Merge branch 'ip-roce' into for-next

Conflicts:
	drivers/infiniband/hw/mlx4/main.c

drivers/infiniband/Kconfig

@@ -3,6 +3,8 @@ menuconfig INFINIBAND
 	depends on PCI || BROKEN
 	depends on HAS_IOMEM
 	depends on NET
+	depends on INET
+	depends on m || IPV6 != m
 	---help---
 	  Core support for InfiniBand (IB).  Make sure to also select
 	  any protocols you wish to use as well as drivers for your
@@ -38,8 +40,7 @@ config INFINIBAND_USER_MEM
 
 config INFINIBAND_ADDR_TRANS
 	bool
-	depends on INET
+	depends on INFINIBAND
-	depends on !(INFINIBAND = y && IPV6 = m)
 	default y
 
 source "drivers/infiniband/hw/mthca/Kconfig"

drivers/infiniband/core/Makefile

@@ -1,8 +1,9 @@
-infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= ib_addr.o rdma_cm.o
+infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_cm.o
 user_access-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_ucm.o
 
 obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_mad.o ib_sa.o \
-					ib_cm.o iw_cm.o $(infiniband-y)
+					ib_cm.o iw_cm.o ib_addr.o \
+					$(infiniband-y)
 obj-$(CONFIG_INFINIBAND_USER_MAD) +=	ib_umad.o
 obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 					$(user_access-y)

drivers/infiniband/core/addr.c

@@ -86,6 +86,8 @@ int rdma_addr_size(struct sockaddr *addr)
 }
 EXPORT_SYMBOL(rdma_addr_size);
 
+static struct rdma_addr_client self;
+
 void rdma_addr_register_client(struct rdma_addr_client *client)
 {
 	atomic_set(&client->refcount, 1);
@@ -119,7 +121,8 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
 }
 EXPORT_SYMBOL(rdma_copy_addr);
 
-int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr)
+int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
+		      u16 *vlan_id)
 {
 	struct net_device *dev;
 	int ret = -EADDRNOTAVAIL;
@@ -142,6 +145,8 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr)
 			return ret;
 
 		ret = rdma_copy_addr(dev_addr, dev, NULL);
+		if (vlan_id)
+			*vlan_id = rdma_vlan_dev_vlan_id(dev);
 		dev_put(dev);
 		break;
 
@@ -153,6 +158,8 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr)
 					  &((struct sockaddr_in6 *) addr)->sin6_addr,
 					  dev, 1)) {
 				ret = rdma_copy_addr(dev_addr, dev, NULL);
+				if (vlan_id)
+					*vlan_id = rdma_vlan_dev_vlan_id(dev);
 				break;
 			}
 		}
@@ -238,7 +245,7 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 	src_in->sin_addr.s_addr = fl4.saddr;
 
 	if (rt->dst.dev->flags & IFF_LOOPBACK) {
-		ret = rdma_translate_ip((struct sockaddr *) dst_in, addr);
+		ret = rdma_translate_ip((struct sockaddr *)dst_in, addr, NULL);
 		if (!ret)
 			memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
 		goto put;
@@ -286,7 +293,7 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 	}
 
 	if (dst->dev->flags & IFF_LOOPBACK) {
-		ret = rdma_translate_ip((struct sockaddr *) dst_in, addr);
+		ret = rdma_translate_ip((struct sockaddr *)dst_in, addr, NULL);
 		if (!ret)
 			memcpy(addr->dst_dev_addr, addr->src_dev_addr, MAX_ADDR_LEN);
 		goto put;
@@ -437,6 +444,88 @@ void rdma_addr_cancel(struct rdma_dev_addr *addr)
 }
 EXPORT_SYMBOL(rdma_addr_cancel);
 
+struct resolve_cb_context {
+	struct rdma_dev_addr *addr;
+	struct completion comp;
+};
+
+static void resolve_cb(int status, struct sockaddr *src_addr,
+	     struct rdma_dev_addr *addr, void *context)
+{
+	memcpy(((struct resolve_cb_context *)context)->addr, addr, sizeof(struct
+				rdma_dev_addr));
+	complete(&((struct resolve_cb_context *)context)->comp);
+}
+
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
+			       u16 *vlan_id)
+{
+	int ret = 0;
+	struct rdma_dev_addr dev_addr;
+	struct resolve_cb_context ctx;
+	struct net_device *dev;
+
+	union {
+		struct sockaddr     _sockaddr;
+		struct sockaddr_in  _sockaddr_in;
+		struct sockaddr_in6 _sockaddr_in6;
+	} sgid_addr, dgid_addr;
+
+
+	ret = rdma_gid2ip(&sgid_addr._sockaddr, sgid);
+	if (ret)
+		return ret;
+
+	ret = rdma_gid2ip(&dgid_addr._sockaddr, dgid);
+	if (ret)
+		return ret;
+
+	memset(&dev_addr, 0, sizeof(dev_addr));
+
+	ctx.addr = &dev_addr;
+	init_completion(&ctx.comp);
+	ret = rdma_resolve_ip(&self, &sgid_addr._sockaddr, &dgid_addr._sockaddr,
+			&dev_addr, 1000, resolve_cb, &ctx);
+	if (ret)
+		return ret;
+
+	wait_for_completion(&ctx.comp);
+
+	memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
+	dev = dev_get_by_index(&init_net, dev_addr.bound_dev_if);
+	if (!dev)
+		return -ENODEV;
+	if (vlan_id)
+		*vlan_id = rdma_vlan_dev_vlan_id(dev);
+	dev_put(dev);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_addr_find_dmac_by_grh);
+
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
+{
+	int ret = 0;
+	struct rdma_dev_addr dev_addr;
+	union {
+		struct sockaddr     _sockaddr;
+		struct sockaddr_in  _sockaddr_in;
+		struct sockaddr_in6 _sockaddr_in6;
+	} gid_addr;
+
+	ret = rdma_gid2ip(&gid_addr._sockaddr, sgid);
+
+	if (ret)
+		return ret;
+	memset(&dev_addr, 0, sizeof(dev_addr));
+	ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id);
+	if (ret)
+		return ret;
+
+	memcpy(smac, dev_addr.src_dev_addr, ETH_ALEN);
+	return ret;
+}
+EXPORT_SYMBOL(rdma_addr_find_smac_by_sgid);
+
 static int netevent_callback(struct notifier_block *self, unsigned long event,
 	void *ctx)
 {
@@ -461,11 +550,13 @@ static int __init addr_init(void)
 		return -ENOMEM;
 
 	register_netevent_notifier(&nb);
+	rdma_addr_register_client(&self);
 	return 0;
 }
 
 static void __exit addr_cleanup(void)
 {
+	rdma_addr_unregister_client(&self);
 	unregister_netevent_notifier(&nb);
 	destroy_workqueue(addr_wq);
 }

drivers/infiniband/core/cm.c

@@ -47,6 +47,7 @@
 #include <linux/sysfs.h>
 #include <linux/workqueue.h>
 #include <linux/kdev_t.h>
+#include <linux/etherdevice.h>
 
 #include <rdma/ib_cache.h>
 #include <rdma/ib_cm.h>
@@ -177,6 +178,8 @@ struct cm_av {
 	struct ib_ah_attr ah_attr;
 	u16 pkey_index;
 	u8 timeout;
+	u8  valid;
+	u8  smac[ETH_ALEN];
 };
 
 struct cm_work {
@@ -346,6 +349,23 @@ static void cm_init_av_for_response(struct cm_port *port, struct ib_wc *wc,
 			   grh, &av->ah_attr);
 }
 
+int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac)
+{
+	struct cm_id_private *cm_id_priv;
+
+	cm_id_priv = container_of(id, struct cm_id_private, id);
+
+	if (smac != NULL)
+		memcpy(cm_id_priv->av.smac, smac, sizeof(cm_id_priv->av.smac));
+
+	if (alt_smac != NULL)
+		memcpy(cm_id_priv->alt_av.smac, alt_smac,
+		       sizeof(cm_id_priv->alt_av.smac));
+
+	return 0;
+}
+EXPORT_SYMBOL(ib_update_cm_av);
+
 static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
 {
 	struct cm_device *cm_dev;
@@ -376,6 +396,9 @@ static int cm_init_av_by_path(struct ib_sa_path_rec *path, struct cm_av *av)
 	ib_init_ah_from_path(cm_dev->ib_device, port->port_num, path,
 			     &av->ah_attr);
 	av->timeout = path->packet_life_time + 1;
+	memcpy(av->smac, path->smac, sizeof(av->smac));
+
+	av->valid = 1;
 	return 0;
 }
 
