aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/clock.c27
-rw-r--r--kernel/sched/core.c484
-rw-r--r--kernel/sched/cpufreq_schedutil.c43
-rw-r--r--kernel/sched/cputime.c4
-rw-r--r--kernel/sched/deadline.c49
-rw-r--r--kernel/sched/fair.c542
-rw-r--r--kernel/sched/idle.c47
-rw-r--r--kernel/sched/membarrier.c39
-rw-r--r--kernel/sched/psi.c107
-rw-r--r--kernel/sched/rt.c5
-rw-r--r--kernel/sched/sched.h161
-rw-r--r--kernel/sched/stats.h22
-rw-r--r--kernel/sched/topology.c99
-rw-r--r--kernel/sched/wait.c18
14 files changed, 1276 insertions, 371 deletions
diff --git a/kernel/sched/clock.c b/kernel/sched/clock.c
index e374c0c923da..5732fa75ebab 100644
--- a/kernel/sched/clock.c
+++ b/kernel/sched/clock.c
@@ -93,7 +93,7 @@ struct sched_clock_data {
static DEFINE_PER_CPU_SHARED_ALIGNED(struct sched_clock_data, sched_clock_data);
-notrace static inline struct sched_clock_data *this_scd(void)
+static __always_inline struct sched_clock_data *this_scd(void)
{
return this_cpu_ptr(&sched_clock_data);
}
@@ -244,12 +244,12 @@ late_initcall(sched_clock_init_late);
* min, max except they take wrapping into account
*/
-notrace static inline u64 wrap_min(u64 x, u64 y)
+static __always_inline u64 wrap_min(u64 x, u64 y)
{
return (s64)(x - y) < 0 ? x : y;
}
-notrace static inline u64 wrap_max(u64 x, u64 y)
+static __always_inline u64 wrap_max(u64 x, u64 y)
{
return (s64)(x - y) > 0 ? x : y;
}
@@ -260,7 +260,7 @@ notrace static inline u64 wrap_max(u64 x, u64 y)
* - filter out backward motion
* - use the GTOD tick value to create a window to filter crazy TSC values
*/
-notrace static u64 sched_clock_local(struct sched_clock_data *scd)
+static __always_inline u64 sched_clock_local(struct sched_clock_data *scd)
{
u64 now, clock, old_clock, min_clock, max_clock, gtod;
s64 delta;
@@ -287,13 +287,28 @@ again:
clock = wrap_max(clock, min_clock);
clock = wrap_min(clock, max_clock);
- if (!try_cmpxchg64(&scd->clock, &old_clock, clock))
+ if (!arch_try_cmpxchg64(&scd->clock, &old_clock, clock))
goto again;
return clock;
}
-notrace static u64 sched_clock_remote(struct sched_clock_data *scd)
+noinstr u64 local_clock(void)
+{
+ u64 clock;
+
+ if (static_branch_likely(&__sched_clock_stable))
+ return sched_clock() + __sched_clock_offset;
+
+ preempt_disable_notrace();
+ clock = sched_clock_local(this_scd());
+ preempt_enable_notrace();
+
+ return clock;
+}
+EXPORT_SYMBOL_GPL(local_clock);
+
+static notrace u64 sched_clock_remote(struct sched_clock_data *scd)
{
struct sched_clock_data *my_scd = this_scd();
u64 this_clock, remote_clock;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index daff72f00385..af017e038b48 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -152,7 +152,7 @@ __read_mostly int scheduler_running;
DEFINE_STATIC_KEY_FALSE(__sched_core_enabled);
/* kernel prio, less is more */
-static inline int __task_prio(struct task_struct *p)
+static inline int __task_prio(const struct task_struct *p)
{
if (p->sched_class == &stop_sched_class) /* trumps deadline */
return -2;
@@ -174,7 +174,8 @@ static inline int __task_prio(struct task_struct *p)
*/
/* real prio, less is less */
-static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool in_fi)
+static inline bool prio_less(const struct task_struct *a,
+ const struct task_struct *b, bool in_fi)
{
int pa = __task_prio(a), pb = __task_prio(b);
@@ -194,7 +195,8 @@ static inline bool prio_less(struct task_struct *a, struct task_struct *b, bool
return false;
}
-static inline bool __sched_core_less(struct task_struct *a, struct task_struct *b)
+static inline bool __sched_core_less(const struct task_struct *a,
+ const struct task_struct *b)
{
if (a->core_cookie < b->core_cookie)
return true;
@@ -1392,7 +1394,7 @@ static inline void uclamp_idle_reset(struct rq *rq, enum uclamp_id clamp_id,
if (!(rq->uclamp_flags & UCLAMP_FLAG_IDLE))
return;
- WRITE_ONCE(rq->uclamp[clamp_id].value, clamp_value);
+ uclamp_rq_set(rq, clamp_id, clamp_value);
}
static inline
@@ -1543,8 +1545,8 @@ static inline void uclamp_rq_inc_id(struct rq *rq, struct task_struct *p,
if (bucket->tasks == 1 || uc_se->value > bucket->value)
bucket->value = uc_se->value;
- if (uc_se->value > READ_ONCE(uc_rq->value))
- WRITE_ONCE(uc_rq->value, uc_se->value);
+ if (uc_se->value > uclamp_rq_get(rq, clamp_id))
+ uclamp_rq_set(rq, clamp_id, uc_se->value);
}
/*
@@ -1610,7 +1612,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
if (likely(bucket->tasks))
return;
- rq_clamp = READ_ONCE(uc_rq->value);
+ rq_clamp = uclamp_rq_get(rq, clamp_id);
/*
* Defensive programming: this should never happen. If it happens,
* e.g. due to future modification, warn and fixup the expected value.
@@ -1618,7 +1620,7 @@ static inline void uclamp_rq_dec_id(struct rq *rq, struct task_struct *p,
SCHED_WARN_ON(bucket->value > rq_clamp);
if (bucket->value >= rq_clamp) {
bkt_clamp = uclamp_rq_max_value(rq, clamp_id, uc_se->value);
- WRITE_ONCE(uc_rq->value, bkt_clamp);
+ uclamp_rq_set(rq, clamp_id, bkt_clamp);
}
}
@@ -2053,7 +2055,7 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags)
if (!(flags & ENQUEUE_RESTORE)) {
sched_info_enqueue(rq, p);
- psi_enqueue(p, flags & ENQUEUE_WAKEUP);
+ psi_enqueue(p, (flags & ENQUEUE_WAKEUP) && !(flags & ENQUEUE_MIGRATED));
}
uclamp_rq_inc(rq, p);
@@ -2189,14 +2191,18 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
#ifdef CONFIG_SMP
static void
-__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
static int __set_cpus_allowed_ptr(struct task_struct *p,
- const struct cpumask *new_mask,
- u32 flags);
+ struct affinity_context *ctx);
static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
{
+ struct affinity_context ac = {
+ .new_mask = cpumask_of(rq->cpu),
+ .flags = SCA_MIGRATE_DISABLE,
+ };
+
if (likely(!p->migration_disabled))
return;
@@ -2206,7 +2212,7 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
/*
* Violates locking rules! see comment in __do_set_cpus_allowed().
*/
- __do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE);
+ __do_set_cpus_allowed(p, &ac);
}
void migrate_disable(void)
@@ -2228,6 +2234,10 @@ EXPORT_SYMBOL_GPL(migrate_disable);
void migrate_enable(void)
{
struct task_struct *p = current;
+ struct affinity_context ac = {
+ .new_mask = &p->cpus_mask,
+ .flags = SCA_MIGRATE_ENABLE,
+ };
if (p->migration_disabled > 1) {
p->migration_disabled--;
@@ -2243,7 +2253,7 @@ void migrate_enable(void)
*/
preempt_disable();
if (p->cpus_ptr != &p->cpus_mask)
- __set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE);
+ __set_cpus_allowed_ptr(p, &ac);
/*
* Mustn't clear migration_disabled() until cpus_ptr points back at the
* regular cpus_mask, otherwise things that race (eg.
@@ -2523,19 +2533,25 @@ out_unlock:
* sched_class::set_cpus_allowed must do the below, but is not required to
* actually call this function.
*/
-void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
+void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx)
{
- if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
- p->cpus_ptr = new_mask;
+ if (ctx->flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) {
+ p->cpus_ptr = ctx->new_mask;
return;
}
- cpumask_copy(&p->cpus_mask, new_mask);
- p->nr_cpus_allowed = cpumask_weight(new_mask);
+ cpumask_copy(&p->cpus_mask, ctx->new_mask);
+ p->nr_cpus_allowed = cpumask_weight(ctx->new_mask);
+
+ /*
+ * Swap in a new user_cpus_ptr if SCA_USER flag set
+ */
+ if (ctx->flags & SCA_USER)
+ swap(p->user_cpus_ptr, ctx->user_mask);
}
static void
-__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags)
+__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
{
struct rq *rq = task_rq(p);
bool queued, running;
@@ -2552,7 +2568,7 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
*
* XXX do further audits, this smells like something putrid.
*/
- if (flags & SCA_MIGRATE_DISABLE)
+ if (ctx->flags & SCA_MIGRATE_DISABLE)
SCHED_WARN_ON(!p->on_cpu);
else
lockdep_assert_held(&p->pi_lock);
@@ -2571,7 +2587,7 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
if (running)
put_prev_task(rq, p);
- p->sched_class->set_cpus_allowed(p, new_mask, flags);
+ p->sched_class->set_cpus_allowed(p, ctx);
if (queued)
enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK);
@@ -2579,22 +2595,82 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32
set_next_task(rq, p);
}
+/*
+ * Used for kthread_bind() and select_fallback_rq(), in both cases the user
+ * affinity (if any) should be destroyed too.
+ */
void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
{
- __do_set_cpus_allowed(p, new_mask, 0);
+ struct affinity_context ac = {
+ .new_mask = new_mask,
+ .user_mask = NULL,
+ .flags = SCA_USER, /* clear the user requested mask */
+ };
+ union cpumask_rcuhead {
+ cpumask_t cpumask;
+ struct rcu_head rcu;
+ };
+
+ __do_set_cpus_allowed(p, &ac);
+
+ /*
+ * Because this is called with p->pi_lock held, it is not possible
+ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
+ * kfree_rcu().
+ */
+ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
+}
+
+static cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ /*
+ * See do_set_cpus_allowed() above for the rcu_head usage.
+ */
+ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
+
+ return kmalloc_node(size, GFP_KERNEL, node);
}
int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
int node)
{
- if (!src->user_cpus_ptr)
+ cpumask_t *user_mask;
+ unsigned long flags;
+
+ /*
+ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
+ * may differ by now due to racing.
+ */
+ dst->user_cpus_ptr = NULL;
+
+ /*
+ * This check is racy and losing the race is a valid situation.
+ * It is not worth the extra overhead of taking the pi_lock on
+ * every fork/clone.
+ */
+ if (data_race(!src->user_cpus_ptr))
return 0;
- dst->user_cpus_ptr = kmalloc_node(cpumask_size(), GFP_KERNEL, node);
- if (!dst->user_cpus_ptr)
+ user_mask = alloc_user_cpus_ptr(node);
+ if (!user_mask)
return -ENOMEM;
- cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ /*
+ * Use pi_lock to protect content of user_cpus_ptr
+ *
+ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
+ * do_set_cpus_allowed().
+ */
+ raw_spin_lock_irqsave(&src->pi_lock, flags);
+ if (src->user_cpus_ptr) {
+ swap(dst->user_cpus_ptr, user_mask);
+ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
+ }
+ raw_spin_unlock_irqrestore(&src->pi_lock, flags);
+
+ if (unlikely(user_mask))
+ kfree(user_mask);
+
return 0;
}
@@ -2690,6 +2766,8 @@ void release_user_cpus_ptr(struct task_struct *p)
*/
static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf,
int dest_cpu, unsigned int flags)
+ __releases(rq->lock)
+ __releases(p->pi_lock)
{
struct set_affinity_pending my_pending = { }, *pending = NULL;
bool stop_pending, complete = false;
@@ -2832,8 +2910,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
* Called with both p->pi_lock and rq->lock held; drops both before returning.
*/
static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
- const struct cpumask *new_mask,
- u32 flags,
+ struct affinity_context *ctx,
struct rq *rq,
struct rq_flags *rf)
__releases(rq->lock)
@@ -2842,7 +2919,6 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
const struct cpumask *cpu_valid_mask = cpu_active_mask;
bool kthread = p->flags & PF_KTHREAD;
- struct cpumask *user_mask = NULL;
unsigned int dest_cpu;
int ret = 0;
@@ -2862,7 +2938,7 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
cpu_valid_mask = cpu_online_mask;
}
- if (!kthread && !cpumask_subset(new_mask, cpu_allowed_mask)) {
+ if (!kthread && !cpumask_subset(ctx->new_mask, cpu_allowed_mask)) {
ret = -EINVAL;
goto out;
}
@@ -2871,18 +2947,21 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
* Must re-check here, to close a race against __kthread_bind(),
* sched_setaffinity() is not guaranteed to observe the flag.
