Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull infiniband updates from Roland Dreier:
 "Main batch of InfiniBand/RDMA changes for 3.14:
   - Flow steering for InfiniBand UD traffic
   - IP-based addressing for IBoE aka RoCE
   - Pass SRP submaintainership from Dave to Bart
   - SRP transport fixes from Bart
   - Add the new Cisco usNIC low-level device driver
   - Various other fixes"

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (75 commits)
  IB/mlx5: Verify reserved fields are cleared
  IB/mlx5: Remove old field for create mkey mailbox
  IB/mlx5: Abort driver cleanup if teardown hca fails
  IB/mlx5: Allow creation of QPs with zero-length work queues
  mlx5_core: Fix PowerPC support
  mlx5_core: Improve debugfs readability
  IB/mlx5: Add support for resize CQ
  IB/mlx5: Implement modify CQ
  IB/mlx5: Make sure doorbell record is visible before doorbell
  mlx5_core: Use mlx5 core style warning
  IB/mlx5: Clear out struct before create QP command
  mlx5_core: Fix out arg size in access_register command
  RDMA/nes: Slight optimization of Ethernet address compare
  IB/qib: Fix QP check when looping back to/from QP1
  RDMA/cxgb4: Fix gcc warning on 32-bit arch
  IB/usnic: Remove unused includes of <linux/version.h>
  RDMA/amso1100: Add check if cache memory was allocated before freeing it
  IPoIB: Report operstate consistently when brought up without a link
  IB/core: Fix unused variable warning
  RDMA/cma: Handle global/non-linklocal IPv6 addresses in cma_check_linklocal()
  ...

Documentation/scsi/scsi_transport_srp/Makefile

@@ -0,0 +1,7 @@
+all: rport_state_diagram.svg rport_state_diagram.png
+
+rport_state_diagram.svg: rport_state_diagram.dot
+	dot -Tsvg -o $@ $<
+
+rport_state_diagram.png: rport_state_diagram.dot
+	dot -Tpng -o $@ $<

Documentation/scsi/scsi_transport_srp/rport_state_diagram.dot

@@ -0,0 +1,26 @@
+digraph srp_initiator {
+	node [shape = doublecircle]; running lost;
+	node [shape = circle];
+
+	{
+	  rank = min;
+	  running_rta	[ label = "running;\nreconnect\ntimer\nactive" ];
+	};
+	running		[ label = "running;\nreconnect\ntimer\nstopped" ];
+	blocked;
+	failfast	[ label = "fail I/O\nfast" ];
+	lost;
+
+	running -> running_rta		[ label = "fast_io_fail_tmo = off and\ndev_loss_tmo = off;\nsrp_start_tl_fail_timers()" ];
+	running_rta -> running		[ label = "fast_io_fail_tmo = off and\ndev_loss_tmo = off;\nreconnecting succeeded" ];
+	running -> blocked		[ label = "fast_io_fail_tmo >= 0 or\ndev_loss_tmo >= 0;\nsrp_start_tl_fail_timers()" ];
+	running -> failfast		[ label = "fast_io_fail_tmo = off and\ndev_loss_tmo = off;\nreconnecting failed\n" ];
+	blocked -> failfast		[ label = "fast_io_fail_tmo\nexpired or\nreconnecting\nfailed" ];
+	blocked -> lost			[ label = "dev_loss_tmo\nexpired or\nsrp_stop_rport_timers()" ];
+	failfast -> lost		[ label = "dev_loss_tmo\nexpired or\nsrp_stop_rport_timers()" ];
+	blocked -> running		[ label = "reconnecting\nsucceeded" ];
+	failfast -> failfast		[ label = "reconnecting\nfailed" ];
+	failfast -> running		[ label = "reconnecting\nsucceeded" ];
+	running -> lost			[ label = "srp_stop_rport_timers()" ];
+	running_rta -> lost		[ label = "srp_stop_rport_timers()" ];
+}

MAINTAINERS

@@ -2195,6 +2195,11 @@ M:	Nishank Trivedi <nistrive@cisco.com>
 S:	Supported
 F:	drivers/net/ethernet/cisco/enic/
 
+CISCO VIC LOW LATENCY NIC DRIVER
+M:      Upinder Malhi <umalhi@cisco.com>
+S:      Supported
+F:      drivers/infiniband/hw/usnic
+
 CIRRUS LOGIC EP93XX ETHERNET DRIVER
 M:	Hartley Sweeten <hsweeten@visionengravers.com>
 L:	netdev@vger.kernel.org
@@ -7528,7 +7533,7 @@ S:	Maintained
 F:	drivers/scsi/sr*
 
 SCSI RDMA PROTOCOL (SRP) INITIATOR
-M:	David Dillow <dillowda@ornl.gov>
+M:	Bart Van Assche <bvanassche@acm.org>
 L:	linux-rdma@vger.kernel.org
 S:	Supported
 W:	http://www.openfabrics.org

drivers/infiniband/Kconfig

@@ -3,6 +3,8 @@ menuconfig INFINIBAND
 	depends on PCI || BROKEN
 	depends on HAS_IOMEM
 	depends on NET
+	depends on INET
+	depends on m || IPV6 != m
 	---help---
 	  Core support for InfiniBand (IB).  Make sure to also select
 	  any protocols you wish to use as well as drivers for your
@@ -38,8 +40,7 @@ config INFINIBAND_USER_MEM
 
 config INFINIBAND_ADDR_TRANS
 	bool
-	depends on INET
-	depends on !(INFINIBAND = y && IPV6 = m)
+	depends on INFINIBAND
 	default y
 
 source "drivers/infiniband/hw/mthca/Kconfig"
@@ -53,6 +54,7 @@ source "drivers/infiniband/hw/mlx4/Kconfig"
 source "drivers/infiniband/hw/mlx5/Kconfig"
 source "drivers/infiniband/hw/nes/Kconfig"
 source "drivers/infiniband/hw/ocrdma/Kconfig"
+source "drivers/infiniband/hw/usnic/Kconfig"
 
 source "drivers/infiniband/ulp/ipoib/Kconfig"
 

drivers/infiniband/Makefile

@@ -10,6 +10,7 @@ obj-$(CONFIG_MLX4_INFINIBAND)		+= hw/mlx4/
 obj-$(CONFIG_MLX5_INFINIBAND)		+= hw/mlx5/
 obj-$(CONFIG_INFINIBAND_NES)		+= hw/nes/
 obj-$(CONFIG_INFINIBAND_OCRDMA)		+= hw/ocrdma/
+obj-$(CONFIG_INFINIBAND_USNIC)		+= hw/usnic/
 obj-$(CONFIG_INFINIBAND_IPOIB)		+= ulp/ipoib/
 obj-$(CONFIG_INFINIBAND_SRP)		+= ulp/srp/
 obj-$(CONFIG_INFINIBAND_SRPT)		+= ulp/srpt/

drivers/infiniband/core/Makefile

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

drivers/infiniband/core/addr.c

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

drivers/infiniband/core/cm.c

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

drivers/infiniband/core/cma.c

@@ -340,7 +340,7 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a
 	int ret;
 
 	if (addr->sa_family != AF_IB) {
-		ret = rdma_translate_ip(addr, dev_addr);
+		ret = rdma_translate_ip(addr, dev_addr, NULL);
 	} else {
 		cma_translate_ib((struct sockaddr_ib *) addr, dev_addr);
 		ret = 0;
@@ -365,7 +365,9 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv,
 		return -EINVAL;
 
 	mutex_lock(&lock);
-	iboe_addr_get_sgid(dev_addr, &iboe_gid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+		    &iboe_gid);
+
 	memcpy(&gid, dev_addr->src_dev_addr +
 	       rdma_addr_gid_offset(dev_addr), sizeof gid);
 	if (listen_id_priv &&
@@ -603,6 +605,7 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 {
 	struct ib_qp_attr qp_attr;
 	int qp_attr_mask, ret;
+	union ib_gid sgid;
 
 	mutex_lock(&id_priv->qp_mutex);
 	if (!id_priv->id.qp) {
@@ -625,6 +628,20 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 	if (ret)
 		goto out;
 
+	ret = ib_query_gid(id_priv->id.device, id_priv->id.port_num,
+			   qp_attr.ah_attr.grh.sgid_index, &sgid);
+	if (ret)
+		goto out;
+
+	if (rdma_node_get_transport(id_priv->cma_dev->device->node_type)
+	    == RDMA_TRANSPORT_IB &&
+	    rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
+	    == IB_LINK_LAYER_ETHERNET) {
+		ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
+
+		if (ret)
+			goto out;
+	}
 	if (conn_param)
 		qp_attr.max_dest_rd_atomic = conn_param->responder_resources;
 	ret = ib_modify_qp(id_priv->id.qp, &qp_attr, qp_attr_mask);
@@ -725,6 +742,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 		else
 			ret = ib_cm_init_qp_attr(id_priv->cm_id.ib, qp_attr,
 						 qp_attr_mask);
+
 		if (qp_attr->qp_state == IB_QPS_RTR)
 			qp_attr->rq_psn = id_priv->seq_num;
 		break;
@@ -1266,6 +1284,15 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	struct rdma_id_private *listen_id, *conn_id;
 	struct rdma_cm_event event;
 	int offset, ret;
+	u8 smac[ETH_ALEN];
+	u8 alt_smac[ETH_ALEN];
+	u8 *psmac = smac;
+	u8 *palt_smac = alt_smac;
+	int is_iboe = ((rdma_node_get_transport(cm_id->device->node_type) ==
+			RDMA_TRANSPORT_IB) &&
+		       (rdma_port_get_link_layer(cm_id->device,
+			ib_event->param.req_rcvd.port) ==
+			IB_LINK_LAYER_ETHERNET));
 
 	listen_id = cm_id->context;
 	if (!cma_check_req_qp_type(&listen_id->id, ib_event))
@@ -1310,12 +1337,29 @@ static int cma_req_handler(struct ib_cm_id *cm_id, struct ib_cm_event *ib_event)
 	if (ret)
 		goto err3;
 
+	if (is_iboe) {
+		if (ib_event->param.req_rcvd.primary_path != NULL)
+			rdma_addr_find_smac_by_sgid(
+				&ib_event->param.req_rcvd.primary_path->sgid,
+				psmac, NULL);
+		else
+			psmac = NULL;
+		if (ib_event->param.req_rcvd.alternate_path != NULL)
+			rdma_addr_find_smac_by_sgid(
+				&ib_event->param.req_rcvd.alternate_path->sgid,
+				palt_smac, NULL);
+		else
+			palt_smac = NULL;
+	}
 	/*
 	 * Acquire mutex to prevent user executing rdma_destroy_id()
 	 * while we're accessing the cm_id.
 	 */
 	mutex_lock(&lock);
-	if (cma_comp(conn_id, RDMA_CM_CONNECT) && (conn_id->id.qp_type != IB_QPT_UD))
+	if (is_iboe)
+		ib_update_cm_av(cm_id, psmac, palt_smac);
+	if (cma_comp(conn_id, RDMA_CM_CONNECT) &&
+	    (conn_id->id.qp_type != IB_QPT_UD))
 		ib_send_cm_mra(cm_id, CMA_CM_MRA_SETTING, NULL, 0);
 	mutex_unlock(&lock);
 	mutex_unlock(&conn_id->handler_mutex);
@@ -1474,7 +1518,7 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 	mutex_lock_nested(&conn_id->handler_mutex, SINGLE_DEPTH_NESTING);
 	conn_id->state = RDMA_CM_CONNECT;
 
-	ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr);
+	ret = rdma_translate_ip(laddr, &conn_id->id.route.addr.dev_addr, NULL);
 	if (ret) {
 		mutex_unlock(&conn_id->handler_mutex);
 		rdma_destroy_id(new_cm_id);
@@ -1873,7 +1917,7 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 	struct cma_work *work;
 	int ret;
 	struct net_device *ndev = NULL;
-	u16 vid;
+
 
 	work = kzalloc(sizeof *work, GFP_KERNEL);
 	if (!work)
@@ -1897,10 +1941,14 @@ static int cma_resolve_iboe_route(struct rdma_id_private *id_priv)
 		goto err2;
 	}
 
-	vid = rdma_vlan_dev_vlan_id(ndev);
+	route->path_rec->vlan_id = rdma_vlan_dev_vlan_id(ndev);
+	memcpy(route->path_rec->dmac, addr->dev_addr.dst_dev_addr, ETH_ALEN);
+	memcpy(route->path_rec->smac, ndev->dev_addr, ndev->addr_len);
 
-	iboe_mac_vlan_to_ll(&route->path_rec->sgid, addr->dev_addr.src_dev_addr, vid);
-	iboe_mac_vlan_to_ll(&route->path_rec->dgid, addr->dev_addr.dst_dev_addr, vid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+		    &route->path_rec->sgid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.dst_addr,
+		    &route->path_rec->dgid);
 
 	route->path_rec->hop_limit = 1;
 	route->path_rec->reversible = 1;
@@ -2063,6 +2111,7 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 			   RDMA_CM_ADDR_RESOLVED))
 		goto out;
 
+	memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
 	if (!status && !id_priv->cma_dev)
 		status = cma_acquire_dev(id_priv, NULL);
 
@@ -2072,10 +2121,8 @@ static void addr_handler(int status, struct sockaddr *src_addr,
 			goto out;
 		event.event = RDMA_CM_EVENT_ADDR_ERROR;
 		event.status = status;
-	} else {
-		memcpy(cma_src_addr(id_priv), src_addr, rdma_addr_size(src_addr));
+	} else
 		event.event = RDMA_CM_EVENT_ADDR_RESOLVED;
-	}
 
 	if (id_priv->id.event_handler(&id_priv->id, &event)) {
 		cma_exch(id_priv, RDMA_CM_DESTROYING);
@@ -2480,8 +2527,11 @@ static int cma_check_linklocal(struct rdma_dev_addr *dev_addr,
 		return 0;
 
 	sin6 = (struct sockaddr_in6 *) addr;
-	if ((ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
-	    !sin6->sin6_scope_id)
+
+	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
+		return 0;
+
+	if (!sin6->sin6_scope_id)
 			return -EINVAL;
 
 	dev_addr->bound_dev_if = sin6->sin6_scope_id;
@@ -2556,6 +2606,7 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 	if (ret)
 		goto err1;
 
+	memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
 	if (!cma_any_addr(addr)) {
 		ret = cma_translate_addr(addr, &id->route.addr.dev_addr);
 		if (ret)
@@ -2566,7 +2617,6 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 			goto err1;
 	}
 
-	memcpy(cma_src_addr(id_priv), addr, rdma_addr_size(addr));
 	if (!(id_priv->options & (1 << CMA_OPTION_AFONLY))) {
 		if (addr->sa_family == AF_INET)
 			id_priv->afonly = 1;
@@ -3295,7 +3345,8 @@ static int cma_iboe_join_multicast(struct rdma_id_private *id_priv,
 		err = -EINVAL;
 		goto out2;
 	}
-	iboe_addr_get_sgid(dev_addr, &mc->multicast.ib->rec.port_gid);
+	rdma_ip2gid((struct sockaddr *)&id_priv->id.route.addr.src_addr,
+		    &mc->multicast.ib->rec.port_gid);
 	work->id = id_priv;
 	work->mc = mc;
 	INIT_WORK(&work->work, iboe_mcast_work_handler);

drivers/infiniband/core/core_priv.h

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

drivers/infiniband/core/iwcm.c

@@ -334,7 +334,6 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 {
 	struct iwcm_id_private *cm_id_priv;
 	unsigned long flags;
-	int ret;
 
 	cm_id_priv = container_of(cm_id, struct iwcm_id_private, id);
 	/*
@@ -350,7 +349,7 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
 		cm_id_priv->state = IW_CM_STATE_DESTROYING;
 		spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 		/* destroy the listening endpoint */
-		ret = cm_id->device->iwcm->destroy_listen(cm_id);
+		cm_id->device->iwcm->destroy_listen(cm_id);
 		spin_lock_irqsave(&cm_id_priv->lock, flags);
 		break;
 	case IW_CM_STATE_ESTABLISHED:

drivers/infiniband/core/sa_query.c

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

drivers/infiniband/core/sysfs.c

@@ -613,6 +613,7 @@ static ssize_t show_node_type(struct device *device,
 	case RDMA_NODE_IB_CA:	  return sprintf(buf, "%d: CA\n", dev->node_type);
 	case RDMA_NODE_RNIC:	  return sprintf(buf, "%d: RNIC\n", dev->node_type);
 	case RDMA_NODE_USNIC:	  return sprintf(buf, "%d: usNIC\n", dev->node_type);
+	case RDMA_NODE_USNIC_UDP: return sprintf(buf, "%d: usNIC UDP\n", dev->node_type);
 	case RDMA_NODE_IB_SWITCH: return sprintf(buf, "%d: switch\n", dev->node_type);
 	case RDMA_NODE_IB_ROUTER: return sprintf(buf, "%d: router\n", dev->node_type);
 	default:		  return sprintf(buf, "%d: <unknown>\n", dev->node_type);

drivers/infiniband/core/ucma.c

@@ -655,24 +655,14 @@ static void ucma_copy_ib_route(struct rdma_ucm_query_route_resp *resp,
 static void ucma_copy_iboe_route(struct rdma_ucm_query_route_resp *resp,
 				 struct rdma_route *route)
 {
-	struct rdma_dev_addr *dev_addr;
-	struct net_device *dev;
-	u16 vid = 0;
 
 	resp->num_paths = route->num_paths;
 	switch (route->num_paths) {
 	case 0:
-		dev_addr = &route->addr.dev_addr;
-		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);
+		rdma_ip2gid((struct sockaddr *)&route->addr.dst_addr,
+			    (union ib_gid *)&resp->ib_route[0].dgid);
+		rdma_ip2gid((struct sockaddr *)&route->addr.src_addr,
+			    (union ib_gid *)&resp->ib_route[0].sgid);
 		resp->ib_route[0].pkey = cpu_to_be16(0xffff);
 		break;
 	case 2:

drivers/infiniband/core/uverbs_cmd.c

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

drivers/infiniband/core/verbs.c

@@ -44,6 +44,9 @@
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_cache.h>
+#include <rdma/ib_addr.h>
+
+#include "core_priv.h"
 
 int ib_rate_to_mult(enum ib_rate rate)
 {
@@ -116,6 +119,8 @@ rdma_node_get_transport(enum rdma_node_type node_type)
 		return RDMA_TRANSPORT_IWARP;
 	case RDMA_NODE_USNIC:
 		return RDMA_TRANSPORT_USNIC;
+	case RDMA_NODE_USNIC_UDP:
+		return RDMA_TRANSPORT_USNIC_UDP;
 	default:
 		BUG();
 		return 0;
@@ -133,6 +138,7 @@ enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device, u8 port_
 		return IB_LINK_LAYER_INFINIBAND;
 	case RDMA_TRANSPORT_IWARP:
 	case RDMA_TRANSPORT_USNIC:
+	case RDMA_TRANSPORT_USNIC_UDP:
 		return IB_LINK_LAYER_ETHERNET;
 	default:
 		return IB_LINK_LAYER_UNSPECIFIED;
@@ -192,8 +198,28 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
 	u32 flow_class;
 	u16 gid_index;
 	int ret;
+	int is_eth = (rdma_port_get_link_layer(device, port_num) ==
+			IB_LINK_LAYER_ETHERNET);
 
 	memset(ah_attr, 0, sizeof *ah_attr);
+	if (is_eth) {
+		if (!(wc->wc_flags & IB_WC_GRH))
+			return -EPROTOTYPE;
+
+		if (wc->wc_flags & IB_WC_WITH_SMAC &&
+		    wc->wc_flags & IB_WC_WITH_VLAN) {
+			memcpy(ah_attr->dmac, wc->smac, ETH_ALEN);
+			ah_attr->vlan_id = wc->vlan_id;
+		} else {
+			ret = rdma_addr_find_dmac_by_grh(&grh->dgid, &grh->sgid,
+					ah_attr->dmac, &ah_attr->vlan_id);
+			if (ret)
+				return ret;
+		}
+	} else {
+		ah_attr->vlan_id = 0xffff;
+	}
+
 	ah_attr->dlid = wc->slid;
 	ah_attr->sl = wc->sl;
 	ah_attr->src_path_bits = wc->dlid_path_bits;
@@ -476,7 +502,9 @@ EXPORT_SYMBOL(ib_create_qp);
 static const struct {
 	int			valid;
 	enum ib_qp_attr_mask	req_param[IB_QPT_MAX];
+	enum ib_qp_attr_mask	req_param_add_eth[IB_QPT_MAX];
 	enum ib_qp_attr_mask	opt_param[IB_QPT_MAX];
+	enum ib_qp_attr_mask	opt_param_add_eth[IB_QPT_MAX];
 } qp_state_table[IB_QPS_ERR + 1][IB_QPS_ERR + 1] = {
 	[IB_QPS_RESET] = {
 		[IB_QPS_RESET] = { .valid = 1 },
@@ -557,6 +585,12 @@ static const struct {
 						IB_QP_MAX_DEST_RD_ATOMIC	|
 						IB_QP_MIN_RNR_TIMER),
 			},
+			.req_param_add_eth = {
+				[IB_QPT_RC]  = (IB_QP_SMAC),
+				[IB_QPT_UC]  = (IB_QP_SMAC),
+				[IB_QPT_XRC_INI]  = (IB_QP_SMAC),
+				[IB_QPT_XRC_TGT]  = (IB_QP_SMAC)
+			},
 			.opt_param = {
 				 [IB_QPT_UD]  = (IB_QP_PKEY_INDEX		|
 						 IB_QP_QKEY),
@@ -576,7 +610,21 @@ static const struct {
 						 IB_QP_QKEY),
 				 [IB_QPT_GSI] = (IB_QP_PKEY_INDEX		|
 						 IB_QP_QKEY),
-			 }
+			 },
+			.opt_param_add_eth = {
+				[IB_QPT_RC]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID),
+				[IB_QPT_UC]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID),
+				[IB_QPT_XRC_INI]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID),
+				[IB_QPT_XRC_TGT]  = (IB_QP_ALT_SMAC			|
+						IB_QP_VID			|
+						IB_QP_ALT_VID)
+			}
 		}
 	},
 	[IB_QPS_RTR]   = {
@@ -779,7 +827,8 @@ static const struct {
 };
 
 int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
-		       enum ib_qp_type type, enum ib_qp_attr_mask mask)
+		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
+		       enum rdma_link_layer ll)
 {
 	enum ib_qp_attr_mask req_param, opt_param;
 
@@ -798,6 +847,13 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 	req_param = qp_state_table[cur_state][next_state].req_param[type];
 	opt_param = qp_state_table[cur_state][next_state].opt_param[type];
 
+	if (ll == IB_LINK_LAYER_ETHERNET) {
+		req_param |= qp_state_table[cur_state][next_state].
+			req_param_add_eth[type];
+		opt_param |= qp_state_table[cur_state][next_state].
+			opt_param_add_eth[type];
+	}
+
 	if ((mask & req_param) != req_param)
 		return 0;
 
@@ -808,10 +864,51 @@ int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
 }
 EXPORT_SYMBOL(ib_modify_qp_is_ok);
 
+int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
+			    struct ib_qp_attr *qp_attr, int *qp_attr_mask)
+{
+	int           ret = 0;
+	union ib_gid  sgid;
+
+	if ((*qp_attr_mask & IB_QP_AV)  &&
+	    (rdma_port_get_link_layer(qp->device, qp_attr->ah_attr.port_num) == IB_LINK_LAYER_ETHERNET)) {
+		ret = ib_query_gid(qp->device, qp_attr->ah_attr.port_num,
+				   qp_attr->ah_attr.grh.sgid_index, &sgid);
+		if (ret)
+			goto out;
+		if (rdma_link_local_addr((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw)) {
+			rdma_get_ll_mac((struct in6_addr *)qp_attr->ah_attr.grh.dgid.raw, qp_attr->ah_attr.dmac);
+			rdma_get_ll_mac((struct in6_addr *)sgid.raw, qp_attr->smac);
+			qp_attr->vlan_id = rdma_get_vlan_id(&sgid);
+		} else {
+			ret = rdma_addr_find_dmac_by_grh(&sgid, &qp_attr->ah_attr.grh.dgid,
+					qp_attr->ah_attr.dmac, &qp_attr->vlan_id);
+			if (ret)
+				goto out;
+			ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr->smac, NULL);
+			if (ret)
+				goto out;
+		}
+		*qp_attr_mask |= IB_QP_SMAC;
+		if (qp_attr->vlan_id < 0xFFFF)
+			*qp_attr_mask |= IB_QP_VID;
+	}
+out:
+	return ret;
+}
+EXPORT_SYMBOL(ib_resolve_eth_l2_attrs);
+
+
 int ib_modify_qp(struct ib_qp *qp,
 		 struct ib_qp_attr *qp_attr,
 		 int qp_attr_mask)
 {
+	int ret;
+
+	ret = ib_resolve_eth_l2_attrs(qp, qp_attr, &qp_attr_mask);
+	if (ret)
+		return ret;
+
 	return qp->device->modify_qp(qp->real_qp, qp_attr, qp_attr_mask, NULL);
 }
 EXPORT_SYMBOL(ib_modify_qp);

drivers/infiniband/hw/amso1100/c2_intr.c

@@ -169,7 +169,8 @@ static void handle_vq(struct c2_dev *c2dev, u32 mq_index)
 		 * We should never get here, as the adapter should
 		 * never send us a reply that we're not expecting.
 		 */
-		vq_repbuf_free(c2dev, host_msg);
+		if (reply_msg != NULL)
+			vq_repbuf_free(c2dev, host_msg);
 		pr_debug("handle_vq: UNEXPECTEDLY got NULL req\n");
 		return;
 	}

drivers/infiniband/hw/cxgb4/mem.c

@@ -76,7 +76,7 @@ static int _c4iw_write_mem_dma_aligned(struct c4iw_rdev *rdev, u32 addr,
 	INIT_ULPTX_WR(req, wr_len, 0, 0);
 	req->wr.wr_hi = cpu_to_be32(FW_WR_OP(FW_ULPTX_WR) |
 			(wait ? FW_WR_COMPL(1) : 0));
-	req->wr.wr_lo = wait ? (__force __be64)&wr_wait : 0;
+	req->wr.wr_lo = wait ? (__force __be64)(unsigned long) &wr_wait : 0L;
 	req->wr.wr_mid = cpu_to_be32(FW_WR_LEN16(DIV_ROUND_UP(wr_len, 16)));
 	req->cmd = cpu_to_be32(ULPTX_CMD(ULP_TX_MEM_WRITE));
 	req->cmd |= cpu_to_be32(V_T5_ULP_MEMIO_ORDER(1));

drivers/infiniband/hw/ehca/ehca_qp.c

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

drivers/infiniband/hw/ipath/ipath_qp.c

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

drivers/infiniband/hw/mlx4/Kconfig

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

drivers/infiniband/hw/mlx4/ah.c

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

drivers/infiniband/hw/mlx4/cq.c

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

drivers/infiniband/hw/mlx4/main.c

@@ -39,6 +39,8 @@
 #include <linux/inetdevice.h>
 #include <linux/rtnetlink.h>
 #include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/addrconf.h>
 
 #include <rdma/ib_smi.h>
 #include <rdma/ib_user_verbs.h>
@@ -55,6 +57,7 @@
 #define DRV_RELDATE	"April 4, 2008"
 
 #define MLX4_IB_FLOW_MAX_PRIO 0xFFF
+#define MLX4_IB_FLOW_QPN_MASK 0xFFFFFF
 
 MODULE_AUTHOR("Roland Dreier");
 MODULE_DESCRIPTION("Mellanox ConnectX HCA InfiniBand driver");
@@ -92,21 +95,27 @@ static union ib_gid zgid;
 
 static int check_flow_steering_support(struct mlx4_dev *dev)
 {
+	int eth_num_ports = 0;
 	int ib_num_ports = 0;
-	int i;
-
-	mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
-		ib_num_ports++;
 
-	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED) {
-		if (ib_num_ports || mlx4_is_mfunc(dev)) {
-			pr_warn("Device managed flow steering is unavailable "
-				"for IB ports or in multifunction env.\n");
-			return 0;
+	int dmfs = dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED;
+
+	if (dmfs) {
+		int i;
+		mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_ETH)
+			eth_num_ports++;
+		mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB)
+			ib_num_ports++;
+		dmfs &= (!ib_num_ports ||
+			 (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DMFS_IPOIB)) &&
+			(!eth_num_ports ||
+			 (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN));
+		if (ib_num_ports && mlx4_is_mfunc(dev)) {
+			pr_warn("Device managed flow steering is unavailable for IB port in multifunction env.\n");
+			dmfs = 0;
 		}
-		return 1;
 	}
-	return 0;
+	return dmfs;
 }
 
 static int mlx4_ib_query_device(struct ib_device *ibdev,
@@ -165,7 +174,7 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
 		else
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
-	if (check_flow_steering_support(dev->dev))
+	if (dev->steering_support ==  MLX4_STEERING_MODE_DEVICE_MANAGED)
 		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 	}
 
@@ -787,7 +796,6 @@ static int add_gid_entry(struct ib_qp *ibqp, union ib_gid *gid)
 int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 		   union ib_gid *gid)
 {
-	u8 mac[6];
 	struct net_device *ndev;
 	int ret = 0;
 
@@ -801,11 +809,7 @@ int mlx4_ib_add_mc(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
 	spin_unlock(&mdev->iboe.lock);
 
 	if (ndev) {
-		rdma_get_mcast_mac((struct in6_addr *)gid, mac);
-		rtnl_lock();
-		dev_mc_add(mdev->iboe.netdevs[mqp->port - 1], mac);
 		ret = 1;
-		rtnl_unlock();
 		dev_put(ndev);
 	}
 
@@ -819,6 +823,7 @@ struct mlx4_ib_steering {
 };
 
 static int parse_flow_attr(struct mlx4_dev *dev,
+			   u32 qp_num,
 			   union ib_flow_spec *ib_spec,
 			   struct _rule_hw *mlx4_spec)
 {
@@ -834,6 +839,14 @@ static int parse_flow_attr(struct mlx4_dev *dev,
 		mlx4_spec->eth.vlan_tag = ib_spec->eth.val.vlan_tag;
 		mlx4_spec->eth.vlan_tag_msk = ib_spec->eth.mask.vlan_tag;
 		break;
+	case IB_FLOW_SPEC_IB:
+		type = MLX4_NET_TRANS_RULE_ID_IB;
+		mlx4_spec->ib.l3_qpn =
+			cpu_to_be32(qp_num);
+		mlx4_spec->ib.qpn_mask =
+			cpu_to_be32(MLX4_IB_FLOW_QPN_MASK);
+		break;
+
 
 	case IB_FLOW_SPEC_IPV4:
 		type = MLX4_NET_TRANS_RULE_ID_IPV4;
@@ -865,6 +878,115 @@ static int parse_flow_attr(struct mlx4_dev *dev,
 	return mlx4_hw_rule_sz(dev, type);
 }
 
+struct default_rules {
+	__u32 mandatory_fields[IB_FLOW_SPEC_SUPPORT_LAYERS];
+	__u32 mandatory_not_fields[IB_FLOW_SPEC_SUPPORT_LAYERS];
+	__u32 rules_create_list[IB_FLOW_SPEC_SUPPORT_LAYERS];
+	__u8  link_layer;
+};
+static const struct default_rules default_table[] = {
+	{
+		.mandatory_fields = {IB_FLOW_SPEC_IPV4},
+		.mandatory_not_fields = {IB_FLOW_SPEC_ETH},
+		.rules_create_list = {IB_FLOW_SPEC_IB},
+		.link_layer = IB_LINK_LAYER_INFINIBAND
+	}
+};
+
+static int __mlx4_ib_default_rules_match(struct ib_qp *qp,
+					 struct ib_flow_attr *flow_attr)
+{
+	int i, j, k;
+	void *ib_flow;
+	const struct default_rules *pdefault_rules = default_table;
+	u8 link_layer = rdma_port_get_link_layer(qp->device, flow_attr->port);
+
+	for (i = 0; i < sizeof(default_table)/sizeof(default_table[0]); i++,
+	     pdefault_rules++) {
+		__u32 field_types[IB_FLOW_SPEC_SUPPORT_LAYERS];
+		memset(&field_types, 0, sizeof(field_types));
+
+		if (link_layer != pdefault_rules->link_layer)
+			continue;
+
+		ib_flow = flow_attr + 1;
+		/* we assume the specs are sorted */
+		for (j = 0, k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS &&
+		     j < flow_attr->num_of_specs; k++) {
+			union ib_flow_spec *current_flow =
+				(union ib_flow_spec *)ib_flow;
+
+			/* same layer but different type */
+			if (((current_flow->type & IB_FLOW_SPEC_LAYER_MASK) ==
+			     (pdefault_rules->mandatory_fields[k] &
+			      IB_FLOW_SPEC_LAYER_MASK)) &&
+			    (current_flow->type !=
+			     pdefault_rules->mandatory_fields[k]))
+				goto out;
+
+			/* same layer, try match next one */
+			if (current_flow->type ==
+			    pdefault_rules->mandatory_fields[k]) {
+				j++;
+				ib_flow +=
+					((union ib_flow_spec *)ib_flow)->size;
+			}
+		}
+
+		ib_flow = flow_attr + 1;
+		for (j = 0; j < flow_attr->num_of_specs;
+		     j++, ib_flow += ((union ib_flow_spec *)ib_flow)->size)
+			for (k = 0; k < IB_FLOW_SPEC_SUPPORT_LAYERS; k++)
+				/* same layer and same type */
+				if (((union ib_flow_spec *)ib_flow)->type ==
+				    pdefault_rules->mandatory_not_fields[k])
+					goto out;
+
+		return i;
+	}
+out:
+	return -1;
+}
+
+static int __mlx4_ib_create_default_rules(
+		struct mlx4_ib_dev *mdev,
+		struct ib_qp *qp,
+		const struct default_rules *pdefault_rules,
+		struct _rule_hw *mlx4_spec) {
+	int size = 0;
+	int i;
+
+	for (i = 0; i < sizeof(pdefault_rules->rules_create_list)/
+			sizeof(pdefault_rules->rules_create_list[0]); i++) {
+		int ret;
+		union ib_flow_spec ib_spec;
+		switch (pdefault_rules->rules_create_list[i]) {
+		case 0:
+			/* no rule */
+			continue;
+		case IB_FLOW_SPEC_IB:
+			ib_spec.type = IB_FLOW_SPEC_IB;
+			ib_spec.size = sizeof(struct ib_flow_spec_ib);
+
+			break;
+		default:
+			/* invalid rule */
+			return -EINVAL;
+		}
+		/* We must put empty rule, qpn is being ignored */
+		ret = parse_flow_attr(mdev->dev, 0, &ib_spec,
+				      mlx4_spec);
+		if (ret < 0) {
+			pr_info("invalid parsing\n");
+			return -EINVAL;
+		}
+
+		mlx4_spec = (void *)mlx4_spec + ret;
+		size += ret;
+	}
+	return size;
+}
+
 static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_attr,
 			  int domain,
 			  enum mlx4_net_trans_promisc_mode flow_type,
@@ -876,6 +998,7 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
 	struct mlx4_ib_dev *mdev = to_mdev(qp->device);
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_net_trans_rule_hw_ctrl *ctrl;
+	int default_flow;
 
 	static const u16 __mlx4_domain[] = {
 		[IB_FLOW_DOMAIN_USER] = MLX4_DOMAIN_UVERBS,
@@ -910,8 +1033,21 @@ static int __mlx4_ib_create_flow(struct ib_qp *qp, struct ib_flow_attr *flow_att
 
 	ib_flow = flow_attr + 1;
 	size += sizeof(struct mlx4_net_trans_rule_hw_ctrl);
+	/* Add default flows */
+	default_flow = __mlx4_ib_default_rules_match(qp, flow_attr);
+	if (default_flow >= 0) {
+		ret = __mlx4_ib_create_default_rules(
+				mdev, qp, default_table + default_flow,
+				mailbox->buf + size);
+		if (ret < 0) {
+			mlx4_free_cmd_mailbox(mdev->dev, mailbox);
+			return -EINVAL;
+		}
+		size += ret;
+	}
 	for (i = 0; i < flow_attr->num_of_specs; i++) {
-		ret = parse_flow_attr(mdev->dev, ib_flow, mailbox->buf + size);
+		ret = parse_flow_attr(mdev->dev, qp->qp_num, ib_flow,
+				      mailbox->buf + size);
 		if (ret < 0) {
 			mlx4_free_cmd_mailbox(mdev->dev, mailbox);
 			return -EINVAL;
@@ -1025,6 +1161,8 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
 	u64 reg_id;
 	struct mlx4_ib_steering *ib_steering = NULL;
+	enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+		MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
 
 	if (mdev->dev->caps.steering_mode ==
 	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -1036,7 +1174,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	err = mlx4_multicast_attach(mdev->dev, &mqp->mqp, gid->raw, mqp->port,
 				    !!(mqp->flags &
 				       MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK),
-				    MLX4_PROT_IB_IPV6, &reg_id);
+				    prot, &reg_id);
 	if (err)
 		goto err_malloc;
 
@@ -1055,7 +1193,7 @@ static int mlx4_ib_mcg_attach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 
 err_add:
 	mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
-			      MLX4_PROT_IB_IPV6, reg_id);
+			      prot, reg_id);
 err_malloc:
 	kfree(ib_steering);
 
@@ -1083,10 +1221,11 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	int err;
 	struct mlx4_ib_dev *mdev = to_mdev(ibqp->device);
 	struct mlx4_ib_qp *mqp = to_mqp(ibqp);
-	u8 mac[6];
 	struct net_device *ndev;
 	struct mlx4_ib_gid_entry *ge;
 	u64 reg_id = 0;
+	enum mlx4_protocol prot = (gid->raw[1] == 0x0e) ?
+		MLX4_PROT_IB_IPV4 : MLX4_PROT_IB_IPV6;
 
 	if (mdev->dev->caps.steering_mode ==
 	    MLX4_STEERING_MODE_DEVICE_MANAGED) {
@@ -1109,7 +1248,7 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 	}
 
 	err = mlx4_multicast_detach(mdev->dev, &mqp->mqp, gid->raw,
-				    MLX4_PROT_IB_IPV6, reg_id);
+				    prot, reg_id);
 	if (err)
 		return err;
 
@@ -1121,13 +1260,8 @@ static int mlx4_ib_mcg_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 		if (ndev)
 			dev_hold(ndev);
 		spin_unlock(&mdev->iboe.lock);
-		rdma_get_mcast_mac((struct in6_addr *)gid, mac);
-		if (ndev) {
-			rtnl_lock();
-			dev_mc_del(mdev->iboe.netdevs[ge->port - 1], mac);
-			rtnl_unlock();
+		if (ndev)
 			dev_put(ndev);
-		}
 		list_del(&ge->list);
 		kfree(ge);
 	} else
@@ -1223,20 +1357,6 @@ static struct device_attribute *mlx4_class_attributes[] = {
 	&dev_attr_board_id
 };
 
-static void mlx4_addrconf_ifid_eui48(u8 *eui, u16 vlan_id, struct net_device *dev)
-{
-	memcpy(eui, dev->dev_addr, 3);
-	memcpy(eui + 5, dev->dev_addr + 3, 3);
-	if (vlan_id < 0x1000) {
-		eui[3] = vlan_id >> 8;
-		eui[4] = vlan_id & 0xff;
-	} else {
-		eui[3] = 0xff;
-		eui[4] = 0xfe;
-	}
-	eui[0] ^= 2;
-}
-
 static void update_gids_task(struct work_struct *work)
 {
 	struct update_gid_work *gw = container_of(work, struct update_gid_work, work);
@@ -1259,161 +1379,318 @@ static void update_gids_task(struct work_struct *work)
 		       MLX4_CMD_WRAPPED);
 	if (err)
 		pr_warn("set port command failed\n");
-	else {
-		memcpy(gw->dev->iboe.gid_table[gw->port - 1], gw->gids, sizeof gw->gids);
+	else
 		mlx4_ib_dispatch_event(gw->dev, gw->port, IB_EVENT_GID_CHANGE);
-	}
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 	kfree(gw);
 }
 
-static int update_ipv6_gids(struct mlx4_ib_dev *dev, int port, int clear)
+static void reset_gids_task(struct work_struct *work)
 {
-	struct net_device *ndev = dev->iboe.netdevs[port - 1];
-	struct update_gid_work *work;
-	struct net_device *tmp;
+	struct update_gid_work *gw =
+			container_of(work, struct update_gid_work, work);
+	struct mlx4_cmd_mailbox *mailbox;
+	union ib_gid *gids;
+	int err;
 	int i;
-	u8 *hits;
-	int ret;
-	union ib_gid gid;
-	int free;
-	int found;
-	int need_update = 0;
-	u16 vid;
+	struct mlx4_dev	*dev = gw->dev->dev;
 
-	work = kzalloc(sizeof *work, GFP_ATOMIC);
-	if (!work)
-		return -ENOMEM;
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox)) {
+		pr_warn("reset gid table failed\n");
+		goto free;
+	}
 
-	hits = kzalloc(128, GFP_ATOMIC);
-	if (!hits) {
-		ret = -ENOMEM;
-		goto out;
+	gids = mailbox->buf;
+	memcpy(gids, gw->gids, sizeof(gw->gids));
+
+	for (i = 1; i < gw->dev->num_ports + 1; i++) {
+		if (mlx4_ib_port_link_layer(&gw->dev->ib_dev, i) ==
+					    IB_LINK_LAYER_ETHERNET) {
+			err = mlx4_cmd(dev, mailbox->dma,
+				       MLX4_SET_PORT_GID_TABLE << 8 | i,
+				       1, MLX4_CMD_SET_PORT,
+				       MLX4_CMD_TIME_CLASS_B,
+				       MLX4_CMD_WRAPPED);
+			if (err)
+				pr_warn(KERN_WARNING
+					"set port %d command failed\n", i);
+		}
 	}
 
-	rcu_read_lock();
-	for_each_netdev_rcu(&init_net, tmp) {
-		if (ndev && (tmp == ndev || rdma_vlan_dev_real_dev(tmp) == ndev)) {
-			gid.global.subnet_prefix = cpu_to_be64(0xfe80000000000000LL);
-			vid = rdma_vlan_dev_vlan_id(tmp);
-			mlx4_addrconf_ifid_eui48(&gid.raw[8], vid, ndev);
-			found = 0;
-			free = -1;
-			for (i = 0; i < 128; ++i) {
-				if (free < 0 &&
-				    !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
-					free = i;
-				if (!memcmp(&dev->iboe.gid_table[port - 1][i], &gid, sizeof gid)) {
-					hits[i] = 1;
-					found = 1;
-					break;
-				}
-			}
+	mlx4_free_cmd_mailbox(dev, mailbox);
+free:
+	kfree(gw);
+}
 
-			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;
-				}
+static int update_gid_table(struct mlx4_ib_dev *dev, int port,
+			    union ib_gid *gid, int clear)
+{
+	struct update_gid_work *work;
+	int i;
+	int need_update = 0;
+	int free = -1;
+	int found = -1;
+	int max_gids;
+
+	max_gids = dev->dev->caps.gid_table_len[port];
+	for (i = 0; i < max_gids; ++i) {
+		if (!memcmp(&dev->iboe.gid_table[port - 1][i], gid,
+			    sizeof(*gid)))
+			found = i;
+
+		if (clear) {
+			if (found >= 0) {
+				need_update = 1;
+				dev->iboe.gid_table[port - 1][found] = zgid;
+				break;
 			}
+		} else {
+			if (found >= 0)
+				break;
+
+			if (free < 0 &&
+			    !memcmp(&dev->iboe.gid_table[port - 1][i], &zgid,
+				    sizeof(*gid)))
+				free = i;
 		}
 	}
-	rcu_read_unlock();
 
