return se->parent;
}
+/* return depth at which a sched entity is present in the hierarchy */
+static inline int depth_se(struct sched_entity *se)
+{
+ int depth = 0;
+
+ for_each_sched_entity(se)
+ depth++;
+
+ return depth;
+}
+
+static void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+ int se_depth, pse_depth;
+
+ /*
+ * preemption test can be made between sibling entities who are in the
+ * same cfs_rq i.e who have a common parent. Walk up the hierarchy of
+ * both tasks until we find their ancestors who are siblings of common
+ * parent.
+ */
+
+ /* First walk up until both entities are at same depth */
+ se_depth = depth_se(*se);
+ pse_depth = depth_se(*pse);
+
+ while (se_depth > pse_depth) {
+ se_depth--;
+ *se = parent_entity(*se);
+ }
+
+ while (pse_depth > se_depth) {
+ pse_depth--;
+ *pse = parent_entity(*pse);
+ }
+
+ while (!is_same_group(*se, *pse)) {
+ *se = parent_entity(*se);
+ *pse = parent_entity(*pse);
+ }
+}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
static inline struct rq *rq_of(struct cfs_rq *cfs_rq)
return NULL;
}
+static inline void
+find_matching_se(struct sched_entity **se, struct sched_entity **pse)
+{
+}
+
#endif /* CONFIG_FAIR_GROUP_SCHED */
return min_vruntime;
}
+static inline int entity_before(struct sched_entity *a,
+ struct sched_entity *b)
+{
+ return (s64)(a->vruntime - b->vruntime) < 0;
+}
+
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
return se->vruntime - cfs_rq->min_vruntime;
}
+static void update_min_vruntime(struct cfs_rq *cfs_rq)
+{
+ u64 vruntime = cfs_rq->min_vruntime;
+
+ if (cfs_rq->curr)
+ vruntime = cfs_rq->curr->vruntime;
+
+ if (cfs_rq->rb_leftmost) {
+ struct sched_entity *se = rb_entry(cfs_rq->rb_leftmost,
+ struct sched_entity,
+ run_node);
+
+ if (!cfs_rq->curr)
+ vruntime = se->vruntime;
+ else
+ vruntime = min_vruntime(vruntime, se->vruntime);
+ }
+
+ cfs_rq->min_vruntime = max_vruntime(cfs_rq->min_vruntime, vruntime);
+}
+
/*
* Enqueue an entity into the rb-tree:
*/
* Maintain a cache of leftmost tree entries (it is frequently
* used):
*/
- if (leftmost) {
+ if (leftmost)
cfs_rq->rb_leftmost = &se->run_node;
- /*
- * maintain cfs_rq->min_vruntime to be a monotonic increasing
- * value tracking the leftmost vruntime in the tree.
- */
- cfs_rq->min_vruntime =
- max_vruntime(cfs_rq->min_vruntime, se->vruntime);
- }
rb_link_node(&se->run_node, parent, link);
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
{
if (cfs_rq->rb_leftmost == &se->run_node) {
struct rb_node *next_node;
- struct sched_entity *next;
next_node = rb_next(&se->run_node);
cfs_rq->rb_leftmost = next_node;
-
- if (next_node) {
- next = rb_entry(next_node,
- struct sched_entity, run_node);
- cfs_rq->min_vruntime =
- max_vruntime(cfs_rq->min_vruntime,
- next->vruntime);
- }
}
- if (cfs_rq->next == se)
- cfs_rq->next = NULL;
-
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
}
-static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
-{
- return cfs_rq->rb_leftmost;
-}
-
static struct sched_entity *__pick_next_entity(struct cfs_rq *cfs_rq)
{
- return rb_entry(first_fair(cfs_rq), struct sched_entity, run_node);
+ struct rb_node *left = cfs_rq->rb_leftmost;
+
+ if (!left)
+ return NULL;
+
+ return rb_entry(left, struct sched_entity, run_node);
}
-static inline struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
+static struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *last = rb_last(&cfs_rq->tasks_timeline);
#endif
/*
- * delta *= w / rw
- */
-static inline unsigned long
-calc_delta_weight(unsigned long delta, struct sched_entity *se)
-{
- for_each_sched_entity(se) {
- delta = calc_delta_mine(delta,
- se->load.weight, &cfs_rq_of(se)->load);
- }
-
- return delta;
-}
-
-/*
- * delta *= rw / w
+ * delta /= w
*/
static inline unsigned long
calc_delta_fair(unsigned long delta, struct sched_entity *se)
{
- for_each_sched_entity(se) {
- delta = calc_delta_mine(delta,
- cfs_rq_of(se)->load.weight, &se->load);
- }
+ if (unlikely(se->load.weight != NICE_0_LOAD))
+ delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
return delta;
}
* We calculate the wall-time slice from the period by taking a part
* proportional to the weight.
