summaryrefslogtreecommitdiffstats
path: root/kernel/sched/core.c
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/sched/core.c')
-rw-r--r--kernel/sched/core.c146
1 files changed, 107 insertions, 39 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 22f86d5e9231..ec67b30f87c4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -163,6 +163,9 @@ static inline int __task_prio(const struct task_struct *p)
if (p->sched_class == &stop_sched_class) /* trumps deadline */
return -2;
+ if (p->dl_server)
+ return -1; /* deadline */
+
if (rt_prio(p->prio)) /* includes deadline */
return p->prio; /* [-1, 99] */
@@ -195,8 +198,24 @@ static inline bool prio_less(const struct task_struct *a,
if (-pb < -pa)
return false;
- if (pa == -1) /* dl_prio() doesn't work because of stop_class above */
- return !dl_time_before(a->dl.deadline, b->dl.deadline);
+ if (pa == -1) { /* dl_prio() doesn't work because of stop_class above */
+ const struct sched_dl_entity *a_dl, *b_dl;
+
+ a_dl = &a->dl;
+ /*
+ * Since,'a' and 'b' can be CFS tasks served by DL server,
+ * __task_prio() can return -1 (for DL) even for those. In that
+ * case, get to the dl_server's DL entity.
+ */
+ if (a->dl_server)
+ a_dl = a->dl_server;
+
+ b_dl = &b->dl;
+ if (b->dl_server)
+ b_dl = b->dl_server;
+
+ return !dl_time_before(a_dl->deadline, b_dl->deadline);
+ }
if (pa == MAX_RT_PRIO + MAX_NICE) /* fair */
return cfs_prio_less(a, b, in_fi);
@@ -1280,7 +1299,7 @@ bool sched_can_stop_tick(struct rq *rq)
* dequeued by migrating while the constrained task continues to run.
* E.g. going from 2->1 without going through pick_next_task().
*/
- if (sched_feat(HZ_BW) && __need_bw_check(rq, rq->curr)) {
+ if (__need_bw_check(rq, rq->curr)) {
if (cfs_task_bw_constrained(rq->curr))
return false;
}
@@ -2255,6 +2274,12 @@ void migrate_disable(void)
struct task_struct *p = current;
if (p->migration_disabled) {
+#ifdef CONFIG_DEBUG_PREEMPT
+ /*
+ *Warn about overflow half-way through the range.
+ */
+ WARN_ON_ONCE((s16)p->migration_disabled < 0);
+#endif
p->migration_disabled++;
return;
}
@@ -2273,14 +2298,20 @@ void migrate_enable(void)
.flags = SCA_MIGRATE_ENABLE,
};
+#ifdef CONFIG_DEBUG_PREEMPT
+ /*
+ * Check both overflow from migrate_disable() and superfluous
+ * migrate_enable().
+ */
+ if (WARN_ON_ONCE((s16)p->migration_disabled <= 0))
+ return;
+#endif
+
if (p->migration_disabled > 1) {
p->migration_disabled--;
return;
}
- if (WARN_ON_ONCE(!p->migration_disabled))
- return;
-
/*
* Ensure stop_task runs either before or after this, and that
* __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
@@ -4737,7 +4768,7 @@ void wake_up_new_task(struct task_struct *p)
update_rq_clock(rq);
post_init_entity_util_avg(p);
- activate_task(rq, p, ENQUEUE_NOCLOCK);
+ activate_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_INITIAL);
trace_sched_wakeup_new(p);
wakeup_preempt(rq, p, WF_FORK);
#ifdef CONFIG_SMP
@@ -5855,6 +5886,14 @@ static void put_prev_task_balance(struct rq *rq, struct task_struct *prev,
#endif
put_prev_task(rq, prev);
+
+ /*
+ * We've updated @prev and no longer need the server link, clear it.
+ * Must be done before ->pick_next_task() because that can (re)set
+ * ->dl_server.
+ */
+ if (prev->dl_server)
+ prev->dl_server = NULL;
}
/*
@@ -5889,6 +5928,13 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
}
/*
+ * This is a normal CFS pick, but the previous could be a DL pick.
+ * Clear it as previous is no longer picked.
+ */
+ if (prev->dl_server)
+ prev->dl_server = NULL;
+
+ /*
* This is the fast path; it cannot be a DL server pick;
* therefore even if @p == @prev, ->dl_server must be NULL.
*/
@@ -5901,14 +5947,6 @@ __pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
restart:
put_prev_task_balance(rq, prev, rf);
- /*
- * We've updated @prev and no longer need the server link, clear it.
- * Must be done before ->pick_next_task() because that can (re)set
- * ->dl_server.
