From a3f5adaf491490089215f863a61b9422fae902f8 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.co.il>
Date: Mon, 27 Sep 2010 17:51:10 -0700
Subject: IB/core: Add link layer property to ports

This patch allows ports to have different link layers:
IB_LINK_LAYER_INFINIBAND or IB_LINK_LAYER_ETHERNET.  This is required
for adding IBoE (InfiniBand-over-Ethernet, aka RoCE) support.  For
devices that do not provide an implementation for querying the link
layer property of a port, we return a default value based on the
transport: RMA_TRANSPORT_IB nodes will return IB_LINK_LAYER_INFINIBAND
and RDMA_TRANSPORT_IWARP nodes will return IB_LINK_LAYER_ETHERNET.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/verbs.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/verbs.c b/drivers/infiniband/core/verbs.c
index e0fa22238715..af7a8b08b2e9 100644
--- a/drivers/infiniband/core/verbs.c
+++ b/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)
-- 
cgit v1.2.3-59-g8ed1b


From 557d0540b96176dc42943e84c88c288f523388ca Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 7 Sep 2010 14:33:31 +0000
Subject: IB/umad: Make user_mad semaphore a real one

Get rid of init_MUTEX[_LOCKED]() and use sema_init() instead.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/user_mad.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/user_mad.c b/drivers/infiniband/core/user_mad.c
index 5fa856909511..cd1996d0ad08 100644
--- a/drivers/infiniband/core/user_mad.c
+++ b/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);
 
-- 
cgit v1.2.3-59-g8ed1b


From 26012f0750dd73348b0a0a680a4bee2715d4a334 Mon Sep 17 00:00:00 2001
From: Animesh K Trivedi <ATR@zurich.ibm.com>
Date: Tue, 28 Sep 2010 14:44:02 +0000
Subject: RDMA/iwcm: Fix hang in uninterruptible wait on cm_id destroy

A process can get stuck in an uninterruptible wait in the
kernel while destroying a cm_id when iw_cm_connect() fails:

For example, When creation of a PD fails but the user continues with
an attempt to connect to the server without checking the return value,
in iw_cm_connect() a NULL qp is found so the call fails.  However the
IWCM_F_CONNECT_WAIT bit is not cleared.  destroy_cm_id() then waits
forever for IWCM_F_CONNECT_WAIT to be cleared.

The same problem exists on the passive side with the accept call.

Fix this by clearing the bit and waking up any waiters in the
appropriate spots.

Signed-off-by: Animesh Trivedi <atr@zurich.ibm.com>
Acked-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/iwcm.c | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
index bfead5bc25f6..2a1e9ae134b4 100644
--- a/drivers/infiniband/core/iwcm.c
+++ b/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);
-- 
cgit v1.2.3-59-g8ed1b


From fac70d51914674ce8ae742ed73441ddb4770ad20 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.co.il>
Date: Mon, 27 Sep 2010 17:51:11 -0700
Subject: IB/mad: IBoE supports only QP1 (no QP0)

Since IBoE is using Ethernet as its link layer, there is no central
management entity so there is need for QP0.  QP1 is still needed since
it handles communications between CM agents.  This patch will skip QP0
and create only QP1 for IBoE ports.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/agent.c     | 29 +++++++++++++++++------------
 drivers/infiniband/core/mad.c       | 27 +++++++++++++++++++++++----
 drivers/infiniband/core/multicast.c | 23 ++++++++++++++++++++---
 drivers/infiniband/core/sa_query.c  | 25 ++++++++++++++++++-------
 4 files changed, 78 insertions(+), 26 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/agent.c b/drivers/infiniband/core/agent.c
index ae7c2880e624..91916a8d5de4 100644
--- a/drivers/infiniband/core/agent.c
+++ b/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;
 }
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index ef1304f151dc..822cfdcd9f78 100644
--- a/drivers/infiniband/core/mad.c
+++ b/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;
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index a519801dcfb7..68b4162fd9d2 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/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);
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 7e1ffd8ccd5c..27674c790a73 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/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);
@@ -1007,7 +1010,7 @@ 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 +1020,12 @@ 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 +1051,15 @@ 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 +1079,12 @@ 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);
-- 
cgit v1.2.3-59-g8ed1b


From 3c86aa70bf677a31b71c8292e349242e26cbc743 Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Wed, 13 Oct 2010 21:26:51 +0200
Subject: RDMA/cm: Add RDMA CM support for IBoE devices

Add support for IBoE device binding and IP --> GID resolution.  Path
resolving and multicast joining are implemented within cma.c by
filling in the responses and running callbacks in the CMA work queue.

