aboutsummaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/completion.c34
-rw-r--r--kernel/sched/core.c487
-rw-r--r--kernel/sched/cpudeadline.c4
-rw-r--r--kernel/sched/cpufreq.c18
-rw-r--r--kernel/sched/cpufreq_schedutil.c8
-rw-r--r--kernel/sched/cpupri.c4
-rw-r--r--kernel/sched/cputime.c6
-rw-r--r--kernel/sched/deadline.c13
-rw-r--r--kernel/sched/debug.c6
-rw-r--r--kernel/sched/fair.c469
-rw-r--r--kernel/sched/features.h8
-rw-r--r--kernel/sched/loadavg.c33
-rw-r--r--kernel/sched/psi.c8
-rw-r--r--kernel/sched/rt.c20
-rw-r--r--kernel/sched/sched.h31
-rw-r--r--kernel/sched/swait.c22
-rw-r--r--kernel/sched/topology.c53
17 files changed, 885 insertions, 339 deletions
diff --git a/kernel/sched/completion.c b/kernel/sched/completion.c
index a1ad5b7d5521..49c14137988e 100644
--- a/kernel/sched/completion.c
+++ b/kernel/sched/completion.c
@@ -29,12 +29,12 @@ void complete(struct completion *x)
{
unsigned long flags;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
if (x->done != UINT_MAX)
x->done++;
- __wake_up_locked(&x->wait, TASK_NORMAL, 1);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ swake_up_locked(&x->wait);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete);
@@ -58,10 +58,10 @@ void complete_all(struct completion *x)
{
unsigned long flags;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
x->done = UINT_MAX;
- __wake_up_locked(&x->wait, TASK_NORMAL, 0);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ swake_up_all_locked(&x->wait);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
}
EXPORT_SYMBOL(complete_all);
@@ -70,20 +70,20 @@ do_wait_for_common(struct completion *x,
long (*action)(long), long timeout, int state)
{
if (!x->done) {
- DECLARE_WAITQUEUE(wait, current);
+ DECLARE_SWAITQUEUE(wait);
- __add_wait_queue_entry_tail_exclusive(&x->wait, &wait);
do {
if (signal_pending_state(state, current)) {
timeout = -ERESTARTSYS;
break;
}
+ __prepare_to_swait(&x->wait, &wait);
__set_current_state(state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);
timeout = action(timeout);
- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
} while (!x->done && timeout);
- __remove_wait_queue(&x->wait, &wait);
+ __finish_swait(&x->wait, &wait);
if (!x->done)
return timeout;
}
@@ -100,9 +100,9 @@ __wait_for_common(struct completion *x,
complete_acquire(x);
- spin_lock_irq(&x->wait.lock);
+ raw_spin_lock_irq(&x->wait.lock);
timeout = do_wait_for_common(x, action, timeout, state);
- spin_unlock_irq(&x->wait.lock);
+ raw_spin_unlock_irq(&x->wait.lock);
complete_release(x);
@@ -291,12 +291,12 @@ bool try_wait_for_completion(struct completion *x)
if (!READ_ONCE(x->done))
return false;
- spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
if (!x->done)
ret = false;
else if (x->done != UINT_MAX)
x->done--;
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return ret;
}
EXPORT_SYMBOL(try_wait_for_completion);
@@ -322,8 +322,8 @@ bool completion_done(struct completion *x)
* otherwise we can end up freeing the completion before complete()
* is done referencing it.
*/
- spin_lock_irqsave(&x->wait.lock, flags);
- spin_unlock_irqrestore(&x->wait.lock, flags);
+ raw_spin_lock_irqsave(&x->wait.lock, flags);
+ raw_spin_unlock_irqrestore(&x->wait.lock, flags);
return true;
}
EXPORT_SYMBOL(completion_done);
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index be7c380c07e6..8c9c77f73e69 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -45,7 +45,11 @@ const_debug unsigned int sysctl_sched_features =
* Number of tasks to iterate in a single balance run.
* Limited because this is done with IRQs disabled.
*/
+#ifdef CONFIG_PREEMPT_RT_FULL
+const_debug unsigned int sysctl_sched_nr_migrate = 8;
+#else
const_debug unsigned int sysctl_sched_nr_migrate = 32;
+#endif
/*
* period over which we measure -rt task CPU usage in us.
@@ -317,7 +321,7 @@ static void hrtick_rq_init(struct rq *rq)
rq->hrtick_csd.info = rq;
#endif
- hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
rq->hrtick_timer.function = hrtick;
}
#else /* CONFIG_SCHED_HRTICK */
@@ -399,9 +403,15 @@ static bool set_nr_if_polling(struct task_struct *p)
#endif
#endif
-static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task,
+ bool sleeper)
{
- struct wake_q_node *node = &task->wake_q;
+ struct wake_q_node *node;
+
+ if (sleeper)
+ node = &task->wake_q_sleeper;
+ else
+ node = &task->wake_q;
/*
* Atomically grab the task, if ->wake_q is !nil already it means
@@ -437,7 +447,13 @@ static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
*/
void wake_q_add(struct wake_q_head *head, struct task_struct *task)
{
- if (__wake_q_add(head, task))
+ if (__wake_q_add(head, task, false))
+ get_task_struct(task);
+}
+
+void wake_q_add_sleeper(struct wake_q_head *head, struct task_struct *task)
+{
+ if (__wake_q_add(head, task, true))
get_task_struct(task);
}
@@ -460,28 +476,39 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
*/
void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
{
- if (!__wake_q_add(head, task))
+ if (!__wake_q_add(head, task, false))
put_task_struct(task);
}
-void wake_up_q(struct wake_q_head *head)
+void __wake_up_q(struct wake_q_head *head, bool sleeper)
{
struct wake_q_node *node = head->first;
while (node != WAKE_Q_TAIL) {
struct task_struct *task;
- task = container_of(node, struct task_struct, wake_q);
+ if (sleeper)
+ task = container_of(node, struct task_struct, wake_q_sleeper);
+ else
+ task = container_of(node, struct task_struct, wake_q);
+
BUG_ON(!task);
/* Task can safely be re-inserted now: */
node = node->next;
- task->wake_q.next = NULL;
+ if (sleeper)
+ task->wake_q_sleeper.next = NULL;
+ else
+ task->wake_q.next = NULL;
/*
* wake_up_process() executes a full barrier, which pairs with
* the queueing in wake_q_add() so as not to miss wakeups.
