}
}
-/* Iterate thr' all leaf cfs_rq's on a runqueue */
-#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \
- list_for_each_entry_safe(cfs_rq, pos, &rq->leaf_cfs_rq_list, \
- leaf_cfs_rq_list)
+/* Iterate through all leaf cfs_rq's on a runqueue: */
+#define for_each_leaf_cfs_rq(rq, cfs_rq) \
+ list_for_each_entry_rcu(cfs_rq, &rq->leaf_cfs_rq_list, leaf_cfs_rq_list)
/* Do the two (enqueued) entities belong to the same group ? */
static inline struct cfs_rq *
{
}
-#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \
- for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
+#define for_each_leaf_cfs_rq(rq, cfs_rq) \
+ for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
* To solve this problem, we also cap the util_avg of successive tasks to
* only 1/2 of the left utilization budget:
*
- * util_avg_cap = (1024 - cfs_rq->avg.util_avg) / 2^n
+ * util_avg_cap = (cpu_scale - cfs_rq->avg.util_avg) / 2^n
*
- * where n denotes the nth task.
+ * where n denotes the nth task and cpu_scale the CPU capacity.
*
- * For example, a simplest series from the beginning would be like:
+ * For example, for a CPU with 1024 of capacity, a simplest series from
+ * the beginning would be like:
*
* task util_avg: 512, 256, 128, 64, 32, 16, 8, ...
* cfs_rq util_avg: 512, 768, 896, 960, 992, 1008, 1016, ...
{
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct sched_avg *sa = &se->avg;
- long cap = (long)(SCHED_CAPACITY_SCALE - cfs_rq->avg.util_avg) / 2;
+ long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
+ long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
if (cap > 0) {
if (cfs_rq->avg.util_avg != 0) {
* put back on, and if we advance min_vruntime, we'll be placed back
* further than we started -- ie. we'll be penalized.
*/
- if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) == DEQUEUE_SAVE)
+ if ((flags & (DEQUEUE_SAVE | DEQUEUE_MOVE)) != DEQUEUE_SAVE)
update_min_vruntime(cfs_rq);
}
void cfs_bandwidth_usage_inc(void)
{
- static_key_slow_inc(&__cfs_bandwidth_used);
+ static_key_slow_inc_cpuslocked(&__cfs_bandwidth_used);
}
void cfs_bandwidth_usage_dec(void)
{
- static_key_slow_dec(&__cfs_bandwidth_used);
+ static_key_slow_dec_cpuslocked(&__cfs_bandwidth_used);
}
#else /* HAVE_JUMP_LABEL */
static bool cfs_bandwidth_used(void)
now = sched_clock_cpu(smp_processor_id());
cfs_b->runtime = cfs_b->quota;
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
+ cfs_b->expires_seq++;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
u64 amount = 0, min_amount, expires;
+ int expires_seq;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
cfs_b->idle = 0;
}
}
+ expires_seq = cfs_b->expires_seq;
expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
* spread between our sched_clock and the one on which runtime was
* issued.
*/
- if ((s64)(expires - cfs_rq->runtime_expires) > 0)
+ if (cfs_rq->expires_seq != expires_seq) {
+ cfs_rq->expires_seq = expires_seq;
cfs_rq->runtime_expires = expires;
+ }
return cfs_rq->runtime_remaining > 0;
}
* has not truly expired.
*
* Fortunately we can check determine whether this the case by checking
- * whether the global deadline has advanced. It is valid to compare
- * cfs_b->runtime_expires without any locks since we only care about
- * exact equality, so a partial write will still work.
+ * whether the global deadline(cfs_b->expires_seq) has advanced.
*/
-
- if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
+ if (cfs_rq->expires_seq == cfs_b->expires_seq) {
/* extend local deadline, drift is bounded above by 2 ticks */
cfs_rq->runtime_expires += TICK_NSEC;
} else {
/*
* Add to the _head_ of the list, so that an already-started
- * distribute_cfs_runtime will not see us
+ * distribute_cfs_runtime will not see us. If disribute_cfs_runtime is
+ * not running add to the tail so that later runqueues don't get starved.
