/*
* SCHED_OTHER wake-up granularity.
- * (default: 10 msec * (1 + ilog(ncpus)), units: nanoseconds)
+ * (default: 5 msec * (1 + ilog(ncpus)), units: nanoseconds)
*
* This option delays the preemption effects of decoupled workloads
* and reduces their over-scheduling. Synchronous workloads will still
* have immediate wakeup/sleep latencies.
*/
-unsigned int sysctl_sched_wakeup_granularity = 10000000UL;
+unsigned int sysctl_sched_wakeup_granularity = 5000000UL;
const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
+static const struct sched_class fair_sched_class;
+
/**************************************************************
* CFS operations on generic schedulable entities:
*/
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 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 (vruntime == cfs_rq->min_vruntime)
+ 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 *= P[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 /= w
+ */
+static inline unsigned long
+calc_delta_fair(unsigned long delta, struct sched_entity *se)
+{
+ if (unlikely(se->load.weight != NICE_0_LOAD))
+ delta = calc_delta_mine(delta, NICE_0_LOAD, &se->load);
+
+ return delta;
+}
+
+/*
* The idea is to set a period in which each task runs once.
*
* When there are too many tasks (sysctl_sched_nr_latency) we have to stretch
* 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)
{
- u64 slice = __sched_period(cfs_rq->nr_running);
-
- for_each_sched_entity(se) {
- cfs_rq = cfs_rq_of(se);
-
- slice *= se->load.weight;
- do_div(slice, cfs_rq->load.weight);
- }
+ unsigned long nr_running = cfs_rq->nr_running;
+ if (unlikely(!se->on_rq))
+ nr_running++;
- return slice;
+ return calc_delta_weight(__sched_period(nr_running), se);
}
/*
* We calculate the vruntime slice of a to be inserted task
*
- * vs = s/w = p/rw
+ * 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;
- unsigned long weight;
- u64 vslice;
-
- if (!se->on_rq)
- nr_running++;
-
- vslice = __sched_period(nr_running);
-
- for_each_sched_entity(se) {
- cfs_rq = cfs_rq_of(se);
-
- weight = cfs_rq->load.weight;
- if (!se->on_rq)
- weight += se->load.weight;
-
- vslice *= NICE_0_LOAD;
- do_div(vslice, weight);
- }
-
- return vslice;
+ return calc_delta_fair(sched_slice(cfs_rq, se), se);
}
/*
curr->sum_exec_runtime += delta_exec;
schedstat_add(cfs_rq, exec_clock, delta_exec);
- delta_exec_weighted = delta_exec;
- if (unlikely(curr->load.weight != NICE_0_LOAD)) {
- delta_exec_weighted = calc_delta_fair(delta_exec_weighted,
- &curr->load);
- }
+ 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)
struct task_struct *curtask = task_of(curr);
cpuacct_charge(curtask, delta_exec);
+ account_group_exec_runtime(curtask, delta_exec);
}
}
update_load_add(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
inc_cpu_load(rq_of(cfs_rq), se->load.weight);
- if (entity_is_task(se))
+ if (entity_is_task(se)) {
add_cfs_task_weight(cfs_rq, se->load.weight);
+ list_add(&se->group_node, &cfs_rq->tasks);
+ }
cfs_rq->nr_running++;
se->on_rq = 1;
- list_add(&se->group_node, &cfs_rq->tasks);
}
static void
update_load_sub(&cfs_rq->load, se->load.weight);
if (!parent_entity(se))
dec_cpu_load(rq_of(cfs_rq), se->load.weight);
- if (entity_is_task(se))
+ if (entity_is_task(se)) {
add_cfs_task_weight(cfs_rq, -se->load.weight);
+ list_del_init(&se->group_node);
+ }
cfs_rq->nr_running--;
se->on_rq = 0;
- list_del_init(&se->group_node);
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
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. */
- if (sched_feat(NEW_FAIR_SLEEPERS))
