Merge branches 'amso1100', 'cma', 'cxgb3', 'cxgb4', 'ehca', 'iboe', 'ipoib', 'misc', 'mlx4', 'nes', 'qib' and 'srp' into for-next

MAINTAINERS

@@ -2951,7 +2951,7 @@ M:	Roland Dreier <rolandd@cisco.com>
 M:	Sean Hefty <sean.hefty@intel.com>
 M:	Hal Rosenstock <hal.rosenstock@gmail.com>
 L:	linux-rdma@vger.kernel.org
-W:	http://www.openib.org/
+W:	http://www.openfabrics.org/
 Q:	http://patchwork.kernel.org/project/linux-rdma/list/
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband.git
 S:	Supported
@@ -5035,6 +5035,16 @@ W:	http://www.kernel.dk
 S:	Maintained
 F:	drivers/scsi/sr*
 
+SCSI RDMA PROTOCOL (SRP) INITIATOR
+M:	David Dillow <dillowda@ornl.gov>
+L:	linux-rdma@vger.kernel.org
+S:	Supported
+W:	http://www.openfabrics.org
+Q:	http://patchwork.kernel.org/project/linux-rdma/list/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/dad/srp-initiator.git
+F:	drivers/infiniband/ulp/srp/
+F:	include/scsi/srp.h
+
 SCSI SG DRIVER
 M:	Doug Gilbert <dgilbert@interlog.com>
 L:	linux-scsi@vger.kernel.org

drivers/infiniband/core/agent.c

@@ -59,8 +59,8 @@ __ib_get_agent_port(struct ib_device *device, int port_num)
 	struct ib_agent_port_private *entry;
 
 	list_for_each_entry(entry, &ib_agent_port_list, port_list) {
-		if (entry->agent[0]->device == device &&
-		    entry->agent[0]->port_num == port_num)
+		if (entry->agent[1]->device == device &&
+		    entry->agent[1]->port_num == port_num)
 			return entry;
 	}
 	return NULL;
@@ -155,14 +155,16 @@ int ib_agent_port_open(struct ib_device *device, int port_num)
 		goto error1;
 	}
 
-	/* Obtain send only MAD agent for SMI QP */
-	port_priv->agent[0] = ib_register_mad_agent(device, port_num,
-						    IB_QPT_SMI, NULL, 0,
-						    &agent_send_handler,
-						    NULL, NULL);
-	if (IS_ERR(port_priv->agent[0])) {
-		ret = PTR_ERR(port_priv->agent[0]);
-		goto error2;
+	if (rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND) {
+		/* Obtain send only MAD agent for SMI QP */
+		port_priv->agent[0] = ib_register_mad_agent(device, port_num,
+							    IB_QPT_SMI, NULL, 0,
+							    &agent_send_handler,
+							    NULL, NULL);
+		if (IS_ERR(port_priv->agent[0])) {
+			ret = PTR_ERR(port_priv->agent[0]);
+			goto error2;
+		}
 	}
 
 	/* Obtain send only MAD agent for GSI QP */
@@ -182,7 +184,8 @@ int ib_agent_port_open(struct ib_device *device, int port_num)
 	return 0;
 
 error3:
-	ib_unregister_mad_agent(port_priv->agent[0]);
+	if (port_priv->agent[0])
+		ib_unregister_mad_agent(port_priv->agent[0]);
 error2:
 	kfree(port_priv);
 error1:
@@ -205,7 +208,9 @@ int ib_agent_port_close(struct ib_device *device, int port_num)
 	spin_unlock_irqrestore(&ib_agent_port_list_lock, flags);
 
 	ib_unregister_mad_agent(port_priv->agent[1]);
-	ib_unregister_mad_agent(port_priv->agent[0]);
+	if (port_priv->agent[0])
+		ib_unregister_mad_agent(port_priv->agent[0]);
+
 	kfree(port_priv);
 	return 0;
 }

drivers/infiniband/core/cma.c

@@ -59,6 +59,7 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_CM_RESPONSE_TIMEOUT 20
 #define CMA_MAX_CM_RETRIES 15
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
+#define CMA_IBOE_PACKET_LIFETIME 18
 
 static void cma_add_one(struct ib_device *device);
 static void cma_remove_one(struct ib_device *device);
@@ -157,6 +158,7 @@ struct cma_multicast {
 	struct list_head	list;
 	void			*context;
 	struct sockaddr_storage	addr;
+	struct kref		mcref;
 };
 
 struct cma_work {
@@ -173,6 +175,12 @@ struct cma_ndev_work {
 	struct rdma_cm_event	event;
 };
 
+struct iboe_mcast_work {
+	struct work_struct	 work;
+	struct rdma_id_private	*id;
+	struct cma_multicast	*mc;
+};
+
 union cma_ip_addr {
 	struct in6_addr ip6;
 	struct {
@@ -281,6 +289,8 @@ static void cma_attach_to_dev(struct rdma_id_private *id_priv,
 	atomic_inc(&cma_dev->refcount);
 	id_priv->cma_dev = cma_dev;
 	id_priv->id.device = cma_dev->device;
+	id_priv->id.route.addr.dev_addr.transport =
+		rdma_node_get_transport(cma_dev->device->node_type);
 	list_add_tail(&id_priv->list, &cma_dev->id_list);
 }
 
@@ -290,6 +300,14 @@ static inline void cma_deref_dev(struct cma_device *cma_dev)
 		complete(&cma_dev->comp);
 }
 
+static inline void release_mc(struct kref *kref)
+{
+	struct cma_multicast *mc = container_of(kref, struct cma_multicast, mcref);
+
+	kfree(mc->multicast.ib);
+	kfree(mc);
+}
+
 static void cma_detach_from_dev(struct rdma_id_private *id_priv)
 {
 	list_del(&id_priv->list);
@@ -323,22 +341,63 @@ static int cma_set_qkey(struct rdma_id_private *id_priv)
 	return ret;
 }
 
+static int find_gid_port(struct ib_device *device, union ib_gid *gid, u8 port_num)
+{
+	int i;
+	int err;
+	struct ib_port_attr props;
+	union ib_gid tmp;
+
+	err = ib_query_port(device, port_num, &props);
+	if (err)
+		return 1;
+
+	for (i = 0; i < props.gid_tbl_len; ++i) {
+		err = ib_query_gid(device, port_num, i, &tmp);
+		if (err)
+			return 1;
+		if (!memcmp(&tmp, gid, sizeof tmp))
+			return 0;
+	}
+
+	return -EAGAIN;
+}
+
 static int cma_acquire_dev(struct rdma_id_private *id_priv)
 {
 	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
 	struct cma_device *cma_dev;
-	union ib_gid gid;
+	union ib_gid gid, iboe_gid;
 	int ret = -ENODEV;
+	u8 port;
+	enum rdma_link_layer dev_ll = dev_addr->dev_type == ARPHRD_INFINIBAND ?
+		IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
 
-	rdma_addr_get_sgid(dev_addr, &gid);
+	iboe_addr_get_sgid(dev_addr, &iboe_gid);
+	memcpy(&gid, dev_addr->src_dev_addr +
+	       rdma_addr_gid_offset(dev_addr), sizeof gid);
 	list_for_each_entry(cma_dev, &dev_list, list) {
-		ret = ib_find_cached_gid(cma_dev->device, &gid,
-					 &id_priv->id.port_num, NULL);
-		if (!ret) {
-			cma_attach_to_dev(id_priv, cma_dev);
-			break;
+		for (port = 1; port <= cma_dev->device->phys_port_cnt; ++port) {
+			if (rdma_port_get_link_layer(cma_dev->device, port) == dev_ll) {
+				if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB &&
+				    rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET)
+					ret = find_gid_port(cma_dev->device, &iboe_gid, port);
+				else
+					ret = find_gid_port(cma_dev->device, &gid, port);
+
+				if (!ret) {
+					id_priv->id.port_num = port;
+					goto out;
+				} else if (ret == 1)
+					break;
+			}
 		}
 	}
+
+out:
+	if (!ret)
+		cma_attach_to_dev(id_priv, cma_dev);
+
 	return ret;
 }
 
@@ -556,10 +615,16 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv,
 {
 	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
 	int ret;
+	u16 pkey;
+
+	if (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) ==
+	    IB_LINK_LAYER_INFINIBAND)
+		pkey = ib_addr_get_pkey(dev_addr);
+	else
+		pkey = 0xffff;
 
 	ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num,
-				  ib_addr_get_pkey(dev_addr),
-				  &qp_attr->pkey_index);
+				  pkey, &qp_attr->pkey_index);
 	if (ret)
 		return ret;
 
@@ -737,8 +802,8 @@ static inline int cma_user_data_offset(enum rdma_port_space ps)
 
 static void cma_cancel_route(struct rdma_id_private *id_priv)
 {
-	switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	switch (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)) {
+	case IB_LINK_LAYER_INFINIBAND:
 		if (id_priv->query)
 			ib_sa_cancel_query(id_priv->query_id, id_priv->query);
 		break;
@@ -816,8 +881,17 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv)
 		mc = container_of(id_priv->mc_list.next,
 				  struct cma_multicast, list);
 		list_del(&mc->list);
-		ib_sa_free_multicast(mc->multicast.ib);
-		kfree(mc);
+		switch (rdma_port_get_link_layer(id_priv->cma_dev->device, id_priv->id.port_num)) {
+		case IB_LINK_LAYER_INFINIBAND:
+			ib_sa_free_multicast(mc->multicast.ib);
+			kfree(mc);
+			break;
+		case IB_LINK_LAYER_ETHERNET:
+			kref_put(&mc->mcref, release_mc);
+			break;
+		default:
+			break;
+		}
 	}
 }
 
@@ -833,7 +907,7 @@ void rdma_destroy_id(struct rdma_cm_id *id)
 	mutex_lock(&lock);
 	if (id_priv->cma_dev) {
 		mutex_unlock(&lock);
-		switch (rdma_node_get_transport(id->device->node_type)) {
+		switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
 		case RDMA_TRANSPORT_IB:
 			if (id_priv->cm_id.ib && !IS_ERR(id_priv->cm_id.ib))
 				ib_destroy_cm_id(id_priv->cm_id.ib);
@@ -1708,6 +1782,81 @@ static int cma_resolve_iw_route(struct rdma_id_private *id_priv, int timeout_ms)
 	return 0;
 }
 
+static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
+{
+	struct rdma_route *route = &id_priv->id.route;
+	struct rdma_addr *addr = &route->addr;
+	struct cma_work *work;
+	int ret;
+	struct sockaddr_in *src_addr = (struct sockaddr_in *)&route->addr.src_addr;
+	struct sockaddr_in *dst_addr = (struct sockaddr_in *)&route->addr.dst_addr;
+	struct net_device *ndev = NULL;
+	u16 vid;
+
+	if (src_addr->sin_family != dst_addr->sin_family)
+		return -EINVAL;
+
+	work = kzalloc(sizeof *work, GFP_KERNEL);
+	if (!work)
+		return -ENOMEM;
+
+	work->id = id_priv;
+	INIT_WORK(&work->work, cma_work_handler);
+
+	route->path_rec = kzalloc(sizeof *route->path_rec, GFP_KERNEL);
+	if (!route->path_rec) {
+		ret = -ENOMEM;
+		goto err1;
+	}
+
+	route->num_paths = 1;
+
+	if (addr->dev_addr.bound_dev_if)
+		ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if);
+	if (!ndev) {
+		ret = -ENODEV;
+		goto err2;
+	}
+
+	vid = rdma_vlan_dev_vlan_id(ndev);
+
+	iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr, vid);
+	iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, vid);
+
+	route->path_rec->hop_limit = 1;
+	route->path_rec->reversible = 1;
+	route->path_rec->pkey = cpu_to_be16(0xffff);
+	route->path_rec->mtu_selector = IB_SA_EQ;
+	route->path_rec->sl = id_priv->tos >> 5;
+
+	route->path_rec->mtu = iboe_get_mtu(ndev->mtu);
+	route->path_rec->rate_selector = IB_SA_EQ;
+	route->path_rec->rate = iboe_get_rate(ndev);
+	dev_put(ndev);
+	route->path_rec->packet_life_time_selector = IB_SA_EQ;
+	route->path_rec->packet_life_time = CMA_IBOE_PACKET_LIFETIME;
+	if (!route->path_rec->mtu) {
+		ret = -EINVAL;
+		goto err2;
+	}
+
+	work->old_state = CMA_ROUTE_QUERY;
+	work->new_state = CMA_ROUTE_RESOLVED;
+	work->event.event = RDMA_CM_EVENT_ROUTE_RESOLVED;
+	work->event.status = 0;
+
+	queue_work(cma_wq, &work->work);
+
+	return 0;
+
+err2:
+	kfree(route->path_rec);
+	route->path_rec = NULL;
+err1:
+	kfree(work);
+	return ret;
+}
+
 int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms)
 {
 	struct rdma_id_private *id_priv;
@@ -1720,7 +1869,16 @@ int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms)
 	atomic_inc(&id_priv->refcount);
 	switch (rdma_node_get_transport(id->device->node_type)) {
 	case RDMA_TRANSPORT_IB:
-		ret = cma_resolve_ib_route(id_priv, timeout_ms);
+		switch (rdma_port_get_link_layer(id->device, id->port_num)) {
+		case IB_LINK_LAYER_INFINIBAND:
+			ret = cma_resolve_ib_route(id_priv, timeout_ms);
+			break;
+		case IB_LINK_LAYER_ETHERNET:
+			ret = cma_resolve_iboe_route(id_priv);
+			break;
+		default:
+			ret = -ENOSYS;
+		}
 		break;
 	case RDMA_TRANSPORT_IWARP:
 		ret = cma_resolve_iw_route(id_priv, timeout_ms);
@@ -1773,7 +1931,7 @@ port_found:
 		goto out;
 
 	id_priv->id.route.addr.dev_addr.dev_type =
-		(rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB) ?
+		(rdma_port_get_link_layer(cma_dev->device, p) == IB_LINK_LAYER_INFINIBAND) ?
 		ARPHRD_INFINIBAND : ARPHRD_ETHER;
 
 	rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid);
@@ -2758,6 +2916,102 @@ static int cma_join_ib_multicast(struct rdma_id_private *id_priv,
 	return 0;
 }
 
+static void iboe_mcast_work_handler(struct work_struct *work)
+{
+	struct iboe_mcast_work *mw = container_of(work, struct iboe_mcast_work, work);
+	struct cma_multicast *mc = mw->mc;
+	struct ib_sa_multicast *m = mc->multicast.ib;
+
+	mc->multicast.ib->context = mc;
+	cma_ib_mc_handler(0, m);
+	kref_put(&mc->mcref, release_mc);
+	kfree(mw);
+}
+
+static void cma_iboe_set_mgid(struct sockaddr *addr, union ib_gid *mgid)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)addr;
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)addr;
+
+	if (cma_any_addr(addr)) {
+		memset(mgid, 0, sizeof *mgid);
+	} else if (addr->sa_family == AF_INET6) {
+		memcpy(mgid, &sin6->sin6_addr, sizeof *mgid);
+	} else {
+		mgid->raw[0] = 0xff;
+		mgid->raw[1] = 0x0e;
+		mgid->raw[2] = 0;
+		mgid->raw[3] = 0;
+		mgid->raw[4] = 0;
+		mgid->raw[5] = 0;
+		mgid->raw[6] = 0;
+		mgid->raw[7] = 0;
+		mgid->raw[8] = 0;
+		mgid->raw[9] = 0;
+		mgid->raw[10] = 0xff;
+		mgid->raw[11] = 0xff;
+		*(__be32 *)(&mgid->raw[12]) = sin->sin_addr.s_addr;
+	}
+}
+
+static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
+				   struct cma_multicast *mc)
+{
+	struct iboe_mcast_work *work;
+	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
+	int err;
+	struct sockaddr *addr = (struct sockaddr *)&mc->addr;
+	struct net_device *ndev = NULL;
+
+	if (cma_zero_addr((struct sockaddr *)&mc->addr))
+		return -EINVAL;
+
+	work = kzalloc(sizeof *work, GFP_KERNEL);
+	if (!work)
+		return -ENOMEM;
+
+	mc->multicast.ib = kzalloc(sizeof(struct ib_sa_multicast), GFP_KERNEL);
+	if (!mc->multicast.ib) {
+		err = -ENOMEM;
+		goto out1;
+	}
+
+	cma_iboe_set_mgid(addr, &mc->multicast.ib->rec.mgid);
+
+	mc->multicast.ib->rec.pkey = cpu_to_be16(0xffff);
+	if (id_priv->id.ps == RDMA_PS_UDP)
+		mc->multicast.ib->rec.qkey = cpu_to_be32(RDMA_UDP_QKEY);
+
+	if (dev_addr->bound_dev_if)
+		ndev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+	if (!ndev) {
+		err = -ENODEV;
+		goto out2;
+	}
+	mc->multicast.ib->rec.rate = iboe_get_rate(ndev);
+	mc->multicast.ib->rec.hop_limit = 1;
+	mc->multicast.ib->rec.mtu = iboe_get_mtu(ndev->mtu);
+	dev_put(ndev);
+	if (!mc->multicast.ib->rec.mtu) {
+		err = -EINVAL;
+		goto out2;
+	}
+	iboe_addr_get_sgid(dev_addr, &mc->multicast.ib->rec.port_gid);
+	work->id = id_priv;
+	work->mc = mc;
+	INIT_WORK(&work->work, iboe_mcast_work_handler);
+	kref_get(&mc->mcref);
+	queue_work(cma_wq, &work->work);
+
+	return 0;
+
+out2:
+	kfree(mc->multicast.ib);
+out1:
+	kfree(work);
+	return err;
+}
+
 int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
 			void *context)
 {
@@ -2784,7 +3038,17 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
 
 	switch (rdma_node_get_transport(id->device->node_type)) {
 	case RDMA_TRANSPORT_IB:
-		ret = cma_join_ib_multicast(id_priv, mc);
+		switch (rdma_port_get_link_layer(id->device, id->port_num)) {
+		case IB_LINK_LAYER_INFINIBAND:
+			ret = cma_join_ib_multicast(id_priv, mc);
+			break;
+		case IB_LINK_LAYER_ETHERNET:
+			kref_init(&mc->mcref);
+			ret = cma_iboe_join_multicast(id_priv, mc);
+			break;
+		default:
+			ret = -EINVAL;
+		}
 		break;
 	default:
 		ret = -ENOSYS;
@@ -2817,8 +3081,19 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr)
 				ib_detach_mcast(id->qp,
 						&mc->multicast.ib->rec.mgid,
 						mc->multicast.ib->rec.mlid);
-			ib_sa_free_multicast(mc->multicast.ib);
-			kfree(mc);
+			if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) == RDMA_TRANSPORT_IB) {
+				switch (rdma_port_get_link_layer(id->device, id->port_num)) {
+				case IB_LINK_LAYER_INFINIBAND:
+					ib_sa_free_multicast(mc->multicast.ib);
+					kfree(mc);
+					break;
+				case IB_LINK_LAYER_ETHERNET:
+					kref_put(&mc->mcref, release_mc);
+					break;
+				default:
+					break;
+				}
+			}
 			return;
 		}
 	}

drivers/infiniband/core/iwcm.c

@@ -506,6 +506,8 @@ int iw_cm_accept(struct iw_cm_id *cm_id,
 	qp = cm_id->device->iwcm->get_qp(cm_id->device, iw_param->qpn);
 	if (!qp) {
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+		clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags);
+		wake_up_all(&cm_id_priv->connect_wait);
 		return -EINVAL;
 	}
 	cm_id->device->iwcm->add_ref(qp);
@@ -565,6 +567,8 @@ int iw_cm_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *iw_param)
 	qp = cm_id->device->iwcm->get_qp(cm_id->device, iw_param->qpn);
 	if (!qp) {
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
+		clear_bit(IWCM_F_CONNECT_WAIT, &cm_id_priv->flags);
+		wake_up_all(&cm_id_priv->connect_wait);
 		return -EINVAL;
 	}
 	cm_id->device->iwcm->add_ref(qp);

drivers/infiniband/core/mad.c

@@ -2598,6 +2598,9 @@ static void cleanup_recv_queue(struct ib_mad_qp_info *qp_info)
 	struct ib_mad_private *recv;
 	struct ib_mad_list_head *mad_list;
 
+	if (!qp_info->qp)
+		return;
+
 	while (!list_empty(&qp_info->recv_queue.list)) {
 
 		mad_list = list_entry(qp_info->recv_queue.list.next,
@@ -2639,6 +2642,9 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 
 	for (i = 0; i < IB_MAD_QPS_CORE; i++) {
 		qp = port_priv->qp_info[i].qp;
+		if (!qp)
+			continue;
+
 		/*
 		 * PKey index for QP1 is irrelevant but
 		 * one is needed for the Reset to Init transition
@@ -2680,6 +2686,9 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 	}
 
 	for (i = 0; i < IB_MAD_QPS_CORE; i++) {
+		if (!port_priv->qp_info[i].qp)
+			continue;
+
 		ret = ib_mad_post_receive_mads(&port_priv->qp_info[i], NULL);
 		if (ret) {
 			printk(KERN_ERR PFX "Couldn't post receive WRs\n");
@@ -2758,6 +2767,9 @@ error:
 
 static void destroy_mad_qp(struct ib_mad_qp_info *qp_info)
 {
+	if (!qp_info->qp)
+		return;
+
 	ib_destroy_qp(qp_info->qp);
 	kfree(qp_info->snoop_table);
 }
@@ -2773,6 +2785,7 @@ static int ib_mad_port_open(struct ib_device *device,
 	struct ib_mad_port_private *port_priv;
 	unsigned long flags;
 	char name[sizeof "ib_mad123"];
+	int has_smi;
 
 	/* Create new device info */
 	port_priv = kzalloc(sizeof *port_priv, GFP_KERNEL);
@@ -2788,7 +2801,11 @@ static int ib_mad_port_open(struct ib_device *device,
 	init_mad_qp(port_priv, &port_priv->qp_info[0]);
 	init_mad_qp(port_priv, &port_priv->qp_info[1]);
 
-	cq_size = (mad_sendq_size + mad_recvq_size) * 2;
+	cq_size = mad_sendq_size + mad_recvq_size;
+	has_smi = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND;
+	if (has_smi)
+		cq_size *= 2;
+
 	port_priv->cq = ib_create_cq(port_priv->device,
 				     ib_mad_thread_completion_handler,
 				     NULL, port_priv, cq_size, 0);
@@ -2812,9 +2829,11 @@ static int ib_mad_port_open(struct ib_device *device,
 		goto error5;
 	}
 
-	ret = create_mad_qp(&port_priv->qp_info[0], IB_QPT_SMI);
-	if (ret)
-		goto error6;
+	if (has_smi) {
+		ret = create_mad_qp(&port_priv->qp_info[0], IB_QPT_SMI);
+		if (ret)
+			goto error6;
+	}
 	ret = create_mad_qp(&port_priv->qp_info[1], IB_QPT_GSI);
 	if (ret)
 		goto error7;

drivers/infiniband/core/multicast.c

@@ -774,6 +774,10 @@ static void mcast_event_handler(struct ib_event_handler *handler,
 	int index;
 
 	dev = container_of(handler, struct mcast_device, event_handler);
+	if (rdma_port_get_link_layer(dev->device, event->element.port_num) !=
+	    IB_LINK_LAYER_INFINIBAND)
+		return;
+
 	index = event->element.port_num - dev->start_port;
 
 	switch (event->event) {
@@ -796,6 +800,7 @@ static void mcast_add_one(struct ib_device *device)
 	struct mcast_device *dev;
 	struct mcast_port *port;
 	int i;
+	int count = 0;
 
 	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
 		return;
@@ -813,6 +818,9 @@ static void mcast_add_one(struct ib_device *device)
 	}
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
+		if (rdma_port_get_link_layer(device, dev->start_port + i) !=
+		    IB_LINK_LAYER_INFINIBAND)
+			continue;
 		port = &dev->port[i];
 		port->dev = dev;
 		port->port_num = dev->start_port + i;
@@ -820,6 +828,12 @@ static void mcast_add_one(struct ib_device *device)
 		port->table = RB_ROOT;
 		init_completion(&port->comp);
 		atomic_set(&port->refcount, 1);
+		++count;
+	}
+
+	if (!count) {
+		kfree(dev);
+		return;
 	}
 
 	dev->device = device;
@@ -843,9 +857,12 @@ static void mcast_remove_one(struct ib_device *device)
 	flush_workqueue(mcast_wq);
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
-		port = &dev->port[i];
-		deref_port(port);
-		wait_for_completion(&port->comp);
+		if (rdma_port_get_link_layer(device, dev->start_port + i) ==
+		    IB_LINK_LAYER_INFINIBAND) {
+			port = &dev->port[i];
+			deref_port(port);
+			wait_for_completion(&port->comp);
+		}
 	}
 
 	kfree(dev);

drivers/infiniband/core/sa_query.c

@@ -416,6 +416,9 @@ static void ib_sa_event(struct ib_event_handler *handler, struct ib_event *event
 		struct ib_sa_port *port =
 			&sa_dev->port[event->element.port_num - sa_dev->start_port];
 
+		if (rdma_port_get_link_layer(handler->device, port->port_num) != IB_LINK_LAYER_INFINIBAND)
+			return;
+
 		spin_lock_irqsave(&port->ah_lock, flags);
 		if (port->sm_ah)
 			kref_put(&port->sm_ah->ref, free_sm_ah);
@@ -493,6 +496,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 {
 	int ret;
 	u16 gid_index;
+	int force_grh;
 
 	memset(ah_attr, 0, sizeof *ah_attr);
 	ah_attr->dlid = be16_to_cpu(rec->dlid);
@@ -502,7 +506,9 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 	ah_attr->port_num = port_num;
 	ah_attr->static_rate = rec->rate;
 
-	if (rec->hop_limit > 1) {
+	force_grh = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_ETHERNET;
+
+	if (rec->hop_limit > 1 || force_grh) {
 		ah_attr->ah_flags = IB_AH_GRH;
 		ah_attr->grh.dgid = rec->dgid;
 
@@ -1007,7 +1013,7 @@ static void ib_sa_add_one(struct ib_device *device)
 		e = device->phys_port_cnt;
 	}
 
-	sa_dev = kmalloc(sizeof *sa_dev +
+	sa_dev = kzalloc(sizeof *sa_dev +
 			 (e - s + 1) * sizeof (struct ib_sa_port),
 			 GFP_KERNEL);
 	if (!sa_dev)
@@ -1017,9 +1023,12 @@ static void ib_sa_add_one(struct ib_device *device)
 	sa_dev->end_port   = e;
 
 	for (i = 0; i <= e - s; ++i) {
+		spin_lock_init(&sa_dev->port[i].ah_lock);
+		if (rdma_port_get_link_layer(device, i + 1) != IB_LINK_LAYER_INFINIBAND)
+			continue;
+
 		sa_dev->port[i].sm_ah    = NULL;
 		sa_dev->port[i].port_num = i + s;
-		spin_lock_init(&sa_dev->port[i].ah_lock);
 
 		sa_dev->port[i].agent =
 			ib_register_mad_agent(device, i + s, IB_QPT_GSI,
@@ -1045,13 +1054,15 @@ static void ib_sa_add_one(struct ib_device *device)
 		goto err;
 
 	for (i = 0; i <= e - s; ++i)
-		update_sm_ah(&sa_dev->port[i].update_task);
+		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+			update_sm_ah(&sa_dev->port[i].update_task);
 
 	return;
 
 err:
 	while (--i >= 0)
-		ib_unregister_mad_agent(sa_dev->port[i].agent);
+		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+			ib_unregister_mad_agent(sa_dev->port[i].agent);
 
 	kfree(sa_dev);
 
@@ -1071,9 +1082,12 @@ static void ib_sa_remove_one(struct ib_device *device)
 	flush_scheduled_work();
 
 	for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) {
-		ib_unregister_mad_agent(sa_dev->port[i].agent);
-		if (sa_dev->port[i].sm_ah)
-			kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);
+		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) {
+			ib_unregister_mad_agent(sa_dev->port[i].agent);
+			if (sa_dev->port[i].sm_ah)
+				kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);
+		}
+
 	}
 
 	kfree(sa_dev);

drivers/infiniband/core/sysfs.c

@@ -222,6 +222,19 @@ static ssize_t phys_state_show(struct ib_port *p, struct port_attribute *unused,
 	}
 }
 
