aboutsummaryrefslogtreecommitdiff
path: root/drivers/block/drbd/drbd_nl.c
diff options
context:
space:
mode:
authorLars Ellenberg <lars.ellenberg@linbit.com>2012-05-07 12:00:56 +0200
committerPhilipp Reisner <philipp.reisner@linbit.com>2012-11-08 16:58:27 +0100
commit5016b82a49eb06cbe2002db7bd8a5501ba4ef6d1 (patch)
tree63b88abacaf6048a64531daced95ef47b6888e03 /drivers/block/drbd/drbd_nl.c
parent07be15b12c41dbc5ceae130be2e0b655f7611691 (diff)
downloadvexpress-lsk-5016b82a49eb06cbe2002db7bd8a5501ba4ef6d1.tar.gz
drbd: fix race between drbdadm invalidate/verify and finishing resync
When a resync or online verify is finished or aborted, drbd does a bulk write-out of changed bitmap pages. If *in that very moment* a new verify or resync is triggered, this can race: ASSERT( !test_bit(BITMAP_IO, &mdev->flags) ) in drbd_main.c FIXME going to queue 'set_n_write from StartingSync' but 'write from resync_finished' still pending? and similar. This can be observed with e.g. tight invalidate loops in test scripts, and probably has no real-life implication. Still, that race can be solved by first quiescen the device, before starting a new resync or verify. Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com> Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Diffstat (limited to 'drivers/block/drbd/drbd_nl.c')
-rw-r--r--drivers/block/drbd/drbd_nl.c10
1 files changed, 10 insertions, 0 deletions
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 3a8fa89f673..cbd45de533c 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2372,6 +2372,7 @@ int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
/* If there is still bitmap IO pending, probably because of a previous
* resync just being finished, wait for it before requesting a new resync. */
+ drbd_suspend_io(mdev);
wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T), CS_ORDERED);
@@ -2390,6 +2391,7 @@ int drbd_adm_invalidate(struct sk_buff *skb, struct genl_info *info)
retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_T));
}
+ drbd_resume_io(mdev);
out:
drbd_adm_finish(info, retcode);
@@ -2435,6 +2437,11 @@ int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
mdev = adm_ctx.mdev;
+ /* If there is still bitmap IO pending, probably because of a previous
+ * resync just being finished, wait for it before requesting a new resync. */
+ drbd_suspend_io(mdev);
+ wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
+
retcode = _drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S), CS_ORDERED);
if (retcode < SS_SUCCESS) {
if (retcode == SS_NEED_CONNECTION && mdev->state.role == R_PRIMARY) {
@@ -2450,6 +2457,7 @@ int drbd_adm_invalidate_peer(struct sk_buff *skb, struct genl_info *info)
} else
retcode = drbd_request_state(mdev, NS(conn, C_STARTING_SYNC_S));
}
+ drbd_resume_io(mdev);
out:
drbd_adm_finish(info, retcode);
@@ -2903,8 +2911,10 @@ int drbd_adm_start_ov(struct sk_buff *skb, struct genl_info *info)
}
/* If there is still bitmap IO pending, e.g. previous resync or verify
* just being finished, wait for it before requesting a new resync. */
+ drbd_suspend_io(mdev);
wait_event(mdev->misc_wait, !test_bit(BITMAP_IO, &mdev->flags));
retcode = drbd_request_state(mdev,NS(conn,C_VERIFY_S));
+ drbd_resume_io(mdev);
out:
drbd_adm_finish(info, retcode);
return 0;