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

Pull rdma updates from Doug Ledford:

 - a large cleanup of how device capabilities are checked for various
   features

 - additional cleanups in the MAD processing

 - update to the srp driver

 - creation and use of centralized log message helpers

 - add const to a number of args to calls and clean up call chain

 - add support for extended cq create verb

 - add support for timestamps on cq completion

 - add support for processing OPA MAD packets

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/dledford/rdma: (92 commits)
  IB/mad: Add final OPA MAD processing
  IB/mad: Add partial Intel OPA MAD support
  IB/mad: Add partial Intel OPA MAD support
  IB/core: Add OPA MAD core capability flag
  IB/mad: Add support for additional MAD info to/from drivers
  IB/mad: Convert allocations from kmem_cache to kzalloc
  IB/core: Add ability for drivers to report an alternate MAD size.
  IB/mad: Support alternate Base Versions when creating MADs
  IB/mad: Create a generic helper for DR forwarding checks
  IB/mad: Create a generic helper for DR SMP Recv processing
  IB/mad: Create a generic helper for DR SMP Send processing
  IB/mad: Split IB SMI handling from MAD Recv handler
  IB/mad cleanup: Generalize processing of MAD data
  IB/mad cleanup: Clean up function params -- find_mad_agent
  IB/mlx4: Add support for CQ time-stamping
  IB/mlx4: Add mmap call to map the hardware clock
  IB/core: Pass hardware specific data in query_device
  IB/core: Add timestamp_mask and hca_core_clock to query_device
  IB/core: Extend ib_uverbs_create_cq
  IB/core: Add CQ creation time-stamping flag
  ...

drivers/infiniband/core/addr.c

@@ -457,8 +457,8 @@ static void resolve_cb(int status, struct sockaddr *src_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 rdma_addr_find_dmac_by_grh(const union ib_gid *sgid, const union ib_gid *dgid,
+			       u8 *dmac, u16 *vlan_id)
 {
 	int ret = 0;
 	struct rdma_dev_addr dev_addr;

drivers/infiniband/core/agent.c

@@ -54,7 +54,7 @@ static DEFINE_SPINLOCK(ib_agent_port_list_lock);
 static LIST_HEAD(ib_agent_port_list);
 
 static struct ib_agent_port_private *
-__ib_get_agent_port(struct ib_device *device, int port_num)
+__ib_get_agent_port(const struct ib_device *device, int port_num)
 {
 	struct ib_agent_port_private *entry;
 
@@ -67,7 +67,7 @@ __ib_get_agent_port(struct ib_device *device, int port_num)
 }
 
 static struct ib_agent_port_private *
-ib_get_agent_port(struct ib_device *device, int port_num)
+ib_get_agent_port(const struct ib_device *device, int port_num)
 {
 	struct ib_agent_port_private *entry;
 	unsigned long flags;
@@ -78,9 +78,9 @@ ib_get_agent_port(struct ib_device *device, int port_num)
 	return entry;
 }
 
-void agent_send_response(struct ib_mad *mad, struct ib_grh *grh,
-			 struct ib_wc *wc, struct ib_device *device,
-			 int port_num, int qpn)
+void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh,
+			 const struct ib_wc *wc, const struct ib_device *device,
+			 int port_num, int qpn, size_t resp_mad_len, bool opa)
 {
 	struct ib_agent_port_private *port_priv;
 	struct ib_mad_agent *agent;
@@ -106,15 +106,20 @@ void agent_send_response(struct ib_mad *mad, struct ib_grh *grh,
 		return;
 	}
 
+	if (opa && mad_hdr->base_version != OPA_MGMT_BASE_VERSION)
+		resp_mad_len = IB_MGMT_MAD_SIZE;
+
 	send_buf = ib_create_send_mad(agent, wc->src_qp, wc->pkey_index, 0,
-				      IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-				      GFP_KERNEL);
+				      IB_MGMT_MAD_HDR,
+				      resp_mad_len - IB_MGMT_MAD_HDR,
+				      GFP_KERNEL,
+				      mad_hdr->base_version);
 	if (IS_ERR(send_buf)) {
 		dev_err(&device->dev, "ib_create_send_mad error\n");
 		goto err1;
 	}
 
-	memcpy(send_buf->mad, mad, sizeof *mad);
+	memcpy(send_buf->mad, mad_hdr, resp_mad_len);
 	send_buf->ah = ah;
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH) {
@@ -156,7 +161,7 @@ int ib_agent_port_open(struct ib_device *device, int port_num)
 		goto error1;
 	}
 
-	if (rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND) {
+	if (rdma_cap_ib_smi(device, port_num)) {
 		/* Obtain send only MAD agent for SMI QP */
 		port_priv->agent[0] = ib_register_mad_agent(device, port_num,
 							    IB_QPT_SMI, NULL, 0,

drivers/infiniband/core/agent.h

@@ -44,8 +44,8 @@ extern int ib_agent_port_open(struct ib_device *device, int port_num);
 
 extern int ib_agent_port_close(struct ib_device *device, int port_num);
 
-extern void agent_send_response(struct ib_mad *mad, struct ib_grh *grh,
-				struct ib_wc *wc, struct ib_device *device,
-				int port_num, int qpn);
+extern void agent_send_response(const struct ib_mad_hdr *mad_hdr, const struct ib_grh *grh,
+				const struct ib_wc *wc, const struct ib_device *device,
+				int port_num, int qpn, size_t resp_mad_len, bool opa);
 
 #endif	/* __AGENT_H_ */

drivers/infiniband/core/cache.c

@@ -58,17 +58,6 @@ struct ib_update_work {
 	u8                 port_num;
 };
 
-static inline int start_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1;
-}
-
-static inline int end_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ?
-		0 : device->phys_port_cnt;
-}
-
 int ib_get_cached_gid(struct ib_device *device,
 		      u8                port_num,
 		      int               index,
@@ -78,12 +67,12 @@ int ib_get_cached_gid(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.gid_cache[port_num - start_port(device)];
+	cache = device->cache.gid_cache[port_num - rdma_start_port(device)];
 
 	if (index < 0 || index >= cache->table_len)
 		ret = -EINVAL;
@@ -96,10 +85,10 @@ int ib_get_cached_gid(struct ib_device *device,
 }
 EXPORT_SYMBOL(ib_get_cached_gid);
 
-int ib_find_cached_gid(struct ib_device *device,
-		       union ib_gid	*gid,
-		       u8               *port_num,
-		       u16              *index)
+int ib_find_cached_gid(struct ib_device   *device,
+		       const union ib_gid *gid,
+		       u8                 *port_num,
+		       u16                *index)
 {
 	struct ib_gid_cache *cache;
 	unsigned long flags;
@@ -112,11 +101,11 @@ int ib_find_cached_gid(struct ib_device *device,
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		cache = device->cache.gid_cache[p];
 		for (i = 0; i < cache->table_len; ++i) {
 			if (!memcmp(gid, &cache->table[i], sizeof *gid)) {
-				*port_num = p + start_port(device);
+				*port_num = p + rdma_start_port(device);
 				if (index)
 					*index = i;
 				ret = 0;
@@ -140,12 +129,12 @@ int ib_get_cached_pkey(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - start_port(device)];
+	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
 
 	if (index < 0 || index >= cache->table_len)
 		ret = -EINVAL;
@@ -169,12 +158,12 @@ int ib_find_cached_pkey(struct ib_device *device,
 	int ret = -ENOENT;
 	int partial_ix = -1;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - start_port(device)];
+	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
 
 	*index = -1;
 
@@ -209,12 +198,12 @@ int ib_find_exact_cached_pkey(struct ib_device *device,
 	int i;
 	int ret = -ENOENT;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
 
-	cache = device->cache.pkey_cache[port_num - start_port(device)];
+	cache = device->cache.pkey_cache[port_num - rdma_start_port(device)];
 
 	*index = -1;
 
@@ -238,11 +227,11 @@ int ib_get_cached_lmc(struct ib_device *device,
 	unsigned long flags;
 	int ret = 0;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	read_lock_irqsave(&device->cache.lock, flags);
-	*lmc = device->cache.lmc_cache[port_num - start_port(device)];
+	*lmc = device->cache.lmc_cache[port_num - rdma_start_port(device)];
 	read_unlock_irqrestore(&device->cache.lock, flags);
 
 	return ret;
@@ -303,13 +292,13 @@ static void ib_cache_update(struct ib_device *device,
 
 	write_lock_irq(&device->cache.lock);
 
-	old_pkey_cache = device->cache.pkey_cache[port - start_port(device)];
-	old_gid_cache  = device->cache.gid_cache [port - start_port(device)];
+	old_pkey_cache = device->cache.pkey_cache[port - rdma_start_port(device)];
+	old_gid_cache  = device->cache.gid_cache [port - rdma_start_port(device)];
 
-	device->cache.pkey_cache[port - start_port(device)] = pkey_cache;
-	device->cache.gid_cache [port - start_port(device)] = gid_cache;
+	device->cache.pkey_cache[port - rdma_start_port(device)] = pkey_cache;
+	device->cache.gid_cache [port - rdma_start_port(device)] = gid_cache;
 
-	device->cache.lmc_cache[port - start_port(device)] = tprops->lmc;
+	device->cache.lmc_cache[port - rdma_start_port(device)] = tprops->lmc;
 
 	write_unlock_irq(&device->cache.lock);
 
@@ -363,14 +352,14 @@ static void ib_cache_setup_one(struct ib_device *device)
 
 	device->cache.pkey_cache =
 		kmalloc(sizeof *device->cache.pkey_cache *
-			(end_port(device) - start_port(device) + 1), GFP_KERNEL);
+			(rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL);
 	device->cache.gid_cache =
 		kmalloc(sizeof *device->cache.gid_cache *
-			(end_port(device) - start_port(device) + 1), GFP_KERNEL);
+			(rdma_end_port(device) - rdma_start_port(device) + 1), GFP_KERNEL);
 
 	device->cache.lmc_cache = kmalloc(sizeof *device->cache.lmc_cache *
-					  (end_port(device) -
-					   start_port(device) + 1),
+					  (rdma_end_port(device) -
+					   rdma_start_port(device) + 1),
 					  GFP_KERNEL);
 
 	if (!device->cache.pkey_cache || !device->cache.gid_cache ||
@@ -380,10 +369,10 @@ static void ib_cache_setup_one(struct ib_device *device)
 		goto err;
 	}
 
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		device->cache.pkey_cache[p] = NULL;
 		device->cache.gid_cache [p] = NULL;
-		ib_cache_update(device, p + start_port(device));
+		ib_cache_update(device, p + rdma_start_port(device));
 	}
 
 	INIT_IB_EVENT_HANDLER(&device->cache.event_handler,
@@ -394,7 +383,7 @@ static void ib_cache_setup_one(struct ib_device *device)
 	return;
 
 err_cache:
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		kfree(device->cache.pkey_cache[p]);
 		kfree(device->cache.gid_cache[p]);
 	}
@@ -412,7 +401,7 @@ static void ib_cache_cleanup_one(struct ib_device *device)
 	ib_unregister_event_handler(&device->cache.event_handler);
 	flush_workqueue(ib_wq);
 
-	for (p = 0; p <= end_port(device) - start_port(device); ++p) {
+	for (p = 0; p <= rdma_end_port(device) - rdma_start_port(device); ++p) {
 		kfree(device->cache.pkey_cache[p]);
 		kfree(device->cache.gid_cache[p]);
 	}

drivers/infiniband/core/cm.c

@@ -267,7 +267,8 @@ static int cm_alloc_msg(struct cm_id_private *cm_id_priv,
 	m = ib_create_send_mad(mad_agent, cm_id_priv->id.remote_cm_qpn,
 			       cm_id_priv->av.pkey_index,
 			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-			       GFP_ATOMIC);
+			       GFP_ATOMIC,
+			       IB_MGMT_BASE_VERSION);
 	if (IS_ERR(m)) {
 		ib_destroy_ah(ah);
 		return PTR_ERR(m);
@@ -297,7 +298,8 @@ static int cm_alloc_response_msg(struct cm_port *port,
 
 	m = ib_create_send_mad(port->mad_agent, 1, mad_recv_wc->wc->pkey_index,
 			       0, IB_MGMT_MAD_HDR, IB_MGMT_MAD_DATA,
-			       GFP_ATOMIC);
+			       GFP_ATOMIC,
+			       IB_MGMT_BASE_VERSION);
 	if (IS_ERR(m)) {
 		ib_destroy_ah(ah);
 		return PTR_ERR(m);
@@ -3759,11 +3761,9 @@ static void cm_add_one(struct ib_device *ib_device)
 	};
 	unsigned long flags;
 	int ret;
+	int count = 0;
 	u8 i;
 
-	if (rdma_node_get_transport(ib_device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	cm_dev = kzalloc(sizeof(*cm_dev) + sizeof(*port) *
 			 ib_device->phys_port_cnt, GFP_KERNEL);
 	if (!cm_dev)
@@ -3782,6 +3782,9 @@ static void cm_add_one(struct ib_device *ib_device)
 
 	set_bit(IB_MGMT_METHOD_SEND, reg_req.method_mask);
 	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
+		if (!rdma_cap_ib_cm(ib_device, i))
+			continue;
+
 		port = kzalloc(sizeof *port, GFP_KERNEL);
 		if (!port)
 			goto error1;
@@ -3808,7 +3811,13 @@ static void cm_add_one(struct ib_device *ib_device)
 		ret = ib_modify_port(ib_device, i, 0, &port_modify);
 		if (ret)
 			goto error3;
+
+		count++;
 	}
+
+	if (!count)
+		goto free;
+
 	ib_set_client_data(ib_device, &cm_client, cm_dev);
 
 	write_lock_irqsave(&cm.device_lock, flags);
@@ -3824,11 +3833,15 @@ error1:
 	port_modify.set_port_cap_mask = 0;
 	port_modify.clr_port_cap_mask = IB_PORT_CM_SUP;
 	while (--i) {
+		if (!rdma_cap_ib_cm(ib_device, i))
+			continue;
+
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
 		ib_unregister_mad_agent(port->mad_agent);
 		cm_remove_port_fs(port);
 	}
+free:
 	device_unregister(cm_dev->device);
 	kfree(cm_dev);
 }
@@ -3852,6 +3865,9 @@ static void cm_remove_one(struct ib_device *ib_device)
 	write_unlock_irqrestore(&cm.device_lock, flags);
 
 	for (i = 1; i <= ib_device->phys_port_cnt; i++) {
+		if (!rdma_cap_ib_cm(ib_device, i))
+			continue;
+
 		port = cm_dev->port[i-1];
 		ib_modify_port(ib_device, port->port_num, 0, &port_modify);
 		ib_unregister_mad_agent(port->mad_agent);

drivers/infiniband/core/cma.c

@@ -65,6 +65,34 @@ MODULE_LICENSE("Dual BSD/GPL");
 #define CMA_CM_MRA_SETTING (IB_CM_MRA_FLAG_DELAY | 24)
 #define CMA_IBOE_PACKET_LIFETIME 18
 
+static const char * const cma_events[] = {
+	[RDMA_CM_EVENT_ADDR_RESOLVED]	 = "address resolved",
+	[RDMA_CM_EVENT_ADDR_ERROR]	 = "address error",
+	[RDMA_CM_EVENT_ROUTE_RESOLVED]	 = "route resolved ",
+	[RDMA_CM_EVENT_ROUTE_ERROR]	 = "route error",
+	[RDMA_CM_EVENT_CONNECT_REQUEST]	 = "connect request",
+	[RDMA_CM_EVENT_CONNECT_RESPONSE] = "connect response",
+	[RDMA_CM_EVENT_CONNECT_ERROR]	 = "connect error",
+	[RDMA_CM_EVENT_UNREACHABLE]	 = "unreachable",
+	[RDMA_CM_EVENT_REJECTED]	 = "rejected",
+	[RDMA_CM_EVENT_ESTABLISHED]	 = "established",
+	[RDMA_CM_EVENT_DISCONNECTED]	 = "disconnected",
+	[RDMA_CM_EVENT_DEVICE_REMOVAL]	 = "device removal",
+	[RDMA_CM_EVENT_MULTICAST_JOIN]	 = "multicast join",
+	[RDMA_CM_EVENT_MULTICAST_ERROR]	 = "multicast error",
+	[RDMA_CM_EVENT_ADDR_CHANGE]	 = "address change",
+	[RDMA_CM_EVENT_TIMEWAIT_EXIT]	 = "timewait exit",
+};
+
+const char *rdma_event_msg(enum rdma_cm_event_type event)
+{
+	size_t index = event;
+
+	return (index < ARRAY_SIZE(cma_events) && cma_events[index]) ?
+			cma_events[index] : "unrecognized event";
+}
+EXPORT_SYMBOL(rdma_event_msg);
+
 static void cma_add_one(struct ib_device *device);
 static void cma_remove_one(struct ib_device *device);
 
@@ -349,18 +377,35 @@ static int cma_translate_addr(struct sockaddr *addr, struct rdma_dev_addr *dev_a
 	return ret;
 }
 
+static inline int cma_validate_port(struct ib_device *device, u8 port,
+				      union ib_gid *gid, int dev_type)
+{
+	u8 found_port;
+	int ret = -ENODEV;
+
+	if ((dev_type == ARPHRD_INFINIBAND) && !rdma_protocol_ib(device, port))
+		return ret;
+
+	if ((dev_type != ARPHRD_INFINIBAND) && rdma_protocol_ib(device, port))
+		return ret;
+
+	ret = ib_find_cached_gid(device, gid, &found_port, NULL);
+	if (port != found_port)
+		return -ENODEV;
+
+	return ret;
+}
+
 static int cma_acquire_dev(struct rdma_id_private *id_priv,
 			   struct rdma_id_private *listen_id_priv)
 {
 	struct rdma_dev_addr *dev_addr = &id_priv->id.route.addr.dev_addr;
 	struct cma_device *cma_dev;
-	union ib_gid gid, iboe_gid;
+	union ib_gid gid, iboe_gid, *gidp;
 	int ret = -ENODEV;
-	u8 port, found_port;
-	enum rdma_link_layer dev_ll = dev_addr->dev_type == ARPHRD_INFINIBAND ?
-		IB_LINK_LAYER_INFINIBAND : IB_LINK_LAYER_ETHERNET;
+	u8 port;
 
-	if (dev_ll != IB_LINK_LAYER_INFINIBAND &&
+	if (dev_addr->dev_type != ARPHRD_INFINIBAND &&
 	    id_priv->id.ps == RDMA_PS_IPOIB)
 		return -EINVAL;
 
@@ -370,41 +415,36 @@ static int cma_acquire_dev(struct rdma_id_private *id_priv,
 
 	memcpy(&gid, dev_addr->src_dev_addr +
 	       rdma_addr_gid_offset(dev_addr), sizeof gid);
-	if (listen_id_priv &&
-	    rdma_port_get_link_layer(listen_id_priv->id.device,
-				     listen_id_priv->id.port_num) == dev_ll) {
+
+	if (listen_id_priv) {
 		cma_dev = listen_id_priv->cma_dev;
 		port = listen_id_priv->id.port_num;
-		if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB &&
-		    rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET)
-			ret = ib_find_cached_gid(cma_dev->device, &iboe_gid,
-						 &found_port, NULL);
-		else
-			ret = ib_find_cached_gid(cma_dev->device, &gid,
-						 &found_port, NULL);
+		gidp = rdma_protocol_roce(cma_dev->device, port) ?
+		       &iboe_gid : &gid;
 
-		if (!ret && (port  == found_port)) {
-			id_priv->id.port_num = found_port;
+		ret = cma_validate_port(cma_dev->device, port, gidp,
+					dev_addr->dev_type);
+		if (!ret) {
+			id_priv->id.port_num = port;
 			goto out;
 		}
 	}
+
 	list_for_each_entry(cma_dev, &dev_list, list) {
 		for (port = 1; port <= cma_dev->device->phys_port_cnt; ++port) {
 			if (listen_id_priv &&
 			    listen_id_priv->cma_dev == cma_dev &&
 			    listen_id_priv->id.port_num == port)
 				continue;
-			if (rdma_port_get_link_layer(cma_dev->device, port) == dev_ll) {
-				if (rdma_node_get_transport(cma_dev->device->node_type) == RDMA_TRANSPORT_IB &&
-				    rdma_port_get_link_layer(cma_dev->device, port) == IB_LINK_LAYER_ETHERNET)
-					ret = ib_find_cached_gid(cma_dev->device, &iboe_gid, &found_port, NULL);
-				else
-					ret = ib_find_cached_gid(cma_dev->device, &gid, &found_port, NULL);
-
-				if (!ret && (port == found_port)) {
-					id_priv->id.port_num = found_port;
-					goto out;
-				}
+
+			gidp = rdma_protocol_roce(cma_dev->device, port) ?
+			       &iboe_gid : &gid;
+
+			ret = cma_validate_port(cma_dev->device, port, gidp,
+						dev_addr->dev_type);
+			if (!ret) {
+				id_priv->id.port_num = port;
+				goto out;
 			}
 		}
 	}
@@ -435,10 +475,10 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 	pkey = ntohs(addr->sib_pkey);
 
 	list_for_each_entry(cur_dev, &dev_list, list) {
-		if (rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB)
-			continue;
-
 		for (p = 1; p <= cur_dev->device->phys_port_cnt; ++p) {
+			if (!rdma_cap_af_ib(cur_dev->device, p))
+				continue;
+
 			if (ib_find_cached_pkey(cur_dev->device, p, pkey, &index))
 				continue;
 
@@ -633,10 +673,9 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 	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) {
+	BUG_ON(id_priv->cma_dev->device != id_priv->id.device);
+
+	if (rdma_protocol_roce(id_priv->id.device, id_priv->id.port_num)) {
 		ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
 
 		if (ret)
@@ -700,11 +739,10 @@ static int cma_ib_init_qp_attr(struct rdma_id_private *id_priv,
 	int ret;
 	u16 pkey;
 
-	if (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num) ==
-	    IB_LINK_LAYER_INFINIBAND)
-		pkey = ib_addr_get_pkey(dev_addr);
-	else
+	if (rdma_cap_eth_ah(id_priv->id.device, id_priv->id.port_num))
 		pkey = 0xffff;
+	else
+		pkey = ib_addr_get_pkey(dev_addr);
 
 	ret = ib_find_cached_pkey(id_priv->id.device, id_priv->id.port_num,
 				  pkey, &qp_attr->pkey_index);
@@ -735,8 +773,7 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 	int ret = 0;
 
 	id_priv = container_of(id, struct rdma_id_private, id);
-	switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (!id_priv->cm_id.ib || (id_priv->id.qp_type == IB_QPT_UD))
 			ret = cma_ib_init_qp_attr(id_priv, qp_attr, qp_attr_mask);
 		else
@@ -745,19 +782,15 @@ int rdma_init_qp_attr(struct rdma_cm_id *id, struct ib_qp_attr *qp_attr,
 
 		if (qp_attr->qp_state == IB_QPS_RTR)
 			qp_attr->rq_psn = id_priv->seq_num;
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		if (!id_priv->cm_id.iw) {
 			qp_attr->qp_access_flags = 0;
 			*qp_attr_mask = IB_QP_STATE | IB_QP_ACCESS_FLAGS;
 		} else
 			ret = iw_cm_init_qp_attr(id_priv->cm_id.iw, qp_attr,
 						 qp_attr_mask);
-		break;
-	default:
+	} else
 		ret = -ENOSYS;
-		break;
-	}
 
 	return ret;
 }
@@ -945,13 +978,9 @@ static inline int cma_user_data_offset(struct rdma_id_private *id_priv)
 
 static void cma_cancel_route(struct rdma_id_private *id_priv)
 {
-	switch (rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)) {
-	case IB_LINK_LAYER_INFINIBAND:
+	if (rdma_cap_ib_sa(id_priv->id.device, id_priv->id.port_num)) {
 		if (id_priv->query)
 			ib_sa_cancel_query(id_priv->query_id, id_priv->query);
-		break;
-	default:
-		break;
 	}
 }
 
@@ -1023,17 +1052,12 @@ static void cma_leave_mc_groups(struct rdma_id_private *id_priv)
 		mc = container_of(id_priv->mc_list.next,
 				  struct cma_multicast, list);
 		list_del(&mc->list);
-		switch (rdma_port_get_link_layer(id_priv->cma_dev->device, id_priv->id.port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
+		if (rdma_cap_ib_mcast(id_priv->cma_dev->device,
+				      id_priv->id.port_num)) {
 			ib_sa_free_multicast(mc->multicast.ib);
 			kfree(mc);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
+		} else
 			kref_put(&mc->mcref, release_mc);
-			break;
-		default:
-			break;
-		}
 	}
 }
 
@@ -1054,17 +1078,12 @@ void rdma_destroy_id(struct rdma_cm_id *id)
 	mutex_unlock(&id_priv->handler_mutex);
 
 	if (id_priv->cma_dev) {
-		switch (rdma_node_get_transport(id_priv->id.device->node_type)) {
-		case RDMA_TRANSPORT_IB:
+		if (rdma_cap_ib_cm(id_priv->id.device, 1)) {
 			if (id_priv->cm_id.ib)
 				ib_destroy_cm_id(id_priv->cm_id.ib);
-			break;
-		case RDMA_TRANSPORT_IWARP:
+		} else if (rdma_cap_iw_cm(id_priv->id.device, 1)) {
 			if (id_priv->cm_id.iw)
 				iw_destroy_cm_id(id_priv->cm_id.iw);
-			break;
-		default:
-			break;
 		}
 		cma_leave_mc_groups(id_priv);
 		cma_release_dev(id_priv);
@@ -1610,6 +1629,7 @@ static int cma_iw_listen(struct rdma_id_private *id_priv, int backlog)
 	if (IS_ERR(id))
 		return PTR_ERR(id);
 
+	id->tos = id_priv->tos;
 	id_priv->cm_id.iw = id;
 
 	memcpy(&id_priv->cm_id.iw->local_addr, cma_src_addr(id_priv),
@@ -1642,8 +1662,7 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 	struct rdma_cm_id *id;
 	int ret;
 
-	if (cma_family(id_priv) == AF_IB &&
-	    rdma_node_get_transport(cma_dev->device->node_type) != RDMA_TRANSPORT_IB)
+	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
 	id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps,
@@ -1984,26 +2003,15 @@ int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms)
 		return -EINVAL;
 
 	atomic_inc(&id_priv->refcount);
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
-		switch (rdma_port_get_link_layer(id->device, id->port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
-			ret = cma_resolve_ib_route(id_priv, timeout_ms);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
-			ret = cma_resolve_iboe_route(id_priv);
-			break;
-		default:
-			ret = -ENOSYS;
-		}
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	if (rdma_cap_ib_sa(id->device, id->port_num))
+		ret = cma_resolve_ib_route(id_priv, timeout_ms);
+	else if (rdma_protocol_roce(id->device, id->port_num))
+		ret = cma_resolve_iboe_route(id_priv);
+	else if (rdma_protocol_iwarp(id->device, id->port_num))
 		ret = cma_resolve_iw_route(id_priv, timeout_ms);
-		break;
-	default:
+	else
 		ret = -ENOSYS;
-		break;
-	}
+
 	if (ret)
 		goto err;
 
@@ -2045,7 +2053,7 @@ static int cma_bind_loopback(struct rdma_id_private *id_priv)
 	mutex_lock(&lock);
 	list_for_each_entry(cur_dev, &dev_list, list) {
 		if (cma_family(id_priv) == AF_IB &&
-		    rdma_node_get_transport(cur_dev->device->node_type) != RDMA_TRANSPORT_IB)
+		    !rdma_cap_ib_cm(cur_dev->device, 1))
 			continue;
 
 		if (!cma_dev)
@@ -2077,7 +2085,7 @@ port_found:
 		goto out;
 
 	id_priv->id.route.addr.dev_addr.dev_type =
-		(rdma_port_get_link_layer(cma_dev->device, p) == IB_LINK_LAYER_INFINIBAND) ?
+		(rdma_protocol_ib(cma_dev->device, p)) ?
 		ARPHRD_INFINIBAND : ARPHRD_ETHER;
 
 	rdma_addr_set_sgid(&id_priv->id.route.addr.dev_addr, &gid);
@@ -2554,18 +2562,15 @@ int rdma_listen(struct rdma_cm_id *id, int backlog)
 
 	id_priv->backlog = backlog;
 	if (id->device) {
-		switch (rdma_node_get_transport(id->device->node_type)) {
-		case RDMA_TRANSPORT_IB:
+		if (rdma_cap_ib_cm(id->device, 1)) {
 			ret = cma_ib_listen(id_priv);
 			if (ret)
 				goto err;
-			break;
-		case RDMA_TRANSPORT_IWARP:
+		} else if (rdma_cap_iw_cm(id->device, 1)) {
 			ret = cma_iw_listen(id_priv, backlog);
 			if (ret)
 				goto err;
-			break;
-		default:
+		} else {
 			ret = -ENOSYS;
 			goto err;
 		}
@@ -2857,6 +2862,7 @@ static int cma_connect_iw(struct rdma_id_private *id_priv,
 	if (IS_ERR(cm_id))
 		return PTR_ERR(cm_id);
 
+	cm_id->tos = id_priv->tos;
 	id_priv->cm_id.iw = cm_id;
 
 	memcpy(&cm_id->local_addr, cma_src_addr(id_priv),
@@ -2901,20 +2907,15 @@ int rdma_connect(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 		id_priv->srq = conn_param->srq;
 	}
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (id->qp_type == IB_QPT_UD)
 			ret = cma_resolve_ib_udp(id_priv, conn_param);
 		else
 			ret = cma_connect_ib(id_priv, conn_param);
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num))
 		ret = cma_connect_iw(id_priv, conn_param);
-		break;
-	default:
+	else
 		ret = -ENOSYS;
-		break;
-	}
 	if (ret)
 		goto err;
 
@@ -3017,8 +3018,7 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 		id_priv->srq = conn_param->srq;
 	}
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (id->qp_type == IB_QPT_UD) {
 			if (conn_param)
 				ret = cma_send_sidr_rep(id_priv, IB_SIDR_SUCCESS,
@@ -3034,14 +3034,10 @@ int rdma_accept(struct rdma_cm_id *id, struct rdma_conn_param *conn_param)
 			else
 				ret = cma_rep_recv(id_priv);
 		}
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num))
 		ret = cma_accept_iw(id_priv, conn_param);
-		break;
-	default:
+	else
 		ret = -ENOSYS;
-		break;
-	}
 
 	if (ret)
 		goto reject;
@@ -3085,8 +3081,7 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
 	if (!id_priv->cm_id.ib)
 		return -EINVAL;
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		if (id->qp_type == IB_QPT_UD)
 			ret = cma_send_sidr_rep(id_priv, IB_SIDR_REJECT, 0,
 						private_data, private_data_len);
@@ -3094,15 +3089,12 @@ int rdma_reject(struct rdma_cm_id *id, const void *private_data,
 			ret = ib_send_cm_rej(id_priv->cm_id.ib,
 					     IB_CM_REJ_CONSUMER_DEFINED, NULL,
 					     0, private_data, private_data_len);
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_reject(id_priv->cm_id.iw,
 				   private_data, private_data_len);
-		break;
-	default:
+	} else
 		ret = -ENOSYS;
-		break;
-	}
+
 	return ret;
 }
 EXPORT_SYMBOL(rdma_reject);
@@ -3116,22 +3108,18 @@ int rdma_disconnect(struct rdma_cm_id *id)
 	if (!id_priv->cm_id.ib)
 		return -EINVAL;
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
+	if (rdma_cap_ib_cm(id->device, id->port_num)) {
 		ret = cma_modify_qp_err(id_priv);
 		if (ret)
 			goto out;
 		/* Initiate or respond to a disconnect. */
 		if (ib_send_cm_dreq(id_priv->cm_id.ib, NULL, 0))
 			ib_send_cm_drep(id_priv->cm_id.ib, NULL, 0);
-		break;
-	case RDMA_TRANSPORT_IWARP:
+	} else if (rdma_cap_iw_cm(id->device, id->port_num)) {
 		ret = iw_cm_disconnect(id_priv->cm_id.iw, 0);
-		break;
-	default:
+	} else
 		ret = -EINVAL;
-		break;
-	}
+
 out:
 	return ret;
 }
@@ -3377,24 +3365,13 @@ int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
 	list_add(&mc->list, &id_priv->mc_list);
 	spin_unlock(&id_priv->lock);
 
-	switch (rdma_node_get_transport(id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
-		switch (rdma_port_get_link_layer(id->device, id->port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
-			ret = cma_join_ib_multicast(id_priv, mc);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
-			kref_init(&mc->mcref);
-			ret = cma_iboe_join_multicast(id_priv, mc);
-			break;
-		default:
-			ret = -EINVAL;
-		}
-		break;
-	default:
+	if (rdma_protocol_roce(id->device, id->port_num)) {
+		kref_init(&mc->mcref);
+		ret = cma_iboe_join_multicast(id_priv, mc);
+	} else if (rdma_cap_ib_mcast(id->device, id->port_num))
+		ret = cma_join_ib_multicast(id_priv, mc);
+	else
 		ret = -ENOSYS;
-		break;
-	}
 
 	if (ret) {
 		spin_lock_irq(&id_priv->lock);
@@ -3422,19 +3399,15 @@ void rdma_leave_multicast(struct rdma_cm_id *id, struct sockaddr *addr)
 				ib_detach_mcast(id->qp,
 						&mc->multicast.ib->rec.mgid,
 						be16_to_cpu(mc->multicast.ib->rec.mlid));
-			if (rdma_node_get_transport(id_priv->cma_dev->device->node_type) == RDMA_TRANSPORT_IB) {
-				switch (rdma_port_get_link_layer(id->device, id->port_num)) {
-				case IB_LINK_LAYER_INFINIBAND:
-					ib_sa_free_multicast(mc->multicast.ib);
-					kfree(mc);
-					break;
-				case IB_LINK_LAYER_ETHERNET:
-					kref_put(&mc->mcref, release_mc);
-					break;
-				default:
-					break;
-				}
-			}
+
+			BUG_ON(id_priv->cma_dev->device != id->device);
+
+			if (rdma_cap_ib_mcast(id->device, id->port_num)) {
+				ib_sa_free_multicast(mc->multicast.ib);
+				kfree(mc);
+			} else if (rdma_protocol_roce(id->device, id->port_num))
+				kref_put(&mc->mcref, release_mc);
+
 			return;
 		}
 	}

drivers/infiniband/core/device.c

@@ -92,7 +92,8 @@ static int ib_device_check_mandatory(struct ib_device *device)
 		IB_MANDATORY_FUNC(poll_cq),
 		IB_MANDATORY_FUNC(req_notify_cq),
 		IB_MANDATORY_FUNC(get_dma_mr),
-		IB_MANDATORY_FUNC(dereg_mr)
+		IB_MANDATORY_FUNC(dereg_mr),
+		IB_MANDATORY_FUNC(get_port_immutable)
 	};
 	int i;
 
@@ -151,18 +152,6 @@ static int alloc_name(char *name)
 	return 0;
 }
 
-static int start_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1;
-}
-
-
-static int end_port(struct ib_device *device)
-{
-	return (device->node_type == RDMA_NODE_IB_SWITCH) ?
-		0 : device->phys_port_cnt;
-}
-
 /**
  * ib_alloc_device - allocate an IB device struct
  * @size:size of structure to allocate
@@ -222,42 +211,49 @@ static int add_client_context(struct ib_device *device, struct ib_client *client
 	return 0;
 }
 
-static int read_port_table_lengths(struct ib_device *device)
+static int verify_immutable(const struct ib_device *dev, u8 port)
 {
-	struct ib_port_attr *tprops = NULL;
-	int num_ports, ret = -ENOMEM;
-	u8 port_index;
-
-	tprops = kmalloc(sizeof *tprops, GFP_KERNEL);
-	if (!tprops)
-		goto out;
-
-	num_ports = end_port(device) - start_port(device) + 1;
+	return WARN_ON(!rdma_cap_ib_mad(dev, port) &&
+			    rdma_max_mad_size(dev, port) != 0);
+}
 
-	device->pkey_tbl_len = kmalloc(sizeof *device->pkey_tbl_len * num_ports,
-				       GFP_KERNEL);
-	device->gid_tbl_len = kmalloc(sizeof *device->gid_tbl_len * num_ports,
-				      GFP_KERNEL);
-	if (!device->pkey_tbl_len || !device->gid_tbl_len)
+static int read_port_immutable(struct ib_device *device)
+{
+	int ret = -ENOMEM;
+	u8 start_port = rdma_start_port(device);
+	u8 end_port = rdma_end_port(device);
+	u8 port;
+
+	/**
+	 * device->port_immutable is indexed directly by the port number to make
+	 * access to this data as efficient as possible.
+	 *
+	 * Therefore port_immutable is declared as a 1 based array with
+	 * potential empty slots at the beginning.
+	 */
+	device->port_immutable = kzalloc(sizeof(*device->port_immutable)
+					 * (end_port + 1),
+					 GFP_KERNEL);
+	if (!device->port_immutable)
 		goto err;
 
-	for (port_index = 0; port_index < num_ports; ++port_index) {
-		ret = ib_query_port(device, port_index + start_port(device),
-					tprops);
+	for (port = start_port; port <= end_port; ++port) {
+		ret = device->get_port_immutable(device, port,
+						 &device->port_immutable[port]);
 		if (ret)
 			goto err;
-		device->pkey_tbl_len[port_index] = tprops->pkey_tbl_len;
-		device->gid_tbl_len[port_index]  = tprops->gid_tbl_len;
+
+		if (verify_immutable(device, port)) {
+			ret = -EINVAL;
+			goto err;
+		}
 	}
 
 	ret = 0;
 	goto out;
-
 err:
-	kfree(device->gid_tbl_len);
-	kfree(device->pkey_tbl_len);
+	kfree(device->port_immutable);
 out:
-	kfree(tprops);
 	return ret;
 }
 
@@ -294,9 +290,9 @@ int ib_register_device(struct ib_device *device,
 	spin_lock_init(&device->event_handler_lock);
 	spin_lock_init(&device->client_data_lock);
 
-	ret = read_port_table_lengths(device);
+	ret = read_port_immutable(device);
 	if (ret) {
-		printk(KERN_WARNING "Couldn't create table lengths cache for device %s\n",
+		printk(KERN_WARNING "Couldn't create per port immutable data %s\n",
 		       device->name);
 		goto out;
 	}
@@ -305,8 +301,7 @@ int ib_register_device(struct ib_device *device,
 	if (ret) {
 		printk(KERN_WARNING "Couldn't register device %s with driver model\n",
 		       device->name);
-		kfree(device->gid_tbl_len);
-		kfree(device->pkey_tbl_len);
+		kfree(device->port_immutable);
 		goto out;
 	}
 
@@ -348,9 +343,6 @@ void ib_unregister_device(struct ib_device *device)
 
 	list_del(&device->core_list);
 
-	kfree(device->gid_tbl_len);
-	kfree(device->pkey_tbl_len);
-
 	mutex_unlock(&device_mutex);
 
 	ib_device_unregister_sysfs(device);
@@ -558,7 +550,11 @@ EXPORT_SYMBOL(ib_dispatch_event);
 int ib_query_device(struct ib_device *device,
 		    struct ib_device_attr *device_attr)
 {
-	return device->query_device(device, device_attr);
+	struct ib_udata uhw = {.outlen = 0, .inlen = 0};
+
+	memset(device_attr, 0, sizeof(*device_attr));
+
+	return device->query_device(device, device_attr, &uhw);
 }
 EXPORT_SYMBOL(ib_query_device);
 
@@ -575,7 +571,7 @@ int ib_query_port(struct ib_device *device,
 		  u8 port_num,
 		  struct ib_port_attr *port_attr)
 {
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	return device->query_port(device, port_num, port_attr);
@@ -653,7 +649,7 @@ int ib_modify_port(struct ib_device *device,
 	if (!device->modify_port)
 		return -ENOSYS;
 
-	if (port_num < start_port(device) || port_num > end_port(device))
+	if (port_num < rdma_start_port(device) || port_num > rdma_end_port(device))
 		return -EINVAL;
 
 	return device->modify_port(device, port_num, port_modify_mask,
@@ -676,8 +672,8 @@ int ib_find_gid(struct ib_device *device, union ib_gid *gid,
 	union ib_gid tmp_gid;
 	int ret, port, i;
 
-	for (port = start_port(device); port <= end_port(device); ++port) {
-		for (i = 0; i < device->gid_tbl_len[port - start_port(device)]; ++i) {
+	for (port = rdma_start_port(device); port <= rdma_end_port(device); ++port) {
+		for (i = 0; i < device->port_immutable[port].gid_tbl_len; ++i) {
 			ret = ib_query_gid(device, port, i, &tmp_gid);
 			if (ret)
 				return ret;
@@ -709,7 +705,7 @@ int ib_find_pkey(struct ib_device *device,
 	u16 tmp_pkey;
 	int partial_ix = -1;
 
-	for (i = 0; i < device->pkey_tbl_len[port_num - start_port(device)]; ++i) {
+	for (i = 0; i < device->port_immutable[port_num].pkey_tbl_len; ++i) {
 		ret = ib_query_pkey(device, port_num, i, &tmp_pkey);
 		if (ret)
 			return ret;

drivers/infiniband/core/mad.c

@@ -3,6 +3,7 @@
  * Copyright (c) 2005 Intel Corporation.  All rights reserved.
  * Copyright (c) 2005 Mellanox Technologies Ltd.  All rights reserved.
  * Copyright (c) 2009 HNR Consulting. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation.  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
@@ -44,6 +45,7 @@
 #include "mad_priv.h"
 #include "mad_rmpp.h"
 #include "smi.h"
+#include "opa_smi.h"
 #include "agent.h"
 
 MODULE_LICENSE("Dual BSD/GPL");
@@ -59,8 +61,6 @@ MODULE_PARM_DESC(send_queue_size, "Size of send queue in number of work requests
 module_param_named(recv_queue_size, mad_recvq_size, int, 0444);
 MODULE_PARM_DESC(recv_queue_size, "Size of receive queue in number of work requests");
 
-static struct kmem_cache *ib_mad_cache;
-
 static struct list_head ib_mad_port_list;
 static u32 ib_mad_client_id = 0;
 
@@ -73,7 +73,7 @@ static int method_in_use(struct ib_mad_mgmt_method_table **method,
 static void remove_mad_reg_req(struct ib_mad_agent_private *priv);
 static struct ib_mad_agent_private *find_mad_agent(
 					struct ib_mad_port_private *port_priv,
-					struct ib_mad *mad);
+					const struct ib_mad_hdr *mad);
 static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 				    struct ib_mad_private *mad);
 static void cancel_mads(struct ib_mad_agent_private *mad_agent_priv);
@@ -179,12 +179,12 @@ static int is_vendor_method_in_use(
 	return 0;
 }
 
-int ib_response_mad(struct ib_mad *mad)
+int ib_response_mad(const struct ib_mad_hdr *hdr)
 {
-	return ((mad->mad_hdr.method & IB_MGMT_METHOD_RESP) ||
-		(mad->mad_hdr.method == IB_MGMT_METHOD_TRAP_REPRESS) ||
-		((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_BM) &&
-		 (mad->mad_hdr.attr_mod & IB_BM_ATTR_MOD_RESP)));
+	return ((hdr->method & IB_MGMT_METHOD_RESP) ||
+		(hdr->method == IB_MGMT_METHOD_TRAP_REPRESS) ||
+		((hdr->mgmt_class == IB_MGMT_CLASS_BM) &&
+		 (hdr->attr_mod & IB_BM_ATTR_MOD_RESP)));
 }
 EXPORT_SYMBOL(ib_response_mad);
 
@@ -717,6 +717,32 @@ static void build_smp_wc(struct ib_qp *qp,
 	wc->port_num = port_num;
 }
 
+static size_t mad_priv_size(const struct ib_mad_private *mp)
+{
+	return sizeof(struct ib_mad_private) + mp->mad_size;
+}
+
+static struct ib_mad_private *alloc_mad_private(size_t mad_size, gfp_t flags)
+{
+	size_t size = sizeof(struct ib_mad_private) + mad_size;
+	struct ib_mad_private *ret = kzalloc(size, flags);
+
+	if (ret)
+		ret->mad_size = mad_size;
+
+	return ret;
+}
+
+static size_t port_mad_size(const struct ib_mad_port_private *port_priv)
+{
+	return rdma_max_mad_size(port_priv->device, port_priv->port_num);
+}
+
+static size_t mad_priv_dma_size(const struct ib_mad_private *mp)
+{
+	return sizeof(struct ib_grh) + mp->mad_size;
+}
+
 /*
  * Return 0 if SMP is to be sent
  * Return 1 if SMP was consumed locally (whether or not solicited)
@@ -727,6 +753,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 {
 	int ret = 0;
 	struct ib_smp *smp = mad_send_wr->send_buf.mad;
+	struct opa_smp *opa_smp = (struct opa_smp *)smp;
 	unsigned long flags;
 	struct ib_mad_local_private *local;
 	struct ib_mad_private *mad_priv;
@@ -736,6 +763,11 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	u8 port_num;
 	struct ib_wc mad_wc;
 	struct ib_send_wr *send_wr = &mad_send_wr->send_wr;
+	size_t mad_size = port_mad_size(mad_agent_priv->qp_info->port_priv);
+	u16 out_mad_pkey_index = 0;
+	u16 drslid;
+	bool opa = rdma_cap_opa_mad(mad_agent_priv->qp_info->port_priv->device,
+				    mad_agent_priv->qp_info->port_priv->port_num);
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH &&
 	    smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
@@ -749,19 +781,48 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	 * If we are at the start of the LID routed part, don't update the
 	 * hop_ptr or hop_cnt.  See section 14.2.2, Vol 1 IB spec.
 	 */
-	if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) ==
-	     IB_LID_PERMISSIVE &&
-	     smi_handle_dr_smp_send(smp, device->node_type, port_num) ==
-	     IB_SMI_DISCARD) {
-		ret = -EINVAL;
-		dev_err(&device->dev, "Invalid directed route\n");
-		goto out;
-	}
+	if (opa && smp->class_version == OPA_SMP_CLASS_VERSION) {
+		u32 opa_drslid;
+
+		if ((opa_get_smp_direction(opa_smp)
+		     ? opa_smp->route.dr.dr_dlid : opa_smp->route.dr.dr_slid) ==
+		     OPA_LID_PERMISSIVE &&
+		     opa_smi_handle_dr_smp_send(opa_smp, device->node_type,
+						port_num) == IB_SMI_DISCARD) {
+			ret = -EINVAL;
+			dev_err(&device->dev, "OPA Invalid directed route\n");
+			goto out;
+		}
+		opa_drslid = be32_to_cpu(opa_smp->route.dr.dr_slid);
+		if (opa_drslid != OPA_LID_PERMISSIVE &&
+		    opa_drslid & 0xffff0000) {
+			ret = -EINVAL;
+			dev_err(&device->dev, "OPA Invalid dr_slid 0x%x\n",
+			       opa_drslid);
+			goto out;
+		}
+		drslid = (u16)(opa_drslid & 0x0000ffff);
 
-	/* Check to post send on QP or process locally */
-	if (smi_check_local_smp(smp, device) == IB_SMI_DISCARD &&
-	    smi_check_local_returning_smp(smp, device) == IB_SMI_DISCARD)
-		goto out;
+		/* Check to post send on QP or process locally */
+		if (opa_smi_check_local_smp(opa_smp, device) == IB_SMI_DISCARD &&
+		    opa_smi_check_local_returning_smp(opa_smp, device) == IB_SMI_DISCARD)
+			goto out;
+	} else {
+		if ((ib_get_smp_direction(smp) ? smp->dr_dlid : smp->dr_slid) ==
+		     IB_LID_PERMISSIVE &&
+		     smi_handle_dr_smp_send(smp, device->node_type, port_num) ==
+		     IB_SMI_DISCARD) {
+			ret = -EINVAL;
+			dev_err(&device->dev, "Invalid directed route\n");
+			goto out;
+		}
+		drslid = be16_to_cpu(smp->dr_slid);
+
+		/* Check to post send on QP or process locally */
+		if (smi_check_local_smp(smp, device) == IB_SMI_DISCARD &&
+		    smi_check_local_returning_smp(smp, device) == IB_SMI_DISCARD)
+			goto out;
+	}
 
 	local = kmalloc(sizeof *local, GFP_ATOMIC);
 	if (!local) {
@@ -771,7 +832,7 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	}
 	local->mad_priv = NULL;
 	local->recv_mad_agent = NULL;
-	mad_priv = kmem_cache_alloc(ib_mad_cache, GFP_ATOMIC);
+	mad_priv = alloc_mad_private(mad_size, GFP_ATOMIC);
 	if (!mad_priv) {
 		ret = -ENOMEM;
 		dev_err(&device->dev, "No memory for local response MAD\n");
@@ -780,18 +841,25 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 	}
 
 	build_smp_wc(mad_agent_priv->agent.qp,
-		     send_wr->wr_id, be16_to_cpu(smp->dr_slid),
+		     send_wr->wr_id, drslid,
 		     send_wr->wr.ud.pkey_index,
 		     send_wr->wr.ud.port_num, &mad_wc);
 
+	if (opa && smp->base_version == OPA_MGMT_BASE_VERSION) {
+		mad_wc.byte_len = mad_send_wr->send_buf.hdr_len
+					+ mad_send_wr->send_buf.data_len
+					+ sizeof(struct ib_grh);
+	}
+
 	/* No GRH for DR SMP */
 	ret = device->process_mad(device, 0, port_num, &mad_wc, NULL,
-				  (struct ib_mad *)smp,
-				  (struct ib_mad *)&mad_priv->mad);
+				  (const struct ib_mad_hdr *)smp, mad_size,
+				  (struct ib_mad_hdr *)mad_priv->mad,
+				  &mad_size, &out_mad_pkey_index);
 	switch (ret)
 	{
 	case IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY:
-		if (ib_response_mad(&mad_priv->mad.mad) &&
+		if (ib_response_mad((const struct ib_mad_hdr *)mad_priv->mad) &&
 		    mad_agent_priv->agent.recv_handler) {
 			local->mad_priv = mad_priv;
 			local->recv_mad_agent = mad_agent_priv;
@@ -801,39 +869,43 @@ static int handle_outgoing_dr_smp(struct ib_mad_agent_private *mad_agent_priv,
 			 */
 			atomic_inc(&mad_agent_priv->refcount);
 		} else
-			kmem_cache_free(ib_mad_cache, mad_priv);
+			kfree(mad_priv);
 		break;
 	case IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED:
-		kmem_cache_free(ib_mad_cache, mad_priv);
+		kfree(mad_priv);
 		break;
 	case IB_MAD_RESULT_SUCCESS:
 		/* Treat like an incoming receive MAD */
 		port_priv = ib_get_mad_port(mad_agent_priv->agent.device,
 					    mad_agent_priv->agent.port_num);
 		if (port_priv) {
-			memcpy(&mad_priv->mad.mad, smp, sizeof(struct ib_mad));
+			memcpy(mad_priv->mad, smp, mad_priv->mad_size);
 			recv_mad_agent = find_mad_agent(port_priv,
-						        &mad_priv->mad.mad);
+						        (const struct ib_mad_hdr *)mad_priv->mad);
 		}
 		if (!port_priv || !recv_mad_agent) {
 			/*
 			 * No receiving agent so drop packet and
 			 * generate send completion.
 			 */
-			kmem_cache_free(ib_mad_cache, mad_priv);
+			kfree(mad_priv);
 			break;
 		}
 		local->mad_priv = mad_priv;
 		local->recv_mad_agent = recv_mad_agent;
 		break;
 	default:
-		kmem_cache_free(ib_mad_cache, mad_priv);
+		kfree(mad_priv);
 		kfree(local);
 		ret = -EINVAL;
 		goto out;
 	}
 
 	local->mad_send_wr = mad_send_wr;
+	if (opa) {
+		local->mad_send_wr->send_wr.wr.ud.pkey_index = out_mad_pkey_index;
+		local->return_wc_byte_len = mad_size;
+	}
 	/* Reference MAD agent until send side of local completion handled */
 	atomic_inc(&mad_agent_priv->refcount);
 	/* Queue local completion to local list */
@@ -847,11 +919,11 @@ out:
 	return ret;
 }
 
-static int get_pad_size(int hdr_len, int data_len)
+static int get_pad_size(int hdr_len, int data_len, size_t mad_size)
 {
 	int seg_size, pad;
 
-	seg_size = sizeof(struct ib_mad) - hdr_len;
+	seg_size = mad_size - hdr_len;
 	if (data_len && seg_size) {
 		pad = seg_size - data_len % seg_size;
 		return pad == seg_size ? 0 : pad;
@@ -870,14 +942,15 @@ static void free_send_rmpp_list(struct ib_mad_send_wr_private *mad_send_wr)
 }
 
 static int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr,
-				gfp_t gfp_mask)
+				size_t mad_size, gfp_t gfp_mask)
 {
 	struct ib_mad_send_buf *send_buf = &send_wr->send_buf;
 	struct ib_rmpp_mad *rmpp_mad = send_buf->mad;
 	struct ib_rmpp_segment *seg = NULL;
 	int left, seg_size, pad;
 
-	send_buf->seg_size = sizeof (struct ib_mad) - send_buf->hdr_len;
+	send_buf->seg_size = mad_size - send_buf->hdr_len;
+	send_buf->seg_rmpp_size = mad_size - IB_MGMT_RMPP_HDR;
 	seg_size = send_buf->seg_size;
 	pad = send_wr->pad;
 
@@ -910,7 +983,7 @@ static int alloc_send_rmpp_list(struct ib_mad_send_wr_private *send_wr,
 	return 0;
 }
 
-int ib_mad_kernel_rmpp_agent(struct ib_mad_agent *agent)
+int ib_mad_kernel_rmpp_agent(const struct ib_mad_agent *agent)
 {
 	return agent->rmpp_version && !(agent->flags & IB_MAD_USER_RMPP);
 }
@@ -920,26 +993,37 @@ struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
 					    u32 remote_qpn, u16 pkey_index,
 					    int rmpp_active,
 					    int hdr_len, int data_len,
-					    gfp_t gfp_mask)
+					    gfp_t gfp_mask,
+					    u8 base_version)
 {
 	struct ib_mad_agent_private *mad_agent_priv;
 	struct ib_mad_send_wr_private *mad_send_wr;
 	int pad, message_size, ret, size;
 	void *buf;
+	size_t mad_size;
+	bool opa;
 
 	mad_agent_priv = container_of(mad_agent, struct ib_mad_agent_private,
 				      agent);
-	pad = get_pad_size(hdr_len, data_len);
+
+	opa = rdma_cap_opa_mad(mad_agent->device, mad_agent->port_num);
+
+	if (opa && base_version == OPA_MGMT_BASE_VERSION)
+		mad_size = sizeof(struct opa_mad);
+	else
+		mad_size = sizeof(struct ib_mad);
+
+	pad = get_pad_size(hdr_len, data_len, mad_size);
 	message_size = hdr_len + data_len + pad;
 
 	if (ib_mad_kernel_rmpp_agent(mad_agent)) {
-		if (!rmpp_active && message_size > sizeof(struct ib_mad))
+		if (!rmpp_active && message_size > mad_size)
 			return ERR_PTR(-EINVAL);
 	} else
-		if (rmpp_active || message_size > sizeof(struct ib_mad))
+		if (rmpp_active || message_size > mad_size)
 			return ERR_PTR(-EINVAL);
 
-	size = rmpp_active ? hdr_len : sizeof(struct ib_mad);
+	size = rmpp_active ? hdr_len : mad_size;
 	buf = kzalloc(sizeof *mad_send_wr + size, gfp_mask);
 	if (!buf)
 		return ERR_PTR(-ENOMEM);
@@ -954,7 +1038,14 @@ struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
 	mad_send_wr->mad_agent_priv = mad_agent_priv;
 	mad_send_wr->sg_list[0].length = hdr_len;
 	mad_send_wr->sg_list[0].lkey = mad_agent->mr->lkey;
-	mad_send_wr->sg_list[1].length = sizeof(struct ib_mad) - hdr_len;
+
+	/* OPA MADs don't have to be the full 2048 bytes */
+	if (opa && base_version == OPA_MGMT_BASE_VERSION &&
+	    data_len < mad_size - hdr_len)
+		mad_send_wr->sg_list[1].length = data_len;
+	else
+		mad_send_wr->sg_list[1].length = mad_size - hdr_len;
+
 	mad_send_wr->sg_list[1].lkey = mad_agent->mr->lkey;
 
 	mad_send_wr->send_wr.wr_id = (unsigned long) mad_send_wr;
@@ -967,7 +1058,7 @@ struct ib_mad_send_buf * ib_create_send_mad(struct ib_mad_agent *mad_agent,
 	mad_send_wr->send_wr.wr.ud.pkey_index = pkey_index;
 
 	if (rmpp_active) {
-		ret = alloc_send_rmpp_list(mad_send_wr, gfp_mask);
+		ret = alloc_send_rmpp_list(mad_send_wr, mad_size, gfp_mask);
 		if (ret) {
 			kfree(buf);
 			return ERR_PTR(ret);
@@ -1237,7 +1328,7 @@ void ib_free_recv_mad(struct ib_mad_recv_wc *mad_recv_wc)
 					    recv_wc);
 		priv = container_of(mad_priv_hdr, struct ib_mad_private,
 				    header);
-		kmem_cache_free(ib_mad_cache, priv);
+		kfree(priv);
 	}
 }
 EXPORT_SYMBOL(ib_free_recv_mad);
@@ -1324,7 +1415,7 @@ static int check_vendor_class(struct ib_mad_mgmt_vendor_class *vendor_class)
 }
 
 static int find_vendor_oui(struct ib_mad_mgmt_vendor_class *vendor_class,
-			   char *oui)
+			   const char *oui)
 {
 	int i;
 
