From 197296ffed71b7d5056d8618a07fec145b040303 Mon Sep 17 00:00:00 2001 From: Philipp Reisner Date: Mon, 26 Mar 2012 16:47:11 +0200 Subject: drbd: Delay/reject other state changes while establishing a connection Changes to the role and disk state should be delayed or rejected while we establish a connection. This is necessary, since the peer will base its resync decision on the UUIDs and the state we sent in the drbd_connect() function. The most prominent example for this race is becoming primary after sending state and UUIDs and before the state changes to C_WF_CONNECTION. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_main.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'drivers/block/drbd/drbd_main.c') diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index 519f286a4299..deccff3af774 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -841,6 +841,13 @@ is_valid_state_transition(struct drbd_conf *mdev, union drbd_state ns, if (ns.conn == os.conn && ns.conn == C_WF_REPORT_PARAMS) rv = SS_IN_TRANSIENT_STATE; + /* While establishing a connection only allow cstate to change. + Delay/refuse role changes, detach attach etc... */ + if (test_bit(STATE_SENT, &mdev->flags) && + !(os.conn == C_WF_REPORT_PARAMS || + (ns.conn == C_WF_REPORT_PARAMS && os.conn == C_WF_CONNECTION))) + rv = SS_IN_TRANSIENT_STATE; + if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) && os.conn < C_CONNECTED) rv = SS_NEED_CONNECTION; @@ -1668,6 +1675,12 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os, if (os.disk < D_UP_TO_DATE && os.conn >= C_SYNC_SOURCE && ns.conn == C_CONNECTED) drbd_send_state(mdev, ns); + /* Wake up role changes, that were delayed because of connection establishing */ + if (os.conn == C_WF_REPORT_PARAMS && ns.conn != C_WF_REPORT_PARAMS) { + clear_bit(STATE_SENT, &mdev->flags); + wake_up(&mdev->state_wait); + } + /* This triggers bitmap writeout of potentially still unwritten pages * if the resync finished cleanly, or aborted because of peer disk * failure, or because of connection loss. -- cgit v1.2.3-55-g7522