#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>
#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>
#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>
*/
#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))
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;
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);
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;
__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
*/
static DEFINE_MUTEX(sched_domains_mutex);
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
#include <linux/cgroup.h>
/* 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 */
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_SHARED_ALIGNED(struct cfs_rq, init_cfs_rq);
-#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_SHARED_ALIGNED(struct rt_rq, init_rt_rq);
-#endif /* CONFIG_RT_GROUP_SCHED */
-#else /* !CONFIG_USER_SCHED */
#define root_task_group init_task_group
-#endif /* CONFIG_USER_SCHED */
/* task_group_lock serializes add/remove of task groups and also changes to
* a task group's cpu shares.
*/
static DEFINE_SPINLOCK(task_group_lock);
+#ifdef CONFIG_FAIR_GROUP_SCHED
+
#ifdef CONFIG_SMP
static int root_task_group_empty(void)
{
}
#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 */
/*
* A weight of 0 or 1 can cause arithmetics problems.
{
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)
+#ifdef CONFIG_CGROUP_SCHED
tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id),
struct task_group, css);
#else
#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;
}
-#endif /* CONFIG_GROUP_SCHED */
+#endif /* CONFIG_CGROUP_SCHED */
/* CFS-related fields in a runqueue */
struct cfs_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;
struct rq *rq;
struct list_head leaf_rt_rq_list;
struct task_group *tg;
- struct sched_rt_entity *rt_se;
#endif
};
#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
};
/*
*/
struct rq {
/* runqueue lock: */
- spinlock_t lock;
+ raw_spinlock_t lock;
/*
* nr_running and cpu_load should be in the same cacheline because
#define CPU_LOAD_IDX_MAX 5
unsigned long cpu_load[CPU_LOAD_IDX_MAX];
#ifdef CONFIG_NO_HZ
- unsigned long last_tick_seen;
unsigned char in_nohz_recently;
#endif
/* 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;
unsigned char idle_at_tick;
/* For active balancing */
+ int post_schedule;
int active_balance;
int push_cpu;
/* cpu of this runqueue: */
struct task_struct *migration_thread;
struct list_head migration_queue;
+
+ u64 rt_avg;
+ u64 age_stamp;
+ u64 idle_stamp;
+ u64 avg_idle;
#endif
/* calc_load related fields */
static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-static inline void check_preempt_curr(struct rq *rq, struct task_struct *p, int sync)
+static inline
+void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
{
- rq->curr->sched_class->check_preempt_curr(rq, p, sync);
+ rq->curr->sched_class->check_preempt_curr(rq, p, flags);
}
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.
* 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))
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);
}
/*
if (!sched_feat_names[i])
return -EINVAL;
- filp->f_pos += cnt;
+ *ppos += cnt;
return cnt;
}
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,
* default: 0.25ms
*/
unsigned int sysctl_sched_shares_ratelimit = 250000;
+unsigned int normalized_sysctl_sched_shares_ratelimit = 250000;
/*
* Inject some fuzzyness into changing the per-cpu group shares
unsigned int sysctl_sched_shares_thresh = 4;
/*
+ * period over which we average the RT time consumption, measured
+ * in ms.
+ *
+ * default: 1s
+ */
+const_debug unsigned int sysctl_sched_time_avg = MSEC_PER_SEC;
+
+/*
* period over which we measure -rt task cpu usage in us.
* default: 1s
*/
*/
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 */
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
}
#endif /* __ARCH_WANT_UNLOCKED_CTXSW */
/*
+ * Check whether the task is waking, we use this to synchronize against
+ * ttwu() so that task_cpu() reports a stable number.
+ *
+ * We need to make an exception for PF_STARTING tasks because the fork
+ * path might require task_rq_lock() to work, eg. it can call
+ * set_cpus_allowed_ptr() from the cpuset clone_ns code.
+ */
+static inline int task_is_waking(struct task_struct *p)
+{
+ return unlikely((p->state == TASK_WAKING) && !(p->flags & PF_STARTING));
+}
+
+/*
* __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);
- if (likely(rq == task_rq(p)))
+ while (task_is_waking(p))
+ cpu_relax();
+ rq = task_rq(p);
+ raw_spin_lock(&rq->lock);
+ if (likely(rq == task_rq(p) && !task_is_waking(p)))
return rq;
- spin_unlock(&rq->lock);
+ raw_spin_unlock(&rq->lock);
}
}
struct rq *rq;
for (;;) {
+ while (task_is_waking(p))
+ cpu_relax();
local_irq_save(*flags);
rq = task_rq(p);
- spin_lock(&rq->lock);
- if (likely(rq == task_rq(p)))
+ raw_spin_lock(&rq->lock);
+ if (likely(rq == task_rq(p) && !task_is_waking(p)))
return rq;
- spin_unlock_irqrestore(&rq->lock, *flags);
+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
}
}
struct rq *rq = task_rq(p);
smp_mb(); /* spin-unlock-wait is not a full memory barrier */
- spin_unlock_wait(&rq->lock);
+ raw_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);
}
/*
local_irq_disable();
rq = this_rq();
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
return rq;
}
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;
}
{
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);
}
/*
{
int cpu;
- assert_spin_locked(&task_rq(p)->lock);
+ assert_raw_spin_locked(&task_rq(p)->lock);
if (test_tsk_need_resched(p))
return;
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
}
#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) {
+ 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)
+{
+}
#endif /* CONFIG_SMP */
#if BITS_PER_LONG == 32
/* 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 */
#endif
#ifdef CONFIG_SMP
-static unsigned long source_load(int cpu, int type);
-static unsigned long target_load(int cpu, int type);
+/* Used instead of source_load when we know the type == 0 */
+static unsigned long weighted_cpuload(const int cpu)
+{
+ return cpu_rq(cpu)->load.weight;
+}
+
+/*
+ * 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 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.
+ */
+static unsigned long target_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 max(rq->cpu_load[type-1], total);
+}
+
+static struct sched_group *group_of(int cpu)
+{
+ struct sched_domain *sd = rcu_dereference_sched(cpu_rq(cpu)->sd);
+
+ if (!sd)
+ return NULL;
+
+ return sd->groups;
+}
+
+static unsigned long power_of(int cpu)
+{
+ struct sched_group *group = group_of(cpu);
+
+ if (!group)
+ return SCHED_LOAD_SCALE;
+
+ return group->cpu_power;
+}
+
static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd);
static unsigned long cpu_avg_load_per_task(int cpu)
#ifdef CONFIG_FAIR_GROUP_SCHED
+static __read_mostly unsigned long __percpu *update_shares_data;
+
static void __set_se_shares(struct sched_entity *se, unsigned long shares);
/*
* Calculate and set the cpu's group shares.