*/
- wake_up_process(task);
+ if (sleeper)
+ wake_up_lock_sleeper(task);
+ else
+ wake_up_process(task);
+
put_task_struct(task);
}
}
@@ -517,6 +544,48 @@ void resched_curr(struct rq *rq)
trace_sched_wake_idle_without_ipi(cpu);
}
+#ifdef CONFIG_PREEMPT_LAZY
+
+static int tsk_is_polling(struct task_struct *p)
+{
+#ifdef TIF_POLLING_NRFLAG
+ return test_tsk_thread_flag(p, TIF_POLLING_NRFLAG);
+#else
+ return 0;
+#endif
+}
+
+void resched_curr_lazy(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ int cpu;
+
+ if (!sched_feat(PREEMPT_LAZY)) {
+ resched_curr(rq);
+ return;
+ }
+
+ lockdep_assert_held(&rq->lock);
+
+ if (test_tsk_need_resched(curr))
+ return;
+
+ if (test_tsk_need_resched_lazy(curr))
+ return;
+
+ set_tsk_need_resched_lazy(curr);
+
+ cpu = cpu_of(rq);
+ if (cpu == smp_processor_id())
+ return;
+
+ /* NEED_RESCHED_LAZY must be visible before we test polling */
+ smp_mb();
+ if (!tsk_is_polling(curr))
+ smp_send_reschedule(cpu);
+}
+#endif
+
void resched_cpu(int cpu)
{
struct rq *rq = cpu_rq(cpu);
@@ -930,10 +999,10 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
*/
static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
{
- if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
return false;
- if (is_per_cpu_kthread(p))
+ if (is_per_cpu_kthread(p) || __migrate_disabled(p))
return cpu_online(cpu);
return cpu_active(cpu);
@@ -982,6 +1051,7 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf,
struct migration_arg {
struct task_struct *task;
int dest_cpu;
+ bool done;
};
/*
@@ -1017,6 +1087,11 @@ static int migration_cpu_stop(void *data)
struct task_struct *p = arg->task;
struct rq *rq = this_rq();
struct rq_flags rf;
+ int dest_cpu = arg->dest_cpu;
+
+ /* We don't look at arg after this point. */
+ smp_mb();
+ arg->done = true;
/*
* The original target CPU might have gone down and we might
@@ -1025,7 +1100,7 @@ static int migration_cpu_stop(void *data)
local_irq_disable();
/*
* We need to explicitly wake pending tasks before running
- * __migrate_task() such that we will not miss enforcing cpus_allowed
+ * __migrate_task() such that we will not miss enforcing cpus_ptr
* during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
*/
sched_ttwu_pending();
@@ -1039,9 +1114,9 @@ static int migration_cpu_stop(void *data)
*/
if (task_rq(p) == rq) {
if (task_on_rq_queued(p))
- rq = __migrate_task(rq, &rf, p, arg->dest_cpu);
+ rq = __migrate_task(rq, &rf, p, dest_cpu);
else
- p->wake_cpu = arg->dest_cpu;
+ p->wake_cpu = dest_cpu;
}
rq_unlock(rq, &rf);
raw_spin_unlock(&p->pi_lock);
@@ -1056,10 +1131,19 @@ static int migration_cpu_stop(void *data)
*/
void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
{
- cpumask_copy(&p->cpus_allowed, new_mask);
- p->nr_cpus_allowed = cpumask_weight(new_mask);
+ cpumask_copy(&p->cpus_mask, new_mask);
+ if (p->cpus_ptr == &p->cpus_mask)
+ p->nr_cpus_allowed = cpumask_weight(new_mask);
}
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+int __migrate_disabled(struct task_struct *p)
+{
+ return p->migrate_disable;
+}
+EXPORT_SYMBOL_GPL(__migrate_disabled);
+#endif
+
void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
struct rq *rq = task_rq(p);
@@ -1126,7 +1210,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
goto out;
}
- if (cpumask_equal(&p->cpus_allowed, new_mask))
+ if (cpumask_equal(&p->cpus_mask, new_mask))
goto out;
dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
@@ -1148,7 +1232,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p,
}
/* Can the task run on the task's current CPU? If so, we're done */
- if (cpumask_test_cpu(task_cpu(p), new_mask))
+ if (cpumask_test_cpu(task_cpu(p), new_mask) ||
+ p->cpus_ptr != &p->cpus_mask)
goto out;
if (task_running(rq, p) || p->state == TASK_WAKING) {
@@ -1286,10 +1371,10 @@ static int migrate_swap_stop(void *data)
if (task_cpu(arg->src_task) != arg->src_cpu)
goto unlock;
- if (!cpumask_test_cpu(arg->dst_cpu, &arg->src_task->cpus_allowed))
+ if (!cpumask_test_cpu(arg->dst_cpu, arg->src_task->cpus_ptr))
goto unlock;
- if (!cpumask_test_cpu(arg->src_cpu, &arg->dst_task->cpus_allowed))
+ if (!cpumask_test_cpu(arg->src_cpu, arg->dst_task->cpus_ptr))
goto unlock;
__migrate_swap_task(arg->src_task, arg->dst_cpu);
@@ -1331,10 +1416,10 @@ int migrate_swap(struct task_struct *cur, struct task_struct *p,
if (!cpu_active(arg.src_cpu) || !cpu_active(arg.dst_cpu))
goto out;
- if (!cpumask_test_cpu(arg.dst_cpu, &arg.src_task->cpus_allowed))
+ if (!cpumask_test_cpu(arg.dst_cpu, arg.src_task->cpus_ptr))
goto out;
- if (!cpumask_test_cpu(arg.src_cpu, &arg.dst_task->cpus_allowed))
+ if (!cpumask_test_cpu(arg.src_cpu, arg.dst_task->cpus_ptr))
goto out;
trace_sched_swap_numa(cur, arg.src_cpu, p, arg.dst_cpu);
@@ -1345,6 +1430,18 @@ out:
}
#endif /* CONFIG_NUMA_BALANCING */
+static bool check_task_state(struct task_struct *p, long match_state)
+{
+ bool match = false;
+
+ raw_spin_lock_irq(&p->pi_lock);
+ if (p->state == match_state || p->saved_state == match_state)
+ match = true;
+ raw_spin_unlock_irq(&p->pi_lock);
+
+ return match;
+}
+
/*
* wait_task_inactive - wait for a thread to unschedule.
