rds: IPv6 support

index ab751a1..fc1a5c6 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -35,6 +35,7 @@
 #include <linux/kernel.h>
 #include <linux/gfp.h>
 #include <linux/in.h>
+#include <linux/ipv6.h>
 #include <linux/poll.h>
 #include <net/sock.h>
 

@@ -113,26 +114,63 @@ void rds_wake_sk_sleep(struct rds_sock *rs)
 static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
 		       int peer)
 {
-	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
 	struct rds_sock *rs = rds_sk_to_rs(sock->sk);
-
-	memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+	struct sockaddr_in6 *sin6;
+	struct sockaddr_in *sin;
+	int uaddr_len;
 
 	/* racey, don't care */
 	if (peer) {
-		if (!rs->rs_conn_addr)
+		if (ipv6_addr_any(&rs->rs_conn_addr))
 			return -ENOTCONN;
 
-		sin->sin_port = rs->rs_conn_port;
-		sin->sin_addr.s_addr = rs->rs_conn_addr;
+		if (ipv6_addr_v4mapped(&rs->rs_conn_addr)) {
+			sin = (struct sockaddr_in *)uaddr;
+			memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+			sin->sin_family = AF_INET;
+			sin->sin_port = rs->rs_conn_port;
+			sin->sin_addr.s_addr = rs->rs_conn_addr_v4;
+			uaddr_len = sizeof(*sin);
+		} else {
+			sin6 = (struct sockaddr_in6 *)uaddr;
+			sin6->sin6_family = AF_INET6;
+			sin6->sin6_port = rs->rs_conn_port;
+			sin6->sin6_addr = rs->rs_conn_addr;
+			sin6->sin6_flowinfo = 0;
+			/* scope_id is the same as in the bound address. */
+			sin6->sin6_scope_id = rs->rs_bound_scope_id;
+			uaddr_len = sizeof(*sin6);
+		}
 	} else {
-		sin->sin_port = rs->rs_bound_port;
-		sin->sin_addr.s_addr = rs->rs_bound_addr;
+		/* If socket is not yet bound, set the return address family
+		 * to be AF_UNSPEC (value 0) and the address size to be that
+		 * of an IPv4 address.
+		 */
+		if (ipv6_addr_any(&rs->rs_bound_addr)) {
+			sin = (struct sockaddr_in *)uaddr;
+			memset(sin, 0, sizeof(*sin));
+			sin->sin_family = AF_UNSPEC;
+			return sizeof(*sin);
+		}
+		if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
+			sin = (struct sockaddr_in *)uaddr;
+			memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+			sin->sin_family = AF_INET;
+			sin->sin_port = rs->rs_bound_port;
+			sin->sin_addr.s_addr = rs->rs_bound_addr_v4;
+			uaddr_len = sizeof(*sin);
+		} else {
+			sin6 = (struct sockaddr_in6 *)uaddr;
+			sin6->sin6_family = AF_INET6;
+			sin6->sin6_port = rs->rs_bound_port;
+			sin6->sin6_addr = rs->rs_bound_addr;
+			sin6->sin6_flowinfo = 0;
+			sin6->sin6_scope_id = rs->rs_bound_scope_id;
+			uaddr_len = sizeof(*sin6);
+		}
 	}
 
-	sin->sin_family = AF_INET;
-
-	return sizeof(*sin);
+	return uaddr_len;
 }
 
 /*

@@ -203,11 +241,12 @@ static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
 static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
 			      int len)
 {
+	struct sockaddr_in6 sin6;
 	struct sockaddr_in sin;
 	int ret = 0;
 
 	/* racing with another thread binding seems ok here */
-	if (rs->rs_bound_addr == 0) {
+	if (ipv6_addr_any(&rs->rs_bound_addr)) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}

@@ -215,14 +254,23 @@ static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval,
 	if (len < sizeof(struct sockaddr_in)) {
 		ret = -EINVAL;
 		goto out;
+	} else if (len < sizeof(struct sockaddr_in6)) {
+		/* Assume IPv4 */
+		if (copy_from_user(&sin, optval, sizeof(struct sockaddr_in))) {
+			ret = -EFAULT;
+			goto out;
+		}
+		ipv6_addr_set_v4mapped(sin.sin_addr.s_addr, &sin6.sin6_addr);
+		sin6.sin6_port = sin.sin_port;
+	} else {
+		if (copy_from_user(&sin6, optval,
+				   sizeof(struct sockaddr_in6))) {
+			ret = -EFAULT;
+			goto out;
+		}
 	}
 
-	if (copy_from_user(&sin, optval, sizeof(sin))) {
-		ret = -EFAULT;
-		goto out;
-	}
-
-	rds_send_drop_to(rs, &sin);
+	rds_send_drop_to(rs, &sin6);
 out:
 	return ret;
 }

@@ -435,31 +483,41 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 		       int addr_len, int flags)
 {
 	struct sock *sk = sock->sk;
-	struct sockaddr_in *sin = (struct sockaddr_in *)uaddr;
+	struct sockaddr_in *sin;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
 	int ret = 0;
 
 	lock_sock(sk);
 
-	if (addr_len != sizeof(struct sockaddr_in)) {
-		ret = -EINVAL;
-		goto out;
-	}
+	switch (addr_len) {
+	case sizeof(struct sockaddr_in):
+		sin = (struct sockaddr_in *)uaddr;
+		if (sin->sin_family != AF_INET) {
+			ret = -EAFNOSUPPORT;
+			break;
+		}
+		if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
+			ret = -EDESTADDRREQ;
+			break;
+		}
+		if (IN_MULTICAST(ntohl(sin->sin_addr.s_addr)) ||
+		    sin->sin_addr.s_addr == htonl(INADDR_BROADCAST)) {
+			ret = -EINVAL;
+			break;
+		}
+		ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &rs->rs_conn_addr);
+		rs->rs_conn_port = sin->sin_port;
+		break;
 
-	if (sin->sin_family != AF_INET) {
-		ret = -EAFNOSUPPORT;
-		goto out;
-	}
+	case sizeof(struct sockaddr_in6):
+		ret = -EPROTONOSUPPORT;
+		break;
 
-	if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {
-		ret = -EDESTADDRREQ;
-		goto out;
+	default:
+		ret = -EINVAL;
+		break;
 	}
 
-	rs->rs_conn_addr = sin->sin_addr.s_addr;
-	rs->rs_conn_port = sin->sin_port;
-
-out:
 	release_sock(sk);
 	return ret;
 }

