SD_LV_NONE = 0,
SD_LV_SIBLING,
SD_LV_MC,
+ SD_LV_BOOK,
SD_LV_CPU,
SD_LV_NODE,
SD_LV_ALLNODES,
struct rcu_node;
+enum perf_event_task_context {
+ perf_invalid_context = -1,
+ perf_hw_context = 0,
+ perf_sw_context,
+ perf_nr_task_contexts,
+};
+
struct task_struct {
volatile long state; /* -1 unrunnable, 0 runnable, >0 stopped */
void *stack;
unsigned int policy;
cpumask_t cpus_allowed;
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
int rcu_read_lock_nesting;
char rcu_read_unlock_special;
- struct rcu_node *rcu_blocked_node;
struct list_head rcu_node_entry;
+#endif /* #ifdef CONFIG_PREEMPT_RCU */
+#ifdef CONFIG_TREE_PREEMPT_RCU
+ struct rcu_node *rcu_blocked_node;
#endif /* #ifdef CONFIG_TREE_PREEMPT_RCU */
#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT)
struct list_head cpu_timers[3];
/* process credentials */
- const struct cred *real_cred; /* objective and real subjective task
+ const struct cred __rcu *real_cred; /* objective and real subjective task
* credentials (COW) */
- const struct cred *cred; /* effective (overridable) subjective task
+ const struct cred __rcu *cred; /* effective (overridable) subjective task
* credentials (COW) */
struct mutex cred_guard_mutex; /* guard against foreign influences on
* credential calculations
#endif
#ifdef CONFIG_CGROUPS
/* Control Group info protected by css_set_lock */
- struct css_set *cgroups;
+ struct css_set __rcu *cgroups;
/* cg_list protected by css_set_lock and tsk->alloc_lock */
struct list_head cg_list;
#endif
struct futex_pi_state *pi_state_cache;
#endif
#ifdef CONFIG_PERF_EVENTS
- struct perf_event_context *perf_event_ctxp;
+ struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
struct mutex perf_event_mutex;
struct list_head perf_event_list;
#endif
/*
* Per process flags
*/
- #define PF_ALIGNWARN 0x00000001 /* Print alignment warning msgs */
- /* Not implemented yet, only for 486*/
+ #define PF_KSOFTIRQD 0x00000001 /* I am ksoftirqd */
#define PF_STARTING 0x00000002 /* being created */
#define PF_EXITING 0x00000004 /* getting shut down */
#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
#define tsk_used_math(p) ((p)->flags & PF_USED_MATH)
#define used_math() tsk_used_math(current)
-#ifdef CONFIG_TREE_PREEMPT_RCU
+#ifdef CONFIG_PREEMPT_RCU
#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
{
p->rcu_read_lock_nesting = 0;
p->rcu_read_unlock_special = 0;
+#ifdef CONFIG_TREE_PREEMPT_RCU
p->rcu_blocked_node = NULL;
+#endif
INIT_LIST_HEAD(&p->rcu_node_entry);
}
extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#endif
+ #ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ /*
+ * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
+ * The reason for this explicit opt-in is not to have perf penalty with
+ * slow sched_clocks.
+ */
+ extern void enable_sched_clock_irqtime(void);
+ extern void disable_sched_clock_irqtime(void);
+ #else
+ static inline void enable_sched_clock_irqtime(void) {}
+ static inline void disable_sched_clock_irqtime(void) {}
+ #endif
+
extern unsigned long long
task_sched_runtime(struct task_struct *task);
extern unsigned long long thread_group_sched_runtime(struct task_struct *task);
extern int __cond_resched_softirq(void);
- #define cond_resched_softirq() ({ \
- __might_sleep(__FILE__, __LINE__, SOFTIRQ_OFFSET); \
- __cond_resched_softirq(); \
+ #define cond_resched_softirq() ({ \
+ __might_sleep(__FILE__, __LINE__, SOFTIRQ_DISABLE_OFFSET); \
+ __cond_resched_softirq(); \
})
/*
*/
cpumask_var_t rto_mask;
atomic_t rto_count;
- #ifdef CONFIG_SMP
struct cpupri cpupri;
- #endif
};
/*
*/
static struct root_domain def_root_domain;
- #endif
+ #endif /* CONFIG_SMP */
/*
* This is the main, per-CPU runqueue data structure.
