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,
        Tim Chen <tim.c.chen@linux.intel.com>,
        kernel test robot <lkp@intel.com>
Subject: [PATCH v6 1/2] percpu: Add percpu_counter_add_local and percpu_counter_sub_local
Date:   Wed, 14 Sep 2022 03:25:37 +0800
Message-Id: <20220913192538.3023708-2-jiebin.sun@intel.com>
In-Reply-To: <20220913192538.3023708-1-jiebin.sun@intel.com>
References: <20220902152243.479592-1-jiebin.sun@intel.com>
 <20220913192538.3023708-1-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>
Reviewed-by: Tim Chen <tim.c.chen@linux.intel.com>
Reported-by: kernel test robot <lkp@intel.com>
---
 include/linux/percpu_counter.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index 01861eebed79..8ed5fba6d156 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 +59,22 @@ static inline void percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	percpu_counter_add_batch(fbc, amount, percpu_counter_batch);
 }
 
+/*
+ * With percpu_counter_add_local() and percpu_counter_sub_local(), counts
+ * are accumulated in local per cpu counter and not in fbc->count until
+ * local count overflows PERCPU_COUNTER_LOCAL_BATCH. This makes counter
+ * write efficient.
+ * But percpu_counter_sum(), instead of percpu_counter_read(), needs to be
+ * used to add up the counts from each CPU to account for all the local
+ * counts. So percpu_counter_add_local() and percpu_counter_sub_local()
+ * should be used when a counter is updated frequently and read rarely.
+ */
+static inline void
+percpu_counter_add_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 +157,13 @@ percpu_counter_add(struct percpu_counter *fbc, s64 amount)
 	preempt_enable();
 }
 
+/* non-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);
+}
+
 static inline void
 percpu_counter_add_batch(struct percpu_counter *fbc, s64 amount, s32 batch)
 {
@@ -193,4 +219,10 @@ static inline void percpu_counter_sub(struct percpu_counter *fbc, s64 amount)
 	percpu_counter_add(fbc, -amount);
 }
 
+static inline void
+percpu_counter_sub_local(struct percpu_counter *fbc, s64 amount)
+{
+	percpu_counter_add_local(fbc, -amount);
+}
+
 #endif /* _LINUX_PERCPU_COUNTER_H */
-- 
2.31.1