}
}
- static inline unsigned long cfs_rq_runnable_load_avg(struct cfs_rq *cfs_rq);
- static inline unsigned long cfs_rq_load_avg(struct cfs_rq *cfs_rq);
#else
void init_entity_runnable_average(struct sched_entity *se)
{
{
if (env->best_task)
put_task_struct(env->best_task);
+ if (p)
+ get_task_struct(p);
env->best_task = p;
env->best_imp = imp;
long imp = env->p->numa_group ? groupimp : taskimp;
long moveimp = imp;
int dist = env->dist;
- bool assigned = false;
rcu_read_lock();
-
- raw_spin_lock_irq(&dst_rq->lock);
- cur = dst_rq->curr;
- /*
- * No need to move the exiting task or idle task.
- */
- if ((cur->flags & PF_EXITING) || is_idle_task(cur))
+ cur = task_rcu_dereference(&dst_rq->curr);
+ if (cur && ((cur->flags & PF_EXITING) || is_idle_task(cur)))
cur = NULL;
- else {
- /*
- * The task_struct must be protected here to protect the
- * p->numa_faults access in the task_weight since the
- * numa_faults could already be freed in the following path:
- * finish_task_switch()
- * --> put_task_struct()
- * --> __put_task_struct()
- * --> task_numa_free()
- */
- get_task_struct(cur);
- }
-
- raw_spin_unlock_irq(&dst_rq->lock);
/*
* Because we have preemption enabled we can get migrated around and
*/
if (!load_too_imbalanced(src_load, dst_load, env)) {
imp = moveimp - 1;
- put_task_struct(cur);
cur = NULL;
goto assign;
}
env->dst_cpu = select_idle_sibling(env->p, env->dst_cpu);
assign:
- assigned = true;
task_numa_assign(env, cur, imp);
unlock:
rcu_read_unlock();
- /*
- * The dst_rq->curr isn't assigned. The protection for task_struct is
- * finished.
- */
- if (cur && !assigned)
- put_task_struct(cur);
}
static void task_numa_find_cpu(struct task_numa_env *env,
#ifdef CONFIG_FAIR_GROUP_SCHED
# ifdef CONFIG_SMP
- static inline long calc_tg_weight(struct task_group *tg, struct cfs_rq *cfs_rq)
+ static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
{
- long tg_weight;
+ long tg_weight, load, shares;
/*
- * Use this CPU's real-time load instead of the last load contribution
- * as the updating of the contribution is delayed, and we will use the
- * the real-time load to calc the share. See update_tg_load_avg().
+ * This really should be: cfs_rq->avg.load_avg, but instead we use
+ * cfs_rq->load.weight, which is its upper bound. This helps ramp up
+ * the shares for small weight interactive tasks.
*/
- tg_weight = atomic_long_read(&tg->load_avg);
- tg_weight -= cfs_rq->tg_load_avg_contrib;
- tg_weight += cfs_rq->load.weight;
+ load = scale_load_down(cfs_rq->load.weight);
- return tg_weight;
- }
-
- static long calc_cfs_shares(struct cfs_rq *cfs_rq, struct task_group *tg)
- {
- long tg_weight, load, shares;
+ tg_weight = atomic_long_read(&tg->load_avg);
- tg_weight = calc_tg_weight(tg, cfs_rq);
- load = cfs_rq->load.weight;
+ /* Ensure tg_weight >= load */
+ tg_weight -= cfs_rq->tg_load_avg_contrib;
+ tg_weight += load;
shares = (tg->shares * load);
if (tg_weight)
return tg->shares;
}
# endif /* CONFIG_SMP */
+
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
unsigned long weight)
{
}
}
+ /*
+ * Unsigned subtract and clamp on underflow.
+ *
+ * Explicitly do a load-store to ensure the intermediate value never hits
+ * memory. This allows lockless observations without ever seeing the negative
+ * values.
