aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/core.c51
-rw-r--r--kernel/sched/cpufreq.c18
-rw-r--r--kernel/sched/cpufreq_schedutil.c8
-rw-r--r--kernel/sched/cputime.c6
-rw-r--r--kernel/sched/deadline.c1
-rw-r--r--kernel/sched/debug.c2
-rw-r--r--kernel/sched/fair.c421
-rw-r--r--kernel/sched/loadavg.c33
-rw-r--r--kernel/sched/psi.c8
-rw-r--r--kernel/sched/rt.c12
-rw-r--r--kernel/sched/sched.h17
-rw-r--r--kernel/sched/topology.c52
12 files changed, 396 insertions, 233 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index be7c380c07e6..dcc54d44fcde 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2338,6 +2338,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
* Silence PROVE_RCU.
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
+ rseq_migrate(p);
/*
* We're setting the CPU for the first time, we don't migrate,
* so use __set_task_cpu().
@@ -2402,6 +2403,7 @@ void wake_up_new_task(struct task_struct *p)
* as we're not fully set-up yet.
*/
p->recent_used_cpu = task_cpu(p);
+ rseq_migrate(p);
__set_task_cpu(p, select_task_rq(p, task_cpu(p), SD_BALANCE_FORK, 0));
#endif
rq = __task_rq_lock(p, &rf);
@@ -3102,28 +3104,31 @@ static void sched_tick_remote(struct work_struct *work)
* statistics and checks timeslices in a time-independent way, regardless
* of when exactly it is running.
*/
- if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+ if (!tick_nohz_tick_stopped_cpu(cpu))
goto out_requeue;
rq_lock_irq(rq, &rf);
curr = rq->curr;
- if (is_idle_task(curr) || cpu_is_offline(cpu))
+ if (cpu_is_offline(cpu))
goto out_unlock;
update_rq_clock(rq);
- delta = rq_clock_task(rq) - curr->se.exec_start;
- /*
- * Make sure the next tick runs within a reasonable
- * amount of time.
- */
- WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ if (!is_idle_task(curr)) {
+ /*
+ * Make sure the next tick runs within a reasonable
+ * amount of time.
+ */
+ delta = rq_clock_task(rq) - curr->se.exec_start;
+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ }
curr->sched_class->task_tick(rq, curr, 0);
+ calc_load_nohz_remote(rq);
out_unlock:
rq_unlock_irq(rq, &rf);
-
out_requeue:
+
/*
* Run the remote tick once per second (1Hz). This arbitrary
* frequency is large enough to avoid overload but short enough
@@ -3857,7 +3862,8 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
*/
if (dl_prio(prio)) {
if (!dl_prio(p->normal_prio) ||
- (pi_task && dl_entity_preempt(&pi_task->dl, &p->dl))) {
+ (pi_task && dl_prio(pi_task->prio) &&
+ dl_entity_preempt(&pi_task->dl, &p->dl))) {
p->dl.dl_boosted = 1;
queue_flag |= ENQUEUE_REPLENISH;
} else
@@ -5405,10 +5411,11 @@ void init_idle(struct task_struct *idle, int cpu)
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
+ __sched_fork(0, idle);
+
raw_spin_lock_irqsave(&idle->pi_lock, flags);
raw_spin_lock(&rq->lock);
- __sched_fork(0, idle);
idle->state = TASK_RUNNING;
idle->se.exec_start = sched_clock();
idle->flags |= PF_IDLE;
@@ -5562,13 +5569,14 @@ void idle_task_exit(void)
struct mm_struct *mm = current->active_mm;
BUG_ON(cpu_online(smp_processor_id()));
+ BUG_ON(current != this_rq()->idle);
if (mm != &init_mm) {
switch_mm(mm, &init_mm, current);
- current->active_mm = &init_mm;
finish_arch_post_lock_switch();
}
- mmdrop(mm);
+
+ /* finish_cpu(), as ran on the BP, will clean up the active_mm state */
}
/*
@@ -6429,8 +6437,15 @@ void sched_move_task(struct task_struct *tsk)
if (queued)
enqueue_task(rq, tsk, queue_flags);
- if (running)
+ if (running) {
set_curr_task(rq, tsk);
+ /*
+ * After changing group, the running task may have joined a
+ * throttled one but it's still the running task. Trigger a
+ * resched to make sure that task can still run.
+ */
+ resched_curr(rq);
+ }
task_rq_unlock(rq, tsk, &rf);
}
@@ -6565,6 +6580,8 @@ static DEFINE_MUTEX(cfs_constraints_mutex);
const u64 max_cfs_quota_period = 1 * NSEC_PER_SEC; /* 1s */
static const u64 min_cfs_quota_period = 1 * NSEC_PER_MSEC; /* 1ms */
+/* More than 203 days if BW_SHIFT equals 20. */
+static const u64 max_cfs_runtime = MAX_BW * NSEC_PER_USEC;
static int __cfs_schedulable(struct task_group *tg, u64 period, u64 runtime);
@@ -6593,6 +6610,12 @@ static int tg_set_cfs_bandwidth(struct task_group *tg, u64 period, u64 quota)
return -EINVAL;
/*
+ * Bound quota to defend quota against overflow during bandwidth shift.
+ */
+ if (quota != RUNTIME_INF && quota > max_cfs_runtime)
+ return -EINVAL;
+
+ /*
* Prevent race between setting of cfs_rq->runtime_enabled and
* unthrottle_offline_cfs_rqs().