*/
-static void
-update_group_shares_cpu(struct task_group *tg, int cpu,
- unsigned long sd_shares, unsigned long sd_rq_weight)
+static void update_group_shares_cpu(struct task_group *tg, int cpu,
+ unsigned long sd_shares,
+ unsigned long sd_rq_weight,
+ unsigned long *usd_rq_weight)
{
- unsigned long shares;
- unsigned long rq_weight;
+ unsigned long shares, rq_weight;
+ int boost = 0;
- if (!tg->se[cpu])
- return;
-
- rq_weight = tg->cfs_rq[cpu]->rq_weight;
+ rq_weight = usd_rq_weight[cpu];
+ if (!rq_weight) {
+ boost = 1;
+ rq_weight = NICE_0_LOAD;
+ }
/*
- * \Sum shares * rq_weight
- * shares = -----------------------
- * \Sum rq_weight
- *
+ * \Sum_j shares_j * rq_weight_i
+ * shares_i = -----------------------------
+ * \Sum_j rq_weight_j
*/
shares = (sd_shares * rq_weight) / sd_rq_weight;
shares = clamp_t(unsigned long, shares, MIN_SHARES, MAX_SHARES);
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
- tg->cfs_rq[cpu]->shares = shares;
-
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ tg->cfs_rq[cpu]->rq_weight = boost ? 0 : rq_weight;
+ tg->cfs_rq[cpu]->shares = boost ? 0 : shares;
__set_se_shares(tg->se[cpu], shares);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
}
*/
static int tg_shares_up(struct task_group *tg, void *data)
{
- unsigned long weight, rq_weight = 0;
- unsigned long shares = 0;
+ unsigned long weight, rq_weight = 0, sum_weight = 0, shares = 0;
+ unsigned long *usd_rq_weight;
struct sched_domain *sd = data;
+ unsigned long flags;
int i;
+ if (!tg->se[0])
+ return 0;
+
+ local_irq_save(flags);
+ usd_rq_weight = per_cpu_ptr(update_shares_data, smp_processor_id());
+
for_each_cpu(i, sched_domain_span(sd)) {
+ weight = tg->cfs_rq[i]->load.weight;
+ usd_rq_weight[i] = weight;
+
+ rq_weight += weight;
/*
* If there are currently no tasks on the cpu pretend there
* is one of average load so that when a new task gets to
* run here it will not get delayed by group starvation.
*/
- weight = tg->cfs_rq[i]->load.weight;
if (!weight)
weight = NICE_0_LOAD;
- tg->cfs_rq[i]->rq_weight = weight;
- rq_weight += weight;
+ sum_weight += weight;
shares += tg->cfs_rq[i]->shares;
}
+ if (!rq_weight)
+ rq_weight = sum_weight;
+
if ((!shares && rq_weight) || shares > tg->shares)
shares = tg->shares;
shares = tg->shares;
for_each_cpu(i, sched_domain_span(sd))
- update_group_shares_cpu(tg, i, shares, rq_weight);
+ update_group_shares_cpu(tg, i, shares, rq_weight, usd_rq_weight);
+
+ local_irq_restore(flags);
return 0;
}
static void update_shares(struct sched_domain *sd)
{
- u64 now = cpu_clock(raw_smp_processor_id());
- s64 elapsed = now - sd->last_update;
+ s64 elapsed;
+ u64 now;
+
+ if (root_task_group_empty())
+ return;
+
+ now = cpu_clock(raw_smp_processor_id());
+ elapsed = now - sd->last_update;
if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) {
sd->last_update = now;
}
}
-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)
{
+ if (root_task_group_empty())
+ return;
+
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
}
{
}
-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
__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;
{
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;
}
{
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);
}
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_);
}
+
+/*
+ * 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)
+{
+ 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);
+ }
+ }
+ update_rq_clock(rq1);
+ update_rq_clock(rq2);
+}
+
+/*
+ * 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
#ifdef CONFIG_FAIR_GROUP_SCHED
#endif
static void calc_load_account_active(struct rq *this_rq);
+static void update_sysctl(void);
+static int get_update_sysctl_factor(void);
-#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
+}
+
+static const struct sched_class rt_sched_class;
#define sched_class_highest (&rt_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++;
*avg += diff >> 3;
}
-static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup)
+static void
+enqueue_task(struct rq *rq, struct task_struct *p, int wakeup, bool head)
{
if (wakeup)
p->se.start_runtime = p->se.sum_exec_runtime;
sched_info_queued(p);
- p->sched_class->enqueue_task(rq, p, wakeup);
+ p->sched_class->enqueue_task(rq, p, wakeup, head);
p->se.on_rq = 1;
}
}
/*
- * __normal_prio - return the priority that is based on the static prio
+ * activate_task - move a task to the runqueue.
*/
-static inline int __normal_prio(struct task_struct *p)
+static void activate_task(struct rq *rq, struct task_struct *p, int wakeup)
{
- return p->static_prio;
-}
+ if (task_contributes_to_load(p))
+ rq->nr_uninterruptible--;
+
+ enqueue_task(rq, p, wakeup, false);
+ 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);
+}
+
+#include "sched_idletask.c"
+#include "sched_fair.c"
+#include "sched_rt.c"
+#ifdef CONFIG_SCHED_DEBUG
+# include "sched_debug.c"
+#endif
+
+/*
+ * __normal_prio - return the priority that is based on the static prio
+ */
+static inline int __normal_prio(struct task_struct *p)
+{
+ return p->static_prio;
+}
/*
* Calculate the expected normal priority: i.e. priority
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.
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)
}
#ifdef CONFIG_SMP
-
-/* Used instead of source_load when we know the type == 0 */
-static unsigned long weighted_cpuload(const int cpu)
-{
- return cpu_rq(cpu)->load.weight;
-}
-
/*
* Is this task likely cache-hot:
*/
{
s64 delta;
+ if (p->sched_class != &fair_sched_class)
+ 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)
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);
}
/*
* 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);
+ if (!p->se.on_rq && !task_running(rq, p))
return 0;
- }
init_completion(&req->done);
req->task = 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();
}
-/*
- * find_idlest_group finds and returns the least busy CPU group within the
- * domain.
- */
-static struct sched_group *
-find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu)
+#ifdef CONFIG_SMP
+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);
-
- avg_load += load;
- }
-
- /* Adjust by relative CPU power of the group */
- avg_load = sg_div_cpu_power(group,
- avg_load * SCHED_LOAD_SCALE);
-
- 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);
+ int dest_cpu;
+ const struct cpumask *nodemask = cpumask_of_node(cpu_to_node(cpu));
- if (!idlest || 100*this_load < imbalance*min_load)
- return NULL;
- return idlest;
-}
+ /* 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;
-/*
- * find_idlest_cpu - find the idlest cpu among the cpus in group.