+static ssize_t link_layer_show(struct ib_port *p, struct port_attribute *unused,
+			       char *buf)
+{
+	switch (rdma_port_get_link_layer(p->ibdev, p->port_num)) {
+	case IB_LINK_LAYER_INFINIBAND:
+		return sprintf(buf, "%s\n", "InfiniBand");
+	case IB_LINK_LAYER_ETHERNET:
+		return sprintf(buf, "%s\n", "Ethernet");
+	default:
+		return sprintf(buf, "%s\n", "Unknown");
+	}
+}
+
 static PORT_ATTR_RO(state);
 static PORT_ATTR_RO(lid);
 static PORT_ATTR_RO(lid_mask_count);
@@ -230,6 +243,7 @@ static PORT_ATTR_RO(sm_sl);
 static PORT_ATTR_RO(cap_mask);
 static PORT_ATTR_RO(rate);
 static PORT_ATTR_RO(phys_state);
+static PORT_ATTR_RO(link_layer);
 
 static struct attribute *port_default_attrs[] = {
 	&port_attr_state.attr,
@@ -240,6 +254,7 @@ static struct attribute *port_default_attrs[] = {
 	&port_attr_cap_mask.attr,
 	&port_attr_rate.attr,
 	&port_attr_phys_state.attr,
+	&port_attr_link_layer.attr,
 	NULL
 };
 

drivers/infiniband/core/ucma.c

@@ -40,6 +40,7 @@
 #include <linux/in6.h>
 #include <linux/miscdevice.h>
 #include <linux/slab.h>
+#include <linux/sysctl.h>
 
 #include <rdma/rdma_user_cm.h>
 #include <rdma/ib_marshall.h>
@@ -50,8 +51,24 @@ MODULE_AUTHOR("Sean Hefty");
 MODULE_DESCRIPTION("RDMA Userspace Connection Manager Access");
 MODULE_LICENSE("Dual BSD/GPL");
 
-enum {
-	UCMA_MAX_BACKLOG	= 128
+static unsigned int max_backlog = 1024;
+
+static struct ctl_table_header *ucma_ctl_table_hdr;
+static ctl_table ucma_ctl_table[] = {
+	{
+		.procname	= "max_backlog",
+		.data		= &max_backlog,
+		.maxlen		= sizeof max_backlog,
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{ }
+};
+
+static struct ctl_path ucma_ctl_path[] = {
+	{ .procname = "net" },
+	{ .procname = "rdma_ucm" },
+	{ }
 };
 
 struct ucma_file {
@@ -583,6 +600,42 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp,
 	}
 }
 
+static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
+				 struct rdma_route *route)
+{
+	struct rdma_dev_addr *dev_addr;
+	struct net_device *dev;
+	u16 vid = 0;
+
+	resp->num_paths = route->num_paths;
+	switch (route->num_paths) {
+	case 0:
+		dev_addr = &route->addr.dev_addr;
+		dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+			if (dev) {
+				vid = rdma_vlan_dev_vlan_id(dev);
+				dev_put(dev);
+			}
+
+		iboe_mac_vlan_to_ll((union ib_gid *) &resp->ib_route[0].dgid,
+				    dev_addr->dst_dev_addr, vid);
+		iboe_addr_get_sgid(dev_addr,
+				   (union ib_gid *) &resp->ib_route[0].sgid);
+		resp->ib_route[0].pkey = cpu_to_be16(0xffff);
+		break;
+	case 2:
+		ib_copy_path_rec_to_user(&resp->ib_route[1],
+					 &route->path_rec[1]);
+		/* fall through */
+	case 1:
+		ib_copy_path_rec_to_user(&resp->ib_route[0],
+					 &route->path_rec[0]);
+		break;
+	default:
+		break;
+	}
+}
+
 static ssize_t ucma_query_route(struct ucma_file *file,
 				const char __user *inbuf,
 				int in_len, int out_len)
@@ -617,12 +670,17 @@ static ssize_t ucma_query_route(struct ucma_file *file,
 
 	resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid;
 	resp.port_num = ctx->cm_id->port_num;
-	switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
-		ucma_copy_ib_route(&resp, &ctx->cm_id->route);
-		break;
-	default:
-		break;
+	if (rdma_node_get_transport(ctx->cm_id->device->node_type) == RDMA_TRANSPORT_IB) {
+		switch (rdma_port_get_link_layer(ctx->cm_id->device, ctx->cm_id->port_num)) {
+		case IB_LINK_LAYER_INFINIBAND:
+			ucma_copy_ib_route(&resp, &ctx->cm_id->route);
+			break;
+		case IB_LINK_LAYER_ETHERNET:
+			ucma_copy_iboe_route(&resp, &ctx->cm_id->route);
+			break;
+		default:
+			break;
+		}
 	}
 
 out:
@@ -686,8 +744,8 @@ static ssize_t ucma_listen(struct ucma_file *file, const char __user *inbuf,
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
 
-	ctx->backlog = cmd.backlog > 0 && cmd.backlog < UCMA_MAX_BACKLOG ?
-		       cmd.backlog : UCMA_MAX_BACKLOG;
+	ctx->backlog = cmd.backlog > 0 && cmd.backlog < max_backlog ?
+		       cmd.backlog : max_backlog;
 	ret = rdma_listen(ctx->cm_id, ctx->backlog);
 	ucma_put_ctx(ctx);
 	return ret;
@@ -1279,16 +1337,26 @@ static int __init ucma_init(void)
 	ret = device_create_file(ucma_misc.this_device, &dev_attr_abi_version);
 	if (ret) {
 		printk(KERN_ERR "rdma_ucm: couldn't create abi_version attr\n");
-		goto err;
+		goto err1;
+	}
+
+	ucma_ctl_table_hdr = register_sysctl_paths(ucma_ctl_path, ucma_ctl_table);
+	if (!ucma_ctl_table_hdr) {
+		printk(KERN_ERR "rdma_ucm: couldn't register sysctl paths\n");
+		ret = -ENOMEM;
+		goto err2;
 	}
 	return 0;
-err:
+err2:
+	device_remove_file(ucma_misc.this_device, &dev_attr_abi_version);
+err1:
 	misc_deregister(&ucma_misc);
 	return ret;
 }
 
 static void __exit ucma_cleanup(void)
 {
+	unregister_sysctl_table(ucma_ctl_table_hdr);
 	device_remove_file(ucma_misc.this_device, &dev_attr_abi_version);
 	misc_deregister(&ucma_misc);
 	idr_destroy(&ctx_idr);

drivers/infiniband/core/ud_header.c

@@ -33,6 +33,7 @@
 
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/if_ether.h>
 
 #include <rdma/ib_pack.h>
 
@@ -80,6 +81,40 @@ static const struct ib_field lrh_table[]  = {
 	  .size_bits    = 16 }
 };
 
+static const struct ib_field eth_table[]  = {
+	{ STRUCT_FIELD(eth, dmac_h),
+	  .offset_words = 0,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ STRUCT_FIELD(eth, dmac_l),
+	  .offset_words = 1,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ STRUCT_FIELD(eth, smac_h),
+	  .offset_words = 1,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 },
+	{ STRUCT_FIELD(eth, smac_l),
+	  .offset_words = 2,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ STRUCT_FIELD(eth, type),
+	  .offset_words = 3,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 }
+};
+
+static const struct ib_field vlan_table[]  = {
+	{ STRUCT_FIELD(vlan, tag),
+	  .offset_words = 0,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ STRUCT_FIELD(vlan, type),
+	  .offset_words = 0,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 }
+};
+
 static const struct ib_field grh_table[]  = {
 	{ STRUCT_FIELD(grh, ip_version),
 	  .offset_words = 0,
@@ -180,38 +215,43 @@ static const struct ib_field deth_table[] = {
 /**
  * ib_ud_header_init - Initialize UD header structure
  * @payload_bytes:Length of packet payload
+ * @lrh_present: specify if LRH is present
+ * @eth_present: specify if Eth header is present
+ * @vlan_present: packet is tagged vlan
  * @grh_present:GRH flag (if non-zero, GRH will be included)
- * @immediate_present: specify if immediate data should be used
+ * @immediate_present: specify if immediate data is present
  * @header:Structure to initialize
- *
- * ib_ud_header_init() initializes the lrh.link_version, lrh.link_next_header,
- * lrh.packet_length, grh.ip_version, grh.payload_length,
- * grh.next_header, bth.opcode, bth.pad_count and
- * bth.transport_header_version fields of a &struct ib_ud_header given
- * the payload length and whether a GRH will be included.
  */
 void ib_ud_header_init(int     		    payload_bytes,
+		       int		    lrh_present,
+		       int		    eth_present,
+		       int		    vlan_present,
 		       int    		    grh_present,
 		       int		    immediate_present,
 		       struct ib_ud_header *header)
 {
-	u16 packet_length;
-
 	memset(header, 0, sizeof *header);
 
-	header->lrh.link_version     = 0;
-	header->lrh.link_next_header =
-		grh_present ? IB_LNH_IBA_GLOBAL : IB_LNH_IBA_LOCAL;
-	packet_length		     = (IB_LRH_BYTES     +
-					IB_BTH_BYTES     +
-					IB_DETH_BYTES    +
-					payload_bytes    +
-					4                + /* ICRC     */
-					3) / 4;            /* round up */
-
-	header->grh_present          = grh_present;
+	if (lrh_present) {
+		u16 packet_length;
+
+		header->lrh.link_version     = 0;
+		header->lrh.link_next_header =
+			grh_present ? IB_LNH_IBA_GLOBAL : IB_LNH_IBA_LOCAL;
+		packet_length = (IB_LRH_BYTES	+
+				 IB_BTH_BYTES	+
+				 IB_DETH_BYTES	+
+				 (grh_present ? IB_GRH_BYTES : 0) +
+				 payload_bytes	+
+				 4		+ /* ICRC     */
+				 3) / 4;	  /* round up */
+		header->lrh.packet_length = cpu_to_be16(packet_length);
+	}
+
+	if (vlan_present)
+		header->eth.type = cpu_to_be16(ETH_P_8021Q);
+
 	if (grh_present) {
-		packet_length		   += IB_GRH_BYTES / 4;
 		header->grh.ip_version      = 6;
 		header->grh.payload_length  =
 			cpu_to_be16((IB_BTH_BYTES     +
@@ -222,18 +262,51 @@ void ib_ud_header_init(int     		    payload_bytes,
 		header->grh.next_header     = 0x1b;
 	}
 
-	header->lrh.packet_length = cpu_to_be16(packet_length);
-
-	header->immediate_present	     = immediate_present;
 	if (immediate_present)
 		header->bth.opcode           = IB_OPCODE_UD_SEND_ONLY_WITH_IMMEDIATE;
 	else
 		header->bth.opcode           = IB_OPCODE_UD_SEND_ONLY;
 	header->bth.pad_count                = (4 - payload_bytes) & 3;
 	header->bth.transport_header_version = 0;
+
+	header->lrh_present = lrh_present;
+	header->eth_present = eth_present;
+	header->vlan_present = vlan_present;
+	header->grh_present = grh_present;
+	header->immediate_present = immediate_present;
 }
 EXPORT_SYMBOL(ib_ud_header_init);
 
+/**
+ * ib_lrh_header_pack - Pack LRH header struct into wire format
+ * @lrh:unpacked LRH header struct
+ * @buf:Buffer to pack into
+ *
+ * ib_lrh_header_pack() packs the LRH header structure @lrh into
+ * wire format in the buffer @buf.
+ */
+int ib_lrh_header_pack(struct ib_unpacked_lrh *lrh, void *buf)
+{
+	ib_pack(lrh_table, ARRAY_SIZE(lrh_table), lrh, buf);
+	return 0;
+}
+EXPORT_SYMBOL(ib_lrh_header_pack);
+
+/**
+ * ib_lrh_header_unpack - Unpack LRH structure from wire format
+ * @lrh:unpacked LRH header struct
+ * @buf:Buffer to pack into
+ *
+ * ib_lrh_header_unpack() unpacks the LRH header structure from
+ * wire format (in buf) into @lrh.
+ */
+int ib_lrh_header_unpack(void *buf, struct ib_unpacked_lrh *lrh)
+{
+	ib_unpack(lrh_table, ARRAY_SIZE(lrh_table), buf, lrh);
+	return 0;
+}
+EXPORT_SYMBOL(ib_lrh_header_unpack);
+
 /**
  * ib_ud_header_pack - Pack UD header struct into wire format
  * @header:UD header struct
@@ -247,10 +320,21 @@ int ib_ud_header_pack(struct ib_ud_header *header,
 {
 	int len = 0;
 
-	ib_pack(lrh_table, ARRAY_SIZE(lrh_table),
-		&header->lrh, buf);
-	len += IB_LRH_BYTES;
-
+	if (header->lrh_present) {
+		ib_pack(lrh_table, ARRAY_SIZE(lrh_table),
+			&header->lrh, buf + len);
+		len += IB_LRH_BYTES;
+	}
+	if (header->eth_present) {
+		ib_pack(eth_table, ARRAY_SIZE(eth_table),
+			&header->eth, buf + len);
+		len += IB_ETH_BYTES;
+	}
+	if (header->vlan_present) {
+		ib_pack(vlan_table, ARRAY_SIZE(vlan_table),
+			&header->vlan, buf + len);
+		len += IB_VLAN_BYTES;
+	}
 	if (header->grh_present) {
 		ib_pack(grh_table, ARRAY_SIZE(grh_table),
 			&header->grh, buf + len);

drivers/infiniband/core/user_mad.c

@@ -1022,7 +1022,7 @@ static int ib_umad_init_port(struct ib_device *device, int port_num,
 
 	port->ib_dev   = device;
 	port->port_num = port_num;
-	init_MUTEX(&port->sm_sem);
+	sema_init(&port->sm_sem, 1);
 	mutex_init(&port->file_mutex);
 	INIT_LIST_HEAD(&port->file_list);
 

drivers/infiniband/core/uverbs_cmd.c

@@ -460,6 +460,8 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file,
 	resp.active_width    = attr.active_width;
 	resp.active_speed    = attr.active_speed;
 	resp.phys_state      = attr.phys_state;
+	resp.link_layer      = rdma_port_get_link_layer(file->device->ib_dev,
+							cmd.port_num);
 
 	if (copy_to_user((void __user *) (unsigned long) cmd.response,
 			 &resp, sizeof resp))

drivers/infiniband/core/verbs.c

@@ -94,6 +94,22 @@ rdma_node_get_transport(enum rdma_node_type node_type)
 }
 EXPORT_SYMBOL(rdma_node_get_transport);
 
+enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_num)
+{
+	if (device->get_link_layer)
+		return device->get_link_layer(device, port_num);
+
+	switch (rdma_node_get_transport(device->node_type)) {
+	case RDMA_TRANSPORT_IB:
+		return IB_LINK_LAYER_INFINIBAND;
+	case RDMA_TRANSPORT_IWARP:
+		return IB_LINK_LAYER_ETHERNET;
+	default:
+		return IB_LINK_LAYER_UNSPECIFIED;
+	}
+}
+EXPORT_SYMBOL(rdma_port_get_link_layer);
+
 /* Protection domains */
 
 struct ib_pd *ib_alloc_pd(struct ib_device *device)

drivers/infiniband/hw/amso1100/Kbuild

@@ -1,6 +1,4 @@
-ifdef CONFIG_INFINIBAND_AMSO1100_DEBUG
-EXTRA_CFLAGS += -DDEBUG
-endif
+ccflags-$(CONFIG_INFINIBAND_AMSO1100_DEBUG) := -DDEBUG
 
 obj-$(CONFIG_INFINIBAND_AMSO1100) += iw_c2.o
 

drivers/infiniband/hw/cxgb3/Makefile

@@ -1,10 +1,8 @@
-EXTRA_CFLAGS += -Idrivers/net/cxgb3
+ccflags-y := -Idrivers/net/cxgb3
 
 obj-$(CONFIG_INFINIBAND_CXGB3) += iw_cxgb3.o
 
 iw_cxgb3-y :=  iwch_cm.o iwch_ev.o iwch_cq.o iwch_qp.o iwch_mem.o \
 	       iwch_provider.o iwch.o cxio_hal.o cxio_resource.o
 
-ifdef CONFIG_INFINIBAND_CXGB3_DEBUG
-EXTRA_CFLAGS += -DDEBUG
-endif
+ccflags-$(CONFIG_INFINIBAND_CXGB3_DEBUG) += -DDEBUG

drivers/infiniband/hw/cxgb3/cxio_hal.c

@@ -160,6 +160,7 @@ int cxio_create_cq(struct cxio_rdev *rdev_p, struct t3_cq *cq, int kernel)
 	struct rdma_cq_setup setup;
 	int size = (1UL << (cq->size_log2)) * sizeof(struct t3_cqe);
 
+	size += 1; /* one extra page for storing cq-in-err state */
 	cq->cqid = cxio_hal_get_cqid(rdev_p->rscp);
 	if (!cq->cqid)
 		return -ENOMEM;

drivers/infiniband/hw/cxgb3/cxio_wr.h

@@ -728,6 +728,22 @@ struct t3_cq {
 #define CQ_VLD_ENTRY(ptr,size_log2,cqe) (Q_GENBIT(ptr,size_log2) == \
 					 CQE_GENBIT(*cqe))
 
+struct t3_cq_status_page {
+	u32 cq_err;
+};
+
+static inline int cxio_cq_in_error(struct t3_cq *cq)
+{
+	return ((struct t3_cq_status_page *)
+		&cq->queue[1 << cq->size_log2])->cq_err;
+}
+
+static inline void cxio_set_cq_in_error(struct t3_cq *cq)
+{
+	((struct t3_cq_status_page *)
+	 &cq->queue[1 << cq->size_log2])->cq_err = 1;
+}
+
 static inline void cxio_set_wq_in_error(struct t3_wq *wq)
 {
 	wq->queue->wq_in_err.err |= 1;

drivers/infiniband/hw/cxgb3/iwch_cm.c

@@ -1093,8 +1093,8 @@ static int tx_ack(struct t3cdev *tdev, struct sk_buff *skb, void *ctx)
 	PDBG("%s ep %p credits %u\n", __func__, ep, credits);
 
 	if (credits == 0) {
-		PDBG(KERN_ERR "%s 0 credit ack  ep %p state %u\n",
-			__func__, ep, state_read(&ep->com));
+		PDBG("%s 0 credit ack  ep %p state %u\n",
+		     __func__, ep, state_read(&ep->com));
 		return CPL_RET_BUF_DONE;
 	}
 

drivers/infiniband/hw/cxgb3/iwch_ev.c

@@ -76,6 +76,14 @@ static void post_qp_event(struct iwch_dev *rnicp, struct iwch_cq *chp,
 	atomic_inc(&qhp->refcnt);
 	spin_unlock(&rnicp->lock);
 
+	if (qhp->attr.state == IWCH_QP_STATE_RTS) {
+		attrs.next_state = IWCH_QP_STATE_TERMINATE;
+		iwch_modify_qp(qhp->rhp, qhp, IWCH_QP_ATTR_NEXT_STATE,
+			       &attrs, 1);
+		if (send_term)
+			iwch_post_terminate(qhp, rsp_msg);
+	}
+
 	event.event = ib_event;
 	event.device = chp->ibcq.device;
 	if (ib_event == IB_EVENT_CQ_ERR)
@@ -86,13 +94,7 @@ static void post_qp_event(struct iwch_dev *rnicp, struct iwch_cq *chp,
 	if (qhp->ibqp.event_handler)
 		(*qhp->ibqp.event_handler)(&event, qhp->ibqp.qp_context);
 
-	if (qhp->attr.state == IWCH_QP_STATE_RTS) {
-		attrs.next_state = IWCH_QP_STATE_TERMINATE;
-		iwch_modify_qp(qhp->rhp, qhp, IWCH_QP_ATTR_NEXT_STATE,
-			       &attrs, 1);
-		if (send_term)
-			iwch_post_terminate(qhp, rsp_msg);
-	}
+	(*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
 
 	if (atomic_dec_and_test(&qhp->refcnt))
 		wake_up(&qhp->wait);
@@ -179,7 +181,6 @@ void iwch_ev_dispatch(struct cxio_rdev *rdev_p, struct sk_buff *skb)
 	case TPT_ERR_BOUND:
 	case TPT_ERR_INVALIDATE_SHARED_MR:
 	case TPT_ERR_INVALIDATE_MR_WITH_MW_BOUND:
-		(*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
 		post_qp_event(rnicp, chp, rsp_msg, IB_EVENT_QP_ACCESS_ERR, 1);
 		break;
 

drivers/infiniband/hw/cxgb3/iwch_provider.c

@@ -154,6 +154,8 @@ static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int ve
 	struct iwch_create_cq_resp uresp;
 	struct iwch_create_cq_req ureq;
 	struct iwch_ucontext *ucontext = NULL;
+	static int warned;
+	size_t resplen;
 
 	PDBG("%s ib_dev %p entries %d\n", __func__, ibdev, entries);
 	rhp = to_iwch_dev(ibdev);
@@ -217,15 +219,26 @@ static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int ve
 		uresp.key = ucontext->key;
 		ucontext->key += PAGE_SIZE;
 		spin_unlock(&ucontext->mmap_lock);
-		if (ib_copy_to_udata(udata, &uresp, sizeof (uresp))) {
+		mm->key = uresp.key;
+		mm->addr = virt_to_phys(chp->cq.queue);
+		if (udata->outlen < sizeof uresp) {
+			if (!warned++)
+				printk(KERN_WARNING MOD "Warning - "
+				       "downlevel libcxgb3 (non-fatal).\n");
+			mm->len = PAGE_ALIGN((1UL << uresp.size_log2) *
+					     sizeof(struct t3_cqe));
+			resplen = sizeof(struct iwch_create_cq_resp_v0);
+		} else {
+			mm->len = PAGE_ALIGN(((1UL << uresp.size_log2) + 1) *
+					     sizeof(struct t3_cqe));
+			uresp.memsize = mm->len;
+			resplen = sizeof uresp;
+		}
+		if (ib_copy_to_udata(udata, &uresp, resplen)) {
 			kfree(mm);
 			iwch_destroy_cq(&chp->ibcq);
 			return ERR_PTR(-EFAULT);
 		}
-		mm->key = uresp.key;
-		mm->addr = virt_to_phys(chp->cq.queue);
-		mm->len = PAGE_ALIGN((1UL << uresp.size_log2) *
-					     sizeof (struct t3_cqe));
 		insert_mmap(ucontext, mm);
 	}
 	PDBG("created cqid 0x%0x chp %p size 0x%0x, dma_addr 0x%0llx\n",
@@ -1414,6 +1427,7 @@ int iwch_register_device(struct iwch_dev *dev)
 	dev->ibdev.post_send = iwch_post_send;
 	dev->ibdev.post_recv = iwch_post_receive;
 	dev->ibdev.get_protocol_stats = iwch_get_mib;
+	dev->ibdev.uverbs_abi_ver = IWCH_UVERBS_ABI_VERSION;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)

drivers/infiniband/hw/cxgb3/iwch_qp.c

@@ -802,14 +802,12 @@ int iwch_post_terminate(struct iwch_qp *qhp, struct respQ_msg_t *rsp_msg)
 /*
  * Assumes qhp lock is held.
  */
-static void __flush_qp(struct iwch_qp *qhp, unsigned long *flag)
+static void __flush_qp(struct iwch_qp *qhp, struct iwch_cq *rchp,
+				struct iwch_cq *schp, unsigned long *flag)
 {
-	struct iwch_cq *rchp, *schp;
 	int count;
 	int flushed;
 
-	rchp = get_chp(qhp->rhp, qhp->attr.rcq);
-	schp = get_chp(qhp->rhp, qhp->attr.scq);
 
 	PDBG("%s qhp %p rchp %p schp %p\n", __func__, qhp, rchp, schp);
 	/* take a ref on the qhp since we must release the lock */
@@ -847,10 +845,23 @@ static void __flush_qp(struct iwch_qp *qhp, unsigned long *flag)
 
 static void flush_qp(struct iwch_qp *qhp, unsigned long *flag)
 {
-	if (qhp->ibqp.uobject)
+	struct iwch_cq *rchp, *schp;
+
+	rchp = get_chp(qhp->rhp, qhp->attr.rcq);
+	schp = get_chp(qhp->rhp, qhp->attr.scq);
+
+	if (qhp->ibqp.uobject) {
 		cxio_set_wq_in_error(&qhp->wq);
-	else
-		__flush_qp(qhp, flag);
+		cxio_set_cq_in_error(&rchp->cq);
+		(*rchp->ibcq.comp_handler)(&rchp->ibcq, rchp->ibcq.cq_context);
+		if (schp != rchp) {
+			cxio_set_cq_in_error(&schp->cq);
+			(*schp->ibcq.comp_handler)(&schp->ibcq,
+						   schp->ibcq.cq_context);
+		}
+		return;
+	}
+	__flush_qp(qhp, rchp, schp, flag);
 }
 
 

drivers/infiniband/hw/cxgb3/iwch_user.h

@@ -45,10 +45,18 @@ struct iwch_create_cq_req {
 	__u64 user_rptr_addr;
 };
 
+struct iwch_create_cq_resp_v0 {
+	__u64 key;
+	__u32 cqid;
+	__u32 size_log2;
+};
+
 struct iwch_create_cq_resp {
 	__u64 key;
 	__u32 cqid;
 	__u32 size_log2;
+	__u32 memsize;
+	__u32 reserved;
 };
 
 struct iwch_create_qp_resp {

drivers/infiniband/hw/cxgb4/Makefile

@@ -1,4 +1,4 @@
-EXTRA_CFLAGS += -Idrivers/net/cxgb4
+ccflags-y := -Idrivers/net/cxgb4
 
 obj-$(CONFIG_INFINIBAND_CXGB4) += iw_cxgb4.o
 

drivers/infiniband/hw/cxgb4/cm.c

@@ -117,9 +117,9 @@ static int rcv_win = 256 * 1024;
 module_param(rcv_win, int, 0644);
 MODULE_PARM_DESC(rcv_win, "TCP receive window in bytes (default=256KB)");
 
-static int snd_win = 32 * 1024;
+static int snd_win = 128 * 1024;
 module_param(snd_win, int, 0644);
-MODULE_PARM_DESC(snd_win, "TCP send window in bytes (default=32KB)");
+MODULE_PARM_DESC(snd_win, "TCP send window in bytes (default=128KB)");
 
 static struct workqueue_struct *workq;
 
@@ -172,7 +172,7 @@ static int c4iw_l2t_send(struct c4iw_rdev *rdev, struct sk_buff *skb,
 	error = cxgb4_l2t_send(rdev->lldi.ports[0], skb, l2e);
 	if (error < 0)
 		kfree_skb(skb);
-	return error;
+	return error < 0 ? error : 0;
 }
 
 int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb)
@@ -187,7 +187,7 @@ int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb)
 	error = cxgb4_ofld_send(rdev->lldi.ports[0], skb);
 	if (error < 0)
 		kfree_skb(skb);
-	return error;
+	return error < 0 ? error : 0;
 }
 
 static void release_tid(struct c4iw_rdev *rdev, u32 hwtid, struct sk_buff *skb)
@@ -219,12 +219,11 @@ static void set_emss(struct c4iw_ep *ep, u16 opt)
 
 static enum c4iw_ep_state state_read(struct c4iw_ep_common *epc)
 {
-	unsigned long flags;
 	enum c4iw_ep_state state;
 
-	spin_lock_irqsave(&epc->lock, flags);
+	mutex_lock(&epc->mutex);
 	state = epc->state;
-	spin_unlock_irqrestore(&epc->lock, flags);
+	mutex_unlock(&epc->mutex);
 	return state;
 }
 
@@ -235,12 +234,10 @@ static void __state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new)
 
 static void state_set(struct c4iw_ep_common *epc, enum c4iw_ep_state new)
 {
-	unsigned long flags;
-
-	spin_lock_irqsave(&epc->lock, flags);
+	mutex_lock(&epc->mutex);
 	PDBG("%s - %s -> %s\n", __func__, states[epc->state], states[new]);
 	__state_set(epc, new);
-	spin_unlock_irqrestore(&epc->lock, flags);
+	mutex_unlock(&epc->mutex);
 	return;
 }
 
@@ -251,8 +248,8 @@ static void *alloc_ep(int size, gfp_t gfp)
 	epc = kzalloc(size, gfp);
 	if (epc) {
 		kref_init(&epc->kref);
-		spin_lock_init(&epc->lock);
-		init_waitqueue_head(&epc->waitq);
+		mutex_init(&epc->mutex);
+		c4iw_init_wr_wait(&epc->wr_wait);
 	}
 	PDBG("%s alloc ep %p\n", __func__, epc);
 	return epc;
@@ -1131,7 +1128,6 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 {
 	struct c4iw_ep *ep;
 	struct cpl_abort_rpl_rss *rpl = cplhdr(skb);
-	unsigned long flags;
 	int release = 0;
 	unsigned int tid = GET_TID(rpl);
 	struct tid_info *t = dev->rdev.lldi.tids;
@@ -1139,7 +1135,7 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	ep = lookup_tid(t, tid);
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 	BUG_ON(!ep);
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case ABORTING:
 		__state_set(&ep->com, DEAD);
@@ -1150,7 +1146,7 @@ static int abort_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		     __func__, ep, ep->com.state);
 		break;
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 
 	if (release)
 		release_ep_resources(ep);
@@ -1213,9 +1209,9 @@ static int pass_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	}
 	PDBG("%s ep %p status %d error %d\n", __func__, ep,
 	     rpl->status, status2errno(rpl->status));
-	ep->com.rpl_err = status2errno(rpl->status);
-	ep->com.rpl_done = 1;
-	wake_up(&ep->com.waitq);
+	ep->com.wr_wait.ret = status2errno(rpl->status);
+	ep->com.wr_wait.done = 1;
+	wake_up(&ep->com.wr_wait.wait);
 
 	return 0;
 }
@@ -1249,9 +1245,9 @@ static int close_listsrv_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_listen_ep *ep = lookup_stid(t, stid);
 