@@ -1554,6 +1577,9 @@ static int cm_req_handler(struct cm_work *work)
 
 	cm_process_routed_req(req_msg, work->mad_recv_wc->wc);
 	cm_format_paths_from_req(req_msg, &work->path[0], &work->path[1]);
+
+	memcpy(work->path[0].dmac, cm_id_priv->av.ah_attr.dmac, ETH_ALEN);
+	work->path[0].vlan_id = cm_id_priv->av.ah_attr.vlan_id;
 	ret = cm_init_av_by_path(&work->path[0], &cm_id_priv->av);
 	if (ret) {
 		ib_get_cached_gid(work->port->cm_dev->ib_device,
@@ -3500,6 +3526,32 @@ static int cm_init_qp_rtr_attr(struct cm_id_private *cm_id_priv,
 		*qp_attr_mask = IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU |
 				IB_QP_DEST_QPN | IB_QP_RQ_PSN;
 		qp_attr->ah_attr = cm_id_priv->av.ah_attr;
+		if (!cm_id_priv->av.valid) {
+			spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+			return -EINVAL;
+		}
+		if (cm_id_priv->av.ah_attr.vlan_id != 0xffff) {
+			qp_attr->vlan_id = cm_id_priv->av.ah_attr.vlan_id;
+			*qp_attr_mask |= IB_QP_VID;
+		}
+		if (!is_zero_ether_addr(cm_id_priv->av.smac)) {
+			memcpy(qp_attr->smac, cm_id_priv->av.smac,
+			       sizeof(qp_attr->smac));
+			*qp_attr_mask |= IB_QP_SMAC;
+		}
+		if (cm_id_priv->alt_av.valid) {
+			if (cm_id_priv->alt_av.ah_attr.vlan_id != 0xffff) {
+				qp_attr->alt_vlan_id =
+					cm_id_priv->alt_av.ah_attr.vlan_id;
+				*qp_attr_mask |= IB_QP_ALT_VID;
+			}
+			if (!is_zero_ether_addr(cm_id_priv->alt_av.smac)) {
+				memcpy(qp_attr->alt_smac,
+				       cm_id_priv->alt_av.smac,
+				       sizeof(qp_attr->alt_smac));
+				*qp_attr_mask |= IB_QP_ALT_SMAC;
+			}
+		}
 		qp_attr->path_mtu = cm_id_priv->path_mtu;
 		qp_attr->dest_qp_num = be32_to_cpu(cm_id_priv->remote_qpn);
 		qp_attr->rq_psn = be32_to_cpu(cm_id_priv->rq_psn);

drivers/infiniband/core/cma.c

@@ -340,7 +340,7 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a
 	int ret;
 
 	if (addr->sa_family != AF_IB) {
-		ret = rdma_translate_ip(addr, dev_addr);
+		ret = rdma_translate_ip(addr, dev_addr, NULL);
 	} else {
 		cma_translate_ib((struct sockaddr_ib *) addr, dev_addr);
 		ret = 0;
@@ -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 &&
@@ -603,6 +605,7 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 {
 	struct ib_qp_attr qp_attr;
 	int qp_attr_mask, ret;
+	union ib_gid sgid;
 
 	mutex_lock(&id_priv->qp_mutex);
 	if (!id_priv->id.qp) {
@@ -625,6 +628,20 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 	if (ret)
 		goto out;
 
+	ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
+			   qp_attr.ah_attr.grh.sgid_index, &sgid);
+	if (ret)
+		goto out;
+
+	if (rdma_node_get_transport(id_priv->cma_dev->device->node_type)
+	    == RDMA_TRANSPORT_IB &&
+	    rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
+	    == IB_LINK_LAYER_ETHERNET) {
+		ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
+
+		if (ret)
+			goto out;
+	}
 	if (conn_param)
 		qp_attr.max_dest_rd_atomic = conn_param->responder_resources;
 	ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
@@ -725,6 +742,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 		else
 			ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr,
 						 qp_attr_mask);
+
 		if (qp_attr->qp_state == IB_QPS_RTR)
 			qp_attr->rq_psn = id_priv->seq_num;
 		break;
@@ -1266,6 +1284,15 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	struct rdma_id_private *listen_id, *conn_id;
 	struct rdma_cm_event event;
 	int offset, ret;
+	u8 smac[ETH_ALEN];
+	u8 alt_smac[ETH_ALEN];
+	u8 *psmac = smac;
+	u8 *palt_smac = alt_smac;
+	int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) ==
+			RDMA_TRANSPORT_IB) &&
+		       (rdma_port_get_link_layer(cm_id->device,
+			ib_event->param.req_rcvd.port) ==
+			IB_LINK_LAYER_ETHERNET));
 
 	listen_id = cm_id->context;
 	if (!cma_check_req_qp_type(&listen_id->id, ib_event))
@@ -1310,12 +1337,29 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	if (ret)
 		goto err3;
 
+	if (is_iboe) {
+		if (ib_event->param.req_rcvd.primary_path != NULL)
+			rdma_addr_find_smac_by_sgid(
+				&ib_event->param.req_rcvd.primary_path->sgid,
+				psmac, NULL);
+		else
+			psmac = NULL;
+		if (ib_event->param.req_rcvd.alternate_path != NULL)
+			rdma_addr_find_smac_by_sgid(
+				&ib_event->param.req_rcvd.alternate_path->sgid,
+				palt_smac, NULL);
+		else
+			palt_smac = NULL;
+	}
 	/*
 	 * Acquire mutex to prevent user executing rdma_destroy_id()
 	 * while we're accessing the cm_id.
 	 */
 	mutex_lock(&lock);
-	if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD))
+	if (is_iboe)
+		ib_update_cm_av(cm_id, psmac, palt_smac);
+	if (cma_comp(conn_id, RDMA_CM_CONNECT) &&
+	    (conn_id->id.qp_type != IB_QPT_UD))
 		ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
 	mutex_unlock(&lock);
 	mutex_unlock(&conn_id->handler_mutex);
@@ -1474,7 +1518,7 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 	mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
 	conn_id->state = RDMA_CM_CONNECT;
 
-	ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr);
+	ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr, NULL);
 	if (ret) {
 		mutex_unlock(&conn_id->handler_mutex);
 		rdma_destroy_id(new_cm_id);
@@ -1873,7 +1917,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	struct cma_work *work;
 	int ret;
 	struct net_device *ndev = NULL;
-	u16 vid;
+
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
 	if (!work)
@@ -1897,10 +1941,14 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 		goto err2;
 	}
 
-	vid = rdma_vlan_dev_vlan_id(ndev);
+	route->path_rec->vlan_id = rdma_vlan_dev_vlan_id(ndev);
+	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, vid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
-	iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, vid);
+		    &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;
@@ -2063,6 +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);
 
@@ -2072,10 +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 {
+	} else
-		memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
 		event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
-	}
 
 	if (id_priv->id.event_handler(&id_priv->id, &event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
@@ -2559,6 +2606,7 @@ 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)
@@ -2569,7 +2617,6 @@ 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;
@@ -3298,7 +3345,8 @@ 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/core_priv.h

@@ -49,4 +49,6 @@ void ib_sysfs_cleanup(void);
 int  ib_cache_setup(void);
 void ib_cache_cleanup(void);
 
+int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
+			    struct ib_qp_attr *qp_attr, int *qp_attr_mask);
 #endif /* _CORE_PRIV_H */

drivers/infiniband/core/sa_query.c

@@ -42,7 +42,7 @@
 #include <linux/kref.h>
 #include <linux/idr.h>
 #include <linux/workqueue.h>
-
+#include <uapi/linux/if_ether.h>
 #include <rdma/ib_pack.h>
 #include <rdma/ib_cache.h>
 #include "sa.h"
@@ -556,6 +556,13 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 		ah_attr->grh.hop_limit     = rec->hop_limit;
 		ah_attr->grh.traffic_class = rec->traffic_class;
 	}
+	if (force_grh) {
+		memcpy(ah_attr->dmac, rec->dmac, ETH_ALEN);
+		ah_attr->vlan_id = rec->vlan_id;
+	} else {
+		ah_attr->vlan_id = 0xffff;
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL(ib_init_ah_from_path);
@@ -670,6 +677,9 @@ static void ib_sa_path_rec_callback(struct ib_sa_query *sa_query,
 
 		ib_unpack(path_rec_table, ARRAY_SIZE(path_rec_table),
 			  mad->data, &rec);
+		rec.vlan_id = 0xffff;
+		memset(rec.dmac, 0, ETH_ALEN);
+		memset(rec.smac, 0, ETH_ALEN);
 		query->callback(status, &rec, query->context);
 	} else
 		query->callback(status, NULL, query->context);

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;
+		rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr,
-		dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+			    (union ib_gid *)&resp->ib_route[0].dgid);
-			if (dev) {
+		rdma_ip2gid((struct sockaddr *)&route->addr.src_addr,
-				vid = rdma_vlan_dev_vlan_id(dev);
+			    (union ib_gid *)&resp->ib_route[0].sgid);
-				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);
 		resp->ib_route[0].pkey = cpu_to_be16(0xffff);
 		break;
 	case 2:

drivers/infiniband/core/uverbs_cmd.c

@@ -40,6 +40,7 @@
 #include <asm/uaccess.h>
 
 #include "uverbs.h"
+#include "core_priv.h"
 
 struct uverbs_lock_class {
 	struct lock_class_key	key;
@@ -1961,6 +1962,9 @@ ssize_t ib_uverbs_modify_qp(struct ib_uverbs_file *file,
 	attr->alt_ah_attr.port_num 	    = cmd.alt_dest.port_num;
 
 	if (qp->real_qp == qp) {
+		ret = ib_resolve_eth_l2_attrs(qp, attr, &cmd.attr_mask);
+		if (ret)
+			goto out;
 		ret = qp->device->modify_qp(qp, attr,
 			modify_qp_mask(qp->qp_type, cmd.attr_mask), &udata);
 	} else {

drivers/infiniband/core/verbs.c

@@ -44,6 +44,9 @@
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
+#include <rdma/ib_addr.h>
+
+#include "core_priv.h"
 
 int ib_rate_to_mult(enum ib_rate rate)
 {
@@ -195,8 +198,28 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
 	u32 flow_class;
 	u16 gid_index;
 	int ret;
+	int is_eth = (rdma_port_get_link_layer(device, port_num) ==
+			IB_LINK_LAYER_ETHERNET);
 