@@ -1622,13 +1713,13 @@ out:
 
 static struct ib_mad_agent_private *
 find_mad_agent(struct ib_mad_port_private *port_priv,
-	       struct ib_mad *mad)
+	       const struct ib_mad_hdr *mad_hdr)
 {
 	struct ib_mad_agent_private *mad_agent = NULL;
 	unsigned long flags;
 
 	spin_lock_irqsave(&port_priv->reg_lock, flags);
-	if (ib_response_mad(mad)) {
+	if (ib_response_mad(mad_hdr)) {
 		u32 hi_tid;
 		struct ib_mad_agent_private *entry;
 
@@ -1636,7 +1727,7 @@ find_mad_agent(struct ib_mad_port_private *port_priv,
 		 * Routing is based on high 32 bits of transaction ID
 		 * of MAD.
 		 */
-		hi_tid = be64_to_cpu(mad->mad_hdr.tid) >> 32;
+		hi_tid = be64_to_cpu(mad_hdr->tid) >> 32;
 		list_for_each_entry(entry, &port_priv->agent_list, agent_list) {
 			if (entry->agent.hi_tid == hi_tid) {
 				mad_agent = entry;
@@ -1648,45 +1739,45 @@ find_mad_agent(struct ib_mad_port_private *port_priv,
 		struct ib_mad_mgmt_method_table *method;
 		struct ib_mad_mgmt_vendor_class_table *vendor;
 		struct ib_mad_mgmt_vendor_class *vendor_class;
-		struct ib_vendor_mad *vendor_mad;
+		const struct ib_vendor_mad *vendor_mad;
 		int index;
 
 		/*
 		 * Routing is based on version, class, and method
 		 * For "newer" vendor MADs, also based on OUI
 		 */
-		if (mad->mad_hdr.class_version >= MAX_MGMT_VERSION)
+		if (mad_hdr->class_version >= MAX_MGMT_VERSION)
 			goto out;
-		if (!is_vendor_class(mad->mad_hdr.mgmt_class)) {
+		if (!is_vendor_class(mad_hdr->mgmt_class)) {
 			class = port_priv->version[
-					mad->mad_hdr.class_version].class;
+					mad_hdr->class_version].class;
 			if (!class)
 				goto out;
-			if (convert_mgmt_class(mad->mad_hdr.mgmt_class) >=
+			if (convert_mgmt_class(mad_hdr->mgmt_class) >=
 			    IB_MGMT_MAX_METHODS)
 				goto out;
 			method = class->method_table[convert_mgmt_class(
-							mad->mad_hdr.mgmt_class)];
+							mad_hdr->mgmt_class)];
 			if (method)
-				mad_agent = method->agent[mad->mad_hdr.method &
+				mad_agent = method->agent[mad_hdr->method &
 							  ~IB_MGMT_METHOD_RESP];
 		} else {
 			vendor = port_priv->version[
-					mad->mad_hdr.class_version].vendor;
+					mad_hdr->class_version].vendor;
 			if (!vendor)
 				goto out;
 			vendor_class = vendor->vendor_class[vendor_class_index(
-						mad->mad_hdr.mgmt_class)];
+						mad_hdr->mgmt_class)];
 			if (!vendor_class)
 				goto out;
 			/* Find matching OUI */
-			vendor_mad = (struct ib_vendor_mad *)mad;
+			vendor_mad = (const struct ib_vendor_mad *)mad_hdr;
 			index = find_vendor_oui(vendor_class, vendor_mad->oui);
 			if (index == -1)
 				goto out;
 			method = vendor_class->method_table[index];
 			if (method) {
-				mad_agent = method->agent[mad->mad_hdr.method &
+				mad_agent = method->agent[mad_hdr->method &
 							  ~IB_MGMT_METHOD_RESP];
 			}
 		}
@@ -1708,20 +1799,24 @@ out:
 	return mad_agent;
 }
 
-static int validate_mad(struct ib_mad *mad, u32 qp_num)
+static int validate_mad(const struct ib_mad_hdr *mad_hdr,
+			const struct ib_mad_qp_info *qp_info,
+			bool opa)
 {
 	int valid = 0;
+	u32 qp_num = qp_info->qp->qp_num;
 
 	/* Make sure MAD base version is understood */
-	if (mad->mad_hdr.base_version != IB_MGMT_BASE_VERSION) {
-		pr_err("MAD received with unsupported base version %d\n",
-			mad->mad_hdr.base_version);
+	if (mad_hdr->base_version != IB_MGMT_BASE_VERSION &&
+	    (!opa || mad_hdr->base_version != OPA_MGMT_BASE_VERSION)) {
+		pr_err("MAD received with unsupported base version %d %s\n",
+		       mad_hdr->base_version, opa ? "(opa)" : "");
 		goto out;
 	}
 
 	/* Filter SMI packets sent to other than QP0 */
-	if ((mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED) ||
-	    (mad->mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)) {
+	if ((mad_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_LID_ROUTED) ||
+	    (mad_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)) {
 		if (qp_num == 0)
 			valid = 1;
 	} else {
@@ -1734,8 +1829,8 @@ out:
 	return valid;
 }
 
-static int is_data_mad(struct ib_mad_agent_private *mad_agent_priv,
-		       struct ib_mad_hdr *mad_hdr)
+static int is_rmpp_data_mad(const struct ib_mad_agent_private *mad_agent_priv,
+			    const struct ib_mad_hdr *mad_hdr)
 {
 	struct ib_rmpp_mad *rmpp_mad;
 
@@ -1747,16 +1842,16 @@ static int is_data_mad(struct ib_mad_agent_private *mad_agent_priv,
 		(rmpp_mad->rmpp_hdr.rmpp_type == IB_MGMT_RMPP_TYPE_DATA);
 }
 
-static inline int rcv_has_same_class(struct ib_mad_send_wr_private *wr,
-				     struct ib_mad_recv_wc *rwc)
+static inline int rcv_has_same_class(const struct ib_mad_send_wr_private *wr,
+				     const struct ib_mad_recv_wc *rwc)
 {
-	return ((struct ib_mad *)(wr->send_buf.mad))->mad_hdr.mgmt_class ==
+	return ((struct ib_mad_hdr *)(wr->send_buf.mad))->mgmt_class ==
 		rwc->recv_buf.mad->mad_hdr.mgmt_class;
 }
 
-static inline int rcv_has_same_gid(struct ib_mad_agent_private *mad_agent_priv,
-				   struct ib_mad_send_wr_private *wr,
-				   struct ib_mad_recv_wc *rwc )
+static inline int rcv_has_same_gid(const struct ib_mad_agent_private *mad_agent_priv,
+				   const struct ib_mad_send_wr_private *wr,
+				   const struct ib_mad_recv_wc *rwc )
 {
 	struct ib_ah_attr attr;
 	u8 send_resp, rcv_resp;
@@ -1765,8 +1860,8 @@ static inline int rcv_has_same_gid(struct ib_mad_agent_private *mad_agent_priv,
 	u8 port_num = mad_agent_priv->agent.port_num;
 	u8 lmc;
 
-	send_resp = ib_response_mad((struct ib_mad *)wr->send_buf.mad);
-	rcv_resp = ib_response_mad(rwc->recv_buf.mad);
+	send_resp = ib_response_mad((struct ib_mad_hdr *)wr->send_buf.mad);
+	rcv_resp = ib_response_mad(&rwc->recv_buf.mad->mad_hdr);
 
 	if (send_resp == rcv_resp)
 		/* both requests, or both responses. GIDs different */
@@ -1811,22 +1906,22 @@ static inline int is_direct(u8 class)
 }
 
 struct ib_mad_send_wr_private*
-ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv,
-		 struct ib_mad_recv_wc *wc)
+ib_find_send_mad(const struct ib_mad_agent_private *mad_agent_priv,
+		 const struct ib_mad_recv_wc *wc)
 {
 	struct ib_mad_send_wr_private *wr;
-	struct ib_mad *mad;
+	const struct ib_mad_hdr *mad_hdr;
 
-	mad = (struct ib_mad *)wc->recv_buf.mad;
+	mad_hdr = &wc->recv_buf.mad->mad_hdr;
 
 	list_for_each_entry(wr, &mad_agent_priv->wait_list, agent_list) {
-		if ((wr->tid == mad->mad_hdr.tid) &&
+		if ((wr->tid == mad_hdr->tid) &&
 		    rcv_has_same_class(wr, wc) &&
 		    /*
 		     * Don't check GID for direct routed MADs.
 		     * These might have permissive LIDs.
 		     */
-		    (is_direct(wc->recv_buf.mad->mad_hdr.mgmt_class) ||
+		    (is_direct(mad_hdr->mgmt_class) ||
 		     rcv_has_same_gid(mad_agent_priv, wr, wc)))
 			return (wr->status == IB_WC_SUCCESS) ? wr : NULL;
 	}
@@ -1836,15 +1931,15 @@ ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv,
 	 * been notified that the send has completed
 	 */
 	list_for_each_entry(wr, &mad_agent_priv->send_list, agent_list) {
-		if (is_data_mad(mad_agent_priv, wr->send_buf.mad) &&
-		    wr->tid == mad->mad_hdr.tid &&
+		if (is_rmpp_data_mad(mad_agent_priv, wr->send_buf.mad) &&
+		    wr->tid == mad_hdr->tid &&
 		    wr->timeout &&
 		    rcv_has_same_class(wr, wc) &&
 		    /*
 		     * Don't check GID for direct routed MADs.
 		     * These might have permissive LIDs.
 		     */
-		    (is_direct(wc->recv_buf.mad->mad_hdr.mgmt_class) ||
+		    (is_direct(mad_hdr->mgmt_class) ||
 		     rcv_has_same_gid(mad_agent_priv, wr, wc)))
 			/* Verify request has not been canceled */
 			return (wr->status == IB_WC_SUCCESS) ? wr : NULL;
@@ -1879,7 +1974,7 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 	}
 
 	/* Complete corresponding request */
-	if (ib_response_mad(mad_recv_wc->recv_buf.mad)) {
+	if (ib_response_mad(&mad_recv_wc->recv_buf.mad->mad_hdr)) {
 		spin_lock_irqsave(&mad_agent_priv->lock, flags);
 		mad_send_wr = ib_find_send_mad(mad_agent_priv, mad_recv_wc);
 		if (!mad_send_wr) {
@@ -1924,26 +2019,163 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
 	}
 }
 
-static bool generate_unmatched_resp(struct ib_mad_private *recv,
-				    struct ib_mad_private *response)
+static enum smi_action handle_ib_smi(const struct ib_mad_port_private *port_priv,
+				     const struct ib_mad_qp_info *qp_info,
+				     const struct ib_wc *wc,
+				     int port_num,
+				     struct ib_mad_private *recv,
+				     struct ib_mad_private *response)
+{
+	enum smi_forward_action retsmi;
+	struct ib_smp *smp = (struct ib_smp *)recv->mad;
+
+	if (smi_handle_dr_smp_recv(smp,
+				   port_priv->device->node_type,
+				   port_num,
+				   port_priv->device->phys_port_cnt) ==
+				   IB_SMI_DISCARD)
+		return IB_SMI_DISCARD;
+
+	retsmi = smi_check_forward_dr_smp(smp);
+	if (retsmi == IB_SMI_LOCAL)
+		return IB_SMI_HANDLE;
+
+	if (retsmi == IB_SMI_SEND) { /* don't forward */
+		if (smi_handle_dr_smp_send(smp,
+					   port_priv->device->node_type,
+					   port_num) == IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+
+		if (smi_check_local_smp(smp, port_priv->device) == IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+		/* forward case for switches */
+		memcpy(response, recv, mad_priv_size(response));
+		response->header.recv_wc.wc = &response->header.wc;
+		response->header.recv_wc.recv_buf.mad = (struct ib_mad *)response->mad;
+		response->header.recv_wc.recv_buf.grh = &response->grh;
+
+		agent_send_response((const struct ib_mad_hdr *)response->mad,
+				    &response->grh, wc,
+				    port_priv->device,
+				    smi_get_fwd_port(smp),
+				    qp_info->qp->qp_num,
+				    response->mad_size,
+				    false);
+
+		return IB_SMI_DISCARD;
+	}
+	return IB_SMI_HANDLE;
+}
+
+static bool generate_unmatched_resp(const struct ib_mad_private *recv,
+				    struct ib_mad_private *response,
+				    size_t *resp_len, bool opa)
 {
-	if (recv->mad.mad.mad_hdr.method == IB_MGMT_METHOD_GET ||
-	    recv->mad.mad.mad_hdr.method == IB_MGMT_METHOD_SET) {
-		memcpy(response, recv, sizeof *response);
+	const struct ib_mad_hdr *recv_hdr = (const struct ib_mad_hdr *)recv->mad;
+	struct ib_mad_hdr *resp_hdr = (struct ib_mad_hdr *)response->mad;
+
+	if (recv_hdr->method == IB_MGMT_METHOD_GET ||
+	    recv_hdr->method == IB_MGMT_METHOD_SET) {
+		memcpy(response, recv, mad_priv_size(response));
 		response->header.recv_wc.wc = &response->header.wc;
-		response->header.recv_wc.recv_buf.mad = &response->mad.mad;
+		response->header.recv_wc.recv_buf.mad = (struct ib_mad *)response->mad;
 		response->header.recv_wc.recv_buf.grh = &response->grh;
-		response->mad.mad.mad_hdr.method = IB_MGMT_METHOD_GET_RESP;
-		response->mad.mad.mad_hdr.status =
-			cpu_to_be16(IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD_ATTRIB);
-		if (recv->mad.mad.mad_hdr.mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
-			response->mad.mad.mad_hdr.status |= IB_SMP_DIRECTION;
+		resp_hdr->method = IB_MGMT_METHOD_GET_RESP;
+		resp_hdr->status = cpu_to_be16(IB_MGMT_MAD_STATUS_UNSUPPORTED_METHOD_ATTRIB);
+		if (recv_hdr->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+			resp_hdr->status |= IB_SMP_DIRECTION;
+
+		if (opa && recv_hdr->base_version == OPA_MGMT_BASE_VERSION) {
+			if (recv_hdr->mgmt_class ==
+			    IB_MGMT_CLASS_SUBN_LID_ROUTED ||
+			    recv_hdr->mgmt_class ==
+			    IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+				*resp_len = opa_get_smp_header_size(
+							(struct opa_smp *)recv->mad);
+			else
+				*resp_len = sizeof(struct ib_mad_hdr);
+		}
 
 		return true;
 	} else {
 		return false;
 	}
 }
+
+static enum smi_action
+handle_opa_smi(struct ib_mad_port_private *port_priv,
+	       struct ib_mad_qp_info *qp_info,
+	       struct ib_wc *wc,
+	       int port_num,
+	       struct ib_mad_private *recv,
+	       struct ib_mad_private *response)
+{
+	enum smi_forward_action retsmi;
+	struct opa_smp *smp = (struct opa_smp *)recv->mad;
+
+	if (opa_smi_handle_dr_smp_recv(smp,
+				   port_priv->device->node_type,
+				   port_num,
+				   port_priv->device->phys_port_cnt) ==
+				   IB_SMI_DISCARD)
+		return IB_SMI_DISCARD;
+
+	retsmi = opa_smi_check_forward_dr_smp(smp);
+	if (retsmi == IB_SMI_LOCAL)
+		return IB_SMI_HANDLE;
+
+	if (retsmi == IB_SMI_SEND) { /* don't forward */
+		if (opa_smi_handle_dr_smp_send(smp,
+					   port_priv->device->node_type,
+					   port_num) == IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+
+		if (opa_smi_check_local_smp(smp, port_priv->device) ==
+		    IB_SMI_DISCARD)
+			return IB_SMI_DISCARD;
+
+	} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
+		/* forward case for switches */
+		memcpy(response, recv, mad_priv_size(response));
+		response->header.recv_wc.wc = &response->header.wc;
+		response->header.recv_wc.recv_buf.opa_mad =
+				(struct opa_mad *)response->mad;
+		response->header.recv_wc.recv_buf.grh = &response->grh;
+
+		agent_send_response((const struct ib_mad_hdr *)response->mad,
+				    &response->grh, wc,
+				    port_priv->device,
+				    opa_smi_get_fwd_port(smp),
+				    qp_info->qp->qp_num,
+				    recv->header.wc.byte_len,
+				    true);
+
+		return IB_SMI_DISCARD;
+	}
+
+	return IB_SMI_HANDLE;
+}
+
+static enum smi_action
+handle_smi(struct ib_mad_port_private *port_priv,
+	   struct ib_mad_qp_info *qp_info,
+	   struct ib_wc *wc,
+	   int port_num,
+	   struct ib_mad_private *recv,
+	   struct ib_mad_private *response,
+	   bool opa)
+{
+	struct ib_mad_hdr *mad_hdr = (struct ib_mad_hdr *)recv->mad;
+
+	if (opa && mad_hdr->base_version == OPA_MGMT_BASE_VERSION &&
+	    mad_hdr->class_version == OPA_SMI_CLASS_VERSION)
+		return handle_opa_smi(port_priv, qp_info, wc, port_num, recv,
+				      response);
+
+	return handle_ib_smi(port_priv, qp_info, wc, port_num, recv, response);
+}
+
 static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv,
 				     struct ib_wc *wc)
 {
@@ -1954,35 +2186,49 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv,
 	struct ib_mad_agent_private *mad_agent;
 	int port_num;
 	int ret = IB_MAD_RESULT_SUCCESS;
+	size_t mad_size;
+	u16 resp_mad_pkey_index = 0;
+	bool opa;
 
 	mad_list = (struct ib_mad_list_head *)(unsigned long)wc->wr_id;
 	qp_info = mad_list->mad_queue->qp_info;
 	dequeue_mad(mad_list);
 
+	opa = rdma_cap_opa_mad(qp_info->port_priv->device,
+			       qp_info->port_priv->port_num);
+
 	mad_priv_hdr = container_of(mad_list, struct ib_mad_private_header,
 				    mad_list);
 	recv = container_of(mad_priv_hdr, struct ib_mad_private, header);
 	ib_dma_unmap_single(port_priv->device,
 			    recv->header.mapping,
-			    sizeof(struct ib_mad_private) -
-			      sizeof(struct ib_mad_private_header),
+			    mad_priv_dma_size(recv),
 			    DMA_FROM_DEVICE);
 
 	/* Setup MAD receive work completion from "normal" work completion */
 	recv->header.wc = *wc;
 	recv->header.recv_wc.wc = &recv->header.wc;
-	recv->header.recv_wc.mad_len = sizeof(struct ib_mad);
-	recv->header.recv_wc.recv_buf.mad = &recv->mad.mad;
+
+	if (opa && ((struct ib_mad_hdr *)(recv->mad))->base_version == OPA_MGMT_BASE_VERSION) {
+		recv->header.recv_wc.mad_len = wc->byte_len - sizeof(struct ib_grh);
+		recv->header.recv_wc.mad_seg_size = sizeof(struct opa_mad);
+	} else {
+		recv->header.recv_wc.mad_len = sizeof(struct ib_mad);
+		recv->header.recv_wc.mad_seg_size = sizeof(struct ib_mad);
+	}
+
+	recv->header.recv_wc.recv_buf.mad = (struct ib_mad *)recv->mad;
 	recv->header.recv_wc.recv_buf.grh = &recv->grh;
 
 	if (atomic_read(&qp_info->snoop_count))
 		snoop_recv(qp_info, &recv->header.recv_wc, IB_MAD_SNOOP_RECVS);
 
 	/* Validate MAD */
-	if (!validate_mad(&recv->mad.mad, qp_info->qp->qp_num))
+	if (!validate_mad((const struct ib_mad_hdr *)recv->mad, qp_info, opa))
 		goto out;
 
-	response = kmem_cache_alloc(ib_mad_cache, GFP_KERNEL);
+	mad_size = recv->mad_size;
+	response = alloc_mad_private(mad_size, GFP_KERNEL);
 	if (!response) {
 		dev_err(&port_priv->device->dev,
 			"ib_mad_recv_done_handler no memory for response buffer\n");
@@ -1994,69 +2240,43 @@ static void ib_mad_recv_done_handler(struct ib_mad_port_private *port_priv,
 	else
 		port_num = port_priv->port_num;
 
-	if (recv->mad.mad.mad_hdr.mgmt_class ==
+	if (((struct ib_mad_hdr *)recv->mad)->mgmt_class ==
 	    IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE) {
-		enum smi_forward_action retsmi;
-
-		if (smi_handle_dr_smp_recv(&recv->mad.smp,
-					   port_priv->device->node_type,
-					   port_num,
-					   port_priv->device->phys_port_cnt) ==
-					   IB_SMI_DISCARD)
+		if (handle_smi(port_priv, qp_info, wc, port_num, recv,
+			       response, opa)
+		    == IB_SMI_DISCARD)
 			goto out;
-
-		retsmi = smi_check_forward_dr_smp(&recv->mad.smp);
-		if (retsmi == IB_SMI_LOCAL)
-			goto local;
-
-		if (retsmi == IB_SMI_SEND) { /* don't forward */
-			if (smi_handle_dr_smp_send(&recv->mad.smp,
-						   port_priv->device->node_type,
-						   port_num) == IB_SMI_DISCARD)
-				goto out;
-
-			if (smi_check_local_smp(&recv->mad.smp, port_priv->device) == IB_SMI_DISCARD)
-				goto out;
-		} else if (port_priv->device->node_type == RDMA_NODE_IB_SWITCH) {
-			/* forward case for switches */
-			memcpy(response, recv, sizeof(*response));
-			response->header.recv_wc.wc = &response->header.wc;
-			response->header.recv_wc.recv_buf.mad = &response->mad.mad;
-			response->header.recv_wc.recv_buf.grh = &response->grh;
-
-			agent_send_response(&response->mad.mad,
-					    &response->grh, wc,
-					    port_priv->device,
-					    smi_get_fwd_port(&recv->mad.smp),
-					    qp_info->qp->qp_num);
-
-			goto out;
-		}
 	}
 
-local:
 	/* Give driver "right of first refusal" on incoming MAD */
 	if (port_priv->device->process_mad) {
 		ret = port_priv->device->process_mad(port_priv->device, 0,
 						     port_priv->port_num,
 						     wc, &recv->grh,
-						     &recv->mad.mad,
-						     &response->mad.mad);
+						     (const struct ib_mad_hdr *)recv->mad,
+						     recv->mad_size,
+						     (struct ib_mad_hdr *)response->mad,
+						     &mad_size, &resp_mad_pkey_index);
+
+		if (opa)
+			wc->pkey_index = resp_mad_pkey_index;
+
 		if (ret & IB_MAD_RESULT_SUCCESS) {
 			if (ret & IB_MAD_RESULT_CONSUMED)
 				goto out;
 			if (ret & IB_MAD_RESULT_REPLY) {
-				agent_send_response(&response->mad.mad,
+				agent_send_response((const struct ib_mad_hdr *)response->mad,
 						    &recv->grh, wc,
 						    port_priv->device,
 						    port_num,
-						    qp_info->qp->qp_num);
+						    qp_info->qp->qp_num,
+						    mad_size, opa);
 				goto out;
 			}
 		}
 	}
 
-	mad_agent = find_mad_agent(port_priv, &recv->mad.mad);
+	mad_agent = find_mad_agent(port_priv, (const struct ib_mad_hdr *)recv->mad);
 	if (mad_agent) {
 		ib_mad_complete_recv(mad_agent, &recv->header.recv_wc);
 		/*
@@ -2065,17 +2285,17 @@ local:
 		 */
 		recv = NULL;
 	} else if ((ret & IB_MAD_RESULT_SUCCESS) &&
-		   generate_unmatched_resp(recv, response)) {
-		agent_send_response(&response->mad.mad, &recv->grh, wc,
-				    port_priv->device, port_num, qp_info->qp->qp_num);
+		   generate_unmatched_resp(recv, response, &mad_size, opa)) {
+		agent_send_response((const struct ib_mad_hdr *)response->mad, &recv->grh, wc,
+				    port_priv->device, port_num,
+				    qp_info->qp->qp_num, mad_size, opa);
 	}
 
 out:
 	/* Post another receive request for this QP */
 	if (response) {
 		ib_mad_post_receive_mads(qp_info, response);
-		if (recv)
-			kmem_cache_free(ib_mad_cache, recv);
+		kfree(recv);
 	} else
 		ib_mad_post_receive_mads(qp_info, recv);
 }
@@ -2411,7 +2631,8 @@ find_send_wr(struct ib_mad_agent_private *mad_agent_priv,
 
 	list_for_each_entry(mad_send_wr, &mad_agent_priv->send_list,
 			    agent_list) {
-		if (is_data_mad(mad_agent_priv, mad_send_wr->send_buf.mad) &&
+		if (is_rmpp_data_mad(mad_agent_priv,
+				     mad_send_wr->send_buf.mad) &&
 		    &mad_send_wr->send_buf == send_buf)
 			return mad_send_wr;
 	}
@@ -2468,10 +2689,14 @@ static void local_completions(struct work_struct *work)
 	int free_mad;
 	struct ib_wc wc;
 	struct ib_mad_send_wc mad_send_wc;
+	bool opa;
 
 	mad_agent_priv =
 		container_of(work, struct ib_mad_agent_private, local_work);
 
+	opa = rdma_cap_opa_mad(mad_agent_priv->qp_info->port_priv->device,
+			       mad_agent_priv->qp_info->port_priv->port_num);
+
 	spin_lock_irqsave(&mad_agent_priv->lock, flags);
 	while (!list_empty(&mad_agent_priv->local_list)) {
 		local = list_entry(mad_agent_priv->local_list.next,
@@ -2481,6 +2706,7 @@ static void local_completions(struct work_struct *work)
 		spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
 		free_mad = 0;
 		if (local->mad_priv) {
+			u8 base_version;
 			recv_mad_agent = local->recv_mad_agent;
 			if (!recv_mad_agent) {
 				dev_err(&mad_agent_priv->agent.device->dev,
@@ -2496,17 +2722,26 @@ static void local_completions(struct work_struct *work)
 			build_smp_wc(recv_mad_agent->agent.qp,
 				     (unsigned long) local->mad_send_wr,
 				     be16_to_cpu(IB_LID_PERMISSIVE),
-				     0, recv_mad_agent->agent.port_num, &wc);
+				     local->mad_send_wr->send_wr.wr.ud.pkey_index,
+				     recv_mad_agent->agent.port_num, &wc);
 
 			local->mad_priv->header.recv_wc.wc = &wc;
-			local->mad_priv->header.recv_wc.mad_len =
-						sizeof(struct ib_mad);
+
+			base_version = ((struct ib_mad_hdr *)(local->mad_priv->mad))->base_version;
+			if (opa && base_version == OPA_MGMT_BASE_VERSION) {
+				local->mad_priv->header.recv_wc.mad_len = local->return_wc_byte_len;
+				local->mad_priv->header.recv_wc.mad_seg_size = sizeof(struct opa_mad);
+			} else {
+				local->mad_priv->header.recv_wc.mad_len = sizeof(struct ib_mad);
+				local->mad_priv->header.recv_wc.mad_seg_size = sizeof(struct ib_mad);
+			}
+
 			INIT_LIST_HEAD(&local->mad_priv->header.recv_wc.rmpp_list);
 			list_add(&local->mad_priv->header.recv_wc.recv_buf.list,
 				 &local->mad_priv->header.recv_wc.rmpp_list);
 			local->mad_priv->header.recv_wc.recv_buf.grh = NULL;
 			local->mad_priv->header.recv_wc.recv_buf.mad =
-						&local->mad_priv->mad.mad;
+						(struct ib_mad *)local->mad_priv->mad;
 			if (atomic_read(&recv_mad_agent->qp_info->snoop_count))
 				snoop_recv(recv_mad_agent->qp_info,
 					  &local->mad_priv->header.recv_wc,
@@ -2534,7 +2769,7 @@ local_send_completion:
 		spin_lock_irqsave(&mad_agent_priv->lock, flags);
 		atomic_dec(&mad_agent_priv->refcount);
 		if (free_mad)
-			kmem_cache_free(ib_mad_cache, local->mad_priv);
+			kfree(local->mad_priv);
 		kfree(local);
 	}
 	spin_unlock_irqrestore(&mad_agent_priv->lock, flags);
@@ -2649,7 +2884,6 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 	struct ib_mad_queue *recv_queue = &qp_info->recv_queue;
 
 	/* Initialize common scatter list fields */
-	sg_list.length = sizeof *mad_priv - sizeof mad_priv->header;
 	sg_list.lkey = (*qp_info->port_priv->mr).lkey;
 
 	/* Initialize common receive WR fields */
@@ -2663,7 +2897,8 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 			mad_priv = mad;
 			mad = NULL;
 		} else {
-			mad_priv = kmem_cache_alloc(ib_mad_cache, GFP_KERNEL);
+			mad_priv = alloc_mad_private(port_mad_size(qp_info->port_priv),
+						     GFP_ATOMIC);
 			if (!mad_priv) {
 				dev_err(&qp_info->port_priv->device->dev,
 					"No memory for receive buffer\n");
@@ -2671,10 +2906,10 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 				break;
 			}
 		}
+		sg_list.length = mad_priv_dma_size(mad_priv);
 		sg_list.addr = ib_dma_map_single(qp_info->port_priv->device,
 						 &mad_priv->grh,
-						 sizeof *mad_priv -
-						   sizeof mad_priv->header,
+						 mad_priv_dma_size(mad_priv),
 						 DMA_FROM_DEVICE);
 		if (unlikely(ib_dma_mapping_error(qp_info->port_priv->device,
 						  sg_list.addr))) {
@@ -2698,10 +2933,9 @@ static int ib_mad_post_receive_mads(struct ib_mad_qp_info *qp_info,
 			spin_unlock_irqrestore(&recv_queue->lock, flags);
 			ib_dma_unmap_single(qp_info->port_priv->device,
 					    mad_priv->header.mapping,
-					    sizeof *mad_priv -
-					      sizeof mad_priv->header,
+					    mad_priv_dma_size(mad_priv),
 					    DMA_FROM_DEVICE);
-			kmem_cache_free(ib_mad_cache, mad_priv);
+			kfree(mad_priv);
 			dev_err(&qp_info->port_priv->device->dev,
 				"ib_post_recv failed: %d\n", ret);
 			break;
@@ -2738,10 +2972,9 @@ static void cleanup_recv_queue(struct ib_mad_qp_info *qp_info)
 
 		ib_dma_unmap_single(qp_info->port_priv->device,
 				    recv->header.mapping,
-				    sizeof(struct ib_mad_private) -
-				      sizeof(struct ib_mad_private_header),
+				    mad_priv_dma_size(recv),
 				    DMA_FROM_DEVICE);
-		kmem_cache_free(ib_mad_cache, recv);
+		kfree(recv);
 	}
 
 	qp_info->recv_queue.count = 0;
@@ -2922,6 +3155,14 @@ static int ib_mad_port_open(struct ib_device *device,
 	unsigned long flags;
 	char name[sizeof "ib_mad123"];
 	int has_smi;
+	struct ib_cq_init_attr cq_attr = {};
+
+	if (WARN_ON(rdma_max_mad_size(device, port_num) < IB_MGMT_MAD_SIZE))
+		return -EFAULT;
+
+	if (WARN_ON(rdma_cap_opa_mad(device, port_num) &&
+		    rdma_max_mad_size(device, port_num) < OPA_MGMT_MAD_SIZE))
+		return -EFAULT;
 
 	/* Create new device info */
 	port_priv = kzalloc(sizeof *port_priv, GFP_KERNEL);
@@ -2938,13 +3179,14 @@ static int ib_mad_port_open(struct ib_device *device,
 	init_mad_qp(port_priv, &port_priv->qp_info[1]);
 
 	cq_size = mad_sendq_size + mad_recvq_size;
-	has_smi = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_INFINIBAND;
+	has_smi = rdma_cap_ib_smi(device, port_num);
 	if (has_smi)
 		cq_size *= 2;
 
+	cq_attr.cqe = cq_size;
 	port_priv->cq = ib_create_cq(port_priv->device,
 				     ib_mad_thread_completion_handler,
-				     NULL, port_priv, cq_size, 0);
+				     NULL, port_priv, &cq_attr);
 	if (IS_ERR(port_priv->cq)) {
 		dev_err(&device->dev, "Couldn't create ib_mad CQ\n");
 		ret = PTR_ERR(port_priv->cq);
@@ -3057,9 +3299,6 @@ static void ib_mad_init_device(struct ib_device *device)
 {
 	int start, end, i;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	if (device->node_type == RDMA_NODE_IB_SWITCH) {
 		start = 0;
 		end   = 0;
@@ -3069,6 +3308,9 @@ static void ib_mad_init_device(struct ib_device *device)
 	}
 
 	for (i = start; i <= end; i++) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
+
 		if (ib_mad_port_open(device, i)) {
 			dev_err(&device->dev, "Couldn't open port %d\n", i);
 			goto error;
@@ -3086,40 +3328,39 @@ error_agent:
 		dev_err(&device->dev, "Couldn't close port %d\n", i);
 
 error:
-	i--;
+	while (--i >= start) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
 
-	while (i >= start) {
 		if (ib_agent_port_close(device, i))
 			dev_err(&device->dev,
 				"Couldn't close port %d for agents\n", i);
 		if (ib_mad_port_close(device, i))
 			dev_err(&device->dev, "Couldn't close port %d\n", i);
-		i--;
 	}
 }
 
 static void ib_mad_remove_device(struct ib_device *device)
 {
-	int i, num_ports, cur_port;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	int start, end, i;
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH) {
-		num_ports = 1;
-		cur_port = 0;
+		start = 0;
+		end   = 0;
 	} else {
-		num_ports = device->phys_port_cnt;
-		cur_port = 1;
+		start = 1;
+		end   = device->phys_port_cnt;
 	}
-	for (i = 0; i < num_ports; i++, cur_port++) {
-		if (ib_agent_port_close(device, cur_port))
+
+	for (i = start; i <= end; i++) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
+
+		if (ib_agent_port_close(device, i))
 			dev_err(&device->dev,
-				"Couldn't close port %d for agents\n",
-				cur_port);
-		if (ib_mad_port_close(device, cur_port))
-			dev_err(&device->dev, "Couldn't close port %d\n",
-				cur_port);
+				"Couldn't close port %d for agents\n", i);
+		if (ib_mad_port_close(device, i))
+			dev_err(&device->dev, "Couldn't close port %d\n", i);
 	}
 }
 
@@ -3131,45 +3372,25 @@ static struct ib_client mad_client = {
 
 static int __init ib_mad_init_module(void)
 {
-	int ret;
-
 	mad_recvq_size = min(mad_recvq_size, IB_MAD_QP_MAX_SIZE);
 	mad_recvq_size = max(mad_recvq_size, IB_MAD_QP_MIN_SIZE);
 
 	mad_sendq_size = min(mad_sendq_size, IB_MAD_QP_MAX_SIZE);
 	mad_sendq_size = max(mad_sendq_size, IB_MAD_QP_MIN_SIZE);
 
-	ib_mad_cache = kmem_cache_create("ib_mad",
-					 sizeof(struct ib_mad_private),
-					 0,
-					 SLAB_HWCACHE_ALIGN,
-					 NULL);
-	if (!ib_mad_cache) {
-		pr_err("Couldn't create ib_mad cache\n");
-		ret = -ENOMEM;
-		goto error1;
-	}
-
 	INIT_LIST_HEAD(&ib_mad_port_list);
 
 	if (ib_register_client(&mad_client)) {
 		pr_err("Couldn't register ib_mad client\n");
-		ret = -EINVAL;
-		goto error2;
+		return -EINVAL;
 	}
 
 	return 0;
-
-error2:
-	kmem_cache_destroy(ib_mad_cache);
-error1:
-	return ret;
 }
 
 static void __exit ib_mad_cleanup_module(void)
 {
 	ib_unregister_client(&mad_client);
-	kmem_cache_destroy(ib_mad_cache);
 }
 
 module_init(ib_mad_init_module);

drivers/infiniband/core/mad_priv.h

@@ -41,6 +41,7 @@
 #include <linux/workqueue.h>
 #include <rdma/ib_mad.h>
 #include <rdma/ib_smi.h>
+#include <rdma/opa_smi.h>
 
 #define IB_MAD_QPS_CORE		2 /* Always QP0 and QP1 as a minimum */
 
@@ -56,7 +57,7 @@
 
 /* Registration table sizes */
 #define MAX_MGMT_CLASS		80
-#define MAX_MGMT_VERSION	8
+#define MAX_MGMT_VERSION	0x83
 #define MAX_MGMT_OUI		8
 #define MAX_MGMT_VENDOR_RANGE2	(IB_MGMT_CLASS_VENDOR_RANGE2_END - \
 				IB_MGMT_CLASS_VENDOR_RANGE2_START + 1)
@@ -75,12 +76,9 @@ struct ib_mad_private_header {
 
 struct ib_mad_private {
 	struct ib_mad_private_header header;
+	size_t mad_size;
 	struct ib_grh grh;
-	union {
-		struct ib_mad mad;
-		struct ib_rmpp_mad rmpp_mad;
-		struct ib_smp smp;
-	} mad;
+	u8 mad[0];
 } __attribute__ ((packed));
 
 struct ib_rmpp_segment {
@@ -150,6 +148,7 @@ struct ib_mad_local_private {
 	struct ib_mad_private *mad_priv;
 	struct ib_mad_agent_private *recv_mad_agent;
 	struct ib_mad_send_wr_private *mad_send_wr;
+	size_t return_wc_byte_len;
 };
 
 struct ib_mad_mgmt_method_table {
@@ -213,8 +212,8 @@ struct ib_mad_port_private {
 int ib_send_mad(struct ib_mad_send_wr_private *mad_send_wr);
 
 struct ib_mad_send_wr_private *
-ib_find_send_mad(struct ib_mad_agent_private *mad_agent_priv,
-		 struct ib_mad_recv_wc *mad_recv_wc);
+ib_find_send_mad(const struct ib_mad_agent_private *mad_agent_priv,
+		 const struct ib_mad_recv_wc *mad_recv_wc);
 
 void ib_mad_complete_send_wr(struct ib_mad_send_wr_private *mad_send_wr,
 			     struct ib_mad_send_wc *mad_send_wc);

drivers/infiniband/core/mad_rmpp.c

@@ -1,6 +1,7 @@
 /*
  * Copyright (c) 2005 Intel Inc. All rights reserved.
  * Copyright (c) 2005-2006 Voltaire, Inc. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation.  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
@@ -67,6 +68,7 @@ struct mad_rmpp_recv {
 	u8 mgmt_class;
 	u8 class_version;
 	u8 method;
+	u8 base_version;
 };
 
 static inline void deref_rmpp_recv(struct mad_rmpp_recv *rmpp_recv)
@@ -139,7 +141,8 @@ static void ack_recv(struct mad_rmpp_recv *rmpp_recv,
 	hdr_len = ib_get_mad_data_offset(recv_wc->recv_buf.mad->mad_hdr.mgmt_class);
 	msg = ib_create_send_mad(&rmpp_recv->agent->agent, recv_wc->wc->src_qp,
 				 recv_wc->wc->pkey_index, 1, hdr_len,
-				 0, GFP_KERNEL);
+				 0, GFP_KERNEL,
+				 IB_MGMT_BASE_VERSION);
 	if (IS_ERR(msg))
 		return;
 
@@ -165,7 +168,8 @@ static struct ib_mad_send_buf *alloc_response_msg(struct ib_mad_agent *agent,
 	hdr_len = ib_get_mad_data_offset(recv_wc->recv_buf.mad->mad_hdr.mgmt_class);
 	msg = ib_create_send_mad(agent, recv_wc->wc->src_qp,
 				 recv_wc->wc->pkey_index, 1,
-				 hdr_len, 0, GFP_KERNEL);
+				 hdr_len, 0, GFP_KERNEL,
+				 IB_MGMT_BASE_VERSION);
 	if (IS_ERR(msg))
 		ib_destroy_ah(ah);
 	else {
@@ -316,6 +320,7 @@ create_rmpp_recv(struct ib_mad_agent_private *agent,
 	rmpp_recv->mgmt_class = mad_hdr->mgmt_class;
 	rmpp_recv->class_version = mad_hdr->class_version;
 	rmpp_recv->method  = mad_hdr->method;
+	rmpp_recv->base_version  = mad_hdr->base_version;
 	return rmpp_recv;
 
 error:	kfree(rmpp_recv);
@@ -431,14 +436,23 @@ static inline int get_mad_len(struct mad_rmpp_recv *rmpp_recv)
 {
 	struct ib_rmpp_mad *rmpp_mad;
 	int hdr_size, data_size, pad;
+	bool opa = rdma_cap_opa_mad(rmpp_recv->agent->qp_info->port_priv->device,
+				    rmpp_recv->agent->qp_info->port_priv->port_num);
 
 	rmpp_mad = (struct ib_rmpp_mad *)rmpp_recv->cur_seg_buf->mad;
 
 	hdr_size = ib_get_mad_data_offset(rmpp_mad->mad_hdr.mgmt_class);
-	data_size = sizeof(struct ib_rmpp_mad) - hdr_size;
-	pad = IB_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
-	if (pad > IB_MGMT_RMPP_DATA || pad < 0)
-		pad = 0;
+	if (opa && rmpp_recv->base_version == OPA_MGMT_BASE_VERSION) {
+		data_size = sizeof(struct opa_rmpp_mad) - hdr_size;
+		pad = OPA_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
+		if (pad > OPA_MGMT_RMPP_DATA || pad < 0)
+			pad = 0;
+	} else {
+		data_size = sizeof(struct ib_rmpp_mad) - hdr_size;
+		pad = IB_MGMT_RMPP_DATA - be32_to_cpu(rmpp_mad->rmpp_hdr.paylen_newwin);
+		if (pad > IB_MGMT_RMPP_DATA || pad < 0)
+			pad = 0;
+	}
 
 	return hdr_size + rmpp_recv->seg_num * data_size - pad;
 }
@@ -570,13 +584,14 @@ static int send_next_seg(struct ib_mad_send_wr_private *mad_send_wr)
 
 	if (mad_send_wr->seg_num == 1) {
 		rmpp_mad->rmpp_hdr.rmpp_rtime_flags |= IB_MGMT_RMPP_FLAG_FIRST;
-		paylen = mad_send_wr->send_buf.seg_count * IB_MGMT_RMPP_DATA -
-			 mad_send_wr->pad;
+		paylen = (mad_send_wr->send_buf.seg_count *
+			  mad_send_wr->send_buf.seg_rmpp_size) -
+			  mad_send_wr->pad;
 	}
 
 	if (mad_send_wr->seg_num == mad_send_wr->send_buf.seg_count) {
 		rmpp_mad->rmpp_hdr.rmpp_rtime_flags |= IB_MGMT_RMPP_FLAG_LAST;
-		paylen = IB_MGMT_RMPP_DATA - mad_send_wr->pad;
+		paylen = mad_send_wr->send_buf.seg_rmpp_size - mad_send_wr->pad;
 	}
 	rmpp_mad->rmpp_hdr.paylen_newwin = cpu_to_be32(paylen);
 

drivers/infiniband/core/multicast.c

@@ -780,8 +780,7 @@ static void mcast_event_handler(struct ib_event_handler *handler,
 	int index;
 
 	dev = container_of(handler, struct mcast_device, event_handler);
-	if (rdma_port_get_link_layer(dev->device, event->element.port_num) !=
-	    IB_LINK_LAYER_INFINIBAND)
+	if (!rdma_cap_ib_mcast(dev->device, event->element.port_num))
 		return;
 
 	index = event->element.port_num - dev->start_port;
@@ -808,9 +807,6 @@ static void mcast_add_one(struct ib_device *device)
 	int i;
 	int count = 0;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	dev = kmalloc(sizeof *dev + device->phys_port_cnt * sizeof *port,
 		      GFP_KERNEL);
 	if (!dev)
@@ -824,8 +820,7 @@ static void mcast_add_one(struct ib_device *device)
 	}
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
-		if (rdma_port_get_link_layer(device, dev->start_port + i) !=
-		    IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_cap_ib_mcast(device, dev->start_port + i))
 			continue;
 		port = &dev->port[i];
 		port->dev = dev;
@@ -863,8 +858,7 @@ static void mcast_remove_one(struct ib_device *device)
 	flush_workqueue(mcast_wq);
 
 	for (i = 0; i <= dev->end_port - dev->start_port; i++) {
-		if (rdma_port_get_link_layer(device, dev->start_port + i) ==
-		    IB_LINK_LAYER_INFINIBAND) {
+		if (rdma_cap_ib_mcast(device, dev->start_port + i)) {
 			port = &dev->port[i];
 			deref_port(port);
 			wait_for_completion(&port->comp);

drivers/infiniband/core/opa_smi.h

@@ -0,0 +1,78 @@
+/*
+ * Copyright (c) 2014 Intel Corporation.  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.
+ *
+ */
+
+#ifndef __OPA_SMI_H_
+#define __OPA_SMI_H_
+
+#include <rdma/ib_smi.h>
+#include <rdma/opa_smi.h>
+
+#include "smi.h"
+
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+				       int port_num, int phys_port_cnt);
+int opa_smi_get_fwd_port(struct opa_smp *smp);
+extern enum smi_forward_action opa_smi_check_forward_dr_smp(struct opa_smp *smp);
+extern enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
+					      u8 node_type, int port_num);
+
+/*
+ * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM
+ * via process_mad
+ */
+static inline enum smi_action opa_smi_check_local_smp(struct opa_smp *smp,
+						      struct ib_device *device)
+{
+	/* C14-9:3 -- We're at the end of the DR segment of path */
+	/* C14-9:4 -- Hop Pointer = Hop Count + 1 -> give to SMA/SM */
+	return (device->process_mad &&
+		!opa_get_smp_direction(smp) &&
+		(smp->hop_ptr == smp->hop_cnt + 1)) ?
+		IB_SMI_HANDLE : IB_SMI_DISCARD;
+}
+
+/*
+ * Return IB_SMI_HANDLE if the SMP should be handled by the local SMA/SM
+ * via process_mad
+ */
+static inline enum smi_action opa_smi_check_local_returning_smp(struct opa_smp *smp,
+								struct ib_device *device)
+{
+	/* C14-13:3 -- We're at the end of the DR segment of path */
+	/* C14-13:4 -- Hop Pointer == 0 -> give to SM */
+	return (device->process_mad &&
+		opa_get_smp_direction(smp) &&
+		!smp->hop_ptr) ? IB_SMI_HANDLE : IB_SMI_DISCARD;
+}
+
+#endif	/* __OPA_SMI_H_ */

drivers/infiniband/core/sa_query.c

@@ -450,7 +450,7 @@ static void ib_sa_event(struct ib_event_handler *handler, struct ib_event *event
 		struct ib_sa_port *port =
 			&sa_dev->port[event->element.port_num - sa_dev->start_port];
 
-		if (rdma_port_get_link_layer(handler->device, port->port_num) != IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_cap_ib_sa(handler->device, port->port_num))
 			return;
 
 		spin_lock_irqsave(&port->ah_lock, flags);
@@ -540,7 +540,7 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 	ah_attr->port_num = port_num;
 	ah_attr->static_rate = rec->rate;
 
-	force_grh = rdma_port_get_link_layer(device, port_num) == IB_LINK_LAYER_ETHERNET;
+	force_grh = rdma_cap_eth_ah(device, port_num);
 
 	if (rec->hop_limit > 1 || force_grh) {
 		ah_attr->ah_flags = IB_AH_GRH;
@@ -583,7 +583,8 @@ static int alloc_mad(struct ib_sa_query *query, gfp_t gfp_mask)
 	query->mad_buf = ib_create_send_mad(query->port->agent, 1,
 					    query->sm_ah->pkey_index,
 					    0, IB_MGMT_SA_HDR, IB_MGMT_SA_DATA,
-					    gfp_mask);
+					    gfp_mask,
+					    IB_MGMT_BASE_VERSION);
 	if (IS_ERR(query->mad_buf)) {
 		kref_put(&query->sm_ah->ref, free_sm_ah);
 		return -ENOMEM;
@@ -1153,9 +1154,7 @@ static void ib_sa_add_one(struct ib_device *device)
 {
 	struct ib_sa_device *sa_dev;
 	int s, e, i;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	int count = 0;
 
 	if (device->node_type == RDMA_NODE_IB_SWITCH)
 		s = e = 0;
@@ -1175,7 +1174,7 @@ static void ib_sa_add_one(struct ib_device *device)
 
 	for (i = 0; i <= e - s; ++i) {
 		spin_lock_init(&sa_dev->port[i].ah_lock);
-		if (rdma_port_get_link_layer(device, i + 1) != IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_cap_ib_sa(device, i + 1))
 			continue;
 
 		sa_dev->port[i].sm_ah    = NULL;
@@ -1189,8 +1188,13 @@ static void ib_sa_add_one(struct ib_device *device)
 			goto err;
 
 		INIT_WORK(&sa_dev->port[i].update_task, update_sm_ah);
+
+		count++;
 	}
 
+	if (!count)
+		goto free;
+
 	ib_set_client_data(device, &sa_client, sa_dev);
 
 	/*
@@ -1204,19 +1208,20 @@ static void ib_sa_add_one(struct ib_device *device)
 	if (ib_register_event_handler(&sa_dev->event_handler))
 		goto err;
 
-	for (i = 0; i <= e - s; ++i)
-		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+	for (i = 0; i <= e - s; ++i) {
+		if (rdma_cap_ib_sa(device, i + 1))
 			update_sm_ah(&sa_dev->port[i].update_task);
+	}
 
 	return;
 
 err:
-	while (--i >= 0)
-		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND)
+	while (--i >= 0) {
+		if (rdma_cap_ib_sa(device, i + 1))
 			ib_unregister_mad_agent(sa_dev->port[i].agent);
-
+	}
+free:
 	kfree(sa_dev);
-
 	return;
 }
 
@@ -1233,7 +1238,7 @@ static void ib_sa_remove_one(struct ib_device *device)
 	flush_workqueue(ib_wq);
 
 	for (i = 0; i <= sa_dev->end_port - sa_dev->start_port; ++i) {
-		if (rdma_port_get_link_layer(device, i + 1) == IB_LINK_LAYER_INFINIBAND) {
+		if (rdma_cap_ib_sa(device, i + 1)) {
 			ib_unregister_mad_agent(sa_dev->port[i].agent);
 			if (sa_dev->port[i].sm_ah)
 				kref_put(&sa_dev->port[i].sm_ah->ref, free_sm_ah);

drivers/infiniband/core/smi.c

@@ -5,6 +5,7 @@
  * Copyright (c) 2004, 2005 Topspin Corporation.  All rights reserved.
  * Copyright (c) 2004-2007 Voltaire Corporation.  All rights reserved.
  * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
+ * Copyright (c) 2014 Intel Corporation.  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
@@ -38,85 +39,82 @@
 
 #include <rdma/ib_smi.h>
 #include "smi.h"
-
-/*
- * Fixup a directed route SMP for sending
- * Return 0 if the SMP should be discarded
- */
-enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
-				       u8 node_type, int port_num)
+#include "opa_smi.h"
+
+static enum smi_action __smi_handle_dr_smp_send(u8 node_type, int port_num,
+						u8 *hop_ptr, u8 hop_cnt,
+						const u8 *initial_path,
+						const u8 *return_path,
+						u8 direction,
+						bool dr_dlid_is_permissive,
+						bool dr_slid_is_permissive)
 {
-	u8 hop_ptr, hop_cnt;
-
-	hop_ptr = smp->hop_ptr;
-	hop_cnt = smp->hop_cnt;
-
 	/* See section 14.2.2.2, Vol 1 IB spec */
 	/* C14-6 -- valid hop_cnt values are from 0 to 63 */
 	if (hop_cnt >= IB_SMP_MAX_PATH_HOPS)
 		return IB_SMI_DISCARD;
 
-	if (!ib_get_smp_direction(smp)) {
+	if (!direction) {
 		/* C14-9:1 */
-		if (hop_cnt && hop_ptr == 0) {
-			smp->hop_ptr++;
-			return (smp->initial_path[smp->hop_ptr] ==
+		if (hop_cnt && *hop_ptr == 0) {
+			(*hop_ptr)++;
+			return (initial_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:2 */
-		if (hop_ptr && hop_ptr < hop_cnt) {
+		if (*hop_ptr && *hop_ptr < hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			/* smp->return_path set when received */
-			smp->hop_ptr++;
-			return (smp->initial_path[smp->hop_ptr] ==
+			/* return_path set when received */
+			(*hop_ptr)++;
+			return (initial_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:3 -- We're at the end of the DR segment of path */
-		if (hop_ptr == hop_cnt) {
-			/* smp->return_path set when received */
-			smp->hop_ptr++;
+		if (*hop_ptr == hop_cnt) {
+			/* return_path set when received */
+			(*hop_ptr)++;
 			return (node_type == RDMA_NODE_IB_SWITCH ||
-				smp->dr_dlid == IB_LID_PERMISSIVE ?
+				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:4 -- hop_ptr = hop_cnt + 1 -> give to SMA/SM */
 		/* C14-9:5 -- Fail unreasonable hop pointer */
-		return (hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
+		return (*hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 
 	} else {
 		/* C14-13:1 */
-		if (hop_cnt && hop_ptr == hop_cnt + 1) {
-			smp->hop_ptr--;
-			return (smp->return_path[smp->hop_ptr] ==
+		if (hop_cnt && *hop_ptr == hop_cnt + 1) {
+			(*hop_ptr)--;
+			return (return_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:2 */
-		if (2 <= hop_ptr && hop_ptr <= hop_cnt) {
+		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			smp->hop_ptr--;
-			return (smp->return_path[smp->hop_ptr] ==
+			(*hop_ptr)--;
+			return (return_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:3 -- at the end of the DR segment of path */
-		if (hop_ptr == 1) {
-			smp->hop_ptr--;
+		if (*hop_ptr == 1) {
+			(*hop_ptr)--;
 			/* C14-13:3 -- SMPs destined for SM shouldn't be here */
 			return (node_type == RDMA_NODE_IB_SWITCH ||
-				smp->dr_slid == IB_LID_PERMISSIVE ?
+				dr_slid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:4 -- hop_ptr = 0 -> should have gone to SM */
-		if (hop_ptr == 0)
+		if (*hop_ptr == 0)
 			return IB_SMI_HANDLE;
 
 		/* C14-13:5 -- Check for unreasonable hop pointer */
@@ -125,105 +123,164 @@ enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
 }
 
 /*
- * Adjust information for a received SMP
- * Return 0 if the SMP should be dropped
+ * Fixup a directed route SMP for sending
+ * Return IB_SMI_DISCARD if the SMP should be discarded
  */
-enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
-				       int port_num, int phys_port_cnt)
+enum smi_action smi_handle_dr_smp_send(struct ib_smp *smp,
+				       u8 node_type, int port_num)
 {
-	u8 hop_ptr, hop_cnt;
+	return __smi_handle_dr_smp_send(node_type, port_num,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->initial_path,
+					smp->return_path,
+					ib_get_smp_direction(smp),
+					smp->dr_dlid == IB_LID_PERMISSIVE,
+					smp->dr_slid == IB_LID_PERMISSIVE);
+}
 
-	hop_ptr = smp->hop_ptr;
-	hop_cnt = smp->hop_cnt;
+enum smi_action opa_smi_handle_dr_smp_send(struct opa_smp *smp,
+				       u8 node_type, int port_num)
+{
+	return __smi_handle_dr_smp_send(node_type, port_num,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->route.dr.initial_path,
+					smp->route.dr.return_path,
+					opa_get_smp_direction(smp),
+					smp->route.dr.dr_dlid ==
+					OPA_LID_PERMISSIVE,
+					smp->route.dr.dr_slid ==
+					OPA_LID_PERMISSIVE);
+}
 
+static enum smi_action __smi_handle_dr_smp_recv(u8 node_type, int port_num,
+						int phys_port_cnt,
+						u8 *hop_ptr, u8 hop_cnt,
+						const u8 *initial_path,
+						u8 *return_path,
+						u8 direction,
+						bool dr_dlid_is_permissive,
+						bool dr_slid_is_permissive)
+{
 	/* See section 14.2.2.2, Vol 1 IB spec */
 	/* C14-6 -- valid hop_cnt values are from 0 to 63 */
 	if (hop_cnt >= IB_SMP_MAX_PATH_HOPS)
 		return IB_SMI_DISCARD;
 
-	if (!ib_get_smp_direction(smp)) {
+	if (!direction) {
 		/* C14-9:1 -- sender should have incremented hop_ptr */
-		if (hop_cnt && hop_ptr == 0)
+		if (hop_cnt && *hop_ptr == 0)
 			return IB_SMI_DISCARD;
 
 		/* C14-9:2 -- intermediate hop */
-		if (hop_ptr && hop_ptr < hop_cnt) {
+		if (*hop_ptr && *hop_ptr < hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			smp->return_path[hop_ptr] = port_num;
-			/* smp->hop_ptr updated when sending */
-			return (smp->initial_path[hop_ptr+1] <= phys_port_cnt ?
+			return_path[*hop_ptr] = port_num;
+			/* hop_ptr updated when sending */
+			return (initial_path[*hop_ptr+1] <= phys_port_cnt ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:3 -- We're at the end of the DR segment of path */
-		if (hop_ptr == hop_cnt) {
+		if (*hop_ptr == hop_cnt) {
 			if (hop_cnt)
-				smp->return_path[hop_ptr] = port_num;
-			/* smp->hop_ptr updated when sending */
+				return_path[*hop_ptr] = port_num;
+			/* hop_ptr updated when sending */
 
 			return (node_type == RDMA_NODE_IB_SWITCH ||
-				smp->dr_dlid == IB_LID_PERMISSIVE ?
+				dr_dlid_is_permissive ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-9:4 -- hop_ptr = hop_cnt + 1 -> give to SMA/SM */
 		/* C14-9:5 -- fail unreasonable hop pointer */
-		return (hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
+		return (*hop_ptr == hop_cnt + 1 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 
 	} else {
 
 		/* C14-13:1 */
-		if (hop_cnt && hop_ptr == hop_cnt + 1) {
-			smp->hop_ptr--;
-			return (smp->return_path[smp->hop_ptr] ==
+		if (hop_cnt && *hop_ptr == hop_cnt + 1) {
+			(*hop_ptr)--;
+			return (return_path[*hop_ptr] ==
 				port_num ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:2 */
-		if (2 <= hop_ptr && hop_ptr <= hop_cnt) {
+		if (2 <= *hop_ptr && *hop_ptr <= hop_cnt) {
 			if (node_type != RDMA_NODE_IB_SWITCH)
 				return IB_SMI_DISCARD;
 