*/
unsigned long nr_uninterruptible;
- struct task_struct *curr, *idle;
+ struct task_struct *curr, *idle, *stop;
unsigned long next_balance;
struct mm_struct *prev_mm;
u64 clock;
+ u64 clock_task;
atomic_t nr_iowait;
u64 avg_idle;
#endif
+ #ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ u64 prev_irq_time;
+ #endif
+
/* calc_load related fields */
unsigned long calc_load_update;
long calc_load_active;
#endif /* CONFIG_CGROUP_SCHED */
+ static u64 irq_time_cpu(int cpu);
+ static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+
inline void update_rq_clock(struct rq *rq)
{
- if (!rq->skip_clock_update)
- rq->clock = sched_clock_cpu(cpu_of(rq));
+ if (!rq->skip_clock_update) {
+ int cpu = cpu_of(rq);
+ u64 irq_time;
+
+ rq->clock = sched_clock_cpu(cpu);
+ irq_time = irq_time_cpu(cpu);
+ if (rq->clock - irq_time > rq->clock_task)
+ rq->clock_task = rq->clock - irq_time;
+
+ sched_irq_time_avg_update(rq, irq_time);
+ }
}
/*
size_t cnt, loff_t *ppos)
{
char buf[64];
- char *cmp = buf;
+ char *cmp;
int neg = 0;
int i;
return -EFAULT;
buf[cnt] = 0;
+ cmp = strstrip(buf);
if (strncmp(buf, "NO_", 3) == 0) {
neg = 1;
}
for (i = 0; sched_feat_names[i]; i++) {
- int len = strlen(sched_feat_names[i]);
-
- if (strncmp(cmp, sched_feat_names[i], len) == 0) {
+ if (strcmp(cmp, sched_feat_names[i]) == 0) {
if (neg)
sysctl_sched_features &= ~(1UL << i);
else
static const struct sched_class rt_sched_class;
- #define sched_class_highest (&rt_sched_class)
+ #define sched_class_highest (&stop_sched_class)
#define for_each_class(class) \
for (class = sched_class_highest; class; class = class->next)
static void set_load_weight(struct task_struct *p)
{
- if (task_has_rt_policy(p)) {
- p->se.load.weight = 0;
- p->se.load.inv_weight = WMULT_CONST;
- return;
- }
-
/*
* SCHED_IDLE tasks get minimal weight:
*/
dec_nr_running(rq);
}
+ #ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+ /*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in account_system_vtime, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/account_system_vtime on this CPU. We would either get old
+ * or new value (or semi updated value on 32 bit) with a side effect of
+ * accounting a slice of irq time to wrong task when irq is in progress
+ * while we read rq->clock. That is a worthy compromise in place of having
+ * locks on each irq in account_system_time.
+ */
+ static DEFINE_PER_CPU(u64, cpu_hardirq_time);
+ static DEFINE_PER_CPU(u64, cpu_softirq_time);
+
+ static DEFINE_PER_CPU(u64, irq_start_time);
+ static int sched_clock_irqtime;
+
+ void enable_sched_clock_irqtime(void)
+ {
+ sched_clock_irqtime = 1;
+ }
+
+ void disable_sched_clock_irqtime(void)
+ {
+ sched_clock_irqtime = 0;
+ }
+
+ static u64 irq_time_cpu(int cpu)
+ {
+ if (!sched_clock_irqtime)
+ return 0;
+
+ return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+ }
+
+ void account_system_vtime(struct task_struct *curr)
+ {
+ unsigned long flags;
+ int cpu;
+ u64 now, delta;
+
+ if (!sched_clock_irqtime)
+ return;
+
+ local_irq_save(flags);
+
+ cpu = smp_processor_id();
+ now = sched_clock_cpu(cpu);
+ delta = now - per_cpu(irq_start_time, cpu);
+ per_cpu(irq_start_time, cpu) = now;
+ /*
+ * We do not account for softirq time from ksoftirqd here.
