[PATCH] md/raid1: protect head_position for read balance

From: Chen Cheng <[email protected]>

KCSAN reports a data race between raid1_end_read_request() and
raid1_read_request().

The completion path updates conf->mirrors[disk].head_position in
update_head_pos() without a lock, while the read-balance heuristic reads
the same field locklessly in is_sequential() and choose_best_rdev().

KCSAN report:
=========================
  BUG: KCSAN: data-race in raid1_end_read_request / raid1_read_request

  write to 0xffff8f0306ba7868 of 8 bytes by interrupt on cpu 9:
    raid1_end_read_request+0xb5/0x440
    bio_endio+0x3c9/0x3e0
    blk_update_request+0x257/0x770
    scsi_end_request+0x4d/0x520
    scsi_io_completion+0x6f/0x990
    scsi_finish_command+0x188/0x280
    scsi_complete+0xac/0x160
    blk_complete_reqs+0x8e/0xb0
    blk_done_softirq+0x1d/0x30
   [...]

  read to 0xffff8f0306ba7868 of 8 bytes by task 667002 on cpu 11:
    raid1_read_request+0x497/0x1a10
    raid1_make_request+0xdf/0x1950
    md_handle_request+0x2c5/0x700
    md_submit_bio+0x126/0x320
    __submit_bio+0x2ec/0x3a0
    submit_bio_noacct_nocheck+0x572/0x890
   [...]

  value changed: 0x0000000000000078 -> 0x00000000005fe448

Signed-off-by: Chen Cheng <[email protected]>
---
 drivers/md/raid1.c | 9 +++++----
 1 file changed, 5 insertions(+), 4 deletions(-)

diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index 5b9368bd9e70..4cdf4484cab6 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -357,12 +357,12 @@ static void raid_end_bio_io(struct r1bio *r1_bio)
  */
 static inline void update_head_pos(int disk, struct r1bio *r1_bio)
 {
 	struct r1conf *conf = r1_bio->mddev->private;
 
-	conf->mirrors[disk].head_position =
-		r1_bio->sector + (r1_bio->sectors);
+	WRITE_ONCE(conf->mirrors[disk].head_position,
+		   r1_bio->sector + r1_bio->sectors);
 }
 
 /*
  * Find the disk number which triggered given bio
  */
@@ -735,11 +735,11 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
 
 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 ||
-	       conf->mirrors[disk].head_position == 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.
@@ -812,11 +812,12 @@ static int choose_best_rdev(struct r1conf *conf, struct r1bio *r1_bio)
 		/* At least two disks to choose from so failfast is OK */
 		if (ctl.readable_disks++ == 1)
 			set_bit(R1BIO_FailFast, &r1_bio->state);
 
 		pending = atomic_read(&rdev->nr_pending);
-		dist = abs(r1_bio->sector - conf->mirrors[disk].head_position);
+		dist = abs(r1_bio->sector -
+			   READ_ONCE(conf->mirrors[disk].head_position));
 
 		/* Don't change to another disk for sequential reads */
 		if (is_sequential(conf, disk, r1_bio)) {
 			if (!should_choose_next(conf, disk))
 				return disk;
-- 
2.54.0