-			/* smp->hop_ptr updated when sending */
-			return (smp->return_path[hop_ptr-1] <= phys_port_cnt ?
+			/* hop_ptr updated when sending */
+			return (return_path[*hop_ptr-1] <= phys_port_cnt ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:3 -- We're at the end of the DR segment of path */
-		if (hop_ptr == 1) {
-			if (smp->dr_slid == IB_LID_PERMISSIVE) {
+		if (*hop_ptr == 1) {
+			if (dr_slid_is_permissive) {
 				/* giving SMP to SM - update hop_ptr */
-				smp->hop_ptr--;
+				(*hop_ptr)--;
 				return IB_SMI_HANDLE;
 			}
-			/* smp->hop_ptr updated when sending */
+			/* hop_ptr updated when sending */
 			return (node_type == RDMA_NODE_IB_SWITCH ?
 				IB_SMI_HANDLE : IB_SMI_DISCARD);
 		}
 
 		/* C14-13:4 -- hop_ptr = 0 -> give to SM */
 		/* C14-13:5 -- Check for unreasonable hop pointer */
-		return (hop_ptr == 0 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
+		return (*hop_ptr == 0 ? IB_SMI_HANDLE : IB_SMI_DISCARD);
 	}
 }
 
-enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp)
+/*
+ * Adjust information for a received SMP
+ * Return IB_SMI_DISCARD if the SMP should be dropped
+ */
+enum smi_action smi_handle_dr_smp_recv(struct ib_smp *smp, u8 node_type,
+				       int port_num, int phys_port_cnt)
 {
-	u8 hop_ptr, hop_cnt;
+	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->initial_path,
+					smp->return_path,
+					ib_get_smp_direction(smp),
+					smp->dr_dlid == IB_LID_PERMISSIVE,
+					smp->dr_slid == IB_LID_PERMISSIVE);
+}
 
-	hop_ptr = smp->hop_ptr;
-	hop_cnt = smp->hop_cnt;
+/*
+ * Adjust information for a received SMP
+ * Return IB_SMI_DISCARD if the SMP should be dropped
+ */
+enum smi_action opa_smi_handle_dr_smp_recv(struct opa_smp *smp, u8 node_type,
+					   int port_num, int phys_port_cnt)
+{
+	return __smi_handle_dr_smp_recv(node_type, port_num, phys_port_cnt,
+					&smp->hop_ptr, smp->hop_cnt,
+					smp->route.dr.initial_path,
+					smp->route.dr.return_path,
+					opa_get_smp_direction(smp),
+					smp->route.dr.dr_dlid ==
+					OPA_LID_PERMISSIVE,
+					smp->route.dr.dr_slid ==
+					OPA_LID_PERMISSIVE);
+}
 
-	if (!ib_get_smp_direction(smp)) {
+static enum smi_forward_action __smi_check_forward_dr_smp(u8 hop_ptr, u8 hop_cnt,
+							  u8 direction,
+							  bool dr_dlid_is_permissive,
+							  bool dr_slid_is_permissive)
+{
+	if (!direction) {
 		/* C14-9:2 -- intermediate hop */
 		if (hop_ptr && hop_ptr < hop_cnt)
 			return IB_SMI_FORWARD;
 
 		/* C14-9:3 -- at the end of the DR segment of path */
 		if (hop_ptr == hop_cnt)
-			return (smp->dr_dlid == IB_LID_PERMISSIVE ?
+			return (dr_dlid_is_permissive ?
 				IB_SMI_SEND : IB_SMI_LOCAL);
 
 		/* C14-9:4 -- hop_ptr = hop_cnt + 1 -> give to SMA/SM */
@@ -236,10 +293,29 @@ enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp)
 
 		/* C14-13:3 -- at the end of the DR segment of path */
 		if (hop_ptr == 1)
-			return (smp->dr_slid != IB_LID_PERMISSIVE ?
+			return (!dr_slid_is_permissive ?
 				IB_SMI_SEND : IB_SMI_LOCAL);
 	}
 	return IB_SMI_LOCAL;
+
+}
+
+enum smi_forward_action smi_check_forward_dr_smp(struct ib_smp *smp)
+{
+	return __smi_check_forward_dr_smp(smp->hop_ptr, smp->hop_cnt,
+					  ib_get_smp_direction(smp),
+					  smp->dr_dlid == IB_LID_PERMISSIVE,
+					  smp->dr_slid == IB_LID_PERMISSIVE);
+}
+
+enum smi_forward_action opa_smi_check_forward_dr_smp(struct opa_smp *smp)
+{
+	return __smi_check_forward_dr_smp(smp->hop_ptr, smp->hop_cnt,
+					  opa_get_smp_direction(smp),
+					  smp->route.dr.dr_dlid ==
+					  OPA_LID_PERMISSIVE,
+					  smp->route.dr.dr_slid ==
+					  OPA_LID_PERMISSIVE);
 }
 
 /*
@@ -251,3 +327,13 @@ int smi_get_fwd_port(struct ib_smp *smp)
 	return (!ib_get_smp_direction(smp) ? smp->initial_path[smp->hop_ptr+1] :
 		smp->return_path[smp->hop_ptr-1]);
 }
+
+/*
+ * Return the forwarding port number from initial_path for outgoing SMP and
+ * from return_path for returning SMP
+ */
+int opa_smi_get_fwd_port(struct opa_smp *smp)
+{
+	return !opa_get_smp_direction(smp) ? smp->route.dr.initial_path[smp->hop_ptr+1] :
+		smp->route.dr.return_path[smp->hop_ptr-1];
+}

drivers/infiniband/core/sysfs.c

@@ -326,6 +326,8 @@ static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
 	int width  = (tab_attr->index >> 16) & 0xff;
 	struct ib_mad *in_mad  = NULL;
 	struct ib_mad *out_mad = NULL;
+	size_t mad_size = sizeof(*out_mad);
+	u16 out_mad_pkey_index = 0;
 	ssize_t ret;
 
 	if (!p->ibdev->process_mad)
@@ -347,7 +349,10 @@ static ssize_t show_pma_counter(struct ib_port *p, struct port_attribute *attr,
 	in_mad->data[41] = p->port_num;	/* PortSelect field */
 
 	if ((p->ibdev->process_mad(p->ibdev, IB_MAD_IGNORE_MKEY,
-		 p->port_num, NULL, NULL, in_mad, out_mad) &
+		 p->port_num, NULL, NULL,
+		 (const struct ib_mad_hdr *)in_mad, mad_size,
+		 (struct ib_mad_hdr *)out_mad, &mad_size,
+		 &out_mad_pkey_index) &
 	     (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) !=
 	    (IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_REPLY)) {
 		ret = -EINVAL;
@@ -456,6 +461,7 @@ static void ib_device_release(struct device *device)
 {
 	struct ib_device *dev = container_of(device, struct ib_device, dev);
 
+	kfree(dev->port_immutable);
 	kfree(dev);
 }
 

drivers/infiniband/core/ucm.c

@@ -1253,8 +1253,7 @@ static void ib_ucm_add_one(struct ib_device *device)
 	dev_t base;
 	struct ib_ucm_device *ucm_dev;
 
-	if (!device->alloc_ucontext ||
-	    rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
+	if (!device->alloc_ucontext || !rdma_cap_ib_cm(device, 1))
 		return;
 
 	ucm_dev = kzalloc(sizeof *ucm_dev, GFP_KERNEL);

drivers/infiniband/core/ucma.c

@@ -722,26 +722,13 @@ static ssize_t ucma_query_route(struct ucma_file *file,
 
 	resp.node_guid = (__force __u64) ctx->cm_id->device->node_guid;
 	resp.port_num = ctx->cm_id->port_num;
-	switch (rdma_node_get_transport(ctx->cm_id->device->node_type)) {
-	case RDMA_TRANSPORT_IB:
-		switch (rdma_port_get_link_layer(ctx->cm_id->device,
-			ctx->cm_id->port_num)) {
-		case IB_LINK_LAYER_INFINIBAND:
-			ucma_copy_ib_route(&resp, &ctx->cm_id->route);
-			break;
-		case IB_LINK_LAYER_ETHERNET:
-			ucma_copy_iboe_route(&resp, &ctx->cm_id->route);
-			break;
-		default:
-			break;
-		}
-		break;
-	case RDMA_TRANSPORT_IWARP:
+
+	if (rdma_cap_ib_sa(ctx->cm_id->device, ctx->cm_id->port_num))
+		ucma_copy_ib_route(&resp, &ctx->cm_id->route);
+	else if (rdma_protocol_roce(ctx->cm_id->device, ctx->cm_id->port_num))
+		ucma_copy_iboe_route(&resp, &ctx->cm_id->route);
+	else if (rdma_protocol_iwarp(ctx->cm_id->device, ctx->cm_id->port_num))
 		ucma_copy_iw_route(&resp, &ctx->cm_id->route);
-		break;
-	default:
-		break;
-	}
 
 out:
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,

drivers/infiniband/core/user_mad.c

@@ -99,7 +99,6 @@ struct ib_umad_port {
 };
 
 struct ib_umad_device {
-	int                  start_port, end_port;
 	struct kobject       kobj;
 	struct ib_umad_port  port[0];
 };
@@ -263,20 +262,23 @@ static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
 {
 	struct ib_mad_recv_buf *recv_buf;
 	int left, seg_payload, offset, max_seg_payload;
+	size_t seg_size;
 
-	/* We need enough room to copy the first (or only) MAD segment. */
 	recv_buf = &packet->recv_wc->recv_buf;
-	if ((packet->length <= sizeof (*recv_buf->mad) &&
+	seg_size = packet->recv_wc->mad_seg_size;
+
+	/* We need enough room to copy the first (or only) MAD segment. */
+	if ((packet->length <= seg_size &&
 	     count < hdr_size(file) + packet->length) ||
-	    (packet->length > sizeof (*recv_buf->mad) &&
-	     count < hdr_size(file) + sizeof (*recv_buf->mad)))
+	    (packet->length > seg_size &&
+	     count < hdr_size(file) + seg_size))
 		return -EINVAL;
 
 	if (copy_to_user(buf, &packet->mad, hdr_size(file)))
 		return -EFAULT;
 
 	buf += hdr_size(file);
-	seg_payload = min_t(int, packet->length, sizeof (*recv_buf->mad));
+	seg_payload = min_t(int, packet->length, seg_size);
 	if (copy_to_user(buf, recv_buf->mad, seg_payload))
 		return -EFAULT;
 
@@ -293,7 +295,7 @@ static ssize_t copy_recv_mad(struct ib_umad_file *file, char __user *buf,
 			return -ENOSPC;
 		}
 		offset = ib_get_mad_data_offset(recv_buf->mad->mad_hdr.mgmt_class);
-		max_seg_payload = sizeof (struct ib_mad) - offset;
+		max_seg_payload = seg_size - offset;
 
 		for (left = packet->length - seg_payload, buf += seg_payload;
 		     left; left -= seg_payload, buf += seg_payload) {
@@ -426,11 +428,11 @@ static int is_duplicate(struct ib_umad_file *file,
 		 * the same TID, reject the second as a duplicate.  This is more
 		 * restrictive than required by the spec.
 		 */
-		if (!ib_response_mad((struct ib_mad *) hdr)) {
-			if (!ib_response_mad((struct ib_mad *) sent_hdr))
+		if (!ib_response_mad(hdr)) {
+			if (!ib_response_mad(sent_hdr))
 				return 1;
 			continue;
-		} else if (!ib_response_mad((struct ib_mad *) sent_hdr))
+		} else if (!ib_response_mad(sent_hdr))
 			continue;
 
 		if (same_destination(&packet->mad.hdr, &sent_packet->mad.hdr))
@@ -451,6 +453,7 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 	struct ib_rmpp_mad *rmpp_mad;
 	__be64 *tid;
 	int ret, data_len, hdr_len, copy_offset, rmpp_active;
+	u8 base_version;
 
 	if (count < hdr_size(file) + IB_MGMT_RMPP_HDR)
 		return -EINVAL;
@@ -517,11 +520,13 @@ static ssize_t ib_umad_write(struct file *filp, const char __user *buf,
 		rmpp_active = 0;
 	}
 
+	base_version = ((struct ib_mad_hdr *)&packet->mad.data)->base_version;
 	data_len = count - hdr_size(file) - hdr_len;
 	packet->msg = ib_create_send_mad(agent,
 					 be32_to_cpu(packet->mad.hdr.qpn),
 					 packet->mad.hdr.pkey_index, rmpp_active,
-					 hdr_len, data_len, GFP_KERNEL);
+					 hdr_len, data_len, GFP_KERNEL,
+					 base_version);
 	if (IS_ERR(packet->msg)) {
 		ret = PTR_ERR(packet->msg);
 		goto err_ah;
@@ -1273,16 +1278,10 @@ static void ib_umad_add_one(struct ib_device *device)
 {
 	struct ib_umad_device *umad_dev;
 	int s, e, i;
+	int count = 0;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
-	if (device->node_type == RDMA_NODE_IB_SWITCH)
-		s = e = 0;
-	else {
-		s = 1;
-		e = device->phys_port_cnt;
-	}
+	s = rdma_start_port(device);
+	e = rdma_end_port(device);
 
 	umad_dev = kzalloc(sizeof *umad_dev +
 			   (e - s + 1) * sizeof (struct ib_umad_port),
@@ -1292,25 +1291,34 @@ static void ib_umad_add_one(struct ib_device *device)
 
 	kobject_init(&umad_dev->kobj, &ib_umad_dev_ktype);
 
-	umad_dev->start_port = s;
-	umad_dev->end_port   = e;
-
 	for (i = s; i <= e; ++i) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
+
 		umad_dev->port[i - s].umad_dev = umad_dev;
 
 		if (ib_umad_init_port(device, i, umad_dev,
 				      &umad_dev->port[i - s]))
 			goto err;
+
+		count++;
 	}
 
+	if (!count)
+		goto free;
+
 	ib_set_client_data(device, &umad_client, umad_dev);
 
 	return;
 
 err:
-	while (--i >= s)
-		ib_umad_kill_port(&umad_dev->port[i - s]);
+	while (--i >= s) {
+		if (!rdma_cap_ib_mad(device, i))
+			continue;
 
+		ib_umad_kill_port(&umad_dev->port[i - s]);
+	}
+free:
 	kobject_put(&umad_dev->kobj);
 }
 
@@ -1322,8 +1330,10 @@ static void ib_umad_remove_one(struct ib_device *device)
 	if (!umad_dev)
 		return;
 
-	for (i = 0; i <= umad_dev->end_port - umad_dev->start_port; ++i)
-		ib_umad_kill_port(&umad_dev->port[i]);
+	for (i = 0; i <= rdma_end_port(device) - rdma_start_port(device); ++i) {
+		if (rdma_cap_ib_mad(device, i + rdma_start_port(device)))
+			ib_umad_kill_port(&umad_dev->port[i]);
+	}
 
 	kobject_put(&umad_dev->kobj);
 }

drivers/infiniband/core/uverbs.h

@@ -259,5 +259,6 @@ IB_UVERBS_DECLARE_CMD(close_xrcd);
 IB_UVERBS_DECLARE_EX_CMD(create_flow);
 IB_UVERBS_DECLARE_EX_CMD(destroy_flow);
 IB_UVERBS_DECLARE_EX_CMD(query_device);
+IB_UVERBS_DECLARE_EX_CMD(create_cq);
 
 #endif /* UVERBS_H */

drivers/infiniband/core/uverbs_cmd.c

@@ -1330,40 +1330,37 @@ ssize_t ib_uverbs_create_comp_channel(struct ib_uverbs_file *file,
 	return in_len;
 }
 
-ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
-			    const char __user *buf, int in_len,
-			    int out_len)
+static struct ib_ucq_object *create_cq(struct ib_uverbs_file *file,
+				       struct ib_udata *ucore,
+				       struct ib_udata *uhw,
+				       struct ib_uverbs_ex_create_cq *cmd,
+				       size_t cmd_sz,
+				       int (*cb)(struct ib_uverbs_file *file,
+						 struct ib_ucq_object *obj,
+						 struct ib_uverbs_ex_create_cq_resp *resp,
+						 struct ib_udata *udata,
+						 void *context),
+				       void *context)
 {
-	struct ib_uverbs_create_cq      cmd;
-	struct ib_uverbs_create_cq_resp resp;
-	struct ib_udata                 udata;
 	struct ib_ucq_object           *obj;
 	struct ib_uverbs_event_file    *ev_file = NULL;
 	struct ib_cq                   *cq;
 	int                             ret;
+	struct ib_uverbs_ex_create_cq_resp resp;
+	struct ib_cq_init_attr attr = {};
 
-	if (out_len < sizeof resp)
-		return -ENOSPC;
-
-	if (copy_from_user(&cmd, buf, sizeof cmd))
-		return -EFAULT;
-
-	INIT_UDATA(&udata, buf + sizeof cmd,
-		   (unsigned long) cmd.response + sizeof resp,
-		   in_len - sizeof cmd, out_len - sizeof resp);
-
-	if (cmd.comp_vector >= file->device->num_comp_vectors)
-		return -EINVAL;
+	if (cmd->comp_vector >= file->device->num_comp_vectors)
+		return ERR_PTR(-EINVAL);
 
 	obj = kmalloc(sizeof *obj, GFP_KERNEL);
 	if (!obj)
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
-	init_uobj(&obj->uobject, cmd.user_handle, file->ucontext, &cq_lock_class);
+	init_uobj(&obj->uobject, cmd->user_handle, file->ucontext, &cq_lock_class);
 	down_write(&obj->uobject.mutex);
 
-	if (cmd.comp_channel >= 0) {
-		ev_file = ib_uverbs_lookup_comp_file(cmd.comp_channel);
+	if (cmd->comp_channel >= 0) {
+		ev_file = ib_uverbs_lookup_comp_file(cmd->comp_channel);
 		if (!ev_file) {
 			ret = -EINVAL;
 			goto err;
@@ -1376,9 +1373,14 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 	INIT_LIST_HEAD(&obj->comp_list);
 	INIT_LIST_HEAD(&obj->async_list);
 
-	cq = file->device->ib_dev->create_cq(file->device->ib_dev, cmd.cqe,
-					     cmd.comp_vector,
-					     file->ucontext, &udata);
+	attr.cqe = cmd->cqe;
+	attr.comp_vector = cmd->comp_vector;
+
+	if (cmd_sz > offsetof(typeof(*cmd), flags) + sizeof(cmd->flags))
+		attr.flags = cmd->flags;
+
+	cq = file->device->ib_dev->create_cq(file->device->ib_dev, &attr,
+					     file->ucontext, uhw);
 	if (IS_ERR(cq)) {
 		ret = PTR_ERR(cq);
 		goto err_file;
@@ -1397,14 +1399,15 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 		goto err_free;
 
 	memset(&resp, 0, sizeof resp);
-	resp.cq_handle = obj->uobject.id;
-	resp.cqe       = cq->cqe;
+	resp.base.cq_handle = obj->uobject.id;
+	resp.base.cqe       = cq->cqe;
 
-	if (copy_to_user((void __user *) (unsigned long) cmd.response,
-			 &resp, sizeof resp)) {
-		ret = -EFAULT;
-		goto err_copy;
-	}
+	resp.response_length = offsetof(typeof(resp), response_length) +
+		sizeof(resp.response_length);
+
+	ret = cb(file, obj, &resp, ucore, context);
+	if (ret)
+		goto err_cb;
 
 	mutex_lock(&file->mutex);
 	list_add_tail(&obj->uobject.list, &file->ucontext->cq_list);
@@ -1414,9 +1417,9 @@ ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
 
 	up_write(&obj->uobject.mutex);
 
-	return in_len;
+	return obj;
 
-err_copy:
+err_cb:
 	idr_remove_uobj(&ib_uverbs_cq_idr, &obj->uobject);
 
 err_free:
@@ -1428,7 +1431,106 @@ err_file:
 
 err:
 	put_uobj_write(&obj->uobject);
-	return ret;
+
+	return ERR_PTR(ret);
+}
+
+static int ib_uverbs_create_cq_cb(struct ib_uverbs_file *file,
+				  struct ib_ucq_object *obj,
+				  struct ib_uverbs_ex_create_cq_resp *resp,
+				  struct ib_udata *ucore, void *context)
+{
+	if (ib_copy_to_udata(ucore, &resp->base, sizeof(resp->base)))
+		return -EFAULT;
+
+	return 0;
+}
+
+ssize_t ib_uverbs_create_cq(struct ib_uverbs_file *file,
+			    const char __user *buf, int in_len,
+			    int out_len)
+{
+	struct ib_uverbs_create_cq      cmd;
+	struct ib_uverbs_ex_create_cq	cmd_ex;
+	struct ib_uverbs_create_cq_resp resp;
+	struct ib_udata                 ucore;
+	struct ib_udata                 uhw;
+	struct ib_ucq_object           *obj;
+
+	if (out_len < sizeof(resp))
+		return -ENOSPC;
+
+	if (copy_from_user(&cmd, buf, sizeof(cmd)))
+		return -EFAULT;
+
+	INIT_UDATA(&ucore, buf, cmd.response, sizeof(cmd), sizeof(resp));
+
+	INIT_UDATA(&uhw, buf + sizeof(cmd),
+		   (unsigned long)cmd.response + sizeof(resp),
+		   in_len - sizeof(cmd), out_len - sizeof(resp));
+
+	memset(&cmd_ex, 0, sizeof(cmd_ex));
+	cmd_ex.user_handle = cmd.user_handle;
+	cmd_ex.cqe = cmd.cqe;
+	cmd_ex.comp_vector = cmd.comp_vector;
+	cmd_ex.comp_channel = cmd.comp_channel;
+
+	obj = create_cq(file, &ucore, &uhw, &cmd_ex,
+			offsetof(typeof(cmd_ex), comp_channel) +
+			sizeof(cmd.comp_channel), ib_uverbs_create_cq_cb,
+			NULL);
+
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	return in_len;
+}
+
+static int ib_uverbs_ex_create_cq_cb(struct ib_uverbs_file *file,
+				     struct ib_ucq_object *obj,
+				     struct ib_uverbs_ex_create_cq_resp *resp,
+				     struct ib_udata *ucore, void *context)
+{
+	if (ib_copy_to_udata(ucore, resp, resp->response_length))
+		return -EFAULT;
+
+	return 0;
+}
+
+int ib_uverbs_ex_create_cq(struct ib_uverbs_file *file,
+			   struct ib_udata *ucore,
+			   struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_create_cq_resp resp;
+	struct ib_uverbs_ex_create_cq  cmd;
+	struct ib_ucq_object           *obj;
+	int err;
+
+	if (ucore->inlen < sizeof(cmd))
+		return -EINVAL;
+
+	err = ib_copy_from_udata(&cmd, ucore, sizeof(cmd));
+	if (err)
+		return err;
+
+	if (cmd.comp_mask)
+		return -EINVAL;
+
+	if (cmd.reserved)
+		return -EINVAL;
+
+	if (ucore->outlen < (offsetof(typeof(resp), response_length) +
+			     sizeof(resp.response_length)))
+		return -ENOSPC;
+
+	obj = create_cq(file, ucore, uhw, &cmd,
+			min(ucore->inlen, sizeof(cmd)),
+			ib_uverbs_ex_create_cq_cb, NULL);
+
+	if (IS_ERR(obj))
+		return PTR_ERR(obj);
+
+	return 0;
 }
 
 ssize_t ib_uverbs_resize_cq(struct ib_uverbs_file *file,
@@ -3324,7 +3426,9 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	if (ucore->outlen < resp.response_length)
 		return -ENOSPC;
 
-	err = device->query_device(device, &attr);
+	memset(&attr, 0, sizeof(attr));
+
+	err = device->query_device(device, &attr, uhw);
 	if (err)
 		return err;
 
@@ -3348,6 +3452,18 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 #endif
 	resp.response_length += sizeof(resp.odp_caps);
 
+	if (ucore->outlen < resp.response_length + sizeof(resp.timestamp_mask))
+		goto end;
+
+	resp.timestamp_mask = attr.timestamp_mask;
+	resp.response_length += sizeof(resp.timestamp_mask);
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.hca_core_clock))
+		goto end;
+
+	resp.hca_core_clock = attr.hca_core_clock;
+	resp.response_length += sizeof(resp.hca_core_clock);
+
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	if (err)

drivers/infiniband/core/uverbs_main.c

@@ -124,6 +124,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_EX_CMD_CREATE_FLOW]	= ib_uverbs_ex_create_flow,
 	[IB_USER_VERBS_EX_CMD_DESTROY_FLOW]	= ib_uverbs_ex_destroy_flow,
 	[IB_USER_VERBS_EX_CMD_QUERY_DEVICE]	= ib_uverbs_ex_query_device,
+	[IB_USER_VERBS_EX_CMD_CREATE_CQ]	= ib_uverbs_ex_create_cq,
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);

drivers/infiniband/core/verbs.c

@@ -48,6 +48,71 @@
 
 #include "core_priv.h"
 
+static const char * const ib_events[] = {
+	[IB_EVENT_CQ_ERR]		= "CQ error",
+	[IB_EVENT_QP_FATAL]		= "QP fatal error",
+	[IB_EVENT_QP_REQ_ERR]		= "QP request error",
+	[IB_EVENT_QP_ACCESS_ERR]	= "QP access error",
+	[IB_EVENT_COMM_EST]		= "communication established",
+	[IB_EVENT_SQ_DRAINED]		= "send queue drained",
+	[IB_EVENT_PATH_MIG]		= "path migration successful",
+	[IB_EVENT_PATH_MIG_ERR]		= "path migration error",
+	[IB_EVENT_DEVICE_FATAL]		= "device fatal error",
+	[IB_EVENT_PORT_ACTIVE]		= "port active",
+	[IB_EVENT_PORT_ERR]		= "port error",
+	[IB_EVENT_LID_CHANGE]		= "LID change",
+	[IB_EVENT_PKEY_CHANGE]		= "P_key change",
+	[IB_EVENT_SM_CHANGE]		= "SM change",
+	[IB_EVENT_SRQ_ERR]		= "SRQ error",
+	[IB_EVENT_SRQ_LIMIT_REACHED]	= "SRQ limit reached",
+	[IB_EVENT_QP_LAST_WQE_REACHED]	= "last WQE reached",
+	[IB_EVENT_CLIENT_REREGISTER]	= "client reregister",
+	[IB_EVENT_GID_CHANGE]		= "GID changed",
+};
+
+const char *ib_event_msg(enum ib_event_type event)
+{
+	size_t index = event;
+
+	return (index < ARRAY_SIZE(ib_events) && ib_events[index]) ?
+			ib_events[index] : "unrecognized event";
+}
+EXPORT_SYMBOL(ib_event_msg);
+
+static const char * const wc_statuses[] = {
+	[IB_WC_SUCCESS]			= "success",
+	[IB_WC_LOC_LEN_ERR]		= "local length error",
+	[IB_WC_LOC_QP_OP_ERR]		= "local QP operation error",
+	[IB_WC_LOC_EEC_OP_ERR]		= "local EE context operation error",
+	[IB_WC_LOC_PROT_ERR]		= "local protection error",
+	[IB_WC_WR_FLUSH_ERR]		= "WR flushed",
+	[IB_WC_MW_BIND_ERR]		= "memory management operation error",
+	[IB_WC_BAD_RESP_ERR]		= "bad response error",
+	[IB_WC_LOC_ACCESS_ERR]		= "local access error",
+	[IB_WC_REM_INV_REQ_ERR]		= "invalid request error",
+	[IB_WC_REM_ACCESS_ERR]		= "remote access error",
+	[IB_WC_REM_OP_ERR]		= "remote operation error",
+	[IB_WC_RETRY_EXC_ERR]		= "transport retry counter exceeded",
+	[IB_WC_RNR_RETRY_EXC_ERR]	= "RNR retry counter exceeded",
+	[IB_WC_LOC_RDD_VIOL_ERR]	= "local RDD violation error",
+	[IB_WC_REM_INV_RD_REQ_ERR]	= "remote invalid RD request",
+	[IB_WC_REM_ABORT_ERR]		= "operation aborted",
+	[IB_WC_INV_EECN_ERR]		= "invalid EE context number",
+	[IB_WC_INV_EEC_STATE_ERR]	= "invalid EE context state",
+	[IB_WC_FATAL_ERR]		= "fatal error",
+	[IB_WC_RESP_TIMEOUT_ERR]	= "response timeout error",
+	[IB_WC_GENERAL_ERR]		= "general error",
+};
+
+const char *ib_wc_status_msg(enum ib_wc_status status)
+{
+	size_t index = status;
+
+	return (index < ARRAY_SIZE(wc_statuses) && wc_statuses[index]) ?
+			wc_statuses[index] : "unrecognized status";
+}
+EXPORT_SYMBOL(ib_wc_status_msg);
+
 __attribute_const__ int ib_rate_to_mult(enum ib_rate rate)
 {
 	switch (rate) {
@@ -192,17 +257,16 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr)
 }
 EXPORT_SYMBOL(ib_create_ah);
 