*/
- if ((flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
+ if ((ctx->flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
ret = -EINVAL;
goto out;
}
- if (!(flags & SCA_MIGRATE_ENABLE)) {
- if (cpumask_equal(&p->cpus_mask, new_mask))
+ if (!(ctx->flags & SCA_MIGRATE_ENABLE)) {
+ if (cpumask_equal(&p->cpus_mask, ctx->new_mask)) {
+ if (ctx->flags & SCA_USER)
+ swap(p->user_cpus_ptr, ctx->user_mask);
goto out;
+ }
if (WARN_ON_ONCE(p == current &&
is_migration_disabled(p) &&
- !cpumask_test_cpu(task_cpu(p), new_mask))) {
+ !cpumask_test_cpu(task_cpu(p), ctx->new_mask))) {
ret = -EBUSY;
goto out;
}
@@ -2893,22 +2972,15 @@ static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
* for groups of tasks (ie. cpuset), so that load balancing is not
* immediately required to distribute the tasks within their new mask.
*/
- dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, new_mask);
+ dest_cpu = cpumask_any_and_distribute(cpu_valid_mask, ctx->new_mask);
if (dest_cpu >= nr_cpu_ids) {
ret = -EINVAL;
goto out;
}
- __do_set_cpus_allowed(p, new_mask, flags);
-
- if (flags & SCA_USER)
- user_mask = clear_user_cpus_ptr(p);
-
- ret = affine_move_task(rq, p, rf, dest_cpu, flags);
+ __do_set_cpus_allowed(p, ctx);
- kfree(user_mask);
-
- return ret;
+ return affine_move_task(rq, p, rf, dest_cpu, ctx->flags);
out:
task_rq_unlock(rq, p, rf);
@@ -2926,25 +2998,41 @@ out:
* call is not atomic; no spinlocks may be held.
*/
static int __set_cpus_allowed_ptr(struct task_struct *p,
- const struct cpumask *new_mask, u32 flags)
+ struct affinity_context *ctx)
{
struct rq_flags rf;
struct rq *rq;
rq = task_rq_lock(p, &rf);
- return __set_cpus_allowed_ptr_locked(p, new_mask, flags, rq, &rf);
+ /*
+ * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
+ * flags are set.
+ */
+ if (p->user_cpus_ptr &&
+ !(ctx->flags & (SCA_USER | SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) &&
+ cpumask_and(rq->scratch_mask, ctx->new_mask, p->user_cpus_ptr))
+ ctx->new_mask = rq->scratch_mask;
+
+ return __set_cpus_allowed_ptr_locked(p, ctx, rq, &rf);
}
int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
{
- return __set_cpus_allowed_ptr(p, new_mask, 0);
+ struct affinity_context ac = {
+ .new_mask = new_mask,
+ .flags = 0,
+ };
+
+ return __set_cpus_allowed_ptr(p, &ac);
}
EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
/*
* Change a given task's CPU affinity to the intersection of its current
- * affinity mask and @subset_mask, writing the resulting mask to @new_mask
- * and pointing @p->user_cpus_ptr to a copy of the old mask.
+ * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
+ * If user_cpus_ptr is defined, use it as the basis for restricting CPU
+ * affinity or use cpu_online_mask instead.
+ *
* If the resulting mask is empty, leave the affinity unchanged and return
* -EINVAL.
*/
@@ -2952,17 +3040,14 @@ static int restrict_cpus_allowed_ptr(struct task_struct *p,
struct cpumask *new_mask,
const struct cpumask *subset_mask)
{
- struct cpumask *user_mask = NULL;
+ struct affinity_context ac = {
+ .new_mask = new_mask,
+ .flags = 0,
+ };
struct rq_flags rf;
struct rq *rq;
int err;
- if (!p->user_cpus_ptr) {
- user_mask = kmalloc(cpumask_size(), GFP_KERNEL);
- if (!user_mask)
- return -ENOMEM;
- }
-
rq = task_rq_lock(p, &rf);
/*
@@ -2975,31 +3060,21 @@ static int restrict_cpus_allowed_ptr(struct task_struct *p,
goto err_unlock;
}
- if (!cpumask_and(new_mask, &p->cpus_mask, subset_mask)) {
+ if (!cpumask_and(new_mask, task_user_cpus(p), subset_mask)) {
err = -EINVAL;
goto err_unlock;
}
- /*
- * We're about to butcher the task affinity, so keep track of what
- * the user asked for in case we're able to restore it later on.
- */
- if (user_mask) {
- cpumask_copy(user_mask, p->cpus_ptr);
- p->user_cpus_ptr = user_mask;
- }
-
- return __set_cpus_allowed_ptr_locked(p, new_mask, 0, rq, &rf);
+ return __set_cpus_allowed_ptr_locked(p, &ac, rq, &rf);
err_unlock:
task_rq_unlock(rq, p, &rf);
- kfree(user_mask);
return err;
}
/*
* Restrict the CPU affinity of task @p so that it is a subset of
- * task_cpu_possible_mask() and point @p->user_cpu_ptr to a copy of the
+ * task_cpu_possible_mask() and point @p->user_cpus_ptr to a copy of the
* old affinity mask. If the resulting mask is empty, we warn and walk
* up the cpuset hierarchy until we find a suitable mask.
*/
@@ -3043,34 +3118,29 @@ out_free_mask:
}
static int
-__sched_setaffinity(struct task_struct *p, const struct cpumask *mask);
+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
/*
* Restore the affinity of a task @p which was previously restricted by a
- * call to force_compatible_cpus_allowed_ptr(). This will clear (and free)
- * @p->user_cpus_ptr.
+ * call to force_compatible_cpus_allowed_ptr().
*
* It is the caller's responsibility to serialise this with any calls to
* force_compatible_cpus_allowed_ptr(@p).
*/
void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
{
- struct cpumask *user_mask = p->user_cpus_ptr;
- unsigned long flags;
+ struct affinity_context ac = {
+ .new_mask = task_user_cpus(p),
+ .flags = 0,
+ };
+ int ret;
/*
- * Try to restore the old affinity mask. If this fails, then
- * we free the mask explicitly to avoid it being inherited across
- * a subsequent fork().
+ * Try to restore the old affinity mask with __sched_setaffinity().
+ * Cpuset masking will be done there too.
*/
- if (!user_mask || !__sched_setaffinity(p, user_mask))
- return;
-
- raw_spin_lock_irqsave(&p->pi_lock, flags);
- user_mask = clear_user_cpus_ptr(p);
- raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-
- kfree(user_mask);
+ ret = __sched_setaffinity(p, &ac);
+ WARN_ON_ONCE(ret);
}
void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
@@ -3548,10 +3618,9 @@ void sched_set_stop_task(int cpu, struct task_struct *stop)
#else /* CONFIG_SMP */
static inline int __set_cpus_allowed_ptr(struct task_struct *p,
- const struct cpumask *new_mask,
- u32 flags)
+ struct affinity_context *ctx)
{
- return set_cpus_allowed_ptr(p, new_mask);
+ return set_cpus_allowed_ptr(p, ctx->new_mask);
}
static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
@@ -3561,6 +3630,11 @@ static inline bool rq_has_pinned_tasks(struct rq *rq)
return false;
}
+static inline cpumask_t *alloc_user_cpus_ptr(int node)
+{
+ return NULL;
+}
+
#endif /* !CONFIG_SMP */
static void
@@ -3603,14 +3677,39 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
}
/*
- * Mark the task runnable and perform wakeup-preemption.
+ * Mark the task runnable.
*/
-static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
- struct rq_flags *rf)
+static inline void ttwu_do_wakeup(struct task_struct *p)
{
- check_preempt_curr(rq, p, wake_flags);
WRITE_ONCE(p->__state, TASK_RUNNING);
trace_sched_wakeup(p);
+}
+
+static void
+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
+ struct rq_flags *rf)
+{
+ int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
+
+ lockdep_assert_rq_held(rq);
+
+ if (p->sched_contributes_to_load)
+ rq->nr_uninterruptible--;
+
+#ifdef CONFIG_SMP
+ if (wake_flags & WF_MIGRATED)
+ en_flags |= ENQUEUE_MIGRATED;
+ else
+#endif
+ if (p->in_iowait) {
+ delayacct_blkio_end(p);
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
+ activate_task(rq, p, en_flags);
+ check_preempt_curr(rq, p, wake_flags);
+
+ ttwu_do_wakeup(p);
#ifdef CONFIG_SMP
if (p->sched_class->task_woken) {
@@ -3640,31 +3739,6 @@ static void ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags,
#endif
}
-static void
-ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
- struct rq_flags *rf)
-{
- int en_flags = ENQUEUE_WAKEUP | ENQUEUE_NOCLOCK;
-
- lockdep_assert_rq_held(rq);
-
- if (p->sched_contributes_to_load)
- rq->nr_uninterruptible--;
-
-#ifdef CONFIG_SMP
- if (wake_flags & WF_MIGRATED)
- en_flags |= ENQUEUE_MIGRATED;
- else
-#endif
- if (p->in_iowait) {
- delayacct_blkio_end(p);
- atomic_dec(&task_rq(p)->nr_iowait);
- }
-
- activate_task(rq, p, en_flags);
- ttwu_do_wakeup(rq, p, wake_flags, rf);
-}
-
/*
* Consider @p being inside a wait loop:
*
@@ -3698,9 +3772,15 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
rq = __task_rq_lock(p, &rf);
if (task_on_rq_queued(p)) {
- /* check_preempt_curr() may use rq clock */
- update_rq_clock(rq);
- ttwu_do_wakeup(rq, p, wake_flags, &rf);
+ if (!task_on_cpu(rq, p)) {
+ /*
+ * When on_rq && !on_cpu the task is preempted, see if
+ * it should preempt the task that is current now.
+ */
+ update_rq_clock(rq);
+ check_preempt_curr(rq, p, wake_flags);
+ }
+ ttwu_do_wakeup(p);
ret = 1;
}
__task_rq_unlock(rq, &rf);
@@ -3719,13 +3799,6 @@ void sched_ttwu_pending(void *arg)
if (!llist)
return;
- /*
- * rq::ttwu_pending racy indication of out-standing wakeups.
- * Races such that false-negatives are possible, since they
- * are shorter lived that false-positives would be.
- */
- WRITE_ONCE(rq->ttwu_pending, 0);
-
rq_lock_irqsave(rq, &rf);
update_rq_clock(rq);
@@ -3739,6 +3812,17 @@ void sched_ttwu_pending(void *arg)
ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0, &rf);
}
+ /*
+ * Must be after enqueueing at least once task such that
+ * idle_cpu() does not observe a false-negative -- if it does,
+ * it is possible for select_idle_siblings() to stack a number
+ * of tasks on this CPU during that window.
+ *
+ * It is ok to clear ttwu_pending when another task pending.
+ * We will receive IPI after local irq enabled and then enqueue it.
+ * Since now nr_running > 0, idle_cpu() will always get correct result.
+ */
+ WRITE_ONCE(rq->ttwu_pending, 0);
rq_unlock_irqrestore(rq, &rf);
}
@@ -4062,8 +4146,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
goto out;
trace_sched_waking(p);
- WRITE_ONCE(p->__state, TASK_RUNNING);
- trace_sched_wakeup(p);
+ ttwu_do_wakeup(p);
goto out;
}
@@ -4419,7 +4502,7 @@ static void reset_memory_tiering(void)
}
}
-int sysctl_numa_balancing(struct ctl_table *table, int write,
+static int sysctl_numa_balancing(struct ctl_table *table, int write,
void *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
@@ -4546,6 +4629,17 @@ static struct ctl_table sched_core_sysctls[] = {
.proc_handler = sysctl_sched_uclamp_handler,
},
#endif /* CONFIG_UCLAMP_TASK */
+#ifdef CONFIG_NUMA_BALANCING
+ {
+ .procname = "numa_balancing",
+ .data = NULL, /* filled in by handler */
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = sysctl_numa_balancing,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_FOUR,
+ },
+#endif /* CONFIG_NUMA_BALANCING */
{}
};
static int __init sched_core_sysctl_init(void)
@@ -5017,6 +5111,7 @@ prepare_task_switch(struct rq *rq, struct task_struct *prev,
sched_info_switch(rq, prev, next);
perf_event_task_sched_out(prev, next);
rseq_preempt(prev);
+ switch_mm_cid(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
kmap_local_sched_out();
prepare_task(next);
@@ -5247,6 +5342,11 @@ bool single_task_running(void)
}
EXPORT_SYMBOL(single_task_running);
+unsigned long long nr_context_switches_cpu(int cpu)
+{
+ return cpu_rq(cpu)->nr_switches;
+}
+
unsigned long long nr_context_switches(void)
{
int i;
@@ -5469,7 +5569,9 @@ void scheduler_tick(void)
unsigned long thermal_pressure;
u64 resched_latency;
- arch_scale_freq_tick();
+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
+ arch_scale_freq_tick();
+
sched_clock_tick();
rq_lock(rq, &rf);
@@ -5747,8 +5849,7 @@ static noinline void __schedule_bug(struct task_struct *prev)
pr_err("Preemption disabled at:");
print_ip_sym(KERN_ERR, preempt_disable_ip);
}
- if (panic_on_warn)
- panic("scheduling while atomic\n");
+ check_panic_on_warn("scheduling while atomic");
dump_stack();
add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
@@ -6172,7 +6273,7 @@ static bool steal_cookie_task(int cpu, struct sched_domain *sd)
{
int i;
- for_each_cpu_wrap(i, sched_domain_span(sd), cpu) {
+ for_each_cpu_wrap(i, sched_domain_span(sd), cpu + 1) {
if (i == cpu)
continue;
@@ -8106,7 +8207,7 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
#endif
static int
-__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
{
int retval;
cpumask_var_t cpus_allowed, new_mask;
@@ -8120,13 +8221,16 @@ __sched_setaffinity(struct task_struct *p, const struct cpumask *mask)
}
cpuset_cpus_allowed(p, cpus_allowed);
- cpumask_and(new_mask, mask, cpus_allowed);
+ cpumask_and(new_mask, ctx->new_mask, cpus_allowed);
+
+ ctx->new_mask = new_mask;
+ ctx->flags |= SCA_CHECK;
retval = dl_task_check_affinity(p, new_mask);
if (retval)
goto out_free_new_mask;
-again:
- retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK | SCA_USER);
+
+ retval = __set_cpus_allowed_ptr(p, ctx);
if (retval)
goto out_free_new_mask;
@@ -8137,7 +8241,24 @@ again:
* Just reset the cpumask to the cpuset's cpus_allowed.