*
@@ -1389,7 +1486,7 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
* is actually now running somewhere else!
*/
while (task_running(rq, p)) {
- if (match_state && unlikely(p->state != match_state))
+ if (match_state && !check_task_state(p, match_state))
return 0;
cpu_relax();
}
@@ -1404,7 +1501,8 @@ unsigned long wait_task_inactive(struct task_struct *p, long match_state)
running = task_running(rq, p);
queued = task_on_rq_queued(p);
ncsw = 0;
- if (!match_state || p->state == match_state)
+ if (!match_state || p->state == match_state ||
+ p->saved_state == match_state)
ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
task_rq_unlock(rq, p, &rf);
@@ -1479,7 +1577,7 @@ void kick_process(struct task_struct *p)
EXPORT_SYMBOL_GPL(kick_process);
/*
- * ->cpus_allowed is protected by both rq->lock and p->pi_lock
+ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
*
* A few notes on cpu_active vs cpu_online:
*
@@ -1519,14 +1617,14 @@ static int select_fallback_rq(int cpu, struct task_struct *p)
for_each_cpu(dest_cpu, nodemask) {
if (!cpu_active(dest_cpu))
continue;
- if (cpumask_test_cpu(dest_cpu, &p->cpus_allowed))
+ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr))
return dest_cpu;
}
}
for (;;) {
/* Any allowed, online CPU? */
- for_each_cpu(dest_cpu, &p->cpus_allowed) {
+ for_each_cpu(dest_cpu, p->cpus_ptr) {
if (!is_cpu_allowed(p, dest_cpu))
continue;
@@ -1570,7 +1668,7 @@ out:
}
/*
- * The caller (fork, wakeup) owns p->pi_lock, ->cpus_allowed is stable.
+ * The caller (fork, wakeup) owns p->pi_lock, ->cpus_ptr is stable.
*/
static inline
int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
@@ -1580,11 +1678,11 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags)
if (p->nr_cpus_allowed > 1)
cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags);
else
- cpu = cpumask_any(&p->cpus_allowed);
+ cpu = cpumask_any(p->cpus_ptr);
/*
* In order not to call set_task_cpu() on a blocking task we need
- * to rely on ttwu() to place the task on a valid ->cpus_allowed
+ * to rely on ttwu() to place the task on a valid ->cpus_ptr
* CPU.
*
* Since this is common to all placement strategies, this lives here.
@@ -1999,8 +2097,27 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
*/
raw_spin_lock_irqsave(&p->pi_lock, flags);
smp_mb__after_spinlock();
- if (!(p->state & state))
+ if (!(p->state & state)) {
+ /*
+ * The task might be running due to a spinlock sleeper
+ * wakeup. Check the saved state and set it to running
+ * if the wakeup condition is true.
+ */
+ if (!(wake_flags & WF_LOCK_SLEEPER)) {
+ if (p->saved_state & state) {
+ p->saved_state = TASK_RUNNING;
+ success = 1;
+ }
+ }
goto out;
+ }
+
+ /*
+ * If this is a regular wakeup, then we can unconditionally
+ * clear the saved state of a "lock sleeper".
+ */
+ if (!(wake_flags & WF_LOCK_SLEEPER))
+ p->saved_state = TASK_RUNNING;
trace_sched_waking(p);
@@ -2115,6 +2232,18 @@ int wake_up_process(struct task_struct *p)
}
EXPORT_SYMBOL(wake_up_process);
+/**
+ * wake_up_lock_sleeper - Wake up a specific process blocked on a "sleeping lock"
+ * @p: The process to be woken up.
+ *
+ * Same as wake_up_process() above, but wake_flags=WF_LOCK_SLEEPER to indicate
+ * the nature of the wakeup.
+ */
+int wake_up_lock_sleeper(struct task_struct *p)
+{
+ return try_to_wake_up(p, TASK_UNINTERRUPTIBLE, WF_LOCK_SLEEPER);
+}
+
int wake_up_state(struct task_struct *p, unsigned int state)
{
return try_to_wake_up(p, state, 0);
@@ -2338,6 +2467,7 @@ 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().
@@ -2355,6 +2485,9 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
p->on_cpu = 0;
#endif
init_task_preempt_count(p);
+#ifdef CONFIG_HAVE_PREEMPT_LAZY
+ task_thread_info(p)->preempt_lazy_count = 0;
+#endif
#ifdef CONFIG_SMP
plist_node_init(&p->pushable_tasks, MAX_PRIO);
RB_CLEAR_NODE(&p->pushable_dl_tasks);
@@ -2395,13 +2528,14 @@ void wake_up_new_task(struct task_struct *p)
#ifdef CONFIG_SMP
/*
* Fork balancing, do it here and not earlier because:
- * - cpus_allowed can change in the fork path
+ * - cpus_ptr can change in the fork path
* - any previously selected CPU might disappear through hotplug
*
* Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
* 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);
@@ -2682,23 +2816,18 @@ static struct rq *finish_task_switch(struct task_struct *prev)
* provided by mmdrop(),
* - a sync_core for SYNC_CORE.
