diff --git a/include/linux/percpu_counter.h b/include/linux/percpu_counter.h
index bd6708e2c02703e70be886a4229eb4071be33137..682525511c9e90d352f2d46730932e9711ce457e 100644
--- a/include/linux/percpu_counter.h
+++ b/include/linux/percpu_counter.h
@@ -39,6 +39,7 @@ static inline void percpu_counter_destroy(struct percpu_counter *fbc)
 }
 
 void percpu_counter_mod(struct percpu_counter *fbc, long amount);
+long percpu_counter_sum(struct percpu_counter *fbc);
 
 static inline long percpu_counter_read(struct percpu_counter *fbc)
 {
@@ -92,6 +93,11 @@ static inline long percpu_counter_read_positive(struct percpu_counter *fbc)
 	return fbc->count;
 }
 
+static inline long percpu_counter_sum(struct percpu_counter *fbc)
+{
+	return percpu_counter_read_positive(fbc);
+}
+
 #endif	/* CONFIG_SMP */
 
 static inline void percpu_counter_inc(struct percpu_counter *fbc)
diff --git a/mm/swap.c b/mm/swap.c
index cce3dda59c595560dc90ede2bf6f12e193e4312f..e9ec06d845e808a36702c6fa64af986ece2f56a1 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -489,13 +489,34 @@ void percpu_counter_mod(struct percpu_counter *fbc, long amount)
 	if (count >= FBC_BATCH || count <= -FBC_BATCH) {
 		spin_lock(&fbc->lock);
 		fbc->count += count;
+		*pcount = 0;
 		spin_unlock(&fbc->lock);
-		count = 0;
+	} else {
+		*pcount = count;
 	}
-	*pcount = count;
 	put_cpu();
 }
 EXPORT_SYMBOL(percpu_counter_mod);
+
+/*
+ * Add up all the per-cpu counts, return the result.  This is a more accurate
+ * but much slower version of percpu_counter_read_positive()
+ */
+long percpu_counter_sum(struct percpu_counter *fbc)
+{
+	long ret;
+	int cpu;
+
+	spin_lock(&fbc->lock);
+	ret = fbc->count;
+	for_each_cpu(cpu) {
+		long *pcount = per_cpu_ptr(fbc->counters, cpu);
+		ret += *pcount;
+	}
+	spin_unlock(&fbc->lock);
+	return ret < 0 ? 0 : ret;
+}
+EXPORT_SYMBOL(percpu_counter_sum);
 #endif
 
 /*