aboutsummaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/events/core.c45
-rw-r--r--kernel/sched/cputime.c6
-rw-r--r--kernel/sched/fair.c127
-rw-r--r--kernel/sched/sched.h4
-rw-r--r--kernel/trace/trace.c1
5 files changed, 75 insertions, 108 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a690905247fe..1624c5a926ab 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3685,11 +3685,23 @@ static void rotate_ctx(struct perf_event_context *ctx, struct perf_event *event)
perf_event_groups_insert(&ctx->flexible_groups, event);
}
+/* pick an event from the flexible_groups to rotate */
static inline struct perf_event *
-ctx_first_active(struct perf_event_context *ctx)
+ctx_event_to_rotate(struct perf_event_context *ctx)
{
- return list_first_entry_or_null(&ctx->flexible_active,
- struct perf_event, active_list);
+ struct perf_event *event;
+
+ /* pick the first active flexible event */
+ event = list_first_entry_or_null(&ctx->flexible_active,
+ struct perf_event, active_list);
+
+ /* if no active flexible event, pick the first event */
+ if (!event) {
+ event = rb_entry_safe(rb_first(&ctx->flexible_groups.tree),
+ typeof(*event), group_node);
+ }
+
+ return event;
}
static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
@@ -3721,9 +3733,9 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
perf_pmu_disable(cpuctx->ctx.pmu);
if (task_rotate)
- task_event = ctx_first_active(ctx);
+ task_event = ctx_event_to_rotate(ctx);
if (cpu_rotate)
- cpu_event = ctx_first_active(&cpuctx->ctx);
+ cpu_event = ctx_event_to_rotate(&cpuctx->ctx);
/*
* As per the order given at ctx_resched() first 'pop' task flexible
@@ -5510,8 +5522,10 @@ static void perf_mmap_close(struct vm_area_struct *vma)
perf_pmu_output_stop(event);
/* now it's safe to free the pages */
- atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
- atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm);
+ if (!rb->aux_mmap_locked)
+ atomic_long_sub(rb->aux_nr_pages, &mmap_user->locked_vm);
+ else
+ atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm);
/* this has to be the last one */
rb_free_aux(rb);
@@ -5583,7 +5597,8 @@ again:
* undo the VM accounting.
*/
- atomic_long_sub((size >> PAGE_SHIFT) + 1, &mmap_user->locked_vm);
+ atomic_long_sub((size >> PAGE_SHIFT) + 1 - mmap_locked,
+ &mmap_user->locked_vm);
atomic64_sub(mmap_locked, &vma->vm_mm->pinned_vm);
free_uid(mmap_user);
@@ -5727,8 +5742,20 @@ accounting:
user_locked = atomic_long_read(&user->locked_vm) + user_extra;
- if (user_locked > user_lock_limit)
+ if (user_locked <= user_lock_limit) {
+ /* charge all to locked_vm */
+ } else if (atomic_long_read(&user->locked_vm) >= user_lock_limit) {
+ /* charge all to pinned_vm */
+ extra = user_extra;
+ user_extra = 0;
+ } else {
+ /*
+ * charge locked_vm until it hits user_lock_limit;
+ * charge the rest from pinned_vm
+ */
extra = user_locked - user_lock_limit;
+ user_extra -= extra;
+ }
lock_limit = rlimit(RLIMIT_MEMLOCK);
lock_limit >>= PAGE_SHIFT;
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2305ce89a26c..46ed4e1383e2 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -740,7 +740,7 @@ void vtime_account_system(struct task_struct *tsk)
write_seqcount_begin(&vtime->seqcount);
/* We might have scheduled out from guest path */
- if (current->flags & PF_VCPU)
+ if (tsk->flags & PF_VCPU)
vtime_account_guest(tsk, vtime);
else
__vtime_account_system(tsk, vtime);
@@ -783,7 +783,7 @@ void vtime_guest_enter(struct task_struct *tsk)
*/
write_seqcount_begin(&vtime->seqcount);
__vtime_account_system(tsk, vtime);
- current->flags |= PF_VCPU;
+ tsk->flags |= PF_VCPU;
write_seqcount_end(&vtime->seqcount);
}
EXPORT_SYMBOL_GPL(vtime_guest_enter);
@@ -794,7 +794,7 @@ void vtime_guest_exit(struct task_struct *tsk)
write_seqcount_begin(&vtime->seqcount);
vtime_account_guest(tsk, vtime);
- current->flags &= ~PF_VCPU;
+ tsk->flags &= ~PF_VCPU;
write_seqcount_end(&vtime->seqcount);
}
EXPORT_SYMBOL_GPL(vtime_guest_exit);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 5a312c030b8d..46ec31450b90 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4334,23 +4334,16 @@ static inline u64 sched_cfs_bandwidth_slice(void)
}
/*
- * Replenish runtime according to assigned quota and update expiration time.