*/
diff --git a/kernel/sched/cpufreq.c b/kernel/sched/cpufreq.c
index b5dcd1d83c7f..7c2fe50fd76d 100644
--- a/kernel/sched/cpufreq.c
+++ b/kernel/sched/cpufreq.c
@@ -5,6 +5,8 @@
* Copyright (C) 2016, Intel Corporation
* Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
*/
+#include <linux/cpufreq.h>
+
#include "sched.h"
DEFINE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
@@ -57,3 +59,19 @@ void cpufreq_remove_update_util_hook(int cpu)
rcu_assign_pointer(per_cpu(cpufreq_update_util_data, cpu), NULL);
}
EXPORT_SYMBOL_GPL(cpufreq_remove_update_util_hook);
+
+/**
+ * cpufreq_this_cpu_can_update - Check if cpufreq policy can be updated.
+ * @policy: cpufreq policy to check.
+ *
+ * Return 'true' if:
+ * - the local and remote CPUs share @policy,
+ * - dvfs_possible_from_any_cpu is set in @policy and the local CPU is not going
+ * offline (in which case it is not expected to run cpufreq updates any more).
+ */
+bool cpufreq_this_cpu_can_update(struct cpufreq_policy *policy)
+{
+ return cpumask_test_cpu(smp_processor_id(), policy->cpus) ||
+ (policy->dvfs_possible_from_any_cpu &&
+ rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)));
+}
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index e139b54716b4..dd44eb122514 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -82,12 +82,10 @@ static bool sugov_should_update_freq(struct sugov_policy *sg_policy, u64 time)
* by the hardware, as calculating the frequency is pointless if
* we cannot in fact act on it.
*
- * For the slow switching platforms, the kthread is always scheduled on
- * the right set of CPUs and any CPU can find the next frequency and
- * schedule the kthread.
+ * This is needed on the slow switching platforms too to prevent CPUs
+ * going offline from leaving stale IRQ work items behind.
*/
- if (sg_policy->policy->fast_switch_enabled &&
- !cpufreq_this_cpu_can_update(sg_policy->policy))
+ if (!cpufreq_this_cpu_can_update(sg_policy->policy))
return false;
if (unlikely(sg_policy->limits_changed)) {
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2305ce89a26c..46ed4e1383e2 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -740,7 +740,7 @@ void vtime_account_system(struct task_struct *tsk)
write_seqcount_begin(&vtime->seqcount);
/* We might have scheduled out from guest path */
- if (current->flags & PF_VCPU)
+ if (tsk->flags & PF_VCPU)
vtime_account_guest(tsk, vtime);
else
__vtime_account_system(tsk, vtime);
@@ -783,7 +783,7 @@ void vtime_guest_enter(struct task_struct *tsk)
*/
write_seqcount_begin(&vtime->seqcount);
__vtime_account_system(tsk, vtime);
- current->flags |= PF_VCPU;
+ tsk->flags |= PF_VCPU;
write_seqcount_end(&vtime->seqcount);
}
EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -794,7 +794,7 @@ void vtime_guest_exit(struct task_struct *tsk)
write_seqcount_begin(&vtime->seqcount);
vtime_account_guest(tsk, vtime);
- current->flags &= ~PF_VCPU;
+ tsk->flags &= ~PF_VCPU;
write_seqcount_end(&vtime->seqcount);
}
EXPORT_SYMBOL_GPL(vtime_guest_exit);
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fcdafdcb129c..3daa9b4cf6d9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2679,6 +2679,7 @@ void __dl_clear_params(struct task_struct *p)
dl_se->dl_bw = 0;
dl_se->dl_density = 0;
+ dl_se->dl_boosted = 0;
dl_se->dl_throttled = 0;
dl_se->dl_yielded = 0;
dl_se->dl_non_contending = 0;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 14c6a8716ba1..0650be5f5bc7 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -272,7 +272,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd)
set_table_entry(&table[7] , "busy_factor", &sd->busy_factor, sizeof(int) , 0644, proc_dointvec_minmax, false);
set_table_entry(&table[8] , "imbalance_pct", &sd->imbalance_pct, sizeof(int) , 0644, proc_dointvec_minmax, false);
set_table_entry(&table[9] , "cache_nice_tries", &sd->cache_nice_tries, sizeof(int) , 0644, proc_dointvec_minmax, false);
- set_table_entry(&table[10], "flags", &sd->flags, sizeof(int) , 0644, proc_dointvec_minmax, false);
+ set_table_entry(&table[10], "flags", &sd->flags, sizeof(int) , 0444, proc_dointvec_minmax, false);
set_table_entry(&table[11], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax, false);
set_table_entry(&table[12], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring, false);
/* &table[13] is terminator */
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5a312c030b8d..50f4b19a5387 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -2659,7 +2659,7 @@ static void task_tick_numa(struct rq *rq, struct task_struct *curr)
/*
* We don't care about NUMA placement if we don't have memory.
*/
- if (!curr->mm || (curr->flags & PF_EXITING) || work->next != work)
+ if ((curr->flags & (PF_EXITING | PF_KTHREAD)) || work->next != work)
return;
/*
@@ -3488,9 +3488,6 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
cfs_rq->load_last_update_time_copy = sa->last_update_time;
#endif
- if (decayed)
- cfs_rq_util_change(cfs_rq, 0);
-
return decayed;
}
@@ -3596,8 +3593,12 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
attach_entity_load_avg(cfs_rq, se, SCHED_CPUFREQ_MIGRATION);
update_tg_load_avg(cfs_rq, 0);
- } else if (decayed && (flags & UPDATE_TG))
- update_tg_load_avg(cfs_rq, 0);
+ } else if (decayed) {
+ cfs_rq_util_change(cfs_rq, 0);
+
+ if (flags & UPDATE_TG)
+ update_tg_load_avg(cfs_rq, 0);
+ }
}
#ifndef CONFIG_64BIT
@@ -3805,7 +3806,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
return;
}
- rq->misfit_task_load = task_h_load(p);
+ /*
+ * Make sure that misfit_task_load will not be null even if
+ * task_h_load() returns 0.
+ */
+ rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
}
#else /* CONFIG_SMP */
@@ -3908,6 +3913,7 @@ static inline void check_schedstat_required(void)
#endif
}
+static inline bool cfs_bandwidth_used(void);
/*
* MIGRATION
@@ -3986,10 +3992,16 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
__enqueue_entity(cfs_rq, se);
se->on_rq = 1;
- if (cfs_rq->nr_running == 1) {
+ /*
+ * When bandwidth control is enabled, cfs might have been removed
+ * because of a parent been throttled but cfs->nr_running > 1. Try to
+ * add it unconditionnally.
+ */
+ if (cfs_rq->nr_running == 1 || cfs_bandwidth_used())
list_add_leaf_cfs_rq(cfs_rq);
+
+ if (cfs_rq->nr_running == 1)
check_enqueue_throttle(cfs_rq);
- }
}
static void __clear_buddies_last(struct sched_entity *se)
@@ -4334,23 +4346,16 @@ static inline u64 sched_cfs_bandwidth_slice(void)
}
/*
- * Replenish runtime according to assigned quota and update expiration time.
- * We use sched_clock_cpu directly instead of rq->clock to avoid adding
- * additional synchronization around rq->lock.
+ * Replenish runtime according to assigned quota. We use sched_clock_cpu
+ * directly instead of rq->clock to avoid adding additional synchronization
+ * around rq->lock.
*
* requires cfs_b->lock
*/
void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
{
- u64 now;
-
- if (cfs_b->quota == RUNTIME_INF)
- return;
-
- 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++;
+ if (cfs_b->quota != RUNTIME_INF)
+ cfs_b->runtime = cfs_b->quota;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4372,8 +4377,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
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;
+ u64 amount = 0, min_amount;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4390,61 +4394,17 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
cfs_b->idle = 0;
}
}
- expires_seq = cfs_b->expires_seq;
- expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
cfs_rq->runtime_remaining += amount;
- /*
- * we may have advanced our local expiration to account for allowed
- * spread between our sched_clock and the one on which runtime was
- * issued.
- */
- if (cfs_rq->expires_seq != expires_seq) {
- cfs_rq->expires_seq = expires_seq;
- cfs_rq->runtime_expires = expires;
- }
return cfs_rq->runtime_remaining > 0;
}
-/*
- * Note: This depends on the synchronization provided by sched_clock and the
- * fact that rq->clock snapshots this value.
- */
-static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
-{
- struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
-
- /* if the deadline is ahead of our clock, nothing to do */
- if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
- return;
-
- if (cfs_rq->runtime_remaining < 0)
- return;
-
- /*
- * If the local deadline has passed we have to consider the
- * possibility that our sched_clock is 'fast' and the global deadline
- * has not truly expired.
- *
- * Fortunately we can check determine whether this the case by checking
- * whether the global deadline(cfs_b->expires_seq) has advanced.
- */
- 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 {
- /* global deadline is ahead, expiration has passed */
- cfs_rq->runtime_remaining = 0;
- }
-}
-
static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
/* dock delta_exec before expiring quota (as it could span periods) */
cfs_rq->runtime_remaining -= delta_exec;
- expire_cfs_rq_runtime(cfs_rq);
if (likely(cfs_rq->runtime_remaining > 0))
return;
@@ -4535,7 +4495,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- long task_delta, dequeue = 1;
+ long task_delta, idle_task_delta, dequeue = 1;
bool empty;
se = cfs_rq->tg->se[cpu_of(rq_of(cfs_rq))];
@@ -4546,6 +4506,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
rcu_read_unlock();
task_delta = cfs_rq->h_nr_running;
+ idle_task_delta = cfs_rq->idle_h_nr_running;
for_each_sched_entity(se) {
struct cfs_rq *qcfs_rq = cfs_rq_of(se);
/* throttled entity or throttle-on-deactivate */
@@ -4555,6 +4516,7 @@ static void throttle_cfs_rq(struct cfs_rq *cfs_rq)
if (dequeue)
dequeue_entity(qcfs_rq, se, DEQUEUE_SLEEP);
qcfs_rq->h_nr_running -= task_delta;
+ qcfs_rq->idle_h_nr_running -= idle_task_delta;
if (qcfs_rq->load.weight)
dequeue = 0;
@@ -4593,8 +4555,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
struct rq *rq = rq_of(cfs_rq);
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
struct sched_entity *se;
- int enqueue = 1;
- long task_delta;
+ long task_delta, idle_task_delta;
se = cfs_rq->tg->se[cpu_of(rq)];
@@ -4614,31 +4575,64 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
return;
task_delta = cfs_rq->h_nr_running;
+ idle_task_delta = cfs_rq->idle_h_nr_running;
for_each_sched_entity(se) {
if (se->on_rq)
- enqueue = 0;
+ break;
+ cfs_rq = cfs_rq_of(se);
+ enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+
+ cfs_rq->h_nr_running += task_delta;
+ cfs_rq->idle_h_nr_running += idle_task_delta;
+
+ /* end evaluation on encountering a throttled cfs_rq */
+ if (cfs_rq_throttled(cfs_rq))
+ goto unthrottle_throttle;
+ }
+ for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
- if (enqueue)
- enqueue_entity(cfs_rq, se, ENQUEUE_WAKEUP);
+
cfs_rq->h_nr_running += task_delta;
+ cfs_rq->idle_h_nr_running += idle_task_delta;
+
+ /* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
+ goto unthrottle_throttle;
+
+ /*
+ * One parent has been throttled and cfs_rq removed from the
+ * list. Add it back to not break the leaf list.