+ * We want to continue accounting softirq time to ksoftirqd thread
+ * in that case, so as not to confuse scheduler with a special task
+ * that do not consume any time, but still wants to run.
+ */
+ if (hardirq_count())
+ per_cpu(cpu_hardirq_time, cpu) += delta;
+ else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
+ per_cpu(cpu_softirq_time, cpu) += delta;
+
+ local_irq_restore(flags);
+ }
+ EXPORT_SYMBOL_GPL(account_system_vtime);
+
+ static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+ {
+ if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
+ u64 delta_irq = curr_irq_time - rq->prev_irq_time;
+ rq->prev_irq_time = curr_irq_time;
+ sched_rt_avg_update(rq, delta_irq);
+ }
+ }
+
+ #else
+
+ static u64 irq_time_cpu(int cpu)
+ {
+ return 0;
+ }
+
+ static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
+
+ #endif
+
#include "sched_idletask.c"
#include "sched_fair.c"
#include "sched_rt.c"
+ #include "sched_stoptask.c"
#ifdef CONFIG_SCHED_DEBUG
# include "sched_debug.c"
#endif
+ void sched_set_stop_task(int cpu, struct task_struct *stop)
+ {
+ struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+ struct task_struct *old_stop = cpu_rq(cpu)->stop;
+
+ if (stop) {
+ /*
+ * Make it appear like a SCHED_FIFO task, its something
+ * userspace knows about and won't get confused about.
+ *
+ * Also, it will make PI more or less work without too
+ * much confusion -- but then, stop work should not
+ * rely on PI working anyway.
+ */
+ sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m);
+
+ stop->sched_class = &stop_sched_class;
+ }
+
+ cpu_rq(cpu)->stop = stop;
+
+ if (old_stop) {
+ /*
+ * Reset it back to a normal scheduling class so that
+ * it can die in pieces.
+ */
+ old_stop->sched_class = &rt_sched_class;
+ }
+ }
+
/*
* __normal_prio - return the priority that is based on the static prio
*/
if (p->sched_class != &fair_sched_class)
return 0;
+ if (unlikely(p->policy == SCHED_IDLE))
+ return 0;
+
/*
* Buddy candidates are cache hot:
*/
*/
arch_start_context_switch(prev);
- if (likely(!mm)) {
+ if (!mm) {
next->active_mm = oldmm;
atomic_inc(&oldmm->mm_count);
enter_lazy_tlb(oldmm, next);
} else
switch_mm(oldmm, mm, next);
- if (likely(!prev->mm)) {
+ if (!prev->mm) {
prev->active_mm = NULL;
rq->prev_mm = oldmm;
}
if (task_current(rq, p)) {
update_rq_clock(rq);
- ns = rq->clock - p->se.exec_start;
+ ns = rq->clock_task - p->se.exec_start;
if ((s64)ns < 0)
ns = 0;
}
tmp = cputime_to_cputime64(cputime);
if (hardirq_count() - hardirq_offset)
cpustat->irq = cputime64_add(cpustat->irq, tmp);
- else if (softirq_count())
+ else if (in_serving_softirq())
cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
else
cpustat->system = cputime64_add(cpustat->system, tmp);
curr->sched_class->task_tick(rq, curr, 0);
raw_spin_unlock(&rq->lock);
- perf_event_task_tick(curr);
+ perf_event_task_tick();
#ifdef CONFIG_SMP
rq->idle_at_tick = idle_cpu(cpu);
return p;
}
- class = sched_class_highest;
- for ( ; ; ) {
+ for_each_class(class) {
p = class->pick_next_task(rq);
if (p)
return p;
- /*
- * Will never be NULL as the idle class always
- * returns a non-NULL p:
- */
- class = class->next;
}
+
+ BUG(); /* the idle class will always have a runnable task */
}
/*
rq = task_rq_lock(p, &flags);
+ trace_sched_pi_setprio(p, prio);
oldprio = p->prio;
prev_class = p->sched_class;
on_rq = p->se.on_rq;
}
if (user) {