@@ -578,8 +636,10 @@ static void rds_sock_inc_info(struct socket *sock, unsigned int len,
 		list_for_each_entry(inc, &rs->rs_recv_queue, i_item) {
 			total++;
 			if (total <= len)
-				rds_inc_info_copy(inc, iter, inc->i_saddr,
-						  rs->rs_bound_addr, 1);
+				rds_inc_info_copy(inc, iter,
+						  inc->i_saddr.s6_addr32[3],
+						  rs->rs_bound_addr_v4,
+						  1);
 		}
 
 		read_unlock(&rs->rs_recv_lock);

@@ -608,8 +668,8 @@ static void rds_sock_info(struct socket *sock, unsigned int len,
 	list_for_each_entry(rs, &rds_sock_list, rs_item) {
 		sinfo.sndbuf = rds_sk_sndbuf(rs);
 		sinfo.rcvbuf = rds_sk_rcvbuf(rs);
-		sinfo.bound_addr = rs->rs_bound_addr;
-		sinfo.connected_addr = rs->rs_conn_addr;
+		sinfo.bound_addr = rs->rs_bound_addr_v4;
+		sinfo.connected_addr = rs->rs_conn_addr_v4;
 		sinfo.bound_port = rs->rs_bound_port;
 		sinfo.connected_port = rs->rs_conn_port;
 		sinfo.inum = sock_i_ino(rds_rs_to_sk(rs));

192 lines not on this page · raw message

index 63da9d2..ccdff09 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007 Oracle.  All rights reserved.
+ * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -101,7 +101,7 @@
 static DEFINE_SPINLOCK(rds_cong_lock);
 static struct rb_root rds_cong_tree = RB_ROOT;
 
-static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
+static struct rds_cong_map *rds_cong_tree_walk(const struct in6_addr *addr,
 					       struct rds_cong_map *insert)
 {
 	struct rb_node **p = &rds_cong_tree.rb_node;

@@ -109,12 +109,15 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
 	struct rds_cong_map *map;
 
 	while (*p) {
+		int diff;
+
 		parent = *p;
 		map = rb_entry(parent, struct rds_cong_map, m_rb_node);
 
-		if (addr < map->m_addr)
+		diff = rds_addr_cmp(addr, &map->m_addr);
+		if (diff < 0)
 			p = &(*p)->rb_left;
-		else if (addr > map->m_addr)
+		else if (diff > 0)
 			p = &(*p)->rb_right;
 		else
 			return map;

@@ -132,7 +135,7 @@ static struct rds_cong_map *rds_cong_tree_walk(__be32 addr,
  * these bitmaps in the process getting pointers to them.  The bitmaps are only
  * ever freed as the module is removed after all connections have been freed.
  */
-static struct rds_cong_map *rds_cong_from_addr(__be32 addr)
+static struct rds_cong_map *rds_cong_from_addr(const struct in6_addr *addr)
 {
 	struct rds_cong_map *map;
 	struct rds_cong_map *ret = NULL;

@@ -144,7 +147,7 @@ static struct rds_cong_map *rds_cong_from_addr(__be32 addr)
 	if (!map)
 		return NULL;
 
-	map->m_addr = addr;
+	map->m_addr = *addr;
 	init_waitqueue_head(&map->m_waitq);
 	INIT_LIST_HEAD(&map->m_conn_list);
 

@@ -171,7 +174,7 @@ static struct rds_cong_map *rds_cong_from_addr(__be32 addr)
 		kfree(map);
 	}
 
-	rdsdebug("map %p for addr %x\n", ret, be32_to_cpu(addr));
+	rdsdebug("map %p for addr %pI6c\n", ret, addr);
 
 	return ret;
 }

@@ -202,8 +205,8 @@ void rds_cong_remove_conn(struct rds_connection *conn)
 
 int rds_cong_get_maps(struct rds_connection *conn)
 {
-	conn->c_lcong = rds_cong_from_addr(conn->c_laddr);
-	conn->c_fcong = rds_cong_from_addr(conn->c_faddr);
+	conn->c_lcong = rds_cong_from_addr(&conn->c_laddr);
+	conn->c_fcong = rds_cong_from_addr(&conn->c_faddr);
 
 	if (!(conn->c_lcong && conn->c_fcong))
 		return -ENOMEM;

@@ -353,7 +356,7 @@ void rds_cong_remove_socket(struct rds_sock *rs)
 
 	/* update congestion map for now-closed port */
 	spin_lock_irqsave(&rds_cong_lock, flags);
-	map = rds_cong_tree_walk(rs->rs_bound_addr, NULL);
+	map = rds_cong_tree_walk(&rs->rs_bound_addr, NULL);
 	spin_unlock_irqrestore(&rds_cong_lock, flags);
 
 	if (map && rds_cong_test_bit(map, rs->rs_bound_port)) {

255 lines not on this page · raw message

index b6ad38e..c712a84 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -296,8 +296,8 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn,
 	if (conn->c_trans != &rds_ib_transport)
 		return 0;
 
-	iinfo->src_addr = conn->c_laddr;
-	iinfo->dst_addr = conn->c_faddr;
+	iinfo->src_addr = conn->c_laddr.s6_addr32[3];
+	iinfo->dst_addr = conn->c_faddr.s6_addr32[3];
 
 	memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid));
 	memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid));

@@ -341,7 +341,8 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
  * allowed to influence which paths have priority.  We could call userspace
  * asserting this policy "routing".
  */
-static int rds_ib_laddr_check(struct net *net, __be32 addr)
+static int rds_ib_laddr_check(struct net *net, const struct in6_addr *addr,
+			      __u32 scope_id)
 {
 	int ret;
 	struct rdma_cm_id *cm_id;

@@ -357,7 +358,7 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr)
 
 	memset(&sin, 0, sizeof(sin));
 	sin.sin_family = AF_INET;
-	sin.sin_addr.s_addr = addr;
+	sin.sin_addr.s_addr = addr->s6_addr32[3];
 
 	/* rdma_bind_addr will only succeed for IB & iWARP devices */
 	ret = rdma_bind_addr(cm_id, (struct sockaddr *)&sin);

@@ -367,9 +368,9 @@ static int rds_ib_laddr_check(struct net *net, __be32 addr)
 	    cm_id->device->node_type != RDMA_NODE_IB_CA)
 		ret = -EADDRNOTAVAIL;
 
-	rdsdebug("addr %pI4 ret %d node type %d\n",
-		&addr, ret,
-		cm_id->device ? cm_id->device->node_type : -1);
+	rdsdebug("addr %pI6c ret %d node type %d\n",
+		 addr, ret,
+		 cm_id->device ? cm_id->device->node_type : -1);
 
 	rdma_destroy_id(cm_id);
 