*
- * s = p*w/rw
+ * s = p*P[w/rw]
*/
static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- return calc_delta_weight(__sched_period(cfs_rq->nr_running), se);
+ u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
+
+ for_each_sched_entity(se) {
+ struct load_weight *load;
+ struct load_weight lw;
+
+ cfs_rq = cfs_rq_of(se);
+ load = &cfs_rq->load;
+
+ if (unlikely(!se->on_rq)) {
+ lw = cfs_rq->load;
+
+ update_load_add(&lw, se->load.weight);
+ load = &lw;
+ }
+ slice = calc_delta_mine(slice, se->load.weight, load);
+ }
+ return slice;
}
/*
* We calculate the vruntime slice of a to be inserted task
*
- * vs = s*rw/w = p
+ * vs = s/w
*/
-static u64 sched_vslice_add(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static u64 sched_vslice(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- unsigned long nr_running = cfs_rq->nr_running;
-
- if (!se->on_rq)
- nr_running++;
-
- return __sched_period(nr_running);
+ return calc_delta_fair(sched_slice(cfs_rq, se), se);
}
/*
schedstat_add(cfs_rq, exec_clock, delta_exec);
delta_exec_weighted = calc_delta_fair(delta_exec, curr);
curr->vruntime += delta_exec_weighted;
+ update_min_vruntime(cfs_rq);
}
static void update_curr(struct cfs_rq *cfs_rq)
* overflow on 32 bits):
*/
delta_exec = (unsigned long)(now - curr->exec_start);
+ if (!delta_exec)
+ return;
__update_curr(cfs_rq, curr, delta_exec);
curr->exec_start = now;
struct task_struct *curtask = task_of(curr);
cpuacct_charge(curtask, delta_exec);
+ account_group_exec_runtime(curtask, delta_exec);
}
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
#ifdef CONFIG_SCHEDSTATS
+ struct task_struct *tsk = NULL;
+
+ if (entity_is_task(se))
+ tsk = task_of(se);
+
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
- struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
se->sleep_start = 0;
se->sum_sleep_runtime += delta;
- account_scheduler_latency(tsk, delta >> 10, 1);
+ if (tsk)
+ account_scheduler_latency(tsk, delta >> 10, 1);
}
if (se->block_start) {
u64 delta = rq_of(cfs_rq)->clock - se->block_start;
- struct task_struct *tsk = task_of(se);
if ((s64)delta < 0)
delta = 0;
se->block_start = 0;
se->sum_sleep_runtime += delta;
- /*
- * Blocking time is in units of nanosecs, so shift by 20 to
- * get a milliseconds-range estimation of the amount of
- * time that the task spent sleeping:
- */
- if (unlikely(prof_on == SLEEP_PROFILING)) {
-
- profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
- delta >> 20);
+ if (tsk) {
+ /*
+ * Blocking time is in units of nanosecs, so shift by
+ * 20 to get a milliseconds-range estimation of the
+ * amount of time that the task spent sleeping:
+ */
+ if (unlikely(prof_on == SLEEP_PROFILING)) {
+ profile_hits(SLEEP_PROFILING,
+ (void *)get_wchan(tsk),
+ delta >> 20);
+ }
+ account_scheduler_latency(tsk, delta >> 10, 0);
}
- account_scheduler_latency(tsk, delta >> 10, 0);
}
#endif
}
static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
- u64 vruntime;
-
- if (first_fair(cfs_rq)) {
- vruntime = min_vruntime(cfs_rq->min_vruntime,
- __pick_next_entity(cfs_rq)->vruntime);
- } else
- vruntime = cfs_rq->min_vruntime;
+ u64 vruntime = cfs_rq->min_vruntime;
/*
* The 'current' period is already promised to the current tasks,
* stays open at the end.
