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:   Jiebin Sun <jiebin.sun@intel.com>
To:     akpm@linux-foundation.org, vasily.averin@linux.dev,
        shakeelb@google.com, dennis@kernel.org, tj@kernel.org,
        cl@linux.com, ebiederm@xmission.com, legion@kernel.org,
        manfred@colorfullife.com, alexander.mikhalitsyn@virtuozzo.com,
        linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc:     tim.c.chen@intel.com, feng.tang@intel.com, ying.huang@intel.com,
        tianyou.li@intel.com, wangyang.guo@intel.com, jiebin.sun@intel.com
Subject: [PATCH v5 1/2] percpu: Add percpu_counter_add_local and percpu_counter_sub_local
Date:   Sat, 10 Sep 2022 04:36:35 +0800
Message-Id: <20220909203636.2652466-2-jiebin.sun@intel.com>
In-Reply-To: <20220909203636.2652466-1-jiebin.sun@intel.com>
References: <20220902152243.479592-1-jiebin.sun@intel.com>
 <20220909203636.2652466-1-jiebin.sun@intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

The batch size in percpu_counter_add_batch should be very large
in heavy writing and rare reading case. Add the "_local" version,
and mostly it will do local adding, reduce the global updating
and mitigate lock contention in writing.

Signed-off-by: Jiebin Sun <jiebin.sun@intel.com>
---
 include/linux/percpu_counter.h | 38 ++++++++++++++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 01861eebed79..6dd7eaba8527 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -15,6 +15,9 @@
 #include <linux/types.h>
 #include <linux/gfp.h>
 
+/* percpu_counter batch for local add or sub */
+#define PERCPU_COUNTER_LOCAL_BATCH	INT_MAX
+
 #ifdef CONFIG_SMP
 
 struct percpu_counter {
@@ -56,6 +59,27 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	percpu_counter_add_batch(fbc, amount, percpu_counter_batch);
 }
 
+/*
+ * Use this function in heavy writing but rare reading case. The large
+ * batch size will reduce the global updating.
+ */
+static inline void
+percpu_counter_add_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_add_batch(fbc, amount, PERCPU_COUNTER_LOCAL_BATCH);
+}
+
+/*
+ * Similar with percpu_counter_add_local, use it in heavy writing but
+ * rare reading case. The large batch size will reduce the global
+ * updating.
+ */
+static inline void
+percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_add_batch(fbc, -amount, PERCPU_COUNTER_LOCAL_BATCH);
+}
+
 static inline s64 percpu_counter_sum_positive(struct percpu_counter *fbc)
 {
 	s64 ret = __percpu_counter_sum(fbc);
@@ -138,6 +162,20 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	preempt_enable();
 }
 
+/* no smp percpu_counter_add_local is the same with percpu_counter_add */
+static inline void
+percpu_counter_add_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_add(fbc, amount);
+}
+
+/* no smp percpu_counter_sub_local is the same with percpu_counter_sub */
+static inline void
+percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_sub(fbc, amount);
+}
+
 static inline void
 percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
-- 
2.31.1