mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: "zhidao su (Xiaomi)" <soolaugust@gmail.com>
To: K Prateek Nayak <kprateek.nayak@amd.com>,
	John Stultz <jstultz@google.com>
Cc: Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@redhat.com>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
	Valentin Schneider <vschneid@redhat.com>,
	linux-kernel@vger.kernel.org,
	"zhidao su (Xiaomi)" <soolaugust@gmail.com>
Subject: [PATCH v5] sched/proxy_exec: Detect cycles in proxy walks
Date: Wed, 22 Jul 2026 20:03:46 +0800	[thread overview]
Message-ID: <20260722120346.93000-1-soolaugust@gmail.com> (raw)
In-Reply-To: <51450a8f-f053-45b3-a2fc-2bd0b75181b6@amd.com>

find_proxy_task() can keep walking the same blocked_on chain if the chain
contains a cycle. A simple A->B->A deadlock can leave the CPU spinning in
__schedule() with rq->lock held.

Use the rq pick sequence as a per-walk marker. Mark each task visited by
the current walk. If the walk sees the same marker again, break the cycle
by clearing blocked_on at the detection point and deactivating that task.

The marker is only consumed while holding rq->lock. Clear it when a task is
activated, so stale state from an earlier pick or another rq is not carried
into the next queued lifetime.

Tested with a PE cycle reproducer in virtme-ng:

  buggy kernel: vng timed out without returning
  fixed kernel: WARN_ONCE "sched/pe: deadlock cycle detected"

Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: zhidao su (Xiaomi) <soolaugust@gmail.com>
---
Changes since v4:
- Use sched_proxy_enqueue_task() to clear stale proxy-walk state when a
  task is activated.
- Stop marking the donor early; only mark the finalized owner.
- Use pr_warn_once() for the cycle warning.

 include/linux/sched.h |  3 +++
 kernel/sched/core.c   | 19 +++++++++++++++++--
 kernel/sched/sched.h  | 11 +++++++++++
 3 files changed, 31 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 968b18a7f4702..b1c46e21bc268 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1256,6 +1256,9 @@ struct task_struct {
 	 * under preempt_disable().
 	 */
 	struct task_struct		*blocked_donor;
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	u64				proxy_pick_seq;
+#endif
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2e7cde033a319..c1bb4f98dd64a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2221,6 +2221,7 @@ void activate_task(struct rq *rq, struct task_struct *p, int flags)
 	if (task_on_rq_migrating(p))
 		flags |= ENQUEUE_MIGRATED;
 
+	sched_proxy_enqueue_task(p);
 	enqueue_task(rq, p, flags);
 
 	WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
@@ -6724,6 +6725,7 @@ static bool try_to_block_task(struct rq *rq, struct task_struct *p,
 }
 
 #ifdef CONFIG_SCHED_PROXY_EXEC
+
 static inline void proxy_set_task_cpu(struct task_struct *p, int cpu)
 {
 	unsigned int wake_cpu;
@@ -6839,14 +6841,14 @@ static void proxy_migrate_task(struct rq *rq, struct rq_flags *rf,
 }
 
 /*
- * Find runnable lock owner to proxy for mutex blocked donor
+ * Find runnable lock owner to proxy for a blocked donor
  *
  * Follow the blocked-on relation:
  *
  *                ,-> task
  *                |     | blocked-on
  *                |     v
- *  blocked_donor |   mutex
+ *  blocked_donor | blocking primitive
  *                |     | owner
  *                |     v
  *                `-- task
@@ -6874,6 +6876,8 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 	struct task_struct *p;
 	int owner_cpu;
 
+	rq->proxy_pick_seq++;
+
 	/* Follow blocked_on chain. */
 	for (p = donor; p->is_blocked; p = owner) {
 		/* if its PROXY_WAKING, do return migration or run if current */
@@ -6990,6 +6994,14 @@ find_proxy_task(struct rq *rq, struct task_struct *donor, struct rq_flags *rf)
 			 */
 			return proxy_resched_idle(rq);
 		}
+
+		if (owner->proxy_pick_seq == rq->proxy_pick_seq) {
+			pr_warn_once("sched/pe: deadlock cycle detected, pid %d\n",
+				     p->pid);
+			__clear_task_blocked_on(p, NULL);
+			goto deactivate;
+		}
+		owner->proxy_pick_seq = rq->proxy_pick_seq;
 		/*
 		 * OK, now we're absolutely sure @owner is on this
 		 * rq, therefore holding @rq->lock is sufficient to
@@ -9057,6 +9069,9 @@ void __init sched_init(void)
 		raw_spin_lock_init(&rq->cpu_epoch_lock);
 		rq->cpu_epoch_next = jiffies;
 #endif
+#ifdef CONFIG_SCHED_PROXY_EXEC
+		rq->proxy_pick_seq = 1;
+#endif
 
 		zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
 	}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 26ae13c86b699..d5d9de509dfdb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1154,6 +1154,7 @@ struct rq {
 #ifdef CONFIG_SCHED_PROXY_EXEC
 	struct task_struct __rcu	*donor;  /* Scheduling context */
 	struct task_struct __rcu	*curr;   /* Execution context */
+	u64				proxy_pick_seq;
 #else
 	union {
 		struct task_struct __rcu *donor; /* Scheduler context */
@@ -3092,6 +3093,16 @@ static inline void __block_task(struct rq *rq, struct task_struct *p)
 extern void activate_task(struct rq *rq, struct task_struct *p, int flags);
 extern void deactivate_task(struct rq *rq, struct task_struct *p, int flags);
 
+static inline void sched_proxy_enqueue_task(struct task_struct *p)
+{
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	if (!sched_proxy_exec())
+		return;
+
+	p->proxy_pick_seq = 0;
+#endif
+}
+
 extern void wakeup_preempt(struct rq *rq, struct task_struct *p, int flags);
 
 /*

base-commit: 04998aa54848f15332202d0bea008d2ca1ed1713
-- 
2.43.0


  reply	other threads:[~2026-07-22 12:03 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-14  5:36 [PATCH] sched/proxy_exec: Limit find_proxy_task() chain depth to prevent CPU hang soolaugust
2026-04-21  2:27 ` John Stultz
2026-04-21  3:13   ` K Prateek Nayak
2026-04-21 12:02     ` zhidao su
2026-04-21 12:08     ` zhidao su
2026-07-14 15:21     ` [PATCH v2] sched/proxy_exec: Break cyclic proxy chains by deactivating blocked tasks soolaugust
2026-07-14 20:46       ` K Prateek Nayak
2026-07-15  2:37       ` soolaugust
2026-07-15  3:01         ` K Prateek Nayak
2026-07-15  8:50           ` zhidao su
2026-07-17 10:52       ` [PATCH v3] sched/proxy_exec: Detect cycles in proxy walks zhidao su (Xiaomi)
2026-07-17 11:50         ` K Prateek Nayak
2026-07-17 12:55           ` [PATCH v4] " zhidao su (Xiaomi)
2026-07-21  3:41             ` K Prateek Nayak
2026-07-22 12:03               ` zhidao su (Xiaomi) [this message]
2026-08-12 21:29                 ` [PATCH v5] " John Stultz
2026-08-13  4:09                   ` zhidao su

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260722120346.93000-1-soolaugust@gmail.com \
    --to=soolaugust@gmail.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=jstultz@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®