-	for (i = 0; i < 128; ++i)
-		if (!hits[i]) {
-			if (memcmp(&dev->iboe.gid_table[port - 1][i], &zgid, sizeof zgid))
-				++need_update;
-			dev->iboe.gid_table[port - 1][i] = zgid;
-		}
+	if (found == -1 && !clear && free >= 0) {
+		dev->iboe.gid_table[port - 1][free] = *gid;
+		need_update = 1;
+	}
 
-	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);
+	if (!need_update)
+		return 0;
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return -ENOMEM;
+
+	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);
 
-	kfree(hits);
 	return 0;
+}
 
-out:
-	kfree(work);
-	return ret;
+static int reset_gid_table(struct mlx4_ib_dev *dev)
+{
+	struct update_gid_work *work;
+
+
+	work = kzalloc(sizeof(*work), GFP_ATOMIC);
+	if (!work)
+		return -ENOMEM;
+	memset(dev->iboe.gid_table, 0, sizeof(dev->iboe.gid_table));
+	memset(work->gids, 0, sizeof(work->gids));
+	INIT_WORK(&work->work, reset_gids_task);
+	work->dev = dev;
+	queue_work(wq, &work->work);
+	return 0;
 }
 
-static void handle_en_event(struct mlx4_ib_dev *dev, int port, unsigned long event)
+static int mlx4_ib_addr_event(int event, struct net_device *event_netdev,
+			      struct mlx4_ib_dev *ibdev, union ib_gid *gid)
 {
-	switch (event) {
-	case NETDEV_UP:
-	case NETDEV_CHANGEADDR:
-		update_ipv6_gids(dev, port, 0);
-		break;
+	struct mlx4_ib_iboe *iboe;
+	int port = 0;
+	struct net_device *real_dev = rdma_vlan_dev_real_dev(event_netdev) ?
+				rdma_vlan_dev_real_dev(event_netdev) :
+				event_netdev;
+
+	if (event != NETDEV_DOWN && event != NETDEV_UP)
+		return 0;
+
+	if ((real_dev != event_netdev) &&
+	    (event == NETDEV_DOWN) &&
+	    rdma_link_local_addr((struct in6_addr *)gid))
+		return 0;
+
+	iboe = &ibdev->iboe;
+	spin_lock(&iboe->lock);
+
+	for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+		if ((netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->masters[port - 1])) ||
+		     (!netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->netdevs[port - 1])))
+			update_gid_table(ibdev, port, gid,
+					 event == NETDEV_DOWN);
+
+	spin_unlock(&iboe->lock);
+	return 0;
 
-	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)
+static u8 mlx4_ib_get_dev_port(struct net_device *dev,
+			       struct mlx4_ib_dev *ibdev)
 {
-	update_ipv6_gids(dev, port, 0);
+	u8 port = 0;
+	struct mlx4_ib_iboe *iboe;
+	struct net_device *real_dev = rdma_vlan_dev_real_dev(dev) ?
+				rdma_vlan_dev_real_dev(dev) : dev;
+
+	iboe = &ibdev->iboe;
+	spin_lock(&iboe->lock);
+
+	for (port = 1; port <= MLX4_MAX_PORTS; ++port)
+		if ((netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->masters[port - 1])) ||
+		     (!netif_is_bond_master(real_dev) &&
+		     (real_dev == iboe->netdevs[port - 1])))
+			break;
+
+	spin_unlock(&iboe->lock);
+
+	if ((port == 0) || (port > MLX4_MAX_PORTS))
+		return 0;
+	else
+		return port;
 }
 
-static void netdev_removed(struct mlx4_ib_dev *dev, int port)
+static int mlx4_ib_inet_event(struct notifier_block *this, unsigned long event,
+				void *ptr)
 {
-	update_ipv6_gids(dev, port, 1);
+	struct mlx4_ib_dev *ibdev;
+	struct in_ifaddr *ifa = ptr;
+	union ib_gid gid;
+	struct net_device *event_netdev = ifa->ifa_dev->dev;
+
+	ipv6_addr_set_v4mapped(ifa->ifa_address, (struct in6_addr *)&gid);
+
+	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet);
+
+	mlx4_ib_addr_event(event, event_netdev, ibdev, &gid);
+	return NOTIFY_DONE;
 }
 
-static int mlx4_ib_netdev_event(struct notifier_block *this, unsigned long event,
+#if IS_ENABLED(CONFIG_IPV6)
+static int mlx4_ib_inet6_event(struct notifier_block *this, unsigned long event,
 				void *ptr)
 {
-	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
 	struct mlx4_ib_dev *ibdev;
-	struct net_device *oldnd;
+	struct inet6_ifaddr *ifa = ptr;
+	union  ib_gid *gid = (union ib_gid *)&ifa->addr;
+	struct net_device *event_netdev = ifa->idev->dev;
+
+	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb_inet6);
+
+	mlx4_ib_addr_event(event, event_netdev, ibdev, gid);
+	return NOTIFY_DONE;
+}
+#endif
+
+static void mlx4_ib_get_dev_addr(struct net_device *dev,
+				 struct mlx4_ib_dev *ibdev, u8 port)
+{
+	struct in_device *in_dev;
+#if IS_ENABLED(CONFIG_IPV6)
+	struct inet6_dev *in6_dev;
+	union ib_gid  *pgid;
+	struct inet6_ifaddr *ifp;
+#endif
+	union ib_gid gid;
+
+
+	if ((port == 0) || (port > MLX4_MAX_PORTS))
+		return;
+
+	/* IPv4 gids */
+	in_dev = in_dev_get(dev);
+	if (in_dev) {
+		for_ifa(in_dev) {
+			/*ifa->ifa_address;*/
+			ipv6_addr_set_v4mapped(ifa->ifa_address,
+					       (struct in6_addr *)&gid);
+			update_gid_table(ibdev, port, &gid, 0);
+		}
+		endfor_ifa(in_dev);
+		in_dev_put(in_dev);
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	/* IPv6 gids */
+	in6_dev = in6_dev_get(dev);
+	if (in6_dev) {
+		read_lock_bh(&in6_dev->lock);
+		list_for_each_entry(ifp, &in6_dev->addr_list, if_list) {
+			pgid = (union ib_gid *)&ifp->addr;
+			update_gid_table(ibdev, port, pgid, 0);
+		}
+		read_unlock_bh(&in6_dev->lock);
+		in6_dev_put(in6_dev);
+	}
+#endif
+}
+
+static int mlx4_ib_init_gid_table(struct mlx4_ib_dev *ibdev)
+{
+	struct	net_device *dev;
+
+	if (reset_gid_table(ibdev))
+		return -1;
+
+	read_lock(&dev_base_lock);
+
+	for_each_netdev(&init_net, dev) {
+		u8 port = mlx4_ib_get_dev_port(dev, ibdev);
+		if (port)
+			mlx4_ib_get_dev_addr(dev, ibdev, port);
+	}
+
+	read_unlock(&dev_base_lock);
+
+	return 0;
+}
+
+static void mlx4_ib_scan_netdevs(struct mlx4_ib_dev *ibdev)
+{
 	struct mlx4_ib_iboe *iboe;
 	int port;
 
-	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];
+		struct net_device *old_master = iboe->masters[port - 1];
+		struct net_device *curr_master;
 		iboe->netdevs[port - 1] =
 			mlx4_get_protocol_dev(ibdev->dev, MLX4_PROT_ETH, port);
-		if (oldnd != iboe->netdevs[port - 1]) {
-			if (iboe->netdevs[port - 1])
-				netdev_added(ibdev, port);
-			else
-				netdev_removed(ibdev, port);
+
+		if (iboe->netdevs[port - 1] &&
+		    netif_is_bond_slave(iboe->netdevs[port - 1])) {
+			rtnl_lock();
+			iboe->masters[port - 1] = netdev_master_upper_dev_get(
+				iboe->netdevs[port - 1]);
+			rtnl_unlock();
 		}
-	}
+		curr_master = iboe->masters[port - 1];
 
-	if (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);
+		/* if bonding is used it is possible that we add it to masters
+		    only after IP address is assigned to the net bonding
+		    interface */
+		if (curr_master && (old_master != curr_master))
+			mlx4_ib_get_dev_addr(curr_master, ibdev, port);
+	}
 
 	spin_unlock(&iboe->lock);
+}
+
+static int mlx4_ib_netdev_event(struct notifier_block *this,
+				unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct mlx4_ib_dev *ibdev;
+
+	if (!net_eq(dev_net(dev), &init_net))
+		return NOTIFY_DONE;
+
+	ibdev = container_of(this, struct mlx4_ib_dev, iboe.nb);
+	mlx4_ib_scan_netdevs(ibdev);
 
 	return NOTIFY_DONE;
 }
@@ -1682,6 +1959,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	}
 
 	if (check_flow_steering_support(dev)) {
+		ibdev->steering_support = MLX4_STEERING_MODE_DEVICE_MANAGED;
 		ibdev->ib_dev.create_flow	= mlx4_ib_create_flow;
 		ibdev->ib_dev.destroy_flow	= mlx4_ib_destroy_flow;
 
@@ -1710,8 +1988,35 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	spin_lock_init(&ibdev->sm_lock);
 	mutex_init(&ibdev->cap_mask_mutex);
 
+	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
+		err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
+					    MLX4_IB_UC_STEER_QPN_ALIGN,
+					    &ibdev->steer_qpn_base);
+		if (err)
+			goto err_counter;
+
+		ibdev->ib_uc_qpns_bitmap =
+			kmalloc(BITS_TO_LONGS(ibdev->steer_qpn_count) *
+				sizeof(long),
+				GFP_KERNEL);
+		if (!ibdev->ib_uc_qpns_bitmap) {
+			dev_err(&dev->pdev->dev, "bit map alloc failed\n");
+			goto err_steer_qp_release;
+		}
+
+		bitmap_zero(ibdev->ib_uc_qpns_bitmap, ibdev->steer_qpn_count);
+
+		err = mlx4_FLOW_STEERING_IB_UC_QP_RANGE(
+				dev, ibdev->steer_qpn_base,
+				ibdev->steer_qpn_base +
+				ibdev->steer_qpn_count - 1);
+		if (err)
+			goto err_steer_free_bitmap;
+	}
+
 	if (ib_register_device(&ibdev->ib_dev, NULL))
-		goto err_counter;
+		goto err_steer_free_bitmap;
 
 	if (mlx4_ib_mad_init(ibdev))
 		goto err_reg;
@@ -1719,11 +2024,35 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	if (mlx4_ib_init_sriov(ibdev))
 		goto err_mad;
 
-	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE && !iboe->nb.notifier_call) {
-		iboe->nb.notifier_call = mlx4_ib_netdev_event;
-		err = register_netdevice_notifier(&iboe->nb);
-		if (err)
-			goto err_sriov;
+	if (dev->caps.flags & MLX4_DEV_CAP_FLAG_IBOE) {
+		if (!iboe->nb.notifier_call) {
+			iboe->nb.notifier_call = mlx4_ib_netdev_event;
+			err = register_netdevice_notifier(&iboe->nb);
+			if (err) {
+				iboe->nb.notifier_call = NULL;
+				goto err_notif;
+			}
+		}
+		if (!iboe->nb_inet.notifier_call) {
+			iboe->nb_inet.notifier_call = mlx4_ib_inet_event;
+			err = register_inetaddr_notifier(&iboe->nb_inet);
+			if (err) {
+				iboe->nb_inet.notifier_call = NULL;
+				goto err_notif;
+			}
+		}
+#if IS_ENABLED(CONFIG_IPV6)
+		if (!iboe->nb_inet6.notifier_call) {
+			iboe->nb_inet6.notifier_call = mlx4_ib_inet6_event;
+			err = register_inet6addr_notifier(&iboe->nb_inet6);
+			if (err) {
+				iboe->nb_inet6.notifier_call = NULL;
+				goto err_notif;
+			}
+		}
+#endif
+		mlx4_ib_scan_netdevs(ibdev);
+		mlx4_ib_init_gid_table(ibdev);
 	}
 
 	for (j = 0; j < ARRAY_SIZE(mlx4_class_attributes); ++j) {
@@ -1749,11 +2078,25 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	return ibdev;
 
 err_notif:
-	if (unregister_netdevice_notifier(&ibdev->iboe.nb))
-		pr_warn("failure unregistering notifier\n");
+	if (ibdev->iboe.nb.notifier_call) {
+		if (unregister_netdevice_notifier(&ibdev->iboe.nb))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb.notifier_call = NULL;
+	}
+	if (ibdev->iboe.nb_inet.notifier_call) {
+		if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet.notifier_call = NULL;
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	if (ibdev->iboe.nb_inet6.notifier_call) {
+		if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet6.notifier_call = NULL;
+	}
+#endif
 	flush_workqueue(wq);
 
-err_sriov:
 	mlx4_ib_close_sriov(ibdev);
 
 err_mad:
@@ -1762,6 +2105,13 @@ err_mad:
 err_reg:
 	ib_unregister_device(&ibdev->ib_dev);
 
+err_steer_free_bitmap:
+	kfree(ibdev->ib_uc_qpns_bitmap);
+
+err_steer_qp_release:
+	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
+		mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
+				      ibdev->steer_qpn_count);
 err_counter:
 	for (; i; --i)
 		if (ibdev->counters[i - 1] != -1)
@@ -1782,6 +2132,69 @@ err_dealloc:
 	return NULL;
 }
 
+int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn)
+{
+	int offset;
+
+	WARN_ON(!dev->ib_uc_qpns_bitmap);
+
+	offset = bitmap_find_free_region(dev->ib_uc_qpns_bitmap,
+					 dev->steer_qpn_count,
+					 get_count_order(count));
+	if (offset < 0)
+		return offset;
+
+	*qpn = dev->steer_qpn_base + offset;
+	return 0;
+}
+
+void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count)
+{
+	if (!qpn ||
+	    dev->steering_support != MLX4_STEERING_MODE_DEVICE_MANAGED)
+		return;
+
+	BUG_ON(qpn < dev->steer_qpn_base);
+
+	bitmap_release_region(dev->ib_uc_qpns_bitmap,
+			      qpn - dev->steer_qpn_base,
+			      get_count_order(count));
+}
+
+int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
+			 int is_attach)
+{
+	int err;
+	size_t flow_size;
+	struct ib_flow_attr *flow = NULL;
+	struct ib_flow_spec_ib *ib_spec;
+
+	if (is_attach) {
+		flow_size = sizeof(struct ib_flow_attr) +
+			    sizeof(struct ib_flow_spec_ib);
+		flow = kzalloc(flow_size, GFP_KERNEL);
+		if (!flow)
+			return -ENOMEM;
+		flow->port = mqp->port;
+		flow->num_of_specs = 1;
+		flow->size = flow_size;
+		ib_spec = (struct ib_flow_spec_ib *)(flow + 1);
+		ib_spec->type = IB_FLOW_SPEC_IB;
+		ib_spec->size = sizeof(struct ib_flow_spec_ib);
+		/* Add an empty rule for IB L2 */
+		memset(&ib_spec->mask, 0, sizeof(ib_spec->mask));
+
+		err = __mlx4_ib_create_flow(&mqp->ibqp, flow,
+					    IB_FLOW_DOMAIN_NIC,
+					    MLX4_FS_REGULAR,
+					    &mqp->reg_id);
+	} else {
+		err = __mlx4_ib_destroy_flow(mdev->dev, mqp->reg_id);
+	}
+	kfree(flow);
+	return err;
+}
+
 static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 {
 	struct mlx4_ib_dev *ibdev = ibdev_ptr;
@@ -1795,6 +2208,26 @@ static void mlx4_ib_remove(struct mlx4_dev *dev, void *ibdev_ptr)
 			pr_warn("failure unregistering notifier\n");
 		ibdev->iboe.nb.notifier_call = NULL;
 	}
+
+	if (ibdev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED) {
+		mlx4_qp_release_range(dev, ibdev->steer_qpn_base,
+				      ibdev->steer_qpn_count);
+		kfree(ibdev->ib_uc_qpns_bitmap);
+	}
+
+	if (ibdev->iboe.nb_inet.notifier_call) {
+		if (unregister_inetaddr_notifier(&ibdev->iboe.nb_inet))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet.notifier_call = NULL;
+	}
+#if IS_ENABLED(CONFIG_IPV6)
+	if (ibdev->iboe.nb_inet6.notifier_call) {
+		if (unregister_inet6addr_notifier(&ibdev->iboe.nb_inet6))
+			pr_warn("failure unregistering notifier\n");
+		ibdev->iboe.nb_inet6.notifier_call = NULL;
+	}
+#endif
+
 	iounmap(ibdev->uar_map);
 	for (p = 0; p < ibdev->num_ports; ++p)
 		if (ibdev->counters[p] != -1)

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -68,6 +68,8 @@ enum {
 /*module param to indicate if SM assigns the alias_GUID*/
 extern int mlx4_ib_sm_guid_assign;
 
+#define MLX4_IB_UC_STEER_QPN_ALIGN 1
+#define MLX4_IB_UC_MAX_NUM_QPS     256
 struct mlx4_ib_ucontext {
 	struct ib_ucontext	ibucontext;
 	struct mlx4_uar		uar;
@@ -153,6 +155,7 @@ struct mlx4_ib_wq {
 enum mlx4_ib_qp_flags {
 	MLX4_IB_QP_LSO = IB_QP_CREATE_IPOIB_UD_LSO,
 	MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK = IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK,
+	MLX4_IB_QP_NETIF = IB_QP_CREATE_NETIF_QP,
 	MLX4_IB_SRIOV_TUNNEL_QP = 1 << 30,
 	MLX4_IB_SRIOV_SQP = 1 << 31,
 };
@@ -270,6 +273,7 @@ struct mlx4_ib_qp {
 	struct list_head	gid_list;
 	struct list_head	steering_rules;
 	struct mlx4_ib_buf	*sqp_proxy_rcv;
+	u64			reg_id;
 
 };
 
@@ -428,7 +432,10 @@ struct mlx4_ib_sriov {
 struct mlx4_ib_iboe {
 	spinlock_t		lock;
 	struct net_device      *netdevs[MLX4_MAX_PORTS];
+	struct net_device      *masters[MLX4_MAX_PORTS];
 	struct notifier_block 	nb;
+	struct notifier_block	nb_inet;
+	struct notifier_block	nb_inet6;
 	union ib_gid		gid_table[MLX4_MAX_PORTS][128];
 };
 
@@ -494,6 +501,10 @@ struct mlx4_ib_dev {
 	struct kobject	       *dev_ports_parent[MLX4_MFUNC_MAX];
 	struct mlx4_ib_iov_port	iov_ports[MLX4_MAX_PORTS];
 	struct pkey_mgt		pkeys;
+	unsigned long *ib_uc_qpns_bitmap;
+	int steer_qpn_count;
+	int steer_qpn_base;
+	int steering_support;
 };
 
 struct ib_event_work {
@@ -675,9 +686,6 @@ int __mlx4_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
 int __mlx4_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
 			union ib_gid *gid, int netw_view);
 
-int mlx4_ib_resolve_grh(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah_attr,
-			u8 *mac, int *is_mcast, u8 port);
-
 static inline bool mlx4_ib_ah_grh_present(struct mlx4_ib_ah *ah)
 {
 	u8 port = be32_to_cpu(ah->av.ib.port_pd) >> 24 & 3;
@@ -752,5 +760,9 @@ void mlx4_ib_device_unregister_sysfs(struct mlx4_ib_dev *device);
 
 __be64 mlx4_ib_gen_node_guid(void);
 
+int mlx4_ib_steer_qp_alloc(struct mlx4_ib_dev *dev, int count, int *qpn);
+void mlx4_ib_steer_qp_free(struct mlx4_ib_dev *dev, u32 qpn, int count);
+int mlx4_ib_steer_qp_reg(struct mlx4_ib_dev *mdev, struct mlx4_ib_qp *mqp,
+			 int is_attach);
 
 #endif /* MLX4_IB_H */

drivers/infiniband/hw/mlx4/qp.c

@@ -90,6 +90,21 @@ enum {
 	MLX4_RAW_QP_MSGMAX	= 31,
 };
 
+#ifndef ETH_ALEN
+#define ETH_ALEN        6
+#endif
+static inline u64 mlx4_mac_to_u64(u8 *addr)
+{
+	u64 mac = 0;
+	int i;
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		mac <<= 8;
+		mac |= addr[i];
+	}
+	return mac;
+}
+
 static const __be32 mlx4_ib_opcode[] = {
 	[IB_WR_SEND]				= cpu_to_be32(MLX4_OPCODE_SEND),
 	[IB_WR_LSO]				= cpu_to_be32(MLX4_OPCODE_LSO),
@@ -716,6 +731,14 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (init_attr->create_flags & IB_QP_CREATE_IPOIB_UD_LSO)
 			qp->flags |= MLX4_IB_QP_LSO;
 
+		if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
+			if (dev->steering_support ==
+			    MLX4_STEERING_MODE_DEVICE_MANAGED)
+				qp->flags |= MLX4_IB_QP_NETIF;
+			else
+				goto err;
+		}
+
 		err = set_kernel_sq_size(dev, &init_attr->cap, qp_type, qp);
 		if (err)
 			goto err;
@@ -765,7 +788,11 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 		if (init_attr->qp_type == IB_QPT_RAW_PACKET)
 			err = mlx4_qp_reserve_range(dev->dev, 1, 1 << 8, &qpn);
 		else
-			err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn);
+			if (qp->flags & MLX4_IB_QP_NETIF)
+				err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
+			else
+				err = mlx4_qp_reserve_range(dev->dev, 1, 1,
+							    &qpn);
 		if (err)
 			goto err_proxy;
 	}
@@ -790,8 +817,12 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 	return 0;
 
 err_qpn:
-	if (!sqpn)
-		mlx4_qp_release_range(dev->dev, qpn, 1);
+	if (!sqpn) {
+		if (qp->flags & MLX4_IB_QP_NETIF)
+			mlx4_ib_steer_qp_free(dev, qpn, 1);
+		else
+			mlx4_qp_release_range(dev->dev, qpn, 1);
+	}
 err_proxy:
 	if (qp->mlx4_ib_qp_type == MLX4_IB_QPT_PROXY_GSI)
 		free_proxy_bufs(pd->device, qp);
@@ -932,8 +963,12 @@ static void destroy_qp_common(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp,
 
 	mlx4_qp_free(dev->dev, &qp->mqp);
 
-	if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp))
-		mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
+	if (!is_sqp(dev, qp) && !is_tunnel_qp(dev, qp)) {
+		if (qp->flags & MLX4_IB_QP_NETIF)
+			mlx4_ib_steer_qp_free(dev, qp->mqp.qpn, 1);
+		else
+			mlx4_qp_release_range(dev->dev, qp->mqp.qpn, 1);
+	}
 
 	mlx4_mtt_cleanup(dev->dev, &qp->mtt);
 
@@ -987,9 +1022,16 @@ struct ib_qp *mlx4_ib_create_qp(struct ib_pd *pd,
 	 */
 	if (init_attr->create_flags & ~(MLX4_IB_QP_LSO |
 					MLX4_IB_QP_BLOCK_MULTICAST_LOOPBACK |
-					MLX4_IB_SRIOV_TUNNEL_QP | MLX4_IB_SRIOV_SQP))
+					MLX4_IB_SRIOV_TUNNEL_QP |
+					MLX4_IB_SRIOV_SQP |
+					MLX4_IB_QP_NETIF))
 		return ERR_PTR(-EINVAL);
 
+	if (init_attr->create_flags & IB_QP_CREATE_NETIF_QP) {
+		if (init_attr->qp_type != IB_QPT_UD)
+			return ERR_PTR(-EINVAL);
+	}
+
 	if (init_attr->create_flags &&
 	    (udata ||
 	     ((init_attr->create_flags & ~MLX4_IB_SRIOV_SQP) &&
@@ -1144,16 +1186,15 @@ static void mlx4_set_sched(struct mlx4_qp_path *path, u8 port)
 	path->sched_queue = (path->sched_queue & 0xbf) | ((port - 1) << 6);
 }
 
-static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
-			 struct mlx4_qp_path *path, u8 port)
+static int _mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
+			  u64 smac, u16 vlan_tag, struct mlx4_qp_path *path,
+			  u8 port)
 {
-	int err;
 	int is_eth = rdma_port_get_link_layer(&dev->ib_dev, port) ==
 		IB_LINK_LAYER_ETHERNET;
-	u8 mac[6];
-	int is_mcast;
-	u16 vlan_tag;
 	int vidx;
+	int smac_index;
+
 
 	path->grh_mylmc     = ah->src_path_bits & 0x7f;
 	path->rlid	    = cpu_to_be16(ah->dlid);
@@ -1188,22 +1229,27 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 		if (!(ah->ah_flags & IB_AH_GRH))
 			return -1;
 
-		err = mlx4_ib_resolve_grh(dev, ah, mac, &is_mcast, port);
-		if (err)
-			return err;
-
-		memcpy(path->dmac, mac, 6);
+		memcpy(path->dmac, ah->dmac, ETH_ALEN);
 		path->ackto = MLX4_IB_LINK_TYPE_ETH;
-		/* use index 0 into MAC table for IBoE */
-		path->grh_mylmc &= 0x80;
+		/* find the index  into MAC table for IBoE */
+		if (!is_zero_ether_addr((const u8 *)&smac)) {
+			if (mlx4_find_cached_mac(dev->dev, port, smac,
+						 &smac_index))
+				return -ENOENT;
+		} else {
+			smac_index = 0;
+		}
+
+		path->grh_mylmc &= 0x80 | smac_index;
 
-		vlan_tag = rdma_get_vlan_id(&dev->iboe.gid_table[port - 1][ah->grh.sgid_index]);
+		path->feup |= MLX4_FEUP_FORCE_ETH_UP;
 		if (vlan_tag < 0x1000) {
 			if (mlx4_find_cached_vlan(dev->dev, port, vlan_tag, &vidx))
 				return -ENOENT;
 
 			path->vlan_index = vidx;
 			path->fl = 1 << 6;
+			path->feup |= MLX4_FVL_FORCE_ETH_VLAN;
 		}
 	} else
 		path->sched_queue = MLX4_IB_DEFAULT_SCHED_QUEUE |
@@ -1212,6 +1258,28 @@ static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_ah_attr *ah,
 	return 0;
 }
 
+static int mlx4_set_path(struct mlx4_ib_dev *dev, const struct ib_qp_attr *qp,
+			 enum ib_qp_attr_mask qp_attr_mask,
+			 struct mlx4_qp_path *path, u8 port)
+{
+	return _mlx4_set_path(dev, &qp->ah_attr,
+			      mlx4_mac_to_u64((u8 *)qp->smac),
+			      (qp_attr_mask & IB_QP_VID) ? qp->vlan_id : 0xffff,
+			      path, port);
+}
+
+static int mlx4_set_alt_path(struct mlx4_ib_dev *dev,
+			     const struct ib_qp_attr *qp,
+			     enum ib_qp_attr_mask qp_attr_mask,
+			     struct mlx4_qp_path *path, u8 port)
+{
+	return _mlx4_set_path(dev, &qp->alt_ah_attr,
+			      mlx4_mac_to_u64((u8 *)qp->alt_smac),
+			      (qp_attr_mask & IB_QP_ALT_VID) ?
+			      qp->alt_vlan_id : 0xffff,
+			      path, port);
+}
+
 static void update_mcg_macs(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp)
 {
 	struct mlx4_ib_gid_entry *ge, *tmp;
@@ -1235,6 +1303,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	struct mlx4_qp_context *context;
 	enum mlx4_qp_optpar optpar = 0;
 	int sqd_event;
+	int steer_qp = 0;
 	int err = -EINVAL;
 
 	context = kzalloc(sizeof *context, GFP_KERNEL);
@@ -1319,6 +1388,11 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 			optpar |= MLX4_QP_OPTPAR_COUNTER_INDEX;
 		} else
 			context->pri_path.counter_index = 0xff;
+
+		if (qp->flags & MLX4_IB_QP_NETIF) {
+			mlx4_ib_steer_qp_reg(dev, qp, 1);
+			steer_qp = 1;
+		}
 	}
 
 	if (attr_mask & IB_QP_PKEY_INDEX) {
@@ -1329,7 +1403,7 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 	}
 
 	if (attr_mask & IB_QP_AV) {
-		if (mlx4_set_path(dev, &attr->ah_attr, &context->pri_path,
+		if (mlx4_set_path(dev, attr, attr_mask, &context->pri_path,
 				  attr_mask & IB_QP_PORT ?
 				  attr->port_num : qp->port))
 			goto out;
@@ -1352,8 +1426,8 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		    dev->dev->caps.pkey_table_len[attr->alt_port_num])
 			goto out;
 
-		if (mlx4_set_path(dev, &attr->alt_ah_attr, &context->alt_path,
-				  attr->alt_port_num))
+		if (mlx4_set_alt_path(dev, attr, attr_mask, &context->alt_path,
+				      attr->alt_port_num))
 			goto out;
 
 		context->alt_path.pkey_index = attr->alt_pkey_index;
@@ -1464,6 +1538,17 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		context->pri_path.ackto = (context->pri_path.ackto & 0xf8) |
 					MLX4_IB_LINK_TYPE_ETH;
 
+	if (ibqp->qp_type == IB_QPT_UD && (new_state == IB_QPS_RTR)) {
+		int is_eth = rdma_port_get_link_layer(
+				&dev->ib_dev, qp->port) ==
+				IB_LINK_LAYER_ETHERNET;
+		if (is_eth) {
+			context->pri_path.ackto = MLX4_IB_LINK_TYPE_ETH;
+			optpar |= MLX4_QP_OPTPAR_PRIMARY_ADDR_PATH;
+		}
+	}
+
+
 	if (cur_state == IB_QPS_RTS && new_state == IB_QPS_SQD	&&
 	    attr_mask & IB_QP_EN_SQD_ASYNC_NOTIFY && attr->en_sqd_async_notify)
 		sqd_event = 1;
@@ -1547,9 +1632,14 @@ static int __mlx4_ib_modify_qp(struct ib_qp *ibqp,
 		qp->sq_next_wqe = 0;
 		if (qp->rq.wqe_cnt)
 			*qp->db.db  = 0;
+
+		if (qp->flags & MLX4_IB_QP_NETIF)
+			mlx4_ib_steer_qp_reg(dev, qp, 0);
 	}
 
 out:
+	if (err && steer_qp)
+		mlx4_ib_steer_qp_reg(dev, qp, 0);
 	kfree(context);
 	return err;
 }
@@ -1561,13 +1651,21 @@ int mlx4_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	struct mlx4_ib_qp *qp = to_mqp(ibqp);
 	enum ib_qp_state cur_state, new_state;
 	int err = -EINVAL;
-
+	int ll;
 	mutex_lock(&qp->mutex);
 
 	cur_state = attr_mask & IB_QP_CUR_STATE ? attr->cur_qp_state : qp->state;
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
-	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask)) {
+	if (cur_state == new_state && cur_state == IB_QPS_RESET) {
+		ll = IB_LINK_LAYER_UNSPECIFIED;
+	} else {
+		int port = attr_mask & IB_QP_PORT ? attr->port_num : qp->port;
+		ll = rdma_port_get_link_layer(&dev->ib_dev, port);
+	}
+
+	if (!ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type,
+				attr_mask, ll)) {
 		pr_debug("qpn 0x%x: invalid attribute mask specified "
 			 "for transition %d to %d. qp_type %d,"
 			 " attr_mask 0x%x\n",
@@ -1784,8 +1882,10 @@ static int build_mlx_header(struct mlx4_ib_sqp *sqp, struct ib_send_wr *wr,
 				return err;
 		}
 
-		vlan = rdma_get_vlan_id(&sgid);
-		is_vlan = vlan < 0x1000;
+		if (ah->av.eth.vlan != 0xffff) {
+			vlan = be16_to_cpu(ah->av.eth.vlan) & 0x0fff;
+			is_vlan = 1;
+		}
 	}
 	ib_ud_header_init(send_size, !is_eth, is_eth, is_vlan, is_grh, 0, &sqp->ud_header);
 
@@ -2762,6 +2862,9 @@ done:
 	if (qp->flags & MLX4_IB_QP_LSO)
 		qp_init_attr->create_flags |= IB_QP_CREATE_IPOIB_UD_LSO;
 
+	if (qp->flags & MLX4_IB_QP_NETIF)
+		qp_init_attr->create_flags |= IB_QP_CREATE_NETIF_QP;
+
 	qp_init_attr->sq_sig_type =
 		qp->sq_signal_bits == cpu_to_be32(MLX4_WQE_CTRL_CQ_UPDATE) ?
 		IB_SIGNAL_ALL_WR : IB_SIGNAL_REQ_WR;

drivers/infiniband/hw/mlx4/sysfs.c

@@ -582,8 +582,10 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
 	p->pkey_group.attrs =
 		alloc_group_attrs(show_port_pkey, store_port_pkey,
 				  dev->dev->caps.pkey_table_len[port_num]);
-	if (!p->pkey_group.attrs)
+	if (!p->pkey_group.attrs) {
+		ret = -ENOMEM;
 		goto err_alloc;
+	}
 
 	ret = sysfs_create_group(&p->kobj, &p->pkey_group);
 	if (ret)
@@ -591,8 +593,10 @@ static int add_port(struct mlx4_ib_dev *dev, int port_num, int slave)
 
 	p->gid_group.name  = "gid_idx";
 	p->gid_group.attrs = alloc_group_attrs(show_port_gid_idx, NULL, 1);
-	if (!p->gid_group.attrs)
+	if (!p->gid_group.attrs) {
+		ret = -ENOMEM;
 		goto err_free_pkey;
+	}
 
 	ret = sysfs_create_group(&p->kobj, &p->gid_group);
 	if (ret)

drivers/infiniband/hw/mlx5/cq.c

@@ -73,14 +73,24 @@ static void *get_cqe(struct mlx5_ib_cq *cq, int n)
 	return get_cqe_from_buf(&cq->buf, n, cq->mcq.cqe_sz);
 }
 
+static u8 sw_ownership_bit(int n, int nent)
+{
+	return (n & nent) ? 1 : 0;
+}
+
 static void *get_sw_cqe(struct mlx5_ib_cq *cq, int n)
 {
 	void *cqe = get_cqe(cq, n & cq->ibcq.cqe);
 	struct mlx5_cqe64 *cqe64;
 
 	cqe64 = (cq->mcq.cqe_sz == 64) ? cqe : cqe + 64;
-	return ((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^
-		!!(n & (cq->ibcq.cqe + 1))) ? NULL : cqe;
+
+	if (likely((cqe64->op_own) >> 4 != MLX5_CQE_INVALID) &&
+	    !((cqe64->op_own & MLX5_CQE_OWNER_MASK) ^ !!(n & (cq->ibcq.cqe + 1)))) {
+		return cqe;
+	} else {
+		return NULL;
+	}
 }
 
 static void *next_cqe_sw(struct mlx5_ib_cq *cq)
@@ -351,6 +361,11 @@ static void handle_atomics(struct mlx5_ib_qp *qp, struct mlx5_cqe64 *cqe64,
 	qp->sq.last_poll = tail;
 }
 
+static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
+{
+	mlx5_buf_free(&dev->mdev, &buf->buf);
+}
+
 static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 			 struct mlx5_ib_qp **cur_qp,
 			 struct ib_wc *wc)
@@ -366,6 +381,7 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	void *cqe;
 	int idx;
 
+repoll:
 	cqe = next_cqe_sw(cq);
 	if (!cqe)
 		return -EAGAIN;
@@ -379,7 +395,18 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	 */
 	rmb();
 
-	/* TBD: resize CQ */
+	opcode = cqe64->op_own >> 4;
+	if (unlikely(opcode == MLX5_CQE_RESIZE_CQ)) {
+		if (likely(cq->resize_buf)) {
+			free_cq_buf(dev, &cq->buf);
+			cq->buf = *cq->resize_buf;
+			kfree(cq->resize_buf);
+			cq->resize_buf = NULL;
+			goto repoll;
+		} else {
+			mlx5_ib_warn(dev, "unexpected resize cqe\n");
+		}
+	}
 
 	qpn = ntohl(cqe64->sop_drop_qpn) & 0xffffff;
 	if (!*cur_qp || (qpn != (*cur_qp)->ibqp.qp_num)) {
@@ -398,7 +425,6 @@ static int mlx5_poll_one(struct mlx5_ib_cq *cq,
 	}
 
 	wc->qp  = &(*cur_qp)->ibqp;
-	opcode = cqe64->op_own >> 4;
 	switch (opcode) {
 	case MLX5_CQE_REQ:
 		wq = &(*cur_qp)->sq;
@@ -503,15 +529,11 @@ static int alloc_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf,
 		return err;
 
 	buf->cqe_size = cqe_size;
+	buf->nent = nent;
 
 	return 0;
 }
 
-static void free_cq_buf(struct mlx5_ib_dev *dev, struct mlx5_ib_cq_buf *buf)
-{
-	mlx5_buf_free(&dev->mdev, &buf->buf);
-}
-
 static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  struct ib_ucontext *context, struct mlx5_ib_cq *cq,
 			  int entries, struct mlx5_create_cq_mbox_in **cqb,
@@ -576,16 +598,16 @@ static void destroy_cq_user(struct mlx5_ib_cq *cq, struct ib_ucontext *context)
 	ib_umem_release(cq->buf.umem);
 }
 
-static void init_cq_buf(struct mlx5_ib_cq *cq, int nent)
+static void init_cq_buf(struct mlx5_ib_cq *cq, struct mlx5_ib_cq_buf *buf)
 {
 	int i;
 	void *cqe;
 	struct mlx5_cqe64 *cqe64;
 
-	for (i = 0; i < nent; i++) {
-		cqe = get_cqe(cq, i);
-		cqe64 = (cq->buf.cqe_size == 64) ? cqe : cqe + 64;
-		cqe64->op_own = 0xf1;
+	for (i = 0; i < buf->nent; i++) {
+		cqe = get_cqe_from_buf(buf, i, buf->cqe_size);
+		cqe64 = buf->cqe_size == 64 ? cqe : cqe + 64;
+		cqe64->op_own = MLX5_CQE_INVALID << 4;
 	}
 }
 
@@ -610,7 +632,7 @@ static int create_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 	if (err)
 		goto err_db;
 
-	init_cq_buf(cq, entries);
+	init_cq_buf(cq, &cq->buf);
 
 	*inlen = sizeof(**cqb) + sizeof(*(*cqb)->pas) * cq->buf.buf.npages;
 	*cqb = mlx5_vzalloc(*inlen);
@@ -818,12 +840,266 @@ void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq)
 
 int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 {
-	return -ENOSYS;
+	struct mlx5_modify_cq_mbox_in *in;
+	struct mlx5_ib_dev *dev = to_mdev(cq->device);
+	struct mlx5_ib_cq *mcq = to_mcq(cq);
+	int err;
+	u32 fsel;
+
+	if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_CQ_MODER))
+		return -ENOSYS;
+
+	in = kzalloc(sizeof(*in), GFP_KERNEL);
+	if (!in)
+		return -ENOMEM;
+
+	in->cqn = cpu_to_be32(mcq->mcq.cqn);
+	fsel = (MLX5_CQ_MODIFY_PERIOD | MLX5_CQ_MODIFY_COUNT);
+	in->ctx.cq_period = cpu_to_be16(cq_period);
+	in->ctx.cq_max_count = cpu_to_be16(cq_count);
+	in->field_select = cpu_to_be32(fsel);
+	err = mlx5_core_modify_cq(&dev->mdev, &mcq->mcq, in, sizeof(*in));
+	kfree(in);
+
+	if (err)
+		mlx5_ib_warn(dev, "modify cq 0x%x failed\n", mcq->mcq.cqn);
+
+	return err;
+}
+
+static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
+		       int entries, struct ib_udata *udata, int *npas,
+		       int *page_shift, int *cqe_size)
+{
+	struct mlx5_ib_resize_cq ucmd;
+	struct ib_umem *umem;
+	int err;
+	int npages;
+	struct ib_ucontext *context = cq->buf.umem->context;
+
+	err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
+	if (err)
+		return err;
+
+	if (ucmd.reserved0 || ucmd.reserved1)
+		return -EINVAL;
+
+	umem = ib_umem_get(context, ucmd.buf_addr, entries * ucmd.cqe_size,
+			   IB_ACCESS_LOCAL_WRITE, 1);
+	if (IS_ERR(umem)) {
+		err = PTR_ERR(umem);
+		return err;
+	}
+
+	mlx5_ib_cont_pages(umem, ucmd.buf_addr, &npages, page_shift,
+			   npas, NULL);
+
+	cq->resize_umem = umem;
+	*cqe_size = ucmd.cqe_size;
+
+	return 0;
+}
+
+static void un_resize_user(struct mlx5_ib_cq *cq)
+{
+	ib_umem_release(cq->resize_umem);
+}
+
+static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
+			 int entries, int cqe_size)
+{
+	int err;
+
+	cq->resize_buf = kzalloc(sizeof(*cq->resize_buf), GFP_KERNEL);
+	if (!cq->resize_buf)
+		return -ENOMEM;
+
+	err = alloc_cq_buf(dev, cq->resize_buf, entries, cqe_size);
+	if (err)
+		goto ex;
+
+	init_cq_buf(cq, cq->resize_buf);
+
+	return 0;
+
+ex:
+	kfree(cq->resize_buf);
+	return err;
+}
+
+static void un_resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
+{
+	free_cq_buf(dev, cq->resize_buf);
+	cq->resize_buf = NULL;
+}
+
+static int copy_resize_cqes(struct mlx5_ib_cq *cq)
+{
+	struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device);
+	struct mlx5_cqe64 *scqe64;
+	struct mlx5_cqe64 *dcqe64;
+	void *start_cqe;
+	void *scqe;
+	void *dcqe;
+	int ssize;
+	int dsize;
+	int i;
+	u8 sw_own;
+
+	ssize = cq->buf.cqe_size;
+	dsize = cq->resize_buf->cqe_size;
+	if (ssize != dsize) {
+		mlx5_ib_warn(dev, "resize from different cqe size is not supported\n");
+		return -EINVAL;
+	}
+
+	i = cq->mcq.cons_index;
+	scqe = get_sw_cqe(cq, i);
+	scqe64 = ssize == 64 ? scqe : scqe + 64;
+	start_cqe = scqe;
+	if (!scqe) {
+		mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
+		return -EINVAL;
+	}
+
+	while ((scqe64->op_own >> 4) != MLX5_CQE_RESIZE_CQ) {
+		dcqe = get_cqe_from_buf(cq->resize_buf,
+					(i + 1) & (cq->resize_buf->nent),
+					dsize);
+		dcqe64 = dsize == 64 ? dcqe : dcqe + 64;
+		sw_own = sw_ownership_bit(i + 1, cq->resize_buf->nent);
+		memcpy(dcqe, scqe, dsize);
+		dcqe64->op_own = (dcqe64->op_own & ~MLX5_CQE_OWNER_MASK) | sw_own;
+
+		++i;
+		scqe = get_sw_cqe(cq, i);
+		scqe64 = ssize == 64 ? scqe : scqe + 64;
+		if (!scqe) {
+			mlx5_ib_warn(dev, "expected cqe in sw ownership\n");
+			return -EINVAL;
+		}
+
+		if (scqe == start_cqe) {
+			pr_warn("resize CQ failed to get resize CQE, CQN 0x%x\n",
+				cq->mcq.cqn);
+			return -ENOMEM;
+		}
+	}
+	++cq->mcq.cons_index;
+	return 0;
 }
 
 int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 {
-	return -ENOSYS;
+	struct mlx5_ib_dev *dev = to_mdev(ibcq->device);
+	struct mlx5_ib_cq *cq = to_mcq(ibcq);
+	struct mlx5_modify_cq_mbox_in *in;
+	int err;
+	int npas;
+	int page_shift;
+	int inlen;
+	int uninitialized_var(cqe_size);
+	unsigned long flags;
+
+	if (!(dev->mdev.caps.flags & MLX5_DEV_CAP_FLAG_RESIZE_CQ)) {
+		pr_info("Firmware does not support resize CQ\n");
+		return -ENOSYS;
+	}
+
+	if (entries < 1)
+		return -EINVAL;
+
+	entries = roundup_pow_of_two(entries + 1);
+	if (entries > dev->mdev.caps.max_cqes + 1)
+		return -EINVAL;
+
+	if (entries == ibcq->cqe + 1)
+		return 0;
+
+	mutex_lock(&cq->resize_mutex);
+	if (udata) {
+		err = resize_user(dev, cq, entries, udata, &npas, &page_shift,
+				  &cqe_size);
+	} else {
+		cqe_size = 64;
+		err = resize_kernel(dev, cq, entries, cqe_size);
+		if (!err) {
+			npas = cq->resize_buf->buf.npages;
+			page_shift = cq->resize_buf->buf.page_shift;
+		}
+	}
+
+	if (err)
+		goto ex;
+
+	inlen = sizeof(*in) + npas * sizeof(in->pas[0]);
+	in = mlx5_vzalloc(inlen);
+	if (!in) {
+		err = -ENOMEM;
+		goto ex_resize;
+	}
+
+	if (udata)
+		mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift,
+				     in->pas, 0);
+	else
+		mlx5_fill_page_array(&cq->resize_buf->buf, in->pas);
+
+	in->field_select = cpu_to_be32(MLX5_MODIFY_CQ_MASK_LOG_SIZE  |
+				       MLX5_MODIFY_CQ_MASK_PG_OFFSET |
+				       MLX5_MODIFY_CQ_MASK_PG_SIZE);
+	in->ctx.log_pg_sz = page_shift - MLX5_ADAPTER_PAGE_SHIFT;
+	in->ctx.cqe_sz_flags = cqe_sz_to_mlx_sz(cqe_size) << 5;
+	in->ctx.page_offset = 0;
+	in->ctx.log_sz_usr_page = cpu_to_be32(ilog2(entries) << 24);
+	in->hdr.opmod = cpu_to_be16(MLX5_CQ_OPMOD_RESIZE);
+	in->cqn = cpu_to_be32(cq->mcq.cqn);
+
+	err = mlx5_core_modify_cq(&dev->mdev, &cq->mcq, in, inlen);
+	if (err)
+		goto ex_alloc;
+
+	if (udata) {
+		cq->ibcq.cqe = entries - 1;
+		ib_umem_release(cq->buf.umem);
+		cq->buf.umem = cq->resize_umem;
+		cq->resize_umem = NULL;
+	} else {
+		struct mlx5_ib_cq_buf tbuf;
+		int resized = 0;
+
+		spin_lock_irqsave(&cq->lock, flags);
+		if (cq->resize_buf) {
+			err = copy_resize_cqes(cq);
+			if (!err) {
+				tbuf = cq->buf;
+				cq->buf = *cq->resize_buf;
+				kfree(cq->resize_buf);
+				cq->resize_buf = NULL;
+				resized = 1;
+			}
+		}
+		cq->ibcq.cqe = entries - 1;
+		spin_unlock_irqrestore(&cq->lock, flags);
+		if (resized)
+			free_cq_buf(dev, &tbuf);
+	}
+	mutex_unlock(&cq->resize_mutex);
+
+	mlx5_vfree(in);
+	return 0;
+
+ex_alloc:
+	mlx5_vfree(in);
+
+ex_resize:
+	if (udata)
+		un_resize_user(cq);
+	else
+		un_resize_kernel(dev, cq);
+ex:
+	mutex_unlock(&cq->resize_mutex);
+	return err;
 }
 
 int mlx5_ib_get_cqe_size(struct mlx5_ib_dev *dev, struct ib_cq *ibcq)

drivers/infiniband/hw/mlx5/main.c

@@ -541,6 +541,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	struct mlx5_ib_ucontext *context;
 	struct mlx5_uuar_info *uuari;
 	struct mlx5_uar *uars;
+	int gross_uuars;
 	int num_uars;
 	int uuarn;
 	int err;
@@ -559,11 +560,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	if (req.total_num_uuars == 0)
 		return ERR_PTR(-EINVAL);
 
