From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
To: linux-kernel@vger.kernel.org,
"Paul E. McKenney" <paulmck@kernel.org>,
Frederic Weisbecker <frederic@kernel.org>,
Neeraj Upadhyay <neeraj.upadhyay@kernel.org>,
Joel Fernandes <joel@joelfernandes.org>,
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.zhang1211@gmail.com>
Cc: urezki@gmail.com, neeraj.iitr10@gmail.com, rcu@vger.kernel.org
Subject: [PATCH v3] rcu/tree: Reduce wake up for synchronize_rcu() common case
Date: Tue, 19 Mar 2024 13:24:11 -0400 [thread overview]
Message-ID: <20240319172412.2083384-1-joel@joelfernandes.org> (raw)
In the synchronize_rcu() common case, we will have less than
SR_MAX_USERS_WAKE_FROM_GP number of users per GP. Waking up the kworker
is pointless just to free the last injected wait head since at that point,
all the users have already been awakened.
Introduce a new counter to track this and prevent the wakeup in the
common case.
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
v1->v2: Rebase on paul/dev
v2->v3: Additional optimization for wait_tail->next == NULL case.
kernel/rcu/tree.c | 37 ++++++++++++++++++++++++++++++++-----
kernel/rcu/tree.h | 1 +
2 files changed, 33 insertions(+), 5 deletions(-)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 9fbb5ab57c84..f06d13993478 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -96,6 +96,7 @@ static struct rcu_state rcu_state = {
.ofl_lock = __ARCH_SPIN_LOCK_UNLOCKED,
.srs_cleanup_work = __WORK_INITIALIZER(rcu_state.srs_cleanup_work,
rcu_sr_normal_gp_cleanup_work),
+ .srs_cleanups_pending = ATOMIC_INIT(0),
};
/* Dump rcu_node combining tree at boot to verify correct setup. */
@@ -1642,8 +1643,11 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
* the done tail list manipulations are protected here.
*/
done = smp_load_acquire(&rcu_state.srs_done_tail);
- if (!done)
+ if (!done) {
+ /* See comments below. */
+ atomic_dec_return_release(&rcu_state.srs_cleanups_pending);
return;
+ }
WARN_ON_ONCE(!rcu_sr_is_wait_head(done));
head = done->next;
@@ -1666,6 +1670,9 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
rcu_sr_put_wait_head(rcu);
}
+
+ /* Order list manipulations with atomic access. */
+ atomic_dec_return_release(&rcu_state.srs_cleanups_pending);
}
/*
@@ -1673,7 +1680,7 @@ static void rcu_sr_normal_gp_cleanup_work(struct work_struct *work)
*/
static void rcu_sr_normal_gp_cleanup(void)
{
- struct llist_node *wait_tail, *next, *rcu;
+ struct llist_node *wait_tail, *next = NULL, *rcu = NULL;
int done = 0;
wait_tail = rcu_state.srs_wait_tail;
@@ -1699,16 +1706,36 @@ static void rcu_sr_normal_gp_cleanup(void)
break;
}
- // concurrent sr_normal_gp_cleanup work might observe this update.
- smp_store_release(&rcu_state.srs_done_tail, wait_tail);
+ /* Fast path, no more users to process. */
+ if (!wait_tail->next)
+ return;
+
+ /*
+ * Fast path, no more users to process except putting the second last
+ * wait head if no inflight-workers. If there are in-flight workers,
+ * they will remove the last wait head.
+ */
+ if (rcu_sr_is_wait_head(rcu) && rcu->next == NULL &&
+ /* Order atomic access with list manipulation. */
+ !atomic_read_acquire(&rcu_state.srs_cleanups_pending)) {
+ wait_tail->next = NULL;
+ rcu_sr_put_wait_head(rcu);
+ smp_store_release(&rcu_state.srs_done_tail, wait_tail);
+ return;
+ }
+
+ /* Concurrent sr_normal_gp_cleanup work might observe this update. */
ASSERT_EXCLUSIVE_WRITER(rcu_state.srs_done_tail);
+ smp_store_release(&rcu_state.srs_done_tail, wait_tail);
/*
* We schedule a work in order to perform a final processing
* of outstanding users(if still left) and releasing wait-heads
* added by rcu_sr_normal_gp_init() call.
*/
- queue_work(sync_wq, &rcu_state.srs_cleanup_work);
+ atomic_inc(&rcu_state.srs_cleanups_pending);
+ if (!queue_work(sync_wq, &rcu_state.srs_cleanup_work))
+ atomic_dec(&rcu_state.srs_cleanups_pending);
}
/*
diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
index bae7925c497f..affcb92a358c 100644
--- a/kernel/rcu/tree.h
+++ b/kernel/rcu/tree.h
@@ -420,6 +420,7 @@ struct rcu_state {
struct llist_node *srs_done_tail; /* ready for GP users. */
struct sr_wait_node srs_wait_nodes[SR_NORMAL_GP_WAIT_HEAD_MAX];
struct work_struct srs_cleanup_work;
+ atomic_t srs_cleanups_pending; /* srs inflight worker cleanups. */
};
/* Values for rcu_state structure's gp_flags field. */
--
2.34.1
reply other threads:[~2024-03-19 17:24 UTC|newest]
Thread overview: [no followups] expand[flat|nested] mbox.gz Atom feed
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=20240319172412.2083384-1-joel@joelfernandes.org \
--to=joel@joelfernandes.org \
--cc=boqun.feng@gmail.com \
--cc=frederic@kernel.org \
--cc=jiangshanlai@gmail.com \
--cc=josh@joshtriplett.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mathieu.desnoyers@efficios.com \
--cc=neeraj.iitr10@gmail.com \
--cc=neeraj.upadhyay@kernel.org \
--cc=paulmck@kernel.org \
--cc=qiang.zhang1211@gmail.com \
--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;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).