IP --> GID resolution always yields IPv6 link local addresses; remote
GIDs are derived from the destination MAC address of the remote port.
Multicast GIDs are always mapped to multicast MACs as is done in IPv6.
(IPv4 multicast is enabled by translating IPv4 multicast addresses to
IPv6 multicast as described in
<http://www.mail-archive.com/ipng@sunroof.eng.sun.com/msg02134.html>.)

Some helper functions are added to ib_addr.h.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/cma.c      | 309 ++++++++++++++++++++++++++++++++++---
 drivers/infiniband/core/sa_query.c |   5 +-
 drivers/infiniband/core/ucma.c     |  45 +++++-
 include/rdma/ib_addr.h             |  99 +++++++++++-
 4 files changed, 431 insertions(+), 27 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index b930b8110a63..f61bc0738488 100644
--- a/drivers/infiniband/core/cma.c
+++ b/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 +1782,77 @@ 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;
+
+	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;
+
+	iboe_mac_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr);
+	iboe_mac_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr);
+
+	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;
+
+	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;
+	}
+
+	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 +1865,16 @@ 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 +1927,7 @@ 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 +2912,102 @@ 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 +3034,17 @@ 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 +3077,19 @@ 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;
 		}
 	}
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 27674c790a73..91a660310b7c 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -496,6 +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);
@@ -505,7 +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;
 
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index ac7edc24165c..3d3c9264c450 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -583,6 +583,34 @@ 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;
+
+	resp->num_paths = route->num_paths;
+	switch (route->num_paths) {
+	case 0:
+		dev_addr = &route->addr.dev_addr;
+		iboe_mac_to_ll((union ib_gid *) &resp->ib_route[0].dgid,
+			       dev_addr->dst_dev_addr);
+		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 +645,17 @@ 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:
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index fa0d52b8e622..904ffa92fc93 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -40,6 +40,7 @@
 #include <linux/netdevice.h>
 #include <linux/socket.h>
 #include <rdma/ib_verbs.h>
+#include <rdma/ib_pack.h>
 
 struct rdma_addr_client {
 	atomic_t refcount;
@@ -63,6 +64,7 @@ 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 +129,31 @@ 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_to_ll(union ib_gid *gid, u8 *mac)
+{
+	memset(gid->raw, 0, 16);
+	*((__be32 *) gid->raw) = cpu_to_be32(0xfe800000);
+	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 void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
+				      union ib_gid *gid)
+{
+	iboe_mac_to_ll(gid, dev_addr->src_dev_addr);
+}
+
 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 +171,77 @@ 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];
+}
+
 #endif /* IB_ADDR_H */
-- 
cgit v1.2.3-59-g8ed1b


From ff7f5aab354dee01f29c9c00933f6d4aa590eadb Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Thu, 26 Aug 2010 14:17:56 +0000
Subject: IB/pack: IBoE UD packet packing support

Add support for packing IBoE packet headers.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>

[ Clean up and fix ib_ud_header_init() a bit.  - Roland ]

Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/ud_header.c    | 117 +++++++++++++++++++++++++--------
 drivers/infiniband/hw/mlx4/qp.c        |   2 +-
 drivers/infiniband/hw/mthca/mthca_qp.c |   2 +-
 include/rdma/ib_pack.h                 |  30 ++++++---
 4 files changed, 113 insertions(+), 38 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/ud_header.c b/drivers/infiniband/core/ud_header.c
index 650b501eb142..cb0dd5ae2777 100644
--- a/drivers/infiniband/core/ud_header.c
+++ b/drivers/infiniband/core/ud_header.c
@@ -80,6 +80,29 @@ 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 grh_table[]  = {
 	{ STRUCT_FIELD(grh, ip_version),
 	  .offset_words = 0,
@@ -180,38 +203,38 @@ 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
  * @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    		    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 (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 +245,50 @@ 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->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 +302,16 @@ 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->grh_present) {
 		ib_pack(grh_table, ARRAY_SIZE(grh_table),
 			&header->grh, buf + len);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 6a60827b2301..bb1277c8fbf0 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1231,7 +1231,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 	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);
+	ib_ud_header_init(send_size, 1, 0, mlx4_ib_ah_grh_present(ah), 0, &sqp->ud_header);
 
 	sqp->ud_header.lrh.service_level   =
 		be32_to_cpu(ah->av.sl_tclass_flowlabel) >> 28;
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index d2d172e6289c..1a1c55fb13f3 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/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,
 			  mthca_ah_grh_present(to_mah(wr->wr.ud.ah)), 0,
 			  &sqp->ud_header);
 