-int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
-		       struct ib_grh *grh, struct ib_ah_attr *ah_attr)
+int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
+		       const struct ib_wc *wc, const struct ib_grh *grh,
+		       struct ib_ah_attr *ah_attr)
 {
 	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 (rdma_cap_eth_ah(device, port_num)) {
 		if (!(wc->wc_flags & IB_WC_GRH))
 			return -EPROTOTYPE;
 
@@ -244,8 +308,8 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
 }
 EXPORT_SYMBOL(ib_init_ah_from_wc);
 
-struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, struct ib_wc *wc,
-				   struct ib_grh *grh, u8 port_num)
+struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc,
+				   const struct ib_grh *grh, u8 port_num)
 {
 	struct ib_ah_attr ah_attr;
 	int ret;
@@ -871,7 +935,7 @@ int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
 	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)) {
+	    (rdma_cap_eth_ah(qp->device, qp_attr->ah_attr.port_num))) {
 		ret = ib_query_gid(qp->device, qp_attr->ah_attr.port_num,
 				   qp_attr->ah_attr.grh.sgid_index, &sgid);
 		if (ret)
@@ -1012,11 +1076,12 @@ EXPORT_SYMBOL(ib_destroy_qp);
 struct ib_cq *ib_create_cq(struct ib_device *device,
 			   ib_comp_handler comp_handler,
 			   void (*event_handler)(struct ib_event *, void *),
-			   void *cq_context, int cqe, int comp_vector)
+			   void *cq_context,
+			   const struct ib_cq_init_attr *cq_attr)
 {
 	struct ib_cq *cq;
 
-	cq = device->create_cq(device, cqe, comp_vector, NULL, NULL);
+	cq = device->create_cq(device, cq_attr, NULL, NULL);
 
 	if (!IS_ERR(cq)) {
 		cq->device        = device;

drivers/infiniband/hw/amso1100/c2_provider.c

@@ -63,13 +63,16 @@
 #include "c2_provider.h"
 #include "c2_user.h"
 
-static int c2_query_device(struct ib_device *ibdev,
-			   struct ib_device_attr *props)
+static int c2_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			   struct ib_udata *uhw)
 {
 	struct c2_dev *c2dev = to_c2dev(ibdev);
 
 	pr_debug("%s:%u\n", __func__, __LINE__);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	*props = c2dev->props;
 	return 0;
 }
@@ -286,13 +289,18 @@ static int c2_destroy_qp(struct ib_qp *ib_qp)
 	return 0;
 }
 
-static struct ib_cq *c2_create_cq(struct ib_device *ibdev, int entries, int vector,
+static struct ib_cq *c2_create_cq(struct ib_device *ibdev,
+				  const struct ib_cq_init_attr *attr,
 				  struct ib_ucontext *context,
 				  struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct c2_cq *cq;
 	int err;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	cq = kmalloc(sizeof(*cq), GFP_KERNEL);
 	if (!cq) {
 		pr_debug("%s: Unable to allocate CQ\n", __func__);
@@ -582,9 +590,13 @@ static int c2_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 static int c2_process_mad(struct ib_device *ibdev,
 			  int mad_flags,
 			  u8 port_num,
-			  struct ib_wc *in_wc,
-			  struct ib_grh *in_grh,
-			  struct ib_mad *in_mad, struct ib_mad *out_mad)
+			  const struct ib_wc *in_wc,
+			  const struct ib_grh *in_grh,
+			  const struct ib_mad_hdr *in_mad,
+			  size_t in_mad_size,
+			  struct ib_mad_hdr *out_mad,
+			  size_t *out_mad_size,
+			  u16 *out_mad_pkey_index)
 {
 	pr_debug("%s:%u\n", __func__, __LINE__);
 	return -ENOSYS;
@@ -757,6 +769,23 @@ static struct net_device *c2_pseudo_netdev_init(struct c2_dev *c2dev)
 	return netdev;
 }
 
+static int c2_port_immutable(struct ib_device *ibdev, u8 port_num,
+			     struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = c2_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
+
 int c2_register_device(struct c2_dev *dev)
 {
 	int ret = -ENOMEM;
@@ -820,6 +849,7 @@ int c2_register_device(struct c2_dev *dev)
 	dev->ibdev.reg_phys_mr = c2_reg_phys_mr;
 	dev->ibdev.reg_user_mr = c2_reg_user_mr;
 	dev->ibdev.dereg_mr = c2_dereg_mr;
+	dev->ibdev.get_port_immutable = c2_port_immutable;
 
 	dev->ibdev.alloc_fmr = NULL;
 	dev->ibdev.unmap_fmr = NULL;

drivers/infiniband/hw/cxgb3/iwch_provider.c

@@ -85,9 +85,13 @@ static int iwch_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 static int iwch_process_mad(struct ib_device *ibdev,
 			    int mad_flags,
 			    u8 port_num,
-			    struct ib_wc *in_wc,
-			    struct ib_grh *in_grh,
-			    struct ib_mad *in_mad, struct ib_mad *out_mad)
+			    const struct ib_wc *in_wc,
+			    const struct ib_grh *in_grh,
+			    const struct ib_mad_hdr *in_mad,
+			    size_t in_mad_size,
+			    struct ib_mad_hdr *out_mad,
+			    size_t *out_mad_size,
+			    u16 *out_mad_pkey_index)
 {
 	return -ENOSYS;
 }
@@ -138,10 +142,12 @@ static int iwch_destroy_cq(struct ib_cq *ib_cq)
 	return 0;
 }
 
-static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int vector,
-			     struct ib_ucontext *ib_context,
-			     struct ib_udata *udata)
+static struct ib_cq *iwch_create_cq(struct ib_device *ibdev,
+				    const struct ib_cq_init_attr *attr,
+				    struct ib_ucontext *ib_context,
+				    struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct iwch_dev *rhp;
 	struct iwch_cq *chp;
 	struct iwch_create_cq_resp uresp;
@@ -151,6 +157,9 @@ static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int ve
 	size_t resplen;
 
 	PDBG("%s ib_dev %p entries %d\n", __func__, ibdev, entries);
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	rhp = to_iwch_dev(ibdev);
 	chp = kzalloc(sizeof(*chp), GFP_KERNEL);
 	if (!chp)
@@ -1145,13 +1154,17 @@ static u64 fw_vers_string_to_u64(struct iwch_dev *iwch_dev)
 	       (fw_mic & 0xffff);
 }
 
-static int iwch_query_device(struct ib_device *ibdev,
-			     struct ib_device_attr *props)
+static int iwch_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			     struct ib_udata *uhw)
 {
 
 	struct iwch_dev *dev;
+
 	PDBG("%s ibdev %p\n", __func__, ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	dev = to_iwch_dev(ibdev);
 	memset(props, 0, sizeof *props);
 	memcpy(&props->sys_image_guid, dev->rdev.t3cdev_p->lldev->dev_addr, 6);
@@ -1343,6 +1356,23 @@ static struct device_attribute *iwch_class_attributes[] = {
 	&dev_attr_board_id,
 };
 
+static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = iwch_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
+
 int iwch_register_device(struct iwch_dev *dev)
 {
 	int ret;
@@ -1420,6 +1450,7 @@ int iwch_register_device(struct iwch_dev *dev)
 	dev->ibdev.post_recv = iwch_post_receive;
 	dev->ibdev.get_protocol_stats = iwch_get_mib;
 	dev->ibdev.uverbs_abi_ver = IWCH_UVERBS_ABI_VERSION;
+	dev->ibdev.get_port_immutable = iwch_port_immutable;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)

drivers/infiniband/hw/cxgb4/cq.c

@@ -156,19 +156,17 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 		goto err4;
 
 	cq->gen = 1;
+	cq->gts = rdev->lldi.gts_reg;
 	cq->rdev = rdev;
-	if (user) {
-		u32 off = (cq->cqid << rdev->cqshift) & PAGE_MASK;
 
-		cq->ugts = (u64)rdev->bar2_pa + off;
-	} else if (is_t4(rdev->lldi.adapter_type)) {
-		cq->gts = rdev->lldi.gts_reg;
-		cq->qid_mask = -1U;
-	} else {
-		u32 off = ((cq->cqid << rdev->cqshift) & PAGE_MASK) + 12;
-
-		cq->gts = rdev->bar2_kva + off;
-		cq->qid_mask = rdev->qpmask;
+	cq->bar2_va = c4iw_bar2_addrs(rdev, cq->cqid, T4_BAR2_QTYPE_INGRESS,
+				      &cq->bar2_qid,
+				      user ? &cq->bar2_pa : NULL);
+	if (user && !cq->bar2_va) {
+		pr_warn(MOD "%s: cqid %u not in BAR2 range.\n",
+			pci_name(rdev->lldi.pdev), cq->cqid);
+		ret = -EINVAL;
+		goto err4;
 	}
 	return 0;
 err4:
@@ -866,10 +864,13 @@ int c4iw_destroy_cq(struct ib_cq *ib_cq)
 	return 0;
 }
 
-struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
-			     int vector, struct ib_ucontext *ib_context,
+struct ib_cq *c4iw_create_cq(struct ib_device *ibdev,
+			     const struct ib_cq_init_attr *attr,
+			     struct ib_ucontext *ib_context,
 			     struct ib_udata *udata)
 {
+	int entries = attr->cqe;
+	int vector = attr->comp_vector;
 	struct c4iw_dev *rhp;
 	struct c4iw_cq *chp;
 	struct c4iw_create_cq_resp uresp;
@@ -879,6 +880,8 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 	struct c4iw_mm_entry *mm, *mm2;
 
 	PDBG("%s ib_dev %p entries %d\n", __func__, ibdev, entries);
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
 
 	rhp = to_c4iw_dev(ibdev);
 
@@ -971,7 +974,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 		insert_mmap(ucontext, mm);
 
 		mm2->key = uresp.gts_key;
-		mm2->addr = chp->cq.ugts;
+		mm2->addr = chp->cq.bar2_pa;
 		mm2->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm2);
 	}

drivers/infiniband/hw/cxgb4/device.c

@@ -795,13 +795,7 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 		goto err1;
 	}
 
-	/*
-	 * qpshift is the number of bits to shift the qpid left in order
-	 * to get the correct address of the doorbell for that qp.
-	 */
-	rdev->qpshift = PAGE_SHIFT - ilog2(rdev->lldi.udb_density);
 	rdev->qpmask = rdev->lldi.udb_density - 1;
-	rdev->cqshift = PAGE_SHIFT - ilog2(rdev->lldi.ucq_density);
 	rdev->cqmask = rdev->lldi.ucq_density - 1;
 	PDBG("%s dev %s stag start 0x%0x size 0x%0x num stags %d "
 	     "pbl start 0x%0x size 0x%0x rq start 0x%0x size 0x%0x "
@@ -815,14 +809,12 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 	     rdev->lldi.vr->qp.size,
 	     rdev->lldi.vr->cq.start,
 	     rdev->lldi.vr->cq.size);
-	PDBG("udb len 0x%x udb base %p db_reg %p gts_reg %p qpshift %lu "
-	     "qpmask 0x%x cqshift %lu cqmask 0x%x\n",
+	PDBG("udb len 0x%x udb base %p db_reg %p gts_reg %p "
+	     "qpmask 0x%x cqmask 0x%x\n",
 	     (unsigned)pci_resource_len(rdev->lldi.pdev, 2),
 	     (void *)pci_resource_start(rdev->lldi.pdev, 2),
-	     rdev->lldi.db_reg,
-	     rdev->lldi.gts_reg,
-	     rdev->qpshift, rdev->qpmask,
-	     rdev->cqshift, rdev->cqmask);
+	     rdev->lldi.db_reg, rdev->lldi.gts_reg,
+	     rdev->qpmask, rdev->cqmask);
 
 	if (c4iw_num_stags(rdev) == 0) {
 		err = -EINVAL;

drivers/infiniband/hw/cxgb4/iw_cxgb4.h

@@ -165,9 +165,7 @@ struct wr_log_entry {
 
 struct c4iw_rdev {
 	struct c4iw_resource resource;
-	unsigned long qpshift;
 	u32 qpmask;
-	unsigned long cqshift;
 	u32 cqmask;
 	struct c4iw_dev_ucontext uctx;
 	struct gen_pool *pbl_pool;
@@ -992,10 +990,10 @@ int c4iw_reregister_phys_mem(struct ib_mr *mr,
 				     int acc, u64 *iova_start);
 int c4iw_dereg_mr(struct ib_mr *ib_mr);
 int c4iw_destroy_cq(struct ib_cq *ib_cq);
-struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
-					int vector,
-					struct ib_ucontext *ib_context,
-					struct ib_udata *udata);
+struct ib_cq *c4iw_create_cq(struct ib_device *ibdev,
+			     const struct ib_cq_init_attr *attr,
+			     struct ib_ucontext *ib_context,
+			     struct ib_udata *udata);
 int c4iw_resize_cq(struct ib_cq *cq, int cqe, struct ib_udata *udata);
 int c4iw_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags);
 int c4iw_destroy_qp(struct ib_qp *ib_qp);
@@ -1032,6 +1030,9 @@ void c4iw_ev_dispatch(struct c4iw_dev *dev, struct t4_cqe *err_cqe);
 
 extern struct cxgb4_client t4c_client;
 extern c4iw_handler_func c4iw_handlers[NUM_CPL_CMDS];
+void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid,
+			      enum cxgb4_bar2_qtype qtype,
+			      unsigned int *pbar2_qid, u64 *pbar2_pa);
 extern void c4iw_log_wr_stats(struct t4_wq *wq, struct t4_cqe *cqe);
 extern int c4iw_wr_log;
 extern int db_fc_threshold;

drivers/infiniband/hw/cxgb4/provider.c

@@ -80,9 +80,13 @@ static int c4iw_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
 }
 
 static int c4iw_process_mad(struct ib_device *ibdev, int mad_flags,
-			    u8 port_num, struct ib_wc *in_wc,
-			    struct ib_grh *in_grh, struct ib_mad *in_mad,
-			    struct ib_mad *out_mad)
+			    u8 port_num, const struct ib_wc *in_wc,
+			    const struct ib_grh *in_grh,
+			    const struct ib_mad_hdr *in_mad,
+			    size_t in_mad_size,
+			    struct ib_mad_hdr *out_mad,
+			    size_t *out_mad_size,
+			    u16 *out_mad_pkey_index)
 {
 	return -ENOSYS;
 }
@@ -301,13 +305,17 @@ static int c4iw_query_gid(struct ib_device *ibdev, u8 port, int index,
 	return 0;
 }
 
-static int c4iw_query_device(struct ib_device *ibdev,
-			     struct ib_device_attr *props)
+static int c4iw_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			     struct ib_udata *uhw)
 {
 
 	struct c4iw_dev *dev;
+
 	PDBG("%s ibdev %p\n", __func__, ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	dev = to_c4iw_dev(ibdev);
 	memset(props, 0, sizeof *props);
 	memcpy(&props->sys_image_guid, dev->rdev.lldi.ports[0]->dev_addr, 6);
@@ -465,6 +473,23 @@ static struct device_attribute *c4iw_class_attributes[] = {
 	&dev_attr_board_id,
 };
 
+static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = c4iw_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
+
 int c4iw_register_device(struct c4iw_dev *dev)
 {
 	int ret;
@@ -542,6 +567,7 @@ int c4iw_register_device(struct c4iw_dev *dev)
 	dev->ibdev.post_recv = c4iw_post_receive;
 	dev->ibdev.get_protocol_stats = c4iw_get_mib;
 	dev->ibdev.uverbs_abi_ver = C4IW_UVERBS_ABI_VERSION;
+	dev->ibdev.get_port_immutable = c4iw_port_immutable;
 
 	dev->ibdev.iwcm = kmalloc(sizeof(struct iw_cm_verbs), GFP_KERNEL);
 	if (!dev->ibdev.iwcm)

drivers/infiniband/hw/cxgb4/qp.c

@@ -165,6 +165,29 @@ static int destroy_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	return 0;
 }
 
+/*
+ * Determine the BAR2 virtual address and qid. If pbar2_pa is not NULL,
+ * then this is a user mapping so compute the page-aligned physical address
+ * for mapping.
+ */
+void __iomem *c4iw_bar2_addrs(struct c4iw_rdev *rdev, unsigned int qid,
+			      enum cxgb4_bar2_qtype qtype,
+			      unsigned int *pbar2_qid, u64 *pbar2_pa)
+{
+	u64 bar2_qoffset;
+	int ret;
+
+	ret = cxgb4_bar2_sge_qregs(rdev->lldi.ports[0], qid, qtype,
+				   pbar2_pa ? 1 : 0,
+				   &bar2_qoffset, pbar2_qid);
+	if (ret)
+		return NULL;
+
+	if (pbar2_pa)
+		*pbar2_pa = (rdev->bar2_pa + bar2_qoffset) & PAGE_MASK;
+	return rdev->bar2_kva + bar2_qoffset;
+}
+
 static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 		     struct t4_cq *rcq, struct t4_cq *scq,
 		     struct c4iw_dev_ucontext *uctx)
@@ -236,25 +259,23 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	dma_unmap_addr_set(&wq->rq, mapping, wq->rq.dma_addr);
 
 	wq->db = rdev->lldi.db_reg;
-	wq->gts = rdev->lldi.gts_reg;
-	if (user || is_t5(rdev->lldi.adapter_type)) {
-		u32 off;
 
-		off = (wq->sq.qid << rdev->qpshift) & PAGE_MASK;
-		if (user) {
-			wq->sq.udb = (u64 __iomem *)(rdev->bar2_pa + off);
-		} else {
-			off += 128 * (wq->sq.qid & rdev->qpmask) + 8;
-			wq->sq.udb = (u64 __iomem *)(rdev->bar2_kva + off);
-		}
-		off = (wq->rq.qid << rdev->qpshift) & PAGE_MASK;
-		if (user) {
-			wq->rq.udb = (u64 __iomem *)(rdev->bar2_pa + off);
-		} else {
-			off += 128 * (wq->rq.qid & rdev->qpmask) + 8;
-			wq->rq.udb = (u64 __iomem *)(rdev->bar2_kva + off);
-		}
+	wq->sq.bar2_va = c4iw_bar2_addrs(rdev, wq->sq.qid, T4_BAR2_QTYPE_EGRESS,
+					 &wq->sq.bar2_qid,
+					 user ? &wq->sq.bar2_pa : NULL);
+	wq->rq.bar2_va = c4iw_bar2_addrs(rdev, wq->rq.qid, T4_BAR2_QTYPE_EGRESS,
+					 &wq->rq.bar2_qid,
+					 user ? &wq->rq.bar2_pa : NULL);
+
+	/*
+	 * User mode must have bar2 access.
+	 */
+	if (user && (!wq->sq.bar2_va || !wq->rq.bar2_va)) {
+		pr_warn(MOD "%s: sqid %u or rqid %u not in BAR2 range.\n",
+			pci_name(rdev->lldi.pdev), wq->sq.qid, wq->rq.qid);
+		goto free_dma;
 	}
+
 	wq->rdev = rdev;
 	wq->rq.msn = 1;
 
@@ -336,10 +357,9 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 	if (ret)
 		goto free_dma;
 
-	PDBG("%s sqid 0x%x rqid 0x%x kdb 0x%p squdb 0x%lx rqudb 0x%lx\n",
+	PDBG("%s sqid 0x%x rqid 0x%x kdb 0x%p sq_bar2_addr %p rq_bar2_addr %p\n",
 	     __func__, wq->sq.qid, wq->rq.qid, wq->db,
-	     (__force unsigned long) wq->sq.udb,
-	     (__force unsigned long) wq->rq.udb);
+	     wq->sq.bar2_va, wq->rq.bar2_va);
 
 	return 0;
 free_dma:
@@ -1766,11 +1786,11 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		mm2->len = PAGE_ALIGN(qhp->wq.rq.memsize);
 		insert_mmap(ucontext, mm2);
 		mm3->key = uresp.sq_db_gts_key;
-		mm3->addr = (__force unsigned long)qhp->wq.sq.udb;
+		mm3->addr = (__force unsigned long)qhp->wq.sq.bar2_pa;
 		mm3->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm3);
 		mm4->key = uresp.rq_db_gts_key;
-		mm4->addr = (__force unsigned long)qhp->wq.rq.udb;
+		mm4->addr = (__force unsigned long)qhp->wq.rq.bar2_pa;
 		mm4->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm4);
 		if (mm5) {

drivers/infiniband/hw/cxgb4/t4.h

@@ -33,6 +33,7 @@
 
 #include "t4_hw.h"
 #include "t4_regs.h"
+#include "t4_values.h"
 #include "t4_msg.h"
 #include "t4fw_ri_api.h"
 
@@ -290,8 +291,10 @@ struct t4_sq {
 	unsigned long phys_addr;
 	struct t4_swsqe *sw_sq;
 	struct t4_swsqe *oldest_read;
-	u64 __iomem *udb;
+	void __iomem *bar2_va;
+	u64 bar2_pa;
 	size_t memsize;
+	u32 bar2_qid;
 	u32 qid;
 	u16 in_use;
 	u16 size;
@@ -314,8 +317,10 @@ struct t4_rq {
 	dma_addr_t dma_addr;
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 	struct t4_swrqe *sw_rq;
-	u64 __iomem *udb;
+	void __iomem *bar2_va;
+	u64 bar2_pa;
 	size_t memsize;
+	u32 bar2_qid;
 	u32 qid;
 	u32 msn;
 	u32 rqt_hwaddr;
@@ -332,7 +337,6 @@ struct t4_wq {
 	struct t4_sq sq;
 	struct t4_rq rq;
 	void __iomem *db;
-	void __iomem *gts;
 	struct c4iw_rdev *rdev;
 	int flushed;
 };
@@ -457,15 +461,18 @@ static inline void t4_ring_sq_db(struct t4_wq *wq, u16 inc, u8 t5,
 
 	/* Flush host queue memory writes. */
 	wmb();
-	if (t5) {
-		if (inc == 1 && wqe) {
+	if (wq->sq.bar2_va) {
+		if (inc == 1 && wq->sq.bar2_qid == 0 && wqe) {
 			PDBG("%s: WC wq->sq.pidx = %d\n",
 			     __func__, wq->sq.pidx);
-			pio_copy(wq->sq.udb + 7, (void *)wqe);
+			pio_copy((u64 __iomem *)
+				 (wq->sq.bar2_va + SGE_UDB_WCDOORBELL),
+				 (u64 *)wqe);
 		} else {
 			PDBG("%s: DB wq->sq.pidx = %d\n",
 			     __func__, wq->sq.pidx);
-			writel(PIDX_T5_V(inc), wq->sq.udb);
+			writel(PIDX_T5_V(inc) | QID_V(wq->sq.bar2_qid),
+			       wq->sq.bar2_va + SGE_UDB_KDOORBELL);
 		}
 
 		/* Flush user doorbell area writes. */
@@ -481,15 +488,18 @@ static inline void t4_ring_rq_db(struct t4_wq *wq, u16 inc, u8 t5,
 
 	/* Flush host queue memory writes. */
 	wmb();
-	if (t5) {
-		if (inc == 1 && wqe) {
+	if (wq->rq.bar2_va) {
+		if (inc == 1 && wq->rq.bar2_qid == 0 && wqe) {
 			PDBG("%s: WC wq->rq.pidx = %d\n",
 			     __func__, wq->rq.pidx);
-			pio_copy(wq->rq.udb + 7, (void *)wqe);
+			pio_copy((u64 __iomem *)
+				 (wq->rq.bar2_va + SGE_UDB_WCDOORBELL),
+				 (void *)wqe);
 		} else {
 			PDBG("%s: DB wq->rq.pidx = %d\n",
 			     __func__, wq->rq.pidx);
-			writel(PIDX_T5_V(inc), wq->rq.udb);
+			writel(PIDX_T5_V(inc) | QID_V(wq->rq.bar2_qid),
+			       wq->rq.bar2_va + SGE_UDB_KDOORBELL);
 		}
 
 		/* Flush user doorbell area writes. */
@@ -534,8 +544,10 @@ struct t4_cq {
 	DEFINE_DMA_UNMAP_ADDR(mapping);
 	struct t4_cqe *sw_queue;
 	void __iomem *gts;
+	void __iomem *bar2_va;
+	u64 bar2_pa;
+	u32 bar2_qid;
 	struct c4iw_rdev *rdev;
-	u64 ugts;
 	size_t memsize;
 	__be64 bits_type_ts;
 	u32 cqid;
@@ -552,6 +564,15 @@ struct t4_cq {
 	unsigned long flags;
 };
 
+static inline void write_gts(struct t4_cq *cq, u32 val)
+{
+	if (cq->bar2_va)
+		writel(val | INGRESSQID_V(cq->bar2_qid),
+		       cq->bar2_va + SGE_UDB_GTS);
+	else
+		writel(val | INGRESSQID_V(cq->cqid), cq->gts);
+}
+
 static inline int t4_clear_cq_armed(struct t4_cq *cq)
 {
 	return test_and_clear_bit(CQ_ARMED, &cq->flags);
@@ -563,14 +584,12 @@ static inline int t4_arm_cq(struct t4_cq *cq, int se)
 
 	set_bit(CQ_ARMED, &cq->flags);
 	while (cq->cidx_inc > CIDXINC_M) {
-		val = SEINTARM_V(0) | CIDXINC_V(CIDXINC_M) | TIMERREG_V(7) |
-		      INGRESSQID_V(cq->cqid & cq->qid_mask);
-		writel(val, cq->gts);
+		val = SEINTARM_V(0) | CIDXINC_V(CIDXINC_M) | TIMERREG_V(7);
+		write_gts(cq, val);
 		cq->cidx_inc -= CIDXINC_M;
 	}
-	val = SEINTARM_V(se) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(6) |
-	      INGRESSQID_V(cq->cqid & cq->qid_mask);
-	writel(val, cq->gts);
+	val = SEINTARM_V(se) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(6);
+	write_gts(cq, val);
 	cq->cidx_inc = 0;
 	return 0;
 }
@@ -601,9 +620,8 @@ static inline void t4_hwcq_consume(struct t4_cq *cq)
 	if (++cq->cidx_inc == (cq->size >> 4) || cq->cidx_inc == CIDXINC_M) {
 		u32 val;
 
-		val = SEINTARM_V(0) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(7) |
-		      INGRESSQID_V(cq->cqid & cq->qid_mask);
-		writel(val, cq->gts);
+		val = SEINTARM_V(0) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(7);
+		write_gts(cq, val);
 		cq->cidx_inc = 0;
 	}
 	if (++cq->cidx == cq->size) {

drivers/infiniband/hw/ehca/ehca_cq.c

@@ -113,10 +113,12 @@ struct ehca_qp *ehca_cq_get_qp(struct ehca_cq *cq, int real_qp_num)
 	return ret;
 }
 
-struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
+struct ib_cq *ehca_create_cq(struct ib_device *device,
+			     const struct ib_cq_init_attr *attr,
 			     struct ib_ucontext *context,
 			     struct ib_udata *udata)
 {
+	int cqe = attr->cqe;
 	static const u32 additional_cqe = 20;
 	struct ib_cq *cq;
 	struct ehca_cq *my_cq;
@@ -131,6 +133,9 @@ struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
 	int ipz_rc, i;
 	unsigned long flags;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (cqe >= 0xFFFFFFFF - 64 - additional_cqe)
 		return ERR_PTR(-EINVAL);
 

drivers/infiniband/hw/ehca/ehca_hca.c

@@ -50,7 +50,8 @@ static unsigned int limit_uint(unsigned int value)
 	return min_t(unsigned int, value, INT_MAX);
 }
 
-int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props)
+int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+		      struct ib_udata *uhw)
 {
 	int i, ret = 0;
 	struct ehca_shca *shca = container_of(ibdev, struct ehca_shca,
@@ -71,6 +72,9 @@ int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props)
 		IB_DEVICE_PORT_ACTIVE_EVENT,  HCA_CAP_PORT_ACTIVE_EVENT,
 	};
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	rblock = ehca_alloc_fw_ctrlblock(GFP_KERNEL);
 	if (!rblock) {
 		ehca_err(&shca->ib_device, "Can't allocate rblock memory.");

drivers/infiniband/hw/ehca/ehca_iverbs.h

@@ -44,11 +44,15 @@
 
 #include "ehca_classes.h"
 
-int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props);
+int ehca_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+		      struct ib_udata *uhw);
 
 int ehca_query_port(struct ib_device *ibdev, u8 port,
 		    struct ib_port_attr *props);
 
+enum rdma_protocol_type
+ehca_query_protocol(struct ib_device *device, u8 port_num);
+
 int ehca_query_sma_attr(struct ehca_shca *shca, u8 port,
 			struct ehca_sma_attr *attr);
 
@@ -126,7 +130,8 @@ int ehca_destroy_eq(struct ehca_shca *shca, struct ehca_eq *eq);
 void *ehca_poll_eq(struct ehca_shca *shca, struct ehca_eq *eq);
 
 
-struct ib_cq *ehca_create_cq(struct ib_device *device, int cqe, int comp_vector,
+struct ib_cq *ehca_create_cq(struct ib_device *device,
+			     const struct ib_cq_init_attr *attr,
 			     struct ib_ucontext *context,
 			     struct ib_udata *udata);
 