71 lines not on this page · raw message

454 lines not on this page · raw message

index e678699..0ec9df0 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -100,18 +100,19 @@ static void rds_ib_remove_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
 		kfree_rcu(to_free, rcu);
 }
 
-int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
+int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev,
+			 struct in6_addr *ipaddr)
 {
 	struct rds_ib_device *rds_ibdev_old;
 
-	rds_ibdev_old = rds_ib_get_device(ipaddr);
+	rds_ibdev_old = rds_ib_get_device(ipaddr->s6_addr32[3]);
 	if (!rds_ibdev_old)
-		return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
+		return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]);
 
 	if (rds_ibdev_old != rds_ibdev) {
-		rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr);
+		rds_ib_remove_ipaddr(rds_ibdev_old, ipaddr->s6_addr32[3]);
 		rds_ib_dev_put(rds_ibdev_old);
-		return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
+		return rds_ib_add_ipaddr(rds_ibdev, ipaddr->s6_addr32[3]);
 	}
 	rds_ib_dev_put(rds_ibdev_old);
 

@@ -544,7 +545,7 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 	struct rds_ib_connection *ic = rs->rs_conn->c_transport_data;
 	int ret;
 
-	rds_ibdev = rds_ib_get_device(rs->rs_bound_addr);
+	rds_ibdev = rds_ib_get_device(rs->rs_bound_addr.s6_addr32[3]);
 	if (!rds_ibdev) {
 		ret = -ENODEV;
 		goto out;

index b4e421a..f101bed 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -266,7 +266,7 @@ static struct rds_ib_incoming *rds_ib_refill_one_inc(struct rds_ib_connection *i
 		rds_ib_stats_inc(s_ib_rx_total_incs);
 	}
 	INIT_LIST_HEAD(&ibinc->ii_frags);
-	rds_inc_init(&ibinc->ii_inc, ic->conn, ic->conn->c_faddr);
+	rds_inc_init(&ibinc->ii_inc, ic->conn, &ic->conn->c_faddr);
 
 	return ibinc;
 }

@@ -420,7 +420,7 @@ void rds_ib_recv_refill(struct rds_connection *conn, int prefill, gfp_t gfp)
 		ret = ib_post_recv(ic->i_cm_id->qp, &recv->r_wr, &failed_wr);
 		if (ret) {
 			rds_ib_conn_error(conn, "recv post on "
-			       "%pI4 returned %d, disconnecting and "
+			       "%pI6c returned %d, disconnecting and "
 			       "reconnecting\n", &conn->c_faddr,
 			       ret);
 			break;

@@ -850,7 +850,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 
 	if (data_len < sizeof(struct rds_header)) {
 		rds_ib_conn_error(conn, "incoming message "
-		       "from %pI4 didn't include a "
+		       "from %pI6c didn't include a "
 		       "header, disconnecting and "
 		       "reconnecting\n",
 		       &conn->c_faddr);

@@ -863,7 +863,7 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 	/* Validate the checksum. */
 	if (!rds_message_verify_checksum(ihdr)) {
 		rds_ib_conn_error(conn, "incoming message "
-		       "from %pI4 has corrupted header - "
+		       "from %pI6c has corrupted header - "
 		       "forcing a reconnect\n",
 		       &conn->c_faddr);
 		rds_stats_inc(s_recv_drop_bad_checksum);

@@ -943,10 +943,10 @@ static void rds_ib_process_recv(struct rds_connection *conn,
 		ic->i_recv_data_rem = 0;
 		ic->i_ibinc = NULL;
 
-		if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP)
+		if (ibinc->ii_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP) {
 			rds_ib_cong_recv(conn, ibinc);
-		else {
-			rds_recv_incoming(conn, conn->c_faddr, conn->c_laddr,
+		} else {
+			rds_recv_incoming(conn, &conn->c_faddr, &conn->c_laddr,
 					  &ibinc->ii_inc, GFP_ATOMIC);
 			state->ack_next = be64_to_cpu(hdr->h_sequence);
 			state->ack_next_valid = 1;

@@ -990,7 +990,7 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic,
 	} else {
 		/* We expect errors as the qp is drained during shutdown */
 		if (rds_conn_up(conn) || rds_conn_connecting(conn))
-			rds_ib_conn_error(conn, "recv completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n",
+			rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
 					  &conn->c_laddr, &conn->c_faddr,
 					  wc->status,
 					  ib_wc_status_msg(wc->status));

index 8557a1c..c4cdfe49 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -305,7 +305,7 @@ void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc)
 
 	/* We expect errors as the qp is drained during shutdown */
 	if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) {
-		rds_ib_conn_error(conn, "send completion on <%pI4,%pI4> had status %u (%s), disconnecting and reconnecting\n",
+		rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n",
 				  &conn->c_laddr, &conn->c_faddr, wc->status,
 				  ib_wc_status_msg(wc->status));
 	}

@@ -730,7 +730,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm,
 		 first, &first->s_wr, ret, failed_wr);
 	BUG_ON(failed_wr != &first->s_wr);
 	if (ret) {
-		printk(KERN_WARNING "RDS/IB: ib_post_send to %pI4 "
+		printk(KERN_WARNING "RDS/IB: ib_post_send to %pI6c "
 		       "returned %d\n", &conn->c_faddr, ret);
 		rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
 		rds_ib_sub_signaled(ic, nr_sig);

@@ -827,7 +827,7 @@ int rds_ib_xmit_atomic(struct rds_connection *conn, struct rm_atomic_op *op)
 		 send, &send->s_atomic_wr, ret, failed_wr);
 	BUG_ON(failed_wr != &send->s_atomic_wr.wr);
 	if (ret) {
-		printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI4 "
+		printk(KERN_WARNING "RDS/IB: atomic ib_post_send to %pI6c "
 		       "returned %d\n", &conn->c_faddr, ret);
 		rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
 		rds_ib_sub_signaled(ic, nr_sig);

@@ -967,7 +967,7 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op)
 		 first, &first->s_rdma_wr.wr, ret, failed_wr);
 	BUG_ON(failed_wr != &first->s_rdma_wr.wr);
 	if (ret) {
-		printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI4 "
+		printk(KERN_WARNING "RDS/IB: rdma ib_post_send to %pI6c "
 		       "returned %d\n", &conn->c_faddr, ret);
 		rds_ib_ring_unalloc(&ic->i_send_ring, work_alloc);
 		rds_ib_sub_signaled(ic, nr_sig);

index feea1f9..1d73ad7 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -35,6 +35,7 @@
 #include <linux/in.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <linux/ipv6.h>
 
 #include "rds_single_path.h"
 #include "rds.h"