*/
+ /*
+ * We use mmdrop_delayed() here so we don't have to do the
+ * full __mmdrop() when we are the last user.
+ */
if (mm) {
membarrier_mm_sync_core_before_usermode(mm);
- mmdrop(mm);
+ mmdrop_delayed(mm);
}
if (unlikely(prev_state == TASK_DEAD)) {
if (prev->sched_class->task_dead)
prev->sched_class->task_dead(prev);
- /*
- * Remove function-return probe instances associated with this
- * task and put them back on the free list.
- */
- kprobe_flush_task(prev);
-
- /* Task is done with its stack. */
- put_task_stack(prev);
-
put_task_struct(prev);
}
@@ -3102,28 +3231,31 @@ 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
@@ -3368,6 +3500,8 @@ again:
BUG();
}
+static void migrate_disabled_sched(struct task_struct *p);
+
/*
* __schedule() is the main scheduler function.
*
@@ -3438,6 +3572,9 @@ static void __sched notrace __schedule(bool preempt)
rq_lock(rq, &rf);
smp_mb__after_spinlock();
+ if (__migrate_disabled(prev))
+ migrate_disabled_sched(prev);
+
/* Promote REQ to ACT */
rq->clock_update_flags <<= 1;
update_rq_clock(rq);
@@ -3459,6 +3596,7 @@ static void __sched notrace __schedule(bool preempt)
next = pick_next_task(rq, prev, &rf);
clear_tsk_need_resched(prev);
+ clear_tsk_need_resched_lazy(prev);
clear_preempt_need_resched();
if (likely(prev != next)) {
@@ -3642,6 +3780,30 @@ static void __sched notrace preempt_schedule_common(void)
} while (need_resched());
}
+#ifdef CONFIG_PREEMPT_LAZY
+/*
+ * If TIF_NEED_RESCHED is then we allow to be scheduled away since this is
+ * set by a RT task. Oterwise we try to avoid beeing scheduled out as long as
+ * preempt_lazy_count counter >0.
+ */
+static __always_inline int preemptible_lazy(void)
+{
+ if (test_thread_flag(TIF_NEED_RESCHED))
+ return 1;
+ if (current_thread_info()->preempt_lazy_count)
+ return 0;
+ return 1;
+}
+
+#else
+
+static inline int preemptible_lazy(void)
+{
+ return 1;
+}
+
+#endif
+
#ifdef CONFIG_PREEMPT
/*
* this is the entry point to schedule() from in-kernel preemption
@@ -3656,7 +3818,8 @@ asmlinkage __visible void __sched notrace preempt_schedule(void)
*/
if (likely(!preemptible()))
return;
-
+ if (!preemptible_lazy())
+ return;
preempt_schedule_common();
}
NOKPROBE_SYMBOL(preempt_schedule);
@@ -3683,6 +3846,9 @@ asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
if (likely(!preemptible()))
return;
+ if (!preemptible_lazy())
+ return;
+
do {
/*
* Because the function tracer can trace preempt_count_sub()
@@ -3857,7 +4023,8 @@ 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
@@ -4311,7 +4478,7 @@ change:
* the entire root_domain to become SCHED_DEADLINE. We
* will also fail if there's no bandwidth available.
*/
- if (!cpumask_subset(span, &p->cpus_allowed) ||
+ if (!cpumask_subset(span, p->cpus_ptr) ||
rq->rd->dl_bw.bw == 0) {
task_rq_unlock(rq, p, &rf);
return -EPERM;
@@ -4910,7 +5077,7 @@ long sched_getaffinity(pid_t pid, struct cpumask *mask)
goto out_unlock;
raw_spin_lock_irqsave(&p->pi_lock, flags);
- cpumask_and(mask, &p->cpus_allowed, cpu_active_mask);
+ cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
raw_spin_unlock_irqrestore(&p->pi_lock, flags);
out_unlock:
@@ -5405,10 +5572,11 @@ 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;
@@ -5448,7 +5616,9 @@ void init_idle(struct task_struct *idle, int cpu)
/* Set the preempt count _outside_ the spinlocks! */
init_idle_preempt_count(idle, cpu);
-
+#ifdef CONFIG_HAVE_PREEMPT_LAZY
+ task_thread_info(idle)->preempt_lazy_count = 0;
+#endif
/*
* The idle tasks have their own, simple scheduling class:
*/
@@ -5487,7 +5657,7 @@ int task_can_attach(struct task_struct *p,
* allowed nodes is unnecessary. Thus, cpusets are not
* applicable for such threads. This prevents checking for
* success of set_cpus_allowed_ptr() on all attached tasks
- * before cpus_allowed may be changed.
+ * before cpus_mask may be changed.
*/
if (p->flags & PF_NO_SETAFFINITY) {
ret = -EINVAL;
@@ -5514,7 +5684,7 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
if (curr_cpu == target_cpu)
return 0;
- if (!cpumask_test_cpu(target_cpu, &p->cpus_allowed))
+ if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
return -EINVAL;
/* TODO: This is not properly updating schedstats */
@@ -5553,6 +5723,8 @@ void sched_setnuma(struct task_struct *p, int nid)
#endif /* CONFIG_NUMA_BALANCING */
#ifdef CONFIG_HOTPLUG_CPU
+static DEFINE_PER_CPU(struct mm_struct *, idle_last_mm);
+
/*
* Ensure that the idle task is using init_mm right before its CPU goes
* offline.
