Merge branch 'rds-ha-failover-fixes'

Sowmini Varadhan says:

====================
RDS: TCP: HA/Failover fixes

This series contains a set of fixes for bugs exposed when
we ran the following in a loop between a test machine pair:

while (1); do
# modprobe rds-tcp on test nodes
# run rds-stress in bi-dir mode between test machine pair
# modprobe -r rds-tcp on test nodes
done

rds-stress in bi-dir mode will cause both nodes to initiate
RDS-TCP connections at almost the same instant, exposing the
bugs fixed in this series.

Without the fixes, rds-stress reports sporadic packet drops,
and packets arriving out of sequence. After the fixes,we have
been able to run the test overnight, without any issues.

Each patch has a detailed description of the root-cause fixed
by the patch.
====================

Signed-off-by: David S. Miller <[e-mail]>

net/rds/af_rds.c

···
 }
 module_exit(rds_exit);
 
+u32 rds_gen_num;
+
 static int rds_init(void)
 {
 	int ret;
+
+	net_get_random_once(&rds_gen_num, sizeof(rds_gen_num));
 
 	ret = rds_bind_lock_init();
 	if (ret)

net/rds/connection.c

···
 			kmem_cache_free(rds_conn_slab, conn);
 			conn = found;
 		} else {
+			conn->c_my_gen_num = rds_gen_num;
+			conn->c_peer_gen_num = 0;
 			hlist_add_head_rcu(&conn->c_hash_node, head);
 			rds_cong_add_conn(conn);
 			rds_conn_count++;
···
 	    !test_and_set_bit(RDS_RECONNECT_PENDING, &cp->cp_flags))
 		queue_delayed_work(rds_wq, &cp->cp_conn_w, 0);
 }
+EXPORT_SYMBOL_GPL(rds_conn_path_connect_if_down);
 
 void rds_conn_connect_if_down(struct rds_connection *conn)
 {

net/rds/message.c

···
 [RDS_EXTHDR_RDMA]	= sizeof(struct rds_ext_header_rdma),
 [RDS_EXTHDR_RDMA_DEST]	= sizeof(struct rds_ext_header_rdma_dest),
 [RDS_EXTHDR_NPATHS]	= sizeof(u16),
+[RDS_EXTHDR_GEN_NUM]	= sizeof(u32),
 };
 
 

net/rds/rds.h

···
 
 	struct rds_conn_path	c_path[RDS_MPATH_WORKERS];
 	wait_queue_head_t	c_hs_waitq; /* handshake waitq */
+
+	u32			c_my_gen_num;
+	u32			c_peer_gen_num;
 };
 
 static inline
···
 /* Extension header announcing number of paths.
  * Implicit length = 2 bytes.
  */
-#define RDS_EXTHDR_NPATHS	4
+#define RDS_EXTHDR_NPATHS	5
+#define RDS_EXTHDR_GEN_NUM	6
 
 #define __RDS_EXTHDR_MAX	16 /* for now */
 
···
 #define RDS_MSG_RETRANSMITTED	5
 #define RDS_MSG_MAPPED		6
 #define RDS_MSG_PAGEVEC		7
+#define RDS_MSG_FLUSH		8
 
 struct rds_message {
 	atomic_t		m_refcount;
···
 struct rds_message *rds_cong_update_alloc(struct rds_connection *conn);
 
 /* conn.c */
+extern u32 rds_gen_num;
 int rds_conn_init(void);
 void rds_conn_exit(void);
 struct rds_connection *rds_conn_create(struct net *net,

net/rds/recv.c

···
 	/* do nothing if no change in cong state */
 }
 
+static void rds_conn_peer_gen_update(struct rds_connection *conn,
+				     u32 peer_gen_num)
+{
+	int i;
+	struct rds_message *rm, *tmp;
+	unsigned long flags;
+
+	WARN_ON(conn->c_trans->t_type != RDS_TRANS_TCP);
+	if (peer_gen_num != 0) {
+		if (conn->c_peer_gen_num != 0 &&
+		    peer_gen_num != conn->c_peer_gen_num) {
+			for (i = 0; i < RDS_MPATH_WORKERS; i++) {
+				struct rds_conn_path *cp;
+
+				cp = &conn->c_path[i];
+				spin_lock_irqsave(&cp->cp_lock, flags);
+				cp->cp_next_tx_seq = 1;
+				cp->cp_next_rx_seq = 0;
+				list_for_each_entry_safe(rm, tmp,
+							 &cp->cp_retrans,
+							 m_conn_item) {
+					set_bit(RDS_MSG_FLUSH, &rm->m_flags);
+				}
+				spin_unlock_irqrestore(&cp->cp_lock, flags);
+			}
+		}
+		conn->c_peer_gen_num = peer_gen_num;
+	}
+}
+
 /*
  * Process all extension headers that come with this message.
  */
···
 	union {
 		struct rds_ext_header_version version;
 		u16 rds_npaths;
+		u32 rds_gen_num;
 	} buffer;
+	u32 new_peer_gen_num = 0;
 
 	while (1) {
 		len = sizeof(buffer);
···
 			conn->c_npaths = min_t(int, RDS_MPATH_WORKERS,
 					       buffer.rds_npaths);
 			break;
+		case RDS_EXTHDR_GEN_NUM:
+			new_peer_gen_num = buffer.rds_gen_num;
+			break;
 		default:
 			pr_warn_ratelimited("ignoring unknown exthdr type "
 					     "0x%x\n", type);
···
 	}
 	/* if RDS_EXTHDR_NPATHS was not found, default to a single-path */
 	conn->c_npaths = max_t(int, conn->c_npaths, 1);
+	rds_conn_peer_gen_update(conn, new_peer_gen_num);
 }
 
