dm-raid456, md/raid456: fix a deadlock for dm-raid456 while io concurrent with reshape

For raid456, if reshape is still in progress, then IO across reshape
position will wait for reshape to make progress. However, for dm-raid,
in following cases reshape will never make progress hence IO will hang:

1) the array is read-only;
2) MD_RECOVERY_WAIT is set;
3) MD_RECOVERY_FROZEN is set;

After commit c467e97f079f ("md/raid6: use valid sector values to determine
if an I/O should wait on the reshape") fix the problem that IO across
reshape position doesn't wait for reshape, the dm-raid test
shell/lvconvert-raid-reshape.sh start to hang:

[root@fedora ~]# cat /proc/979/stack
[<0>] wait_woken+0x7d/0x90
[<0>] raid5_make_request+0x929/0x1d70 [raid456]
[<0>] md_handle_request+0xc2/0x3b0 [md_mod]
[<0>] raid_map+0x2c/0x50 [dm_raid]
[<0>] __map_bio+0x251/0x380 [dm_mod]
[<0>] dm_submit_bio+0x1f0/0x760 [dm_mod]
[<0>] __submit_bio+0xc2/0x1c0
[<0>] submit_bio_noacct_nocheck+0x17f/0x450
[<0>] submit_bio_noacct+0x2bc/0x780
[<0>] submit_bio+0x70/0xc0
[<0>] mpage_readahead+0x169/0x1f0
[<0>] blkdev_readahead+0x18/0x30
[<0>] read_pages+0x7c/0x3b0
[<0>] page_cache_ra_unbounded+0x1ab/0x280
[<0>] force_page_cache_ra+0x9e/0x130
[<0>] page_cache_sync_ra+0x3b/0x110
[<0>] filemap_get_pages+0x143/0xa30
[<0>] filemap_read+0xdc/0x4b0
[<0>] blkdev_read_iter+0x75/0x200
[<0>] vfs_read+0x272/0x460
[<0>] ksys_read+0x7a/0x170
[<0>] __x64_sys_read+0x1c/0x30
[<0>] do_syscall_64+0xc6/0x230
[<0>] entry_SYSCALL_64_after_hwframe+0x6c/0x74

This is because reshape can't make progress.

For md/raid, the problem doesn't exist because register new sync_thread
doesn't rely on the IO to be done any more:

1) If array is read-only, it can switch to read-write by ioctl/sysfs;
2) md/raid never set MD_RECOVERY_WAIT;
3) If MD_RECOVERY_FROZEN is set, mddev_suspend() doesn't hold
   'reconfig_mutex', hence it can be cleared and reshape can continue by
   sysfs api 'sync_action'.

However, I'm not sure yet how to avoid the problem in dm-raid yet. This
patch on the one hand make sure raid_message() can't change
sync_thread() through raid_message() after presuspend(), on the other
hand detect the above 3 cases before wait for IO do be done in
dm_suspend(), and let dm-raid requeue those IO.

Cc: stable@vger.kernel.org # v6.7+
Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Signed-off-by: Xiao Ni <xni@redhat.com>
Acked-by: Mike Snitzer <snitzer@kernel.org>
Signed-off-by: Song Liu <song@kernel.org>
Link: https://lore.kernel.org/r/20240305072306.2562024-9-yukuai1@huaweicloud.com

1 files changed, 20 insertions, 2 deletions

diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
index 7d48943acd57..ea45f777691c 100644
--- a/drivers/md/dm-raid.c
+++ b/drivers/md/dm-raid.c
@@ -213,6 +213,7 @@ struct raid_dev {
 #define RT_FLAG_RS_IN_SYNC		6
 #define RT_FLAG_RS_RESYNCING		7
 #define RT_FLAG_RS_GROW			8
+#define RT_FLAG_RS_FROZEN		9
 
 /* Array elements of 64 bit needed for rebuild/failed disk bits */
 #define DISKS_ARRAY_ELEMS ((MAX_RAID_DEVICES + (sizeof(uint64_t) * 8 - 1)) / sizeof(uint64_t) / 8)
@@ -3340,7 +3341,8 @@ static int raid_map(struct dm_target *ti, struct bio *bio)
 	if (unlikely(bio_end_sector(bio) > mddev->array_sectors))
 		return DM_MAPIO_REQUEUE;
 
-	md_handle_request(mddev, bio);
+	if (unlikely(!md_handle_request(mddev, bio)))
+		return DM_MAPIO_REQUEUE;
 
 	return DM_MAPIO_SUBMITTED;
 }
@@ -3724,7 +3726,8 @@ static int raid_message(struct dm_target *ti, unsigned int argc, char **argv,
 	if (!mddev->pers || !mddev->pers->sync_request)
 		return -EINVAL;
 
-	if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags))
+	if (test_bit(RT_FLAG_RS_SUSPENDED, &rs->runtime_flags) ||
+	    test_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags))
 		return -EBUSY;
 
 	if (!strcasecmp(argv[0], "frozen")) {
@@ -3808,6 +3811,12 @@ static void raid_presuspend(struct dm_target *ti)
 	struct raid_set *rs = ti->private;
 	struct mddev *mddev = &rs->md;
 
+	/*
+	 * From now on, disallow raid_message() to change sync_thread until
+	 * resume, raid_postsuspend() is too late.
+	 */
+	set_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+
 	if (!reshape_interrupted(mddev))
 		return;
 
@@ -3820,6 +3829,13 @@ static void raid_presuspend(struct dm_target *ti)
 		mddev->pers->prepare_suspend(mddev);
 }
 
+static void raid_presuspend_undo(struct dm_target *ti)
+{
+	struct raid_set *rs = ti->private;
+
+	clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+}
+
 static void raid_postsuspend(struct dm_target *ti)
 {
 	struct raid_set *rs = ti->private;
@@ -4085,6 +4101,7 @@ static void raid_resume(struct dm_target *ti)
 
 		WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery));
 		WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
+		clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
 		mddev_lock_nointr(mddev);
 		mddev->ro = 0;
 		mddev->in_sync = 0;
@@ -4105,6 +4122,7 @@ static struct target_type raid_target = {
 	.iterate_devices = raid_iterate_devices,
 	.io_hints = raid_io_hints,
 	.presuspend = raid_presuspend,
+	.presuspend_undo = raid_presuspend_undo,
 	.postsuspend = raid_postsuspend,
 	.preresume = raid_preresume,
 	.resume = raid_resume,