-	req.total_num_uuars = ALIGN(req.total_num_uuars, MLX5_BF_REGS_PER_PAGE);
+	req.total_num_uuars = ALIGN(req.total_num_uuars,
+				    MLX5_NON_FP_BF_REGS_PER_PAGE);
 	if (req.num_low_latency_uuars > req.total_num_uuars - 1)
 		return ERR_PTR(-EINVAL);
 
-	num_uars = req.total_num_uuars / MLX5_BF_REGS_PER_PAGE;
+	num_uars = req.total_num_uuars / MLX5_NON_FP_BF_REGS_PER_PAGE;
+	gross_uuars = num_uars * MLX5_BF_REGS_PER_PAGE;
 	resp.qp_tab_size      = 1 << dev->mdev.caps.log_max_qp;
 	resp.bf_reg_size      = dev->mdev.caps.bf_reg_size;
 	resp.cache_line_size  = L1_CACHE_BYTES;
@@ -585,7 +588,7 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 		goto out_ctx;
 	}
 
-	uuari->bitmap = kcalloc(BITS_TO_LONGS(req.total_num_uuars),
+	uuari->bitmap = kcalloc(BITS_TO_LONGS(gross_uuars),
 				sizeof(*uuari->bitmap),
 				GFP_KERNEL);
 	if (!uuari->bitmap) {
@@ -595,13 +598,13 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 	/*
 	 * clear all fast path uuars
 	 */
-	for (i = 0; i < req.total_num_uuars; i++) {
+	for (i = 0; i < gross_uuars; i++) {
 		uuarn = i & 3;
 		if (uuarn == 2 || uuarn == 3)
 			set_bit(i, uuari->bitmap);
 	}
 
-	uuari->count = kcalloc(req.total_num_uuars, sizeof(*uuari->count), GFP_KERNEL);
+	uuari->count = kcalloc(gross_uuars, sizeof(*uuari->count), GFP_KERNEL);
 	if (!uuari->count) {
 		err = -ENOMEM;
 		goto out_bitmap;

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -195,6 +195,7 @@ struct mlx5_ib_cq_buf {
 	struct mlx5_buf		buf;
 	struct ib_umem		*umem;
 	int			cqe_size;
+	int			nent;
 };
 
 enum mlx5_ib_qp_flags {
@@ -220,7 +221,7 @@ struct mlx5_ib_cq {
 	/* protect resize cq
 	 */
 	struct mutex		resize_mutex;
-	struct mlx5_ib_cq_resize *resize_buf;
+	struct mlx5_ib_cq_buf  *resize_buf;
 	struct ib_umem	       *resize_umem;
 	int			cqe_size;
 };
@@ -264,7 +265,6 @@ struct mlx5_ib_mr {
 	enum ib_wc_status	status;
 	struct mlx5_ib_dev     *dev;
 	struct mlx5_create_mkey_mbox_out out;
-	unsigned long		start;
 };
 
 struct mlx5_ib_fast_reg_page_list {

drivers/infiniband/hw/mlx5/mr.c

@@ -146,7 +146,6 @@ static int add_keys(struct mlx5_ib_dev *dev, int c, int num)
 		spin_lock_irq(&ent->lock);
 		ent->pending++;
 		spin_unlock_irq(&ent->lock);
-		mr->start = jiffies;
 		err = mlx5_core_create_mkey(&dev->mdev, &mr->mmr, in,
 					    sizeof(*in), reg_mr_callback,
 					    mr, &mr->out);

drivers/infiniband/hw/mlx5/qp.c

@@ -340,14 +340,57 @@ static int qp_has_rq(struct ib_qp_init_attr *attr)
 	return 1;
 }
 
+static int first_med_uuar(void)
+{
+	return 1;
+}
+
+static int next_uuar(int n)
+{
+	n++;
+
+	while (((n % 4) & 2))
+		n++;
+
+	return n;
+}
+
+static int num_med_uuar(struct mlx5_uuar_info *uuari)
+{
+	int n;
+
+	n = uuari->num_uars * MLX5_NON_FP_BF_REGS_PER_PAGE -
+		uuari->num_low_latency_uuars - 1;
+
+	return n >= 0 ? n : 0;
+}
+
+static int max_uuari(struct mlx5_uuar_info *uuari)
+{
+	return uuari->num_uars * 4;
+}
+
+static int first_hi_uuar(struct mlx5_uuar_info *uuari)
+{
+	int med;
+	int i;
+	int t;
+
+	med = num_med_uuar(uuari);
+	for (t = 0, i = first_med_uuar();; i = next_uuar(i)) {
+		t++;
+		if (t == med)
+			return next_uuar(i);
+	}
+
+	return 0;
+}
+
 static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
 {
-	int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE;
-	int start_uuar;
 	int i;
 
-	start_uuar = nuuars - uuari->num_low_latency_uuars;
-	for (i = start_uuar; i < nuuars; i++) {
+	for (i = first_hi_uuar(uuari); i < max_uuari(uuari); i = next_uuar(i)) {
 		if (!test_bit(i, uuari->bitmap)) {
 			set_bit(i, uuari->bitmap);
 			uuari->count[i]++;
@@ -360,19 +403,10 @@ static int alloc_high_class_uuar(struct mlx5_uuar_info *uuari)
 
 static int alloc_med_class_uuar(struct mlx5_uuar_info *uuari)
 {
-	int nuuars = uuari->num_uars * MLX5_BF_REGS_PER_PAGE;
-	int minidx = 1;
-	int uuarn;
-	int end;
+	int minidx = first_med_uuar();
 	int i;
 
-	end = nuuars - uuari->num_low_latency_uuars;
-
-	for (i = 1; i < end; i++) {
-		uuarn = i & 3;
-		if (uuarn == 2 || uuarn == 3)
-			continue;
-
+	for (i = first_med_uuar(); i < first_hi_uuar(uuari); i = next_uuar(i)) {
 		if (uuari->count[i] < uuari->count[minidx])
 			minidx = i;
 	}
@@ -489,12 +523,12 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 {
 	struct mlx5_ib_ucontext *context;
 	struct mlx5_ib_create_qp ucmd;
-	int page_shift;
+	int page_shift = 0;
 	int uar_index;
 	int npages;
-	u32 offset;
+	u32 offset = 0;
 	int uuarn;
-	int ncont;
+	int ncont = 0;
 	int err;
 
 	err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
@@ -510,11 +544,16 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_HIGH);
 	if (uuarn < 0) {
 		mlx5_ib_dbg(dev, "failed to allocate low latency UUAR\n");
-		mlx5_ib_dbg(dev, "reverting to high latency\n");
-		uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
+		mlx5_ib_dbg(dev, "reverting to medium latency\n");
+		uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_MEDIUM);
 		if (uuarn < 0) {
-			mlx5_ib_dbg(dev, "uuar allocation failed\n");
-			return uuarn;
+			mlx5_ib_dbg(dev, "failed to allocate medium latency UUAR\n");
+			mlx5_ib_dbg(dev, "reverting to high latency\n");
+			uuarn = alloc_uuar(&context->uuari, MLX5_IB_LATENCY_CLASS_LOW);
+			if (uuarn < 0) {
+				mlx5_ib_warn(dev, "uuar allocation failed\n");
+				return uuarn;
+			}
 		}
 	}
 
@@ -525,23 +564,29 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 	if (err)
 		goto err_uuar;
 
-	qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
-			       qp->buf_size, 0, 0);
-	if (IS_ERR(qp->umem)) {
-		mlx5_ib_dbg(dev, "umem_get failed\n");
-		err = PTR_ERR(qp->umem);
-		goto err_uuar;
+	if (ucmd.buf_addr && qp->buf_size) {
+		qp->umem = ib_umem_get(pd->uobject->context, ucmd.buf_addr,
+				       qp->buf_size, 0, 0);
+		if (IS_ERR(qp->umem)) {
+			mlx5_ib_dbg(dev, "umem_get failed\n");
+			err = PTR_ERR(qp->umem);
+			goto err_uuar;
+		}
+	} else {
+		qp->umem = NULL;
 	}
 
-	mlx5_ib_cont_pages(qp->umem, ucmd.buf_addr, &npages, &page_shift,
-			   &ncont, NULL);
-	err = mlx5_ib_get_buf_offset(ucmd.buf_addr, page_shift, &offset);
-	if (err) {
-		mlx5_ib_warn(dev, "bad offset\n");
-		goto err_umem;
+	if (qp->umem) {
+		mlx5_ib_cont_pages(qp->umem, ucmd.buf_addr, &npages, &page_shift,
+				   &ncont, NULL);
+		err = mlx5_ib_get_buf_offset(ucmd.buf_addr, page_shift, &offset);
+		if (err) {
+			mlx5_ib_warn(dev, "bad offset\n");
+			goto err_umem;
+		}
+		mlx5_ib_dbg(dev, "addr 0x%llx, size %d, npages %d, page_shift %d, ncont %d, offset %d\n",
+			    ucmd.buf_addr, qp->buf_size, npages, page_shift, ncont, offset);
 	}
-	mlx5_ib_dbg(dev, "addr 0x%llx, size %d, npages %d, page_shift %d, ncont %d, offset %d\n",
-		    ucmd.buf_addr, qp->buf_size, npages, page_shift, ncont, offset);
 
 	*inlen = sizeof(**in) + sizeof(*(*in)->pas) * ncont;
 	*in = mlx5_vzalloc(*inlen);
@@ -549,7 +594,8 @@ static int create_user_qp(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		err = -ENOMEM;
 		goto err_umem;
 	}
-	mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
+	if (qp->umem)
+		mlx5_ib_populate_pas(dev, qp->umem, page_shift, (*in)->pas, 0);
 	(*in)->ctx.log_pg_sz_remote_qpn =
 		cpu_to_be32((page_shift - MLX5_ADAPTER_PAGE_SHIFT) << 24);
 	(*in)->ctx.params2 = cpu_to_be32(offset << 6);
@@ -580,7 +626,8 @@ err_free:
 	mlx5_vfree(*in);
 
 err_umem:
-	ib_umem_release(qp->umem);
+	if (qp->umem)
+		ib_umem_release(qp->umem);
 
 err_uuar:
 	free_uuar(&context->uuari, uuarn);
@@ -593,7 +640,8 @@ static void destroy_qp_user(struct ib_pd *pd, struct mlx5_ib_qp *qp)
 
 	context = to_mucontext(pd->uobject->context);
 	mlx5_ib_db_unmap_user(context, &qp->db);
-	ib_umem_release(qp->umem);
+	if (qp->umem)
+		ib_umem_release(qp->umem);
 	free_uuar(&context->uuari, qp->uuarn);
 }
 
@@ -1616,7 +1664,8 @@ int mlx5_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	new_state = attr_mask & IB_QP_STATE ? attr->qp_state : cur_state;
 
 	if (ibqp->qp_type != MLX5_IB_QPT_REG_UMR &&
-	    !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask))
+	    !ib_modify_qp_is_ok(cur_state, new_state, ibqp->qp_type, attr_mask,
+				IB_LINK_LAYER_UNSPECIFIED))
 		goto out;
 
 	if ((attr_mask & IB_QP_PORT) &&
@@ -2212,6 +2261,10 @@ out:
 
 		qp->db.db[MLX5_SND_DBR] = cpu_to_be32(qp->sq.cur_post);
 
+		/* Make sure doorbell record is visible to the HCA before
+		 * we hit doorbell */
+		wmb();
+
 		if (bf->need_lock)
 			spin_lock(&bf->lock);
 

drivers/infiniband/hw/mlx5/user.h

@@ -93,6 +93,9 @@ struct mlx5_ib_create_cq_resp {
 
 struct mlx5_ib_resize_cq {
 	__u64	buf_addr;
+	__u16	cqe_size;
+	__u16	reserved0;
+	__u32	reserved1;
 };
 
 struct mlx5_ib_create_srq {

drivers/infiniband/hw/mthca/mthca_qp.c

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

drivers/infiniband/hw/nes/nes_cm.c

@@ -1354,8 +1354,7 @@ static int nes_addr_resolve_neigh(struct nes_vnic *nesvnic, u32 dst_ip, int arpi
 				  neigh->ha, ntohl(rt->rt_gateway));
 
 			if (arpindex >= 0) {
-				if (!memcmp(nesadapter->arp_table[arpindex].mac_addr,
-					    neigh->ha, ETH_ALEN)) {
+				if (ether_addr_equal(nesadapter->arp_table[arpindex].mac_addr, neigh->ha)) {
 					/* Mac address same as in nes_arp_table */
 					goto out;
 				}

drivers/infiniband/hw/ocrdma/Kconfig

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

drivers/infiniband/hw/ocrdma/ocrdma.h

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

drivers/infiniband/hw/ocrdma/ocrdma_ah.c

@@ -49,7 +49,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 
 	ah->sgid_index = attr->grh.sgid_index;
 
-	vlan_tag = rdma_get_vlan_id(&attr->grh.dgid);
+	vlan_tag = attr->vlan_id;
 	if (!vlan_tag || (vlan_tag > 0xFFF))
 		vlan_tag = dev->pvid;
 	if (vlan_tag && (vlan_tag < 0x1000)) {
@@ -64,7 +64,8 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 		eth_sz = sizeof(struct ocrdma_eth_basic);
 	}
 	memcpy(&eth.smac[0], &dev->nic_info.mac_addr[0], ETH_ALEN);
-	status = ocrdma_resolve_dgid(dev, &attr->grh.dgid, &eth.dmac[0]);
+	memcpy(&eth.dmac[0], attr->dmac, ETH_ALEN);
+	status = ocrdma_resolve_dmac(dev, attr, &eth.dmac[0]);
 	if (status)
 		return status;
 	status = ocrdma_query_gid(&dev->ibdev, 1, attr->grh.sgid_index,
@@ -84,6 +85,7 @@ static inline int set_av_attr(struct ocrdma_dev *dev, struct ocrdma_ah *ah,
 	memcpy((u8 *)ah->av + eth_sz, &grh, sizeof(struct ocrdma_grh));
 	if (vlan_enabled)
 		ah->av->valid |= OCRDMA_AV_VLAN_VALID;
+	ah->av->valid = cpu_to_le32(ah->av->valid);
 	return status;
 }
 

drivers/infiniband/hw/ocrdma/ocrdma_hw.c

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

drivers/infiniband/hw/ocrdma/ocrdma_hw.h

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

drivers/infiniband/hw/ocrdma/ocrdma_main.c

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

drivers/infiniband/hw/ocrdma/ocrdma_sli.h

@@ -31,7 +31,7 @@
 #define Bit(_b) (1 << (_b))
 
 #define OCRDMA_GEN1_FAMILY	0xB
-#define OCRDMA_GEN2_FAMILY	0x2
+#define OCRDMA_GEN2_FAMILY	0x0F
 
 #define OCRDMA_SUBSYS_ROCE 10
 enum {
@@ -1694,7 +1694,7 @@ struct ocrdma_grh {
 	u16	rsvd;
 } __packed;
 
-#define OCRDMA_AV_VALID		Bit(0)
+#define OCRDMA_AV_VALID		Bit(7)
 #define OCRDMA_AV_VLAN_VALID	Bit(1)
 
 struct ocrdma_av {

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c

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

drivers/infiniband/hw/qib/qib_qp.c

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

drivers/infiniband/hw/qib/qib_ud.c

@@ -57,13 +57,20 @@ static void qib_ud_loopback(struct qib_qp *sqp, struct qib_swqe *swqe)
 	struct qib_sge *sge;
 	struct ib_wc wc;
 	u32 length;
+	enum ib_qp_type sqptype, dqptype;
 
 	qp = qib_lookup_qpn(ibp, swqe->wr.wr.ud.remote_qpn);
 	if (!qp) {
 		ibp->n_pkt_drops++;
 		return;
 	}
-	if (qp->ibqp.qp_type != sqp->ibqp.qp_type ||
+
+	sqptype = sqp->ibqp.qp_type == IB_QPT_GSI ?
+			IB_QPT_UD : sqp->ibqp.qp_type;
+	dqptype = qp->ibqp.qp_type == IB_QPT_GSI ?
+			IB_QPT_UD : qp->ibqp.qp_type;
+
+	if (dqptype != sqptype ||
 	    !(ib_qib_state_ops[qp->state] & QIB_PROCESS_RECV_OK)) {
 		ibp->n_pkt_drops++;
 		goto drop;

drivers/infiniband/hw/usnic/Kconfig

@@ -0,0 +1,10 @@
+config INFINIBAND_USNIC
+	tristate "Verbs support for Cisco VIC"
+	depends on NETDEVICES && ETHERNET && INET && PCI && INTEL_IOMMU
+	select ENIC
+	select NET_VENDOR_CISCO
+	select PCI_IOV
+	select INFINIBAND_USER_ACCESS
+	---help---
+	  This is a low-level driver for Cisco's Virtual Interface
+	  Cards (VICs), including the VIC 1240 and 1280 cards.

drivers/infiniband/hw/usnic/Makefile

@@ -0,0 +1,15 @@
+ccflags-y := -Idrivers/net/ethernet/cisco/enic
+
+obj-$(CONFIG_INFINIBAND_USNIC)+= usnic_verbs.o
+
+usnic_verbs-y=\
+usnic_fwd.o \
+usnic_transport.o \
+usnic_uiom.o \
+usnic_uiom_interval_tree.o \
+usnic_vnic.o \
+usnic_ib_main.o \
+usnic_ib_qp_grp.o \
+usnic_ib_sysfs.o \
+usnic_ib_verbs.o \
+usnic_debugfs.o \

drivers/infiniband/hw/usnic/usnic.h

@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_H_
+#define USNIC_H_
+
+#define DRV_NAME	"usnic_verbs"
+
+#define PCI_DEVICE_ID_CISCO_VIC_USPACE_NIC	0x00cf	/* User space NIC */
+
+#define DRV_VERSION    "1.0.3"
+#define DRV_RELDATE    "December 19, 2013"
+
+#endif /* USNIC_H_ */

drivers/infiniband/hw/usnic/usnic_abi.h

@@ -0,0 +1,73 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+
+#ifndef USNIC_ABI_H
+#define USNIC_ABI_H
+
+/* ABI between userspace and kernel */
+#define USNIC_UVERBS_ABI_VERSION	4
+
+#define USNIC_QP_GRP_MAX_WQS		8
+#define USNIC_QP_GRP_MAX_RQS		8
+#define USNIC_QP_GRP_MAX_CQS		16
+
+enum usnic_transport_type {
+	USNIC_TRANSPORT_UNKNOWN		= 0,
+	USNIC_TRANSPORT_ROCE_CUSTOM	= 1,
+	USNIC_TRANSPORT_IPV4_UDP	= 2,
+	USNIC_TRANSPORT_MAX		= 3,
+};
+
+struct usnic_transport_spec {
+	enum usnic_transport_type	trans_type;
+	union {
+		struct {
+			uint16_t	port_num;
+		} usnic_roce;
+		struct {
+			uint32_t	sock_fd;
+		} udp;
+	};
+};
+
+struct usnic_ib_create_qp_cmd {
+	struct usnic_transport_spec	spec;
+};
+
+/*TODO: Future - usnic_modify_qp needs to pass in generic filters */
+struct usnic_ib_create_qp_resp {
+	u32				vfid;
+	u32				qp_grp_id;
+	u64				bar_bus_addr;
+	u32				bar_len;
+/*
+ * WQ, RQ, CQ are explicity specified bc exposing a generic resources inteface
+ * expands the scope of ABI to many files.
+ */
+	u32				wq_cnt;
+	u32				rq_cnt;
+	u32				cq_cnt;
+	u32				wq_idx[USNIC_QP_GRP_MAX_WQS];
+	u32				rq_idx[USNIC_QP_GRP_MAX_RQS];
+	u32				cq_idx[USNIC_QP_GRP_MAX_CQS];
+	u32				transport;
+	u32				reserved[9];
+};
+
+#endif /* USNIC_ABI_H */

drivers/infiniband/hw/usnic/usnic_common_pkt_hdr.h

@@ -0,0 +1,27 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_CMN_PKT_HDR_H
+#define USNIC_CMN_PKT_HDR_H
+
+#define USNIC_ROCE_ETHERTYPE		(0x8915)
+#define USNIC_ROCE_GRH_VER              (8)
+#define USNIC_PROTO_VER                 (1)
+#define USNIC_ROCE_GRH_VER_SHIFT        (4)
+
+#endif /* USNIC_COMMON_PKT_HDR_H */

drivers/infiniband/hw/usnic/usnic_common_util.h

@@ -0,0 +1,68 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_CMN_UTIL_H
+#define USNIC_CMN_UTIL_H
+
+static inline void
+usnic_mac_to_gid(const char *const mac, char *raw_gid)
+{
+	raw_gid[0] = 0xfe;
+	raw_gid[1] = 0x80;
+	memset(&raw_gid[2], 0, 6);
+	raw_gid[8] = mac[0]^2;
+	raw_gid[9] = mac[1];
+	raw_gid[10] = mac[2];
+	raw_gid[11] = 0xff;
+	raw_gid[12] = 0xfe;
+	raw_gid[13] = mac[3];
+	raw_gid[14] = mac[4];
+	raw_gid[15] = mac[5];
+}
+
+static inline void
+usnic_mac_ip_to_gid(const char *const mac, const __be32 inaddr, char *raw_gid)
+{
+	raw_gid[0] = 0xfe;
+	raw_gid[1] = 0x80;
+	memset(&raw_gid[2], 0, 2);
+	memcpy(&raw_gid[4], &inaddr, 4);
+	raw_gid[8] = mac[0]^2;
+	raw_gid[9] = mac[1];
+	raw_gid[10] = mac[2];
+	raw_gid[11] = 0xff;
+	raw_gid[12] = 0xfe;
+	raw_gid[13] = mac[3];
+	raw_gid[14] = mac[4];
+	raw_gid[15] = mac[5];
+}
+
+static inline void
+usnic_write_gid_if_id_from_mac(char *mac, char *raw_gid)
+{
+	raw_gid[8] = mac[0]^2;
+	raw_gid[9] = mac[1];
+	raw_gid[10] = mac[2];
+	raw_gid[11] = 0xff;
+	raw_gid[12] = 0xfe;
+	raw_gid[13] = mac[3];
+	raw_gid[14] = mac[4];
+	raw_gid[15] = mac[5];
+}
+
+#endif /* USNIC_COMMON_UTIL_H */

drivers/infiniband/hw/usnic/usnic_debugfs.c

@@ -0,0 +1,154 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/debugfs.h>
+#include <linux/module.h>
+
+#include "usnic.h"
+#include "usnic_log.h"
+#include "usnic_debugfs.h"
+#include "usnic_ib_qp_grp.h"
+#include "usnic_transport.h"
+
+static struct dentry *debugfs_root;
+static struct dentry *flows_dentry;
+
+static ssize_t usnic_debugfs_buildinfo_read(struct file *f, char __user *data,
+						size_t count, loff_t *ppos)
+{
+	char buf[500];
+	int res;
+
+	if (*ppos > 0)
+		return 0;
+
+	res = scnprintf(buf, sizeof(buf),
+			"version:       %s\n"
+			"build date:    %s\n",
+			DRV_VERSION, DRV_RELDATE);
+
+	return simple_read_from_buffer(data, count, ppos, buf, res);
+}
+
+static const struct file_operations usnic_debugfs_buildinfo_ops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = usnic_debugfs_buildinfo_read
+};
+
+static ssize_t flowinfo_read(struct file *f, char __user *data,
+				size_t count, loff_t *ppos)
+{
+	struct usnic_ib_qp_grp_flow *qp_flow;
+	int n;
+	int left;
+	char *ptr;
+	char buf[512];
+
+	qp_flow = f->private_data;
+	ptr = buf;
+	left = count;
+
+	if (*ppos > 0)
+		return 0;
+
+	spin_lock(&qp_flow->qp_grp->lock);
+	n = scnprintf(ptr, left,
+			"QP Grp ID: %d Transport: %s ",
+			qp_flow->qp_grp->grp_id,
+			usnic_transport_to_str(qp_flow->trans_type));
+	UPDATE_PTR_LEFT(n, ptr, left);
+	if (qp_flow->trans_type == USNIC_TRANSPORT_ROCE_CUSTOM) {
+		n = scnprintf(ptr, left, "Port_Num:%hu\n",
+					qp_flow->usnic_roce.port_num);
+		UPDATE_PTR_LEFT(n, ptr, left);
+	} else if (qp_flow->trans_type == USNIC_TRANSPORT_IPV4_UDP) {
+		n = usnic_transport_sock_to_str(ptr, left,
+				qp_flow->udp.sock);
+		UPDATE_PTR_LEFT(n, ptr, left);
+		n = scnprintf(ptr, left, "\n");
+		UPDATE_PTR_LEFT(n, ptr, left);
+	}
+	spin_unlock(&qp_flow->qp_grp->lock);
+
+	return simple_read_from_buffer(data, count, ppos, buf, ptr - buf);
+}
+
+static const struct file_operations flowinfo_ops = {
+	.owner = THIS_MODULE,
+	.open = simple_open,
+	.read = flowinfo_read,
+};
+
+void usnic_debugfs_init(void)
+{
+	debugfs_root = debugfs_create_dir(DRV_NAME, NULL);
+	if (IS_ERR(debugfs_root)) {
+		usnic_err("Failed to create debugfs root dir, check if debugfs is enabled in kernel configuration\n");
+		goto out_clear_root;
+	}
+
+	flows_dentry = debugfs_create_dir("flows", debugfs_root);
+	if (IS_ERR_OR_NULL(flows_dentry)) {
+		usnic_err("Failed to create debugfs flow dir with err %ld\n",
+				PTR_ERR(flows_dentry));
+		goto out_free_root;
+	}
+
+	debugfs_create_file("build-info", S_IRUGO, debugfs_root,
+				NULL, &usnic_debugfs_buildinfo_ops);
+	return;
+
+out_free_root:
+	debugfs_remove_recursive(debugfs_root);
+out_clear_root:
+	debugfs_root = NULL;
+}
+
+void usnic_debugfs_exit(void)
+{
+	if (!debugfs_root)
+		return;
+
+	debugfs_remove_recursive(debugfs_root);
+	debugfs_root = NULL;
+}
+
+void usnic_debugfs_flow_add(struct usnic_ib_qp_grp_flow *qp_flow)
+{
+	if (IS_ERR_OR_NULL(flows_dentry))
+		return;
+
+	scnprintf(qp_flow->dentry_name, sizeof(qp_flow->dentry_name),
+			"%u", qp_flow->flow->flow_id);
+	qp_flow->dbgfs_dentry = debugfs_create_file(qp_flow->dentry_name,
+							S_IRUGO,
+							flows_dentry,
+							qp_flow,
+							&flowinfo_ops);
+	if (IS_ERR_OR_NULL(qp_flow->dbgfs_dentry)) {
+		usnic_err("Failed to create dbg fs entry for flow %u\n",
+				qp_flow->flow->flow_id);
+	}
+}
+
+void usnic_debugfs_flow_remove(struct usnic_ib_qp_grp_flow *qp_flow)
+{
+	if (!IS_ERR_OR_NULL(qp_flow->dbgfs_dentry))
+		debugfs_remove(qp_flow->dbgfs_dentry);
+}

drivers/infiniband/hw/usnic/usnic_debugfs.h

@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+#ifndef USNIC_DEBUGFS_H_
+#define USNIC_DEBUGFS_H_
+
+#include "usnic_ib_qp_grp.h"
+
+void usnic_debugfs_init(void);
+
+void usnic_debugfs_exit(void);
+void usnic_debugfs_flow_add(struct usnic_ib_qp_grp_flow *qp_flow);
+void usnic_debugfs_flow_remove(struct usnic_ib_qp_grp_flow *qp_flow);
+
+#endif /*!USNIC_DEBUGFS_H_ */

drivers/infiniband/hw/usnic/usnic_fwd.c

@@ -0,0 +1,350 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+
+#include "enic_api.h"
+#include "usnic_common_pkt_hdr.h"
+#include "usnic_fwd.h"
+#include "usnic_log.h"
+
+static int usnic_fwd_devcmd_locked(struct usnic_fwd_dev *ufdev, int vnic_idx,
+					enum vnic_devcmd_cmd cmd, u64 *a0,
+					u64 *a1)
+{
+	int status;
+	struct net_device *netdev = ufdev->netdev;
+
+	lockdep_assert_held(&ufdev->lock);
+
+	status = enic_api_devcmd_proxy_by_index(netdev,
+			vnic_idx,
+			cmd,
+			a0, a1,
+			1000);
+	if (status) {
+		if (status == ERR_EINVAL && cmd == CMD_DEL_FILTER) {
+			usnic_dbg("Dev %s vnic idx %u cmd %u already deleted",
+					ufdev->name, vnic_idx, cmd);
+		} else {
+			usnic_err("Dev %s vnic idx %u cmd %u failed with status %d\n",
+					ufdev->name, vnic_idx, cmd,
+					status);
+		}
+	} else {
+		usnic_dbg("Dev %s vnic idx %u cmd %u success",
+				ufdev->name, vnic_idx, cmd);
+	}
+
+	return status;
+}
+
+static int usnic_fwd_devcmd(struct usnic_fwd_dev *ufdev, int vnic_idx,
+				enum vnic_devcmd_cmd cmd, u64 *a0, u64 *a1)
+{
+	int status;
+
+	spin_lock(&ufdev->lock);
+	status = usnic_fwd_devcmd_locked(ufdev, vnic_idx, cmd, a0, a1);
+	spin_unlock(&ufdev->lock);
+
+	return status;
+}
+
+struct usnic_fwd_dev *usnic_fwd_dev_alloc(struct pci_dev *pdev)
+{
+	struct usnic_fwd_dev *ufdev;
+
+	ufdev = kzalloc(sizeof(*ufdev), GFP_KERNEL);
+	if (!ufdev)
+		return NULL;
+
+	ufdev->pdev = pdev;
+	ufdev->netdev = pci_get_drvdata(pdev);
+	spin_lock_init(&ufdev->lock);
+	strncpy(ufdev->name, netdev_name(ufdev->netdev),
+			sizeof(ufdev->name) - 1);
+
+	return ufdev;
+}
+
+void usnic_fwd_dev_free(struct usnic_fwd_dev *ufdev)
+{
+	kfree(ufdev);
+}
+
+void usnic_fwd_set_mac(struct usnic_fwd_dev *ufdev, char mac[ETH_ALEN])
+{
+	spin_lock(&ufdev->lock);
+	memcpy(&ufdev->mac, mac, sizeof(ufdev->mac));
+	spin_unlock(&ufdev->lock);
+}
+
+int usnic_fwd_add_ipaddr(struct usnic_fwd_dev *ufdev, __be32 inaddr)
+{
+	int status;
+
+	spin_lock(&ufdev->lock);
+	if (ufdev->inaddr == 0) {
+		ufdev->inaddr = inaddr;
+		status = 0;
+	} else {
+		status = -EFAULT;
+	}
+	spin_unlock(&ufdev->lock);
+
+	return status;
+}
+
+void usnic_fwd_del_ipaddr(struct usnic_fwd_dev *ufdev)
+{
+	spin_lock(&ufdev->lock);
+	ufdev->inaddr = 0;
+	spin_unlock(&ufdev->lock);
+}
+
+void usnic_fwd_carrier_up(struct usnic_fwd_dev *ufdev)
+{
+	spin_lock(&ufdev->lock);
+	ufdev->link_up = 1;
+	spin_unlock(&ufdev->lock);
+}
+
+void usnic_fwd_carrier_down(struct usnic_fwd_dev *ufdev)
+{
+	spin_lock(&ufdev->lock);
+	ufdev->link_up = 0;
+	spin_unlock(&ufdev->lock);
+}
+
+void usnic_fwd_set_mtu(struct usnic_fwd_dev *ufdev, unsigned int mtu)
+{
+	spin_lock(&ufdev->lock);
+	ufdev->mtu = mtu;
+	spin_unlock(&ufdev->lock);
+}
+
+static int usnic_fwd_dev_ready_locked(struct usnic_fwd_dev *ufdev)
+{
+	lockdep_assert_held(&ufdev->lock);
+
+	if (!ufdev->link_up)
+		return -EPERM;
+
+	return 0;
+}
+
+static int validate_filter_locked(struct usnic_fwd_dev *ufdev,
+					struct filter *filter)
+{
+
+	lockdep_assert_held(&ufdev->lock);
+
+	if (filter->type == FILTER_IPV4_5TUPLE) {
+		if (!(filter->u.ipv4.flags & FILTER_FIELD_5TUP_DST_AD))
+			return -EACCES;
+		if (!(filter->u.ipv4.flags & FILTER_FIELD_5TUP_DST_PT))
+			return -EBUSY;
+		else if (ufdev->inaddr == 0)
+			return -EINVAL;
+		else if (filter->u.ipv4.dst_port == 0)
+			return -ERANGE;
+		else if (ntohl(ufdev->inaddr) != filter->u.ipv4.dst_addr)
+			return -EFAULT;
+		else
+			return 0;
+	}
+
+	return 0;
+}
+
+static void fill_tlv(struct filter_tlv *tlv, struct filter *filter,
+		struct filter_action *action)
+{
+	tlv->type = CLSF_TLV_FILTER;
+	tlv->length = sizeof(struct filter);
+	*((struct filter *)&tlv->val) = *filter;
+
+	tlv = (struct filter_tlv *)((char *)tlv + sizeof(struct filter_tlv) +
+			sizeof(struct filter));
+	tlv->type = CLSF_TLV_ACTION;
+	tlv->length = sizeof(struct filter_action);
+	*((struct filter_action *)&tlv->val) = *action;
+}
+
+struct usnic_fwd_flow*
+usnic_fwd_alloc_flow(struct usnic_fwd_dev *ufdev, struct filter *filter,
+				struct usnic_filter_action *uaction)
+{
+	struct filter_tlv *tlv;
+	struct pci_dev *pdev;
+	struct usnic_fwd_flow *flow;
+	uint64_t a0, a1;
+	uint64_t tlv_size;
+	dma_addr_t tlv_pa;
+	int status;
+
+	pdev = ufdev->pdev;
+	tlv_size = (2*sizeof(struct filter_tlv) + sizeof(struct filter) +
+			sizeof(struct filter_action));
+
+	flow = kzalloc(sizeof(*flow), GFP_ATOMIC);
+	if (!flow)
+		return ERR_PTR(-ENOMEM);
+
+	tlv = pci_alloc_consistent(pdev, tlv_size, &tlv_pa);
+	if (!tlv) {
+		usnic_err("Failed to allocate memory\n");
+		status = -ENOMEM;
+		goto out_free_flow;
+	}
+
+	fill_tlv(tlv, filter, &uaction->action);
+
+	spin_lock(&ufdev->lock);
+	status = usnic_fwd_dev_ready_locked(ufdev);
+	if (status) {
+		usnic_err("Forwarding dev %s not ready with status %d\n",
+				ufdev->name, status);
+		goto out_free_tlv;
+	}
+
+	status = validate_filter_locked(ufdev, filter);
+	if (status) {
+		usnic_err("Failed to validate filter with status %d\n",
+				status);
+		goto out_free_tlv;
+	}
+
+	/* Issue Devcmd */
+	a0 = tlv_pa;
+	a1 = tlv_size;
+	status = usnic_fwd_devcmd_locked(ufdev, uaction->vnic_idx,
+						CMD_ADD_FILTER, &a0, &a1);
+	if (status) {
+		usnic_err("VF %s Filter add failed with status:%d",
+				ufdev->name, status);
+		status = -EFAULT;
+		goto out_free_tlv;
+	} else {
+		usnic_dbg("VF %s FILTER ID:%llu", ufdev->name, a0);
+	}
+
+	flow->flow_id = (uint32_t) a0;
+	flow->vnic_idx = uaction->vnic_idx;
+	flow->ufdev = ufdev;
+
+out_free_tlv:
+	spin_unlock(&ufdev->lock);
+	pci_free_consistent(pdev, tlv_size, tlv, tlv_pa);
+	if (!status)
+		return flow;
+out_free_flow:
+	kfree(flow);
+	return ERR_PTR(status);
+}
+
+int usnic_fwd_dealloc_flow(struct usnic_fwd_flow *flow)
+{
+	int status;
+	u64 a0, a1;
+
+	a0 = flow->flow_id;
+
+	status = usnic_fwd_devcmd(flow->ufdev, flow->vnic_idx,
+					CMD_DEL_FILTER, &a0, &a1);
+	if (status) {
+		if (status == ERR_EINVAL) {
+			usnic_dbg("Filter %u already deleted for VF Idx %u pf: %s status: %d",
+					flow->flow_id, flow->vnic_idx,
+					flow->ufdev->name, status);
+		} else {
+			usnic_err("PF %s VF Idx %u Filter: %u FILTER DELETE failed with status %d",
+					flow->ufdev->name, flow->vnic_idx,
+					flow->flow_id, status);
+		}
+		status = 0;
+		/*
+		 * Log the error and fake success to the caller because if
+		 * a flow fails to be deleted in the firmware, it is an
+		 * unrecoverable error.
+		 */
+	} else {
+		usnic_dbg("PF %s VF Idx %u Filter: %u FILTER DELETED",
+				flow->ufdev->name, flow->vnic_idx,
+				flow->flow_id);
+	}
+
+	kfree(flow);
+	return status;
+}
+
+int usnic_fwd_enable_qp(struct usnic_fwd_dev *ufdev, int vnic_idx, int qp_idx)
+{
+	int status;
+	struct net_device *pf_netdev;
+	u64 a0, a1;
+
+	pf_netdev = ufdev->netdev;
+	a0 = qp_idx;
+	a1 = CMD_QP_RQWQ;
+
+	status = usnic_fwd_devcmd(ufdev, vnic_idx, CMD_QP_ENABLE,
+						&a0, &a1);
+	if (status) {
+		usnic_err("PF %s VNIC Index %u RQ Index: %u ENABLE Failed with status %d",
+				netdev_name(pf_netdev),
+				vnic_idx,
+				qp_idx,
+				status);
+	} else {
+		usnic_dbg("PF %s VNIC Index %u RQ Index: %u ENABLED",
+				netdev_name(pf_netdev),
+				vnic_idx, qp_idx);
+	}
+
+	return status;
+}
+
+int usnic_fwd_disable_qp(struct usnic_fwd_dev *ufdev, int vnic_idx, int qp_idx)
+{
+	int status;
+	u64 a0, a1;
+	struct net_device *pf_netdev;
+
+	pf_netdev = ufdev->netdev;
+	a0 = qp_idx;
+	a1 = CMD_QP_RQWQ;
+
+	status = usnic_fwd_devcmd(ufdev, vnic_idx, CMD_QP_DISABLE,
+			&a0, &a1);
+	if (status) {
+		usnic_err("PF %s VNIC Index %u RQ Index: %u DISABLE Failed with status %d",
+				netdev_name(pf_netdev),
+				vnic_idx,
+				qp_idx,
+				status);
+	} else {
+		usnic_dbg("PF %s VNIC Index %u RQ Index: %u DISABLED",
+				netdev_name(pf_netdev),
+				vnic_idx,
+				qp_idx);
+	}
+
+	return status;
+}

