preempt_enable_no_resched(); @@ -5364,7 +4019,7 @@ need_resched_nonpreemptible: } EXPORT_SYMBOL(schedule); -#ifdef CONFIG_SMP +#ifdef CONFIG_MUTEX_SPIN_ON_OWNER /* * Look out! "owner" is an entirely speculative pointer * access and not reliable. @@ -5384,7 +4039,7 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) * the mutex owner just released it and exited. */ if (probe_kernel_address(&owner->cpu, cpu)) - goto out; + return 0; #else cpu = owner->cpu; #endif @@ -5394,14 +4049,14 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) * the cpu field may no longer be valid. */ if (cpu >= nr_cpumask_bits) - goto out; + return 0; /* * We need to validate that we can do a * get_cpu() and that we have the percpu area. */ if (!cpu_online(cpu)) - goto out; + return 0; rq = cpu_rq(cpu); @@ -5409,8 +4064,16 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) /* * Owner changed, break to re-assess state. */ - if (lock->owner != owner) + if (lock->owner != owner) { + /* + * If the lock has switched to a different owner, + * we likely have heavy contention. Return 0 to quit + * optimistic spinning and not contend further: + */ + if (lock->owner) + return 0; break; + } /* * Is that owner really running on that cpu? @@ -5418,9 +4081,9 @@ int mutex_spin_on_owner(struct mutex *lock, struct thread_info *owner) if (task_thread_info(rq->curr) != owner || need_resched()) return 0; - cpu_relax(); + arch_mutex_cpu_relax(); } -out: + return 1; } #endif @@ -5431,7 +4094,7 @@ out: * off of preempt_enable. Kernel preemptions off return from interrupt * occur there and call schedule directly. */ -asmlinkage void __sched preempt_schedule(void) +asmlinkage void __sched notrace preempt_schedule(void) { struct thread_info *ti = current_thread_info(); @@ -5443,9 +4106,9 @@ asmlinkage void __sched preempt_schedule(void) return; do { - add_preempt_count(PREEMPT_ACTIVE); + add_preempt_count_notrace(PREEMPT_ACTIVE); schedule(); - sub_preempt_count(PREEMPT_ACTIVE); + sub_preempt_count_notrace(PREEMPT_ACTIVE); /* * Check again in case we missed a preemption opportunity @@ -5486,10 +4149,10 @@ asmlinkage void __sched preempt_schedule_irq(void) #endif /* CONFIG_PREEMPT */ -int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, +int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, void *key) { - return try_to_wake_up(curr->private, mode, sync); + return try_to_wake_up(curr->private, mode, wake_flags); } EXPORT_SYMBOL(default_wake_function); @@ -5503,14 +4166,14 @@ EXPORT_SYMBOL(default_wake_function); * zero in this (rare) case, and we handle it by continuing to scan the queue. */ static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, - int nr_exclusive, int sync, void *key) + int nr_exclusive, int wake_flags, void *key) { wait_queue_t *curr, *next; list_for_each_entry_safe(curr, next, &q->task_list, task_list) { unsigned flags = curr->flags; - if (curr->func(curr, mode, sync, key) && + if (curr->func(curr, mode, wake_flags, key) && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) break; } @@ -5544,6 +4207,7 @@ void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) { __wake_up_common(q, mode, 1, 0, NULL); } +EXPORT_SYMBOL_GPL(__wake_up_locked); void __wake_up_locked_key(wait_queue_head_t *q, unsigned int mode, void *key) { @@ -5571,16 +4235,16 @@ void __wake_up_sync_key(wait_queue_head_t *q, unsigned int mode, int nr_exclusive, void *key) { unsigned long flags; - int sync = 1; + int wake_flags = WF_SYNC; if (unlikely(!q)) return; if (unlikely(!nr_exclusive)) - sync = 0; + wake_flags = 0; spin_lock_irqsave(&q->lock, flags); - __wake_up_common(q, mode, nr_exclusive, sync, key); + __wake_up_common(q, mode, nr_exclusive, wake_flags, key); spin_unlock_irqrestore(&q->lock, flags); } EXPORT_SYMBOL_GPL(__wake_up_sync_key); @@ -5643,8 +4307,7 @@ do_wait_for_common(struct completion *x, long timeout, int state) if (!x->done) { DECLARE_WAITQUEUE(wait, current); - wait.flags |= WQ_FLAG_EXCLUSIVE; - __add_wait_queue_tail(&x->wait, &wait); + __add_wait_queue_tail_exclusive(&x->wait, &wait); do { if (signal_pending_state(state, current)) { timeout = -ERESTARTSYS; @@ -5730,7 +4393,7 @@ EXPORT_SYMBOL(wait_for_completion_interruptible); * This waits for either a completion of a specific task to be signaled or for a * specified timeout to expire. It is interruptible. The timeout is in jiffies. */ -unsigned long __sched +long __sched wait_for_completion_interruptible_timeout(struct completion *x, unsigned long timeout) { @@ -5755,6 +4418,23 @@ int __sched wait_for_completion_killable(struct completion *x) EXPORT_SYMBOL(wait_for_completion_killable); /** + * wait_for_completion_killable_timeout: - waits for completion of a task (w/(to,killable)) + * @x: holds the state of this particular completion + * @timeout: timeout value in jiffies + * + * This waits for either a completion of a specific task to be + * signaled or for a specified timeout to expire. It can be + * interrupted by a kill signal. The timeout is in jiffies. + */ +long __sched +wait_for_completion_killable_timeout(struct completion *x, + unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_KILLABLE); +} +EXPORT_SYMBOL(wait_for_completion_killable_timeout); + +/** * try_wait_for_completion - try to decrement a completion without blocking * @x: completion structure * @@ -5768,14 +4448,15 @@ EXPORT_SYMBOL(wait_for_completion_killable); */ bool try_wait_for_completion(struct completion *x) { + unsigned long flags; int ret = 1; - spin_lock_irq(&x->wait.lock); + spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; else x->done--; - spin_unlock_irq(&x->wait.lock); + spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(try_wait_for_completion); @@ -5790,12 +4471,13 @@ EXPORT_SYMBOL(try_wait_for_completion); */ bool completion_done(struct completion *x) { + unsigned long flags; int ret = 1; - spin_lock_irq(&x->wait.lock); + spin_lock_irqsave(&x->wait.lock, flags); if (!x->done) ret = 0; - spin_unlock_irq(&x->wait.lock); + spin_unlock_irqrestore(&x->wait.lock, flags); return ret; } EXPORT_SYMBOL(completion_done); @@ -5863,14 +4545,15 @@ void rt_mutex_setprio(struct task_struct *p, int prio) unsigned long flags; int oldprio, on_rq, running; struct rq *rq; - const struct sched_class *prev_class = p->sched_class; + const struct sched_class *prev_class; BUG_ON(prio < 0 || prio > MAX_PRIO); rq = task_rq_lock(p, &flags); - update_rq_clock(rq); + trace_sched_pi_setprio(p, prio); oldprio = p->prio; + prev_class = p->sched_class; on_rq = p->se.on_rq; running = task_current(rq, p); if (on_rq) @@ -5888,7 +4571,7 @@ void rt_mutex_setprio(struct task_struct *p, int prio) if (running) p->sched_class->set_curr_task(rq); if (on_rq) { - enqueue_task(rq, p, 0); + enqueue_task(rq, p, oldprio < prio ? ENQUEUE_HEAD : 0); check_class_changed(rq, p, prev_class, oldprio, running); } @@ -5910,7 +4593,6 @@ void set_user_nice(struct task_struct *p, long nice) * the task might be in the middle of scheduling on another CPU. */ rq = task_rq_lock(p, &flags); - update_rq_clock(rq); /* * The RT priorities are set via sched_setscheduler(), but we still * allow the 'normal' nice value to be set - but as expected @@ -5955,7 +4637,7 @@ int can_nice(const struct task_struct *p, const int nice) /* convert nice value [19,-20] to rlimit style value [1,40] */ int nice_rlim = 20 - nice; - return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur || + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || capable(CAP_SYS_NICE)); } @@ -6058,22 +4740,14 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) BUG_ON(p->se.on_rq); p->policy = policy; - switch (p->policy) { - case SCHED_NORMAL: - case SCHED_BATCH: - case SCHED_IDLE: - p->sched_class = &fair_sched_class; - break; - case SCHED_FIFO: - case SCHED_RR: - p->sched_class = &rt_sched_class; - break; - } - p->rt_priority = prio; p->normal_prio = normal_prio(p); /* we are holding p->pi_lock already */ p->prio = rt_mutex_getprio(p); + if (rt_prio(p->prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; set_load_weight(p); } @@ -6094,23 +4768,31 @@ static bool check_same_owner(struct task_struct *p) } static int __sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param, bool user) + const struct sched_param *param, bool user) { int retval, oldprio, oldpolicy = -1, on_rq, running; unsigned long flags; - const struct sched_class *prev_class = p->sched_class; + const struct sched_class *prev_class; struct rq *rq; + int reset_on_fork; /* may grab non-irq protected spin_locks */ BUG_ON(in_interrupt()); recheck: /* double check policy once rq lock held */ - if (policy < 0) + if (policy < 0) { + reset_on_fork = p->sched_reset_on_fork; policy = oldpolicy = p->policy; - else if (policy != SCHED_FIFO && policy != SCHED_RR && - policy != SCHED_NORMAL && policy != SCHED_BATCH && - policy != SCHED_IDLE) - return -EINVAL; + } else { + reset_on_fork = !!(policy & SCHED_RESET_ON_FORK); + policy &= ~SCHED_RESET_ON_FORK; + + if (policy != SCHED_FIFO && policy != SCHED_RR && + policy != SCHED_NORMAL && policy != SCHED_BATCH && + policy != SCHED_IDLE) + return -EINVAL; + } + /* * Valid priorities for SCHED_FIFO and SCHED_RR are * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, @@ -6128,12 +4810,8 @@ recheck: */ if (user && !capable(CAP_SYS_NICE)) { if (rt_policy(policy)) { - unsigned long rlim_rtprio; - - if (!lock_task_sighand(p, &flags)) - return -ESRCH; - rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur; - unlock_task_sighand(p, &flags); + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); /* can't set/change the rt policy */ if (policy != p->policy && !rlim_rtprio) @@ -6154,20 +4832,14 @@ recheck: /* can't change other user's priorities */ if (!check_same_owner(p)) return -EPERM; - } - if (user) { -#ifdef CONFIG_RT_GROUP_SCHED - /* - * Do not allow realtime tasks into groups that have no runtime - * assigned. - */ - if (rt_bandwidth_enabled() && rt_policy(policy) && - task_group(p)->rt_bandwidth.rt_runtime == 0) + /* Normal users shall not reset the sched_reset_on_fork flag */ + if (p->sched_reset_on_fork && !reset_on_fork) return -EPERM; -#endif + } - retval = security_task_setscheduler(p, policy, param); + if (user) { + retval = security_task_setscheduler(p); if (retval) return retval; } @@ -6176,20 +4848,44 @@ recheck: * make sure no PI-waiters arrive (or leave) while we are * changing the priority of the task: */ - spin_lock_irqsave(&p->pi_lock, flags); + raw_spin_lock_irqsave(&p->pi_lock, flags); /* * To be able to change p->policy safely, the apropriate * runqueue lock must be held. */ rq = __task_rq_lock(p); + + /* + * Changing the policy of the stop threads its a very bad idea + */ + if (p == rq->stop) { + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return -EINVAL; + } + +#ifdef CONFIG_RT_GROUP_SCHED + if (user) { + /* + * Do not allow realtime tasks into groups that have no runtime + * assigned. + */ + if (rt_bandwidth_enabled() && rt_policy(policy) && + task_group(p)->rt_bandwidth.rt_runtime == 0) { + __task_rq_unlock(rq); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return -EPERM; + } + } +#endif + /* recheck policy now with rq lock held */ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { policy = oldpolicy = -1; __task_rq_unlock(rq); - spin_unlock_irqrestore(&p->pi_lock, flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); goto recheck; } - update_rq_clock(rq); on_rq = p->se.on_rq; running = task_current(rq, p); if (on_rq) @@ -6197,7 +4893,10 @@ recheck: if (running) p->sched_class->put_prev_task(rq, p); + p->sched_reset_on_fork = reset_on_fork; + oldprio = p->prio; + prev_class = p->sched_class; __setscheduler(rq, p, policy, param->sched_priority); if (running) @@ -6208,7 +4907,7 @@ recheck: check_class_changed(rq, p, prev_class, oldprio, running); } __task_rq_unlock(rq); - spin_unlock_irqrestore(&p->pi_lock, flags); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); rt_mutex_adjust_pi(p); @@ -6224,7 +4923,7 @@ recheck: * NOTE that the task may be already dead. */ int sched_setscheduler(struct task_struct *p, int policy, - struct sched_param *param) + const struct sched_param *param) { return __sched_setscheduler(p, policy, param, true); } @@ -6242,7 +4941,7 @@ EXPORT_SYMBOL_GPL(sched_setscheduler); * but our caller might not have that capability. */ int sched_setscheduler_nocheck(struct task_struct *p, int policy, - struct sched_param *param) + const struct sched_param *param) { return __sched_setscheduler(p, policy, param, false); } @@ -6308,19 +5007,20 @@ SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) return -EINVAL; retval = -ESRCH; - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); if (p) { retval = security_task_getscheduler(p); if (!retval) - retval = p->policy; + retval = p->policy + | (p->sched_reset_on_fork ? SCHED_RESET_ON_FORK : 0); } - read_unlock(&tasklist_lock); + rcu_read_unlock(); return retval; } /** - * sys_sched_getscheduler - get the RT priority of a thread + * sys_sched_getparam - get the RT priority of a thread * @pid: the pid in question. * @param: structure containing the RT priority. */ @@ -6333,7 +5033,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) if (!param || pid < 0) return -EINVAL; - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); retval = -ESRCH; if (!p) @@ -6344,7 +5044,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) goto out_unlock; lp.sched_priority = p->rt_priority; - read_unlock(&tasklist_lock); + rcu_read_unlock(); /* * This one might sleep, we cannot do it with a spinlock held ... @@ -6354,7 +5054,7 @@ SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) return retval; out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return retval; } @@ -6365,22 +5065,18 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) int retval; get_online_cpus(); - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); if (!p) { - read_unlock(&tasklist_lock); + rcu_read_unlock(); put_online_cpus(); return -ESRCH; } - /* - * It is not safe to call set_cpus_allowed with the - * tasklist_lock held. We will bump the task_struct's - * usage count and then drop tasklist_lock. - */ + /* Prevent p going away */ get_task_struct(p); - read_unlock(&tasklist_lock); + rcu_read_unlock(); if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { retval = -ENOMEM; @@ -6394,13 +5090,13 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) if (!check_same_owner(p) && !capable(CAP_SYS_NICE)) goto out_unlock; - retval = security_task_setscheduler(p, 0, NULL); + retval = security_task_setscheduler(p); if (retval) goto out_unlock; cpuset_cpus_allowed(p, cpus_allowed); cpumask_and(new_mask, in_mask, cpus_allowed); - again: +again: retval = set_cpus_allowed_ptr(p, new_mask); if (!retval) { @@ -6461,10 +5157,12 @@ SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, long sched_getaffinity(pid_t pid, struct cpumask *mask) { struct task_struct *p; + unsigned long flags; + struct rq *rq; int retval; get_online_cpus(); - read_lock(&tasklist_lock); + rcu_read_lock(); retval = -ESRCH; p = find_process_by_pid(pid); @@ -6475,10 +5173,12 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask) if (retval) goto out_unlock; + rq = task_rq_lock(p, &flags); cpumask_and(mask, &p->cpus_allowed, cpu_online_mask); + task_rq_unlock(rq, &flags); out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); put_online_cpus(); return retval; @@ -6496,7 +5196,9 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, int ret; cpumask_var_t mask; - if (len < cpumask_size()) + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) return -EINVAL; if (!alloc_cpumask_var(&mask, GFP_KERNEL)) @@ -6504,10 +5206,12 @@ SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, ret = sched_getaffinity(pid, mask); if (ret == 0) { - if (copy_to_user(user_mask_ptr, mask, cpumask_size())) + size_t retlen = min_t(size_t, len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) ret = -EFAULT; else - ret = cpumask_size(); + ret = retlen; } free_cpumask_var(mask); @@ -6533,7 +5237,7 @@ SYSCALL_DEFINE0(sched_yield) */ __release(rq->lock); spin_release(&rq->lock.dep_map, 1, _THIS_IP_); - _raw_spin_unlock(&rq->lock); + do_raw_spin_unlock(&rq->lock); preempt_enable_no_resched(); schedule(); @@ -6541,27 +5245,21 @@ SYSCALL_DEFINE0(sched_yield) return 0; } +static inline int should_resched(void) +{ + return need_resched() && !(preempt_count() & PREEMPT_ACTIVE); +} + static void __cond_resched(void) { -#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP - __might_sleep(__FILE__, __LINE__); -#endif - /* - * The BKS might be reacquired before we have dropped - * PREEMPT_ACTIVE, which could trigger a second - * cond_resched() call. - */ - do { - add_preempt_count(PREEMPT_ACTIVE); - schedule(); - sub_preempt_count(PREEMPT_ACTIVE); - } while (need_resched()); + add_preempt_count(PREEMPT_ACTIVE); + schedule(); + sub_preempt_count(PREEMPT_ACTIVE); } int __sched _cond_resched(void) { - if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) && - system_state == SYSTEM_RUNNING) { + if (should_resched()) { __cond_resched(); return 1; } @@ -6570,21 +5268,23 @@ int __sched _cond_resched(void) EXPORT_SYMBOL(_cond_resched); /* - * cond_resched_lock() - if a reschedule is pending, drop the given lock, + * __cond_resched_lock() - if a reschedule is pending, drop the given lock, * call schedule, and on return reacquire the lock. * * This works OK both with and without CONFIG_PREEMPT. We do strange low-level * operations here to prevent schedule() from being called twice (once via * spin_unlock(), once by hand). */ -int cond_resched_lock(spinlock_t *lock) +int __cond_resched_lock(spinlock_t *lock) { - int resched = need_resched() && system_state == SYSTEM_RUNNING; + int resched = should_resched(); int ret = 0; + lockdep_assert_held(lock); + if (spin_needbreak(lock) || resched) { spin_unlock(lock); - if (resched && need_resched()) + if (resched) __cond_resched(); else cpu_relax(); @@ -6593,13 +5293,13 @@ int cond_resched_lock(spinlock_t *lock) } return ret; } -EXPORT_SYMBOL(cond_resched_lock); +EXPORT_SYMBOL(__cond_resched_lock); -int __sched cond_resched_softirq(void) +int __sched __cond_resched_softirq(void) { BUG_ON(!in_softirq()); - if (need_resched() && system_state == SYSTEM_RUNNING) { + if (should_resched()) { local_bh_enable(); __cond_resched(); local_bh_disable(); @@ -6607,7 +5307,7 @@ int __sched cond_resched_softirq(void) } return 0; } -EXPORT_SYMBOL(cond_resched_softirq); +EXPORT_SYMBOL(__cond_resched_softirq); /** * yield - yield the current processor to other threads. @@ -6625,17 +5325,16 @@ EXPORT_SYMBOL(yield); /* * This task is about to go to sleep on IO. Increment rq->nr_iowait so * that process accounting knows that this is a task in IO wait state. - * - * But don't do that if it is a deliberate, throttling IO wait (this task - * has set its backing_dev_info: the queue against which it should throttle) */ void __sched io_schedule(void) { - struct rq *rq = &__raw_get_cpu_var(runqueues); + struct rq *rq = raw_rq(); delayacct_blkio_start(); atomic_inc(&rq->nr_iowait); + current->in_iowait = 1; schedule(); + current->in_iowait = 0; atomic_dec(&rq->nr_iowait); delayacct_blkio_end(); } @@ -6643,12 +5342,14 @@ EXPORT_SYMBOL(io_schedule); long __sched io_schedule_timeout(long timeout) { - struct rq *rq = &__raw_get_cpu_var(runqueues); + struct rq *rq = raw_rq(); long ret; delayacct_blkio_start(); atomic_inc(&rq->nr_iowait); + current->in_iowait = 1; ret = schedule_timeout(timeout); + current->in_iowait = 0; atomic_dec(&rq->nr_iowait); delayacct_blkio_end(); return ret; @@ -6716,6 +5417,8 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, { struct task_struct *p; unsigned int time_slice; + unsigned long flags; + struct rq *rq; int retval; struct timespec t; @@ -6723,7 +5426,7 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, return -EINVAL; retval = -ESRCH; - read_lock(&tasklist_lock); + rcu_read_lock(); p = find_process_by_pid(pid); if (!p) goto out_unlock; @@ -6732,30 +5435,17 @@ SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, if (retval) goto out_unlock; - /* - * 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 if (p->policy != SCHED_FIFO) { - struct sched_entity *se = &p->se; - unsigned long flags; - struct rq *rq; + rq = task_rq_lock(p, &flags); + time_slice = p->sched_class->get_rr_interval(rq, p); + task_rq_unlock(rq, &flags); - rq = task_rq_lock(p, &flags); - if (rq->cfs.load.weight) - time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); - task_rq_unlock(rq, &flags); - } - read_unlock(&tasklist_lock); + rcu_read_unlock(); jiffies_to_timespec(time_slice, &t); retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; return retval; out_unlock: - read_unlock(&tasklist_lock); + rcu_read_unlock(); return retval; } @@ -6767,7 +5457,7 @@ void sched_show_task(struct task_struct *p) unsigned state; state = p->state ? __ffs(p->state) + 1 : 0; - printk(KERN_INFO "%-13.13s %c", p->comm, + printk(KERN_INFO "%-15.15s %c", p->comm, state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); #if BITS_PER_LONG == 32 if (state == TASK_RUNNING) @@ -6821,7 +5511,7 @@ void show_state_filter(unsigned long state_filter) /* * Only show locks if all tasks are dumped: */ - if (state_filter == -1) + if (!state_filter) debug_show_all_locks(); } @@ -6843,20 +5533,32 @@ void __cpuinit init_idle(struct task_struct *idle, int cpu) struct rq *rq = cpu_rq(cpu); unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); __sched_fork(idle); + idle->state = TASK_RUNNING; idle->se.exec_start = sched_clock(); - idle->prio = idle->normal_prio = MAX_PRIO; cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu)); + /* + * We're having a chicken and egg problem, even though we are + * holding rq->lock, the cpu isn't yet set to this cpu so the + * lockdep check in task_group() will fail. + * + * Similar case to sched_fork(). / Alternatively we could + * use task_rq_lock() here and obtain the other rq->lock. + * + * Silence PROVE_RCU + */ + rcu_read_lock(); __set_task_cpu(idle, cpu); + rcu_read_unlock(); rq->curr = rq->idle = idle; #if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) idle->oncpu = 1; #endif - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); /* Set the preempt count _outside_ the spinlocks! */ #if defined(CONFIG_PREEMPT) @@ -6889,39 +5591,57 @@ cpumask_var_t nohz_cpu_mask; * * This idea comes from the SD scheduler of Con Kolivas: */ -static inline void sched_init_granularity(void) +static int get_update_sysctl_factor(void) { - unsigned int factor = 1 + ilog2(num_online_cpus()); - const unsigned long limit = 200000000; + unsigned int cpus = min_t(int, num_online_cpus(), 8); + unsigned int factor; - sysctl_sched_min_granularity *= factor; - if (sysctl_sched_min_granularity > limit) - sysctl_sched_min_granularity = limit; + switch (sysctl_sched_tunable_scaling) { + case SCHED_TUNABLESCALING_NONE: + factor = 1; + break; + case SCHED_TUNABLESCALING_LINEAR: + factor = cpus; + break; + case SCHED_TUNABLESCALING_LOG: + default: + factor = 1 + ilog2(cpus); + break; + } - sysctl_sched_latency *= factor; - if (sysctl_sched_latency > limit) - sysctl_sched_latency = limit; + return factor; +} - sysctl_sched_wakeup_granularity *= factor; +static void update_sysctl(void) +{ + unsigned int factor = get_update_sysctl_factor(); + +#define SET_SYSCTL(name) \ + (sysctl_##name = (factor) * normalized_sysctl_##name) + SET_SYSCTL(sched_min_granularity); + SET_SYSCTL(sched_latency); + SET_SYSCTL(sched_wakeup_granularity); +#undef SET_SYSCTL +} - sysctl_sched_shares_ratelimit *= factor; +static inline void sched_init_granularity(void) +{ + update_sysctl(); } #ifdef CONFIG_SMP /* * This is how migration works: * - * 1) we queue a struct migration_req structure in the source CPU's - * runqueue and wake up that CPU's migration thread. - * 2) we down() the locked semaphore => thread blocks. - * 3) migration thread wakes up (implicitly it forces the migrated - * thread off the CPU) - * 4) it gets the migration request and checks whether the migrated - * task is still in the wrong runqueue. - * 5) if it's in the wrong runqueue then the migration thread removes + * 1) we invoke migration_cpu_stop() on the target CPU using + * stop_one_cpu(). + * 2) stopper starts to run (implicitly forcing the migrated thread + * off the CPU) + * 3) it checks whether the migrated task is still in the wrong runqueue. + * 4) if it's in the wrong runqueue then the migration thread removes * it and puts it into the right queue. - * 6) migration thread up()s the semaphore. - * 7) we wake up and the migration is done. + * 5) stopper completes and stop_one_cpu() returns and the migration + * is done. */ /* @@ -6935,13 +5655,25 @@ static inline void sched_init_granularity(void) */ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { - struct migration_req req; unsigned long flags; struct rq *rq; + unsigned int dest_cpu; int ret = 0; + /* + * Serialize