 	memset(ah_attr, 0, sizeof *ah_attr);
+	if (is_eth) {
+		if (!(wc->wc_flags & IB_WC_GRH))
+			return -EPROTOTYPE;
+
+		if (wc->wc_flags & IB_WC_WITH_SMAC &&
+		    wc->wc_flags & IB_WC_WITH_VLAN) {
+			memcpy(ah_attr->dmac, wc->smac, ETH_ALEN);
+			ah_attr->vlan_id = wc->vlan_id;
+		} else {
+			ret = rdma_addr_find_dmac_by_grh(&grh->dgid, &grh->sgid,
+					ah_attr->dmac, &ah_attr->vlan_id);
+			if (ret)
+				return ret;
+		}
+	} else {
+		ah_attr->vlan_id = 0xffff;
+	}
+
 	ah_attr->dlid = wc->slid;
 	ah_attr->sl = wc->sl;
 	ah_attr->src_path_bits = wc->dlid_path_bits;
@@ -479,7 +502,9 @@ EXPORT_SYMBOL(ib_create_qp);
 static const struct {
 	int			valid;
 	enum ib_qp_attr_mask	req_param[IB_QPT_MAX];
+	enum ib_qp_attr_mask	req_param_add_eth[IB_QPT_MAX];
 	enum ib_qp_attr_mask	opt_param[IB_QPT_MAX];
+	enum ib_qp_attr_mask	opt_param_add_eth[IB_QPT_MAX];
 } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = {
 	[IB_QPS_RESET] = {
 		[IB_QPS_RESET] = { .valid = 1 },
@@ -560,6 +585,12 @@ static const struct {
 						IB_QP_MAX_DEST_RD_ATOMIC	|
 						IB_QP_MIN_RNR_TIMER),
 			},
+			.req_param_add_eth = {
+				[IB_QPT_RC]  = (IB_QP_SMAC),
+				[IB_QPT_UC]  = (IB_QP_SMAC),
+				[IB_QPT_XRC_INI]  = (IB_QP_SMAC),
+				[IB_QPT_XRC_TGT]  = (IB_QP_SMAC)
+			},
 			.opt_param = {
 				 [IB_QPT_UD]  = (IB_QP_PKEY_INDEX		|
 						 IB_QP_QKEY),
@@ -579,7 +610,21 @@ static const struct {
 						 IB_QP_QKEY),
 				 [IB_QPT_GSI] = (IB_QP_PKEY_INDEX		|
 						 IB_QP_QKEY),
-			 }
+			 },
+			.opt_param_add_eth = {
+				[IB_QPT_RC]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID),
+				[IB_QPT_UC]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID),
+				[IB_QPT_XRC_INI]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID),
+				[IB_QPT_XRC_TGT]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID)
+			}
 		}
 	},
 	[IB_QPS_RTR]   = {
@@ -782,7 +827,8 @@ static const struct {
 };
 
 int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
-		       enum ib_qp_type type, enum ib_qp_attr_mask mask)
+		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
+		       enum rdma_link_layer ll)
 {
 	enum ib_qp_attr_mask req_param, opt_param;
 
@@ -801,6 +847,13 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 	req_param = qp_state_table[cur_state][next_state].req_param[type];
 	opt_param = qp_state_table[cur_state][next_state].opt_param[type];
 
+	if (ll == IB_LINK_LAYER_ETHERNET) {
+		req_param |= qp_state_table[cur_state][next_state].
+			req_param_add_eth[type];
+		opt_param |= qp_state_table[cur_state][next_state].
+			opt_param_add_eth[type];
+	}
+
 	if ((mask & req_param) != req_param)
 		return 0;
 
@@ -811,10 +864,51 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 }
 EXPORT_SYMBOL(ib_modify_qp_is_ok);
 
+int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
+			    struct ib_qp_attr *qp_attr, int *qp_attr_mask)
+{
+	int           ret = 0;
+	union ib_gid  sgid;
+
+	if ((*qp_attr_mask & IB_QP_AV)  &&
+	    (rdma_port_get_link_layer(qp->device, qp_attr->ah_attr.port_num) == IB_LINK_LAYER_ETHERNET)) {
+		ret = ib_query_gid(qp->device, qp_attr->ah_attr.port_num,
+				   qp_attr->ah_attr.grh.sgid_index, &sgid);
+		if (ret)
+			goto out;
+		if (rdma_link_local_addr((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw)) {
+			rdma_get_ll_mac((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw, qp_attr->ah_attr.dmac);
+			rdma_get_ll_mac((struct in6_addr *)sgid.raw, qp_attr->smac);
+			qp_attr->vlan_id = rdma_get_vlan_id(&sgid);
+		} else {
+			ret = rdma_addr_find_dmac_by_grh(&sgid, &qp_attr->ah_attr.grh.dgid,
+					qp_attr->ah_attr.dmac, &qp_attr->vlan_id);
+			if (ret)
+				goto out;
+			ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr->smac, NULL);
+			if (ret)
+				goto out;
+		}
+		*qp_attr_mask |= IB_QP_SMAC;
+		if (qp_attr->vlan_id < 0xFFFF)
+			*qp_attr_mask |= IB_QP_VID;
+	}
+out:
+	return ret;
+}
+EXPORT_SYMBOL(ib_resolve_eth_l2_attrs);
+
+
 int ib_modify_qp(struct ib_qp *qp,
 		 struct ib_qp_attr *qp_attr,
 		 int qp_attr_mask)
 {
+	int ret;
+
+	ret = ib_resolve_eth_l2_attrs(qp, qp_attr, &qp_attr_mask);
+	if (ret)
+		return ret;
+
 	return qp->device->modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL);
 }
 EXPORT_SYMBOL(ib_modify_qp);

drivers/infiniband/hw/ehca/ehca_qp.c

@@ -1329,7 +1329,7 @@ static int internal_modify_qp(struct ib_qp *ibqp,
 	qp_new_state = attr_mask & IB_QP_STATE ? attr->qp_state : qp_cur_state;
 	if (!smi_reset2init &&
 	    !ib_modify_qp_is_ok(qp_cur_state, qp_new_state, ibqp->qp_type,
-				attr_mask)) {
+				attr_mask, IB_LINK_LAYER_UNSPECIFIED)) {
 		ret = -EINVAL;
 		ehca_err(ibqp->device,
 			 "Invalid qp transition new_state=%x cur_state=%x "

drivers/infiniband/hw/ipath/ipath_qp.c

@@ -463,7 +463,7 @@ int ipath_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
 	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
-				attr_mask))
+				attr_mask, IB_LINK_LAYER_UNSPECIFIED))
 		goto inval;
 
 	if (attr_mask & IB_QP_AV) {

drivers/infiniband/hw/mlx4/Kconfig

@@ -1,6 +1,6 @@
 config MLX4_INFINIBAND
 	tristate "Mellanox ConnectX HCA support"
-	depends on NETDEVICES && ETHERNET && PCI
+	depends on NETDEVICES && ETHERNET && PCI && INET
 	select NET_VENDOR_MELLANOX
 	select MLX4_CORE
 	---help---

drivers/infiniband/hw/mlx4/ah.c

@@ -39,25 +39,6 @@
 
 #include "mlx4_ib.h"
 
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
-			u8 *mac, int *is_mcast, u8 port)
-{
-	struct in6_addr in6;
-
-	*is_mcast = 0;
-
-	memcpy(&in6, ah_attr->grh.dgid.raw, sizeof in6);
-	if (rdma_link_local_addr(&in6))
-		rdma_get_ll_mac(&in6, mac);
-	else if (rdma_is_multicast_addr(&in6)) {
-		rdma_get_mcast_mac(&in6, mac);
-		*is_mcast = 1;
-	} else
-		return -EINVAL;
-
-	return 0;
-}
-
 static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 				  struct mlx4_ib_ah *ah)
 {
@@ -92,21 +73,18 @@ static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr
 {
 	struct mlx4_ib_dev *ibdev = to_mdev(pd->device);
 	struct mlx4_dev *dev = ibdev->dev;
-	union ib_gid sgid;
-	u8 mac[6];
-	int err;
 	int is_mcast;
+	struct in6_addr in6;
 	u16 vlan_tag;
 
-	err = mlx4_ib_resolve_grh(ibdev, ah_attr, mac, &is_mcast, ah_attr->port_num);
+	memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
-	if (err)
+	if (rdma_is_multicast_addr(&in6)) {
-		return ERR_PTR(err);
+		is_mcast = 1;
-
+		rdma_get_mcast_mac(&in6, ah->av.eth.mac);
-	memcpy(ah->av.eth.mac, mac, 6);
+	} else {
-	err = ib_get_cached_gid(pd->device, ah_attr->port_num, ah_attr->grh.sgid_index, &sgid);
+		memcpy(ah->av.eth.mac, ah_attr->dmac, ETH_ALEN);
-	if (err)
+	}
-		return ERR_PTR(err);
+	vlan_tag = ah_attr->vlan_id;
-	vlan_tag = rdma_get_vlan_id(&sgid);
 	if (vlan_tag < 0x1000)
 		vlan_tag |= (ah_attr->sl & 7) << 13;
 	ah->av.eth.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));

drivers/infiniband/hw/mlx4/cq.c

@@ -798,6 +798,15 @@ repoll:
 			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 13;
 		else
 			wc->sl  = be16_to_cpu(cqe->sl_vid) >> 12;
+		if (be32_to_cpu(cqe->vlan_my_qpn) & MLX4_CQE_VLAN_PRESENT_MASK) {
+			wc->vlan_id = be16_to_cpu(cqe->sl_vid) &
+				MLX4_CQE_VID_MASK;
+		} else {
+			wc->vlan_id = 0xffff;
+		}
+		wc->wc_flags |= IB_WC_WITH_VLAN;
+		memcpy(wc->smac, cqe->smac, ETH_ALEN);
+		wc->wc_flags |= IB_WC_WITH_SMAC;
 	}
 
 	return 0;

drivers/infiniband/hw/mlx4/main.c

@@ -39,6 +39,8 @@
 #include <linux/inetdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
 
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
@@ -794,7 +796,6 @@ static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
 int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 		   union ib_gid *gid)
 {
-	u8 mac[6];
 	struct net_device *ndev;
 	int ret = 0;
 
@@ -808,11 +809,7 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 	spin_unlock(&mdev->iboe.lock);
 
 	if (ndev) {
-		rdma_get_mcast_mac((struct in6_addr *)gid, mac);
-		rtnl_lock();
-		dev_mc_add(mdev->iboe.netdevs[mqp->port - 1], mac);
 		ret = 1;
-		rtnl_unlock();
 		dev_put(ndev);
 	}
 
