Merge branch 'net-smc-add-failover-processing'

Karsten Graul says:

====================
net/smc: add failover processing

This patch series adds the actual SMC-R link failover processing and
improved link group termination. There will be one more (very small)
series after this which will complete the SMC-R link failover support.
====================

Signed-off-by: David S. Miller <[email protected]>

Author: davem330

net/smc/af_smc.c

@@ -390,6 +390,7 @@ static int smcr_clnt_conf_first_link(struct smc_sock *smc)
 				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
+	smc_llc_save_peer_uid(qentry);
 	rc = smc_llc_eval_conf_link(qentry, SMC_LLC_REQ);
 	smc_llc_flow_qentry_del(&link->lgr->llc_flow_lcl);
 	if (rc)
@@ -1056,6 +1057,7 @@ static int smcr_serv_conf_first_link(struct smc_sock *smc)
 				      SMC_CLC_DECLINE, CLC_WAIT_TIME_SHORT);
 		return rc == -EAGAIN ? SMC_CLC_DECL_TIMEOUT_CL : rc;
 	}
+	smc_llc_save_peer_uid(qentry);
 	rc = smc_llc_eval_conf_link(qentry, SMC_LLC_RESP);
 	smc_llc_flow_qentry_del(&link->lgr->llc_flow_lcl);
 	if (rc)

net/smc/smc.h

@@ -143,6 +143,9 @@ struct smc_connection {
 						 * .prod cf. TCP snd_nxt
 						 * .cons cf. TCP sends ack
 						 */
+	union smc_host_cursor	local_tx_ctrl_fin;
+						/* prod crsr - confirmed by peer
+						 */
 	union smc_host_cursor	tx_curs_prep;	/* tx - prepared data
 						 * snd_max..wmem_alloc
 						 */
@@ -154,6 +157,7 @@ struct smc_connection {
 						 */
 	atomic_t		sndbuf_space;	/* remaining space in sndbuf */
 	u16			tx_cdc_seq;	/* sequence # for CDC send */
+	u16			tx_cdc_seq_fin;	/* sequence # - tx completed */
 	spinlock_t		send_lock;	/* protect wr_sends */
 	struct delayed_work	tx_work;	/* retry of smc_cdc_msg_send */
 	u32			tx_off;		/* base offset in peer rmb */
@@ -184,12 +188,14 @@ struct smc_connection {
 	spinlock_t		acurs_lock;	/* protect cursors */
 #endif
 	struct work_struct	close_work;	/* peer sent some closing */
+	struct work_struct	abort_work;	/* abort the connection */
 	struct tasklet_struct	rx_tsklet;	/* Receiver tasklet for SMC-D */
 	u8			rx_off;		/* receive offset:
 						 * 0 for SMC-R, 32 for SMC-D
 						 */
 	u64			peer_token;	/* SMC-D token of peer */
 	u8			killed : 1;	/* abnormal termination */
+	u8			out_of_sync : 1; /* out of sync with peer */
 };
 
 struct smc_sock {				/* smc sock container */

net/smc/smc_cdc.c

@@ -47,17 +47,20 @@ static void smc_cdc_tx_handler(struct smc_wr_tx_pend_priv *pnd_snd,
 		/* guarantee 0 <= sndbuf_space <= sndbuf_desc->len */
 		smp_mb__after_atomic();
 		smc_curs_copy(&conn->tx_curs_fin, &cdcpend->cursor, conn);
+		smc_curs_copy(&conn->local_tx_ctrl_fin, &cdcpend->p_cursor,
+			      conn);
+		conn->tx_cdc_seq_fin = cdcpend->ctrl_seq;
 	}
 	smc_tx_sndbuf_nonfull(smc);
 	bh_unlock_sock(&smc->sk);
 }
 
 int smc_cdc_get_free_slot(struct smc_connection *conn,
+			  struct smc_link *link,
 			  struct smc_wr_buf **wr_buf,
 			  struct smc_rdma_wr **wr_rdma_buf,
 			  struct smc_cdc_tx_pend **pend)
 {
-	struct smc_link *link = conn->lnk;
 	int rc;
 
 	rc = smc_wr_tx_get_free_slot(link, smc_cdc_tx_handler, wr_buf,
@@ -104,22 +107,64 @@ int smc_cdc_msg_send(struct smc_connection *conn,
 	if (!rc) {
 		smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn);
 		conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0;
+	} else {
+		conn->tx_cdc_seq--;
+		conn->local_tx_ctrl.seqno = conn->tx_cdc_seq;
 	}
 
