If peers are "simultaneously" told to disconnect from each other,
either explicitly, or implicitly by taking down the resource,
with bad timing, one side may see its disconnect "fail" with
a result of "state change failed by peer", and interpret this as
"please oudate yourself".
Try to catch this by checking for current connection status,
and possibly retry as local-only state change instead.
Signed-off-by: Lars Ellenberg <lars.ellenb...@linbit.com>
---
drivers/block/drbd/drbd_nl.c | 7 +++++++
1 file changed, 7 insertions(+)
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 1958eb33b643..82915880c5e9 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2711,8 +2711,10 @@ int drbd_adm_connect(struct sk_buff *skb, struct
genl_info *info)
static enum drbd_state_rv conn_try_disconnect(struct drbd_connection
*connection, bool force)
{
+ enum drbd_conns cstate;
enum drbd_state_rv rv;
+repeat:
rv = conn_request_state(connection, NS(conn, C_DISCONNECTING),
force ? CS_HARD : 0);
@@ -2730,6 +2732,11 @@ static enum drbd_state_rv conn_try_disconnect(struct
drbd_connection *connection
break;
case SS_CW_FAILED_BY_PEER:
+ spin_lock_irq(&connection->resource->req_lock);
+ cstate = connection->cstate;
+ spin_unlock_irq(&connection->resource->req_lock);
+ if (cstate <= C_WF_CONNECTION)
+ goto repeat;
/* The peer probably wants to see us outdated. */
rv = conn_request_state(connection, NS2(conn, C_DISCONNECTING,
disk, D_OUTDATED), 0);
--
2.17.1