 /* rds_start_mprds() will synchronously start multiple paths when appropriate.

net/rds/send.c

···
 			 * connection.
 			 * Therefore, we never retransmit messages with RDMA ops.
 			 */
-			if (rm->rdma.op_active &&
-			    test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags)) {
+			if (test_bit(RDS_MSG_FLUSH, &rm->m_flags) ||
+			    (rm->rdma.op_active &&
+			    test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags))) {
 				spin_lock_irqsave(&cp->cp_lock, flags);
 				if (test_and_clear_bit(RDS_MSG_ON_CONN, &rm->m_flags))
 					list_move(&rm->m_conn_item, &to_be_dropped);
···
 		rds_message_add_extension(&rm->m_inc.i_hdr,
 					  RDS_EXTHDR_NPATHS, &npaths,
 					  sizeof(npaths));
+		rds_message_add_extension(&rm->m_inc.i_hdr,
+					  RDS_EXTHDR_GEN_NUM,
+					  &cp->cp_conn->c_my_gen_num,
+					  sizeof(u32));
 	}
 	spin_unlock_irqrestore(&cp->cp_lock, flags);
 

net/rds/tcp_connect.c

···
 	case TCP_SYN_RECV:
 		break;
 	case TCP_ESTABLISHED:
-		rds_connect_path_complete(cp, RDS_CONN_CONNECTING);
+		/* Force the peer to reconnect so that we have the
+		 * TCP ports going from <smaller-ip>.<transient> to
+		 * <larger-ip>.<RDS_TCP_PORT>. We avoid marking the
+		 * RDS connection as RDS_CONN_UP until the reconnect,
+		 * to avoid RDS datagram loss.
+		 */
+		if (cp->cp_conn->c_laddr > cp->cp_conn->c_faddr &&
+		    rds_conn_path_transition(cp, RDS_CONN_CONNECTING,
+					     RDS_CONN_ERROR)) {
+			rds_conn_path_drop(cp);
+		} else {
+			rds_connect_path_complete(cp, RDS_CONN_CONNECTING);
+		}
 		break;
 	case TCP_CLOSE_WAIT:
 	case TCP_CLOSE:

net/rds/tcp_listen.c

···
 {
 	int i;
 	bool peer_is_smaller = (conn->c_faddr < conn->c_laddr);
-	int npaths = conn->c_npaths;
+	int npaths = max_t(int, 1, conn->c_npaths);
 
-	if (npaths <= 1) {
-		struct rds_conn_path *cp = &conn->c_path[0];
-		int ret;
-
-		ret = rds_conn_path_transition(cp, RDS_CONN_DOWN,
-					       RDS_CONN_CONNECTING);
-		if (!ret)
-			rds_conn_path_transition(cp, RDS_CONN_ERROR,
-						 RDS_CONN_CONNECTING);
-		return cp->cp_transport_data;
-	}
-
-	/* for mprds, paths with cp_index > 0 MUST be initiated by the peer
+	/* for mprds, all paths MUST be initiated by the peer
 	 * with the smaller address.
 	 */
-	if (!peer_is_smaller)
+	if (!peer_is_smaller) {
+		/* Make sure we initiate at least one path if this
+		 * has not already been done; rds_start_mprds() will
+		 * take care of additional paths, if necessary.
+		 */
+		if (npaths == 1)
+			rds_conn_path_connect_if_down(&conn->c_path[0]);
 		return NULL;
+	}
 
 	for (i = 0; i < npaths; i++) {
 		struct rds_conn_path *cp = &conn->c_path[i];
···
 	mutex_lock(&rs_tcp->t_conn_path_lock);
 	cp = rs_tcp->t_cpath;
 	conn_state = rds_conn_path_state(cp);
-	if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_UP &&
-	    conn_state != RDS_CONN_ERROR)
+	WARN_ON(conn_state == RDS_CONN_UP);
+	if (conn_state != RDS_CONN_CONNECTING && conn_state != RDS_CONN_ERROR)
 		goto rst_nsk;
 	if (rs_tcp->t_sock) {
 		/* Need to resolve a duelling SYN between peers.

net/rds/tcp_send.c

···
 		set_bit(RDS_MSG_HAS_ACK_SEQ, &rm->m_flags);
 		tc->t_last_expected_una = rm->m_ack_seq + 1;
 
+		if (test_bit(RDS_MSG_RETRANSMITTED, &rm->m_flags))
+			rm->m_inc.i_hdr.h_flags |= RDS_FLAG_RETRANSMITTED;
+
 		rdsdebug("rm %p tcp nxt %u ack_seq %llu\n",
 			 rm, rds_tcp_snd_nxt(tc),
 			 (unsigned long long)rm->m_ack_seq);