- retval = security_task_setscheduler(p, policy, param);
+ retval = security_task_setscheduler(p);
if (retval)
return retval;
}
*/
rq = __task_rq_lock(p);
+ /*
+ * Changing the policy of the stop threads its a very bad idea
+ */
+ if (p == rq->stop) {
+ __task_rq_unlock(rq);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ return -EINVAL;
+ }
+
#ifdef CONFIG_RT_GROUP_SCHED
if (user) {
/*
if (!check_same_owner(p) && !capable(CAP_SYS_NICE))
goto out_unlock;
- retval = security_task_setscheduler(p, 0, NULL);
+ retval = security_task_setscheduler(p);
if (retval)
goto out_unlock;
cpuset_cpus_allowed(p, cpus_allowed);
cpumask_and(new_mask, in_mask, cpus_allowed);
- again:
+ again:
retval = set_cpus_allowed_ptr(p, new_mask);
if (!retval) {
idle->se.exec_start = sched_clock();
cpumask_copy(&idle->cpus_allowed, cpumask_of(cpu));
+ /*
+ * We're having a chicken and egg problem, even though we are
+ * holding rq->lock, the cpu isn't yet set to this cpu so the
+ * lockdep check in task_group() will fail.
+ *
+ * Similar case to sched_fork(). / Alternatively we could
+ * use task_rq_lock() here and obtain the other rq->lock.
+ *
+ * Silence PROVE_RCU
+ */
+ rcu_read_lock();
__set_task_cpu(idle, cpu);
+ rcu_read_unlock();
rq->curr = rq->idle = idle;
#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW)
cpumask_var_t nodemask;
cpumask_var_t this_sibling_map;
cpumask_var_t this_core_map;
+ cpumask_var_t this_book_map;
cpumask_var_t send_covered;
cpumask_var_t tmpmask;
struct sched_group **sched_group_nodes;
sa_rootdomain,
sa_tmpmask,
sa_send_covered,
+ sa_this_book_map,
sa_this_core_map,
sa_this_sibling_map,
sa_nodemask,
#ifdef CONFIG_SCHED_MC
static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
- #endif /* CONFIG_SCHED_MC */
- #if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
static int
cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
struct sched_group **sg, struct cpumask *mask)
{
int group;
-
+ #ifdef CONFIG_SCHED_SMT
cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
group = cpumask_first(mask);
+ #else
+ group = cpu;
+ #endif
if (sg)
*sg = &per_cpu(sched_group_core, group).sg;
return group;
}
- #elif defined(CONFIG_SCHED_MC)
+ #endif /* CONFIG_SCHED_MC */
+
+ /*
+ * book sched-domains:
+ */
+ #ifdef CONFIG_SCHED_BOOK
+ static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
+ static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
+
static int
- cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
- struct sched_group **sg, struct cpumask *unused)
+ cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
+ struct sched_group **sg, struct cpumask *mask)
{
+ int group = cpu;
+ #ifdef CONFIG_SCHED_MC
+ cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+ group = cpumask_first(mask);
+ #elif defined(CONFIG_SCHED_SMT)
+ cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+ group = cpumask_first(mask);
+ #endif
if (sg)
- *sg = &per_cpu(sched_group_core, cpu).sg;
- return cpu;
+ *sg = &per_cpu(sched_group_book, group).sg;
+ return group;
}
- #endif
+ #endif /* CONFIG_SCHED_BOOK */
static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
struct sched_group **sg, struct cpumask *mask)
{
int group;
- #ifdef CONFIG_SCHED_MC
+ #ifdef CONFIG_SCHED_BOOK
+ cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
+ group = cpumask_first(mask);
+ #elif defined(CONFIG_SCHED_MC)
cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
group = cpumask_first(mask);