@@ -88,11 +89,11 @@ static int rds_loop_xmit(struct rds_connection *conn, struct rds_message *rm,
 
 	BUG_ON(hdr_off || sg || off);
 
-	rds_inc_init(&rm->m_inc, conn, conn->c_laddr);
+	rds_inc_init(&rm->m_inc, conn, &conn->c_laddr);
 	/* For the embedded inc. Matching put is in loop_inc_free() */
 	rds_message_addref(rm);
 
-	rds_recv_incoming(conn, conn->c_laddr, conn->c_faddr, &rm->m_inc,
+	rds_recv_incoming(conn, &conn->c_laddr, &conn->c_faddr, &rm->m_inc,
 			  GFP_KERNEL);
 
 	rds_send_drop_acked(conn, be64_to_cpu(rm->m_inc.i_hdr.h_sequence),

index 634cfcb..7b39980 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2007 Oracle.  All rights reserved.
+ * Copyright (c) 2007, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -183,7 +183,7 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args,
 	long i;
 	int ret;
 
-	if (rs->rs_bound_addr == 0 || !rs->rs_transport) {
+	if (ipv6_addr_any(&rs->rs_bound_addr) || !rs->rs_transport) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out;
 	}

@@ -574,7 +574,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm,
 
 	args = CMSG_DATA(cmsg);
 
-	if (rs->rs_bound_addr == 0) {
+	if (ipv6_addr_any(&rs->rs_bound_addr)) {
 		ret = -ENOTCONN; /* XXX not a great errno */
 		goto out_ret;
 	}

122 lines not on this page · raw message

169 lines not on this page · raw message

126 lines not on this page · raw message

125 lines not on this page · raw message

index 351a284..dadb337 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -37,6 +37,8 @@
 #include <net/tcp.h>
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
+#include <net/tcp.h>
+#include <net/addrconf.h>
 
 #include "rds.h"
 #include "tcp.h"

@@ -262,9 +264,33 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len,
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
 
-static int rds_tcp_laddr_check(struct net *net, __be32 addr)
+static int rds_tcp_laddr_check(struct net *net, const struct in6_addr *addr,
+			       __u32 scope_id)
 {
-	if (inet_addr_type(net, addr) == RTN_LOCAL)
+	struct net_device *dev = NULL;
+	int ret;
+
+	if (ipv6_addr_v4mapped(addr)) {
+		if (inet_addr_type(net, addr->s6_addr32[3]) == RTN_LOCAL)
+			return 0;
+		return -EADDRNOTAVAIL;
+	}
+
+	/* If the scope_id is specified, check only those addresses
+	 * hosted on the specified interface.
+	 */
+	if (scope_id != 0) {
+		rcu_read_lock();
+		dev = dev_get_by_index_rcu(net, scope_id);
+		/* scope_id is not valid... */
+		if (!dev) {
+			rcu_read_unlock();
+			return -EADDRNOTAVAIL;
+		}
+		rcu_read_unlock();
+	}
+	ret = ipv6_chk_addr(net, addr, dev, 0);
+	if (ret)
 		return 0;
 	return -EADDRNOTAVAIL;
 }

index d999e70..231ae92 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -66,7 +66,8 @@ void rds_tcp_state_change(struct sock *sk)
 		 * RDS connection as RDS_CONN_UP until the reconnect,
 		 * to avoid RDS datagram loss.
 		 */
-		if (!IS_CANONICAL(cp->cp_conn->c_laddr, cp->cp_conn->c_faddr) &&
+		if (rds_addr_cmp(&cp->cp_conn->c_laddr,
+				 &cp->cp_conn->c_faddr) >= 0 &&
 		    rds_conn_path_transition(cp, RDS_CONN_CONNECTING,
 					     RDS_CONN_ERROR)) {
 			rds_conn_path_drop(cp, false);

@@ -88,7 +89,9 @@ void rds_tcp_state_change(struct sock *sk)
 int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 {
 	struct socket *sock = NULL;
-	struct sockaddr_in src, dest;
+	struct sockaddr_in sin;
+	struct sockaddr *addr;
+	int addrlen;
 	int ret;
 	struct rds_connection *conn = cp->cp_conn;
 	struct rds_tcp_connection *tc = cp->cp_transport_data;

@@ -112,30 +115,33 @@ int rds_tcp_conn_path_connect(struct rds_conn_path *cp)
 
 	rds_tcp_tune(sock);
 
-	src.sin_family = AF_INET;
-	src.sin_addr.s_addr = (__force u32)conn->c_laddr;
-	src.sin_port = (__force u16)htons(0);
+	sin.sin_family = AF_INET;
+	sin.sin_addr.s_addr = conn->c_laddr.s6_addr32[3];
+	sin.sin_port = 0;
+	addr = (struct sockaddr *)&sin;
+	addrlen = sizeof(sin);
 
-	ret = sock->ops->bind(sock, (struct sockaddr *)&src, sizeof(src));
+	ret = sock->ops->bind(sock, addr, addrlen);
 	if (ret) {
-		rdsdebug("bind failed with %d at address %pI4\n",
+		rdsdebug("bind failed with %d at address %pI6c\n",
 			 ret, &conn->c_laddr);
 		goto out;
 	}
 
-	dest.sin_family = AF_INET;
-	dest.sin_addr.s_addr = (__force u32)conn->c_faddr;
-	dest.sin_port = (__force u16)htons(RDS_TCP_PORT);
+	sin.sin_family = AF_INET;
+	sin.sin_addr.s_addr = conn->c_faddr.s6_addr32[3];
+	sin.sin_port = htons(RDS_TCP_PORT);
+	addr = (struct sockaddr *)&sin;
+	addrlen = sizeof(sin);
 
 	/*
 	 * once we call connect() we can start getting callbacks and they
 	 * own the socket
 	 */
 	rds_tcp_set_callbacks(sock, cp);
-	ret = sock->ops->connect(sock, (struct sockaddr *)&dest, sizeof(dest),
-				 O_NONBLOCK);
+	ret = sock->ops->connect(sock, addr, addrlen, O_NONBLOCK);
 
-	rdsdebug("connect to address %pI4 returned %d\n", &conn->c_faddr, ret);
+	rdsdebug("connect to address %pI6c returned %d\n", &conn->c_faddr, ret);
 	if (ret == -EINPROGRESS)
 		ret = 0;
 	if (ret == 0) {

index 2257118..4fdf5b3 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2018 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -83,13 +83,12 @@ int rds_tcp_keepalive(struct socket *sock)
 struct rds_tcp_connection *rds_tcp_accept_one_path(struct rds_connection *conn)
 {
 	int i;
-	bool peer_is_smaller = IS_CANONICAL(conn->c_faddr, conn->c_laddr);
 	int npaths = max_t(int, 1, conn->c_npaths);
 
 	/* for mprds, all paths MUST be initiated by the peer
 	 * with the smaller address.
 	 */
-	if (!peer_is_smaller) {
+	if (rds_addr_cmp(&conn->c_faddr, &conn->c_laddr) >= 0) {
 		/* 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.

