Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
From:   Qi Zheng <zhengqi.arch@bytedance.com>
To:     akpm@linux-foundation.org, tglx@linutronix.de,
        kirill.shutemov@linux.intel.com, mika.penttila@nextfour.com,
        david@redhat.com, jgg@nvidia.com, tj@kernel.org, dennis@kernel.org,
        ming.lei@redhat.com
Cc:     linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
        linux-mm@kvack.org, songmuchun@bytedance.com,
        zhouchengming@bytedance.com, Qi Zheng <zhengqi.arch@bytedance.com>
Subject: [RFC PATCH 03/18] percpu_ref: make percpu_ref_switch_lock per percpu_ref
Date:   Fri, 29 Apr 2022 21:35:37 +0800
Message-Id: <20220429133552.33768-4-zhengqi.arch@bytedance.com>
In-Reply-To: <20220429133552.33768-1-zhengqi.arch@bytedance.com>
References: <20220429133552.33768-1-zhengqi.arch@bytedance.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Currently, percpu_ref uses the global percpu_ref_switch_lock to
protect the mode switching operation. When multiple percpu_ref
perform mode switching at the same time, the lock may become a
performance bottleneck.

This patch introduces per percpu_ref percpu_ref_switch_lock to
fixes this situation.

Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com>
---
 include/linux/percpu-refcount.h |  2 ++
 lib/percpu-refcount.c           | 30 +++++++++++++++---------------
 2 files changed, 17 insertions(+), 15 deletions(-)

diff --git a/include/linux/percpu-refcount.h b/include/linux/percpu-refcount.h
index 75844939a965..eb8695e578fd 100644
--- a/include/linux/percpu-refcount.h
+++ b/include/linux/percpu-refcount.h
@@ -110,6 +110,8 @@ struct percpu_ref {
 	 */
 	unsigned long		percpu_count_ptr;
 
+	spinlock_t percpu_ref_switch_lock;
+
 	/*
 	 * 'percpu_ref' is often embedded into user structure, and only
 	 * 'percpu_count_ptr' is required in fast path, move other fields
diff --git a/lib/percpu-refcount.c b/lib/percpu-refcount.c
index 3a8906715e09..4336fd1bd77a 100644
--- a/lib/percpu-refcount.c
+++ b/lib/percpu-refcount.c
@@ -36,7 +36,6 @@
 
 #define PERCPU_COUNT_BIAS	(1LU << (BITS_PER_LONG - 1))
 
-static DEFINE_SPINLOCK(percpu_ref_switch_lock);
 static DECLARE_WAIT_QUEUE_HEAD(percpu_ref_switch_waitq);
 
 static unsigned long __percpu *percpu_count_ptr(struct percpu_ref *ref)
@@ -95,6 +94,7 @@ int percpu_ref_init(struct percpu_ref *ref, percpu_ref_func_t *release,
 		start_count++;
 
 	atomic_long_set(&data->count, start_count);
+	spin_lock_init(&ref->percpu_ref_switch_lock);
 
 	data->release = release;
 	data->confirm_switch = NULL;
@@ -137,11 +137,11 @@ void percpu_ref_exit(struct percpu_ref *ref)
 	if (!data)
 		return;
 
-	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	spin_lock_irqsave(&ref->percpu_ref_switch_lock, flags);
 	ref->percpu_count_ptr |= atomic_long_read(&ref->data->count) <<
 		__PERCPU_REF_FLAG_BITS;
 	ref->data = NULL;
-	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+	spin_unlock_irqrestore(&ref->percpu_ref_switch_lock, flags);
 
 	kfree(data);
 }
@@ -287,7 +287,7 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref,
 {
 	struct percpu_ref_data *data = ref->data;
 
-	lockdep_assert_held(&percpu_ref_switch_lock);
+	lockdep_assert_held(&ref->percpu_ref_switch_lock);
 
 	/*
 	 * If the previous ATOMIC switching hasn't finished yet, wait for
@@ -295,7 +295,7 @@ static void __percpu_ref_switch_mode(struct percpu_ref *ref,
 	 * isn't in progress, this function can be called from any context.
 	 */
 	wait_event_lock_irq(percpu_ref_switch_waitq, !data->confirm_switch,
-			    percpu_ref_switch_lock);
+			    ref->percpu_ref_switch_lock);
 
 	if (data->force_atomic || percpu_ref_is_dying(ref))
 		__percpu_ref_switch_to_atomic(ref, confirm_switch, sync);
@@ -329,12 +329,12 @@ void percpu_ref_switch_to_atomic(struct percpu_ref *ref,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	spin_lock_irqsave(&ref->percpu_ref_switch_lock, flags);
 
 	ref->data->force_atomic = true;
 	__percpu_ref_switch_mode(ref, confirm_switch, sync);
 
-	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+	spin_unlock_irqrestore(&ref->percpu_ref_switch_lock, flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_switch_to_atomic);
 
@@ -376,12 +376,12 @@ void percpu_ref_switch_to_percpu(struct percpu_ref *ref)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	spin_lock_irqsave(&ref->percpu_ref_switch_lock, flags);
 
 	ref->data->force_atomic = false;
 	__percpu_ref_switch_mode(ref, NULL, false);
 
-	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+	spin_unlock_irqrestore(&ref->percpu_ref_switch_lock, flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_switch_to_percpu);
 
@@ -407,7 +407,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	spin_lock_irqsave(&ref->percpu_ref_switch_lock, flags);
 
 	WARN_ONCE(percpu_ref_is_dying(ref),
 		  "%s called more than once on %ps!", __func__,
@@ -417,7 +417,7 @@ void percpu_ref_kill_and_confirm(struct percpu_ref *ref,
 	__percpu_ref_switch_mode(ref, confirm_kill, false);
 	percpu_ref_put(ref);
 
-	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+	spin_unlock_irqrestore(&ref->percpu_ref_switch_lock, flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_kill_and_confirm);
 
@@ -438,12 +438,12 @@ bool percpu_ref_is_zero(struct percpu_ref *ref)
 		return false;
 
 	/* protect us from being destroyed */
-	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	spin_lock_irqsave(&ref->percpu_ref_switch_lock, flags);
 	if (ref->data)
 		count = atomic_long_read(&ref->data->count);
 	else
 		count = ref->percpu_count_ptr >> __PERCPU_REF_FLAG_BITS;
-	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+	spin_unlock_irqrestore(&ref->percpu_ref_switch_lock, flags);
 
 	return count == 0;
 }
@@ -487,7 +487,7 @@ void percpu_ref_resurrect(struct percpu_ref *ref)
 	unsigned long __percpu *percpu_count;
 	unsigned long flags;
 
-	spin_lock_irqsave(&percpu_ref_switch_lock, flags);
+	spin_lock_irqsave(&ref->percpu_ref_switch_lock, flags);
 
 	WARN_ON_ONCE(!percpu_ref_is_dying(ref));
 	WARN_ON_ONCE(__ref_is_percpu(ref, &percpu_count));
@@ -496,6 +496,6 @@ void percpu_ref_resurrect(struct percpu_ref *ref)
 	percpu_ref_get(ref);
 	__percpu_ref_switch_mode(ref, NULL, false);
 
-	spin_unlock_irqrestore(&percpu_ref_switch_lock, flags);
+	spin_unlock_irqrestore(&ref->percpu_ref_switch_lock, flags);
 }
 EXPORT_SYMBOL_GPL(percpu_ref_resurrect);
-- 
2.20.1