@@ -1164,6 +1161,8 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
 	u64 reg_id;
 	struct mlx4_ib_steering *ib_steering = NULL;
+	enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+		MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
 
 	if (mdev->dev->caps.steering_mode ==
 	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -1175,7 +1174,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
 				    !!(mqp->flags &
 				       MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
-				    MLX4_PROT_IB_IPV6, &reg_id);
+				    prot, &reg_id);
 	if (err)
 		goto err_malloc;
 
@@ -1194,7 +1193,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 
 err_add:
 	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
-			      MLX4_PROT_IB_IPV6, reg_id);
+			      prot, reg_id);
 err_malloc:
 	kfree(ib_steering);
 
@@ -1222,10 +1221,11 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	int err;
 	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
 	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
-	u8 mac[6];
 	struct net_device *ndev;
 	struct mlx4_ib_gid_entry *ge;
 	u64 reg_id = 0;
+	enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+		MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
 
 	if (mdev->dev->caps.steering_mode ==
 	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -1248,7 +1248,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	}
 
 	err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
-				    MLX4_PROT_IB_IPV6, reg_id);
+				    prot, reg_id);
 	if (err)
 		return err;
 
@@ -1260,13 +1260,8 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 		if (ndev)
 			dev_hold(ndev);
 		spin_unlock(&mdev->iboe.lock);
-		rdma_get_mcast_mac((struct in6_addr *)gid, mac);
+		if (ndev)
-		if (ndev) {
-			rtnl_lock();
-			dev_mc_del(mdev->iboe.netdevs[ge->port - 1], mac);
-			rtnl_unlock();
 			dev_put(ndev);
-		}
 		list_del(&ge->list);
 		kfree(ge);
 	} else
@@ -1362,20 +1357,6 @@ static struct device_attribute *mlx4_class_attributes[] = {
 	&dev_attr_board_id
 };
 
-static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id, struct net_device *dev)
-{
-	memcpy(eui, dev->dev_addr, 3);
-	memcpy(eui + 5, dev->dev_addr + 3, 3);
-	if (vlan_id < 0x1000) {
-		eui[3] = vlan_id >> 8;
-		eui[4] = vlan_id & 0xff;
-	} else {
-		eui[3] = 0xff;
-		eui[4] = 0xfe;
-	}
-	eui[0] ^= 2;
-}
-
 static void update_gids_task(struct work_struct *work)
 {
 	struct update_gid_work *gw = container_of(work, struct update_gid_work, work);
@@ -1398,161 +1379,318 @@ static void update_gids_task(struct work_struct *work)
 		       MLX4_CMD_WRAPPED);
 	if (err)
 		pr_warn("set port command failed\n");
-	else {
+	else
-		memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids);
 		mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE);
-	}
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	kfree(gw);
 }
 
-static int update_ipv6_gids(struct mlx4_ib_dev *dev, int port, int clear)
+static void reset_gids_task(struct work_struct *work)
 {
-	struct net_device *ndev = dev->iboe.netdevs[port - 1];
+	struct update_gid_work *gw =
-	struct update_gid_work *work;
+			container_of(work, struct update_gid_work, work);
-	struct net_device *tmp;
+	struct mlx4_cmd_mailbox *mailbox;
+	union ib_gid *gids;
+	int err;
 	int i;
-	u8 *hits;
+	struct mlx4_dev	*dev = gw->dev->dev;
-	int ret;
-	union ib_gid gid;
-	int free;
-	int found;
-	int need_update = 0;
-	u16 vid;
 
-	work = kzalloc(sizeof *work, GFP_ATOMIC);
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		pr_warn("reset gid table failed\n");
+		goto free;
+	}
+
+	gids = mailbox->buf;
+	memcpy(gids, gw->gids, sizeof(gw->gids));
+
+	for (i = 1; i < gw->dev->num_ports + 1; i++) {
+		if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, i) ==
+					    IB_LINK_LAYER_ETHERNET) {
+			err = mlx4_cmd(dev, mailbox->dma,
+				       MLX4_SET_PORT_GID_TABLE << 8 | i,
+				       1, MLX4_CMD_SET_PORT,
+				       MLX4_CMD_TIME_CLASS_B,
+				       MLX4_CMD_WRAPPED);
+			if (err)
+				pr_warn(KERN_WARNING
+					"set port %d command failed\n", i);
+		}
+	}
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+free:
+	kfree(gw);
+}
+
+static int update_gid_table(struct mlx4_ib_dev *dev, int port,
+			    union ib_gid *gid, int clear)
+{
+	struct update_gid_work *work;
+	int i;
+	int need_update = 0;
+	int free = -1;
+	int found = -1;
+	int max_gids;
+
+	max_gids = dev->dev->caps.gid_table_len[port];
+	for (i = 0; i < max_gids; ++i) {
+		if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
+			    sizeof(*gid)))
+			found = i;
+
+		if (clear) {
+			if (found >= 0) {
+				need_update = 1;
+				dev->iboe.gid_table[port - 1][found] = zgid;
+				break;
+			}
+		} else {
+			if (found >= 0)
+				break;
+
+			if (free < 0 &&
+			    !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid,
+				    sizeof(*gid)))
+				free = i;
+		}
+	}
+
+	if (found == -1 && !clear && free >= 0) {
+		dev->iboe.gid_table[port - 1][free] = *gid;
+		need_update = 1;
+	}
+
+	if (!need_update)
+		return 0;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
 	if (!work)
 		return -ENOMEM;
 
-	hits = kzalloc(128, GFP_ATOMIC);
+	memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof(work->gids));
-	if (!hits) {
+	INIT_WORK(&work->work, update_gids_task);
-		ret = -ENOMEM;
+	work->port = port;
-		goto out;
+	work->dev = dev;
-	}
+	queue_work(wq, &work->work);
 
-	rcu_read_lock();
+	return 0;
-	for_each_netdev_rcu(&init_net, tmp) {
+}
-		if (ndev && (tmp == ndev || rdma_vlan_dev_real_dev(tmp) == ndev)) {
-			gid.global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
-			vid = rdma_vlan_dev_vlan_id(tmp);
-			mlx4_addrconf_ifid_eui48(&gid.raw[8], vid, ndev);
-			found = 0;
-			free = -1;
-			for (i = 0; i < 128; ++i) {
-				if (free < 0 &&
-				    !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
-					free = i;
-				if (!memcmp(&dev->iboe.gid_table[port - 1][i], &gid, sizeof gid)) {
-					hits[i] = 1;
-					found = 1;
-					break;
-				}
-			}
 
-			if (!found) {
+static int reset_gid_table(struct mlx4_ib_dev *dev)
-				if (tmp == ndev &&
+{
-				    (memcmp(&dev->iboe.gid_table[port - 1][0],
+	struct update_gid_work *work;
-					    &gid, sizeof gid) ||
-				     !memcmp(&dev->iboe.gid_table[port - 1][0],
-					     &zgid, sizeof gid))) {
-					dev->iboe.gid_table[port - 1][0] = gid;
-					++need_update;
-					hits[0] = 1;
-				} else if (free >= 0) {
-					dev->iboe.gid_table[port - 1][free] = gid;
-					hits[free] = 1;
-					++need_update;
-				}
-			}
-		}
-	}
-	rcu_read_unlock();
 
-	for (i = 0; i < 128; ++i)
-		if (!hits[i]) {
-			if (memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
-				++need_update;
-			dev->iboe.gid_table[port - 1][i] = zgid;
-		}
 
-	if (need_update) {
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
-		memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof work->gids);
+	if (!work)
-		INIT_WORK(&work->work, update_gids_task);
+		return -ENOMEM;
-		work->port = port;
+	memset(dev->iboe.gid_table, 0, sizeof(dev->iboe.gid_table));
-		work->dev = dev;
+	memset(work->gids, 0, sizeof(work->gids));
-		queue_work(wq, &work->work);
+	INIT_WORK(&work->work, reset_gids_task);
-	} else
+	work->dev = dev;
-		kfree(work);
+	queue_work(wq, &work->work);
+	return 0;
+}
 
-	kfree(hits);
+static int mlx4_ib_addr_event(int event, struct net_device *event_netdev,
+			      struct mlx4_ib_dev *ibdev, union ib_gid *gid)
+{
+	struct mlx4_ib_iboe *iboe;
+	int port = 0;
+	struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
+				rdma_vlan_dev_real_dev(event_netdev) :
+				event_netdev;
+
+	if (event != NETDEV_DOWN && event != NETDEV_UP)
+		return 0;
+
+	if ((real_dev != event_netdev) &&
+	    (event == NETDEV_DOWN) &&
+	    rdma_link_local_addr((struct in6_addr *)gid))
+		return 0;
+
+	iboe = &ibdev->iboe;
+	spin_lock(&iboe->lock);
+
+	for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+		if ((netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->masters[port - 1])) ||
+		     (!netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->netdevs[port - 1])))
+			update_gid_table(ibdev, port, gid,
+					 event == NETDEV_DOWN);
+
+	spin_unlock(&iboe->lock);
 	return 0;
 
-out:
-	kfree(work);
-	return ret;
 }
 
-static void handle_en_event(struct mlx4_ib_dev *dev, int port, unsigned long event)
+static u8 mlx4_ib_get_dev_port(struct net_device *dev,
+			       struct mlx4_ib_dev *ibdev)
 {
-	switch (event) {
+	u8 port = 0;
-	case NETDEV_UP:
+	struct mlx4_ib_iboe *iboe;
-	case NETDEV_CHANGEADDR:
+	struct net_device *real_dev = rdma_vlan_dev_real_dev(dev) ?
-		update_ipv6_gids(dev, port, 0);
+				rdma_vlan_dev_real_dev(dev) : dev;
-		break;
 