+ */
+ if (throttled_hierarchy(cfs_rq))
+ list_add_leaf_cfs_rq(cfs_rq);
+ }
+
+ /* At this point se is NULL and we are at root level*/
+ add_nr_running(rq, task_delta);
+
+unthrottle_throttle:
+ /*
+ * 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);
- if (!se)
- add_nr_running(rq, task_delta);
-
/* Determine whether we need to wake up potentially idle CPU: */
if (rq->curr == rq->idle && rq->cfs.nr_running)
resched_curr(rq);
}
-static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
- u64 remaining, u64 expires)
+static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
{
struct cfs_rq *cfs_rq;
u64 runtime;
@@ -4663,7 +4657,6 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
remaining -= runtime;
cfs_rq->runtime_remaining += runtime;
- cfs_rq->runtime_expires = expires;
/* we check whether we're throttled above */
if (cfs_rq->runtime_remaining > 0)
@@ -4688,7 +4681,7 @@ next:
*/
static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags)
{
- u64 runtime, runtime_expires;
+ u64 runtime;
int throttled;
/* no need to continue the timer with no bandwidth constraint */
@@ -4716,8 +4709,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
/* account preceding periods in which throttling occurred */
cfs_b->nr_throttled += overrun;
- runtime_expires = cfs_b->runtime_expires;
-
/*
* This check is repeated as we are holding onto the new bandwidth while
* we unthrottle. This can potentially race with an unthrottled group
@@ -4730,8 +4721,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
cfs_b->distribute_running = 1;
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
/* we can't nest cfs_b->lock while distributing bandwidth */
- runtime = distribute_cfs_runtime(cfs_b, runtime,
- runtime_expires);
+ runtime = distribute_cfs_runtime(cfs_b, runtime);
raw_spin_lock_irqsave(&cfs_b->lock, flags);
cfs_b->distribute_running = 0;
@@ -4808,8 +4798,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
return;
raw_spin_lock(&cfs_b->lock);
- if (cfs_b->quota != RUNTIME_INF &&
- cfs_rq->runtime_expires == cfs_b->runtime_expires) {
+ if (cfs_b->quota != RUNTIME_INF) {
cfs_b->runtime += slack_runtime;
/* we are under rq->lock, defer unthrottling using a timer */
@@ -4842,7 +4831,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
{
u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
unsigned long flags;
- u64 expires;
/* confirm we're still not at a refresh boundary */
raw_spin_lock_irqsave(&cfs_b->lock, flags);
@@ -4859,7 +4847,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
runtime = cfs_b->runtime;
- expires = cfs_b->runtime_expires;
if (runtime)
cfs_b->distribute_running = 1;
@@ -4868,11 +4855,10 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
if (!runtime)
return;
- runtime = distribute_cfs_runtime(cfs_b, runtime, expires);
+ runtime = distribute_cfs_runtime(cfs_b, runtime);
raw_spin_lock_irqsave(&cfs_b->lock, flags);
- if (expires == cfs_b->runtime_expires)
- lsub_positive(&cfs_b->runtime, runtime);
+ lsub_positive(&cfs_b->runtime, runtime);
cfs_b->distribute_running = 0;
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
}
@@ -4965,29 +4951,37 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
if (!overrun)
break;
+ idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
+
if (++count > 3) {
u64 new, old = ktime_to_ns(cfs_b->period);
- new = (old * 147) / 128; /* ~115% */
- new = min(new, max_cfs_quota_period);
-
- cfs_b->period = ns_to_ktime(new);
-
- /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
- cfs_b->quota *= new;
- cfs_b->quota = div64_u64(cfs_b->quota, old);
-
- pr_warn_ratelimited(
- "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
- smp_processor_id(),
- div_u64(new, NSEC_PER_USEC),
- div_u64(cfs_b->quota, NSEC_PER_USEC));
+ /*
+ * Grow period by a factor of 2 to avoid losing precision.
+ * Precision loss in the quota/period ratio can cause __cfs_schedulable
+ * to fail.
+ */
+ new = old * 2;
+ if (new < max_cfs_quota_period) {
+ cfs_b->period = ns_to_ktime(new);
+ cfs_b->quota *= 2;
+
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(new, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ } else {
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(old, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ }
/* reset count so we don't come right back in here */
count = 0;
}
-
- idle = do_sched_cfs_period_timer(cfs_b, overrun, flags);
}
if (idle)
cfs_b->period_active = 0;
@@ -5019,17 +5013,13 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
- u64 overrun;
-
lockdep_assert_held(&cfs_b->lock);
if (cfs_b->period_active)
return;
cfs_b->period_active = 1;
- overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
- cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
- cfs_b->expires_seq++;
+ hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}
@@ -5229,6 +5219,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
{
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
+ int idle_h_nr_running = task_has_idle_policy(p);
/*
* The code below (indirectly) updates schedutil which looks at
@@ -5252,30 +5243,38 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
cfs_rq = cfs_rq_of(se);
enqueue_entity(cfs_rq, se, flags);
- /*
- * end evaluation on encountering a throttled cfs_rq
- *
- * note: in the case of encountering a throttled cfs_rq we will
- * post the final h_nr_running increment below.
