return grp->my_q;
}
-static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
struct rq *rq = rq_of(cfs_rq);
int cpu = cpu_of(rq);
if (cfs_rq->on_list)
- return;
+ return rq->tmp_alone_branch == &rq->leaf_cfs_rq_list;
cfs_rq->on_list = 1;
* list.
*/
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
- return;
+ return true;
}
if (!cfs_rq->tg->parent) {
* tmp_alone_branch to the beginning of the list.
*/
rq->tmp_alone_branch = &rq->leaf_cfs_rq_list;
- return;
+ return true;
}
/*
* of the branch
*/
rq->tmp_alone_branch = &cfs_rq->leaf_cfs_rq_list;
+ return false;
}
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
if (cfs_rq->on_list) {
+ struct rq *rq = rq_of(cfs_rq);
+
+ /*
+ * With cfs_rq being unthrottled/throttled during an enqueue,
+ * it can happen the tmp_alone_branch points the a leaf that
+ * we finally want to del. In this case, tmp_alone_branch moves
+ * to the prev element but it will point to rq->leaf_cfs_rq_list
+ * at the end of the enqueue.
+ */
+ if (rq->tmp_alone_branch == &cfs_rq->leaf_cfs_rq_list)
+ rq->tmp_alone_branch = cfs_rq->leaf_cfs_rq_list.prev;
+
list_del_rcu(&cfs_rq->leaf_cfs_rq_list);
cfs_rq->on_list = 0;
}
SCHED_WARN_ON(rq->tmp_alone_branch != &rq->leaf_cfs_rq_list);
}
-/* Iterate through all cfs_rq's on a runqueue in bottom-up order */
-#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)
+/* 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)
/* Do the two (enqueued) entities belong to the same group ? */
static inline struct cfs_rq *
return NULL;
}
-static inline void list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
+static inline bool list_add_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
+ return true;
}
static inline void list_del_leaf_cfs_rq(struct cfs_rq *cfs_rq)
{
}
-#define for_each_leaf_cfs_rq(rq, cfs_rq) \
- for (cfs_rq = &rq->cfs; cfs_rq; cfs_rq = NULL)
+#define for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) \
+ for (cfs_rq = &rq->cfs, pos = NULL; cfs_rq; cfs_rq = pos)
static inline struct sched_entity *parent_entity(struct sched_entity *se)
{
* Finally, that extrapolated util_avg is clamped to the cap (util_avg_cap)
* if util_avg > util_avg_cap.
*/
-void post_init_entity_util_avg(struct sched_entity *se)
+void post_init_entity_util_avg(struct task_struct *p)
{
+ struct sched_entity *se = &p->se;
struct cfs_rq *cfs_rq = cfs_rq_of(se);
struct sched_avg *sa = &se->avg;
long cpu_scale = arch_scale_cpu_capacity(NULL, cpu_of(rq_of(cfs_rq)));
}
}
- if (entity_is_task(se)) {
- struct task_struct *p = task_of(se);
- if (p->sched_class != &fair_sched_class) {
- /*
- * For !fair tasks do:
- *
- update_cfs_rq_load_avg(now, cfs_rq);
- attach_entity_load_avg(cfs_rq, se, 0);
- switched_from_fair(rq, p);
- *
- * such that the next switched_to_fair() has the
- * expected state.
- */
- se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq);
- return;
- }
+ if (p->sched_class != &fair_sched_class) {
+ /*
+ * For !fair tasks do:
+ *
+ update_cfs_rq_load_avg(now, cfs_rq);
+ attach_entity_load_avg(cfs_rq, se, 0);
+ switched_from_fair(rq, p);
+ *
+ * such that the next switched_to_fair() has the
+ * expected state.
+ */
+ se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq);
+ return;
}
attach_entity_cfs_rq(se);
void init_entity_runnable_average(struct sched_entity *se)
{
}
-void post_init_entity_util_avg(struct sched_entity *se)
+void post_init_entity_util_avg(struct task_struct *p)
{
}
static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force)
* tasks cannot exit without having gone through wake_up_new_task() ->
* post_init_entity_util_avg() which will have added things to the
* cfs_rq, so we can remove unconditionally.
- *
- * Similarly for groups, they will have passed through
- * post_init_entity_util_avg() before unregister_sched_fair_group()
- * calls this.