-	case NETDEV_DOWN:
+	iboe = &ibdev->iboe;
-		update_ipv6_gids(dev, port, 1);
+	spin_lock(&iboe->lock);
-		dev->iboe.netdevs[port - 1] = NULL;
+
-	}
+	for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+		if ((netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->masters[port - 1])) ||
+		     (!netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->netdevs[port - 1])))
+			break;
+
+	spin_unlock(&iboe->lock);
+
+	if ((port == 0) || (port > MLX4_MAX_PORTS))
+		return 0;
+	else
+		return port;
 }
 
-static void netdev_added(struct mlx4_ib_dev *dev, int port)
+static int mlx4_ib_inet_event(struct notifier_block *this, unsigned long event,
-{
-	update_ipv6_gids(dev, port, 0);
-}
-
-static void netdev_removed(struct mlx4_ib_dev *dev, int port)
-{
-	update_ipv6_gids(dev, port, 1);
-}
-
-static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event,
 				void *ptr)
+{
+	struct mlx4_ib_dev *ibdev;
+	struct in_ifaddr *ifa = ptr;
+	union ib_gid gid;
+	struct net_device *event_netdev = ifa->ifa_dev->dev;
+
+	ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
+
+	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet);
+
+	mlx4_ib_addr_event(event, event_netdev, ibdev, &gid);
+	return NOTIFY_DONE;
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static int mlx4_ib_inet6_event(struct notifier_block *this, unsigned long event,
+				void *ptr)
+{
+	struct mlx4_ib_dev *ibdev;
+	struct inet6_ifaddr *ifa = ptr;
+	union  ib_gid *gid = (union ib_gid *)&ifa->addr;
+	struct net_device *event_netdev = ifa->idev->dev;
+
+	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet6);
+
+	mlx4_ib_addr_event(event, event_netdev, ibdev, gid);
+	return NOTIFY_DONE;
+}
+#endif
+
+static void mlx4_ib_get_dev_addr(struct net_device *dev,
+				 struct mlx4_ib_dev *ibdev, u8 port)
+{
+	struct in_device *in_dev;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct inet6_dev *in6_dev;
+	union ib_gid  *pgid;
+	struct inet6_ifaddr *ifp;
+#endif
+	union ib_gid gid;
+
+
+	if ((port == 0) || (port > MLX4_MAX_PORTS))
+		return;
+
+	/* IPv4 gids */
+	in_dev = in_dev_get(dev);
+	if (in_dev) {
+		for_ifa(in_dev) {
+			/*ifa->ifa_address;*/
+			ipv6_addr_set_v4mapped(ifa->ifa_address,
+					       (struct in6_addr *)&gid);
+			update_gid_table(ibdev, port, &gid, 0);
+		}
+		endfor_ifa(in_dev);
+		in_dev_put(in_dev);
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	/* IPv6 gids */
+	in6_dev = in6_dev_get(dev);
+	if (in6_dev) {
+		read_lock_bh(&in6_dev->lock);
+		list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
+			pgid = (union ib_gid *)&ifp->addr;
+			update_gid_table(ibdev, port, pgid, 0);
+		}
+		read_unlock_bh(&in6_dev->lock);
+		in6_dev_put(in6_dev);
+	}
+#endif
+}
+
+static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
+{
+	struct	net_device *dev;
+
+	if (reset_gid_table(ibdev))
+		return -1;
+
+	read_lock(&dev_base_lock);
+
+	for_each_netdev(&init_net, dev) {
+		u8 port = mlx4_ib_get_dev_port(dev, ibdev);
+		if (port)
+			mlx4_ib_get_dev_addr(dev, ibdev, port);
+	}
+
+	read_unlock(&dev_base_lock);
+
+	return 0;
+}
+
+static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev)
+{
+	struct mlx4_ib_iboe *iboe;
+	int port;
+
+	iboe = &ibdev->iboe;
+
+	spin_lock(&iboe->lock);
+	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
+		struct net_device *old_master = iboe->masters[port - 1];
+		struct net_device *curr_master;
+		iboe->netdevs[port - 1] =
+			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
+
+		if (iboe->netdevs[port - 1] &&
+		    netif_is_bond_slave(iboe->netdevs[port - 1])) {
+			rtnl_lock();
+			iboe->masters[port - 1] = netdev_master_upper_dev_get(
+				iboe->netdevs[port - 1]);
+			rtnl_unlock();
+		}
+		curr_master = iboe->masters[port - 1];
+
+		/* if bonding is used it is possible that we add it to masters
+		    only after IP address is assigned to the net bonding
+		    interface */
+		if (curr_master && (old_master != curr_master))
+			mlx4_ib_get_dev_addr(curr_master, ibdev, port);
+	}
+
+	spin_unlock(&iboe->lock);
+}
+
+static int mlx4_ib_netdev_event(struct notifier_block *this,
+				unsigned long event, void *ptr)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct mlx4_ib_dev *ibdev;
-	struct net_device *oldnd;
-	struct mlx4_ib_iboe *iboe;
-	int port;
 
 	if (!net_eq(dev_net(dev), &init_net))
 		return NOTIFY_DONE;
 
 	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
-	iboe = &ibdev->iboe;
+	mlx4_ib_scan_netdevs(ibdev);
-
-	spin_lock(&iboe->lock);
-	mlx4_foreach_ib_transport_port(port, ibdev->dev) {
-		oldnd = iboe->netdevs[port - 1];
-		iboe->netdevs[port - 1] =
-			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
-		if (oldnd != iboe->netdevs[port - 1]) {
-			if (iboe->netdevs[port - 1])
-				netdev_added(ibdev, port);
-			else
-				netdev_removed(ibdev, port);
-		}
-	}
-
-	if (dev == iboe->netdevs[0] ||
-	    (iboe->netdevs[0] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[0]))
-		handle_en_event(ibdev, 1, event);
-	else if (dev == iboe->netdevs[1]
-		 || (iboe->netdevs[1] && rdma_vlan_dev_real_dev(dev) == iboe->netdevs[1]))
-		handle_en_event(ibdev, 2, event);
-
-	spin_unlock(&iboe->lock);
 
 	return NOTIFY_DONE;
 }
@@ -1886,11 +2024,35 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	if (mlx4_ib_init_sriov(ibdev))
 		goto err_mad;
 
-	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE && !iboe->nb.notifier_call) {
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE) {
-		iboe->nb.notifier_call = mlx4_ib_netdev_event;
+		if (!iboe->nb.notifier_call) {
-		err = register_netdevice_notifier(&iboe->nb);
+			iboe->nb.notifier_call = mlx4_ib_netdev_event;
-		if (err)
+			err = register_netdevice_notifier(&iboe->nb);
-			goto err_sriov;
+			if (err) {
+				iboe->nb.notifier_call = NULL;
+				goto err_notif;
+			}
+		}
+		if (!iboe->nb_inet.notifier_call) {
+			iboe->nb_inet.notifier_call = mlx4_ib_inet_event;
+			err = register_inetaddr_notifier(&iboe->nb_inet);
+			if (err) {
+				iboe->nb_inet.notifier_call = NULL;
+				goto err_notif;
+			}
+		}
+#if IS_ENABLED(CONFIG_IPV6)
+		if (!iboe->nb_inet6.notifier_call) {
+			iboe->nb_inet6.notifier_call = mlx4_ib_inet6_event;
+			err = register_inet6addr_notifier(&iboe->nb_inet6);
+			if (err) {
+				iboe->nb_inet6.notifier_call = NULL;
+				goto err_notif;
+			}
+		}
+#endif
+		mlx4_ib_scan_netdevs(ibdev);
+		mlx4_ib_init_gid_table(ibdev);
 	}
 
 	for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) {
@@ -1916,11 +2078,25 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	return ibdev;
 
 err_notif:
-	if (unregister_netdevice_notifier(&ibdev->iboe.nb))
+	if (ibdev->iboe.nb.notifier_call) {
-		pr_warn("failure unregistering notifier\n");
+		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb.notifier_call = NULL;
+	}
+	if (ibdev->iboe.nb_inet.notifier_call) {
+		if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet.notifier_call = NULL;
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	if (ibdev->iboe.nb_inet6.notifier_call) {
+		if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet6.notifier_call = NULL;
+	}
+#endif
 	flush_workqueue(wq);
 
-err_sriov:
 	mlx4_ib_close_sriov(ibdev);
 
 err_mad:
@@ -2039,6 +2215,19 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 		kfree(ibdev->ib_uc_qpns_bitmap);
 	}
 
+	if (ibdev->iboe.nb_inet.notifier_call) {
+		if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet.notifier_call = NULL;
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	if (ibdev->iboe.nb_inet6.notifier_call) {
+		if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet6.notifier_call = NULL;
+	}
+#endif
+
 	iounmap(ibdev->uar_map);
 	for (p = 0; p < ibdev->num_ports; ++p)
 		if (ibdev->counters[p] != -1)

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -432,7 +432,10 @@ struct mlx4_ib_sriov {
 struct mlx4_ib_iboe {
 	spinlock_t		lock;
 	struct net_device      *netdevs[MLX4_MAX_PORTS];
+	struct net_device      *masters[MLX4_MAX_PORTS];
 	struct notifier_block 	nb;
+	struct notifier_block	nb_inet;
+	struct notifier_block	nb_inet6;
 	union ib_gid		gid_table[MLX4_MAX_PORTS][128];
 };
 
@@ -683,9 +686,6 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
 int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
 			union ib_gid *gid, int netw_view);
 
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
-			u8 *mac, int *is_mcast, u8 port);
-
 static inline bool mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
 {
 	u8 port = be32_to_cpu(ah->av.ib.port_pd) >> 24 & 3;

drivers/infiniband/hw/mlx4/qp.c

@@ -90,6 +90,21 @@ enum {
 	MLX4_RAW_QP_MSGMAX	= 31,
 };
 
