[PATCH] md/raid1: protect sequential read hints for read balance

[PATCH] md/raid1: protect sequential read hints for read balance

[Chen Cheng]

From: Chen Cheng <chencheng@fnnas.com>

The patch just suppress KCSAN noise. No functional change.

KCSAN reports a race, point to update_read_sectors() update next_seq_sect vs.
read next_seq_sect.

Protect next_seq_sect and seq_start with READ_ONCE/WRITE_ONCE, otherwise,
read balance see stale sequential-read hints.

KCSAN report:
==============
 BUG: KCSAN: data-race in raid1_read_request / raid1_read_request

 write to 0xffff8e3a2d6736d0 of 8 bytes by task 593784 on cpu 10:
  raid1_read_request+0xe5a/0x19f0
  raid1_make_request+0xdf/0x1990
  md_handle_request+0x4a2/0xa40
  [...]

 read to 0xffff8e3a2d6736d0 of 8 bytes by task 593776 on cpu 11:
  raid1_read_request+0xe3f/0x19f0
  raid1_make_request+0xdf/0x1990
  md_handle_request+0x4a2/0xa40
  [...]

 value changed: 0x0000000000356368 -> 0x0000000000356370

Signed-off-by: Chen Cheng <chencheng@fnnas.com>
---
 drivers/md/raid1.c | 18 ++++++++++--------
 1 file changed, 10 insertions(+), 8 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 4cdf4484cab6..29b58583e381 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -602,13 +602,13 @@ static void update_read_sectors(struct r1conf *conf, int disk,
 				sector_t this_sector, int len)
 {
 	struct raid1_info *info = &conf->mirrors[disk];
 
 	atomic_inc(&info->rdev->nr_pending);
-	if (info->next_seq_sect != this_sector)
-		info->seq_start = this_sector;
-	info->next_seq_sect = this_sector + len;
+	if (READ_ONCE(info->next_seq_sect) != this_sector)
+		WRITE_ONCE(info->seq_start, this_sector);
+	WRITE_ONCE(info->next_seq_sect, this_sector + len);
 }
 
 static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
 			     int *max_sectors)
 {
@@ -733,31 +733,33 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
 	return bb_disk;
 }
 
 static bool is_sequential(struct r1conf *conf, int disk, struct r1bio *r1_bio)
 {
-	/* TODO: address issues with this check and concurrency. */
-	return conf->mirrors[disk].next_seq_sect == r1_bio->sector ||
+	return READ_ONCE(conf->mirrors[disk].next_seq_sect) == r1_bio->sector ||
 	       READ_ONCE(conf->mirrors[disk].head_position) == r1_bio->sector;
 }
 
 /*
  * If buffered sequential IO size exceeds optimal iosize, check if there is idle
  * disk. If yes, choose the idle disk.
  */
 static bool should_choose_next(struct r1conf *conf, int disk)
 {
 	struct raid1_info *mirror = &conf->mirrors[disk];
+	sector_t seq_start, next_seq_sect;
 	int opt_iosize;
 
 	if (!test_bit(Nonrot, &mirror->rdev->flags))
 		return false;
 
 	opt_iosize = bdev_io_opt(mirror->rdev->bdev) >> 9;
-	return opt_iosize > 0 && mirror->seq_start != MaxSector &&
-	       mirror->next_seq_sect > opt_iosize &&
-	       mirror->next_seq_sect - opt_iosize >= mirror->seq_start;
+	seq_start = READ_ONCE(mirror->seq_start);
+	next_seq_sect = READ_ONCE(mirror->next_seq_sect);
+	return opt_iosize > 0 && seq_start != MaxSector &&
+	       next_seq_sect > opt_iosize &&
+	       next_seq_sect - opt_iosize >= seq_start;
 }
 
 static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio)
 {
 	if (!rdev || test_bit(Faulty, &rdev->flags))
-- 
2.54.0