*/
sync_entity_load_avg(se);
/* adjust cfs_rq_clock_task() */
cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
cfs_rq->throttled_clock_task;
+
+ /* Add cfs_rq with already running entity in the list */
+ if (cfs_rq->nr_running >= 1)
+ list_add_leaf_cfs_rq(cfs_rq);
}
return 0;
struct cfs_rq *cfs_rq = tg->cfs_rq[cpu_of(rq)];
/* group is entering throttled state, stop time */
- if (!cfs_rq->throttle_count)
+ if (!cfs_rq->throttle_count) {
cfs_rq->throttled_clock_task = rq_clock_task(rq);
+ list_del_leaf_cfs_rq(cfs_rq);
+ }
cfs_rq->throttle_count++;
return 0;
break;
}
+ assert_list_leaf_cfs_rq(rq);
+
if (!se)
add_nr_running(rq, task_delta);
}
#else /* CONFIG_CFS_BANDWIDTH */
+
+static inline bool cfs_bandwidth_used(void)
+{
+ return false;
+}
+
static inline u64 cfs_rq_clock_task(struct cfs_rq *cfs_rq)
{
return rq_clock_task(rq_of(cfs_rq));
}
+ if (cfs_bandwidth_used()) {
+ /*
+ * When bandwidth control is enabled; the cfs_rq_throttled()
+ * breaks in the above iteration can result in incomplete
+ * leaf list maintenance, resulting in triggering the assertion
+ * below.
+ */
+ for_each_sched_entity(se) {
+ cfs_rq = cfs_rq_of(se);
+
+ if (list_add_leaf_cfs_rq(cfs_rq))
+ break;
+ }
+ }
+
assert_list_leaf_cfs_rq(rq);
hrtick_update(rq);
#ifdef CONFIG_SCHED_SMT
DEFINE_STATIC_KEY_FALSE(sched_smt_present);
+EXPORT_SYMBOL_GPL(sched_smt_present);
static inline void set_idle_cores(int cpu, int val)
{
bool idle = true;
for_each_cpu(cpu, cpu_smt_mask(core)) {
- cpumask_clear_cpu(cpu, cpus);
+ __cpumask_clear_cpu(cpu, cpus);
if (!available_idle_cpu(cpu))
idle = false;
}
/*
* Scan the local SMT mask for idle CPUs.
*/
-static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
+static int select_idle_smt(struct task_struct *p, int target)
{
int cpu;
return -1;
}
-static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target)
+static inline int select_idle_smt(struct task_struct *p, int target)
{
return -1;
}
if ((unsigned)i < nr_cpumask_bits)
return i;
- i = select_idle_smt(p, sd, target);
+ i = select_idle_smt(p, target);
if ((unsigned)i < nr_cpumask_bits)
return i;
#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->avg.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;
+ struct cfs_rq *cfs_rq, *pos;
const struct sched_class *curr_class;
struct rq_flags rf;
bool done = true;
* Iterates the task_group tree in a bottom up fashion, see
* list_add_leaf_cfs_rq() for details.
*/
- for_each_leaf_cfs_rq(rq, cfs_rq) {
+ for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
struct sched_entity *se;
- /* throttled entities do not contribute to load */
- if (throttled_hierarchy(cfs_rq))
- continue;
-
if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq))
update_tg_load_avg(cfs_rq, 0);
if (se && !skip_blocked_update(se))
update_load_avg(cfs_rq_of(se), 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);
+
/* Don't need periodic decay once load/util_avg are null */
if (cfs_rq_has_blocked(cfs_rq))
done = false;
(rq->cpu_capacity_orig * 100));
}
+/*
+ * Check whether a rq has a misfit task and if it looks like we can actually
+ * help that task: we can migrate the task to a CPU of higher capacity, or
+ * the task's current CPU is heavily pressured.