drivers/infiniband/hw/usnic/usnic_fwd.h

@@ -0,0 +1,113 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_FWD_H_
+#define USNIC_FWD_H_
+
+#include <linux/if.h>
+#include <linux/netdevice.h>
+#include <linux/pci.h>
+#include <linux/in.h>
+
+#include "usnic_abi.h"
+#include "usnic_common_pkt_hdr.h"
+#include "vnic_devcmd.h"
+
+struct usnic_fwd_dev {
+	struct pci_dev			*pdev;
+	struct net_device		*netdev;
+	spinlock_t			lock;
+	/*
+	 * The following fields can be read directly off the device.
+	 * However, they should be set by a accessor function, except name,
+	 * which cannot be changed.
+	 */
+	bool				link_up;
+	char				mac[ETH_ALEN];
+	unsigned int			mtu;
+	__be32				inaddr;
+	char				name[IFNAMSIZ+1];
+};
+
+struct usnic_fwd_flow {
+	uint32_t			flow_id;
+	struct usnic_fwd_dev		*ufdev;
+	unsigned int			vnic_idx;
+};
+
+struct usnic_filter_action {
+	int				vnic_idx;
+	struct filter_action		action;
+};
+
+struct usnic_fwd_dev *usnic_fwd_dev_alloc(struct pci_dev *pdev);
+void usnic_fwd_dev_free(struct usnic_fwd_dev *ufdev);
+
+void usnic_fwd_set_mac(struct usnic_fwd_dev *ufdev, char mac[ETH_ALEN]);
+int usnic_fwd_add_ipaddr(struct usnic_fwd_dev *ufdev, __be32 inaddr);
+void usnic_fwd_del_ipaddr(struct usnic_fwd_dev *ufdev);
+void usnic_fwd_carrier_up(struct usnic_fwd_dev *ufdev);
+void usnic_fwd_carrier_down(struct usnic_fwd_dev *ufdev);
+void usnic_fwd_set_mtu(struct usnic_fwd_dev *ufdev, unsigned int mtu);
+
+/*
+ * Allocate a flow on this forwarding device. Whoever calls this function,
+ * must monitor netdev events on ufdev's netdevice. If NETDEV_REBOOT or
+ * NETDEV_DOWN is seen, flow will no longer function and must be
+ * immediately freed by calling usnic_dealloc_flow.
+ */
+struct usnic_fwd_flow*
+usnic_fwd_alloc_flow(struct usnic_fwd_dev *ufdev, struct filter *filter,
+				struct usnic_filter_action *action);
+int usnic_fwd_dealloc_flow(struct usnic_fwd_flow *flow);
+int usnic_fwd_enable_qp(struct usnic_fwd_dev *ufdev, int vnic_idx, int qp_idx);
+int usnic_fwd_disable_qp(struct usnic_fwd_dev *ufdev, int vnic_idx, int qp_idx);
+
+static inline void usnic_fwd_init_usnic_filter(struct filter *filter,
+						uint32_t usnic_id)
+{
+	filter->type = FILTER_USNIC_ID;
+	filter->u.usnic.ethtype = USNIC_ROCE_ETHERTYPE;
+	filter->u.usnic.flags = FILTER_FIELD_USNIC_ETHTYPE |
+				FILTER_FIELD_USNIC_ID |
+				FILTER_FIELD_USNIC_PROTO;
+	filter->u.usnic.proto_version = (USNIC_ROCE_GRH_VER <<
+					 USNIC_ROCE_GRH_VER_SHIFT) |
+					 USNIC_PROTO_VER;
+	filter->u.usnic.usnic_id = usnic_id;
+}
+
+static inline void usnic_fwd_init_udp_filter(struct filter *filter,
+						uint32_t daddr, uint16_t dport)
+{
+	filter->type = FILTER_IPV4_5TUPLE;
+	filter->u.ipv4.flags = FILTER_FIELD_5TUP_PROTO;
+	filter->u.ipv4.protocol = PROTO_UDP;
+
+	if (daddr) {
+		filter->u.ipv4.flags |= FILTER_FIELD_5TUP_DST_AD;
+		filter->u.ipv4.dst_addr = daddr;
+	}
+
+	if (dport) {
+		filter->u.ipv4.flags |= FILTER_FIELD_5TUP_DST_PT;
+		filter->u.ipv4.dst_port = dport;
+	}
+}
+
+#endif /* !USNIC_FWD_H_ */

drivers/infiniband/hw/usnic/usnic_ib.h

@@ -0,0 +1,118 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_IB_H_
+#define USNIC_IB_H_
+
+#include <linux/iommu.h>
+#include <linux/netdevice.h>
+
+#include <rdma/ib_verbs.h>
+
+
+#include "usnic.h"
+#include "usnic_abi.h"
+#include "usnic_vnic.h"
+
+#define USNIC_IB_PORT_CNT		1
+#define USNIC_IB_NUM_COMP_VECTORS	1
+
+extern unsigned int usnic_ib_share_vf;
+
+struct usnic_ib_ucontext {
+	struct ib_ucontext		ibucontext;
+	/* Protected by usnic_ib_dev->usdev_lock */
+	struct list_head		qp_grp_list;
+	struct list_head		link;
+};
+
+struct usnic_ib_pd {
+	struct ib_pd			ibpd;
+	struct usnic_uiom_pd		*umem_pd;
+};
+
+struct usnic_ib_mr {
+	struct ib_mr			ibmr;
+	struct usnic_uiom_reg		*umem;
+};
+
+struct usnic_ib_dev {
+	struct ib_device		ib_dev;
+	struct pci_dev			*pdev;
+	struct net_device		*netdev;
+	struct usnic_fwd_dev		*ufdev;
+	struct list_head		ib_dev_link;
+	struct list_head		vf_dev_list;
+	struct list_head		ctx_list;
+	struct mutex			usdev_lock;
+
+	/* provisioning information */
+	struct kref			vf_cnt;
+	unsigned int			vf_res_cnt[USNIC_VNIC_RES_TYPE_MAX];
+
+	/* sysfs vars for QPN reporting */
+	struct kobject *qpn_kobj;
+};
+
+struct usnic_ib_vf {
+	struct usnic_ib_dev		*pf;
+	spinlock_t			lock;
+	struct usnic_vnic		*vnic;
+	unsigned int			qp_grp_ref_cnt;
+	struct usnic_ib_pd		*pd;
+	struct list_head		link;
+};
+
+static inline
+struct usnic_ib_dev *to_usdev(struct ib_device *ibdev)
+{
+	return container_of(ibdev, struct usnic_ib_dev, ib_dev);
+}
+
+static inline
+struct usnic_ib_ucontext *to_ucontext(struct ib_ucontext *ibucontext)
+{
+	return container_of(ibucontext, struct usnic_ib_ucontext, ibucontext);
+}
+
+static inline
+struct usnic_ib_pd *to_upd(struct ib_pd *ibpd)
+{
+	return container_of(ibpd, struct usnic_ib_pd, ibpd);
+}
+
+static inline
+struct usnic_ib_ucontext *to_uucontext(struct ib_ucontext *ibucontext)
+{
+	return container_of(ibucontext, struct usnic_ib_ucontext, ibucontext);
+}
+
+static inline
+struct usnic_ib_mr *to_umr(struct ib_mr *ibmr)
+{
+	return container_of(ibmr, struct usnic_ib_mr, ibmr);
+}
+void usnic_ib_log_vf(struct usnic_ib_vf *vf);
+
+#define UPDATE_PTR_LEFT(N, P, L)			\
+do {							\
+	L -= (N);					\
+	P += (N);					\
+} while (0)
+
+#endif /* USNIC_IB_H_ */

drivers/infiniband/hw/usnic/usnic_ib_main.c

@@ -0,0 +1,682 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ * Author: Upinder Malhi <umalhi@cisco.com>
+ * Author: Anant Deepak <anadeepa@cisco.com>
+ * Author: Cesare Cantu' <cantuc@cisco.com>
+ * Author: Jeff Squyres <jsquyres@cisco.com>
+ * Author: Kiran Thirumalai <kithirum@cisco.com>
+ * Author: Xuyang Wang <xuywang@cisco.com>
+ * Author: Reese Faucette <rfaucett@cisco.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/inetdevice.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/pci.h>
+#include <linux/netdevice.h>
+
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_addr.h>
+
+#include "usnic_abi.h"
+#include "usnic_common_util.h"
+#include "usnic_ib.h"
+#include "usnic_ib_qp_grp.h"
+#include "usnic_log.h"
+#include "usnic_fwd.h"
+#include "usnic_debugfs.h"
+#include "usnic_ib_verbs.h"
+#include "usnic_transport.h"
+#include "usnic_uiom.h"
+#include "usnic_ib_sysfs.h"
+
+unsigned int usnic_log_lvl = USNIC_LOG_LVL_ERR;
+unsigned int usnic_ib_share_vf = 1;
+
+static const char usnic_version[] =
+	DRV_NAME ": Cisco VIC (USNIC) Verbs Driver v"
+	DRV_VERSION " (" DRV_RELDATE ")\n";
+
+static DEFINE_MUTEX(usnic_ib_ibdev_list_lock);
+static LIST_HEAD(usnic_ib_ibdev_list);
+
+/* Callback dump funcs */
+static int usnic_ib_dump_vf_hdr(void *obj, char *buf, int buf_sz)
+{
+	struct usnic_ib_vf *vf = obj;
+	return scnprintf(buf, buf_sz, "PF: %s ", vf->pf->ib_dev.name);
+}
+/* End callback dump funcs */
+
+static void usnic_ib_dump_vf(struct usnic_ib_vf *vf, char *buf, int buf_sz)
+{
+	usnic_vnic_dump(vf->vnic, buf, buf_sz, vf,
+			usnic_ib_dump_vf_hdr,
+			usnic_ib_qp_grp_dump_hdr, usnic_ib_qp_grp_dump_rows);
+}
+
+void usnic_ib_log_vf(struct usnic_ib_vf *vf)
+{
+	char buf[1000];
+	usnic_ib_dump_vf(vf, buf, sizeof(buf));
+	usnic_dbg("%s\n", buf);
+}
+
+/* Start of netdev section */
+static inline const char *usnic_ib_netdev_event_to_string(unsigned long event)
+{
+	const char *event2str[] = {"NETDEV_NONE", "NETDEV_UP", "NETDEV_DOWN",
+		"NETDEV_REBOOT", "NETDEV_CHANGE",
+		"NETDEV_REGISTER", "NETDEV_UNREGISTER", "NETDEV_CHANGEMTU",
+		"NETDEV_CHANGEADDR", "NETDEV_GOING_DOWN", "NETDEV_FEAT_CHANGE",
+		"NETDEV_BONDING_FAILOVER", "NETDEV_PRE_UP",
+		"NETDEV_PRE_TYPE_CHANGE", "NETDEV_POST_TYPE_CHANGE",
+		"NETDEV_POST_INT", "NETDEV_UNREGISTER_FINAL", "NETDEV_RELEASE",
+		"NETDEV_NOTIFY_PEERS", "NETDEV_JOIN"
+	};
+
+	if (event >= ARRAY_SIZE(event2str))
+		return "UNKNOWN_NETDEV_EVENT";
+	else
+		return event2str[event];
+}
+
+static void usnic_ib_qp_grp_modify_active_to_err(struct usnic_ib_dev *us_ibdev)
+{
+	struct usnic_ib_ucontext *ctx;
+	struct usnic_ib_qp_grp *qp_grp;
+	enum ib_qp_state cur_state;
+	int status;
+
+	BUG_ON(!mutex_is_locked(&us_ibdev->usdev_lock));
+
+	list_for_each_entry(ctx, &us_ibdev->ctx_list, link) {
+		list_for_each_entry(qp_grp, &ctx->qp_grp_list, link) {
+			cur_state = qp_grp->state;
+			if (cur_state == IB_QPS_INIT ||
+				cur_state == IB_QPS_RTR ||
+				cur_state == IB_QPS_RTS) {
+				status = usnic_ib_qp_grp_modify(qp_grp,
+								IB_QPS_ERR,
+								NULL);
+				if (status) {
+					usnic_err("Failed to transistion qp grp %u from %s to %s\n",
+						qp_grp->grp_id,
+						usnic_ib_qp_grp_state_to_string
+						(cur_state),
+						usnic_ib_qp_grp_state_to_string
+						(IB_QPS_ERR));
+				}
+			}
+		}
+	}
+}
+
+static void usnic_ib_handle_usdev_event(struct usnic_ib_dev *us_ibdev,
+					unsigned long event)
+{
+	struct net_device *netdev;
+	struct ib_event ib_event;
+
+	memset(&ib_event, 0, sizeof(ib_event));
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	netdev = us_ibdev->netdev;
+	switch (event) {
+	case NETDEV_REBOOT:
+		usnic_info("PF Reset on %s\n", us_ibdev->ib_dev.name);
+		usnic_ib_qp_grp_modify_active_to_err(us_ibdev);
+		ib_event.event = IB_EVENT_PORT_ERR;
+		ib_event.device = &us_ibdev->ib_dev;
+		ib_event.element.port_num = 1;
+		ib_dispatch_event(&ib_event);
+		break;
+	case NETDEV_UP:
+	case NETDEV_DOWN:
+	case NETDEV_CHANGE:
+		if (!us_ibdev->ufdev->link_up &&
+				netif_carrier_ok(netdev)) {
+			usnic_fwd_carrier_up(us_ibdev->ufdev);
+			usnic_info("Link UP on %s\n", us_ibdev->ib_dev.name);
+			ib_event.event = IB_EVENT_PORT_ACTIVE;
+			ib_event.device = &us_ibdev->ib_dev;
+			ib_event.element.port_num = 1;
+			ib_dispatch_event(&ib_event);
+		} else if (us_ibdev->ufdev->link_up &&
+				!netif_carrier_ok(netdev)) {
+			usnic_fwd_carrier_down(us_ibdev->ufdev);
+			usnic_info("Link DOWN on %s\n", us_ibdev->ib_dev.name);
+			usnic_ib_qp_grp_modify_active_to_err(us_ibdev);
+			ib_event.event = IB_EVENT_PORT_ERR;
+			ib_event.device = &us_ibdev->ib_dev;
+			ib_event.element.port_num = 1;
+			ib_dispatch_event(&ib_event);
+		} else {
+			usnic_dbg("Ignoring %s on %s\n",
+					usnic_ib_netdev_event_to_string(event),
+					us_ibdev->ib_dev.name);
+		}
+		break;
+	case NETDEV_CHANGEADDR:
+		if (!memcmp(us_ibdev->ufdev->mac, netdev->dev_addr,
+				sizeof(us_ibdev->ufdev->mac))) {
+			usnic_dbg("Ignoring addr change on %s\n",
+					us_ibdev->ib_dev.name);
+		} else {
+			usnic_info(" %s old mac: %pM new mac: %pM\n",
+					us_ibdev->ib_dev.name,
+					us_ibdev->ufdev->mac,
+					netdev->dev_addr);
+			usnic_fwd_set_mac(us_ibdev->ufdev, netdev->dev_addr);
+			usnic_ib_qp_grp_modify_active_to_err(us_ibdev);
+			ib_event.event = IB_EVENT_GID_CHANGE;
+			ib_event.device = &us_ibdev->ib_dev;
+			ib_event.element.port_num = 1;
+			ib_dispatch_event(&ib_event);
+		}
+
+		break;
+	case NETDEV_CHANGEMTU:
+		if (us_ibdev->ufdev->mtu != netdev->mtu) {
+			usnic_info("MTU Change on %s old: %u new: %u\n",
+					us_ibdev->ib_dev.name,
+					us_ibdev->ufdev->mtu, netdev->mtu);
+			usnic_fwd_set_mtu(us_ibdev->ufdev, netdev->mtu);
+			usnic_ib_qp_grp_modify_active_to_err(us_ibdev);
+		} else {
+			usnic_dbg("Ignoring MTU change on %s\n",
+					us_ibdev->ib_dev.name);
+		}
+		break;
+	default:
+		usnic_dbg("Ignoring event %s on %s",
+				usnic_ib_netdev_event_to_string(event),
+				us_ibdev->ib_dev.name);
+	}
+	mutex_unlock(&us_ibdev->usdev_lock);
+}
+
+static int usnic_ib_netdevice_event(struct notifier_block *notifier,
+					unsigned long event, void *ptr)
+{
+	struct usnic_ib_dev *us_ibdev;
+
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	mutex_lock(&usnic_ib_ibdev_list_lock);
+	list_for_each_entry(us_ibdev, &usnic_ib_ibdev_list, ib_dev_link) {
+		if (us_ibdev->netdev == netdev) {
+			usnic_ib_handle_usdev_event(us_ibdev, event);
+			break;
+		}
+	}
+	mutex_unlock(&usnic_ib_ibdev_list_lock);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block usnic_ib_netdevice_notifier = {
+	.notifier_call = usnic_ib_netdevice_event
+};
+/* End of netdev section */
+
+/* Start of inet section */
+static int usnic_ib_handle_inet_event(struct usnic_ib_dev *us_ibdev,
+					unsigned long event, void *ptr)
+{
+	struct in_ifaddr *ifa = ptr;
+	struct ib_event ib_event;
+
+	mutex_lock(&us_ibdev->usdev_lock);
+
+	switch (event) {
+	case NETDEV_DOWN:
+		usnic_info("%s via ip notifiers",
+				usnic_ib_netdev_event_to_string(event));
+		usnic_fwd_del_ipaddr(us_ibdev->ufdev);
+		usnic_ib_qp_grp_modify_active_to_err(us_ibdev);
+		ib_event.event = IB_EVENT_GID_CHANGE;
+		ib_event.device = &us_ibdev->ib_dev;
+		ib_event.element.port_num = 1;
+		ib_dispatch_event(&ib_event);
+		break;
+	case NETDEV_UP:
+		usnic_fwd_add_ipaddr(us_ibdev->ufdev, ifa->ifa_address);
+		usnic_info("%s via ip notifiers: ip %pI4",
+				usnic_ib_netdev_event_to_string(event),
+				&us_ibdev->ufdev->inaddr);
+		ib_event.event = IB_EVENT_GID_CHANGE;
+		ib_event.device = &us_ibdev->ib_dev;
+		ib_event.element.port_num = 1;
+		ib_dispatch_event(&ib_event);
+		break;
+	default:
+		usnic_info("Ignoring event %s on %s",
+				usnic_ib_netdev_event_to_string(event),
+				us_ibdev->ib_dev.name);
+	}
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return NOTIFY_DONE;
+}
+
+static int usnic_ib_inetaddr_event(struct notifier_block *notifier,
+					unsigned long event, void *ptr)
+{
+	struct usnic_ib_dev *us_ibdev;
+	struct in_ifaddr *ifa = ptr;
+	struct net_device *netdev = ifa->ifa_dev->dev;
+
+	mutex_lock(&usnic_ib_ibdev_list_lock);
+	list_for_each_entry(us_ibdev, &usnic_ib_ibdev_list, ib_dev_link) {
+		if (us_ibdev->netdev == netdev) {
+			usnic_ib_handle_inet_event(us_ibdev, event, ptr);
+			break;
+		}
+	}
+	mutex_unlock(&usnic_ib_ibdev_list_lock);
+
+	return NOTIFY_DONE;
+}
+static struct notifier_block usnic_ib_inetaddr_notifier = {
+	.notifier_call = usnic_ib_inetaddr_event
+};
+/* End of inet section*/
+
+/* Start of PF discovery section */
+static void *usnic_ib_device_add(struct pci_dev *dev)
+{
+	struct usnic_ib_dev *us_ibdev;
+	union ib_gid gid;
+	struct in_ifaddr *in;
+	struct net_device *netdev;
+
+	usnic_dbg("\n");
+	netdev = pci_get_drvdata(dev);
+
+	us_ibdev = (struct usnic_ib_dev *)ib_alloc_device(sizeof(*us_ibdev));
+	if (IS_ERR_OR_NULL(us_ibdev)) {
+		usnic_err("Device %s context alloc failed\n",
+				netdev_name(pci_get_drvdata(dev)));
+		return ERR_PTR(us_ibdev ? PTR_ERR(us_ibdev) : -EFAULT);
+	}
+
+	us_ibdev->ufdev = usnic_fwd_dev_alloc(dev);
+	if (IS_ERR_OR_NULL(us_ibdev->ufdev)) {
+		usnic_err("Failed to alloc ufdev for %s with err %ld\n",
+				pci_name(dev), PTR_ERR(us_ibdev->ufdev));
+		goto err_dealloc;
+	}
+
+	mutex_init(&us_ibdev->usdev_lock);
+	INIT_LIST_HEAD(&us_ibdev->vf_dev_list);
+	INIT_LIST_HEAD(&us_ibdev->ctx_list);
+
+	us_ibdev->pdev = dev;
+	us_ibdev->netdev = pci_get_drvdata(dev);
+	us_ibdev->ib_dev.owner = THIS_MODULE;
+	us_ibdev->ib_dev.node_type = RDMA_NODE_USNIC_UDP;
+	us_ibdev->ib_dev.phys_port_cnt = USNIC_IB_PORT_CNT;
+	us_ibdev->ib_dev.num_comp_vectors = USNIC_IB_NUM_COMP_VECTORS;
+	us_ibdev->ib_dev.dma_device = &dev->dev;
+	us_ibdev->ib_dev.uverbs_abi_ver = USNIC_UVERBS_ABI_VERSION;
+	strlcpy(us_ibdev->ib_dev.name, "usnic_%d", IB_DEVICE_NAME_MAX);
+
+	us_ibdev->ib_dev.uverbs_cmd_mask =
+		(1ull << IB_USER_VERBS_CMD_GET_CONTEXT) |
+		(1ull << IB_USER_VERBS_CMD_QUERY_DEVICE) |
+		(1ull << IB_USER_VERBS_CMD_QUERY_PORT) |
+		(1ull << IB_USER_VERBS_CMD_ALLOC_PD) |
+		(1ull << IB_USER_VERBS_CMD_DEALLOC_PD) |
+		(1ull << IB_USER_VERBS_CMD_REG_MR) |
+		(1ull << IB_USER_VERBS_CMD_DEREG_MR) |
+		(1ull << IB_USER_VERBS_CMD_CREATE_COMP_CHANNEL) |
+		(1ull << IB_USER_VERBS_CMD_CREATE_CQ) |
+		(1ull << IB_USER_VERBS_CMD_DESTROY_CQ) |
+		(1ull << IB_USER_VERBS_CMD_CREATE_QP) |
+		(1ull << IB_USER_VERBS_CMD_MODIFY_QP) |
+		(1ull << IB_USER_VERBS_CMD_QUERY_QP) |
+		(1ull << IB_USER_VERBS_CMD_DESTROY_QP) |
+		(1ull << IB_USER_VERBS_CMD_ATTACH_MCAST) |
+		(1ull << IB_USER_VERBS_CMD_DETACH_MCAST) |
+		(1ull << IB_USER_VERBS_CMD_OPEN_QP);
+
+	us_ibdev->ib_dev.query_device = usnic_ib_query_device;
+	us_ibdev->ib_dev.query_port = usnic_ib_query_port;
+	us_ibdev->ib_dev.query_pkey = usnic_ib_query_pkey;
+	us_ibdev->ib_dev.query_gid = usnic_ib_query_gid;
+	us_ibdev->ib_dev.get_link_layer = usnic_ib_port_link_layer;
+	us_ibdev->ib_dev.alloc_pd = usnic_ib_alloc_pd;
+	us_ibdev->ib_dev.dealloc_pd = usnic_ib_dealloc_pd;
+	us_ibdev->ib_dev.create_qp = usnic_ib_create_qp;
+	us_ibdev->ib_dev.modify_qp = usnic_ib_modify_qp;
+	us_ibdev->ib_dev.query_qp = usnic_ib_query_qp;
+	us_ibdev->ib_dev.destroy_qp = usnic_ib_destroy_qp;
+	us_ibdev->ib_dev.create_cq = usnic_ib_create_cq;
+	us_ibdev->ib_dev.destroy_cq = usnic_ib_destroy_cq;
+	us_ibdev->ib_dev.reg_user_mr = usnic_ib_reg_mr;
+	us_ibdev->ib_dev.dereg_mr = usnic_ib_dereg_mr;
+	us_ibdev->ib_dev.alloc_ucontext = usnic_ib_alloc_ucontext;
+	us_ibdev->ib_dev.dealloc_ucontext = usnic_ib_dealloc_ucontext;
+	us_ibdev->ib_dev.mmap = usnic_ib_mmap;
+	us_ibdev->ib_dev.create_ah = usnic_ib_create_ah;
+	us_ibdev->ib_dev.destroy_ah = usnic_ib_destroy_ah;
+	us_ibdev->ib_dev.post_send = usnic_ib_post_send;
+	us_ibdev->ib_dev.post_recv = usnic_ib_post_recv;
+	us_ibdev->ib_dev.poll_cq = usnic_ib_poll_cq;
+	us_ibdev->ib_dev.req_notify_cq = usnic_ib_req_notify_cq;
+	us_ibdev->ib_dev.get_dma_mr = usnic_ib_get_dma_mr;
+
+
+	if (ib_register_device(&us_ibdev->ib_dev, NULL))
+		goto err_fwd_dealloc;
+
+	usnic_fwd_set_mtu(us_ibdev->ufdev, us_ibdev->netdev->mtu);
+	usnic_fwd_set_mac(us_ibdev->ufdev, us_ibdev->netdev->dev_addr);
+	if (netif_carrier_ok(us_ibdev->netdev))
+		usnic_fwd_carrier_up(us_ibdev->ufdev);
+
+	in = ((struct in_device *)(netdev->ip_ptr))->ifa_list;
+	if (in != NULL)
+		usnic_fwd_add_ipaddr(us_ibdev->ufdev, in->ifa_address);
+
+	usnic_mac_ip_to_gid(us_ibdev->netdev->perm_addr,
+				us_ibdev->ufdev->inaddr, &gid.raw[0]);
+	memcpy(&us_ibdev->ib_dev.node_guid, &gid.global.interface_id,
+		sizeof(gid.global.interface_id));
+	kref_init(&us_ibdev->vf_cnt);
+
+	usnic_info("Added ibdev: %s netdev: %s with mac %pM Link: %u MTU: %u\n",
+			us_ibdev->ib_dev.name, netdev_name(us_ibdev->netdev),
+			us_ibdev->ufdev->mac, us_ibdev->ufdev->link_up,
+			us_ibdev->ufdev->mtu);
+	return us_ibdev;
+
+err_fwd_dealloc:
+	usnic_fwd_dev_free(us_ibdev->ufdev);
+err_dealloc:
+	usnic_err("failed -- deallocing device\n");
+	ib_dealloc_device(&us_ibdev->ib_dev);
+	return NULL;
+}
+
+static void usnic_ib_device_remove(struct usnic_ib_dev *us_ibdev)
+{
+	usnic_info("Unregistering %s\n", us_ibdev->ib_dev.name);
+	usnic_ib_sysfs_unregister_usdev(us_ibdev);
+	usnic_fwd_dev_free(us_ibdev->ufdev);
+	ib_unregister_device(&us_ibdev->ib_dev);
+	ib_dealloc_device(&us_ibdev->ib_dev);
+}
+
+static void usnic_ib_undiscover_pf(struct kref *kref)
+{
+	struct usnic_ib_dev *us_ibdev, *tmp;
+	struct pci_dev *dev;
+	bool found = false;
+
+	dev = container_of(kref, struct usnic_ib_dev, vf_cnt)->pdev;
+	mutex_lock(&usnic_ib_ibdev_list_lock);
+	list_for_each_entry_safe(us_ibdev, tmp,
+				&usnic_ib_ibdev_list, ib_dev_link) {
+		if (us_ibdev->pdev == dev) {
+			list_del(&us_ibdev->ib_dev_link);
+			usnic_ib_device_remove(us_ibdev);
+			found = true;
+			break;
+		}
+	}
+
+	WARN(!found, "Failed to remove PF %s\n", pci_name(dev));
+
+	mutex_unlock(&usnic_ib_ibdev_list_lock);
+}
+
+static struct usnic_ib_dev *usnic_ib_discover_pf(struct usnic_vnic *vnic)
+{
+	struct usnic_ib_dev *us_ibdev;
+	struct pci_dev *parent_pci, *vf_pci;
+	int err;
+
+	vf_pci = usnic_vnic_get_pdev(vnic);
+	parent_pci = pci_physfn(vf_pci);
+
+	BUG_ON(!parent_pci);
+
+	mutex_lock(&usnic_ib_ibdev_list_lock);
+	list_for_each_entry(us_ibdev, &usnic_ib_ibdev_list, ib_dev_link) {
+		if (us_ibdev->pdev == parent_pci) {
+			kref_get(&us_ibdev->vf_cnt);
+			goto out;
+		}
+	}
+
+	us_ibdev = usnic_ib_device_add(parent_pci);
+	if (IS_ERR_OR_NULL(us_ibdev)) {
+		us_ibdev = us_ibdev ? us_ibdev : ERR_PTR(-EFAULT);
+		goto out;
+	}
+
+	err = usnic_ib_sysfs_register_usdev(us_ibdev);
+	if (err) {
+		usnic_ib_device_remove(us_ibdev);
+		us_ibdev = ERR_PTR(err);
+		goto out;
+	}
+
+	list_add(&us_ibdev->ib_dev_link, &usnic_ib_ibdev_list);
+out:
+	mutex_unlock(&usnic_ib_ibdev_list_lock);
+	return us_ibdev;
+}
+/* End of PF discovery section */
+
+/* Start of PCI section */
+
+static DEFINE_PCI_DEVICE_TABLE(usnic_ib_pci_ids) = {
+	{PCI_DEVICE(PCI_VENDOR_ID_CISCO, PCI_DEVICE_ID_CISCO_VIC_USPACE_NIC)},
+	{0,}
+};
+
+static int usnic_ib_pci_probe(struct pci_dev *pdev,
+				const struct pci_device_id *id)
+{
+	int err;
+	struct usnic_ib_dev *pf;
+	struct usnic_ib_vf *vf;
+	enum usnic_vnic_res_type res_type;
+
+	vf = kzalloc(sizeof(*vf), GFP_KERNEL);
+	if (!vf)
+		return -ENOMEM;
+
+	err = pci_enable_device(pdev);
+	if (err) {
+		usnic_err("Failed to enable %s with err %d\n",
+				pci_name(pdev), err);
+		goto out_clean_vf;
+	}
+
+	err = pci_request_regions(pdev, DRV_NAME);
+	if (err) {
+		usnic_err("Failed to request region for %s with err %d\n",
+				pci_name(pdev), err);
+		goto out_disable_device;
+	}
+
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, vf);
+
+	vf->vnic = usnic_vnic_alloc(pdev);
+	if (IS_ERR_OR_NULL(vf->vnic)) {
+		err = vf->vnic ? PTR_ERR(vf->vnic) : -ENOMEM;
+		usnic_err("Failed to alloc vnic for %s with err %d\n",
+				pci_name(pdev), err);
+		goto out_release_regions;
+	}
+
+	pf = usnic_ib_discover_pf(vf->vnic);
+	if (IS_ERR_OR_NULL(pf)) {
+		usnic_err("Failed to discover pf of vnic %s with err%ld\n",
+				pci_name(pdev), PTR_ERR(pf));
+		err = pf ? PTR_ERR(pf) : -EFAULT;
+		goto out_clean_vnic;
+	}
+
+	vf->pf = pf;
+	spin_lock_init(&vf->lock);
+	mutex_lock(&pf->usdev_lock);
+	list_add_tail(&vf->link, &pf->vf_dev_list);
+	/*
+	 * Save max settings (will be same for each VF, easier to re-write than
+	 * to say "if (!set) { set_values(); set=1; }
+	 */
+	for (res_type = USNIC_VNIC_RES_TYPE_EOL+1;
+			res_type < USNIC_VNIC_RES_TYPE_MAX;
+			res_type++) {
+		pf->vf_res_cnt[res_type] = usnic_vnic_res_cnt(vf->vnic,
+								res_type);
+	}
+
+	mutex_unlock(&pf->usdev_lock);
+
+	usnic_info("Registering usnic VF %s into PF %s\n", pci_name(pdev),
+			pf->ib_dev.name);
+	usnic_ib_log_vf(vf);
+	return 0;
+
+out_clean_vnic:
+	usnic_vnic_free(vf->vnic);
+out_release_regions:
+	pci_set_drvdata(pdev, NULL);
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+out_disable_device:
+	pci_disable_device(pdev);
+out_clean_vf:
+	kfree(vf);
+	return err;
+}
+
+static void usnic_ib_pci_remove(struct pci_dev *pdev)
+{
+	struct usnic_ib_vf *vf = pci_get_drvdata(pdev);
+	struct usnic_ib_dev *pf = vf->pf;
+
+	mutex_lock(&pf->usdev_lock);
+	list_del(&vf->link);
+	mutex_unlock(&pf->usdev_lock);
+
+	kref_put(&pf->vf_cnt, usnic_ib_undiscover_pf);
+	usnic_vnic_free(vf->vnic);
+	pci_set_drvdata(pdev, NULL);
+	pci_clear_master(pdev);
+	pci_release_regions(pdev);
+	pci_disable_device(pdev);
+	kfree(vf);
+
+	usnic_info("Removed VF %s\n", pci_name(pdev));
+}
+
+/* PCI driver entry points */
+static struct pci_driver usnic_ib_pci_driver = {
+	.name = DRV_NAME,
+	.id_table = usnic_ib_pci_ids,
+	.probe = usnic_ib_pci_probe,
+	.remove = usnic_ib_pci_remove,
+};
+/* End of PCI section */
+
+/* Start of module section */
+static int __init usnic_ib_init(void)
+{
+	int err;
+
+	printk_once(KERN_INFO "%s", usnic_version);
+
+	err = usnic_uiom_init(DRV_NAME);
+	if (err) {
+		usnic_err("Unable to initalize umem with err %d\n", err);
+		return err;
+	}
+
+	if (pci_register_driver(&usnic_ib_pci_driver)) {
+		usnic_err("Unable to register with PCI\n");
+		goto out_umem_fini;
+	}
+
+	err = register_netdevice_notifier(&usnic_ib_netdevice_notifier);
+	if (err) {
+		usnic_err("Failed to register netdev notifier\n");
+		goto out_pci_unreg;
+	}
+
+	err = register_inetaddr_notifier(&usnic_ib_inetaddr_notifier);
+	if (err) {
+		usnic_err("Failed to register inet addr notifier\n");
+		goto out_unreg_netdev_notifier;
+	}
+
+	err = usnic_transport_init();
+	if (err) {
+		usnic_err("Failed to initialize transport\n");
+		goto out_unreg_inetaddr_notifier;
+	}
+
+	usnic_debugfs_init();
+
+	return 0;
+
+out_unreg_inetaddr_notifier:
+	unregister_inetaddr_notifier(&usnic_ib_inetaddr_notifier);
+out_unreg_netdev_notifier:
+	unregister_netdevice_notifier(&usnic_ib_netdevice_notifier);
+out_pci_unreg:
+	pci_unregister_driver(&usnic_ib_pci_driver);
+out_umem_fini:
+	usnic_uiom_fini();
+
+	return err;
+}
+
+static void __exit usnic_ib_destroy(void)
+{
+	usnic_dbg("\n");
+	usnic_debugfs_exit();
+	usnic_transport_fini();
+	unregister_inetaddr_notifier(&usnic_ib_inetaddr_notifier);
+	unregister_netdevice_notifier(&usnic_ib_netdevice_notifier);
+	pci_unregister_driver(&usnic_ib_pci_driver);
+	usnic_uiom_fini();
+}
+
+MODULE_DESCRIPTION("Cisco VIC (usNIC) Verbs Driver");
+MODULE_AUTHOR("Upinder Malhi <umalhi@cisco.com>");
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(DRV_VERSION);
+module_param(usnic_log_lvl, uint, S_IRUGO | S_IWUSR);
+module_param(usnic_ib_share_vf, uint, S_IRUGO | S_IWUSR);
+MODULE_PARM_DESC(usnic_log_lvl, " Off=0, Err=1, Info=2, Debug=3");
+MODULE_PARM_DESC(usnic_ib_share_vf, "Off=0, On=1 VF sharing amongst QPs");
+MODULE_DEVICE_TABLE(pci, usnic_ib_pci_ids);
+
+module_init(usnic_ib_init);
+module_exit(usnic_ib_destroy);
+/* End of module section */

