drbd: Fix disconnect to keep the peer disk state if connection breaks during operation
The issue was that if the connection broke while we did the
gracefull state change to C_DISCONNECTING (C_TEARDOWN), then
we returned a success code from the state engine. (SS_CW_NO_NEED)
The result of that is that we missed to call the fence-peer
script in such a case.
Fixed that by introducing a new error code (SS_OUTDATE_WO_CONN).
This one should never reach back into user space.
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>
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 56bafdc..39e9a91 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -2198,8 +2198,11 @@
return SS_SUCCESS;
case SS_PRIMARY_NOP:
/* Our state checking code wants to see the peer outdated. */
- rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING,
- pdsk, D_OUTDATED), CS_VERBOSE);
+ rv = conn_request_state(tconn, NS2(conn, C_DISCONNECTING, pdsk, D_OUTDATED), 0);
+
+ if (rv == SS_OUTDATE_WO_CONN) /* lost connection before graceful disconnect succeeded */
+ rv = conn_request_state(tconn, NS(conn, C_DISCONNECTING), CS_VERBOSE);
+
break;
case SS_CW_FAILED_BY_PEER:
/* The peer probably wants to see us outdated. */
diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
index 22e259f..90c5be2 100644
--- a/drivers/block/drbd/drbd_state.c
+++ b/drivers/block/drbd/drbd_state.c
@@ -642,6 +642,10 @@
&& os.conn < C_WF_REPORT_PARAMS)
rv = SS_NEED_CONNECTION; /* No NetworkFailure -> SyncTarget etc... */
+ if (ns.conn == C_DISCONNECTING && ns.pdsk == D_OUTDATED &&
+ os.conn < C_CONNECTED && os.pdsk > D_OUTDATED)
+ rv = SS_OUTDATE_WO_CONN;
+
return rv;
}
@@ -1748,13 +1752,9 @@
if (test_and_clear_bit(CONN_WD_ST_CHG_FAIL, &tconn->flags))
return SS_CW_FAILED_BY_PEER;
- rv = tconn->cstate != C_WF_REPORT_PARAMS ? SS_CW_NO_NEED : SS_UNKNOWN_ERROR;
-
- if (rv == SS_UNKNOWN_ERROR)
- rv = conn_is_valid_transition(tconn, mask, val, 0);
-
- if (rv == SS_SUCCESS)
- rv = SS_UNKNOWN_ERROR; /* cont waiting, otherwise fail. */
+ rv = conn_is_valid_transition(tconn, mask, val, 0);
+ if (rv == SS_SUCCESS && tconn->cstate == C_WF_REPORT_PARAMS)
+ rv = SS_UNKNOWN_ERROR; /* continue waiting */
return rv;
}
diff --git a/drivers/block/drbd/drbd_strings.c b/drivers/block/drbd/drbd_strings.c
index 9a664bd..58e08ff 100644
--- a/drivers/block/drbd/drbd_strings.c
+++ b/drivers/block/drbd/drbd_strings.c
@@ -89,6 +89,7 @@
[-SS_LOWER_THAN_OUTDATED] = "Disk state is lower than outdated",
[-SS_IN_TRANSIENT_STATE] = "In transient state, retry after next state change",
[-SS_CONCURRENT_ST_CHG] = "Concurrent state changes detected and aborted",
+ [-SS_OUTDATE_WO_CONN] = "Need a connection for a graceful disconnect/outdate peer",
[-SS_O_VOL_PEER_PRI] = "Other vol primary on peer not allowed by config",
};
diff --git a/include/linux/drbd.h b/include/linux/drbd.h
index 0c5a18e..3163307 100644
--- a/include/linux/drbd.h
+++ b/include/linux/drbd.h
@@ -319,7 +319,8 @@
SS_IN_TRANSIENT_STATE = -18, /* Retry after the next state change */
SS_CONCURRENT_ST_CHG = -19, /* Concurrent cluster side state change! */
SS_O_VOL_PEER_PRI = -20,
- SS_AFTER_LAST_ERROR = -21, /* Keep this at bottom */
+ SS_OUTDATE_WO_CONN = -21,
+ SS_AFTER_LAST_ERROR = -22, /* Keep this at bottom */
};
/* from drbd_strings.c */
