* Minimal preemption granularity for CPU-bound tasks:
* (default: 2 msec, units: nanoseconds)
*/
-unsigned int sysctl_sched_min_granularity __read_mostly = 2000000ULL;
+const_debug unsigned int sysctl_sched_nr_latency = 20;
/*
* sys_sched_yield() compat mode
*/
const_debug unsigned int sysctl_sched_wakeup_granularity = 2000000UL;
-unsigned int sysctl_sched_runtime_limit __read_mostly;
-
extern struct sched_class fair_sched_class;
/**************************************************************
* Scheduling class tree data structure manipulation methods:
*/
-static inline void
-set_leftmost(struct cfs_rq *cfs_rq, struct rb_node *leftmost)
+static inline u64
+max_vruntime(u64 min_vruntime, u64 vruntime)
{
- struct sched_entity *se;
+ s64 delta = (s64)(vruntime - min_vruntime);
+ if (delta > 0)
+ min_vruntime = vruntime;
- cfs_rq->rb_leftmost = leftmost;
- if (leftmost) {
- se = rb_entry(leftmost, struct sched_entity, run_node);
- if ((se->vruntime > cfs_rq->min_vruntime) ||
- (cfs_rq->min_vruntime > (1ULL << 61) &&
- se->vruntime < (1ULL << 50)))
- cfs_rq->min_vruntime = se->vruntime;
- }
+ return min_vruntime;
+}
+
+static inline u64
+min_vruntime(u64 min_vruntime, u64 vruntime)
+{
+ s64 delta = (s64)(vruntime - min_vruntime);
+ if (delta < 0)
+ min_vruntime = vruntime;
+
+ return min_vruntime;
}
-s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static inline s64
+entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- return se->fair_key - cfs_rq->min_vruntime;
+ return se->vruntime - cfs_rq->min_vruntime;
}
/*
* used):
*/
if (leftmost)
- set_leftmost(cfs_rq, &se->run_node);
+ cfs_rq->rb_leftmost = &se->run_node;
rb_link_node(&se->run_node, parent, link);
rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
- update_load_add(&cfs_rq->load, se->load.weight);
- cfs_rq->nr_running++;
- se->on_rq = 1;
-
- schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
}
static void
__dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
if (cfs_rq->rb_leftmost == &se->run_node)
- set_leftmost(cfs_rq, rb_next(&se->run_node));
+ cfs_rq->rb_leftmost = rb_next(&se->run_node);
rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
- update_load_sub(&cfs_rq->load, se->load.weight);
- cfs_rq->nr_running--;
- se->on_rq = 0;
-
- schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
}
static inline struct rb_node *first_fair(struct cfs_rq *cfs_rq)
static u64 __sched_period(unsigned long nr_running)
{
u64 period = sysctl_sched_latency;
- unsigned long nr_latency =
- sysctl_sched_latency / sysctl_sched_min_granularity;
+ unsigned long nr_latency = sysctl_sched_nr_latency;
if (unlikely(nr_running > nr_latency)) {
period *= nr_running;
return period;
}
-static inline void
-limit_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static u64 __sched_vslice(unsigned long nr_running)
{
- long limit = sysctl_sched_runtime_limit;
+ unsigned long period = sysctl_sched_latency;
+ unsigned long nr_latency = sysctl_sched_nr_latency;
- /*
- * Niced tasks have the same history dynamic range as
- * non-niced tasks:
- */
- if (unlikely(se->wait_runtime > limit)) {
- se->wait_runtime = limit;
- schedstat_inc(se, wait_runtime_overruns);
- schedstat_inc(cfs_rq, wait_runtime_overruns);
- }
- if (unlikely(se->wait_runtime < -limit)) {
- se->wait_runtime = -limit;
- schedstat_inc(se, wait_runtime_underruns);
- schedstat_inc(cfs_rq, wait_runtime_underruns);
- }
-}
+ if (unlikely(nr_running > nr_latency))
+ nr_running = nr_latency;
-static inline void
-__add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
-{
- se->wait_runtime += delta;
- schedstat_add(se, sum_wait_runtime, delta);
- limit_wait_runtime(cfs_rq, se);
-}
+ period /= nr_running;
-static void
-add_wait_runtime(struct cfs_rq *cfs_rq, struct sched_entity *se, long delta)
-{
- schedstat_add(cfs_rq, wait_runtime, -se->wait_runtime);