 	PDBG("%s ep %p\n", __func__, ep);
-	ep->com.rpl_err = status2errno(rpl->status);
-	ep->com.rpl_done = 1;
-	wake_up(&ep->com.waitq);
+	ep->com.wr_wait.ret = status2errno(rpl->status);
+	ep->com.wr_wait.done = 1;
+	wake_up(&ep->com.wr_wait.wait);
 	return 0;
 }
 
@@ -1478,7 +1474,6 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct cpl_peer_close *hdr = cplhdr(skb);
 	struct c4iw_ep *ep;
 	struct c4iw_qp_attributes attrs;
-	unsigned long flags;
 	int disconnect = 1;
 	int release = 0;
 	int closing = 0;
@@ -1489,7 +1484,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
 	dst_confirm(ep->dst);
 
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case MPA_REQ_WAIT:
 		__state_set(&ep->com, CLOSING);
@@ -1507,17 +1502,17 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 		 * in rdma connection migration (see c4iw_accept_cr()).
 		 */
 		__state_set(&ep->com, CLOSING);
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
+		ep->com.wr_wait.done = 1;
+		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.waitq);
+		wake_up(&ep->com.wr_wait.wait);
 		break;
 	case MPA_REP_SENT:
 		__state_set(&ep->com, CLOSING);
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
+		ep->com.wr_wait.done = 1;
+		ep->com.wr_wait.ret = -ECONNRESET;
 		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.waitq);
+		wake_up(&ep->com.wr_wait.wait);
 		break;
 	case FPDU_MODE:
 		start_ep_timer(ep);
@@ -1550,7 +1545,7 @@ static int peer_close(struct c4iw_dev *dev, struct sk_buff *skb)
 	default:
 		BUG_ON(1);
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 	if (closing) {
 		attrs.next_state = C4IW_QP_STATE_CLOSING;
 		c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
@@ -1581,7 +1576,6 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_qp_attributes attrs;
 	int ret;
 	int release = 0;
-	unsigned long flags;
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int tid = GET_TID(req);
 
@@ -1591,9 +1585,17 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		     ep->hwtid);
 		return 0;
 	}
-	spin_lock_irqsave(&ep->com.lock, flags);
 	PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
 	     ep->com.state);
+
+	/*
+	 * Wake up any threads in rdma_init() or rdma_fini().
+	 */
+	ep->com.wr_wait.done = 1;
+	ep->com.wr_wait.ret = -ECONNRESET;
+	wake_up(&ep->com.wr_wait.wait);
+
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case CONNECTING:
 		break;
@@ -1605,23 +1607,8 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		connect_reply_upcall(ep, -ECONNRESET);
 		break;
 	case MPA_REP_SENT:
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
-		PDBG("waking up ep %p\n", ep);
-		wake_up(&ep->com.waitq);
 		break;
 	case MPA_REQ_RCVD:
-
-		/*
-		 * We're gonna mark this puppy DEAD, but keep
-		 * the reference on it until the ULP accepts or
-		 * rejects the CR. Also wake up anyone waiting
-		 * in rdma connection migration (see c4iw_accept_cr()).
-		 */
-		ep->com.rpl_done = 1;
-		ep->com.rpl_err = -ECONNRESET;
-		PDBG("waking up ep %p tid %u\n", ep, ep->hwtid);
-		wake_up(&ep->com.waitq);
 		break;
 	case MORIBUND:
 	case CLOSING:
@@ -1644,7 +1631,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		break;
 	case DEAD:
 		PDBG("%s PEER_ABORT IN DEAD STATE!!!!\n", __func__);
-		spin_unlock_irqrestore(&ep->com.lock, flags);
+		mutex_unlock(&ep->com.mutex);
 		return 0;
 	default:
 		BUG_ON(1);
@@ -1655,7 +1642,7 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 		__state_set(&ep->com, DEAD);
 		release = 1;
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 
 	rpl_skb = get_skb(skb, sizeof(*rpl), GFP_KERNEL);
 	if (!rpl_skb) {
@@ -1681,7 +1668,6 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	struct c4iw_ep *ep;
 	struct c4iw_qp_attributes attrs;
 	struct cpl_close_con_rpl *rpl = cplhdr(skb);
-	unsigned long flags;
 	int release = 0;
 	struct tid_info *t = dev->rdev.lldi.tids;
 	unsigned int tid = GET_TID(rpl);
@@ -1692,7 +1678,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	BUG_ON(!ep);
 
 	/* The cm_id may be null if we failed to connect */
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 	switch (ep->com.state) {
 	case CLOSING:
 		__state_set(&ep->com, MORIBUND);
@@ -1717,7 +1703,7 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		BUG_ON(1);
 		break;
 	}
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 	if (release)
 		release_ep_resources(ep);
 	return 0;
@@ -1725,23 +1711,24 @@ static int close_con_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 
 static int terminate(struct c4iw_dev *dev, struct sk_buff *skb)
 {
-	struct c4iw_ep *ep;
-	struct cpl_rdma_terminate *term = cplhdr(skb);
+	struct cpl_rdma_terminate *rpl = cplhdr(skb);
 	struct tid_info *t = dev->rdev.lldi.tids;
-	unsigned int tid = GET_TID(term);
+	unsigned int tid = GET_TID(rpl);
+	struct c4iw_ep *ep;
+	struct c4iw_qp_attributes attrs;
 
 	ep = lookup_tid(t, tid);
+	BUG_ON(!ep);
 
-	if (state_read(&ep->com) != FPDU_MODE)
-		return 0;
+	if (ep->com.qp) {
+		printk(KERN_WARNING MOD "TERM received tid %u qpid %u\n", tid,
+		       ep->com.qp->wq.sq.qid);
+		attrs.next_state = C4IW_QP_STATE_TERMINATE;
+		c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
+			       C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
+	} else
+		printk(KERN_WARNING MOD "TERM received tid %u no qp\n", tid);
 
-	PDBG("%s ep %p tid %u\n", __func__, ep, ep->hwtid);
-	skb_pull(skb, sizeof *term);
-	PDBG("%s saving %d bytes of term msg\n", __func__, skb->len);
-	skb_copy_from_linear_data(skb, ep->com.qp->attr.terminate_buffer,
-				  skb->len);
-	ep->com.qp->attr.terminate_msg_len = skb->len;
-	ep->com.qp->attr.is_terminate_local = 0;
 	return 0;
 }
 
@@ -1762,8 +1749,8 @@ static int fw4_ack(struct c4iw_dev *dev, struct sk_buff *skb)
 	ep = lookup_tid(t, tid);
 	PDBG("%s ep %p tid %u credits %u\n", __func__, ep, ep->hwtid, credits);
 	if (credits == 0) {
-		PDBG(KERN_ERR "%s 0 credit ack ep %p tid %u state %u\n",
-			__func__, ep, ep->hwtid, state_read(&ep->com));
+		PDBG("%s 0 credit ack ep %p tid %u state %u\n",
+		     __func__, ep, ep->hwtid, state_read(&ep->com));
 		return 0;
 	}
 
@@ -2042,6 +2029,7 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 	}
 
 	state_set(&ep->com, LISTEN);
+	c4iw_init_wr_wait(&ep->com.wr_wait);
 	err = cxgb4_create_server(ep->com.dev->rdev.lldi.ports[0], ep->stid,
 				  ep->com.local_addr.sin_addr.s_addr,
 				  ep->com.local_addr.sin_port,
@@ -2050,15 +2038,8 @@ int c4iw_create_listen(struct iw_cm_id *cm_id, int backlog)
 		goto fail3;
 
 	/* wait for pass_open_rpl */
-	wait_event_timeout(ep->com.waitq, ep->com.rpl_done, C4IW_WR_TO);
-	if (ep->com.rpl_done)
-		err = ep->com.rpl_err;
-	else {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(ep->com.dev->rdev.lldi.pdev));
-		ep->com.dev->rdev.flags = T4_FATAL_ERROR;
-		err = -EIO;
-	}
+	err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
+				  __func__);
 	if (!err) {
 		cm_id->provider_data = ep;
 		goto out;
@@ -2082,20 +2063,12 @@ int c4iw_destroy_listen(struct iw_cm_id *cm_id)
 
 	might_sleep();
 	state_set(&ep->com, DEAD);
-	ep->com.rpl_done = 0;
-	ep->com.rpl_err = 0;
+	c4iw_init_wr_wait(&ep->com.wr_wait);
 	err = listen_stop(ep);
 	if (err)
 		goto done;
-	wait_event_timeout(ep->com.waitq, ep->com.rpl_done, C4IW_WR_TO);
-	if (ep->com.rpl_done)
-		err = ep->com.rpl_err;
-	else {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(ep->com.dev->rdev.lldi.pdev));
-		ep->com.dev->rdev.flags = T4_FATAL_ERROR;
-		err = -EIO;
-	}
+	err = c4iw_wait_for_reply(&ep->com.dev->rdev, &ep->com.wr_wait, 0, 0,
+				  __func__);
 	cxgb4_free_stid(ep->com.dev->rdev.lldi.tids, ep->stid, PF_INET);
 done:
 	cm_id->rem_ref(cm_id);
@@ -2106,12 +2079,11 @@ done:
 int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
 {
 	int ret = 0;
-	unsigned long flags;
 	int close = 0;
 	int fatal = 0;
 	struct c4iw_rdev *rdev;
 
-	spin_lock_irqsave(&ep->com.lock, flags);
+	mutex_lock(&ep->com.mutex);
 
 	PDBG("%s ep %p state %s, abrupt %d\n", __func__, ep,
 	     states[ep->com.state], abrupt);
@@ -2158,7 +2130,7 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
 		break;
 	}
 
-	spin_unlock_irqrestore(&ep->com.lock, flags);
+	mutex_unlock(&ep->com.mutex);
 	if (close) {
 		if (abrupt)
 			ret = abort_connection(ep, NULL, gfp);
@@ -2172,6 +2144,13 @@ int c4iw_ep_disconnect(struct c4iw_ep *ep, int abrupt, gfp_t gfp)
 	return ret;
 }
 
+static int async_event(struct c4iw_dev *dev, struct sk_buff *skb)
+{
+	struct cpl_fw6_msg *rpl = cplhdr(skb);
+	c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+	return 0;
+}
+
 /*
  * These are the real handlers that are called from a
  * work queue.
@@ -2190,7 +2169,8 @@ static c4iw_handler_func work_handlers[NUM_CPL_CMDS] = {
 	[CPL_ABORT_REQ_RSS] = peer_abort,
 	[CPL_CLOSE_CON_RPL] = close_con_rpl,
 	[CPL_RDMA_TERMINATE] = terminate,
-	[CPL_FW4_ACK] = fw4_ack
+	[CPL_FW4_ACK] = fw4_ack,
+	[CPL_FW6_MSG] = async_event
 };
 
 static void process_timeout(struct c4iw_ep *ep)
@@ -2198,7 +2178,7 @@ static void process_timeout(struct c4iw_ep *ep)
 	struct c4iw_qp_attributes attrs;
 	int abort = 1;
 
-	spin_lock_irq(&ep->com.lock);
+	mutex_lock(&ep->com.mutex);
 	PDBG("%s ep %p tid %u state %d\n", __func__, ep, ep->hwtid,
 	     ep->com.state);
 	switch (ep->com.state) {
@@ -2225,7 +2205,7 @@ static void process_timeout(struct c4iw_ep *ep)
 		WARN_ON(1);
 		abort = 0;
 	}
-	spin_unlock_irq(&ep->com.lock);
+	mutex_unlock(&ep->com.mutex);
 	if (abort)
 		abort_connection(ep, NULL, GFP_KERNEL);
 	c4iw_put_ep(&ep->com);
@@ -2309,6 +2289,7 @@ static int set_tcb_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 		printk(KERN_ERR MOD "Unexpected SET_TCB_RPL status %u "
 		       "for tid %u\n", rpl->status, GET_TID(rpl));
 	}
+	kfree_skb(skb);
 	return 0;
 }
 
@@ -2323,20 +2304,25 @@ static int fw6_msg(struct c4iw_dev *dev, struct sk_buff *skb)
 	switch (rpl->type) {
 	case 1:
 		ret = (int)((be64_to_cpu(rpl->data[0]) >> 8) & 0xff);
-		wr_waitp = (__force struct c4iw_wr_wait *)rpl->data[1];
+		wr_waitp = (struct c4iw_wr_wait *)(__force unsigned long) rpl->data[1];
 		PDBG("%s wr_waitp %p ret %u\n", __func__, wr_waitp, ret);
 		if (wr_waitp) {
-			wr_waitp->ret = ret;
+			if (ret)
+				wr_waitp->ret = -ret;
+			else
+				wr_waitp->ret = 0;
 			wr_waitp->done = 1;
 			wake_up(&wr_waitp->wait);
 		}
+		kfree_skb(skb);
 		break;
 	case 2:
-		c4iw_ev_dispatch(dev, (struct t4_cqe *)&rpl->data[0]);
+		sched(dev, skb);
 		break;
 	default:
 		printk(KERN_ERR MOD "%s unexpected fw6 msg type %u\n", __func__,
 		       rpl->type);
+		kfree_skb(skb);
 		break;
 	}
 	return 0;

drivers/infiniband/hw/cxgb4/cq.c

@@ -55,7 +55,7 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			V_FW_RI_RES_WR_NRES(1) |
 			FW_WR_COMPL(1));
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (u64)&wr_wait;
+	res_wr->cookie = (unsigned long) &wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_RESET;
@@ -64,14 +64,7 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 	c4iw_init_wr_wait(&wr_wait);
 	ret = c4iw_ofld_send(rdev, skb);
 	if (!ret) {
-		wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-		if (!wr_wait.done) {
-			printk(KERN_ERR MOD "Device %s not responding!\n",
-			       pci_name(rdev->lldi.pdev));
-			rdev->flags = T4_FATAL_ERROR;
-			ret = -EIO;
-		} else
-			ret = wr_wait.ret;
+		ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
 	}
 
 	kfree(cq->sw_queue);
@@ -132,7 +125,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			V_FW_RI_RES_WR_NRES(1) |
 			FW_WR_COMPL(1));
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (u64)&wr_wait;
+	res_wr->cookie = (unsigned long) &wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_WRITE;
@@ -157,14 +150,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 	if (ret)
 		goto err4;
 	PDBG("%s wait_event wr_wait %p\n", __func__, &wr_wait);
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rdev->lldi.pdev));
-		rdev->flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
 	if (ret)
 		goto err4;
 
@@ -476,6 +462,11 @@ static int poll_cq(struct t4_wq *wq, struct t4_cq *cq, struct t4_cqe *cqe,
 		goto proc_cqe;
 	}
 
+	if (CQE_OPCODE(hw_cqe) == FW_RI_TERMINATE) {
+		ret = -EAGAIN;
+		goto skip_cqe;
+	}
+
 	/*
 	 * RECV completion.
 	 */
@@ -696,6 +687,7 @@ static int c4iw_poll_cq_one(struct c4iw_cq *chp, struct ib_wc *wc)
 		case T4_ERR_MSN_RANGE:
 		case T4_ERR_IRD_OVERFLOW:
 		case T4_ERR_OPCODE:
+		case T4_ERR_INTERNAL_ERR:
 			wc->status = IB_WC_FATAL_ERR;
 			break;
 		case T4_ERR_SWFLUSH:

drivers/infiniband/hw/cxgb4/device.c

@@ -49,29 +49,33 @@ static DEFINE_MUTEX(dev_mutex);
 
 static struct dentry *c4iw_debugfs_root;
 
-struct debugfs_qp_data {
+struct c4iw_debugfs_data {
 	struct c4iw_dev *devp;
 	char *buf;
 	int bufsize;
 	int pos;
 };
 
-static int count_qps(int id, void *p, void *data)
+static int count_idrs(int id, void *p, void *data)
 {
-	struct c4iw_qp *qp = p;
 	int *countp = data;
 
-	if (id != qp->wq.sq.qid)
-		return 0;
-
 	*countp = *countp + 1;
 	return 0;
 }
 
-static int dump_qps(int id, void *p, void *data)
+static ssize_t debugfs_read(struct file *file, char __user *buf, size_t count,
+			    loff_t *ppos)
+{
+	struct c4iw_debugfs_data *d = file->private_data;
+
+	return simple_read_from_buffer(buf, count, ppos, d->buf, d->pos);
+}
+
+static int dump_qp(int id, void *p, void *data)
 {
 	struct c4iw_qp *qp = p;
-	struct debugfs_qp_data *qpd = data;
+	struct c4iw_debugfs_data *qpd = data;
 	int space;
 	int cc;
 
@@ -101,7 +105,7 @@ static int dump_qps(int id, void *p, void *data)
 
 static int qp_release(struct inode *inode, struct file *file)
 {
-	struct debugfs_qp_data *qpd = file->private_data;
+	struct c4iw_debugfs_data *qpd = file->private_data;
 	if (!qpd) {
 		printk(KERN_INFO "%s null qpd?\n", __func__);
 		return 0;
@@ -113,7 +117,7 @@ static int qp_release(struct inode *inode, struct file *file)
 
 static int qp_open(struct inode *inode, struct file *file)
 {
-	struct debugfs_qp_data *qpd;
+	struct c4iw_debugfs_data *qpd;
 	int ret = 0;
 	int count = 1;
 
@@ -126,7 +130,7 @@ static int qp_open(struct inode *inode, struct file *file)
 	qpd->pos = 0;
 
 	spin_lock_irq(&qpd->devp->lock);
-	idr_for_each(&qpd->devp->qpidr, count_qps, &count);
+	idr_for_each(&qpd->devp->qpidr, count_idrs, &count);
 	spin_unlock_irq(&qpd->devp->lock);
 
 	qpd->bufsize = count * 128;
@@ -137,7 +141,7 @@ static int qp_open(struct inode *inode, struct file *file)
 	}
 
 	spin_lock_irq(&qpd->devp->lock);
-	idr_for_each(&qpd->devp->qpidr, dump_qps, qpd);
+	idr_for_each(&qpd->devp->qpidr, dump_qp, qpd);
 	spin_unlock_irq(&qpd->devp->lock);
 
 	qpd->buf[qpd->pos++] = 0;
@@ -149,43 +153,86 @@ out:
 	return ret;
 }
 
-static ssize_t qp_read(struct file *file, char __user *buf, size_t count,
-			loff_t *ppos)
+static const struct file_operations qp_debugfs_fops = {
+	.owner   = THIS_MODULE,
+	.open    = qp_open,
+	.release = qp_release,
+	.read    = debugfs_read,
+	.llseek  = default_llseek,
+};
+
+static int dump_stag(int id, void *p, void *data)
 {
-	struct debugfs_qp_data *qpd = file->private_data;
-	loff_t pos = *ppos;
-	loff_t avail = qpd->pos;
+	struct c4iw_debugfs_data *stagd = data;
+	int space;
+	int cc;
 
-	if (pos < 0)
-		return -EINVAL;
-	if (pos >= avail)
+	space = stagd->bufsize - stagd->pos - 1;
+	if (space == 0)
+		return 1;
+
+	cc = snprintf(stagd->buf + stagd->pos, space, "0x%x\n", id<<8);
+	if (cc < space)
+		stagd->pos += cc;
+	return 0;
+}
+
+static int stag_release(struct inode *inode, struct file *file)
+{
+	struct c4iw_debugfs_data *stagd = file->private_data;
+	if (!stagd) {
+		printk(KERN_INFO "%s null stagd?\n", __func__);
 		return 0;
-	if (count > avail - pos)
-		count = avail - pos;
+	}
+	kfree(stagd->buf);
+	kfree(stagd);
+	return 0;
+}
 
-	while (count) {
-		size_t len = 0;
+static int stag_open(struct inode *inode, struct file *file)
+{
+	struct c4iw_debugfs_data *stagd;
+	int ret = 0;
+	int count = 1;
 
-		len = min((int)count, (int)qpd->pos - (int)pos);
-		if (copy_to_user(buf, qpd->buf + pos, len))
-			return -EFAULT;
-		if (len == 0)
-			return -EINVAL;
+	stagd = kmalloc(sizeof *stagd, GFP_KERNEL);
+	if (!stagd) {
+		ret = -ENOMEM;
+		goto out;
+	}
+	stagd->devp = inode->i_private;
+	stagd->pos = 0;
+
+	spin_lock_irq(&stagd->devp->lock);
+	idr_for_each(&stagd->devp->mmidr, count_idrs, &count);
+	spin_unlock_irq(&stagd->devp->lock);
 
-		buf += len;
-		pos += len;
-		count -= len;
+	stagd->bufsize = count * sizeof("0x12345678\n");
+	stagd->buf = kmalloc(stagd->bufsize, GFP_KERNEL);
+	if (!stagd->buf) {
+		ret = -ENOMEM;
+		goto err1;
 	}
-	count = pos - *ppos;
-	*ppos = pos;
-	return count;
+
+	spin_lock_irq(&stagd->devp->lock);
+	idr_for_each(&stagd->devp->mmidr, dump_stag, stagd);
+	spin_unlock_irq(&stagd->devp->lock);
+
+	stagd->buf[stagd->pos++] = 0;
+	file->private_data = stagd;
+	goto out;
+err1:
+	kfree(stagd);
+out:
+	return ret;
 }
 
-static const struct file_operations qp_debugfs_fops = {
+static const struct file_operations stag_debugfs_fops = {
 	.owner   = THIS_MODULE,
-	.open    = qp_open,
-	.release = qp_release,
-	.read    = qp_read,
+	.open    = stag_open,
+	.release = stag_release,
+	.read    = debugfs_read,
+	.llseek  = default_llseek,
 };
 
 static int setup_debugfs(struct c4iw_dev *devp)
@@ -199,6 +246,11 @@ static int setup_debugfs(struct c4iw_dev *devp)
 				 (void *)devp, &qp_debugfs_fops);
 	if (de && de->d_inode)
 		de->d_inode->i_size = 4096;
+
+	de = debugfs_create_file("stags", S_IWUSR, devp->debugfs_root,
+				 (void *)devp, &stag_debugfs_fops);
+	if (de && de->d_inode)
+		de->d_inode->i_size = 4096;
 	return 0;
 }
 
@@ -290,7 +342,14 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 		printk(KERN_ERR MOD "error %d initializing rqt pool\n", err);
 		goto err3;
 	}
+	err = c4iw_ocqp_pool_create(rdev);
+	if (err) {
+		printk(KERN_ERR MOD "error %d initializing ocqp pool\n", err);
+		goto err4;
+	}
 	return 0;
+err4:
+	c4iw_rqtpool_destroy(rdev);
 err3:
 	c4iw_pblpool_destroy(rdev);
 err2:
@@ -317,6 +376,7 @@ static void c4iw_remove(struct c4iw_dev *dev)
 	idr_destroy(&dev->cqidr);
 	idr_destroy(&dev->qpidr);
 	idr_destroy(&dev->mmidr);
+	iounmap(dev->rdev.oc_mw_kva);
 	ib_dealloc_device(&dev->ibdev);
 }
 
@@ -332,6 +392,17 @@ static struct c4iw_dev *c4iw_alloc(const struct cxgb4_lld_info *infop)
 	}
 	devp->rdev.lldi = *infop;
 
+	devp->rdev.oc_mw_pa = pci_resource_start(devp->rdev.lldi.pdev, 2) +
+		(pci_resource_len(devp->rdev.lldi.pdev, 2) -
+		 roundup_pow_of_two(devp->rdev.lldi.vr->ocq.size));
+	devp->rdev.oc_mw_kva = ioremap_wc(devp->rdev.oc_mw_pa,
+					       devp->rdev.lldi.vr->ocq.size);
+
+	printk(KERN_INFO MOD "ocq memory: "
+	       "hw_start 0x%x size %u mw_pa 0x%lx mw_kva %p\n",
+	       devp->rdev.lldi.vr->ocq.start, devp->rdev.lldi.vr->ocq.size,
+	       devp->rdev.oc_mw_pa, devp->rdev.oc_mw_kva);
+
 	mutex_lock(&dev_mutex);
 
 	ret = c4iw_rdev_open(&devp->rdev);
@@ -383,46 +454,6 @@ out:
 	return dev;
 }
 
-static struct sk_buff *t4_pktgl_to_skb(const struct pkt_gl *gl,
-				       unsigned int skb_len,
-				       unsigned int pull_len)
-{
-	struct sk_buff *skb;
-	struct skb_shared_info *ssi;
-
-	if (gl->tot_len <= 512) {
-		skb = alloc_skb(gl->tot_len, GFP_ATOMIC);
-		if (unlikely(!skb))
-			goto out;
-		__skb_put(skb, gl->tot_len);
-		skb_copy_to_linear_data(skb, gl->va, gl->tot_len);
-	} else {
-		skb = alloc_skb(skb_len, GFP_ATOMIC);
-		if (unlikely(!skb))
-			goto out;
-		__skb_put(skb, pull_len);
-		skb_copy_to_linear_data(skb, gl->va, pull_len);
-
-		ssi = skb_shinfo(skb);
-		ssi->frags[0].page = gl->frags[0].page;
-		ssi->frags[0].page_offset = gl->frags[0].page_offset + pull_len;
-		ssi->frags[0].size = gl->frags[0].size - pull_len;
-		if (gl->nfrags > 1)
-			memcpy(&ssi->frags[1], &gl->frags[1],
-			       (gl->nfrags - 1) * sizeof(skb_frag_t));
-		ssi->nr_frags = gl->nfrags;
-
-		skb->len = gl->tot_len;
-		skb->data_len = skb->len - pull_len;
-		skb->truesize += skb->data_len;
-
-		/* Get a reference for the last page, we don't own it */
-		get_page(gl->frags[gl->nfrags - 1].page);
-	}
-out:
-	return skb;
-}
-
 static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
 			const struct pkt_gl *gl)
 {
@@ -447,7 +478,7 @@ static int c4iw_uld_rx_handler(void *handle, const __be64 *rsp,
 		c4iw_ev_handler(dev, qid);
 		return 0;
 	} else {
-		skb = t4_pktgl_to_skb(gl, 128, 128);
+		skb = cxgb4_pktgl_to_skb(gl, 128, 128);
 		if (unlikely(!skb))
 			goto nomem;
 	}

drivers/infiniband/hw/cxgb4/ev.c

@@ -60,7 +60,7 @@ static void post_qp_event(struct c4iw_dev *dev, struct c4iw_cq *chp,
 	if (qhp->attr.state == C4IW_QP_STATE_RTS) {
 		attrs.next_state = C4IW_QP_STATE_TERMINATE;
 		c4iw_modify_qp(qhp->rhp, qhp, C4IW_QP_ATTR_NEXT_STATE,
-			       &attrs, 1);
+			       &attrs, 0);
 	}
 
 	event.event = ib_event;

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -46,6 +46,7 @@
 #include <linux/timer.h>
 #include <linux/io.h>
 #include <linux/kfifo.h>
+#include <linux/mutex.h>
 
 #include <asm/byteorder.h>
 
@@ -79,21 +80,6 @@ static inline void *cplhdr(struct sk_buff *skb)
 	return skb->data;
 }
 
-#define C4IW_WR_TO (10*HZ)
-
-struct c4iw_wr_wait {
-	wait_queue_head_t wait;
-	int done;
-	int ret;
-};
-
-static inline void c4iw_init_wr_wait(struct c4iw_wr_wait *wr_waitp)
-{
-	wr_waitp->ret = 0;
-	wr_waitp->done = 0;
-	init_waitqueue_head(&wr_waitp->wait);
-}
-
 struct c4iw_resource {
 	struct kfifo tpt_fifo;
 	spinlock_t tpt_fifo_lock;
@@ -127,8 +113,11 @@ struct c4iw_rdev {
 	struct c4iw_dev_ucontext uctx;
 	struct gen_pool *pbl_pool;
 	struct gen_pool *rqt_pool;
+	struct gen_pool *ocqp_pool;
 	u32 flags;
 	struct cxgb4_lld_info lldi;
+	unsigned long oc_mw_pa;
+	void __iomem *oc_mw_kva;
 };
 
 static inline int c4iw_fatal_error(struct c4iw_rdev *rdev)
@@ -141,6 +130,44 @@ static inline int c4iw_num_stags(struct c4iw_rdev *rdev)
 	return min((int)T4_MAX_NUM_STAG, (int)(rdev->lldi.vr->stag.size >> 5));
 }
 
