md: fix md_write_start() deadlock w/o metadata devices

If no metadata devices are configured on raid1/4/5/6/10
(e.g. via dm-raid), md_write_start() unconditionally waits
for superblocks to be written thus deadlocking.

Fix introduces mddev->has_superblocks bool, defines it in md_run()
and checks for it in md_write_start() to conditionally avoid waiting.

Once on it, check for non-existing superblocks in md_super_write().

Link: https://bugzilla.kernel.org/show_bug.cgi?id=198647
Fixes: cc27b0c78c796 ("md: fix deadlock between mddev_suspend() and md_write_start()")

Signed-off-by: Heinz Mauelshagen <heinzm@redhat.com>
Signed-off-by: Shaohua Li <sh.li@alibaba-inc.com>

diff --git a/drivers/md/md.c b/drivers/md/md.c
index bcf4ab9..9b73cf1 100644 (file)
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -801,6 +801,9 @@ void md_super_write(struct mddev *mddev, struct md_rdev *rdev,
        struct bio *bio;
        int ff = 0;
 
+       if (!page)
+               return;
+
        if (test_bit(Faulty, &rdev->flags))
                return;
 
@@ -5452,6 +5455,7 @@ int md_run(struct mddev *mddev)
         * the only valid external interface is through the md
         * device.
         */
+       mddev->has_superblocks = false;
        rdev_for_each(rdev, mddev) {
                if (test_bit(Faulty, &rdev->flags))
                        continue;
@@ -5465,6 +5469,9 @@ int md_run(struct mddev *mddev)
                                set_disk_ro(mddev->gendisk, 1);
                }
 
+               if (rdev->sb_page)
+                       mddev->has_superblocks = true;
+
                /* perform some consistency tests on the device.
                 * We don't want the data to overlap the metadata,
                 * Internal Bitmap issues have been handled elsewhere.
@@ -8065,6 +8072,7 @@ EXPORT_SYMBOL(md_done_sync);
 bool md_write_start(struct mddev *mddev, struct bio *bi)
 {
        int did_change = 0;
+
        if (bio_data_dir(bi) != WRITE)
                return true;
 
@@ -8097,6 +8105,8 @@ bool md_write_start(struct mddev *mddev, struct bio *bi)
        rcu_read_unlock();
        if (did_change)
                sysfs_notify_dirent_safe(mddev->sysfs_state);
+       if (!mddev->has_superblocks)
+               return true;
        wait_event(mddev->sb_wait,
                   !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) ||
                   mddev->suspended);

diff --git a/drivers/md/md.h b/drivers/md/md.h
index 58cd20a..fbc925c 100644 (file)
--- a/drivers/md/md.h
+++ b/drivers/md/md.h
@@ -468,6 +468,8 @@ struct mddev {
        void (*sync_super)(struct mddev *mddev, struct md_rdev *rdev);
        struct md_cluster_info          *cluster_info;
        unsigned int                    good_device_nr; /* good device num within cluster raid */
+
+       bool    has_superblocks:1;
 };
 
 enum recovery_flags {