From: Joel Fernandes <joelagnelf@nvidia.com>
To: linux-kernel@vger.kernel.org
Cc: "Paul E . McKenney" <paulmck@kernel.org>,
Frederic Weisbecker <frederic@kernel.org>,
Neeraj Upadhyay <neeraj.upadhyay@kernel.org>,
Joel Fernandes <joelagnelf@nvidia.com>,
Josh Triplett <josh@joshtriplett.org>,
Boqun Feng <boqun.feng@gmail.com>,
Steven Rostedt <rostedt@goodmis.org>,
Mathieu Desnoyers <mathieu.desnoyers@efficios.com>,
Lai Jiangshan <jiangshanlai@gmail.com>,
Zqiang <qiang.zhang@linux.dev>,
Uladzislau Rezki <urezki@gmail.com>,
joel@joelfernandes.org, rcu@vger.kernel.org
Subject: [PATCH RFC 05/14] rcu: Promote blocked tasks for expedited GPs
Date: Fri, 2 Jan 2026 19:23:34 -0500 [thread overview]
Message-ID: <20260103002343.6599-6-joelagnelf@nvidia.com> (raw)
In-Reply-To: <20260103002343.6599-1-joelagnelf@nvidia.com>
Add a call to rcu_promote_blocked_tasks() in sync_exp_reset_tree()
before checking for blocked tasks. This ensures that expedited grace
periods properly wait for tasks that were blocked on per-CPU lists
before the expedited GP was initiated.
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
kernel/rcu/tree.h | 1 +
kernel/rcu/tree_exp.h | 5 +++++
kernel/rcu/tree_plugin.h | 8 +++++---
3 files changed, 11 insertions(+), 3 deletions(-)
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 13d5649a80fb..b71c6c1de8d3 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -501,6 +501,7 @@ static bool rcu_is_callbacks_kthread(struct rcu_data *rdp);
static void rcu_cpu_kthread_setup(unsigned int cpu);
static void rcu_spawn_one_boost_kthread(struct rcu_node *rnp);
static bool rcu_preempt_has_tasks(struct rcu_node *rnp);
+static void rcu_promote_blocked_tasks(struct rcu_node *rnp);
static bool rcu_preempt_need_deferred_qs(struct task_struct *t);
static void zero_cpu_stall_ticks(struct rcu_data *rdp);
static struct swait_queue_head *rcu_nocb_gp_get(struct rcu_node *rnp);
diff --git a/kernel/rcu/tree_exp.h b/kernel/rcu/tree_exp.h
index 96c49c56fc14..f6cb0e3147c4 100644
--- a/kernel/rcu/tree_exp.h
+++ b/kernel/rcu/tree_exp.h
@@ -141,6 +141,11 @@ static void __maybe_unused sync_exp_reset_tree(void)
raw_spin_lock_irqsave_rcu_node(rnp, flags);
WARN_ON_ONCE(rnp->expmask);
WRITE_ONCE(rnp->expmask, rnp->expmaskinit);
+ /*
+ * Promote tasks from per-CPU lists before checking blkd_tasks.
+ * This ensures expedited GPs see tasks blocked.
+ */
+ rcu_promote_blocked_tasks(rnp);
/*
* Need to wait for any blocked tasks as well. Note that
* additional blocking tasks will also block the expedited GP
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index 6810f1b72d2a..ad33fdd0efe8 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -810,8 +810,8 @@ static void rcu_read_unlock_special(struct task_struct *t)
/*
* Promote blocked tasks from a single CPU's per-CPU list to the rnp list.
*
- * If there are no tracked blockers (gp_tasks NULL) and this CPU
- * is still blocking the corresponding GP (bit set in qsmask), set
+ * If there are no tracked blockers (gp_tasks/exp_tasks NULL) and this CPU
+ * is still blocking the corresponding GP (bit set in qsmask/expmask), set
* the pointer to ensure the GP machinery knows about the blocking task.
* This handles late promotion during QS reporting, where tasks may have
* blocked after rcu_gp_init() or sync_exp_reset_tree() ran their scans.