@@ -5562,13 +5734,17 @@ 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);
+ /*
+ * Defer the cleanup to an alive cpu. On RT we can neither
+ * call mmdrop() nor mmdrop_delayed() from here.
+ */
+ per_cpu(idle_last_mm, smp_processor_id()) = mm;
}
/*
@@ -5651,8 +5827,10 @@ static void migrate_tasks(struct rq *dead_rq, struct rq_flags *rf)
BUG_ON(!next);
put_prev_task(rq, next);
+ WARN_ON_ONCE(__migrate_disabled(next));
+
/*
- * Rules for changing task_struct::cpus_allowed are holding
+ * Rules for changing task_struct::cpus_mask are holding
* both pi_lock and rq->lock, such that holding either
* stabilizes the mask.
*
@@ -5880,6 +6058,10 @@ int sched_cpu_dying(unsigned int cpu)
update_max_interval();
nohz_balance_exit_idle(rq);
hrtick_clear(rq);
+ if (per_cpu(idle_last_mm, cpu)) {
+ mmdrop_delayed(per_cpu(idle_last_mm, cpu));
+ per_cpu(idle_last_mm, cpu) = NULL;
+ }
return 0;
}
#endif
@@ -6113,7 +6295,7 @@ void __init sched_init(void)
#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
static inline int preempt_count_equals(int preempt_offset)
{
- int nested = preempt_count() + rcu_preempt_depth();
+ int nested = preempt_count() + sched_rcu_preempt_depth();
return (nested == preempt_offset);
}
@@ -6429,8 +6611,15 @@ 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 +6754,8 @@ 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 +6784,12 @@ 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().
*/
@@ -7123,3 +7320,165 @@ const u32 sched_prio_to_wmult[40] = {
};
#undef CREATE_TRACE_POINTS
+
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+
+static inline void
+update_nr_migratory(struct task_struct *p, long delta)
+{
+ if (unlikely((p->sched_class == &rt_sched_class ||
+ p->sched_class == &dl_sched_class) &&
+ p->nr_cpus_allowed > 1)) {
+ if (p->sched_class == &rt_sched_class)
+ task_rq(p)->rt.rt_nr_migratory += delta;
+ else
+ task_rq(p)->dl.dl_nr_migratory += delta;
+ }
+}
+
+static inline void
+migrate_disable_update_cpus_allowed(struct task_struct *p)
+{
+ p->cpus_ptr = cpumask_of(smp_processor_id());
+ update_nr_migratory(p, -1);
+ p->nr_cpus_allowed = 1;
+}
+
+static inline void
+migrate_enable_update_cpus_allowed(struct task_struct *p)
+{
+ struct rq *rq;
+ struct rq_flags rf;
+
+ rq = task_rq_lock(p, &rf);
+ p->cpus_ptr = &p->cpus_mask;
+ p->nr_cpus_allowed = cpumask_weight(&p->cpus_mask);
+ update_nr_migratory(p, 1);
+ task_rq_unlock(rq, p, &rf);
+}
+
+void migrate_disable(void)
+{
+ preempt_disable();
+
+ if (++current->migrate_disable == 1) {
+ this_rq()->nr_pinned++;
+ preempt_lazy_disable();
+#ifdef CONFIG_SCHED_DEBUG
+ WARN_ON_ONCE(current->pinned_on_cpu >= 0);
+ current->pinned_on_cpu = smp_processor_id();
+#endif
+ }
+
+ preempt_enable();
+}
+EXPORT_SYMBOL(migrate_disable);
+
+static void migrate_disabled_sched(struct task_struct *p)
+{
+ if (p->migrate_disable_scheduled)
+ return;
+
+ migrate_disable_update_cpus_allowed(p);
+ p->migrate_disable_scheduled = 1;
+}
+
+void migrate_enable(void)
+{
+ struct task_struct *p = current;
+ struct rq *rq = this_rq();
+ int cpu = task_cpu(p);
+
+ WARN_ON_ONCE(p->migrate_disable <= 0);
+ if (p->migrate_disable > 1) {
+ p->migrate_disable--;
+ return;
+ }
+
+ preempt_disable();
+
+#ifdef CONFIG_SCHED_DEBUG
+ WARN_ON_ONCE(current->pinned_on_cpu != cpu);
+ current->pinned_on_cpu = -1;
+#endif
+
+ WARN_ON_ONCE(rq->nr_pinned < 1);
+
+ p->migrate_disable = 0;
+ rq->nr_pinned--;
+#ifdef CONFIG_HOTPLUG_CPU
+ if (rq->nr_pinned == 0 && unlikely(!cpu_active(cpu)) &&
+ takedown_cpu_task)
+ wake_up_process(takedown_cpu_task);
+#endif
+
+ if (!p->migrate_disable_scheduled)
+ goto out;
+
+ p->migrate_disable_scheduled = 0;
+
+ migrate_enable_update_cpus_allowed(p);
+
+ WARN_ON(smp_processor_id() != cpu);
+ if (!is_cpu_allowed(p, cpu)) {
+ struct migration_arg arg = { .task = p };
+ struct cpu_stop_work work;
+ struct rq_flags rf;
+
+ rq = task_rq_lock(p, &rf);
+ update_rq_clock(rq);
+ arg.dest_cpu = select_fallback_rq(cpu, p);
+ task_rq_unlock(rq, p, &rf);
+
+ stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop,
+ &arg, &work);
+ __schedule(true);
+ if (!work.disabled) {
+ while (!arg.done)
+ cpu_relax();
+ }
+ }
+
+out:
+ preempt_lazy_enable();
+ preempt_enable();
+}
+EXPORT_SYMBOL(migrate_enable);
+
+int cpu_nr_pinned(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ return rq->nr_pinned;
+}
+
+#elif !defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+static void migrate_disabled_sched(struct task_struct *p)
+{
+}
+
+void migrate_disable(void)
+{
+#ifdef CONFIG_SCHED_DEBUG
+ current->migrate_disable++;
+#endif
+ barrier();
+}
+EXPORT_SYMBOL(migrate_disable);
+
+void migrate_enable(void)
+{
+#ifdef CONFIG_SCHED_DEBUG
+ struct task_struct *p = current;
+
+ WARN_ON_ONCE(p->migrate_disable <= 0);
+ p->migrate_disable--;
+#endif
+ barrier();
+}
+EXPORT_SYMBOL(migrate_enable);
+#else
+static void migrate_disabled_sched(struct task_struct *p)
+{
+}
+#endif
diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c
index ec4e4a9aab5f..5cc4012572ec 100644
--- a/kernel/sched/cpudeadline.c
+++ b/kernel/sched/cpudeadline.c
@@ -120,14 +120,14 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p,
const struct sched_dl_entity *dl_se = &p->dl;
if (later_mask &&
- cpumask_and(later_mask, cp->free_cpus, &p->cpus_allowed)) {
+ cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) {
return 1;
} else {
int best_cpu = cpudl_maximum(cp);
WARN_ON(best_cpu != -1 && !cpu_present(best_cpu));
- if (cpumask_test_cpu(best_cpu, &p->cpus_allowed) &&
+ if (cpumask_test_cpu(best_cpu, p->cpus_ptr) &&
dl_time_before(dl_se->deadline, cp->elements[0].dl)) {
if (later_mask)
cpumask_set_cpu(best_cpu, later_mask);
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/cpupri.c b/kernel/sched/cpupri.c
index 9c6480e6d62d..b7abca987d94 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -94,11 +94,11 @@ int cpupri_find(struct cpupri *cp, struct task_struct *p,
if (skip)
continue;
- if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
+ if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids)
continue;
if (lowest_mask) {
- cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
+ cpumask_and(lowest_mask, p->cpus_ptr, vec->mask);
/*
* We have to ensure that we have at least one bit
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..de9f74874ec1 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -287,7 +287,7 @@ static void task_non_contending(struct task_struct *p)
dl_se->dl_non_contending = 1;
get_task_struct(p);
- hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL);
+ hrtimer_start(timer, ns_to_ktime(zerolag_time), HRTIMER_MODE_REL_HARD);
}
static void task_contending(struct sched_dl_entity *dl_se, int flags)
@@ -539,7 +539,7 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
* If we cannot preempt any rq, fall back to pick any
* online CPU:
*/
- cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);
+ cpu = cpumask_any_and(cpu_active_mask, p->cpus_ptr);
if (cpu >= nr_cpu_ids) {
/*
* Failed to find any suitable CPU.
@@ -1086,7 +1086,7 @@ void init_dl_task_timer(struct sched_dl_entity *dl_se)
{
struct hrtimer *timer = &dl_se->dl_timer;
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
timer->function = dl_task_timer;
}
@@ -1325,7 +1325,7 @@ void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
{
struct hrtimer *timer = &dl_se->inactive_timer;
- hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
timer->function = inactive_task_timer;
}
@@ -1857,7 +1857,7 @@ static void set_curr_task_dl(struct rq *rq)
static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu)
{
if (!task_running(rq, p) &&
- cpumask_test_cpu(cpu, &p->cpus_allowed))
+ cpumask_test_cpu(cpu, p->cpus_ptr))
return 1;
return 0;
}
@@ -2007,7 +2007,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq)
/* Retry if something changed. */
if (double_lock_balance(rq, later_rq)) {
if (unlikely(task_rq(task) != rq ||
- !cpumask_test_cpu(later_rq->cpu, &task->cpus_allowed) ||
+ !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) ||
task_running(rq, task) ||
!dl_task(task) ||
!task_on_rq_queued(task))) {
@@ -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..333ce07c78c6 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 */
@@ -979,6 +979,10 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
P(dl.runtime);
P(dl.deadline);
}
+#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT_BASE)
+ P(migrate_disable);
+#endif
+ P(nr_cpus_allowed);
#undef PN_SCHEDSTAT
#undef PN
#undef __PN
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5a312c030b8d..ba052a06da61 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1653,7 +1653,7 @@ static void task_numa_compare(struct task_numa_env *env,
* be incurred if the tasks were swapped.
*/
/* Skip this swap candidate if cannot move to the source cpu */
- if (!cpumask_test_cpu(env->src_cpu, &cur->cpus_allowed))
+ if (!cpumask_test_cpu(env->src_cpu, cur->cpus_ptr))
goto unlock;
/*
@@ -1751,7 +1751,7 @@ static void task_numa_find_cpu(struct task_numa_env *env,
for_each_cpu(cpu, cpumask_of_node(env->dst_nid)) {
/* Skip this CPU if the source task cannot migrate */
- if (!cpumask_test_cpu(cpu, &env->p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, env->p->cpus_ptr))
continue;
env->dst_cpu = cpu;
@@ -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)
@@ -4104,7 +4116,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
if (delta_exec > ideal_runtime) {
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
/*
* The current task ran long enough, ensure it doesn't get
* re-elected due to buddy favours.
@@ -4128,7 +4140,7 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
return;
if (delta > ideal_runtime)
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
}
static void
@@ -4270,7 +4282,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
* validating it and just reschedule.