*/
cpumask_copy(new_mask, cpus_allowed);
- goto again;
+
+ /*
+ * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr()
+ * will restore the previous user_cpus_ptr value.
+ *
+ * In the unlikely event a previous user_cpus_ptr exists,
+ * we need to further restrict the mask to what is allowed
+ * by that old user_cpus_ptr.
+ */
+ if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) {
+ bool empty = !cpumask_and(new_mask, new_mask,
+ ctx->user_mask);
+
+ if (WARN_ON_ONCE(empty))
+ cpumask_copy(new_mask, cpus_allowed);
+ }
+ __set_cpus_allowed_ptr(p, ctx);
+ retval = -EINVAL;
}
out_free_new_mask:
@@ -8149,6 +8270,8 @@ out_free_cpus_allowed:
long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
{
+ struct affinity_context ac;
+ struct cpumask *user_mask;
struct task_struct *p;
int retval;
@@ -8183,7 +8306,27 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
if (retval)
goto out_put_task;
- retval = __sched_setaffinity(p, in_mask);
+ /*
+ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
+ * alloc_user_cpus_ptr() returns NULL.
+ */
+ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
+ if (user_mask) {
+ cpumask_copy(user_mask, in_mask);
+ } else if (IS_ENABLED(CONFIG_SMP)) {
+ retval = -ENOMEM;
+ goto out_put_task;
+ }
+
+ ac = (struct affinity_context){
+ .new_mask = in_mask,
+ .user_mask = user_mask,
+ .flags = SCA_USER,
+ };
+
+ retval = __sched_setaffinity(p, &ac);
+ kfree(ac.user_mask);
+
out_put_task:
put_task_struct(p);
return retval;
@@ -8964,6 +9107,12 @@ void show_state_filter(unsigned int state_filter)
*/
void __init init_idle(struct task_struct *idle, int cpu)
{
+#ifdef CONFIG_SMP
+ struct affinity_context ac = (struct affinity_context) {
+ .new_mask = cpumask_of(cpu),
+ .flags = 0,
+ };
+#endif
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
@@ -8988,7 +9137,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
*
* And since this is boot we can forgo the serialization.
*/
- set_cpus_allowed_common(idle, cpumask_of(cpu), 0);
+ set_cpus_allowed_common(idle, &ac);
#endif
/*
* We're having a chicken and egg problem, even though we are
@@ -9775,6 +9924,7 @@ void __init sched_init(void)
rq->core_cookie = 0UL;
#endif
+ zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
}
set_load_weight(&init_task, false);
@@ -11228,3 +11378,53 @@ void call_trace_sched_update_nr_running(struct rq *rq, int count)
{
trace_sched_update_nr_running_tp(rq, count);
}
+
+#ifdef CONFIG_SCHED_MM_CID
+void sched_mm_cid_exit_signals(struct task_struct *t)
+{
+ struct mm_struct *mm = t->mm;
+ unsigned long flags;
+
+ if (!mm)
+ return;
+ local_irq_save(flags);
+ mm_cid_put(mm, t->mm_cid);
+ t->mm_cid = -1;
+ t->mm_cid_active = 0;
+ local_irq_restore(flags);
+}
+
+void sched_mm_cid_before_execve(struct task_struct *t)
+{
+ struct mm_struct *mm = t->mm;
+ unsigned long flags;
+
+ if (!mm)
+ return;
+ local_irq_save(flags);
+ mm_cid_put(mm, t->mm_cid);
+ t->mm_cid = -1;
+ t->mm_cid_active = 0;
+ local_irq_restore(flags);
+}
+
+void sched_mm_cid_after_execve(struct task_struct *t)
+{
+ struct mm_struct *mm = t->mm;
+ unsigned long flags;
+
+ if (!mm)
+ return;
+ local_irq_save(flags);
+ t->mm_cid = mm_cid_get(mm);
+ t->mm_cid_active = 1;
+ local_irq_restore(flags);
+ rseq_set_notify_resume(t);
+}
+
+void sched_mm_cid_fork(struct task_struct *t)
+{
+ WARN_ON_ONCE(!t->mm || t->mm_cid != -1);
+ t->mm_cid_active = 1;
+}
+#endif
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 1207c78f85c1..5c840151f3bb 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -48,7 +48,6 @@ struct sugov_cpu {
unsigned long util;
unsigned long bw_dl;
- unsigned long max;
/* The field below is for single-CPU policies only: */
#ifdef CONFIG_NO_HZ_COMMON
@@ -158,7 +157,6 @@ static void sugov_get_util(struct sugov_cpu *sg_cpu)
{
struct rq *rq = cpu_rq(sg_cpu->cpu);
- sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);
sg_cpu->bw_dl = cpu_bw_dl(rq);
sg_cpu->util = effective_cpu_util(sg_cpu->cpu, cpu_util_cfs(sg_cpu->cpu),
FREQUENCY_UTIL, NULL);
@@ -238,6 +236,7 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
* sugov_iowait_apply() - Apply the IO boost to a CPU.
* @sg_cpu: the sugov data for the cpu to boost
* @time: the update time from the caller
+ * @max_cap: the max CPU capacity
*
* A CPU running a task which woken up after an IO operation can have its
* utilization boosted to speed up the completion of those IO operations.
@@ -251,7 +250,8 @@ static void sugov_iowait_boost(struct sugov_cpu *sg_cpu, u64 time,
* This mechanism is designed to boost high frequently IO waiting tasks, while
* being more conservative on tasks which does sporadic IO operations.
*/
-static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
+static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time,
+ unsigned long max_cap)
{
unsigned long boost;
@@ -280,7 +280,7 @@ static void sugov_iowait_apply(struct sugov_cpu *sg_cpu, u64 time)
* sg_cpu->util is already in capacity scale; convert iowait_boost
* into the same scale so we can compare.
*/
- boost = (sg_cpu->iowait_boost * sg_cpu->max) >> SCHED_CAPACITY_SHIFT;
+ boost = (sg_cpu->iowait_boost * max_cap) >> SCHED_CAPACITY_SHIFT;
boost = uclamp_rq_util_with(cpu_rq(sg_cpu->cpu), boost, NULL);
if (sg_cpu->util < boost)
sg_cpu->util = boost;
@@ -310,7 +310,8 @@ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
}
static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
- u64 time, unsigned int flags)
+ u64 time, unsigned long max_cap,
+ unsigned int flags)
{
sugov_iowait_boost(sg_cpu, time, flags);
sg_cpu->last_update = time;
@@ -321,7 +322,7 @@ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
return false;
sugov_get_util(sg_cpu);
- sugov_iowait_apply(sg_cpu, time);
+ sugov_iowait_apply(sg_cpu, time, max_cap);
return true;
}
@@ -332,12 +333,15 @@ static void sugov_update_single_freq(struct update_util_data *hook, u64 time,
struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
unsigned int cached_freq = sg_policy->cached_raw_freq;
+ unsigned long max_cap;
unsigned int next_f;
- if (!sugov_update_single_common(sg_cpu, time, flags))
+ max_cap = arch_scale_cpu_capacity(sg_cpu->cpu);
+
+ if (!sugov_update_single_common(sg_cpu, time, max_cap, flags))
return;
- next_f = get_next_freq(sg_policy, sg_cpu->util, sg_cpu->max);
+ next_f = get_next_freq(sg_policy, sg_cpu->util, max_cap);
/*
* Do not reduce the frequency if the CPU has not been idle
* recently, as the reduction is likely to be premature then.
@@ -374,6 +378,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
{
struct sugov_cpu *sg_cpu = container_of(hook, struct sugov_cpu, update_util);
unsigned long prev_util = sg_cpu->util;
+ unsigned long max_cap;
/*
* Fall back to the "frequency" path if frequency invariance is not
@@ -385,7 +390,9 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
return;
}
- if (!sugov_update_single_common(sg_cpu, time, flags))
+ max_cap = arch_scale_cpu_capacity(sg_cpu->cpu);
+
+ if (!sugov_update_single_common(sg_cpu, time, max_cap, flags))
return;
/*
@@ -399,7 +406,7 @@ static void sugov_update_single_perf(struct update_util_data *hook, u64 time,
sg_cpu->util = prev_util;
cpufreq_driver_adjust_perf(sg_cpu->cpu, map_util_perf(sg_cpu->bw_dl),
- map_util_perf(sg_cpu->util), sg_cpu->max);
+ map_util_perf(sg_cpu->util), max_cap);
sg_cpu->sg_policy->last_freq_update_time = time;
}
@@ -408,25 +415,21 @@ static unsigned int sugov_next_freq_shared(struct sugov_cpu *sg_cpu, u64 time)
{
struct sugov_policy *sg_policy = sg_cpu->sg_policy;
struct cpufreq_policy *policy = sg_policy->policy;
- unsigned long util = 0, max = 1;
+ unsigned long util = 0, max_cap;
unsigned int j;
+ max_cap = arch_scale_cpu_capacity(sg_cpu->cpu);
+
for_each_cpu(j, policy->cpus) {
struct sugov_cpu *j_sg_cpu = &per_cpu(sugov_cpu, j);
- unsigned long j_util, j_max;
sugov_get_util(j_sg_cpu);
- sugov_iowait_apply(j_sg_cpu, time);
- j_util = j_sg_cpu->util;
- j_max = j_sg_cpu->max;
+ sugov_iowait_apply(j_sg_cpu, time, max_cap);
- if (j_util * max > j_max * util) {
- util = j_util;
- max = j_max;
- }
+ util = max(j_sg_cpu->util, util);
}
- return get_next_freq(sg_policy, util, max);
+ return get_next_freq(sg_policy, util, max_cap);
}
static void
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 95fc77853743..af7952f12e6c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -3,6 +3,10 @@
* Simple CPU accounting cgroup controller
*/
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
+ #include <asm/cputime.h>
+#endif
+
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 9ae8f41e3372..71b24371a6f7 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2485,8 +2485,7 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p)
}
static void set_cpus_allowed_dl(struct task_struct *p,
- const struct cpumask *new_mask,
- u32 flags)
+ struct affinity_context *ctx)
{
struct root_domain *src_rd;
struct rq *rq;
@@ -2501,7 +2500,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
* update. We already made space for us in the destination
* domain (see cpuset_can_attach()).
*/
- if (!cpumask_intersects(src_rd->span, new_mask)) {
+ if (!cpumask_intersects(src_rd->span, ctx->new_mask)) {
struct dl_bw *src_dl_b;
src_dl_b = dl_bw_of(cpu_of(rq));
@@ -2515,7 +2514,7 @@ static void set_cpus_allowed_dl(struct task_struct *p,
raw_spin_unlock(&src_dl_b->lock);
}
- set_cpus_allowed_common(p, new_mask, flags);
+ set_cpus_allowed_common(p, ctx);
}
/* Assumes rq->lock is held */
@@ -2664,17 +2663,20 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
static void prio_changed_dl(struct rq *rq, struct task_struct *p,
int oldprio)
{
- if (task_on_rq_queued(p) || task_current(rq, p)) {
+ if (!task_on_rq_queued(p))
+ return;
+
#ifdef CONFIG_SMP
- /*
- * This might be too much, but unfortunately
- * we don't have the old deadline value, and
- * we can't argue if the task is increasing
- * or lowering its prio, so...
- */
- if (!rq->dl.overloaded)
- deadline_queue_pull_task(rq);
+ /*
+ * This might be too much, but unfortunately
+ * we don't have the old deadline value, and
+ * we can't argue if the task is increasing
+ * or lowering its prio, so...