against TASK_WAKING so that ttwu() and wunt() can + * drop the rq->lock and still rely on ->cpus_allowed. + */ +again: + while (task_is_waking(p)) + cpu_relax(); rq = task_rq_lock(p, &flags); - if (!cpumask_intersects(new_mask, cpu_online_mask)) { + if (task_is_waking(p)) { + task_rq_unlock(rq, &flags); + goto again; + } + + if (!cpumask_intersects(new_mask, cpu_active_mask)) { ret = -EINVAL; goto out; } @@ -6963,11 +5695,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) if (cpumask_test_cpu(task_cpu(p), new_mask)) goto out; - if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) { + dest_cpu = cpumask_any_and(cpu_active_mask, new_mask); + if (migrate_task(p, rq)) { + struct migration_arg arg = { p, dest_cpu }; /* Need help from migration thread: drop lock and wait. */ task_rq_unlock(rq, &flags); - wake_up_process(rq->migration_thread); - wait_for_completion(&req.done); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); tlb_migrate_finish(p->mm); return 0; } @@ -6992,7 +5725,7 @@ EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) { struct rq *rq_dest, *rq_src; - int ret = 0, on_rq; + int ret = 0; if (unlikely(!cpu_active(dest_cpu))) return ret; @@ -7008,12 +5741,13 @@ static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) if (!cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) goto fail; - on_rq = p->se.on_rq; - if (on_rq) + /* + * If we're not on a rq, the next wake-up will ensure we're + * placed properly. + */ + if (p->se.on_rq) { deactivate_task(rq_src, p, 0); - - set_task_cpu(p, dest_cpu); - if (on_rq) { + set_task_cpu(p, dest_cpu); activate_task(rq_dest, p, 0); check_preempt_curr(rq_dest, p, 0); } @@ -7025,109 +5759,39 @@ fail: } /* - * migration_thread - this is a highprio system thread that performs - * thread migration by bumping thread off CPU then 'pushing' onto - * another runqueue. + * migration_cpu_stop - this will be executed by a highprio stopper thread + * and performs thread migration by bumping thread off CPU then + * 'pushing' onto another runqueue. */ -static int migration_thread(void *data) +static int migration_cpu_stop(void *data) { - int cpu = (long)data; - struct rq *rq; - - rq = cpu_rq(cpu); - BUG_ON(rq->migration_thread != current); - - set_current_state(TASK_INTERRUPTIBLE); - while (!kthread_should_stop()) { - struct migration_req *req; - struct list_head *head; - - spin_lock_irq(&rq->lock); - - if (cpu_is_offline(cpu)) { - spin_unlock_irq(&rq->lock); - break; - } - - if (rq->active_balance) { - active_load_balance(rq, cpu); - rq->active_balance = 0; - } - - head = &rq->migration_queue; - - if (list_empty(head)) { - spin_unlock_irq(&rq->lock); - schedule(); - set_current_state(TASK_INTERRUPTIBLE); - continue; - } - req = list_entry(head->next, struct migration_req, list); - list_del_init(head->next); - - spin_unlock(&rq->lock); - __migrate_task(req->task, cpu, req->dest_cpu); - local_irq_enable(); - - complete(&req->done); - } - __set_current_state(TASK_RUNNING); + struct migration_arg *arg = data; + /* + * The original target cpu might have gone down and we might + * be on another cpu but it doesn't matter. + */ + local_irq_disable(); + __migrate_task(arg->task, raw_smp_processor_id(), arg->dest_cpu); + local_irq_enable(); return 0; } #ifdef CONFIG_HOTPLUG_CPU -static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) -{ - int ret; - - local_irq_disable(); - ret = __migrate_task(p, src_cpu, dest_cpu); - local_irq_enable(); - return ret; -} - /* - * Figure out where task on dead CPU should go, use force if necessary. + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. */ -static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) +void idle_task_exit(void) { - int dest_cpu; - const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(dead_cpu)); - -again: - /* Look for allowed, online CPU in same node. */ - for_each_cpu_and(dest_cpu, nodemask, cpu_online_mask) - if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed)) - goto move; - - /* Any allowed, online CPU? */ - dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_online_mask); - if (dest_cpu < nr_cpu_ids) - goto move; - - /* No more Mr. Nice Guy. */ - if (dest_cpu >= nr_cpu_ids) { - cpuset_cpus_allowed_locked(p, &p->cpus_allowed); - dest_cpu = cpumask_any_and(cpu_online_mask, &p->cpus_allowed); + struct mm_struct *mm = current->active_mm; - /* - * Don't tell them about moving exiting tasks or - * kernel threads (both mm NULL), since they never - * leave kernel. - */ - if (p->mm && printk_ratelimit()) { - printk(KERN_INFO "process %d (%s) no " - "longer affine to cpu%d\n", - task_pid_nr(p), p->comm, dead_cpu); - } - } + BUG_ON(cpu_online(smp_processor_id())); -move: - /* It can have affinity changed while we were choosing. */ - if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu))) - goto again; + if (mm != &init_mm) + switch_mm(mm, &init_mm, current); + mmdrop(mm); } /* @@ -7139,130 +5803,70 @@ move: */ static void migrate_nr_uninterruptible(struct rq *rq_src) { - struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask)); - unsigned long flags; + struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask)); - local_irq_save(flags); - double_rq_lock(rq_src, rq_dest); rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; rq_src->nr_uninterruptible = 0; - double_rq_unlock(rq_src, rq_dest); - local_irq_restore(flags); -} - -/* Run through task list and migrate tasks from the dead cpu. */ -static void migrate_live_tasks(int src_cpu) -{ - struct task_struct *p, *t; - - read_lock(&tasklist_lock); - - do_each_thread(t, p) { - if (p == current) - continue; - - if (task_cpu(p) == src_cpu) - move_task_off_dead_cpu(src_cpu, p); - } while_each_thread(t, p); - - read_unlock(&tasklist_lock); } /* - * Schedules idle task to be the next runnable task on current CPU. - * It does so by boosting its priority to highest possible. - * Used by CPU offline code. + * remove the tasks which were accounted by rq from calc_load_tasks. */ -void sched_idle_next(void) +static void calc_global_load_remove(struct rq *rq) { - int this_cpu = smp_processor_id(); - struct rq *rq = cpu_rq(this_cpu); - struct task_struct *p = rq->idle; - unsigned long flags; - - /* cpu has to be offline */ - BUG_ON(cpu_online(this_cpu)); - - /* - * Strictly not necessary since rest of the CPUs are stopped by now - * and interrupts disabled on the current cpu. - */ - spin_lock_irqsave(&rq->lock, flags); - - __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - - update_rq_clock(rq); - activate_task(rq, p, 0); - - spin_unlock_irqrestore(&rq->lock, flags); + atomic_long_sub(rq->calc_load_active, &calc_load_tasks); + rq->calc_load_active = 0; } /* - * Ensures that the idle task is using init_mm right before its cpu goes - * offline. + * Migrate all tasks from the rq, sleeping tasks will be migrated by + * try_to_wake_up()->select_task_rq(). + * + * Called with rq->lock held even though we'er in stop_machine() and + * there's no concurrency possible, we hold the required locks anyway + * because of lock validation efforts. */ -void idle_task_exit(void) -{ - struct mm_struct *mm = current->active_mm; - - BUG_ON(cpu_online(smp_processor_id())); - - if (mm != &init_mm) - switch_mm(mm, &init_mm, current); - mmdrop(mm); -} - -/* called under rq->lock with disabled interrupts */ -static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) +static void migrate_tasks(unsigned int dead_cpu) { struct rq *rq = cpu_rq(dead_cpu); - - /* Must be exiting, otherwise would be on tasklist. */ - BUG_ON(!p->exit_state); - - /* Cannot have done final schedule yet: would have vanished. */ - BUG_ON(p->state == TASK_DEAD); - - get_task_struct(p); + struct task_struct *next, *stop = rq->stop; + int dest_cpu; /* - * Drop lock around migration; if someone else moves it, - * that's OK. No task can be added to this CPU, so iteration is - * fine. + * Fudge the rq selection such that the below task selection loop + * doesn't get stuck on the currently eligible stop task. + * + * We're currently inside stop_machine() and the rq is either stuck + * in the stop_machine_cpu_stop() loop, or we're executing this code, + * either way we should never end up calling schedule() until we're + * done here. */ - spin_unlock_irq(&rq->lock); - move_task_off_dead_cpu(dead_cpu, p); - spin_lock_irq(&rq->lock); - - put_task_struct(p); -} - -/* release_task() removes task from tasklist, so we won't find dead tasks. */ -static void migrate_dead_tasks(unsigned int dead_cpu) -{ - struct rq *rq = cpu_rq(dead_cpu); - struct task_struct *next; + rq->stop = NULL; for ( ; ; ) { - if (!rq->nr_running) + /* + * There's this thread running, bail when that's the only + * remaining thread. + */ + if (rq->nr_running == 1) break; - update_rq_clock(rq); + next = pick_next_task(rq); - if (!next) - break; + BUG_ON(!next); next->sched_class->put_prev_task(rq, next); - migrate_dead(dead_cpu, next); + /* Find suitable destination for @next, with force if needed. */ + dest_cpu = select_fallback_rq(dead_cpu, next); + raw_spin_unlock(&rq->lock); + + __migrate_task(next, dead_cpu, dest_cpu); + + raw_spin_lock(&rq->lock); } -} -/* - * 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); + rq->stop = stop; } + #endif /* CONFIG_HOTPLUG_CPU */ #if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) @@ -7272,17 +5876,16 @@ static struct ctl_table sd_ctl_dir[] = { .procname = "sched_domain", .mode = 0555, }, - {0, }, + {} }; static struct ctl_table sd_ctl_root[] = { { - .ctl_name = CTL_KERN, .procname = "kernel", .mode = 0555, .child = sd_ctl_dir, }, - {0, }, + {} }; static struct ctl_table *sd_alloc_ctl_entry(int n) @@ -7392,7 +5995,7 @@ static ctl_table *sd_alloc_ctl_cpu_table(int cpu) static struct ctl_table_header *sd_sysctl_header; static void register_sched_domain_sysctl(void) { - int i, cpu_num = num_online_cpus(); + int i, cpu_num = num_possible_cpus(); struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); char buf[32]; @@ -7402,7 +6005,7 @@ static void register_sched_domain_sysctl(void) if (entry == NULL) return; - for_each_online_cpu(i) { + for_each_possible_cpu(i) { snprintf(buf, 32, "cpu%d", i); entry->procname = kstrdup(buf, GFP_KERNEL); entry->mode = 0555; @@ -7469,108 +6072,41 @@ static void set_rq_offline(struct rq *rq) static int __cpuinit migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) { - struct task_struct *p; int cpu = (long)hcpu; unsigned long flags; - struct rq *rq; + struct rq *rq = cpu_rq(cpu); - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_UP_PREPARE: - case CPU_UP_PREPARE_FROZEN: - p = kthread_create(migration_thread, hcpu, "migration/%d", cpu); - if (IS_ERR(p)) - return NOTIFY_BAD; - kthread_bind(p, cpu); - /* Must be high prio: stop_machine expects to yield to it. */ - rq = task_rq_lock(p, &flags); - __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); - task_rq_unlock(rq, &flags); - get_task_struct(p); - cpu_rq(cpu)->migration_thread = p; + rq->calc_load_update = calc_load_update; break; case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - /* Strictly unnecessary, as first user will wake it. */ - wake_up_process(cpu_rq(cpu)->migration_thread); - /* 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; + raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_online(rq); } - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); break; #ifdef CONFIG_HOTPLUG_CPU - case CPU_UP_CANCELED: - case CPU_UP_CANCELED_FROZEN: - if (!cpu_rq(cpu)->migration_thread) - break; - /* Unbind it from offline cpu so it can run. Fall thru. */ - kthread_bind(cpu_rq(cpu)->migration_thread, - cpumask_any(cpu_online_mask)); - kthread_stop(cpu_rq(cpu)->migration_thread); - put_task_struct(cpu_rq(cpu)->migration_thread); - cpu_rq(cpu)->migration_thread = NULL; - break; - - case CPU_DEAD: - case CPU_DEAD_FROZEN: - cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */ - migrate_live_tasks(cpu); - rq = cpu_rq(cpu); - kthread_stop(rq->migration_thread); - put_task_struct(rq->migration_thread); - rq->migration_thread = NULL; - /* Idle task back to normal (off runqueue, low prio) */ - spin_lock_irq(&rq->lock); - update_rq_clock(rq); - deactivate_task(rq, rq->idle, 0); - rq->idle->static_prio = MAX_PRIO; - __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); - rq->idle->sched_class = &idle_sched_class; - migrate_dead_tasks(cpu); - spin_unlock_irq(&rq->lock); - 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 - * the requestors. - */ - spin_lock_irq(&rq->lock); - while (!list_empty(&rq->migration_queue)) { - struct migration_req *req; - - req = list_entry(rq->migration_queue.next, - struct migration_req, list); - list_del_init(&req->list); - spin_unlock_irq(&rq->lock); - complete(&req->done); - spin_lock_irq(&rq->lock); - } - spin_unlock_irq(&rq->lock); - break; - case CPU_DYING: - case CPU_DYING_FROZEN: /* Update our root-domain */ - rq = cpu_rq(cpu); - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); set_rq_offline(rq); } - spin_unlock_irqrestore(&rq->lock, flags); + migrate_tasks(cpu); + BUG_ON(rq->nr_running != 1); /* the migration thread */ + raw_spin_unlock_irqrestore(&rq->lock, flags); + + migrate_nr_uninterruptible(rq); + calc_global_load_remove(rq); break; #endif } @@ -7580,25 +6116,54 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) /* * 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. + * the notifier in the perf_event subsystem, though. */ static struct notifier_block __cpuinitdata migration_notifier = { .notifier_call = migration_call, - .priority = 10 + .priority = CPU_PRI_MIGRATION, }; +static int __cpuinit sched_cpu_active(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + case CPU_DOWN_FAILED: + set_cpu_active((long)hcpu, true); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + +static int __cpuinit sched_cpu_inactive(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + set_cpu_active((long)hcpu, false); + return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} + static int __init migration_init(void) { void *cpu = (void *)(long)smp_processor_id(); int err; - /* Start one for the boot CPU: */ + /* Initialize migration for the boot CPU */ err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); BUG_ON(err == NOTIFY_BAD); migration_call(&migration_notifier, CPU_ONLINE, cpu); register_cpu_notifier(&migration_notifier); - return err; + /* Register cpu active notifiers */ + cpu_notifier(sched_cpu_active, CPU_PRI_SCHED_ACTIVE); + cpu_notifier(sched_cpu_inactive, CPU_PRI_SCHED_INACTIVE); + + return 0; } early_initcall(migration_init); #endif @@ -7607,6 +6172,16 @@ early_initcall(migration_init); #ifdef CONFIG_SCHED_DEBUG +static __read_mostly int sched_domain_debug_enabled; + +static int __init sched_domain_debug_setup(char *str) +{ + sched_domain_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_domain_debug_setup); + static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, struct cpumask *groupmask) { @@ -7645,7 +6220,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, break; } - if (!group->__cpu_power) { + if (!group->cpu_power) { printk(KERN_CONT "\n"); printk(KERN_ERR "ERROR: domain->cpu_power not " "set\n"); @@ -7669,9 +6244,9 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, 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); + if (group->cpu_power != SCHED_LOAD_SCALE) { + printk(KERN_CONT " (cpu_power = %d)", + group->cpu_power); } group = group->next; @@ -7693,6 +6268,9 @@ static void sched_domain_debug(struct sched_domain *sd, int cpu) cpumask_var_t groupmask; int level = 0; + if (!sched_domain_debug_enabled) + return; + if (!sd) { printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); return; @@ -7736,9 +6314,7 @@ static int sd_degenerate(struct sched_domain *sd) } /* Following flags don't use groups */ - if (sd->flags & (SD_WAKE_IDLE | - SD_WAKE_AFFINE | - SD_WAKE_BALANCE)) + if (sd->flags & (SD_WAKE_AFFINE)) return 0; return 1; @@ -7755,10 +6331,6 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) if (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) return 0; - /* Does parent contain flags not in child? */ - /* WAKE_BALANCE is a subset of WAKE_AFFINE */ - if (cflags & SD_WAKE_AFFINE) - pflags &= ~SD_WAKE_BALANCE; /* Flags needing groups don't count if only 1 group in parent */ if (parent->groups == parent->groups->next) { pflags &= ~(SD_LOAD_BALANCE | @@ -7778,6 +6350,8 @@ sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) static void free_rootdomain(struct root_domain *rd) { + synchronize_sched(); + cpupri_cleanup(&rd->cpupri); free_cpumask_var(rd->rto_mask); @@ -7791,7 +6365,7 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) struct root_domain *old_rd = NULL; unsigned long flags; - spin_lock_irqsave(&rq->lock, flags); + raw_spin_lock_irqsave(&rq->lock, flags); if (rq->rd) { old_rd = rq->rd; @@ -7814,32 +6388,27 @@ static void rq_attach_root(struct rq *rq, struct root_domain *rd) rq->rd = rd; cpumask_set_cpu(rq->cpu, rd->span); - if (cpumask_test_cpu(rq->cpu, cpu_online_mask)) + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) set_rq_online(rq); - spin_unlock_irqrestore(&rq->lock, flags); + raw_spin_unlock_irqrestore(&rq->lock, flags); if (old_rd) free_rootdomain(old_rd); } -static int init_rootdomain(struct root_domain *rd, bool bootmem) +static int init_rootdomain(struct root_domain *rd) { - gfp_t gfp = GFP_KERNEL; - memset(rd, 0, sizeof(*rd)); - if (bootmem) - gfp = GFP_NOWAIT; - - if (!alloc_cpumask_var(&rd->span, gfp)) + if (!alloc_cpumask_var(&rd->span, GFP_KERNEL)) goto out; - if (!alloc_cpumask_var(&rd->online, gfp)) + if (!alloc_cpumask_var(&rd->online, GFP_KERNEL)) goto free_span; - if (!alloc_cpumask_var(&rd->rto_mask, gfp)) + if (!alloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) goto free_online; - if (cpupri_init(&rd->cpupri, bootmem) != 0) + if (cpupri_init(&rd->cpupri) != 0) goto free_rto_mask; return 0; @@ -7855,7 +6424,7 @@ out: static void init_defrootdomain(void) { - init_rootdomain(&def_root_domain, true); + init_rootdomain(&def_root_domain); atomic_set(&def_root_domain.refcount, 1); } @@ -7868,7 +6437,7 @@ static struct root_domain *alloc_rootdomain(void) if (!rd) return NULL; - if (init_rootdomain(rd, false) != 0) { + if (init_rootdomain(rd) != 0) { kfree(rd); return NULL; } @@ -7886,6 +6455,9 @@ cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) struct rq *rq = cpu_rq(cpu); struct sched_domain *tmp; + for (tmp = sd; tmp; tmp = tmp->parent) + tmp->span_weight = cpumask_weight(sched_domain_span(tmp)); + /* Remove the sched domains which do not contribute to scheduling. */ for (tmp = sd; tmp; ) { struct sched_domain *parent = tmp->parent; @@ -7918,6 +6490,7 @@ static cpumask_var_t cpu_isolated_map; /* Setup the mask of cpus configured for isolated domains */ static int __init isolated_cpu_setup(char *str) { + alloc_bootmem_cpumask_var(&cpu_isolated_map); cpulist_parse(str, cpu_isolated_map); return 1; } @@ -7956,7 +6529,7 @@ init_sched_build_groups(const struct cpumask *span, continue; cpumask_clear(sched_group_cpus(sg)); - sg->__cpu_power = 0; + sg->cpu_power = 0; for_each_cpu(j, span) { if (group_fn(j, cpu_map, NULL, tmpmask) != group) @@ -8064,19 +6637,54 @@ struct static_sched_domain { DECLARE_BITMAP(span, CONFIG_NR_CPUS); }; +struct s_data { +#ifdef CONFIG_NUMA + int sd_allnodes; + cpumask_var_t domainspan; + cpumask_var_t covered; + cpumask_var_t notcovered; +#endif + cpumask_var_t nodemask; + cpumask_var_t this_sibling_map; + cpumask_var_t this_core_map; + cpumask_var_t this_book_map; + cpumask_var_t send_covered; + cpumask_var_t tmpmask; + struct sched_group **sched_group_nodes; + struct root_domain *rd; +}; + +enum s_alloc { + sa_sched_groups = 0, + sa_rootdomain, + sa_tmpmask, + sa_send_covered, + sa_this_book_map, + sa_this_core_map, + sa_this_sibling_map, + sa_nodemask, + sa_sched_group_nodes, +#ifdef CONFIG_NUMA + sa_notcovered, + sa_covered, + sa_domainspan, +#endif + sa_none, +}; + /* * SMT sched-domains: */ #ifdef CONFIG_SCHED_SMT static DEFINE_PER_CPU(struct static_sched_domain, cpu_domains); -static DEFINE_PER_CPU(struct static_sched_group, sched_group_cpus); +static DEFINE_PER_CPU(struct static_sched_group, sched_groups); static int cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, struct sched_group **sg, struct cpumask *unused) { if (sg) - *sg = &per_cpu(sched_group_cpus, cpu).sg; + *sg = &per_cpu(sched_groups, cpu).sg; return cpu; } #endif /* CONFIG_SCHED_SMT */ @@ -8087,31 +6695,48 @@ cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map, #ifdef CONFIG_SCHED_MC static DEFINE_PER_CPU(struct static_sched_domain, core_domains); static DEFINE_PER_CPU(struct static_sched_group, sched_group_core); -#endif /* CONFIG_SCHED_MC */ -#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) static int cpu_to_core_group(int cpu, const struct cpumask *cpu_map, struct sched_group **sg, struct cpumask *mask) { int group; - +#ifdef CONFIG_SCHED_SMT cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); group = cpumask_first(mask); +#else + group = cpu; +#endif if (sg) *sg = &per_cpu(sched_group_core, group).sg; return group; } -#elif defined(CONFIG_SCHED_MC) +#endif /* CONFIG_SCHED_MC */ + +/* + * book sched-domains: + */ +#ifdef CONFIG_SCHED_BOOK +static DEFINE_PER_CPU(struct static_sched_domain, book_domains); +static DEFINE_PER_CPU(struct static_sched_group, sched_group_book); + static int -cpu_to_core_group(int cpu, const struct cpumask *cpu_map, - struct sched_group **sg, struct cpumask *unused) +cpu_to_book_group(int cpu, const struct cpumask *cpu_map, + struct sched_group **sg, struct cpumask *mask) { + int group = cpu; +#ifdef CONFIG_SCHED_MC + cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); + group = cpumask_first(mask); +#elif defined(CONFIG_SCHED_SMT) + cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map); + group = cpumask_first(mask); +#endif if (sg) - *sg = &per_cpu(sched_group_core, cpu).sg; - return cpu; + *sg = &per_cpu(sched_group_book, group).sg; + return group; } -#endif +#endif /* CONFIG_SCHED_BOOK */ static DEFINE_PER_CPU(struct static_sched_domain, phys_domains); static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys); @@ -8121,7 +6746,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map, struct sched_group **sg, struct cpumask *mask) { int group; -#ifdef CONFIG_SCHED_MC +#ifdef CONFIG_SCHED_BOOK + cpumask_and(mask, cpu_book_mask(cpu), cpu_map); + group = cpumask_first(mask); +#elif defined(CONFIG_SCHED_MC) cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map); group = cpumask_first(mask); #elif defined(CONFIG_SCHED_SMT) @@ -8181,11 +6809,76 @@ static void init_numa_sched_groups_power(struct sched_group *group_head) continue; } - sg_inc_cpu_power(sg, sd->groups->__cpu_power); + sg->cpu_power += sd->groups->cpu_power; } sg = sg->next; } while (sg != group_head); } + +static int build_numa_sched_groups(struct s_data *d, + const struct cpumask *cpu_map, int num) +{ + struct sched_domain *sd; + struct sched_group *sg, *prev; + int n, j; + + cpumask_clear(d->covered); + cpumask_and(d->nodemask, cpumask_of_node(num), cpu_map); + if (cpumask_empty(d->nodemask)) { + d->sched_group_nodes[num] = NULL; + goto out; + } + + sched_domain_node_span(num, d->domainspan); + cpumask_and(d->domainspan, d->domainspan, cpu_map); + + sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, num); + if (!sg) { + printk(KERN_WARNING "Can not alloc domain group for node %d\n", + num); + return -ENOMEM; + } + d->sched_group_nodes[num] = sg; + + for_each_cpu(j, d->nodemask) { + sd = &per_cpu(node_domains, j).sd; + sd->groups = sg; + } + + sg->cpu_power = 0; + cpumask_copy(sched_group_cpus(sg), d->nodemask); + sg->next = sg; + cpumask_or(d->covered, d->covered, d->nodemask); + + prev = sg; + for (j = 0; j < nr_node_ids; j++) { + n = (num + j) % nr_node_ids; + cpumask_complement(d->notcovered, d->covered); + cpumask_and(d->tmpmask, d->notcovered, cpu_map); + cpumask_and(d->tmpmask, d->tmpmask, d->domainspan); + if (cpumask_empty(d->tmpmask)) + break; + cpumask_and(d->tmpmask, d->tmpmask, cpumask_of_node(n)); + if (cpumask_empty(d->tmpmask)) + continue; + sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), + GFP_KERNEL, num); + if (!sg) { + printk(KERN_WARNING + "Can not alloc domain group for node %d\n", j); + return -ENOMEM; + } + sg->cpu_power = 0; + cpumask_copy(sched_group_cpus(sg), d->tmpmask); + sg->next = prev->next; + cpumask_or(d->covered, d->covered, d->tmpmask); + prev->next = sg; + prev = sg; + } +out: + return 0; +} #endif /* CONFIG_NUMA */ #ifdef CONFIG_NUMA @@ -8239,45 +6932,49 @@ static void free_sched_groups(const struct cpumask *cpu_map, * there are asymmetries in the topology. If there are asymmetries, group * having more cpu_power will pickup more load compared to the group having * less cpu_power. - * - * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents - * the maximum number of tasks a group can handle in the presence of other idle - * or lightly loaded groups in the same sched domain. */ static void init_sched_groups_power(int cpu, struct sched_domain *sd) { struct sched_domain *child; struct sched_group *group; + long power; + int weight; WARN_ON(!sd || !sd->groups); if (cpu != group_first_cpu(sd->groups)) return; + sd->groups->group_weight = cpumask_weight(sched_group_cpus(sd->groups)); + child = sd->child; - sd->groups->__cpu_power = 0; + sd->groups->cpu_power = 0; - /* - * For perf policy, if the groups in child domain share resources - * (for example cores sharing some portions of the cache hierarchy - * or SMT), then set this domain groups cpu_power such that each group - * can handle only one task, when there are other idle groups in the - * same sched domain. - */ - if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) && - (child->flags & - (SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) { - sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE); + if (!child) { + power = SCHED_LOAD_SCALE; + weight = cpumask_weight(sched_domain_span(sd)); + /* + * SMT siblings share the power of a single core. + * Usually multiple threads get a better yield out of + * that one core than a single thread would have, + * reflect that in sd->smt_gain. + */ + if ((sd->flags & SD_SHARE_CPUPOWER) && weight > 1) { + power *= sd->smt_gain; + power /= weight; + power >>= SCHED_LOAD_SHIFT; + } + sd->groups->cpu_power += power; return; } /* - * add cpu_power of each child group to this groups cpu_power + * Add cpu_power of each child group to this groups cpu_power. */ group = child->groups; do { - sg_inc_cpu_power(sd->groups, group->__cpu_power); + sd->groups->cpu_power += group->cpu_power; group = group->next; } while (group != child->groups); } @@ -8315,6 +7012,9 @@ SD_INIT_FUNC(CPU) #ifdef CONFIG_SCHED_MC SD_INIT_FUNC(MC) #endif +#ifdef CONFIG_SCHED_BOOK + SD_INIT_FUNC(BOOK) +#endif static int default_relax_domain_level = -1; @@ -8344,332 +7044,349 @@ static void set_domain_attribute(struct sched_domain *sd, request = attr->relax_domain_level; if (request < sd->level) { /* turn off idle balance on this domain */ - sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE); + sd->flags &= ~(SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); } else { /* turn on idle balance on this domain */ - sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE); + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } +} + +static void __free_domain_allocs(struct s_data *d, enum s_alloc what, + const struct cpumask *cpu_map) +{ + switch (what) { + case sa_sched_groups: + free_sched_groups(cpu_map, d->tmpmask); /* fall through */ + d->sched_group_nodes = NULL; + case sa_rootdomain: + free_rootdomain(d->rd); /* fall through */ + case sa_tmpmask: + free_cpumask_var(d->tmpmask); /* fall through */ + case sa_send_covered: + free_cpumask_var(d->send_covered); /* fall through */ + case sa_this_book_map: + free_cpumask_var(d->this_book_map); /* fall through */ + case sa_this_core_map: + free_cpumask_var(d->this_core_map); /* fall through */ + case sa_this_sibling_map: + free_cpumask_var(d->this_sibling_map); /* fall through */ + case sa_nodemask: + free_cpumask_var(d->nodemask); /* fall through */ + case sa_sched_group_nodes: +#ifdef CONFIG_NUMA + kfree(d->sched_group_nodes); /* fall through */ + case sa_notcovered: + free_cpumask_var(d->notcovered); /* fall through */ + case sa_covered: + free_cpumask_var(d->covered); /* fall through */ + case sa_domainspan: + free_cpumask_var(d->domainspan); /* fall through */ +#endif + case sa_none: + break; } } -/* - * Build sched domains for a given set of cpus and attach the sched domains - * to the individual cpus - */ -static int __build_sched_domains(const struct cpumask *cpu_map, - struct sched_domain_attr *attr) +static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, + const struct cpumask *cpu_map) { - int i, err = -ENOMEM; - struct root_domain *rd; - cpumask_var_t nodemask, this_sibling_map, this_core_map, send_covered, - tmpmask; #ifdef CONFIG_NUMA - cpumask_var_t domainspan, covered, notcovered; - struct sched_group **sched_group_nodes = NULL; - int sd_allnodes = 0; - - if (!alloc_cpumask_var(&domainspan, GFP_KERNEL)) - goto out; - if (!alloc_cpumask_var(&covered, GFP_KERNEL)) - goto free_domainspan; - if (!alloc_cpumask_var(¬covered, GFP_KERNEL)) - goto free_covered; -#endif - - if (!alloc_cpumask_var(&nodemask, GFP_KERNEL)) - goto free_notcovered; - if (!alloc_cpumask_var(&this_sibling_map, GFP_KERNEL)) - goto free_nodemask; - if (!alloc_cpumask_var(&this_core_map, GFP_KERNEL)) - goto free_this_sibling_map; - if (!alloc_cpumask_var(&send_covered, GFP_KERNEL)) - goto free_this_core_map; - if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) - goto free_send_covered; - -#ifdef CONFIG_NUMA - /* - * Allocate the per-node list of sched groups - */ - sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *), - GFP_KERNEL); - if (!sched_group_nodes) { + if (!alloc_cpumask_var(&d->domainspan, GFP_KERNEL)) + return sa_none; + if (!alloc_cpumask_var(&d->covered, GFP_KERNEL)) + return sa_domainspan; + if (!alloc_cpumask_var(&d->notcovered, GFP_KERNEL)) + return sa_covered; + /* Allocate the per-node list of sched groups */ + d->sched_group_nodes = kcalloc(nr_node_ids, + sizeof(struct sched_group *), GFP_KERNEL); + if (!d->sched_group_nodes) { printk(KERN_WARNING "Can not alloc sched group node list\n"); - goto free_tmpmask; - } -#endif - - rd = alloc_rootdomain(); - if (!rd) { + return sa_notcovered; + } + sched_group_nodes_bycpu[cpumask_first(cpu_map)] = d->sched_group_nodes; +#endif + if (!alloc_cpumask_var(&d->nodemask, GFP_KERNEL)) + return sa_sched_group_nodes; + if (!alloc_cpumask_var(&d->this_sibling_map, GFP_KERNEL)) + return sa_nodemask; + if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL)) + return sa_this_sibling_map; + if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL)) + return sa_this_core_map; + if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL)) + return sa_this_book_map; + if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL)) + return sa_send_covered; + d->rd = alloc_rootdomain(); + if (!d->rd) { printk(KERN_WARNING "Cannot alloc root domain\n"); - goto free_sched_groups; + return sa_tmpmask; } + return sa_rootdomain; +} +static struct sched_domain *__build_numa_sched_domains(struct s_data *d, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, int i) +{ + struct sched_domain *sd = NULL; #ifdef CONFIG_NUMA - sched_group_nodes_bycpu[cpumask_first(cpu_map)] = sched_group_nodes; -#endif + struct sched_domain *parent; - /* - * Set up domains for cpus specified by the cpu_map. - */ - for_each_cpu(i, cpu_map) { - struct sched_domain *sd = NULL, *p; + d->sd_allnodes = 0; + if (cpumask_weight(cpu_map) > + SD_NODES_PER_DOMAIN * cpumask_weight(d->nodemask)) { + sd = &per_cpu(allnodes_domains, i).sd; + SD_INIT(sd, ALLNODES); + set_domain_attribute(sd, attr); + cpumask_copy(sched_domain_span(sd), cpu_map); + cpu_to_allnodes_group(i, cpu_map, &sd->groups, d->tmpmask); + d->sd_allnodes = 1; + } + parent = sd; - cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map); + sd = &per_cpu(node_domains, i).sd; + SD_INIT(sd, NODE); + set_domain_attribute(sd, attr); + sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); + sd->parent = parent; + if (parent) + parent->child = sd; + cpumask_and(sched_domain_span(sd), sched_domain_span(sd), cpu_map); +#endif + return sd; +} -#ifdef CONFIG_NUMA - if (cpumask_weight(cpu_map) > - SD_NODES_PER_DOMAIN*cpumask_weight(nodemask)) { - sd = &per_cpu(allnodes_domains, i).sd; - SD_INIT(sd, ALLNODES); - set_domain_attribute(sd, attr); - cpumask_copy(sched_domain_span(sd), cpu_map); - cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask); - p = sd; - sd_allnodes = 1; - } else - p = NULL; +static struct sched_domain *__build_cpu_sched_domain(struct s_data *d, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *parent, int i) +{ + struct sched_domain *sd; + sd = &per_cpu(phys_domains, i).sd; + SD_INIT(sd, CPU); + set_domain_attribute(sd, attr); + cpumask_copy(sched_domain_span(sd), d->nodemask); + sd->parent = parent; + if (parent) + parent->child = sd; + cpu_to_phys_group(i, cpu_map, &sd->groups, d->tmpmask); + return sd; +} - sd = &per_cpu(node_domains, i).sd; - SD_INIT(sd, NODE); - set_domain_attribute(sd, attr); - sched_domain_node_span(cpu_to_node(i), sched_domain_span(sd)); - sd->parent = p; - if (p) - p->child = sd; - cpumask_and(sched_domain_span(sd), - sched_domain_span(sd), cpu_map); +static struct sched_domain *__build_book_sched_domain(struct s_data *d, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *parent, int i) +{ + struct sched_domain *sd = parent; +#ifdef CONFIG_SCHED_BOOK + sd = &per_cpu(book_domains, i).sd; + SD_INIT(sd, BOOK); + set_domain_attribute(sd, attr); + cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i)); + sd->parent = parent; + parent->child = sd; + cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask); #endif + return sd; +} - p = sd; - sd = &per_cpu(phys_domains, i).sd; - SD_INIT(sd, CPU); - set_domain_attribute(sd, attr); - cpumask_copy(sched_domain_span(sd), nodemask); - sd->parent = p; - if (p) - p->child = sd; - cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask); - +static struct sched_domain *__build_mc_sched_domain(struct s_data *d, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *parent, int i) +{ + struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_MC - p = sd; - sd = &per_cpu(core_domains, i).sd; - SD_INIT(sd, MC); - set_domain_attribute(sd, attr); - cpumask_and(sched_domain_span(sd), cpu_map, - cpu_coregroup_mask(i)); - sd->parent = p; - p->child = sd; - cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask); + sd = &per_cpu(core_domains, i).sd; + SD_INIT(sd, MC); + set_domain_attribute(sd, attr); + cpumask_and(sched_domain_span(sd), cpu_map, cpu_coregroup_mask(i)); + sd->parent = parent; + parent->child = sd; + cpu_to_core_group(i, cpu_map, &sd->groups, d->tmpmask); #endif + return sd; +} +static struct sched_domain *__build_smt_sched_domain(struct s_data *d, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *parent, int i) +{ + struct sched_domain *sd = parent; #ifdef CONFIG_SCHED_SMT - p = sd; - sd = &per_cpu(cpu_domains, i).sd; - SD_INIT(sd, SIBLING); - set_domain_attribute(sd, attr); - cpumask_and(sched_domain_span(sd), - topology_thread_cpumask(i), cpu_map); - sd->parent = p; - p->child = sd; - cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask); + sd = &per_cpu(cpu_domains, i).sd; + SD_INIT(sd, SIBLING); + set_domain_attribute(sd, attr); + cpumask_and(sched_domain_span(sd), cpu_map, topology_thread_cpumask(i)); + sd->parent = parent; + parent->child = sd; + cpu_to_cpu_group(i, cpu_map, &sd->groups, d->tmpmask); #endif - } + return sd; +} +static void build_sched_groups(struct s_data *d, enum sched_domain_level l, + const struct cpumask *cpu_map, int cpu) +{ + switch (l) { #ifdef CONFIG_SCHED_SMT - /* Set up CPU (sibling) groups */ - for_each_cpu(i, cpu_map) { - cpumask_and(this_sibling_map, - topology_thread_cpumask(i), cpu_map); - if (i != cpumask_first(this_sibling_map)) - continue; - - init_sched_build_groups(this_sibling_map, cpu_map, - &cpu_to_cpu_group, - send_covered, tmpmask); - } + case SD_LV_SIBLING: /* set up CPU (sibling) groups */ + cpumask_and(d->this_sibling_map, cpu_map, + topology_thread_cpumask(cpu)); + if (cpu == cpumask_first(d->this_sibling_map)) + init_sched_build_groups(d->this_sibling_map, cpu_map, + &cpu_to_cpu_group, + d->send_covered, d->tmpmask); + break; #endif - #ifdef CONFIG_SCHED_MC - /* Set up multi-core groups */ - for_each_cpu(i, cpu_map) { - cpumask_and(this_core_map, cpu_coregroup_mask(i), cpu_map); - if (i != cpumask_first(this_core_map)) - continue; - - init_sched_build_groups(this_core_map, cpu_map, - &cpu_to_core_group, - send_covered, tmpmask); - } + case SD_LV_MC: /* set up multi-core groups */ + cpumask_and(d->this_core_map, cpu_map, cpu_coregroup_mask(cpu)); + if (cpu == cpumask_first(d->this_core_map)) + init_sched_build_groups(d->this_core_map, cpu_map, + &cpu_to_core_group, + d->send_covered, d->tmpmask); + break; #endif - - /* Set up physical groups */ - for (i = 0; i < nr_node_ids; i++) { - cpumask_and(nodemask, cpumask_of_node(i), cpu_map); - if (cpumask_empty(nodemask)) - continue; - - init_sched_build_groups(nodemask, cpu_map, - &cpu_to_phys_group, - send_covered, tmpmask); - } - +#ifdef