linux-kernel - [PATCH -next v2 2/4] rcu/nocb: Add warning if no rcuog wake up attempt happened during overload

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 for Android: free password hash cracker in your pocket

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

Message-Id: <20260114173154.1701056-3-joelagnelf@nvidia.com>
Date: Wed, 14 Jan 2026 12:31:52 -0500
From: Joel Fernandes <joelagnelf@...dia.com>
To: linux-kernel@...r.kernel.org
Cc: "Paul E . McKenney" <paulmck@...nel.org>,
	Boqun Feng <boqun.feng@...il.com>,
	rcu@...r.kernel.org,
	Frederic Weisbecker <frederic@...nel.org>,
	Neeraj Upadhyay <neeraj.upadhyay@...nel.org>,
	Josh Triplett <josh@...htriplett.org>,
	Uladzislau Rezki <urezki@...il.com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
	Lai Jiangshan <jiangshanlai@...il.com>,
	Zqiang <qiang.zhang@...ux.dev>,
	Joel Fernandes <joelagnelf@...dia.com>
Subject: [PATCH -next v2 2/4] rcu/nocb: Add warning if no rcuog wake up attempt happened during overload

To be sure we have no rcog wake ups that were lost, add a warning
to cover the case where the rdp is overloaded with callbacks but
no wake up was attempted.

[applied Frederic's adjustment to clearing of nocb_gp_handling flag]

Signed-off-by: Joel Fernandes <joelagnelf@...dia.com>
---
 kernel/rcu/tree.c      |  4 ++++
 kernel/rcu/tree.h      |  1 +
 kernel/rcu/tree_nocb.h | 11 ++++++++++-
 3 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 2921ffb19939..958b61be87ea 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -3767,6 +3767,10 @@ static void rcu_barrier_entrain(struct rcu_data *rdp)
 		debug_rcu_head_unqueue(&rdp->barrier_head);
 		rcu_barrier_trace(TPS("IRQNQ"), -1, rcu_state.barrier_sequence);
 	}
+#ifdef CONFIG_RCU_NOCB_CPU
+	/* wake_nocb implies all CBs queued before were bypass/lazy. */
+	WARN_ON_ONCE(wake_nocb && !rdp->nocb_gp_handling);
+#endif
 	rcu_nocb_unlock(rdp);
 	if (wake_nocb)
 		wake_nocb_gp(rdp);
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index 7dfc57e9adb1..af1d065e3215 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -257,6 +257,7 @@ struct rcu_data {
 	unsigned long nocb_gp_loops;	/* # passes through wait code. */
 	struct swait_queue_head nocb_gp_wq; /* For nocb kthreads to sleep on. */
 	bool nocb_cb_sleep;		/* Is the nocb CB thread asleep? */
+	bool nocb_gp_handling;		/* Is rcuog handling this rdp? */
 	struct task_struct *nocb_cb_kthread;
 	struct list_head nocb_head_rdp; /*
 					 * Head of rcu_data list in wakeup chain,
diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
index f525e4f7985b..acca24670a8c 100644
--- a/kernel/rcu/tree_nocb.h
+++ b/kernel/rcu/tree_nocb.h
@@ -546,6 +546,7 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 	lazy_len = READ_ONCE(rdp->lazy_len);
 	if (was_alldone) {
 		rdp->qlen_last_fqs_check = len;
+		rdp->nocb_gp_handling = true;
 		rcu_nocb_unlock(rdp);
 		// Only lazy CBs in bypass list
 		if (lazy_len && bypass_len == lazy_len) {
@@ -563,7 +564,8 @@ static void __call_rcu_nocb_wake(struct rcu_data *rdp, bool was_alldone,
 
 		return;
 	} else if (len > rdp->qlen_last_fqs_check + qhimark) {
-		/* ... or if many callbacks queued. */
+		/* Callback overload condition. */
+		WARN_ON_ONCE(!rdp->nocb_gp_handling);
 		rdp->qlen_last_fqs_check = len;
 		j = jiffies;
 		if (j != rdp->nocb_gp_adv_time &&
@@ -732,6 +734,12 @@ static void nocb_gp_wait(struct rcu_data *my_rdp)
 			needwait_gp = true;
 			trace_rcu_nocb_wake(rcu_state.name, rdp->cpu,
 					    TPS("NeedWaitGP"));
+		} else if (!rcu_cblist_n_cbs(&rdp->nocb_bypass)) {
+			/*
+			 * No pending callbacks and no bypass callbacks.
+			 * The rcuog kthread is done handling this rdp.
+			 */
+			rdp->nocb_gp_handling = false;
 		}
 		if (rcu_segcblist_ready_cbs(&rdp->cblist)) {
 			needwake = rdp->nocb_cb_sleep;
@@ -1254,6 +1262,7 @@ lazy_rcu_shrink_scan(struct shrinker *shrink, struct shrink_control *sc)
 			continue;
 		}
 		rcu_nocb_try_flush_bypass(rdp, jiffies);
+		rdp->nocb_gp_handling = true;
 		rcu_nocb_unlock_irqrestore(rdp, flags);
 		wake_nocb_gp(rdp);
 		sc->nr_to_scan -= _count;
-- 
2.34.1