+#ifndef ETH_ALEN
+#define ETH_ALEN        6
+#endif
+static inline u64 mlx4_mac_to_u64(u8 *addr)
+{
+	u64 mac = 0;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		mac <<= 8;
+		mac |= addr[i];
+	}
+	return mac;
+}
+
 static const __be32 mlx4_ib_opcode[] = {
 	[IB_WR_SEND]				= cpu_to_be32(MLX4_OPCODE_SEND),
 	[IB_WR_LSO]				= cpu_to_be32(MLX4_OPCODE_LSO),
@@ -1171,16 +1186,15 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port)
 	path->sched_queue = (path->sched_queue & 0xbf) | ((port - 1) << 6);
 }
 
-static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
+static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
-			 struct mlx4_qp_path *path, u8 port)
+			  u64 smac, u16 vlan_tag, struct mlx4_qp_path *path,
+			  u8 port)
 {
-	int err;
 	int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) ==
 		IB_LINK_LAYER_ETHERNET;
-	u8 mac[6];
-	int is_mcast;
-	u16 vlan_tag;
 	int vidx;
+	int smac_index;
+
 
 	path->grh_mylmc     = ah->src_path_bits & 0x7f;
 	path->rlid	    = cpu_to_be16(ah->dlid);
@@ -1215,22 +1229,27 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 		if (!(ah->ah_flags & IB_AH_GRH))
 			return -1;
 
-		err = mlx4_ib_resolve_grh(dev, ah, mac, &is_mcast, port);
+		memcpy(path->dmac, ah->dmac, ETH_ALEN);
-		if (err)
-			return err;
-
-		memcpy(path->dmac, mac, 6);
 		path->ackto = MLX4_IB_LINK_TYPE_ETH;
-		/* use index 0 into MAC table for IBoE */
+		/* find the index  into MAC table for IBoE */
-		path->grh_mylmc &= 0x80;
+		if (!is_zero_ether_addr((const u8 *)&smac)) {
+			if (mlx4_find_cached_mac(dev->dev, port, smac,
+						 &smac_index))
+				return -ENOENT;
+		} else {
+			smac_index = 0;
+		}
 
-		vlan_tag = rdma_get_vlan_id(&dev->iboe.gid_table[port - 1][ah->grh.sgid_index]);
+		path->grh_mylmc &= 0x80 | smac_index;
+
+		path->feup |= MLX4_FEUP_FORCE_ETH_UP;
 		if (vlan_tag < 0x1000) {
 			if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx))
 				return -ENOENT;
 
 			path->vlan_index = vidx;
 			path->fl = 1 << 6;
+			path->feup |= MLX4_FVL_FORCE_ETH_VLAN;
 		}
 	} else
 		path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
@@ -1239,6 +1258,28 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 	return 0;
 }
 
+static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp,
+			 enum ib_qp_attr_mask qp_attr_mask,
+			 struct mlx4_qp_path *path, u8 port)
+{
+	return _mlx4_set_path(dev, &qp->ah_attr,
+			      mlx4_mac_to_u64((u8 *)qp->smac),
+			      (qp_attr_mask & IB_QP_VID) ? qp->vlan_id : 0xffff,
+			      path, port);
+}
+
+static int mlx4_set_alt_path(struct mlx4_ib_dev *dev,
+			     const struct ib_qp_attr *qp,
+			     enum ib_qp_attr_mask qp_attr_mask,
+			     struct mlx4_qp_path *path, u8 port)
+{
+	return _mlx4_set_path(dev, &qp->alt_ah_attr,
+			      mlx4_mac_to_u64((u8 *)qp->alt_smac),
+			      (qp_attr_mask & IB_QP_ALT_VID) ?
+			      qp->alt_vlan_id : 0xffff,
+			      path, port);
+}
+
 static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
 {
 	struct mlx4_ib_gid_entry *ge, *tmp;
@@ -1362,7 +1403,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (attr_mask & IB_QP_AV) {
-		if (mlx4_set_path(dev, &attr->ah_attr, &context->pri_path,
+		if (mlx4_set_path(dev, attr, attr_mask, &context->pri_path,
 				  attr_mask & IB_QP_PORT ?
 				  attr->port_num : qp->port))
 			goto out;
@@ -1385,8 +1426,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		    dev->dev->caps.pkey_table_len[attr->alt_port_num])
 			goto out;
 
-		if (mlx4_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
+		if (mlx4_set_alt_path(dev, attr, attr_mask, &context->alt_path,
-				  attr->alt_port_num))
+				      attr->alt_port_num))
 			goto out;
 
 		context->alt_path.pkey_index = attr->alt_pkey_index;
@@ -1497,6 +1538,17 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		context->pri_path.ackto = (context->pri_path.ackto & 0xf8) |
 					MLX4_IB_LINK_TYPE_ETH;
 
+	if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
+		int is_eth = rdma_port_get_link_layer(
+				&dev->ib_dev, qp->port) ==
+				IB_LINK_LAYER_ETHERNET;
+		if (is_eth) {
+			context->pri_path.ackto = MLX4_IB_LINK_TYPE_ETH;
+			optpar |= MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH;
+		}
+	}
+
+
 	if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD	&&
 	    attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify)
 		sqd_event = 1;
@@ -1599,13 +1651,21 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	struct mlx4_ib_qp *qp = to_mqp(ibqp);
 	enum ib_qp_state cur_state, new_state;
 	int err = -EINVAL;
-
+	int ll;
 	mutex_lock(&qp->mutex);
 
 	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
-	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) {
+	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
+		ll = IB_LINK_LAYER_UNSPECIFIED;
+	} else {
+		int port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+		ll = rdma_port_get_link_layer(&dev->ib_dev, port);
+	}
+
+	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
+				attr_mask, ll)) {
 		pr_debug("qpn 0x%x: invalid attribute mask specified "
 			 "for transition %d to %d. qp_type %d,"
 			 " attr_mask 0x%x\n",
@@ -1822,8 +1882,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 				return err;
 		}
 
-		vlan = rdma_get_vlan_id(&sgid);
+		if (ah->av.eth.vlan != 0xffff) {
-		is_vlan = vlan < 0x1000;
+			vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
+			is_vlan = 1;
+		}
 	}
 	ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header);
 

drivers/infiniband/hw/mlx5/qp.c

@@ -1664,7 +1664,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
 	if (ibqp->qp_type != MLX5_IB_QPT_REG_UMR &&
-	    !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
+	    !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
+				IB_LINK_LAYER_UNSPECIFIED))
 		goto out;
 
 	if ((attr_mask & IB_QP_PORT) &&

drivers/infiniband/hw/mthca/mthca_qp.c

@@ -860,7 +860,8 @@ int mthca_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask,
 
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
-	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) {
+	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
+				IB_LINK_LAYER_UNSPECIFIED)) {
 		mthca_dbg(dev, "Bad QP transition (transport %d) "
 			  "%d->%d with attr 0x%08x\n",
 			  qp->transport, cur_state, new_state,

drivers/infiniband/hw/ocrdma/Kconfig

@@ -1,6 +1,6 @@
 config INFINIBAND_OCRDMA
 	tristate "Emulex One Connect HCA support"
-	depends on ETHERNET && NETDEVICES && PCI && (IPV6 || IPV6=n)
+	depends on ETHERNET && NETDEVICES && PCI && INET && (IPV6 || IPV6=n)
 	select NET_VENDOR_EMULEX
 	select BE2NET
 	---help---

drivers/infiniband/hw/ocrdma/ocrdma.h

@@ -423,5 +423,17 @@ static inline int is_cqe_wr_imm(struct ocrdma_cqe *cqe)
 		OCRDMA_CQE_WRITE_IMM) ? 1 : 0;
 }
 
+static inline int ocrdma_resolve_dmac(struct ocrdma_dev *dev,
+		struct ib_ah_attr *ah_attr, u8 *mac_addr)
+{
+	struct in6_addr in6;
+
+	memcpy(&in6, ah_attr->grh.dgid.raw, sizeof(in6));
+	if (rdma_is_multicast_addr(&in6))
+		rdma_get_mcast_mac(&in6, mac_addr);
+	else
+		memcpy(mac_addr, ah_attr->dmac, ETH_ALEN);
+	return 0;
+}
 
 #endif

drivers/infiniband/hw/ocrdma/ocrdma_ah.c

@@ -49,7 +49,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 
 	ah->sgid_index = attr->grh.sgid_index;
 
-	vlan_tag = rdma_get_vlan_id(&attr->grh.dgid);
+	vlan_tag = attr->vlan_id;
 	if (!vlan_tag || (vlan_tag > 0xFFF))
 		vlan_tag = dev->pvid;
 	if (vlan_tag && (vlan_tag < 0x1000)) {
@@ -64,7 +64,8 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 		eth_sz = sizeof(struct ocrdma_eth_basic);
 	}
 	memcpy(&eth.smac[0], &dev->nic_info.mac_addr[0], ETH_ALEN);
-	status = ocrdma_resolve_dgid(dev, &attr->grh.dgid, &eth.dmac[0]);
+	memcpy(&eth.dmac[0], attr->dmac, ETH_ALEN);
+	status = ocrdma_resolve_dmac(dev, attr, &eth.dmac[0]);
 	if (status)
 		return status;
 	status = ocrdma_query_gid(&dev->ibdev, 1, attr->grh.sgid_index,

drivers/infiniband/hw/ocrdma/ocrdma_hw.c

@@ -2076,23 +2076,6 @@ mbx_err:
 	return status;
 }
 
-int ocrdma_resolve_dgid(struct ocrdma_dev *dev, union ib_gid *dgid,
-			u8 *mac_addr)
-{
-	struct in6_addr in6;
-
-	memcpy(&in6, dgid, sizeof in6);
-	if (rdma_is_multicast_addr(&in6)) {
-		rdma_get_mcast_mac(&in6, mac_addr);
-	} else if (rdma_link_local_addr(&in6)) {
-		rdma_get_ll_mac(&in6, mac_addr);
-	} else {
-		pr_err("%s() fail to resolve mac_addr.\n", __func__);
-		return -EINVAL;
-	}
-	return 0;
-}
-
 static int ocrdma_set_av_params(struct ocrdma_qp *qp,
 				struct ocrdma_modify_qp *cmd,
 				struct ib_qp_attr *attrs)
@@ -2126,14 +2109,14 @@ static int ocrdma_set_av_params(struct ocrdma_qp *qp,
 