drivers/infiniband/hw/usnic/usnic_ib_qp_grp.c

@@ -0,0 +1,754 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+#include <linux/bug.h>
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+
+#include "usnic_log.h"
+#include "usnic_vnic.h"
+#include "usnic_fwd.h"
+#include "usnic_uiom.h"
+#include "usnic_debugfs.h"
+#include "usnic_ib_qp_grp.h"
+#include "usnic_ib_sysfs.h"
+#include "usnic_transport.h"
+
+#define DFLT_RQ_IDX	0
+
+const char *usnic_ib_qp_grp_state_to_string(enum ib_qp_state state)
+{
+	switch (state) {
+	case IB_QPS_RESET:
+		return "Rst";
+	case IB_QPS_INIT:
+		return "Init";
+	case IB_QPS_RTR:
+		return "RTR";
+	case IB_QPS_RTS:
+		return "RTS";
+	case IB_QPS_SQD:
+		return "SQD";
+	case IB_QPS_SQE:
+		return "SQE";
+	case IB_QPS_ERR:
+		return "ERR";
+	default:
+		return "UNKOWN STATE";
+
+	}
+}
+
+int usnic_ib_qp_grp_dump_hdr(char *buf, int buf_sz)
+{
+	return scnprintf(buf, buf_sz, "|QPN\t|State\t|PID\t|VF Idx\t|Fil ID");
+}
+
+int usnic_ib_qp_grp_dump_rows(void *obj, char *buf, int buf_sz)
+{
+	struct usnic_ib_qp_grp *qp_grp = obj;
+	struct usnic_ib_qp_grp_flow *default_flow;
+	if (obj) {
+		default_flow = list_first_entry(&qp_grp->flows_lst,
+					struct usnic_ib_qp_grp_flow, link);
+		return scnprintf(buf, buf_sz, "|%d\t|%s\t|%d\t|%hu\t|%d",
+					qp_grp->ibqp.qp_num,
+					usnic_ib_qp_grp_state_to_string(
+							qp_grp->state),
+					qp_grp->owner_pid,
+					usnic_vnic_get_index(qp_grp->vf->vnic),
+					default_flow->flow->flow_id);
+	} else {
+		return scnprintf(buf, buf_sz, "|N/A\t|N/A\t|N/A\t|N/A\t|N/A");
+	}
+}
+
+static struct usnic_vnic_res_chunk *
+get_qp_res_chunk(struct usnic_ib_qp_grp *qp_grp)
+{
+	lockdep_assert_held(&qp_grp->lock);
+	/*
+	 * The QP res chunk, used to derive qp indices,
+	 * are just indices of the RQs
+	 */
+	return usnic_ib_qp_grp_get_chunk(qp_grp, USNIC_VNIC_RES_TYPE_RQ);
+}
+
+static int enable_qp_grp(struct usnic_ib_qp_grp *qp_grp)
+{
+
+	int status;
+	int i, vnic_idx;
+	struct usnic_vnic_res_chunk *res_chunk;
+	struct usnic_vnic_res *res;
+
+	lockdep_assert_held(&qp_grp->lock);
+
+	vnic_idx = usnic_vnic_get_index(qp_grp->vf->vnic);
+
+	res_chunk = get_qp_res_chunk(qp_grp);
+	if (IS_ERR_OR_NULL(res_chunk)) {
+		usnic_err("Unable to get qp res with err %ld\n",
+				PTR_ERR(res_chunk));
+		return res_chunk ? PTR_ERR(res_chunk) : -ENOMEM;
+	}
+
+	for (i = 0; i < res_chunk->cnt; i++) {
+		res = res_chunk->res[i];
+		status = usnic_fwd_enable_qp(qp_grp->ufdev, vnic_idx,
+						res->vnic_idx);
+		if (status) {
+			usnic_err("Failed to enable qp %d of %s:%d\n with err %d\n",
+					res->vnic_idx, qp_grp->ufdev->name,
+					vnic_idx, status);
+			goto out_err;
+		}
+	}
+
+	return 0;
+
+out_err:
+	for (i--; i >= 0; i--) {
+		res = res_chunk->res[i];
+		usnic_fwd_disable_qp(qp_grp->ufdev, vnic_idx,
+					res->vnic_idx);
+	}
+
+	return status;
+}
+
+static int disable_qp_grp(struct usnic_ib_qp_grp *qp_grp)
+{
+	int i, vnic_idx;
+	struct usnic_vnic_res_chunk *res_chunk;
+	struct usnic_vnic_res *res;
+	int status = 0;
+
+	lockdep_assert_held(&qp_grp->lock);
+	vnic_idx = usnic_vnic_get_index(qp_grp->vf->vnic);
+
+	res_chunk = get_qp_res_chunk(qp_grp);
+	if (IS_ERR_OR_NULL(res_chunk)) {
+		usnic_err("Unable to get qp res with err %ld\n",
+			PTR_ERR(res_chunk));
+		return res_chunk ? PTR_ERR(res_chunk) : -ENOMEM;
+	}
+
+	for (i = 0; i < res_chunk->cnt; i++) {
+		res = res_chunk->res[i];
+		status = usnic_fwd_disable_qp(qp_grp->ufdev, vnic_idx,
+						res->vnic_idx);
+		if (status) {
+			usnic_err("Failed to disable rq %d of %s:%d\n with err %d\n",
+					res->vnic_idx,
+					qp_grp->ufdev->name,
+					vnic_idx, status);
+		}
+	}
+
+	return status;
+
+}
+
+static int init_filter_action(struct usnic_ib_qp_grp *qp_grp,
+				struct usnic_filter_action *uaction)
+{
+	struct usnic_vnic_res_chunk *res_chunk;
+
+	res_chunk = usnic_ib_qp_grp_get_chunk(qp_grp, USNIC_VNIC_RES_TYPE_RQ);
+	if (IS_ERR_OR_NULL(res_chunk)) {
+		usnic_err("Unable to get %s with err %ld\n",
+			usnic_vnic_res_type_to_str(USNIC_VNIC_RES_TYPE_RQ),
+			PTR_ERR(res_chunk));
+		return res_chunk ? PTR_ERR(res_chunk) : -ENOMEM;
+	}
+
+	uaction->vnic_idx = usnic_vnic_get_index(qp_grp->vf->vnic);
+	uaction->action.type = FILTER_ACTION_RQ_STEERING;
+	uaction->action.u.rq_idx = res_chunk->res[DFLT_RQ_IDX]->vnic_idx;
+
+	return 0;
+}
+
+static struct usnic_ib_qp_grp_flow*
+create_roce_custom_flow(struct usnic_ib_qp_grp *qp_grp,
+			struct usnic_transport_spec *trans_spec)
+{
+	uint16_t port_num;
+	int err;
+	struct filter filter;
+	struct usnic_filter_action uaction;
+	struct usnic_ib_qp_grp_flow *qp_flow;
+	struct usnic_fwd_flow *flow;
+	enum usnic_transport_type trans_type;
+
+	trans_type = trans_spec->trans_type;
+	port_num = trans_spec->usnic_roce.port_num;
+
+	/* Reserve Port */
+	port_num = usnic_transport_rsrv_port(trans_type, port_num);
+	if (port_num == 0)
+		return ERR_PTR(-EINVAL);
+
+	/* Create Flow */
+	usnic_fwd_init_usnic_filter(&filter, port_num);
+	err = init_filter_action(qp_grp, &uaction);
+	if (err)
+		goto out_unreserve_port;
+
+	flow = usnic_fwd_alloc_flow(qp_grp->ufdev, &filter, &uaction);
+	if (IS_ERR_OR_NULL(flow)) {
+		usnic_err("Unable to alloc flow failed with err %ld\n",
+				PTR_ERR(flow));
+		err = flow ? PTR_ERR(flow) : -EFAULT;
+		goto out_unreserve_port;
+	}
+
+	/* Create Flow Handle */
+	qp_flow = kzalloc(sizeof(*qp_flow), GFP_ATOMIC);
+	if (IS_ERR_OR_NULL(qp_flow)) {
+		err = qp_flow ? PTR_ERR(qp_flow) : -ENOMEM;
+		goto out_dealloc_flow;
+	}
+	qp_flow->flow = flow;
+	qp_flow->trans_type = trans_type;
+	qp_flow->usnic_roce.port_num = port_num;
+	qp_flow->qp_grp = qp_grp;
+	return qp_flow;
+
+out_dealloc_flow:
+	usnic_fwd_dealloc_flow(flow);
+out_unreserve_port:
+	usnic_transport_unrsrv_port(trans_type, port_num);
+	return ERR_PTR(err);
+}
+
+static void release_roce_custom_flow(struct usnic_ib_qp_grp_flow *qp_flow)
+{
+	usnic_fwd_dealloc_flow(qp_flow->flow);
+	usnic_transport_unrsrv_port(qp_flow->trans_type,
+					qp_flow->usnic_roce.port_num);
+	kfree(qp_flow);
+}
+
+static struct usnic_ib_qp_grp_flow*
+create_udp_flow(struct usnic_ib_qp_grp *qp_grp,
+		struct usnic_transport_spec *trans_spec)
+{
+	struct socket *sock;
+	int sock_fd;
+	int err;
+	struct filter filter;
+	struct usnic_filter_action uaction;
+	struct usnic_ib_qp_grp_flow *qp_flow;
+	struct usnic_fwd_flow *flow;
+	enum usnic_transport_type trans_type;
+	uint32_t addr;
+	uint16_t port_num;
+	int proto;
+
+	trans_type = trans_spec->trans_type;
+	sock_fd = trans_spec->udp.sock_fd;
+
+	/* Get and check socket */
+	sock = usnic_transport_get_socket(sock_fd);
+	if (IS_ERR_OR_NULL(sock))
+		return ERR_CAST(sock);
+
+	err = usnic_transport_sock_get_addr(sock, &proto, &addr, &port_num);
+	if (err)
+		goto out_put_sock;
+
+	if (proto != IPPROTO_UDP) {
+		usnic_err("Protocol for fd %d is not UDP", sock_fd);
+		err = -EPERM;
+		goto out_put_sock;
+	}
+
+	/* Create flow */
+	usnic_fwd_init_udp_filter(&filter, addr, port_num);
+	err = init_filter_action(qp_grp, &uaction);
+	if (err)
+		goto out_put_sock;
+
+	flow = usnic_fwd_alloc_flow(qp_grp->ufdev, &filter, &uaction);
+	if (IS_ERR_OR_NULL(flow)) {
+		usnic_err("Unable to alloc flow failed with err %ld\n",
+				PTR_ERR(flow));
+		err = flow ? PTR_ERR(flow) : -EFAULT;
+		goto out_put_sock;
+	}
+
+	/* Create qp_flow */
+	qp_flow = kzalloc(sizeof(*qp_flow), GFP_ATOMIC);
+	if (IS_ERR_OR_NULL(qp_flow)) {
+		err = qp_flow ? PTR_ERR(qp_flow) : -ENOMEM;
+		goto out_dealloc_flow;
+	}
+	qp_flow->flow = flow;
+	qp_flow->trans_type = trans_type;
+	qp_flow->udp.sock = sock;
+	qp_flow->qp_grp = qp_grp;
+	return qp_flow;
+
+out_dealloc_flow:
+	usnic_fwd_dealloc_flow(flow);
+out_put_sock:
+	usnic_transport_put_socket(sock);
+	return ERR_PTR(err);
+}
+
+static void release_udp_flow(struct usnic_ib_qp_grp_flow *qp_flow)
+{
+	usnic_fwd_dealloc_flow(qp_flow->flow);
+	usnic_transport_put_socket(qp_flow->udp.sock);
+	kfree(qp_flow);
+}
+
+static struct usnic_ib_qp_grp_flow*
+create_and_add_flow(struct usnic_ib_qp_grp *qp_grp,
+			struct usnic_transport_spec *trans_spec)
+{
+	struct usnic_ib_qp_grp_flow *qp_flow;
+	enum usnic_transport_type trans_type;
+
+	trans_type = trans_spec->trans_type;
+	switch (trans_type) {
+	case USNIC_TRANSPORT_ROCE_CUSTOM:
+		qp_flow = create_roce_custom_flow(qp_grp, trans_spec);
+		break;
+	case USNIC_TRANSPORT_IPV4_UDP:
+		qp_flow = create_udp_flow(qp_grp, trans_spec);
+		break;
+	default:
+		usnic_err("Unsupported transport %u\n",
+				trans_spec->trans_type);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (!IS_ERR_OR_NULL(qp_flow)) {
+		list_add_tail(&qp_flow->link, &qp_grp->flows_lst);
+		usnic_debugfs_flow_add(qp_flow);
+	}
+
+
+	return qp_flow;
+}
+
+static void release_and_remove_flow(struct usnic_ib_qp_grp_flow *qp_flow)
+{
+	usnic_debugfs_flow_remove(qp_flow);
+	list_del(&qp_flow->link);
+
+	switch (qp_flow->trans_type) {
+	case USNIC_TRANSPORT_ROCE_CUSTOM:
+		release_roce_custom_flow(qp_flow);
+		break;
+	case USNIC_TRANSPORT_IPV4_UDP:
+		release_udp_flow(qp_flow);
+		break;
+	default:
+		WARN(1, "Unsupported transport %u\n",
+				qp_flow->trans_type);
+		break;
+	}
+}
+
+static void release_and_remove_all_flows(struct usnic_ib_qp_grp *qp_grp)
+{
+	struct usnic_ib_qp_grp_flow *qp_flow, *tmp;
+	list_for_each_entry_safe(qp_flow, tmp, &qp_grp->flows_lst, link)
+		release_and_remove_flow(qp_flow);
+}
+
+int usnic_ib_qp_grp_modify(struct usnic_ib_qp_grp *qp_grp,
+				enum ib_qp_state new_state,
+				void *data)
+{
+	int status = 0;
+	int vnic_idx;
+	struct ib_event ib_event;
+	enum ib_qp_state old_state;
+	struct usnic_transport_spec *trans_spec;
+	struct usnic_ib_qp_grp_flow *qp_flow;
+
+	old_state = qp_grp->state;
+	vnic_idx = usnic_vnic_get_index(qp_grp->vf->vnic);
+	trans_spec = (struct usnic_transport_spec *) data;
+
+	spin_lock(&qp_grp->lock);
+	switch (new_state) {
+	case IB_QPS_RESET:
+		switch (old_state) {
+		case IB_QPS_RESET:
+			/* NO-OP */
+			break;
+		case IB_QPS_INIT:
+			release_and_remove_all_flows(qp_grp);
+			status = 0;
+			break;
+		case IB_QPS_RTR:
+		case IB_QPS_RTS:
+		case IB_QPS_ERR:
+			status = disable_qp_grp(qp_grp);
+			release_and_remove_all_flows(qp_grp);
+			break;
+		default:
+			status = -EINVAL;
+		}
+		break;
+	case IB_QPS_INIT:
+		switch (old_state) {
+		case IB_QPS_RESET:
+			if (trans_spec) {
+				qp_flow = create_and_add_flow(qp_grp,
+								trans_spec);
+				if (IS_ERR_OR_NULL(qp_flow)) {
+					status = qp_flow ? PTR_ERR(qp_flow) : -EFAULT;
+					break;
+				}
+			} else {
+				/*
+				 * Optional to specify filters.
+				 */
+				status = 0;
+			}
+			break;
+		case IB_QPS_INIT:
+			if (trans_spec) {
+				qp_flow = create_and_add_flow(qp_grp,
+								trans_spec);
+				if (IS_ERR_OR_NULL(qp_flow)) {
+					status = qp_flow ? PTR_ERR(qp_flow) : -EFAULT;
+					break;
+				}
+			} else {
+				/*
+				 * Doesn't make sense to go into INIT state
+				 * from INIT state w/o adding filters.
+				 */
+				status = -EINVAL;
+			}
+			break;
+		case IB_QPS_RTR:
+			status = disable_qp_grp(qp_grp);
+			break;
+		case IB_QPS_RTS:
+			status = disable_qp_grp(qp_grp);
+			break;
+		default:
+			status = -EINVAL;
+		}
+		break;
+	case IB_QPS_RTR:
+		switch (old_state) {
+		case IB_QPS_INIT:
+			status = enable_qp_grp(qp_grp);
+			break;
+		default:
+			status = -EINVAL;
+		}
+		break;
+	case IB_QPS_RTS:
+		switch (old_state) {
+		case IB_QPS_RTR:
+			/* NO-OP FOR NOW */
+			break;
+		default:
+			status = -EINVAL;
+		}
+		break;
+	case IB_QPS_ERR:
+		ib_event.device = &qp_grp->vf->pf->ib_dev;
+		ib_event.element.qp = &qp_grp->ibqp;
+		ib_event.event = IB_EVENT_QP_FATAL;
+
+		switch (old_state) {
+		case IB_QPS_RESET:
+			qp_grp->ibqp.event_handler(&ib_event,
+					qp_grp->ibqp.qp_context);
+			break;
+		case IB_QPS_INIT:
+			release_and_remove_all_flows(qp_grp);
+			qp_grp->ibqp.event_handler(&ib_event,
+					qp_grp->ibqp.qp_context);
+			break;
+		case IB_QPS_RTR:
+		case IB_QPS_RTS:
+			status = disable_qp_grp(qp_grp);
+			release_and_remove_all_flows(qp_grp);
+			qp_grp->ibqp.event_handler(&ib_event,
+					qp_grp->ibqp.qp_context);
+			break;
+		default:
+			status = -EINVAL;
+		}
+		break;
+	default:
+		status = -EINVAL;
+	}
+	spin_unlock(&qp_grp->lock);
+
+	if (!status) {
+		qp_grp->state = new_state;
+		usnic_info("Transistioned %u from %s to %s",
+		qp_grp->grp_id,
+		usnic_ib_qp_grp_state_to_string(old_state),
+		usnic_ib_qp_grp_state_to_string(new_state));
+	} else {
+		usnic_err("Failed to transistion %u from %s to %s",
+		qp_grp->grp_id,
+		usnic_ib_qp_grp_state_to_string(old_state),
+		usnic_ib_qp_grp_state_to_string(new_state));
+	}
+
+	return status;
+}
+
+static struct usnic_vnic_res_chunk**
+alloc_res_chunk_list(struct usnic_vnic *vnic,
+			struct usnic_vnic_res_spec *res_spec, void *owner_obj)
+{
+	enum usnic_vnic_res_type res_type;
+	struct usnic_vnic_res_chunk **res_chunk_list;
+	int err, i, res_cnt, res_lst_sz;
+
+	for (res_lst_sz = 0;
+		res_spec->resources[res_lst_sz].type != USNIC_VNIC_RES_TYPE_EOL;
+		res_lst_sz++) {
+		/* Do Nothing */
+	}
+
+	res_chunk_list = kzalloc(sizeof(*res_chunk_list)*(res_lst_sz+1),
+					GFP_ATOMIC);
+	if (!res_chunk_list)
+		return ERR_PTR(-ENOMEM);
+
+	for (i = 0; res_spec->resources[i].type != USNIC_VNIC_RES_TYPE_EOL;
+		i++) {
+		res_type = res_spec->resources[i].type;
+		res_cnt = res_spec->resources[i].cnt;
+
+		res_chunk_list[i] = usnic_vnic_get_resources(vnic, res_type,
+					res_cnt, owner_obj);
+		if (IS_ERR_OR_NULL(res_chunk_list[i])) {
+			err = res_chunk_list[i] ?
+					PTR_ERR(res_chunk_list[i]) : -ENOMEM;
+			usnic_err("Failed to get %s from %s with err %d\n",
+				usnic_vnic_res_type_to_str(res_type),
+				usnic_vnic_pci_name(vnic),
+				err);
+			goto out_free_res;
+		}
+	}
+
+	return res_chunk_list;
+
+out_free_res:
+	for (i--; i > 0; i--)
+		usnic_vnic_put_resources(res_chunk_list[i]);
+	kfree(res_chunk_list);
+	return ERR_PTR(err);
+}
+
+static void free_qp_grp_res(struct usnic_vnic_res_chunk **res_chunk_list)
+{
+	int i;
+	for (i = 0; res_chunk_list[i]; i++)
+		usnic_vnic_put_resources(res_chunk_list[i]);
+	kfree(res_chunk_list);
+}
+
+static int qp_grp_and_vf_bind(struct usnic_ib_vf *vf,
+				struct usnic_ib_pd *pd,
+				struct usnic_ib_qp_grp *qp_grp)
+{
+	int err;
+	struct pci_dev *pdev;
+
+	lockdep_assert_held(&vf->lock);
+
+	pdev = usnic_vnic_get_pdev(vf->vnic);
+	if (vf->qp_grp_ref_cnt == 0) {
+		err = usnic_uiom_attach_dev_to_pd(pd->umem_pd, &pdev->dev);
+		if (err) {
+			usnic_err("Failed to attach %s to domain\n",
+					pci_name(pdev));
+			return err;
+		}
+		vf->pd = pd;
+	}
+	vf->qp_grp_ref_cnt++;
+
+	WARN_ON(vf->pd != pd);
+	qp_grp->vf = vf;
+
+	return 0;
+}
+
+static void qp_grp_and_vf_unbind(struct usnic_ib_qp_grp *qp_grp)
+{
+	struct pci_dev *pdev;
+	struct usnic_ib_pd *pd;
+
+	lockdep_assert_held(&qp_grp->vf->lock);
+
+	pd = qp_grp->vf->pd;
+	pdev = usnic_vnic_get_pdev(qp_grp->vf->vnic);
+	if (--qp_grp->vf->qp_grp_ref_cnt == 0) {
+		qp_grp->vf->pd = NULL;
+		usnic_uiom_detach_dev_from_pd(pd->umem_pd, &pdev->dev);
+	}
+	qp_grp->vf = NULL;
+}
+
+static void log_spec(struct usnic_vnic_res_spec *res_spec)
+{
+	char buf[512];
+	usnic_vnic_spec_dump(buf, sizeof(buf), res_spec);
+	usnic_dbg("%s\n", buf);
+}
+
+static int qp_grp_id_from_flow(struct usnic_ib_qp_grp_flow *qp_flow,
+				uint32_t *id)
+{
+	enum usnic_transport_type trans_type = qp_flow->trans_type;
+	int err;
+
+	switch (trans_type) {
+	case USNIC_TRANSPORT_ROCE_CUSTOM:
+		*id = qp_flow->usnic_roce.port_num;
+		break;
+	case USNIC_TRANSPORT_IPV4_UDP:
+		err = usnic_transport_sock_get_addr(qp_flow->udp.sock,
+							NULL, NULL,
+							(uint16_t *) id);
+		if (err)
+			return err;
+		break;
+	default:
+		usnic_err("Unsupported transport %u\n", trans_type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+struct usnic_ib_qp_grp *
+usnic_ib_qp_grp_create(struct usnic_fwd_dev *ufdev, struct usnic_ib_vf *vf,
+			struct usnic_ib_pd *pd,
+			struct usnic_vnic_res_spec *res_spec,
+			struct usnic_transport_spec *transport_spec)
+{
+	struct usnic_ib_qp_grp *qp_grp;
+	int err;
+	enum usnic_transport_type transport = transport_spec->trans_type;
+	struct usnic_ib_qp_grp_flow *qp_flow;
+
+	lockdep_assert_held(&vf->lock);
+
+	err = usnic_vnic_res_spec_satisfied(&min_transport_spec[transport],
+						res_spec);
+	if (err) {
+		usnic_err("Spec does not meet miniumum req for transport %d\n",
+				transport);
+		log_spec(res_spec);
+		return ERR_PTR(err);
+	}
+
+	qp_grp = kzalloc(sizeof(*qp_grp), GFP_ATOMIC);
+	if (!qp_grp) {
+		usnic_err("Unable to alloc qp_grp - Out of memory\n");
+		return NULL;
+	}
+
+	qp_grp->res_chunk_list = alloc_res_chunk_list(vf->vnic, res_spec,
+							qp_grp);
+	if (IS_ERR_OR_NULL(qp_grp->res_chunk_list)) {
+		err = qp_grp->res_chunk_list ?
+				PTR_ERR(qp_grp->res_chunk_list) : -ENOMEM;
+		usnic_err("Unable to alloc res for %d with err %d\n",
+				qp_grp->grp_id, err);
+		goto out_free_qp_grp;
+	}
+
+	err = qp_grp_and_vf_bind(vf, pd, qp_grp);
+	if (err)
+		goto out_free_res;
+
+	INIT_LIST_HEAD(&qp_grp->flows_lst);
+	spin_lock_init(&qp_grp->lock);
+	qp_grp->ufdev = ufdev;
+	qp_grp->state = IB_QPS_RESET;
+	qp_grp->owner_pid = current->pid;
+
+	qp_flow = create_and_add_flow(qp_grp, transport_spec);
+	if (IS_ERR_OR_NULL(qp_flow)) {
+		usnic_err("Unable to create and add flow with err %ld\n",
+				PTR_ERR(qp_flow));
+		err = qp_flow ? PTR_ERR(qp_flow) : -EFAULT;
+		goto out_qp_grp_vf_unbind;
+	}
+
+	err = qp_grp_id_from_flow(qp_flow, &qp_grp->grp_id);
+	if (err)
+		goto out_release_flow;
+	qp_grp->ibqp.qp_num = qp_grp->grp_id;
+
+	usnic_ib_sysfs_qpn_add(qp_grp);
+
+	return qp_grp;
+
+out_release_flow:
+	release_and_remove_flow(qp_flow);
+out_qp_grp_vf_unbind:
+	qp_grp_and_vf_unbind(qp_grp);
+out_free_res:
+	free_qp_grp_res(qp_grp->res_chunk_list);
+out_free_qp_grp:
+	kfree(qp_grp);
+
+	return ERR_PTR(err);
+}
+
+void usnic_ib_qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp)
+{
+
+	WARN_ON(qp_grp->state != IB_QPS_RESET);
+	lockdep_assert_held(&qp_grp->vf->lock);
+
+	release_and_remove_all_flows(qp_grp);
+	usnic_ib_sysfs_qpn_remove(qp_grp);
+	qp_grp_and_vf_unbind(qp_grp);
+	free_qp_grp_res(qp_grp->res_chunk_list);
+	kfree(qp_grp);
+}
+
+struct usnic_vnic_res_chunk*
+usnic_ib_qp_grp_get_chunk(struct usnic_ib_qp_grp *qp_grp,
+				enum usnic_vnic_res_type res_type)
+{
+	int i;
+
+	for (i = 0; qp_grp->res_chunk_list[i]; i++) {
+		if (qp_grp->res_chunk_list[i]->type == res_type)
+			return qp_grp->res_chunk_list[i];
+	}
+
+	return ERR_PTR(-EINVAL);
+}

drivers/infiniband/hw/usnic/usnic_ib_qp_grp.h

@@ -0,0 +1,117 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_IB_QP_GRP_H_
+#define USNIC_IB_QP_GRP_H_
+
+#include <linux/debugfs.h>
+#include <rdma/ib_verbs.h>
+
+#include "usnic_ib.h"
+#include "usnic_abi.h"
+#include "usnic_fwd.h"
+#include "usnic_vnic.h"
+
+/*
+ * The qp group struct represents all the hw resources needed to present a ib_qp
+ */
+struct usnic_ib_qp_grp {
+	struct ib_qp				ibqp;
+	enum ib_qp_state			state;
+	int					grp_id;
+
+	struct usnic_fwd_dev			*ufdev;
+	struct usnic_ib_ucontext		*ctx;
+	struct list_head			flows_lst;
+
+	struct usnic_vnic_res_chunk		**res_chunk_list;
+
+	pid_t					owner_pid;
+	struct usnic_ib_vf			*vf;
+	struct list_head			link;
+
+	spinlock_t				lock;
+
+	struct kobject				kobj;
+};
+
+struct usnic_ib_qp_grp_flow {
+	struct usnic_fwd_flow		*flow;
+	enum usnic_transport_type	trans_type;
+	union {
+		struct {
+			uint16_t	port_num;
+		} usnic_roce;
+		struct {
+			struct socket	*sock;
+		} udp;
+	};
+	struct usnic_ib_qp_grp		*qp_grp;
+	struct list_head		link;
+
+	/* Debug FS */
+	struct dentry			*dbgfs_dentry;
+	char				dentry_name[32];
+};
+
+static const struct
+usnic_vnic_res_spec min_transport_spec[USNIC_TRANSPORT_MAX] = {
+	{ /*USNIC_TRANSPORT_UNKNOWN*/
+		.resources = {
+			{.type = USNIC_VNIC_RES_TYPE_EOL,	.cnt = 0,},
+		},
+	},
+	{ /*USNIC_TRANSPORT_ROCE_CUSTOM*/
+		.resources = {
+			{.type = USNIC_VNIC_RES_TYPE_WQ,	.cnt = 1,},
+			{.type = USNIC_VNIC_RES_TYPE_RQ,	.cnt = 1,},
+			{.type = USNIC_VNIC_RES_TYPE_CQ,	.cnt = 1,},
+			{.type = USNIC_VNIC_RES_TYPE_EOL,	.cnt = 0,},
+		},
+	},
+	{ /*USNIC_TRANSPORT_IPV4_UDP*/
+		.resources = {
+			{.type = USNIC_VNIC_RES_TYPE_WQ,	.cnt = 1,},
+			{.type = USNIC_VNIC_RES_TYPE_RQ,	.cnt = 1,},
+			{.type = USNIC_VNIC_RES_TYPE_CQ,	.cnt = 1,},
+			{.type = USNIC_VNIC_RES_TYPE_EOL,	.cnt = 0,},
+		},
+	},
+};
+
+const char *usnic_ib_qp_grp_state_to_string(enum ib_qp_state state);
+int usnic_ib_qp_grp_dump_hdr(char *buf, int buf_sz);
+int usnic_ib_qp_grp_dump_rows(void *obj, char *buf, int buf_sz);
+struct usnic_ib_qp_grp *
+usnic_ib_qp_grp_create(struct usnic_fwd_dev *ufdev, struct usnic_ib_vf *vf,
+			struct usnic_ib_pd *pd,
+			struct usnic_vnic_res_spec *res_spec,
+			struct usnic_transport_spec *trans_spec);
+void usnic_ib_qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp);
+int usnic_ib_qp_grp_modify(struct usnic_ib_qp_grp *qp_grp,
+				enum ib_qp_state new_state,
+				void *data);
+struct usnic_vnic_res_chunk
+*usnic_ib_qp_grp_get_chunk(struct usnic_ib_qp_grp *qp_grp,
+				enum usnic_vnic_res_type type);
+static inline
+struct usnic_ib_qp_grp *to_uqp_grp(struct ib_qp *ibqp)
+{
+	return container_of(ibqp, struct usnic_ib_qp_grp, ibqp);
+}
+#endif /* USNIC_IB_QP_GRP_H_ */

drivers/infiniband/hw/usnic/usnic_ib_sysfs.c

@@ -0,0 +1,341 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_addr.h>
+
+#include "usnic_common_util.h"
+#include "usnic_ib.h"
+#include "usnic_ib_qp_grp.h"
+#include "usnic_vnic.h"
+#include "usnic_ib_verbs.h"
+#include "usnic_log.h"
+
+static ssize_t usnic_ib_show_fw_ver(struct device *device,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct usnic_ib_dev *us_ibdev =
+		container_of(device, struct usnic_ib_dev, ib_dev.dev);
+	struct ethtool_drvinfo info;
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	us_ibdev->netdev->ethtool_ops->get_drvinfo(us_ibdev->netdev, &info);
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n", info.fw_version);
+}
+
+static ssize_t usnic_ib_show_board(struct device *device,
+					struct device_attribute *attr,
+					char *buf)
+{
+	struct usnic_ib_dev *us_ibdev =
+		container_of(device, struct usnic_ib_dev, ib_dev.dev);
+	unsigned short subsystem_device_id;
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	subsystem_device_id = us_ibdev->pdev->subsystem_device;
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return scnprintf(buf, PAGE_SIZE, "%hu\n", subsystem_device_id);
+}
+
+/*
+ * Report the configuration for this PF
+ */
+static ssize_t
+usnic_ib_show_config(struct device *device, struct device_attribute *attr,
+			char *buf)
+{
+	struct usnic_ib_dev *us_ibdev;
+	char *ptr;
+	unsigned left;
+	unsigned n;
+	enum usnic_vnic_res_type res_type;
+
+	us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev);
+
+	/* Buffer space limit is 1 page */
+	ptr = buf;
+	left = PAGE_SIZE;
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	if (atomic_read(&us_ibdev->vf_cnt.refcount) > 0) {
+		char *busname;
+
+		/*
+		 * bus name seems to come with annoying prefix.
+		 * Remove it if it is predictable
+		 */
+		busname = us_ibdev->pdev->bus->name;
+		if (strncmp(busname, "PCI Bus ", 8) == 0)
+			busname += 8;
+
+		n = scnprintf(ptr, left,
+			"%s: %s:%d.%d, %s, %pM, %u VFs\n Per VF:",
+			us_ibdev->ib_dev.name,
+			busname,
+			PCI_SLOT(us_ibdev->pdev->devfn),
+			PCI_FUNC(us_ibdev->pdev->devfn),
+			netdev_name(us_ibdev->netdev),
+			us_ibdev->ufdev->mac,
+			atomic_read(&us_ibdev->vf_cnt.refcount));
+		UPDATE_PTR_LEFT(n, ptr, left);
+
+		for (res_type = USNIC_VNIC_RES_TYPE_EOL;
+				res_type < USNIC_VNIC_RES_TYPE_MAX;
+				res_type++) {
+			if (us_ibdev->vf_res_cnt[res_type] == 0)
+				continue;
+			n = scnprintf(ptr, left, " %d %s%s",
+				us_ibdev->vf_res_cnt[res_type],
+				usnic_vnic_res_type_to_str(res_type),
+				(res_type < (USNIC_VNIC_RES_TYPE_MAX - 1)) ?
+				 "," : "");
+			UPDATE_PTR_LEFT(n, ptr, left);
+		}
+		n = scnprintf(ptr, left, "\n");
+		UPDATE_PTR_LEFT(n, ptr, left);
+	} else {
+		n = scnprintf(ptr, left, "%s: no VFs\n",
+				us_ibdev->ib_dev.name);
+		UPDATE_PTR_LEFT(n, ptr, left);
+	}
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return ptr - buf;
+}
+
+static ssize_t
+usnic_ib_show_iface(struct device *device, struct device_attribute *attr,
+			char *buf)
+{
+	struct usnic_ib_dev *us_ibdev;
+
+	us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%s\n",
+			netdev_name(us_ibdev->netdev));
+}
+
+static ssize_t
+usnic_ib_show_max_vf(struct device *device, struct device_attribute *attr,
+			char *buf)
+{
+	struct usnic_ib_dev *us_ibdev;
+
+	us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%u\n",
+			atomic_read(&us_ibdev->vf_cnt.refcount));
+}
+
+static ssize_t
+usnic_ib_show_qp_per_vf(struct device *device, struct device_attribute *attr,
+			char *buf)
+{
+	struct usnic_ib_dev *us_ibdev;
+	int qp_per_vf;
+
+	us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev);
+	qp_per_vf = max(us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_WQ],
+			us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_RQ]);
+
+	return scnprintf(buf, PAGE_SIZE,
+				"%d\n", qp_per_vf);
+}
+
+static ssize_t
+usnic_ib_show_cq_per_vf(struct device *device, struct device_attribute *attr,
+			char *buf)
+{
+	struct usnic_ib_dev *us_ibdev;
+
+	us_ibdev = container_of(device, struct usnic_ib_dev, ib_dev.dev);
+
+	return scnprintf(buf, PAGE_SIZE, "%d\n",
+			us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_CQ]);
+}
+
+static DEVICE_ATTR(fw_ver, S_IRUGO, usnic_ib_show_fw_ver, NULL);
+static DEVICE_ATTR(board_id, S_IRUGO, usnic_ib_show_board, NULL);
+static DEVICE_ATTR(config, S_IRUGO, usnic_ib_show_config, NULL);
+static DEVICE_ATTR(iface, S_IRUGO, usnic_ib_show_iface, NULL);
+static DEVICE_ATTR(max_vf, S_IRUGO, usnic_ib_show_max_vf, NULL);
+static DEVICE_ATTR(qp_per_vf, S_IRUGO, usnic_ib_show_qp_per_vf, NULL);
+static DEVICE_ATTR(cq_per_vf, S_IRUGO, usnic_ib_show_cq_per_vf, NULL);
+
+static struct device_attribute *usnic_class_attributes[] = {
+	&dev_attr_fw_ver,
+	&dev_attr_board_id,
+	&dev_attr_config,
+	&dev_attr_iface,
+	&dev_attr_max_vf,
+	&dev_attr_qp_per_vf,
+	&dev_attr_cq_per_vf,
+};
+
+struct qpn_attribute {
+	struct attribute attr;
+	ssize_t (*show)(struct usnic_ib_qp_grp *, char *buf);
+};
+
+/*
+ * Definitions for supporting QPN entries in sysfs
+ */
+static ssize_t
+usnic_ib_qpn_attr_show(struct kobject *kobj, struct attribute *attr, char *buf)
+{
+	struct usnic_ib_qp_grp *qp_grp;
+	struct qpn_attribute *qpn_attr;
+
+	qp_grp = container_of(kobj, struct usnic_ib_qp_grp, kobj);
+	qpn_attr = container_of(attr, struct qpn_attribute, attr);
+
+	return qpn_attr->show(qp_grp, buf);
+}
+
+static const struct sysfs_ops usnic_ib_qpn_sysfs_ops = {
+	.show = usnic_ib_qpn_attr_show
+};
+
+#define QPN_ATTR_RO(NAME) \
+struct qpn_attribute qpn_attr_##NAME = __ATTR_RO(NAME)
+
+static ssize_t context_show(struct usnic_ib_qp_grp *qp_grp, char *buf)
+{
+	return scnprintf(buf, PAGE_SIZE, "0x%p\n", qp_grp->ctx);
+}
+
+static ssize_t summary_show(struct usnic_ib_qp_grp *qp_grp, char *buf)
+{
+	int i, j, n;
+	int left;
+	char *ptr;
+	struct usnic_vnic_res_chunk *res_chunk;
+	struct usnic_vnic_res *vnic_res;
+
+	left = PAGE_SIZE;
+	ptr = buf;
+
+	n = scnprintf(ptr, left,
+			"QPN: %d State: (%s) PID: %u VF Idx: %hu ",
+			qp_grp->ibqp.qp_num,
+			usnic_ib_qp_grp_state_to_string(qp_grp->state),
+			qp_grp->owner_pid,
+			usnic_vnic_get_index(qp_grp->vf->vnic));
+	UPDATE_PTR_LEFT(n, ptr, left);
+
+	for (i = 0; qp_grp->res_chunk_list[i]; i++) {
+		res_chunk = qp_grp->res_chunk_list[i];
+		for (j = 0; j < res_chunk->cnt; j++) {
+			vnic_res = res_chunk->res[j];
+			n = scnprintf(ptr, left, "%s[%d] ",
+				usnic_vnic_res_type_to_str(vnic_res->type),
+				vnic_res->vnic_idx);
+			UPDATE_PTR_LEFT(n, ptr, left);
+		}
+	}
+
+	n = scnprintf(ptr, left, "\n");
+	UPDATE_PTR_LEFT(n, ptr, left);
+
+	return ptr - buf;
+}
+
+static QPN_ATTR_RO(context);
+static QPN_ATTR_RO(summary);
+
+static struct attribute *usnic_ib_qpn_default_attrs[] = {
+	&qpn_attr_context.attr,
+	&qpn_attr_summary.attr,
+	NULL
+};
+
+static struct kobj_type usnic_ib_qpn_type = {
+	.sysfs_ops = &usnic_ib_qpn_sysfs_ops,
+	.default_attrs = usnic_ib_qpn_default_attrs
+};
+
+int usnic_ib_sysfs_register_usdev(struct usnic_ib_dev *us_ibdev)
+{
+	int i;
+	int err;
+	for (i = 0; i < ARRAY_SIZE(usnic_class_attributes); ++i) {
+		err = device_create_file(&us_ibdev->ib_dev.dev,
+						usnic_class_attributes[i]);
+		if (err) {
+			usnic_err("Failed to create device file %d for %s eith err %d",
+				i, us_ibdev->ib_dev.name, err);
+			return -EINVAL;
+		}
+	}
+
+	/* create kernel object for looking at individual QPs */
+	kobject_get(&us_ibdev->ib_dev.dev.kobj);
+	us_ibdev->qpn_kobj = kobject_create_and_add("qpn",
+			&us_ibdev->ib_dev.dev.kobj);
+	if (us_ibdev->qpn_kobj == NULL) {
+		kobject_put(&us_ibdev->ib_dev.dev.kobj);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void usnic_ib_sysfs_unregister_usdev(struct usnic_ib_dev *us_ibdev)
+{
+	int i;
+	for (i = 0; i < ARRAY_SIZE(usnic_class_attributes); ++i) {
+		device_remove_file(&us_ibdev->ib_dev.dev,
+					usnic_class_attributes[i]);
+	}
+
+	kobject_put(us_ibdev->qpn_kobj);
+}
+
+void usnic_ib_sysfs_qpn_add(struct usnic_ib_qp_grp *qp_grp)
+{
+	struct usnic_ib_dev *us_ibdev;
+	int err;
+
+	us_ibdev = qp_grp->vf->pf;
+
+	err = kobject_init_and_add(&qp_grp->kobj, &usnic_ib_qpn_type,
+			kobject_get(us_ibdev->qpn_kobj),
+			"%d", qp_grp->grp_id);
+	if (err) {
+		kobject_put(us_ibdev->qpn_kobj);
+		return;
+	}
+}
+
+void usnic_ib_sysfs_qpn_remove(struct usnic_ib_qp_grp *qp_grp)
+{
+	struct usnic_ib_dev *us_ibdev;
+
+	us_ibdev = qp_grp->vf->pf;
+
+	kobject_put(&qp_grp->kobj);
+	kobject_put(us_ibdev->qpn_kobj);
+}

drivers/infiniband/hw/usnic/usnic_ib_sysfs.h

@@ -0,0 +1,29 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_IB_SYSFS_H_
+#define USNIC_IB_SYSFS_H_
+
+#include "usnic_ib.h"
+
+int usnic_ib_sysfs_register_usdev(struct usnic_ib_dev *us_ibdev);
+void usnic_ib_sysfs_unregister_usdev(struct usnic_ib_dev *us_ibdev);
+void usnic_ib_sysfs_qpn_add(struct usnic_ib_qp_grp *qp_grp);
+void usnic_ib_sysfs_qpn_remove(struct usnic_ib_qp_grp *qp_grp);
+
+#endif /* !USNIC_IB_SYSFS_H_ */

