summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/core.c2
-rw-r--r--kernel/sched/ext.c11
-rw-r--r--kernel/sched/sched.h25
3 files changed, 30 insertions, 8 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 9aecd914ac69..67189907214d 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7285,7 +7285,7 @@ out_unlock:
#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
int __sched __cond_resched(void)
{
- if (should_resched(0)) {
+ if (should_resched(0) && !irqs_disabled()) {
preempt_schedule_common();
return 1;
}
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 5a81d9a1e31f..0f1da199cfc7 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -3117,7 +3117,6 @@ static struct task_struct *pick_task_scx(struct rq *rq)
{
struct task_struct *prev = rq->curr;
struct task_struct *p;
- bool prev_on_scx = prev->sched_class == &ext_sched_class;
bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
bool kick_idle = false;
@@ -3137,14 +3136,18 @@ static struct task_struct *pick_task_scx(struct rq *rq)
* if pick_task_scx() is called without preceding balance_scx().
*/
if (unlikely(rq->scx.flags & SCX_RQ_BAL_PENDING)) {
- if (prev_on_scx) {
+ if (prev->scx.flags & SCX_TASK_QUEUED) {
keep_prev = true;
} else {
keep_prev = false;
kick_idle = true;
}
- } else if (unlikely(keep_prev && !prev_on_scx)) {
- /* only allowed during transitions */
+ } else if (unlikely(keep_prev &&
+ prev->sched_class != &ext_sched_class)) {
+ /*
+ * Can happen while enabling as SCX_RQ_BAL_PENDING assertion is
+ * conditional on scx_enabled() and may have been skipped.
+ */
WARN_ON_ONCE(scx_ops_enable_state() == SCX_OPS_ENABLED);
keep_prev = false;
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b93c8c3dc05a..c8512a9fb022 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3698,10 +3698,28 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
{
struct cpumask *cidmask = mm_cidmask(mm);
struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
- int cid = __this_cpu_read(pcpu_cid->recent_cid);
+ int cid, max_nr_cid, allowed_max_nr_cid;
+ /*
+ * After shrinking the number of threads or reducing the number
+ * of allowed cpus, reduce the value of max_nr_cid so expansion
+ * of cid allocation will preserve cache locality if the number
+ * of threads or allowed cpus increase again.
+ */
+ max_nr_cid = atomic_read(&mm->max_nr_cid);
+ while ((allowed_max_nr_cid = min_t(int, READ_ONCE(mm->nr_cpus_allowed),
+ atomic_read(&mm->mm_users))),
+ max_nr_cid > allowed_max_nr_cid) {
+ /* atomic_try_cmpxchg loads previous mm->max_nr_cid into max_nr_cid. */
+ if (atomic_try_cmpxchg(&mm->max_nr_cid, &max_nr_cid, allowed_max_nr_cid)) {
+ max_nr_cid = allowed_max_nr_cid;
+ break;
+ }
+ }
/* Try to re-use recent cid. This improves cache locality. */
- if (!mm_cid_is_unset(cid) && !cpumask_test_and_set_cpu(cid, cidmask))
+ cid = __this_cpu_read(pcpu_cid->recent_cid);
+ if (!mm_cid_is_unset(cid) && cid < max_nr_cid &&
+ !cpumask_test_and_set_cpu(cid, cidmask))
return cid;
/*
* Expand cid allocation if the maximum number of concurrency
@@ -3709,8 +3727,9 @@ static inline int __mm_cid_try_get(struct task_struct *t, struct mm_struct *mm)
* and number of threads. Expanding cid allocation as much as
* possible improves cache locality.
*/
- cid = atomic_read(&mm->max_nr_cid);
+ cid = max_nr_cid;
while (cid < READ_ONCE(mm->nr_cpus_allowed) && cid < atomic_read(&mm->mm_users)) {
+ /* atomic_try_cmpxchg loads previous mm->max_nr_cid into cid. */
if (!atomic_try_cmpxchg(&mm->max_nr_cid, &cid, cid + 1))
continue;
if (!cpumask_test_and_set_cpu(cid, cidmask))