- vruntime -= sysctl_sched_latency;
+ if (sched_feat(NEW_FAIR_SLEEPERS)) {
+ unsigned long thresh = sysctl_sched_latency;
+
+ /*
+ * convert the sleeper threshold into virtual time
+ */
+ if (sched_feat(NORMALIZED_SLEEPER))
+ thresh = calc_delta_fair(thresh, se);
+
+ vruntime -= thresh;
+ }
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
__enqueue_entity(cfs_rq, se);
}
-static void update_avg(u64 *avg, u64 sample)
-{
- s64 diff = sample - *avg;
- *avg += diff >> 3;
-}
-
-static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- if (!se->last_wakeup)
- return;
+ if (cfs_rq->last == se)
+ cfs_rq->last = NULL;
- update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
- se->last_wakeup = 0;
+ if (cfs_rq->next == se)
+ cfs_rq->next = NULL;
}
static void
update_stats_dequeue(cfs_rq, se);
if (sleep) {
- update_avg_stats(cfs_rq, se);
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
#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);
}
/*
static int
wakeup_preempt_entity(struct sched_entity *curr, struct sched_entity *se);
-static struct sched_entity *
-pick_next(struct cfs_rq *cfs_rq, struct sched_entity *se)
-{
- if (!cfs_rq->next)
- return se;
-
- if (wakeup_preempt_entity(cfs_rq->next, se) != 0)
- return se;
-
- return cfs_rq->next;
-}
-
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;
}
#ifdef CONFIG_SCHED_HRTICK
static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
- int requeue = rq->curr == p;
struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
* Don't schedule slices shorter than 10000ns, that just
* doesn't make sense. Rely on vruntime for fairness.
*/
- if (!requeue)
- delta = max(10000LL, delta);
+ if (rq->curr != p)
+ delta = max_t(s64, 10000LL, delta);
- hrtick_start(rq, delta, requeue);
+ hrtick_start(rq, delta);
}
}
-#else
+
+/*
+ * called from enqueue/dequeue and updates the hrtick when the
+ * current task is from our class and nr_running is low enough
+ * to matter.
+ */
+static void hrtick_update(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+
+ if (curr->sched_class != &fair_sched_class)
+ return;
+
+ if (cfs_rq_of(&curr->se)->nr_running < sched_nr_latency)
+ hrtick_start_fair(rq, curr);
+}
+#else /* !CONFIG_SCHED_HRTICK */
static inline void
hrtick_start_fair(struct rq *rq, struct task_struct *p)
{
}
+
+static inline void hrtick_update(struct rq *rq)
+{
+}
#endif
/*
wakeup = 1;
}
- hrtick_start_fair(rq, rq->curr);
+ hrtick_update(rq);
}
/*
sleep = 1;
}
- hrtick_start_fair(rq, rq->curr);
+ hrtick_update(rq);
}
/*
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);
/*
* not idle and an idle cpu is available. The span of cpus to
* 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)
*
* Returns the CPU we should wake onto.
*/
|| ((sd->flags & SD_WAKE_IDLE_FAR)
&& !task_hot(p, task_rq(p)->clock, sd))) {
cpus_and(tmp, sd->span, p->cpus_allowed);
- for_each_cpu_mask(i, tmp) {
+ cpus_and(tmp, tmp, cpu_active_map);
+ for_each_cpu_mask_nr(i, tmp) {
if (idle_cpu(i)) {
if (i != task_cpu(p)) {
schedstat_inc(p,
}
return cpu;
}
-#else
+#else /* !ARCH_HAS_SCHED_WAKE_IDLE*/
static inline int wake_idle(int cpu, struct task_struct *p)
{
return cpu;
#ifdef CONFIG_SMP
-static const struct sched_class fair_sched_class;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/*
+ * effective_load() calculates the load change as seen from the root_task_group
+ *
+ * Adding load to a group doesn't make a group heavier, but can cause movement
+ * of group shares between cpus. Assuming the shares were perfectly aligned one
+ * can calculate the shift in shares.