@@ -188,9 +193,10 @@ int ehca_dealloc_ucontext(struct ib_ucontext *context);
 int ehca_mmap(struct ib_ucontext *context, struct vm_area_struct *vma);
 
 int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		     struct ib_wc *in_wc, struct ib_grh *in_grh,
-		     struct ib_mad *in_mad,
-		     struct ib_mad *out_mad);
+		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		     const struct ib_mad_hdr *in, size_t in_mad_size,
+		     struct ib_mad_hdr *out, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index);
 
 void ehca_poll_eqs(unsigned long data);
 

drivers/infiniband/hw/ehca/ehca_main.c

@@ -46,6 +46,7 @@
 
 #include <linux/notifier.h>
 #include <linux/memory.h>
+#include <rdma/ib_mad.h>
 #include "ehca_classes.h"
 #include "ehca_iverbs.h"
 #include "ehca_mrmw.h"
@@ -431,6 +432,24 @@ init_node_guid1:
 	return ret;
 }
 
+static int ehca_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = ehca_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 static int ehca_init_device(struct ehca_shca *shca)
 {
 	int ret;
@@ -510,6 +529,7 @@ static int ehca_init_device(struct ehca_shca *shca)
 	shca->ib_device.process_mad	    = ehca_process_mad;
 	shca->ib_device.mmap		    = ehca_mmap;
 	shca->ib_device.dma_ops		    = &ehca_dma_mapping_ops;
+	shca->ib_device.get_port_immutable  = ehca_port_immutable;
 
 	if (EHCA_BMASK_GET(HCA_CAP_SRQ, shca->hca_cap)) {
 		shca->ib_device.uverbs_cmd_mask |=
@@ -534,6 +554,7 @@ static int ehca_create_aqp1(struct ehca_shca *shca, u32 port)
 	struct ib_cq *ibcq;
 	struct ib_qp *ibqp;
 	struct ib_qp_init_attr qp_init_attr;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	if (sport->ibcq_aqp1) {
@@ -541,7 +562,9 @@ static int ehca_create_aqp1(struct ehca_shca *shca, u32 port)
 		return -EPERM;
 	}
 
-	ibcq = ib_create_cq(&shca->ib_device, NULL, NULL, (void *)(-1), 10, 0);
+	cq_attr.cqe = 10;
+	ibcq = ib_create_cq(&shca->ib_device, NULL, NULL, (void *)(-1),
+			    &cq_attr);
 	if (IS_ERR(ibcq)) {
 		ehca_err(&shca->ib_device, "Cannot create AQP1 CQ.");
 		return PTR_ERR(ibcq);

drivers/infiniband/hw/ehca/ehca_sqp.c

@@ -140,10 +140,10 @@ struct vertcfl {
 } __attribute__ ((packed));
 
 static int ehca_process_perf(struct ib_device *ibdev, u8 port_num,
-			     struct ib_wc *in_wc, struct ib_grh *in_grh,
-			     struct ib_mad *in_mad, struct ib_mad *out_mad)
+			     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			     const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
-	struct ib_perf *in_perf = (struct ib_perf *)in_mad;
+	const struct ib_perf *in_perf = (const struct ib_perf *)in_mad;
 	struct ib_perf *out_perf = (struct ib_perf *)out_mad;
 	struct ib_class_port_info *poi =
 		(struct ib_class_port_info *)out_perf->data;
@@ -187,8 +187,8 @@ static int ehca_process_perf(struct ib_device *ibdev, u8 port_num,
 
 		/* if request was globally routed, copy route info */
 		if (in_grh) {
-			struct vertcfl *vertcfl =
-				(struct vertcfl *)&in_grh->version_tclass_flow;
+			const struct vertcfl *vertcfl =
+				(const struct vertcfl *)&in_grh->version_tclass_flow;
 			memcpy(poi->redirect_gid, in_grh->dgid.raw,
 			       sizeof(poi->redirect_gid));
 			tcslfl->tc        = vertcfl->tc;
@@ -217,10 +217,17 @@ perf_reply:
 }
 
 int ehca_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		     struct ib_wc *in_wc, struct ib_grh *in_grh,
-		     struct ib_mad *in_mad, struct ib_mad *out_mad)
+		     const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		     const struct ib_mad_hdr *in, size_t in_mad_size,
+		     struct ib_mad_hdr *out, size_t *out_mad_size,
+		     u16 *out_mad_pkey_index)
 {
 	int ret;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	if (!port_num || port_num > ibdev->phys_port_cnt || !in_wc)
 		return IB_MAD_RESULT_FAILURE;

drivers/infiniband/hw/ipath/ipath_cq.c

@@ -188,7 +188,7 @@ static void send_complete(unsigned long data)
 /**
  * ipath_create_cq - create a completion queue
  * @ibdev: the device this completion queue is attached to
- * @entries: the minimum size of the completion queue
+ * @attr: creation attributes
  * @context: unused by the InfiniPath driver
  * @udata: unused by the InfiniPath driver
  *
@@ -197,16 +197,21 @@ static void send_complete(unsigned long data)
  *
  * Called by ib_create_cq() in the generic verbs code.
  */
-struct ib_cq *ipath_create_cq(struct ib_device *ibdev, int entries, int comp_vector,
+struct ib_cq *ipath_create_cq(struct ib_device *ibdev,
+			      const struct ib_cq_init_attr *attr,
 			      struct ib_ucontext *context,
 			      struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct ipath_ibdev *dev = to_idev(ibdev);
 	struct ipath_cq *cq;
 	struct ipath_cq_wc *wc;
 	struct ib_cq *ret;
 	u32 sz;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 1 || entries > ib_ipath_max_cqes) {
 		ret = ERR_PTR(-EINVAL);
 		goto done;

drivers/infiniband/hw/ipath/ipath_mad.c

@@ -1257,7 +1257,7 @@ static int recv_pma_set_portcounters_ext(struct ib_pma_mad *pmp,
 }
 
 static int process_subn(struct ib_device *ibdev, int mad_flags,
-			u8 port_num, struct ib_mad *in_mad,
+			u8 port_num, const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_smp *smp = (struct ib_smp *)out_mad;
@@ -1389,7 +1389,7 @@ bail:
 }
 
 static int process_perf(struct ib_device *ibdev, u8 port_num,
-			struct ib_mad *in_mad,
+			const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_pma_mad *pmp = (struct ib_pma_mad *)out_mad;
@@ -1490,10 +1490,17 @@ bail:
  * This is called by the ib_mad module.
  */
 int ipath_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		      struct ib_wc *in_wc, struct ib_grh *in_grh,
-		      struct ib_mad *in_mad, struct ib_mad *out_mad)
+		      const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index)
 {
 	int ret;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:

drivers/infiniband/hw/ipath/ipath_verbs.c

@@ -1495,11 +1495,14 @@ bail:
 	return 0;
 }
 
-static int ipath_query_device(struct ib_device *ibdev,
-			      struct ib_device_attr *props)
+static int ipath_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			      struct ib_udata *uhw)
 {
 	struct ipath_ibdev *dev = to_idev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	memset(props, 0, sizeof(*props));
 
 	props->device_cap_flags = IB_DEVICE_BAD_PKEY_CNTR |
@@ -1980,6 +1983,24 @@ static int disable_timer(struct ipath_devdata *dd)
 	return 0;
 }
 
+static int ipath_port_immutable(struct ib_device *ibdev, u8 port_num,
+			        struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = ipath_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 /**
  * ipath_register_ib_device - register our device with the infiniband core
  * @dd: the device data structure
@@ -2179,6 +2200,7 @@ int ipath_register_ib_device(struct ipath_devdata *dd)
 	dev->process_mad = ipath_process_mad;
 	dev->mmap = ipath_mmap;
 	dev->dma_ops = &ipath_dma_mapping_ops;
+	dev->get_port_immutable = ipath_port_immutable;
 
 	snprintf(dev->node_desc, sizeof(dev->node_desc),
 		 IPATH_IDSTR " %s", init_utsname()->nodename);

drivers/infiniband/hw/ipath/ipath_verbs.h

@@ -701,9 +701,11 @@ static inline void ipath_schedule_send(struct ipath_qp *qp)
 int ipath_process_mad(struct ib_device *ibdev,
 		      int mad_flags,
 		      u8 port_num,
-		      struct ib_wc *in_wc,
-		      struct ib_grh *in_grh,
-		      struct ib_mad *in_mad, struct ib_mad *out_mad);
+		      const struct ib_wc *in_wc,
+		      const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index);
 
 /*
  * Compare the lower 24 bits of the two values.
@@ -807,7 +809,8 @@ void ipath_cq_enter(struct ipath_cq *cq, struct ib_wc *entry, int sig);
 
 int ipath_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry);
 
-struct ib_cq *ipath_create_cq(struct ib_device *ibdev, int entries, int comp_vector,
+struct ib_cq *ipath_create_cq(struct ib_device *ibdev,
+			      const struct ib_cq_init_attr *attr,
 			      struct ib_ucontext *context,
 			      struct ib_udata *udata);
 

drivers/infiniband/hw/mlx4/cq.c

@@ -166,10 +166,14 @@ err_buf:
 	return err;
 }
 
-struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector,
+#define CQ_CREATE_FLAGS_SUPPORTED IB_CQ_FLAGS_TIMESTAMP_COMPLETION
+struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
 				struct ib_ucontext *context,
 				struct ib_udata *udata)
 {
+	int entries = attr->cqe;
+	int vector = attr->comp_vector;
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct mlx4_ib_cq *cq;
 	struct mlx4_uar *uar;
@@ -178,6 +182,9 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	if (entries < 1 || entries > dev->dev->caps.max_cqes)
 		return ERR_PTR(-EINVAL);
 
+	if (attr->flags & ~CQ_CREATE_FLAGS_SUPPORTED)
+		return ERR_PTR(-EINVAL);
+
 	cq = kmalloc(sizeof *cq, GFP_KERNEL);
 	if (!cq)
 		return ERR_PTR(-ENOMEM);
@@ -188,6 +195,7 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	spin_lock_init(&cq->lock);
 	cq->resize_buf = NULL;
 	cq->resize_umem = NULL;
+	cq->create_flags = attr->flags;
 	INIT_LIST_HEAD(&cq->send_qp_list);
 	INIT_LIST_HEAD(&cq->recv_qp_list);
 
@@ -231,7 +239,8 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 		vector = dev->eq_table[vector % ibdev->num_comp_vectors];
 
 	err = mlx4_cq_alloc(dev->dev, entries, &cq->buf.mtt, uar,
-			    cq->db.dma, &cq->mcq, vector, 0, 0);
+			    cq->db.dma, &cq->mcq, vector, 0,
+			    !!(cq->create_flags & IB_CQ_FLAGS_TIMESTAMP_COMPLETION));
 	if (err)
 		goto err_dbmap;
 

drivers/infiniband/hw/mlx4/mad.c

@@ -111,8 +111,9 @@ __be64 mlx4_ib_get_new_demux_tid(struct mlx4_ib_demux_ctx *ctx)
 }
 
 int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
-		 int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad)
+		 int port, const struct ib_wc *in_wc,
+		 const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad)
 {
 	struct mlx4_cmd_mailbox *inmailbox, *outmailbox;
 	void *inbox;
@@ -220,7 +221,7 @@ static void update_sm_ah(struct mlx4_ib_dev *dev, u8 port_num, u16 lid, u8 sl)
  * Snoop SM MADs for port info, GUID info, and  P_Key table sets, so we can
  * synthesize LID change, Client-Rereg, GID change, and P_Key change events.
  */
-static void smp_snoop(struct ib_device *ibdev, u8 port_num, struct ib_mad *mad,
+static void smp_snoop(struct ib_device *ibdev, u8 port_num, const struct ib_mad *mad,
 		      u16 prev_lid)
 {
 	struct ib_port_info *pinfo;
@@ -356,7 +357,7 @@ static void node_desc_override(struct ib_device *dev,
 	}
 }
 
-static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *mad)
+static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, const struct ib_mad *mad)
 {
 	int qpn = mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED;
 	struct ib_mad_send_buf *send_buf;
@@ -366,7 +367,8 @@ static void forward_trap(struct mlx4_ib_dev *dev, u8 port_num, struct ib_mad *ma
 
 	if (agent) {
 		send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
-					      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+					      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+					      IB_MGMT_BASE_VERSION);
 		if (IS_ERR(send_buf))
 			return;
 		/*
@@ -722,8 +724,8 @@ static int mlx4_ib_demux_mad(struct ib_device *ibdev, u8 port,
 }
 
 static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
 	u16 slid, prev_lid = 0;
 	int err;
@@ -825,8 +827,8 @@ static void edit_counter(struct mlx4_counter *cnt,
 }
 
 static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad *in_mad, struct ib_mad *out_mad)
 {
 	struct mlx4_cmd_mailbox *mailbox;
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
@@ -866,9 +868,17 @@ static int iboe_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 }
 
 int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index)
 {
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
+
 	switch (rdma_port_get_link_layer(ibdev, port_num)) {
 	case IB_LINK_LAYER_INFINIBAND:
 		return ib_process_mad(ibdev, mad_flags, port_num, in_wc,
@@ -1773,6 +1783,7 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
 			       int create_tun, struct mlx4_ib_demux_pv_ctx *ctx)
 {
 	int ret, cq_size;
+	struct ib_cq_init_attr cq_attr = {};
 
 	if (ctx->state != DEMUX_PV_STATE_DOWN)
 		return -EEXIST;
@@ -1801,8 +1812,9 @@ static int create_pv_resources(struct ib_device *ibdev, int slave, int port,
 	if (ctx->has_smi)
 		cq_size *= 2;
 
+	cq_attr.cqe = cq_size;
 	ctx->cq = ib_create_cq(ctx->ib_dev, mlx4_ib_tunnel_comp_handler,
-			       NULL, ctx, cq_size, 0);
+			       NULL, ctx, &cq_attr);
 	if (IS_ERR(ctx->cq)) {
 		ret = PTR_ERR(ctx->cq);
 		pr_err("Couldn't create tunnel CQ (%d)\n", ret);

drivers/infiniband/hw/mlx4/main.c

@@ -132,14 +132,35 @@ static int num_ib_ports(struct mlx4_dev *dev)
 }
 
 static int mlx4_ib_query_device(struct ib_device *ibdev,
-				struct ib_device_attr *props)
+				struct ib_device_attr *props,
+				struct ib_udata *uhw)
 {
 	struct mlx4_ib_dev *dev = to_mdev(ibdev);
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
 	int err = -ENOMEM;
 	int have_ib_ports;
+	struct mlx4_uverbs_ex_query_device cmd;
+	struct mlx4_uverbs_ex_query_device_resp resp = {.comp_mask = 0};
+	struct mlx4_clock_params clock_params;
 
+	if (uhw->inlen) {
+		if (uhw->inlen < sizeof(cmd))
+			return -EINVAL;
+
+		err = ib_copy_from_udata(&cmd, uhw, sizeof(cmd));
+		if (err)
+			return err;
+
+		if (cmd.comp_mask)
+			return -EINVAL;
+
+		if (cmd.reserved)
+			return -EINVAL;
+	}
+
+	resp.response_length = offsetof(typeof(resp), response_length) +
+		sizeof(resp.response_length);
 	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
 	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
 	if (!in_mad || !out_mad)
@@ -229,7 +250,24 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 	props->max_total_mcast_qp_attach = props->max_mcast_qp_attach *
 					   props->max_mcast_grp;
 	props->max_map_per_fmr = dev->dev->caps.max_fmr_maps;
+	props->hca_core_clock = dev->dev->caps.hca_core_clock * 1000UL;
+	props->timestamp_mask = 0xFFFFFFFFFFFFULL;
+
+	err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
+	if (err)
+		goto out;
+
+	if (uhw->outlen >= resp.response_length + sizeof(resp.hca_core_clock_offset)) {
+		resp.hca_core_clock_offset = clock_params.offset % PAGE_SIZE;
+		resp.response_length += sizeof(resp.hca_core_clock_offset);
+		resp.comp_mask |= QUERY_DEVICE_RESP_MASK_TIMESTAMP;
+	}
 
+	if (uhw->outlen) {
+		err = ib_copy_to_udata(uhw, &resp, resp.response_length);
+		if (err)
+			goto out;
+	}
 out:
 	kfree(in_mad);
 	kfree(out_mad);
@@ -712,8 +750,24 @@ static int mlx4_ib_mmap(struct ib_ucontext *context, struct vm_area_struct *vma)
 				       dev->dev->caps.num_uars,
 				       PAGE_SIZE, vma->vm_page_prot))
 			return -EAGAIN;
-	} else
+	} else if (vma->vm_pgoff == 3) {
+		struct mlx4_clock_params params;
+		int ret = mlx4_get_internal_clock_params(dev->dev, &params);
+
+		if (ret)
+			return ret;
+
+		vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+		if (io_remap_pfn_range(vma, vma->vm_start,
+				       (pci_resource_start(dev->dev->persist->pdev,
+							   params.bar) +
+					params.offset)
+				       >> PAGE_SHIFT,
+				       PAGE_SIZE, vma->vm_page_prot))
+			return -EAGAIN;
+	} else {
 		return -EINVAL;
+	}
 
 	return 0;
 }
@@ -758,6 +812,7 @@ static struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev,
 					  struct ib_udata *udata)
 {
 	struct mlx4_ib_xrcd *xrcd;
+	struct ib_cq_init_attr cq_attr = {};
 	int err;
 
 	if (!(to_mdev(ibdev)->dev->caps.flags & MLX4_DEV_CAP_FLAG_XRC))
@@ -777,7 +832,8 @@ static struct ib_xrcd *mlx4_ib_alloc_xrcd(struct ib_device *ibdev,
 		goto err2;
 	}
 
-	xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, 1, 0);
+	cq_attr.cqe = 1;
+	xrcd->cq = ib_create_cq(ibdev, NULL, NULL, xrcd, &cq_attr);
 	if (IS_ERR(xrcd->cq)) {
 		err = PTR_ERR(xrcd->cq);
 		goto err3;
@@ -1185,7 +1241,6 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 					    &mflow->reg_id[i].id);
 		if (err)
 			goto err_create_flow;
-		i++;
 		if (is_bonded) {
 			/* Application always sees one port so the mirror rule
 			 * must be on port #2
@@ -1200,6 +1255,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 			j++;
 		}
 
+		i++;
 	}
 
 	if (i < ARRAY_SIZE(type) && flow_attr->type == IB_FLOW_ATTR_NORMAL) {
@@ -1207,7 +1263,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 					       &mflow->reg_id[i].id);
 		if (err)
 			goto err_create_flow;
-		i++;
+
 		if (is_bonded) {
 			flow_attr->port = 2;
 			err = mlx4_ib_tunnel_steer_add(qp, flow_attr,
@@ -1218,6 +1274,7 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 			j++;
 		}
 		/* function to create mirror rule */
+		i++;
 	}
 
 	return &mflow->ibflow;
@@ -2114,6 +2171,29 @@ static void mlx4_ib_free_eqs(struct mlx4_dev *dev, struct mlx4_ib_dev *ibdev)
 	kfree(ibdev->eq_table);
 }
 
+static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = mlx4_ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+
+	if (mlx4_ib_port_link_layer(ibdev, port_num) == IB_LINK_LAYER_INFINIBAND)
+		immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	else
+		immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 static void *mlx4_ib_add(struct mlx4_dev *dev)
 {
 	struct mlx4_ib_dev *ibdev;
@@ -2241,6 +2321,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.attach_mcast	= mlx4_ib_mcg_attach;
 	ibdev->ib_dev.detach_mcast	= mlx4_ib_mcg_detach;
 	ibdev->ib_dev.process_mad	= mlx4_ib_process_mad;
+	ibdev->ib_dev.get_port_immutable = mlx4_port_immutable;
 
 	if (!mlx4_is_slave(ibdev->dev)) {
 		ibdev->ib_dev.alloc_fmr		= mlx4_ib_fmr_alloc;
@@ -2278,6 +2359,10 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 			(1ull << IB_USER_VERBS_EX_CMD_DESTROY_FLOW);
 	}
 
+	ibdev->ib_dev.uverbs_ex_cmd_mask |=
+		(1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE) |
+		(1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ);
+
 	mlx4_ib_alloc_eqs(dev, ibdev);
 
 	spin_lock_init(&iboe->lock);

drivers/infiniband/hw/mlx4/mlx4_ib.h

@@ -110,6 +110,7 @@ struct mlx4_ib_cq {
 	struct mutex		resize_mutex;
 	struct ib_umem	       *umem;
 	struct ib_umem	       *resize_umem;
+	int			create_flags;
 	/* List of qps that it serves.*/
 	struct list_head		send_qp_list;
 	struct list_head		recv_qp_list;
@@ -555,6 +556,21 @@ struct mlx4_ib_qp_tunnel_init_attr {
 	u8 port;
 };
 
+struct mlx4_uverbs_ex_query_device {
+	__u32 comp_mask;
+	__u32 reserved;
+};
+
+enum query_device_resp_mask {
+	QUERY_DEVICE_RESP_MASK_TIMESTAMP = 1UL << 0,
+};
+
+struct mlx4_uverbs_ex_query_device_resp {
+	__u32 comp_mask;
+	__u32 response_length;
+	__u64 hca_core_clock_offset;
+};
+
 static inline struct mlx4_ib_dev *to_mdev(struct ib_device *ibdev)
 {
 	return container_of(ibdev, struct mlx4_ib_dev, ib_dev);
@@ -668,7 +684,8 @@ void mlx4_ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
 
 int mlx4_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 int mlx4_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata);
-struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector,
+struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
 				struct ib_ucontext *context,
 				struct ib_udata *udata);
 int mlx4_ib_destroy_cq(struct ib_cq *cq);
@@ -706,11 +723,13 @@ int mlx4_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 		      struct ib_recv_wr **bad_wr);
 
 int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
-		 int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad);
+		 int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad);
 int mlx4_ib_process_mad(struct ib_device *ibdev, int mad_flags,	u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad);
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index);
 int mlx4_ib_mad_init(struct mlx4_ib_dev *dev);
 void mlx4_ib_mad_cleanup(struct mlx4_ib_dev *dev);
 

drivers/infiniband/hw/mlx5/cq.c

@@ -736,10 +736,13 @@ static void destroy_cq_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq)
 	mlx5_db_free(dev->mdev, &cq->db);
 }
 
-struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
-				int vector, struct ib_ucontext *context,
+struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
+				struct ib_ucontext *context,
 				struct ib_udata *udata)
 {
+	int entries = attr->cqe;
+	int vector = attr->comp_vector;
 	struct mlx5_create_cq_mbox_in *cqb = NULL;
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct mlx5_ib_cq *cq;
@@ -750,6 +753,9 @@ struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
 	int eqn;
 	int err;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 0)
 		return ERR_PTR(-EINVAL);
 

drivers/infiniband/hw/mlx5/mad.c

@@ -41,8 +41,8 @@ enum {
 };
 
 int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
-		 u8 port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad)
+		 u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad)
 {
 	u8 op_modifier = 0;
 
@@ -58,11 +58,18 @@ int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
 }
 
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad)
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index)
 {
 	u16 slid;
 	int err;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 

drivers/infiniband/hw/mlx5/main.c

@@ -63,7 +63,8 @@ static char mlx5_version[] =
 	DRIVER_VERSION " (" DRIVER_RELDATE ")\n";
 
 static int mlx5_ib_query_device(struct ib_device *ibdev,
-				struct ib_device_attr *props)
+				struct ib_device_attr *props,
+				struct ib_udata *uhw)
 {
 	struct mlx5_ib_dev *dev = to_mdev(ibdev);
 	struct ib_smp *in_mad  = NULL;
@@ -74,6 +75,9 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 	int max_sq_sg;
 	u64 flags;
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	gen = &dev->mdev->caps.gen;
 	in_mad  = kzalloc(sizeof(*in_mad), GFP_KERNEL);
 	out_mad = kmalloc(sizeof(*out_mad), GFP_KERNEL);
@@ -910,6 +914,7 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	struct mlx5_general_caps *gen;
 	int err = -ENOMEM;
 	int port;
+	struct ib_udata uhw = {.inlen = 0, .outlen = 0};
 
 	gen = &dev->mdev->caps.gen;
 	pprops = kmalloc(sizeof(*pprops), GFP_KERNEL);
@@ -920,7 +925,7 @@ static int get_port_caps(struct mlx5_ib_dev *dev)
 	if (!dprops)
 		goto out;
 
-	err = mlx5_ib_query_device(&dev->ib_dev, dprops);
+	err = mlx5_ib_query_device(&dev->ib_dev, dprops, &uhw);
 	if (err) {
 		mlx5_ib_warn(dev, "query_device failed %d\n", err);
 		goto out;
@@ -971,6 +976,7 @@ static int create_umr_res(struct mlx5_ib_dev *dev)
 	struct ib_cq *cq;
 	struct ib_qp *qp;
 	struct ib_mr *mr;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	attr = kzalloc(sizeof(*attr), GFP_KERNEL);
@@ -994,8 +1000,9 @@ static int create_umr_res(struct mlx5_ib_dev *dev)
 		goto error_1;
 	}
 
-	cq = ib_create_cq(&dev->ib_dev, mlx5_umr_cq_handler, NULL, NULL, 128,
-			  0);
+	cq_attr.cqe = 128;
+	cq = ib_create_cq(&dev->ib_dev, mlx5_umr_cq_handler, NULL, NULL,
+			  &cq_attr);
 	if (IS_ERR(cq)) {
 		mlx5_ib_dbg(dev, "Couldn't create CQ for sync UMR QP\n");
 		ret = PTR_ERR(cq);
@@ -1087,6 +1094,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 {
 	struct ib_srq_init_attr attr;
 	struct mlx5_ib_dev *dev;
+	struct ib_cq_init_attr cq_attr = {.cqe = 1};
 	int ret = 0;
 
 	dev = container_of(devr, struct mlx5_ib_dev, devr);
@@ -1100,7 +1108,7 @@ static int create_dev_resources(struct mlx5_ib_resources *devr)
 	devr->p0->uobject = NULL;
 	atomic_set(&devr->p0->usecnt, 0);
 
-	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, 1, 0, NULL, NULL);
+	devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, &cq_attr, NULL, NULL);
 	if (IS_ERR(devr->c0)) {
 		ret = PTR_ERR(devr->c0);
 		goto error1;
@@ -1182,6 +1190,24 @@ static void destroy_dev_resources(struct mlx5_ib_resources *devr)
 	mlx5_ib_dealloc_pd(devr->p0);
 }
 