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index cbb50f4da3dd..6b91d8e7a1fa 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -37,6 +37,7 @@
 
 enum {
 	IB_LRH_BYTES  = 8,
+	IB_ETH_BYTES  = 14,
 	IB_GRH_BYTES  = 40,
 	IB_BTH_BYTES  = 12,
 	IB_DETH_BYTES = 8
@@ -210,14 +211,25 @@ 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_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			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 +242,11 @@ 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		    grh_present,
+		       int		    immediate_present,
 		       struct ib_ud_header *header);
 
 int ib_ud_header_pack(struct ib_ud_header *header,
-- 
cgit v1.2.3-59-g8ed1b


From 97cb7e40c69618ba03030b467faf60dc3ee982ee Mon Sep 17 00:00:00 2001
From: Steve Wise <swise@opengridcomputing.com>
Date: Fri, 13 Aug 2010 20:56:34 +0000
Subject: RDMA/ucma: Allow tuning the max listen backlog

For iWARP connections, the connect request is carried in a TCP payload
on an already established TCP connection.  So if the ucma's backlog is
full, the connection request is transmitted and acked at the TCP level
by the time the connect request gets dropped in the ucma.  The end
result is the connection gets rejected by the iWARP provider.
Further, a 32 node 256NP OpenMPI job will generate > 128 connect
requests on some ranks.

This patch increases the default max backlog to 1024, and adds a
sysctl variable so the backlog can be adjusted at run time.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/ucma.c | 39 +++++++++++++++++++++++++++++++++------
 1 file changed, 33 insertions(+), 6 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index ac7edc24165c..b2748a673989 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/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 {
@@ -686,8 +703,8 @@ 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 +1296,26 @@ 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);
-- 
cgit v1.2.3-59-g8ed1b


From 2420b60b1dc4ed98cb1788e928bc57ff2efa1a8d Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.co.il>
Date: Mon, 18 Oct 2010 14:45:20 -0700
Subject: IB/uverbs: Return link layer type to userspace for query port
 operation

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/uverbs_cmd.c | 2 ++
 include/rdma/ib_user_verbs.h         | 3 ++-
 2 files changed, 4 insertions(+), 1 deletion(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index 6fcfbeb24a23..b342248aec05 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/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))
diff --git a/include/rdma/ib_user_verbs.h b/include/rdma/ib_user_verbs.h
index a17f77106149..fe5b05177a2c 100644
--- a/include/rdma/ib_user_verbs.h
+++ b/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 {
-- 
cgit v1.2.3-59-g8ed1b


From af7bd463761c6abd8ca8d831f9cc0ac19f3b7d4b Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@dev.mellanox.co.il>
Date: Thu, 26 Aug 2010 17:18:59 +0300
Subject: IB/core: Add VLAN support for IBoE

Add 802.1q VLAN support to IBoE. The VLAN tag is encoded within the
GID derived from a link local address in the following way:

    GID[11] GID[12] contain the VLAN ID when the GID contains a VLAN.

The 3 bits user priority field of the packets are identical to the 3
bits of the SL.

In case of rdma_cm apps, the TOS field is used to generate the SL
field by doing a shift right of 5 bits effectively taking to 3 MS bits
of the TOS field.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/cma.c          | 20 +++++++++-------
 drivers/infiniband/core/ucma.c         | 12 ++++++++--
 drivers/infiniband/core/ud_header.c    | 23 ++++++++++++++++++
 drivers/infiniband/hw/mlx4/qp.c        |  2 +-
 drivers/infiniband/hw/mthca/mthca_qp.c |  2 +-
 include/rdma/ib_addr.h                 | 43 ++++++++++++++++++++++++++++++----
 include/rdma/ib_pack.h                 |  9 +++++++
 7 files changed, 95 insertions(+), 16 deletions(-)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index f61bc0738488..6884da24fde1 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -1791,6 +1791,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	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;
@@ -1810,14 +1811,6 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 
 	route->num_paths = 1;
 