@@ -844,11 +844,13 @@ static void rcu_promote_blocked_tasks_rdp(struct rcu_data *rdp,
t->rcu_blocked_cpu = -1;
/*
- * Set gp_tasks if this is the first blocker and
+ * Set gp_tasks/exp_tasks if this is the first blocker and
* this CPU is still blocking the corresponding GP.
*/
if (!rnp->gp_tasks && (rnp->qsmask & rdp->grpmask))
WRITE_ONCE(rnp->gp_tasks, &t->rcu_node_entry);
+ if (!rnp->exp_tasks && (rnp->expmask & rdp->grpmask))
+ WRITE_ONCE(rnp->exp_tasks, &t->rcu_node_entry);
}
raw_spin_unlock(&rdp->blkd_lock);
}
--
2.34.1
next prev parent reply other threads:[~2026-01-03 0:24 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-03 0:23 [PATCH RFC 00/14] rcu: Reduce rnp->lock contention with per-CPU blocked task lists Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 01/14] rcu: Add WARN_ON_ONCE for blocked flag invariant in exit_rcu() Joel Fernandes
2026-01-05 15:31 ` Steven Rostedt
2026-01-05 15:44 ` Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 02/14] rcu: Add per-CPU blocked task lists for PREEMPT_RCU Joel Fernandes
2026-01-05 15:48 ` Steven Rostedt
2026-01-03 0:23 ` [PATCH RFC 03/14] rcu: Early return during unlock for tasks only on per-CPU blocked list Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 04/14] rcu: Promote blocked tasks from per-CPU to rnp lists Joel Fernandes
2026-01-05 15:59 ` Steven Rostedt
2026-01-09 3:52 ` Joel Fernandes
2026-01-03 0:23 ` Joel Fernandes [this message]
2026-01-03 0:23 ` [PATCH RFC 06/14] rcu: Promote per-CPU blocked tasks before checking for blocked readers Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 07/14] rcu: Promote late-arriving blocked tasks before reporting QS Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 08/14] rcu: Promote blocked tasks before QS report in force_qs_rnp() Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 09/14] rcu: Promote blocked tasks before QS report in rcutree_report_cpu_dead() Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 10/14] rcu: Promote blocked tasks before QS report in rcu_gp_init() Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 11/14] rcu: Add per-CPU blocked list check in exit_rcu() Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 12/14] rcu: Skip per-CPU list addition when GP already started Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 13/14] rcu: Skip rnp addition when no grace period waiting Joel Fernandes
2026-01-03 0:23 ` [PATCH RFC 14/14] rcu: Remove checking of per-cpu blocked list against the node list Joel Fernandes
2026-01-05 16:46 ` [PATCH RFC 00/14] rcu: Reduce rnp->lock contention with per-CPU blocked task lists Paul E. McKenney
2026-01-06 0:55 ` Joel Fernandes
2026-01-06 15:08 ` Joel Fernandes
2026-01-06 19:24 ` Paul E. McKenney
2026-01-06 21:24 ` Joel Fernandes
2026-01-09 2:00 ` Paul E. McKenney
2026-01-06 19:17 ` Paul E. McKenney
2026-01-06 20:19 ` Steven Rostedt
2026-01-06 20:35 ` Paul E. McKenney
2026-01-06 20:49 ` Joel Fernandes
2026-01-09 1:55 ` Paul E. McKenney
2026-01-06 20:40 ` Joel Fernandes
2026-01-09 1:52 ` Paul E. McKenney
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=20260103002343.6599-6-joelagnelf@nvidia.com \
--to=joelagnelf@nvidia.com \
--cc=boqun.feng@gmail.com \
--cc=frederic@kernel.org \
--cc=jiangshanlai@gmail.com \
--cc=joel@joelfernandes.org \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=neeraj.upadhyay@kernel.org \
--cc=paulmck@kernel.org \
--cc=qiang.zhang@linux.dev \
--cc=rcu@vger.kernel.org \
--cc=rostedt@goodmis.org \
--cc=urezki@gmail.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®