IB/cma: IBoE (RoCE) IP-based GID addressing

Currently, the IB core and specifically the RDMA-CM assumes that IBoE
(RoCE) gids encode related Ethernet netdevice interface MAC address
and possibly VLAN id.

Change GIDs to be treated as they encode interface IP address.

Since Ethernet layer 2 address parameters are not longer encoded
within gids, we have to extend the Infiniband address structures (e.g.
ib_ah_attr) with layer 2 address parameters, namely mac and vlan.

Signed-off-by: Moni Shoua <monis@mellanox.com>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

drivers/infiniband/core/cma.c

@@ -365,7 +365,9 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv,
 		return -EINVAL;
 
 	mutex_lock(&lock);
-	iboe_addr_get_sgid(dev_addr, &iboe_gid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+		    &iboe_gid);
+
 	memcpy(&gid, dev_addr->src_dev_addr +
 	       rdma_addr_gid_offset(dev_addr), sizeof gid);
 	if (listen_id_priv &&
@@ -1943,10 +1945,10 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	memcpy(route->path_rec->dmac, addr->dev_addr.dst_dev_addr, ETH_ALEN);
 	memcpy(route->path_rec->smac, ndev->dev_addr, ndev->addr_len);
 
-	iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr,
-			    route->path_rec->vlan_id);
-	iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr,
-			    route->path_rec->vlan_id);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+		    &route->path_rec->sgid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr,
+		    &route->path_rec->dgid);
 
 	route->path_rec->hop_limit = 1;
 	route->path_rec->reversible = 1;
@@ -2109,6 +2111,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 			   RDMA_CM_ADDR_RESOLVED))
 		goto out;
 
+	memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
 	if (!status && !id_priv->cma_dev)
 		status = cma_acquire_dev(id_priv, NULL);
 
@@ -2118,10 +2121,8 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 			goto out;
 		event.event = RDMA_CM_EVENT_ADDR_ERROR;
 		event.status = status;
-	} else {
-		memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
+	} else
 		event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
-	}
 
 	if (id_priv->id.event_handler(&id_priv->id, &event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
@@ -2602,6 +2603,7 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 	if (ret)
 		goto err1;
 
+	memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
 	if (!cma_any_addr(addr)) {
 		ret = cma_translate_addr(addr, &id->route.addr.dev_addr);
 		if (ret)
@@ -2612,7 +2614,6 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 			goto err1;
 	}
 
-	memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
 	if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) {
 		if (addr->sa_family == AF_INET)
 			id_priv->afonly = 1;
@@ -3341,7 +3342,8 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 		err = -EINVAL;
 		goto out2;
 	}
-	iboe_addr_get_sgid(dev_addr, &mc->multicast.ib->rec.port_gid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+		    &mc->multicast.ib->rec.port_gid);
 	work->id = id_priv;
 	work->mc = mc;
 	INIT_WORK(&work->work, iboe_mcast_work_handler);

drivers/infiniband/core/ucma.c

@@ -655,24 +655,14 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp,
 static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
 				 struct rdma_route *route)
 {
-	struct rdma_dev_addr *dev_addr;
-	struct net_device *dev;
-	u16 vid = 0;
 
 	resp->num_paths = route->num_paths;
 	switch (route->num_paths) {
 	case 0:
-		dev_addr = &route->addr.dev_addr;
-		dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
-			if (dev) {
-				vid = rdma_vlan_dev_vlan_id(dev);
-				dev_put(dev);
-			}
-
-		iboe_mac_vlan_to_ll((union ib_gid *) &resp->ib_route[0].dgid,
-				    dev_addr->dst_dev_addr, vid);
-		iboe_addr_get_sgid(dev_addr,
-				   (union ib_gid *) &resp->ib_route[0].sgid);
+		rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr,
+			    (union ib_gid *)&resp->ib_route[0].dgid);
+		rdma_ip2gid((struct sockaddr *)&route->addr.src_addr,
+			    (union ib_gid *)&resp->ib_route[0].sgid);
 		resp->ib_route[0].pkey = cpu_to_be16(0xffff);
 		break;
 	case 2:

include/rdma/ib_addr.h

@@ -38,8 +38,12 @@
 #include <linux/in6.h>
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
+#include <linux/inetdevice.h>
 #include <linux/socket.h>
 #include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/if_inet6.h>
+#include <net/ip.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
 #include <net/ipv6.h>
@@ -132,20 +136,10 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr)
 	return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0;
 }
 
-static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid)
+static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
 {
-	memset(gid->raw, 0, 16);
-	*((__be32 *) gid->raw) = cpu_to_be32(0xfe800000);
-	if (vid < 0x1000) {
-		gid->raw[12] = vid & 0xff;
-		gid->raw[11] = vid >> 8;
-	} else {
-		gid->raw[12] = 0xfe;
-		gid->raw[11] = 0xff;
-	}
-	memcpy(gid->raw + 13, mac + 3, 3);
-	memcpy(gid->raw + 8, mac, 3);
-	gid->raw[8] ^= 2;
+	return dev->priv_flags & IFF_802_1Q_VLAN ?
+		vlan_dev_vlan_id(dev) : 0xffff;
 }
 
 static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
@@ -182,25 +176,20 @@ static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
 	return 0;
 }
 
-static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
-{
-	return dev->priv_flags & IFF_802_1Q_VLAN ?
-		vlan_dev_vlan_id(dev) : 0xffff;
-}
-
 static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 				      union ib_gid *gid)
 {
 	struct net_device *dev;
-	u16 vid = 0xffff;
+	struct in_device *ip4;
 
 	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
 	if (dev) {
-		vid = rdma_vlan_dev_vlan_id(dev);
+		ip4 = (struct in_device *)dev->ip_ptr;
+		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)
+			ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address,
+					       (struct in6_addr *)gid);
 		dev_put(dev);
 	}
-
-	iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid);
 }
 
 static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)