[PATCH] block: fix the problem of io_ticks becoming smaller

[brookxu]

From: Chunguang Xu <brookxu@xxxxxxxxxxx>

Before the wraparound occurs, the value of io_ticks should
be monotonically increasing, but we sometimes find that io_ticks
will become smaller, which leads to abnormal values in monitoring
tools. On the IO submission path, blk_account_io_start() may
interrupt the system interruption. When the interruption returns,
the value of part->stamp may have been updated by other cores, so
the time value now collected before the interruption may be less
than part->stamp, and then make the calculated value of io_ticks
become smaller. Therefore, when now is less than part->stamp, we
should do nothing.

Signed-off-by: Chunguang Xu <brookxu@xxxxxxxxxxx>
---
 block/blk-core.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/block/blk-core.c b/block/blk-core.c
index 514838c..a5d1cc2 100644
--- a/block/blk-core.c
+++ b/block/blk-core.c
@@ -1243,7 +1243,7 @@ static void update_io_ticks(struct block_device *part, unsigned long now,
 	unsigned long stamp;
 again:
 	stamp = READ_ONCE(part->bd_stamp);
-	if (unlikely(stamp != now)) {
+	if (unlikely(time_after(now, stamp)) {
 		if (likely(cmpxchg(&part->bd_stamp, stamp, now) == stamp))
 			__part_stat_add(part, io_ticks, end ? now - stamp : 1);
 	}
-- 
1.8.3.1