*/
- list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ if (cfs_b->distribute_running)
+ list_add_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
+ else
+ list_add_tail_rcu(&cfs_rq->throttled_list, &cfs_b->throttled_cfs_rq);
/*
* If we're the first throttled task, make sure the bandwidth
* in us over-using our runtime if it is all used during this loop, but
* only by limited amounts in that extreme case.
*/
- while (throttled && cfs_b->runtime > 0) {
+ while (throttled && cfs_b->runtime > 0 && !cfs_b->distribute_running) {
runtime = cfs_b->runtime;
+ cfs_b->distribute_running = 1;
raw_spin_unlock(&cfs_b->lock);
/* we can't nest cfs_b->lock while distributing bandwidth */
runtime = distribute_cfs_runtime(cfs_b, runtime,
runtime_expires);
raw_spin_lock(&cfs_b->lock);
+ cfs_b->distribute_running = 0;
throttled = !list_empty(&cfs_b->throttled_cfs_rq);
cfs_b->runtime -= min(runtime, cfs_b->runtime);
/* confirm we're still not at a refresh boundary */
raw_spin_lock(&cfs_b->lock);
+ if (cfs_b->distribute_running) {
+ raw_spin_unlock(&cfs_b->lock);
+ return;
+ }
+
if (runtime_refresh_within(cfs_b, min_bandwidth_expiration)) {
raw_spin_unlock(&cfs_b->lock);
return;
runtime = cfs_b->runtime;
expires = cfs_b->runtime_expires;
+ if (runtime)
+ cfs_b->distribute_running = 1;
+
raw_spin_unlock(&cfs_b->lock);
if (!runtime)
raw_spin_lock(&cfs_b->lock);
if (expires == cfs_b->runtime_expires)
cfs_b->runtime -= min(runtime, cfs_b->runtime);
+ cfs_b->distribute_running = 0;
raw_spin_unlock(&cfs_b->lock);
}
cfs_b->period_timer.function = sched_cfs_period_timer;
hrtimer_init(&cfs_b->slack_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
cfs_b->slack_timer.function = sched_cfs_slack_timer;
+ cfs_b->distribute_running = 0;
}
static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
}
#ifdef CONFIG_SCHED_SMT
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
static inline void set_idle_cores(int cpu, int val)
{
#ifdef CONFIG_FAIR_GROUP_SCHED
-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
-{
- if (cfs_rq->load.weight)
- return false;
-
- if (cfs_rq->avg.load_sum)
- return false;
-
- if (cfs_rq->avg.util_sum)
- return false;
-
- if (cfs_rq->runnable_load_sum)
- return false;
-
- return true;
-}
-
static void update_blocked_averages(int cpu)
{
struct rq *rq = cpu_rq(cpu);
- struct cfs_rq *cfs_rq, *pos;
+ struct cfs_rq *cfs_rq;
struct rq_flags rf;
rq_lock_irqsave(rq, &rf);
* Iterates the task_group tree in a bottom up fashion, see
* list_add_leaf_cfs_rq() for details.
*/
- for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
+ for_each_leaf_cfs_rq(rq, cfs_rq) {
struct sched_entity *se;
/* throttled entities do not contribute to load */
se = cfs_rq->tg->se[cpu];
if (se && !skip_blocked_update(se))
update_load_avg(se, 0);
-
- /*
- * There can be a lot of idle CPU cgroups. Don't let fully
- * decayed cfs_rqs linger on the list.
- */
- if (cfs_rq_is_decayed(cfs_rq))
- list_del_leaf_cfs_rq(cfs_rq);
}
update_rt_rq_load_avg(rq_clock_task(rq), cpu, &rq->rt, 0);
#ifdef CONFIG_NO_HZ_COMMON
* - A task which has been woken up by try_to_wake_up() and
* waiting for actually being woken up by sched_ttwu_pending().
*/
- if (!se->sum_exec_runtime || p->state == TASK_WAKING)
+ if (!se->sum_exec_runtime ||
+ (p->state == TASK_WAKING && p->sched_remote_wakeup))
return true;
return false;
#ifdef CONFIG_SCHED_DEBUG
void print_cfs_stats(struct seq_file *m, int cpu)
{
- struct cfs_rq *cfs_rq, *pos;
+ struct cfs_rq *cfs_rq;
rcu_read_lock();
- for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
+ for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}