net/smc: retrieve v2 gid from IB device

In smc_ib.c, scan for RoCE devices that support UDP encapsulation.
Find an eligible device and check that there is a route to the
remote peer.
Signed-off-by: Karsten Graul <kgraul@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/smc_core.c

@@ -715,7 +715,9 @@ int smcr_link_init(struct smc_link_group *lgr, struct smc_link *lnk,
 	lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
 		(rndvec[2] << 16);
 	rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport,
-				  ini->vlan_id, lnk->gid, &lnk->sgid_index);
+				  ini->vlan_id, lnk->gid, &lnk->sgid_index,
+				  lgr->smc_version == SMC_V2 ?
+						  &ini->smcrv2 : NULL);
 	if (rc)
 		goto out;
 	rc = smc_llc_link_init(lnk);

net/smc/smc_ib.c

@@ -17,6 +17,7 @@
 #include <linux/scatterlist.h>
 #include <linux/wait.h>
 #include <linux/mutex.h>
+#include <linux/inetdevice.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
 
@@ -62,14 +63,21 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
 		IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN |
 		IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER;
 	struct ib_qp_attr qp_attr;
+	u8 hop_lim = 1;
 
 	memset(&qp_attr, 0, sizeof(qp_attr));
 	qp_attr.qp_state = IB_QPS_RTR;
 	qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu);
 	qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
 	rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport);
-	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
+	if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway)
+		hop_lim = IPV6_DEFAULT_HOPLIMIT;
+	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, hop_lim, 0);
 	rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
+	if (lnk->lgr->smc_version == SMC_V2 && lnk->lgr->uses_gateway)
+		memcpy(&qp_attr.ah_attr.roce.dmac, lnk->lgr->nexthop_mac,
+		       sizeof(lnk->lgr->nexthop_mac));
+	else
 		memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
 		       sizeof(lnk->peer_mac));
 	qp_attr.dest_qp_num = lnk->peer_qpn;
@@ -210,9 +218,54 @@ int smc_ib_find_route(__be32 saddr, __be32 daddr,
 	return -ENOENT;
 }
 
+static int smc_ib_determine_gid_rcu(const struct net_device *ndev,
+				    const struct ib_gid_attr *attr,
+				    u8 gid[], u8 *sgid_index,
+				    struct smc_init_info_smcrv2 *smcrv2)
+{
+	if (!smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE) {
+		if (gid)
+			memcpy(gid, &attr->gid, SMC_GID_SIZE);
+		if (sgid_index)
+			*sgid_index = attr->index;
+		return 0;
+	}
+	if (smcrv2 && attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP &&
+	    smc_ib_gid_to_ipv4((u8 *)&attr->gid) != cpu_to_be32(INADDR_NONE)) {
+		struct in_device *in_dev = __in_dev_get_rcu(ndev);
+		const struct in_ifaddr *ifa;
+		bool subnet_match = false;
+
+		if (!in_dev)
+			goto out;
+		in_dev_for_each_ifa_rcu(ifa, in_dev) {
+			if (!inet_ifa_match(smcrv2->saddr, ifa))
+				continue;
+			subnet_match = true;
+			break;
+		}
+		if (!subnet_match)
+			goto out;
+		if (smcrv2->daddr && smc_ib_find_route(smcrv2->saddr,
+						       smcrv2->daddr,
+						       smcrv2->nexthop_mac,
+						       &smcrv2->uses_gateway))
+			goto out;
+
+		if (gid)
+			memcpy(gid, &attr->gid, SMC_GID_SIZE);
+		if (sgid_index)
+			*sgid_index = attr->index;
+		return 0;
+	}
+out:
+	return -ENODEV;
+}
+
 /* determine the gid for an ib-device port and vlan id */
 int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
-			 unsigned short vlan_id, u8 gid[], u8 *sgid_index)
+			 unsigned short vlan_id, u8 gid[], u8 *sgid_index,
+			 struct smc_init_info_smcrv2 *smcrv2)
 {
 	const struct ib_gid_attr *attr;
 	const struct net_device *ndev;
@@ -228,16 +281,14 @@ int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
 		if (!IS_ERR(ndev) &&
 		    ((!vlan_id && !is_vlan_dev(ndev)) ||
 		     (vlan_id && is_vlan_dev(ndev) &&
-		      vlan_dev_vlan_id(ndev) == vlan_id)) &&
-		    attr->gid_type == IB_GID_TYPE_ROCE) {
+		      vlan_dev_vlan_id(ndev) == vlan_id))) {
+			if (!smc_ib_determine_gid_rcu(ndev, attr, gid,
+						      sgid_index, smcrv2)) {
 				rcu_read_unlock();
-			if (gid)
-				memcpy(gid, &attr->gid, SMC_GID_SIZE);
-			if (sgid_index)
-				*sgid_index = attr->index;
 				rdma_put_gid_attr(attr);
 				return 0;
 			}
+		}
 		rcu_read_unlock();
 		rdma_put_gid_attr(attr);
 	}