+ */
+ if (!rq->dl.overloaded)
+ deadline_queue_pull_task(rq);
+ if (task_current(rq, p)) {
/*
* If we now have a earlier deadline task than p,
* then reschedule, provided p is still on this
@@ -2682,15 +2684,24 @@ static void prio_changed_dl(struct rq *rq, struct task_struct *p,
*/
if (dl_time_before(rq->dl.earliest_dl.curr, p->dl.deadline))
resched_curr(rq);
-#else
+ } else {
/*
- * Again, we don't know if p has a earlier
- * or later deadline, so let's blindly set a
- * (maybe not needed) rescheduling point.
+ * Current may not be deadline in case p was throttled but we
+ * have just replenished it (e.g. rt_mutex_setprio()).
+ *
+ * Otherwise, if p was given an earlier deadline, reschedule.
*/
- resched_curr(rq);
-#endif /* CONFIG_SMP */
+ if (!dl_task(rq->curr) ||
+ dl_time_before(p->dl.deadline, rq->curr->dl.deadline))
+ resched_curr(rq);
}
+#else
+ /*
+ * We don't know if p has a earlier or later deadline, so let's blindly
+ * set a (maybe not needed) rescheduling point.
+ */
+ resched_curr(rq);
+#endif
}
DEFINE_SCHED_CLASS(dl) = {
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e4a0b8bd941c..ff4dbbae3b10 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -178,6 +178,11 @@ int __weak arch_asym_cpu_priority(int cpu)
static unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
#endif
+#ifdef CONFIG_NUMA_BALANCING
+/* Restrict the NUMA promotion throughput (MB/s) for each target node. */
+static unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
+#endif
+
#ifdef CONFIG_SYSCTL
static struct ctl_table sched_fair_sysctls[] = {
{
@@ -197,6 +202,16 @@ static struct ctl_table sched_fair_sysctls[] = {
.extra1 = SYSCTL_ONE,
},
#endif
+#ifdef CONFIG_NUMA_BALANCING
+ {
+ .procname = "numa_balancing_promote_rate_limit_MBps",
+ .data = &sysctl_numa_balancing_promote_rate_limit,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ },
+#endif /* CONFIG_NUMA_BALANCING */
{}
};
@@ -453,7 +468,7 @@ is_same_group(struct sched_entity *se, struct sched_entity *pse)
return NULL;
}
-static inline struct sched_entity *parent_entity(struct sched_entity *se)
+static inline struct sched_entity *parent_entity(const struct sched_entity *se)
{
return se->parent;
}
@@ -580,8 +595,8 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
return min_vruntime;
}
-static inline bool entity_before(struct sched_entity *a,
- struct sched_entity *b)
+static inline bool entity_before(const struct sched_entity *a,
+ const struct sched_entity *b)
{
return (s64)(a->vruntime - b->vruntime) < 0;
}
@@ -1094,9 +1109,6 @@ unsigned int sysctl_numa_balancing_scan_delay = 1000;
/* The page with hint page fault latency < threshold in ms is considered hot */
unsigned int sysctl_numa_balancing_hot_threshold = MSEC_PER_SEC;
-/* Restrict the NUMA promotion throughput (MB/s) for each target node. */
-unsigned int sysctl_numa_balancing_promote_rate_limit = 65536;
-
struct numa_group {
refcount_t refcount;
@@ -1792,7 +1804,7 @@ static void update_numa_stats(struct task_numa_env *env,
ns->nr_running += rq->cfs.h_nr_running;
ns->compute_capacity += capacity_of(cpu);
- if (find_idle && !rq->nr_running && idle_cpu(cpu)) {
+ if (find_idle && idle_core < 0 && !rq->nr_running && idle_cpu(cpu)) {
if (READ_ONCE(rq->numa_migrate_on) ||
!cpumask_test_cpu(cpu, env->p->cpus_ptr))
continue;
@@ -1824,7 +1836,7 @@ static void task_numa_assign(struct task_numa_env *env,
int start = env->dst_cpu;
/* Find alternative idle CPU. */
- for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start) {
+ for_each_cpu_wrap(cpu, cpumask_of_node(env->dst_nid), start + 1) {
if (cpu == env->best_cpu || !idle_cpu(cpu) ||
!cpumask_test_cpu(cpu, env->p->cpus_ptr)) {
continue;
@@ -2964,7 +2976,7 @@ static void task_numa_work(struct callback_head *work)
}
next_scan = now + msecs_to_jiffies(p->numa_scan_period);
- if (cmpxchg(&mm->numa_next_scan, migrate, next_scan) != migrate)
+ if (!try_cmpxchg(&mm->numa_next_scan, &migrate, next_scan))
return;
/*
@@ -4280,14 +4292,16 @@ static inline unsigned long task_util_est(struct task_struct *p)
}
#ifdef CONFIG_UCLAMP_TASK
-static inline unsigned long uclamp_task_util(struct task_struct *p)
+static inline unsigned long uclamp_task_util(struct task_struct *p,
+ unsigned long uclamp_min,
+ unsigned long uclamp_max)
{
- return clamp(task_util_est(p),
- uclamp_eff_value(p, UCLAMP_MIN),
- uclamp_eff_value(p, UCLAMP_MAX));
+ return clamp(task_util_est(p), uclamp_min, uclamp_max);
}
#else
-static inline unsigned long uclamp_task_util(struct task_struct *p)
+static inline unsigned long uclamp_task_util(struct task_struct *p,
+ unsigned long uclamp_min,
+ unsigned long uclamp_max)
{
return task_util_est(p);
}
@@ -4426,10 +4440,135 @@ done:
trace_sched_util_est_se_tp(&p->se);
}
-static inline int task_fits_capacity(struct task_struct *p,
- unsigned long capacity)
+static inline int util_fits_cpu(unsigned long util,
+ unsigned long uclamp_min,
+ unsigned long uclamp_max,
+ int cpu)
{
- return fits_capacity(uclamp_task_util(p), capacity);
+ unsigned long capacity_orig, capacity_orig_thermal;
+ unsigned long capacity = capacity_of(cpu);
+ bool fits, uclamp_max_fits;
+
+ /*
+ * Check if the real util fits without any uclamp boost/cap applied.
+ */
+ fits = fits_capacity(util, capacity);
+
+ if (!uclamp_is_used())
+ return fits;
+
+ /*
+ * We must use capacity_orig_of() for comparing against uclamp_min and
+ * uclamp_max. We only care about capacity pressure (by using
+ * capacity_of()) for comparing against the real util.
+ *
+ * If a task is boosted to 1024 for example, we don't want a tiny
+ * pressure to skew the check whether it fits a CPU or not.
+ *
+ * Similarly if a task is capped to capacity_orig_of(little_cpu), it
+ * should fit a little cpu even if there's some pressure.
+ *
+ * Only exception is for thermal pressure since it has a direct impact
+ * on available OPP of the system.
+ *
+ * We honour it for uclamp_min only as a drop in performance level
+ * could result in not getting the requested minimum performance level.
+ *
+ * For uclamp_max, we can tolerate a drop in performance level as the
+ * goal is to cap the task. So it's okay if it's getting less.
+ */
+ capacity_orig = capacity_orig_of(cpu);
+ capacity_orig_thermal = capacity_orig - arch_scale_thermal_pressure(cpu);
+
+ /*
+ * We want to force a task to fit a cpu as implied by uclamp_max.
+ * But we do have some corner cases to cater for..
+ *
+ *
+ * C=z
+ * | ___
+ * | C=y | |
+ * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max
+ * | C=x | | | |
+ * | ___ | | | |
+ * | | | | | | | (util somewhere in this region)
+ * | | | | | | |
+ * | | | | | | |
+ * +----------------------------------------
+ * cpu0 cpu1 cpu2
+ *
+ * In the above example if a task is capped to a specific performance
+ * point, y, then when:
+ *
+ * * util = 80% of x then it does not fit on cpu0 and should migrate
+ * to cpu1
+ * * util = 80% of y then it is forced to fit on cpu1 to honour
+ * uclamp_max request.
+ *
+ * which is what we're enforcing here. A task always fits if
+ * uclamp_max <= capacity_orig. But when uclamp_max > capacity_orig,
+ * the normal upmigration rules should withhold still.
+ *
+ * Only exception is when we are on max capacity, then we need to be
+ * careful not to block overutilized state. This is so because:
+ *
+ * 1. There's no concept of capping at max_capacity! We can't go
+ * beyond this performance level anyway.
+ * 2. The system is being saturated when we're operating near
+ * max capacity, it doesn't make sense to block overutilized.
+ */
+ uclamp_max_fits = (capacity_orig == SCHED_CAPACITY_SCALE) && (uclamp_max == SCHED_CAPACITY_SCALE);
+ uclamp_max_fits = !uclamp_max_fits && (uclamp_max <= capacity_orig);
+ fits = fits || uclamp_max_fits;
+
+ /*
+ *
+ * C=z
+ * | ___ (region a, capped, util >= uclamp_max)
+ * | C=y | |
+ * |_ _ _ _ _ _ _ _ _ ___ _ _ _ | _ | _ _ _ _ _ uclamp_max
+ * | C=x | | | |
+ * | ___ | | | | (region b, uclamp_min <= util <= uclamp_max)
+ * |_ _ _|_ _|_ _ _ _| _ | _ _ _| _ | _ _ _ _ _ uclamp_min
+ * | | | | | | |
+ * | | | | | | | (region c, boosted, util < uclamp_min)
+ * +----------------------------------------
+ * cpu0 cpu1 cpu2
+ *
+ * a) If util > uclamp_max, then we're capped, we don't care about
+ * actual fitness value here. We only care if uclamp_max fits
+ * capacity without taking margin/pressure into account.
+ * See comment above.
+ *
+ * b) If uclamp_min <= util <= uclamp_max, then the normal
+ * fits_capacity() rules apply. Except we need to ensure that we
+ * enforce we remain within uclamp_max, see comment above.
+ *
+ * c) If util < uclamp_min, then we are boosted. Same as (b) but we
+ * need to take into account the boosted value fits the CPU without
+ * taking margin/pressure into account.
+ *
+ * Cases (a) and (b) are handled in the 'fits' variable already. We
+ * just need to consider an extra check for case (c) after ensuring we
+ * handle the case uclamp_min > uclamp_max.
+ */
+ uclamp_min = min(uclamp_min, uclamp_max);
+ if (fits && (util < uclamp_min) && (uclamp_min > capacity_orig_thermal))
+ return -1;
+
+ return fits;
+}
+
+static inline int task_fits_cpu(struct task_struct *p, int cpu)
+{
+ unsigned long uclamp_min = uclamp_eff_value(p, UCLAMP_MIN);
+ unsigned long uclamp_max = uclamp_eff_value(p, UCLAMP_MAX);
+ unsigned long util = task_util_est(p);
+ /*
+ * Return true only if the cpu fully fits the task requirements, which
+ * include the utilization but also the performance hints.
+ */
+ return (util_fits_cpu(util, uclamp_min, uclamp_max, cpu) > 0);
}
static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
@@ -4442,7 +4581,7 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
return;
}
- if (task_fits_capacity(p, capacity_of(cpu_of(rq)))) {
+ if (task_fits_cpu(p, cpu_of(rq))) {
rq->misfit_task_load = 0;
return;
}
@@ -4513,6 +4652,7 @@ static void
place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
{
u64 vruntime = cfs_rq->min_vruntime;
+ u64 sleep_time;
/*
* The 'current' period is already promised to the current tasks,
@@ -4542,8 +4682,18 @@ place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int initial)
vruntime -= thresh;
}
- /* ensure we never gain time by being placed backwards. */
- se->vruntime = max_vruntime(se->vruntime, vruntime);
+ /*
+ * Pull vruntime of the entity being placed to the base level of
+ * cfs_rq, to prevent boosting it if placed backwards. If the entity
+ * slept for a long time, don't even try to compare its vruntime with
+ * the base as it may be too far off and the comparison may get
+ * inversed due to s64 overflow.
+ */
+ sleep_time = rq_clock_task(rq_of(cfs_rq)) - se->exec_start;
+ if ((s64)sleep_time > 60LL * NSEC_PER_SEC)
+ se->vruntime = vruntime;
+ else
+ se->vruntime = max_vruntime(se->vruntime, vruntime);
}
static void check_enqueue_throttle(struct cfs_rq *cfs_rq);
@@ -4753,7 +4903,13 @@ check_preempt_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr)
struct sched_entity *se;
s64 delta;
- ideal_runtime = sched_slice(cfs_rq, curr);
+ /*
+ * When many tasks blow up the sched_period; it is possible that
+ * sched_slice() reports unusually large results (when many tasks are
+ * very light for example). Therefore impose a maximum.
