rds: Enable RDS IPv6 support

This patch enables RDS to use IPv6 addresses. For RDS/TCP, the
listener is now an IPv6 endpoint which accepts both IPv4 and IPv6
connection requests.  RDS/RDMA/IB uses a private data (struct
rds_ib_connect_private) exchange between endpoints at RDS connection
establishment time to support RDMA. This private data exchange uses a
32 bit integer to represent an IP address. This needs to be changed in
order to support IPv6. A new private data struct
rds6_ib_connect_private is introduced to handle this. To ensure
backward compatibility, an IPv6 capable RDS stack uses another RDMA
listener port (RDS_CM_PORT) to accept IPv6 connection. And it
continues to use the original RDS_PORT for IPv4 RDS connections. When
it needs to communicate with an IPv6 peer, it uses the RDS_CM_PORT to
send the connection set up request.

v5: Fixed syntax problem (David Miller).

v4: Changed port history comments in rds.h (Sowmini Varadhan).

v3: Added support to set up IPv4 connection using mapped address
    (David Miller).
    Added support to set up connection between link local and non-link
    addresses.
    Various review comments from Santosh Shilimkar and Sowmini Varadhan.

v2: Fixed bound and peer address scope mismatched issue.
    Added back rds_connect() IPv6 changes.

Signed-off-by: Ka-Cheong Poon <ka-cheong.poon@oracle.com>
Acked-by: Santosh Shilimkar <santosh.shilimkar@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 54 insertions, 7 deletions

diff --git a/net/rds/send.c b/net/rds/send.c
index 6ed2e925c36a..9604e1faa564 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -1091,10 +1091,9 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			ret = -EINVAL;
 			goto out;
 		}
-		switch (namelen) {
-		case sizeof(*usin):
-			if (usin->sin_family != AF_INET ||
-			    usin->sin_addr.s_addr == htonl(INADDR_ANY) ||
+		switch (usin->sin_family) {
+		case AF_INET:
+			if (usin->sin_addr.s_addr == htonl(INADDR_ANY) ||
 			    usin->sin_addr.s_addr == htonl(INADDR_BROADCAST) ||
 			    IN_MULTICAST(ntohl(usin->sin_addr.s_addr))) {
 				ret = -EINVAL;
@@ -1104,9 +1103,44 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			dport = usin->sin_port;
 			break;
 
-		case sizeof(*sin6): {
-			ret = -EPROTONOSUPPORT;
-			goto out;
+		case AF_INET6: {
+			int addr_type;
+
+			if (namelen < sizeof(*sin6)) {
+				ret = -EINVAL;
+				goto out;
+			}
+			addr_type = ipv6_addr_type(&sin6->sin6_addr);
+			if (!(addr_type & IPV6_ADDR_UNICAST)) {
+				__be32 addr4;
+
+				if (!(addr_type & IPV6_ADDR_MAPPED)) {
+					ret = -EINVAL;
+					goto out;
+				}
+
+				/* 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))) {
+					return -EINVAL;
+					goto out;
+				}
+			}
+			if (addr_type & IPV6_ADDR_LINKLOCAL) {
+				if (sin6->sin6_scope_id == 0) {
+					ret = -EINVAL;
+					goto out;
+				}
+				scope_id = sin6->sin6_scope_id;
+			}
+
+			daddr = sin6->sin6_addr;
+			dport = sin6->sin6_port;
+			break;
 		}
 
 		default:
@@ -1138,6 +1172,19 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 			ret = -EOPNOTSUPP;
 			goto out;
 		}
+		/* If the socket is already bound to a link local address,
+		 * it can only send to peers on the same link.  But allow
+		 * communicating beween link local and non-link local address.
+		 */
+		if (scope_id != rs->rs_bound_scope_id) {
+			if (!scope_id) {
+				scope_id = rs->rs_bound_scope_id;
+			} else if (rs->rs_bound_scope_id) {
+				release_sock(sk);
+				ret = -EINVAL;
+				goto out;
+			}
+		}
 	}
 	release_sock(sk);