+ *
+ * The problem is that perfectly aligning the shares is rather expensive, hence
+ * we try to avoid doing that too often - see update_shares(), which ratelimits
+ * this change.
+ *
+ * We compensate this by not only taking the current delta into account, but
+ * also considering the delta between when the shares were last adjusted and
+ * now.
+ *
+ * We still saw a performance dip, some tracing learned us that between
+ * cgroup:/ and cgroup:/foo balancing the number of affine wakeups increased
+ * significantly. Therefore try to bias the error in direction of failing
+ * the affine wakeup.
+ *
+ */
+static long effective_load(struct task_group *tg, int cpu,
+ long wl, long wg)
+{
+ struct sched_entity *se = tg->se[cpu];
+
+ if (!tg->parent)
+ return wl;
+
+ /*
+ * By not taking the decrease of shares on the other cpu into
+ * account our error leans towards reducing the affine wakeups.
+ */
+ if (!wl && sched_feat(ASYM_EFF_LOAD))
+ return wl;
+
+ for_each_sched_entity(se) {
+ long S, rw, s, a, b;
+ long more_w;
+
+ /*
+ * Instead of using this increment, also add the difference
+ * between when the shares were last updated and now.
+ */
+ more_w = se->my_q->load.weight - se->my_q->rq_weight;
+ wl += more_w;
+ wg += more_w;
+
+ S = se->my_q->tg->shares;
+ s = se->my_q->shares;
+ rw = se->my_q->rq_weight;
+
+ a = S*(rw + wl);
+ b = S*rw + s*wg;
+
+ wl = s*(a-b);
+
+ if (likely(b))
+ wl /= b;
+
+ /*
+ * Assume the group is already running and will
+ * thus already be accounted for in the weight.
+ *
+ * That is, moving shares between CPUs, does not
+ * alter the group weight.
+ */
+ wg = 0;
+ }
+
+ return wl;
+}
+
+#else
+
+static inline unsigned long effective_load(struct task_group *tg, int cpu,
+ unsigned long wl, unsigned long wg)
+{
+ return wl;
+}
+
+#endif
static int
-wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+wake_affine(struct sched_domain *this_sd, struct rq *this_rq,
struct task_struct *p, int prev_cpu, int this_cpu, int sync,
int idx, unsigned long load, unsigned long this_load,
unsigned int imbalance)
{
struct task_struct *curr = this_rq->curr;
+ struct task_group *tg;
unsigned long tl = this_load;
unsigned long tl_per_task;
+ unsigned long weight;
+ int balanced;
- if (!(this_sd->flags & SD_WAKE_AFFINE))
+ if (!(this_sd->flags & SD_WAKE_AFFINE) || !sched_feat(AFFINE_WAKEUPS))
return 0;
+ 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)
+ * effect of the currently running task from the load
+ * of the current CPU:
+ */
+ if (sync) {
+ tg = task_group(current);
+ weight = current->se.load.weight;
+
+ tl += effective_load(tg, this_cpu, -weight, -weight);
+ load += effective_load(tg, prev_cpu, 0, -weight);
+ }
+
+ tg = task_group(p);
+ weight = p->se.load.weight;
+
+ balanced = 100*(tl + effective_load(tg, this_cpu, weight, weight)) <=
+ imbalance*(load + effective_load(tg, prev_cpu, 0, weight));
+
/*
* If the currently running task will sleep within
* a reasonable amount of time then attract this newly
* woken task:
*/
- if (sync && curr->sched_class == &fair_sched_class) {