+ */
+ ideal_runtime = min_t(u64, sched_slice(cfs_rq, curr), sysctl_sched_latency);
+
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
if (delta_exec > ideal_runtime) {
resched_curr(rq_of(cfs_rq));
@@ -5318,22 +5474,105 @@ unthrottle_throttle:
resched_curr(rq);
}
-static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
+#ifdef CONFIG_SMP
+static void __cfsb_csd_unthrottle(void *arg)
{
- struct cfs_rq *cfs_rq;
+ struct cfs_rq *cursor, *tmp;
+ struct rq *rq = arg;
+ struct rq_flags rf;
+
+ rq_lock(rq, &rf);
+
+ /*
+ * Since we hold rq lock we're safe from concurrent manipulation of
+ * the CSD list. However, this RCU critical section annotates the
+ * fact that we pair with sched_free_group_rcu(), so that we cannot
+ * race with group being freed in the window between removing it
+ * from the list and advancing to the next entry in the list.
+ */
+ rcu_read_lock();
+
+ list_for_each_entry_safe(cursor, tmp, &rq->cfsb_csd_list,
+ throttled_csd_list) {
+ list_del_init(&cursor->throttled_csd_list);
+
+ if (cfs_rq_throttled(cursor))
+ unthrottle_cfs_rq(cursor);
+ }
+
+ rcu_read_unlock();
+
+ rq_unlock(rq, &rf);
+}
+
+static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
+{
+ struct rq *rq = rq_of(cfs_rq);
+ bool first;
+
+ if (rq == this_rq()) {
+ unthrottle_cfs_rq(cfs_rq);
+ return;
+ }
+
+ /* Already enqueued */
+ if (SCHED_WARN_ON(!list_empty(&cfs_rq->throttled_csd_list)))
+ return;
+
+ first = list_empty(&rq->cfsb_csd_list);
+ list_add_tail(&cfs_rq->throttled_csd_list, &rq->cfsb_csd_list);
+ if (first)
+ smp_call_function_single_async(cpu_of(rq), &rq->cfsb_csd);
+}
+#else
+static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
+{
+ unthrottle_cfs_rq(cfs_rq);
+}
+#endif
+
+static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
+{
+ lockdep_assert_rq_held(rq_of(cfs_rq));
+
+ if (SCHED_WARN_ON(!cfs_rq_throttled(cfs_rq) ||
+ cfs_rq->runtime_remaining <= 0))
+ return;
+
+ __unthrottle_cfs_rq_async(cfs_rq);
+}
+
+static bool distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
+{
+ struct cfs_rq *local_unthrottle = NULL;
+ int this_cpu = smp_processor_id();
u64 runtime, remaining = 1;
+ bool throttled = false;
+ struct cfs_rq *cfs_rq;
+ struct rq_flags rf;
+ struct rq *rq;
rcu_read_lock();
list_for_each_entry_rcu(cfs_rq, &cfs_b->throttled_cfs_rq,
throttled_list) {
- struct rq *rq = rq_of(cfs_rq);
- struct rq_flags rf;
+ rq = rq_of(cfs_rq);
+
+ if (!remaining) {
+ throttled = true;
+ break;
+ }
rq_lock_irqsave(rq, &rf);
if (!cfs_rq_throttled(cfs_rq))
goto next;
- /* By the above check, this should never be true */
+#ifdef CONFIG_SMP
+ /* Already queued for async unthrottle */
+ if (!list_empty(&cfs_rq->throttled_csd_list))
+ goto next;
+#endif
+
+ /* By the above checks, this should never be true */
SCHED_WARN_ON(cfs_rq->runtime_remaining > 0);
raw_spin_lock(&cfs_b->lock);
@@ -5347,16 +5586,30 @@ static void distribute_cfs_runtime(struct cfs_bandwidth *cfs_b)
cfs_rq->runtime_remaining += runtime;
/* we check whether we're throttled above */
- if (cfs_rq->runtime_remaining > 0)
- unthrottle_cfs_rq(cfs_rq);
+ if (cfs_rq->runtime_remaining > 0) {
+ if (cpu_of(rq) != this_cpu ||
+ SCHED_WARN_ON(local_unthrottle))
+ unthrottle_cfs_rq_async(cfs_rq);
+ else
+ local_unthrottle = cfs_rq;
+ } else {
+ throttled = true;
+ }
next:
rq_unlock_irqrestore(rq, &rf);
-
- if (!remaining)
- break;
}
rcu_read_unlock();
+
+ if (local_unthrottle) {
+ rq = cpu_rq(this_cpu);
+ rq_lock_irqsave(rq, &rf);
+ if (cfs_rq_throttled(local_unthrottle))
+ unthrottle_cfs_rq(local_unthrottle);
+ rq_unlock_irqrestore(rq, &rf);
+ }
+
+ return throttled;
}
/*
@@ -5401,10 +5654,8 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
while (throttled && cfs_b->runtime > 0) {
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
/* we can't nest cfs_b->lock while distributing bandwidth */
- distribute_cfs_runtime(cfs_b);
+ throttled = distribute_cfs_runtime(cfs_b);
raw_spin_lock_irqsave(&cfs_b->lock, flags);
-
- throttled = !list_empty(&cfs_b->throttled_cfs_rq);
}
/*
@@ -5681,6 +5932,9 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
cfs_rq->runtime_enabled = 0;
INIT_LIST_HEAD(&cfs_rq->throttled_list);
+#ifdef CONFIG_SMP
+ INIT_LIST_HEAD(&cfs_rq->throttled_csd_list);
+#endif
}
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
@@ -5697,12 +5951,38 @@ void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
+ int __maybe_unused i;
+
/* init_cfs_bandwidth() was not called */
if (!cfs_b->throttled_cfs_rq.next)
return;
hrtimer_cancel(&cfs_b->period_timer);
hrtimer_cancel(&cfs_b->slack_timer);
+
+ /*
+ * It is possible that we still have some cfs_rq's pending on a CSD
+ * list, though this race is very rare. In order for this to occur, we
+ * must have raced with the last task leaving the group while there
+ * exist throttled cfs_rq(s), and the period_timer must have queued the
+ * CSD item but the remote cpu has not yet processed it. To handle this,
+ * we can simply flush all pending CSD work inline here. We're
+ * guaranteed at this point that no additional cfs_rq of this group can
+ * join a CSD list.
+ */
+#ifdef CONFIG_SMP
+ for_each_possible_cpu(i) {
+ struct rq *rq = cpu_rq(i);
+ unsigned long flags;
+
+ if (list_empty(&rq->cfsb_csd_list))
+ continue;
+
+ local_irq_save(flags);
+ __cfsb_csd_unthrottle(rq);
+ local_irq_restore(flags);
+ }
+#endif
}
/*
@@ -5862,7 +6142,11 @@ static inline void hrtick_update(struct rq *rq)
#ifdef CONFIG_SMP
static inline bool cpu_overutilized(int cpu)
{
- return !fits_capacity(cpu_util_cfs(cpu), capacity_of(cpu));
+ unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
+ unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
+
+ /* Return true only if the utilization doesn't fit CPU's capacity */
+ return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu);
}
static inline void update_overutilized_status(struct rq *rq)
@@ -6654,36 +6938,62 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
static int
select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
{
- unsigned long task_util, best_cap = 0;
+ unsigned long task_util, util_min, util_max, best_cap = 0;
+ int fits, best_fits = 0;
int cpu, best_cpu = -1;
struct cpumask *cpus;
cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
- task_util = uclamp_task_util(p);
+ task_util = task_util_est(p);
+ util_min = uclamp_eff_value(p, UCLAMP_MIN);
+ util_max = uclamp_eff_value(p, UCLAMP_MAX);
- for_each_cpu_wrap(cpu, cpus, target) {
+ for_each_cpu_wrap(cpu, cpus, target + 1) {
unsigned long cpu_cap = capacity_of(cpu);
if (!available_idle_cpu(cpu) && !sched_idle_cpu(cpu))
continue;
- if (fits_capacity(task_util, cpu_cap))
+
+ fits = util_fits_cpu(task_util, util_min, util_max, cpu);
+
+ /* This CPU fits with all requirements */
+ if (fits > 0)
return cpu;
+ /*
+ * Only the min performance hint (i.e. uclamp_min) doesn't fit.
+ * Look for the CPU with best capacity.
+ */
+ else if (fits < 0)
+ cpu_cap = capacity_orig_of(cpu) - thermal_load_avg(cpu_rq(cpu));
- if (cpu_cap > best_cap) {
+ /*
+ * First, select CPU which fits better (-1 being better than 0).
+ * Then, select the one with best capacity at same level.
+ */
+ if ((fits < best_fits) ||
+ ((fits == best_fits) && (cpu_cap > best_cap))) {
best_cap = cpu_cap;
best_cpu = cpu;
+ best_fits = fits;
}
}
return best_cpu;
}
-static inline bool asym_fits_capacity(unsigned long task_util, int cpu)
+static inline bool asym_fits_cpu(unsigned long util,
+ unsigned long util_min,
+ unsigned long util_max,
+ int cpu)
{
if (sched_asym_cpucap_active())
- return fits_capacity(task_util, capacity_of(cpu));
+ /*
+ * Return true only if the cpu fully fits the task requirements
+ * which include the utilization and the performance hints.
+ */
+ return (util_fits_cpu(util, util_min, util_max, cpu) > 0);
return true;
}
@@ -6695,7 +7005,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
{
bool has_idle_core = false;
struct sched_domain *sd;
- unsigned long task_util;
+ unsigned long task_util, util_min, util_max;
int i, recent_used_cpu;
/*
@@ -6704,7 +7014,9 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
*/
if (sched_asym_cpucap_active()) {
sync_entity_load_avg(&p->se);
- task_util = uclamp_task_util(p);
+ task_util = task_util_est(p);
+ util_min = uclamp_eff_value(p, UCLAMP_MIN);
+ util_max = uclamp_eff_value(p, UCLAMP_MAX);
}
/*
@@ -6713,7 +7025,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
lockdep_assert_irqs_disabled();
if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
- asym_fits_capacity(task_util, target))
+ asym_fits_cpu(task_util, util_min, util_max, target))
return target;
/*
@@ -6721,7 +7033,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
*/
if (prev != target && cpus_share_cache(prev, target) &&
(available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
- asym_fits_capacity(task_util, prev))
+ asym_fits_cpu(task_util, util_min, util_max, prev))
return prev;
/*
@@ -6736,7 +7048,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
in_task() &&
prev == smp_processor_id() &&
this_rq()->nr_running <= 1 &&
- asym_fits_capacity(task_util, prev)) {
+ asym_fits_cpu(task_util, util_min, util_max, prev)) {
return prev;
}
@@ -6748,7 +7060,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
cpus_share_cache(recent_used_cpu, target) &&
(available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) &&
- asym_fits_capacity(task_util, recent_used_cpu)) {
+ asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
return recent_used_cpu;
}
@@ -7044,8 +7356,13 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
{
struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_rq_mask);
unsigned long prev_delta = ULONG_MAX, best_delta = ULONG_MAX;
+ unsigned long p_util_min = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MIN) : 0;
+ unsigned long p_util_max = uclamp_is_used() ? uclamp_eff_value(p, UCLAMP_MAX) : 1024;
struct root_domain *rd = this_rq()->rd;
int cpu, best_energy_cpu, target = -1;
+ int prev_fits = -1, best_fits = -1;
+ unsigned long best_thermal_cap = 0;
+ unsigned long prev_thermal_cap = 0;
struct sched_domain *sd;
struct perf_domain *pd;
struct energy_env eenv;
@@ -7068,17 +7385,20 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
target = prev_cpu;
sync_entity_load_avg(&p->se);
- if (!task_util_est(p))
+ if (!uclamp_task_util(p, p_util_min, p_util_max))
goto unlock;
eenv_task_busy_time(&eenv, p, prev_cpu);
for (; pd; pd = pd->next) {
+ unsigned long util_min = p_util_min, util_max = p_util_max;
unsigned long cpu_cap, cpu_thermal_cap, util;
unsigned long cur_delta, max_spare_cap = 0;
- bool compute_prev_delta = false;
+ unsigned long rq_util_min, rq_util_max;
+ unsigned long prev_spare_cap = 0;
int max_spare_cap_cpu = -1;
unsigned long base_energy;
+ int fits, max_fits = -1;
cpumask_and(cpus, perf_domain_span(pd), cpu_online_mask);
@@ -7094,6 +7414,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
eenv.pd_cap = 0;
for_each_cpu(cpu, cpus) {
+ struct rq *rq = cpu_rq(cpu);
+
eenv.pd_cap += cpu_thermal_cap;
if (!cpumask_test_cpu(cpu, sched_domain_span(sd)))
@@ -7112,26 +7434,45 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
* much capacity we can get out of the CPU; this is
* aligned with sched_cpu_util().
*/
- util = uclamp_rq_util_with(cpu_rq(cpu), util, p);
- if (!fits_capacity(util, cpu_cap))
+ if (uclamp_is_used() && !uclamp_rq_is_idle(rq)) {
+ /*
+ * Open code uclamp_rq_util_with() except for
+ * the clamp() part. Ie: apply max aggregation
+ * only. util_fits_cpu() logic requires to
+ * operate on non clamped util but must use the
+ * max-aggregated uclamp_{min, max}.