+#define C4IW_WR_TO (10*HZ)
+
+struct c4iw_wr_wait {
+	wait_queue_head_t wait;
+	int done;
+	int ret;
+};
+
+static inline void c4iw_init_wr_wait(struct c4iw_wr_wait *wr_waitp)
+{
+	wr_waitp->ret = 0;
+	wr_waitp->done = 0;
+	init_waitqueue_head(&wr_waitp->wait);
+}
+
+static inline int c4iw_wait_for_reply(struct c4iw_rdev *rdev,
+				 struct c4iw_wr_wait *wr_waitp,
+				 u32 hwtid, u32 qpid,
+				 const char *func)
+{
+	unsigned to = C4IW_WR_TO;
+	do {
+
+		wait_event_timeout(wr_waitp->wait, wr_waitp->done, to);
+		if (!wr_waitp->done) {
+			printk(KERN_ERR MOD "%s - Device %s not responding - "
+			       "tid %u qpid %u\n", func,
+			       pci_name(rdev->lldi.pdev), hwtid, qpid);
+			to = to << 2;
+		}
+	} while (!wr_waitp->done);
+	if (wr_waitp->ret)
+		printk(KERN_WARNING MOD "%s: FW reply %d tid %u qpid %u\n",
+		       pci_name(rdev->lldi.pdev), wr_waitp->ret, hwtid, qpid);
+	return wr_waitp->ret;
+}
+
+
 struct c4iw_dev {
 	struct ib_device ibdev;
 	struct c4iw_rdev rdev;
@@ -327,6 +354,7 @@ struct c4iw_qp {
 	struct c4iw_qp_attributes attr;
 	struct t4_wq wq;
 	spinlock_t lock;
+	struct mutex mutex;
 	atomic_t refcnt;
 	wait_queue_head_t wait;
 	struct timer_list timer;
@@ -579,12 +607,10 @@ struct c4iw_ep_common {
 	struct c4iw_dev *dev;
 	enum c4iw_ep_state state;
 	struct kref kref;
-	spinlock_t lock;
+	struct mutex mutex;
 	struct sockaddr_in local_addr;
 	struct sockaddr_in remote_addr;
-	wait_queue_head_t waitq;
-	int rpl_done;
-	int rpl_err;
+	struct c4iw_wr_wait wr_wait;
 	unsigned long flags;
 };
 
@@ -654,8 +680,10 @@ int c4iw_init_resource(struct c4iw_rdev *rdev, u32 nr_tpt, u32 nr_pdid);
 int c4iw_init_ctrl_qp(struct c4iw_rdev *rdev);
 int c4iw_pblpool_create(struct c4iw_rdev *rdev);
 int c4iw_rqtpool_create(struct c4iw_rdev *rdev);
+int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev);
 void c4iw_pblpool_destroy(struct c4iw_rdev *rdev);
 void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev);
+void c4iw_ocqp_pool_destroy(struct c4iw_rdev *rdev);
 void c4iw_destroy_resource(struct c4iw_resource *rscp);
 int c4iw_destroy_ctrl_qp(struct c4iw_rdev *rdev);
 int c4iw_register_device(struct c4iw_dev *dev);
@@ -721,6 +749,8 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size);
 void c4iw_rqtpool_free(struct c4iw_rdev *rdev, u32 addr, int size);
 u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size);
 void c4iw_pblpool_free(struct c4iw_rdev *rdev, u32 addr, int size);
+u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size);
+void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size);
 int c4iw_ofld_send(struct c4iw_rdev *rdev, struct sk_buff *skb);
 void c4iw_flush_hw_cq(struct t4_cq *cq);
 void c4iw_count_rcqes(struct t4_cq *cq, struct t4_wq *wq, int *count);

drivers/infiniband/hw/cxgb4/mem.c

@@ -71,7 +71,7 @@ static int write_adapter_mem(struct c4iw_rdev *rdev, u32 addr, u32 len,
 		if (i == (num_wqe-1)) {
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP(FW_ULPTX_WR) |
 						    FW_WR_COMPL(1));
-			req->wr.wr_lo = (__force __be64)&wr_wait;
+			req->wr.wr_lo = (__force __be64)(unsigned long) &wr_wait;
 		} else
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP(FW_ULPTX_WR));
 		req->wr.wr_mid = cpu_to_be32(
@@ -103,14 +103,7 @@ static int write_adapter_mem(struct c4iw_rdev *rdev, u32 addr, u32 len,
 		len -= C4IW_MAX_INLINE_SIZE;
 	}
 
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rdev->lldi.pdev));
-		rdev->flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, 0, __func__);
 	return ret;
 }
 

drivers/infiniband/hw/cxgb4/provider.c

@@ -54,9 +54,9 @@
 
 #include "iw_cxgb4.h"
 
-static int fastreg_support;
+static int fastreg_support = 1;
 module_param(fastreg_support, int, 0644);
-MODULE_PARM_DESC(fastreg_support, "Advertise fastreg support (default=0)");
+MODULE_PARM_DESC(fastreg_support, "Advertise fastreg support (default=1)");
 
 static int c4iw_modify_port(struct ib_device *ibdev,
 			    u8 port, int port_modify_mask,
@@ -149,19 +149,28 @@ static int c4iw_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 	addr = mm->addr;
 	kfree(mm);
 
-	if ((addr >= pci_resource_start(rdev->lldi.pdev, 2)) &&
-	    (addr < (pci_resource_start(rdev->lldi.pdev, 2) +
-		       pci_resource_len(rdev->lldi.pdev, 2)))) {
+	if ((addr >= pci_resource_start(rdev->lldi.pdev, 0)) &&
+	    (addr < (pci_resource_start(rdev->lldi.pdev, 0) +
+		    pci_resource_len(rdev->lldi.pdev, 0)))) {
 
 		/*
-		 * Map T4 DB register.
+		 * MA_SYNC register...
 		 */
-		if (vma->vm_flags & VM_READ)
-			return -EPERM;
-
 		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-		vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND;
-		vma->vm_flags &= ~VM_MAYREAD;
+		ret = io_remap_pfn_range(vma, vma->vm_start,
+					 addr >> PAGE_SHIFT,
+					 len, vma->vm_page_prot);
+	} else if ((addr >= pci_resource_start(rdev->lldi.pdev, 2)) &&
+		   (addr < (pci_resource_start(rdev->lldi.pdev, 2) +
+		    pci_resource_len(rdev->lldi.pdev, 2)))) {
+
+		/*
+		 * Map user DB or OCQP memory...
+		 */
+		if (addr >= rdev->oc_mw_pa)
+			vma->vm_page_prot = t4_pgprot_wc(vma->vm_page_prot);
+		else
+			vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 		ret = io_remap_pfn_range(vma, vma->vm_start,
 					 addr >> PAGE_SHIFT,
 					 len, vma->vm_page_prot);
@@ -382,7 +391,17 @@ static ssize_t show_board(struct device *dev, struct device_attribute *attr,
 static int c4iw_get_mib(struct ib_device *ibdev,
 			union rdma_protocol_stats *stats)
 {
-	return -ENOSYS;
+	struct tp_tcp_stats v4, v6;
+	struct c4iw_dev *c4iw_dev = to_c4iw_dev(ibdev);
+
+	cxgb4_get_tcp_stats(c4iw_dev->rdev.lldi.pdev, &v4, &v6);
+	memset(stats, 0, sizeof *stats);
+	stats->iw.tcpInSegs = v4.tcpInSegs + v6.tcpInSegs;
+	stats->iw.tcpOutSegs = v4.tcpOutSegs + v6.tcpOutSegs;
+	stats->iw.tcpRetransSegs = v4.tcpRetransSegs + v6.tcpRetransSegs;
+	stats->iw.tcpOutRsts = v4.tcpOutRsts + v6.tcpOutSegs;
+
+	return 0;
 }
 
 static DEVICE_ATTR(hw_rev, S_IRUGO, show_rev, NULL);
@@ -472,6 +491,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.post_send = c4iw_post_send;
 	dev->ibdev.post_recv = c4iw_post_receive;
 	dev->ibdev.get_protocol_stats = c4iw_get_mib;
+	dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)

drivers/infiniband/hw/cxgb4/qp.c

@@ -31,6 +31,63 @@
  */
 #include "iw_cxgb4.h"
 
+static int ocqp_support;
+module_param(ocqp_support, int, 0644);
+MODULE_PARM_DESC(ocqp_support, "Support on-chip SQs (default=0)");
+
+static void set_state(struct c4iw_qp *qhp, enum c4iw_qp_state state)
+{
+	unsigned long flag;
+	spin_lock_irqsave(&qhp->lock, flag);
+	qhp->attr.state = state;
+	spin_unlock_irqrestore(&qhp->lock, flag);
+}
+
+static void dealloc_oc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	c4iw_ocqp_pool_free(rdev, sq->dma_addr, sq->memsize);
+}
+
+static void dealloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	dma_free_coherent(&(rdev->lldi.pdev->dev), sq->memsize, sq->queue,
+			  pci_unmap_addr(sq, mapping));
+}
+
+static void dealloc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	if (t4_sq_onchip(sq))
+		dealloc_oc_sq(rdev, sq);
+	else
+		dealloc_host_sq(rdev, sq);
+}
+
+static int alloc_oc_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	if (!ocqp_support || !t4_ocqp_supported())
+		return -ENOSYS;
+	sq->dma_addr = c4iw_ocqp_pool_alloc(rdev, sq->memsize);
+	if (!sq->dma_addr)
+		return -ENOMEM;
+	sq->phys_addr = rdev->oc_mw_pa + sq->dma_addr -
+			rdev->lldi.vr->ocq.start;
+	sq->queue = (__force union t4_wr *)(rdev->oc_mw_kva + sq->dma_addr -
+					    rdev->lldi.vr->ocq.start);
+	sq->flags |= T4_SQ_ONCHIP;
+	return 0;
+}
+
+static int alloc_host_sq(struct c4iw_rdev *rdev, struct t4_sq *sq)
+{
+	sq->queue = dma_alloc_coherent(&(rdev->lldi.pdev->dev), sq->memsize,
+				       &(sq->dma_addr), GFP_KERNEL);
+	if (!sq->queue)
+		return -ENOMEM;
+	sq->phys_addr = virt_to_phys(sq->queue);
+	pci_unmap_addr_set(sq, mapping, sq->dma_addr);
+	return 0;
+}
+
 static int destroy_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		      struct c4iw_dev_ucontext *uctx)
 {
@@ -41,9 +98,7 @@ static int destroy_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	dma_free_coherent(&(rdev->lldi.pdev->dev),
 			  wq->rq.memsize, wq->rq.queue,
 			  dma_unmap_addr(&wq->rq, mapping));
-	dma_free_coherent(&(rdev->lldi.pdev->dev),
-			  wq->sq.memsize, wq->sq.queue,
-			  dma_unmap_addr(&wq->sq, mapping));
+	dealloc_sq(rdev, &wq->sq);
 	c4iw_rqtpool_free(rdev, wq->rq.rqt_hwaddr, wq->rq.rqt_size);
 	kfree(wq->rq.sw_rq);
 	kfree(wq->sq.sw_sq);
@@ -93,11 +148,12 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	if (!wq->rq.rqt_hwaddr)
 		goto err4;
 
-	wq->sq.queue = dma_alloc_coherent(&(rdev->lldi.pdev->dev),
-					  wq->sq.memsize, &(wq->sq.dma_addr),
-					  GFP_KERNEL);
-	if (!wq->sq.queue)
-		goto err5;
+	if (user) {
+		if (alloc_oc_sq(rdev, &wq->sq) && alloc_host_sq(rdev, &wq->sq))
+			goto err5;
+	} else
+		if (alloc_host_sq(rdev, &wq->sq))
+			goto err5;
 	memset(wq->sq.queue, 0, wq->sq.memsize);
 	dma_unmap_addr_set(&wq->sq, mapping, wq->sq.dma_addr);
 
@@ -144,7 +200,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 			V_FW_RI_RES_WR_NRES(2) |
 			FW_WR_COMPL(1));
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (u64)&wr_wait;
+	res_wr->cookie = (unsigned long) &wr_wait;
 	res = res_wr->res;
 	res->u.sqrq.restype = FW_RI_RES_TYPE_SQ;
 	res->u.sqrq.op = FW_RI_RES_OP_WRITE;
@@ -158,6 +214,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		V_FW_RI_RES_WR_HOSTFCMODE(0) |	/* no host cidx updates */
 		V_FW_RI_RES_WR_CPRIO(0) |	/* don't keep in chip cache */
 		V_FW_RI_RES_WR_PCIECHN(0) |	/* set by uP at ri_init time */
+		t4_sq_onchip(&wq->sq) ? F_FW_RI_RES_WR_ONCHIP : 0 |
 		V_FW_RI_RES_WR_IQID(scq->cqid));
 	res->u.sqrq.dcaen_to_eqsize = cpu_to_be32(
 		V_FW_RI_RES_WR_DCAEN(0) |
@@ -198,14 +255,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	ret = c4iw_ofld_send(rdev, skb);
 	if (ret)
 		goto err7;
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rdev->lldi.pdev));
-		rdev->flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(rdev, &wr_wait, 0, wq->sq.qid, __func__);
 	if (ret)
 		goto err7;
 
@@ -219,9 +269,7 @@ err7:
 			  wq->rq.memsize, wq->rq.queue,
 			  dma_unmap_addr(&wq->rq, mapping));
 err6:
-	dma_free_coherent(&(rdev->lldi.pdev->dev),
-			  wq->sq.memsize, wq->sq.queue,
-			  dma_unmap_addr(&wq->sq, mapping));
+	dealloc_sq(rdev, &wq->sq);
 err5:
 	c4iw_rqtpool_free(rdev, wq->rq.rqt_hwaddr, wq->rq.rqt_size);
 err4:
@@ -263,6 +311,9 @@ static int build_immd(struct t4_sq *sq, struct fw_ri_immd *immdp,
 			rem -= len;
 		}
 	}
+	len = roundup(plen + sizeof *immdp, 16) - (plen + sizeof *immdp);
+	if (len)
+		memset(dstp, 0, len);
 	immdp->op = FW_RI_DATA_IMMD;
 	immdp->r1 = 0;
 	immdp->r2 = 0;
@@ -292,6 +343,7 @@ static int build_isgl(__be64 *queue_start, __be64 *queue_end,
 		if (++flitp == queue_end)
 			flitp = queue_start;
 	}
+	*flitp = (__force __be64)0;
 	isglp->op = FW_RI_DATA_ISGL;
 	isglp->r1 = 0;
 	isglp->nsge = cpu_to_be16(num_sge);
@@ -453,13 +505,15 @@ static int build_rdma_recv(struct c4iw_qp *qhp, union t4_recv_wr *wqe,
 	return 0;
 }
 
-static int build_fastreg(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16)
+static int build_fastreg(struct t4_sq *sq, union t4_wr *wqe,
+			 struct ib_send_wr *wr, u8 *len16)
 {
 
 	struct fw_ri_immd *imdp;
 	__be64 *p;
 	int i;
 	int pbllen = roundup(wr->wr.fast_reg.page_list_len * sizeof(u64), 32);
+	int rem;
 
 	if (wr->wr.fast_reg.page_list_len > T4_MAX_FR_DEPTH)
 		return -EINVAL;
@@ -474,32 +528,28 @@ static int build_fastreg(union t4_wr *wqe, struct ib_send_wr *wr, u8 *len16)
 	wqe->fr.va_hi = cpu_to_be32(wr->wr.fast_reg.iova_start >> 32);
 	wqe->fr.va_lo_fbo = cpu_to_be32(wr->wr.fast_reg.iova_start &
 					0xffffffff);
-	if (pbllen > T4_MAX_FR_IMMD) {
-		struct c4iw_fr_page_list *c4pl =
-				to_c4iw_fr_page_list(wr->wr.fast_reg.page_list);
-		struct fw_ri_dsgl *sglp;
-
-		sglp = (struct fw_ri_dsgl *)(&wqe->fr + 1);
-		sglp->op = FW_RI_DATA_DSGL;
-		sglp->r1 = 0;
-		sglp->nsge = cpu_to_be16(1);
-		sglp->addr0 = cpu_to_be64(c4pl->dma_addr);
-		sglp->len0 = cpu_to_be32(pbllen);
-
-		*len16 = DIV_ROUND_UP(sizeof wqe->fr + sizeof *sglp, 16);
-	} else {
-		imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
-		imdp->op = FW_RI_DATA_IMMD;
-		imdp->r1 = 0;
-		imdp->r2 = 0;
-		imdp->immdlen = cpu_to_be32(pbllen);
-		p = (__be64 *)(imdp + 1);
-		for (i = 0; i < wr->wr.fast_reg.page_list_len; i++, p++)
-			*p = cpu_to_be64(
-				(u64)wr->wr.fast_reg.page_list->page_list[i]);
-		*len16 = DIV_ROUND_UP(sizeof wqe->fr + sizeof *imdp + pbllen,
-				      16);
+	WARN_ON(pbllen > T4_MAX_FR_IMMD);
+	imdp = (struct fw_ri_immd *)(&wqe->fr + 1);
+	imdp->op = FW_RI_DATA_IMMD;
+	imdp->r1 = 0;
+	imdp->r2 = 0;
+	imdp->immdlen = cpu_to_be32(pbllen);
+	p = (__be64 *)(imdp + 1);
+	rem = pbllen;
+	for (i = 0; i < wr->wr.fast_reg.page_list_len; i++) {
+		*p = cpu_to_be64((u64)wr->wr.fast_reg.page_list->page_list[i]);
+		rem -= sizeof *p;
+		if (++p == (__be64 *)&sq->queue[sq->size])
+			p = (__be64 *)sq->queue;
 	}
+	BUG_ON(rem < 0);
+	while (rem) {
+		*p = 0;
+		rem -= sizeof *p;
+		if (++p == (__be64 *)&sq->queue[sq->size])
+			p = (__be64 *)sq->queue;
+	}
+	*len16 = DIV_ROUND_UP(sizeof wqe->fr + sizeof *imdp + pbllen, 16);
 	return 0;
 }
 
@@ -587,7 +637,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			fw_opcode = FW_RI_RDMA_READ_WR;
 			swsqe->opcode = FW_RI_READ_REQ;
 			if (wr->opcode == IB_WR_RDMA_READ_WITH_INV)
-				fw_flags |= FW_RI_RDMA_READ_INVALIDATE;
+				fw_flags = FW_RI_RDMA_READ_INVALIDATE;
 			else
 				fw_flags = 0;
 			err = build_rdma_read(wqe, wr, &len16);
@@ -600,7 +650,7 @@ int c4iw_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		case IB_WR_FAST_REG_MR:
 			fw_opcode = FW_RI_FR_NSMR_WR;
 			swsqe->opcode = FW_RI_FAST_REGISTER;
-			err = build_fastreg(wqe, wr, &len16);
+			err = build_fastreg(&qhp->wq.sq, wqe, wr, &len16);
 			break;
 		case IB_WR_LOCAL_INV:
 			if (wr->send_flags & IB_SEND_FENCE)
@@ -905,46 +955,38 @@ static void post_terminate(struct c4iw_qp *qhp, struct t4_cqe *err_cqe,
  * Assumes qhp lock is held.
  */
 static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
-		       struct c4iw_cq *schp, unsigned long *flag)
+		       struct c4iw_cq *schp)
 {
 	int count;
 	int flushed;
+	unsigned long flag;
 
 	PDBG("%s qhp %p rchp %p schp %p\n", __func__, qhp, rchp, schp);
-	/* take a ref on the qhp since we must release the lock */
-	atomic_inc(&qhp->refcnt);
-	spin_unlock_irqrestore(&qhp->lock, *flag);
 
 	/* locking hierarchy: cq lock first, then qp lock. */
-	spin_lock_irqsave(&rchp->lock, *flag);
+	spin_lock_irqsave(&rchp->lock, flag);
 	spin_lock(&qhp->lock);
 	c4iw_flush_hw_cq(&rchp->cq);
 	c4iw_count_rcqes(&rchp->cq, &qhp->wq, &count);
 	flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
 	spin_unlock(&qhp->lock);
-	spin_unlock_irqrestore(&rchp->lock, *flag);
+	spin_unlock_irqrestore(&rchp->lock, flag);
 	if (flushed)
 		(*rchp->ibcq.comp_handler)(&rchp->ibcq, rchp->ibcq.cq_context);
 
 	/* locking hierarchy: cq lock first, then qp lock. */
-	spin_lock_irqsave(&schp->lock, *flag);
+	spin_lock_irqsave(&schp->lock, flag);
 	spin_lock(&qhp->lock);
 	c4iw_flush_hw_cq(&schp->cq);
 	c4iw_count_scqes(&schp->cq, &qhp->wq, &count);
 	flushed = c4iw_flush_sq(&qhp->wq, &schp->cq, count);
 	spin_unlock(&qhp->lock);
-	spin_unlock_irqrestore(&schp->lock, *flag);
+	spin_unlock_irqrestore(&schp->lock, flag);
 	if (flushed)
 		(*schp->ibcq.comp_handler)(&schp->ibcq, schp->ibcq.cq_context);
-
-	/* deref */
-	if (atomic_dec_and_test(&qhp->refcnt))
-		wake_up(&qhp->wait);
-
-	spin_lock_irqsave(&qhp->lock, *flag);
 }
 
-static void flush_qp(struct c4iw_qp *qhp, unsigned long *flag)
+static void flush_qp(struct c4iw_qp *qhp)
 {
 	struct c4iw_cq *rchp, *schp;
 
@@ -958,7 +1000,7 @@ static void flush_qp(struct c4iw_qp *qhp, unsigned long *flag)
 			t4_set_cq_in_error(&schp->cq);
 		return;
 	}
-	__flush_qp(qhp, rchp, schp, flag);
+	__flush_qp(qhp, rchp, schp);
 }
 
 static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
@@ -966,7 +1008,6 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 {
 	struct fw_ri_wr *wqe;
 	int ret;
-	struct c4iw_wr_wait wr_wait;
 	struct sk_buff *skb;
 
 	PDBG("%s qhp %p qid 0x%x tid %u\n", __func__, qhp, qhp->wq.sq.qid,
@@ -985,28 +1026,16 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	wqe->flowid_len16 = cpu_to_be32(
 		FW_WR_FLOWID(ep->hwtid) |
 		FW_WR_LEN16(DIV_ROUND_UP(sizeof *wqe, 16)));
-	wqe->cookie = (u64)&wr_wait;
+	wqe->cookie = (unsigned long) &ep->com.wr_wait;
 
 	wqe->u.fini.type = FW_RI_TYPE_FINI;
-	c4iw_init_wr_wait(&wr_wait);
+	c4iw_init_wr_wait(&ep->com.wr_wait);
 	ret = c4iw_ofld_send(&rhp->rdev, skb);
 	if (ret)
 		goto out;
 
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rhp->rdev.lldi.pdev));
-		rhp->rdev.flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else {
-		ret = wr_wait.ret;
-		if (ret)
-			printk(KERN_WARNING MOD
-			       "%s: Abnormal close qpid %d ret %u\n",
-			       pci_name(rhp->rdev.lldi.pdev), qhp->wq.sq.qid,
-			       ret);
-	}
+	ret = c4iw_wait_for_reply(&rhp->rdev, &ep->com.wr_wait, qhp->ep->hwtid,
+			     qhp->wq.sq.qid, __func__);
 out:
 	PDBG("%s ret %d\n", __func__, ret);
 	return ret;
@@ -1040,7 +1069,6 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 {
 	struct fw_ri_wr *wqe;
 	int ret;
-	struct c4iw_wr_wait wr_wait;
 	struct sk_buff *skb;
 
 	PDBG("%s qhp %p qid 0x%x tid %u\n", __func__, qhp, qhp->wq.sq.qid,
@@ -1060,7 +1088,7 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 		FW_WR_FLOWID(qhp->ep->hwtid) |
 		FW_WR_LEN16(DIV_ROUND_UP(sizeof *wqe, 16)));
 
-	wqe->cookie = (u64)&wr_wait;
+	wqe->cookie = (unsigned long) &qhp->ep->com.wr_wait;
 
 	wqe->u.init.type = FW_RI_TYPE_INIT;
 	wqe->u.init.mpareqbit_p2ptype =
@@ -1097,19 +1125,13 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 	if (qhp->attr.mpa_attr.initiator)
 		build_rtr_msg(qhp->attr.mpa_attr.p2p_type, &wqe->u.init);
 
-	c4iw_init_wr_wait(&wr_wait);
+	c4iw_init_wr_wait(&qhp->ep->com.wr_wait);
 	ret = c4iw_ofld_send(&rhp->rdev, skb);
 	if (ret)
 		goto out;
 
-	wait_event_timeout(wr_wait.wait, wr_wait.done, C4IW_WR_TO);
-	if (!wr_wait.done) {
-		printk(KERN_ERR MOD "Device %s not responding!\n",
-		       pci_name(rhp->rdev.lldi.pdev));
-		rhp->rdev.flags = T4_FATAL_ERROR;
-		ret = -EIO;
-	} else
-		ret = wr_wait.ret;
+	ret = c4iw_wait_for_reply(&rhp->rdev, &qhp->ep->com.wr_wait,
+				  qhp->ep->hwtid, qhp->wq.sq.qid, __func__);
 out:
 	PDBG("%s ret %d\n", __func__, ret);
 	return ret;
@@ -1122,7 +1144,6 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 {
 	int ret = 0;
 	struct c4iw_qp_attributes newattr = qhp->attr;
-	unsigned long flag;
 	int disconnect = 0;
 	int terminate = 0;
 	int abort = 0;
@@ -1133,7 +1154,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	     qhp, qhp->wq.sq.qid, qhp->wq.rq.qid, qhp->ep, qhp->attr.state,
 	     (mask & C4IW_QP_ATTR_NEXT_STATE) ? attrs->next_state : -1);
 
-	spin_lock_irqsave(&qhp->lock, flag);
+	mutex_lock(&qhp->mutex);
 
 	/* Process attr changes if in IDLE */
 	if (mask & C4IW_QP_ATTR_VALID_MODIFY) {
@@ -1184,7 +1205,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			qhp->attr.mpa_attr = attrs->mpa_attr;
 			qhp->attr.llp_stream_handle = attrs->llp_stream_handle;
 			qhp->ep = qhp->attr.llp_stream_handle;
-			qhp->attr.state = C4IW_QP_STATE_RTS;
+			set_state(qhp, C4IW_QP_STATE_RTS);
 
 			/*
 			 * Ref the endpoint here and deref when we
@@ -1193,15 +1214,13 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			 * transition.
 			 */
 			c4iw_get_ep(&qhp->ep->com);
-			spin_unlock_irqrestore(&qhp->lock, flag);
 			ret = rdma_init(rhp, qhp);
-			spin_lock_irqsave(&qhp->lock, flag);
 			if (ret)
 				goto err;
 			break;
 		case C4IW_QP_STATE_ERROR:
-			qhp->attr.state = C4IW_QP_STATE_ERROR;
-			flush_qp(qhp, &flag);
+			set_state(qhp, C4IW_QP_STATE_ERROR);
+			flush_qp(qhp);
 			break;
 		default:
 			ret = -EINVAL;
@@ -1212,38 +1231,38 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 		switch (attrs->next_state) {
 		case C4IW_QP_STATE_CLOSING:
 			BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
-			qhp->attr.state = C4IW_QP_STATE_CLOSING;
+			set_state(qhp, C4IW_QP_STATE_CLOSING);
 			ep = qhp->ep;
 			if (!internal) {
 				abort = 0;
 				disconnect = 1;
-				c4iw_get_ep(&ep->com);
+				c4iw_get_ep(&qhp->ep->com);
 			}
-			spin_unlock_irqrestore(&qhp->lock, flag);
 			ret = rdma_fini(rhp, qhp, ep);
-			spin_lock_irqsave(&qhp->lock, flag);
 			if (ret) {
-				c4iw_get_ep(&ep->com);
+				if (internal)
+					c4iw_get_ep(&qhp->ep->com);
 				disconnect = abort = 1;
 				goto err;
 			}
 			break;
 		case C4IW_QP_STATE_TERMINATE:
-			qhp->attr.state = C4IW_QP_STATE_TERMINATE;
+			set_state(qhp, C4IW_QP_STATE_TERMINATE);
 			if (qhp->ibqp.uobject)
 				t4_set_wq_in_error(&qhp->wq);
 			ep = qhp->ep;
-			c4iw_get_ep(&ep->com);
-			terminate = 1;
+			if (!internal)
+				terminate = 1;
 			disconnect = 1;
+			c4iw_get_ep(&qhp->ep->com);
 			break;
 		case C4IW_QP_STATE_ERROR:
-			qhp->attr.state = C4IW_QP_STATE_ERROR;
+			set_state(qhp, C4IW_QP_STATE_ERROR);
 			if (!internal) {
 				abort = 1;
 				disconnect = 1;
 				ep = qhp->ep;
-				c4iw_get_ep(&ep->com);
+				c4iw_get_ep(&qhp->ep->com);
 			}
 			goto err;
 			break;
@@ -1259,8 +1278,8 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 		}
 		switch (attrs->next_state) {
 		case C4IW_QP_STATE_IDLE:
-			flush_qp(qhp, &flag);
-			qhp->attr.state = C4IW_QP_STATE_IDLE;
+			flush_qp(qhp);
+			set_state(qhp, C4IW_QP_STATE_IDLE);
 			qhp->attr.llp_stream_handle = NULL;
 			c4iw_put_ep(&qhp->ep->com);
 			qhp->ep = NULL;
@@ -1282,7 +1301,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 			ret = -EINVAL;
 			goto out;
 		}
-		qhp->attr.state = C4IW_QP_STATE_IDLE;
+		set_state(qhp, C4IW_QP_STATE_IDLE);
 		break;
 	case C4IW_QP_STATE_TERMINATE:
 		if (!internal) {
@@ -1305,15 +1324,16 @@ err:
 