net/smc/smc_ib.h

@@ -101,7 +101,8 @@ void smc_ib_sync_sg_for_device(struct smc_link *lnk,
 			       struct smc_buf_desc *buf_slot,
 			       enum dma_data_direction data_direction);
 int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
-			 unsigned short vlan_id, u8 gid[], u8 *sgid_index);
+			 unsigned short vlan_id, u8 gid[], u8 *sgid_index,
+			 struct smc_init_info_smcrv2 *smcrv2);
 int smc_ib_find_route(__be32 saddr, __be32 daddr,
 		      u8 nexthop_mac[], u8 *uses_gateway);
 bool smc_ib_is_valid_local_systemid(void);

net/smc/smc_pnet.c

@@ -953,6 +953,26 @@ static int smc_pnet_find_ndev_pnetid_by_table(struct net_device *ndev,
 	return rc;
 }
 
+static int smc_pnet_determine_gid(struct smc_ib_device *ibdev, int i,
+				  struct smc_init_info *ini)
+{
+	if (!ini->check_smcrv2 &&
+	    !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->ib_gid, NULL,
+				  NULL)) {
+		ini->ib_dev = ibdev;
+		ini->ib_port = i;
+		return 0;
+	}
+	if (ini->check_smcrv2 &&
+	    !smc_ib_determine_gid(ibdev, i, ini->vlan_id, ini->smcrv2.ib_gid_v2,
+				  NULL, &ini->smcrv2)) {
+		ini->smcrv2.ib_dev_v2 = ibdev;
+		ini->smcrv2.ib_port_v2 = i;
+		return 0;
+	}
+	return -ENODEV;
+}
+
 /* find a roce device for the given pnetid */
 static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id,
 					  struct smc_init_info *ini,
@@ -961,7 +981,6 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id,
 	struct smc_ib_device *ibdev;
 	int i;
 
-	ini->ib_dev = NULL;
 	mutex_lock(&smc_ib_devices.mutex);
 	list_for_each_entry(ibdev, &smc_ib_devices.list, list) {
 		if (ibdev == known_dev)
@@ -971,11 +990,8 @@ static void _smc_pnet_find_roce_by_pnetid(u8 *pnet_id,
 				continue;
 			if (smc_pnet_match(ibdev->pnetid[i - 1], pnet_id) &&
 			    smc_ib_port_active(ibdev, i) &&
-			    !test_bit(i - 1, ibdev->ports_going_away) &&
-			    !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
-						  ini->ib_gid, NULL)) {
-				ini->ib_dev = ibdev;
-				ini->ib_port = i;
+			    !test_bit(i - 1, ibdev->ports_going_away)) {
+				if (!smc_pnet_determine_gid(ibdev, i, ini))
 					goto out;
 			}
 		}
@@ -1016,11 +1032,8 @@ static void smc_pnet_find_rdma_dev(struct net_device *netdev,
 			dev_put(ndev);
 			if (netdev == ndev &&
 			    smc_ib_port_active(ibdev, i) &&
-			    !test_bit(i - 1, ibdev->ports_going_away) &&
-			    !smc_ib_determine_gid(ibdev, i, ini->vlan_id,
-						  ini->ib_gid, NULL)) {
-				ini->ib_dev = ibdev;
-				ini->ib_port = i;
+			    !test_bit(i - 1, ibdev->ports_going_away)) {
+				if (!smc_pnet_determine_gid(ibdev, i, ini))
 					break;
 			}
 		}
@@ -1083,8 +1096,6 @@ void smc_pnet_find_roce_resource(struct sock *sk, struct smc_init_info *ini)
 {
 	struct dst_entry *dst = sk_dst_get(sk);
 
-	ini->ib_dev = NULL;
-	ini->ib_port = 0;
 	if (!dst)
 		goto out;
 	if (!dst->dev)