- if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
- p->se.avg_overlap < sysctl_sched_migration_cost)
- return 1;
- }
+ if (sync && balanced)
+ return 1;
schedstat_inc(p, se.nr_wakeups_affine_attempts);
tl_per_task = cpu_avg_load_per_task(this_cpu);
- /*
- * If sync wakeup then subtract the (maximum possible)
- * effect of the currently running task from the load
- * of the current CPU:
- */
- if (sync)
- tl -= current->se.load.weight;
-
- if ((tl <= load && tl + target_load(prev_cpu, idx) <= tl_per_task) ||
- 100*(tl + p->se.load.weight) <= imbalance*load) {
+ if (balanced || (tl <= load && tl + target_load(prev_cpu, idx) <=
+ tl_per_task)) {
/*
* This domain has SD_WAKE_AFFINE and
* p is cache cold in this domain, and
struct sched_domain *sd, *this_sd = NULL;
int prev_cpu, this_cpu, new_cpu;
unsigned long load, this_load;
- struct rq *rq, *this_rq;
+ struct rq *this_rq;
unsigned int imbalance;
int idx;
prev_cpu = task_cpu(p);
- rq = task_rq(p);
this_cpu = smp_processor_id();
this_rq = cpu_rq(this_cpu);
new_cpu = prev_cpu;
+ if (prev_cpu == this_cpu)
+ goto out;
/*
* 'this_sd' is the first domain that both
* this_cpu and prev_cpu are present in:
load = source_load(prev_cpu, idx);
this_load = target_load(this_cpu, idx);
- if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+ if (wake_affine(this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
load, this_load, imbalance))
return this_cpu;
- if (prev_cpu == this_cpu)
- goto out;
-
/*
* Start passive balancing when half the imbalance_pct
* limit is reached.
unsigned long gran = sysctl_sched_wakeup_granularity;
/*
- * More easily preempt - nice tasks, while not making
- * it harder for + nice tasks.
+ * More easily preempt - nice tasks, while not making it harder for
+ * + nice tasks.
*/
- if (unlikely(se->load.weight > NICE_0_LOAD))
- gran = calc_delta_fair(gran, &se->load);
+ if (!sched_feat(ASYM_GRAN) || se->load.weight > NICE_0_LOAD)
+ gran = calc_delta_fair(sysctl_sched_wakeup_granularity, se);
return gran;
}
{
s64 gran, vdiff = curr->vruntime - se->vruntime;
- if (vdiff < 0)
+ if (vdiff <= 0)
return -1;
gran = wakeup_gran(curr);
return 0;
}
-/* return depth at which a sched entity is present in the hierarchy */
-static inline int depth_se(struct sched_entity *se)
+static void set_last_buddy(struct sched_entity *se)
{
- int depth = 0;
-
for_each_sched_entity(se)
- depth++;
+ cfs_rq_of(se)->last = se;
+}
- return depth;
+static void set_next_buddy(struct sched_entity *se)
+{
+ 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)
+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;
- int se_depth, pse_depth;
if (unlikely(rt_prio(p->prio))) {
+ struct cfs_rq *cfs_rq = task_cfs_rq(curr);
+
update_rq_clock(rq);
update_curr(cfs_rq);
resched_task(curr);
return;
}
- se->last_wakeup = se->sum_exec_runtime;
+ 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
+ * wake up path.
+ */
+ if (test_tsk_need_resched(curr))
+ return;
/*
* Batch tasks do not preempt (their preemption is driven by
if (!sched_feat(WAKEUP_PREEMPT))
return;
- /*
- * 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.