- __add_wait_runtime(cfs_rq, se, delta);
- schedstat_add(cfs_rq, wait_runtime, se->wait_runtime);
+ return (u64)period;
}
/*
__update_curr(struct cfs_rq *cfs_rq, struct sched_entity *curr,
unsigned long delta_exec)
{
- unsigned long delta, delta_fair, delta_mine, delta_exec_weighted;
- struct load_weight *lw = &cfs_rq->load;
- unsigned long load = lw->weight;
+ unsigned long delta_exec_weighted;
+ u64 vruntime;
schedstat_set(curr->exec_max, max((u64)delta_exec, curr->exec_max));
curr->sum_exec_runtime += delta_exec;
- cfs_rq->exec_clock += 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->vruntime += delta_exec_weighted;
- if (!sched_feat(FAIR_SLEEPERS))
- return;
-
- if (unlikely(!load))
- return;
-
- delta_fair = calc_delta_fair(delta_exec, lw);
- delta_mine = calc_delta_mine(delta_exec, curr->load.weight, lw);
-
- if (cfs_rq->sleeper_bonus > sysctl_sched_min_granularity) {
- delta = min((u64)delta_mine, cfs_rq->sleeper_bonus);
- delta = min(delta, (unsigned long)(
- (long)sysctl_sched_runtime_limit - curr->wait_runtime));
- cfs_rq->sleeper_bonus -= delta;
- delta_mine -= delta;
- }
-
- cfs_rq->fair_clock += delta_fair;
/*
- * We executed delta_exec amount of time on the CPU,
- * but we were only entitled to delta_mine amount of
- * time during that period (if nr_running == 1 then
- * the two values are equal)
- * [Note: delta_mine - delta_exec is negative]:
+ * maintain cfs_rq->min_vruntime to be a monotonic increasing
+ * value tracking the leftmost vruntime in the tree.
*/
- add_wait_runtime(cfs_rq, curr, delta_mine - delta_exec);
+ if (first_fair(cfs_rq)) {
+ vruntime = min_vruntime(curr->vruntime,
+ __pick_next_entity(cfs_rq)->vruntime);
+ } else
+ vruntime = curr->vruntime;
+
+ cfs_rq->min_vruntime =
+ max_vruntime(cfs_rq->min_vruntime, vruntime);
}
static void update_curr(struct cfs_rq *cfs_rq)
static inline void
update_stats_wait_start(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- se->wait_start_fair = cfs_rq->fair_clock;
schedstat_set(se->wait_start, rq_of(cfs_rq)->clock);
}
*/
if (se != cfs_rq->curr)
update_stats_wait_start(cfs_rq, se);
- /*
- * Update the key:
- */
- se->fair_key = se->vruntime;
-}
-
-/*
- * Note: must be called with a freshly updated rq->fair_clock.
- */
-static inline void
-__update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se,
- unsigned long delta_fair)
-{
- schedstat_set(se->wait_max, max(se->wait_max,
- rq_of(cfs_rq)->clock - se->wait_start));
-
- delta_fair = calc_weighted(delta_fair, se);
-
- add_wait_runtime(cfs_rq, se, delta_fair);
}
static void
update_stats_wait_end(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- unsigned long delta_fair;
-
- if (unlikely(!se->wait_start_fair))
- return;
-
- delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
- (u64)(cfs_rq->fair_clock - se->wait_start_fair));
-
- __update_stats_wait_end(cfs_rq, se, delta_fair);
-
- se->wait_start_fair = 0;
+ schedstat_set(se->wait_max, max(se->wait_max,
+ rq_of(cfs_rq)->clock - se->wait_start));
schedstat_set(se->wait_start, 0);
}
* Scheduling class queueing methods:
*/
-static void __enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se,
- unsigned long delta_fair)
+static void
+account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- unsigned long load = cfs_rq->load.weight;
- long prev_runtime;
-
- /*
- * Do not boost sleepers if there's too much bonus 'in flight'
- * already:
- */
- if (unlikely(cfs_rq->sleeper_bonus > sysctl_sched_runtime_limit))
- return;
-
- if (sched_feat(SLEEPER_LOAD_AVG))
- load = rq_of(cfs_rq)->cpu_load[2];
-
- /*
- * Fix up delta_fair with the effect of us running
- * during the whole sleep period:
- */
- if (sched_feat(SLEEPER_AVG))
- delta_fair = div64_likely32((u64)delta_fair * load,
- load + se->load.weight);
-
- delta_fair = calc_weighted(delta_fair, se);
-
- prev_runtime = se->wait_runtime;
