net/smc: use correct vlan gid of RoCE device

SMC code uses the base gid for VLAN traffic. The gids exchanged in
the CLC handshake and the gid index used for the QP have to switch
from the base gid to the appropriate vlan gid.

When searching for a matching IB device port for a certain vlan
device, it does not make sense to return an IB device port, which
is not enabled for the used vlan_id. Add another check whether a
vlan gid exists for a certain IB device port.

Signed-off-by: Ursula Braun <ubraun@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/smc/af_smc.c

@@ -370,8 +370,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc)
 	/* send add link reject message, only one link supported for now */
 	rc = smc_llc_send_add_link(link,
 				   link->smcibdev->mac[link->ibport - 1],
-				   &link->smcibdev->gid[link->ibport - 1],
-				   SMC_LLC_RESP);
+				   link->gid, SMC_LLC_RESP);
 	if (rc < 0)
 		return SMC_CLC_DECL_TCL;
 
@@ -469,15 +468,16 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code,
 /* check if there is a rdma device available for this connection. */
 /* called for connect and listen */
 static int smc_check_rdma(struct smc_sock *smc, struct smc_ib_device **ibdev,
-			  u8 *ibport)
+			  u8 *ibport, unsigned short vlan_id, u8 gid[])
 {
 	int reason_code = 0;
 
 	/* PNET table look up: search active ib_device and port
 	 * within same PNETID that also contains the ethernet device
 	 * used for the internal TCP socket
 	 */
-	smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport);
+	smc_pnet_find_roce_resource(smc->clcsock->sk, ibdev, ibport, vlan_id,
+				    gid);
 	if (!(*ibdev))
 		reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */
 
@@ -523,12 +523,12 @@ static int smc_connect_ism_vlan_cleanup(struct smc_sock *smc, bool is_smcd,
 static int smc_connect_clc(struct smc_sock *smc, int smc_type,
 			   struct smc_clc_msg_accept_confirm *aclc,
 			   struct smc_ib_device *ibdev, u8 ibport,
-			   struct smcd_dev *ismdev)
+			   u8 gid[], struct smcd_dev *ismdev)
 {
 	int rc = 0;
 
 	/* do inband token exchange */
-	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, ismdev);
+	rc = smc_clc_send_proposal(smc, smc_type, ibdev, ibport, gid, ismdev);
 	if (rc)
 		return rc;
 	/* receive SMC Accept CLC message */
@@ -650,6 +650,7 @@ static int __smc_connect(struct smc_sock *smc)
 	struct smc_clc_msg_accept_confirm aclc;
 	struct smc_ib_device *ibdev;
 	struct smcd_dev *ismdev;
+	u8 gid[SMC_GID_SIZE];
 	unsigned short vlan;
 	int smc_type;
 	int rc = 0;
@@ -681,7 +682,7 @@ static int __smc_connect(struct smc_sock *smc)
 	}
 
 	/* check if there is a rdma device available */
-	if (!smc_check_rdma(smc, &ibdev, &ibport)) {
+	if (!smc_check_rdma(smc, &ibdev, &ibport, vlan, gid)) {
 		/* RDMA is supported for this connection */
 		rdma_supported = true;
 		if (ism_supported)
@@ -695,7 +696,7 @@ static int __smc_connect(struct smc_sock *smc)
 		return smc_connect_decline_fallback(smc, SMC_CLC_DECL_CNFERR);
 
 	/* perform CLC handshake */
-	rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, ismdev);
+	rc = smc_connect_clc(smc, smc_type, &aclc, ibdev, ibport, gid, ismdev);
 	if (rc) {
 		smc_connect_ism_vlan_cleanup(smc, ism_supported, ismdev, vlan);
 		return smc_connect_decline_fallback(smc, rc);
@@ -970,8 +971,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc)
 	/* send ADD LINK request to client over the RoCE fabric */
 	rc = smc_llc_send_add_link(link,
 				   link->smcibdev->mac[link->ibport - 1],
-				   &link->smcibdev->gid[link->ibport - 1],
-				   SMC_LLC_REQ);
+				   link->gid, SMC_LLC_REQ);
 	if (rc < 0)
 		return SMC_CLC_DECL_TCL;
 