+ */
+ #define sub_positive(_ptr, _val) do { \
+ typeof(_ptr) ptr = (_ptr); \
+ typeof(*ptr) val = (_val); \
+ typeof(*ptr) res, var = READ_ONCE(*ptr); \
+ res = var - val; \
+ if (res > var) \
+ res = 0; \
+ WRITE_ONCE(*ptr, res); \
+ } while (0)
+
/* Group cfs_rq's load_avg is used for task_h_load and update_cfs_share */
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq, bool update_freq)
if (atomic_long_read(&cfs_rq->removed_load_avg)) {
s64 r = atomic_long_xchg(&cfs_rq->removed_load_avg, 0);
- sa->load_avg = max_t(long, sa->load_avg - r, 0);
- sa->load_sum = max_t(s64, sa->load_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->load_avg, r);
+ sub_positive(&sa->load_sum, r * LOAD_AVG_MAX);
removed_load = 1;
}
if (atomic_long_read(&cfs_rq->removed_util_avg)) {
long r = atomic_long_xchg(&cfs_rq->removed_util_avg, 0);
- sa->util_avg = max_t(long, sa->util_avg - r, 0);
- sa->util_sum = max_t(s32, sa->util_sum - r * LOAD_AVG_MAX, 0);
+ sub_positive(&sa->util_avg, r);
+ sub_positive(&sa->util_sum, r * LOAD_AVG_MAX);
removed_util = 1;
}
&se->avg, se->on_rq * scale_load_down(se->load.weight),
cfs_rq->curr == se, NULL);
- cfs_rq->avg.load_avg = max_t(long, cfs_rq->avg.load_avg - se->avg.load_avg, 0);
- cfs_rq->avg.load_sum = max_t(s64, cfs_rq->avg.load_sum - se->avg.load_sum, 0);
- cfs_rq->avg.util_avg = max_t(long, cfs_rq->avg.util_avg - se->avg.util_avg, 0);
- cfs_rq->avg.util_sum = max_t(s32, cfs_rq->avg.util_sum - se->avg.util_sum, 0);
+ sub_positive(&cfs_rq->avg.load_avg, se->avg.load_avg);
+ sub_positive(&cfs_rq->avg.load_sum, se->avg.load_sum);
+ sub_positive(&cfs_rq->avg.util_avg, se->avg.util_avg);
+ sub_positive(&cfs_rq->avg.util_sum, se->avg.util_sum);
cfs_rq_util_change(cfs_rq);
}
trace_sched_stat_iowait_enabled() ||
trace_sched_stat_blocked_enabled() ||
trace_sched_stat_runtime_enabled()) {
- pr_warn_once("Scheduler tracepoints stat_sleep, stat_iowait, "
+ printk_deferred_once("Scheduler tracepoints stat_sleep, stat_iowait, "
"stat_blocked and stat_runtime require the "
"kernel parameter schedstats=enabled or "
"kernel.sched_schedstats=1\n");
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
if (unlikely(cfs_rq->throttle_count))
- return cfs_rq->throttled_clock_task;
+ return cfs_rq->throttled_clock_task - cfs_rq->throttled_clock_task_time;
return rq_clock_task(rq_of(cfs_rq)) - cfs_rq->throttled_clock_task_time;
}
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
cfs_rq->throttle_count--;
-#ifdef CONFIG_SMP
if (!cfs_rq->throttle_count) {
/* adjust cfs_rq_clock_task() */
cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
cfs_rq->throttled_clock_task;
}
-#endif
return 0;
}
if (!cfs_bandwidth_used())
return;
+ /* Synchronize hierarchical throttle counter: */
+ if (unlikely(!cfs_rq->throttle_uptodate)) {
+ struct rq *rq = rq_of(cfs_rq);
+ struct cfs_rq *pcfs_rq;
+ struct task_group *tg;
+
+ cfs_rq->throttle_uptodate = 1;
+
+ /* Get closest up-to-date node, because leaves go first: */
+ for (tg = cfs_rq->tg->parent; tg; tg = tg->parent) {
+ pcfs_rq = tg->cfs_rq[cpu_of(rq)];
+ if (pcfs_rq->throttle_uptodate)
+ break;
+ }
+ if (tg) {
+ cfs_rq->throttle_count = pcfs_rq->throttle_count;
+ cfs_rq->throttled_clock_task = rq_clock_task(rq);
+ }
+ }
+
/* an active group must be handled by the update_curr()->put() path */
if (!cfs_rq->runtime_enabled || cfs_rq->curr)
return;
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
+ /* Avoid re-evaluating load for this entity: */
+ se = parent_entity(se);
/*
* Bias pick_next to pick a task from this cfs_rq, as
* p is sleeping when it is within its sched_slice.
*/
- if (task_sleep && parent_entity(se))
- set_next_buddy(parent_entity(se));
-
- /* avoid re-evaluating load for this entity */
- se = parent_entity(se);
+ if (task_sleep && se && !throttled_hierarchy(cfs_rq))
+ set_next_buddy(se);
break;
}
flags |= DEQUEUE_SLEEP;
return wl;
for_each_sched_entity(se) {
- long w, W;
+ struct cfs_rq *cfs_rq = se->my_q;
+ long W, w = cfs_rq_load_avg(cfs_rq);
- tg = se->my_q->tg;
+ tg = cfs_rq->tg;
/*
* W = @wg + \Sum rw_j
*/
- W = wg + calc_tg_weight(tg, se->my_q);
+ W = wg + atomic_long_read(&tg->load_avg);
+
+ /* Ensure \Sum rw_j >= rw_i */
+ W -= cfs_rq->tg_load_avg_contrib;
+ W += w;
/*
* w = rw_i + @wl
*/
- w = cfs_rq_load_avg(se->my_q) + wl;
+ w += wl;
/*
* wl = S * s'_i; see (2)