All of lore.kernel.org
 help / color / mirror / Atom feed
From: Tejun Heo <tj@kernel.org>
To: David Vernet <void@manifault.com>,
	Andrea Righi <arighi@nvidia.com>,
	Changwoo Min <changwoo@igalia.com>
Cc: sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org,
	Emil Tsalapatis <emil@etsalapatis.com>,
	Chris Mason <clm@meta.com>, Ryan Newton <newton@meta.com>,
	Tejun Heo <tj@kernel.org>,
	stable@vger.kernel.org
Subject: [PATCH 07/13] sched_ext: Use dsq->first_task instead of list_empty() in dispatch_enqueue() FIFO-tail
Date: Fri, 24 Apr 2026 10:44:12 -1000	[thread overview]
Message-ID: <20260424204418.3809733-8-tj@kernel.org> (raw)
In-Reply-To: <20260424204418.3809733-1-tj@kernel.org>

dispatch_enqueue()'s FIFO-tail path used list_empty(&dsq->list) to decide
whether to set dsq->first_task on enqueue. dsq->list can contain parked BPF
iterator cursors (SCX_DSQ_LNODE_ITER_CURSOR), so list_empty() is not a
reliable "no real task" check. If the last real task is unlinked while a
cursor is parked, first_task becomes NULL; the next FIFO-tail enqueue then
sees list_empty() == false and skips the first_task update, leaving
scx_bpf_dsq_peek() returning NULL for a non-empty DSQ.

Test dsq->first_task directly, which already tracks only real tasks and is
maintained under dsq->lock.

Fixes: 44f5c8ec5b9a ("sched_ext: Add lockless peek operation for DSQs")
Cc: stable@vger.kernel.org # v6.19+
Reported-by: Chris Mason <clm@meta.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Ryan Newton <newton@meta.com>
---
 kernel/sched/ext.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 4bd1fcba50c5..045b4c914768 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -1495,11 +1495,13 @@ static void dispatch_enqueue(struct scx_sched *sch, struct rq *rq,
 			if (!(dsq->id & SCX_DSQ_FLAG_BUILTIN))
 				rcu_assign_pointer(dsq->first_task, p);
 		} else {
-			bool was_empty;
-
-			was_empty = list_empty(&dsq->list);
+			/*
+			 * dsq->list can contain parked BPF iterator cursors, so
+			 * list_empty() here isn't a reliable proxy for "no real
+			 * task in the DSQ". Test dsq->first_task directly.
+			 */
 			list_add_tail(&p->scx.dsq_list.node, &dsq->list);
-			if (was_empty && !(dsq->id & SCX_DSQ_FLAG_BUILTIN))
+			if (!dsq->first_task && !(dsq->id & SCX_DSQ_FLAG_BUILTIN))
 				rcu_assign_pointer(dsq->first_task, p);
 		}
 	}
-- 
2.53.0


  parent reply	other threads:[~2026-04-24 20:44 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-04-24 20:44 [PATCHSET sched_ext/for-7.1-fixes] sched_ext: Assorted fixes Tejun Heo
2026-04-24 20:44 ` [PATCH 01/13] sched_ext: Unregister sub_kset on scheduler disable Tejun Heo
2026-04-24 20:44 ` [PATCH 02/13] sched_ext: Guard scx_dsq_move() against NULL kit->dsq after failed iter_new Tejun Heo
2026-04-24 20:44 ` [PATCH 03/13] sched_ext: Skip tasks with stale task_rq in bypass_lb_cpu() Tejun Heo
2026-04-24 20:44 ` [PATCH 04/13] sched_ext: Don't disable tasks in scx_sub_enable_workfn() abort path Tejun Heo
2026-04-24 20:44 ` [PATCH 05/13] sched_ext: Read scx_root under scx_cgroup_ops_rwsem in cgroup setters Tejun Heo
2026-04-24 20:44 ` [PATCH 06/13] sched_ext: Resolve caller's scheduler in scx_bpf_destroy_dsq() / scx_bpf_dsq_nr_queued() Tejun Heo
2026-04-24 20:44 ` Tejun Heo [this message]
2026-04-24 20:44 ` [PATCH 08/13] sched_ext: Save and restore scx_locked_rq across SCX_CALL_OP Tejun Heo
2026-04-24 20:44 ` [PATCH 09/13] sched_ext: Pass held rq to SCX_CALL_OP() for dump_cpu/dump_task Tejun Heo
2026-04-24 20:44 ` [PATCH 10/13] sched_ext: Pass held rq to SCX_CALL_OP() for core_sched_before Tejun Heo
2026-04-24 20:44 ` [PATCH 11/13] sched_ext: Make bypass LB cpumasks per-scheduler Tejun Heo
2026-04-24 20:44 ` [PATCH 12/13] sched_ext: Align cgroup #ifdef guards with SUB_SCHED vs GROUP_SCHED Tejun Heo
2026-04-24 20:44 ` [PATCH 13/13] sched_ext: Refuse cross-task select_cpu_from_kfunc calls Tejun Heo
2026-04-24 21:46   ` Andrea Righi
2026-04-25  0:19   ` [PATCH v2 " Tejun Heo
2026-04-25  6:50     ` Andrea Righi
2026-04-24 21:08 ` [PATCH 14/13] sched_ext: Reject NULL-sch callers in scx_bpf_task_set_slice/dsq_vtime Tejun Heo
2026-04-24 21:08   ` [PATCH 15/13] sched_ext: Release cpus_read_lock on scx_link_sched() failure in root enable Tejun Heo
2026-04-24 22:00     ` Andrea Righi
2026-04-25  0:19     ` [PATCH v2 " Tejun Heo
2026-04-25  6:51       ` Andrea Righi
2026-04-24 22:10 ` [PATCHSET sched_ext/for-7.1-fixes] sched_ext: Assorted fixes Andrea Righi
2026-04-25  0:39 ` Tejun Heo

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=20260424204418.3809733-8-tj@kernel.org \
    --to=tj@kernel.org \
    --cc=arighi@nvidia.com \
    --cc=changwoo@igalia.com \
    --cc=clm@meta.com \
    --cc=emil@etsalapatis.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=newton@meta.com \
    --cc=sched-ext@lists.linux.dev \
    --cc=stable@vger.kernel.org \
    --cc=void@manifault.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.