 	/* disassociate the LLP connection */
 	qhp->attr.llp_stream_handle = NULL;
-	ep = qhp->ep;
+	if (!ep)
+		ep = qhp->ep;
 	qhp->ep = NULL;
-	qhp->attr.state = C4IW_QP_STATE_ERROR;
+	set_state(qhp, C4IW_QP_STATE_ERROR);
 	free = 1;
 	wake_up(&qhp->wait);
 	BUG_ON(!ep);
-	flush_qp(qhp, &flag);
+	flush_qp(qhp);
 out:
-	spin_unlock_irqrestore(&qhp->lock, flag);
+	mutex_unlock(&qhp->mutex);
 
 	if (terminate)
 		post_terminate(qhp, NULL, internal ? GFP_ATOMIC : GFP_KERNEL);
@@ -1335,7 +1355,6 @@ out:
 	 */
 	if (free)
 		c4iw_put_ep(&ep->com);
-
 	PDBG("%s exit state %d\n", __func__, qhp->attr.state);
 	return ret;
 }
@@ -1380,7 +1399,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	int sqsize, rqsize;
 	struct c4iw_ucontext *ucontext;
 	int ret;
-	struct c4iw_mm_entry *mm1, *mm2, *mm3, *mm4;
+	struct c4iw_mm_entry *mm1, *mm2, *mm3, *mm4, *mm5 = NULL;
 
 	PDBG("%s ib_pd %p\n", __func__, pd);
 
@@ -1450,6 +1469,7 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	qhp->attr.max_ord = 1;
 	qhp->attr.max_ird = 1;
 	spin_lock_init(&qhp->lock);
+	mutex_init(&qhp->mutex);
 	init_waitqueue_head(&qhp->wait);
 	atomic_set(&qhp->refcnt, 1);
 
@@ -1478,7 +1498,15 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 			ret = -ENOMEM;
 			goto err6;
 		}
-
+		if (t4_sq_onchip(&qhp->wq.sq)) {
+			mm5 = kmalloc(sizeof *mm5, GFP_KERNEL);
+			if (!mm5) {
+				ret = -ENOMEM;
+				goto err7;
+			}
+			uresp.flags = C4IW_QPF_ONCHIP;
+		} else
+			uresp.flags = 0;
 		uresp.qid_mask = rhp->rdev.qpmask;
 		uresp.sqid = qhp->wq.sq.qid;
 		uresp.sq_size = qhp->wq.sq.size;
@@ -1487,6 +1515,10 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		uresp.rq_size = qhp->wq.rq.size;
 		uresp.rq_memsize = qhp->wq.rq.memsize;
 		spin_lock(&ucontext->mmap_lock);
+		if (mm5) {
+			uresp.ma_sync_key = ucontext->key;
+			ucontext->key += PAGE_SIZE;
+		}
 		uresp.sq_key = ucontext->key;
 		ucontext->key += PAGE_SIZE;
 		uresp.rq_key = ucontext->key;
@@ -1498,9 +1530,9 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		spin_unlock(&ucontext->mmap_lock);
 		ret = ib_copy_to_udata(udata, &uresp, sizeof uresp);
 		if (ret)
-			goto err7;
+			goto err8;
 		mm1->key = uresp.sq_key;
-		mm1->addr = virt_to_phys(qhp->wq.sq.queue);
+		mm1->addr = qhp->wq.sq.phys_addr;
 		mm1->len = PAGE_ALIGN(qhp->wq.sq.memsize);
 		insert_mmap(ucontext, mm1);
 		mm2->key = uresp.rq_key;
@@ -1515,6 +1547,13 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		mm4->addr = qhp->wq.rq.udb;
 		mm4->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm4);
+		if (mm5) {
+			mm5->key = uresp.ma_sync_key;
+			mm5->addr = (pci_resource_start(rhp->rdev.lldi.pdev, 0)
+				    + A_PCIE_MA_SYNC) & PAGE_MASK;
+			mm5->len = PAGE_SIZE;
+			insert_mmap(ucontext, mm5);
+		}
 	}
 	qhp->ibqp.qp_num = qhp->wq.sq.qid;
 	init_timer(&(qhp->timer));
@@ -1522,6 +1561,8 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 	     __func__, qhp, qhp->attr.sq_num_entries, qhp->attr.rq_num_entries,
 	     qhp->wq.sq.qid);
 	return &qhp->ibqp;
+err8:
+	kfree(mm5);
 err7:
 	kfree(mm4);
 err6:

drivers/infiniband/hw/cxgb4/resource.c

@@ -311,6 +311,9 @@ u32 c4iw_pblpool_alloc(struct c4iw_rdev *rdev, int size)
 {
 	unsigned long addr = gen_pool_alloc(rdev->pbl_pool, size);
 	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
+	if (!addr && printk_ratelimit())
+		printk(KERN_WARNING MOD "%s: Out of PBL memory\n",
+		       pci_name(rdev->lldi.pdev));
 	return (u32)addr;
 }
 
@@ -370,6 +373,9 @@ u32 c4iw_rqtpool_alloc(struct c4iw_rdev *rdev, int size)
 {
 	unsigned long addr = gen_pool_alloc(rdev->rqt_pool, size << 6);
 	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size << 6);
+	if (!addr && printk_ratelimit())
+		printk(KERN_WARNING MOD "%s: Out of RQT memory\n",
+		       pci_name(rdev->lldi.pdev));
 	return (u32)addr;
 }
 
@@ -416,3 +422,59 @@ void c4iw_rqtpool_destroy(struct c4iw_rdev *rdev)
 {
 	gen_pool_destroy(rdev->rqt_pool);
 }
+
+/*
+ * On-Chip QP Memory.
+ */
+#define MIN_OCQP_SHIFT 12	/* 4KB == min ocqp size */
+
+u32 c4iw_ocqp_pool_alloc(struct c4iw_rdev *rdev, int size)
+{
+	unsigned long addr = gen_pool_alloc(rdev->ocqp_pool, size);
+	PDBG("%s addr 0x%x size %d\n", __func__, (u32)addr, size);
+	return (u32)addr;
+}
+
+void c4iw_ocqp_pool_free(struct c4iw_rdev *rdev, u32 addr, int size)
+{
+	PDBG("%s addr 0x%x size %d\n", __func__, addr, size);
+	gen_pool_free(rdev->ocqp_pool, (unsigned long)addr, size);
+}
+
+int c4iw_ocqp_pool_create(struct c4iw_rdev *rdev)
+{
+	unsigned start, chunk, top;
+
+	rdev->ocqp_pool = gen_pool_create(MIN_OCQP_SHIFT, -1);
+	if (!rdev->ocqp_pool)
+		return -ENOMEM;
+
+	start = rdev->lldi.vr->ocq.start;
+	chunk = rdev->lldi.vr->ocq.size;
+	top = start + chunk;
+
+	while (start < top) {
+		chunk = min(top - start + 1, chunk);
+		if (gen_pool_add(rdev->ocqp_pool, start, chunk, -1)) {
+			PDBG("%s failed to add OCQP chunk (%x/%x)\n",
+			     __func__, start, chunk);
+			if (chunk <= 1024 << MIN_OCQP_SHIFT) {
+				printk(KERN_WARNING MOD
+				       "Failed to add all OCQP chunks (%x/%x)\n",
+				       start, top - start);
+				return 0;
+			}
+			chunk >>= 1;
+		} else {
+			PDBG("%s added OCQP chunk (%x/%x)\n",
+			     __func__, start, chunk);
+			start += chunk;
+		}
+	}
+	return 0;
+}
+
+void c4iw_ocqp_pool_destroy(struct c4iw_rdev *rdev)
+{
+	gen_pool_destroy(rdev->ocqp_pool);
+}

drivers/infiniband/hw/cxgb4/t4.h

@@ -52,6 +52,7 @@
 #define T4_STAG_UNSET 0xffffffff
 #define T4_FW_MAJ 0
 #define T4_EQ_STATUS_ENTRIES (L1_CACHE_BYTES > 64 ? 2 : 1)
+#define A_PCIE_MA_SYNC 0x30b4
 
 struct t4_status_page {
 	__be32 rsvd1;	/* flit 0 - hw owns */
@@ -65,7 +66,7 @@ struct t4_status_page {
 
 #define T4_EQ_ENTRY_SIZE 64
 
-#define T4_SQ_NUM_SLOTS 4
+#define T4_SQ_NUM_SLOTS 5
 #define T4_SQ_NUM_BYTES (T4_EQ_ENTRY_SIZE * T4_SQ_NUM_SLOTS)
 #define T4_MAX_SEND_SGE ((T4_SQ_NUM_BYTES - sizeof(struct fw_ri_send_wr) - \
 			sizeof(struct fw_ri_isgl)) / sizeof(struct fw_ri_sge))
@@ -78,7 +79,7 @@ struct t4_status_page {
 			sizeof(struct fw_ri_rdma_write_wr) - \
 			sizeof(struct fw_ri_isgl)) / sizeof(struct fw_ri_sge))
 #define T4_MAX_FR_IMMD ((T4_SQ_NUM_BYTES - sizeof(struct fw_ri_fr_nsmr_wr) - \
-			sizeof(struct fw_ri_immd)))
+			sizeof(struct fw_ri_immd)) & ~31UL)
 #define T4_MAX_FR_DEPTH (T4_MAX_FR_IMMD / sizeof(u64))
 
 #define T4_RQ_NUM_SLOTS 2
@@ -266,10 +267,36 @@ struct t4_swsqe {
 	u16			idx;
 };
 
+static inline pgprot_t t4_pgprot_wc(pgprot_t prot)
+{
+#if defined(__i386__) || defined(__x86_64__)
+	return pgprot_writecombine(prot);
+#elif defined(CONFIG_PPC64)
+	return __pgprot((pgprot_val(prot) | _PAGE_NO_CACHE) &
+			~(pgprot_t)_PAGE_GUARDED);
+#else
+	return pgprot_noncached(prot);
+#endif
+}
+
+static inline int t4_ocqp_supported(void)
+{
+#if defined(__i386__) || defined(__x86_64__) || defined(CONFIG_PPC64)
+	return 1;
+#else
+	return 0;
+#endif
+}
+
+enum {
+	T4_SQ_ONCHIP = (1<<0),
+};
+
 struct t4_sq {
 	union t4_wr *queue;
 	dma_addr_t dma_addr;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
+	unsigned long phys_addr;
 	struct t4_swsqe *sw_sq;
 	struct t4_swsqe *oldest_read;
 	u64 udb;
@@ -280,6 +307,7 @@ struct t4_sq {
 	u16 cidx;
 	u16 pidx;
 	u16 wq_pidx;
+	u16 flags;
 };
 
 struct t4_swrqe {
@@ -350,6 +378,11 @@ static inline void t4_rq_consume(struct t4_wq *wq)
 		wq->rq.cidx = 0;
 }
 
+static inline int t4_sq_onchip(struct t4_sq *sq)
+{
+	return sq->flags & T4_SQ_ONCHIP;
+}
+
 static inline int t4_sq_empty(struct t4_wq *wq)
 {
 	return wq->sq.in_use == 0;
@@ -396,30 +429,27 @@ static inline void t4_ring_rq_db(struct t4_wq *wq, u16 inc)
 
 static inline int t4_wq_in_error(struct t4_wq *wq)
 {
-	return wq->sq.queue[wq->sq.size].status.qp_err;
+	return wq->rq.queue[wq->rq.size].status.qp_err;
 }
 
 static inline void t4_set_wq_in_error(struct t4_wq *wq)
 {
-	wq->sq.queue[wq->sq.size].status.qp_err = 1;
 	wq->rq.queue[wq->rq.size].status.qp_err = 1;
 }
 
 static inline void t4_disable_wq_db(struct t4_wq *wq)
 {
-	wq->sq.queue[wq->sq.size].status.db_off = 1;
 	wq->rq.queue[wq->rq.size].status.db_off = 1;
 }
 
 static inline void t4_enable_wq_db(struct t4_wq *wq)
 {
-	wq->sq.queue[wq->sq.size].status.db_off = 0;
 	wq->rq.queue[wq->rq.size].status.db_off = 0;
 }
 
 static inline int t4_wq_db_enabled(struct t4_wq *wq)
 {
-	return !wq->sq.queue[wq->sq.size].status.db_off;
+	return !wq->rq.queue[wq->rq.size].status.db_off;
 }
 
 struct t4_cq {

drivers/infiniband/hw/cxgb4/user.h

@@ -50,7 +50,13 @@ struct c4iw_create_cq_resp {
 	__u32 qid_mask;
 };
 
+
+enum {
+	C4IW_QPF_ONCHIP = (1<<0)
+};
+
 struct c4iw_create_qp_resp {
+	__u64 ma_sync_key;
 	__u64 sq_key;
 	__u64 rq_key;
 	__u64 sq_db_gts_key;
@@ -62,5 +68,6 @@ struct c4iw_create_qp_resp {
 	__u32 sq_size;
 	__u32 rq_size;
 	__u32 qid_mask;
+	__u32 flags;
 };
 #endif

drivers/infiniband/hw/ehca/ehca_mrmw.c

@@ -171,7 +171,7 @@ struct ib_mr *ehca_get_dma_mr(struct ib_pd *pd, int mr_access_flags)
 		}
 
 		ret = ehca_reg_maxmr(shca, e_maxmr,
-				     (void *)ehca_map_vaddr((void *)KERNELBASE),
+				     (void *)ehca_map_vaddr((void *)(KERNELBASE + PHYSICAL_START)),
 				     mr_access_flags, e_pd,
 				     &e_maxmr->ib.ib_mr.lkey,
 				     &e_maxmr->ib.ib_mr.rkey);
@@ -1636,7 +1636,7 @@ int ehca_reg_internal_maxmr(
 
 	/* register internal max-MR on HCA */
 	size_maxmr = ehca_mr_len;
-	iova_start = (u64 *)ehca_map_vaddr((void *)KERNELBASE);
+	iova_start = (u64 *)ehca_map_vaddr((void *)(KERNELBASE + PHYSICAL_START));
 	ib_pbuf.addr = 0;
 	ib_pbuf.size = size_maxmr;
 	num_kpages = NUM_CHUNKS(((u64)iova_start % PAGE_SIZE) + size_maxmr,
@@ -2209,7 +2209,7 @@ int ehca_mr_is_maxmr(u64 size,
 {
 	/* a MR is treated as max-MR only if it fits following: */
 	if ((size == ehca_mr_len) &&
-	    (iova_start == (void *)ehca_map_vaddr((void *)KERNELBASE))) {
+	    (iova_start == (void *)ehca_map_vaddr((void *)(KERNELBASE + PHYSICAL_START)))) {
 		ehca_gen_dbg("this is a max-MR");
 		return 1;
 	} else

drivers/infiniband/hw/ipath/Makefile

@@ -1,4 +1,4 @@
-EXTRA_CFLAGS += -DIPATH_IDSTR='"QLogic kernel.org driver"' \
+ccflags-y := -DIPATH_IDSTR='"QLogic kernel.org driver"' \
 	-DIPATH_KERN_TYPE=0
 
 obj-$(CONFIG_INFINIBAND_IPATH) += ib_ipath.o

drivers/infiniband/hw/mlx4/ah.c

@@ -30,66 +30,163 @@
  * SOFTWARE.
  */
 
+#include <rdma/ib_addr.h>
+#include <rdma/ib_cache.h>
+
 #include <linux/slab.h>
+#include <linux/inet.h>
+#include <linux/string.h>
 
 #include "mlx4_ib.h"
 
-struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+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 mlx4_dev *dev = to_mdev(pd->device)->dev;
-	struct mlx4_ib_ah *ah;
+	struct in6_addr in6;
 
-	ah = kmalloc(sizeof *ah, GFP_ATOMIC);
-	if (!ah)
-		return ERR_PTR(-ENOMEM);
+	*is_mcast = 0;
 
-	memset(&ah->av, 0, sizeof ah->av);
+	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;
 
-	ah->av.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
-	ah->av.g_slid  = ah_attr->src_path_bits;
-	ah->av.dlid    = cpu_to_be16(ah_attr->dlid);
-	if (ah_attr->static_rate) {
-		ah->av.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET;
-		while (ah->av.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET &&
-		       !(1 << ah->av.stat_rate & dev->caps.stat_rate_support))
-			--ah->av.stat_rate;
-	}
-	ah->av.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
+	return 0;
+}
+
+static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				  struct mlx4_ib_ah *ah)
+{
+	struct mlx4_dev *dev = to_mdev(pd->device)->dev;
+
+	ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
+	ah->av.ib.g_slid  = ah_attr->src_path_bits;
 	if (ah_attr->ah_flags & IB_AH_GRH) {
-		ah->av.g_slid   |= 0x80;
-		ah->av.gid_index = ah_attr->grh.sgid_index;
-		ah->av.hop_limit = ah_attr->grh.hop_limit;
-		ah->av.sl_tclass_flowlabel |=
+		ah->av.ib.g_slid   |= 0x80;
+		ah->av.ib.gid_index = ah_attr->grh.sgid_index;
+		ah->av.ib.hop_limit = ah_attr->grh.hop_limit;
+		ah->av.ib.sl_tclass_flowlabel |=
 			cpu_to_be32((ah_attr->grh.traffic_class << 20) |
 				    ah_attr->grh.flow_label);
-		memcpy(ah->av.dgid, ah_attr->grh.dgid.raw, 16);
+		memcpy(ah->av.ib.dgid, ah_attr->grh.dgid.raw, 16);
+	}
+
+	ah->av.ib.dlid    = cpu_to_be16(ah_attr->dlid);
+	if (ah_attr->static_rate) {
+		ah->av.ib.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET;
+		while (ah->av.ib.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET &&
+		       !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
+			--ah->av.ib.stat_rate;
 	}
+	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 
 	return &ah->ibah;
 }
 
+static struct ib_ah *create_iboe_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
+				    struct mlx4_ib_ah *ah)
+{
+	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;
+	u16 vlan_tag;
+
+	err = mlx4_ib_resolve_grh(ibdev, ah_attr, mac, &is_mcast, ah_attr->port_num);
+	if (err)
+		return ERR_PTR(err);
+
+	memcpy(ah->av.eth.mac, mac, 6);
+	err = ib_get_cached_gid(pd->device, ah_attr->port_num, ah_attr->grh.sgid_index, &sgid);
+	if (err)
+		return ERR_PTR(err);
+	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));
+	ah->av.eth.gid_index = ah_attr->grh.sgid_index;
+	ah->av.eth.vlan = cpu_to_be16(vlan_tag);
+	if (ah_attr->static_rate) {
+		ah->av.eth.stat_rate = ah_attr->static_rate + MLX4_STAT_RATE_OFFSET;
+		while (ah->av.eth.stat_rate > IB_RATE_2_5_GBPS + MLX4_STAT_RATE_OFFSET &&
+		       !(1 << ah->av.eth.stat_rate & dev->caps.stat_rate_support))
+			--ah->av.eth.stat_rate;
+	}
+
+	/*
+	 * HW requires multicast LID so we just choose one.
+	 */
+	if (is_mcast)
+		ah->av.ib.dlid = cpu_to_be16(0xc000);
+
+	memcpy(ah->av.eth.dgid, ah_attr->grh.dgid.raw, 16);
+	ah->av.eth.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
+
+	return &ah->ibah;
+}
+
+struct ib_ah *mlx4_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
+{
+	struct mlx4_ib_ah *ah;
+	struct ib_ah *ret;
+
+	ah = kzalloc(sizeof *ah, GFP_ATOMIC);
+	if (!ah)
+		return ERR_PTR(-ENOMEM);
+
+	if (rdma_port_get_link_layer(pd->device, ah_attr->port_num) == IB_LINK_LAYER_ETHERNET) {
+		if (!(ah_attr->ah_flags & IB_AH_GRH)) {
+			ret = ERR_PTR(-EINVAL);
+		} else {
+			/*
+			 * TBD: need to handle the case when we get
+			 * called in an atomic context and there we
+			 * might sleep.  We don't expect this
+			 * currently since we're working with link
+			 * local addresses which we can translate
+			 * without going to sleep.
+			 */
+			ret = create_iboe_ah(pd, ah_attr, ah);
+		}
+
+		if (IS_ERR(ret))
+			kfree(ah);
+
+		return ret;
+	} else
+		return create_ib_ah(pd, ah_attr, ah); /* never fails */
+}
+
 int mlx4_ib_query_ah(struct ib_ah *ibah, struct ib_ah_attr *ah_attr)
 {
 	struct mlx4_ib_ah *ah = to_mah(ibah);
+	enum rdma_link_layer ll;
 
 	memset(ah_attr, 0, sizeof *ah_attr);
-	ah_attr->dlid	       = be16_to_cpu(ah->av.dlid);
-	ah_attr->sl	       = be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 28;
-	ah_attr->port_num      = be32_to_cpu(ah->av.port_pd) >> 24;
-	if (ah->av.stat_rate)
-		ah_attr->static_rate = ah->av.stat_rate - MLX4_STAT_RATE_OFFSET;
-	ah_attr->src_path_bits = ah->av.g_slid & 0x7F;
+	ah_attr->sl = be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28;
+	ah_attr->port_num = be32_to_cpu(ah->av.ib.port_pd) >> 24;
+	ll = rdma_port_get_link_layer(ibah->device, ah_attr->port_num);
+	ah_attr->dlid = ll == IB_LINK_LAYER_INFINIBAND ? be16_to_cpu(ah->av.ib.dlid) : 0;
+	if (ah->av.ib.stat_rate)
+		ah_attr->static_rate = ah->av.ib.stat_rate - MLX4_STAT_RATE_OFFSET;
+	ah_attr->src_path_bits = ah->av.ib.g_slid & 0x7F;
 
 	if (mlx4_ib_ah_grh_present(ah)) {
 		ah_attr->ah_flags = IB_AH_GRH;
 
 		ah_attr->grh.traffic_class =
-			be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 20;
+			be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20;
 		ah_attr->grh.flow_label =
-			be32_to_cpu(ah->av.sl_tclass_flowlabel) & 0xfffff;
-		ah_attr->grh.hop_limit  = ah->av.hop_limit;
-		ah_attr->grh.sgid_index = ah->av.gid_index;
-		memcpy(ah_attr->grh.dgid.raw, ah->av.dgid, 16);
+			be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) & 0xfffff;
+		ah_attr->grh.hop_limit  = ah->av.ib.hop_limit;
+		ah_attr->grh.sgid_index = ah->av.ib.gid_index;
+		memcpy(ah_attr->grh.dgid.raw, ah->av.ib.dgid, 16);
 	}
 
 	return 0;

drivers/infiniband/hw/mlx4/mad.c

@@ -311,19 +311,25 @@ int mlx4_ib_mad_init(struct mlx4_ib_dev *dev)
 	struct ib_mad_agent *agent;
 	int p, q;
 	int ret;
+	enum rdma_link_layer ll;
 
-	for (p = 0; p < dev->num_ports; ++p)
+	for (p = 0; p < dev->num_ports; ++p) {
+		ll = rdma_port_get_link_layer(&dev->ib_dev, p + 1);
 		for (q = 0; q <= 1; ++q) {
-			agent = ib_register_mad_agent(&dev->ib_dev, p + 1,
-						      q ? IB_QPT_GSI : IB_QPT_SMI,
-						      NULL, 0, send_handler,
-						      NULL, NULL);
-			if (IS_ERR(agent)) {
-				ret = PTR_ERR(agent);
-				goto err;
-			}
-			dev->send_agent[p][q] = agent;
+			if (ll == IB_LINK_LAYER_INFINIBAND) {
+				agent = ib_register_mad_agent(&dev->ib_dev, p + 1,
+							      q ? IB_QPT_GSI : IB_QPT_SMI,
+							      NULL, 0, send_handler,
+							      NULL, NULL);
+				if (IS_ERR(agent)) {
+					ret = PTR_ERR(agent);
+					goto err;
+				}
+				dev->send_agent[p][q] = agent;
+			} else
+				dev->send_agent[p][q] = NULL;
 		}
+	}
 
 	return 0;
 
@@ -344,8 +350,10 @@ void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev)
 	for (p = 0; p < dev->num_ports; ++p) {
 		for (q = 0; q <= 1; ++q) {
 			agent = dev->send_agent[p][q];
-			dev->send_agent[p][q] = NULL;
-			ib_unregister_mad_agent(agent);
+			if (agent) {
+				dev->send_agent[p][q] = NULL;
+				ib_unregister_mad_agent(agent);
+			}
 		}
 
 		if (dev->sm_ah[p])

drivers/infiniband/hw/mlx4/main.c

@@ -35,9 +35,14 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/inetdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/if_vlan.h>
 
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
+#include <rdma/ib_addr.h>
 
 #include <linux/mlx4/driver.h>
 #include <linux/mlx4/cmd.h>
@@ -58,6 +63,15 @@ static const char mlx4_ib_version[] =
 	DRV_NAME ": Mellanox ConnectX InfiniBand driver v"
 	DRV_VERSION " (" DRV_RELDATE ")\n";
 
+struct update_gid_work {
+	struct work_struct	work;
+	union ib_gid		gids[128];
+	struct mlx4_ib_dev     *dev;
+	int			port;
+};
+
+static struct workqueue_struct *wq;
+
 static void init_query_mad(struct ib_smp *mad)
 {
 	mad->base_version  = 1;
@@ -66,6 +80,8 @@ static void init_query_mad(struct ib_smp *mad)
 	mad->method	   = IB_MGMT_METHOD_GET;
 }
 
+static union ib_gid zgid;
+
 static int mlx4_ib_query_device(struct ib_device *ibdev,
 				struct ib_device_attr *props)
 {
@@ -135,7 +151,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_srq		   = dev->dev->caps.num_srqs - dev->dev->caps.reserved_srqs;
 	props->max_srq_wr	   = dev->dev->caps.max_srq_wqes - 1;
 	props->max_srq_sge	   = dev->dev->caps.max_srq_sge;
-	props->max_fast_reg_page_list_len = PAGE_SIZE / sizeof (u64);
+	props->max_fast_reg_page_list_len = MLX4_MAX_FAST_REG_PAGES;
 	props->local_ca_ack_delay  = dev->dev->caps.local_ca_ack_delay;
 	props->atomic_cap	   = dev->dev->caps.flags & MLX4_DEV_CAP_FLAG_ATOMIC ?
 		IB_ATOMIC_HCA : IB_ATOMIC_NONE;
@@ -154,28 +170,19 @@ out:
 	return err;
 }
 
-static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
-			      struct ib_port_attr *props)
+static enum rdma_link_layer
+mlx4_ib_port_link_layer(struct ib_device *device, u8 port_num)
 {
-	struct ib_smp *in_mad  = NULL;
-	struct ib_smp *out_mad = NULL;
-	int err = -ENOMEM;
-
-	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
-	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
-	if (!in_mad || !out_mad)
-		goto out;
-
-	memset(props, 0, sizeof *props);
-
-	init_query_mad(in_mad);
-	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
-	in_mad->attr_mod = cpu_to_be32(port);
+	struct mlx4_dev *dev = to_mdev(device)->dev;
 
-	err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad);
-	if (err)
-		goto out;
+	return dev->caps.port_mask & (1 << (port_num - 1)) ?
+		IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
+}
 