*/
if (queued) {
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
return;
}
/*
@@ -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;
@@ -4456,7 +4416,7 @@ static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
* hierarchy can be throttled
*/
if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
}
static __always_inline
@@ -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);
}
@@ -5169,7 +5159,7 @@ static void hrtick_start_fair(struct rq *rq, struct task_struct *p)
if (delta < 0) {
if (rq->curr == p)
- resched_curr(rq);
+ resched_curr_lazy(rq);
return;
}
hrtick_start(rq, delta);
@@ -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);
@@ -5890,7 +5892,7 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
/* Skip over this group if it has no CPUs allowed */
if (!cpumask_intersects(sched_group_span(group),
- &p->cpus_allowed))
+ p->cpus_ptr))
continue;
local_group = cpumask_test_cpu(this_cpu,
@@ -6022,7 +6024,7 @@ find_idlest_group_cpu(struct sched_group *group, struct task_struct *p, int this
return cpumask_first(sched_group_span(group));
/* Traverse only the allowed CPUs */
- for_each_cpu_and(i, sched_group_span(group), &p->cpus_allowed) {
+ for_each_cpu_and(i, sched_group_span(group), p->cpus_ptr) {
if (available_idle_cpu(i)) {
struct rq *rq = cpu_rq(i);
struct cpuidle_state *idle = idle_get_state(rq);
@@ -6062,7 +6064,7 @@ static inline int find_idlest_cpu(struct sched_domain *sd, struct task_struct *p
{
int new_cpu = cpu;
- if (!cpumask_intersects(sched_domain_span(sd), &p->cpus_allowed))
+ if (!cpumask_intersects(sched_domain_span(sd), p->cpus_ptr))
return prev_cpu;
/*
@@ -6179,7 +6181,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
if (!test_idle_cores(target, false))
return -1;
- cpumask_and(cpus, sched_domain_span(sd), &p->cpus_allowed);
+ cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
for_each_cpu_wrap(core, cpus, target) {
bool idle = true;
@@ -6213,7 +6215,7 @@ static int select_idle_smt(struct task_struct *p, int target)
return -1;
for_each_cpu(cpu, cpu_smt_mask(target)) {
- if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
if (available_idle_cpu(cpu))
return cpu;
@@ -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_ptr);
+
+ 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;
}
@@ -6313,7 +6316,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
recent_used_cpu != target &&
cpus_share_cache(recent_used_cpu, target) &&
available_idle_cpu(recent_used_cpu) &&
- cpumask_test_cpu(p->recent_used_cpu, &p->cpus_allowed)) {
+ cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr)) {
/*
* Replace recent_used_cpu with prev as it is a potential
* candidate for the next wake:
@@ -6659,7 +6662,7 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
int max_spare_cap_cpu = -1;
for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
- if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
continue;
/* Skip CPUs that will be overutilized. */
@@ -6748,7 +6751,7 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
}
want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
- cpumask_test_cpu(cpu, &p->cpus_allowed);
+ cpumask_test_cpu(cpu, p->cpus_ptr);
}
rcu_read_lock();
@@ -7009,7 +7012,7 @@ static void check_preempt_wakeup(struct rq *rq, struct task_struct *p, int wake_
return;
preempt:
- resched_curr(rq);
+ resched_curr_lazy(rq);
/*
* Only set the backward buddy when the current task is still
* on the rq. This can happen when a wakeup gets interleaved
@@ -7504,14 +7507,14 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
/*
* We do not migrate tasks that are:
* 1) throttled_lb_pair, or
- * 2) cannot be migrated to this CPU due to cpus_allowed, or
+ * 2) cannot be migrated to this CPU due to cpus_ptr, or
* 3) running (obviously), or
* 4) are cache-hot on their current CPU.
*/
if (throttled_lb_pair(task_group(p), env->src_cpu, env->dst_cpu))
return 0;
- if (!cpumask_test_cpu(env->dst_cpu, &p->cpus_allowed)) {
+ if (!cpumask_test_cpu(env->dst_cpu, p->cpus_ptr)) {
int cpu;
schedstat_inc(p->se.statistics.nr_failed_migrations_affine);
@@ -7531,7 +7534,7 @@ int can_migrate_task(struct task_struct *p, struct lb_env *env)
/* Prevent to re-select dst_cpu via env's CPUs: */
for_each_cpu_and(cpu, env->dst_grpmask, env->cpus) {
- if (cpumask_test_cpu(cpu, &p->cpus_allowed)) {
+ if (cpumask_test_cpu(cpu, p->cpus_ptr)) {
env->flags |= LBF_DST_PINNED;
env->new_dst_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 ************************/
/*
@@ -8158,7 +8198,7 @@ static inline int check_misfit_status(struct rq *rq, struct sched_domain *sd)
/*
* Group imbalance indicates (and tries to solve) the problem where balancing
- * groups is inadequate due to ->cpus_allowed constraints.
+ * groups is inadequate due to ->cpus_ptr constraints.
*
* Imagine a situation of two groups of 4 CPUs each and 4 tasks each with a
* cpumask covering 1 CPU of the first group and 3 CPUs of the second group.
@@ -8827,7 +8867,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
/*
* If the busiest group is imbalanced the below checks don't
* work because they assume all things are equal, which typically
- * isn't true due to cpus_allowed constraints and the like.
+ * isn't true due to cpus_ptr constraints and the like.