drivers/infiniband/hw/usnic/usnic_ib_verbs.c

@@ -0,0 +1,765 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+
+#include <rdma/ib_user_verbs.h>
+#include <rdma/ib_addr.h>
+
+#include "usnic_abi.h"
+#include "usnic_ib.h"
+#include "usnic_common_util.h"
+#include "usnic_ib_qp_grp.h"
+#include "usnic_fwd.h"
+#include "usnic_log.h"
+#include "usnic_uiom.h"
+#include "usnic_transport.h"
+
+#define USNIC_DEFAULT_TRANSPORT USNIC_TRANSPORT_ROCE_CUSTOM
+
+static void usnic_ib_fw_string_to_u64(char *fw_ver_str, u64 *fw_ver)
+{
+	*fw_ver = (u64) *fw_ver_str;
+}
+
+static int usnic_ib_fill_create_qp_resp(struct usnic_ib_qp_grp *qp_grp,
+					struct ib_udata *udata)
+{
+	struct usnic_ib_dev *us_ibdev;
+	struct usnic_ib_create_qp_resp resp;
+	struct pci_dev *pdev;
+	struct vnic_dev_bar *bar;
+	struct usnic_vnic_res_chunk *chunk;
+	struct usnic_ib_qp_grp_flow *default_flow;
+	int i, err;
+
+	memset(&resp, 0, sizeof(resp));
+
+	us_ibdev = qp_grp->vf->pf;
+	pdev = usnic_vnic_get_pdev(qp_grp->vf->vnic);
+	if (!pdev) {
+		usnic_err("Failed to get pdev of qp_grp %d\n",
+				qp_grp->grp_id);
+		return -EFAULT;
+	}
+
+	bar = usnic_vnic_get_bar(qp_grp->vf->vnic, 0);
+	if (!bar) {
+		usnic_err("Failed to get bar0 of qp_grp %d vf %s",
+				qp_grp->grp_id, pci_name(pdev));
+		return -EFAULT;
+	}
+
+	resp.vfid = usnic_vnic_get_index(qp_grp->vf->vnic);
+	resp.bar_bus_addr = bar->bus_addr;
+	resp.bar_len = bar->len;
+
+	chunk = usnic_ib_qp_grp_get_chunk(qp_grp, USNIC_VNIC_RES_TYPE_RQ);
+	if (IS_ERR_OR_NULL(chunk)) {
+		usnic_err("Failed to get chunk %s for qp_grp %d with err %ld\n",
+			usnic_vnic_res_type_to_str(USNIC_VNIC_RES_TYPE_RQ),
+			qp_grp->grp_id,
+			PTR_ERR(chunk));
+		return chunk ? PTR_ERR(chunk) : -ENOMEM;
+	}
+
+	WARN_ON(chunk->type != USNIC_VNIC_RES_TYPE_RQ);
+	resp.rq_cnt = chunk->cnt;
+	for (i = 0; i < chunk->cnt; i++)
+		resp.rq_idx[i] = chunk->res[i]->vnic_idx;
+
+	chunk = usnic_ib_qp_grp_get_chunk(qp_grp, USNIC_VNIC_RES_TYPE_WQ);
+	if (IS_ERR_OR_NULL(chunk)) {
+		usnic_err("Failed to get chunk %s for qp_grp %d with err %ld\n",
+			usnic_vnic_res_type_to_str(USNIC_VNIC_RES_TYPE_WQ),
+			qp_grp->grp_id,
+			PTR_ERR(chunk));
+		return chunk ? PTR_ERR(chunk) : -ENOMEM;
+	}
+
+	WARN_ON(chunk->type != USNIC_VNIC_RES_TYPE_WQ);
+	resp.wq_cnt = chunk->cnt;
+	for (i = 0; i < chunk->cnt; i++)
+		resp.wq_idx[i] = chunk->res[i]->vnic_idx;
+
+	chunk = usnic_ib_qp_grp_get_chunk(qp_grp, USNIC_VNIC_RES_TYPE_CQ);
+	if (IS_ERR_OR_NULL(chunk)) {
+		usnic_err("Failed to get chunk %s for qp_grp %d with err %ld\n",
+			usnic_vnic_res_type_to_str(USNIC_VNIC_RES_TYPE_CQ),
+			qp_grp->grp_id,
+			PTR_ERR(chunk));
+		return chunk ? PTR_ERR(chunk) : -ENOMEM;
+	}
+
+	WARN_ON(chunk->type != USNIC_VNIC_RES_TYPE_CQ);
+	resp.cq_cnt = chunk->cnt;
+	for (i = 0; i < chunk->cnt; i++)
+		resp.cq_idx[i] = chunk->res[i]->vnic_idx;
+
+	default_flow = list_first_entry(&qp_grp->flows_lst,
+					struct usnic_ib_qp_grp_flow, link);
+	resp.transport = default_flow->trans_type;
+
+	err = ib_copy_to_udata(udata, &resp, sizeof(resp));
+	if (err) {
+		usnic_err("Failed to copy udata for %s", us_ibdev->ib_dev.name);
+		return err;
+	}
+
+	return 0;
+}
+
+static struct usnic_ib_qp_grp*
+find_free_vf_and_create_qp_grp(struct usnic_ib_dev *us_ibdev,
+				struct usnic_ib_pd *pd,
+				struct usnic_transport_spec *trans_spec,
+				struct usnic_vnic_res_spec *res_spec)
+{
+	struct usnic_ib_vf *vf;
+	struct usnic_vnic *vnic;
+	struct usnic_ib_qp_grp *qp_grp;
+	struct device *dev, **dev_list;
+	int i, found = 0;
+
+	BUG_ON(!mutex_is_locked(&us_ibdev->usdev_lock));
+
+	if (list_empty(&us_ibdev->vf_dev_list)) {
+		usnic_info("No vfs to allocate\n");
+		return NULL;
+	}
+
+	if (usnic_ib_share_vf) {
+		/* Try to find resouces on a used vf which is in pd */
+		dev_list = usnic_uiom_get_dev_list(pd->umem_pd);
+		for (i = 0; dev_list[i]; i++) {
+			dev = dev_list[i];
+			vf = pci_get_drvdata(to_pci_dev(dev));
+			spin_lock(&vf->lock);
+			vnic = vf->vnic;
+			if (!usnic_vnic_check_room(vnic, res_spec)) {
+				usnic_dbg("Found used vnic %s from %s\n",
+						us_ibdev->ib_dev.name,
+						pci_name(usnic_vnic_get_pdev(
+									vnic)));
+				found = 1;
+				break;
+			}
+			spin_unlock(&vf->lock);
+
+		}
+		usnic_uiom_free_dev_list(dev_list);
+	}
+
+	if (!found) {
+		/* Try to find resources on an unused vf */
+		list_for_each_entry(vf, &us_ibdev->vf_dev_list, link) {
+			spin_lock(&vf->lock);
+			vnic = vf->vnic;
+			if (vf->qp_grp_ref_cnt == 0 &&
+				usnic_vnic_check_room(vnic, res_spec) == 0) {
+				found = 1;
+				break;
+			}
+			spin_unlock(&vf->lock);
+		}
+	}
+
+	if (!found) {
+		usnic_info("No free qp grp found on %s\n",
+				us_ibdev->ib_dev.name);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	qp_grp = usnic_ib_qp_grp_create(us_ibdev->ufdev, vf, pd, res_spec,
+						trans_spec);
+	spin_unlock(&vf->lock);
+	if (IS_ERR_OR_NULL(qp_grp)) {
+		usnic_err("Failed to allocate qp_grp\n");
+		return ERR_PTR(qp_grp ? PTR_ERR(qp_grp) : -ENOMEM);
+	}
+
+	return qp_grp;
+}
+
+static void qp_grp_destroy(struct usnic_ib_qp_grp *qp_grp)
+{
+	struct usnic_ib_vf *vf = qp_grp->vf;
+
+	WARN_ON(qp_grp->state != IB_QPS_RESET);
+
+	spin_lock(&vf->lock);
+	usnic_ib_qp_grp_destroy(qp_grp);
+	spin_unlock(&vf->lock);
+}
+
+static void eth_speed_to_ib_speed(int speed, u8 *active_speed,
+					u8 *active_width)
+{
+	if (speed <= 10000) {
+		*active_width = IB_WIDTH_1X;
+		*active_speed = IB_SPEED_FDR10;
+	} else if (speed <= 20000) {
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_DDR;
+	} else if (speed <= 30000) {
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_QDR;
+	} else if (speed <= 40000) {
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_FDR10;
+	} else {
+		*active_width = IB_WIDTH_4X;
+		*active_speed = IB_SPEED_EDR;
+	}
+}
+
+static int create_qp_validate_user_data(struct usnic_ib_create_qp_cmd cmd)
+{
+	if (cmd.spec.trans_type <= USNIC_TRANSPORT_UNKNOWN ||
+			cmd.spec.trans_type >= USNIC_TRANSPORT_MAX)
+		return -EINVAL;
+
+	return 0;
+}
+
+/* Start of ib callback functions */
+
+enum rdma_link_layer usnic_ib_port_link_layer(struct ib_device *device,
+						u8 port_num)
+{
+	return IB_LINK_LAYER_ETHERNET;
+}
+
+int usnic_ib_query_device(struct ib_device *ibdev,
+				struct ib_device_attr *props)
+{
+	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
+	union ib_gid gid;
+	struct ethtool_drvinfo info;
+	struct ethtool_cmd cmd;
+	int qp_per_vf;
+
+	usnic_dbg("\n");
+	mutex_lock(&us_ibdev->usdev_lock);
+	us_ibdev->netdev->ethtool_ops->get_drvinfo(us_ibdev->netdev, &info);
+	us_ibdev->netdev->ethtool_ops->get_settings(us_ibdev->netdev, &cmd);
+	memset(props, 0, sizeof(*props));
+	usnic_mac_ip_to_gid(us_ibdev->ufdev->mac, us_ibdev->ufdev->inaddr,
+			&gid.raw[0]);
+	memcpy(&props->sys_image_guid, &gid.global.interface_id,
+		sizeof(gid.global.interface_id));
+	usnic_ib_fw_string_to_u64(&info.fw_version[0], &props->fw_ver);
+	props->max_mr_size = USNIC_UIOM_MAX_MR_SIZE;
+	props->page_size_cap = USNIC_UIOM_PAGE_SIZE;
+	props->vendor_id = PCI_VENDOR_ID_CISCO;
+	props->vendor_part_id = PCI_DEVICE_ID_CISCO_VIC_USPACE_NIC;
+	props->hw_ver = us_ibdev->pdev->subsystem_device;
+	qp_per_vf = max(us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_WQ],
+			us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_RQ]);
+	props->max_qp = qp_per_vf *
+		atomic_read(&us_ibdev->vf_cnt.refcount);
+	props->device_cap_flags = IB_DEVICE_PORT_ACTIVE_EVENT |
+		IB_DEVICE_SYS_IMAGE_GUID | IB_DEVICE_BLOCK_MULTICAST_LOOPBACK;
+	props->max_cq = us_ibdev->vf_res_cnt[USNIC_VNIC_RES_TYPE_CQ] *
+		atomic_read(&us_ibdev->vf_cnt.refcount);
+	props->max_pd = USNIC_UIOM_MAX_PD_CNT;
+	props->max_mr = USNIC_UIOM_MAX_MR_CNT;
+	props->local_ca_ack_delay = 0;
+	props->max_pkeys = 0;
+	props->atomic_cap = IB_ATOMIC_NONE;
+	props->masked_atomic_cap = props->atomic_cap;
+	props->max_qp_rd_atom = 0;
+	props->max_qp_init_rd_atom = 0;
+	props->max_res_rd_atom = 0;
+	props->max_srq = 0;
+	props->max_srq_wr = 0;
+	props->max_srq_sge = 0;
+	props->max_fast_reg_page_list_len = 0;
+	props->max_mcast_grp = 0;
+	props->max_mcast_qp_attach = 0;
+	props->max_total_mcast_qp_attach = 0;
+	props->max_map_per_fmr = 0;
+	/* Owned by Userspace
+	 * max_qp_wr, max_sge, max_sge_rd, max_cqe */
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return 0;
+}
+
+int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
+				struct ib_port_attr *props)
+{
+	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
+	struct ethtool_cmd cmd;
+
+	usnic_dbg("\n");
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	us_ibdev->netdev->ethtool_ops->get_settings(us_ibdev->netdev, &cmd);
+	memset(props, 0, sizeof(*props));
+
+	props->lid = 0;
+	props->lmc = 1;
+	props->sm_lid = 0;
+	props->sm_sl = 0;
+
+	if (!us_ibdev->ufdev->link_up) {
+		props->state = IB_PORT_DOWN;
+		props->phys_state = 3;
+	} else if (!us_ibdev->ufdev->inaddr) {
+		props->state = IB_PORT_INIT;
+		props->phys_state = 4;
+	} else {
+		props->state = IB_PORT_ACTIVE;
+		props->phys_state = 5;
+	}
+
+	props->port_cap_flags = 0;
+	props->gid_tbl_len = 1;
+	props->pkey_tbl_len = 1;
+	props->bad_pkey_cntr = 0;
+	props->qkey_viol_cntr = 0;
+	eth_speed_to_ib_speed(cmd.speed, &props->active_speed,
+				&props->active_width);
+	props->max_mtu = IB_MTU_4096;
+	props->active_mtu = iboe_get_mtu(us_ibdev->ufdev->mtu);
+	/* Userspace will adjust for hdrs */
+	props->max_msg_sz = us_ibdev->ufdev->mtu;
+	props->max_vl_num = 1;
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return 0;
+}
+
+int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
+				int qp_attr_mask,
+				struct ib_qp_init_attr *qp_init_attr)
+{
+	struct usnic_ib_qp_grp *qp_grp;
+	struct usnic_ib_vf *vf;
+	int err;
+
+	usnic_dbg("\n");
+
+	memset(qp_attr, 0, sizeof(*qp_attr));
+	memset(qp_init_attr, 0, sizeof(*qp_init_attr));
+
+	qp_grp = to_uqp_grp(qp);
+	vf = qp_grp->vf;
+	mutex_lock(&vf->pf->usdev_lock);
+	usnic_dbg("\n");
+	qp_attr->qp_state = qp_grp->state;
+	qp_attr->cur_qp_state = qp_grp->state;
+
+	switch (qp_grp->ibqp.qp_type) {
+	case IB_QPT_UD:
+		qp_attr->qkey = 0;
+		break;
+	default:
+		usnic_err("Unexpected qp_type %d\n", qp_grp->ibqp.qp_type);
+		err = -EINVAL;
+		goto err_out;
+	}
+
+	mutex_unlock(&vf->pf->usdev_lock);
+	return 0;
+
+err_out:
+	mutex_unlock(&vf->pf->usdev_lock);
+	return err;
+}
+
+int usnic_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
+				union ib_gid *gid)
+{
+
+	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
+	usnic_dbg("\n");
+
+	if (index > 1)
+		return -EINVAL;
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	memset(&(gid->raw[0]), 0, sizeof(gid->raw));
+	usnic_mac_ip_to_gid(us_ibdev->ufdev->mac, us_ibdev->ufdev->inaddr,
+			&gid->raw[0]);
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return 0;
+}
+
+int usnic_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
+				u16 *pkey)
+{
+	if (index > 1)
+		return -EINVAL;
+
+	*pkey = 0xffff;
+	return 0;
+}
+
+struct ib_pd *usnic_ib_alloc_pd(struct ib_device *ibdev,
+					struct ib_ucontext *context,
+					struct ib_udata *udata)
+{
+	struct usnic_ib_pd *pd;
+	void *umem_pd;
+
+	usnic_dbg("\n");
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return ERR_PTR(-ENOMEM);
+
+	umem_pd = pd->umem_pd = usnic_uiom_alloc_pd();
+	if (IS_ERR_OR_NULL(umem_pd)) {
+		kfree(pd);
+		return ERR_PTR(umem_pd ? PTR_ERR(umem_pd) : -ENOMEM);
+	}
+
+	usnic_info("domain 0x%p allocated for context 0x%p and device %s\n",
+			pd, context, ibdev->name);
+	return &pd->ibpd;
+}
+
+int usnic_ib_dealloc_pd(struct ib_pd *pd)
+{
+	usnic_info("freeing domain 0x%p\n", pd);
+
+	usnic_uiom_dealloc_pd((to_upd(pd))->umem_pd);
+	kfree(pd);
+	return 0;
+}
+
+struct ib_qp *usnic_ib_create_qp(struct ib_pd *pd,
+					struct ib_qp_init_attr *init_attr,
+					struct ib_udata *udata)
+{
+	int err;
+	struct usnic_ib_dev *us_ibdev;
+	struct usnic_ib_qp_grp *qp_grp;
+	struct usnic_ib_ucontext *ucontext;
+	int cq_cnt;
+	struct usnic_vnic_res_spec res_spec;
+	struct usnic_ib_create_qp_cmd cmd;
+	struct usnic_transport_spec trans_spec;
+
+	usnic_dbg("\n");
+
+	ucontext = to_uucontext(pd->uobject->context);
+	us_ibdev = to_usdev(pd->device);
+
+	err = ib_copy_from_udata(&cmd, udata, sizeof(cmd));
+	if (err) {
+		usnic_err("%s: cannot copy udata for create_qp\n",
+				us_ibdev->ib_dev.name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	err = create_qp_validate_user_data(cmd);
+	if (err) {
+		usnic_err("%s: Failed to validate user data\n",
+				us_ibdev->ib_dev.name);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (init_attr->qp_type != IB_QPT_UD) {
+		usnic_err("%s asked to make a non-UD QP: %d\n",
+				us_ibdev->ib_dev.name, init_attr->qp_type);
+		return ERR_PTR(-EINVAL);
+	}
+
+	trans_spec = cmd.spec;
+	mutex_lock(&us_ibdev->usdev_lock);
+	cq_cnt = (init_attr->send_cq == init_attr->recv_cq) ? 1 : 2;
+	res_spec = min_transport_spec[trans_spec.trans_type];
+	usnic_vnic_res_spec_update(&res_spec, USNIC_VNIC_RES_TYPE_CQ, cq_cnt);
+	qp_grp = find_free_vf_and_create_qp_grp(us_ibdev, to_upd(pd),
+						&trans_spec,
+						&res_spec);
+	if (IS_ERR_OR_NULL(qp_grp)) {
+		err = qp_grp ? PTR_ERR(qp_grp) : -ENOMEM;
+		goto out_release_mutex;
+	}
+
+	err = usnic_ib_fill_create_qp_resp(qp_grp, udata);
+	if (err) {
+		err = -EBUSY;
+		goto out_release_qp_grp;
+	}
+
+	qp_grp->ctx = ucontext;
+	list_add_tail(&qp_grp->link, &ucontext->qp_grp_list);
+	usnic_ib_log_vf(qp_grp->vf);
+	mutex_unlock(&us_ibdev->usdev_lock);
+	return &qp_grp->ibqp;
+
+out_release_qp_grp:
+	qp_grp_destroy(qp_grp);
+out_release_mutex:
+	mutex_unlock(&us_ibdev->usdev_lock);
+	return ERR_PTR(err);
+}
+
+int usnic_ib_destroy_qp(struct ib_qp *qp)
+{
+	struct usnic_ib_qp_grp *qp_grp;
+	struct usnic_ib_vf *vf;
+
+	usnic_dbg("\n");
+
+	qp_grp = to_uqp_grp(qp);
+	vf = qp_grp->vf;
+	mutex_lock(&vf->pf->usdev_lock);
+	if (usnic_ib_qp_grp_modify(qp_grp, IB_QPS_RESET, NULL)) {
+		usnic_err("Failed to move qp grp %u to reset\n",
+				qp_grp->grp_id);
+	}
+
+	list_del(&qp_grp->link);
+	qp_grp_destroy(qp_grp);
+	mutex_unlock(&vf->pf->usdev_lock);
+
+	return 0;
+}
+
+int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+				int attr_mask, struct ib_udata *udata)
+{
+	struct usnic_ib_qp_grp *qp_grp;
+	int status;
+	usnic_dbg("\n");
+
+	qp_grp = to_uqp_grp(ibqp);
+
+	/* TODO: Future Support All States */
+	mutex_lock(&qp_grp->vf->pf->usdev_lock);
+	if ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_INIT) {
+		status = usnic_ib_qp_grp_modify(qp_grp, IB_QPS_INIT, NULL);
+	} else if ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_RTR) {
+		status = usnic_ib_qp_grp_modify(qp_grp, IB_QPS_RTR, NULL);
+	} else if ((attr_mask & IB_QP_STATE) && attr->qp_state == IB_QPS_RTS) {
+		status = usnic_ib_qp_grp_modify(qp_grp, IB_QPS_RTS, NULL);
+	} else {
+		usnic_err("Unexpected combination mask: %u state: %u\n",
+				attr_mask & IB_QP_STATE, attr->qp_state);
+		status = -EINVAL;
+	}
+
+	mutex_unlock(&qp_grp->vf->pf->usdev_lock);
+	return status;
+}
+
+struct ib_cq *usnic_ib_create_cq(struct ib_device *ibdev, int entries,
+					int vector, struct ib_ucontext *context,
+					struct ib_udata *udata)
+{
+	struct ib_cq *cq;
+
+	usnic_dbg("\n");
+	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
+	if (!cq)
+		return ERR_PTR(-EBUSY);
+
+	return cq;
+}
+
+int usnic_ib_destroy_cq(struct ib_cq *cq)
+{
+	usnic_dbg("\n");
+	kfree(cq);
+	return 0;
+}
+
+struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
+					u64 virt_addr, int access_flags,
+					struct ib_udata *udata)
+{
+	struct usnic_ib_mr *mr;
+	int err;
+
+	usnic_dbg("start 0x%llx va 0x%llx length 0x%llx\n", start,
+			virt_addr, length);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (IS_ERR_OR_NULL(mr))
+		return ERR_PTR(mr ? PTR_ERR(mr) : -ENOMEM);
+
+	mr->umem = usnic_uiom_reg_get(to_upd(pd)->umem_pd, start, length,
+					access_flags, 0);
+	if (IS_ERR_OR_NULL(mr->umem)) {
+		err = mr->umem ? PTR_ERR(mr->umem) : -EFAULT;
+		goto err_free;
+	}
+
+	mr->ibmr.lkey = mr->ibmr.rkey = 0;
+	return &mr->ibmr;
+
+err_free:
+	kfree(mr);
+	return ERR_PTR(err);
+}
+
+int usnic_ib_dereg_mr(struct ib_mr *ibmr)
+{
+	struct usnic_ib_mr *mr = to_umr(ibmr);
+
+	usnic_dbg("va 0x%lx length 0x%zx\n", mr->umem->va, mr->umem->length);
+
+	usnic_uiom_reg_release(mr->umem, ibmr->pd->uobject->context->closing);
+	kfree(mr);
+	return 0;
+}
+
+struct ib_ucontext *usnic_ib_alloc_ucontext(struct ib_device *ibdev,
+							struct ib_udata *udata)
+{
+	struct usnic_ib_ucontext *context;
+	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
+	usnic_dbg("\n");
+
+	context = kmalloc(sizeof(*context), GFP_KERNEL);
+	if (!context)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&context->qp_grp_list);
+	mutex_lock(&us_ibdev->usdev_lock);
+	list_add_tail(&context->link, &us_ibdev->ctx_list);
+	mutex_unlock(&us_ibdev->usdev_lock);
+
+	return &context->ibucontext;
+}
+
+int usnic_ib_dealloc_ucontext(struct ib_ucontext *ibcontext)
+{
+	struct usnic_ib_ucontext *context = to_uucontext(ibcontext);
+	struct usnic_ib_dev *us_ibdev = to_usdev(ibcontext->device);
+	usnic_dbg("\n");
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	BUG_ON(!list_empty(&context->qp_grp_list));
+	list_del(&context->link);
+	mutex_unlock(&us_ibdev->usdev_lock);
+	kfree(context);
+	return 0;
+}
+
+int usnic_ib_mmap(struct ib_ucontext *context,
+				struct vm_area_struct *vma)
+{
+	struct usnic_ib_ucontext *uctx = to_ucontext(context);
+	struct usnic_ib_dev *us_ibdev;
+	struct usnic_ib_qp_grp *qp_grp;
+	struct usnic_ib_vf *vf;
+	struct vnic_dev_bar *bar;
+	dma_addr_t bus_addr;
+	unsigned int len;
+	unsigned int vfid;
+
+	usnic_dbg("\n");
+
+	us_ibdev = to_usdev(context->device);
+	vma->vm_flags |= VM_IO;
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+	vfid = vma->vm_pgoff;
+	usnic_dbg("Page Offset %lu PAGE_SHIFT %u VFID %u\n",
+			vma->vm_pgoff, PAGE_SHIFT, vfid);
+
+	mutex_lock(&us_ibdev->usdev_lock);
+	list_for_each_entry(qp_grp, &uctx->qp_grp_list, link) {
+		vf = qp_grp->vf;
+		if (usnic_vnic_get_index(vf->vnic) == vfid) {
+			bar = usnic_vnic_get_bar(vf->vnic, 0);
+			if ((vma->vm_end - vma->vm_start) != bar->len) {
+				usnic_err("Bar0 Len %lu - Request map %lu\n",
+						bar->len,
+						vma->vm_end - vma->vm_start);
+				mutex_unlock(&us_ibdev->usdev_lock);
+				return -EINVAL;
+			}
+			bus_addr = bar->bus_addr;
+			len = bar->len;
+			usnic_dbg("bus: %pa vaddr: %p size: %ld\n",
+					&bus_addr, bar->vaddr, bar->len);
+			mutex_unlock(&us_ibdev->usdev_lock);
+
+			return remap_pfn_range(vma,
+						vma->vm_start,
+						bus_addr >> PAGE_SHIFT,
+						len, vma->vm_page_prot);
+		}
+	}
+
+	mutex_unlock(&us_ibdev->usdev_lock);
+	usnic_err("No VF %u found\n", vfid);
+	return -EINVAL;
+}
+
+/* In ib callbacks section -  Start of stub funcs */
+struct ib_ah *usnic_ib_create_ah(struct ib_pd *pd,
+					struct ib_ah_attr *ah_attr)
+{
+	usnic_dbg("\n");
+	return ERR_PTR(-EPERM);
+}
+
+int usnic_ib_destroy_ah(struct ib_ah *ah)
+{
+	usnic_dbg("\n");
+	return -EINVAL;
+}
+
+int usnic_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+				struct ib_send_wr **bad_wr)
+{
+	usnic_dbg("\n");
+	return -EINVAL;
+}
+
+int usnic_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
+				struct ib_recv_wr **bad_wr)
+{
+	usnic_dbg("\n");
+	return -EINVAL;
+}
+
+int usnic_ib_poll_cq(struct ib_cq *ibcq, int num_entries,
+				struct ib_wc *wc)
+{
+	usnic_dbg("\n");
+	return -EINVAL;
+}
+
+int usnic_ib_req_notify_cq(struct ib_cq *cq,
+					enum ib_cq_notify_flags flags)
+{
+	usnic_dbg("\n");
+	return -EINVAL;
+}
+
+struct ib_mr *usnic_ib_get_dma_mr(struct ib_pd *pd, int acc)
+{
+	usnic_dbg("\n");
+	return ERR_PTR(-ENOMEM);
+}
+
+
+/* In ib callbacks section - End of stub funcs */
+/* End of ib callbacks section */

drivers/infiniband/hw/usnic/usnic_ib_verbs.h

@@ -0,0 +1,72 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_IB_VERBS_H_
+#define USNIC_IB_VERBS_H_
+
+#include "usnic_ib.h"
+
+enum rdma_link_layer usnic_ib_port_link_layer(struct ib_device *device,
+						u8 port_num);
+int usnic_ib_query_device(struct ib_device *ibdev,
+				struct ib_device_attr *props);
+int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
+				struct ib_port_attr *props);
+int usnic_ib_query_qp(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
+				int qp_attr_mask,
+				struct ib_qp_init_attr *qp_init_attr);
+int usnic_ib_query_gid(struct ib_device *ibdev, u8 port, int index,
+				union ib_gid *gid);
+int usnic_ib_query_pkey(struct ib_device *ibdev, u8 port, u16 index,
+				u16 *pkey);
+struct ib_pd *usnic_ib_alloc_pd(struct ib_device *ibdev,
+				struct ib_ucontext *context,
+				struct ib_udata *udata);
+int usnic_ib_dealloc_pd(struct ib_pd *pd);
+struct ib_qp *usnic_ib_create_qp(struct ib_pd *pd,
+					struct ib_qp_init_attr *init_attr,
+					struct ib_udata *udata);
+int usnic_ib_destroy_qp(struct ib_qp *qp);
+int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+				int attr_mask, struct ib_udata *udata);
+struct ib_cq *usnic_ib_create_cq(struct ib_device *ibdev, int entries,
+					int vector, struct ib_ucontext *context,
+					struct ib_udata *udata);
+int usnic_ib_destroy_cq(struct ib_cq *cq);
+struct ib_mr *usnic_ib_reg_mr(struct ib_pd *pd, u64 start, u64 length,
+				u64 virt_addr, int access_flags,
+				struct ib_udata *udata);
+int usnic_ib_dereg_mr(struct ib_mr *ibmr);
+struct ib_ucontext *usnic_ib_alloc_ucontext(struct ib_device *ibdev,
+						struct ib_udata *udata);
+int usnic_ib_dealloc_ucontext(struct ib_ucontext *ibcontext);
+int usnic_ib_mmap(struct ib_ucontext *context,
+			struct vm_area_struct *vma);
+struct ib_ah *usnic_ib_create_ah(struct ib_pd *pd,
+					struct ib_ah_attr *ah_attr);
+int usnic_ib_destroy_ah(struct ib_ah *ah);
+int usnic_ib_post_send(struct ib_qp *ibqp, struct ib_send_wr *wr,
+			struct ib_send_wr **bad_wr);
+int usnic_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
+			struct ib_recv_wr **bad_wr);
+int usnic_ib_poll_cq(struct ib_cq *ibcq, int num_entries,
+			struct ib_wc *wc);
+int usnic_ib_req_notify_cq(struct ib_cq *cq,
+				enum ib_cq_notify_flags flags);
+struct ib_mr *usnic_ib_get_dma_mr(struct ib_pd *pd, int acc);
+#endif /* !USNIC_IB_VERBS_H */

drivers/infiniband/hw/usnic/usnic_log.h

@@ -0,0 +1,58 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_LOG_H_
+#define USNIC_LOG_H_
+
+#include "usnic.h"
+
+extern unsigned int usnic_log_lvl;
+
+#define USNIC_LOG_LVL_NONE		(0)
+#define USNIC_LOG_LVL_ERR		(1)
+#define USNIC_LOG_LVL_INFO		(2)
+#define USNIC_LOG_LVL_DBG		(3)
+
+#define usnic_printk(lvl, args...) \
+	do { \
+		printk(lvl "%s:%s:%d: ", DRV_NAME, __func__, \
+				__LINE__); \
+		printk(args); \
+	} while (0)
+
+#define usnic_dbg(args...) \
+	do { \
+		if (unlikely(usnic_log_lvl >= USNIC_LOG_LVL_DBG)) { \
+			usnic_printk(KERN_INFO, args); \
+	} \
+} while (0)
+
+#define usnic_info(args...) \
+do { \
+	if (usnic_log_lvl >= USNIC_LOG_LVL_INFO) { \
+			usnic_printk(KERN_INFO, args); \
+	} \
+} while (0)
+
+#define usnic_err(args...) \
+	do { \
+		if (usnic_log_lvl >= USNIC_LOG_LVL_ERR) { \
+			usnic_printk(KERN_ERR, args); \
+		} \
+	} while (0)
+#endif /* !USNIC_LOG_H_ */

drivers/infiniband/hw/usnic/usnic_transport.c

@@ -0,0 +1,202 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+#include <linux/bitmap.h>
+#include <linux/file.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <net/inet_sock.h>
+
+#include "usnic_transport.h"
+#include "usnic_log.h"
+
+/* ROCE */
+static unsigned long *roce_bitmap;
+static u16 roce_next_port = 1;
+#define ROCE_BITMAP_SZ ((1 << (8 /*CHAR_BIT*/ * sizeof(u16)))/8 /*CHAR BIT*/)
+static DEFINE_SPINLOCK(roce_bitmap_lock);
+
+const char *usnic_transport_to_str(enum usnic_transport_type type)
+{
+	switch (type) {
+	case USNIC_TRANSPORT_UNKNOWN:
+		return "Unknown";
+	case USNIC_TRANSPORT_ROCE_CUSTOM:
+		return "roce custom";
+	case USNIC_TRANSPORT_IPV4_UDP:
+		return "IPv4 UDP";
+	case USNIC_TRANSPORT_MAX:
+		return "Max?";
+	default:
+		return "Not known";
+	}
+}
+
+int usnic_transport_sock_to_str(char *buf, int buf_sz,
+					struct socket *sock)
+{
+	int err;
+	uint32_t addr;
+	uint16_t port;
+	int proto;
+
+	memset(buf, 0, buf_sz);
+	err = usnic_transport_sock_get_addr(sock, &proto, &addr, &port);
+	if (err)
+		return 0;
+
+	return scnprintf(buf, buf_sz, "Proto:%u Addr:%pI4h Port:%hu",
+			proto, &addr, port);
+}
+
+/*
+ * reserve a port number.  if "0" specified, we will try to pick one
+ * starting at roce_next_port.  roce_next_port will take on the values
+ * 1..4096
+ */
+u16 usnic_transport_rsrv_port(enum usnic_transport_type type, u16 port_num)
+{
+	if (type == USNIC_TRANSPORT_ROCE_CUSTOM) {
+		spin_lock(&roce_bitmap_lock);
+		if (!port_num) {
+			port_num = bitmap_find_next_zero_area(roce_bitmap,
+						ROCE_BITMAP_SZ,
+						roce_next_port /* start */,
+						1 /* nr */,
+						0 /* align */);
+			roce_next_port = (port_num & 4095) + 1;
+		} else if (test_bit(port_num, roce_bitmap)) {
+			usnic_err("Failed to allocate port for %s\n",
+					usnic_transport_to_str(type));
+			spin_unlock(&roce_bitmap_lock);
+			goto out_fail;
+		}
+		bitmap_set(roce_bitmap, port_num, 1);
+		spin_unlock(&roce_bitmap_lock);
+	} else {
+		usnic_err("Failed to allocate port - transport %s unsupported\n",
+				usnic_transport_to_str(type));
+		goto out_fail;
+	}
+
+	usnic_dbg("Allocating port %hu for %s\n", port_num,
+			usnic_transport_to_str(type));
+	return port_num;
+
+out_fail:
+	return 0;
+}
+
+void usnic_transport_unrsrv_port(enum usnic_transport_type type, u16 port_num)
+{
+	if (type == USNIC_TRANSPORT_ROCE_CUSTOM) {
+		spin_lock(&roce_bitmap_lock);
+		if (!port_num) {
+			usnic_err("Unreserved unvalid port num 0 for %s\n",
+					usnic_transport_to_str(type));
+			goto out_roce_custom;
+		}
+
+		if (!test_bit(port_num, roce_bitmap)) {
+			usnic_err("Unreserving invalid %hu for %s\n",
+					port_num,
+					usnic_transport_to_str(type));
+			goto out_roce_custom;
+		}
+		bitmap_clear(roce_bitmap, port_num, 1);
+		usnic_dbg("Freeing port %hu for %s\n", port_num,
+				usnic_transport_to_str(type));
+out_roce_custom:
+		spin_unlock(&roce_bitmap_lock);
+	} else {
+		usnic_err("Freeing invalid port %hu for %d\n", port_num, type);
+	}
+}
+
+struct socket *usnic_transport_get_socket(int sock_fd)
+{
+	struct socket *sock;
+	int err;
+	char buf[25];
+
+	/* sockfd_lookup will internally do a fget */
+	sock = sockfd_lookup(sock_fd, &err);
+	if (!sock) {
+		usnic_err("Unable to lookup socket for fd %d with err %d\n",
+				sock_fd, err);
+		return ERR_PTR(-ENOENT);
+	}
+
+	usnic_transport_sock_to_str(buf, sizeof(buf), sock);
+	usnic_dbg("Get sock %s\n", buf);
+
+	return sock;
+}
+
+void usnic_transport_put_socket(struct socket *sock)
+{
+	char buf[100];
+
+	usnic_transport_sock_to_str(buf, sizeof(buf), sock);
+	usnic_dbg("Put sock %s\n", buf);
+	sockfd_put(sock);
+}
+
+int usnic_transport_sock_get_addr(struct socket *sock, int *proto,
+					uint32_t *addr, uint16_t *port)
+{
+	int len;
+	int err;
+	struct sockaddr_in sock_addr;
+
+	err = sock->ops->getname(sock,
+				(struct sockaddr *)&sock_addr,
+				&len, 0);
+	if (err)
+		return err;
+
+	if (sock_addr.sin_family != AF_INET)
+		return -EINVAL;
+
+	if (proto)
+		*proto = sock->sk->sk_protocol;
+	if (port)
+		*port = ntohs(((struct sockaddr_in *)&sock_addr)->sin_port);
+	if (addr)
+		*addr = ntohl(((struct sockaddr_in *)
+					&sock_addr)->sin_addr.s_addr);
+
+	return 0;
+}
+
+int usnic_transport_init(void)
+{
+	roce_bitmap = kzalloc(ROCE_BITMAP_SZ, GFP_KERNEL);
+	if (!roce_bitmap) {
+		usnic_err("Failed to allocate bit map");
+		return -ENOMEM;
+	}
+
+	/* Do not ever allocate bit 0, hence set it here */
+	bitmap_set(roce_bitmap, 0, 1);
+	return 0;
+}
+
+void usnic_transport_fini(void)
+{
+	kfree(roce_bitmap);
+}

drivers/infiniband/hw/usnic/usnic_transport.h

@@ -0,0 +1,51 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_TRANSPORT_H_
+#define USNIC_TRANSPORT_H_
+
+#include "usnic_abi.h"
+
+const char *usnic_transport_to_str(enum usnic_transport_type trans_type);
+/*
+ * Returns number of bytes written, excluding null terminator. If
+ * nothing was written, the function returns 0.
+ */
+int usnic_transport_sock_to_str(char *buf, int buf_sz,
+					struct socket *sock);
+/*
+ * Reserve a port. If "port_num" is set, then the function will try
+ * to reserve that particular port.
+ */
+u16 usnic_transport_rsrv_port(enum usnic_transport_type type, u16 port_num);
+void usnic_transport_unrsrv_port(enum usnic_transport_type type, u16 port_num);
+/*
+ * Do a fget on the socket refered to by sock_fd and returns the socket.
+ * Socket will not be destroyed before usnic_transport_put_socket has
+ * been called.
+ */
+struct socket *usnic_transport_get_socket(int sock_fd);
+void usnic_transport_put_socket(struct socket *sock);
+/*
+ * Call usnic_transport_get_socket before calling *_sock_get_addr
+ */
+int usnic_transport_sock_get_addr(struct socket *sock, int *proto,
+					uint32_t *addr, uint16_t *port);
+int usnic_transport_init(void);
+void usnic_transport_fini(void);
+#endif /* !USNIC_TRANSPORT_H */

drivers/infiniband/hw/usnic/usnic_uiom.c

@@ -0,0 +1,604 @@
+/*
+ * Copyright (c) 2005 Topspin Communications.  All rights reserved.
+ * Copyright (c) 2005 Mellanox Technologies. All rights reserved.
+ * Copyright (c) 2013 Cisco Systems.  All rights reserved.
+ *
+ * This software is available to you under a choice of one of two
+ * licenses.  You may choose to be licensed under the terms of the GNU
+ * General Public License (GPL) Version 2, available from the file
+ * COPYING in the main directory of this source tree, or the
+ * OpenIB.org BSD license below:
+ *
+ *     Redistribution and use in source and binary forms, with or
+ *     without modification, are permitted provided that the following
+ *     conditions are met:
+ *
+ *      - Redistributions of source code must retain the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer.
+ *
+ *      - Redistributions in binary form must reproduce the above
+ *        copyright notice, this list of conditions and the following
+ *        disclaimer in the documentation and/or other materials
+ *        provided with the distribution.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/sched.h>
+#include <linux/hugetlb.h>
+#include <linux/dma-attrs.h>
+#include <linux/iommu.h>
+#include <linux/workqueue.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+
+#include "usnic_log.h"
+#include "usnic_uiom.h"
+#include "usnic_uiom_interval_tree.h"
+
+static struct workqueue_struct *usnic_uiom_wq;
+
+#define USNIC_UIOM_PAGE_CHUNK						\
+	((PAGE_SIZE - offsetof(struct usnic_uiom_chunk, page_list))	/\
+	((void *) &((struct usnic_uiom_chunk *) 0)->page_list[1] -	\
+	(void *) &((struct usnic_uiom_chunk *) 0)->page_list[0]))
+
+static void usnic_uiom_reg_account(struct work_struct *work)
+{
+	struct usnic_uiom_reg *umem = container_of(work,
+						struct usnic_uiom_reg, work);
+
+	down_write(&umem->mm->mmap_sem);
+	umem->mm->locked_vm -= umem->diff;
+	up_write(&umem->mm->mmap_sem);
+	mmput(umem->mm);
+	kfree(umem);
+}
+
+static int usnic_uiom_dma_fault(struct iommu_domain *domain,
+				struct device *dev,
+				unsigned long iova, int flags,
+				void *token)
+{
+	usnic_err("Device %s iommu fault domain 0x%pK va 0x%lx flags 0x%x\n",
+		dev_name(dev),
+		domain, iova, flags);
+	return -ENOSYS;
+}
+
+static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
+{
+	struct usnic_uiom_chunk *chunk, *tmp;
+	struct page *page;
+	struct scatterlist *sg;
+	int i;
+	dma_addr_t pa;
+
+	list_for_each_entry_safe(chunk, tmp, chunk_list, list) {
+		for_each_sg(chunk->page_list, sg, chunk->nents, i) {
+			page = sg_page(sg);
+			pa = sg_phys(sg);
+			if (dirty)
+				set_page_dirty_lock(page);
+			put_page(page);
+			usnic_dbg("pa: %pa\n", &pa);
+		}
+		kfree(chunk);
+	}
+}
+
+static int usnic_uiom_get_pages(unsigned long addr, size_t size, int writable,
+				int dmasync, struct list_head *chunk_list)
+{
+	struct page **page_list;
+	struct scatterlist *sg;
+	struct usnic_uiom_chunk *chunk;
+	unsigned long locked;
+	unsigned long lock_limit;
+	unsigned long cur_base;
+	unsigned long npages;
+	int ret;
+	int off;
+	int i;
+	int flags;
+	dma_addr_t pa;
+	DEFINE_DMA_ATTRS(attrs);
+
+	if (dmasync)
+		dma_set_attr(DMA_ATTR_WRITE_BARRIER, &attrs);
+
+	if (!can_do_mlock())
+		return -EPERM;
+
+	INIT_LIST_HEAD(chunk_list);
+
+	page_list = (struct page **) __get_free_page(GFP_KERNEL);
+	if (!page_list)
+		return -ENOMEM;
+
+	npages = PAGE_ALIGN(size + (addr & ~PAGE_MASK)) >> PAGE_SHIFT;
+
+	down_write(&current->mm->mmap_sem);
+
+	locked = npages + current->mm->locked_vm;
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+	if ((locked > lock_limit) && !capable(CAP_IPC_LOCK)) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	flags = IOMMU_READ | IOMMU_CACHE;
+	flags |= (writable) ? IOMMU_WRITE : 0;
+	cur_base = addr & PAGE_MASK;
+	ret = 0;
+
+	while (npages) {
+		ret = get_user_pages(current, current->mm, cur_base,
+					min_t(unsigned long, npages,
+					PAGE_SIZE / sizeof(struct page *)),
+					1, !writable, page_list, NULL);
+
+		if (ret < 0)
+			goto out;
+
+		npages -= ret;
+		off = 0;
+
+		while (ret) {
+			chunk = kmalloc(sizeof(*chunk) +
+					sizeof(struct scatterlist) *
+					min_t(int, ret, USNIC_UIOM_PAGE_CHUNK),
+					GFP_KERNEL);
+			if (!chunk) {
+				ret = -ENOMEM;
+				goto out;
+			}
+
+			chunk->nents = min_t(int, ret, USNIC_UIOM_PAGE_CHUNK);
+			sg_init_table(chunk->page_list, chunk->nents);
+			for_each_sg(chunk->page_list, sg, chunk->nents, i) {
+				sg_set_page(sg, page_list[i + off],
+						PAGE_SIZE, 0);
+				pa = sg_phys(sg);
+				usnic_dbg("va: 0x%lx pa: %pa\n",
+						cur_base + i*PAGE_SIZE, &pa);
+			}
+			cur_base += chunk->nents * PAGE_SIZE;
+			ret -= chunk->nents;
+			off += chunk->nents;
+			list_add_tail(&chunk->list, chunk_list);
+		}
+
+		ret = 0;
+	}
+
+out:
+	if (ret < 0)
+		usnic_uiom_put_pages(chunk_list, 0);
+	else
+		current->mm->locked_vm = locked;
+
+	up_write(&current->mm->mmap_sem);
+	free_page((unsigned long) page_list);
+	return ret;
+}
+
+static void usnic_uiom_unmap_sorted_intervals(struct list_head *intervals,
+						struct usnic_uiom_pd *pd)
+{
+	struct usnic_uiom_interval_node *interval, *tmp;
+	long unsigned va, size;
+
+	list_for_each_entry_safe(interval, tmp, intervals, link) {
+		va = interval->start << PAGE_SHIFT;
+		size = ((interval->last - interval->start) + 1) << PAGE_SHIFT;
+		while (size > 0) {
+			/* Workaround for RH 970401 */
+			usnic_dbg("va 0x%lx size 0x%lx", va, PAGE_SIZE);
+			iommu_unmap(pd->domain, va, PAGE_SIZE);
+			va += PAGE_SIZE;
+			size -= PAGE_SIZE;
+		}
+	}
+}
+
+static void __usnic_uiom_reg_release(struct usnic_uiom_pd *pd,
+					struct usnic_uiom_reg *uiomr,
+					int dirty)
+{
+	int npages;
+	unsigned long vpn_start, vpn_last;
+	struct usnic_uiom_interval_node *interval, *tmp;
+	int writable = 0;
+	LIST_HEAD(rm_intervals);
+
+	npages = PAGE_ALIGN(uiomr->length + uiomr->offset) >> PAGE_SHIFT;
+	vpn_start = (uiomr->va & PAGE_MASK) >> PAGE_SHIFT;
+	vpn_last = vpn_start + npages - 1;
+
+	spin_lock(&pd->lock);
+	usnic_uiom_remove_interval(&pd->rb_root, vpn_start,
+					vpn_last, &rm_intervals);
+	usnic_uiom_unmap_sorted_intervals(&rm_intervals, pd);
+
+	list_for_each_entry_safe(interval, tmp, &rm_intervals, link) {
+		if (interval->flags & IOMMU_WRITE)
+			writable = 1;
+		list_del(&interval->link);
+		kfree(interval);
+	}
+
+	usnic_uiom_put_pages(&uiomr->chunk_list, dirty & writable);
+	spin_unlock(&pd->lock);
+}
+
+static int usnic_uiom_map_sorted_intervals(struct list_head *intervals,
+						struct usnic_uiom_reg *uiomr)
+{
+	int i, err;
+	size_t size;
+	struct usnic_uiom_chunk *chunk;
+	struct usnic_uiom_interval_node *interval_node;
+	dma_addr_t pa;
+	dma_addr_t pa_start = 0;
+	dma_addr_t pa_end = 0;
+	long int va_start = -EINVAL;
+	struct usnic_uiom_pd *pd = uiomr->pd;
+	long int va = uiomr->va & PAGE_MASK;
+	int flags = IOMMU_READ | IOMMU_CACHE;
+
+	flags |= (uiomr->writable) ? IOMMU_WRITE : 0;
+	chunk = list_first_entry(&uiomr->chunk_list, struct usnic_uiom_chunk,
+									list);
+	list_for_each_entry(interval_node, intervals, link) {
+iter_chunk:
+		for (i = 0; i < chunk->nents; i++, va += PAGE_SIZE) {
+			pa = sg_phys(&chunk->page_list[i]);
+			if ((va >> PAGE_SHIFT) < interval_node->start)
+				continue;
+
+			if ((va >> PAGE_SHIFT) == interval_node->start) {
+				/* First page of the interval */
+				va_start = va;
+				pa_start = pa;
+				pa_end = pa;
+			}
+
+			WARN_ON(va_start == -EINVAL);
+
+			if ((pa_end + PAGE_SIZE != pa) &&
+					(pa != pa_start)) {
+				/* PAs are not contiguous */
+				size = pa_end - pa_start + PAGE_SIZE;
+				usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x",
+					va_start, &pa_start, size, flags);
+				err = iommu_map(pd->domain, va_start, pa_start,
+							size, flags);
+				if (err) {
+					usnic_err("Failed to map va 0x%lx pa 0x%pa size 0x%zx with err %d\n",
+						va_start, &pa_start, size, err);
+					goto err_out;
+				}
+				va_start = va;
+				pa_start = pa;
+				pa_end = pa;
+			}
+
+			if ((va >> PAGE_SHIFT) == interval_node->last) {
+				/* Last page of the interval */
+				size = pa - pa_start + PAGE_SIZE;
+				usnic_dbg("va 0x%lx pa %pa size 0x%zx flags 0x%x\n",
+					va_start, &pa_start, size, flags);
+				err = iommu_map(pd->domain, va_start, pa_start,
+						size, flags);
+				if (err) {
+					usnic_err("Failed to map va 0x%lx pa %pa size 0x%zx with err %d\n",
+						va_start, &pa_start, size, err);
+					goto err_out;
+				}
+				break;
+			}
+
+			if (pa != pa_start)
+				pa_end += PAGE_SIZE;
+		}
+
+		if (i == chunk->nents) {
+			/*
+			 * Hit last entry of the chunk,
+			 * hence advance to next chunk
+			 */
+			chunk = list_first_entry(&chunk->list,
+							struct usnic_uiom_chunk,
+							list);
+			goto iter_chunk;
+		}
+	}
+
+	return 0;
+
+err_out:
+	usnic_uiom_unmap_sorted_intervals(intervals, pd);
+	return err;
+}
+
+struct usnic_uiom_reg *usnic_uiom_reg_get(struct usnic_uiom_pd *pd,
+						unsigned long addr, size_t size,
+						int writable, int dmasync)
+{
+	struct usnic_uiom_reg *uiomr;
+	unsigned long va_base, vpn_start, vpn_last;
+	unsigned long npages;
+	int offset, err;
+	LIST_HEAD(sorted_diff_intervals);
+
+	/*
+	 * Intel IOMMU map throws an error if a translation entry is
+	 * changed from read to write.  This module may not unmap
+	 * and then remap the entry after fixing the permission
+	 * b/c this open up a small windows where hw DMA may page fault
+	 * Hence, make all entries to be writable.
+	 */
+	writable = 1;
+
+	va_base = addr & PAGE_MASK;
+	offset = addr & ~PAGE_MASK;
+	npages = PAGE_ALIGN(size + offset) >> PAGE_SHIFT;
+	vpn_start = (addr & PAGE_MASK) >> PAGE_SHIFT;
+	vpn_last = vpn_start + npages - 1;
+
+	uiomr = kmalloc(sizeof(*uiomr), GFP_KERNEL);
+	if (!uiomr)
+		return ERR_PTR(-ENOMEM);
+
+	uiomr->va = va_base;
+	uiomr->offset = offset;
+	uiomr->length = size;
+	uiomr->writable = writable;
+	uiomr->pd = pd;
+
+	err = usnic_uiom_get_pages(addr, size, writable, dmasync,
+					&uiomr->chunk_list);
+	if (err) {
+		usnic_err("Failed get_pages vpn [0x%lx,0x%lx] err %d\n",
+				vpn_start, vpn_last, err);
+		goto out_free_uiomr;
+	}
+
+	spin_lock(&pd->lock);
+	err = usnic_uiom_get_intervals_diff(vpn_start, vpn_last,
+						(writable) ? IOMMU_WRITE : 0,
+						IOMMU_WRITE,
+						&pd->rb_root,
+						&sorted_diff_intervals);
+	if (err) {
+		usnic_err("Failed disjoint interval vpn [0x%lx,0x%lx] err %d\n",
+						vpn_start, vpn_last, err);
+		goto out_put_pages;
+	}
+
+	err = usnic_uiom_map_sorted_intervals(&sorted_diff_intervals, uiomr);
+	if (err) {
+		usnic_err("Failed map interval vpn [0x%lx,0x%lx] err %d\n",
+						vpn_start, vpn_last, err);
+		goto out_put_intervals;
+
+	}
+
+	err = usnic_uiom_insert_interval(&pd->rb_root, vpn_start, vpn_last,
+					(writable) ? IOMMU_WRITE : 0);
+	if (err) {
+		usnic_err("Failed insert interval vpn [0x%lx,0x%lx] err %d\n",
+						vpn_start, vpn_last, err);
+		goto out_unmap_intervals;
+	}
+
+	usnic_uiom_put_interval_set(&sorted_diff_intervals);
+	spin_unlock(&pd->lock);
+
+	return uiomr;
+
+out_unmap_intervals:
+	usnic_uiom_unmap_sorted_intervals(&sorted_diff_intervals, pd);
+out_put_intervals:
+	usnic_uiom_put_interval_set(&sorted_diff_intervals);
+out_put_pages:
+	usnic_uiom_put_pages(&uiomr->chunk_list, 0);
+	spin_unlock(&pd->lock);
+out_free_uiomr:
+	kfree(uiomr);
+	return ERR_PTR(err);
+}
+
+void usnic_uiom_reg_release(struct usnic_uiom_reg *uiomr, int closing)
+{
+	struct mm_struct *mm;
+	unsigned long diff;
+
+	__usnic_uiom_reg_release(uiomr->pd, uiomr, 1);
+
+	mm = get_task_mm(current);
+	if (!mm) {
+		kfree(uiomr);
+		return;
+	}
+
+	diff = PAGE_ALIGN(uiomr->length + uiomr->offset) >> PAGE_SHIFT;
+
+	/*
+	 * We may be called with the mm's mmap_sem already held.  This
+	 * can happen when a userspace munmap() is the call that drops
+	 * the last reference to our file and calls our release
+	 * method.  If there are memory regions to destroy, we'll end
+	 * up here and not be able to take the mmap_sem.  In that case
+	 * we defer the vm_locked accounting to the system workqueue.
+	 */
+	if (closing) {
+		if (!down_write_trylock(&mm->mmap_sem)) {
+			INIT_WORK(&uiomr->work, usnic_uiom_reg_account);
+			uiomr->mm = mm;
+			uiomr->diff = diff;
+
+			queue_work(usnic_uiom_wq, &uiomr->work);
+			return;
+		}
+	} else
+		down_write(&mm->mmap_sem);
+
+	current->mm->locked_vm -= diff;
+	up_write(&mm->mmap_sem);
+	mmput(mm);
+	kfree(uiomr);
+}
+
+struct usnic_uiom_pd *usnic_uiom_alloc_pd(void)
+{
+	struct usnic_uiom_pd *pd;
+	void *domain;
+
+	pd = kzalloc(sizeof(*pd), GFP_KERNEL);
+	if (!pd)
+		return ERR_PTR(-ENOMEM);
+
+	pd->domain = domain = iommu_domain_alloc(&pci_bus_type);
+	if (IS_ERR_OR_NULL(domain)) {
+		usnic_err("Failed to allocate IOMMU domain with err %ld\n",
+				PTR_ERR(pd->domain));
+		kfree(pd);
+		return ERR_PTR(domain ? PTR_ERR(domain) : -ENOMEM);
+	}
+
+	iommu_set_fault_handler(pd->domain, usnic_uiom_dma_fault, NULL);
+
+	spin_lock_init(&pd->lock);
+	INIT_LIST_HEAD(&pd->devs);
+
+	return pd;
+}
+
+void usnic_uiom_dealloc_pd(struct usnic_uiom_pd *pd)
+{
+	iommu_domain_free(pd->domain);
+	kfree(pd);
+}
+
+int usnic_uiom_attach_dev_to_pd(struct usnic_uiom_pd *pd, struct device *dev)
+{
+	struct usnic_uiom_dev *uiom_dev;
+	int err;
+
+	uiom_dev = kzalloc(sizeof(*uiom_dev), GFP_ATOMIC);
+	if (!uiom_dev)
+		return -ENOMEM;
+	uiom_dev->dev = dev;
+
+	err = iommu_attach_device(pd->domain, dev);
+	if (err)
+		goto out_free_dev;
+
+	if (!iommu_domain_has_cap(pd->domain, IOMMU_CAP_CACHE_COHERENCY)) {
+		usnic_err("IOMMU of %s does not support cache coherency\n",
+				dev_name(dev));
+		err = -EINVAL;
+		goto out_detach_device;
+	}
+
+	spin_lock(&pd->lock);
+	list_add_tail(&uiom_dev->link, &pd->devs);
+	pd->dev_cnt++;
+	spin_unlock(&pd->lock);
+
+	return 0;
+
+out_detach_device:
+	iommu_detach_device(pd->domain, dev);
+out_free_dev:
+	kfree(uiom_dev);
+	return err;
+}
+
+void usnic_uiom_detach_dev_from_pd(struct usnic_uiom_pd *pd, struct device *dev)
+{
+	struct usnic_uiom_dev *uiom_dev;
+	int found = 0;
+
+	spin_lock(&pd->lock);
+	list_for_each_entry(uiom_dev, &pd->devs, link) {
+		if (uiom_dev->dev == dev) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found) {
+		usnic_err("Unable to free dev %s - not found\n",
+				dev_name(dev));
+		spin_unlock(&pd->lock);
+		return;
+	}
+
+	list_del(&uiom_dev->link);
+	pd->dev_cnt--;
+	spin_unlock(&pd->lock);
+
+	return iommu_detach_device(pd->domain, dev);
+}
+
+struct device **usnic_uiom_get_dev_list(struct usnic_uiom_pd *pd)
+{
+	struct usnic_uiom_dev *uiom_dev;
+	struct device **devs;
+	int i = 0;
+
+	spin_lock(&pd->lock);
+	devs = kcalloc(pd->dev_cnt + 1, sizeof(*devs), GFP_ATOMIC);
+	if (!devs) {
+		devs = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	list_for_each_entry(uiom_dev, &pd->devs, link) {
+		devs[i++] = uiom_dev->dev;
+	}
+out:
+	spin_unlock(&pd->lock);
+	return devs;
+}
+
+void usnic_uiom_free_dev_list(struct device **devs)
+{
+	kfree(devs);
+}
+
+int usnic_uiom_init(char *drv_name)
+{
+	if (!iommu_present(&pci_bus_type)) {
+		usnic_err("IOMMU required but not present or enabled.  USNIC QPs will not function w/o enabling IOMMU\n");
+		return -EPERM;
+	}
+
+	usnic_uiom_wq = create_workqueue(drv_name);
+	if (!usnic_uiom_wq) {
+		usnic_err("Unable to alloc wq for drv %s\n", drv_name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+void usnic_uiom_fini(void)
+{
+	flush_workqueue(usnic_uiom_wq);
+	destroy_workqueue(usnic_uiom_wq);
+}