+ */
+static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
+{
+ return rq->misfit_task_load &&
+ (rq->cpu_capacity_orig < rq->rd->max_cpu_capacity ||
+ check_cpu_capacity(rq, sd));
+}
+
/*
* Group imbalance indicates (and tries to solve) the problem where balancing
* groups is inadequate due to ->cpus_allowed constraints.
if ((env.flags & LBF_DST_PINNED) && env.imbalance > 0) {
/* Prevent to re-select dst_cpu via env's CPUs */
- cpumask_clear_cpu(env.dst_cpu, env.cpus);
+ __cpumask_clear_cpu(env.dst_cpu, env.cpus);
env.dst_rq = cpu_rq(env.new_dst_cpu);
env.dst_cpu = env.new_dst_cpu;
/* All tasks on this runqueue were pinned by CPU affinity */
if (unlikely(env.flags & LBF_ALL_PINNED)) {
- cpumask_clear_cpu(cpu_of(busiest), cpus);
+ __cpumask_clear_cpu(cpu_of(busiest), cpus);
/*
* Attempting to continue load balancing at the current
* sched_domain level only makes sense if there are
}
/*
- * Current heuristic for kicking the idle load balancer in the presence
- * of an idle cpu in the system.
- * - This rq has more than one task.
- * - This rq has at least one CFS task and the capacity of the CPU is
- * significantly reduced because of RT tasks or IRQs.
- * - At parent of LLC scheduler domain level, this cpu's scheduler group has
- * multiple busy cpu.
- * - For SD_ASYM_PACKING, if the lower numbered cpu's in the scheduler
- * domain span are idle.
+ * Current decision point for kicking the idle load balancer in the presence
+ * of idle CPUs in the system.
*/
static void nohz_balancer_kick(struct rq *rq)
{
if (time_before(now, nohz.next_balance))
goto out;
- if (rq->nr_running >= 2 || rq->misfit_task_load) {
+ if (rq->nr_running >= 2) {
flags = NOHZ_KICK_MASK;
goto out;
}
sds = rcu_dereference(per_cpu(sd_llc_shared, cpu));
if (sds) {
/*
- * XXX: write a coherent comment on why we do this.
- * See also: http://lkml.kernel.org/r/20111202010832.602203411@sbsiddha-desk.sc.intel.com
+ * If there is an imbalance between LLC domains (IOW we could
+ * increase the overall cache use), we need some less-loaded LLC
+ * domain to pull some load. Likewise, we may need to spread
+ * load within the current LLC domain (e.g. packed SMT cores but
+ * other CPUs are idle). We can't really know from here how busy
+ * the others are - so just get a nohz balance going if it looks
+ * like this LLC domain has tasks we could move.
*/
nr_busy = atomic_read(&sds->nr_busy_cpus);
if (nr_busy > 1) {
sd = rcu_dereference(rq->sd);
if (sd) {
- if ((rq->cfs.h_nr_running >= 1) &&
- check_cpu_capacity(rq, sd)) {
+ /*
+ * If there's a CFS task and the current CPU has reduced
+ * capacity; kick the ILB to see if there's a better CPU to run
+ * on.
+ */
+ if (rq->cfs.h_nr_running >= 1 && check_cpu_capacity(rq, sd)) {
flags = NOHZ_KICK_MASK;
goto unlock;
}
}
- sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
+ sd = rcu_dereference(per_cpu(sd_asym_cpucapacity, cpu));
if (sd) {
- for_each_cpu(i, sched_domain_span(sd)) {
- if (i == cpu ||
- !cpumask_test_cpu(i, nohz.idle_cpus_mask))
- continue;
+ /*
+ * When ASYM_CPUCAPACITY; see if there's a higher capacity CPU
+ * to run the misfit task on.
+ */
+ if (check_misfit_status(rq, sd)) {
+ flags = NOHZ_KICK_MASK;
+ goto unlock;
+ }
+ }
+ sd = rcu_dereference(per_cpu(sd_asym_packing, cpu));
+ if (sd) {
+ /*
+ * When ASYM_PACKING; see if there's a more preferred CPU
+ * currently idle; in which case, kick the ILB to move tasks
+ * around.
+ */
+ for_each_cpu_and(i, sched_domain_span(sd), nohz.idle_cpus_mask) {
if (sched_asym_prefer(i, cpu)) {
flags = NOHZ_KICK_MASK;
goto unlock;
#ifdef CONFIG_SCHED_DEBUG
void print_cfs_stats(struct seq_file *m, int cpu)
{
- struct cfs_rq *cfs_rq;
+ struct cfs_rq *cfs_rq, *pos;
rcu_read_lock();
- for_each_leaf_cfs_rq(cpu_rq(cpu), cfs_rq)
+ for_each_leaf_cfs_rq_safe(cpu_rq(cpu), cfs_rq, pos)
print_cfs_rq(m, cpu, cfs_rq);
rcu_read_unlock();
}