@@ -164,13 +163,16 @@ int rds_tcp_accept_one(struct socket *sock)
 
 	inet = inet_sk(new_sock->sk);
 
-	rdsdebug("accepted tcp %pI4:%u -> %pI4:%u\n",
-		 &inet->inet_saddr, ntohs(inet->inet_sport),
-		 &inet->inet_daddr, ntohs(inet->inet_dport));
+	rdsdebug("accepted tcp %pI6c:%u -> %pI6c:%u\n",
+		 &new_sock->sk->sk_v6_rcv_saddr, ntohs(inet->inet_sport),
+		 &new_sock->sk->sk_v6_daddr, ntohs(inet->inet_dport));
 
 	conn = rds_conn_create(sock_net(sock->sk),
-			       inet->inet_saddr, inet->inet_daddr,
-			       &rds_tcp_transport, GFP_KERNEL);
+			       &new_sock->sk->sk_v6_rcv_saddr,
+			       &new_sock->sk->sk_v6_daddr,
+			       &rds_tcp_transport, GFP_KERNEL,
+			       new_sock->sk->sk_bound_dev_if);
+
 	if (IS_ERR(conn)) {
 		ret = PTR_ERR(conn);
 		goto out;

index b9fbd2e..42c5ff1 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -179,7 +179,7 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			tc->t_tinc = tinc;
 			rdsdebug("alloced tinc %p\n", tinc);
 			rds_inc_path_init(&tinc->ti_inc, cp,
-					  cp->cp_conn->c_faddr);
+					  &cp->cp_conn->c_faddr);
 			tinc->ti_inc.i_rx_lat_trace[RDS_MSG_RX_HDR] =
 					local_clock();
 

@@ -239,8 +239,9 @@ static int rds_tcp_data_recv(read_descriptor_t *desc, struct sk_buff *skb,
 			if (tinc->ti_inc.i_hdr.h_flags == RDS_FLAG_CONG_BITMAP)
 				rds_tcp_cong_recv(conn, tinc);
 			else
-				rds_recv_incoming(conn, conn->c_faddr,
-						  conn->c_laddr, &tinc->ti_inc,
+				rds_recv_incoming(conn, &conn->c_faddr,
+						  &conn->c_laddr,
+						  &tinc->ti_inc,
 						  arg->gfp);
 
 			tc->t_tinc_hdr_rem = sizeof(struct rds_header);

index 7df869d..78a2554 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -153,7 +153,7 @@ int rds_tcp_xmit(struct rds_connection *conn, struct rds_message *rm,
 			 * an incoming RST.
 			 */
 			if (rds_conn_path_up(cp)) {
-				pr_warn("RDS/tcp: send to %pI4 on cp [%d]"
+				pr_warn("RDS/tcp: send to %pI6c on cp [%d]"
 					"returned %d, "
 					"disconnecting and reconnecting\n",
 					&conn->c_faddr, cp->cp_index, ret);

108 lines not on this page · raw message

index 0b188dd..c9788db 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006 Oracle.  All rights reserved.
+ * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -33,6 +33,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/in.h>
+#include <linux/ipv6.h>
 
 #include "rds.h"
 #include "loop.h"

@@ -75,20 +76,26 @@ void rds_trans_put(struct rds_transport *trans)
 		module_put(trans->t_owner);
 }
 
-struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr)
+struct rds_transport *rds_trans_get_preferred(struct net *net,
+					      const struct in6_addr *addr,
+					      __u32 scope_id)
 {
 	struct rds_transport *ret = NULL;
 	struct rds_transport *trans;
 	unsigned int i;
 
-	if (IN_LOOPBACK(ntohl(addr)))
+	if (ipv6_addr_v4mapped(addr)) {
+		if (*(u_int8_t *)&addr->s6_addr32[3] == IN_LOOPBACKNET)
+			return &rds_loop_transport;
+	} else if (ipv6_addr_loopback(addr)) {
 		return &rds_loop_transport;
+	}
 
 	down_read(&rds_trans_sem);
 	for (i = 0; i < RDS_TRANS_COUNT; i++) {
 		trans = transports[i];
 
-		if (trans && (trans->laddr_check(net, addr) == 0) &&
+		if (trans && (trans->laddr_check(net, addr, scope_id) == 0) &&
 		    (!trans->t_owner || try_module_get(trans->t_owner))) {
 			ret = trans;
 			break;

index fc1a5c6..fc5c48b 100644
@@ -142,15 +142,32 @@ static int rds_getname(struct socket *sock, struct sockaddr *uaddr,
 			uaddr_len = sizeof(*sin6);
 		}
 	} else {
-		/* If socket is not yet bound, set the return address family
-		 * to be AF_UNSPEC (value 0) and the address size to be that
-		 * of an IPv4 address.
+		/* If socket is not yet bound and the socket is connected,
+		 * set the return address family to be the same as the
+		 * connected address, but with 0 address value.  If it is not
+		 * connected, set the family to be AF_UNSPEC (value 0) and
+		 * the address size to be that of an IPv4 address.
 		 */
 		if (ipv6_addr_any(&rs->rs_bound_addr)) {
-			sin = (struct sockaddr_in *)uaddr;
-			memset(sin, 0, sizeof(*sin));
-			sin->sin_family = AF_UNSPEC;
-			return sizeof(*sin);
+			if (ipv6_addr_any(&rs->rs_conn_addr)) {
+				sin = (struct sockaddr_in *)uaddr;
+				memset(sin, 0, sizeof(*sin));
+				sin->sin_family = AF_UNSPEC;
+				return sizeof(*sin);
+			}
+
+			if (ipv6_addr_type(&rs->rs_conn_addr) &
+			    IPV6_ADDR_MAPPED) {
+				sin = (struct sockaddr_in *)uaddr;
+				memset(sin, 0, sizeof(*sin));
+				sin->sin_family = AF_INET;
+				return sizeof(*sin);
+			}
+
+			sin6 = (struct sockaddr_in6 *)uaddr;
+			memset(sin6, 0, sizeof(*sin6));
+			sin6->sin6_family = AF_INET6;
+			return sizeof(*sin6);
 		}
 		if (ipv6_addr_v4mapped(&rs->rs_bound_addr)) {
 			sin = (struct sockaddr_in *)uaddr;