CONFIG_SCHED_BOOK + case SD_LV_BOOK: /* set up book groups */ + cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu)); + if (cpu == cpumask_first(d->this_book_map)) + init_sched_build_groups(d->this_book_map, cpu_map, + &cpu_to_book_group, + d->send_covered, d->tmpmask); + break; +#endif + case SD_LV_CPU: /* set up physical groups */ + cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map); + if (!cpumask_empty(d->nodemask)) + init_sched_build_groups(d->nodemask, cpu_map, + &cpu_to_phys_group, + d->send_covered, d->tmpmask); + break; #ifdef CONFIG_NUMA - /* Set up node groups */ - if (sd_allnodes) { - init_sched_build_groups(cpu_map, cpu_map, - &cpu_to_allnodes_group, - send_covered, tmpmask); + case SD_LV_ALLNODES: + init_sched_build_groups(cpu_map, cpu_map, &cpu_to_allnodes_group, + d->send_covered, d->tmpmask); + break; +#endif + default: + break; } +} - for (i = 0; i < nr_node_ids; i++) { - /* Set up node groups */ - struct sched_group *sg, *prev; - int j; - - cpumask_clear(covered); - cpumask_and(nodemask, cpumask_of_node(i), cpu_map); - if (cpumask_empty(nodemask)) { - sched_group_nodes[i] = NULL; - continue; - } +/* + * Build sched domains for a given set of cpus and attach the sched domains + * to the individual cpus + */ +static int __build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) +{ + enum s_alloc alloc_state = sa_none; + struct s_data d; + struct sched_domain *sd; + int i; +#ifdef CONFIG_NUMA + d.sd_allnodes = 0; +#endif - sched_domain_node_span(i, domainspan); - cpumask_and(domainspan, domainspan, cpu_map); + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); + if (alloc_state != sa_rootdomain) + goto error; + alloc_state = sa_sched_groups; - sg = kmalloc_node(sizeof(struct sched_group) + cpumask_size(), - GFP_KERNEL, i); - if (!sg) { - printk(KERN_WARNING "Can not alloc domain group for " - "node %d\n", i); - goto error; - } - sched_group_nodes[i] = sg; - for_each_cpu(j, nodemask) { - struct sched_domain *sd; + /* + * Set up domains for cpus specified by the cpu_map. + */ + for_each_cpu(i, cpu_map) { + cpumask_and(d.nodemask, cpumask_of_node(cpu_to_node(i)), + cpu_map); - sd = &per_cpu(node_domains, j).sd; - sd->groups = sg; - } - sg->__cpu_power = 0; - cpumask_copy(sched_group_cpus(sg), nodemask); - sg->next = sg; - cpumask_or(covered, covered, nodemask); - prev = sg; + sd = __build_numa_sched_domains(&d, cpu_map, attr, i); + sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i); + sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i); + sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i); + sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i); + } - for (j = 0; j < nr_node_ids; j++) { - int n = (i + j) % nr_node_ids; + for_each_cpu(i, cpu_map) { + build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i); + build_sched_groups(&d, SD_LV_BOOK, cpu_map, i); + build_sched_groups(&d, SD_LV_MC, cpu_map, i); + } - cpumask_complement(notcovered, covered); - cpumask_and(tmpmask, notcovered, cpu_map); - cpumask_and(tmpmask, tmpmask, domainspan); - if (cpumask_empty(tmpmask)) - break; + /* Set up physical groups */ + for (i = 0; i < nr_node_ids; i++) + build_sched_groups(&d, SD_LV_CPU, cpu_map, i); - cpumask_and(tmpmask, tmpmask, cpumask_of_node(n)); - if (cpumask_empty(tmpmask)) - continue; +#ifdef CONFIG_NUMA + /* Set up node groups */ + if (d.sd_allnodes) + build_sched_groups(&d, SD_LV_ALLNODES, cpu_map, 0); - sg = kmalloc_node(sizeof(struct sched_group) + - cpumask_size(), - GFP_KERNEL, i); - if (!sg) { - printk(KERN_WARNING - "Can not alloc domain group for node %d\n", j); - goto error; - } - sg->__cpu_power = 0; - cpumask_copy(sched_group_cpus(sg), tmpmask); - sg->next = prev->next; - cpumask_or(covered, covered, tmpmask); - prev->next = sg; - prev = sg; - } - } + for (i = 0; i < nr_node_ids; i++) + if (build_numa_sched_groups(&d, cpu_map, i)) + goto error; #endif /* Calculate CPU power for physical packages and nodes */ #ifdef CONFIG_SCHED_SMT for_each_cpu(i, cpu_map) { - struct sched_domain *sd = &per_cpu(cpu_domains, i).sd; - + sd = &per_cpu(cpu_domains, i).sd; init_sched_groups_power(i, sd); } #endif #ifdef CONFIG_SCHED_MC for_each_cpu(i, cpu_map) { - struct sched_domain *sd = &per_cpu(core_domains, i).sd; - + sd = &per_cpu(core_domains, i).sd; init_sched_groups_power(i, sd); } #endif - +#ifdef CONFIG_SCHED_BOOK for_each_cpu(i, cpu_map) { - struct sched_domain *sd = &per_cpu(phys_domains, i).sd; + sd = &per_cpu(book_domains, i).sd; + init_sched_groups_power(i, sd); + } +#endif + for_each_cpu(i, cpu_map) { + sd = &per_cpu(phys_domains, i).sd; init_sched_groups_power(i, sd); } #ifdef CONFIG_NUMA for (i = 0; i < nr_node_ids; i++) - init_numa_sched_groups_power(sched_group_nodes[i]); + init_numa_sched_groups_power(d.sched_group_nodes[i]); - if (sd_allnodes) { + if (d.sd_allnodes) { struct sched_group *sg; cpu_to_allnodes_group(cpumask_first(cpu_map), cpu_map, &sg, - tmpmask); + d.tmpmask); init_numa_sched_groups_power(sg); } #endif /* Attach the domains */ for_each_cpu(i, cpu_map) { - struct sched_domain *sd; #ifdef CONFIG_SCHED_SMT sd = &per_cpu(cpu_domains, i).sd; #elif defined(CONFIG_SCHED_MC) sd = &per_cpu(core_domains, i).sd; +#elif defined(CONFIG_SCHED_BOOK) + sd = &per_cpu(book_domains, i).sd; #else sd = &per_cpu(phys_domains, i).sd; #endif - cpu_attach_domain(sd, rd, i); + cpu_attach_domain(sd, d.rd, i); } - err = 0; - -free_tmpmask: - free_cpumask_var(tmpmask); -free_send_covered: - free_cpumask_var(send_covered); -free_this_core_map: - free_cpumask_var(this_core_map); -free_this_sibling_map: - free_cpumask_var(this_sibling_map); -free_nodemask: - free_cpumask_var(nodemask); -free_notcovered: -#ifdef CONFIG_NUMA - free_cpumask_var(notcovered); -free_covered: - free_cpumask_var(covered); -free_domainspan: - free_cpumask_var(domainspan); -out: -#endif - return err; - -free_sched_groups: -#ifdef CONFIG_NUMA - kfree(sched_group_nodes); -#endif - goto free_tmpmask; + d.sched_group_nodes = NULL; /* don't free this we still need it */ + __free_domain_allocs(&d, sa_tmpmask, cpu_map); + return 0; -#ifdef CONFIG_NUMA error: - free_sched_groups(cpu_map, tmpmask); - free_rootdomain(rd); - goto free_tmpmask; -#endif + __free_domain_allocs(&d, alloc_state, cpu_map); + return -ENOMEM; } static int build_sched_domains(const struct cpumask *cpu_map) @@ -8677,7 +7394,7 @@ static int build_sched_domains(const struct cpumask *cpu_map) return __build_sched_domains(cpu_map, NULL); } -static struct cpumask *doms_cur; /* current sched domains */ +static cpumask_var_t *doms_cur; /* current sched domains */ static int ndoms_cur; /* number of sched domains in 'doms_cur' */ static struct sched_domain_attr *dattr_cur; /* attribues of custom domains in 'doms_cur' */ @@ -8699,6 +7416,31 @@ int __attribute__((weak)) arch_update_cpu_topology(void) return 0; } +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + /* * Set up scheduler domains and groups. Callers must hold the hotplug lock. * For now this just excludes isolated cpus, but could be used to @@ -8710,12 +7452,12 @@ static int arch_init_sched_domains(const struct cpumask *cpu_map) arch_update_cpu_topology(); ndoms_cur = 1; - doms_cur = kmalloc(cpumask_size(), GFP_KERNEL); + doms_cur = alloc_sched_domains(ndoms_cur); if (!doms_cur) - doms_cur = fallback_doms; - cpumask_andnot(doms_cur, cpu_map, cpu_isolated_map); + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); dattr_cur = NULL; - err = build_sched_domains(doms_cur); + err = build_sched_domains(doms_cur[0]); register_sched_domain_sysctl(); return err; @@ -8765,19 +7507,19 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * doms_new[] to the current sched domain partitioning, doms_cur[]. * It destroys each deleted domain and builds each new domain. * - * 'doms_new' is an array of cpumask's of length 'ndoms_new'. + * 'doms_new' is an array of cpumask_var_t's of length 'ndoms_new'. * The masks don't intersect (don't overlap.) We should setup one * sched domain for each mask. CPUs not in any of the cpumasks will * not be load balanced. If the same cpumask appears both in the * current 'doms_cur' domains and in the new 'doms_new', we can leave * it as it is. * - * The passed in 'doms_new' should be kmalloc'd. This routine takes - * ownership of it and will kfree it when done with it. If the caller - * failed the kmalloc call, then it can pass in doms_new == NULL && - * ndoms_new == 1, and partition_sched_domains() will fallback to - * the single partition 'fallback_doms', it also forces the domains - * to be rebuilt. + * The passed in 'doms_new' should be allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc call, then it can pass in doms_new == NULL && ndoms_new == 1, + * and partition_sched_domains() will fallback to the single partition + * 'fallback_doms', it also forces the domains to be rebuilt. * * If doms_new == NULL it will be replaced with cpu_online_mask. * ndoms_new == 0 is a special case for destroying existing domains, @@ -8785,8 +7527,7 @@ static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, * * Call with hotplug lock held */ -/* FIXME: Change to struct cpumask *doms_new[] */ -void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, +void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { int i, j, n; @@ -8805,40 +7546,40 @@ void partition_sched_domains(int ndoms_new, struct cpumask *doms_new, /* Destroy deleted domains */ for (i = 0; i < ndoms_cur; i++) { for (j = 0; j < n && !new_topology; j++) { - if (cpumask_equal(&doms_cur[i], &doms_new[j]) + if (cpumask_equal(doms_cur[i], doms_new[j]) && dattrs_equal(dattr_cur, i, dattr_new, j)) goto match1; } /* no match - a current sched domain not in new doms_new[] */ - detach_destroy_domains(doms_cur + i); + detach_destroy_domains(doms_cur[i]); match1: ; } if (doms_new == NULL) { ndoms_cur = 0; - doms_new = fallback_doms; - cpumask_andnot(&doms_new[0], cpu_online_mask, cpu_isolated_map); + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); WARN_ON_ONCE(dattr_new); } /* Build new domains */ for (i = 0; i < ndoms_new; i++) { for (j = 0; j < ndoms_cur && !new_topology; j++) { - if (cpumask_equal(&doms_new[i], &doms_cur[j]) + if (cpumask_equal(doms_new[i], doms_cur[j]) && dattrs_equal(dattr_new, i, dattr_cur, j)) goto match2; } /* no match - add a new doms_new */ - __build_sched_domains(doms_new + i, + __build_sched_domains(doms_new[i], dattr_new ? dattr_new + i : NULL); match2: ; } /* Remember the new sched domains */ - if (doms_cur != fallback_doms) - kfree(doms_cur); + if (doms_cur != &fallback_doms) + free_sched_domains(doms_cur, ndoms_cur); kfree(dattr_cur); /* kfree(NULL) is safe */ doms_cur = doms_new; dattr_cur = dattr_new; @@ -8890,11 +7631,13 @@ static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) #ifdef CONFIG_SCHED_MC static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, + struct sysdev_class_attribute *attr, char *page) { return sprintf(page, "%u\n", sched_mc_power_savings); } static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 0); @@ -8906,11 +7649,13 @@ static SYSDEV_CLASS_ATTR(sched_mc_power_savings, 0644, #ifdef CONFIG_SCHED_SMT static ssize_t sched_smt_power_savings_show(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, char *page) { return sprintf(page, "%u\n", sched_smt_power_savings); } static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, + struct sysdev_class_attribute *attr, const char *buf, size_t count) { return sched_power_savings_store(buf, count, 1); @@ -8938,27 +7683,35 @@ int __init sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) } #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ -#ifndef CONFIG_CPUSETS /* - * Add online and remove offline CPUs from the scheduler domains. - * When cpusets are enabled they take over this function. + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). */ -static int update_sched_domains(struct notifier_block *nfb, - unsigned long action, void *hcpu) +static int cpuset_cpu_active(struct notifier_block *nfb, unsigned long action, + void *hcpu) { - switch (action) { + switch (action & ~CPU_TASKS_FROZEN) { case CPU_ONLINE: - case CPU_ONLINE_FROZEN: - case CPU_DEAD: - case CPU_DEAD_FROZEN: - partition_sched_domains(1, NULL, NULL); + case CPU_DOWN_FAILED: + cpuset_update_active_cpus(); return NOTIFY_OK; + default: + return NOTIFY_DONE; + } +} +static int cpuset_cpu_inactive(struct notifier_block *nfb, unsigned long action, + void *hcpu) +{ + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_DOWN_PREPARE: + cpuset_update_active_cpus(); + return NOTIFY_OK; default: return NOTIFY_DONE; } } -#endif static int update_runtime(struct notifier_block *nfb, unsigned long action, void *hcpu) @@ -8988,6 +7741,7 @@ void __init sched_init_smp(void) cpumask_var_t non_isolated_cpus; alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); #if defined(CONFIG_NUMA) sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), @@ -8996,17 +7750,15 @@ void __init sched_init_smp(void) #endif get_online_cpus(); mutex_lock(&sched_domains_mutex); - arch_init_sched_domains(cpu_online_mask); + arch_init_sched_domains(cpu_active_mask); cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); if (cpumask_empty(non_isolated_cpus)) cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); mutex_unlock(&sched_domains_mutex); put_online_cpus(); -#ifndef CONFIG_CPUSETS - /* XXX: Theoretical race here - CPU may be hotplugged now */ - hotcpu_notifier(update_sched_domains, 0); -#endif + hotcpu_notifier(cpuset_cpu_active, CPU_PRI_CPUSET_ACTIVE); + hotcpu_notifier(cpuset_cpu_inactive, CPU_PRI_CPUSET_INACTIVE); /* RT runtime code needs to handle some hotplug events */ hotcpu_notifier(update_runtime, 0); @@ -9019,7 +7771,6 @@ void __init sched_init_smp(void) sched_init_granularity(); free_cpumask_var(non_isolated_cpus); - alloc_cpumask_var(&fallback_doms, GFP_KERNEL); init_sched_rt_class(); } #else @@ -9070,13 +7821,13 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) #ifdef CONFIG_SMP rt_rq->rt_nr_migratory = 0; rt_rq->overloaded = 0; - plist_head_init(&rq->rt.pushable_tasks, &rq->lock); + plist_head_init_raw(&rt_rq->pushable_tasks, &rq->lock); #endif rt_rq->rt_time = 0; rt_rq->rt_throttled = 0; rt_rq->rt_runtime = 0; - spin_lock_init(&rt_rq->rt_runtime_lock); + raw_spin_lock_init(&rt_rq->rt_runtime_lock); #ifdef CONFIG_RT_GROUP_SCHED rt_rq->rt_nr_boosted = 0; @@ -9086,18 +7837,16 @@ static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) #ifdef CONFIG_FAIR_GROUP_SCHED static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, - struct sched_entity *se, int cpu, int add, + struct sched_entity *se, int cpu, struct sched_entity *parent) { struct rq *rq = cpu_rq(cpu); tg->cfs_rq[cpu] = cfs_rq; init_cfs_rq(cfs_rq, rq); cfs_rq->tg = tg; - if (add) - list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list); tg->se[cpu] = se; - /* se could be NULL for init_task_group */ + /* se could be NULL for root_task_group */ if (!se) return; @@ -9107,15 +7856,14 @@ static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, se->cfs_rq = parent->my_q; se->my_q = cfs_rq; - se->load.weight = tg->shares; - se->load.inv_weight = 0; + update_load_set(&se->load, 0); se->parent = parent; } #endif #ifdef CONFIG_RT_GROUP_SCHED static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, - struct sched_rt_entity *rt_se, int cpu, int add, + struct sched_rt_entity *rt_se, int cpu, struct sched_rt_entity *parent) { struct rq *rq = cpu_rq(cpu); @@ -9123,10 +7871,7 @@ static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, tg->rt_rq[cpu] = rt_rq; init_rt_rq(rt_rq, rq); rt_rq->tg = tg; - rt_rq->rt_se = rt_se; rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; - if (add) - list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list); tg->rt_se[cpu] = rt_se; if (!rt_se) @@ -9154,48 +7899,27 @@ void __init sched_init(void) #ifdef CONFIG_RT_GROUP_SCHED alloc_size += 2 * nr_cpu_ids * sizeof(void **); #endif -#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)kzalloc(alloc_size, GFP_NOWAIT); #ifdef CONFIG_FAIR_GROUP_SCHED - init_task_group.se = (struct sched_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - init_task_group.cfs_rq = (struct cfs_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - -#ifdef CONFIG_USER_SCHED root_task_group.se = (struct sched_entity **)ptr; ptr += nr_cpu_ids * sizeof(void **); root_task_group.cfs_rq = (struct cfs_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#endif /* CONFIG_USER_SCHED */ + #endif /* CONFIG_FAIR_GROUP_SCHED */ #ifdef CONFIG_RT_GROUP_SCHED - init_task_group.rt_se = (struct sched_rt_entity **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - - init_task_group.rt_rq = (struct rt_rq **)ptr; - ptr += nr_cpu_ids * sizeof(void **); - -#ifdef CONFIG_USER_SCHED root_task_group.rt_se = (struct sched_rt_entity **)ptr; ptr += nr_cpu_ids * sizeof(void **); root_task_group.rt_rq = (struct rt_rq **)ptr; ptr += nr_cpu_ids * sizeof(void **); -#endif /* CONFIG_USER_SCHED */ + #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CPUMASK_OFFSTACK for_each_possible_cpu(i) { @@ -9213,108 +7937,79 @@ void __init sched_init(void) global_rt_period(), global_rt_runtime()); #ifdef CONFIG_RT_GROUP_SCHED - init_rt_bandwidth(&init_task_group.rt_bandwidth, - global_rt_period(), global_rt_runtime()); -#ifdef CONFIG_USER_SCHED init_rt_bandwidth(&root_task_group.rt_bandwidth, - global_rt_period(), RUNTIME_INF); -#endif /* CONFIG_USER_SCHED */ + global_rt_period(), global_rt_runtime()); #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_GROUP_SCHED - list_add(&init_task_group.list, &task_groups); - INIT_LIST_HEAD(&init_task_group.children); - -#ifdef CONFIG_USER_SCHED +#ifdef CONFIG_CGROUP_SCHED + list_add(&root_task_group.list, &task_groups); INIT_LIST_HEAD(&root_task_group.children); - init_task_group.parent = &root_task_group; - list_add(&init_task_group.siblings, &root_task_group.children); -#endif /* CONFIG_USER_SCHED */ -#endif /* CONFIG_GROUP_SCHED */ + autogroup_init(&init_task); +#endif /* CONFIG_CGROUP_SCHED */ for_each_possible_cpu(i) { struct rq *rq; rq = cpu_rq(i); - spin_lock_init(&rq->lock); + raw_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 - init_task_group.shares = init_task_group_load; + root_task_group.shares = root_task_group_load; INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); -#ifdef CONFIG_CGROUP_SCHED /* - * How much cpu bandwidth does init_task_group get? + * How much cpu bandwidth does root_task_group get? * * In case of task-groups formed thr' the cgroup filesystem, it * gets 100% of the cpu resources in the system. This overall * system cpu resource is divided among the tasks of - * init_task_group and its child task-groups in a fair manner, + * root_task_group and its child task-groups in a fair manner, * based on each entity's (task or task-group's) weight * (se->load.weight). * - * In other words, if init_task_group has 10 tasks of weight + * In other words, if root_task_group has 10 tasks of weight * 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% * - * We achieve this by letting init_task_group's tasks sit - * directly in rq->cfs (i.e init_task_group->se[] = NULL). + * We achieve this by letting root_task_group's tasks sit + * directly in rq->cfs (i.e root_task_group->se[] = NULL). */ - init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL); -#elif defined CONFIG_USER_SCHED - root_task_group.shares = NICE_0_LOAD; - init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL); - /* - * In case of task-groups formed thr' the user id of tasks, - * init_task_group represents tasks belonging to root user. - * Hence it forms a sibling of all subsequent groups formed. - * In this case, init_task_group gets only a fraction of overall - * system cpu resource, based on the weight assigned to root - * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished - * by letting tasks of init_task_group sit in a separate cfs_rq - * (init_cfs_rq) and having one entity represent this group of - * tasks in rq->cfs (i.e init_task_group->se[] != NULL). - */ - init_tg_cfs_entry(&init_task_group, - &per_cpu(init_cfs_rq, i), - &per_cpu(init_sched_entity, i), i, 1, - root_task_group.se[i]); - -#endif + init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL); #endif /* CONFIG_FAIR_GROUP_SCHED */ rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; #ifdef CONFIG_RT_GROUP_SCHED INIT_LIST_HEAD(&rq->leaf_rt_rq_list); -#ifdef CONFIG_CGROUP_SCHED - init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL); -#elif defined CONFIG_USER_SCHED - init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL); - init_tg_rt_entry(&init_task_group, - &per_cpu(init_rt_rq, i), - &per_cpu(init_sched_rt_entity, i), i, 1, - root_task_group.rt_se[i]); -#endif + init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL); #endif for (j = 0; j < CPU_LOAD_IDX_MAX; j++) rq->cpu_load[j] = 0; + + rq->last_load_update_tick = jiffies; + #ifdef CONFIG_SMP rq->sd = NULL; rq->rd = NULL; + rq->cpu_power = SCHED_LOAD_SCALE; + rq->post_schedule = 0; rq->active_balance = 0; rq->next_balance = jiffies; rq->push_cpu = 0; rq->cpu = i; rq->online = 0; - rq->migration_thread = NULL; - INIT_LIST_HEAD(&rq->migration_queue); + rq->idle_stamp = 0; + rq->avg_idle = 2*sysctl_sched_migration_cost; rq_attach_root(rq, &def_root_domain); +#ifdef CONFIG_NO_HZ + rq->nohz_balance_kick = 0; + init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i)); +#endif #endif init_rq_hrtick(rq); atomic_set(&rq->nr_iowait, 0); @@ -9331,7 +8026,7 @@ void __init sched_init(void) #endif #ifdef CONFIG_RT_MUTEXES - plist_head_init(&init_task.pi_waiters, &init_task.pi_lock); + plist_head_init_raw(&init_task.pi_waiters, &init_task.pi_lock); #endif /* @@ -9356,28 +8051,38 @@ void __init sched_init(void) current->sched_class = &fair_sched_class; /* Allocate the nohz_cpu_mask if CONFIG_CPUMASK_OFFSTACK */ - alloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); + zalloc_cpumask_var(&nohz_cpu_mask, GFP_NOWAIT); #ifdef CONFIG_SMP #ifdef CONFIG_NO_HZ - alloc_cpumask_var(&nohz.cpu_mask, GFP_NOWAIT); - alloc_cpumask_var(&nohz.ilb_grp_nohz_mask, GFP_NOWAIT); -#endif - alloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT); + alloc_cpumask_var(&nohz.grp_idle_mask, GFP_NOWAIT); + atomic_set(&nohz.load_balancer, nr_cpu_ids); + atomic_set(&nohz.first_pick_cpu, nr_cpu_ids); + atomic_set(&nohz.second_pick_cpu, nr_cpu_ids); +#endif + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); #endif /* SMP */ - perf_counter_init(); - scheduler_running = 1; } #ifdef CONFIG_DEBUG_SPINLOCK_SLEEP -void __might_sleep(char *file, int line) +static inline int preempt_count_equals(int preempt_offset) +{ + int nested = (preempt_count() & ~PREEMPT_ACTIVE) + rcu_preempt_depth(); + + return (nested == PREEMPT_INATOMIC_BASE + preempt_offset); +} + +void __might_sleep(const char *file, int line, int preempt_offset) { #ifdef in_atomic static unsigned long prev_jiffy; /* ratelimiting */ - if ((!in_atomic() && !irqs_disabled()) || - system_state != SYSTEM_RUNNING || oops_in_progress) + if ((preempt_count_equals(preempt_offset) && !irqs_disabled()) || + system_state != SYSTEM_RUNNING || oops_in_progress) return; if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) return; @@ -9405,7 +8110,6 @@ static void normalize_task(struct rq *rq, struct task_struct *p) { int on_rq; - update_rq_clock(rq); on_rq = p->se.on_rq; if (on_rq) deactivate_task(rq, p, 0); @@ -9432,9 +8136,9 @@ void normalize_rt_tasks(void) p->se.exec_start = 0; #ifdef CONFIG_SCHEDSTATS - p->se.wait_start = 0; - p->se.sleep_start = 0; - p->se.block_start = 0; + p->se.statistics.wait_start = 0; + p->se.statistics.sleep_start = 0; + p->se.statistics.block_start = 0; #endif if (!rt_task(p)) { @@ -9447,13 +8151,13 @@ void normalize_rt_tasks(void) continue; } - spin_lock(&p->pi_lock); + raw_spin_lock(&p->pi_lock); rq = __task_rq_lock(p); normalize_task(rq, p); __task_rq_unlock(rq); - spin_unlock(&p->pi_lock); + raw_spin_unlock(&p->pi_lock); } while_each_thread(g, p); read_unlock_irqrestore(&tasklist_lock, flags); @@ -9461,9 +8165,9 @@ void normalize_rt_tasks(void) #endif /* CONFIG_MAGIC_SYSRQ */ -#ifdef CONFIG_IA64 +#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) /* - * These functions are only useful for the IA64 MCA handling. + * These functions are only useful for the IA64 MCA handling, or kdb. * * They can only be called when the whole system has been * stopped - every CPU needs to be quiescent, and no scheduling @@ -9483,6 +8187,9 @@ struct task_struct *curr_task(int cpu) return cpu_curr(cpu); } +#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ + +#ifdef CONFIG_IA64 /** * set_curr_task - set the current task for a given cpu. * @cpu: the processor in question. @@ -9549,26 +8256,34 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) se = kzalloc_node(sizeof(struct sched_entity), GFP_KERNEL, cpu_to_node(i)); if (!se) - goto err; + goto