 	return rc;
 }
 
+/* send a validation msg indicating the move of a conn to an other QP link */
+int smcr_cdc_msg_send_validation(struct smc_connection *conn)
+{
+	struct smc_host_cdc_msg *local = &conn->local_tx_ctrl;
+	struct smc_link *link = conn->lnk;
+	struct smc_cdc_tx_pend *pend;
+	struct smc_wr_buf *wr_buf;
+	struct smc_cdc_msg *peer;
+	int rc;
+
+	rc = smc_cdc_get_free_slot(conn, link, &wr_buf, NULL, &pend);
+	if (rc)
+		return rc;
+
+	peer = (struct smc_cdc_msg *)wr_buf;
+	peer->common.type = local->common.type;
+	peer->len = local->len;
+	peer->seqno = htons(conn->tx_cdc_seq_fin); /* seqno last compl. tx */
+	peer->token = htonl(local->token);
+	peer->prod_flags.failover_validation = 1;
+
+	rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend);
+	return rc;
+}
+
 static int smcr_cdc_get_slot_and_msg_send(struct smc_connection *conn)
 {
 	struct smc_cdc_tx_pend *pend;
 	struct smc_wr_buf *wr_buf;
+	struct smc_link *link;
+	bool again = false;
 	int rc;
 
-	rc = smc_cdc_get_free_slot(conn, &wr_buf, NULL, &pend);
+again:
+	link = conn->lnk;
+	rc = smc_cdc_get_free_slot(conn, link, &wr_buf, NULL, &pend);
 	if (rc)
 		return rc;
 
 	spin_lock_bh(&conn->send_lock);
+	if (link != conn->lnk) {
+		/* link of connection changed, try again one time*/
+		spin_unlock_bh(&conn->send_lock);
+		smc_wr_tx_put_slot(link,
+				   (struct smc_wr_tx_pend_priv *)pend);
+		if (again)
+			return -ENOLINK;
+		again = true;
+		goto again;
+	}
 	rc = smc_cdc_msg_send(conn, wr_buf, pend);
 	spin_unlock_bh(&conn->send_lock);
 	return rc;
@@ -237,6 +282,28 @@ static void smc_cdc_handle_urg_data_arrival(struct smc_sock *smc,
 	sk_send_sigurg(&smc->sk);
 }
 
+static void smc_cdc_msg_validate(struct smc_sock *smc, struct smc_cdc_msg *cdc,
+				 struct smc_link *link)
+{
+	struct smc_connection *conn = &smc->conn;
+	u16 recv_seq = ntohs(cdc->seqno);
+	s16 diff;
+
+	/* check that seqnum was seen before */
+	diff = conn->local_rx_ctrl.seqno - recv_seq;
+	if (diff < 0) { /* diff larger than 0x7fff */
+		/* drop connection */
+		conn->out_of_sync = 1;	/* prevent any further receives */
+		spin_lock_bh(&conn->send_lock);
+		conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1;
+		conn->lnk = link;
+		spin_unlock_bh(&conn->send_lock);
+		sock_hold(&smc->sk); /* sock_put in abort_work */
+		if (!schedule_work(&conn->abort_work))
+			sock_put(&smc->sk);
+	}
+}
+
 static void smc_cdc_msg_recv_action(struct smc_sock *smc,
 				    struct smc_cdc_msg *cdc)
 {
@@ -367,16 +434,19 @@ static void smc_cdc_rx_handler(struct ib_wc *wc, void *buf)
 	read_lock_bh(&lgr->conns_lock);
 	conn = smc_lgr_find_conn(ntohl(cdc->token), lgr);
 	read_unlock_bh(&lgr->conns_lock);
-	if (!conn)
+	if (!conn || conn->out_of_sync)
 		return;
 	smc = container_of(conn, struct smc_sock, conn);
 
-	if (!cdc->prod_flags.failover_validation) {
-		if (smc_cdc_before(ntohs(cdc->seqno),
-				   conn->local_rx_ctrl.seqno))
-			/* received seqno is old */
-			return;
+	if (cdc->prod_flags.failover_validation) {
+		smc_cdc_msg_validate(smc, cdc, link);
+		return;
 	}
+	if (smc_cdc_before(ntohs(cdc->seqno),
+			   conn->local_rx_ctrl.seqno))
+		/* received seqno is old */
+		return;
+
 	smc_cdc_msg_recv(smc, cdc);
 }
 

net/smc/smc_cdc.h

@@ -304,6 +304,7 @@ struct smc_cdc_tx_pend {
 };
 
 int smc_cdc_get_free_slot(struct smc_connection *conn,
+			  struct smc_link *link,
 			  struct smc_wr_buf **wr_buf,
 			  struct smc_rdma_wr **wr_rdma_buf,
 			  struct smc_cdc_tx_pend **pend);
@@ -312,6 +313,7 @@ int smc_cdc_msg_send(struct smc_connection *conn, struct smc_wr_buf *wr_buf,
 		     struct smc_cdc_tx_pend *pend);
 int smc_cdc_get_slot_and_msg_send(struct smc_connection *conn);
 int smcd_cdc_msg_send(struct smc_connection *conn);
+int smcr_cdc_msg_send_validation(struct smc_connection *conn);
 int smc_cdc_init(void) __init;
 void smcd_cdc_rx_init(struct smc_connection *conn);