Commit 4a99c3d9 authored by David Teigland's avatar David Teigland Committed by Steven Whitehouse
Browse files

[DLM] reject replies to old requests



When recoveries are aborted by other recoveries we can get replies to
status or names requests that we've given up on.  This can cause problems
if we're making another request and receive an old reply.  Add a sequence
number to status/names requests and reject replies that don't match.  A
field already exists for the seq number that's used in other message
types.

Signed-off-by: default avatarDavid Teigland <teigland@redhat.com>
Signed-off-by: default avatarSteven Whitehouse <swhiteho@redhat.com>
parent faa0f267
Loading
Loading
Loading
Loading
+1 −0
Original line number Diff line number Diff line
@@ -468,6 +468,7 @@ struct dlm_ls {
	struct mutex		ls_requestqueue_mutex;
	char			*ls_recover_buf;
	int			ls_recover_nodeid; /* for debugging */
	uint64_t		ls_rcom_seq;
	struct list_head	ls_recover_list;
	spinlock_t		ls_recover_list_lock;
	int			ls_recover_list_count;
+16 −4
Original line number Diff line number Diff line
@@ -108,6 +108,7 @@ int dlm_rcom_status(struct dlm_ls *ls, int nodeid)
	error = create_rcom(ls, nodeid, DLM_RCOM_STATUS, 0, &rc, &mh);
	if (error)
		goto out;
	rc->rc_id = ++ls->ls_rcom_seq;

	send_rcom(ls, mh, rc);

@@ -140,19 +141,30 @@ static void receive_rcom_status(struct dlm_ls *ls, struct dlm_rcom *rc_in)
			    sizeof(struct rcom_config), &rc, &mh);
	if (error)
		return;
	rc->rc_id = rc_in->rc_id;
	rc->rc_result = dlm_recover_status(ls);
	make_config(ls, (struct rcom_config *) rc->rc_buf);

	send_rcom(ls, mh, rc);
}

static void receive_rcom_status_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
	if (rc_in->rc_id != ls->ls_rcom_seq) {
		log_debug(ls, "reject old reply %d got %llx wanted %llx",
			  rc_in->rc_type, rc_in->rc_id, ls->ls_rcom_seq);
		return;
	}
	memcpy(ls->ls_recover_buf, rc_in, rc_in->rc_header.h_length);
	set_bit(LSFL_RCOM_READY, &ls->ls_flags);
	wake_up(&ls->ls_wait_general);
}

static void receive_rcom_status_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
	receive_sync_reply(ls, rc_in);
}

int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
{
	struct dlm_rcom *rc;
@@ -173,6 +185,7 @@ int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
	if (error)
		goto out;
	memcpy(rc->rc_buf, last_name, last_len);
	rc->rc_id = ++ls->ls_rcom_seq;

	send_rcom(ls, mh, rc);

@@ -209,6 +222,7 @@ static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in)
	error = create_rcom(ls, nodeid, DLM_RCOM_NAMES_REPLY, outlen, &rc, &mh);
	if (error)
		return;
	rc->rc_id = rc_in->rc_id;

	dlm_copy_master_names(ls, rc_in->rc_buf, inlen, rc->rc_buf, outlen,
			      nodeid);
@@ -217,9 +231,7 @@ static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in)

static void receive_rcom_names_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
{
	memcpy(ls->ls_recover_buf, rc_in, rc_in->rc_header.h_length);
	set_bit(LSFL_RCOM_READY, &ls->ls_flags);
	wake_up(&ls->ls_wait_general);
	receive_sync_reply(ls, rc_in);
}

int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid)