percpu: Add percpu_counter_add_local and percpu_counter_sub_local

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

@@ -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)
 {