Re: [PATCH v7 11/23] sched: Add a initial sketch of the find_proxy_task() function

From: Metin Kaya
Date: Thu Dec 21 2023 - 08:01:00 EST

On 20/12/2023 12:18 am, John Stultz wrote:
Add a find_proxy_task() function which doesn't do much.

When we select a blocked task to run, we will just deactivate it
and pick again. The exception being if it has become unblocked
after find_proxy_task() was called.

Greatly simplified from patch by:
Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Juri Lelli <juri.lelli@xxxxxxxxxx>
Valentin Schneider <valentin.schneider@xxxxxxx>
Connor O'Brien <connoro@xxxxxxxxxx>

Cc: Joel Fernandes <joelaf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Zimuzo Ezeozue <zezeozue@xxxxxxxxxx>
Cc: Youssef Esmat <youssefesmat@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Waiman Long <longman@xxxxxxxxxx>
Cc: Boqun Feng <boqun.feng@xxxxxxxxx>
Cc: "Paul E. McKenney" <paulmck@xxxxxxxxxx>
Cc: Metin Kaya <Metin.Kaya@xxxxxxx>
Cc: Xuewen Yan <xuewen.yan94@xxxxxxxxx>
Cc: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
[jstultz: Split out from larger proxy patch and simplified
for review and testing.]
Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
v5:
* Split out from larger proxy patch
v7:
* Fixed unused function arguments, spelling nits, and tweaks for
clarity, pointed out by Metin Kaya
* Moved task_is_blocked() implementation to this patch where it is
first used. Also drop unused arguments. Suggested by Metin Kaya.
* Tweaks to make things easier to read, as suggested by Metin Kaya.
* Rename proxy() to find_proxy_task() for clarity, and typo
fixes suggested by Metin Kaya
* Fix build warning Reported-by: kernel test robot <lkp@xxxxxxxxx>
Closes: https://lore.kernel.org/oe-kbuild-all/202311081028.yDLmCWgr-lkp@xxxxxxxxx/

Super-nit: s/Add a/Add an/ in commit header.