@@ -484,16 +501,18 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 {
 	struct sock *sk = sock->sk;
 	struct sockaddr_in *sin;
+	struct sockaddr_in6 *sin6;
 	struct rds_sock *rs = rds_sk_to_rs(sk);
+	int addr_type;
 	int ret = 0;
 
 	lock_sock(sk);
 
-	switch (addr_len) {
-	case sizeof(struct sockaddr_in):
+	switch (uaddr->sa_family) {
+	case AF_INET:
 		sin = (struct sockaddr_in *)uaddr;
-		if (sin->sin_family != AF_INET) {
-			ret = -EAFNOSUPPORT;
+		if (addr_len < sizeof(struct sockaddr_in)) {
+			ret = -EINVAL;
 			break;
 		}
 		if (sin->sin_addr.s_addr == htonl(INADDR_ANY)) {

@@ -509,12 +528,56 @@ static int rds_connect(struct socket *sock, struct sockaddr *uaddr,
 		rs->rs_conn_port = sin->sin_port;
 		break;
 
-	case sizeof(struct sockaddr_in6):
-		ret = -EPROTONOSUPPORT;
+	case AF_INET6:
+		sin6 = (struct sockaddr_in6 *)uaddr;
+		if (addr_len < sizeof(struct sockaddr_in6)) {
+			ret = -EINVAL;
+			break;
+		}
+		addr_type = ipv6_addr_type(&sin6->sin6_addr);
+		if (!(addr_type & IPV6_ADDR_UNICAST)) {
+			__be32 addr4;
+
+			if (!(addr_type & IPV6_ADDR_MAPPED)) {
+				ret = -EPROTOTYPE;
+				break;
+			}
+
+			/* It is a mapped address.  Need to do some sanity
+			 * checks.
+			 */
+			addr4 = sin6->sin6_addr.s6_addr32[3];
+			if (addr4 == htonl(INADDR_ANY) ||
+			    addr4 == htonl(INADDR_BROADCAST) ||
+			    IN_MULTICAST(ntohl(addr4))) {
+				ret = -EPROTOTYPE;
+				break;
+			}
+		}
+
+		if (addr_type & IPV6_ADDR_LINKLOCAL) {
+			/* If socket is arleady bound to a link local address,
+			 * the peer address must be on the same link.
+			 */
+			if (sin6->sin6_scope_id == 0 ||
+			    (!ipv6_addr_any(&rs->rs_bound_addr) &&
+			     rs->rs_bound_scope_id &&
+			     sin6->sin6_scope_id != rs->rs_bound_scope_id)) {
+				ret = -EINVAL;
+				break;
+			}
+			/* Remember the connected address scope ID.  It will
+			 * be checked against the binding local address when
+			 * the socket is bound.
+			 */
+			rs->rs_bound_scope_id = sin6->sin6_scope_id;
+		}
+		rs->rs_conn_addr = sin6->sin6_addr;
+		rs->rs_conn_port = sin6->sin6_port;
 		break;
 
 	default:
-		ret = -EINVAL;
+		ret = -EAFNOSUPPORT;
 		break;
 	}
 

88 lines not on this page · raw message

96 lines not on this page · raw message

99 lines not on this page · raw message

index dd8a867..a33b82d 100644
@@ -678,7 +678,7 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6)
 	return version;
 }
 
-/* Given an IPv6 address, find the IB net_device which hosts that address and
+/* Given an IPv6 address, find the net_device which hosts that address and
  * return its index.  This is used by the rds_ib_cm_handle_connect() code to
  * find the interface index of where an incoming request comes from when
  * the request is using a link local address.

@@ -695,8 +695,7 @@ static u32 __rds_find_ifindex(struct net *net, const struct in6_addr *addr)
 
 	rcu_read_lock();
 	for_each_netdev_rcu(net, dev) {
-		if (dev->type == ARPHRD_INFINIBAND &&
-		    ipv6_chk_addr(net, addr, dev, 0)) {
+		if (ipv6_chk_addr(net, addr, dev, 1)) {
 			idx = dev->ifindex;
 			break;
 		}

@@ -736,7 +735,7 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 		dp_cmn = &dp->ricp_v6.dp_cmn;
 		saddr6 = &dp->ricp_v6.dp_saddr;
 		daddr6 = &dp->ricp_v6.dp_daddr;
-		/* If the local address is link local, need to find the
+		/* If either address is link local, need to find the
 		 * interface index in order to create a proper RDS
 		 * connection.
 		 */

@@ -748,6 +747,14 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 				err = -EOPNOTSUPP;
 				goto out;
 			}
+		} else if (ipv6_addr_type(saddr6) & IPV6_ADDR_LINKLOCAL) {
+			/* Use our address to find the correct index. */
+			ifindex = __rds_find_ifindex(&init_net, daddr6);
+			/* No index found...  Need to bail out. */
+			if (ifindex == 0) {
+				err = -EOPNOTSUPP;
+				goto out;
+			}
 		}
 	} else {
 		dp_cmn = &dp->ricp_v4.dp_cmn;

@@ -886,7 +893,10 @@ int rds_ib_conn_path_connect(struct rds_conn_path *cp)
 
 	/* XXX I wonder what affect the port space has */
 	/* delegate cm event handler to rdma_transport */
-	handler = rds_rdma_cm_event_handler;
+	if (conn->c_isv6)
+		handler = rds6_rdma_cm_event_handler;
+	else
+		handler = rds_rdma_cm_event_handler;
 	ic->i_cm_id = rdma_create_id(&init_net, handler, conn,
 				     RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(ic->i_cm_id)) {

index f49abef6..bd67e55 100644
@@ -37,7 +37,9 @@
 #include "rdma_transport.h"
 #include "ib.h"
 
+/* Global IPv4 and IPv6 RDS RDMA listener cm_id */
 static struct rdma_cm_id *rds_rdma_listen_id;
+static struct rdma_cm_id *rds6_rdma_listen_id;
 
 static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id,
 					 struct rdma_cm_event *event,

@@ -153,6 +155,12 @@ int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 	return rds_rdma_cm_event_handler_cmn(cm_id, event, false);
 }
 
+int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
+			       struct rdma_cm_event *event)
+{
+	return rds_rdma_cm_event_handler_cmn(cm_id, event, true);
+}
+
 static int rds_rdma_listen_init_common(rdma_cm_event_handler handler,
 				       struct sockaddr *sa,
 				       struct rdma_cm_id **ret_cm_id)