+static int ib_link_query_port(struct ib_device *ibdev, u8 port,
+			      struct ib_port_attr *props,
+			      struct ib_smp *out_mad)
+{
 	props->lid		= be16_to_cpup((__be16 *) (out_mad->data + 16));
 	props->lmc		= out_mad->data[34] & 0x7;
 	props->sm_lid		= be16_to_cpup((__be16 *) (out_mad->data + 18));
@@ -196,6 +203,80 @@ static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
 	props->max_vl_num	= out_mad->data[37] >> 4;
 	props->init_type_reply	= out_mad->data[41] >> 4;
 
+	return 0;
+}
+
+static u8 state_to_phys_state(enum ib_port_state state)
+{
+	return state == IB_PORT_ACTIVE ? 5 : 3;
+}
+
+static int eth_link_query_port(struct ib_device *ibdev, u8 port,
+			       struct ib_port_attr *props,
+			       struct ib_smp *out_mad)
+{
+	struct mlx4_ib_iboe *iboe = &to_mdev(ibdev)->iboe;
+	struct net_device *ndev;
+	enum ib_mtu tmp;
+
+	props->active_width	= IB_WIDTH_4X;
+	props->active_speed	= 4;
+	props->port_cap_flags	= IB_PORT_CM_SUP;
+	props->gid_tbl_len	= to_mdev(ibdev)->dev->caps.gid_table_len[port];
+	props->max_msg_sz	= to_mdev(ibdev)->dev->caps.max_msg_sz;
+	props->pkey_tbl_len	= 1;
+	props->bad_pkey_cntr	= be16_to_cpup((__be16 *) (out_mad->data + 46));
+	props->qkey_viol_cntr	= be16_to_cpup((__be16 *) (out_mad->data + 48));
+	props->max_mtu		= IB_MTU_2048;
+	props->subnet_timeout	= 0;
+	props->max_vl_num	= out_mad->data[37] >> 4;
+	props->init_type_reply	= 0;
+	props->state		= IB_PORT_DOWN;
+	props->phys_state	= state_to_phys_state(props->state);
+	props->active_mtu	= IB_MTU_256;
+	spin_lock(&iboe->lock);
+	ndev = iboe->netdevs[port - 1];
+	if (!ndev)
+		goto out;
+
+	tmp = iboe_get_mtu(ndev->mtu);
+	props->active_mtu = tmp ? min(props->max_mtu, tmp) : IB_MTU_256;
+
+	props->state		= netif_running(ndev) &&  netif_oper_up(ndev) ?
+					IB_PORT_ACTIVE : IB_PORT_DOWN;
+	props->phys_state	= state_to_phys_state(props->state);
+
+out:
+	spin_unlock(&iboe->lock);
+	return 0;
+}
+
+static int mlx4_ib_query_port(struct ib_device *ibdev, u8 port,
+			      struct ib_port_attr *props)
+{
+	struct ib_smp *in_mad  = NULL;
+	struct ib_smp *out_mad = NULL;
+	int err = -ENOMEM;
+
+	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
+	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
+	if (!in_mad || !out_mad)
+		goto out;
+
+	memset(props, 0, sizeof *props);
+
+	init_query_mad(in_mad);
+	in_mad->attr_id  = IB_SMP_ATTR_PORT_INFO;
+	in_mad->attr_mod = cpu_to_be32(port);
+
+	err = mlx4_MAD_IFC(to_mdev(ibdev), 1, 1, port, NULL, NULL, in_mad, out_mad);
+	if (err)
+		goto out;
+
+	err = mlx4_ib_port_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND ?
+		ib_link_query_port(ibdev, port, props, out_mad) :
+		eth_link_query_port(ibdev, port, props, out_mad);
+
 out:
 	kfree(in_mad);
 	kfree(out_mad);
@@ -203,8 +284,8 @@ out:
 	return err;
 }
 
-static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
-			     union ib_gid *gid)
+static int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
+			       union ib_gid *gid)
 {
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
@@ -241,6 +322,25 @@ out:
 	return err;
 }
 
+static int iboe_query_gid(struct ib_device *ibdev, u8 port, int index,
+			  union ib_gid *gid)
+{
+	struct mlx4_ib_dev *dev = to_mdev(ibdev);
+
+	*gid = dev->iboe.gid_table[port - 1][index];
+
+	return 0;
+}
+
+static int mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
+			     union ib_gid *gid)
+{
+	if (rdma_port_get_link_layer(ibdev, port) == IB_LINK_LAYER_INFINIBAND)
+		return __mlx4_ib_query_gid(ibdev, port, index, gid);
+	else
+		return iboe_query_gid(ibdev, port, index, gid);
+}
+
 static int mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
 			      u16 *pkey)
 {
@@ -272,14 +372,32 @@ out:
 static int mlx4_ib_modify_device(struct ib_device *ibdev, int mask,
 				 struct ib_device_modify *props)
 {
+	struct mlx4_cmd_mailbox *mailbox;
+
 	if (mask & ~IB_DEVICE_MODIFY_NODE_DESC)
 		return -EOPNOTSUPP;
 
-	if (mask & IB_DEVICE_MODIFY_NODE_DESC) {
-		spin_lock(&to_mdev(ibdev)->sm_lock);
-		memcpy(ibdev->node_desc, props->node_desc, 64);
-		spin_unlock(&to_mdev(ibdev)->sm_lock);
-	}
+	if (!(mask & IB_DEVICE_MODIFY_NODE_DESC))
+		return 0;
+
+	spin_lock(&to_mdev(ibdev)->sm_lock);
+	memcpy(ibdev->node_desc, props->node_desc, 64);
+	spin_unlock(&to_mdev(ibdev)->sm_lock);
+
+	/*
+	 * If possible, pass node desc to FW, so it can generate
+	 * a 144 trap.  If cmd fails, just ignore.
+	 */
+	mailbox = mlx4_alloc_cmd_mailbox(to_mdev(ibdev)->dev);
+	if (IS_ERR(mailbox))
+		return 0;
+
+	memset(mailbox->buf, 0, 256);
+	memcpy(mailbox->buf, props->node_desc, 64);
+	mlx4_cmd(to_mdev(ibdev)->dev, mailbox->dma, 1, 0,
+		 MLX4_CMD_SET_NODE, MLX4_CMD_TIME_CLASS_A);
+
+	mlx4_free_cmd_mailbox(to_mdev(ibdev)->dev, mailbox);
 
 	return 0;
 }
@@ -289,6 +407,7 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	int err;
+	u8 is_eth = dev->dev->caps.port_type[port] == MLX4_PORT_TYPE_ETH;
 
 	mailbox = mlx4_alloc_cmd_mailbox(dev->dev);
 	if (IS_ERR(mailbox))
@@ -304,7 +423,7 @@ static int mlx4_SET_PORT(struct mlx4_ib_dev *dev, u8 port, int reset_qkey_viols,
 		((__be32 *) mailbox->buf)[1] = cpu_to_be32(cap_mask);
 	}
 
-	err = mlx4_cmd(dev->dev, mailbox->dma, port, 0, MLX4_CMD_SET_PORT,
+	err = mlx4_cmd(dev->dev, mailbox->dma, port, is_eth, MLX4_CMD_SET_PORT,
 		       MLX4_CMD_TIME_CLASS_B);
 
 	mlx4_free_cmd_mailbox(dev->dev, mailbox);
@@ -447,18 +566,132 @@ static int mlx4_ib_dealloc_pd(struct ib_pd *pd)
 	return 0;
 }
 
+static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
+{
+	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
+	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
+	struct mlx4_ib_gid_entry *ge;
+
+	ge = kzalloc(sizeof *ge, GFP_KERNEL);
+	if (!ge)
+		return -ENOMEM;
+
+	ge->gid = *gid;
+	if (mlx4_ib_add_mc(mdev, mqp, gid)) {
+		ge->port = mqp->port;
+		ge->added = 1;
+	}
+
+	mutex_lock(&mqp->mutex);
+	list_add_tail(&ge->list, &mqp->gid_list);
+	mutex_unlock(&mqp->mutex);
+
+	return 0;
+}
+
+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;
+
+	if (!mqp->port)
+		return 0;
+
+	spin_lock(&mdev->iboe.lock);
+	ndev = mdev->iboe.netdevs[mqp->port - 1];
+	if (ndev)
+		dev_hold(ndev);
+	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);
+	}
+
+	return ret;
+}
+
 static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
-	return mlx4_multicast_attach(to_mdev(ibqp->device)->dev,
-				     &to_mqp(ibqp)->mqp, gid->raw,
-				     !!(to_mqp(ibqp)->flags &
-					MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK));
+	int err;
+	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
+	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
+
+	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, !!(mqp->flags &
+				    MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK));
+	if (err)
+		return err;
+
+	err = add_gid_entry(ibqp, gid);
+	if (err)
+		goto err_add;
+
+	return 0;
+
+err_add:
+	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw);
+	return err;
+}
+
+static struct mlx4_ib_gid_entry *find_gid_entry(struct mlx4_ib_qp *qp, u8 *raw)
+{
+	struct mlx4_ib_gid_entry *ge;
+	struct mlx4_ib_gid_entry *tmp;
+	struct mlx4_ib_gid_entry *ret = NULL;
+
+	list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) {
+		if (!memcmp(raw, ge->gid.raw, 16)) {
+			ret = ge;
+			break;
+		}
+	}
+
+	return ret;
 }
 
 static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 {
-	return mlx4_multicast_detach(to_mdev(ibqp->device)->dev,
-				     &to_mqp(ibqp)->mqp, gid->raw);
+	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;
+
+	err = mlx4_multicast_detach(mdev->dev,
+				    &mqp->mqp, gid->raw);
+	if (err)
+		return err;
+
+	mutex_lock(&mqp->mutex);
+	ge = find_gid_entry(mqp, gid->raw);
+	if (ge) {
+		spin_lock(&mdev->iboe.lock);
+		ndev = ge->added ? mdev->iboe.netdevs[ge->port - 1] : NULL;
+		if (ndev)
+			dev_hold(ndev);
+		spin_unlock(&mdev->iboe.lock);
+		rdma_get_mcast_mac((struct in6_addr *)gid, mac);
+		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
+		printk(KERN_WARNING "could not find mgid entry\n");
+
+	mutex_unlock(&mqp->mutex);
+
+	return 0;
 }
 
 static int init_node_data(struct mlx4_ib_dev *dev)
@@ -543,15 +776,215 @@ 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);
+	struct mlx4_cmd_mailbox *mailbox;
+	union ib_gid *gids;
+	int err;
+	struct mlx4_dev	*dev = gw->dev->dev;
+	struct ib_event event;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		printk(KERN_WARNING "update gid table failed %ld\n", PTR_ERR(mailbox));
+		return;
+	}
+
+	gids = mailbox->buf;
+	memcpy(gids, gw->gids, sizeof gw->gids);
+
+	err = mlx4_cmd(dev, mailbox->dma, MLX4_SET_PORT_GID_TABLE << 8 | gw->port,
+		       1, MLX4_CMD_SET_PORT, MLX4_CMD_TIME_CLASS_B);
+	if (err)
+		printk(KERN_WARNING "set port command failed\n");
+	else {
+		memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids);
+		event.device = &gw->dev->ib_dev;
+		event.element.port_num = gw->port;
+		event.event    = IB_EVENT_LID_CHANGE;
+		ib_dispatch_event(&event);
+	}
+
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	kfree(gw);
+}
+
+static int update_ipv6_gids(struct mlx4_ib_dev *dev, int port, int clear)
+{
+	struct net_device *ndev = dev->iboe.netdevs[port - 1];
+	struct update_gid_work *work;
+	struct net_device *tmp;
+	int i;
+	u8 *hits;
+	int ret;
+	union ib_gid gid;
+	int free;
+	int found;
+	int need_update = 0;
+	u16 vid;
+
+	work = kzalloc(sizeof *work, GFP_ATOMIC);
+	if (!work)
+		return -ENOMEM;
+
+	hits = kzalloc(128, GFP_ATOMIC);
+	if (!hits) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	read_lock(&dev_base_lock);
+	for_each_netdev(&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) {
+				if (tmp == ndev &&
+				    (memcmp(&dev->iboe.gid_table[port - 1][0],
+					    &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;
+				}
+			}
+		}
+	}
+	read_unlock(&dev_base_lock);
+
+	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) {
+		memcpy(work->gids, dev->iboe.gid_table[port - 1], sizeof work->gids);
+		INIT_WORK(&work->work, update_gids_task);
+		work->port = port;
+		work->dev = dev;
+		queue_work(wq, &work->work);
+	} else
+		kfree(work);
+
+	kfree(hits);
+	return 0;
+
+out:
+	kfree(work);
+	return ret;
+}
+
+static void handle_en_event(struct mlx4_ib_dev *dev, int port, unsigned long event)
+{
+	switch (event) {
+	case NETDEV_UP:
+	case NETDEV_CHANGEADDR:
+		update_ipv6_gids(dev, port, 0);
+		break;
+
+	case NETDEV_DOWN:
+		update_ipv6_gids(dev, port, 1);
+		dev->iboe.netdevs[port - 1] = NULL;
+	}
+}
+
+static void netdev_added(struct mlx4_ib_dev *dev, int port)
+{
+	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 net_device *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;
+
+	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_PROTOCOL_EN, 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;
+}
+
 static void *mlx4_ib_add(struct mlx4_dev *dev)
 {
 	struct mlx4_ib_dev *ibdev;
 	int num_ports = 0;
 	int i;
+	int err;
+	struct mlx4_ib_iboe *iboe;
 
 	printk_once(KERN_INFO "%s", mlx4_ib_version);
 
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+	mlx4_foreach_ib_transport_port(i, dev)
 		num_ports++;
 
 	/* No point in registering a device with no ports... */
@@ -564,6 +997,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		return NULL;
 	}
 
+	iboe = &ibdev->iboe;
+
 	if (mlx4_pd_alloc(dev, &ibdev->priv_pdn))
 		goto err_dealloc;
 
@@ -612,6 +1047,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 
 	ibdev->ib_dev.query_device	= mlx4_ib_query_device;
 	ibdev->ib_dev.query_port	= mlx4_ib_query_port;
+	ibdev->ib_dev.get_link_layer	= mlx4_ib_port_link_layer;
 	ibdev->ib_dev.query_gid		= mlx4_ib_query_gid;
 	ibdev->ib_dev.query_pkey	= mlx4_ib_query_pkey;
 	ibdev->ib_dev.modify_device	= mlx4_ib_modify_device;
@@ -656,6 +1092,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.unmap_fmr		= mlx4_ib_unmap_fmr;
 	ibdev->ib_dev.dealloc_fmr	= mlx4_ib_fmr_dealloc;
 
+	spin_lock_init(&iboe->lock);
+
 	if (init_node_data(ibdev))
 		goto err_map;
 
@@ -668,16 +1106,28 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	if (mlx4_ib_mad_init(ibdev))
 		goto err_reg;
 
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE && !iboe->nb.notifier_call) {
+		iboe->nb.notifier_call = mlx4_ib_netdev_event;
+		err = register_netdevice_notifier(&iboe->nb);
+		if (err)
+			goto err_reg;
+	}
+
 	for (i = 0; i < ARRAY_SIZE(mlx4_class_attributes); ++i) {
 		if (device_create_file(&ibdev->ib_dev.dev,
 				       mlx4_class_attributes[i]))
-			goto err_reg;
+			goto err_notif;
 	}
 
 	ibdev->ib_active = true;
 
 	return ibdev;
 
+err_notif:
+	if (unregister_netdevice_notifier(&ibdev->iboe.nb))
+		printk(KERN_WARNING "failure unregistering notifier\n");
+	flush_workqueue(wq);
+
 err_reg:
 	ib_unregister_device(&ibdev->ib_dev);
 
@@ -703,11 +1153,16 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 
 	mlx4_ib_mad_cleanup(ibdev);
 	ib_unregister_device(&ibdev->ib_dev);
+	if (ibdev->iboe.nb.notifier_call) {
+		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
+			printk(KERN_WARNING "failure unregistering notifier\n");
+		ibdev->iboe.nb.notifier_call = NULL;
+	}
+	iounmap(ibdev->uar_map);
 
-	for (p = 1; p <= ibdev->num_ports; ++p)
+	mlx4_foreach_port(p, dev, MLX4_PORT_TYPE_IB)
 		mlx4_CLOSE_PORT(dev, p);
 
-	iounmap(ibdev->uar_map);
 	mlx4_uar_free(dev, &ibdev->priv_uar);
 	mlx4_pd_free(dev, ibdev->priv_pdn);
 	ib_dealloc_device(&ibdev->ib_dev);
@@ -747,19 +1202,33 @@ static void mlx4_ib_event(struct mlx4_dev *dev, void *ibdev_ptr,
 }
 
 static struct mlx4_interface mlx4_ib_interface = {
-	.add	= mlx4_ib_add,
-	.remove	= mlx4_ib_remove,
-	.event	= mlx4_ib_event
+	.add		= mlx4_ib_add,
+	.remove		= mlx4_ib_remove,
+	.event		= mlx4_ib_event,
+	.protocol	= MLX4_PROTOCOL_IB
 };
 
 static int __init mlx4_ib_init(void)
 {
-	return mlx4_register_interface(&mlx4_ib_interface);
+	int err;
+
+	wq = create_singlethread_workqueue("mlx4_ib");
+	if (!wq)
+		return -ENOMEM;
+
+	err = mlx4_register_interface(&mlx4_ib_interface);
+	if (err) {
+		destroy_workqueue(wq);
+		return err;
+	}
+
+	return 0;
 }
 
 static void __exit mlx4_ib_cleanup(void)
 {
 	mlx4_unregister_interface(&mlx4_ib_interface);
+	destroy_workqueue(wq);
 }
 
 module_init(mlx4_ib_init);

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -112,6 +112,13 @@ enum mlx4_ib_qp_flags {
 	MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK	= 1 << 1,
 };
 
+struct mlx4_ib_gid_entry {
+	struct list_head	list;
+	union ib_gid		gid;
+	int			added;
+	u8			port;
+};
+
 struct mlx4_ib_qp {
 	struct ib_qp		ibqp;
 	struct mlx4_qp		mqp;
@@ -138,6 +145,8 @@ struct mlx4_ib_qp {
 	u8			resp_depth;
 	u8			sq_no_prefetch;
 	u8			state;
+	int			mlx_type;
+	struct list_head	gid_list;
 };
 
 struct mlx4_ib_srq {
@@ -157,7 +166,14 @@ struct mlx4_ib_srq {
 
 struct mlx4_ib_ah {
 	struct ib_ah		ibah;
-	struct mlx4_av		av;
+	union mlx4_ext_av       av;
+};
+
+struct mlx4_ib_iboe {
+	spinlock_t		lock;
+	struct net_device      *netdevs[MLX4_MAX_PORTS];
+	struct notifier_block 	nb;
+	union ib_gid		gid_table[MLX4_MAX_PORTS][128];
 };
 
 struct mlx4_ib_dev {
@@ -176,6 +192,7 @@ struct mlx4_ib_dev {
 
 	struct mutex		cap_mask_mutex;
 	bool			ib_active;
+	struct mlx4_ib_iboe	iboe;
 };
 
 static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev)
@@ -314,9 +331,20 @@ int mlx4_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list, int npages,
 int mlx4_ib_unmap_fmr(struct list_head *fmr_list);
 int mlx4_ib_fmr_dealloc(struct ib_fmr *fmr);
 
+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 int mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
 {
-	return !!(ah->av.g_slid & 0x80);
+	u8 port = be32_to_cpu(ah->av.ib.port_pd) >> 24 & 3;
+
+	if (rdma_port_get_link_layer(ah->ibah.device, port) == IB_LINK_LAYER_ETHERNET)
+		return 1;
+
+	return !!(ah->av.ib.g_slid & 0x80);
 }
 
+int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
+		   union ib_gid *gid);
+
 #endif /* MLX4_IB_H */

drivers/infiniband/hw/mlx4/mr.c

@@ -226,7 +226,7 @@ struct ib_fast_reg_page_list *mlx4_ib_alloc_fast_reg_page_list(struct ib_device
 	struct mlx4_ib_fast_reg_page_list *mfrpl;
 	int size = page_list_len * sizeof (u64);
 
-	if (size > PAGE_SIZE)
+	if (page_list_len > MLX4_MAX_FAST_REG_PAGES)
 		return ERR_PTR(-EINVAL);
 
 	mfrpl = kmalloc(sizeof *mfrpl, GFP_KERNEL);

drivers/infiniband/hw/mlx4/qp.c

@@ -33,9 +33,11 @@
 
 #include <linux/log2.h>
 #include <linux/slab.h>
+#include <linux/netdevice.h>
 
 #include <rdma/ib_cache.h>
 #include <rdma/ib_pack.h>
+#include <rdma/ib_addr.h>
 
 #include <linux/mlx4/qp.h>
 
@@ -48,17 +50,26 @@ enum {
 
 enum {
 	MLX4_IB_DEFAULT_SCHED_QUEUE	= 0x83,
-	MLX4_IB_DEFAULT_QP0_SCHED_QUEUE	= 0x3f
+	MLX4_IB_DEFAULT_QP0_SCHED_QUEUE	= 0x3f,
+	MLX4_IB_LINK_TYPE_IB		= 0,
+	MLX4_IB_LINK_TYPE_ETH		= 1
 };
 
 enum {
 	/*
-	 * Largest possible UD header: send with GRH and immediate data.
+	 * Largest possible UD header: send with GRH and immediate
+	 * data plus 18 bytes for an Ethernet header with VLAN/802.1Q
+	 * tag.  (LRH would only use 8 bytes, so Ethernet is the
+	 * biggest case)
 	 */
-	MLX4_IB_UD_HEADER_SIZE		= 72,
+	MLX4_IB_UD_HEADER_SIZE		= 82,
 	MLX4_IB_LSO_HEADER_SPARE	= 128,
 };
 
+enum {
+	MLX4_IB_IBOE_ETHERTYPE		= 0x8915
+};
+
 struct mlx4_ib_sqp {
 	struct mlx4_ib_qp	qp;
 	int			pkey_index;
@@ -462,6 +473,7 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	mutex_init(&qp->mutex);
 	spin_lock_init(&qp->sq.lock);
 	spin_lock_init(&qp->rq.lock);
+	INIT_LIST_HEAD(&qp->gid_list);
 
 	qp->state	 = IB_QPS_RESET;
 	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
@@ -649,6 +661,16 @@ static void mlx4_ib_unlock_cqs(struct mlx4_ib_cq *send_cq, struct mlx4_ib_cq *re
 	}
 }
 
+static void del_gid_entries(struct mlx4_ib_qp *qp)
+{
+	struct mlx4_ib_gid_entry *ge, *tmp;
+
+	list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) {
+		list_del(&ge->list);
+		kfree(ge);
+	}
+}
+
 static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 			      int is_user)
 {
@@ -695,6 +717,8 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 		if (!qp->ibqp.srq)
 			mlx4_db_free(dev->dev, &qp->db);
 	}
+
+	del_gid_entries(qp);
 }
 
 struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
@@ -852,6 +876,14 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port)
 static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 			 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;
+
 	path->grh_mylmc     = ah->src_path_bits & 0x7f;
 	path->rlid	    = cpu_to_be16(ah->dlid);
 	if (ah->static_rate) {
@@ -879,12 +911,49 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 		memcpy(path->rgid, ah->grh.dgid.raw, 16);
 	}
 
-	path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
-		((port - 1) << 6) | ((ah->sl & 0xf) << 2);
+	if (is_eth) {
+		path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
+			((port - 1) << 6) | ((ah->sl & 7) << 3) | ((ah->sl & 8) >> 1);
+
+		if (!(ah->ah_flags & IB_AH_GRH))
+			return -1;
+
+		err = mlx4_ib_resolve_grh(dev, ah, mac, &is_mcast, port);
+		if (err)
+			return err;
+
+		memcpy(path->dmac, mac, 6);
+		path->ackto = MLX4_IB_LINK_TYPE_ETH;
+		/* use index 0 into MAC table for IBoE */
+		path->grh_mylmc &= 0x80;
+
+		vlan_tag = rdma_get_vlan_id(&dev->iboe.gid_table[port - 1][ah->grh.sgid_index]);
+		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;
+		}
+	} else
+		path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
+			((port - 1) << 6) | ((ah->sl & 0xf) << 2);
 
 	return 0;
 }
 
+static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
+{
+	struct mlx4_ib_gid_entry *ge, *tmp;
+
+	list_for_each_entry_safe(ge, tmp, &qp->gid_list, list) {
+		if (!ge->added && mlx4_ib_add_mc(dev, qp, &ge->gid)) {
+			ge->added = 1;
+			ge->port = qp->port;
+		}
+	}
+}
+
 static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 			       const struct ib_qp_attr *attr, int attr_mask,
 			       enum ib_qp_state cur_state, enum ib_qp_state new_state)
@@ -980,7 +1049,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (attr_mask & IB_QP_TIMEOUT) {
-		context->pri_path.ackto = attr->timeout << 3;
+		context->pri_path.ackto |= attr->timeout << 3;
 		optpar |= MLX4_QP_OPTPAR_ACK_TIMEOUT;
 	}
 
@@ -1118,8 +1187,10 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		qp->atomic_rd_en = attr->qp_access_flags;
 	if (attr_mask & IB_QP_MAX_DEST_RD_ATOMIC)
 		qp->resp_depth = attr->max_dest_rd_atomic;
-	if (attr_mask & IB_QP_PORT)
+	if (attr_mask & IB_QP_PORT) {
 		qp->port = attr->port_num;
+		update_mcg_macs(dev, qp);
+	}
 	if (attr_mask & IB_QP_ALT_PATH)
 		qp->alt_port = attr->alt_port_num;
 
@@ -1221,40 +1292,59 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 	struct mlx4_wqe_mlx_seg *mlx = wqe;
 	struct mlx4_wqe_inline_seg *inl = wqe + sizeof *mlx;
 	struct mlx4_ib_ah *ah = to_mah(wr->wr.ud.ah);
+	union ib_gid sgid;
 	u16 pkey;
 	int send_size;
 	int header_size;
 	int spc;
 	int i;
+	int is_eth;
+	int is_vlan = 0;
+	int is_grh;
+	u16 vlan;
 
 	send_size = 0;
 	for (i = 0; i < wr->num_sge; ++i)
 		send_size += wr->sg_list[i].length;
 
-	ib_ud_header_init(send_size, mlx4_ib_ah_grh_present(ah), 0, &sqp->ud_header);
+	is_eth = rdma_port_get_link_layer(sqp->qp.ibqp.device, sqp->qp.port) == IB_LINK_LAYER_ETHERNET;
+	is_grh = mlx4_ib_ah_grh_present(ah);
+	if (is_eth) {
+		ib_get_cached_gid(ib_dev, be32_to_cpu(ah->av.ib.port_pd) >> 24,
+				  ah->av.ib.gid_index, &sgid);
+		vlan = rdma_get_vlan_id(&sgid);
+		is_vlan = vlan < 0x1000;
+	}
+	ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header);
+
+	if (!is_eth) {
+		sqp->ud_header.lrh.service_level =
+			be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 28;
+		sqp->ud_header.lrh.destination_lid = ah->av.ib.dlid;
+		sqp->ud_header.lrh.source_lid = cpu_to_be16(ah->av.ib.g_slid & 0x7f);
+	}
 
-	sqp->ud_header.lrh.service_level   =
-		be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 28;
-	sqp->ud_header.lrh.destination_lid = ah->av.dlid;
-	sqp->ud_header.lrh.source_lid      = cpu_to_be16(ah->av.g_slid & 0x7f);
-	if (mlx4_ib_ah_grh_present(ah)) {
+	if (is_grh) {
 		sqp->ud_header.grh.traffic_class =
-			(be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 20) & 0xff;
+			(be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 20) & 0xff;
 		sqp->ud_header.grh.flow_label    =
-			ah->av.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
-		sqp->ud_header.grh.hop_limit     = ah->av.hop_limit;
-		ib_get_cached_gid(ib_dev, be32_to_cpu(ah->av.port_pd) >> 24,
-				  ah->av.gid_index, &sqp->ud_header.grh.source_gid);
+			ah->av.ib.sl_tclass_flowlabel & cpu_to_be32(0xfffff);
+		sqp->ud_header.grh.hop_limit     = ah->av.ib.hop_limit;
+		ib_get_cached_gid(ib_dev, be32_to_cpu(ah->av.ib.port_pd) >> 24,
+				  ah->av.ib.gid_index, &sqp->ud_header.grh.source_gid);
 		memcpy(sqp->ud_header.grh.destination_gid.raw,
-		       ah->av.dgid, 16);
+		       ah->av.ib.dgid, 16);
 	}
 
 	mlx->flags &= cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE);
-	mlx->flags |= cpu_to_be32((!sqp->qp.ibqp.qp_num ? MLX4_WQE_MLX_VL15 : 0) |
-				  (sqp->ud_header.lrh.destination_lid ==
-				   IB_LID_PERMISSIVE ? MLX4_WQE_MLX_SLR : 0) |
-				  (sqp->ud_header.lrh.service_level << 8));
-	mlx->rlid   = sqp->ud_header.lrh.destination_lid;
+
+	if (!is_eth) {
+		mlx->flags |= cpu_to_be32((!sqp->qp.ibqp.qp_num ? MLX4_WQE_MLX_VL15 : 0) |
+					  (sqp->ud_header.lrh.destination_lid ==
+					   IB_LID_PERMISSIVE ? MLX4_WQE_MLX_SLR : 0) |
+					  (sqp->ud_header.lrh.service_level << 8));
+		mlx->rlid = sqp->ud_header.lrh.destination_lid;
+	}
 
 	switch (wr->opcode) {
 	case IB_WR_SEND:
@@ -1270,9 +1360,29 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 		return -EINVAL;
 	}
 
