drbd: Consider the disk-timeout also for meta-data IO operations

If the backing device is already frozen during attach, we failed
to recognize that. The current disk-timeout code works on top
of the drbd_request objects. During attach we do not allow IO
and therefore never generate a drbd_request object but block
before that in drbd_make_request().

This patch adds the timeout to all drbd_md_sync_page_io().

Before this patch we used to go from D_ATTACHING directly
to D_DISKLESS if IO failed during attach. We can no longer
do this since we have to stay in D_FAILED until all IO
ops issued to the backing device returned.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>

1 files changed, 15 insertions, 3 deletions

diff --git a/drivers/block/drbd/drbd_actlog.c b/drivers/block/drbd/drbd_actlog.c
index d69fb7d61817..b2355994a4d6 100644
--- a/drivers/block/drbd/drbd_actlog.c
+++ b/drivers/block/drbd/drbd_actlog.c
@@ -129,9 +129,21 @@ static bool md_io_allowed(struct drbd_conf *mdev)
         return ds >= D_NEGOTIATING || ds == D_ATTACHING;
 }
 
-void wait_until_done_or_disk_failure(struct drbd_conf *mdev, unsigned int *done)
+void wait_until_done_or_disk_failure(struct drbd_conf *mdev, struct drbd_backing_dev *bdev,
+                                     unsigned int *done)
 {
-        wait_event(mdev->misc_wait, *done || !md_io_allowed(mdev));
+        long dt;
+
+        rcu_read_lock();
+        dt = rcu_dereference(bdev->disk_conf)->disk_timeout;
+        rcu_read_unlock();
+        dt = dt * HZ / 10;
+        if (dt == 0)
+                dt = MAX_SCHEDULE_TIMEOUT;
+
+        dt = wait_event_timeout(mdev->misc_wait, *done || !md_io_allowed(mdev), dt);
+        if (dt == 0)
+                dev_err(DEV, "meta-data IO operation timed out\n");
 }
 
 static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
@@ -171,7 +183,7 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
                 bio_endio(bio, -EIO);
         else
                 submit_bio(rw, bio);
-        wait_until_done_or_disk_failure(mdev, &mdev->md_io.done);
+        wait_until_done_or_disk_failure(mdev, bdev, &mdev->md_io.done);
         if (bio_flagged(bio, BIO_UPTODATE))
                 err = mdev->md_io.error;