 	qp->sgid_idx = ah_attr->grh.sgid_index;
 	memcpy(&cmd->params.sgid[0], &sgid.raw[0], sizeof(cmd->params.sgid));
-	ocrdma_resolve_dgid(qp->dev, &ah_attr->grh.dgid, &mac_addr[0]);
+	ocrdma_resolve_dmac(qp->dev, ah_attr, &mac_addr[0]);
 	cmd->params.dmac_b0_to_b3 = mac_addr[0] | (mac_addr[1] << 8) |
 				(mac_addr[2] << 16) | (mac_addr[3] << 24);
 	/* convert them to LE format. */
 	ocrdma_cpu_to_le32(&cmd->params.dgid[0], sizeof(cmd->params.dgid));
 	ocrdma_cpu_to_le32(&cmd->params.sgid[0], sizeof(cmd->params.sgid));
 	cmd->params.vlan_dmac_b4_to_b5 = mac_addr[4] | (mac_addr[5] << 8);
-	vlan_id = rdma_get_vlan_id(&sgid);
+	vlan_id = ah_attr->vlan_id;
 	if (vlan_id && (vlan_id < 0x1000)) {
 		cmd->params.vlan_dmac_b4_to_b5 |=
 		    vlan_id << OCRDMA_QP_PARAMS_VLAN_SHIFT;

drivers/infiniband/hw/ocrdma/ocrdma_hw.h

@@ -94,7 +94,6 @@ void ocrdma_ring_cq_db(struct ocrdma_dev *, u16 cq_id, bool armed,
 int ocrdma_mbx_get_link_speed(struct ocrdma_dev *dev, u8 *lnk_speed);
 int ocrdma_query_config(struct ocrdma_dev *,
 			struct ocrdma_mbx_query_config *config);
-int ocrdma_resolve_dgid(struct ocrdma_dev *, union ib_gid *dgid, u8 *mac_addr);
 
 int ocrdma_mbx_alloc_pd(struct ocrdma_dev *, struct ocrdma_pd *);
 int ocrdma_mbx_dealloc_pd(struct ocrdma_dev *, struct ocrdma_pd *);

drivers/infiniband/hw/ocrdma/ocrdma_main.c

@@ -67,46 +67,24 @@ void ocrdma_get_guid(struct ocrdma_dev *dev, u8 *guid)
 	guid[7] = mac_addr[5];
 }
 
-static void ocrdma_build_sgid_mac(union ib_gid *sgid, unsigned char *mac_addr,
+static bool ocrdma_add_sgid(struct ocrdma_dev *dev, union ib_gid *new_sgid)
-				  bool is_vlan, u16 vlan_id)
-{
-	sgid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
-	sgid->raw[8] = mac_addr[0] ^ 2;
-	sgid->raw[9] = mac_addr[1];
-	sgid->raw[10] = mac_addr[2];
-	if (is_vlan) {
-		sgid->raw[11] = vlan_id >> 8;
-		sgid->raw[12] = vlan_id & 0xff;
-	} else {
-		sgid->raw[11] = 0xff;
-		sgid->raw[12] = 0xfe;
-	}
-	sgid->raw[13] = mac_addr[3];
-	sgid->raw[14] = mac_addr[4];
-	sgid->raw[15] = mac_addr[5];
-}
-
-static bool ocrdma_add_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
-			    bool is_vlan, u16 vlan_id)
 {
 	int i;
-	union ib_gid new_sgid;
 	unsigned long flags;
 
 	memset(&ocrdma_zero_sgid, 0, sizeof(union ib_gid));
 
-	ocrdma_build_sgid_mac(&new_sgid, mac_addr, is_vlan, vlan_id);
 
 	spin_lock_irqsave(&dev->sgid_lock, flags);
 	for (i = 0; i < OCRDMA_MAX_SGID; i++) {
 		if (!memcmp(&dev->sgid_tbl[i], &ocrdma_zero_sgid,
 			    sizeof(union ib_gid))) {
 			/* found free entry */
-			memcpy(&dev->sgid_tbl[i], &new_sgid,
+			memcpy(&dev->sgid_tbl[i], new_sgid,
 			       sizeof(union ib_gid));
 			spin_unlock_irqrestore(&dev->sgid_lock, flags);
 			return true;
-		} else if (!memcmp(&dev->sgid_tbl[i], &new_sgid,
+		} else if (!memcmp(&dev->sgid_tbl[i], new_sgid,
 				   sizeof(union ib_gid))) {
 			/* entry already present, no addition is required. */
 			spin_unlock_irqrestore(&dev->sgid_lock, flags);
@@ -117,20 +95,17 @@ static bool ocrdma_add_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
 	return false;
 }
 
-static bool ocrdma_del_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
+static bool ocrdma_del_sgid(struct ocrdma_dev *dev, union ib_gid *sgid)
-			    bool is_vlan, u16 vlan_id)
 {
 	int found = false;
 	int i;
-	union ib_gid sgid;
 	unsigned long flags;
 
-	ocrdma_build_sgid_mac(&sgid, mac_addr, is_vlan, vlan_id);
 
 	spin_lock_irqsave(&dev->sgid_lock, flags);
 	/* first is default sgid, which cannot be deleted. */
 	for (i = 1; i < OCRDMA_MAX_SGID; i++) {
-		if (!memcmp(&dev->sgid_tbl[i], &sgid, sizeof(union ib_gid))) {
+		if (!memcmp(&dev->sgid_tbl[i], sgid, sizeof(union ib_gid))) {
 			/* found matching entry */
 			memset(&dev->sgid_tbl[i], 0, sizeof(union ib_gid));
 			found = true;
@@ -141,75 +116,18 @@ static bool ocrdma_del_sgid(struct ocrdma_dev *dev, unsigned char *mac_addr,
 	return found;
 }
 
-static void ocrdma_add_default_sgid(struct ocrdma_dev *dev)
+static int ocrdma_addr_event(unsigned long event, struct net_device *netdev,
+			     union ib_gid *gid)
 {
-	/* GID Index 0 - Invariant manufacturer-assigned EUI-64 */
-	union ib_gid *sgid = &dev->sgid_tbl[0];
-
-	sgid->global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
-	ocrdma_get_guid(dev, &sgid->raw[8]);
-}
-
-#if IS_ENABLED(CONFIG_VLAN_8021Q)
-static void ocrdma_add_vlan_sgids(struct ocrdma_dev *dev)
-{
-	struct net_device *netdev, *tmp;
-	u16 vlan_id;
-	bool is_vlan;
-
-	netdev = dev->nic_info.netdev;
-
-	rcu_read_lock();
-	for_each_netdev_rcu(&init_net, tmp) {
-		if (netdev == tmp || vlan_dev_real_dev(tmp) == netdev) {
-			if (!netif_running(tmp) || !netif_oper_up(tmp))
-				continue;
-			if (netdev != tmp) {
-				vlan_id = vlan_dev_vlan_id(tmp);
-				is_vlan = true;
-			} else {
-				is_vlan = false;
-				vlan_id = 0;
-				tmp = netdev;
-			}
-			ocrdma_add_sgid(dev, tmp->dev_addr, is_vlan, vlan_id);
-		}
-	}
-	rcu_read_unlock();
-}
-#else
-static void ocrdma_add_vlan_sgids(struct ocrdma_dev *dev)
-{
-
-}
-#endif /* VLAN */
-
-static int ocrdma_build_sgid_tbl(struct ocrdma_dev *dev)
-{
-	ocrdma_add_default_sgid(dev);
-	ocrdma_add_vlan_sgids(dev);
-	return 0;
-}
-
-#if IS_ENABLED(CONFIG_IPV6)
-
-static int ocrdma_inet6addr_event(struct notifier_block *notifier,
-				  unsigned long event, void *ptr)
-{
-	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
-	struct net_device *netdev = ifa->idev->dev;
 	struct ib_event gid_event;
 	struct ocrdma_dev *dev;
 	bool found = false;
 	bool updated = false;
 	bool is_vlan = false;
-	u16 vid = 0;
 
 	is_vlan = netdev->priv_flags & IFF_802_1Q_VLAN;
-	if (is_vlan) {
+	if (is_vlan)
-		vid = vlan_dev_vlan_id(netdev);
 		netdev = vlan_dev_real_dev(netdev);
-	}
 
 	rcu_read_lock();
 	list_for_each_entry_rcu(dev, &ocrdma_dev_list, entry) {
@@ -222,16 +140,14 @@ static int ocrdma_inet6addr_event(struct notifier_block *notifier,
 
 	if (!found)
 		return NOTIFY_DONE;
-	if (!rdma_link_local_addr((struct in6_addr *)&ifa->addr))
-		return NOTIFY_DONE;
 
 	mutex_lock(&dev->dev_lock);
 	switch (event) {
 	case NETDEV_UP:
-		updated = ocrdma_add_sgid(dev, netdev->dev_addr, is_vlan, vid);
+		updated = ocrdma_add_sgid(dev, gid);
 		break;
 	case NETDEV_DOWN:
-		updated = ocrdma_del_sgid(dev, netdev->dev_addr, is_vlan, vid);
+		updated = ocrdma_del_sgid(dev, gid);
 		break;
 	default:
 		break;
@@ -247,6 +163,32 @@ static int ocrdma_inet6addr_event(struct notifier_block *notifier,
 	return NOTIFY_OK;
 }
 