-	sqp->ud_header.lrh.virtual_lane    = !sqp->qp.ibqp.qp_num ? 15 : 0;
-	if (sqp->ud_header.lrh.destination_lid == IB_LID_PERMISSIVE)
-		sqp->ud_header.lrh.source_lid = IB_LID_PERMISSIVE;
+	if (is_eth) {
+		u8 *smac;
+
+		memcpy(sqp->ud_header.eth.dmac_h, ah->av.eth.mac, 6);
+		/* FIXME: cache smac value? */
+		smac = to_mdev(sqp->qp.ibqp.device)->iboe.netdevs[sqp->qp.port - 1]->dev_addr;
+		memcpy(sqp->ud_header.eth.smac_h, smac, 6);
+		if (!memcmp(sqp->ud_header.eth.smac_h, sqp->ud_header.eth.dmac_h, 6))
+			mlx->flags |= cpu_to_be32(MLX4_WQE_CTRL_FORCE_LOOPBACK);
+		if (!is_vlan) {
+			sqp->ud_header.eth.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE);
+		} else {
+			u16 pcp;
+
+			sqp->ud_header.vlan.type = cpu_to_be16(MLX4_IB_IBOE_ETHERTYPE);
+			pcp = (be32_to_cpu(ah->av.ib.sl_tclass_flowlabel) >> 27 & 3) << 13;
+			sqp->ud_header.vlan.tag = cpu_to_be16(vlan | pcp);
+		}
+	} else {
+		sqp->ud_header.lrh.virtual_lane    = !sqp->qp.ibqp.qp_num ? 15 : 0;
+		if (sqp->ud_header.lrh.destination_lid == IB_LID_PERMISSIVE)
+			sqp->ud_header.lrh.source_lid = IB_LID_PERMISSIVE;
+	}
 	sqp->ud_header.bth.solicited_event = !!(wr->send_flags & IB_SEND_SOLICITED);
 	if (!sqp->qp.ibqp.qp_num)
 		ib_get_cached_pkey(ib_dev, sqp->qp.port, sqp->pkey_index, &pkey);
@@ -1429,11 +1539,14 @@ static void set_masked_atomic_seg(struct mlx4_wqe_masked_atomic_seg *aseg,
 }
 
 static void set_datagram_seg(struct mlx4_wqe_datagram_seg *dseg,
-			     struct ib_send_wr *wr)
+			     struct ib_send_wr *wr, __be16 *vlan)
 {
 	memcpy(dseg->av, &to_mah(wr->wr.ud.ah)->av, sizeof (struct mlx4_av));
 	dseg->dqpn = cpu_to_be32(wr->wr.ud.remote_qpn);
 	dseg->qkey = cpu_to_be32(wr->wr.ud.remote_qkey);
+	dseg->vlan = to_mah(wr->wr.ud.ah)->av.eth.vlan;
+	memcpy(dseg->mac, to_mah(wr->wr.ud.ah)->av.eth.mac, 6);
+	*vlan = dseg->vlan;
 }
 
 static void set_mlx_icrc_seg(void *dseg)
@@ -1536,6 +1649,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 	__be32 uninitialized_var(lso_hdr_sz);
 	__be32 blh;
 	int i;
+	__be16 vlan = cpu_to_be16(0xffff);
 
 	spin_lock_irqsave(&qp->sq.lock, flags);
 
@@ -1639,7 +1753,7 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 			break;
 
 		case IB_QPT_UD:
-			set_datagram_seg(wqe, wr);
+			set_datagram_seg(wqe, wr, &vlan);
 			wqe  += sizeof (struct mlx4_wqe_datagram_seg);
 			size += sizeof (struct mlx4_wqe_datagram_seg) / 16;
 
@@ -1717,6 +1831,11 @@ int mlx4_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
 		ctrl->owner_opcode = mlx4_ib_opcode[wr->opcode] |
 			(ind & qp->sq.wqe_cnt ? cpu_to_be32(1 << 31) : 0) | blh;
 
+		if (be16_to_cpu(vlan) < 0x1000) {
+			ctrl->ins_vlan = 1 << 6;
+			ctrl->vlan_tag = vlan;
+		}
+
 		stamp = ind + qp->sq_spare_wqes;
 		ind += DIV_ROUND_UP(size * 16, 1U << qp->sq.wqe_shift);
 
@@ -1866,17 +1985,27 @@ static int to_ib_qp_access_flags(int mlx4_flags)
 	return ib_flags;
 }
 
-static void to_ib_ah_attr(struct mlx4_dev *dev, struct ib_ah_attr *ib_ah_attr,
+static void to_ib_ah_attr(struct mlx4_ib_dev *ibdev, struct ib_ah_attr *ib_ah_attr,
 				struct mlx4_qp_path *path)
 {
+	struct mlx4_dev *dev = ibdev->dev;
+	int is_eth;
+
 	memset(ib_ah_attr, 0, sizeof *ib_ah_attr);
 	ib_ah_attr->port_num	  = path->sched_queue & 0x40 ? 2 : 1;
 
 	if (ib_ah_attr->port_num == 0 || ib_ah_attr->port_num > dev->caps.num_ports)
 		return;
 
+	is_eth = rdma_port_get_link_layer(&ibdev->ib_dev, ib_ah_attr->port_num) ==
+		IB_LINK_LAYER_ETHERNET;
+	if (is_eth)
+		ib_ah_attr->sl = ((path->sched_queue >> 3) & 0x7) |
+		((path->sched_queue & 4) << 1);
+	else
+		ib_ah_attr->sl = (path->sched_queue >> 2) & 0xf;
+
 	ib_ah_attr->dlid	  = be16_to_cpu(path->rlid);
-	ib_ah_attr->sl		  = (path->sched_queue >> 2) & 0xf;
 	ib_ah_attr->src_path_bits = path->grh_mylmc & 0x7f;
 	ib_ah_attr->static_rate   = path->static_rate ? path->static_rate - 5 : 0;
 	ib_ah_attr->ah_flags      = (path->grh_mylmc & (1 << 7)) ? IB_AH_GRH : 0;
@@ -1929,8 +2058,8 @@ int mlx4_ib_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr, int qp_attr
 		to_ib_qp_access_flags(be32_to_cpu(context.params2));
 
 	if (qp->ibqp.qp_type == IB_QPT_RC || qp->ibqp.qp_type == IB_QPT_UC) {
-		to_ib_ah_attr(dev->dev, &qp_attr->ah_attr, &context.pri_path);
-		to_ib_ah_attr(dev->dev, &qp_attr->alt_ah_attr, &context.alt_path);
+		to_ib_ah_attr(dev, &qp_attr->ah_attr, &context.pri_path);
+		to_ib_ah_attr(dev, &qp_attr->alt_ah_attr, &context.alt_path);
 		qp_attr->alt_pkey_index = context.alt_path.pkey_index & 0x7f;
 		qp_attr->alt_port_num	= qp_attr->alt_ah_attr.port_num;
 	}

drivers/infiniband/hw/mthca/mthca_qp.c

@@ -1493,7 +1493,7 @@ static int build_mlx_header(struct mthca_dev *dev, struct mthca_sqp *sqp,
 	int err;
 	u16 pkey;
 
-	ib_ud_header_init(256, /* assume a MAD */
+	ib_ud_header_init(256, /* assume a MAD */ 1, 0, 0,
 			  mthca_ah_grh_present(to_mah(wr->wr.ud.ah)), 0,
 			  &sqp->ud_header);
 

drivers/infiniband/hw/nes/nes_cm.c

@@ -1424,7 +1424,6 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 {
 
 	int	reset = 0;	/* whether to send reset in case of err.. */
-	int	passive_state;
 	atomic_inc(&cm_resets_recvd);
 	nes_debug(NES_DBG_CM, "Received Reset, cm_node = %p, state = %u."
 			" refcnt=%d\n", cm_node, cm_node->state,
@@ -1439,7 +1438,7 @@ static void handle_rst_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 		active_open_err(cm_node, skb, reset);
 		break;
 	case NES_CM_STATE_MPAREQ_RCVD:
-		passive_state = atomic_add_return(1, &cm_node->passive_state);
+		atomic_inc(&cm_node->passive_state);
 		dev_kfree_skb_any(skb);
 		break;
 	case NES_CM_STATE_ESTABLISHED:

drivers/infiniband/hw/nes/nes_nic.c

@@ -271,6 +271,7 @@ static int nes_netdev_stop(struct net_device *netdev)
 
 	if (netif_msg_ifdown(nesvnic))
 		printk(KERN_INFO PFX "%s: disabling interface\n", netdev->name);
+	netif_carrier_off(netdev);
 
 	/* Disable network packets */
 	napi_disable(&nesvnic->napi);

drivers/infiniband/hw/nes/nes_verbs.c

@@ -476,9 +476,9 @@ static struct ib_fast_reg_page_list *nes_alloc_fast_reg_page_list(
 	}
 	nes_debug(NES_DBG_MR, "nes_alloc_fast_reg_pbl: nes_frpl = %p, "
 		  "ibfrpl = %p, ibfrpl.page_list = %p, pbl.kva = %p, "
-		  "pbl.paddr= %p\n", pnesfrpl, &pnesfrpl->ibfrpl,
+		  "pbl.paddr = %llx\n", pnesfrpl, &pnesfrpl->ibfrpl,
 		  pnesfrpl->ibfrpl.page_list, pnesfrpl->nes_wqe_pbl.kva,
-		  (void *)pnesfrpl->nes_wqe_pbl.paddr);
+		  (unsigned long long) pnesfrpl->nes_wqe_pbl.paddr);
 
 	return pifrpl;
 }
@@ -584,7 +584,9 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr
 	props->lmc = 0;
 	props->sm_lid = 0;
 	props->sm_sl = 0;
-	if (nesvnic->linkup)
+	if (netif_queue_stopped(netdev))
+		props->state = IB_PORT_DOWN;
+	else if (nesvnic->linkup)
 		props->state = IB_PORT_ACTIVE;
 	else
 		props->state = IB_PORT_DOWN;
@@ -3483,13 +3485,13 @@ static int nes_post_send(struct ib_qp *ibqp, struct ib_send_wr *ib_wr,
 			for (i = 0; i < ib_wr->wr.fast_reg.page_list_len; i++)
 				dst_page_list[i] = cpu_to_le64(src_page_list[i]);
 
-			nes_debug(NES_DBG_IW_TX, "SQ_FMR: iova_start: %p, "
-				  "length: %d, rkey: %0x, pgl_paddr: %p, "
+			nes_debug(NES_DBG_IW_TX, "SQ_FMR: iova_start: %llx, "
+				  "length: %d, rkey: %0x, pgl_paddr: %llx, "
 				  "page_list_len: %u, wqe_misc: %x\n",
-				  (void *)ib_wr->wr.fast_reg.iova_start,
+				  (unsigned long long) ib_wr->wr.fast_reg.iova_start,
 				  ib_wr->wr.fast_reg.length,
 				  ib_wr->wr.fast_reg.rkey,
-				  (void *)pnesfrpl->nes_wqe_pbl.paddr,
+				  (unsigned long long) pnesfrpl->nes_wqe_pbl.paddr,
 				  ib_wr->wr.fast_reg.page_list_len,
 				  wqe_misc);
 			break;

drivers/infiniband/hw/qib/qib.h

@@ -1406,7 +1406,7 @@ extern struct mutex qib_mutex;
  */
 #define qib_early_err(dev, fmt, ...) \
 	do { \
-		dev_info(dev, KERN_ERR QIB_DRV_NAME ": " fmt, ##__VA_ARGS__); \
+		dev_err(dev, fmt, ##__VA_ARGS__); \
 	} while (0)
 
 #define qib_dev_err(dd, fmt, ...) \

drivers/infiniband/hw/qib/qib_file_ops.c

@@ -1722,7 +1722,7 @@ static int qib_close(struct inode *in, struct file *fp)
 
 	mutex_lock(&qib_mutex);
 
-	fd = (struct qib_filedata *) fp->private_data;
+	fd = fp->private_data;
 	fp->private_data = NULL;
 	rcd = fd->rcd;
 	if (!rcd) {
@@ -1808,7 +1808,7 @@ static int qib_ctxt_info(struct file *fp, struct qib_ctxt_info __user *uinfo)
 	struct qib_ctxtdata *rcd = ctxt_fp(fp);
 	struct qib_filedata *fd;
 
-	fd = (struct qib_filedata *) fp->private_data;
+	fd = fp->private_data;
 
 	info.num_active = qib_count_active_units();
 	info.unit = rcd->dd->unit;

drivers/infiniband/hw/qib/qib_init.c

@@ -1243,6 +1243,7 @@ static int __devinit qib_init_one(struct pci_dev *pdev,
 		qib_early_err(&pdev->dev, "QLogic PCIE device 0x%x cannot "
 		      "work if CONFIG_PCI_MSI is not enabled\n",
 		      ent->device);
+		dd = ERR_PTR(-ENODEV);
 #endif
 		break;
 

drivers/infiniband/hw/qib/qib_pcie.c

@@ -103,16 +103,20 @@ int qib_pcie_init(struct pci_dev *pdev, const struct pci_device_id *ent)
 		ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32));
 	} else
 		ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
-	if (ret)
+	if (ret) {
 		qib_early_err(&pdev->dev,
 			      "Unable to set DMA consistent mask: %d\n", ret);
+		goto bail;
+	}
 
 	pci_set_master(pdev);
 	ret = pci_enable_pcie_error_reporting(pdev);
-	if (ret)
+	if (ret) {
 		qib_early_err(&pdev->dev,
 			      "Unable to enable pcie error reporting: %d\n",
 			      ret);
+		ret = 0;
+	}
 	goto done;
 
 bail:

drivers/infiniband/hw/qib/qib_rc.c

@@ -2068,7 +2068,10 @@ send_last:
 			goto nack_op_err;
 		if (!ret)
 			goto rnr_nak;
-		goto send_last_imm;
+		wc.ex.imm_data = ohdr->u.rc.imm_data;
+		hdrsize += 4;
+		wc.wc_flags = IB_WC_WITH_IMM;
+		goto send_last;
 
 	case OP(RDMA_READ_REQUEST): {
 		struct qib_ack_entry *e;

drivers/infiniband/hw/qib/qib_uc.c

@@ -457,8 +457,10 @@ rdma_first:
 		}
 		if (opcode == OP(RDMA_WRITE_ONLY))
 			goto rdma_last;
-		else if (opcode == OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE))
+		else if (opcode == OP(RDMA_WRITE_ONLY_WITH_IMMEDIATE)) {
+			wc.ex.imm_data = ohdr->u.rc.imm_data;
 			goto rdma_last_imm;
+		}
 		/* FALLTHROUGH */
 	case OP(RDMA_WRITE_MIDDLE):
 		/* Check for invalid length PMTU or posted rwqe len. */
@@ -471,8 +473,8 @@ rdma_first:
 		break;
 
 	case OP(RDMA_WRITE_LAST_WITH_IMMEDIATE):
-rdma_last_imm:
 		wc.ex.imm_data = ohdr->u.imm_data;
+rdma_last_imm:
 		hdrsize += 4;
 		wc.wc_flags = IB_WC_WITH_IMM;
 

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -223,6 +223,7 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	unsigned int wr_id = wc->wr_id & ~IPOIB_OP_RECV;
 	struct sk_buff *skb;
 	u64 mapping[IPOIB_UD_RX_SG];
+	union ib_gid *dgid;
 
 	ipoib_dbg_data(priv, "recv completion: id %d, status: %d\n",
 		       wr_id, wc->status);
@@ -271,6 +272,16 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	ipoib_ud_dma_unmap_rx(priv, mapping);
 	ipoib_ud_skb_put_frags(priv, skb, wc->byte_len);
 
+	/* First byte of dgid signals multicast when 0xff */
+	dgid = &((struct ib_grh *)skb->data)->dgid;
+
+	if (!(wc->wc_flags & IB_WC_GRH) || dgid->raw[0] != 0xff)
+		skb->pkt_type = PACKET_HOST;
+	else if (memcmp(dgid, dev->broadcast + 4, sizeof(union ib_gid)) == 0)
+		skb->pkt_type = PACKET_BROADCAST;
+	else
+		skb->pkt_type = PACKET_MULTICAST;
+
 	skb_pull(skb, IB_GRH_BYTES);
 
 	skb->protocol = ((struct ipoib_header *) skb->data)->proto;
@@ -281,9 +292,6 @@ static void ipoib_ib_handle_rx_wc(struct net_device *dev, struct ib_wc *wc)
 	dev->stats.rx_bytes += skb->len;
 
 	skb->dev = dev;
-	/* XXX get correct PACKET_ type here */
-	skb->pkt_type = PACKET_HOST;
-
 	if (test_bit(IPOIB_FLAG_CSUM, &priv->flags) && likely(wc->csum_ok))
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -1240,6 +1240,7 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto alloc_mem_failed;
 
 	SET_NETDEV_DEV(priv->dev, hca->dma_device);
+	priv->dev->dev_id = port - 1;
 
 	if (!ib_query_port(hca, port, &attr))
 		priv->max_ib_mtu = ib_mtu_enum_to_int(attr.max_mtu);
@@ -1362,6 +1363,8 @@ static void ipoib_add_one(struct ib_device *device)
 	}
 
 	for (p = s; p <= e; ++p) {
+		if (rdma_port_get_link_layer(device, p) != IB_LINK_LAYER_INFINIBAND)
+			continue;
 		dev = ipoib_add_port("ib%d", device, p);
 		if (!IS_ERR(dev)) {
 			priv = netdev_priv(dev);

drivers/infiniband/ulp/srp/ib_srp.c

@@ -291,7 +291,7 @@ static void srp_free_target_ib(struct srp_target_port *target)
 
 	for (i = 0; i < SRP_RQ_SIZE; ++i)
 		srp_free_iu(target->srp_host, target->rx_ring[i]);
-	for (i = 0; i < SRP_SQ_SIZE + 1; ++i)
+	for (i = 0; i < SRP_SQ_SIZE; ++i)
 		srp_free_iu(target->srp_host, target->tx_ring[i]);
 }
 
@@ -811,6 +811,75 @@ static int srp_map_data(struct scsi_cmnd *scmnd, struct srp_target_port *target,
 	return len;
 }
 
+/*
+ * Must be called with target->scsi_host->host_lock held to protect
+ * req_lim and tx_head.  Lock cannot be dropped between call here and
+ * call to __srp_post_send().
+ *
+ * Note:
+ * An upper limit for the number of allocated information units for each
+ * request type is:
+ * - SRP_IU_CMD: SRP_CMD_SQ_SIZE, since the SCSI mid-layer never queues
+ *   more than Scsi_Host.can_queue requests.
+ * - SRP_IU_TSK_MGMT: SRP_TSK_MGMT_SQ_SIZE.
+ * - SRP_IU_RSP: 1, since a conforming SRP target never sends more than
+ *   one unanswered SRP request to an initiator.
+ */
+static struct srp_iu *__srp_get_tx_iu(struct srp_target_port *target,
+				      enum srp_iu_type iu_type)
+{
+	s32 rsv = (iu_type == SRP_IU_TSK_MGMT) ? 0 : SRP_TSK_MGMT_SQ_SIZE;
+	struct srp_iu *iu;
+
+	srp_send_completion(target->send_cq, target);
+
+	if (target->tx_head - target->tx_tail >= SRP_SQ_SIZE)
+		return NULL;
+
+	/* Initiator responses to target requests do not consume credits */
+	if (target->req_lim <= rsv && iu_type != SRP_IU_RSP) {
+		++target->zero_req_lim;
+		return NULL;
+	}
+
+	iu = target->tx_ring[target->tx_head & SRP_SQ_MASK];
+	iu->type = iu_type;
+	return iu;
+}
+
+/*
+ * Must be called with target->scsi_host->host_lock held to protect
+ * req_lim and tx_head.
+ */
+static int __srp_post_send(struct srp_target_port *target,
+			   struct srp_iu *iu, int len)
+{
+	struct ib_sge list;
+	struct ib_send_wr wr, *bad_wr;
+	int ret = 0;
+
+	list.addr   = iu->dma;
+	list.length = len;
+	list.lkey   = target->srp_host->srp_dev->mr->lkey;
+
+	wr.next       = NULL;
+	wr.wr_id      = target->tx_head & SRP_SQ_MASK;
+	wr.sg_list    = &list;
+	wr.num_sge    = 1;
+	wr.opcode     = IB_WR_SEND;
+	wr.send_flags = IB_SEND_SIGNALED;
+
+	ret = ib_post_send(target->qp, &wr, &bad_wr);
+
+	if (!ret) {
+		++target->tx_head;
+		if (iu->type != SRP_IU_RSP)
+			--target->req_lim;
+	}
+
+	return ret;
+}
+
 static int srp_post_recv(struct srp_target_port *target)
 {
 	unsigned long flags;
@@ -822,7 +891,7 @@ static int srp_post_recv(struct srp_target_port *target)
 
 	spin_lock_irqsave(target->scsi_host->host_lock, flags);
 
-	next	 = target->rx_head & (SRP_RQ_SIZE - 1);
+	next	 = target->rx_head & SRP_RQ_MASK;
 	wr.wr_id = next;
 	iu	 = target->rx_ring[next];
 
@@ -896,6 +965,71 @@ static void srp_process_rsp(struct srp_target_port *target, struct srp_rsp *rsp)
 	spin_unlock_irqrestore(target->scsi_host->host_lock, flags);
 }
 
+static int srp_response_common(struct srp_target_port *target, s32 req_delta,
+			       void *rsp, int len)
+{
+	struct ib_device *dev;
+	unsigned long flags;
+	struct srp_iu *iu;
+	int err = 1;
+
+	dev = target->srp_host->srp_dev->dev;
+
+	spin_lock_irqsave(target->scsi_host->host_lock, flags);
+	target->req_lim += req_delta;
+
+	iu = __srp_get_tx_iu(target, SRP_IU_RSP);
+	if (!iu) {
+		shost_printk(KERN_ERR, target->scsi_host, PFX
+			     "no IU available to send response\n");
+		goto out;
+	}
+
+	ib_dma_sync_single_for_cpu(dev, iu->dma, len, DMA_TO_DEVICE);
+	memcpy(iu->buf, rsp, len);
+	ib_dma_sync_single_for_device(dev, iu->dma, len, DMA_TO_DEVICE);
+
+	err = __srp_post_send(target, iu, len);
+	if (err)
+		shost_printk(KERN_ERR, target->scsi_host, PFX
+			     "unable to post response: %d\n", err);
+
+out:
+	spin_unlock_irqrestore(target->scsi_host->host_lock, flags);
+	return err;
+}
+
+static void srp_process_cred_req(struct srp_target_port *target,
+				 struct srp_cred_req *req)
+{
+	struct srp_cred_rsp rsp = {
+		.opcode = SRP_CRED_RSP,
+		.tag = req->tag,
+	};
+	s32 delta = be32_to_cpu(req->req_lim_delta);
+
+	if (srp_response_common(target, delta, &rsp, sizeof rsp))
+		shost_printk(KERN_ERR, target->scsi_host, PFX
+			     "problems processing SRP_CRED_REQ\n");
+}
+
+static void srp_process_aer_req(struct srp_target_port *target,
+				struct srp_aer_req *req)
+{
+	struct srp_aer_rsp rsp = {
+		.opcode = SRP_AER_RSP,
+		.tag = req->tag,
+	};
+	s32 delta = be32_to_cpu(req->req_lim_delta);
+
+	shost_printk(KERN_ERR, target->scsi_host, PFX
+		     "ignoring AER for LUN %llu\n", be64_to_cpu(req->lun));
+
+	if (srp_response_common(target, delta, &rsp, sizeof rsp))
+		shost_printk(KERN_ERR, target->scsi_host, PFX
+			     "problems processing SRP_AER_REQ\n");
+}
+
 static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc)
 {
 	struct ib_device *dev;
@@ -923,6 +1057,14 @@ static void srp_handle_recv(struct srp_target_port *target, struct ib_wc *wc)
 		srp_process_rsp(target, iu->buf);
 		break;
 
+	case SRP_CRED_REQ:
+		srp_process_cred_req(target, iu->buf);
+		break;
+
+	case SRP_AER_REQ:
+		srp_process_aer_req(target, iu->buf);
+		break;
+
 	case SRP_T_LOGOUT:
 		/* XXX Handle target logout */
 		shost_printk(KERN_WARNING, target->scsi_host,
@@ -981,61 +1123,6 @@ static void srp_send_completion(struct ib_cq *cq, void *target_ptr)
 	}
 }
 
-/*
- * Must be called with target->scsi_host->host_lock held to protect
- * req_lim and tx_head.  Lock cannot be dropped between call here and
- * call to __srp_post_send().
- */
-static struct srp_iu *__srp_get_tx_iu(struct srp_target_port *target,
-					enum srp_request_type req_type)
-{
-	s32 min = (req_type == SRP_REQ_TASK_MGMT) ? 1 : 2;
-
-	srp_send_completion(target->send_cq, target);
-
-	if (target->tx_head - target->tx_tail >= SRP_SQ_SIZE)
-		return NULL;
-
-	if (target->req_lim < min) {
-		++target->zero_req_lim;
-		return NULL;
-	}
-
-	return target->tx_ring[target->tx_head & SRP_SQ_SIZE];
-}
-
-/*
- * Must be called with target->scsi_host->host_lock held to protect
- * req_lim and tx_head.
- */
-static int __srp_post_send(struct srp_target_port *target,
-			   struct srp_iu *iu, int len)
-{
-	struct ib_sge list;
-	struct ib_send_wr wr, *bad_wr;
-	int ret = 0;
-
-	list.addr   = iu->dma;
-	list.length = len;
-	list.lkey   = target->srp_host->srp_dev->mr->lkey;
-
-	wr.next       = NULL;
-	wr.wr_id      = target->tx_head & SRP_SQ_SIZE;
-	wr.sg_list    = &list;
-	wr.num_sge    = 1;
-	wr.opcode     = IB_WR_SEND;
-	wr.send_flags = IB_SEND_SIGNALED;
-
-	ret = ib_post_send(target->qp, &wr, &bad_wr);
-
-	if (!ret) {
-		++target->tx_head;
-		--target->req_lim;
-	}
-
-	return ret;
-}
-
 static int srp_queuecommand(struct scsi_cmnd *scmnd,
 			    void (*done)(struct scsi_cmnd *))
 {
@@ -1056,7 +1143,7 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd,
 		return 0;
 	}
 
-	iu = __srp_get_tx_iu(target, SRP_REQ_NORMAL);
+	iu = __srp_get_tx_iu(target, SRP_IU_CMD);
 	if (!iu)
 		goto err;
 
@@ -1064,7 +1151,7 @@ static int srp_queuecommand(struct scsi_cmnd *scmnd,
 	ib_dma_sync_single_for_cpu(dev, iu->dma, srp_max_iu_len,
 				   DMA_TO_DEVICE);
 
-	req = list_entry(target->free_reqs.next, struct srp_request, list);
+	req = list_first_entry(&target->free_reqs, struct srp_request, list);
 
 	scmnd->scsi_done     = done;
 	scmnd->result        = 0;
@@ -1121,7 +1208,7 @@ static int srp_alloc_iu_bufs(struct srp_target_port *target)
 			goto err;
 	}
 
-	for (i = 0; i < SRP_SQ_SIZE + 1; ++i) {
+	for (i = 0; i < SRP_SQ_SIZE; ++i) {
 		target->tx_ring[i] = srp_alloc_iu(target->srp_host,
 						  srp_max_iu_len,
 						  GFP_KERNEL, DMA_TO_DEVICE);
@@ -1137,7 +1224,7 @@ err:
 		target->rx_ring[i] = NULL;
 	}
 
-	for (i = 0; i < SRP_SQ_SIZE + 1; ++i) {
+	for (i = 0; i < SRP_SQ_SIZE; ++i) {
 		srp_free_iu(target->srp_host, target->tx_ring[i]);
 		target->tx_ring[i] = NULL;
 	}
@@ -1252,8 +1339,13 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
 			target->max_ti_iu_len = be32_to_cpu(rsp->max_ti_iu_len);
 			target->req_lim       = be32_to_cpu(rsp->req_lim_delta);
 