#elif defined(CONFIG_SCHED_SMT)
#ifdef CONFIG_SCHED_MC
SD_INIT_FUNC(MC)
#endif
+ #ifdef CONFIG_SCHED_BOOK
+ SD_INIT_FUNC(BOOK)
+ #endif
static int default_relax_domain_level = -1;
free_cpumask_var(d->tmpmask); /* fall through */
case sa_send_covered:
free_cpumask_var(d->send_covered); /* fall through */
+ case sa_this_book_map:
+ free_cpumask_var(d->this_book_map); /* fall through */
case sa_this_core_map:
free_cpumask_var(d->this_core_map); /* fall through */
case sa_this_sibling_map:
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))
+ if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
return sa_this_core_map;
+ if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+ return sa_this_book_map;
if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
return sa_send_covered;
d->rd = alloc_rootdomain();
return sd;
}
+ static struct sched_domain *__build_book_sched_domain(struct s_data *d,
+ const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+ struct sched_domain *parent, int i)
+ {
+ struct sched_domain *sd = parent;
+ #ifdef CONFIG_SCHED_BOOK
+ sd = &per_cpu(book_domains, i).sd;
+ SD_INIT(sd, BOOK);
+ set_domain_attribute(sd, attr);
+ cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
+ sd->parent = parent;
+ parent->child = sd;
+ cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
+ #endif
+ return sd;
+ }
+
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)
&cpu_to_core_group,
d->send_covered, d->tmpmask);
break;
+ #endif
+ #ifdef CONFIG_SCHED_BOOK
+ case SD_LV_BOOK: /* set up book groups */
+ cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
+ if (cpu == cpumask_first(d->this_book_map))
+ init_sched_build_groups(d->this_book_map, cpu_map,
+ &cpu_to_book_group,
+ d->send_covered, d->tmpmask);
+ break;
#endif
case SD_LV_CPU: /* set up physical groups */
cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+ sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
}
for_each_cpu(i, cpu_map) {
build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+ build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
build_sched_groups(&d, SD_LV_MC, cpu_map, i);
}
init_sched_groups_power(i, sd);
}
#endif
+ #ifdef CONFIG_SCHED_BOOK
+ for_each_cpu(i, cpu_map) {
+ sd = &per_cpu(book_domains, i).sd;
+ init_sched_groups_power(i, sd);
+ }
+ #endif
for_each_cpu(i, cpu_map) {
sd = &per_cpu(phys_domains, i).sd;
sd = &per_cpu(cpu_domains, i).sd;
#elif defined(CONFIG_SCHED_MC)
sd = &per_cpu(core_domains, i).sd;
+ #elif defined(CONFIG_SCHED_BOOK)
+ sd = &per_cpu(book_domains, i).sd;
#else
sd = &per_cpu(phys_domains, i).sd;
#endif
return 1;
- err_free_rq:
+ err_free_rq:
kfree(cfs_rq);
- err:
+ err:
return 0;
}
return 1;
- err_free_rq:
+ err_free_rq:
kfree(rt_rq);
- err:
+ err:
return 0;
}
raw_spin_unlock(&rt_rq->rt_runtime_lock);
}
raw_spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock);
- unlock:
+ unlock:
read_unlock(&tasklist_lock);
mutex_unlock(&rt_constraints_mutex);
/*
* Targeted preemption latency for CPU-bound tasks:
- * (default: 5ms * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 6ms * (1 + ilog(ncpus)), units: nanoseconds)
*
* NOTE: this latency value is not the same as the concept of
* 'timeslice length' - timeslices in CFS are of variable length
/*
* Minimal preemption granularity for CPU-bound tasks:
- * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 0.75 msec * (1 + ilog(ncpus)), units: nanoseconds)
