sched/fair: Make SCHED_IDLE entity be preempted in strict hierarchy

Consider the following cgroup:

                       root
                        |
             ------------------------
             |                      |
       normal_cgroup            idle_cgroup
             |                      |
   SCHED_IDLE task_A           SCHED_NORMAL task_B

According to the cgroup hierarchy, A should preempt B. But current
check_preempt_wakeup_fair() treats cgroup se and task separately, so B
will preempt A unexpectedly.
Unify the wakeup logic by {c,p}se_is_idle only. This makes SCHED_IDLE of
a task a relative policy that is effective only within its own cgroup,
similar to the behavior of NICE.

Also fix se_is_idle() definition when !CONFIG_FAIR_GROUP_SCHED.

Fixes: 304000390f88 ("sched: Cgroup SCHED_IDLE support")
Signed-off-by: Tianchen Ding <dtcccc@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Josh Don <joshdon@google.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20240626023505.1332596-1-dtcccc@linux.alibaba.com

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 02694fc5fce9ca3ff5baa9f2177a9ce4cbdf8c13..99c80abdbaaac11dab79d73166f68a3535f6bcfb 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -511,7 +511,7 @@ static int cfs_rq_is_idle(struct cfs_rq *cfs_rq)
 
 static int se_is_idle(struct sched_entity *se)
 {
-       return 0;
+       return task_has_idle_policy(task_of(se));
 }
 
 #endif /* CONFIG_FAIR_GROUP_SCHED */
@@ -8381,16 +8381,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
        if (test_tsk_need_resched(curr))
                return;
 
-       /* Idle tasks are by definition preempted by non-idle tasks. */
-       if (unlikely(task_has_idle_policy(curr)) &&
-           likely(!task_has_idle_policy(p)))
-               goto preempt;
-
-       /*
-        * Batch and idle tasks do not preempt non-idle tasks (their preemption
-        * is driven by the tick):
-        */
-       if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
+       if (!sched_feat(WAKEUP_PREEMPTION))
                return;
 
        find_matching_se(&se, &pse);
@@ -8400,7 +8391,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
        pse_is_idle = se_is_idle(pse);
 
        /*
-        * Preempt an idle group in favor of a non-idle group (and don't preempt
+        * Preempt an idle entity in favor of a non-idle entity (and don't preempt
         * in the inverse case).
         */
        if (cse_is_idle && !pse_is_idle)
@@ -8408,9 +8399,14 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
        if (cse_is_idle != pse_is_idle)
                return;
 
+       /*
+        * BATCH and IDLE tasks do not preempt others.
+        */
+       if (unlikely(p->policy != SCHED_NORMAL))
+               return;
+
        cfs_rq = cfs_rq_of(se);
        update_curr(cfs_rq);
-
        /*
         * XXX pick_eevdf(cfs_rq) != se ?
         */