---
kernel/sched/core.c | 87 ++++++++++++++++++++++++++++++++++++++++++--
kernel/sched/rt.c | 19 +++++++++-
kernel/sched/sched.h | 15 ++++++++
3 files changed, 115 insertions(+), 6 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 34acd80b6bd0..12f5a0618328 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6572,11 +6572,11 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
#endif
static bool try_to_deactivate_task(struct rq *rq, struct task_struct *p,
- unsigned long task_state)
+ unsigned long task_state, bool deactivate_cond)
{
if (signal_pending_state(task_state, p)) {
WRITE_ONCE(p->__state, TASK_RUNNING);
- } else {
+ } else if (deactivate_cond) {
p->sched_contributes_to_load =
(task_state & TASK_UNINTERRUPTIBLE) &&
!(task_state & TASK_NOLOAD) &&
@@ -6607,6 +6607,73 @@ static bool try_to_deactivate_task(struct rq *rq, struct task_struct *p,
return false;
}
+#ifdef CONFIG_SCHED_PROXY_EXEC
+
+static bool proxy_deactivate(struct rq *rq, struct task_struct *next)
+{
+ unsigned long state = READ_ONCE(next->__state);
+
+ /* Don't deactivate if the state has been changed to TASK_RUNNING */
+ if (state == TASK_RUNNING)
+ return false;
+ if (!try_to_deactivate_task(rq, next, state, true))
+ return false;
+ put_prev_task(rq, next);
+ rq_set_selected(rq, rq->idle);
+ resched_curr(rq);
+ return true;
+}
+
+/*
+ * Initial simple proxy that just returns the task if it's waking
+ * or deactivates the blocked task so we can pick something that
+ * isn't blocked.
+ */
+static struct task_struct *
+find_proxy_task(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
+{
+ struct task_struct *ret = NULL;
+ struct task_struct *p = next;
+ struct mutex *mutex;
+
+ mutex = p->blocked_on;
+ /* Something changed in the chain, so pick again */
+ if (!mutex)
+ return NULL;
+ /*
+ * By taking mutex->wait_lock we hold off concurrent mutex_unlock()
+ * and ensure @owner sticks around.
+ */
+ raw_spin_lock(&mutex->wait_lock);
+ raw_spin_lock(&p->blocked_lock);
+
+ /* Check again that p is blocked with blocked_lock held */
+ if (!task_is_blocked(p) || mutex != p->blocked_on) {
+ /*
+ * Something changed in the blocked_on chain and
+ * we don't know if only at this level. So, let's
+ * just bail out completely and let __schedule
+ * figure things out (pick_again loop).
+ */
+ goto out;
+ }
+
+ if (!proxy_deactivate(rq, next))
+ ret = p;
+out:
+ raw_spin_unlock(&p->blocked_lock);
+ raw_spin_unlock(&mutex->wait_lock);
+ return ret;
+}
+#else /* SCHED_PROXY_EXEC */
+static struct task_struct *
+find_proxy_task(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
+{
+ BUG(); // This should never be called in the !PROXY case
+ return next;
+}
+#endif /* SCHED_PROXY_EXEC */
+
/*
* __schedule() is the main scheduler function.
*
@@ -6698,12 +6765,24 @@ static void __sched notrace __schedule(unsigned int sched_mode)
*/
prev_state = READ_ONCE(prev->__state);
if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
- try_to_deactivate_task(rq, prev, prev_state);
+ try_to_deactivate_task(rq, prev, prev_state,
+ !task_is_blocked(prev));
switch_count = &prev->nvcsw;
}
- next = pick_next_task(rq, prev, &rf);
+pick_again:
+ next = pick_next_task(rq, rq_selected(rq), &rf);
rq_set_selected(rq, next);
+ if (unlikely(task_is_blocked(next))) {
+ next = find_proxy_task(rq, next, &rf);
+ if (!next) {
+ rq_unpin_lock(rq, &rf);
+ __balance_callbacks(rq);
+ rq_repin_lock(rq, &rf);
+ goto pick_again;
+ }
+ }
+
clear_tsk_need_resched(prev);
clear_preempt_need_resched();
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 2682cec45aaa..81cd22eaa6dc 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1491,8 +1491,19 @@ enqueue_task_rt(struct rq *rq, struct task_struct *p, int flags)
enqueue_rt_entity(rt_se, flags);
- if (!task_current(rq, p) && p->nr_cpus_allowed > 1)
- enqueue_pushable_task(rq, p);
+ /*
+ * Current can't be pushed away. Selected is tied to current,
+ * so don't push it either.
+ */
+ if (task_current(rq, p) || task_current_selected(rq, p))
+ return;
+ /*
+ * Pinned tasks can't be pushed.
+ */
+ if (p->nr_cpus_allowed == 1)
+ return;
+
+ enqueue_pushable_task(rq, p);
}
static void dequeue_task_rt(struct rq *rq, struct task_struct *p, int flags)
@@ -1779,6 +1790,10 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p)
update_rt_rq_load_avg(rq_clock_pelt(rq), rq, 1);
+ /* Avoid marking selected as pushable */
+ if (task_current_selected(rq, p))
+ return;
+
/*
* The previous task needs to be made eligible for pushing
* if it is still active
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6ea1dfbe502a..765ba10661de 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2148,6 +2148,21 @@ static inline int task_current_selected(struct rq *rq, struct task_struct *p)
return rq_selected(rq) == p;
}
+#ifdef CONFIG_SCHED_PROXY_EXEC
+static inline bool task_is_blocked(struct task_struct *p)
+{
+ if (!sched_proxy_exec())
+ return false;
+
+ return !!p->blocked_on && p->blocked_on_state != BO_RUNNABLE;
+}
+#else /* !SCHED_PROXY_EXEC */
+static inline bool task_is_blocked(struct task_struct *p)
+{
+ return false;
+}
+#endif /* SCHED_PROXY_EXEC */
+

We can drop #else part, IMHO. Because sched_proxy_exec() already returns false in !CONFIG_SCHED_PROXY_EXEC case.

static inline int task_on_cpu(struct rq *rq, struct task_struct *p)
{
#ifdef CONFIG_SMP