*/
if (initial && sched_feat(START_DEBIT))
- vruntime += sched_vslice_add(cfs_rq, se);
+ vruntime += sched_vslice(cfs_rq, se);
if (!initial) {
/* sleeps upto a single latency don't count. */
unsigned long thresh = sysctl_sched_latency;
/*
- * convert the sleeper threshold into virtual time
+ * Convert the sleeper threshold into virtual time.
+ * SCHED_IDLE is a special sub-class. We care about
+ * fairness only relative to other SCHED_IDLE tasks,
+ * all of which have the same weight.
*/
- if (sched_feat(NORMALIZED_SLEEPER))
+ if (sched_feat(NORMALIZED_SLEEPER) &&
+ (!entity_is_task(se) ||
+ task_of(se)->policy != SCHED_IDLE))
thresh = calc_delta_fair(thresh, se);
vruntime -= thresh;
__enqueue_entity(cfs_rq, se);
}
+static void __clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (cfs_rq->last == se)
+ cfs_rq->last = NULL;
+
+ if (cfs_rq->next == se)
+ cfs_rq->next = NULL;
+}
+
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ for_each_sched_entity(se)
+ __clear_buddies(cfs_rq_of(se), se);
+}
+
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
#endif
}
+ clear_buddies(cfs_rq, se);
+
if (se != cfs_rq->curr)
__dequeue_entity(cfs_rq, se);
account_entity_dequeue(cfs_rq, se);
+ update_min_vruntime(cfs_rq);
}
/*
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
- if (delta_exec > ideal_runtime)
+ if (delta_exec > ideal_runtime) {
resched_task(rq_of(cfs_rq)->curr);
+ /*
+ * The current task ran long enough, ensure it doesn't get
+ * re-elected due to buddy favours.
+ */
+ clear_buddies(cfs_rq, curr);
+ }
}
static void
se->prev_sum_exec_runtime = se->sum_exec_runtime;
}
-static struct sched_entity *
-pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- struct rq *rq = rq_of(cfs_rq);
- u64 pair_slice = rq->clock - cfs_rq->pair_start;
-
- if (!cfs_rq->next || pair_slice > sysctl_sched_min_granularity) {
- cfs_rq->pair_start = rq->clock;
- return se;
- }
-
- return cfs_rq->next;
-}
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
static struct sched_entity *pick_next_entity(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = NULL;
+ struct sched_entity *se = __pick_next_entity(cfs_rq);
- if (first_fair(cfs_rq)) {
- se = __pick_next_entity(cfs_rq);
- se = pick_next(cfs_rq, se);
- set_next_entity(cfs_rq, se);
- }
+ if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, se) < 1)
+ return cfs_rq->next;
+
+ if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, se) < 1)
+ return cfs_rq->last;
return se;
}
if (unlikely(cfs_rq->nr_running == 1))
return;
+ clear_buddies(cfs_rq, se);
+
if (likely(!sysctl_sched_compat_yield) && curr->policy != SCHED_BATCH) {
update_rq_clock(rq);
/*
/*
* Already in the rightmost position?
*/
- if (unlikely(!rightmost || rightmost->vruntime < se->vruntime))
+ if (unlikely(!rightmost || entity_before(rightmost, se)))
return;
/*
* search starts with cpus closest then further out as needed,
* so we always favor a closer, idle cpu.
* Domains may include CPUs that are not usable for migration,
- * hence we need to mask them out (cpu_active_map)
+ * hence we need to mask them out (cpu_active_mask)
*
* Returns the CPU we should wake onto.
*/
#if defined(ARCH_HAS_SCHED_WAKE_IDLE)
static int wake_idle(int cpu, struct task_struct *p)
{
- cpumask_t tmp;
struct sched_domain *sd;
int i;
+ unsigned int chosen_wakeup_cpu;
+ int this_cpu;
+
+ /*
+ * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
+ * are idle and this is not a kernel thread and this task's affinity
+ * allows it to be moved to preferred cpu, then just move!
