iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

drbd: fix drbd epoch write count for ahead/behind mode

Browse Source 
The sanity check when receiving P_BARRIER_ACK does expect all write
requests with a given req->epoch to have been either all replicated,
or all not replicated.

Because req->epoch was assigned before calling maybe_pull_ahead(),
this expectation was not met, leading to an off-by-one in the sanity
check, and further to a "Protocol Error".

Fix: move the call to maybe_pull_ahead() a few lines up,
and assign req->epoch only after that.

Signed-off-by: Philipp Reisner <philipp.reisner@linbit.com>
Signed-off-by: Lars Ellenberg <lars.ellenberg@linbit.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
This commit is contained in:
Lars Ellenberg
2013-03-27 14:08:45 +01:00
committed by Jens Axboe
parent ef57f9e6bb
commit 607f25e56e
1 changed files with 7 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
drivers/block/drbd/drbd_req.c
View File

@@ -865,8 +865,10 @@ static void maybe_pull_ahead(struct drbd_conf *mdev)
bool congested = false; bool congested = false;
enum drbd_on_congestion on_congestion; enum drbd_on_congestion on_congestion;
rcu_read_lock();
nc = rcu_dereference(tconn->net_conf); nc = rcu_dereference(tconn->net_conf);
on_congestion = nc ? nc->on_congestion : OC_BLOCK; on_congestion = nc ? nc->on_congestion : OC_BLOCK;
rcu_read_unlock();
if (on_congestion == OC_BLOCK || if (on_congestion == OC_BLOCK ||
tconn->agreed_pro_version < 96) tconn->agreed_pro_version < 96)
return; return;
@@ -960,14 +962,8 @@ static int drbd_process_write_request(struct drbd_request *req)
struct drbd_conf *mdev = req->w.mdev; struct drbd_conf *mdev = req->w.mdev;
int remote, send_oos; int remote, send_oos;
rcu_read_lock();
remote = drbd_should_do_remote(mdev->state); remote = drbd_should_do_remote(mdev->state);
if (remote) {
maybe_pull_ahead(mdev);
remote = drbd_should_do_remote(mdev->state);
}
send_oos = drbd_should_send_out_of_sync(mdev->state); send_oos = drbd_should_send_out_of_sync(mdev->state);
rcu_read_unlock();
/* Need to replicate writes. Unless it is an empty flush, /* Need to replicate writes. Unless it is an empty flush,
* which is better mapped to a DRBD P_BARRIER packet, * which is better mapped to a DRBD P_BARRIER packet,
@@ -1087,9 +1083,13 @@ static void drbd_send_and_submit(struct drbd_conf *mdev, struct drbd_request *re
* but will re-aquire it before it returns here. * but will re-aquire it before it returns here.
* Needs to be before the check on drbd_suspended() */ * Needs to be before the check on drbd_suspended() */
complete_conflicting_writes(req); complete_conflicting_writes(req);
/* no more giving up req_lock from now on! */
/* check for congestion, and potentially stop sending
* full data updates, but start sending "dirty bits" only. */
maybe_pull_ahead(mdev);
} }
/* no more giving up req_lock from now on! */
if (drbd_suspended(mdev)) { if (drbd_suspended(mdev)) {
/* push back and retry: */ /* push back and retry: */