linux-kernel - [PATCH 27/46] sched_ext: Ignore insertions of not-owned tasks into DSQs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250920005931.2753828-28-tj@kernel.org>
Date: Fri, 19 Sep 2025 14:58:50 -1000
From: Tejun Heo <tj@...nel.org>
To: void@...ifault.com,
	arighi@...dia.com,
	multics69@...il.com
Cc: linux-kernel@...r.kernel.org,
	sched-ext@...ts.linux.dev,
	memxor@...il.com,
	bpf@...r.kernel.org,
	Tejun Heo <tj@...nel.org>
Subject: [PATCH 27/46] sched_ext: Ignore insertions of not-owned tasks into DSQs

As BPF schedulers are allowed to ignore dequeues, after a sub-sched
enabling moved tasks out of the parent scheduler, the parent scheduler may
try to dispatch an already moved task. As this doesn't necessarily
indicate a malfunction, ignore and count such attempts.

Signed-off-by: Tejun Heo <tj@...nel.org>
---
 kernel/sched/ext.c          |  9 +++++++++
 kernel/sched/ext_internal.h | 12 ++++++++++++
 2 files changed, 21 insertions(+)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index b5f5106ddbf8..891b956a92b6 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2125,6 +2125,12 @@ static void finish_dispatch(struct scx_sched *sch, struct rq *rq,
 		if ((opss & SCX_OPSS_QSEQ_MASK) != qseq_at_dispatch)
 			return;
 
+		/* see SCX_EV_INSERT_NOT_OWNED definition */
+		if (unlikely(sch != rcu_access_pointer(p->scx.sched))) {
+			__scx_add_event(sch, SCX_EV_INSERT_NOT_OWNED, 1);
+			return;
+		}
+
 		/*
 		 * While we know @p is accessible, we don't yet have a claim on
 		 * it - the BPF scheduler is allowed to dispatch tasks
@@ -3739,6 +3745,7 @@ static ssize_t scx_attr_events_show(struct kobject *kobj,
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_DURATION);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_DISPATCH);
 	at += scx_attr_event_show(buf, at, &events, SCX_EV_BYPASS_ACTIVATE);
+	at += scx_attr_event_show(buf, at, &events, SCX_EV_INSERT_NOT_OWNED);
 	return at;
 }
 SCX_ATTR(events);
@@ -4631,6 +4638,7 @@ static void scx_dump_state(struct scx_exit_info *ei, size_t dump_len)
 	scx_dump_event(s, &events, SCX_EV_BYPASS_DURATION);
 	scx_dump_event(s, &events, SCX_EV_BYPASS_DISPATCH);
 	scx_dump_event(s, &events, SCX_EV_BYPASS_ACTIVATE);
+	scx_dump_event(s, &events, SCX_EV_INSERT_NOT_OWNED);
 
 	if (seq_buf_has_overflowed(&s) && dump_len >= sizeof(trunc_marker))
 		memcpy(ei->dump + dump_len - sizeof(trunc_marker),
@@ -7247,6 +7255,7 @@ static void scx_read_events(struct scx_sched *sch, struct scx_event_stats *event
 		scx_agg_event(events, e_cpu, SCX_EV_BYPASS_DURATION);
 		scx_agg_event(events, e_cpu, SCX_EV_BYPASS_DISPATCH);
 		scx_agg_event(events, e_cpu, SCX_EV_BYPASS_ACTIVATE);
+		scx_agg_event(events, e_cpu, SCX_EV_INSERT_NOT_OWNED);
 	}
 }
 
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index 64d0f0787c8e..154993921c38 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -895,6 +895,18 @@ struct scx_event_stats {
 	 * The number of times the bypassing mode has been activated.
 	 */
 	s64		SCX_EV_BYPASS_ACTIVATE;
+
+	/*
+	 * The number of times the scheduler attempted to insert a task that it
+	 * doesn't own into a DSQ. Such attempts are ignored.
+	 *
+	 * As BPF schedulers are allowed to ignore dequeues, it's difficult to
+	 * tell whether such an attempt is from a scheduler malfunction or an
+	 * ignored dequeue around sub-sched enabling. If this count keeps going
+	 * up regardless of sub-sched enabling, it likely indicates a bug in the
+	 * scheduler.
+	 */
+	s64		SCX_EV_INSERT_NOT_OWNED;
 };
 
 struct scx_sched_pcpu {
-- 
2.51.0