- */
- if (cfs_rq_throttled(cfs_rq))
- break;
cfs_rq->h_nr_running++;
+ cfs_rq->idle_h_nr_running += idle_h_nr_running;
+
+ /* end evaluation on encountering a throttled cfs_rq */
+ if (cfs_rq_throttled(cfs_rq))
+ goto enqueue_throttle;
flags = ENQUEUE_WAKEUP;
}
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
+
+ update_load_avg(cfs_rq, se, UPDATE_TG);
+ update_cfs_group(se);
+
cfs_rq->h_nr_running++;
+ cfs_rq->idle_h_nr_running += idle_h_nr_running;
+ /* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
- break;
+ goto enqueue_throttle;
- update_load_avg(cfs_rq, se, UPDATE_TG);
- update_cfs_group(se);
+ /*
+ * One parent has been throttled and cfs_rq removed from the
+ * list. Add it back to not break the leaf list.
+ */
+ if (throttled_hierarchy(cfs_rq))
+ list_add_leaf_cfs_rq(cfs_rq);
}
+enqueue_throttle:
if (!se) {
add_nr_running(rq, 1);
/*
@@ -5329,20 +5328,18 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
struct cfs_rq *cfs_rq;
struct sched_entity *se = &p->se;
int task_sleep = flags & DEQUEUE_SLEEP;
+ int idle_h_nr_running = task_has_idle_policy(p);
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
dequeue_entity(cfs_rq, se, flags);
- /*
- * end evaluation on encountering a throttled cfs_rq
- *
- * note: in the case of encountering a throttled cfs_rq we will
- * post the final h_nr_running decrement below.
- */
- if (cfs_rq_throttled(cfs_rq))
- break;
cfs_rq->h_nr_running--;
+ cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+
+ /* end evaluation on encountering a throttled cfs_rq */
+ if (cfs_rq_throttled(cfs_rq))
+ goto dequeue_throttle;
/* Don't dequeue parent if it has other entities besides us */
if (cfs_rq->load.weight) {
@@ -5361,15 +5358,20 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
for_each_sched_entity(se) {
cfs_rq = cfs_rq_of(se);
+
+ update_load_avg(cfs_rq, se, UPDATE_TG);
+ update_cfs_group(se);
+
cfs_rq->h_nr_running--;
+ cfs_rq->idle_h_nr_running -= idle_h_nr_running;
+ /* end evaluation on encountering a throttled cfs_rq */
if (cfs_rq_throttled(cfs_rq))
- break;
+ goto dequeue_throttle;
- update_load_avg(cfs_rq, se, UPDATE_TG);
- update_cfs_group(se);
}
+dequeue_throttle:
if (!se)
sub_nr_running(rq, 1);
@@ -6243,6 +6245,7 @@ static inline int select_idle_smt(struct task_struct *p, int target)
*/
static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int target)
{
+ struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
struct sched_domain *this_sd;
u64 avg_cost, avg_idle;
u64 time, cost;
@@ -6273,11 +6276,11 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
time = local_clock();
- for_each_cpu_wrap(cpu, sched_domain_span(sd), target) {
+ cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
+
+ for_each_cpu_wrap(cpu, cpus, target) {
if (!--nr)
return -1;
- if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
- continue;
if (available_idle_cpu(cpu))
break;
}
@@ -7659,7 +7662,15 @@ static int detach_tasks(struct lb_env *env)
if (!can_migrate_task(p, env))
goto next;
- load = task_h_load(p);
+ /*
+ * Depending of the number of CPUs and tasks and the
+ * cgroup hierarchy, task_h_load() can return a null
+ * value. Make sure that env->imbalance decreases
+ * otherwise detach_tasks() will stop only after
+ * detaching up to loop_max tasks.
+ */
+ load = max_t(unsigned long, task_h_load(p), 1);
+
if (sched_feat(LB_MIN) && load < 16 && !env->sd->nr_balance_failed)
goto next;
@@ -7754,6 +7765,7 @@ static void attach_tasks(struct lb_env *env)
rq_unlock(env->dst_rq, &rf);
}
+#ifdef CONFIG_NO_HZ_COMMON
static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq)
{
if (cfs_rq->avg.load_avg)
@@ -7781,6 +7793,41 @@ static inline bool others_have_blocked(struct rq *rq)
return false;
}
+static inline void update_blocked_load_status(struct rq *rq, bool has_blocked)
+{
+ rq->last_blocked_load_update_tick = jiffies;
+
+ if (!has_blocked)
+ rq->has_blocked_load = 0;
+}
+#else
+static inline bool cfs_rq_has_blocked(struct cfs_rq *cfs_rq) { return false; }
+static inline bool others_have_blocked(struct rq *rq) { return false; }
+static inline void update_blocked_load_status(struct rq *rq, bool has_blocked) {}
+#endif
+
+static bool __update_blocked_others(struct rq *rq, bool *done)
+{
+ const struct sched_class *curr_class;
+ u64 now = rq_clock_pelt(rq);
+ bool decayed;
+
+ /*
+ * update_load_avg() can call cpufreq_update_util(). Make sure that RT,
+ * DL and IRQ signals have been updated before updating CFS.
