[PATCH v29 6/9] sched: Add is_blocked task flag

[John Stultz]

Add a new is_blocked flag to the task struct. This flag is set
by try_to_block_task() and cleared by ttwu_do_wakeup() and
tracks if the task is blocked.

Traditionally this would mirror !p->on_rq, however due things
like DELAY_DEQUEUE and PROXY_EXEC, this can diverge, so its
useful to manage separately.

Additionally with this, we might be able to get rid of the
p->se.sched_delayed (ab)use in the core code (eventually).

Taken whole cloth from Peter's email:
  https://lore.kernel.org/lkml/20260501132143.GC1026330@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx/

With a few additional p->is_blocked = 0 in a few cases where
we return current if blocked_on gets zeroed or there is
no owner. This may hint that these current special cases
might be dropped eventually.

This change also helps resolve wait-queue stalls seen with
proxy-execution. See previous patch attempts for details:
  https://lore.kernel.org/lkml/20260430215103.2978955-2-jstultz@xxxxxxxxxx/

Reported-by: Vineeth Pillai <vineethrp@xxxxxxxxxx>
Suggested-by: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
Cc: Joel Fernandes <joelagnelf@xxxxxxxxxx>
Cc: Qais Yousef <qyousef@xxxxxxxxxxx>
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: 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: Daniel Lezcano <daniel.lezcano@xxxxxxxxxx>
Cc: Suleiman Souhlal <suleiman@xxxxxxxxxx>
Cc: kuyo chang <kuyo.chang@xxxxxxxxxxxx>
Cc: hupu <hupu.gm@xxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
---
 include/linux/sched.h |  7 +++++--
 kernel/sched/core.c   | 16 +++++++++++++++-
 2 files changed, 20 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5b68a1c9eedcf..bbb183233855a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -846,7 +846,11 @@ struct task_struct {
 	struct alloc_tag		*alloc_tag;
 #endif
 
-	int				on_cpu;
+	u8				on_cpu;
+	u8				on_rq;
+	u8				is_blocked;
+	u8				__pad;
+
 	struct __call_single_node	wake_entry;
 	unsigned int			wakee_flips;
 	unsigned long			wakee_flip_decay_ts;
@@ -861,7 +865,6 @@ struct task_struct {
 	 */
 	int				recent_used_cpu;
 	int				wake_cpu;
-	int				on_rq;
 
 	int				prio;
 	int				static_prio;
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 633dd5b8428e5..8a223555be2e9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -615,6 +615,12 @@ EXPORT_SYMBOL(__trace_set_current_state);
  *   [ The astute reader will observe that it is possible for two tasks on one
  *     CPU to have ->on_cpu = 1 at the same time. ]
  *
+ * p->is_blocked <- { 0, 1 }:
+ *
+ *   is set by try_to_block_task() and cleared by ttwu_do_wakeup() and tracks
+ *   if the task is blocked. Traditionally this would mirror p->on_rq, however
+ *   due things like DELAY_DEQUEUE and PROXY_EXEC, this can diverge.
+ *
  * task_cpu(p): is changed by set_task_cpu(), the rules are:
  *
  *  - Don't call set_task_cpu() on a blocked task:
@@ -3706,6 +3712,7 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
  */
 static inline void ttwu_do_wakeup(struct task_struct *p)
 {
+	p->is_blocked = 0;
 	WRITE_ONCE(p->__state, TASK_RUNNING);
 	trace_sched_wakeup(p);
 }
@@ -4239,6 +4246,7 @@ int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		 *    it disabling IRQs (this allows not taking ->pi_lock).
 		 */
 		WARN_ON_ONCE(p->se.sched_delayed);
+		WARN_ON_ONCE(p->is_blocked);
 		/* If p is current, we know we can run here, so clear blocked_on */
 		clear_task_blocked_on(p, NULL);
 		if (!ttwu_state_match(p, state, &success))
@@ -4550,6 +4558,7 @@ static void __sched_fork(u64 clone_flags, struct task_struct *p)
 
 	/* A delayed task cannot be in clone(). */
 	WARN_ON_ONCE(p->se.sched_delayed);
+	WARN_ON_ONCE(p->is_blocked);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	p->se.cfs_rq			= NULL;
@@ -6671,6 +6680,7 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p,
 	unsigned long task_state = *task_state_p;
 
 	if (signal_pending_state(task_state, p)) {
+		p->is_blocked = 0;
 		WRITE_ONCE(p->__state, TASK_RUNNING);
 		*task_state_p = TASK_RUNNING;
 		clear_task_blocked_on(p, NULL);
@@ -6678,6 +6688,8 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p,
 		return false;
 	}
 
+	p->is_blocked = 1;
+
 	/*
 	 * We check should_block after signal_pending because we
 	 * will want to wake the task in that case. But if
@@ -6837,6 +6849,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 		/* if its PROXY_WAKING, do return migration or run if current */
 		if (mutex == PROXY_WAKING) {
 			if (task_current(rq, p)) {
+				p->is_blocked = 0;
 				clear_task_blocked_on(p, PROXY_WAKING);
 				return p;
 			}
@@ -6872,6 +6885,7 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 			 * just run on this rq), or return-migrate the task.
 			 */
 			if (task_current(rq, p)) {
+				p->is_blocked = 0;
 				__clear_task_blocked_on(p, NULL);
 				return p;
 			}
@@ -7105,7 +7119,7 @@ static void __sched notrace __schedule(int sched_mode)
 			clear_task_blocked_on(prev, NULL);
 
 		rq_set_donor(rq, next);
-		if (unlikely(next->blocked_on)) {
+		if (unlikely(next->is_blocked && next->blocked_on)) {
 			next = find_proxy_task(rq, next, &rf);
 			if (!next) {
 				zap_balance_callbacks(rq);
-- 
2.54.0.563.g4f69b47b94-goog