- * We use sched_clock_cpu directly instead of rq->clock to avoid adding
- * additional synchronization around rq->lock.
+ * Replenish runtime according to assigned quota. We use sched_clock_cpu
+ * directly instead of rq->clock to avoid adding additional synchronization
+ * around rq->lock.
*
* requires cfs_b->lock
*/
void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
{
- u64 now;
-
- if (cfs_b->quota == RUNTIME_INF)
- return;
-
- now = sched_clock_cpu(smp_processor_id());
- cfs_b->runtime = cfs_b->quota;
- cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
- cfs_b->expires_seq++;
+ if (cfs_b->quota != RUNTIME_INF)
+ cfs_b->runtime = cfs_b->quota;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4372,8 +4365,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
{
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
- u64 amount = 0, min_amount, expires;
- int expires_seq;
+ u64 amount = 0, min_amount;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4390,61 +4382,17 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
cfs_b->idle = 0;
}
}
- expires_seq = cfs_b->expires_seq;
- expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
cfs_rq->runtime_remaining += amount;
- /*
- * we may have advanced our local expiration to account for allowed
- * spread between our sched_clock and the one on which runtime was
- * issued.
- */
- if (cfs_rq->expires_seq != expires_seq) {
- cfs_rq->expires_seq = expires_seq;
- cfs_rq->runtime_expires = expires;
- }
return cfs_rq->runtime_remaining > 0;
}
-/*
- * Note: This depends on the synchronization provided by sched_clock and the
- * fact that rq->clock snapshots this value.
- */
-static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
-{
- struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
-
- /* if the deadline is ahead of our clock, nothing to do */
- if (likely((s64)(rq_clock(rq_of(cfs_rq)) - cfs_rq->runtime_expires) < 0))
- return;
-
- if (cfs_rq->runtime_remaining < 0)
- return;
-
- /*
- * If the local deadline has passed we have to consider the
- * possibility that our sched_clock is 'fast' and the global deadline
- * has not truly expired.
- *
- * Fortunately we can check determine whether this the case by checking
- * whether the global deadline(cfs_b->expires_seq) has advanced.
- */
- if (cfs_rq->expires_seq == cfs_b->expires_seq) {
- /* extend local deadline, drift is bounded above by 2 ticks */
- cfs_rq->runtime_expires += TICK_NSEC;
- } else {
- /* global deadline is ahead, expiration has passed */
- cfs_rq->runtime_remaining = 0;
- }
-}
-
static void __account_cfs_rq_runtime(struct cfs_rq *cfs_rq, u64 delta_exec)
{
/* dock delta_exec before expiring quota (as it could span periods) */
cfs_rq->runtime_remaining -= delta_exec;
- expire_cfs_rq_runtime(cfs_rq);
if (likely(cfs_rq->runtime_remaining > 0))
return;
@@ -4637,8 +4585,7 @@ void unthrottle_cfs_rq(struct cfs_rq *cfs_rq)
resched_curr(rq);
}
-static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
- u64 remaining, u64 expires)
+static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b, u64 remaining)
{
struct cfs_rq *cfs_rq;
u64 runtime;
@@ -4663,7 +4610,6 @@ static u64 distribute_cfs_runtime(struct cfs_bandwidth *cfs_b,
remaining -= runtime;
cfs_rq->runtime_remaining += runtime;
- cfs_rq->runtime_expires = expires;
/* we check whether we're throttled above */
if (cfs_rq->runtime_remaining > 0)
@@ -4688,7 +4634,7 @@ next:
*/
static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, unsigned long flags)
{
- u64 runtime, runtime_expires;
+ u64 runtime;
int throttled;
/* no need to continue the timer with no bandwidth constraint */
@@ -4716,8 +4662,6 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
/* account preceding periods in which throttling occurred */
cfs_b->nr_throttled += overrun;
- runtime_expires = cfs_b->runtime_expires;
-
/*
* This check is repeated as we are holding onto the new bandwidth while
* we unthrottle. This can potentially race with an unthrottled group
@@ -4730,8 +4674,7 @@ static int do_sched_cfs_period_timer(struct cfs_bandwidth *cfs_b, int overrun, u
cfs_b->distribute_running = 1;
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