+ */
+ curr_class = rq->curr->sched_class;
+
+ decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
+ update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+ update_irq_load_avg(rq, 0);
+
+ if (others_have_blocked(rq))
+ *done = false;
+
+ return decayed;
+}
+
#ifdef CONFIG_FAIR_GROUP_SCHED
static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
@@ -7800,16 +7847,11 @@ static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
return true;
}
-static void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
{
- struct rq *rq = cpu_rq(cpu);
struct cfs_rq *cfs_rq, *pos;
- const struct sched_class *curr_class;
- struct rq_flags rf;
- bool done = true;
-
- rq_lock_irqsave(rq, &rf);
- update_rq_clock(rq);
+ bool decayed = false;
+ int cpu = cpu_of(rq);
/*
* Iterates the task_group tree in a bottom up fashion, see
@@ -7818,9 +7860,13 @@ static void update_blocked_averages(int cpu)
for_each_leaf_cfs_rq_safe(rq, cfs_rq, pos) {
struct sched_entity *se;
- if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq))
+ if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) {
update_tg_load_avg(cfs_rq, 0);
+ if (cfs_rq == &rq->cfs)
+ decayed = true;
+ }
+
/* Propagate pending load changes to the parent, if any: */
se = cfs_rq->tg->se[cpu];
if (se && !skip_blocked_update(se))
@@ -7835,23 +7881,10 @@ static void update_blocked_averages(int cpu)
/* Don't need periodic decay once load/util_avg are null */
if (cfs_rq_has_blocked(cfs_rq))
- done = false;
+ *done = false;
}
- curr_class = rq->curr->sched_class;
- update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
- update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
- update_irq_load_avg(rq, 0);
- /* Don't need periodic decay once load/util_avg are null */
- if (others_have_blocked(rq))
- done = false;
-
-#ifdef CONFIG_NO_HZ_COMMON
- rq->last_blocked_load_update_tick = jiffies;
- if (done)
- rq->has_blocked_load = 0;
-#endif
- rq_unlock_irqrestore(rq, &rf);
+ return decayed;
}
/*
@@ -7901,27 +7934,16 @@ static unsigned long task_h_load(struct task_struct *p)
cfs_rq_load_avg(cfs_rq) + 1);
}
#else
-static inline void update_blocked_averages(int cpu)
+static bool __update_blocked_fair(struct rq *rq, bool *done)
{
- struct rq *rq = cpu_rq(cpu);
struct cfs_rq *cfs_rq = &rq->cfs;
- const struct sched_class *curr_class;
- struct rq_flags rf;
+ bool decayed;
- rq_lock_irqsave(rq, &rf);
- update_rq_clock(rq);
- update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+ decayed = update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq);
+ if (cfs_rq_has_blocked(cfs_rq))
+ *done = false;
- curr_class = rq->curr->sched_class;
- update_rt_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &rt_sched_class);
- update_dl_rq_load_avg(rq_clock_pelt(rq), rq, curr_class == &dl_sched_class);
- update_irq_load_avg(rq, 0);
-#ifdef CONFIG_NO_HZ_COMMON
- rq->last_blocked_load_update_tick = jiffies;
- if (!cfs_rq_has_blocked(cfs_rq) && !others_have_blocked(rq))
- rq->has_blocked_load = 0;
-#endif
- rq_unlock_irqrestore(rq, &rf);
+ return decayed;
}
static unsigned long task_h_load(struct task_struct *p)
@@ -7930,6 +7952,24 @@ static unsigned long task_h_load(struct task_struct *p)
}
#endif
+static void update_blocked_averages(int cpu)
+{
+ bool decayed = false, done = true;
+ struct rq *rq = cpu_rq(cpu);
+ struct rq_flags rf;
+
+ rq_lock_irqsave(rq, &rf);
+ update_rq_clock(rq);
+
+ decayed |= __update_blocked_others(rq, &done);
+ decayed |= __update_blocked_fair(rq, &done);
+
+ update_blocked_load_status(rq, !done);
+ if (decayed)
+ cpufreq_update_util(rq, 0);
+ rq_unlock_irqrestore(rq, &rf);
+}
+
/********** Helpers for find_busiest_group ************************/
/*
@@ -9633,7 +9673,12 @@ static void kick_ilb(unsigned int flags)
{
int ilb_cpu;
- nohz.next_balance++;
+ /*
+ * Increase nohz.next_balance only when if full ilb is triggered but
+ * not if we only update stats.
+ */
+ if (flags & NOHZ_BALANCE_KICK)
+ nohz.next_balance = jiffies+1;
ilb_cpu = find_new_ilb();
@@ -9952,6 +9997,14 @@ static bool _nohz_idle_balance(struct rq *this_rq, unsigned int flags,
}
}
+ /*
+ * next_balance will be updated only when there is a need.
+ * When the CPU is attached to null domain for ex, it will not be
+ * updated.
+ */
+ if (likely(update_next_balance))
+ nohz.next_balance = next_balance;
+
/* Newly idle CPU doesn't need an update */
if (idle != CPU_NEWLY_IDLE) {
update_blocked_averages(this_cpu);
@@ -9972,14 +10025,6 @@ abort:
if (has_blocked_load)
WRITE_ONCE(nohz.has_blocked, 1);
- /*
- * next_balance will be updated only when there is a need.