- */
-static int
-find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu)
-{
- unsigned long load, min_load = ULONG_MAX;
- int idlest = -1;
- int i;
+ /* Any allowed, online CPU? */
+ dest_cpu = cpumask_any_and(&p->cpus_allowed, cpu_active_mask);
+ if (dest_cpu < nr_cpu_ids)
+ return dest_cpu;
- /* Traverse only the allowed CPUs */
- for_each_cpu_and(i, sched_group_cpus(group), &p->cpus_allowed) {
- load = weighted_cpuload(i);
+ /* No more Mr. Nice Guy. */
+ if (dest_cpu >= nr_cpu_ids) {
+ rcu_read_lock();
+ cpuset_cpus_allowed_locked(p, &p->cpus_allowed);
+ rcu_read_unlock();
+ dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
- if (load < min_load || (load == min_load && i == this_cpu)) {
- min_load = load;
- idlest = i;
+ /*
+ * 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);
}
}
- return idlest;
+ return dest_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.
+ * Gets called from 3 sites (exec, fork, wakeup), since it is called without
+ * holding rq->lock we need to ensure ->cpus_allowed is stable, this is done
+ * by:
*
- * Returns the target CPU number, or the same CPU if no balancing is needed.
- *
- * preempt must be disabled.
+ * exec: is unstable, retry loop
+ * fork & wake-up: serialize ->cpus_allowed against TASK_WAKING
*/
-static int sched_balance_self(int cpu, int flag)
+static inline
+int select_task_rq(struct task_struct *p, int sd_flags, int wake_flags)
{
- 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;
- }
-
- if (sd)
- update_shares(sd);
-
- while (sd) {
- struct sched_group *group;
- int new_cpu, weight;
-
- if (!(sd->flags & flag)) {
- sd = sd->child;
- continue;
- }
-
- group = find_idlest_group(sd, t, cpu);
- if (!group) {
- sd = sd->child;
- continue;
- }
-
- 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;
- }
+ int cpu = p->sched_class->select_task_rq(p, sd_flags, wake_flags);
- /* 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 */
- }
+ /*
+ * 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 cpu;
}
-
-#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();
-}
+#endif
/***
* try_to_wake_up - wake up a thread
*
* returns failure only if the task is already active.
*/
-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;
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;
+ wake_flags &= ~WF_SYNC;
- 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)
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);
+ /*
+ * 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))
+ rq->nr_uninterruptible--;
+ p->state = TASK_WAKING;
+
+ if (p->sched_class->task_waking)
+ p->sched_class->task_waking(rq, p);
+
+ __task_rq_unlock(rq);
+
+ cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
if (cpu != orig_cpu) {
+ /*
+ * Since we migrate the task without holding any rq->lock,
+ * we need to be careful with task_rq_lock(), since that
+ * might end up locking an invalid rq.
+ */
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;
-
- this_cpu = smp_processor_id();
- cpu = task_cpu(p);
}
+ rq = cpu_rq(cpu);
+ raw_spin_lock(&rq->lock);
+ update_rq_clock(rq);
+
+ /*
+ * 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)
out_activate:
#endif /* CONFIG_SMP */
schedstat_inc(p, se.nr_wakeups);
- if (sync)
+ if (wake_flags & WF_SYNC)
schedstat_inc(p, se.nr_wakeups_sync);
if (orig_cpu != cpu)
schedstat_inc(p, se.nr_wakeups_migrate);
out_running:
trace_sched_wakeup(rq, p, success);
- check_preempt_curr(rq, p, sync);
+ check_preempt_curr(rq, p, wake_flags);
p->state = TASK_RUNNING;
#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);
+
+ if (unlikely(rq->idle_stamp)) {
+ u64 delta = rq->clock - rq->idle_stamp;
+ u64 max = 2*sysctl_sched_migration_cost;
+
+ if (delta > max)
+ rq->avg_idle = max;
+ else
+ update_avg(&rq->avg_idle, delta);
+ rq->idle_stamp = 0;
+ }
#endif
out:
task_rq_unlock(rq, &flags);
+ put_cpu();
return success;
}
p->se.nr_failed_migrations_running = 0;
p->se.nr_failed_migrations_hot = 0;
p->se.nr_forced_migrations = 0;
- p->se.nr_forced2_migrations = 0;
p->se.nr_wakeups = 0;
p->se.nr_wakeups_sync = 0;
#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;
}
/*
int cpu = get_cpu();
__sched_fork(p);
+ /*
+ * We mark the process as waking 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_WAKING;
-#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);
+
+ set_task_cpu(p, cpu);
+
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
if (likely(sched_info_on()))
memset(&p->sched_info, 0, sizeof(p->sched_info));
{
unsigned long flags;
struct rq *rq;
+ int cpu __maybe_unused = get_cpu();
- rq = task_rq_lock(p, &flags);
- BUG_ON(p->state != TASK_RUNNING);
- update_rq_clock(rq);
+#ifdef CONFIG_SMP
+ /*
+ * 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 still have TASK_WAKING but PF_STARTING is gone now, meaning
+ * ->cpus_allowed is stable, we have preemption disabled, meaning
+ * cpu_online_mask is stable.
+ */
+ cpu = select_task_rq(p, SD_BALANCE_FORK, 0);
+ set_task_cpu(p, cpu);
+#endif
- p->prio = effective_prio(p);
+ /*
+ * Since the task is not on the rq and we still have TASK_WAKING set
+ * nobody else will migrate this task.
+ */
+ rq = cpu_rq(cpu);
+ raw_spin_lock_irqsave(&rq->lock, flags);
- 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);
- }
+ BUG_ON(p->state != TASK_WAKING);
+ p->state = TASK_RUNNING;
+ update_rq_clock(rq);
+ activate_task(rq, p, 0);
trace_sched_wakeup_new(rq, p, 1);
- check_preempt_curr(rq, p, 0);
+ 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
{
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;
*/
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)
}
}
+#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.
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();
*/
arch_start_context_switch(prev);
- if (unlikely(!mm)) {
+ if (likely(!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 (likely(!prev->mm)) {
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
return sum;
}
+unsigned long nr_iowait_cpu(void)
+{
+ struct rq *this = this_rq();
+ return atomic_read(&this->nr_iowait);
+}
+
+unsigned long this_cpu_load(void)
+{
+ struct rq *this = this_rq();
+ return this->cpu_load[0];
+}
+
+
/* Variables and functions for calc_load */
static atomic_long_t calc_load_tasks;
static unsigned long calc_load_update;
}
/*
- * 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).
