sched/core: Add ENQUEUE_RQ_SELECTED to indicate whether ->select_task_rq() was called

During ttwu, ->select_task_rq() can be skipped if only one CPU is allowed or
migration is disabled. sched_ext schedulers may perform operations such as
direct dispatch from ->select_task_rq() path and it is useful for them to
know whether ->select_task_rq() was skipped in the ->enqueue_task() path.

Currently, sched_ext schedulers are using ENQUEUE_WAKEUP for this purpose
and end up assuming incorrectly that ->select_task_rq() was called for tasks
that are bound to a single CPU or migration disabled.

Make select_task_rq() indicate whether ->select_task_rq() was called by
setting WF_RQ_SELECTED in *wake_flags and make ttwu_do_activate() map that
to ENQUEUE_RQ_SELECTED for ->enqueue_task().

This will be used by sched_ext to fix ->select_task_rq() skip detection.

Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: David Vernet <void@manifault.com>

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e70b57a5693ecfec70818269c11b7083d6b3d829..aeb59551446193e715c76c80bcf7b701d2451514 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3522,10 +3522,12 @@ int select_task_rq(struct task_struct *p, int cpu, int *wake_flags)
 {
        lockdep_assert_held(&p->pi_lock);
 
-       if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p))
+       if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) {
                cpu = p->sched_class->select_task_rq(p, cpu, *wake_flags);
-       else
+               *wake_flags |= WF_RQ_SELECTED;
+       } else {
                cpu = cpumask_any(p->cpus_ptr);
+       }
 
        /*
         * In order not to call set_task_cpu() on a blocking task we need
@@ -3659,6 +3661,8 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
                rq->nr_uninterruptible--;
 
 #ifdef CONFIG_SMP
+       if (wake_flags & WF_RQ_SELECTED)
+               en_flags |= ENQUEUE_RQ_SELECTED;
        if (wake_flags & WF_MIGRATED)
                en_flags |= ENQUEUE_MIGRATED;
        else

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b1c3588a8f0039ca260f237b5c1967e3a5d6710b..6085ef50febfafaa4db8587fab05f64dba5e4299 100644 (file)
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2292,6 +2292,7 @@ static inline int task_on_rq_migrating(struct task_struct *p)
 #define WF_SYNC                        0x10 /* Waker goes to sleep after wakeup */
 #define WF_MIGRATED            0x20 /* Internal use, task got migrated */
 #define WF_CURRENT_CPU         0x40 /* Prefer to move the wakee to the current CPU. */
+#define WF_RQ_SELECTED         0x80 /* ->select_task_rq() was called */
 
 #ifdef CONFIG_SMP
 static_assert(WF_EXEC == SD_BALANCE_EXEC);
@@ -2334,6 +2335,7 @@ extern const u32          sched_prio_to_wmult[40];
  * ENQUEUE_HEAD      - place at front of runqueue (tail if not specified)
  * ENQUEUE_REPLENISH - CBS (replenish runtime and postpone deadline)
  * ENQUEUE_MIGRATED  - the task was migrated during wakeup
+ * ENQUEUE_RQ_SELECTED - ->select_task_rq() was called
  *
  */
 
@@ -2360,6 +2362,7 @@ extern const u32          sched_prio_to_wmult[40];
 #define ENQUEUE_INITIAL                0x80
 #define ENQUEUE_MIGRATING      0x100
 #define ENQUEUE_DELAYED                0x200
+#define ENQUEUE_RQ_SELECTED    0x400
 
 #define RETRY_TASK             ((void *)-1UL)