+static int ocrdma_inetaddr_event(struct notifier_block *notifier,
+				  unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = ptr;
+	union ib_gid gid;
+	struct net_device *netdev = ifa->ifa_dev->dev;
+
+	ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
+	return ocrdma_addr_event(event, netdev, &gid);
+}
+
+static struct notifier_block ocrdma_inetaddr_notifier = {
+	.notifier_call = ocrdma_inetaddr_event
+};
+
+#if IS_ENABLED(CONFIG_IPV6)
+
+static int ocrdma_inet6addr_event(struct notifier_block *notifier,
+				  unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = (struct inet6_ifaddr *)ptr;
+	union  ib_gid *gid = (union ib_gid *)&ifa->addr;
+	struct net_device *netdev = ifa->idev->dev;
+	return ocrdma_addr_event(event, netdev, gid);
+}
+
 static struct notifier_block ocrdma_inet6addr_notifier = {
 	.notifier_call = ocrdma_inet6addr_event
 };
@@ -423,10 +365,6 @@ static struct ocrdma_dev *ocrdma_add(struct be_dev_info *dev_info)
 	if (status)
 		goto alloc_err;
 
-	status = ocrdma_build_sgid_tbl(dev);
-	if (status)
-		goto alloc_err;
-
 	status = ocrdma_register_device(dev);
 	if (status)
 		goto alloc_err;
@@ -553,6 +491,10 @@ static int __init ocrdma_init_module(void)
 {
 	int status;
 
+	status = register_inetaddr_notifier(&ocrdma_inetaddr_notifier);
+	if (status)
+		return status;
+
 #if IS_ENABLED(CONFIG_IPV6)
 	status = register_inet6addr_notifier(&ocrdma_inet6addr_notifier);
 	if (status)

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c

@@ -1326,7 +1326,8 @@ int ocrdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		new_qps = old_qps;
 	spin_unlock_irqrestore(&qp->q_lock, flags);
 
-	if (!ib_modify_qp_is_ok(old_qps, new_qps, ibqp->qp_type, attr_mask)) {
+	if (!ib_modify_qp_is_ok(old_qps, new_qps, ibqp->qp_type, attr_mask,
+				IB_LINK_LAYER_ETHERNET)) {
 		pr_err("%s(%d) invalid attribute mask=0x%x specified for\n"
 		       "qpn=0x%x of type=0x%x old_qps=0x%x, new_qps=0x%x\n",
 		       __func__, dev->id, attr_mask, qp->id, ibqp->qp_type,

drivers/infiniband/hw/qib/qib_qp.c

@@ -585,7 +585,7 @@ int qib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
 	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
-				attr_mask))
+				attr_mask, IB_LINK_LAYER_UNSPECIFIED))
 		goto inval;
 
 	if (attr_mask & IB_QP_AV) {

drivers/net/ethernet/mellanox/mlx4/port.c

@@ -123,6 +123,26 @@ static int mlx4_set_port_mac_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx)
+{
+	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];
+	struct mlx4_mac_table *table = &info->mac_table;
+	int i;
+
+	for (i = 0; i < MLX4_MAX_MAC_NUM; i++) {
+		if (!table->refs[i])
+			continue;
+
+		if (mac == (MLX4_MAC_MASK & be64_to_cpu(table->entries[i]))) {
+			*idx = i;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(mlx4_find_cached_mac);
+
 int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac)
 {
 	struct mlx4_port_info *info = &mlx4_priv(dev)->port[port];

include/linux/mlx4/cq.h

@@ -34,6 +34,7 @@
 #define MLX4_CQ_H
 
 #include <linux/types.h>
+#include <uapi/linux/if_ether.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
@@ -43,10 +44,15 @@ struct mlx4_cqe {
 	__be32			immed_rss_invalid;
 	__be32			g_mlpath_rqpn;
 	__be16			sl_vid;
-	__be16			rlid;
+	union {
-	__be16			status;
+		struct {
-	u8			ipv6_ext_mask;
+			__be16	rlid;
-	u8			badfcs_enc;
+			__be16  status;
+			u8      ipv6_ext_mask;
+			u8      badfcs_enc;
+		};
+		u8  smac[ETH_ALEN];
+	};
 	__be32			byte_cnt;
 	__be16			wqe_index;
 	__be16			checksum;
@@ -83,6 +89,7 @@ struct mlx4_ts_cqe {
 enum {
 	MLX4_CQE_VLAN_PRESENT_MASK	= 1 << 29,
 	MLX4_CQE_QPN_MASK		= 0xffffff,
+	MLX4_CQE_VID_MASK		= 0xfff,
 };
 
 enum {

include/linux/mlx4/device.h

@@ -1096,6 +1096,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
 int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
 int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
 		u8 *pg, u16 *ratelimit);
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);

include/rdma/ib_addr.h

@@ -38,10 +38,15 @@
 #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>
 
 struct rdma_addr_client {
 	atomic_t refcount;
@@ -72,7 +77,8 @@ struct rdma_dev_addr {
  * rdma_translate_ip - Translate a local IP address to an RDMA hardware
  *   address.
  */
-int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr);
+int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
+		      u16 *vlan_id);
 
 /**
  * rdma_resolve_ip - Resolve source and destination IP addresses to
@@ -104,6 +110,10 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
 
 int rdma_addr_size(struct sockaddr *addr);
 
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id);
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac,
+			       u16 *vlan_id);
+
 static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
 {
 	return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9];
@@ -126,41 +136,60 @@ 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)
-{
-	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;
-}
-
 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 int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
+{
+	switch (addr->sa_family) {
+	case AF_INET:
+		ipv6_addr_set_v4mapped(((struct sockaddr_in *)
+					addr)->sin_addr.s_addr,
+				       (struct in6_addr *)gid);
+		break;
+	case AF_INET6:
+		memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16);
+		break;
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */
+static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
+{
+	if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
+		struct sockaddr_in *out_in = (struct sockaddr_in *)out;
+		memset(out_in, 0, sizeof(*out_in));
+		out_in->sin_family = AF_INET;
+		memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4);
+	} else {
+		struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out;
+		memset(out_in, 0, sizeof(*out_in));
+		out_in->sin6_family = AF_INET6;
+		memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16);
+	}
+	return 0;
+}
+
 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)

include/rdma/ib_cm.h

@@ -601,4 +601,5 @@ struct ib_cm_sidr_rep_param {
 int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
 			struct ib_cm_sidr_rep_param *param);
 
+int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac);
 #endif /* IB_CM_H */

include/rdma/ib_pack.h

@@ -34,6 +34,7 @@
 #define IB_PACK_H
 
 #include <rdma/ib_verbs.h>
+#include <uapi/linux/if_ether.h>
 
 enum {
 	IB_LRH_BYTES  = 8,

include/rdma/ib_sa.h

@@ -154,6 +154,9 @@ struct ib_sa_path_rec {
 	u8           packet_life_time_selector;
 	u8           packet_life_time;
 	u8           preference;
+	u8           smac[ETH_ALEN];
+	u8           dmac[ETH_ALEN];
+	u16	     vlan_id;
 };
 
 #define IB_SA_MCMEMBER_REC_MGID				IB_SA_COMP_MASK( 0)

include/rdma/ib_verbs.h

@@ -48,6 +48,7 @@
 #include <linux/rwsem.h>
 #include <linux/scatterlist.h>
 #include <linux/workqueue.h>
+#include <uapi/linux/if_ether.h>
 
 #include <linux/atomic.h>
 #include <asm/uaccess.h>
@@ -474,6 +475,8 @@ struct ib_ah_attr {
 	u8			static_rate;
 	u8			ah_flags;
 	u8			port_num;
+	u8			dmac[ETH_ALEN];
+	u16			vlan_id;
 };
 
 enum ib_wc_status {
@@ -526,6 +529,8 @@ enum ib_wc_flags {
 	IB_WC_WITH_IMM		= (1<<1),
 	IB_WC_WITH_INVALIDATE	= (1<<2),
 	IB_WC_IP_CSUM_OK	= (1<<3),
+	IB_WC_WITH_SMAC		= (1<<4),
+	IB_WC_WITH_VLAN		= (1<<5),
 };
 
 struct ib_wc {
@@ -546,6 +551,8 @@ struct ib_wc {
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */
+	u8			smac[ETH_ALEN];
+	u16			vlan_id;
 };
 
 enum ib_cq_notify_flags {
@@ -724,7 +731,11 @@ enum ib_qp_attr_mask {
 	IB_QP_MAX_DEST_RD_ATOMIC	= (1<<17),
 	IB_QP_PATH_MIG_STATE		= (1<<18),
 	IB_QP_CAP			= (1<<19),
-	IB_QP_DEST_QPN			= (1<<20)
+	IB_QP_DEST_QPN			= (1<<20),
+	IB_QP_SMAC			= (1<<21),
+	IB_QP_ALT_SMAC			= (1<<22),
+	IB_QP_VID			= (1<<23),
+	IB_QP_ALT_VID			= (1<<24),
 };
 
 enum ib_qp_state {
@@ -774,6 +785,10 @@ struct ib_qp_attr {
 	u8			rnr_retry;
 	u8			alt_port_num;
 	u8			alt_timeout;
+	u8			smac[ETH_ALEN];
+	u8			alt_smac[ETH_ALEN];
+	u16			vlan_id;
+	u16			alt_vlan_id;
 };
 
 enum ib_wr_opcode {
@@ -1505,6 +1520,7 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
  * @next_state: Next QP state
  * @type: QP type
  * @mask: Mask of supplied QP attributes
+ * @ll : link layer of port
  *
  * This function is a helper function that a low-level driver's
  * modify_qp method can use to validate the consumer's input.  It
@@ -1513,7 +1529,8 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
  * and that the attribute mask supplied is allowed for the transition.
  */
 int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
-		       enum ib_qp_type type, enum ib_qp_attr_mask mask);
+		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
+		       enum rdma_link_layer ll);
 
 int ib_register_event_handler  (struct ib_event_handler *event_handler);
 int ib_unregister_event_handler(struct ib_event_handler *event_handler);