diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c
index e41cc6f..07371cf 100644
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@@ -441,15 +441,27 @@
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_completion_stats);
 
+/*  Merged stats are per cpu.  */
 void blkiocg_update_io_merged_stats(struct blkio_group *blkg, bool direction,
 					bool sync)
 {
+	struct blkio_group_stats_cpu *stats_cpu;
 	unsigned long flags;
 
-	spin_lock_irqsave(&blkg->stats_lock, flags);
-	blkio_add_stat(blkg->stats.stat_arr[BLKIO_STAT_MERGED], 1, direction,
-			sync);
-	spin_unlock_irqrestore(&blkg->stats_lock, flags);
+	/*
+	 * Disabling interrupts to provide mutual exclusion between two
+	 * writes on same cpu. It probably is not needed for 64bit. Not
+	 * optimizing that case yet.
+	 */
+	local_irq_save(flags);
+
+	stats_cpu = this_cpu_ptr(blkg->stats_cpu);
+
+	u64_stats_update_begin(&stats_cpu->syncp);
+	blkio_add_stat(stats_cpu->stat_arr_cpu[BLKIO_STAT_CPU_MERGED], 1,
+				direction, sync);
+	u64_stats_update_end(&stats_cpu->syncp);
+	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(blkiocg_update_io_merged_stats);
 
@@ -1244,7 +1256,7 @@
 						BLKIO_STAT_WAIT_TIME, 1, 0);
 		case BLKIO_PROP_io_merged:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
-						BLKIO_STAT_MERGED, 1, 0);
+						BLKIO_STAT_CPU_MERGED, 1, 1);
 		case BLKIO_PROP_io_queued:
 			return blkio_read_blkg_stats(blkcg, cft, cb,
 						BLKIO_STAT_QUEUED, 1, 0);
diff --git a/block/blk-cgroup.h b/block/blk-cgroup.h
index 2622267..a71d290 100644
--- a/block/blk-cgroup.h
+++ b/block/blk-cgroup.h
@@ -39,8 +39,6 @@
 	BLKIO_STAT_SERVICE_TIME = 0,
 	/* Total time spent waiting in scheduler queue in ns */
 	BLKIO_STAT_WAIT_TIME,
-	/* Number of IOs merged */
-	BLKIO_STAT_MERGED,
 	/* Number of IOs queued up */
 	BLKIO_STAT_QUEUED,
 	/* All the single valued stats go below this */
@@ -63,6 +61,8 @@
 	BLKIO_STAT_CPU_SERVICE_BYTES,
 	/* Total IOs serviced, post merge */
 	BLKIO_STAT_CPU_SERVICED,
+	/* Number of IOs merged */
+	BLKIO_STAT_CPU_MERGED,
 	BLKIO_STAT_CPU_NR
 };