*/
unsigned int sysctl_sched_min_granularity = 750000ULL;
unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
static void update_curr(struct cfs_rq *cfs_rq)
{
struct sched_entity *curr = cfs_rq->curr;
- u64 now = rq_of(cfs_rq)->clock;
+ u64 now = rq_of(cfs_rq)->clock_task;
unsigned long delta_exec;
if (unlikely(!curr))
/*
* We are starting a new run period:
*/
- se->exec_start = rq_of(cfs_rq)->clock;
+ se->exec_start = rq_of(cfs_rq)->clock_task;
}
/**************************************************
set_task_cpu(p, this_cpu);
activate_task(this_rq, p, 0);
check_preempt_curr(this_rq, p, 0);
+
+ /* re-arm NEWIDLE balancing when moving tasks */
+ src_rq->avg_idle = this_rq->avg_idle = 2*sysctl_sched_migration_cost;
+ this_rq->idle_stamp = 0;
}
/*
* 2) too many balance attempts have failed.
*/
- tsk_cache_hot = task_hot(p, rq->clock, sd);
+ tsk_cache_hot = task_hot(p, rq->clock_task, sd);
if (!tsk_cache_hot ||
sd->nr_balance_failed > sd->cache_nice_tries) {
#ifdef CONFIG_SCHEDSTATS
unsigned long this_load;
unsigned long this_load_per_task;
unsigned long this_nr_running;
+ unsigned long this_has_capacity;
/* Statistics of the busiest group */
unsigned long max_load;
unsigned long busiest_load_per_task;
unsigned long busiest_nr_running;
unsigned long busiest_group_capacity;
+ unsigned long busiest_has_capacity;
int group_imb; /* Is there imbalance in this sd */
#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
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 ? */
+ int group_has_capacity; /* Is there extra capacity in the group? */
};
/**
u64 total, available;
total = sched_avg_period() + (rq->clock - rq->age_stamp);
- available = total - rq->rt_avg;
+
+ if (unlikely(total < rq->rt_avg)) {
+ /* Ensures that power won't end up being negative */
+ available = 0;
+ } else {
+ available = total - rq->rt_avg;
+ }
if (unlikely((s64)total < SCHED_LOAD_SCALE))
total = SCHED_LOAD_SCALE;
int local_group, const struct cpumask *cpus,
int *balance, struct sg_lb_stats *sgs)
{
- unsigned long load, max_cpu_load, min_cpu_load;
+ unsigned long load, max_cpu_load, min_cpu_load, max_nr_running;
int i;
unsigned int balance_cpu = -1, first_idle_cpu = 0;
unsigned long avg_load_per_task = 0;
/* Tally up the load of all CPUs in the group */
max_cpu_load = 0;
min_cpu_load = ~0UL;
+ max_nr_running = 0;
for_each_cpu_and(i, sched_group_cpus(group), cpus) {
struct rq *rq = cpu_rq(i);
load = target_load(i, load_idx);
} else {
load = source_load(i, load_idx);
- if (load > max_cpu_load)
+ if (load > max_cpu_load) {
max_cpu_load = load;
+ max_nr_running = rq->nr_running;
+ }
if (min_cpu_load > load)
min_cpu_load = load;
}
if (sgs->sum_nr_running)
avg_load_per_task = sgs->sum_weighted_load / sgs->sum_nr_running;
- if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task)
+ if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task && max_nr_running > 1)
sgs->group_imb = 1;
- sgs->group_capacity =
- DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
+ sgs->group_capacity = DIV_ROUND_CLOSEST(group->cpu_power, SCHED_LOAD_SCALE);
if (!sgs->group_capacity)
sgs->group_capacity = fix_small_capacity(sd, group);
+
+ if (sgs->group_capacity > sgs->sum_nr_running)
+ sgs->group_has_capacity = 1;
}
/**
/*
* In case the child domain prefers tasks go to siblings
* first, lower the sg capacity to one so that we'll try
- * and move all the excess tasks away.