/* we can't nest cfs_b->lock while distributing bandwidth */
- runtime = distribute_cfs_runtime(cfs_b, runtime,
- runtime_expires);
+ runtime = distribute_cfs_runtime(cfs_b, runtime);
raw_spin_lock_irqsave(&cfs_b->lock, flags);
cfs_b->distribute_running = 0;
@@ -4808,8 +4751,7 @@ static void __return_cfs_rq_runtime(struct cfs_rq *cfs_rq)
return;
raw_spin_lock(&cfs_b->lock);
- if (cfs_b->quota != RUNTIME_INF &&
- cfs_rq->runtime_expires == cfs_b->runtime_expires) {
+ if (cfs_b->quota != RUNTIME_INF) {
cfs_b->runtime += slack_runtime;
/* we are under rq->lock, defer unthrottling using a timer */
@@ -4842,7 +4784,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
{
u64 runtime = 0, slice = sched_cfs_bandwidth_slice();
unsigned long flags;
- u64 expires;
/* confirm we're still not at a refresh boundary */
raw_spin_lock_irqsave(&cfs_b->lock, flags);
@@ -4859,7 +4800,6 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
if (cfs_b->quota != RUNTIME_INF && cfs_b->runtime > slice)
runtime = cfs_b->runtime;
- expires = cfs_b->runtime_expires;
if (runtime)
cfs_b->distribute_running = 1;
@@ -4868,11 +4808,10 @@ static void do_sched_cfs_slack_timer(struct cfs_bandwidth *cfs_b)
if (!runtime)
return;
- runtime = distribute_cfs_runtime(cfs_b, runtime, expires);
+ runtime = distribute_cfs_runtime(cfs_b, runtime);
raw_spin_lock_irqsave(&cfs_b->lock, flags);
- if (expires == cfs_b->runtime_expires)
- lsub_positive(&cfs_b->runtime, runtime);
+ lsub_positive(&cfs_b->runtime, runtime);
cfs_b->distribute_running = 0;
raw_spin_unlock_irqrestore(&cfs_b->lock, flags);
}
@@ -4968,20 +4907,28 @@ static enum hrtimer_restart sched_cfs_period_timer(struct hrtimer *timer)
if (++count > 3) {
u64 new, old = ktime_to_ns(cfs_b->period);
- new = (old * 147) / 128; /* ~115% */
- new = min(new, max_cfs_quota_period);
-
- cfs_b->period = ns_to_ktime(new);
-
- /* since max is 1s, this is limited to 1e9^2, which fits in u64 */
- cfs_b->quota *= new;
- cfs_b->quota = div64_u64(cfs_b->quota, old);
-
- pr_warn_ratelimited(
- "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us %lld, cfs_quota_us = %lld)\n",
- smp_processor_id(),
- div_u64(new, NSEC_PER_USEC),
- div_u64(cfs_b->quota, NSEC_PER_USEC));
+ /*
+ * Grow period by a factor of 2 to avoid losing precision.
+ * Precision loss in the quota/period ratio can cause __cfs_schedulable
+ * to fail.
+ */
+ new = old * 2;
+ if (new < max_cfs_quota_period) {
+ cfs_b->period = ns_to_ktime(new);
+ cfs_b->quota *= 2;
+
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, scaling up (new cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(new, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ } else {
+ pr_warn_ratelimited(
+ "cfs_period_timer[cpu%d]: period too short, but cannot scale up without losing precision (cfs_period_us = %lld, cfs_quota_us = %lld)\n",
+ smp_processor_id(),
+ div_u64(old, NSEC_PER_USEC),
+ div_u64(cfs_b->quota, NSEC_PER_USEC));
+ }
/* reset count so we don't come right back in here */
count = 0;
@@ -5019,17 +4966,13 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
- u64 overrun;
-
lockdep_assert_held(&cfs_b->lock);
if (cfs_b->period_active)
return;
cfs_b->period_active = 1;
- overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
- cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
- cfs_b->expires_seq++;
+ hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b52ed1ada0be..0c0ed23f315a 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -341,8 +341,6 @@ struct cfs_bandwidth {
u64 quota;
u64 runtime;
s64 hierarchical_quota;
- u64 runtime_expires;
- int expires_seq;
short idle;
short period_active;
@@ -562,8 +560,6 @@ struct cfs_rq {
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
- int expires_seq;
- u64 runtime_expires;
s64 runtime_remaining;
u64 throttled_clock;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 1a65ca0a91f6..44206f7d0394 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -6009,6 +6009,7 @@ waitagain:
sizeof(struct trace_iterator) -
offsetof(struct trace_iterator, seq));
cpumask_clear(iter->started);
+ trace_seq_init(&iter->seq);
iter->pos = -1;
trace_event_read_lock();
generated by cgit 1.2.3-korg (git 2.39.0) at 2024-06-16 10:09:17 +0000