*/
#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)
-{
- 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);
-}
-
-/*
- * 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)
-{
- spin_unlock(&rq1->lock);
- if (rq1 != rq2)
- spin_unlock(&rq2->lock);
- else
- __release(rq2->lock);
-}
-
-/*
- * 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)
-{
- 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;
-
- /* 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);
-}
-
-/*
- * 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)
-{
- 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);
-}
-
-/*
- * 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.
- */
- check_preempt_curr(this_rq, p, 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;
-}
-
-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.
- *
- * Called with both runqueues locked.
- */
-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)
-{
- struct task_struct *p = iterator->start(iterator->arg);
- int pinned = 0;
-
- while (p) {
- if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) {
- pull_task(busiest, p, this_rq, this_cpu);
- /*
- * Right now, this is only the second place pull_task()
- * is called, so we can safely collect pull_task()
- * stats here rather than inside pull_task().
- */
- schedstat_inc(sd, lb_gained[idle]);
-
- return 1;
- }
- p = iterator->next(iterator->arg);
- }
-
- return 0;
-}
-
-/*
- * move_one_task tries to move exactly one task from busiest to this_rq, as
- * part of active balancing operations within "domain".
- * Returns 1 if successful and 0 otherwise.
- *
- * Called with both runqueues locked.
- */
-static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest,
- struct sched_domain *sd, enum cpu_idle_type idle)
-{
- const struct sched_class *class;
-
- 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;
-}
-/********** 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.
- *
- * @sd: Sched domain whose power-savings statistics are to be initialized.
- * @sds: Variable containing the statistics for sd.
- * @idle: Idle status of the CPU at which we're performing load-balancing.
- */
-static inline void init_sd_power_savings_stats(struct sched_domain *sd,
- struct sd_lb_stats *sds, enum cpu_idle_type idle)
-{
- /*
- * Busy processors will not participate in power savings
- * balance.
- */
- if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE))
- sds->power_savings_balance = 0;
- else {
- sds->power_savings_balance = 1;
- sds->min_nr_running = ULONG_MAX;
- sds->leader_nr_running = 0;
- }
-}
-
-/**
- * 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;
-
- /*
- * If a group is already running at full capacity or idle,
- * don't include that group in power savings calculations
- */
- if (!sds->power_savings_balance ||
- sgs->sum_nr_running >= sgs->group_capacity ||
- !sgs->sum_nr_running)
- return;
-
- /*
- * Calculate the group which has the least non-idle load.
- * This is the group from where we need to pick up the load
- * for saving power
- */
- if ((sgs->sum_nr_running < sds->min_nr_running) ||
- (sgs->sum_nr_running == sds->min_nr_running &&
- group_first_cpu(group) > group_first_cpu(sds->group_min))) {
- sds->group_min = group;
- sds->min_nr_running = sgs->sum_nr_running;
- sds->min_load_per_task = sgs->sum_weighted_load /
- sgs->sum_nr_running;
- }
-
- /*
- * Calculate the group which is almost near its
- * capacity but still has some space to pick up some load
- * from other group and save more power
- */
- if (sgs->sum_nr_running > sgs->group_capacity - 1)
- return;
-
- 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;
- }
-}
-
-/**
- * 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;
-
- 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);
- }
-
- 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.
- *
- * APZ: with cgroup the avg task weight can vary wildly and
- * might not be a suitable number - should we keep a
- * normalized nr_running number somewhere that negates
- * the hierarchy?
- */
- avg_load_per_task = sg_div_cpu_power(group,
- sum_avg_load_per_task * SCHED_LOAD_SCALE);
-
- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
- sgs->group_imb = 1;
-
- sgs->group_capacity = group->__cpu_power / SCHED_LOAD_SCALE;
-
-}
-
-/**
- * update_sd_lb_stats - Update sched_group's statistics for load balancing.
- * @sd: sched_domain whose statistics are to be updated.
- * @this_cpu: Cpu for which load balance is currently performed.
- * @idle: Idle status of this_cpu
- * @sd_idle: Idle status of the sched_domain containing group.
- * @cpus: Set of cpus considered for load balancing.
- * @balance: Should we balance.
- * @sds: variable to hold the statistics for this sched_domain.
- */
-static inline void update_sd_lb_stats(struct sched_domain *sd, int this_cpu,
- enum cpu_idle_type idle, int *sd_idle,
- const struct cpumask *cpus, int *balance,
- struct sd_lb_stats *sds)
-{
- struct sched_group *group = sd->groups;
- struct sg_lb_stats sgs;
- int load_idx;
-
- init_sd_power_savings_stats(sd, sds, idle);
- load_idx = get_sd_load_idx(sd, idle);
-
- do {
- int local_group;
-
- local_group = cpumask_test_cpu(this_cpu,
- sched_group_cpus(group));
- memset(&sgs, 0, sizeof(sgs));
- update_sg_lb_stats(group, this_cpu, idle, load_idx, sd_idle,
- local_group, cpus, balance, &sgs);
-
- if (local_group && balance && !(*balance))
- return;
-
- sds->total_load += sgs.group_load;
- sds->total_pwr += group->__cpu_power;
-
- if (local_group) {
- sds->this_load = sgs.avg_load;
- sds->this = group;
- sds->this_nr_running = sgs.sum_nr_running;
- sds->this_load_per_task = sgs.sum_weighted_load;
- } else if (sgs.avg_load > sds->max_load &&
- (sgs.sum_nr_running > sgs.group_capacity ||
- sgs.group_imb)) {
- sds->max_load = sgs.avg_load;
- sds->busiest = group;
- sds->busiest_nr_running = sgs.sum_nr_running;
- sds->busiest_load_per_task = sgs.sum_weighted_load;
- sds->group_imb = sgs.group_imb;
- }
-
- 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;
-}
-
-/**
- * calculate_imbalance - Calculate the amount of imbalance present within the
- * groups of a given sched_domain during load balance.
- * @sds: statistics of the sched_domain whose imbalance is to be calculated.
- * @this_cpu: Cpu for which currently load balance is being performed.
- * @imbalance: The variable to store the imbalance.
- */
-static inline void calculate_imbalance(struct sd_lb_stats *sds, int this_cpu,
- unsigned long *imbalance)
-{
- unsigned long max_pull;
- /*
- * In the presence of smp nice balancing, certain scenarios can have
- * max load less than avg load(as we skip the groups at or below
- * its cpu_power, while calculating max_load..)