drivers/infiniband/hw/usnic/usnic_uiom.h

@@ -0,0 +1,80 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_UIOM_H_
+#define USNIC_UIOM_H_
+
+#include <linux/list.h>
+#include <linux/scatterlist.h>
+
+#include "usnic_uiom_interval_tree.h"
+
+#define USNIC_UIOM_READ			(1)
+#define USNIC_UIOM_WRITE		(2)
+
+#define USNIC_UIOM_MAX_PD_CNT		(1000)
+#define USNIC_UIOM_MAX_MR_CNT		(1000000)
+#define USNIC_UIOM_MAX_MR_SIZE		(~0UL)
+#define USNIC_UIOM_PAGE_SIZE		(PAGE_SIZE)
+
+struct usnic_uiom_dev {
+	struct device			*dev;
+	struct list_head		link;
+};
+
+struct usnic_uiom_pd {
+	struct iommu_domain		*domain;
+	spinlock_t			lock;
+	struct rb_root			rb_root;
+	struct list_head		devs;
+	int				dev_cnt;
+};
+
+struct usnic_uiom_reg {
+	struct usnic_uiom_pd		*pd;
+	unsigned long			va;
+	size_t				length;
+	int				offset;
+	int				page_size;
+	int				writable;
+	struct list_head		chunk_list;
+	struct work_struct		work;
+	struct mm_struct		*mm;
+	unsigned long			diff;
+};
+
+struct usnic_uiom_chunk {
+	struct list_head		list;
+	int				nents;
+	struct scatterlist		page_list[0];
+};
+
+struct usnic_uiom_pd *usnic_uiom_alloc_pd(void);
+void usnic_uiom_dealloc_pd(struct usnic_uiom_pd *pd);
+int usnic_uiom_attach_dev_to_pd(struct usnic_uiom_pd *pd, struct device *dev);
+void usnic_uiom_detach_dev_from_pd(struct usnic_uiom_pd *pd,
+					struct device *dev);
+struct device **usnic_uiom_get_dev_list(struct usnic_uiom_pd *pd);
+void usnic_uiom_free_dev_list(struct device **devs);
+struct usnic_uiom_reg *usnic_uiom_reg_get(struct usnic_uiom_pd *pd,
+						unsigned long addr, size_t size,
+						int access, int dmasync);
+void usnic_uiom_reg_release(struct usnic_uiom_reg *uiomr, int closing);
+int usnic_uiom_init(char *drv_name);
+void usnic_uiom_fini(void);
+#endif /* USNIC_UIOM_H_ */

drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.c

@@ -0,0 +1,236 @@
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/list_sort.h>
+
+#include <linux/interval_tree_generic.h>
+#include "usnic_uiom_interval_tree.h"
+
+#define START(node) ((node)->start)
+#define LAST(node) ((node)->last)
+
+#define MAKE_NODE(node, start, end, ref_cnt, flags, err, err_out)	\
+		do {							\
+			node = usnic_uiom_interval_node_alloc(start,	\
+					end, ref_cnt, flags);		\
+				if (!node) {				\
+					err = -ENOMEM;			\
+					goto err_out;			\
+				}					\
+		} while (0)
+
+#define MARK_FOR_ADD(node, list) (list_add_tail(&node->link, list))
+
+#define MAKE_NODE_AND_APPEND(node, start, end, ref_cnt, flags, err,	\
+				err_out, list)				\
+				do {					\
+					MAKE_NODE(node, start, end,	\
+						ref_cnt, flags, err,	\
+						err_out);		\
+					MARK_FOR_ADD(node, list);	\
+				} while (0)
+
+#define FLAGS_EQUAL(flags1, flags2, mask)				\
+			(((flags1) & (mask)) == ((flags2) & (mask)))
+
+static struct usnic_uiom_interval_node*
+usnic_uiom_interval_node_alloc(long int start, long int last, int ref_cnt,
+				int flags)
+{
+	struct usnic_uiom_interval_node *interval = kzalloc(sizeof(*interval),
+								GFP_ATOMIC);
+	if (!interval)
+		return NULL;
+
+	interval->start = start;
+	interval->last = last;
+	interval->flags = flags;
+	interval->ref_cnt = ref_cnt;
+
+	return interval;
+}
+
+static int interval_cmp(void *priv, struct list_head *a, struct list_head *b)
+{
+	struct usnic_uiom_interval_node *node_a, *node_b;
+
+	node_a = list_entry(a, struct usnic_uiom_interval_node, link);
+	node_b = list_entry(b, struct usnic_uiom_interval_node, link);
+
+	/* long to int */
+	if (node_a->start < node_b->start)
+		return -1;
+	else if (node_a->start > node_b->start)
+		return 1;
+
+	return 0;
+}
+
+static void
+find_intervals_intersection_sorted(struct rb_root *root, unsigned long start,
+					unsigned long last,
+					struct list_head *list)
+{
+	struct usnic_uiom_interval_node *node;
+
+	INIT_LIST_HEAD(list);
+
+	for (node = usnic_uiom_interval_tree_iter_first(root, start, last);
+		node;
+		node = usnic_uiom_interval_tree_iter_next(node, start, last))
+		list_add_tail(&node->link, list);
+
+	list_sort(NULL, list, interval_cmp);
+}
+
+int usnic_uiom_get_intervals_diff(unsigned long start, unsigned long last,
+					int flags, int flag_mask,
+					struct rb_root *root,
+					struct list_head *diff_set)
+{
+	struct usnic_uiom_interval_node *interval, *tmp;
+	int err = 0;
+	long int pivot = start;
+	LIST_HEAD(intersection_set);
+
+	INIT_LIST_HEAD(diff_set);
+
+	find_intervals_intersection_sorted(root, start, last,
+						&intersection_set);
+
+	list_for_each_entry(interval, &intersection_set, link) {
+		if (pivot < interval->start) {
+			MAKE_NODE_AND_APPEND(tmp, pivot, interval->start - 1,
+						1, flags, err, err_out,
+						diff_set);
+			pivot = interval->start;
+		}
+
+		/*
+		 * Invariant: Set [start, pivot] is either in diff_set or root,
+		 * but not in both.
+		 */
+
+		if (pivot > interval->last) {
+			continue;
+		} else if (pivot <= interval->last &&
+				FLAGS_EQUAL(interval->flags, flags,
+				flag_mask)) {
+			pivot = interval->last + 1;
+		}
+	}
+
+	if (pivot <= last)
+		MAKE_NODE_AND_APPEND(tmp, pivot, last, 1, flags, err, err_out,
+					diff_set);
+
+	return 0;
+
+err_out:
+	list_for_each_entry_safe(interval, tmp, diff_set, link) {
+		list_del(&interval->link);
+		kfree(interval);
+	}
+
+	return err;
+}
+
+void usnic_uiom_put_interval_set(struct list_head *intervals)
+{
+	struct usnic_uiom_interval_node *interval, *tmp;
+	list_for_each_entry_safe(interval, tmp, intervals, link)
+		kfree(interval);
+}
+
+int usnic_uiom_insert_interval(struct rb_root *root, unsigned long start,
+				unsigned long last, int flags)
+{
+	struct usnic_uiom_interval_node *interval, *tmp;
+	unsigned long istart, ilast;
+	int iref_cnt, iflags;
+	unsigned long lpivot = start;
+	int err = 0;
+	LIST_HEAD(to_add);
+	LIST_HEAD(intersection_set);
+
+	find_intervals_intersection_sorted(root, start, last,
+						&intersection_set);
+
+	list_for_each_entry(interval, &intersection_set, link) {
+		/*
+		 * Invariant - lpivot is the left edge of next interval to be
+		 * inserted
+		 */
+		istart = interval->start;
+		ilast = interval->last;
+		iref_cnt = interval->ref_cnt;
+		iflags = interval->flags;
+
+		if (istart < lpivot) {
+			MAKE_NODE_AND_APPEND(tmp, istart, lpivot - 1, iref_cnt,
+						iflags, err, err_out, &to_add);
+		} else if (istart > lpivot) {
+			MAKE_NODE_AND_APPEND(tmp, lpivot, istart - 1, 1, flags,
+						err, err_out, &to_add);
+			lpivot = istart;
+		} else {
+			lpivot = istart;
+		}
+
+		if (ilast > last) {
+			MAKE_NODE_AND_APPEND(tmp, lpivot, last, iref_cnt + 1,
+						iflags | flags, err, err_out,
+						&to_add);
+			MAKE_NODE_AND_APPEND(tmp, last + 1, ilast, iref_cnt,
+						iflags, err, err_out, &to_add);
+		} else {
+			MAKE_NODE_AND_APPEND(tmp, lpivot, ilast, iref_cnt + 1,
+						iflags | flags, err, err_out,
+						&to_add);
+		}
+
+		lpivot = ilast + 1;
+	}
+
+	if (lpivot <= last)
+		MAKE_NODE_AND_APPEND(tmp, lpivot, last, 1, flags, err, err_out,
+					&to_add);
+
+	list_for_each_entry_safe(interval, tmp, &intersection_set, link) {
+		usnic_uiom_interval_tree_remove(interval, root);
+		kfree(interval);
+	}
+
+	list_for_each_entry(interval, &to_add, link)
+		usnic_uiom_interval_tree_insert(interval, root);
+
+	return 0;
+
+err_out:
+	list_for_each_entry_safe(interval, tmp, &to_add, link)
+		kfree(interval);
+
+	return err;
+}
+
+void usnic_uiom_remove_interval(struct rb_root *root, unsigned long start,
+				unsigned long last, struct list_head *removed)
+{
+	struct usnic_uiom_interval_node *interval;
+
+	for (interval = usnic_uiom_interval_tree_iter_first(root, start, last);
+			interval;
+			interval = usnic_uiom_interval_tree_iter_next(interval,
+									start,
+									last)) {
+		if (--interval->ref_cnt == 0)
+			list_add_tail(&interval->link, removed);
+	}
+
+	list_for_each_entry(interval, removed, link)
+		usnic_uiom_interval_tree_remove(interval, root);
+}
+
+INTERVAL_TREE_DEFINE(struct usnic_uiom_interval_node, rb,
+			unsigned long, __subtree_last,
+			START, LAST, , usnic_uiom_interval_tree)

drivers/infiniband/hw/usnic/usnic_uiom_interval_tree.h

@@ -0,0 +1,73 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_UIOM_INTERVAL_TREE_H_
+#define USNIC_UIOM_INTERVAL_TREE_H_
+
+#include <linux/rbtree.h>
+
+struct usnic_uiom_interval_node {
+	struct rb_node			rb;
+	struct list_head		link;
+	unsigned long			start;
+	unsigned long			last;
+	unsigned long			__subtree_last;
+	unsigned int			ref_cnt;
+	int				flags;
+};
+
+extern void
+usnic_uiom_interval_tree_insert(struct usnic_uiom_interval_node *node,
+					struct rb_root *root);
+extern void
+usnic_uiom_interval_tree_remove(struct usnic_uiom_interval_node *node,
+					struct rb_root *root);
+extern struct usnic_uiom_interval_node *
+usnic_uiom_interval_tree_iter_first(struct rb_root *root,
+					unsigned long start,
+					unsigned long last);
+extern struct usnic_uiom_interval_node *
+usnic_uiom_interval_tree_iter_next(struct usnic_uiom_interval_node *node,
+			unsigned long start, unsigned long last);
+/*
+ * Inserts {start...last} into {root}.  If there are overlaps,
+ * nodes will be broken up and merged
+ */
+int usnic_uiom_insert_interval(struct rb_root *root,
+				unsigned long start, unsigned long last,
+				int flags);
+/*
+ * Removed {start...last} from {root}.  The nodes removed are returned in
+ * 'removed.' The caller is responsibile for freeing memory of nodes in
+ * 'removed.'
+ */
+void usnic_uiom_remove_interval(struct rb_root *root,
+				unsigned long start, unsigned long last,
+				struct list_head *removed);
+/*
+ * Returns {start...last} - {root} (relative complement of {start...last} in
+ * {root}) in diff_set sorted ascendingly
+ */
+int usnic_uiom_get_intervals_diff(unsigned long start,
+					unsigned long last, int flags,
+					int flag_mask,
+					struct rb_root *root,
+					struct list_head *diff_set);
+/* Call this to free diff_set returned by usnic_uiom_get_intervals_diff */
+void usnic_uiom_put_interval_set(struct list_head *intervals);
+#endif /* USNIC_UIOM_INTERVAL_TREE_H_ */

drivers/infiniband/hw/usnic/usnic_vnic.c

@@ -0,0 +1,467 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+
+#include "usnic_ib.h"
+#include "vnic_resource.h"
+#include "usnic_log.h"
+#include "usnic_vnic.h"
+
+struct usnic_vnic {
+	struct vnic_dev			*vdev;
+	struct vnic_dev_bar		bar[PCI_NUM_RESOURCES];
+	struct usnic_vnic_res_chunk	chunks[USNIC_VNIC_RES_TYPE_MAX];
+	spinlock_t			res_lock;
+};
+
+static enum vnic_res_type _to_vnic_res_type(enum usnic_vnic_res_type res_type)
+{
+#define DEFINE_USNIC_VNIC_RES_AT(usnic_vnic_res_t, vnic_res_type, desc, val) \
+		vnic_res_type,
+#define DEFINE_USNIC_VNIC_RES(usnic_vnic_res_t, vnic_res_type, desc) \
+		vnic_res_type,
+	static enum vnic_res_type usnic_vnic_type_2_vnic_type[] = {
+						USNIC_VNIC_RES_TYPES};
+#undef DEFINE_USNIC_VNIC_RES
+#undef DEFINE_USNIC_VNIC_RES_AT
+
+	if (res_type >= USNIC_VNIC_RES_TYPE_MAX)
+		return RES_TYPE_MAX;
+
+	return usnic_vnic_type_2_vnic_type[res_type];
+}
+
+const char *usnic_vnic_res_type_to_str(enum usnic_vnic_res_type res_type)
+{
+#define DEFINE_USNIC_VNIC_RES_AT(usnic_vnic_res_t, vnic_res_type, desc, val) \
+		desc,
+#define DEFINE_USNIC_VNIC_RES(usnic_vnic_res_t, vnic_res_type, desc) \
+		desc,
+	static const char * const usnic_vnic_res_type_desc[] = {
+						USNIC_VNIC_RES_TYPES};
+#undef DEFINE_USNIC_VNIC_RES
+#undef DEFINE_USNIC_VNIC_RES_AT
+
+	if (res_type >= USNIC_VNIC_RES_TYPE_MAX)
+		return "unknown";
+
+	return usnic_vnic_res_type_desc[res_type];
+
+}
+
+const char *usnic_vnic_pci_name(struct usnic_vnic *vnic)
+{
+	return pci_name(usnic_vnic_get_pdev(vnic));
+}
+
+int usnic_vnic_dump(struct usnic_vnic *vnic, char *buf,
+			int buf_sz,
+			void *hdr_obj,
+			int (*printtitle)(void *, char*, int),
+			int (*printcols)(char *, int),
+			int (*printrow)(void *, char *, int))
+{
+	struct usnic_vnic_res_chunk *chunk;
+	struct usnic_vnic_res *res;
+	struct vnic_dev_bar *bar0;
+	int i, j, offset;
+
+	offset = 0;
+	bar0 = usnic_vnic_get_bar(vnic, 0);
+	offset += scnprintf(buf + offset, buf_sz - offset,
+			"VF:%hu BAR0 bus_addr=%pa vaddr=0x%p size=%ld ",
+			usnic_vnic_get_index(vnic),
+			&bar0->bus_addr,
+			bar0->vaddr, bar0->len);
+	if (printtitle)
+		offset += printtitle(hdr_obj, buf + offset, buf_sz - offset);
+	offset += scnprintf(buf + offset, buf_sz - offset, "\n");
+	offset += scnprintf(buf + offset, buf_sz - offset,
+			"|RES\t|CTRL_PIN\t\t|IN_USE\t");
+	if (printcols)
+		offset += printcols(buf + offset, buf_sz - offset);
+	offset += scnprintf(buf + offset, buf_sz - offset, "\n");
+
+	spin_lock(&vnic->res_lock);
+	for (i = 0; i < ARRAY_SIZE(vnic->chunks); i++) {
+		chunk = &vnic->chunks[i];
+		for (j = 0; j < chunk->cnt; j++) {
+			res = chunk->res[j];
+			offset += scnprintf(buf + offset, buf_sz - offset,
+					"|%s[%u]\t|0x%p\t|%u\t",
+					usnic_vnic_res_type_to_str(res->type),
+					res->vnic_idx, res->ctrl, !!res->owner);
+			if (printrow) {
+				offset += printrow(res->owner, buf + offset,
+							buf_sz - offset);
+			}
+			offset += scnprintf(buf + offset, buf_sz - offset,
+						"\n");
+		}
+	}
+	spin_unlock(&vnic->res_lock);
+	return offset;
+}
+
+void usnic_vnic_res_spec_update(struct usnic_vnic_res_spec *spec,
+				enum usnic_vnic_res_type trgt_type,
+				u16 cnt)
+{
+	int i;
+
+	for (i = 0; i < USNIC_VNIC_RES_TYPE_MAX; i++) {
+		if (spec->resources[i].type == trgt_type) {
+			spec->resources[i].cnt = cnt;
+			return;
+		}
+	}
+
+	WARN_ON(1);
+}
+
+int usnic_vnic_res_spec_satisfied(const struct usnic_vnic_res_spec *min_spec,
+					struct usnic_vnic_res_spec *res_spec)
+{
+	int found, i, j;
+
+	for (i = 0; i < USNIC_VNIC_RES_TYPE_MAX; i++) {
+		found = 0;
+
+		for (j = 0; j < USNIC_VNIC_RES_TYPE_MAX; j++) {
+			if (res_spec->resources[i].type !=
+				min_spec->resources[i].type)
+				continue;
+			found = 1;
+			if (min_spec->resources[i].cnt >
+					res_spec->resources[i].cnt)
+				return -EINVAL;
+			break;
+		}
+
+		if (!found)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+int usnic_vnic_spec_dump(char *buf, int buf_sz,
+				struct usnic_vnic_res_spec *res_spec)
+{
+	enum usnic_vnic_res_type res_type;
+	int res_cnt;
+	int i;
+	int offset = 0;
+
+	for (i = 0; i < USNIC_VNIC_RES_TYPE_MAX; i++) {
+		res_type = res_spec->resources[i].type;
+		res_cnt = res_spec->resources[i].cnt;
+		offset += scnprintf(buf + offset, buf_sz - offset,
+				"Res: %s Cnt: %d ",
+				usnic_vnic_res_type_to_str(res_type),
+				res_cnt);
+	}
+
+	return offset;
+}
+
+int usnic_vnic_check_room(struct usnic_vnic *vnic,
+				struct usnic_vnic_res_spec *res_spec)
+{
+	int i;
+	enum usnic_vnic_res_type res_type;
+	int res_cnt;
+
+	for (i = 0; i < USNIC_VNIC_RES_TYPE_MAX; i++) {
+		res_type = res_spec->resources[i].type;
+		res_cnt = res_spec->resources[i].cnt;
+
+		if (res_type == USNIC_VNIC_RES_TYPE_EOL)
+			break;
+
+		if (res_cnt > usnic_vnic_res_free_cnt(vnic, res_type))
+			return -EBUSY;
+	}
+
+	return 0;
+}
+
+int usnic_vnic_res_cnt(struct usnic_vnic *vnic,
+				enum usnic_vnic_res_type type)
+{
+	return vnic->chunks[type].cnt;
+}
+
+int usnic_vnic_res_free_cnt(struct usnic_vnic *vnic,
+				enum usnic_vnic_res_type type)
+{
+	return vnic->chunks[type].free_cnt;
+}
+
+struct usnic_vnic_res_chunk *
+usnic_vnic_get_resources(struct usnic_vnic *vnic, enum usnic_vnic_res_type type,
+				int cnt, void *owner)
+{
+	struct usnic_vnic_res_chunk *src, *ret;
+	struct usnic_vnic_res *res;
+	int i;
+
+	if (usnic_vnic_res_free_cnt(vnic, type) < cnt || cnt < 1 || !owner)
+		return ERR_PTR(-EINVAL);
+
+	ret = kzalloc(sizeof(*ret), GFP_ATOMIC);
+	if (!ret) {
+		usnic_err("Failed to allocate chunk for %s - Out of memory\n",
+				usnic_vnic_pci_name(vnic));
+		return ERR_PTR(-ENOMEM);
+	}
+
+	ret->res = kzalloc(sizeof(*(ret->res))*cnt, GFP_ATOMIC);
+	if (!ret->res) {
+		usnic_err("Failed to allocate resources for %s. Out of memory\n",
+				usnic_vnic_pci_name(vnic));
+		kfree(ret);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	spin_lock(&vnic->res_lock);
+	src = &vnic->chunks[type];
+	for (i = 0; i < src->cnt && ret->cnt < cnt; i++) {
+		res = src->res[i];
+		if (!res->owner) {
+			src->free_cnt--;
+			res->owner = owner;
+			ret->res[ret->cnt++] = res;
+		}
+	}
+
+	spin_unlock(&vnic->res_lock);
+	ret->type = type;
+	ret->vnic = vnic;
+	WARN_ON(ret->cnt != cnt);
+
+	return ret;
+}
+
+void usnic_vnic_put_resources(struct usnic_vnic_res_chunk *chunk)
+{
+
+	struct usnic_vnic_res *res;
+	int i;
+	struct usnic_vnic *vnic = chunk->vnic;
+
+	spin_lock(&vnic->res_lock);
+	while ((i = --chunk->cnt) >= 0) {
+		res = chunk->res[i];
+		chunk->res[i] = NULL;
+		res->owner = NULL;
+		vnic->chunks[res->type].free_cnt++;
+	}
+	spin_unlock(&vnic->res_lock);
+
+	kfree(chunk->res);
+	kfree(chunk);
+}
+
+u16 usnic_vnic_get_index(struct usnic_vnic *vnic)
+{
+	return usnic_vnic_get_pdev(vnic)->devfn - 1;
+}
+
+static int usnic_vnic_alloc_res_chunk(struct usnic_vnic *vnic,
+					enum usnic_vnic_res_type type,
+					struct usnic_vnic_res_chunk *chunk)
+{
+	int cnt, err, i;
+	struct usnic_vnic_res *res;
+
+	cnt = vnic_dev_get_res_count(vnic->vdev, _to_vnic_res_type(type));
+	if (cnt < 1)
+		return -EINVAL;
+
+	chunk->cnt = chunk->free_cnt = cnt;
+	chunk->res = kzalloc(sizeof(*(chunk->res))*cnt, GFP_KERNEL);
+	if (!chunk->res)
+		return -ENOMEM;
+
+	for (i = 0; i < cnt; i++) {
+		res = kzalloc(sizeof(*res), GFP_KERNEL);
+		if (!res) {
+			err = -ENOMEM;
+			goto fail;
+		}
+		res->type = type;
+		res->vnic_idx = i;
+		res->vnic = vnic;
+		res->ctrl = vnic_dev_get_res(vnic->vdev,
+						_to_vnic_res_type(type), i);
+		chunk->res[i] = res;
+	}
+
+	chunk->vnic = vnic;
+	return 0;
+fail:
+	for (i--; i >= 0; i--)
+		kfree(chunk->res[i]);
+	kfree(chunk->res);
+	return err;
+}
+
+static void usnic_vnic_free_res_chunk(struct usnic_vnic_res_chunk *chunk)
+{
+	int i;
+	for (i = 0; i < chunk->cnt; i++)
+		kfree(chunk->res[i]);
+	kfree(chunk->res);
+}
+
+static int usnic_vnic_discover_resources(struct pci_dev *pdev,
+						struct usnic_vnic *vnic)
+{
+	enum usnic_vnic_res_type res_type;
+	int i;
+	int err = 0;
+
+	for (i = 0; i < ARRAY_SIZE(vnic->bar); i++) {
+		if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM))
+			continue;
+		vnic->bar[i].len = pci_resource_len(pdev, i);
+		vnic->bar[i].vaddr = pci_iomap(pdev, i, vnic->bar[i].len);
+		if (!vnic->bar[i].vaddr) {
+			usnic_err("Cannot memory-map BAR %d, aborting\n",
+					i);
+			err = -ENODEV;
+			goto out_clean_bar;
+		}
+		vnic->bar[i].bus_addr = pci_resource_start(pdev, i);
+	}
+
+	vnic->vdev = vnic_dev_register(NULL, pdev, pdev, vnic->bar,
+			ARRAY_SIZE(vnic->bar));
+	if (!vnic->vdev) {
+		usnic_err("Failed to register device %s\n",
+				pci_name(pdev));
+		err = -EINVAL;
+		goto out_clean_bar;
+	}
+
+	for (res_type = USNIC_VNIC_RES_TYPE_EOL + 1;
+			res_type < USNIC_VNIC_RES_TYPE_MAX; res_type++) {
+		err = usnic_vnic_alloc_res_chunk(vnic, res_type,
+						&vnic->chunks[res_type]);
+		if (err) {
+			usnic_err("Failed to alloc res %s with err %d\n",
+					usnic_vnic_res_type_to_str(res_type),
+					err);
+			goto out_clean_chunks;
+		}
+	}
+
+	return 0;
+
+out_clean_chunks:
+	for (res_type--; res_type > USNIC_VNIC_RES_TYPE_EOL; res_type--)
+		usnic_vnic_free_res_chunk(&vnic->chunks[res_type]);
+	vnic_dev_unregister(vnic->vdev);
+out_clean_bar:
+	for (i = 0; i < ARRAY_SIZE(vnic->bar); i++) {
+		if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM))
+			continue;
+		if (!vnic->bar[i].vaddr)
+			break;
+
+		iounmap(vnic->bar[i].vaddr);
+	}
+
+	return err;
+}
+
+struct pci_dev *usnic_vnic_get_pdev(struct usnic_vnic *vnic)
+{
+	return vnic_dev_get_pdev(vnic->vdev);
+}
+
+struct vnic_dev_bar *usnic_vnic_get_bar(struct usnic_vnic *vnic,
+				int bar_num)
+{
+	return (bar_num < ARRAY_SIZE(vnic->bar)) ? &vnic->bar[bar_num] : NULL;
+}
+
+static void usnic_vnic_release_resources(struct usnic_vnic *vnic)
+{
+	int i;
+	struct pci_dev *pdev;
+	enum usnic_vnic_res_type res_type;
+
+	pdev = usnic_vnic_get_pdev(vnic);
+
+	for (res_type = USNIC_VNIC_RES_TYPE_EOL + 1;
+			res_type < USNIC_VNIC_RES_TYPE_MAX; res_type++)
+		usnic_vnic_free_res_chunk(&vnic->chunks[res_type]);
+
+	vnic_dev_unregister(vnic->vdev);
+
+	for (i = 0; i < ARRAY_SIZE(vnic->bar); i++) {
+		if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM))
+			continue;
+		iounmap(vnic->bar[i].vaddr);
+	}
+}
+
+struct usnic_vnic *usnic_vnic_alloc(struct pci_dev *pdev)
+{
+	struct usnic_vnic *vnic;
+	int err = 0;
+
+	if (!pci_is_enabled(pdev)) {
+		usnic_err("PCI dev %s is disabled\n", pci_name(pdev));
+		return ERR_PTR(-EINVAL);
+	}
+
+	vnic = kzalloc(sizeof(*vnic), GFP_KERNEL);
+	if (!vnic) {
+		usnic_err("Failed to alloc vnic for %s - out of memory\n",
+				pci_name(pdev));
+		return ERR_PTR(-ENOMEM);
+	}
+
+	spin_lock_init(&vnic->res_lock);
+
+	err = usnic_vnic_discover_resources(pdev, vnic);
+	if (err) {
+		usnic_err("Failed to discover %s resources with err %d\n",
+				pci_name(pdev), err);
+		goto out_free_vnic;
+	}
+
+	usnic_dbg("Allocated vnic for %s\n", usnic_vnic_pci_name(vnic));
+
+	return vnic;
+
+out_free_vnic:
+	kfree(vnic);
+
+	return ERR_PTR(err);
+}
+
+void usnic_vnic_free(struct usnic_vnic *vnic)
+{
+	usnic_vnic_release_resources(vnic);
+	kfree(vnic);
+}

drivers/infiniband/hw/usnic/usnic_vnic.h

@@ -0,0 +1,103 @@
+/*
+ * Copyright (c) 2013, Cisco Systems, Inc. All rights reserved.
+ *
+ * This program is free software; you may redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#ifndef USNIC_VNIC_H_
+#define USNIC_VNIC_H_
+
+#include <linux/pci.h>
+
+#include "vnic_dev.h"
+
+/*                      =USNIC_VNIC_RES_TYPE= =VNIC_RES=   =DESC= */
+#define USNIC_VNIC_RES_TYPES \
+	DEFINE_USNIC_VNIC_RES_AT(EOL, RES_TYPE_EOL, "EOL", 0) \
+	DEFINE_USNIC_VNIC_RES(WQ, RES_TYPE_WQ, "WQ") \
+	DEFINE_USNIC_VNIC_RES(RQ, RES_TYPE_RQ, "RQ") \
+	DEFINE_USNIC_VNIC_RES(CQ, RES_TYPE_CQ, "CQ") \
+	DEFINE_USNIC_VNIC_RES(INTR, RES_TYPE_INTR_CTRL, "INT") \
+	DEFINE_USNIC_VNIC_RES(MAX, RES_TYPE_MAX, "MAX")\
+
+#define DEFINE_USNIC_VNIC_RES_AT(usnic_vnic_res_t, vnic_res_type, desc, val) \
+	USNIC_VNIC_RES_TYPE_##usnic_vnic_res_t = val,
+#define DEFINE_USNIC_VNIC_RES(usnic_vnic_res_t, vnic_res_type, desc) \
+	USNIC_VNIC_RES_TYPE_##usnic_vnic_res_t,
+enum usnic_vnic_res_type {
+	USNIC_VNIC_RES_TYPES
+};
+#undef DEFINE_USNIC_VNIC_RES
+#undef DEFINE_USNIC_VNIC_RES_AT
+
+struct usnic_vnic_res {
+	enum usnic_vnic_res_type	type;
+	unsigned int			vnic_idx;
+	struct usnic_vnic		*vnic;
+	void __iomem			*ctrl;
+	void				*owner;
+};
+
+struct usnic_vnic_res_chunk {
+	enum usnic_vnic_res_type	type;
+	int				cnt;
+	int				free_cnt;
+	struct usnic_vnic_res		**res;
+	struct usnic_vnic		*vnic;
+};
+
+struct usnic_vnic_res_desc {
+	enum usnic_vnic_res_type	type;
+	uint16_t			cnt;
+};
+
+struct usnic_vnic_res_spec {
+	struct usnic_vnic_res_desc resources[USNIC_VNIC_RES_TYPE_MAX];
+};
+
+const char *usnic_vnic_res_type_to_str(enum usnic_vnic_res_type res_type);
+const char *usnic_vnic_pci_name(struct usnic_vnic *vnic);
+int usnic_vnic_dump(struct usnic_vnic *vnic, char *buf, int buf_sz,
+			void *hdr_obj,
+			int (*printtitle)(void *, char*, int),
+			int (*printcols)(char *, int),
+			int (*printrow)(void *, char *, int));
+void usnic_vnic_res_spec_update(struct usnic_vnic_res_spec *spec,
+				enum usnic_vnic_res_type trgt_type,
+				u16 cnt);
+int usnic_vnic_res_spec_satisfied(const struct usnic_vnic_res_spec *min_spec,
+					struct usnic_vnic_res_spec *res_spec);
+int usnic_vnic_spec_dump(char *buf, int buf_sz,
+				struct usnic_vnic_res_spec *res_spec);
+int usnic_vnic_check_room(struct usnic_vnic *vnic,
+				struct usnic_vnic_res_spec *res_spec);
+int usnic_vnic_res_cnt(struct usnic_vnic *vnic,
+				enum usnic_vnic_res_type type);
+int usnic_vnic_res_free_cnt(struct usnic_vnic *vnic,
+				enum usnic_vnic_res_type type);
+struct usnic_vnic_res_chunk *
+usnic_vnic_get_resources(struct usnic_vnic *vnic,
+				enum usnic_vnic_res_type type,
+				int cnt,
+				void *owner);
+void usnic_vnic_put_resources(struct usnic_vnic_res_chunk *chunk);
+struct pci_dev *usnic_vnic_get_pdev(struct usnic_vnic *vnic);
+struct vnic_dev_bar *usnic_vnic_get_bar(struct usnic_vnic *vnic,
+				int bar_num);
+struct usnic_vnic *usnic_vnic_alloc(struct pci_dev *pdev);
+void usnic_vnic_free(struct usnic_vnic *vnic);
+u16 usnic_vnic_get_index(struct usnic_vnic *vnic);
+
+#endif /*!USNIC_VNIC_H_*/

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -104,6 +104,8 @@ int ipoib_open(struct net_device *dev)
 
 	ipoib_dbg(priv, "bringing up interface\n");
 
+	netif_carrier_off(dev);
+
 	set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
 
 	if (ipoib_pkey_dev_delay_open(dev))
@@ -1366,8 +1368,6 @@ void ipoib_setup(struct net_device *dev)
 
 	memcpy(dev->broadcast, ipv4_bcast_addr, INFINIBAND_ALEN);
 
-	netif_carrier_off(dev);
-
 	priv->dev = dev;
 
 	spin_lock_init(&priv->lock);

drivers/infiniband/ulp/ipoib/ipoib_verbs.c

@@ -192,6 +192,9 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	if (priv->hca_caps & IB_DEVICE_BLOCK_MULTICAST_LOOPBACK)
 		init_attr.create_flags |= IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK;
 
+	if (priv->hca_caps & IB_DEVICE_MANAGED_FLOW_STEERING)
+		init_attr.create_flags |= IB_QP_CREATE_NETIF_QP;
+
 	if (dev->features & NETIF_F_SG)
 		init_attr.cap.max_send_sge = MAX_SKB_FRAGS + 1;
 

drivers/infiniband/ulp/srp/ib_srp.c

@@ -660,6 +660,7 @@ static void srp_remove_target(struct srp_target_port *target)
 	srp_rport_get(target->rport);
 	srp_remove_host(target->scsi_host);
 	scsi_remove_host(target->scsi_host);
+	srp_stop_rport_timers(target->rport);
 	srp_disconnect_target(target);
 	ib_destroy_cm_id(target->cm_id);
 	srp_free_target_ib(target);

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

@@ -1371,6 +1371,15 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.verify = NULL,
 		.wrapper = mlx4_QP_FLOW_STEERING_DETACH_wrapper
 	},
+	{
+		.opcode = MLX4_FLOW_STEERING_IB_UC_QP_RANGE,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper
+	},
 };
 
 static int mlx4_master_process_vhcr(struct mlx4_dev *dev, int slave,

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

@@ -513,6 +513,7 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_MAX_XRC_OFFSET		0x67
 #define QUERY_DEV_CAP_MAX_COUNTERS_OFFSET	0x68
 #define QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET	0x70
+#define QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET	0x74
 #define QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET	0x76
 #define QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET	0x77
 #define QUERY_DEV_CAP_RDMARC_ENTRY_SZ_OFFSET	0x80
@@ -603,6 +604,9 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	if (field & 0x80)
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_FS_EN;
 	dev_cap->fs_log_max_ucast_qp_range_size = field & 0x1f;
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+	if (field & 0x80)
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DMFS_IPOIB;
 	MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_MAX_QP_OFFSET);
 	dev_cap->fs_max_num_qp_per_entry = field;
 	MLX4_GET(stat_rate, outbox, QUERY_DEV_CAP_RATE_SUPPORT_OFFSET);
@@ -860,6 +864,12 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		MLX4_PUT(outbox->buf, field,
 			 QUERY_DEV_CAP_FLOW_STEERING_RANGE_EN_OFFSET);
 	}
+
+	/* turn off ipoib managed steering for guests */
+	MLX4_GET(field, outbox, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+	field &= ~0x80;
+	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
+
 	return 0;
 }
 

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

@@ -895,6 +895,23 @@ int mlx4_flow_detach(struct mlx4_dev *dev, u64 reg_id)
 }
 EXPORT_SYMBOL_GPL(mlx4_flow_detach);
 