- */
- if (prev->dl_server)
- prev->dl_server = NULL;
-
for_each_active_class(class) {
p = class->pick_next_task(rq);
if (p) {
@@ -7925,6 +7963,30 @@ void set_rq_offline(struct rq *rq)
}
}
+static inline void sched_set_rq_online(struct rq *rq, int cpu)
+{
+ struct rq_flags rf;
+
+ rq_lock_irqsave(rq, &rf);
+ if (rq->rd) {
+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+ set_rq_online(rq);
+ }
+ rq_unlock_irqrestore(rq, &rf);
+}
+
+static inline void sched_set_rq_offline(struct rq *rq, int cpu)
+{
+ struct rq_flags rf;
+
+ rq_lock_irqsave(rq, &rf);
+ if (rq->rd) {
+ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+ set_rq_offline(rq);
+ }
+ rq_unlock_irqrestore(rq, &rf);
+}
+
/*
* used to mark begin/end of suspend/resume:
*/
@@ -7975,10 +8037,25 @@ static int cpuset_cpu_inactive(unsigned int cpu)
return 0;
}
+static inline void sched_smt_present_inc(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_inc_cpuslocked(&sched_smt_present);
+#endif
+}
+
+static inline void sched_smt_present_dec(int cpu)
+{
+#ifdef CONFIG_SCHED_SMT
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
+}
+
int sched_cpu_activate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
- struct rq_flags rf;
/*
* Clear the balance_push callback and prepare to schedule
@@ -7986,13 +8063,10 @@ int sched_cpu_activate(unsigned int cpu)
*/
balance_push_set(cpu, false);
-#ifdef CONFIG_SCHED_SMT
/*
* When going up, increment the number of cores with SMT present.
*/
- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
- static_branch_inc_cpuslocked(&sched_smt_present);
-#endif
+ sched_smt_present_inc(cpu);
set_cpu_active(cpu, true);
if (sched_smp_initialized) {
@@ -8012,12 +8086,7 @@ int sched_cpu_activate(unsigned int cpu)
* 2) At runtime, if cpuset_cpu_active() fails to rebuild the
* domains.
*/
- rq_lock_irqsave(rq, &rf);
- if (rq->rd) {
- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
- set_rq_online(rq);
- }
- rq_unlock_irqrestore(rq, &rf);
+ sched_set_rq_online(rq, cpu);
return 0;
}
@@ -8025,7 +8094,6 @@ int sched_cpu_activate(unsigned int cpu)
int sched_cpu_deactivate(unsigned int cpu)
{
struct rq *rq = cpu_rq(cpu);
- struct rq_flags rf;
int ret;
/*
@@ -8056,22 +8124,16 @@ int sched_cpu_deactivate(unsigned int cpu)
*/
synchronize_rcu();
- rq_lock_irqsave(rq, &rf);
- if (rq->rd) {
- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
- set_rq_offline(rq);
- }
- rq_unlock_irqrestore(rq, &rf);
+ sched_set_rq_offline(rq, cpu);
scx_rq_deactivate(rq);
-#ifdef CONFIG_SCHED_SMT
/*
* When going down, decrement the number of cores with SMT present.
*/
- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
- static_branch_dec_cpuslocked(&sched_smt_present);
+ sched_smt_present_dec(cpu);
+#ifdef CONFIG_SCHED_SMT
sched_core_cpu_deactivate(cpu);
#endif
@@ -8081,6 +8143,8 @@ int sched_cpu_deactivate(unsigned int cpu)
sched_update_numa(cpu, false);
ret = cpuset_cpu_inactive(cpu);
if (ret) {
+ sched_smt_present_inc(cpu);
+ sched_set_rq_online(rq, cpu);
balance_push_set(cpu, false);
set_cpu_active(cpu, true);
sched_update_numa(cpu, true);
@@ -8290,8 +8354,6 @@ void __init sched_init(void)
#endif /* CONFIG_RT_GROUP_SCHED */
}
- init_rt_bandwidth(&def_rt_bandwidth, global_rt_period(), global_rt_runtime());
-
#ifdef CONFIG_SMP
init_defrootdomain();
#endif
@@ -8346,8 +8408,13 @@ void __init sched_init(void)
init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, NULL);
#endif /* CONFIG_FAIR_GROUP_SCHED */
- rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime;
#ifdef CONFIG_RT_GROUP_SCHED
+ /*
+ * This is required for init cpu because rt.c:__enable_runtime()
+ * starts working after scheduler_running, which is not the case
+ * yet.
+ */
+ rq->rt.rt_runtime = global_rt_runtime();
init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
#endif
#ifdef CONFIG_SMP
@@ -8379,6 +8446,7 @@ void __init sched_init(void)
#endif /* CONFIG_SMP */
hrtick_rq_init(rq);
atomic_set(&rq->nr_iowait, 0);
+ fair_server_init(rq);
#ifdef CONFIG_SCHED_CORE
rq->core = rq;
generated by cgit v1.2.3 (git 2.46.0) at 2025-04-26 12:10:30 +0000