-			target->scsi_host->can_queue = min(target->req_lim,
-							   target->scsi_host->can_queue);
+			/*
+			 * Reserve credits for task management so we don't
+			 * bounce requests back to the SCSI mid-layer.
+			 */
+			target->scsi_host->can_queue
+				= min(target->req_lim - SRP_TSK_MGMT_SQ_SIZE,
+				      target->scsi_host->can_queue);
 		} else {
 			shost_printk(KERN_WARNING, target->scsi_host,
 				    PFX "Unhandled RSP opcode %#x\n", opcode);
@@ -1350,6 +1442,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
 static int srp_send_tsk_mgmt(struct srp_target_port *target,
 			     struct srp_request *req, u8 func)
 {
+	struct ib_device *dev = target->srp_host->srp_dev->dev;
 	struct srp_iu *iu;
 	struct srp_tsk_mgmt *tsk_mgmt;
 
@@ -1363,10 +1456,12 @@ static int srp_send_tsk_mgmt(struct srp_target_port *target,
 
 	init_completion(&req->done);
 
-	iu = __srp_get_tx_iu(target, SRP_REQ_TASK_MGMT);
+	iu = __srp_get_tx_iu(target, SRP_IU_TSK_MGMT);
 	if (!iu)
 		goto out;
 
+	ib_dma_sync_single_for_cpu(dev, iu->dma, sizeof *tsk_mgmt,
+				   DMA_TO_DEVICE);
 	tsk_mgmt = iu->buf;
 	memset(tsk_mgmt, 0, sizeof *tsk_mgmt);
 
@@ -1376,6 +1471,8 @@ static int srp_send_tsk_mgmt(struct srp_target_port *target,
 	tsk_mgmt->tsk_mgmt_func = func;
 	tsk_mgmt->task_tag 	= req->index;
 
+	ib_dma_sync_single_for_device(dev, iu->dma, sizeof *tsk_mgmt,
+				      DMA_TO_DEVICE);
 	if (__srp_post_send(target, iu, sizeof *tsk_mgmt))
 		goto out;
 
@@ -1626,9 +1723,9 @@ static struct scsi_host_template srp_template = {
 	.eh_abort_handler		= srp_abort,
 	.eh_device_reset_handler	= srp_reset_device,
 	.eh_host_reset_handler		= srp_reset_host,
-	.can_queue			= SRP_SQ_SIZE,
+	.can_queue			= SRP_CMD_SQ_SIZE,
 	.this_id			= -1,
-	.cmd_per_lun			= SRP_SQ_SIZE,
+	.cmd_per_lun			= SRP_CMD_SQ_SIZE,
 	.use_clustering			= ENABLE_CLUSTERING,
 	.shost_attrs			= srp_host_attrs
 };
@@ -1813,7 +1910,7 @@ static int srp_parse_options(const char *buf, struct srp_target_port *target)
 				printk(KERN_WARNING PFX "bad max cmd_per_lun parameter '%s'\n", p);
 				goto out;
 			}
-			target->scsi_host->cmd_per_lun = min(token, SRP_SQ_SIZE);
+			target->scsi_host->cmd_per_lun = min(token, SRP_CMD_SQ_SIZE);
 			break;
 
 		case SRP_OPT_IO_CLASS:
@@ -1891,7 +1988,7 @@ static ssize_t srp_create_target(struct device *dev,
 
 	INIT_LIST_HEAD(&target->free_reqs);
 	INIT_LIST_HEAD(&target->req_queue);
-	for (i = 0; i < SRP_SQ_SIZE; ++i) {
+	for (i = 0; i < SRP_CMD_SQ_SIZE; ++i) {
 		target->req_ring[i].index = i;
 		list_add_tail(&target->req_ring[i].list, &target->free_reqs);
 	}
@@ -2159,6 +2256,9 @@ static int __init srp_init_module(void)
 {
 	int ret;
 
+	BUILD_BUG_ON_NOT_POWER_OF_2(SRP_SQ_SIZE);
+	BUILD_BUG_ON_NOT_POWER_OF_2(SRP_RQ_SIZE);
+
 	if (srp_sg_tablesize > 255) {
 		printk(KERN_WARNING PFX "Clamping srp_sg_tablesize to 255\n");
 		srp_sg_tablesize = 255;

drivers/infiniband/ulp/srp/ib_srp.h

@@ -59,7 +59,14 @@ enum {
 
 	SRP_RQ_SHIFT    	= 6,
 	SRP_RQ_SIZE		= 1 << SRP_RQ_SHIFT,
-	SRP_SQ_SIZE		= SRP_RQ_SIZE - 1,
+	SRP_RQ_MASK		= SRP_RQ_SIZE - 1,
+
+	SRP_SQ_SIZE		= SRP_RQ_SIZE,
+	SRP_SQ_MASK		= SRP_SQ_SIZE - 1,
+	SRP_RSP_SQ_SIZE		= 1,
+	SRP_REQ_SQ_SIZE		= SRP_SQ_SIZE - SRP_RSP_SQ_SIZE,
+	SRP_TSK_MGMT_SQ_SIZE	= 1,
+	SRP_CMD_SQ_SIZE		= SRP_REQ_SQ_SIZE - SRP_TSK_MGMT_SQ_SIZE,
 
 	SRP_TAG_TSK_MGMT	= 1 << (SRP_RQ_SHIFT + 1),
 
@@ -75,9 +82,10 @@ enum srp_target_state {
 	SRP_TARGET_REMOVED
 };
 
-enum srp_request_type {
-	SRP_REQ_NORMAL,
-	SRP_REQ_TASK_MGMT,
+enum srp_iu_type {
+	SRP_IU_CMD,
+	SRP_IU_TSK_MGMT,
+	SRP_IU_RSP,
 };
 
 struct srp_device {
@@ -144,11 +152,11 @@ struct srp_target_port {
 
 	unsigned		tx_head;
 	unsigned		tx_tail;
-	struct srp_iu	       *tx_ring[SRP_SQ_SIZE + 1];
+	struct srp_iu	       *tx_ring[SRP_SQ_SIZE];
 
 	struct list_head	free_reqs;
 	struct list_head	req_queue;
-	struct srp_request	req_ring[SRP_SQ_SIZE];
+	struct srp_request	req_ring[SRP_CMD_SQ_SIZE];
 
 	struct work_struct	work;
 
@@ -164,6 +172,7 @@ struct srp_iu {
 	void		       *buf;
 	size_t			size;
 	enum dma_data_direction	direction;
+	enum srp_iu_type	type;
 };
 
 #endif /* IB_SRP_H */

drivers/net/mlx4/en_main.c

@@ -124,6 +124,13 @@ static int mlx4_en_get_profile(struct mlx4_en_dev *mdev)
 	return 0;
 }
 
+static void *mlx4_en_get_netdev(struct mlx4_dev *dev, void *ctx, u8 port)
+{
+	struct mlx4_en_dev *endev = ctx;
+
+	return endev->pndev[port];
+}
+
 static void mlx4_en_event(struct mlx4_dev *dev, void *endev_ptr,
 			  enum mlx4_dev_event event, int port)
 {
@@ -282,9 +289,11 @@ err_free_res:
 }
 
 static struct mlx4_interface mlx4_en_interface = {
-	.add	= mlx4_en_add,
-	.remove	= mlx4_en_remove,
-	.event	= mlx4_en_event,
+	.add		= mlx4_en_add,
+	.remove		= mlx4_en_remove,
+	.event		= mlx4_en_event,
+	.get_dev	= mlx4_en_get_netdev,
+	.protocol	= MLX4_PROTOCOL_EN,
 };
 
 static int __init mlx4_en_init(void)

drivers/net/mlx4/en_netdev.c

@@ -69,6 +69,7 @@ static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int err;
+	int idx;
 
 	if (!priv->vlgrp)
 		return;
@@ -83,7 +84,10 @@ static void mlx4_en_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
 		if (err)
 			en_err(priv, "Failed configuring VLAN filter\n");
 	}
+	if (mlx4_register_vlan(mdev->dev, priv->port, vid, &idx))
+		en_err(priv, "failed adding vlan %d\n", vid);
 	mutex_unlock(&mdev->state_lock);
+
 }
 
 static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
@@ -91,6 +95,7 @@ static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 	struct mlx4_en_priv *priv = netdev_priv(dev);
 	struct mlx4_en_dev *mdev = priv->mdev;
 	int err;
+	int idx;
 
 	if (!priv->vlgrp)
 		return;
@@ -101,6 +106,11 @@ static void mlx4_en_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
 
 	/* Remove VID from port VLAN filter */
 	mutex_lock(&mdev->state_lock);
+	if (!mlx4_find_cached_vlan(mdev->dev, priv->port, vid, &idx))
+		mlx4_unregister_vlan(mdev->dev, priv->port, idx);
+	else
+		en_err(priv, "could not find vid %d in cache\n", vid);
+
 	if (mdev->device_up && priv->port_up) {
 		err = mlx4_SET_VLAN_FLTR(mdev->dev, priv->port, priv->vlgrp);
 		if (err)

drivers/net/mlx4/en_port.c

@@ -127,8 +127,8 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
 	memset(context, 0, sizeof *context);
 
 	context->base_qpn = cpu_to_be32(base_qpn);
-	context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_SHIFT | base_qpn);
-	context->mcast = cpu_to_be32(1 << SET_PORT_PROMISC_SHIFT | base_qpn);
+	context->promisc = cpu_to_be32(promisc << SET_PORT_PROMISC_EN_SHIFT | base_qpn);
+	context->mcast = cpu_to_be32(1 << SET_PORT_PROMISC_MODE_SHIFT | base_qpn);
 	context->intra_no_vlan = 0;
 	context->no_vlan = MLX4_NO_VLAN_IDX;
 	context->intra_vlan_miss = 0;

drivers/net/mlx4/en_port.h

@@ -36,7 +36,8 @@
 
 
 #define SET_PORT_GEN_ALL_VALID	0x7
-#define SET_PORT_PROMISC_SHIFT	31
+#define SET_PORT_PROMISC_EN_SHIFT	31
+#define SET_PORT_PROMISC_MODE_SHIFT	30
 
 enum {
 	MLX4_CMD_SET_VLAN_FLTR  = 0x47,

drivers/net/mlx4/fw.c

@@ -98,7 +98,8 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u32 flags)
 		[20] = "Address vector port checking support",
 		[21] = "UD multicast support",
 		[24] = "Demand paging support",
-		[25] = "Router support"
+		[25] = "Router support",
+		[30] = "IBoE support"
 	};
 	int i;
 

drivers/net/mlx4/intf.c

@@ -161,3 +161,24 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
 
 	mutex_unlock(&intf_mutex);
 }
+
+void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+	struct mlx4_device_context *dev_ctx;
+	unsigned long flags;
+	void *result = NULL;
+
+	spin_lock_irqsave(&priv->ctx_lock, flags);
+
+	list_for_each_entry(dev_ctx, &priv->ctx_list, list)
+		if (dev_ctx->intf->protocol == proto && dev_ctx->intf->get_dev) {
+			result = dev_ctx->intf->get_dev(dev, dev_ctx->context, port);
+			break;
+		}
+
+	spin_unlock_irqrestore(&priv->ctx_lock, flags);
+
+	return result;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_protocol_dev);

drivers/net/mlx4/main.c

@@ -103,7 +103,7 @@ MODULE_PARM_DESC(use_prio, "Enable steering by VLAN priority on ETH ports "
 
 static int log_mtts_per_seg = ilog2(MLX4_MTT_ENTRY_PER_SEG);
 module_param_named(log_mtts_per_seg, log_mtts_per_seg, int, 0444);
-MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-5)");
+MODULE_PARM_DESC(log_mtts_per_seg, "Log2 number of MTT entries per segment (1-7)");
 
 int mlx4_check_port_params(struct mlx4_dev *dev,
 			   enum mlx4_port_type *port_type)
@@ -1304,7 +1304,7 @@ static int __init mlx4_verify_params(void)
 		return -1;
 	}
 
-	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 5)) {
+	if ((log_mtts_per_seg < 1) || (log_mtts_per_seg > 7)) {
 		pr_warning("mlx4_core: bad log_mtts_per_seg: %d\n", log_mtts_per_seg);
 		return -1;
 	}

drivers/net/mlx4/mlx4_en.h

@@ -463,6 +463,7 @@ struct mlx4_en_priv {
 	char *mc_addrs;
 	int mc_addrs_cnt;
 	struct mlx4_en_stat_out_mbox hw_stats;
+	int vids[128];
 };
 
 

drivers/net/mlx4/port.c

@@ -182,6 +182,25 @@ static int mlx4_set_port_vlan_table(struct mlx4_dev *dev, u8 port,
 	return err;
 }
 
+int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx)
+{
+	struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;
+	int i;
+
+	for (i = 0; i < MLX4_MAX_VLAN_NUM; ++i) {
+		if (table->refs[i] &&
+		    (vid == (MLX4_VLAN_MASK &
+			      be32_to_cpu(table->entries[i])))) {
+			/* VLAN already registered, increase reference count */
+			*idx = i;
+			return 0;
+		}
+	}
+
+	return -ENOENT;
+}
+EXPORT_SYMBOL_GPL(mlx4_find_cached_vlan);
+
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index)
 {
 	struct mlx4_vlan_table *table = &mlx4_priv(dev)->port[port].vlan_table;

include/linux/mlx4/cmd.h

@@ -57,6 +57,7 @@ enum {
 	MLX4_CMD_QUERY_PORT	 = 0x43,
 	MLX4_CMD_SENSE_PORT	 = 0x4d,
 	MLX4_CMD_SET_PORT	 = 0xc,
+	MLX4_CMD_SET_NODE	 = 0x5a,
 	MLX4_CMD_ACCESS_DDR	 = 0x2e,
 	MLX4_CMD_MAP_ICM	 = 0xffa,
 	MLX4_CMD_UNMAP_ICM	 = 0xff9,
@@ -140,6 +141,7 @@ enum {
 	MLX4_SET_PORT_MAC_TABLE = 0x2,
 	MLX4_SET_PORT_VLAN_TABLE = 0x3,
 	MLX4_SET_PORT_PRIO_MAP  = 0x4,
+	MLX4_SET_PORT_GID_TABLE = 0x5,
 };
 
 struct mlx4_dev;

include/linux/mlx4/device.h

@@ -67,7 +67,8 @@ enum {
 	MLX4_DEV_CAP_FLAG_ATOMIC	= 1 << 18,
 	MLX4_DEV_CAP_FLAG_RAW_MCAST	= 1 << 19,
 	MLX4_DEV_CAP_FLAG_UD_AV_PORT	= 1 << 20,
-	MLX4_DEV_CAP_FLAG_UD_MCAST	= 1 << 21
+	MLX4_DEV_CAP_FLAG_UD_MCAST	= 1 << 21,
+	MLX4_DEV_CAP_FLAG_IBOE		= 1 << 30
 };
 
 enum {
@@ -171,6 +172,10 @@ enum {
 	MLX4_NUM_FEXCH          = 64 * 1024,
 };
 
+enum {
+	MLX4_MAX_FAST_REG_PAGES = 511,
+};
+
 static inline u64 mlx4_fw_ver(u64 major, u64 minor, u64 subminor)
 {
 	return (major << 32) | (minor << 16) | subminor;
@@ -373,6 +378,27 @@ struct mlx4_av {
 	u8			dgid[16];
 };
 
+struct mlx4_eth_av {
+	__be32		port_pd;
+	u8		reserved1;
+	u8		smac_idx;
+	u16		reserved2;
+	u8		reserved3;
+	u8		gid_index;
+	u8		stat_rate;
+	u8		hop_limit;
+	__be32		sl_tclass_flowlabel;
+	u8		dgid[16];
+	u32		reserved4[2];
+	__be16		vlan;
+	u8		mac[6];
+};
+
+union mlx4_ext_av {
+	struct mlx4_av		ib;
+	struct mlx4_eth_av	eth;
+};
+
 struct mlx4_dev {
 	struct pci_dev	       *pdev;
 	unsigned long		flags;
@@ -401,6 +427,12 @@ struct mlx4_init_port_param {
 		if (((type) == MLX4_PORT_TYPE_IB ? (dev)->caps.port_mask : \
 		     ~(dev)->caps.port_mask) & 1 << ((port) - 1))
 
+#define mlx4_foreach_ib_transport_port(port, dev)			\
+	for ((port) = 1; (port) <= (dev)->caps.num_ports; (port)++)	\
+		if (((dev)->caps.port_mask & 1 << ((port) - 1)) ||	\
+		    ((dev)->caps.flags & MLX4_DEV_CAP_FLAG_IBOE))
+
+
 int mlx4_buf_alloc(struct mlx4_dev *dev, int size, int max_direct,
 		   struct mlx4_buf *buf);
 void mlx4_buf_free(struct mlx4_dev *dev, int size, struct mlx4_buf *buf);
@@ -468,6 +500,7 @@ int mlx4_multicast_detach(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16]);
 int mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *index);
 void mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, int index);
 
+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, int index);
 

include/linux/mlx4/driver.h

@@ -44,15 +44,24 @@ enum mlx4_dev_event {
 	MLX4_DEV_EVENT_PORT_REINIT,
 };
 
+enum mlx4_protocol {
+	MLX4_PROTOCOL_IB,
+	MLX4_PROTOCOL_EN,
+};
+
 struct mlx4_interface {
 	void *			(*add)	 (struct mlx4_dev *dev);
 	void			(*remove)(struct mlx4_dev *dev, void *context);
 	void			(*event) (struct mlx4_dev *dev, void *context,
 					  enum mlx4_dev_event event, int port);
+	void *			(*get_dev)(struct mlx4_dev *dev, void *context, u8 port);
 	struct list_head	list;
+	enum mlx4_protocol	protocol;
 };
 
 int mlx4_register_interface(struct mlx4_interface *intf);
 void mlx4_unregister_interface(struct mlx4_interface *intf);
 
+void *mlx4_get_protocol_dev(struct mlx4_dev *dev, enum mlx4_protocol proto, int port);
+
 #endif /* MLX4_DRIVER_H */

include/linux/mlx4/qp.h

@@ -109,10 +109,11 @@ struct mlx4_qp_path {
 	__be32			tclass_flowlabel;
 	u8			rgid[16];
 	u8			sched_queue;
-	u8			snooper_flags;
+	u8			vlan_index;
 	u8			reserved3[2];
 	u8			counter_index;
-	u8			reserved4[7];
+	u8			reserved4;
+	u8			dmac[6];
 };
 
 struct mlx4_qp_context {
@@ -166,6 +167,7 @@ enum {
 	MLX4_WQE_CTRL_TCP_UDP_CSUM	= 1 << 5,
 	MLX4_WQE_CTRL_INS_VLAN		= 1 << 6,
 	MLX4_WQE_CTRL_STRONG_ORDER	= 1 << 7,
+	MLX4_WQE_CTRL_FORCE_LOOPBACK	= 1 << 0,
 };
 
 struct mlx4_wqe_ctrl_seg {
@@ -219,7 +221,8 @@ struct mlx4_wqe_datagram_seg {
 	__be32			av[8];
 	__be32			dqpn;
 	__be32			qkey;
-	__be32			reservd[2];
+	__be16			vlan;
+	u8			mac[6];
 };
 
 struct mlx4_wqe_lso_seg {

include/rdma/ib_addr.h

@@ -39,7 +39,9 @@
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
 #include <linux/socket.h>
+#include <linux/if_vlan.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_pack.h>
 
 struct rdma_addr_client {
 	atomic_t refcount;
@@ -63,6 +65,7 @@ struct rdma_dev_addr {
 	unsigned char broadcast[MAX_ADDR_LEN];
 	unsigned short dev_type;
 	int bound_dev_if;
+	enum rdma_transport_type transport;
 };
 
 /**
@@ -127,9 +130,51 @@ 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 void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
+				      union ib_gid *gid)
+{
+	struct net_device *dev;
+	u16 vid = 0xffff;
+
+	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+	if (dev) {
+		vid = rdma_vlan_dev_vlan_id(dev);
+		dev_put(dev);
+	}
+
+	iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid);
+}
+
 static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
 {
-	memcpy(gid, dev_addr->src_dev_addr + rdma_addr_gid_offset(dev_addr), sizeof *gid);
+	if (dev_addr->transport == RDMA_TRANSPORT_IB &&
+	    dev_addr->dev_type != ARPHRD_INFINIBAND)
+		iboe_addr_get_sgid(dev_addr, gid);
+	else
+		memcpy(gid, dev_addr->src_dev_addr +
+		       rdma_addr_gid_offset(dev_addr), sizeof *gid);
 }
 
 static inline void rdma_addr_set_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
@@ -147,4 +192,91 @@ static inline void rdma_addr_set_dgid(struct rdma_dev_addr *dev_addr, union ib_g
 	memcpy(dev_addr->dst_dev_addr + rdma_addr_gid_offset(dev_addr), gid, sizeof *gid);
 }
 
+static inline enum ib_mtu iboe_get_mtu(int mtu)
+{
+	/*
+	 * reduce IB headers from effective IBoE MTU. 28 stands for
+	 * atomic header which is the biggest possible header after BTH
+	 */
+	mtu = mtu - IB_GRH_BYTES - IB_BTH_BYTES - 28;
+
+	if (mtu >= ib_mtu_enum_to_int(IB_MTU_4096))
+		return IB_MTU_4096;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_2048))
+		return IB_MTU_2048;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_1024))
+		return IB_MTU_1024;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_512))
+		return IB_MTU_512;
+	else if (mtu >= ib_mtu_enum_to_int(IB_MTU_256))
+		return IB_MTU_256;
+	else
+		return 0;
+}
+
+static inline int iboe_get_rate(struct net_device *dev)
+{
+	struct ethtool_cmd cmd;
+
+	if (!dev->ethtool_ops || !dev->ethtool_ops->get_settings ||
+	    dev->ethtool_ops->get_settings(dev, &cmd))
+		return IB_RATE_PORT_CURRENT;
+
+	if (cmd.speed >= 40000)
+		return IB_RATE_40_GBPS;
+	else if (cmd.speed >= 30000)
+		return IB_RATE_30_GBPS;
+	else if (cmd.speed >= 20000)
+		return IB_RATE_20_GBPS;
+	else if (cmd.speed >= 10000)
+		return IB_RATE_10_GBPS;
+	else
+		return IB_RATE_PORT_CURRENT;
+}
+
+static inline int rdma_link_local_addr(struct in6_addr *addr)
+{
+	if (addr->s6_addr32[0] == htonl(0xfe800000) &&
+	    addr->s6_addr32[1] == 0)
+		return 1;
+
+	return 0;
+}
+
+static inline void rdma_get_ll_mac(struct in6_addr *addr, u8 *mac)
+{
+	memcpy(mac, &addr->s6_addr[8], 3);
+	memcpy(mac + 3, &addr->s6_addr[13], 3);
+	mac[0] ^= 2;
+}
+
+static inline int rdma_is_multicast_addr(struct in6_addr *addr)
+{
+	return addr->s6_addr[0] == 0xff;
+}
+
+static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
+{
+	int i;
+
+	mac[0] = 0x33;
+	mac[1] = 0x33;
+	for (i = 2; i < 6; ++i)
+		mac[i] = addr->s6_addr[i + 10];
+}
+
+static inline u16 rdma_get_vlan_id(union ib_gid *dgid)
+{
+	u16 vid;
+
+	vid = dgid->raw[11] << 8 | dgid->raw[12];
+	return vid < 0x1000 ? vid : 0xffff;
+}
+
+static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_802_1Q_VLAN ?
+		vlan_dev_real_dev(dev) : 0;
+}
+
 #endif /* IB_ADDR_H */

include/rdma/ib_pack.h

@@ -37,6 +37,8 @@
 
 enum {
 	IB_LRH_BYTES  = 8,
+	IB_ETH_BYTES  = 14,
+	IB_VLAN_BYTES = 4,
 	IB_GRH_BYTES  = 40,
 	IB_BTH_BYTES  = 12,
 	IB_DETH_BYTES = 8
@@ -210,14 +212,32 @@ struct ib_unpacked_deth {
 	__be32       source_qpn;
 };
 
+struct ib_unpacked_eth {
+	u8	dmac_h[4];
+	u8	dmac_l[2];
+	u8	smac_h[2];
+	u8	smac_l[4];
+	__be16	type;
+};
+
+struct ib_unpacked_vlan {
+	__be16  tag;
+	__be16  type;
+};
+
 struct ib_ud_header {
+	int                     lrh_present;
 	struct ib_unpacked_lrh  lrh;
-	int                     grh_present;
-	struct ib_unpacked_grh  grh;
-	struct ib_unpacked_bth  bth;
+	int			eth_present;
+	struct ib_unpacked_eth	eth;
+	int                     vlan_present;
+	struct ib_unpacked_vlan vlan;
+	int			grh_present;
+	struct ib_unpacked_grh	grh;
+	struct ib_unpacked_bth	bth;
 	struct ib_unpacked_deth deth;
-	int            		immediate_present;
-	__be32         		immediate_data;
+	int			immediate_present;
+	__be32			immediate_data;
 };
 
 void ib_pack(const struct ib_field        *desc,
@@ -230,9 +250,12 @@ void ib_unpack(const struct ib_field        *desc,
 	       void                         *buf,
 	       void                         *structure);
 
-void ib_ud_header_init(int     		   payload_bytes,
-		       int    		   grh_present,
-		       int		   immediate_present,
+void ib_ud_header_init(int		    payload_bytes,
+		       int		    lrh_present,
+		       int		    eth_present,
+		       int		    vlan_present,
+		       int		    grh_present,
+		       int		    immediate_present,
 		       struct ib_ud_header *header);
 
 int ib_ud_header_pack(struct ib_ud_header *header,

include/rdma/ib_user_verbs.h

@@ -205,7 +205,8 @@ struct ib_uverbs_query_port_resp {
 	__u8  active_width;
 	__u8  active_speed;
 	__u8  phys_state;
-	__u8  reserved[3];
+	__u8  link_layer;
+	__u8  reserved[2];
 };
 
 struct ib_uverbs_alloc_pd {

include/rdma/ib_verbs.h

@@ -75,6 +75,12 @@ enum rdma_transport_type {
 enum rdma_transport_type
 rdma_node_get_transport(enum rdma_node_type node_type) __attribute_const__;
 
+enum rdma_link_layer {
+	IB_LINK_LAYER_UNSPECIFIED,
+	IB_LINK_LAYER_INFINIBAND,
+	IB_LINK_LAYER_ETHERNET,
+};
+
 enum ib_device_cap_flags {
 	IB_DEVICE_RESIZE_MAX_WR		= 1,
 	IB_DEVICE_BAD_PKEY_CNTR		= (1<<1),
@@ -1010,6 +1016,8 @@ struct ib_device {
 	int		           (*query_port)(struct ib_device *device,
 						 u8 port_num,
 						 struct ib_port_attr *port_attr);
+	enum rdma_link_layer	   (*get_link_layer)(struct ib_device *device,
+						     u8 port_num);
 	int		           (*query_gid)(struct ib_device *device,
 						u8 port_num, int index,
 						union ib_gid *gid);
@@ -1222,6 +1230,9 @@ int ib_query_device(struct ib_device *device,
 int ib_query_port(struct ib_device *device,
 		  u8 port_num, struct ib_port_attr *port_attr);
 
+enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
+					       u8 port_num);
+
 int ib_query_gid(struct ib_device *device,
 		 u8 port_num, int index, union ib_gid *gid);
 

include/scsi/srp.h

@@ -239,4 +239,42 @@ struct srp_rsp {
 	u8	data[0];
 } __attribute__((packed));
 
+struct srp_cred_req {
+	u8	opcode;
+	u8	sol_not;
+	u8	reserved[2];
+	__be32	req_lim_delta;
+	u64	tag;
+};
+
+struct srp_cred_rsp {
+	u8	opcode;
+	u8	reserved[7];
+	u64	tag;
+};
+
+/*
+ * The SRP spec defines the fixed portion of the AER_REQ structure to be
+ * 36 bytes, so it needs to be packed to avoid having it padded to 40 bytes
+ * on 64-bit architectures.
+ */
+struct srp_aer_req {
+	u8	opcode;
+	u8	sol_not;
+	u8	reserved[2];
+	__be32	req_lim_delta;
+	u64	tag;
+	u32	reserved2;
+	__be64	lun;
+	__be32	sense_data_len;
+	u32	reserved3;
+	u8	sense_data[0];
+} __attribute__((packed));
+
+struct srp_aer_rsp {
+	u8	opcode;
+	u8	reserved[7];
+	u64	tag;
+};
+
 #endif /* SCSI_SRP_H */