@@ -206,6 +214,7 @@ static int rds_rdma_listen_init_common(rdma_cm_event_handler handler,
 static int rds_rdma_listen_init(void)
 {
 	int ret;
+	struct sockaddr_in6 sin6;
 	struct sockaddr_in sin;
 
 	sin.sin_family = PF_INET;

@@ -214,7 +223,21 @@ static int rds_rdma_listen_init(void)
 	ret = rds_rdma_listen_init_common(rds_rdma_cm_event_handler,
 					  (struct sockaddr *)&sin,
 					  &rds_rdma_listen_id);
-	return ret;
+	if (ret != 0)
+		return ret;
+
+	sin6.sin6_family = PF_INET6;
+	sin6.sin6_addr = in6addr_any;
+	sin6.sin6_port = htons(RDS_CM_PORT);
+	sin6.sin6_scope_id = 0;
+	sin6.sin6_flowinfo = 0;
+	ret = rds_rdma_listen_init_common(rds6_rdma_cm_event_handler,
+					  (struct sockaddr *)&sin6,
+					  &rds6_rdma_listen_id);
+	/* Keep going even when IPv6 is not enabled in the system. */
+	if (ret != 0)
+		rdsdebug("Cannot set up IPv6 RDMA listener\n");
+	return 0;
 }
 
 static void rds_rdma_listen_stop(void)

@@ -224,6 +247,11 @@ static void rds_rdma_listen_stop(void)
 		rdma_destroy_id(rds_rdma_listen_id);
 		rds_rdma_listen_id = NULL;
 	}
+	if (rds6_rdma_listen_id) {
+		rdsdebug("cm %p\n", rds6_rdma_listen_id);
+		rdma_destroy_id(rds6_rdma_listen_id);
+		rds6_rdma_listen_id = NULL;
+	}
 }
 
 static int rds_rdma_init(void)

index d309c44..200d313 100644
@@ -6,11 +6,16 @@
 #include <rdma/rdma_cm.h>
 #include "rds.h"
 
+/* RDMA_CM also uses 16385 as the listener port. */
+#define RDS_CM_PORT	16385
+
 #define RDS_RDMA_RESOLVE_TIMEOUT_MS     5000
 
 int rds_rdma_conn_connect(struct rds_connection *conn);
 int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
 			      struct rdma_cm_event *event);
+int rds6_rdma_cm_event_handler(struct rdma_cm_id *cm_id,
+			       struct rdma_cm_event *event);
 
 /* from ib.c */
 extern struct rds_transport rds_ib_transport;

index 1bff269..f2c4f44 100644
@@ -24,14 +24,14 @@
 #define RDS_PROTOCOL_MINOR(v)	((v) & 255)
 #define RDS_PROTOCOL(maj, min)	(((maj) << 8) | min)
 
-/*
- * XXX randomly chosen, but at least seems to be unused:
- * #               18464-18768 Unassigned
- * We should do better.  We want a reserved port to discourage unpriv'ed
- * userspace from listening.
+/* The following ports, 16385, 18634, 18635, are registered with IANA as
+ * the ports to be used for RDS over TCP and UDP.  18634 is the historical
+ * value used for the RDMA_CM listener port.  RDS/TCP uses port 16385.  After
+ * IPv6 work, RDMA_CM also uses 16385 as the listener port.  18634 is kept
+ * to ensure compatibility with older RDS modules.  Those ports are defined
+ * in each transport's header file.
  */
 #define RDS_PORT	18634
-#define RDS_CM_PORT	16385
 
 #ifdef ATOMIC64_INIT
 #define KERNEL_HAS_ATOMIC64

@@ -140,7 +140,8 @@ struct rds_connection {
 	struct hlist_node	c_hash_node;
 	struct in6_addr		c_laddr;
 	struct in6_addr		c_faddr;
-	int			c_dev_if; /* c_laddrs's interface index */
+	int			c_dev_if; /* ifindex used for this conn */
+	int			c_bound_if; /* ifindex of c_laddr */
 	unsigned int		c_loopback:1,
 				c_isv6:1,
 				c_ping_triggered:1,

@@ -736,7 +737,7 @@ struct rds_sock *rds_find_bound(const struct in6_addr *addr, __be16 port,
 void rds_cong_exit(void);
 struct rds_message *rds_cong_update_alloc(struct rds_connection *conn);
 
-/* conn.c */
+/* connection.c */
 extern u32 rds_gen_num;
 int rds_conn_init(void);
 void rds_conn_exit(void);

@@ -874,6 +875,10 @@ int rds_recvmsg(struct socket *sock, struct msghdr *msg, size_t size,
 void rds_inc_info_copy(struct rds_incoming *inc,
 		       struct rds_info_iterator *iter,
 		       __be32 saddr, __be32 daddr, int flip);
+void rds6_inc_info_copy(struct rds_incoming *inc,
+			struct rds_info_iterator *iter,
+			struct in6_addr *saddr, struct in6_addr *daddr,
+			int flip);
 
 /* send.c */
 int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len);

index 4217961..1402c21 100644
@@ -364,7 +364,7 @@ void rds_recv_incoming(struct rds_connection *conn, struct in6_addr *saddr,
 		goto out;
 	}
 
-	rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_dev_if);
+	rs = rds_find_bound(daddr, inc->i_hdr.h_dport, conn->c_bound_if);
 	if (!rs) {
 		rds_stats_inc(s_recv_drop_no_sock);
 		goto out;

79 lines not on this page · raw message

103 lines not on this page · raw message

index c6fa080..3c69361 100644
@@ -67,7 +67,7 @@ void rds_tcp_restore_callbacks(struct socket *sock,
 void rds_tcp_state_change(struct sock *sk);
 
 /* tcp_listen.c */
-struct socket *rds_tcp_listen_init(struct net *);
+struct socket *rds_tcp_listen_init(struct net *net, bool isv6);
 void rds_tcp_listen_stop(struct socket *sock, struct work_struct *acceptor);
 void rds_tcp_listen_data_ready(struct sock *sk);
 int rds_tcp_accept_one(struct socket *sock);

80 lines not on this page · raw message

100 lines not on this page · raw message

index 20c6bd0..518d40f 100644
@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR Linux-OpenIB) */
 /*
- * Copyright (c) 2008 Oracle.  All rights reserved.
+ * Copyright (c) 2008, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -52,7 +52,7 @@
 #define RDS_RECVERR			5
 #define RDS_CONG_MONITOR		6
 #define RDS_GET_MR_FOR_DEST		7
-#define SO_RDS_TRANSPORT		8
+#define SO_RDS_TRANSPORT		9
 
 /* Socket option to tap receive path latency
  *	SO_RDS: SO_RDS_MSG_RXPATH_LATENCY

