aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/md.c
diff options
context:
space:
mode:
authorGravatar Yu Kuai <yukuai3@huawei.com> 2024-03-05 15:23:05 +0800
committerGravatar Song Liu <song@kernel.org> 2024-03-05 12:53:33 -0800
commit41425f96d7aa59bc865f60f5dda3d7697b555677 (patch)
tree40a9ad8d2d7ac227f6d6cec9447b5d08ada59b0a /drivers/md/md.c
parentdm-raid: add a new helper prepare_suspend() in md_personality (diff)
downloadlinux-41425f96d7aa59bc865f60f5dda3d7697b555677.tar.gz
linux-41425f96d7aa59bc865f60f5dda3d7697b555677.tar.bz2
linux-41425f96d7aa59bc865f60f5dda3d7697b555677.zip
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
Diffstat (limited to 'drivers/md/md.c')
-rw-r--r--drivers/md/md.c24
1 files changed, 22 insertions, 2 deletions
diff --git a/drivers/md/md.c b/drivers/md/md.c
index 167db7744239..64d544f09295 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -366,7 +366,7 @@ static bool is_suspended(struct mddev *mddev, struct bio *bio)
return true;
}
-void md_handle_request(struct mddev *mddev, struct bio *bio)
+bool md_handle_request(struct mddev *mddev, struct bio *bio)
{
check_suspended:
if (is_suspended(mddev, bio)) {
@@ -374,7 +374,7 @@ check_suspended:
/* Bail out if REQ_NOWAIT is set for the bio */
if (bio->bi_opf & REQ_NOWAIT) {
bio_wouldblock_error(bio);
- return;
+ return true;
}
for (;;) {
prepare_to_wait(&mddev->sb_wait, &__wait,
@@ -390,10 +390,13 @@ check_suspended:
if (!mddev->pers->make_request(mddev, bio)) {
percpu_ref_put(&mddev->active_io);
+ if (!mddev->gendisk && mddev->pers->prepare_suspend)
+ return false;
goto check_suspended;
}
percpu_ref_put(&mddev->active_io);
+ return true;
}
EXPORT_SYMBOL(md_handle_request);
@@ -8733,6 +8736,23 @@ void md_account_bio(struct mddev *mddev, struct bio **bio)
}
EXPORT_SYMBOL_GPL(md_account_bio);
+void md_free_cloned_bio(struct bio *bio)
+{
+ struct md_io_clone *md_io_clone = bio->bi_private;
+ struct bio *orig_bio = md_io_clone->orig_bio;
+ struct mddev *mddev = md_io_clone->mddev;
+
+ if (bio->bi_status && !orig_bio->bi_status)
+ orig_bio->bi_status = bio->bi_status;
+
+ if (md_io_clone->start_time)
+ bio_end_io_acct(orig_bio, md_io_clone->start_time);
+
+ bio_put(bio);
+ percpu_ref_put(&mddev->active_io);
+}
+EXPORT_SYMBOL_GPL(md_free_cloned_bio);
+
/* md_allow_write(mddev)
* Calling this ensures that the array is marked 'active' so that writes
* may proceed without blocking. It is important to call this before