+ */
+
+ this_cpu = smp_processor_id();
+ chosen_wakeup_cpu =
+ cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
+
+ if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
+ idle_cpu(cpu) && idle_cpu(this_cpu) &&
+ p->mm && !(p->flags & PF_KTHREAD) &&
+ cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))
+ return chosen_wakeup_cpu;
/*
* If it is idle, then it is the best cpu to run this task.
if ((sd->flags & SD_WAKE_IDLE)
|| ((sd->flags & SD_WAKE_IDLE_FAR)
&& !task_hot(p, task_rq(p)->clock, sd))) {
- cpus_and(tmp, sd->span, p->cpus_allowed);
- cpus_and(tmp, tmp, cpu_active_map);
- for_each_cpu_mask_nr(i, tmp) {
- if (idle_cpu(i)) {
+ for_each_cpu_and(i, sched_domain_span(sd),
+ &p->cpus_allowed) {
+ if (cpu_active(i) && idle_cpu(i)) {
if (i != task_cpu(p)) {
schedstat_inc(p,
se.nr_wakeups_idle);
if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
return 0;
- if (!sync && sched_feat(SYNC_WAKEUPS) &&
- curr->se.avg_overlap < sysctl_sched_migration_cost &&
- p->se.avg_overlap < sysctl_sched_migration_cost)
- sync = 1;
+ if (sync && (curr->se.avg_overlap > sysctl_sched_migration_cost ||
+ p->se.avg_overlap > sysctl_sched_migration_cost))
+ sync = 0;
/*
* If sync wakeup then subtract the (maximum possible)
* this_cpu and prev_cpu are present in:
*/
for_each_domain(this_cpu, sd) {
- if (cpu_isset(prev_cpu, sd->span)) {
+ if (cpumask_test_cpu(prev_cpu, sched_domain_span(sd))) {
this_sd = sd;
break;
}
}
- if (unlikely(!cpu_isset(this_cpu, p->cpus_allowed)))
+ if (unlikely(!cpumask_test_cpu(this_cpu, &p->cpus_allowed)))
goto out;
/*
}
#endif /* CONFIG_SMP */
-static unsigned long wakeup_gran(struct sched_entity *se)
+/*
+ * Adaptive granularity
+ *
+ * se->avg_wakeup gives the average time a task runs until it does a wakeup,
+ * with the limit of wakeup_gran -- when it never does a wakeup.
+ *
+ * So the smaller avg_wakeup is the faster we want this task to preempt,
+ * but we don't want to treat the preemptee unfairly and therefore allow it
+ * to run for at least the amount of time we'd like to run.
+ *
+ * NOTE: we use 2*avg_wakeup to increase the probability of actually doing one
+ *
+ * NOTE: we use *nr_running to scale with load, this nicely matches the
+ * degrading latency on load.
+ */
+static unsigned long
+adaptive_gran(struct sched_entity *curr, struct sched_entity *se)
+{
+ u64 this_run = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
+ u64 expected_wakeup = 2*se->avg_wakeup * cfs_rq_of(se)->nr_running;
+ u64 gran = 0;
+
+ if (this_run < expected_wakeup)
+ gran = expected_wakeup - this_run;
+
+ return min_t(s64, gran, sysctl_sched_wakeup_granularity);
+}
+
+static unsigned long
+wakeup_gran(struct sched_entity *curr, struct sched_entity *se)
{
unsigned long gran = sysctl_sched_wakeup_granularity;
+ if (cfs_rq_of(curr)->curr && sched_feat(ADAPTIVE_GRAN))
+ gran = adaptive_gran(curr, se);
+
/*
- * More easily preempt - nice tasks, while not making it harder for
- * + nice tasks.
+ * Since its curr running now, convert the gran from real-time
+ * to virtual-time in his units.
*/
- if (sched_feat(ASYM_GRAN))
- gran = calc_delta_mine(gran, NICE_0_LOAD, &se->load);
+ if (sched_feat(ASYM_GRAN)) {
+ /*
+ * By using 'se' instead of 'curr' we penalize light tasks, so
+ * they get preempted easier. That is, if 'se' < 'curr' then
+ * the resulting gran will be larger, therefore penalizing the
+ * lighter, if otoh 'se' > 'curr' then the resulting gran will
+ * be smaller, again penalizing the lighter task.
+ *
+ * This is especially important for buddies when the leftmost
+ * task is higher priority than the buddy.
+ */
+ if (unlikely(se->load.weight != NICE_0_LOAD))
+ gran = calc_delta_fair(gran, se);
+ } else {
+ if (unlikely(curr->load.weight != NICE_0_LOAD))
+ gran = calc_delta_fair(gran, curr);
+ }
return gran;
}
/*
+ * Should 'se' preempt 'curr'.