+ */
+ rq_util_min = uclamp_rq_get(rq, UCLAMP_MIN);
+ rq_util_max = uclamp_rq_get(rq, UCLAMP_MAX);
+
+ util_min = max(rq_util_min, p_util_min);
+ util_max = max(rq_util_max, p_util_max);
+ }
+
+ fits = util_fits_cpu(util, util_min, util_max, cpu);
+ if (!fits)
continue;
lsub_positive(&cpu_cap, util);
if (cpu == prev_cpu) {
/* Always use prev_cpu as a candidate. */
- compute_prev_delta = true;
- } else if (cpu_cap > max_spare_cap) {
+ prev_spare_cap = cpu_cap;
+ prev_fits = fits;
+ } else if ((fits > max_fits) ||
+ ((fits == max_fits) && (cpu_cap > max_spare_cap))) {
/*
* Find the CPU with the maximum spare capacity
- * in the performance domain.
+ * among the remaining CPUs in the performance
+ * domain.
*/
max_spare_cap = cpu_cap;
max_spare_cap_cpu = cpu;
+ max_fits = fits;
}
}
- if (max_spare_cap_cpu < 0 && !compute_prev_delta)
+ if (max_spare_cap_cpu < 0 && prev_spare_cap == 0)
continue;
eenv_pd_busy_time(&eenv, cpus, p);
@@ -7139,33 +7480,57 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
base_energy = compute_energy(&eenv, pd, cpus, p, -1);
/* Evaluate the energy impact of using prev_cpu. */
- if (compute_prev_delta) {
+ if (prev_spare_cap > 0) {
prev_delta = compute_energy(&eenv, pd, cpus, p,
prev_cpu);
/* CPU utilization has changed */
if (prev_delta < base_energy)
goto unlock;
prev_delta -= base_energy;
+ prev_thermal_cap = cpu_thermal_cap;
best_delta = min(best_delta, prev_delta);
}
/* Evaluate the energy impact of using max_spare_cap_cpu. */
- if (max_spare_cap_cpu >= 0) {
+ if (max_spare_cap_cpu >= 0 && max_spare_cap > prev_spare_cap) {
+ /* Current best energy cpu fits better */
+ if (max_fits < best_fits)
+ continue;
+
+ /*
+ * Both don't fit performance hint (i.e. uclamp_min)
+ * but best energy cpu has better capacity.
+ */
+ if ((max_fits < 0) &&
+ (cpu_thermal_cap <= best_thermal_cap))
+ continue;
+
cur_delta = compute_energy(&eenv, pd, cpus, p,
max_spare_cap_cpu);
/* CPU utilization has changed */
if (cur_delta < base_energy)
goto unlock;
cur_delta -= base_energy;
- if (cur_delta < best_delta) {
- best_delta = cur_delta;
- best_energy_cpu = max_spare_cap_cpu;
- }
+
+ /*
+ * Both fit for the task but best energy cpu has lower
+ * energy impact.
+ */
+ if ((max_fits > 0) && (best_fits > 0) &&
+ (cur_delta >= best_delta))
+ continue;
+
+ best_delta = cur_delta;
+ best_energy_cpu = max_spare_cap_cpu;
+ best_fits = max_fits;
+ best_thermal_cap = cpu_thermal_cap;
}
}
rcu_read_unlock();
- if (best_delta < prev_delta)
+ if ((best_fits > prev_fits) ||
+ ((best_fits > 0) && (best_delta < prev_delta)) ||
+ ((best_fits < 0) && (best_thermal_cap > prev_thermal_cap)))
target = best_energy_cpu;
return target;
@@ -8276,7 +8641,7 @@ static int detach_tasks(struct lb_env *env)
case migrate_misfit:
/* This is not a misfit task */
- if (task_fits_capacity(p, capacity_of(env->src_cpu)))
+ if (task_fits_cpu(p, env->src_cpu))
goto next;
env->imbalance = 0;
@@ -9281,6 +9646,10 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
memset(sgs, 0, sizeof(*sgs));
+ /* Assume that task can't fit any CPU of the group */
+ if (sd->flags & SD_ASYM_CPUCAPACITY)
+ sgs->group_misfit_task_load = 1;
+
for_each_cpu(i, sched_group_span(group)) {
struct rq *rq = cpu_rq(i);
unsigned int local;
@@ -9300,12 +9669,12 @@ static inline void update_sg_wakeup_stats(struct sched_domain *sd,
if (!nr_running && idle_cpu_without(i, p))
sgs->idle_cpus++;
- }
+ /* Check if task fits in the CPU */
+ if (sd->flags & SD_ASYM_CPUCAPACITY &&
+ sgs->group_misfit_task_load &&
+ task_fits_cpu(p, i))
+ sgs->group_misfit_task_load = 0;
- /* Check if task fits in the group */
- if (sd->flags & SD_ASYM_CPUCAPACITY &&
- !task_fits_capacity(p, group->sgc->max_capacity)) {
- sgs->group_misfit_task_load = 1;
}
sgs->group_capacity = group->sgc->capacity;
@@ -9898,24 +10267,23 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
*/
update_sd_lb_stats(env, &sds);
- if (sched_energy_enabled()) {
- struct root_domain *rd = env->dst_rq->rd;
-
- if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized))
- goto out_balanced;
- }
-
- local = &sds.local_stat;
- busiest = &sds.busiest_stat;
-
/* There is no busy sibling group to pull tasks from */
if (!sds.busiest)
goto out_balanced;
+ busiest = &sds.busiest_stat;
+
/* Misfit tasks should be dealt with regardless of the avg load */
if (busiest->group_type == group_misfit_task)
goto force_balance;
+ if (sched_energy_enabled()) {
+ struct root_domain *rd = env->dst_rq->rd;
+
+ if (rcu_dereference(rd->pd) && !READ_ONCE(rd->overutilized))
+ goto out_balanced;
+ }
+
/* ASYM feature bypasses nice load balance check */
if (busiest->group_type == group_asym_packing)
goto force_balance;
@@ -9928,6 +10296,7 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
if (busiest->group_type == group_imbalanced)
goto force_balance;
+ local = &sds.local_stat;
/*
* If the local group is busier than the selected busiest group
* don't try and pull any tasks.
@@ -11491,7 +11860,8 @@ static inline void task_tick_core(struct rq *rq, struct task_struct *curr)
/*
* se_fi_update - Update the cfs_rq->min_vruntime_fi in a CFS hierarchy if needed.
*/
-static void se_fi_update(struct sched_entity *se, unsigned int fi_seq, bool forceidle)
+static void se_fi_update(const struct sched_entity *se, unsigned int fi_seq,
+ bool forceidle)
{
for_each_sched_entity(se) {
struct cfs_rq *cfs_rq = cfs_rq_of(se);
@@ -11516,11 +11886,12 @@ void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi)
se_fi_update(se, rq->core->core_forceidle_seq, in_fi);
}
-bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool in_fi)
+bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
+ bool in_fi)
{
struct rq *rq = task_rq(a);
- struct sched_entity *sea = &a->se;
- struct sched_entity *seb = &b->se;
+ const struct sched_entity *sea = &a->se;
+ const struct sched_entity *seb = &b->se;
struct cfs_rq *cfs_rqa;
struct cfs_rq *cfs_rqb;
s64 delta;
@@ -12237,6 +12608,11 @@ __init void init_sched_fair_class(void)
for_each_possible_cpu(i) {
zalloc_cpumask_var_node(&per_cpu(load_balance_mask, i), GFP_KERNEL, cpu_to_node(i));
zalloc_cpumask_var_node(&per_cpu(select_rq_mask, i), GFP_KERNEL, cpu_to_node(i));
+
+#ifdef CONFIG_CFS_BANDWIDTH
+ INIT_CSD(&cpu_rq(i)->cfsb_csd, __cfsb_csd_unthrottle, cpu_rq(i));
+ INIT_LIST_HEAD(&cpu_rq(i)->cfsb_csd_list);
+#endif
}
open_softirq(SCHED_SOFTIRQ, run_rebalance_domains);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f26ab2675f7d..e9ef66be2870 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -51,18 +51,22 @@ __setup("hlt", cpu_idle_nopoll_setup);
static noinline int __cpuidle cpu_idle_poll(void)
{
+ instrumentation_begin();
trace_cpu_idle(0, smp_processor_id());
stop_critical_timings();
- ct_idle_enter();
- local_irq_enable();
+ ct_cpuidle_enter();
+ raw_local_irq_enable();
while (!tif_need_resched() &&
(cpu_idle_force_poll || tick_check_broadcast_expired()))
cpu_relax();
+ raw_local_irq_disable();
- ct_idle_exit();
+ ct_cpuidle_exit();
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
+ local_irq_enable();
+ instrumentation_end();
return 1;
}
@@ -75,7 +79,6 @@ void __weak arch_cpu_idle_dead(void) { }
void __weak arch_cpu_idle(void)
{
cpu_idle_force_poll = 1;
- raw_local_irq_enable();
}
/**
@@ -85,44 +88,20 @@ void __weak arch_cpu_idle(void)
*/
void __cpuidle default_idle_call(void)
{
- if (current_clr_polling_and_test()) {
- local_irq_enable();
- } else {
-
+ instrumentation_begin();
+ if (!current_clr_polling_and_test()) {
trace_cpu_idle(1, smp_processor_id());
stop_critical_timings();
- /*
- * arch_cpu_idle() is supposed to enable IRQs, however
- * we can't do that because of RCU and tracing.
- *
- * Trace IRQs enable here, then switch off RCU, and have
- * arch_cpu_idle() use raw_local_irq_enable(). Note that
- * ct_idle_enter() relies on lockdep IRQ state, so switch that
- * last -- this is very similar to the entry code.
- */
- trace_hardirqs_on_prepare();
- lockdep_hardirqs_on_prepare();
- ct_idle_enter();
- lockdep_hardirqs_on(_THIS_IP_);
-
+ ct_cpuidle_enter();
arch_cpu_idle();
-
- /*
- * OK, so IRQs are enabled here, but RCU needs them disabled to
- * turn itself back on.. funny thing is that disabling IRQs
- * will cause tracing, which needs RCU. Jump through hoops to
- * make it 'work'.
- */
- raw_local_irq_disable();
- lockdep_hardirqs_off(_THIS_IP_);
- ct_idle_exit();
- lockdep_hardirqs_on(_THIS_IP_);
- raw_local_irq_enable();
+ ct_cpuidle_exit();
start_critical_timings();
trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
}
+ local_irq_enable();
+ instrumentation_end();
}
static int call_cpuidle_s2idle(struct cpuidle_driver *drv,
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index 0c5be7ebb1dc..2ad881d07752 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -159,7 +159,8 @@
| MEMBARRIER_CMD_PRIVATE_EXPEDITED \
| MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED \
| MEMBARRIER_PRIVATE_EXPEDITED_SYNC_CORE_BITMASK \
- | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK)
+ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \
+ | MEMBARRIER_CMD_GET_REGISTRATIONS)
static void ipi_mb(void *info)
{
@@ -540,6 +541,40 @@ static int membarrier_register_private_expedited(int flags)
return 0;
}
+static int membarrier_get_registrations(void)
+{
+ struct task_struct *p = current;
+ struct mm_struct *mm = p->mm;
+ int registrations_mask = 0, membarrier_state, i;
+ static const int states[] = {
+ MEMBARRIER_STATE_GLOBAL_EXPEDITED |
+ MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY,
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED |
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY,
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE |
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY,
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ |
+ MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY
+ };
+ static const int registration_cmds[] = {
+ MEMBARRIER_CMD_REGISTER_GLOBAL_EXPEDITED,
+ MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED,
+ MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE,
+ MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ
+ };
+ BUILD_BUG_ON(ARRAY_SIZE(states) != ARRAY_SIZE(registration_cmds));
+
+ membarrier_state = atomic_read(&mm->membarrier_state);
+ for (i = 0; i < ARRAY_SIZE(states); ++i) {
+ if (membarrier_state & states[i]) {
+ registrations_mask |= registration_cmds[i];
+ membarrier_state &= ~states[i];
+ }
+ }
+ WARN_ON_ONCE(membarrier_state != 0);
+ return registrations_mask;
+}
+
/**
* sys_membarrier - issue memory barriers on a set of threads
* @cmd: Takes command values defined in enum membarrier_cmd.