- __add_wait_runtime(cfs_rq, se, delta_fair);
- delta_fair = se->wait_runtime - prev_runtime;
+ update_load_add(&cfs_rq->load, se->load.weight);
+ cfs_rq->nr_running++;
+ se->on_rq = 1;
+}
- /*
- * Track the amount of bonus we've given to sleepers:
- */
- cfs_rq->sleeper_bonus += delta_fair;
+static void
+account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ update_load_sub(&cfs_rq->load, se->load.weight);
+ cfs_rq->nr_running--;
+ se->on_rq = 0;
}
static void enqueue_sleeper(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- struct task_struct *tsk = task_of(se);
- unsigned long delta_fair;
-
- if ((entity_is_task(se) && tsk->policy == SCHED_BATCH) ||
- !sched_feat(FAIR_SLEEPERS))
- return;
-
- delta_fair = (unsigned long)min((u64)(2*sysctl_sched_runtime_limit),
- (u64)(cfs_rq->fair_clock - se->sleep_start_fair));
-
- __enqueue_sleeper(cfs_rq, se, delta_fair);
-
- se->sleep_start_fair = 0;
-
#ifdef CONFIG_SCHEDSTATS
if (se->sleep_start) {
u64 delta = rq_of(cfs_rq)->clock - se->sleep_start;
* time that the task spent sleeping:
*/
if (unlikely(prof_on == SLEEP_PROFILING)) {
+ struct task_struct *tsk = task_of(se);
+
profile_hits(SLEEP_PROFILING, (void *)get_wchan(tsk),
delta >> 20);
}
#endif
}
+static void check_spread(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+#ifdef CONFIG_SCHED_DEBUG
+ s64 d = se->vruntime - cfs_rq->min_vruntime;
+
+ if (d < 0)
+ d = -d;
+
+ if (d > 3*sysctl_sched_latency)
+ schedstat_inc(cfs_rq, nr_spread_over);
+#endif
+}
+
static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
- u64 min_runtime, latency;
+ u64 vruntime;
- min_runtime = cfs_rq->min_vruntime;
+ vruntime = cfs_rq->min_vruntime;
if (sched_feat(USE_TREE_AVG)) {
struct sched_entity *last = __pick_last_entity(cfs_rq);
if (last) {
- min_runtime = __pick_next_entity(cfs_rq)->vruntime;
- min_runtime += last->vruntime;
- min_runtime >>= 1;
+ vruntime += last->vruntime;
+ vruntime >>= 1;
}
- } else if (sched_feat(APPROX_AVG))
- min_runtime += sysctl_sched_latency/2;
+ } else if (sched_feat(APPROX_AVG) && cfs_rq->nr_running)
+ vruntime += __sched_vslice(cfs_rq->nr_running)/2;
if (initial && sched_feat(START_DEBIT))
- min_runtime += sched_slice(cfs_rq, se);
-
- if (!initial && sched_feat(NEW_FAIR_SLEEPERS)) {
- latency = sysctl_sched_latency;
- if (min_runtime > latency)
- min_runtime -= latency;
- else
- min_runtime = 0;
+ vruntime += __sched_vslice(cfs_rq->nr_running + 1);
+
+ if (!initial) {
+ if (sched_feat(NEW_FAIR_SLEEPERS))
+ vruntime -= sysctl_sched_latency;
+
+ vruntime = max_t(s64, vruntime, se->vruntime);
}
- se->vruntime = max(se->vruntime, min_runtime);
+ se->vruntime = vruntime;
+
}
static void
}
update_stats_enqueue(cfs_rq, se);
- __enqueue_entity(cfs_rq, se);
+ check_spread(cfs_rq, se);
+ if (se != cfs_rq->curr)
+ __enqueue_entity(cfs_rq, se);
+ account_entity_enqueue(cfs_rq, se);
}
static void
{
update_stats_dequeue(cfs_rq, se);
if (sleep) {
- se->sleep_start_fair = cfs_rq->fair_clock;
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
}
#endif
}
- __dequeue_entity(cfs_rq, se);
+
+ if (se != cfs_rq->curr)
+ __dequeue_entity(cfs_rq, se);
+ account_entity_dequeue(cfs_rq, se);
}
/*
resched_task(rq_of(cfs_rq)->curr);
}
-static inline void
+static void
set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
- /*
- * Any task has to be enqueued before it get to execute on
- * a CPU. So account for the time it spent waiting on the
- * runqueue. (note, here we rely on pick_next_task() having
- * done a put_prev_task_fair() shortly before this, which
- * updated rq->fair_clock - used by update_stats_wait_end())
- */
- update_stats_wait_end(cfs_rq, se);
+ /* 'current' is not kept within the tree. */
+ if (se->on_rq) {
+ /*
+ * Any task has to be enqueued before it get to execute on
+ * a CPU. So account for the time it spent waiting on the
+ * runqueue.