+ * and move all the excess tasks away. We lower the capacity
+ * of a group only if the local group has the capacity to fit
+ * these excess tasks, i.e. nr_running < group_capacity. The
+ * extra check prevents the case where you always pull from the
+ * heaviest group when it is already under-utilized (possible
+ * with a large weight task outweighs the tasks on the system).
*/
- if (prefer_sibling)
+ if (prefer_sibling && !local_group && sds->this_has_capacity)
sgs.group_capacity = min(sgs.group_capacity, 1UL);
if (local_group) {
sds->this = sg;
sds->this_nr_running = sgs.sum_nr_running;
sds->this_load_per_task = sgs.sum_weighted_load;
+ sds->this_has_capacity = sgs.group_has_capacity;
} else if (update_sd_pick_busiest(sd, sds, sg, &sgs, this_cpu)) {
sds->max_load = sgs.avg_load;
sds->busiest = sg;
sds->busiest_nr_running = sgs.sum_nr_running;
sds->busiest_group_capacity = sgs.group_capacity;
sds->busiest_load_per_task = sgs.sum_weighted_load;
+ sds->busiest_has_capacity = sgs.group_has_capacity;
sds->group_imb = sgs.group_imb;
}
return fix_small_imbalance(sds, this_cpu, imbalance);
}
+
/******* find_busiest_group() helpers end here *********************/
/**
* 4) This group is more busy than the avg busieness at this
* sched_domain.
* 5) The imbalance is within the specified limit.
+ *
+ * Note: when doing newidle balance, if the local group has excess
+ * capacity (i.e. nr_running < group_capacity) and the busiest group
+ * does not have any capacity, we force a load balance to pull tasks
+ * to the local group. In this case, we skip past checks 3, 4 and 5.
*/
if (!(*balance))
goto ret;
if (!sds.busiest || sds.busiest_nr_running == 0)
goto out_balanced;
+ /* SD_BALANCE_NEWIDLE trumps SMP nice when underutilized */
+ if (idle == CPU_NEWLY_IDLE && sds.this_has_capacity &&
+ !sds.busiest_has_capacity)
+ goto force_balance;
+
if (sds.this_load >= sds.max_load)
goto out_balanced;
if (100 * sds.max_load <= sd->imbalance_pct * sds.this_load)
goto out_balanced;
+ force_balance:
/* Looks like there is an imbalance. Compute it */
calculate_imbalance(&sds, this_cpu, imbalance);
return sds.busiest;
if (!ld_moved) {
schedstat_inc(sd, lb_failed[idle]);
- sd->nr_balance_failed++;
+ /*
+ * Increment the failure counter only on periodic balance.
+ * We do not want newidle balance, which can be very
+ * frequent, pollute the failure counter causing
+ * excessive cache_hot migrations and active balances.
+ */
+ if (idle != CPU_NEWLY_IDLE)
+ sd->nr_balance_failed++;
if (need_active_balance(sd, sd_idle, idle, cpu_of(busiest),
this_cpu)) {
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) {
- this_rq->idle_stamp = 0;
+ if (pulled_task)
break;
- }
}
raw_spin_lock(&this_rq->lock);
update_rq_clock(rq);
- if (unlikely(task_cpu(p) != this_cpu))
+ if (unlikely(task_cpu(p) != this_cpu)) {
+ rcu_read_lock();
__set_task_cpu(p, this_cpu);
+ rcu_read_unlock();
+ }
update_curr(cfs_rq);