@@ -118,7 +118,17 @@
 #define RDS_INFO_IB_CONNECTIONS		10008
 #define RDS_INFO_CONNECTION_STATS	10009
 #define RDS_INFO_IWARP_CONNECTIONS	10010
-#define RDS_INFO_LAST			10010
+
+/* PF_RDS6 options */
+#define RDS6_INFO_CONNECTIONS		10011
+#define RDS6_INFO_SEND_MESSAGES		10012
+#define RDS6_INFO_RETRANS_MESSAGES	10013
+#define RDS6_INFO_RECV_MESSAGES		10014
+#define RDS6_INFO_SOCKETS		10015
+#define RDS6_INFO_TCP_SOCKETS		10016
+#define RDS6_INFO_IB_CONNECTIONS	10017
+
+#define RDS_INFO_LAST			10017
 
 struct rds_info_counter {
 	__u8	name[32];

@@ -140,6 +150,15 @@ struct rds_info_connection {
 	__u8		flags;
 } __attribute__((packed));
 
+struct rds6_info_connection {
+	__u64		next_tx_seq;
+	__u64		next_rx_seq;
+	struct in6_addr	laddr;
+	struct in6_addr	faddr;
+	__u8		transport[TRANSNAMSIZ];		/* null term ascii */
+	__u8		flags;
+} __attribute__((packed));
+
 #define RDS_INFO_MESSAGE_FLAG_ACK               0x01
 #define RDS_INFO_MESSAGE_FLAG_FAST_ACK          0x02
 

@@ -153,6 +172,17 @@ struct rds_info_message {
 	__u8		flags;
 } __attribute__((packed));
 
+struct rds6_info_message {
+	__u64	seq;
+	__u32	len;
+	struct in6_addr	laddr;
+	struct in6_addr	faddr;
+	__be16		lport;
+	__be16		fport;
+	__u8		flags;
+	__u8		tos;
+} __attribute__((packed));
+
 struct rds_info_socket {
 	__u32		sndbuf;
 	__be32		bound_addr;

@@ -163,6 +193,16 @@ struct rds_info_socket {
 	__u64		inum;
 } __attribute__((packed));
 
+struct rds6_info_socket {
+	__u32		sndbuf;
+	struct in6_addr	bound_addr;
+	struct in6_addr	connected_addr;
+	__be16		bound_port;
+	__be16		connected_port;
+	__u32		rcvbuf;
+	__u64		inum;
+} __attribute__((packed));
+
 struct rds_info_tcp_socket {
 	__be32          local_addr;
 	__be16          local_port;

@@ -175,6 +215,18 @@ struct rds_info_tcp_socket {
 	__u32           last_seen_una;
 } __attribute__((packed));
 
+struct rds6_info_tcp_socket {
+	struct in6_addr	local_addr;
+	__be16		local_port;
+	struct in6_addr	peer_addr;
+	__be16		peer_port;
+	__u64		hdr_rem;
+	__u64		data_rem;
+	__u32		last_sent_nxt;
+	__u32		last_expected_una;
+	__u32		last_seen_una;
+} __attribute__((packed));
+
 #define RDS_IB_GID_LEN	16
 struct rds_info_rdma_connection {
 	__be32		src_addr;

@@ -189,6 +241,19 @@ struct rds_info_rdma_connection {
 	__u32		rdma_mr_size;
 };
 
+struct rds6_info_rdma_connection {
+	struct in6_addr	src_addr;
+	struct in6_addr	dst_addr;
+	__u8		src_gid[RDS_IB_GID_LEN];
+	__u8		dst_gid[RDS_IB_GID_LEN];
+
+	__u32		max_send_wr;
+	__u32		max_recv_wr;
+	__u32		max_send_sge;
+	__u32		rdma_mr_max;
+	__u32		rdma_mr_size;
+};
+
 /* RDS message Receive Path Latency points */
 enum rds_message_rxpath_latency {
 	RDS_MSG_RX_HDR_TO_DGRAM_START = 0,

179 lines not on this page · raw message

76 lines not on this page · raw message

index 0ea4ab0..f440ace 100644
@@ -113,6 +113,8 @@ struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *rds_dev,
 					     int npages);
 void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
 			struct rds_info_rdma_connection *iinfo);
+void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
+			 struct rds6_info_rdma_connection *iinfo6);
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
 void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents,
 		    struct rds_sock *rs, u32 *key_ret);

index 0ec9df0..e3c8bbb 100644
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2006, 2017 Oracle and/or its affiliates. All rights reserved.
+ * Copyright (c) 2006, 2018 Oracle and/or its affiliates. All rights reserved.
  *
  * This software is available to you under a choice of one of two
  * licenses.  You may choose to be licensed under the terms of the GNU

@@ -180,6 +180,15 @@ void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_co
 	iinfo->rdma_mr_size = pool_1m->fmr_attr.max_pages;
 }
 
+void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev,
+			 struct rds6_info_rdma_connection *iinfo6)
+{
+	struct rds_ib_mr_pool *pool_1m = rds_ibdev->mr_1m_pool;
+
+	iinfo6->rdma_mr_max = pool_1m->max_items;
+	iinfo6->rdma_mr_size = pool_1m->fmr_attr.max_pages;
+}
+
 struct rds_ib_mr *rds_ib_reuse_mr(struct rds_ib_mr_pool *pool)
 {
 	struct rds_ib_mr *ibmr = NULL;

index 1402c21..03cd8df 100644
@@ -792,3 +792,28 @@ void rds_inc_info_copy(struct rds_incoming *inc,
 
 	rds_info_copy(iter, &minfo, sizeof(minfo));
 }
+
+void rds6_inc_info_copy(struct rds_incoming *inc,
+			struct rds_info_iterator *iter,
+			struct in6_addr *saddr, struct in6_addr *daddr,
+			int flip)
+{
+	struct rds6_info_message minfo6;
+
+	minfo6.seq = be64_to_cpu(inc->i_hdr.h_sequence);
+	minfo6.len = be32_to_cpu(inc->i_hdr.h_len);
+
+	if (flip) {
+		minfo6.laddr = *daddr;
+		minfo6.faddr = *saddr;
+		minfo6.lport = inc->i_hdr.h_dport;
+		minfo6.fport = inc->i_hdr.h_sport;
+	} else {
+		minfo6.laddr = *saddr;
+		minfo6.faddr = *daddr;
+		minfo6.lport = inc->i_hdr.h_sport;
+		minfo6.fport = inc->i_hdr.h_dport;
+	}
+
+	rds_info_copy(iter, &minfo6, sizeof(minfo6));
+}

62 lines not on this page · raw message