- */
- if (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 *********************/
-
-/**
- * find_busiest_group - Returns the busiest group within the sched_domain
- * if there is an imbalance. If there isn't an imbalance, and
- * the user has opted for power-savings, it returns a group whose
- * CPUs can be put to idle by rebalancing those tasks elsewhere, if
- * such a group exists.
- *
- * Also calculates the amount of weighted load which should be moved
- * to restore balance.
- *
- * @sd: The sched_domain whose busiest group is to be returned.
- * @this_cpu: The cpu for which load balancing is currently being performed.
- * @imbalance: Variable which stores amount of weighted load which should
- * be moved to restore balance/put a group to idle.
- * @idle: The idle status of this_cpu.
- * @sd_idle: The idleness of sd
- * @cpus: The set of CPUs under consideration for load-balancing.
- * @balance: Pointer to a variable indicating if this_cpu
- * is the appropriate cpu to perform load balancing at this_level.
- *
- * Returns: - the busiest group if imbalance exists.
- * - If no imbalance and user has opted for power-savings balance,
- * return the least loaded group whose CPUs can be
- * put to idle by rebalancing its tasks onto our group.
- */
-static struct sched_group *
-find_busiest_group(struct sched_domain *sd, int this_cpu,
- unsigned long *imbalance, enum cpu_idle_type idle,
- int *sd_idle, const struct cpumask *cpus, int *balance)
-{
- struct sd_lb_stats sds;
-
- 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.
- */
-static int load_balance(int this_cpu, struct rq *this_rq,
- struct sched_domain *sd, enum cpu_idle_type idle,
- int *balance)
-{
- int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
- struct sched_group *group;
- unsigned long imbalance;
- struct rq *busiest;
- unsigned long flags;
- struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
-
- cpumask_setall(cpus);
-
- /*
- * 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;
-}
-
-/*
- * 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.
- */
-static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
-{
- 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;
-
- return 0;
-}
-
-/*
- * 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 (!(sd->flags & SD_LOAD_BALANCE))
- continue;
-
- if (sd->flags & SD_BALANCE_NEWIDLE)
- /* If we've pulled tasks over stop searching: */
- pulled_task = load_balance_newidle(this_cpu, this_rq,
- sd);
-
- 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;
- }
-}
-
-/*
- * 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.
- */
-static void active_load_balance(struct rq *busiest_rq, int busiest_cpu)
-{
- int target_cpu = busiest_rq->push_cpu;
- struct sched_domain *sd;
- struct rq *target_rq;
-
- /* Is there any task to move? */
- if (busiest_rq->nr_running <= 1)
- 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),
-};
-
-int get_nohz_load_balancer(void)
-{
- return atomic_read(&nohz.load_balancer);
-}
-
-#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
-/**
- * lowest_flag_domain - Return lowest sched_domain containing flag.
- * @cpu: The cpu whose lowest level of sched domain is to
- * be returned.
- * @flag: The flag to check for the lowest sched_domain
- * for the given cpu.
- *
- * Returns the lowest sched_domain of a cpu which contains the given flag.
- */
-static inline struct sched_domain *lowest_flag_domain(int cpu, int flag)
-{
- struct sched_domain *sd;
-
- for_each_domain(cpu, sd)
- if (sd && (sd->flags & flag))
- break;
-
- return sd;
-}
-
-/**
- * for_each_flag_domain - Iterates over sched_domains containing the flag.
- * @cpu: The cpu whose domains we're iterating over.
- * @sd: variable holding the value of the power_savings_sd
- * for cpu.
- * @flag: The flag to filter the sched_domains to be iterated.
- *
- * Iterates over all the scheduler domains for a given cpu that has the 'flag'
- * set, starting from the lowest sched_domain to the highest.
- */
-#define for_each_flag_domain(cpu, sd, flag) \
- for (sd = lowest_flag_domain(cpu, flag); \
- (sd && (sd->flags & flag)); sd = sd->parent)
-
-/**
- * is_semi_idle_group - Checks if the given sched_group is semi-idle.
- * @ilb_group: group to be checked for semi-idleness
- *
- * Returns: 1 if the group is semi-idle. 0 otherwise.
- *
- * We define a sched_group to be semi idle if it has atleast one idle-CPU
- * and atleast one non-idle CPU. This helper function checks if the given
- * sched_group is semi-idle or not.
- */
-static inline int is_semi_idle_group(struct sched_group *ilb_group)
-{
- cpumask_and(nohz.ilb_grp_nohz_mask, nohz.cpu_mask,
- sched_group_cpus(ilb_group));
-
- /*
- * A sched_group is semi-idle when it has atleast one busy cpu
- * and atleast one idle cpu.
- */
- if (cpumask_empty(nohz.ilb_grp_nohz_mask))
- return 0;
-
- if (cpumask_equal(nohz.ilb_grp_nohz_mask, sched_group_cpus(ilb_group)))
- return 0;
-
- return 1;
-}
-/**
- * find_new_ilb - Finds the optimum idle load balancer for nomination.
- * @cpu: The cpu which is nominating a new idle_load_balancer.
- *
- * Returns: Returns the id of the idle load balancer if it exists,
- * Else, returns >= nr_cpu_ids.
- *
- * This algorithm picks the idle load balancer such that it belongs to a
- * semi-idle powersavings sched_domain. The idea is to try and avoid
- * completely idle packages/cores just for the purpose of idle load balancing
- * when there are other idle cpu's which are better suited for that job.
- */
-static int find_new_ilb(int cpu)
-{
- struct sched_domain *sd;
- struct sched_group *ilb_group;
-
- /*
- * Have idle load balancer selection from semi-idle packages only
- * when power-aware load balancing is enabled
- */
- if (!(sched_smt_power_savings || sched_mc_power_savings))
- goto out_done;
-
- /*
- * Optimize for the case when we have no idle CPUs or only one
- * idle CPU. Don't walk the sched_domain hierarchy in such cases
- */
- if (cpumask_weight(nohz.cpu_mask) < 2)
- goto out_done;
-
- for_each_flag_domain(cpu, sd, SD_POWERSAVINGS_BALANCE) {
- ilb_group = sd->groups;
-
- do {
- if (is_semi_idle_group(ilb_group))
- return cpumask_first(nohz.ilb_grp_nohz_mask);
-
- ilb_group = ilb_group->next;
-
- } while (ilb_group != sd->groups);
- }
-
-out_done:
- return cpumask_first(nohz.cpu_mask);
-}
-#else /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */
-static inline int find_new_ilb(int call_cpu)
-{
- return cpumask_first(nohz.cpu_mask);
-}
-#endif
-
-/*
- * This routine will try to nominate the ilb (idle load balancing)
- * owner among the cpus whose ticks are stopped. ilb owner will do the idle
- * 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;
-
- cpumask_clear_cpu(cpu, nohz.cpu_mask);
-
- if (atomic_read(&nohz.load_balancer) == cpu)
- if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu)
- BUG();
- }
- return 0;
-}
-#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.