- * When the CPU is attached to null domain for ex, it will not be
- * updated.
- */
- if (likely(update_next_balance))
- nohz.next_balance = next_balance;
-
return ret;
}
diff --git a/kernel/sched/loadavg.c b/kernel/sched/loadavg.c
index 28a516575c18..de22da666ac7 100644
--- a/kernel/sched/loadavg.c
+++ b/kernel/sched/loadavg.c
@@ -231,16 +231,11 @@ static inline int calc_load_read_idx(void)
return calc_load_idx & 1;
}
-void calc_load_nohz_start(void)
+static void calc_load_nohz_fold(struct rq *rq)
{
- struct rq *this_rq = this_rq();
long delta;
- /*
- * We're going into NO_HZ mode, if there's any pending delta, fold it
- * into the pending NO_HZ delta.
- */
- delta = calc_load_fold_active(this_rq, 0);
+ delta = calc_load_fold_active(rq, 0);
if (delta) {
int idx = calc_load_write_idx();
@@ -248,6 +243,24 @@ void calc_load_nohz_start(void)
}
}
+void calc_load_nohz_start(void)
+{
+ /*
+ * We're going into NO_HZ mode, if there's any pending delta, fold it
+ * into the pending NO_HZ delta.
+ */
+ calc_load_nohz_fold(this_rq());
+}
+
+/*
+ * Keep track of the load for NOHZ_FULL, must be called between
+ * calc_load_nohz_{start,stop}().
+ */
+void calc_load_nohz_remote(struct rq *rq)
+{
+ calc_load_nohz_fold(rq);
+}
+
void calc_load_nohz_stop(void)
{
struct rq *this_rq = this_rq();
@@ -268,7 +281,7 @@ void calc_load_nohz_stop(void)
this_rq->calc_load_update += LOAD_FREQ;
}
-static long calc_load_nohz_fold(void)
+static long calc_load_nohz_read(void)
{
int idx = calc_load_read_idx();
long delta = 0;
@@ -323,7 +336,7 @@ static void calc_global_nohz(void)
}
#else /* !CONFIG_NO_HZ_COMMON */
-static inline long calc_load_nohz_fold(void) { return 0; }
+static inline long calc_load_nohz_read(void) { return 0; }
static inline void calc_global_nohz(void) { }
#endif /* CONFIG_NO_HZ_COMMON */
@@ -346,7 +359,7 @@ void calc_global_load(unsigned long ticks)
/*
* Fold the 'old' NO_HZ-delta to include all NO_HZ CPUs.
*/
- delta = calc_load_nohz_fold();
+ delta = calc_load_nohz_read();
if (delta)
atomic_long_add(delta, &calc_load_tasks);
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 517e3719027e..9154e745f097 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -185,7 +185,8 @@ static void group_init(struct psi_group *group)
for_each_possible_cpu(cpu)
seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
- group->avg_next_update = sched_clock() + psi_period;
+ group->avg_last_update = sched_clock();
+ group->avg_next_update = group->avg_last_update + psi_period;
INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
mutex_init(&group->avgs_lock);
/* Init trigger-related members */
@@ -481,7 +482,7 @@ static u64 window_update(struct psi_window *win, u64 now, u64 value)
u32 remaining;
remaining = win->size - elapsed;
- growth += div_u64(win->prev_growth * remaining, win->size);
+ growth += div64_u64(win->prev_growth * remaining, win->size);
}
return growth;
@@ -1198,6 +1199,9 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf,
if (static_branch_likely(&psi_disabled))
return -EOPNOTSUPP;
+ if (!nbytes)
+ return -EINVAL;
+
buf_size = min(nbytes, sizeof(buf));
if (copy_from_user(buf, user_buf, buf_size))
return -EFAULT;
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 1e6b909dca36..c4108c93b2cf 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -9,6 +9,8 @@
int sched_rr_timeslice = RR_TIMESLICE;
int sysctl_sched_rr_timeslice = (MSEC_PER_SEC / HZ) * RR_TIMESLICE;
+/* More than 4 hours if BW_SHIFT equals 20. */
+static const u64 max_rt_runtime = MAX_BW;
static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun);
@@ -2522,6 +2524,12 @@ static int tg_set_rt_bandwidth(struct task_group *tg,
if (rt_period == 0)
return -EINVAL;
+ /*
+ * Bound quota to defend quota against overflow during bandwidth shift.