@@ -1193,6 +1193,7 @@ static void smc_listen_work(struct work_struct *work)
 	struct smcd_dev *ismdev;
 	u8 buf[SMC_CLC_MAX_LEN];
 	int local_contact = 0;
+	unsigned short vlan;
 	int reason_code = 0;
 	int rc = 0;
 	u8 ibport;
@@ -1241,7 +1242,8 @@ static void smc_listen_work(struct work_struct *work)
 	/* check if RDMA is available */
 	if (!ism_supported &&
 	    ((pclc->hdr.path != SMC_TYPE_R && pclc->hdr.path != SMC_TYPE_B) ||
-	     smc_check_rdma(new_smc, &ibdev, &ibport) ||
+	     smc_vlan_by_tcpsk(new_smc->clcsock, &vlan) ||
+	     smc_check_rdma(new_smc, &ibdev, &ibport, vlan, NULL) ||
 	     smc_listen_rdma_check(new_smc, pclc) ||
 	     smc_listen_rdma_init(new_smc, pclc, ibdev, ibport,
 				  &local_contact) ||

net/smc/smc_clc.c

@@ -378,7 +378,7 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info)
 
 /* send CLC PROPOSAL message across internal TCP socket */
 int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_ib_device *ibdev, u8 ibport,
+			  struct smc_ib_device *ibdev, u8 ibport, u8 gid[],
 			  struct smcd_dev *ismdev)
 {
 	struct smc_clc_ipv6_prefix ipv6_prfx[SMC_CLC_MAX_V6_PREFIX];
@@ -409,7 +409,7 @@ int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
 		/* add SMC-R specifics */
 		memcpy(pclc.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&pclc.lcl.gid, &ibdev->gid[ibport - 1], SMC_GID_SIZE);
+		memcpy(&pclc.lcl.gid, gid, SMC_GID_SIZE);
 		memcpy(&pclc.lcl.mac, &ibdev->mac[ibport - 1], ETH_ALEN);
 		pclc.iparea_offset = htons(0);
 	}
@@ -492,8 +492,7 @@ int smc_clc_send_confirm(struct smc_sock *smc)
 		cclc.hdr.length = htons(SMCR_CLC_ACCEPT_CONFIRM_LEN);
 		memcpy(cclc.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&cclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
-		       SMC_GID_SIZE);
+		memcpy(&cclc.lcl.gid, link->gid, SMC_GID_SIZE);
 		memcpy(&cclc.lcl.mac, &link->smcibdev->mac[link->ibport - 1],
 		       ETH_ALEN);
 		hton24(cclc.qpn, link->roce_qp->qp_num);
@@ -566,8 +565,7 @@ int smc_clc_send_accept(struct smc_sock *new_smc, int srv_first_contact)
 		link = &conn->lgr->lnk[SMC_SINGLE_LINK];
 		memcpy(aclc.lcl.id_for_peer, local_systemid,
 		       sizeof(local_systemid));
-		memcpy(&aclc.lcl.gid, &link->smcibdev->gid[link->ibport - 1],
-		       SMC_GID_SIZE);
+		memcpy(&aclc.lcl.gid, link->gid, SMC_GID_SIZE);
 		memcpy(&aclc.lcl.mac, link->smcibdev->mac[link->ibport - 1],
 		       ETH_ALEN);
 		hton24(aclc.qpn, link->roce_qp->qp_num);

net/smc/smc_clc.h

@@ -179,7 +179,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen,
 		     u8 expected_type);
 int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info);
 int smc_clc_send_proposal(struct smc_sock *smc, int smc_type,
-			  struct smc_ib_device *smcibdev, u8 ibport,
+			  struct smc_ib_device *smcibdev, u8 ibport, u8 gid[],
 			  struct smcd_dev *ismdev);
 int smc_clc_send_confirm(struct smc_sock *smc);
 int smc_clc_send_accept(struct smc_sock *smc, int srv_first_contact);

net/smc/smc_core.c

@@ -219,6 +219,10 @@ static int smc_lgr_create(struct smc_sock *smc, bool is_smcd,
 		get_random_bytes(rndvec, sizeof(rndvec));
 		lnk->psn_initial = rndvec[0] + (rndvec[1] << 8) +
 			(rndvec[2] << 16);
+		rc = smc_ib_determine_gid(lnk->smcibdev, lnk->ibport,
+					  vlan_id, lnk->gid, &lnk->sgid_index);
+		if (rc)
+			goto free_lgr;
 		rc = smc_llc_link_init(lnk);
 		if (rc)
 			goto free_lgr;
@@ -522,37 +526,6 @@ int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id)
 	return rc;
 }
 