*/
if (busiest->group_type == group_imbalanced)
goto force_balance;
@@ -9269,7 +9309,7 @@ more_balance:
* if the curr task on busiest CPU can't be
* moved to this_cpu:
*/
- if (!cpumask_test_cpu(this_cpu, &busiest->curr->cpus_allowed)) {
+ if (!cpumask_test_cpu(this_cpu, busiest->curr->cpus_ptr)) {
raw_spin_unlock_irqrestore(&busiest->lock,
flags);
env.flags |= LBF_ALL_PINNED;
@@ -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;
}
@@ -10282,7 +10327,7 @@ static void task_fork_fair(struct task_struct *p)
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
- resched_curr(rq);
+ resched_curr_lazy(rq);
}
se->vruntime -= cfs_rq->min_vruntime;
@@ -10306,7 +10351,7 @@ prio_changed_fair(struct rq *rq, struct task_struct *p, int oldprio)
*/
if (rq->curr == p) {
if (p->prio > oldprio)
- resched_curr(rq);
+ resched_curr_lazy(rq);
} else
check_preempt_curr(rq, p, 0);
}
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index 858589b83377..4d020e6b1501 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -46,11 +46,19 @@ SCHED_FEAT(LB_BIAS, false)
*/
SCHED_FEAT(NONTASK_CAPACITY, true)
+#ifdef CONFIG_PREEMPT_RT_FULL
+SCHED_FEAT(TTWU_QUEUE, false)
+# ifdef CONFIG_PREEMPT_LAZY
+SCHED_FEAT(PREEMPT_LAZY, true)
+# endif
+#else
+
/*
* Queue remote wakeups on the target CPU and process them
* using the scheduler IPI. Reduces rq->lock contention/bounces.
*/
SCHED_FEAT(TTWU_QUEUE, true)
+#endif
/*
* When doing wakeups, attempt to limit superfluous scans of the LLC domain.
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..a910c8de0d49 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);
@@ -45,8 +47,8 @@ void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime)
raw_spin_lock_init(&rt_b->rt_runtime_lock);
- hrtimer_init(&rt_b->rt_period_timer,
- CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_init(&rt_b->rt_period_timer, CLOCK_MONOTONIC,
+ HRTIMER_MODE_REL_HARD);
rt_b->rt_period_timer.function = sched_rt_period_timer;
}
@@ -1614,7 +1616,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu)
{
if (!task_running(rq, p) &&
- cpumask_test_cpu(cpu, &p->cpus_allowed))
+ cpumask_test_cpu(cpu, p->cpus_ptr))
return 1;
return 0;
@@ -1751,7 +1753,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq)
* Also make sure that it wasn't scheduled on its rq.
*/
if (unlikely(task_rq(task) != rq ||
- !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_allowed) ||
+ !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) ||
task_running(rq, task) ||
!rt_task(task) ||
!task_on_rq_queued(task))) {
@@ -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..62d55d5a4fbf 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;
@@ -952,6 +955,10 @@ struct rq {
/* Must be inspected within a rcu lock section */
struct cpuidle_state *idle_state;
#endif
+
+#if defined(CONFIG_PREEMPT_RT_BASE) && defined(CONFIG_SMP)
+ int nr_pinned;
+#endif
};
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1591,6 +1598,7 @@ static inline int task_on_rq_migrating(struct task_struct *p)
#define WF_SYNC 0x01 /* Waker goes to sleep after wakeup */
#define WF_FORK 0x02 /* Child wakeup after fork */
#define WF_MIGRATED 0x4 /* Internal use, task got migrated */
+#define WF_LOCK_SLEEPER 0x08 /* wakeup spinlock "sleeper" */
/*
* To aid in avoiding the subversion of "niceness" due to uneven distribution
@@ -1785,6 +1793,15 @@ extern void reweight_task(struct task_struct *p, int prio);
extern void resched_curr(struct rq *rq);
extern void resched_cpu(int cpu);
+#ifdef CONFIG_PREEMPT_LAZY
+extern void resched_curr_lazy(struct rq *rq);
+#else
+static inline void resched_curr_lazy(struct rq *rq)
+{
+ resched_curr(rq);
+}
+#endif
+
extern struct rt_bandwidth def_rt_bandwidth;
extern void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime);
@@ -1797,6 +1814,8 @@ 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/swait.c b/kernel/sched/swait.c
index e83a3f8449f6..c58068d2ee06 100644
--- a/kernel/sched/swait.c
+++ b/kernel/sched/swait.c
@@ -32,6 +32,25 @@ void swake_up_locked(struct swait_queue_head *q)
}
EXPORT_SYMBOL(swake_up_locked);
+void swake_up_all_locked(struct swait_queue_head *q)
+{
+ struct swait_queue *curr;
+ int wakes = 0;
+
+ while (!list_empty(&q->task_list)) {
+
+ curr = list_first_entry(&q->task_list, typeof(*curr),
+ task_list);
+ wake_up_process(curr->task);
+ list_del_init(&curr->task_list);
+ wakes++;
+ }
+ if (pm_in_action)
+ return;
+ WARN(wakes > 2, "complete_all() with %d waiters\n", wakes);
+}
+EXPORT_SYMBOL(swake_up_all_locked);
+
void swake_up_one(struct swait_queue_head *q)
{
unsigned long flags;
@@ -51,6 +70,7 @@ void swake_up_all(struct swait_queue_head *q)
struct swait_queue *curr;
LIST_HEAD(tmp);
+ WARN_ON(irqs_disabled());
raw_spin_lock_irq(&q->lock);
list_splice_init(&q->task_list, &tmp);
while (!list_empty(&tmp)) {
@@ -69,7 +89,7 @@ void swake_up_all(struct swait_queue_head *q)
}
EXPORT_SYMBOL(swake_up_all);
-static void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
+void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait)
{
wait->task = current;
if (list_empty(&wait->task_list))
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index f53f89df837d..aa7e33d467da 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -502,6 +502,7 @@ static int init_rootdomain(struct root_domain *rd)
rd->rto_cpu = -1;
raw_spin_lock_init(&rd->rto_lock);
init_irq_work(&rd->rto_push_work, rto_push_irq_work_func);
+ rd->rto_push_work.flags |= IRQ_WORK_HARD_IRQ;
#endif
init_dl_bw(&rd->dl_bw);
@@ -1332,7 +1333,7 @@ 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 +1873,42 @@ 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 +1974,7 @@ 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 +1982,9 @@ 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 +2004,9 @@ 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 +2058,7 @@ 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 +2153,12 @@ 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 2024-04-27 11:24:22 +0000