- */
-static void rebalance_domains(int cpu, enum cpu_idle_type idle)
-{
- 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;
-
- interval = sd->balance_interval;
- if (idle != CPU_IDLE)
- interval *= sd->busy_factor;
-
- /* 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;
-
- need_serialize = sd->flags & SD_SERIALIZE;
-
- if (need_serialize) {
- if (!spin_trylock(&balancing))
- goto out;
- }
-
- 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;
- }
-
- /*
- * Stop the load balance at this level. There is another
- * CPU in our sched group which is doing load balancing more
- * actively.
- */
- if (!balance)
- break;
- }
-
- /*
- * 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;
-}
-
-/*
- * 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)
-{
- 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;
-
- 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
-}
-
-static inline int on_null_domain(int cpu)
-{
- return !rcu_dereference(cpu_rq(cpu)->sd);
-}
-
-/*
- * 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.
- */
-static inline void trigger_load_balance(struct rq *rq, int cpu)
-{
-#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);
+/*
+ * 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)
+{
+ struct task_struct *p = current;
+ struct migration_req req;
+ int dest_cpu, this_cpu;
+ unsigned long flags;
+ struct rq *rq;
- if (ilb < nr_cpu_ids)
- resched_cpu(ilb);
- }
+again:
+ this_cpu = get_cpu();
+ dest_cpu = select_task_rq(p, SD_BALANCE_EXEC, 0);
+ if (dest_cpu == this_cpu) {
+ put_cpu();
+ return;
}
+ rq = task_rq_lock(p, &flags);
+ put_cpu();
+
/*
- * 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)
+ || unlikely(!cpu_active(dest_cpu))) {
+ task_rq_unlock(rq, &flags);
+ goto again;
}
- /*
- * 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))
- 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);
-}
+ /* 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;
-#else /* CONFIG_SMP */
+ get_task_struct(mt);
+ task_rq_unlock(rq, &flags);
+ wake_up_process(mt);
+ put_task_struct(mt);
+ wait_for_completion(&req.done);
-/*
- * on UP we do not need to balance between CPUs:
- */
-static inline void idle_balance(int cpu, struct rq *rq)
-{
+ return;
+ }
+ task_rq_unlock(rq, &flags);
}
#endif
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);
+ }
}
/*
*/
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);
}
/*
* 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) {
- temp *= utime;
+ u64 temp;
+
+ temp = (u64)(rtime * utime);
do_div(temp, total);
- }
- utime = (clock_t)temp;
+ utime = (cputime_t)temp;
+ } else
+ utime = rtime;
+
+ /*
+ * 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));
- p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime));
- return 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;
-inline cputime_t task_gtime(struct task_struct *p)
-{
- return p->gtime;
+ temp = (u64)(rtime * 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.
sched_clock_tick();
- spin_lock(&rq->lock);
+ raw_spin_lock(&rq->lock);
update_rq_clock(rq);
update_cpu_load(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(curr);
#ifdef CONFIG_SMP
rq->idle_at_tick = idle_cpu(cpu);
preempt_disable();
cpu = smp_processor_id();
rq = cpu_rq(cpu);
- rcu_qsctr_inc(cpu);
+ rcu_sched_qs(cpu);
prev = rq->curr;
switch_count = &prev->nivcsw;
if (sched_feat(HRTICK))
hrtick_clear(rq);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
update_rq_clock(rq);
clear_tsk_need_resched(prev);
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);
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;
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(current) < 0)) {
+ prev = rq->curr;
+ switch_count = &prev->nivcsw;
goto need_resched_nonpreemptible;
+ }
preempt_enable_no_resched();
if (need_resched())
}
EXPORT_SYMBOL(schedule);
-#ifdef CONFIG_SMP
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
/*
* Look out! "owner" is an entirely speculative pointer
* access and not reliable.
#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);
* 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;
}
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);
*/
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);
*/
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);
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);
update_rq_clock(rq);
oldprio = p->prio;
+ prev_class = p->sched_class;
on_rq = p->se.on_rq;
running = task_current(rq, p);
if (on_rq)
if (running)
p->sched_class->set_curr_task(rq);
if (on_rq) {
- enqueue_task(rq, p, 0);
+ enqueue_task(rq, p, 0, oldprio < prio);
check_class_changed(rq, p, prev_class, oldprio, running);
}
delta = p->prio - old_prio;
if (on_rq) {
- enqueue_task(rq, p, 0);
+ enqueue_task(rq, p, 0, false);
/*
* If the task increased its priority or is running and
* lowered its priority, then reschedule its CPU:
/* 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));
}
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);
}
{
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,
if (!lock_task_sighand(p, &flags))
return -ESRCH;
- rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur;
+ rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
unlock_task_sighand(p, &flags);
/* can't set/change the rt policy */
/* can't change other user's priorities */
if (!check_same_owner(p))
return -EPERM;
+
+ /* Normal users shall not reset the sched_reset_on_fork flag */
+ if (p->sched_reset_on_fork && !reset_on_fork)
+ return -EPERM;
}
if (user) {
* 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.
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);
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)
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);
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.
*/
if (!param || pid < 0)
return -EINVAL;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
p = find_process_by_pid(pid);
retval = -ESRCH;
if (!p)
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 ...
return retval;
out_unlock:
- read_unlock(&tasklist_lock);
+ rcu_read_unlock();
return retval;
}
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;
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);
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;
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))
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);
*/
__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();
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)
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 = should_resched();
int ret = 0;
+ lockdep_assert_held(lock);
+
if (spin_needbreak(lock) || resched) {
spin_unlock(lock);
if (resched)
}
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());
}
return 0;
}
-EXPORT_SYMBOL(cond_resched_softirq);
+EXPORT_SYMBOL(__cond_resched_softirq);
/**
* yield - yield the current processor to other threads.