-/* determine the link gid matching the vlan id of the link group */
-static int smc_link_determine_gid(struct smc_link_group *lgr)
-{
-	struct smc_link *lnk = &lgr->lnk[SMC_SINGLE_LINK];
-	struct ib_gid_attr gattr;
-	union ib_gid gid;
-	int i;
-
-	if (!lgr->vlan_id) {
-		lnk->gid = lnk->smcibdev->gid[lnk->ibport - 1];
-		return 0;
-	}
-
-	for (i = 0; i < lnk->smcibdev->pattr[lnk->ibport - 1].gid_tbl_len;
-	     i++) {
-		if (ib_query_gid(lnk->smcibdev->ibdev, lnk->ibport, i, &gid,
-				 &gattr))
-			continue;
-		if (gattr.ndev) {
-			if (is_vlan_dev(gattr.ndev) &&
-			    vlan_dev_vlan_id(gattr.ndev) == lgr->vlan_id) {
-				lnk->gid = gid;
-				dev_put(gattr.ndev);
-				return 0;
-			}
-			dev_put(gattr.ndev);
-		}
-	}
-	return -ENODEV;
-}
-
 static bool smcr_lgr_match(struct smc_link_group *lgr,
 			   struct smc_clc_msg_local *lcl,
 			   enum smc_lgr_role role)
@@ -631,8 +604,6 @@ int smc_conn_create(struct smc_sock *smc, bool is_smcd, int srv_first_contact,
 		if (rc)
 			goto out;
 		smc_lgr_register_conn(conn); /* add smc conn to lgr */
-		if (!is_smcd)
-			rc = smc_link_determine_gid(conn->lgr);
 	}
 	conn->local_tx_ctrl.common.type = SMC_CDC_MSG_TYPE;
 	conn->local_tx_ctrl.len = SMC_WR_TX_SIZE;

net/smc/smc_core.h

@@ -84,14 +84,15 @@ struct smc_link {
 	wait_queue_head_t	wr_reg_wait;	/* wait for wr_reg result */
 	enum smc_wr_reg_state	wr_reg_state;	/* state of wr_reg request */
 
-	union ib_gid		gid;		/* gid matching used vlan id */
+	u8			gid[SMC_GID_SIZE];/* gid matching used vlan id*/
+	u8			sgid_index;	/* gid index for vlan id      */
 	u32			peer_qpn;	/* QP number of peer */
 	enum ib_mtu		path_mtu;	/* used mtu */
 	enum ib_mtu		peer_mtu;	/* mtu size of peer */
 	u32			psn_initial;	/* QP tx initial packet seqno */
 	u32			peer_psn;	/* QP rx initial packet seqno */
 	u8			peer_mac[ETH_ALEN];	/* = gid[8:10||13:15] */
-	u8			peer_gid[sizeof(union ib_gid)];	/* gid of peer*/
+	u8			peer_gid[SMC_GID_SIZE];	/* gid of peer*/
 	u8			link_id;	/* unique # within link group */
 
 	enum smc_link_state	state;		/* state of link */

net/smc/smc_diag.c

@@ -154,7 +154,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb,
 		       smc->conn.lgr->lnk[0].smcibdev->ibdev->name,
 		       sizeof(smc->conn.lgr->lnk[0].smcibdev->ibdev->name));
 		smc_gid_be16_convert(linfo.lnk[0].gid,
-				     smc->conn.lgr->lnk[0].gid.raw);
+				     smc->conn.lgr->lnk[0].gid);
 		smc_gid_be16_convert(linfo.lnk[0].peer_gid,
 				     smc->conn.lgr->lnk[0].peer_gid);
 

net/smc/smc_ib.c

@@ -68,7 +68,7 @@ static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
 	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, 0, 1, 0);
+	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
 	rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
 	memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
 	       sizeof(lnk->peer_mac));
@@ -142,13 +142,13 @@ int smc_ib_ready_link(struct smc_link *lnk)
 	return rc;
 }
 
-static int smc_ib_fill_gid_and_mac(struct smc_ib_device *smcibdev, u8 ibport)
+static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	struct ib_gid_attr gattr;
+	union ib_gid gid;
 	int rc;
 
-	rc = ib_query_gid(smcibdev->ibdev, ibport, 0,
-			  &smcibdev->gid[ibport - 1], &gattr);
+	rc = ib_query_gid(smcibdev->ibdev, ibport, 0, &gid, &gattr);
 	if (rc || !gattr.ndev)
 		return -ENODEV;
 
@@ -175,6 +175,37 @@ bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
 	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
 }
 