@@ -623,6 +658,8 @@ SYSCALL_DEFINE3(membarrier, int, cmd, unsigned int, flags, int, cpu_id)
return membarrier_private_expedited(MEMBARRIER_FLAG_RSEQ, cpu_id);
case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ:
return membarrier_register_private_expedited(MEMBARRIER_FLAG_RSEQ);
+ case MEMBARRIER_CMD_GET_REGISTRATIONS:
+ return membarrier_get_registrations();
default:
return -EINVAL;
}
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index ee2ecc081422..02e011cabe91 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -189,6 +189,7 @@ static void group_init(struct psi_group *group)
INIT_DELAYED_WORK(&group->avgs_work, psi_avgs_work);
mutex_init(&group->avgs_lock);
/* Init trigger-related members */
+ atomic_set(&group->poll_scheduled, 0);
mutex_init(&group->trigger_lock);
INIT_LIST_HEAD(&group->triggers);
group->poll_min_period = U32_MAX;
@@ -242,6 +243,8 @@ static void get_recent_times(struct psi_group *group, int cpu,
u32 *pchanged_states)
{
struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
+ int current_cpu = raw_smp_processor_id();
+ unsigned int tasks[NR_PSI_TASK_COUNTS];
u64 now, state_start;
enum psi_states s;
unsigned int seq;
@@ -256,6 +259,8 @@ static void get_recent_times(struct psi_group *group, int cpu,
memcpy(times, groupc->times, sizeof(groupc->times));
state_mask = groupc->state_mask;
state_start = groupc->state_start;
+ if (cpu == current_cpu)
+ memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
} while (read_seqcount_retry(&groupc->seq, seq));
/* Calculate state time deltas against the previous snapshot */
@@ -280,6 +285,28 @@ static void get_recent_times(struct psi_group *group, int cpu,
if (delta)
*pchanged_states |= (1 << s);
}
+
+ /*
+ * When collect_percpu_times() from the avgs_work, we don't want to
+ * re-arm avgs_work when all CPUs are IDLE. But the current CPU running
+ * this avgs_work is never IDLE, cause avgs_work can't be shut off.
+ * So for the current CPU, we need to re-arm avgs_work only when
+ * (NR_RUNNING > 1 || NR_IOWAIT > 0 || NR_MEMSTALL > 0), for other CPUs
+ * we can just check PSI_NONIDLE delta.
+ */
+ if (current_work() == &group->avgs_work.work) {
+ bool reschedule;
+
+ if (cpu == current_cpu)
+ reschedule = tasks[NR_RUNNING] +
+ tasks[NR_IOWAIT] +
+ tasks[NR_MEMSTALL] > 1;
+ else
+ reschedule = *pchanged_states & (1 << PSI_NONIDLE);
+
+ if (reschedule)
+ *pchanged_states |= PSI_STATE_RESCHEDULE;
+ }
}
static void calc_avgs(unsigned long avg[3], int missed_periods,
@@ -415,7 +442,6 @@ static void psi_avgs_work(struct work_struct *work)
struct delayed_work *dwork;
struct psi_group *group;
u32 changed_states;
- bool nonidle;
u64 now;
dwork = to_delayed_work(work);
@@ -426,7 +452,6 @@ static void psi_avgs_work(struct work_struct *work)
now = sched_clock();
collect_percpu_times(group, PSI_AVGS, &changed_states);
- nonidle = changed_states & (1 << PSI_NONIDLE);
/*
* If there is task activity, periodically fold the per-cpu
* times and feed samples into the running averages. If things
@@ -437,7 +462,7 @@ static void psi_avgs_work(struct work_struct *work)
if (now >= group->avg_next_update)
group->avg_next_update = update_averages(group, now);
- if (nonidle) {
+ if (changed_states & PSI_STATE_RESCHEDULE) {
schedule_delayed_work(dwork, nsecs_to_jiffies(
group->avg_next_update - now) + 1);
}
@@ -539,10 +564,12 @@ static u64 update_triggers(struct psi_group *group, u64 now)
/* Calculate growth since last update */
growth = window_update(&t->win, now, total[t->state]);
- if (growth < t->threshold)
- continue;
+ if (!t->pending_event) {
+ if (growth < t->threshold)
+ continue;
- t->pending_event = true;
+ t->pending_event = true;
+ }
}
/* Limit event signaling to once per window */
if (now < t->last_event_time + t->win.size)
@@ -563,18 +590,17 @@ static u64 update_triggers(struct psi_group *group, u64 now)
return now + group->poll_min_period;
}
-/* Schedule polling if it's not already scheduled. */
-static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
+/* Schedule polling if it's not already scheduled or forced. */
+static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay,
+ bool force)
{
struct task_struct *task;
/*
- * Do not reschedule if already scheduled.
- * Possible race with a timer scheduled after this check but before
- * mod_timer below can be tolerated because group->polling_next_update
- * will keep updates on schedule.
+ * atomic_xchg should be called even when !force to provide a
+ * full memory barrier (see the comment inside psi_poll_work).
*/
- if (timer_pending(&group->poll_timer))
+ if (atomic_xchg(&group->poll_scheduled, 1) && !force)
return;
rcu_read_lock();
@@ -586,12 +612,15 @@ static void psi_schedule_poll_work(struct psi_group *group, unsigned long delay)
*/
if (likely(task))
mod_timer(&group->poll_timer, jiffies + delay);
+ else
+ atomic_set(&group->poll_scheduled, 0);
rcu_read_unlock();
}
static void psi_poll_work(struct psi_group *group)
{
+ bool force_reschedule = false;
u32 changed_states;
u64 now;
@@ -599,6 +628,43 @@ static void psi_poll_work(struct psi_group *group)
now = sched_clock();
+ if (now > group->polling_until) {
+ /*
+ * We are either about to start or might stop polling if no
+ * state change was recorded. Resetting poll_scheduled leaves
+ * a small window for psi_group_change to sneak in and schedule
+ * an immediate poll_work before we get to rescheduling. One
+ * potential extra wakeup at the end of the polling window
+ * should be negligible and polling_next_update still keeps
+ * updates correctly on schedule.
+ */
+ atomic_set(&group->poll_scheduled, 0);
+ /*
+ * A task change can race with the poll worker that is supposed to
+ * report on it. To avoid missing events, ensure ordering between
+ * poll_scheduled and the task state accesses, such that if the poll
+ * worker misses the state update, the task change is guaranteed to
+ * reschedule the poll worker:
+ *
+ * poll worker:
+ * atomic_set(poll_scheduled, 0)
+ * smp_mb()
+ * LOAD states
+ *
+ * task change:
+ * STORE states
+ * if atomic_xchg(poll_scheduled, 1) == 0:
+ * schedule poll worker
+ *
+ * The atomic_xchg() implies a full barrier.
+ */
+ smp_mb();
+ } else {
+ /* Polling window is not over, keep rescheduling */
+ force_reschedule = true;
+ }
+
+
collect_percpu_times(group, PSI_POLL, &changed_states);
if (changed_states & group->poll_states) {
@@ -624,7 +690,8 @@ static void psi_poll_work(struct psi_group *group)
group->polling_next_update = update_triggers(group, now);
psi_schedule_poll_work(group,
- nsecs_to_jiffies(group->polling_next_update - now) + 1);
+ nsecs_to_jiffies(group->polling_next_update - now) + 1,
+ force_reschedule);
out:
mutex_unlock(&group->trigger_lock);
@@ -785,7 +852,7 @@ static void psi_group_change(struct psi_group *group, int cpu,
write_seqcount_end(&groupc->seq);
if (state_mask & group->poll_states)
- psi_schedule_poll_work(group, 1);
+ psi_schedule_poll_work(group, 1, false);
if (wake_clock && !delayed_work_pending(&group->avgs_work))
schedule_delayed_work(&group->avgs_work, PSI_FREQ);
@@ -939,7 +1006,7 @@ void psi_account_irqtime(struct task_struct *task, u32 delta)
write_seqcount_end(&groupc->seq);
if (group->poll_states & (1 << PSI_IRQ_FULL))
- psi_schedule_poll_work(group, 1);
+ psi_schedule_poll_work(group, 1, false);
} while ((group = group->parent));
}
#endif
@@ -1276,10 +1343,11 @@ void psi_trigger_destroy(struct psi_trigger *t)
group = t->group;
/*
- * Wakeup waiters to stop polling. Can happen if cgroup is deleted
- * from under a polling process.
+ * Wakeup waiters to stop polling and clear the queue to prevent it from
+ * being accessed later. Can happen if cgroup is deleted from under a
+ * polling process.
*/
- wake_up_interruptible(&t->event_wait);
+ wake_up_pollfree(&t->event_wait);
mutex_lock(&group->trigger_lock);
@@ -1325,6 +1393,7 @@ void psi_trigger_destroy(struct psi_trigger *t)
* can no longer be found through group->poll_task.
*/
kthread_stop(task_to_destroy);
+ atomic_set(&group->poll_scheduled, 0);
}
kfree(t);
}
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index ed2a47e4ddae..0a11f44adee5 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1777,6 +1777,8 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rt_rq *rt_rq)
BUG_ON(idx >= MAX_RT_PRIO);
queue = array->queue + idx;
+ if (SCHED_WARN_ON(list_empty(queue)))
+ return NULL;
next = list_entry(queue->next, struct sched_rt_entity, run_list);
return next;
@@ -1789,7 +1791,8 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq)
do {
rt_se = pick_next_rt_entity(rt_rq);
- BUG_ON(!rt_se);
+ if (unlikely(!rt_se))
+ return NULL;
rt_rq = group_rt_rq(rt_se);
} while (rt_rq);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index a4a20046e586..3e8df6d31c1e 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -248,7 +248,7 @@ static inline void update_avg(u64 *avg, u64 sample)
#define SCHED_DL_FLAGS (SCHED_FLAG_RECLAIM | SCHED_FLAG_DL_OVERRUN | SCHED_FLAG_SUGOV)
-static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se)
+static inline bool dl_entity_is_special(const struct sched_dl_entity *dl_se)
{
#ifdef CONFIG_CPU_FREQ_GOV_SCHEDUTIL
return unlikely(dl_se->flags & SCHED_FLAG_SUGOV);
@@ -260,8 +260,8 @@ static inline bool dl_entity_is_special(struct sched_dl_entity *dl_se)
/*
* Tells if entity @a should preempt entity @b.
*/
-static inline bool
-dl_entity_preempt(struct sched_dl_entity *a, struct sched_dl_entity *b)
+static inline bool dl_entity_preempt(const struct sched_dl_entity *a,
+ const struct sched_dl_entity *b)
{
return dl_entity_is_special(a) ||
dl_time_before(a->deadline, b->deadline);
@@ -645,6 +645,9 @@ struct cfs_rq {
int throttled;
int throttle_count;
struct list_head throttled_list;
+#ifdef CONFIG_SMP
+ struct list_head throttled_csd_list;
+#endif
#endif /* CONFIG_CFS_BANDWIDTH */
#endif /* CONFIG_FAIR_GROUP_SCHED */
};
@@ -1150,6 +1153,14 @@ struct rq {
unsigned int core_forceidle_occupation;
u64 core_forceidle_start;
#endif
+
+ /* Scratch cpumask to be temporarily used under rq_lock */
+ cpumask_var_t scratch_mask;
+
+#if defined(CONFIG_CFS_BANDWIDTH) && defined(CONFIG_SMP)
+ call_single_data_t cfsb_csd;
+ struct list_head cfsb_csd_list;
+#endif
};
#ifdef CONFIG_FAIR_GROUP_SCHED
@@ -1232,7 +1243,8 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
return &rq->__lock;
}
-bool cfs_prio_less(struct task_struct *a, struct task_struct *b, bool fi);
+bool cfs_prio_less(const struct task_struct *a, const struct task_struct *b,
+ bool fi);
/*
* Helpers to check if the CPU's core cookie matches with the task's cookie
@@ -1411,7 +1423,7 @@ static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
}
/* runqueue on which this entity is (to be) queued */
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+static inline struct cfs_rq *cfs_rq_of(const struct sched_entity *se)
{
return se->cfs_rq;
}
@@ -1424,19 +1436,16 @@ static inline struct cfs_rq *group_cfs_rq(struct sched_entity *grp)
#else
-static inline struct task_struct *task_of(struct sched_entity *se)
-{
- return container_of(se, struct task_struct, se);
-}
+#define task_of(_se) container_of(_se, struct task_struct, se)
-static inline struct cfs_rq *task_cfs_rq(struct task_struct *p)
+static inline struct cfs_rq *task_cfs_rq(const struct task_struct *p)
{
return &task_rq(p)->cfs;
}
-static inline struct cfs_rq *cfs_rq_of(struct sched_entity *se)
+static inline struct cfs_rq *cfs_rq_of(const struct sched_entity *se)
{
- struct task_struct *p = task_of(se);
+ const struct task_struct *p = task_of(se);
struct rq *rq = task_rq(p);
return &rq->cfs;
@@ -1877,6 +1886,13 @@ static inline void dirty_sched_domain_sysctl(int cpu)
#endif
extern int sched_update_scaling(void);
+
+static inline const struct cpumask *task_user_cpus(struct task_struct *p)
+{
+ if (!p->user_cpus_ptr)
+ return cpu_possible_mask; /* &init_task.cpus_mask */
+ return p->user_cpus_ptr;
+}
#endif /* CONFIG_SMP */
#include "stats.h"
@@ -2144,6 +2160,12 @@ extern const u32 sched_prio_to_wmult[40];
#define RETRY_TASK ((void *)-1UL)
+struct affinity_context {
+ const struct cpumask *new_mask;
+ struct cpumask *user_mask;
+ unsigned int flags;
+};
+
struct sched_class {
#ifdef CONFIG_UCLAMP_TASK
@@ -2172,9 +2194,7 @@ struct sched_class {
void (*task_woken)(struct rq *this_rq, struct task_struct *task);
- void (*set_cpus_allowed)(struct task_struct *p,
- const struct cpumask *newmask,
- u32 flags);
+ void (*set_cpus_allowed)(struct task_struct *p, struct affinity_context *ctx);
void (*rq_online)(struct rq *rq);
void (*rq_offline)(struct rq *rq);
@@ -2285,7 +2305,7 @@ extern void update_group_capacity(struct sched_domain *sd, int cpu);
extern void trigger_load_balance(struct rq *rq);
-extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags);
+extern void set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx);
static inline struct task_struct *get_push_task(struct rq *rq)
{
@@ -2979,6 +2999,23 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
#ifdef CONFIG_UCLAMP_TASK
unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
+static inline unsigned long uclamp_rq_get(struct rq *rq,
+ enum uclamp_id clamp_id)
+{
+ return READ_ONCE(rq->uclamp[clamp_id].value);
+}
+
+static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id,
+ unsigned int value)
+{
+ WRITE_ONCE(rq->uclamp[clamp_id].value, value);
+}
+
+static inline bool uclamp_rq_is_idle(struct rq *rq)
+{
+ return rq->uclamp_flags & UCLAMP_FLAG_IDLE;
+}
+
/**
* uclamp_rq_util_with - clamp @util with @rq and @p effective uclamp values.