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
+				      u32 max_range_qpn)
+{
+	int err;
+	u64 in_param;
+
+	in_param = ((u64) min_range_qpn) << 32;
+	in_param |= ((u64) max_range_qpn) & 0xFFFFFFFF;
+
+	err = mlx4_cmd(dev, in_param, 0, 0,
+			MLX4_FLOW_STEERING_IB_UC_QP_RANGE,
+			MLX4_CMD_TIME_CLASS_A, MLX4_CMD_NATIVE);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_FLOW_STEERING_IB_UC_QP_RANGE);
+
 int mlx4_qp_attach_common(struct mlx4_dev *dev, struct mlx4_qp *qp, u8 gid[16],
 			  int block_mcast_loopback, enum mlx4_protocol prot,
 			  enum mlx4_steer_type steer)

drivers/net/ethernet/mellanox/mlx4/mlx4.h

@@ -1236,6 +1236,11 @@ int mlx4_QP_FLOW_STEERING_DETACH_wrapper(struct mlx4_dev *dev, int slave,
 					 struct mlx4_cmd_mailbox *inbox,
 					 struct mlx4_cmd_mailbox *outbox,
 					 struct mlx4_cmd_info *cmd);
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave,
+					      struct mlx4_vhcr *vhcr,
+					      struct mlx4_cmd_mailbox *inbox,
+					      struct mlx4_cmd_mailbox *outbox,
+					      struct mlx4_cmd_info *cmd);
 
 int mlx4_get_mgm_entry_size(struct mlx4_dev *dev);
 int mlx4_get_qp_per_mgm(struct mlx4_dev *dev);

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

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

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

@@ -3844,6 +3844,16 @@ int mlx4_QUERY_IF_STAT_wrapper(struct mlx4_dev *dev, int slave,
 	return err;
 }
 
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE_wrapper(struct mlx4_dev *dev, int slave,
+					      struct mlx4_vhcr *vhcr,
+					      struct mlx4_cmd_mailbox *inbox,
+					      struct mlx4_cmd_mailbox *outbox,
+					      struct mlx4_cmd_info *cmd)
+{
+	return -EPERM;
+}
+
+
 static void detach_qp(struct mlx4_dev *dev, int slave, struct res_qp *rqp)
 {
 	struct res_gid *rgid;

drivers/net/ethernet/mellanox/mlx5/core/cq.c

@@ -201,10 +201,23 @@ EXPORT_SYMBOL(mlx5_core_query_cq);
 
 
 int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
-			int type, struct mlx5_cq_modify_params *params)
+			struct mlx5_modify_cq_mbox_in *in, int in_sz)
 {
-	return -ENOSYS;
+	struct mlx5_modify_cq_mbox_out out;
+	int err;
+
+	memset(&out, 0, sizeof(out));
+	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_MODIFY_CQ);
+	err = mlx5_cmd_exec(dev, in, in_sz, &out, sizeof(out));
+	if (err)
+		return err;
+
+	if (out.hdr.status)
+		return mlx5_cmd_status_to_err(&out.hdr);
+
+	return 0;
 }
+EXPORT_SYMBOL(mlx5_core_modify_cq);
 
 int mlx5_init_cq_table(struct mlx5_core_dev *dev)
 {

drivers/net/ethernet/mellanox/mlx5/core/debugfs.c

@@ -275,7 +275,7 @@ void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev)
 }
 
 static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
-			 int index)
+			 int index, int *is_str)
 {
 	struct mlx5_query_qp_mbox_out *out;
 	struct mlx5_qp_context *ctx;
@@ -293,19 +293,40 @@ static u64 qp_read_field(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp,
 		goto out;
 	}
 
+	*is_str = 0;
 	ctx = &out->ctx;
 	switch (index) {
 	case QP_PID:
 		param = qp->pid;
 		break;
 	case QP_STATE:
-		param = be32_to_cpu(ctx->flags) >> 28;
+		param = (u64)mlx5_qp_state_str(be32_to_cpu(ctx->flags) >> 28);
+		*is_str = 1;
 		break;
 	case QP_XPORT:
-		param = (be32_to_cpu(ctx->flags) >> 16) & 0xff;
+		param = (u64)mlx5_qp_type_str((be32_to_cpu(ctx->flags) >> 16) & 0xff);
+		*is_str = 1;
 		break;
 	case QP_MTU:
-		param = ctx->mtu_msgmax >> 5;
+		switch (ctx->mtu_msgmax >> 5) {
+		case IB_MTU_256:
+			param = 256;
+			break;
+		case IB_MTU_512:
+			param = 512;
+			break;
+		case IB_MTU_1024:
+			param = 1024;
+			break;
+		case IB_MTU_2048:
+			param = 2048;
+			break;
+		case IB_MTU_4096:
+			param = 4096;
+			break;
+		default:
+			param = 0;
+		}
 		break;
 	case QP_N_RECV:
 		param = 1 << ((ctx->rq_size_stride >> 3) & 0xf);
@@ -414,6 +435,7 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count,
 	struct mlx5_field_desc *desc;
 	struct mlx5_rsc_debug *d;
 	char tbuf[18];
+	int is_str = 0;
 	u64 field;
 	int ret;
 
@@ -424,7 +446,7 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count,
 	d = (void *)(desc - desc->i) - sizeof(*d);
 	switch (d->type) {
 	case MLX5_DBG_RSC_QP:
-		field = qp_read_field(d->dev, d->object, desc->i);
+		field = qp_read_field(d->dev, d->object, desc->i, &is_str);
 		break;
 
 	case MLX5_DBG_RSC_EQ:
@@ -440,7 +462,12 @@ static ssize_t dbg_read(struct file *filp, char __user *buf, size_t count,
 		return -EINVAL;
 	}
 
-	ret = snprintf(tbuf, sizeof(tbuf), "0x%llx\n", field);
+
+	if (is_str)
+		ret = snprintf(tbuf, sizeof(tbuf), "%s\n", (const char *)field);
+	else
+		ret = snprintf(tbuf, sizeof(tbuf), "0x%llx\n", field);
+
 	if (ret > 0) {
 		if (copy_to_user(buf, tbuf, ret))
 			return -EFAULT;

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -460,7 +460,10 @@ disable_msix:
 
 err_stop_poll:
 	mlx5_stop_health_poll(dev);
-	mlx5_cmd_teardown_hca(dev);
+	if (mlx5_cmd_teardown_hca(dev)) {
+		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
+		return err;
+	}
 
 err_pagealloc_stop:
 	mlx5_pagealloc_stop(dev);
@@ -503,7 +506,10 @@ void mlx5_dev_cleanup(struct mlx5_core_dev *dev)
 	mlx5_eq_cleanup(dev);
 	mlx5_disable_msix(dev);
 	mlx5_stop_health_poll(dev);
-	mlx5_cmd_teardown_hca(dev);
+	if (mlx5_cmd_teardown_hca(dev)) {
+		dev_err(&dev->pdev->dev, "tear_down_hca failed, skip cleanup\n");
+		return;
+	}
 	mlx5_pagealloc_stop(dev);
 	mlx5_reclaim_startup_pages(dev);
 	mlx5_core_disable_hca(dev);

drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c

@@ -99,7 +99,7 @@ enum {
 
 enum {
 	MLX5_MAX_RECLAIM_TIME_MILI	= 5000,
-	MLX5_NUM_4K_IN_PAGE		= PAGE_SIZE / 4096,
+	MLX5_NUM_4K_IN_PAGE		= PAGE_SIZE / MLX5_ADAPTER_PAGE_SIZE,
 };
 
 static int insert_page(struct mlx5_core_dev *dev, u64 addr, struct page *page, u16 func_id)
@@ -192,10 +192,8 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
 	struct fw_page *fp;
 	unsigned n;
 
-	if (list_empty(&dev->priv.free_list)) {
+	if (list_empty(&dev->priv.free_list))
 		return -ENOMEM;
-		mlx5_core_warn(dev, "\n");
-	}
 
 	fp = list_entry(dev->priv.free_list.next, struct fw_page, list);
 	n = find_first_bit(&fp->bitmask, 8 * sizeof(fp->bitmask));
@@ -208,7 +206,7 @@ static int alloc_4k(struct mlx5_core_dev *dev, u64 *addr)
 	if (!fp->free_count)
 		list_del(&fp->list);
 
-	*addr = fp->addr + n * 4096;
+	*addr = fp->addr + n * MLX5_ADAPTER_PAGE_SIZE;
 
 	return 0;
 }
@@ -224,14 +222,15 @@ static void free_4k(struct mlx5_core_dev *dev, u64 addr)
 		return;
 	}
 
-	n = (addr & ~PAGE_MASK) % 4096;
+	n = (addr & ~PAGE_MASK) >> MLX5_ADAPTER_PAGE_SHIFT;
 	fwp->free_count++;
 	set_bit(n, &fwp->bitmask);
 	if (fwp->free_count == MLX5_NUM_4K_IN_PAGE) {
 		rb_erase(&fwp->rb_node, &dev->priv.page_root);
 		if (fwp->free_count != 1)
 			list_del(&fwp->list);
-		dma_unmap_page(&dev->pdev->dev, addr, PAGE_SIZE, DMA_BIDIRECTIONAL);
+		dma_unmap_page(&dev->pdev->dev, addr & PAGE_MASK, PAGE_SIZE,
+			       DMA_BIDIRECTIONAL);
 		__free_page(fwp->page);
 		kfree(fwp);
 	} else if (fwp->free_count == 1) {

drivers/net/ethernet/mellanox/mlx5/core/port.c

@@ -57,7 +57,7 @@ int mlx5_core_access_reg(struct mlx5_core_dev *dev, void *data_in,
 	in->arg = cpu_to_be32(arg);
 	in->register_id = cpu_to_be16(reg_num);
 	err = mlx5_cmd_exec(dev, in, sizeof(*in) + size_in, out,
-			    sizeof(out) + size_out);
+			    sizeof(*out) + size_out);
 	if (err)
 		goto ex2;
 

drivers/net/ethernet/mellanox/mlx5/core/qp.c

@@ -74,7 +74,7 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 	struct mlx5_destroy_qp_mbox_out dout;
 	int err;
 
-	memset(&dout, 0, sizeof(dout));
+	memset(&out, 0, sizeof(out));
 	in->hdr.opcode = cpu_to_be16(MLX5_CMD_OP_CREATE_QP);
 
 	err = mlx5_cmd_exec(dev, in, inlen, &out, sizeof(out));
@@ -84,7 +84,8 @@ int mlx5_core_create_qp(struct mlx5_core_dev *dev,
 	}
 
 	if (out.hdr.status) {
-		pr_warn("current num of QPs 0x%x\n", atomic_read(&dev->num_qps));
+		mlx5_core_warn(dev, "current num of QPs 0x%x\n",
+			       atomic_read(&dev->num_qps));
 		return mlx5_cmd_status_to_err(&out.hdr);
 	}
 

drivers/scsi/scsi_transport_srp.c

@@ -64,10 +64,14 @@ static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r)
 
 /**
  * srp_tmo_valid() - check timeout combination validity
+ * @reconnect_delay: Reconnect delay in seconds.
+ * @fast_io_fail_tmo: Fast I/O fail timeout in seconds.
+ * @dev_loss_tmo: Device loss timeout in seconds.
  *
  * The combination of the timeout parameters must be such that SCSI commands
  * are finished in a reasonable time. Hence do not allow the fast I/O fail
- * timeout to exceed SCSI_DEVICE_BLOCK_MAX_TIMEOUT. Furthermore, these
+ * timeout to exceed SCSI_DEVICE_BLOCK_MAX_TIMEOUT nor allow dev_loss_tmo to
+ * exceed that limit if failing I/O fast has been disabled. Furthermore, these
  * parameters must be such that multipath can detect failed paths timely.
  * Hence do not allow all three parameters to be disabled simultaneously.
  */
@@ -79,6 +83,9 @@ int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo, int dev_loss_tmo)
 		return -EINVAL;
 	if (fast_io_fail_tmo > SCSI_DEVICE_BLOCK_MAX_TIMEOUT)
 		return -EINVAL;
+	if (fast_io_fail_tmo < 0 &&
+	    dev_loss_tmo > SCSI_DEVICE_BLOCK_MAX_TIMEOUT)
+		return -EINVAL;
 	if (dev_loss_tmo >= LONG_MAX / HZ)
 		return -EINVAL;
 	if (fast_io_fail_tmo >= 0 && dev_loss_tmo >= 0 &&
@@ -368,6 +375,7 @@ invalid:
 
 /**
  * srp_reconnect_work() - reconnect and schedule a new attempt if necessary
+ * @work: Work structure used for scheduling this operation.
  */
 static void srp_reconnect_work(struct work_struct *work)
 {
@@ -408,6 +416,7 @@ static void __rport_fail_io_fast(struct srp_rport *rport)
 
 /**
  * rport_fast_io_fail_timedout() - fast I/O failure timeout handler
+ * @work: Work structure used for scheduling this operation.
  */
 static void rport_fast_io_fail_timedout(struct work_struct *work)
 {
@@ -426,6 +435,7 @@ static void rport_fast_io_fail_timedout(struct work_struct *work)
 
 /**
  * rport_dev_loss_timedout() - device loss timeout handler
+ * @work: Work structure used for scheduling this operation.
  */
 static void rport_dev_loss_timedout(struct work_struct *work)
 {
@@ -452,42 +462,35 @@ static void __srp_start_tl_fail_timers(struct srp_rport *rport)
 
 	lockdep_assert_held(&rport->mutex);
 
-	if (!rport->deleted) {
-		delay = rport->reconnect_delay;
-		fast_io_fail_tmo = rport->fast_io_fail_tmo;
-		dev_loss_tmo = rport->dev_loss_tmo;
-		pr_debug("%s current state: %d\n",
-			 dev_name(&shost->shost_gendev), rport->state);
+	delay = rport->reconnect_delay;
+	fast_io_fail_tmo = rport->fast_io_fail_tmo;
+	dev_loss_tmo = rport->dev_loss_tmo;
+	pr_debug("%s current state: %d\n", dev_name(&shost->shost_gendev),
+		 rport->state);
 
-		if (delay > 0)
-			queue_delayed_work(system_long_wq,
-					   &rport->reconnect_work,
-					   1UL * delay * HZ);
-		if (fast_io_fail_tmo >= 0 &&
-		    srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) {
-			pr_debug("%s new state: %d\n",
-				 dev_name(&shost->shost_gendev),
-				 rport->state);
-			scsi_target_block(&shost->shost_gendev);
+	if (rport->state == SRP_RPORT_LOST)
+		return;
+	if (delay > 0)
+		queue_delayed_work(system_long_wq, &rport->reconnect_work,
+				   1UL * delay * HZ);
+	if (srp_rport_set_state(rport, SRP_RPORT_BLOCKED) == 0) {
+		pr_debug("%s new state: %d\n", dev_name(&shost->shost_gendev),
+			 rport->state);
+		scsi_target_block(&shost->shost_gendev);
+		if (fast_io_fail_tmo >= 0)
 			queue_delayed_work(system_long_wq,
 					   &rport->fast_io_fail_work,
 					   1UL * fast_io_fail_tmo * HZ);
-		}
 		if (dev_loss_tmo >= 0)
 			queue_delayed_work(system_long_wq,
 					   &rport->dev_loss_work,
 					   1UL * dev_loss_tmo * HZ);
-	} else {
-		pr_debug("%s has already been deleted\n",
-			 dev_name(&shost->shost_gendev));
-		srp_rport_set_state(rport, SRP_RPORT_FAIL_FAST);
-		scsi_target_unblock(&shost->shost_gendev,
-				    SDEV_TRANSPORT_OFFLINE);
 	}
 }
 
 /**
  * srp_start_tl_fail_timers() - start the transport layer failure timers
+ * @rport: SRP target port.
  *
  * Start the transport layer fast I/O failure and device loss timers. Do not
  * modify a timer that was already started.
@@ -502,6 +505,7 @@ EXPORT_SYMBOL(srp_start_tl_fail_timers);
 
 /**
  * scsi_request_fn_active() - number of kernel threads inside scsi_request_fn()
+ * @shost: SCSI host for which to count the number of scsi_request_fn() callers.
  */
 static int scsi_request_fn_active(struct Scsi_Host *shost)
 {
@@ -522,6 +526,7 @@ static int scsi_request_fn_active(struct Scsi_Host *shost)
 
 /**
  * srp_reconnect_rport() - reconnect to an SRP target port
+ * @rport: SRP target port.
  *
  * Blocks SCSI command queueing before invoking reconnect() such that
  * queuecommand() won't be invoked concurrently with reconnect() from outside
@@ -556,7 +561,7 @@ int srp_reconnect_rport(struct srp_rport *rport)
 	scsi_target_block(&shost->shost_gendev);
 	while (scsi_request_fn_active(shost))
 		msleep(20);
-	res = i->f->reconnect(rport);
+	res = rport->state != SRP_RPORT_LOST ? i->f->reconnect(rport) : -ENODEV;
 	pr_debug("%s (state %d): transport.reconnect() returned %d\n",
 		 dev_name(&shost->shost_gendev), rport->state, res);
 	if (res == 0) {
@@ -578,9 +583,9 @@ int srp_reconnect_rport(struct srp_rport *rport)
 		spin_unlock_irq(shost->host_lock);
 	} else if (rport->state == SRP_RPORT_RUNNING) {
 		/*
-		 * srp_reconnect_rport() was invoked with fast_io_fail
-		 * off. Mark the port as failed and start the TL failure
-		 * timers if these had not yet been started.
+		 * srp_reconnect_rport() has been invoked with fast_io_fail
+		 * and dev_loss off. Mark the port as failed and start the TL
+		 * failure timers if these had not yet been started.
 		 */
 		__rport_fail_io_fast(rport);
 		scsi_target_unblock(&shost->shost_gendev,
@@ -599,6 +604,7 @@ EXPORT_SYMBOL(srp_reconnect_rport);
 
 /**
  * srp_timed_out() - SRP transport intercept of the SCSI timeout EH
+ * @scmd: SCSI command.
  *
  * If a timeout occurs while an rport is in the blocked state, ask the SCSI
  * EH to continue waiting (BLK_EH_RESET_TIMER). Otherwise let the SCSI core
@@ -622,10 +628,6 @@ static void srp_rport_release(struct device *dev)
 {
 	struct srp_rport *rport = dev_to_rport(dev);
 
-	cancel_delayed_work_sync(&rport->reconnect_work);
-	cancel_delayed_work_sync(&rport->fast_io_fail_work);
-	cancel_delayed_work_sync(&rport->dev_loss_work);
-
 	put_device(dev->parent);
 	kfree(rport);
 }
@@ -674,6 +676,7 @@ static int srp_host_match(struct attribute_container *cont, struct device *dev)
 
 /**
  * srp_rport_get() - increment rport reference count
+ * @rport: SRP target port.
  */
 void srp_rport_get(struct srp_rport *rport)
 {
@@ -683,6 +686,7 @@ EXPORT_SYMBOL(srp_rport_get);
 
 /**
  * srp_rport_put() - decrement rport reference count
+ * @rport: SRP target port.
  */
 void srp_rport_put(struct srp_rport *rport)
 {
@@ -780,12 +784,6 @@ void srp_rport_del(struct srp_rport *rport)
 	device_del(dev);
 	transport_destroy_device(dev);
 
-	mutex_lock(&rport->mutex);
-	if (rport->state == SRP_RPORT_BLOCKED)
-		__rport_fail_io_fast(rport);
-	rport->deleted = true;
-	mutex_unlock(&rport->mutex);
-
 	put_device(dev);
 }
 EXPORT_SYMBOL_GPL(srp_rport_del);
@@ -810,6 +808,27 @@ void srp_remove_host(struct Scsi_Host *shost)
 }
 EXPORT_SYMBOL_GPL(srp_remove_host);
 
+/**
+ * srp_stop_rport_timers - stop the transport layer recovery timers
+ *
+ * Must be called after srp_remove_host() and scsi_remove_host(). The caller
+ * must hold a reference on the rport (rport->dev) and on the SCSI host
+ * (rport->dev.parent).
+ */
+void srp_stop_rport_timers(struct srp_rport *rport)
+{
+	mutex_lock(&rport->mutex);
+	if (rport->state == SRP_RPORT_BLOCKED)
+		__rport_fail_io_fast(rport);
+	srp_rport_set_state(rport, SRP_RPORT_LOST);
+	mutex_unlock(&rport->mutex);
+
+	cancel_delayed_work_sync(&rport->reconnect_work);
+	cancel_delayed_work_sync(&rport->fast_io_fail_work);
+	cancel_delayed_work_sync(&rport->dev_loss_work);
+}
+EXPORT_SYMBOL_GPL(srp_stop_rport_timers);
+
 static int srp_tsk_mgmt_response(struct Scsi_Host *shost, u64 nexus, u64 tm_id,
 				 int result)
 {

include/linux/mlx4/cmd.h

@@ -157,6 +157,7 @@ enum {
 	/* register/delete flow steering network rules */
 	MLX4_QP_FLOW_STEERING_ATTACH = 0x65,
 	MLX4_QP_FLOW_STEERING_DETACH = 0x66,
+	MLX4_FLOW_STEERING_IB_UC_QP_RANGE = 0x64,
 };
 
 enum {

include/linux/mlx4/cq.h

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

include/linux/mlx4/device.h

@@ -160,7 +160,8 @@ enum {
 	MLX4_DEV_CAP_FLAG2_TS			= 1LL <<  5,
 	MLX4_DEV_CAP_FLAG2_VLAN_CONTROL		= 1LL <<  6,
 	MLX4_DEV_CAP_FLAG2_FSM			= 1LL <<  7,
-	MLX4_DEV_CAP_FLAG2_UPDATE_QP		= 1LL <<  8
+	MLX4_DEV_CAP_FLAG2_UPDATE_QP		= 1LL <<  8,
+	MLX4_DEV_CAP_FLAG2_DMFS_IPOIB		= 1LL <<  9
 };
 
 enum {
@@ -1095,6 +1096,7 @@ int mlx4_SET_PORT_qpn_calc(struct mlx4_dev *dev, u8 port, u32 base_qpn,
 int mlx4_SET_PORT_PRIO2TC(struct mlx4_dev *dev, u8 port, u8 *prio2tc);
 int mlx4_SET_PORT_SCHEDULER(struct mlx4_dev *dev, u8 port, u8 *tc_tx_bw,
 		u8 *pg, u16 *ratelimit);
+int mlx4_find_cached_mac(struct mlx4_dev *dev, u8 port, u64 mac, int *idx);
 int mlx4_find_cached_vlan(struct mlx4_dev *dev, u8 port, u16 vid, int *idx);
 int mlx4_register_vlan(struct mlx4_dev *dev, u8 port, u16 vlan, int *index);
 void mlx4_unregister_vlan(struct mlx4_dev *dev, u8 port, u16 vlan);
@@ -1144,6 +1146,9 @@ int set_and_calc_slave_port_state(struct mlx4_dev *dev, int slave, u8 port, int
 void mlx4_put_slave_node_guid(struct mlx4_dev *dev, int slave, __be64 guid);
 __be64 mlx4_get_slave_node_guid(struct mlx4_dev *dev, int slave);
 
+int mlx4_FLOW_STEERING_IB_UC_QP_RANGE(struct mlx4_dev *dev, u32 min_range_qpn,
+				      u32 max_range_qpn);
+
 cycle_t mlx4_read_clock(struct mlx4_dev *dev);
 
 #endif /* MLX4_DEVICE_H */

include/linux/mlx5/cq.h

@@ -79,15 +79,23 @@ enum {
 	MLX5_CQE_RESP_SEND	= 2,
 	MLX5_CQE_RESP_SEND_IMM	= 3,
 	MLX5_CQE_RESP_SEND_INV	= 4,
-	MLX5_CQE_RESIZE_CQ	= 0xff, /* TBD */
+	MLX5_CQE_RESIZE_CQ	= 5,
 	MLX5_CQE_REQ_ERR	= 13,
 	MLX5_CQE_RESP_ERR	= 14,
+	MLX5_CQE_INVALID	= 15,
 };
 
 enum {
-	MLX5_CQ_MODIFY_RESEIZE = 0,
-	MLX5_CQ_MODIFY_MODER = 1,
-	MLX5_CQ_MODIFY_MAPPING = 2,
+	MLX5_CQ_MODIFY_PERIOD	= 1 << 0,
+	MLX5_CQ_MODIFY_COUNT	= 1 << 1,
+	MLX5_CQ_MODIFY_OVERRUN	= 1 << 2,
+};
+
+enum {
+	MLX5_CQ_OPMOD_RESIZE		= 1,
+	MLX5_MODIFY_CQ_MASK_LOG_SIZE	= 1 << 0,
+	MLX5_MODIFY_CQ_MASK_PG_OFFSET	= 1 << 1,
+	MLX5_MODIFY_CQ_MASK_PG_SIZE	= 1 << 2,
 };
 
 struct mlx5_cq_modify_params {
@@ -158,7 +166,7 @@ int mlx5_core_destroy_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq);
 int mlx5_core_query_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
 		       struct mlx5_query_cq_mbox_out *out);
 int mlx5_core_modify_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq,
-			int type, struct mlx5_cq_modify_params *params);
+			struct mlx5_modify_cq_mbox_in *in, int in_sz);
 int mlx5_debug_cq_add(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq);
 void mlx5_debug_cq_remove(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq);
 

include/linux/mlx5/device.h

@@ -104,9 +104,10 @@ enum {
 };
 
 enum {
-	MLX5_BF_REGS_PER_PAGE	= 4,
-	MLX5_MAX_UAR_PAGES	= 1 << 8,
-	MLX5_MAX_UUARS		= MLX5_MAX_UAR_PAGES * MLX5_BF_REGS_PER_PAGE,
+	MLX5_BF_REGS_PER_PAGE		= 4,
+	MLX5_MAX_UAR_PAGES		= 1 << 8,
+	MLX5_NON_FP_BF_REGS_PER_PAGE	= 2,
+	MLX5_MAX_UUARS	= MLX5_MAX_UAR_PAGES * MLX5_NON_FP_BF_REGS_PER_PAGE,
 };
 
 enum {
@@ -176,6 +177,8 @@ enum {
 	MLX5_DEV_CAP_FLAG_APM		= 1LL << 17,
 	MLX5_DEV_CAP_FLAG_ATOMIC	= 1LL << 18,
 	MLX5_DEV_CAP_FLAG_ON_DMND_PG	= 1LL << 24,
+	MLX5_DEV_CAP_FLAG_CQ_MODER	= 1LL << 29,
+	MLX5_DEV_CAP_FLAG_RESIZE_CQ	= 1LL << 30,
 	MLX5_DEV_CAP_FLAG_RESIZE_SRQ	= 1LL << 32,
 	MLX5_DEV_CAP_FLAG_REMOTE_FENCE	= 1LL << 38,
 	MLX5_DEV_CAP_FLAG_TLP_HINTS	= 1LL << 39,
@@ -231,7 +234,8 @@ enum {
 };
 
 enum {
-	MLX5_ADAPTER_PAGE_SHIFT		= 12
+	MLX5_ADAPTER_PAGE_SHIFT		= 12,
+	MLX5_ADAPTER_PAGE_SIZE		= 1 << MLX5_ADAPTER_PAGE_SHIFT,
 };
 
 enum {
@@ -697,6 +701,20 @@ struct mlx5_query_cq_mbox_out {
 	__be64			pas[0];
 };
 
+struct mlx5_modify_cq_mbox_in {
+	struct mlx5_inbox_hdr	hdr;
+	__be32			cqn;
+	__be32			field_select;
+	struct mlx5_cq_context	ctx;
+	u8			rsvd[192];
+	__be64			pas[0];
+};
+
+struct mlx5_modify_cq_mbox_out {
+	struct mlx5_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
 struct mlx5_enable_hca_mbox_in {
 	struct mlx5_inbox_hdr	hdr;
 	u8			rsvd[8];
@@ -831,8 +849,8 @@ struct mlx5_create_mkey_mbox_in {
 	struct mlx5_mkey_seg	seg;
 	u8			rsvd1[16];
 	__be32			xlat_oct_act_size;
-	__be32			bsf_coto_act_size;
-	u8			rsvd2[168];
+	__be32			rsvd2;
+	u8			rsvd3[168];
 	__be64			pas[0];
 };
 
@@ -871,6 +889,7 @@ struct mlx5_modify_mkey_mbox_in {
 
 struct mlx5_modify_mkey_mbox_out {
 	struct mlx5_outbox_hdr	hdr;
+	u8			rsvd[8];
 };
 
 struct mlx5_dump_mkey_mbox_in {

include/linux/mlx5/qp.h

@@ -464,4 +464,49 @@ void mlx5_cleanup_qp_table(struct mlx5_core_dev *dev);
 int mlx5_debug_qp_add(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 void mlx5_debug_qp_remove(struct mlx5_core_dev *dev, struct mlx5_core_qp *qp);
 
+static inline const char *mlx5_qp_type_str(int type)
+{
+	switch (type) {
+	case MLX5_QP_ST_RC: return "RC";
+	case MLX5_QP_ST_UC: return "C";
+	case MLX5_QP_ST_UD: return "UD";
+	case MLX5_QP_ST_XRC: return "XRC";
+	case MLX5_QP_ST_MLX: return "MLX";
+	case MLX5_QP_ST_QP0: return "QP0";
+	case MLX5_QP_ST_QP1: return "QP1";
+	case MLX5_QP_ST_RAW_ETHERTYPE: return "RAW_ETHERTYPE";
+	case MLX5_QP_ST_RAW_IPV6: return "RAW_IPV6";
+	case MLX5_QP_ST_SNIFFER: return "SNIFFER";
+	case MLX5_QP_ST_SYNC_UMR: return "SYNC_UMR";
+	case MLX5_QP_ST_PTP_1588: return "PTP_1588";
+	case MLX5_QP_ST_REG_UMR: return "REG_UMR";
+	default: return "Invalid transport type";
+	}
+}
+
+static inline const char *mlx5_qp_state_str(int state)
+{
+	switch (state) {
+	case MLX5_QP_STATE_RST:
+	return "RST";
+	case MLX5_QP_STATE_INIT:
+	return "INIT";
+	case MLX5_QP_STATE_RTR:
+	return "RTR";
+	case MLX5_QP_STATE_RTS:
+	return "RTS";
+	case MLX5_QP_STATE_SQER:
+	return "SQER";
+	case MLX5_QP_STATE_SQD:
+	return "SQD";
+	case MLX5_QP_STATE_ERR:
+	return "ERR";
+	case MLX5_QP_STATE_SQ_DRAINING:
+	return "SQ_DRAINING";
+	case MLX5_QP_STATE_SUSPENDED:
+	return "SUSPENDED";
+	default: return "Invalid QP state";
+	}
+}
+
 #endif /* MLX5_QP_H */

include/rdma/ib_addr.h

@@ -38,10 +38,15 @@
 #include <linux/in6.h>
 #include <linux/if_arp.h>
 #include <linux/netdevice.h>
+#include <linux/inetdevice.h>
 #include <linux/socket.h>
 #include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/if_inet6.h>
+#include <net/ip.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
+#include <net/ipv6.h>
 
 struct rdma_addr_client {
 	atomic_t refcount;
@@ -72,7 +77,8 @@ struct rdma_dev_addr {
  * rdma_translate_ip - Translate a local IP address to an RDMA hardware
  *   address.
  */
-int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr);
+int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
+		      u16 *vlan_id);
 
 /**
  * rdma_resolve_ip - Resolve source and destination IP addresses to
@@ -104,6 +110,10 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
 
 int rdma_addr_size(struct sockaddr *addr);
 
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id);
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac,
+			       u16 *vlan_id);
+
 static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
 {
 	return ((u16)dev_addr->broadcast[8] << 8) | (u16)dev_addr->broadcast[9];
@@ -126,41 +136,60 @@ static inline int rdma_addr_gid_offset(struct rdma_dev_addr *dev_addr)
 	return dev_addr->dev_type == ARPHRD_INFINIBAND ? 4 : 0;
 }
 
-static inline void iboe_mac_vlan_to_ll(union ib_gid *gid, u8 *mac, u16 vid)
+static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
 {
-	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;
+	return dev->priv_flags & IFF_802_1Q_VLAN ?
+		vlan_dev_vlan_id(dev) : 0xffff;
+}
+
+static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
+{
+	switch (addr->sa_family) {
+	case AF_INET:
+		ipv6_addr_set_v4mapped(((struct sockaddr_in *)
+					addr)->sin_addr.s_addr,
+				       (struct in6_addr *)gid);
+		break;
+	case AF_INET6:
+		memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr, 16);
+		break;
+	default:
+		return -EINVAL;
 	}
-	memcpy(gid->raw + 13, mac + 3, 3);
-	memcpy(gid->raw + 8, mac, 3);
-	gid->raw[8] ^= 2;
+	return 0;
 }
 
-static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
+/* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */
+static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
 {
-	return dev->priv_flags & IFF_802_1Q_VLAN ?
-		vlan_dev_vlan_id(dev) : 0xffff;
+	if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
+		struct sockaddr_in *out_in = (struct sockaddr_in *)out;
+		memset(out_in, 0, sizeof(*out_in));
+		out_in->sin_family = AF_INET;
+		memcpy(&out_in->sin_addr.s_addr, gid->raw + 12, 4);
+	} else {
+		struct sockaddr_in6 *out_in = (struct sockaddr_in6 *)out;
+		memset(out_in, 0, sizeof(*out_in));
+		out_in->sin6_family = AF_INET6;
+		memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16);
+	}
+	return 0;
 }
 
 static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 				      union ib_gid *gid)
 {
 	struct net_device *dev;
-	u16 vid = 0xffff;
+	struct in_device *ip4;
 
 	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
 	if (dev) {
-		vid = rdma_vlan_dev_vlan_id(dev);
+		ip4 = (struct in_device *)dev->ip_ptr;
+		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)
+			ipv6_addr_set_v4mapped(ip4->ifa_list->ifa_address,
+					       (struct in6_addr *)gid);
 		dev_put(dev);
 	}
-
-	iboe_mac_vlan_to_ll(gid, dev_addr->src_dev_addr, vid);
 }
 
 static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)

include/rdma/ib_cm.h

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

include/rdma/ib_pack.h

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

include/rdma/ib_sa.h

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

include/rdma/ib_verbs.h

@@ -48,6 +48,7 @@
 #include <linux/rwsem.h>
 #include <linux/scatterlist.h>
 #include <linux/workqueue.h>
+#include <uapi/linux/if_ether.h>
 
 #include <linux/atomic.h>
 #include <asm/uaccess.h>
@@ -69,12 +70,14 @@ enum rdma_node_type {
 	RDMA_NODE_IB_ROUTER,
 	RDMA_NODE_RNIC,
 	RDMA_NODE_USNIC,
+	RDMA_NODE_USNIC_UDP,
 };
 
 enum rdma_transport_type {
 	RDMA_TRANSPORT_IB,
 	RDMA_TRANSPORT_IWARP,
-	RDMA_TRANSPORT_USNIC
+	RDMA_TRANSPORT_USNIC,
+	RDMA_TRANSPORT_USNIC_UDP
 };
 
 enum rdma_transport_type
@@ -472,6 +475,8 @@ struct ib_ah_attr {
 	u8			static_rate;
 	u8			ah_flags;
 	u8			port_num;
+	u8			dmac[ETH_ALEN];
+	u16			vlan_id;
 };
 
 enum ib_wc_status {
@@ -524,6 +529,8 @@ enum ib_wc_flags {
 	IB_WC_WITH_IMM		= (1<<1),
 	IB_WC_WITH_INVALIDATE	= (1<<2),
 	IB_WC_IP_CSUM_OK	= (1<<3),
+	IB_WC_WITH_SMAC		= (1<<4),
+	IB_WC_WITH_VLAN		= (1<<5),
 };
 
 struct ib_wc {
@@ -544,6 +551,8 @@ struct ib_wc {
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */
+	u8			smac[ETH_ALEN];
+	u16			vlan_id;
 };
 
 enum ib_cq_notify_flags {
@@ -633,6 +642,7 @@ enum ib_qp_type {
 enum ib_qp_create_flags {
 	IB_QP_CREATE_IPOIB_UD_LSO		= 1 << 0,
 	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	= 1 << 1,
+	IB_QP_CREATE_NETIF_QP			= 1 << 5,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
@@ -721,7 +731,11 @@ enum ib_qp_attr_mask {
 	IB_QP_MAX_DEST_RD_ATOMIC	= (1<<17),
 	IB_QP_PATH_MIG_STATE		= (1<<18),
 	IB_QP_CAP			= (1<<19),
-	IB_QP_DEST_QPN			= (1<<20)
+	IB_QP_DEST_QPN			= (1<<20),
+	IB_QP_SMAC			= (1<<21),
+	IB_QP_ALT_SMAC			= (1<<22),
+	IB_QP_VID			= (1<<23),
+	IB_QP_ALT_VID			= (1<<24),
 };
 
 enum ib_qp_state {
@@ -771,6 +785,10 @@ struct ib_qp_attr {
 	u8			rnr_retry;
 	u8			alt_port_num;
 	u8			alt_timeout;
+	u8			smac[ETH_ALEN];
+	u8			alt_smac[ETH_ALEN];
+	u16			vlan_id;
+	u16			alt_vlan_id;
 };
 
 enum ib_wr_opcode {
@@ -1099,13 +1117,14 @@ enum ib_flow_attr_type {
 enum ib_flow_spec_type {
 	/* L2 headers*/
 	IB_FLOW_SPEC_ETH	= 0x20,
+	IB_FLOW_SPEC_IB		= 0x22,
 	/* L3 header*/
 	IB_FLOW_SPEC_IPV4	= 0x30,
 	/* L4 headers*/
 	IB_FLOW_SPEC_TCP	= 0x40,
 	IB_FLOW_SPEC_UDP	= 0x41
 };
-
+#define IB_FLOW_SPEC_LAYER_MASK	0xF0
 #define IB_FLOW_SPEC_SUPPORT_LAYERS 4
 
 /* Flow steering rule priority is set according to it's domain.
@@ -1133,6 +1152,18 @@ struct ib_flow_spec_eth {
 	struct ib_flow_eth_filter mask;
 };
 
+struct ib_flow_ib_filter {
+	__be16 dlid;
+	__u8   sl;
+};
+
+struct ib_flow_spec_ib {
+	enum ib_flow_spec_type	 type;
+	u16			 size;
+	struct ib_flow_ib_filter val;
+	struct ib_flow_ib_filter mask;
+};
+
 struct ib_flow_ipv4_filter {
 	__be32	src_ip;
 	__be32	dst_ip;
@@ -1163,6 +1194,7 @@ union ib_flow_spec {
 		u16			size;
 	};
 	struct ib_flow_spec_eth		eth;
+	struct ib_flow_spec_ib		ib;
 	struct ib_flow_spec_ipv4        ipv4;
 	struct ib_flow_spec_tcp_udp	tcp_udp;
 };
@@ -1488,6 +1520,7 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
  * @next_state: Next QP state
  * @type: QP type
  * @mask: Mask of supplied QP attributes
+ * @ll : link layer of port
  *
  * This function is a helper function that a low-level driver's
  * modify_qp method can use to validate the consumer's input.  It
@@ -1496,7 +1529,8 @@ static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len
  * and that the attribute mask supplied is allowed for the transition.
  */
 int ib_modify_qp_is_ok(enum ib_qp_state cur_state, enum ib_qp_state next_state,
-		       enum ib_qp_type type, enum ib_qp_attr_mask mask);
+		       enum ib_qp_type type, enum ib_qp_attr_mask mask,
+		       enum rdma_link_layer ll);
 
 int ib_register_event_handler  (struct ib_event_handler *event_handler);
 int ib_unregister_event_handler(struct ib_event_handler *event_handler);

include/scsi/scsi_transport_srp.h

@@ -19,7 +19,7 @@ struct srp_rport_identifiers {
  * @SRP_RPORT_BLOCKED:   Transport layer not operational; fast I/O fail timer
  *                       is running and I/O has been blocked.
  * @SRP_RPORT_FAIL_FAST: Fast I/O fail timer has expired; fail I/O fast.
- * @SRP_RPORT_LOST:      Device loss timer has expired; port is being removed.
+ * @SRP_RPORT_LOST:      Port is being removed.
  */
 enum srp_rport_state {
 	SRP_RPORT_RUNNING,
@@ -29,10 +29,26 @@ enum srp_rport_state {
 };
 
 /**
- * struct srp_rport
- * @lld_data: LLD private data.
- * @mutex:    Protects against concurrent rport reconnect / fast_io_fail /
- *   dev_loss_tmo activity.
+ * struct srp_rport - SRP initiator or target port
+ *
+ * Fields that are relevant for SRP initiator and SRP target drivers:
+ * @dev:               Device associated with this rport.
+ * @port_id:           16-byte port identifier.
+ * @roles:             Role of this port - initiator or target.
+ *
+ * Fields that are only relevant for SRP initiator drivers:
+ * @lld_data:          LLD private data.
+ * @mutex:             Protects against concurrent rport reconnect /
+ *                     fast_io_fail / dev_loss_tmo activity.
+ * @state:             rport state.
+ * @deleted:           Whether or not srp_rport_del() has already been invoked.
+ * @reconnect_delay:   Reconnect delay in seconds.
+ * @failed_reconnects: Number of failed reconnect attempts.
+ * @reconnect_work:    Work structure used for scheduling reconnect attempts.
+ * @fast_io_fail_tmo:  Fast I/O fail timeout in seconds.
+ * @dev_loss_tmo:      Device loss timeout in seconds.
+ * @fast_io_fail_work: Work structure used for scheduling fast I/O fail work.
+ * @dev_loss_work:     Work structure used for scheduling device loss work.
  */
 struct srp_rport {
 	/* for initiator and target drivers */
@@ -48,7 +64,6 @@ struct srp_rport {
 
 	struct mutex		mutex;
 	enum srp_rport_state	state;
-	bool			deleted;
 	int			reconnect_delay;
 	int			failed_reconnects;
 	struct delayed_work	reconnect_work;
@@ -60,6 +75,8 @@ struct srp_rport {
 
 /**
  * struct srp_function_template
+ *
+ * Fields that are only relevant for SRP initiator drivers:
  * @has_rport_state: Whether or not to create the state, fast_io_fail_tmo and
  *     dev_loss_tmo sysfs attribute for an rport.
  * @reset_timer_if_blocked: Whether or srp_timed_out() should reset the command
@@ -71,6 +88,11 @@ struct srp_rport {
  *     srp_reconnect_rport().
  * @terminate_rport_io: Callback function for terminating all outstanding I/O
  *     requests for an rport.
+ * @rport_delete: Callback function that deletes an rport.
+ *
+ * Fields that are only relevant for SRP target drivers:
+ * @tsk_mgmt_response: Callback function for sending a task management response.
+ * @it_nexus_response: Callback function for processing an IT nexus response.
  */
 struct srp_function_template {
 	/* for initiator drivers */
@@ -101,9 +123,11 @@ extern int srp_tmo_valid(int reconnect_delay, int fast_io_fail_tmo,
 extern int srp_reconnect_rport(struct srp_rport *rport);
 extern void srp_start_tl_fail_timers(struct srp_rport *rport);
 extern void srp_remove_host(struct Scsi_Host *);
+extern void srp_stop_rport_timers(struct srp_rport *rport);
 
 /**
  * srp_chkready() - evaluate the transport layer state before I/O
+ * @rport: SRP target port pointer.
  *
  * Returns a SCSI result code that can be returned by the LLD queuecommand()
  * implementation. The role of this function is similar to that of