+ */
+ update_stats_wait_end(cfs_rq, se);
+ __dequeue_entity(cfs_rq, se);
+ }
+
update_stats_curr_start(cfs_rq, se);
cfs_rq->curr = se;
#ifdef CONFIG_SCHEDSTATS
* least twice that of our own weight (i.e. dont track it
* when there are only lesser-weight tasks around):
*/
- if (rq_of(cfs_rq)->ls.load.weight >= 2*se->load.weight) {
+ if (rq_of(cfs_rq)->load.weight >= 2*se->load.weight) {
se->slice_max = max(se->slice_max,
se->sum_exec_runtime - se->prev_sum_exec_runtime);
}
update_stats_curr_end(cfs_rq, prev);
- if (prev->on_rq)
+ check_spread(cfs_rq, prev);
+ if (prev->on_rq) {
update_stats_wait_start(cfs_rq, prev);
+ /* Put 'current' back into the tree. */
+ __enqueue_entity(cfs_rq, prev);
+ }
cfs_rq->curr = NULL;
}
static void entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
/*
- * Dequeue and enqueue the task to update its
- * position within the tree:
+ * Update run-time statistics of the 'current'.
*/
- dequeue_entity(cfs_rq, curr, 0);
- enqueue_entity(cfs_rq, curr, 0);
+ update_curr(cfs_rq);
if (cfs_rq->nr_running > 1)
check_preempt_tick(cfs_rq, curr);
*/
static inline struct cfs_rq *cpu_cfs_rq(struct cfs_rq *cfs_rq, int this_cpu)
{
- /* A later patch will take group into account */
- return &cpu_rq(this_cpu)->cfs;
+ return cfs_rq->tg->cfs_rq[this_cpu];
}
/* Iterate thr' all leaf cfs_rq's on a runqueue */
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
list_for_each_entry(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
-/* Do the two (enqueued) tasks belong to the same group ? */
-static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
+/* Do the two (enqueued) entities belong to the same group ? */
+static inline int
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
- if (curr->se.cfs_rq == p->se.cfs_rq)
+ if (se->cfs_rq == pse->cfs_rq)
return 1;
return 0;
}
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+ return se->parent;
+}
+
#else /* CONFIG_FAIR_GROUP_SCHED */
#define for_each_sched_entity(se) \
#define for_each_leaf_cfs_rq(rq, cfs_rq) \
for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
-static inline int is_same_group(struct task_struct *curr, struct task_struct *p)
+static inline int
+is_same_group(struct sched_entity *se, struct sched_entity *pse)
{
return 1;
}
+static inline struct sched_entity *parent_entity(struct sched_entity *se)
+{
+ return NULL;
+}
+
#endif /* CONFIG_FAIR_GROUP_SCHED */
/*
break;
cfs_rq = cfs_rq_of(se);
enqueue_entity(cfs_rq, se, wakeup);
+ wakeup = 1;
}
}
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight)
break;
+ sleep = 1;
}
}
*
* If compat_yield is turned on then we requeue to the end of the tree.
*/
-static void yield_task_fair(struct rq *rq, struct task_struct *p)
+static void yield_task_fair(struct rq *rq)
{
- struct cfs_rq *cfs_rq = task_cfs_rq(p);
- struct rb_node **link = &cfs_rq->tasks_timeline.rb_node;
- struct sched_entity *rightmost, *se = &p->se;
- struct rb_node *parent;
+ struct cfs_rq *cfs_rq = task_cfs_rq(rq->curr);
+ struct sched_entity *rightmost, *se = &rq->curr->se;
/*
* Are we the only task in the tree?