+/* 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)
+{
+	struct ib_gid_attr gattr;
+	union ib_gid _gid;
+	int i;
+
+	for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
+		memset(&_gid, 0, SMC_GID_SIZE);
+		memset(&gattr, 0, sizeof(gattr));
+		if (ib_query_gid(smcibdev->ibdev, ibport, i, &_gid, &gattr))
+			continue;
+		if (!gattr.ndev)
+			continue;
+		if (((!vlan_id && !is_vlan_dev(gattr.ndev)) ||
+		     (vlan_id && is_vlan_dev(gattr.ndev) &&
+		      vlan_dev_vlan_id(gattr.ndev) == vlan_id)) &&
+		    gattr.gid_type == IB_GID_TYPE_IB) {
+			if (gid)
+				memcpy(gid, &_gid, SMC_GID_SIZE);
+			if (sgid_index)
+				*sgid_index = i;
+			dev_put(gattr.ndev);
+			return 0;
+		}
+		dev_put(gattr.ndev);
+	}
+	return -ENODEV;
+}
+
 static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
 {
 	int rc;
@@ -186,7 +217,7 @@ static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
 	if (rc)
 		goto out;
 	/* the SMC protocol requires specification of the RoCE MAC address */
-	rc = smc_ib_fill_gid_and_mac(smcibdev, ibport);
+	rc = smc_ib_fill_mac(smcibdev, ibport);
 	if (rc)
 		goto out;
 	if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,

net/smc/smc_ib.h

@@ -40,7 +40,6 @@ struct smc_ib_device {				/* ib-device infos for smc */
 	struct tasklet_struct	recv_tasklet;	/* called by recv cq handler */
 	char			mac[SMC_MAX_PORTS][ETH_ALEN];
 						/* mac address per port*/
-	union ib_gid		gid[SMC_MAX_PORTS]; /* gid per port */
 	u8			pnetid[SMC_MAX_PORTS][SMC_MAX_PNETID_LEN];
 						/* pnetid per port */
 	u8			initialized : 1; /* ib dev CQ, evthdl done */
@@ -77,4 +76,6 @@ void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
 void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
 			       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);
 #endif

net/smc/smc_llc.c

@@ -203,8 +203,7 @@ int smc_llc_send_confirm_link(struct smc_link *link,
 		confllc->hd.flags |= SMC_LLC_FLAG_RESP;
 	memcpy(confllc->sender_mac, link->smcibdev->mac[link->ibport - 1],
 	       ETH_ALEN);
-	memcpy(confllc->sender_gid, &link->smcibdev->gid[link->ibport - 1],
-	       SMC_GID_SIZE);
+	memcpy(confllc->sender_gid, link->gid, SMC_GID_SIZE);
 	hton24(confllc->sender_qp_num, link->roce_qp->qp_num);
 	confllc->link_num = link->link_id;
 	memcpy(confllc->link_uid, lgr->id, SMC_LGR_ID_SIZE);
@@ -241,8 +240,7 @@ static int smc_llc_send_confirm_rkey(struct smc_link *link,
 
 /* prepare an add link message */
 static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
-				  struct smc_link *link, u8 mac[],
-				  union ib_gid *gid,
+				  struct smc_link *link, u8 mac[], u8 gid[],
 				  enum smc_llc_reqresp reqresp)
 {
 	memset(addllc, 0, sizeof(*addllc));
@@ -259,8 +257,7 @@ static void smc_llc_prep_add_link(struct smc_llc_msg_add_link *addllc,
 }
 
 /* send ADD LINK request or response */
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[],
-			  union ib_gid *gid,
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
 			  enum smc_llc_reqresp reqresp)
 {
 	struct smc_llc_msg_add_link *addllc;
@@ -423,14 +420,12 @@ static void smc_llc_rx_add_link(struct smc_link *link,
 		if (lgr->role == SMC_SERV) {
 			smc_llc_prep_add_link(llc, link,
 					link->smcibdev->mac[link->ibport - 1],
-					&link->smcibdev->gid[link->ibport - 1],
-					SMC_LLC_REQ);
+					link->gid, SMC_LLC_REQ);
 
 		} else {
 			smc_llc_prep_add_link(llc, link,
 					link->smcibdev->mac[link->ibport - 1],
-					&link->smcibdev->gid[link->ibport - 1],
-					SMC_LLC_RESP);
+					link->gid, SMC_LLC_RESP);
 		}
 		smc_llc_send_message(link, llc, sizeof(*llc));
 	}

net/smc/smc_llc.h

@@ -38,7 +38,7 @@ enum smc_llc_msg_type {
 /* transmit */
 int smc_llc_send_confirm_link(struct smc_link *lnk,
 			      enum smc_llc_reqresp reqresp);
-int smc_llc_send_add_link(struct smc_link *link, u8 mac[], union ib_gid *gid,
+int smc_llc_send_add_link(struct smc_link *link, u8 mac[], u8 gid[],
 			  enum smc_llc_reqresp reqresp);
 int smc_llc_send_delete_link(struct smc_link *link,
 			     enum smc_llc_reqresp reqresp);