* @rq: The rq to clamp against. Must not be NULL.
@@ -3014,12 +3051,12 @@ unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
* Ignore last runnable task's max clamp, as this task will
* reset it. Similarly, no need to read the rq's min clamp.
*/
- if (rq->uclamp_flags & UCLAMP_FLAG_IDLE)
+ if (uclamp_rq_is_idle(rq))
goto out;
}
- min_util = max_t(unsigned long, min_util, READ_ONCE(rq->uclamp[UCLAMP_MIN].value));
- max_util = max_t(unsigned long, max_util, READ_ONCE(rq->uclamp[UCLAMP_MAX].value));
+ min_util = max_t(unsigned long, min_util, uclamp_rq_get(rq, UCLAMP_MIN));
+ max_util = max_t(unsigned long, max_util, uclamp_rq_get(rq, UCLAMP_MAX));
out:
/*
* Since CPU's {min,max}_util clamps are MAX aggregated considering
@@ -3060,6 +3097,15 @@ static inline bool uclamp_is_used(void)
return static_branch_likely(&sched_uclamp_used);
}
#else /* CONFIG_UCLAMP_TASK */
+static inline unsigned long uclamp_eff_value(struct task_struct *p,
+ enum uclamp_id clamp_id)
+{
+ if (clamp_id == UCLAMP_MIN)
+ return 0;
+
+ return SCHED_CAPACITY_SCALE;
+}
+
static inline
unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
struct task_struct *p)
@@ -3073,6 +3119,25 @@ static inline bool uclamp_is_used(void)
{
return false;
}
+
+static inline unsigned long uclamp_rq_get(struct rq *rq,
+ enum uclamp_id clamp_id)
+{
+ if (clamp_id == UCLAMP_MIN)
+ return 0;
+
+ return SCHED_CAPACITY_SCALE;
+}
+
+static inline void uclamp_rq_set(struct rq *rq, enum uclamp_id clamp_id,
+ unsigned int value)
+{
+}
+
+static inline bool uclamp_rq_is_idle(struct rq *rq)
+{
+ return false;
+}
#endif /* CONFIG_UCLAMP_TASK */
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
@@ -3183,4 +3248,62 @@ static inline void update_current_exec_runtime(struct task_struct *curr,
cgroup_account_cputime(curr, delta_exec);
}
+#ifdef CONFIG_SCHED_MM_CID
+static inline int __mm_cid_get(struct mm_struct *mm)
+{
+ struct cpumask *cpumask;
+ int cid;
+
+ cpumask = mm_cidmask(mm);
+ cid = cpumask_first_zero(cpumask);
+ if (cid >= nr_cpu_ids)
+ return -1;
+ __cpumask_set_cpu(cid, cpumask);
+ return cid;
+}
+
+static inline void mm_cid_put(struct mm_struct *mm, int cid)
+{
+ lockdep_assert_irqs_disabled();
+ if (cid < 0)
+ return;
+ raw_spin_lock(&mm->cid_lock);
+ __cpumask_clear_cpu(cid, mm_cidmask(mm));
+ raw_spin_unlock(&mm->cid_lock);
+}
+
+static inline int mm_cid_get(struct mm_struct *mm)
+{
+ int ret;
+
+ lockdep_assert_irqs_disabled();
+ raw_spin_lock(&mm->cid_lock);
+ ret = __mm_cid_get(mm);
+ raw_spin_unlock(&mm->cid_lock);
+ return ret;
+}
+
+static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next)
+{
+ if (prev->mm_cid_active) {
+ if (next->mm_cid_active && next->mm == prev->mm) {
+ /*
+ * Context switch between threads in same mm, hand over
+ * the mm_cid from prev to next.
+ */
+ next->mm_cid = prev->mm_cid;
+ prev->mm_cid = -1;
+ return;
+ }
+ mm_cid_put(prev->mm, prev->mm_cid);
+ prev->mm_cid = -1;
+ }
+ if (next->mm_cid_active)
+ next->mm_cid = mm_cid_get(next->mm);
+}
+
+#else
+static inline void switch_mm_cid(struct task_struct *prev, struct task_struct *next) { }
+#endif
+
#endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
index 84a188913cc9..38f3698f5e5b 100644
--- a/kernel/sched/stats.h
+++ b/kernel/sched/stats.h
@@ -128,11 +128,9 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup)
if (p->in_memstall)
set |= TSK_MEMSTALL_RUNNING;
- if (!wakeup || p->sched_psi_wake_requeue) {
+ if (!wakeup) {
if (p->in_memstall)
set |= TSK_MEMSTALL;
- if (p->sched_psi_wake_requeue)
- p->sched_psi_wake_requeue = 0;
} else {
if (p->in_iowait)
clear |= TSK_IOWAIT;
@@ -143,8 +141,6 @@ static inline void psi_enqueue(struct task_struct *p, bool wakeup)
static inline void psi_dequeue(struct task_struct *p, bool sleep)
{
- int clear = TSK_RUNNING;
-
if (static_branch_likely(&psi_disabled))
return;
@@ -157,10 +153,7 @@ static inline void psi_dequeue(struct task_struct *p, bool sleep)
if (sleep)
return;
- if (p->in_memstall)
- clear |= (TSK_MEMSTALL | TSK_MEMSTALL_RUNNING);
-
- psi_task_change(p, clear, 0);
+ psi_task_change(p, p->psi_flags, 0);
}
static inline void psi_ttwu_dequeue(struct task_struct *p)
@@ -172,19 +165,12 @@ static inline void psi_ttwu_dequeue(struct task_struct *p)
* deregister its sleep-persistent psi states from the old
* queue, and let psi_enqueue() know it has to requeue.
*/
- if (unlikely(p->in_iowait || p->in_memstall)) {
+ if (unlikely(p->psi_flags)) {
struct rq_flags rf;
struct rq *rq;
- int clear = 0;
-
- if (p->in_iowait)
- clear |= TSK_IOWAIT;
- if (p->in_memstall)
- clear |= TSK_MEMSTALL;
rq = __task_rq_lock(p, &rf);
- psi_task_change(p, clear, 0);
- p->sched_psi_wake_requeue = 1;
+ psi_task_change(p, p->psi_flags, 0);
__task_rq_unlock(rq, &rf);
}
}
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8739c2a5a54e..051aaf65c749 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -3,6 +3,8 @@
* Scheduler topology setup/handling methods
*/
+#include <linux/bsearch.h>
+
DEFINE_MUTEX(sched_domains_mutex);
/* Protected by sched_domains_mutex: */
@@ -578,7 +580,7 @@ out:
*/
struct root_domain def_root_domain;
-void init_defrootdomain(void)
+void __init init_defrootdomain(void)
{
init_rootdomain(&def_root_domain);
@@ -2067,6 +2069,99 @@ unlock:
return found;
}
+struct __cmp_key {
+ const struct cpumask *cpus;
+ struct cpumask ***masks;
+ int node;
+ int cpu;
+ int w;
+};
+
+static int hop_cmp(const void *a, const void *b)
+{
+ struct cpumask **prev_hop, **cur_hop = *(struct cpumask ***)b;
+ struct __cmp_key *k = (struct __cmp_key *)a;
+
+ if (cpumask_weight_and(k->cpus, cur_hop[k->node]) <= k->cpu)
+ return 1;
+
+ if (b == k->masks) {
+ k->w = 0;
+ return 0;
+ }
+
+ prev_hop = *((struct cpumask ***)b - 1);
+ k->w = cpumask_weight_and(k->cpus, prev_hop[k->node]);
+ if (k->w <= k->cpu)
+ return 0;
+
+ return -1;
+}
+
+/*
+ * sched_numa_find_nth_cpu() - given the NUMA topology, find the Nth next cpu
+ * closest to @cpu from @cpumask.
+ * cpumask: cpumask to find a cpu from
+ * cpu: Nth cpu to find
+ *
+ * returns: cpu, or nr_cpu_ids when nothing found.
+ */
+int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
+{
+ struct __cmp_key k = { .cpus = cpus, .node = node, .cpu = cpu };
+ struct cpumask ***hop_masks;
+ int hop, ret = nr_cpu_ids;
+
+ rcu_read_lock();
+
+ k.masks = rcu_dereference(sched_domains_numa_masks);
+ if (!k.masks)
+ goto unlock;
+
+ hop_masks = bsearch(&k, k.masks, sched_domains_numa_levels, sizeof(k.masks[0]), hop_cmp);
+ hop = hop_masks - k.masks;
+
+ ret = hop ?
+ cpumask_nth_and_andnot(cpu - k.w, cpus, k.masks[hop][node], k.masks[hop-1][node]) :
+ cpumask_nth_and(cpu, cpus, k.masks[0][node]);
+unlock:
+ rcu_read_unlock();
+ return ret;
+}
+EXPORT_SYMBOL_GPL(sched_numa_find_nth_cpu);
+
+/**
+ * sched_numa_hop_mask() - Get the cpumask of CPUs at most @hops hops away from
+ * @node
+ * @node: The node to count hops from.
+ * @hops: Include CPUs up to that many hops away. 0 means local node.
+ *
+ * Return: On success, a pointer to a cpumask of CPUs at most @hops away from
+ * @node, an error value otherwise.
+ *
+ * Requires rcu_lock to be held. Returned cpumask is only valid within that
+ * read-side section, copy it if required beyond that.
+ *
+ * Note that not all hops are equal in distance; see sched_init_numa() for how
+ * distances and masks are handled.
+ * Also note that this is a reflection of sched_domains_numa_masks, which may change
+ * during the lifetime of the system (offline nodes are taken out of the masks).
+ */
+const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops)
+{
+ struct cpumask ***masks;
+
+ if (node >= nr_node_ids || hops >= sched_domains_numa_levels)
+ return ERR_PTR(-EINVAL);
+
+ masks = rcu_dereference(sched_domains_numa_masks);
+ if (!masks)
+ return ERR_PTR(-EBUSY);
+
+ return masks[hops][node];
+}
+EXPORT_SYMBOL_GPL(sched_numa_hop_mask);
+
#endif /* CONFIG_NUMA */
static int __sdt_alloc(const struct cpumask *cpu_map)
@@ -2451,7 +2546,7 @@ void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms)
* Set up scheduler domains and groups. For now this just excludes isolated
* CPUs, but could be used to exclude other special cases in the future.
*/
-int sched_init_domains(const struct cpumask *cpu_map)
+int __init sched_init_domains(const struct cpumask *cpu_map)
{
int err;
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 9860bb9a847c..133b74730738 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -121,11 +121,12 @@ static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
return nr_exclusive;
}
-static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int mode,
+static int __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int mode,
int nr_exclusive, int wake_flags, void *key)
{
unsigned long flags;
wait_queue_entry_t bookmark;
+ int remaining = nr_exclusive;
bookmark.flags = 0;
bookmark.private = NULL;
@@ -134,10 +135,12 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
do {
spin_lock_irqsave(&wq_head->lock, flags);
- nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive,
+ remaining = __wake_up_common(wq_head, mode, remaining,
wake_flags, key, &bookmark);
spin_unlock_irqrestore(&wq_head->lock, flags);
} while (bookmark.flags & WQ_FLAG_BOOKMARK);
+
+ return nr_exclusive - remaining;
}
/**
@@ -147,13 +150,14 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
* @nr_exclusive: how many wake-one or wake-many threads to wake up
* @key: is directly passed to the wakeup function
*
- * If this function wakes up a task, it executes a full memory barrier before
- * accessing the task state.
+ * If this function wakes up a task, it executes a full memory barrier
+ * before accessing the task state. Returns the number of exclusive
+ * tasks that were awaken.
*/
-void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
- int nr_exclusive, void *key)
+int __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
+ int nr_exclusive, void *key)
{
- __wake_up_common_lock(wq_head, mode, nr_exclusive, 0, key);
+ return __wake_up_common_lock(wq_head, mode, nr_exclusive, 0, key);
}
EXPORT_SYMBOL(__wake_up);