* Dequeue and enqueue the task to update its
* position within the tree:
*/
- dequeue_entity(cfs_rq, &p->se, 0);
- enqueue_entity(cfs_rq, &p->se, 0);
+ update_curr(cfs_rq);
return;
}
/*
* Find the rightmost entry in the rbtree:
*/
- do {
- parent = *link;
- link = &parent->rb_right;
- } while (*link);
-
- rightmost = rb_entry(parent, struct sched_entity, run_node);
+ rightmost = __pick_last_entity(cfs_rq);
/*
* Already in the rightmost position?
*/
- if (unlikely(rightmost == se))
+ if (unlikely(rightmost->vruntime < se->vruntime))
return;
/*
* Minimally necessary key value to be last in the tree:
+ * Upon rescheduling, sched_class::put_prev_task() will place
+ * 'current' within the tree based on its new key value.
*/
- se->fair_key = rightmost->fair_key + 1;
-
- if (cfs_rq->rb_leftmost == &se->run_node)
- cfs_rq->rb_leftmost = rb_next(&se->run_node);
- /*
- * Relink the task to the rightmost position:
- */
- rb_erase(&se->run_node, &cfs_rq->tasks_timeline);
- rb_link_node(&se->run_node, parent, link);
- rb_insert_color(&se->run_node, &cfs_rq->tasks_timeline);
+ se->vruntime = rightmost->vruntime + 1;
}
/*
{
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;
if (unlikely(rt_prio(p->prio))) {
update_rq_clock(rq);
resched_task(curr);
return;
}
- if (is_same_group(curr, p)) {
- s64 delta = curr->se.vruntime - p->se.vruntime;
- if (delta > (s64)sysctl_sched_wakeup_granularity)
- resched_task(curr);
+ while (!is_same_group(se, pse)) {
+ se = parent_entity(se);
+ pse = parent_entity(pse);
}
+
+ delta = se->vruntime - pse->vruntime;
+
+ if (delta > (s64)sysctl_sched_wakeup_granularity)
+ resched_task(curr);
}
static struct task_struct *pick_next_task_fair(struct rq *rq)
if (!cfs_rq->nr_running)
return MAX_PRIO;
- curr = __pick_next_entity(cfs_rq);
+ curr = cfs_rq->curr;
+ if (!curr)
+ curr = __pick_next_entity(cfs_rq);
+
p = task_of(curr);
return p->prio;
update_curr(cfs_rq);
place_entity(cfs_rq, se, 1);
- /*
- * The statistical average of wait_runtime is about
- * -granularity/2, so initialize the task with that:
- */
- if (sched_feat(START_DEBIT))
- se->wait_runtime = -(__sched_period(cfs_rq->nr_running+1) / 2);
-
if (sysctl_sched_child_runs_first &&
curr->vruntime < se->vruntime) {
-
- dequeue_entity(cfs_rq, curr, 0);
+ /*
+ * Upon rescheduling, sched_class::put_prev_task() will place
+ * 'current' within the tree based on its new key value.
+ */
swap(curr->vruntime, se->vruntime);
- enqueue_entity(cfs_rq, curr, 0);
}
update_stats_enqueue(cfs_rq, se);
+ check_spread(cfs_rq, se);
+ check_spread(cfs_rq, curr);
__enqueue_entity(cfs_rq, se);
+ account_entity_enqueue(cfs_rq, se);
resched_task(rq->curr);
}
-#ifdef CONFIG_FAIR_GROUP_SCHED
/* Account for a task changing its policy or group.
*
* This routine is mostly called to set cfs_rq->curr field when a task
for_each_sched_entity(se)
set_next_entity(cfs_rq_of(se), se);
}
-#else
-static void set_curr_task_fair(struct rq *rq)
-{
-}
-#endif
/*
* All the scheduling class methods:
{
struct cfs_rq *cfs_rq;
+#ifdef CONFIG_FAIR_GROUP_SCHED
+ print_cfs_rq(m, cpu, &cpu_rq(cpu)->cfs);
+#endif
for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);
}