err_free_rq; - init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent->se[i]); + init_tg_cfs_entry(tg, cfs_rq, se, i, parent->se[i]); } return 1; - err: +err_free_rq: + kfree(cfs_rq); +err: return 0; } -static inline void register_fair_sched_group(struct task_group *tg, int cpu) -{ - list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list, - &cpu_rq(cpu)->leaf_cfs_rq_list); -} - static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) { - list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list); + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + /* + * Only empty task groups can be destroyed; so we can speculatively + * check on_list without danger of it being re-added. + */ + if (!tg->cfs_rq[cpu]->on_list) + return; + + raw_spin_lock_irqsave(&rq->lock, flags); + list_del_leaf_cfs_rq(tg->cfs_rq[cpu]); + raw_spin_unlock_irqrestore(&rq->lock, flags); } #else /* !CONFG_FAIR_GROUP_SCHED */ static inline void free_fair_sched_group(struct task_group *tg) @@ -9581,10 +8296,6 @@ int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) return 1; } -static inline void register_fair_sched_group(struct task_group *tg, int cpu) -{ -} - static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) { } @@ -9637,27 +8348,18 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) rt_se = kzalloc_node(sizeof(struct sched_rt_entity), GFP_KERNEL, cpu_to_node(i)); if (!rt_se) - goto err; + goto err_free_rq; - init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent->rt_se[i]); + init_tg_rt_entry(tg, rt_rq, rt_se, i, parent->rt_se[i]); } return 1; - err: +err_free_rq: + kfree(rt_rq); +err: return 0; } - -static inline void register_rt_sched_group(struct task_group *tg, int cpu) -{ - list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list, - &cpu_rq(cpu)->leaf_rt_rq_list); -} - -static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) -{ - list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list); -} #else /* !CONFIG_RT_GROUP_SCHED */ static inline void free_rt_sched_group(struct task_group *tg) { @@ -9668,21 +8370,14 @@ int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) { return 1; } - -static inline void register_rt_sched_group(struct task_group *tg, int cpu) -{ -} - -static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) -{ -} #endif /* CONFIG_RT_GROUP_SCHED */ -#ifdef CONFIG_GROUP_SCHED +#ifdef CONFIG_CGROUP_SCHED static void free_sched_group(struct task_group *tg) { free_fair_sched_group(tg); free_rt_sched_group(tg); + autogroup_free(tg); kfree(tg); } @@ -9691,7 +8386,6 @@ struct task_group *sched_create_group(struct task_group *parent) { struct task_group *tg; unsigned long flags; - int i; tg = kzalloc(sizeof(*tg), GFP_KERNEL); if (!tg) @@ -9704,10 +8398,6 @@ struct task_group *sched_create_group(struct task_group *parent) goto err; spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) { - register_fair_sched_group(tg, i); - register_rt_sched_group(tg, i); - } list_add_rcu(&tg->list, &task_groups); WARN_ON(!parent); /* root should already exist */ @@ -9737,11 +8427,11 @@ void sched_destroy_group(struct task_group *tg) unsigned long flags; int i; - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) { + /* end participation in shares distribution */ + for_each_possible_cpu(i) unregister_fair_sched_group(tg, i); - unregister_rt_sched_group(tg, i); - } + + spin_lock_irqsave(&task_group_lock, flags); list_del_rcu(&tg->list); list_del_rcu(&tg->siblings); spin_unlock_irqrestore(&task_group_lock, flags); @@ -9763,8 +8453,6 @@ void sched_move_task(struct task_struct *tsk) rq = task_rq_lock(tsk, &flags); - update_rq_clock(rq); - running = task_current(rq, tsk); on_rq = tsk->se.on_rq; @@ -9773,12 +8461,12 @@ void sched_move_task(struct task_struct *tsk) if (unlikely(running)) tsk->sched_class->put_prev_task(rq, tsk); - set_task_rq(tsk, task_cpu(tsk)); - #ifdef CONFIG_FAIR_GROUP_SCHED - if (tsk->sched_class->moved_group) - tsk->sched_class->moved_group(tsk); + if (tsk->sched_class->task_move_group) + tsk->sched_class->task_move_group(tsk, on_rq); + else #endif + set_task_rq(tsk, task_cpu(tsk)); if (unlikely(running)) tsk->sched_class->set_curr_task(rq); @@ -9787,36 +8475,9 @@ void sched_move_task(struct task_struct *tsk) task_rq_unlock(rq, &flags); } -#endif /* CONFIG_GROUP_SCHED */ +#endif /* CONFIG_CGROUP_SCHED */ #ifdef CONFIG_FAIR_GROUP_SCHED -static void __set_se_shares(struct sched_entity *se, unsigned long shares) -{ - struct cfs_rq *cfs_rq = se->cfs_rq; - int on_rq; - - on_rq = se->on_rq; - if (on_rq) - dequeue_entity(cfs_rq, se, 0); - - se->load.weight = shares; - se->load.inv_weight = 0; - - if (on_rq) - enqueue_entity(cfs_rq, se, 0); -} - -static void set_se_shares(struct sched_entity *se, unsigned long shares) -{ - struct cfs_rq *cfs_rq = se->cfs_rq; - struct rq *rq = cfs_rq->rq; - unsigned long flags; - - spin_lock_irqsave(&rq->lock, flags); - __set_se_shares(se, shares); - spin_unlock_irqrestore(&rq->lock, flags); -} - static DEFINE_MUTEX(shares_mutex); int sched_group_set_shares(struct task_group *tg, unsigned long shares) @@ -9839,37 +8500,19 @@ int sched_group_set_shares(struct task_group *tg, unsigned long shares) if (tg->shares == shares) goto done; - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) - unregister_fair_sched_group(tg, i); - list_del_rcu(&tg->siblings); - spin_unlock_irqrestore(&task_group_lock, flags); - - /* wait for any ongoing reference to this group to finish */ - synchronize_sched(); - - /* - * Now we are free to modify the group's share on each cpu - * w/o tripping rebalance_share or load_balance_fair. - */ tg->shares = shares; for_each_possible_cpu(i) { - /* - * force a rebalance - */ - cfs_rq_set_shares(tg->cfs_rq[i], 0); - set_se_shares(tg->se[i], shares); + struct rq *rq = cpu_rq(i); + struct sched_entity *se; + + se = tg->se[i]; + /* Propagate contribution to hierarchy */ + raw_spin_lock_irqsave(&rq->lock, flags); + for_each_sched_entity(se) + update_cfs_shares(group_cfs_rq(se), 0); + raw_spin_unlock_irqrestore(&rq->lock, flags); } - /* - * Enable load balance activity on this group, by inserting it back on - * each cpu's rq->leaf_cfs_rq_list. - */ - spin_lock_irqsave(&task_group_lock, flags); - for_each_possible_cpu(i) - register_fair_sched_group(tg, i); - list_add_rcu(&tg->siblings, &tg->parent->children); - spin_unlock_irqrestore(&task_group_lock, flags); done: mutex_unlock(&shares_mutex); return 0; @@ -9929,13 +8572,6 @@ static int tg_schedulable(struct task_group *tg, void *data) runtime = d->rt_runtime; } -#ifdef CONFIG_USER_SCHED - if (tg == &root_task_group) { - period = global_rt_period(); - runtime = global_rt_runtime(); - } -#endif - /* * Cannot have more runtime than the period. */ @@ -9999,19 +8635,19 @@ static int tg_set_bandwidth(struct task_group *tg, if (err) goto unlock; - spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); + raw_spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); tg->rt_bandwidth.rt_runtime = rt_runtime; for_each_possible_cpu(i) { struct rt_rq *rt_rq = tg->rt_rq[i]; - spin_lock(&rt_rq->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_runtime = rt_runtime; - spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_rq->rt_runtime_lock); } - spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); - unlock: + raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); +unlock: read_unlock(&tasklist_lock); mutex_unlock(&rt_constraints_mutex); @@ -10115,22 +8751,22 @@ static int sched_rt_global_constraints(void) if (sysctl_sched_rt_runtime == 0) return -EBUSY; - spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); + raw_spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); for_each_possible_cpu(i) { struct rt_rq *rt_rq = &cpu_rq(i)->rt; - spin_lock(&rt_rq->rt_runtime_lock); + raw_spin_lock(&rt_rq->rt_runtime_lock); rt_rq->rt_runtime = global_rt_runtime(); - spin_unlock(&rt_rq->rt_runtime_lock); + raw_spin_unlock(&rt_rq->rt_runtime_lock); } - spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); + raw_spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); return 0; } #endif /* CONFIG_RT_GROUP_SCHED */ int sched_rt_handler(struct ctl_table *table, int write, - struct file *filp, void __user *buffer, size_t *lenp, + void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -10141,7 +8777,7 @@ int sched_rt_handler(struct ctl_table *table, int write, old_period = sysctl_sched_rt_period; old_runtime = sysctl_sched_rt_runtime; - ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + ret = proc_dointvec(table, write, buffer, lenp, ppos); if (!ret && write) { ret = sched_rt_global_constraints(); @@ -10175,7 +8811,7 @@ cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) if (!cgrp->parent) { /* This is early initialization for the top cgroup */ - return &init_task_group.css; + return &root_task_group.css; } parent = cgroup_tg(cgrp->parent); @@ -10195,8 +8831,7 @@ cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) } static int -cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct task_struct *tsk) +cpu_cgroup_can_attach_task(struct cgroup *cgrp, struct task_struct *tsk) { #ifdef CONFIG_RT_GROUP_SCHED if (!sched_rt_can_attach(cgroup_tg(cgrp), tsk)) @@ -10206,15 +8841,45 @@ cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, if (tsk->sched_class != &fair_sched_class) return -EINVAL; #endif + return 0; +} +static int +cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk, bool threadgroup) +{ + int retval = cpu_cgroup_can_attach_task(cgrp, tsk); + if (retval) + return retval; + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + retval = cpu_cgroup_can_attach_task(cgrp, c); + if (retval) { + rcu_read_unlock(); + return retval; + } + } + rcu_read_unlock(); + } return 0; } static void cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, - struct cgroup *old_cont, struct task_struct *tsk) + struct cgroup *old_cont, struct task_struct *tsk, + bool threadgroup) { sched_move_task(tsk); + if (threadgroup) { + struct task_struct *c; + rcu_read_lock(); + list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) { + sched_move_task(c); + } + rcu_read_unlock(); + } } #ifdef CONFIG_FAIR_GROUP_SCHED @@ -10309,7 +8974,7 @@ struct cgroup_subsys cpu_cgroup_subsys = { struct cpuacct { struct cgroup_subsys_state css; /* cpuusage holds pointer to a u64-type object on every cpu */ - u64 *cpuusage; + u64 __percpu *cpuusage; struct percpu_counter cpustat[CPUACCT_STAT_NSTATS]; struct cpuacct *parent; }; @@ -10385,9 +9050,9 @@ static u64 cpuacct_cpuusage_read(struct cpuacct *ca, int cpu) /* * Take rq->lock to make 64-bit read safe on 32-bit platforms. */ - spin_lock_irq(&cpu_rq(cpu)->lock); + raw_spin_lock_irq(&cpu_rq(cpu)->lock); data = *cpuusage; - spin_unlock_irq(&cpu_rq(cpu)->lock); + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); #else data = *cpuusage; #endif @@ -10403,9 +9068,9 @@ static void cpuacct_cpuusage_write(struct cpuacct *ca, int cpu, u64 val) /* * Take rq->lock to make 64-bit write safe on 32-bit platforms. */ - spin_lock_irq(&cpu_rq(cpu)->lock); + raw_spin_lock_irq(&cpu_rq(cpu)->lock); *cpuusage = val; - spin_unlock_irq(&cpu_rq(cpu)->lock); + raw_spin_unlock_irq(&cpu_rq(cpu)->lock); #else *cpuusage = val; #endif @@ -10526,12 +9191,30 @@ static void cpuacct_charge(struct task_struct *tsk, u64 cputime) } /* + * When CONFIG_VIRT_CPU_ACCOUNTING is enabled one jiffy can be very large + * in cputime_t units. As a result, cpuacct_update_stats calls + * percpu_counter_add with values large enough to always overflow the + * per cpu batch limit causing bad SMP scalability. + * + * To fix this we scale percpu_counter_batch by cputime_one_jiffy so we + * batch the same amount of time with CONFIG_VIRT_CPU_ACCOUNTING disabled + * and enabled. We cap it at INT_MAX which is the largest allowed batch value. + */ +#ifdef CONFIG_SMP +#define CPUACCT_BATCH \ + min_t(long, percpu_counter_batch * cputime_one_jiffy, INT_MAX) +#else +#define CPUACCT_BATCH 0 +#endif + +/* * 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; + int batch = CPUACCT_BATCH; if (unlikely(!cpuacct_subsys.active)) return; @@ -10540,7 +9223,7 @@ static void cpuacct_update_stats(struct task_struct *tsk, ca = task_ca(tsk); do { - percpu_counter_add(&ca->cpustat[idx], val); + __percpu_counter_add(&ca->cpustat[idx], val, batch); ca = ca->parent; } while (ca); rcu_read_unlock(); @@ -10554,3 +9237,4 @@ struct cgroup_subsys cpuacct_subsys = { .subsys_id = cpuacct_subsys_id, }; #endif /* CONFIG_CGROUP_CPUACCT */ + |