-	iboe_mac_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr);
-	iboe_mac_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr);
-
-	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;
-
 	if (addr->dev_addr.bound_dev_if)
 		ndev = dev_get_by_index(&init_net, addr->dev_addr.bound_dev_if);
 	if (!ndev) {
@@ -1825,6 +1818,17 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 		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);
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 3d3c9264c450..357a766bd220 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -587,13 +587,21 @@ 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;
-		iboe_mac_to_ll((union ib_gid *) &resp->ib_route[0].dgid,
-			       dev_addr->dst_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);
diff --git a/drivers/infiniband/core/ud_header.c b/drivers/infiniband/core/ud_header.c
index cb0dd5ae2777..bb7e19280821 100644
--- a/drivers/infiniband/core/ud_header.c
+++ b/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>
 
@@ -103,6 +104,17 @@ static const struct ib_field eth_table[]  = {
 	  .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,
@@ -205,6 +217,7 @@ static const struct ib_field deth_table[] = {
  * @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 is present
  * @header:Structure to initialize
@@ -212,6 +225,7 @@ static const struct ib_field deth_table[] = {
 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)
@@ -234,6 +248,9 @@ void ib_ud_header_init(int     		    payload_bytes,
 		header->lrh.packet_length = cpu_to_be16(packet_length);
 	}
 
+	if (vlan_present)
+		header->eth.type = cpu_to_be16(ETH_P_8021Q);
+
 	if (grh_present) {
 		header->grh.ip_version      = 6;
 		header->grh.payload_length  =
@@ -254,6 +271,7 @@ void ib_ud_header_init(int     		    payload_bytes,
 
 	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;
 }
@@ -312,6 +330,11 @@ int ib_ud_header_pack(struct ib_ud_header *header,
 			&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);
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 17f60fe6e5b6..269648445113 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -1291,7 +1291,7 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 
 	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);
-	ib_ud_header_init(send_size, !is_eth, is_eth, is_grh, 0, &sqp->ud_header);
+	ib_ud_header_init(send_size, !is_eth, is_eth, 0, is_grh, 0, &sqp->ud_header);
 
 	if (!is_eth) {
 		sqp->ud_header.lrh.service_level =
diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 1a1c55fb13f3..a34c9d38e822 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/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 */ 1, 0,
+	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);
 
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index 904ffa92fc93..b5fc9f39122b 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -39,6 +39,7 @@
 #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>
 
@@ -129,21 +130,41 @@ 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_to_ll(union ib_gid *gid, u8 *mac)
+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);
-	gid->raw[12] = 0xfe;
-	gid->raw[11] = 0xff;
+	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)
 {
-	iboe_mac_to_ll(gid, dev_addr->src_dev_addr);
+	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)
@@ -244,4 +265,18 @@ static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
 		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 */
diff --git a/include/rdma/ib_pack.h b/include/rdma/ib_pack.h
index 6b91d8e7a1fa..b37fe3b10a9d 100644
--- a/include/rdma/ib_pack.h
+++ b/include/rdma/ib_pack.h
@@ -38,6 +38,7 @@
 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
@@ -219,11 +220,18 @@ struct ib_unpacked_eth {
 	__be16	type;
 };
 
+struct ib_unpacked_vlan {
+	__be16  tag;
+	__be16  type;
+};
+
 struct ib_ud_header {
 	int                     lrh_present;
 	struct ib_unpacked_lrh  lrh;
 	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;
@@ -245,6 +253,7 @@ void ib_unpack(const struct ib_field        *desc,
 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);
-- 
cgit v1.2.3-59-g8ed1b


From 8ad330a002ffbc422f32a77398666832f0df8a3d Mon Sep 17 00:00:00 2001
From: Eli Cohen <eli@mellanox.co.il>
Date: Fri, 22 Oct 2010 14:32:05 +0200
Subject: IB/core: Add link layer type information to sysfs

Since an IB transport port may use either IB or Ethernet as its link layer,
add the file /sys/class/infiniband/<device>/ports/<port_num>/link_layer to
show the link layer for the port.

Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
---
 drivers/infiniband/core/sysfs.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'drivers/infiniband/core')

diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 3627300e2a10..9ab5df72df7b 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/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
 };
 
-- 
cgit v1.2.3-59-g8ed1b