[PATCH] nvmet: drop the extra RCU grace period in nvmet_ns_disable()

[PATCH] nvmet: drop the extra RCU grace period in nvmet_ns_disable()

[Qiliang Yuan]

nvmet_ns_disable() kills the namespace's percpu ref, waits in
synchronize_rcu() for anyone looking the namespace up under
rcu_read_lock(), and then waits for the ref to drop to zero.

Killing a percpu ref already switches it to atomic mode from an RCU
callback, so the ref can't drop to zero before a grace period has
passed since the kill. synchronize_rcu() thus adds a second grace
period in a row, about 4 ms here, and disabling the namespaces of a
subsystem one by one takes about 9 ms each.

Drop synchronize_rcu() and rely on the wait for the ref to cover the
RCU readers as well.

Disabling 64 namespaces through configfs, median of 3 runs on each of
two boots per kernel:

  host connected  before          after
  none            588 / 590 ms    409 / 409 ms
  nvme-tcp        617 / 619 ms    542 / 511 ms

Signed-off-by: Qiliang Yuan <odys.yuan@gmail.com>
---
 drivers/nvme/target/core.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
index a8171b88035c5..8aca4b279bb9a 100644
--- a/drivers/nvme/target/core.c
+++ b/drivers/nvme/target/core.c
@@ -669,13 +669,13 @@ void nvmet_ns_disable(struct nvmet_ns *ns)
 	/*
 	 * Now that we removed the namespaces from the lookup list, we
 	 * can kill the per_cpu ref and wait for any remaining references
-	 * to be dropped, as well as a RCU grace period for anyone only
-	 * using the namespace under rcu_read_lock().  Note that we can't
-	 * use call_rcu here as we need to ensure the namespaces have
-	 * been fully destroyed before unloading the module.
+	 * to be dropped.  Rely on that wait for anyone only using the
+	 * namespace under rcu_read_lock() too: the ref can't drop to zero
+	 * before an RCU grace period has passed since the kill.  Note that
+	 * we can't use call_rcu here as we need to ensure the namespaces
+	 * have been fully destroyed before unloading the module.
 	 */
 	percpu_ref_kill(&ns->ref);
-	synchronize_rcu();
 	wait_for_completion(&ns->disable_done);
 	percpu_ref_exit(&ns->ref);
 

---
base-commit: 6628e7d4c6b25c8d18f1345e3a20d21829aae7e4
change-id: 20261102-bug-nvmet-ns-disable-rcu-30ebdfe414ff

Best regards,
-- 
Qiliang Yuan <odys.yuan@gmail.com>

Re: [PATCH] nvmet: drop the extra RCU grace period in nvmet_ns_disable()

[Christoph Hellwig]

On Tue, Nov 03, 2026 at 01:31:25AM -0500, Qiliang Yuan wrote:
>  	 * Now that we removed the namespaces from the lookup list, we
>  	 * can kill the per_cpu ref and wait for any remaining references
> -	 * to be dropped, as well as a RCU grace period for anyone only
> -	 * using the namespace under rcu_read_lock().  Note that we can't
> -	 * use call_rcu here as we need to ensure the namespaces have
> -	 * been fully destroyed before unloading the module.
> +	 * to be dropped.  Rely on that wait for anyone only using the
> +	 * namespace under rcu_read_lock() too: the ref can't drop to zero
> +	 * before an RCU grace period has passed since the kill.  Note that
> +	 * we can't use call_rcu here as we need to ensure the namespaces
> +	 * have been fully destroyed before unloading the module.
>  	 */
>  	percpu_ref_kill(&ns->ref);
> -	synchronize_rcu();

This assumes the percpu_ref is never moved to atomic mode otherwise.
Which we don't do in nvmet, but maybe leaving a reminder of that here
would be useful.