+ *
+ * |s1
+ * |s2
+ * |s3
+ * g
+ * |<--->|c
+ *
+ * w(c, s1) = -1
+ * w(c, s2) = 0
+ * w(c, s3) = 1
+ *
+ */
+static int
+wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se)
+{
+ s64 gran, vdiff = curr->vruntime - se->vruntime;
+
+ if (vdiff <= 0)
+ return -1;
+
+ gran = wakeup_gran(curr, se);
+ if (vdiff > gran)
+ return 1;
+
+ return 0;
+}
+
+static void set_last_buddy(struct sched_entity *se)
+{
+ if (likely(task_of(se)->policy != SCHED_IDLE)) {
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->last = se;
+ }
+}
+
+static void set_next_buddy(struct sched_entity *se)
+{
+ if (likely(task_of(se)->policy != SCHED_IDLE)) {
+ for_each_sched_entity(se)
+ cfs_rq_of(se)->next = se;
+ }
+}
+
+/*
* Preempt the current task with a newly woken task if needed:
*/
static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int sync)
{
struct task_struct *curr = rq->curr;
- struct cfs_rq *cfs_rq = task_cfs_rq(curr);
struct sched_entity *se = &curr->se, *pse = &p->se;
- s64 delta_exec;
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+
+ update_curr(cfs_rq);
if (unlikely(rt_prio(p->prio))) {
- update_rq_clock(rq);
- update_curr(cfs_rq);
resched_task(curr);
return;
}
+ if (unlikely(p->sched_class != &fair_sched_class))
+ return;
+
if (unlikely(se == pse))
return;
- cfs_rq_of(pse)->next = pse;
+ /*
+ * Only set the backward buddy when the current task is still on the
+ * rq. This can happen when a wakeup gets interleaved with schedule on
+ * the ->pre_schedule() or idle_balance() point, either of which can
+ * drop the rq lock.
+ *
+ * Also, during early boot the idle thread is in the fair class, for
+ * obvious reasons its a bad idea to schedule back to the idle thread.
+ */
+ if (sched_feat(LAST_BUDDY) && likely(se->on_rq && curr != rq->idle))
+ set_last_buddy(se);
+ set_next_buddy(pse);
/*
* We can come here with TIF_NEED_RESCHED already set from new task
return;
/*
- * Batch tasks do not preempt (their preemption is driven by
+ * Batch and idle tasks do not preempt (their preemption is driven by
* the tick):
*/
- if (unlikely(p->policy == SCHED_BATCH))
+ if (unlikely(p->policy != SCHED_NORMAL))
return;
+ /* Idle tasks are by definition preempted by everybody. */
+ if (unlikely(curr->policy == SCHED_IDLE)) {
+ resched_task(curr);
+ return;
+ }
+
if (!sched_feat(WAKEUP_PREEMPT))
return;
return;
}
- delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
- if (delta_exec > wakeup_gran(pse))
+ find_matching_se(&se, &pse);
+
+ BUG_ON(!pse);
+
+ if (wakeup_preempt_entity(se, pse) == 1)
resched_task(curr);
}
do {
se = pick_next_entity(cfs_rq);
+ /*
+ * If se was a buddy, clear it so that it will have to earn
+ * the favour again.
+ */
+ __clear_buddies(cfs_rq, se);
+ set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
}
}
-#define swap(a, b) do { typeof(a) tmp = (a); (a) = (b); (b) = tmp; } while (0)
-
/*
* Share the fairness runtime between parent and child, thus the
* total amount of pressure for CPU stays equal - new tasks
/* 'curr' will be NULL if the child belongs to a different group */
if (sysctl_sched_child_runs_first && this_cpu == task_cpu(p) &&
- curr && curr->vruntime < se->vruntime) {
+ curr && entity_before(curr, se)) {
/*
* Upon rescheduling, sched_class::put_prev_task() will place
* 'current' within the tree based on its new key value.
.enqueue_task = enqueue_task_fair,
.dequeue_task = dequeue_task_fair,
.yield_task = yield_task_fair,
-#ifdef CONFIG_SMP
- .select_task_rq = select_task_rq_fair,
-#endif /* CONFIG_SMP */
.check_preempt_curr = check_preempt_wakeup,
.put_prev_task = put_prev_task_fair,
#ifdef CONFIG_SMP
+ .select_task_rq = select_task_rq_fair,
+
.load_balance = load_balance_fair,
.move_one_task = move_one_task_fair,
#endif