+ */
+ if (rt_runtime != RUNTIME_INF && rt_runtime > max_rt_runtime)
+ return -EINVAL;
+
mutex_lock(&rt_constraints_mutex);
read_lock(&tasklist_lock);
err = __rt_schedulable(tg, rt_period, rt_runtime);
@@ -2643,7 +2651,9 @@ static int sched_rt_global_validate(void)
return -EINVAL;
if ((sysctl_sched_rt_runtime != RUNTIME_INF) &&
- (sysctl_sched_rt_runtime > sysctl_sched_rt_period))
+ ((sysctl_sched_rt_runtime > sysctl_sched_rt_period) ||
+ ((u64)sysctl_sched_rt_runtime *
+ NSEC_PER_USEC > max_rt_runtime)))
return -EINVAL;
return 0;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b52ed1ada0be..2efae7800633 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -124,7 +124,13 @@ static inline void cpu_load_update_active(struct rq *this_rq) { }
#ifdef CONFIG_64BIT
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
-# define scale_load_down(w) ((w) >> SCHED_FIXEDPOINT_SHIFT)
+# define scale_load_down(w) \
+({ \
+ unsigned long __w = (w); \
+ if (__w) \
+ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
+ __w; \
+})
#else
# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
# define scale_load(w) (w)
@@ -341,8 +347,6 @@ struct cfs_bandwidth {
u64 quota;
u64 runtime;
s64 hierarchical_quota;
- u64 runtime_expires;
- int expires_seq;
short idle;
short period_active;
@@ -489,7 +493,8 @@ struct cfs_rq {
struct load_weight load;
unsigned long runnable_weight;
unsigned int nr_running;
- unsigned int h_nr_running;
+ unsigned int h_nr_running; /* SCHED_{NORMAL,BATCH,IDLE} */
+ unsigned int idle_h_nr_running; /* SCHED_IDLE */
u64 exec_clock;
u64 min_vruntime;
@@ -562,8 +567,6 @@ struct cfs_rq {
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
- int expires_seq;
- u64 runtime_expires;
s64 runtime_remaining;
u64 throttled_clock;
@@ -1797,6 +1800,8 @@ extern void init_dl_rq_bw_ratio(struct dl_rq *dl_rq);
#define BW_SHIFT 20
#define BW_UNIT (1 << BW_SHIFT)
#define RATIO_SHIFT 8
+#define MAX_BW_BITS (64 - BW_SHIFT)
+#define MAX_BW ((1ULL << MAX_BW_BITS) - 1)
unsigned long to_ratio(u64 period, u64 runtime);
extern void init_entity_runnable_average(struct sched_entity *se);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f53f89df837d..6fb3e636fbe1 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1332,7 +1332,7 @@ sd_init(struct sched_domain_topology_level *tl,
sd_flags = (*tl->sd_flags)();
if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS,
"wrong sd_flags in topology description\n"))
- sd_flags &= ~TOPOLOGY_SD_FLAGS;
+ sd_flags &= TOPOLOGY_SD_FLAGS;
/* Apply detected topology flags */
sd_flags |= dflags;
@@ -1872,6 +1872,42 @@ static struct sched_domain *build_sched_domain(struct sched_domain_topology_leve
}
/*
+ * Ensure topology masks are sane, i.e. there are no conflicts (overlaps) for
+ * any two given CPUs at this (non-NUMA) topology level.
+ */
+static bool topology_span_sane(struct sched_domain_topology_level *tl,
+ const struct cpumask *cpu_map, int cpu)
+{
+ int i;
+
+ /* NUMA levels are allowed to overlap */
+ if (tl->flags & SDTL_OVERLAP)
+ return true;
+
+ /*
+ * Non-NUMA levels cannot partially overlap - they must be either
+ * completely equal or completely disjoint. Otherwise we can end up
+ * breaking the sched_group lists - i.e. a later get_group() pass
+ * breaks the linking done for an earlier span.
+ */
+ for_each_cpu(i, cpu_map) {
+ if (i == cpu)
+ continue;
+ /*
+ * We should 'and' all those masks with 'cpu_map' to exactly
+ * match the topology we're about to build, but that can only
+ * remove CPUs, which only lessens our ability to detect
+ * overlaps
+ */
+ if (!cpumask_equal(tl->mask(cpu), tl->mask(i)) &&
+ cpumask_intersects(tl->mask(cpu), tl->mask(i)))
+ return false;
+ }
+
+ return true;
+}
+
+/*
* Find the sched_domain_topology_level where all CPU capacities are visible
* for all CPUs.
*/
@@ -1937,7 +1973,7 @@ next_level:
static int
build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *attr)
{
- enum s_alloc alloc_state;
+ enum s_alloc alloc_state = sa_none;
struct sched_domain *sd;
struct s_data d;
struct rq *rq = NULL;
@@ -1945,6 +1981,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
struct sched_domain_topology_level *tl_asym;
bool has_asym = false;
+ if (WARN_ON(cpumask_empty(cpu_map)))
+ goto error;
+
alloc_state = __visit_domain_allocation_hell(&d, cpu_map);
if (alloc_state != sa_rootdomain)
goto error;
@@ -1964,6 +2003,9 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
has_asym = true;
}
+ if (WARN_ON(!topology_span_sane(tl, cpu_map, i)))
+ goto error;
+
sd = build_sched_domain(tl, cpu_map, attr, sd, dflags, i);
if (tl == sched_domain_topology)
@@ -2015,7 +2057,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
rcu_read_unlock();
if (has_asym)
- static_branch_enable_cpuslocked(&sched_asym_cpucapacity);
+ static_branch_inc_cpuslocked(&sched_asym_cpucapacity);
if (rq && sched_debug_enabled) {
pr_info("root domain span: %*pbl (max cpu_capacity = %lu)\n",
@@ -2110,8 +2152,12 @@ int sched_init_domains(const struct cpumask *cpu_map)
*/
static void detach_destroy_domains(const struct cpumask *cpu_map)
{
+ unsigned int cpu = cpumask_any(cpu_map);
int i;
+ if (rcu_access_pointer(per_cpu(sd_asym_cpucapacity, cpu)))
+ static_branch_dec_cpuslocked(&sched_asym_cpucapacity);
+
rcu_read_lock();
for_each_cpu(i, cpu_map)
cpu_attach_domain(NULL, &def_root_domain, i);
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-04-28 06:55:36 +0000