[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20221011180142.2742289-7-joel@joelfernandes.org>
Date: Tue, 11 Oct 2022 18:01:35 +0000
From: "Joel Fernandes (Google)" <joel@...lfernandes.org>
To: rcu@...r.kernel.org
Cc: linux-kernel@...r.kernel.org, rushikesh.s.kadam@...el.com,
urezki@...il.com, neeraj.iitr10@...il.com, frederic@...nel.org,
paulmck@...nel.org, rostedt@...dmis.org, youssefesmat@...gle.com,
surenb@...gle.com,
"Joel Fernandes (Google)" <joel@...lfernandes.org>
Subject: [PATCH v8 06/13] percpu-refcount: Use call_rcu_flush() for atomic switch
call_rcu() changes to save power will slow down the percpu refcounter's
"per-CPU to atomic switch" path. The primitive uses RCU when switching to
atomic mode. The enqueued async callback wakes up waiters waiting in the
percpu_ref_switch_waitq. Due to this, per-CPU refcount users will slow down,
such as blk_pre_runtime_suspend().
Use the call_rcu_flush() API instead which reverts to the old behavior.
Signed-off-by: Joel Fernandes (Google) <joel@...lfernandes.org>
---
lib/percpu-refcount.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index e5c5315da274..65c58a029297 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -230,7 +230,8 @@ static void __percpu_ref_switch_to_atomic(struct percpu_ref *ref,
percpu_ref_noop_confirm_switch;
percpu_ref_get(ref); /* put after confirmation */
- call_rcu(&ref->data->rcu, percpu_ref_switch_to_atomic_rcu);
+ call_rcu_flush(&ref->data->rcu,
+ percpu_ref_switch_to_atomic_rcu);
}
static void __percpu_ref_switch_to_percpu(struct percpu_ref *ref)
--
2.38.0.rc1.362.ged0d419d3c-goog
Powered by blists - more mailing lists