/*
* 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();
}
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;
{
struct task_struct *p;
unsigned int time_slice;
+ unsigned long flags;
+ struct rq *rq;
int retval;
struct timespec t;
return -EINVAL;
retval = -ESRCH;
- read_lock(&tasklist_lock);
+ rcu_read_lock();
p = find_process_by_pid(pid);
if (!p)
goto out_unlock;
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;
}
/*
* Only show locks if all tasks are dumped:
*/
- if (state_filter == -1)
+ if (!state_filter)
debug_show_all_locks();
}
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));
__set_task_cpu(idle, cpu);
#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)
*
* 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;
+
+ 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_min_granularity *= factor;
- if (sysctl_sched_min_granularity > limit)
- sysctl_sched_min_granularity = limit;
+ return factor;
+}
- sysctl_sched_latency *= factor;
- if (sysctl_sched_latency > limit)
- sysctl_sched_latency = limit;
+static void update_sysctl(void)
+{
+ unsigned int factor = get_update_sysctl_factor();
- sysctl_sched_wakeup_granularity *= 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);
+ SET_SYSCTL(sched_shares_ratelimit);
+#undef SET_SYSCTL
+}
- sysctl_sched_shares_ratelimit *= factor;
+static inline void sched_init_granularity(void)
+{
+ update_sysctl();
}
#ifdef CONFIG_SMP
int ret = 0;
rq = task_rq_lock(p, &flags);
- if (!cpumask_intersects(new_mask, cpu_online_mask)) {
+
+ if (!cpumask_intersects(new_mask, cpu_active_mask)) {
ret = -EINVAL;
goto out;
}
if (cpumask_test_cpu(task_cpu(p), new_mask))
goto out;
- if (migrate_task(p, cpumask_any_and(cpu_online_mask, new_mask), &req)) {
+ if (migrate_task(p, cpumask_any_and(cpu_active_mask, new_mask), &req)) {
/* Need help from migration thread: drop lock and wait. */
+ struct task_struct *mt = rq->migration_thread;
+
+ get_task_struct(mt);
task_rq_unlock(rq, &flags);
- wake_up_process(rq->migration_thread);
+ wake_up_process(mt);
+ put_task_struct(mt);
wait_for_completion(&req.done);
tlb_migrate_finish(p->mm);
return 0;
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;
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);
}
return ret;
}
+#define RCU_MIGRATION_IDLE 0
+#define RCU_MIGRATION_NEED_QS 1
+#define RCU_MIGRATION_GOT_QS 2
+#define RCU_MIGRATION_MUST_SYNC 3
+
/*
* migration_thread - this is a highprio system thread that performs
* thread migration by bumping thread off CPU then 'pushing' onto
*/
static int migration_thread(void *data)
{
+ int badcpu;
int cpu = (long)data;
struct rq *rq;
struct migration_req *req;
struct list_head *head;
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
if (cpu_is_offline(cpu)) {
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
break;
}
head = &rq->migration_queue;
if (list_empty(head)) {
- spin_unlock_irq(&rq->lock);
+ raw_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);
+ if (req->task != NULL) {
+ raw_spin_unlock(&rq->lock);
+ __migrate_task(req->task, cpu, req->dest_cpu);
+ } else if (likely(cpu == (badcpu = smp_processor_id()))) {
+ req->dest_cpu = RCU_MIGRATION_GOT_QS;
+ raw_spin_unlock(&rq->lock);
+ } else {
+ req->dest_cpu = RCU_MIGRATION_MUST_SYNC;
+ raw_spin_unlock(&rq->lock);
+ WARN_ONCE(1, "migration_thread() on CPU %d, expected %d\n", badcpu, cpu);
+ }
local_irq_enable();
complete(&req->done);
static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p)
{
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);
-
- /*
- * 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);
- }
- }
+ dest_cpu = select_fallback_rq(dead_cpu, p);
-move:
/* It can have affinity changed while we were choosing. */
if (unlikely(!__migrate_task_irq(p, dead_cpu, dest_cpu)))
goto again;
*/
static void migrate_nr_uninterruptible(struct rq *rq_src)
{
- struct rq *rq_dest = cpu_rq(cpumask_any(cpu_online_mask));
+ struct rq *rq_dest = cpu_rq(cpumask_any(cpu_active_mask));
unsigned long flags;
local_irq_save(flags);
* 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);
+ raw_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);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
/*
* that's OK. No task can be added to this CPU, so iteration is
* fine.
*/
- spin_unlock_irq(&rq->lock);
+ raw_spin_unlock_irq(&rq->lock);
move_task_off_dead_cpu(dead_cpu, p);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
put_task_struct(p);
}
.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)
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];
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;
/* 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_online(rq);
}
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
#ifdef CONFIG_HOTPLUG_CPU
put_task_struct(rq->migration_thread);
rq->migration_thread = NULL;
/* Idle task back to normal (off runqueue, low prio) */
- spin_lock_irq(&rq->lock);
+ raw_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);
+ raw_spin_unlock_irq(&rq->lock);
cpuset_unlock();
migrate_nr_uninterruptible(rq);
BUG_ON(rq->nr_running != 0);
* they didn't take sched_hotcpu_mutex. Just wake up
* the requestors.
*/
- spin_lock_irq(&rq->lock);
+ raw_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);
+ raw_spin_unlock_irq(&rq->lock);
complete(&req->done);
- spin_lock_irq(&rq->lock);
+ raw_spin_lock_irq(&rq->lock);
}
- spin_unlock_irq(&rq->lock);
+ raw_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);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
break;
#endif
}
/*
* 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,
migration_call(&migration_notifier, CPU_ONLINE, cpu);
register_cpu_notifier(&migration_notifier);
- return err;
+ return 0;
}
early_initcall(migration_init);
#endif
#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)
{
break;
}
- if (!group->__cpu_power) {
+ if (!group->cpu_power) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: domain->cpu_power not "
"set\n");
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;
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;
}
/* 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;
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 |
static void free_rootdomain(struct root_domain *rd)
{
+ synchronize_sched();
+
cpupri_cleanup(&rd->cpupri);
free_cpumask_var(rd->rto_mask);
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;
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);
/* 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;
}
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)
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 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_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 */
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
* 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);
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);
}
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_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->send_covered, GFP_KERNEL))
+ return sa_this_core_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
-
- /*
- * Set up domains for cpus specified by the cpu_map.