- */
+ if (sched_feat(WAKEUP_OVERLAP) && (sync ||
+ (se->avg_overlap < sysctl_sched_migration_cost &&
+ pse->avg_overlap < sysctl_sched_migration_cost))) {
+ resched_task(curr);
+ return;
+ }
- /* First walk up until both entities are at same depth */
- se_depth = depth_se(se);
- pse_depth = depth_se(pse);
+ find_matching_se(&se, &pse);
- while (se_depth > pse_depth) {
- se_depth--;
- se = parent_entity(se);
- }
+ while (se) {
+ BUG_ON(!pse);
- while (pse_depth > se_depth) {
- pse_depth--;
- pse = parent_entity(pse);
- }
+ if (wakeup_preempt_entity(se, pse) == 1) {
+ resched_task(curr);
+ break;
+ }
- while (!is_same_group(se, pse)) {
se = parent_entity(se);
pse = parent_entity(pse);
}
-
- if (wakeup_preempt_entity(se, pse) == 1)
- resched_task(curr);
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
do {
se = pick_next_entity(cfs_rq);
+ set_next_entity(cfs_rq, se);
cfs_rq = group_cfs_rq(se);
} while (cfs_rq);
if (next == &cfs_rq->tasks)
return NULL;
- /* Skip over entities that are not tasks */
- do {
- se = list_entry(next, struct sched_entity, group_node);
- next = next->next;
- } while (next != &cfs_rq->tasks && !entity_is_task(se));
-
- if (next == &cfs_rq->tasks)
- return NULL;
-
- cfs_rq->balance_iterator = next;
-
- if (entity_is_task(se))
- p = task_of(se);
+ se = list_entry(next, struct sched_entity, group_node);
+ p = task_of(se);
+ cfs_rq->balance_iterator = next->next;
return p;
}
struct task_group *tg;
rcu_read_lock();
- list_for_each_entry(tg, &task_groups, list) {
- long imbalance;
- unsigned long this_weight, busiest_weight;
- long rem_load, max_load, moved_load;
+ update_h_load(busiest_cpu);
+
+ list_for_each_entry_rcu(tg, &task_groups, list) {
+ struct cfs_rq *busiest_cfs_rq = tg->cfs_rq[busiest_cpu];
+ unsigned long busiest_h_load = busiest_cfs_rq->h_load;
+ unsigned long busiest_weight = busiest_cfs_rq->load.weight;
+ u64 rem_load, moved_load;
/*
* empty group
*/
- if (!aggregate(tg, sd)->task_weight)
+ if (!busiest_cfs_rq->task_weight)
continue;
- rem_load = rem_load_move * aggregate(tg, sd)->rq_weight;
- rem_load /= aggregate(tg, sd)->load + 1;
+ rem_load = (u64)rem_load_move * busiest_weight;
+ rem_load = div_u64(rem_load, busiest_h_load + 1);
- this_weight = tg->cfs_rq[this_cpu]->task_weight;
- busiest_weight = tg->cfs_rq[busiest_cpu]->task_weight;
-
- imbalance = (busiest_weight - this_weight) / 2;
-
- if (imbalance < 0)
- imbalance = busiest_weight;
-
- max_load = max(rem_load, imbalance);
moved_load = __load_balance_fair(this_rq, this_cpu, busiest,
- max_load, sd, idle, all_pinned, this_best_prio,
+ rem_load, sd, idle, all_pinned, this_best_prio,
tg->cfs_rq[busiest_cpu]);
if (!moved_load)
continue;
- move_group_shares(tg, sd, busiest_cpu, this_cpu);
-
- moved_load *= aggregate(tg, sd)->load;
- moved_load /= aggregate(tg, sd)->rq_weight + 1;
+ moved_load *= busiest_h_load;
+ moved_load = div_u64(moved_load, busiest_weight + 1);
rem_load_move -= moved_load;
if (rem_load_move < 0)
return 0;
}
-#endif
+#endif /* CONFIG_SMP */
/*
* scheduler tick hitting a task of our scheduling class:
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
+ resched_task(rq->curr);
}
enqueue_task_fair(rq, p, 0);
- resched_task(rq->curr);
}
/*
if (p->prio > oldprio)
resched_task(rq->curr);
} else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
/*
if (running)
resched_task(rq->curr);
else
- check_preempt_curr(rq, p);
+ check_preempt_curr(rq, p, 0);
}
/* Account for a task changing its policy or group.
.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