- */
- for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = NULL, *p;
-
- cpumask_and(nodemask, cpumask_of_node(cpu_to_node(i)), cpu_map);
-
-#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;
+ struct sched_domain *parent;
- sd = &per_cpu(node_domains, i).sd;
- SD_INIT(sd, NODE);
+ 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);
- 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);
+ 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;
+
+ 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;
+}
- 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_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;
+}
+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);
- }
-
+ 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_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_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
for_each_cpu(i, cpu_map) {
- struct sched_domain *sd = &per_cpu(phys_domains, i).sd;
-
+ 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)
#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)
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' */
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
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;
* 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,
*
* 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;
/* 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;
#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);
#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);
switch (action) {
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
- case CPU_DEAD:
- case CPU_DEAD_FROZEN:
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ case CPU_DOWN_FAILED:
+ case CPU_DOWN_FAILED_FROZEN:
partition_sched_domains(1, NULL, NULL);
return NOTIFY_OK;
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 **),
#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);
sched_init_granularity();
free_cpumask_var(non_isolated_cpus);
- alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
init_sched_rt_class();
}
#else
#ifdef CONFIG_SMP
rt_rq->rt_nr_migratory = 0;
rt_rq->overloaded = 0;
- plist_head_init(&rt_rq->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;
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);
#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);
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;
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) {
#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 */
#endif /* CONFIG_RT_GROUP_SCHED */
-#ifdef CONFIG_GROUP_SCHED
+#ifdef CONFIG_CGROUP_SCHED
list_add(&init_task_group.list, &task_groups);
INIT_LIST_HEAD(&init_task_group.children);
-#ifdef CONFIG_USER_SCHED
- 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 */
+#endif /* CONFIG_CGROUP_SCHED */
+#if defined CONFIG_FAIR_GROUP_SCHED && defined CONFIG_SMP
+ update_shares_data = __alloc_percpu(nr_cpu_ids * sizeof(unsigned long),
+ __alignof__(unsigned long));
+#endif
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;
* directly in rq->cfs (i.e init_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
#endif /* CONFIG_FAIR_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
#endif
#ifdef CONFIG_SMP
rq->sd = NULL;
rq->rd = NULL;
+ 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;
+ rq->idle_stamp = 0;
+ rq->avg_idle = 2*sysctl_sched_migration_cost;
INIT_LIST_HEAD(&rq->migration_queue);
rq_attach_root(rq, &def_root_domain);
#endif
#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
/*
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);
+ zalloc_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);
+ /* 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();
+ perf_event_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;
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);
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]);
}
return 1;
+ err_free_rq:
+ kfree(cfs_rq);
err:
return 0;
}
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]);
}
return 1;
+ err_free_rq:
+ kfree(rt_rq);
err:
return 0;
}
}
#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);
#ifdef CONFIG_FAIR_GROUP_SCHED
if (tsk->sched_class->moved_group)
- tsk->sched_class->moved_group(tsk);
+ tsk->sched_class->moved_group(tsk, on_rq);
#endif
if (unlikely(running))
tsk->sched_class->set_curr_task(rq);
if (on_rq)
- enqueue_task(rq, tsk, 0);
+ enqueue_task(rq, tsk, 0, false);
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 rq *rq = cfs_rq->rq;
unsigned long flags;
- spin_lock_irqsave(&rq->lock, flags);
+ raw_spin_lock_irqsave(&rq->lock, flags);
__set_se_shares(se, shares);
- spin_unlock_irqrestore(&rq->lock, flags);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
}
static DEFINE_MUTEX(shares_mutex);
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.
*/
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);
+ raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
unlock:
read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
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;
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();
}
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))
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
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;
};
/*
* 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
/*
* 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
}
/*
+ * 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;
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();
.subsys_id = cpuacct_subsys_id,
};
#endif /* CONFIG_CGROUP_CPUACCT */
+
+#ifndef CONFIG_SMP
+
+int rcu_expedited_torture_stats(char *page)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+void synchronize_sched_expedited(void)
+{
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#else /* #ifndef CONFIG_SMP */
+
+static DEFINE_PER_CPU(struct migration_req, rcu_migration_req);
+static DEFINE_MUTEX(rcu_sched_expedited_mutex);
+
+#define RCU_EXPEDITED_STATE_POST -2
+#define RCU_EXPEDITED_STATE_IDLE -1
+
+static int rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+
+int rcu_expedited_torture_stats(char *page)
+{
+ int cnt = 0;
+ int cpu;
+
+ cnt += sprintf(&page[cnt], "state: %d /", rcu_expedited_state);
+ for_each_online_cpu(cpu) {
+ cnt += sprintf(&page[cnt], " %d:%d",
+ cpu, per_cpu(rcu_migration_req, cpu).dest_cpu);
+ }
+ cnt += sprintf(&page[cnt], "\n");
+ return cnt;
+}
+EXPORT_SYMBOL_GPL(rcu_expedited_torture_stats);
+
+static long synchronize_sched_expedited_count;
+
+/*
+ * Wait for an rcu-sched grace period to elapse, but use "big hammer"
+ * approach to force grace period to end quickly. This consumes
+ * significant time on all CPUs, and is thus not recommended for
+ * any sort of common-case code.
+ *
+ * Note that it is illegal to call this function while holding any
+ * lock that is acquired by a CPU-hotplug notifier. Failing to
+ * observe this restriction will result in deadlock.
+ */
+void synchronize_sched_expedited(void)
+{
+ int cpu;
+ unsigned long flags;
+ bool need_full_sync = 0;
+ struct rq *rq;
+ struct migration_req *req;
+ long snap;
+ int trycount = 0;
+
+ smp_mb(); /* ensure prior mod happens before capturing snap. */
+ snap = ACCESS_ONCE(synchronize_sched_expedited_count) + 1;
+ get_online_cpus();
+ while (!mutex_trylock(&rcu_sched_expedited_mutex)) {
+ put_online_cpus();
+ if (trycount++ < 10)
+ udelay(trycount * num_online_cpus());
+ else {
+ synchronize_sched();
+ return;
+ }
+ if (ACCESS_ONCE(synchronize_sched_expedited_count) - snap > 0) {
+ smp_mb(); /* ensure test happens before caller kfree */
+ return;
+ }
+ get_online_cpus();
+ }
+ rcu_expedited_state = RCU_EXPEDITED_STATE_POST;
+ for_each_online_cpu(cpu) {
+ rq = cpu_rq(cpu);
+ req = &per_cpu(rcu_migration_req, cpu);
+ init_completion(&req->done);
+ req->task = NULL;
+ req->dest_cpu = RCU_MIGRATION_NEED_QS;
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ list_add(&req->list, &rq->migration_queue);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ wake_up_process(rq->migration_thread);
+ }
+ for_each_online_cpu(cpu) {
+ rcu_expedited_state = cpu;
+ req = &per_cpu(rcu_migration_req, cpu);
+ rq = cpu_rq(cpu);
+ wait_for_completion(&req->done);
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ if (unlikely(req->dest_cpu == RCU_MIGRATION_MUST_SYNC))
+ need_full_sync = 1;
+ req->dest_cpu = RCU_MIGRATION_IDLE;
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ }
+ rcu_expedited_state = RCU_EXPEDITED_STATE_IDLE;
+ synchronize_sched_expedited_count++;
+ mutex_unlock(&rcu_sched_expedited_mutex);
+ put_online_cpus();
+ if (need_full_sync)
+ synchronize_sched();
+}
+EXPORT_SYMBOL_GPL(synchronize_sched_expedited);
+
+#endif /* #else #ifndef CONFIG_SMP */