+static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
+			       struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = mlx5_ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_dev *dev;
@@ -1285,6 +1311,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.alloc_fast_reg_page_list = mlx5_ib_alloc_fast_reg_page_list;
 	dev->ib_dev.free_fast_reg_page_list  = mlx5_ib_free_fast_reg_page_list;
 	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
+	dev->ib_dev.get_port_immutable  = mlx5_port_immutable;
 
 	mlx5_ib_internal_query_odp_caps(dev);
 

drivers/infiniband/hw/mlx5/mlx5_ib.h

@@ -525,8 +525,8 @@ void __mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq)
 void mlx5_ib_cq_clean(struct mlx5_ib_cq *cq, u32 qpn, struct mlx5_ib_srq *srq);
 void mlx5_ib_free_srq_wqe(struct mlx5_ib_srq *srq, int wqe_index);
 int mlx5_MAD_IFC(struct mlx5_ib_dev *dev, int ignore_mkey, int ignore_bkey,
-		 u8 port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		 void *in_mad, void *response_mad);
+		 u8 port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		 const void *in_mad, void *response_mad);
 struct ib_ah *create_ib_ah(struct ib_ah_attr *ah_attr,
 			   struct mlx5_ib_ah *ah);
 struct ib_ah *mlx5_ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
@@ -556,8 +556,9 @@ int mlx5_ib_post_recv(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 void *mlx5_get_send_wqe(struct mlx5_ib_qp *qp, int n);
 int mlx5_ib_read_user_wqe(struct mlx5_ib_qp *qp, int send, int wqe_index,
 			  void *buffer, u32 length);
-struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, int entries,
-				int vector, struct ib_ucontext *context,
+struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev,
+				const struct ib_cq_init_attr *attr,
+				struct ib_ucontext *context,
 				struct ib_udata *udata);
 int mlx5_ib_destroy_cq(struct ib_cq *cq);
 int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc);
@@ -586,8 +587,10 @@ int mlx5_ib_map_phys_fmr(struct ib_fmr *ibfmr, u64 *page_list,
 int mlx5_ib_unmap_fmr(struct list_head *fmr_list);
 int mlx5_ib_fmr_dealloc(struct ib_fmr *ibfmr);
 int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-			struct ib_wc *in_wc, struct ib_grh *in_grh,
-			struct ib_mad *in_mad, struct ib_mad *out_mad);
+			const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+			const struct ib_mad_hdr *in, size_t in_mad_size,
+			struct ib_mad_hdr *out, size_t *out_mad_size,
+			u16 *out_mad_pkey_index);
 struct ib_xrcd *mlx5_ib_alloc_xrcd(struct ib_device *ibdev,
 					  struct ib_ucontext *context,
 					  struct ib_udata *udata);

drivers/infiniband/hw/mthca/mthca_cmd.c

@@ -1858,8 +1858,8 @@ int mthca_CONF_SPECIAL_QP(struct mthca_dev *dev, int type, u32 qpn)
 }
 
 int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
-		  int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		  void *in_mad, void *response_mad)
+		  int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		  const void *in_mad, void *response_mad)
 {
 	struct mthca_mailbox *inmailbox, *outmailbox;
 	void *inbox;

drivers/infiniband/hw/mthca/mthca_cmd.h

@@ -312,8 +312,8 @@ int mthca_QUERY_QP(struct mthca_dev *dev, u32 num, int is_ee,
 		   struct mthca_mailbox *mailbox);
 int mthca_CONF_SPECIAL_QP(struct mthca_dev *dev, int type, u32 qpn);
 int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
-		  int port, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		  void *in_mad, void *response_mad);
+		  int port, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		  const void *in_mad, void *response_mad);
 int mthca_READ_MGM(struct mthca_dev *dev, int index,
 		   struct mthca_mailbox *mailbox);
 int mthca_WRITE_MGM(struct mthca_dev *dev, int index,

drivers/infiniband/hw/mthca/mthca_dev.h

@@ -576,10 +576,11 @@ int mthca_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid);
 int mthca_process_mad(struct ib_device *ibdev,
 		      int mad_flags,
 		      u8 port_num,
-		      struct ib_wc *in_wc,
-		      struct ib_grh *in_grh,
-		      struct ib_mad *in_mad,
-		      struct ib_mad *out_mad);
+		      const struct ib_wc *in_wc,
+		      const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index);
 int mthca_create_agents(struct mthca_dev *dev);
 void mthca_free_agents(struct mthca_dev *dev);
 

drivers/infiniband/hw/mthca/mthca_mad.c

@@ -104,7 +104,7 @@ static void update_sm_ah(struct mthca_dev *dev,
  */
 static void smp_snoop(struct ib_device *ibdev,
 		      u8 port_num,
-		      struct ib_mad *mad,
+		      const struct ib_mad *mad,
 		      u16 prev_lid)
 {
 	struct ib_event event;
@@ -160,7 +160,7 @@ static void node_desc_override(struct ib_device *dev,
 
 static void forward_trap(struct mthca_dev *dev,
 			 u8 port_num,
-			 struct ib_mad *mad)
+			 const struct ib_mad *mad)
 {
 	int qpn = mad->mad_hdr.mgmt_class != IB_MGMT_CLASS_SUBN_LID_ROUTED;
 	struct ib_mad_send_buf *send_buf;
@@ -170,7 +170,8 @@ static void forward_trap(struct mthca_dev *dev,
 
 	if (agent) {
 		send_buf = ib_create_send_mad(agent, qpn, 0, 0, IB_MGMT_MAD_HDR,
-					      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+					      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+					      IB_MGMT_BASE_VERSION);
 		if (IS_ERR(send_buf))
 			return;
 		/*
@@ -195,15 +196,21 @@ static void forward_trap(struct mthca_dev *dev,
 int mthca_process_mad(struct ib_device *ibdev,
 		      int mad_flags,
 		      u8 port_num,
-		      struct ib_wc *in_wc,
-		      struct ib_grh *in_grh,
-		      struct ib_mad *in_mad,
-		      struct ib_mad *out_mad)
+		      const struct ib_wc *in_wc,
+		      const struct ib_grh *in_grh,
+		      const struct ib_mad_hdr *in, size_t in_mad_size,
+		      struct ib_mad_hdr *out, size_t *out_mad_size,
+		      u16 *out_mad_pkey_index)
 {
 	int err;
 	u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	/* Forward locally generated traps to the SM */
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP &&

drivers/infiniband/hw/mthca/mthca_profile.c

@@ -77,7 +77,6 @@ s64 mthca_make_profile(struct mthca_dev *dev,
 	u64 mem_base, mem_avail;
 	s64 total_size = 0;
 	struct mthca_resource *profile;
-	struct mthca_resource tmp;
 	int i, j;
 
 	profile = kzalloc(MTHCA_RES_NUM * sizeof *profile, GFP_KERNEL);
@@ -136,11 +135,8 @@ s64 mthca_make_profile(struct mthca_dev *dev,
 	 */
 	for (i = MTHCA_RES_NUM; i > 0; --i)
 		for (j = 1; j < i; ++j) {
-			if (profile[j].size > profile[j - 1].size) {
-				tmp            = profile[j];
-				profile[j]     = profile[j - 1];
-				profile[j - 1] = tmp;
-			}
+			if (profile[j].size > profile[j - 1].size)
+				swap(profile[j], profile[j - 1]);
 		}
 
 	for (i = 0; i < MTHCA_RES_NUM; ++i) {

drivers/infiniband/hw/mthca/mthca_provider.c

@@ -57,14 +57,17 @@ static void init_query_mad(struct ib_smp *mad)
 	mad->method    	   = IB_MGMT_METHOD_GET;
 }
 
-static int mthca_query_device(struct ib_device *ibdev,
-			      struct ib_device_attr *props)
+static int mthca_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			      struct ib_udata *uhw)
 {
 	struct ib_smp *in_mad  = NULL;
 	struct ib_smp *out_mad = NULL;
 	int err = -ENOMEM;
 	struct mthca_dev *mdev = to_mdev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	in_mad  = kzalloc(sizeof *in_mad, GFP_KERNEL);
 	out_mad = kmalloc(sizeof *out_mad, GFP_KERNEL);
 	if (!in_mad || !out_mad)
@@ -641,16 +644,20 @@ static int mthca_destroy_qp(struct ib_qp *qp)
 	return 0;
 }
 
-static struct ib_cq *mthca_create_cq(struct ib_device *ibdev, int entries,
-				     int comp_vector,
+static struct ib_cq *mthca_create_cq(struct ib_device *ibdev,
+				     const struct ib_cq_init_attr *attr,
 				     struct ib_ucontext *context,
 				     struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct mthca_create_cq ucmd;
 	struct mthca_cq *cq;
 	int nent;
 	int err;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 1 || entries > to_mdev(ibdev)->limits.max_cqes)
 		return ERR_PTR(-EINVAL);
 
@@ -1244,6 +1251,24 @@ out:
 	return err;
 }
 
+static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num,
+			        struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = mthca_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 int mthca_register_device(struct mthca_dev *dev)
 {
 	int ret;
@@ -1323,6 +1348,7 @@ int mthca_register_device(struct mthca_dev *dev)
 	dev->ib_dev.reg_phys_mr          = mthca_reg_phys_mr;
 	dev->ib_dev.reg_user_mr          = mthca_reg_user_mr;
 	dev->ib_dev.dereg_mr             = mthca_dereg_mr;
+	dev->ib_dev.get_port_immutable   = mthca_port_immutable;
 
 	if (dev->mthca_flags & MTHCA_FLAG_FMR) {
 		dev->ib_dev.alloc_fmr            = mthca_alloc_fmr;

drivers/infiniband/hw/nes/nes_cm.c

@@ -1616,6 +1616,8 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 		  &cm_node->loc_addr, cm_node->loc_port,
 		  &cm_node->rem_addr, cm_node->rem_port);
 	cm_node->listener = listener;
+	if (listener)
+		cm_node->tos = listener->tos;
 	cm_node->netdev = nesvnic->netdev;
 	cm_node->cm_id = cm_info->cm_id;
 	memcpy(cm_node->loc_mac, nesvnic->netdev->dev_addr, ETH_ALEN);
@@ -2938,6 +2940,9 @@ static int nes_cm_init_tsa_conn(struct nes_qp *nesqp, struct nes_cm_node *cm_nod
 
 	nesqp->nesqp_context->misc2 |= cpu_to_le32(64 << NES_QPCONTEXT_MISC2_TTL_SHIFT);
 
+	nesqp->nesqp_context->misc2 |= cpu_to_le32(
+		cm_node->tos << NES_QPCONTEXT_MISC2_TOS_SHIFT);
+
 	nesqp->nesqp_context->mss |= cpu_to_le32(((u32)cm_node->tcp_cntxt.mss) << 16);
 
 	nesqp->nesqp_context->tcp_state_flow_label |= cpu_to_le32(
@@ -3612,6 +3617,7 @@ int nes_connect(struct iw_cm_id *cm_id, struct iw_cm_conn_param *conn_param)
 		cm_node->ord_size = 1;
 
 	cm_node->apbvt_set = apbvt_set;
+	cm_node->tos = cm_id->tos;
 	nesqp->cm_node = cm_node;
 	cm_node->nesqp = nesqp;
 	nes_add_ref(&nesqp->ibqp);
@@ -3666,6 +3672,7 @@ int nes_create_listen(struct iw_cm_id *cm_id, int backlog)
 	}
 
 	cm_id->provider_data = cm_node;
+	cm_node->tos = cm_id->tos;
 
 	if (!cm_node->reused_node) {
 		if (nes_create_mapinfo(&cm_info))

drivers/infiniband/hw/nes/nes_cm.h

@@ -303,6 +303,7 @@ struct nes_cm_listener {
 	int                        backlog;
 	enum nes_cm_listener_state listener_state;
 	u32                        reused_node;
+	u8			   tos;
 };
 
 /* per connection node and node state information */
@@ -352,6 +353,7 @@ struct nes_cm_node {
 	struct list_head	reset_entry;
 	struct nes_qp		*nesqp;
 	atomic_t 		passive_state;
+	u8			tos;
 };
 
 /* structure for client or CM to fill when making CM api calls. */

drivers/infiniband/hw/nes/nes_verbs.c

@@ -512,12 +512,16 @@ static void nes_free_fast_reg_page_list(struct ib_fast_reg_page_list *pifrpl)
 /**
  * nes_query_device
  */
-static int nes_query_device(struct ib_device *ibdev, struct ib_device_attr *props)
+static int nes_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			    struct ib_udata *uhw)
 {
 	struct nes_vnic *nesvnic = to_nesvnic(ibdev);
 	struct nes_device *nesdev = nesvnic->nesdev;
 	struct nes_ib_device *nesibdev = nesvnic->nesibdev;
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	memset(props, 0, sizeof(*props));
 	memcpy(&props->sys_image_guid, nesvnic->netdev->dev_addr, 6);
 
@@ -606,7 +610,6 @@ static int nes_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr
 	return 0;
 }
 
-
 /**
  * nes_query_pkey
  */
@@ -1527,10 +1530,12 @@ static int nes_destroy_qp(struct ib_qp *ibqp)
 /**
  * nes_create_cq
  */
-static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
-		int comp_vector,
-		struct ib_ucontext *context, struct ib_udata *udata)
+static struct ib_cq *nes_create_cq(struct ib_device *ibdev,
+				   const struct ib_cq_init_attr *attr,
+				   struct ib_ucontext *context,
+				   struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	u64 u64temp;
 	struct nes_vnic *nesvnic = to_nesvnic(ibdev);
 	struct nes_device *nesdev = nesvnic->nesdev;
@@ -1550,6 +1555,9 @@ static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
 	unsigned long flags;
 	int ret;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries > nesadapter->max_cqe)
 		return ERR_PTR(-EINVAL);
 
@@ -3222,8 +3230,10 @@ static int nes_multicast_detach(struct ib_qp *ibqp, union ib_gid *gid, u16 lid)
  * nes_process_mad
  */
 static int nes_process_mad(struct ib_device *ibdev, int mad_flags,
-		u8 port_num, struct ib_wc *in_wc, struct ib_grh *in_grh,
-		struct ib_mad *in_mad, struct ib_mad *out_mad)
+		u8 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		const struct ib_mad_hdr *in, size_t in_mad_size,
+		struct ib_mad_hdr *out, size_t *out_mad_size,
+		u16 *out_mad_pkey_index)
 {
 	nes_debug(NES_DBG_INIT, "\n");
 	return -ENOSYS;
@@ -3828,6 +3838,22 @@ static int nes_req_notify_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags notify_
 	return 0;
 }
 
+static int nes_port_immutable(struct ib_device *ibdev, u8 port_num,
+			      struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = nes_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IWARP;
+
+	return 0;
+}
 
 /**
  * nes_init_ofa_device
@@ -3928,6 +3954,7 @@ struct nes_ib_device *nes_init_ofa_device(struct net_device *netdev)
 	nesibdev->ibdev.iwcm->reject = nes_reject;
 	nesibdev->ibdev.iwcm->create_listen = nes_create_listen;
 	nesibdev->ibdev.iwcm->destroy_listen = nes_destroy_listen;
+	nesibdev->ibdev.get_port_immutable   = nes_port_immutable;
 
 	return nesibdev;
 }

drivers/infiniband/hw/ocrdma/ocrdma_ah.c

@@ -204,12 +204,19 @@ int ocrdma_modify_ah(struct ib_ah *ibah, struct ib_ah_attr *attr)
 int ocrdma_process_mad(struct ib_device *ibdev,
 		       int process_mad_flags,
 		       u8 port_num,
-		       struct ib_wc *in_wc,
-		       struct ib_grh *in_grh,
-		       struct ib_mad *in_mad, struct ib_mad *out_mad)
+		       const struct ib_wc *in_wc,
+		       const struct ib_grh *in_grh,
+		       const struct ib_mad_hdr *in, size_t in_mad_size,
+		       struct ib_mad_hdr *out, size_t *out_mad_size,
+		       u16 *out_mad_pkey_index)
 {
 	int status;
 	struct ocrdma_dev *dev;
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_PERF_MGMT:

drivers/infiniband/hw/ocrdma/ocrdma_ah.h

@@ -42,7 +42,9 @@ int ocrdma_modify_ah(struct ib_ah *, struct ib_ah_attr *);
 int ocrdma_process_mad(struct ib_device *,
 		       int process_mad_flags,
 		       u8 port_num,
-		       struct ib_wc *in_wc,
-		       struct ib_grh *in_grh,
-		       struct ib_mad *in_mad, struct ib_mad *out_mad);
+		       const struct ib_wc *in_wc,
+		       const struct ib_grh *in_grh,
+		       const struct ib_mad_hdr *in, size_t in_mad_size,
+		       struct ib_mad_hdr *out, size_t *out_mad_size,
+		       u16 *out_mad_pkey_index);
 #endif				/* __OCRDMA_AH_H__ */

drivers/infiniband/hw/ocrdma/ocrdma_main.c

@@ -30,6 +30,7 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_addr.h>
+#include <rdma/ib_mad.h>
 
 #include <linux/netdevice.h>
 #include <net/addrconf.h>
@@ -202,6 +203,24 @@ static enum rdma_link_layer ocrdma_link_layer(struct ib_device *device,
 	return IB_LINK_LAYER_ETHERNET;
 }
 
+static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
+			         struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = ocrdma_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_ROCE;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 static int ocrdma_register_device(struct ocrdma_dev *dev)
 {
 	strlcpy(dev->ibdev.name, "ocrdma%d", IB_DEVICE_NAME_MAX);
@@ -286,6 +305,7 @@ static int ocrdma_register_device(struct ocrdma_dev *dev)
 	dev->ibdev.dma_device = &dev->nic_info.pdev->dev;
 
 	dev->ibdev.process_mad = ocrdma_process_mad;
+	dev->ibdev.get_port_immutable = ocrdma_port_immutable;
 
 	if (ocrdma_get_asic_type(dev) == OCRDMA_ASIC_GEN_SKH_R) {
 		dev->ibdev.uverbs_cmd_mask |=

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c

@@ -61,10 +61,14 @@ int ocrdma_query_gid(struct ib_device *ibdev, u8 port,
 	return 0;
 }
 
-int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr)
+int ocrdma_query_device(struct ib_device *ibdev, struct ib_device_attr *attr,
+			struct ib_udata *uhw)
 {
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	memset(attr, 0, sizeof *attr);
 	memcpy(&attr->fw_ver, &dev->attr.fw_ver[0],
 	       min(sizeof(dev->attr.fw_ver), sizeof(attr->fw_ver)));
@@ -375,7 +379,12 @@ static struct ocrdma_pd *_ocrdma_alloc_pd(struct ocrdma_dev *dev,
 
 	if (dev->pd_mgr->pd_prealloc_valid) {
 		status = ocrdma_get_pd_num(dev, pd);
-		return (status == 0) ? pd : ERR_PTR(status);
+		if (status == 0) {
+			return pd;
+		} else {
+			kfree(pd);
+			return ERR_PTR(status);
+		}
 	}
 
 retry:
@@ -679,7 +688,6 @@ err:
 		ocrdma_release_ucontext_pd(uctx);
 	} else {
 		status = _ocrdma_dealloc_pd(dev, pd);
-		kfree(pd);
 	}
 exit:
 	return ERR_PTR(status);
@@ -1000,10 +1008,12 @@ err:
 	return status;
 }
 
-struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, int entries, int vector,
+struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
+			       const struct ib_cq_init_attr *attr,
 			       struct ib_ucontext *ib_ctx,
 			       struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct ocrdma_cq *cq;
 	struct ocrdma_dev *dev = get_ocrdma_dev(ibdev);
 	struct ocrdma_ucontext *uctx = NULL;
@@ -1011,6 +1021,9 @@ struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev, int entries, int vector,
 	int status;
 	struct ocrdma_create_cq_ureq ureq;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (udata) {
 		if (ib_copy_from_udata(&ureq, udata, sizeof(ureq)))
 			return ERR_PTR(-EFAULT);

drivers/infiniband/hw/ocrdma/ocrdma_verbs.h

@@ -36,11 +36,15 @@ int ocrdma_post_recv(struct ib_qp *, struct ib_recv_wr *,
 int ocrdma_poll_cq(struct ib_cq *, int num_entries, struct ib_wc *wc);
 int ocrdma_arm_cq(struct ib_cq *, enum ib_cq_notify_flags flags);
 
-int ocrdma_query_device(struct ib_device *, struct ib_device_attr *props);
+int ocrdma_query_device(struct ib_device *, struct ib_device_attr *props,
+			struct ib_udata *uhw);
 int ocrdma_query_port(struct ib_device *, u8 port, struct ib_port_attr *props);
 int ocrdma_modify_port(struct ib_device *, u8 port, int mask,
 		       struct ib_port_modify *props);
 
+enum rdma_protocol_type
+ocrdma_query_protocol(struct ib_device *device, u8 port_num);
+
 void ocrdma_get_guid(struct ocrdma_dev *, u8 *guid);
 int ocrdma_query_gid(struct ib_device *, u8 port,
 		     int index, union ib_gid *gid);
@@ -56,8 +60,10 @@ struct ib_pd *ocrdma_alloc_pd(struct ib_device *,
 			      struct ib_ucontext *, struct ib_udata *);
 int ocrdma_dealloc_pd(struct ib_pd *pd);
 
-struct ib_cq *ocrdma_create_cq(struct ib_device *, int entries, int vector,
-			       struct ib_ucontext *, struct ib_udata *);
+struct ib_cq *ocrdma_create_cq(struct ib_device *ibdev,
+			       const struct ib_cq_init_attr *attr,
+			       struct ib_ucontext *ib_ctx,
+			       struct ib_udata *udata);
 int ocrdma_resize_cq(struct ib_cq *, int cqe, struct ib_udata *);
 int ocrdma_destroy_cq(struct ib_cq *);
 

drivers/infiniband/hw/qib/qib_cq.c

@@ -203,7 +203,7 @@ static void send_complete(struct kthread_work *work)
 /**
  * qib_create_cq - create a completion queue
  * @ibdev: the device this completion queue is attached to
- * @entries: the minimum size of the completion queue
+ * @attr: creation attributes
  * @context: unused by the QLogic_IB driver
  * @udata: user data for libibverbs.so
  *
@@ -212,16 +212,21 @@ static void send_complete(struct kthread_work *work)
  *
  * Called by ib_create_cq() in the generic verbs code.
  */
-struct ib_cq *qib_create_cq(struct ib_device *ibdev, int entries,
-			    int comp_vector, struct ib_ucontext *context,
+struct ib_cq *qib_create_cq(struct ib_device *ibdev,
+			    const struct ib_cq_init_attr *attr,
+			    struct ib_ucontext *context,
 			    struct ib_udata *udata)
 {
+	int entries = attr->cqe;
 	struct qib_ibdev *dev = to_idev(ibdev);
 	struct qib_cq *cq;
 	struct qib_cq_wc *wc;
 	struct ib_cq *ret;
 	u32 sz;
 
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	if (entries < 1 || entries > ib_qib_max_cqes) {
 		ret = ERR_PTR(-EINVAL);
 		goto done;

drivers/infiniband/hw/qib/qib_iba7322.c

@@ -5502,7 +5502,8 @@ static void try_7322_ipg(struct qib_pportdata *ppd)
 		goto retry;
 
 	send_buf = ib_create_send_mad(agent, 0, 0, 0, IB_MGMT_MAD_HDR,
-				      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+				      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+				      IB_MGMT_BASE_VERSION);
 	if (IS_ERR(send_buf))
 		goto retry;
 

drivers/infiniband/hw/qib/qib_mad.c

@@ -83,7 +83,8 @@ static void qib_send_trap(struct qib_ibport *ibp, void *data, unsigned len)
 		return;
 
 	send_buf = ib_create_send_mad(agent, 0, 0, 0, IB_MGMT_MAD_HDR,
-				      IB_MGMT_MAD_DATA, GFP_ATOMIC);
+				      IB_MGMT_MAD_DATA, GFP_ATOMIC,
+				      IB_MGMT_BASE_VERSION);
 	if (IS_ERR(send_buf))
 		return;
 
@@ -1854,7 +1855,7 @@ static int pma_set_portcounters_ext(struct ib_pma_mad *pmp,
 }
 
 static int process_subn(struct ib_device *ibdev, int mad_flags,
-			u8 port, struct ib_mad *in_mad,
+			u8 port, const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_smp *smp = (struct ib_smp *)out_mad;
@@ -2006,7 +2007,7 @@ bail:
 }
 
 static int process_perf(struct ib_device *ibdev, u8 port,
-			struct ib_mad *in_mad,
+			const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_pma_mad *pmp = (struct ib_pma_mad *)out_mad;
@@ -2299,7 +2300,7 @@ static int check_cc_key(struct qib_ibport *ibp,
 }
 
 static int process_cc(struct ib_device *ibdev, int mad_flags,
-			u8 port, struct ib_mad *in_mad,
+			u8 port, const struct ib_mad *in_mad,
 			struct ib_mad *out_mad)
 {
 	struct ib_cc_mad *ccp = (struct ib_cc_mad *)out_mad;
@@ -2400,12 +2401,19 @@ bail:
  * This is called by the ib_mad module.
  */
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port,
-		    struct ib_wc *in_wc, struct ib_grh *in_grh,
-		    struct ib_mad *in_mad, struct ib_mad *out_mad)
+		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		    const struct ib_mad_hdr *in, size_t in_mad_size,
+		    struct ib_mad_hdr *out, size_t *out_mad_size,
+		    u16 *out_mad_pkey_index)
 {
 	int ret;
 	struct qib_ibport *ibp = to_iport(ibdev, port);
 	struct qib_pportdata *ppd = ppd_from_ibp(ibp);
+	const struct ib_mad *in_mad = (const struct ib_mad *)in;
+	struct ib_mad *out_mad = (struct ib_mad *)out;
+
+	BUG_ON(in_mad_size != sizeof(*in_mad) ||
+	       *out_mad_size != sizeof(*out_mad));
 
 	switch (in_mad->mad_hdr.mgmt_class) {
 	case IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE:

drivers/infiniband/hw/qib/qib_verbs.c

@@ -1550,12 +1550,14 @@ full:
 	}
 }
 
-static int qib_query_device(struct ib_device *ibdev,
-			    struct ib_device_attr *props)
+static int qib_query_device(struct ib_device *ibdev, struct ib_device_attr *props,
+			    struct ib_udata *uhw)
 {
 	struct qib_devdata *dd = dd_from_ibdev(ibdev);
 	struct qib_ibdev *dev = to_idev(ibdev);
 
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
 	memset(props, 0, sizeof(*props));
 
 	props->device_cap_flags = IB_DEVICE_BAD_PKEY_CNTR |
@@ -2040,6 +2042,24 @@ static void init_ibport(struct qib_pportdata *ppd)
 	RCU_INIT_POINTER(ibp->qp1, NULL);
 }
 
+static int qib_port_immutable(struct ib_device *ibdev, u8 port_num,
+			      struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = qib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+	immutable->core_cap_flags = RDMA_CORE_PORT_IBA_IB;
+	immutable->max_mad_size = IB_MGMT_MAD_SIZE;
+
+	return 0;
+}
+
 /**
  * qib_register_ib_device - register our device with the infiniband core
  * @dd: the device data structure
@@ -2227,6 +2247,7 @@ int qib_register_ib_device(struct qib_devdata *dd)
 	ibdev->process_mad = qib_process_mad;
 	ibdev->mmap = qib_mmap;
 	ibdev->dma_ops = &qib_dma_mapping_ops;
+	ibdev->get_port_immutable = qib_port_immutable;
 
 	snprintf(ibdev->node_desc, sizeof(ibdev->node_desc),
 		 "Intel Infiniband HCA %s", init_utsname()->nodename);

drivers/infiniband/hw/qib/qib_verbs.h

@@ -872,8 +872,10 @@ void qib_cap_mask_chg(struct qib_ibport *ibp);
 void qib_sys_guid_chg(struct qib_ibport *ibp);
 void qib_node_desc_chg(struct qib_ibport *ibp);
 int qib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
-		    struct ib_wc *in_wc, struct ib_grh *in_grh,
-		    struct ib_mad *in_mad, struct ib_mad *out_mad);
+		    const struct ib_wc *in_wc, const struct ib_grh *in_grh,
+		    const struct ib_mad_hdr *in, size_t in_mad_size,
+		    struct ib_mad_hdr *out, size_t *out_mad_size,
+		    u16 *out_mad_pkey_index);
 int qib_create_agents(struct qib_ibdev *dev);
 void qib_free_agents(struct qib_ibdev *dev);
 
@@ -1007,8 +1009,9 @@ void qib_cq_enter(struct qib_cq *cq, struct ib_wc *entry, int sig);
 
 int qib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *entry);
 
-struct ib_cq *qib_create_cq(struct ib_device *ibdev, int entries,
-			    int comp_vector, struct ib_ucontext *context,
+struct ib_cq *qib_create_cq(struct ib_device *ibdev,
+			    const struct ib_cq_init_attr *attr,
+			    struct ib_ucontext *context,
 			    struct ib_udata *udata);
 
 int qib_destroy_cq(struct ib_cq *ibcq);

drivers/infiniband/hw/usnic/usnic_ib_main.c

@@ -300,6 +300,22 @@ static struct notifier_block usnic_ib_inetaddr_notifier = {
 };
 /* End of inet section*/
 
+static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num,
+			        struct ib_port_immutable *immutable)
+{
+	struct ib_port_attr attr;
+	int err;
+
+	err = usnic_ib_query_port(ibdev, port_num, &attr);
+	if (err)
+		return err;
+
+	immutable->pkey_tbl_len = attr.pkey_tbl_len;
+	immutable->gid_tbl_len = attr.gid_tbl_len;
+
+	return 0;
+}
+
 /* Start of PF discovery section */
 static void *usnic_ib_device_add(struct pci_dev *dev)
 {
@@ -383,6 +399,7 @@ static void *usnic_ib_device_add(struct pci_dev *dev)
 	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;
+	us_ibdev->ib_dev.get_port_immutable = usnic_port_immutable;
 
 
 	if (ib_register_device(&us_ibdev->ib_dev, NULL))

drivers/infiniband/hw/usnic/usnic_ib_verbs.c

@@ -248,7 +248,8 @@ enum rdma_link_layer usnic_ib_port_link_layer(struct ib_device *device,
 }
 
 int usnic_ib_query_device(struct ib_device *ibdev,
-				struct ib_device_attr *props)
+			  struct ib_device_attr *props,
+			  struct ib_udata *uhw)
 {
 	struct usnic_ib_dev *us_ibdev = to_usdev(ibdev);
 	union ib_gid gid;
@@ -257,6 +258,9 @@ int usnic_ib_query_device(struct ib_device *ibdev,
 	int qp_per_vf;
 
 	usnic_dbg("\n");
+	if (uhw->inlen || uhw->outlen)
+		return -EINVAL;
+
 	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);
@@ -570,13 +574,17 @@ int usnic_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 	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 *usnic_ib_create_cq(struct ib_device *ibdev,
+				 const struct ib_cq_init_attr *attr,
+				 struct ib_ucontext *context,
+				 struct ib_udata *udata)
 {
 	struct ib_cq *cq;
 
 	usnic_dbg("\n");
+	if (attr->flags)
+		return ERR_PTR(-EINVAL);
+
 	cq = kzalloc(sizeof(*cq), GFP_KERNEL);
 	if (!cq)
 		return ERR_PTR(-EBUSY);

drivers/infiniband/hw/usnic/usnic_ib_verbs.h

@@ -24,9 +24,12 @@
 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);
+				struct ib_device_attr *props,
+			  struct ib_udata *uhw);
 int usnic_ib_query_port(struct ib_device *ibdev, u8 port,
 				struct ib_port_attr *props);
+enum rdma_protocol_type
+usnic_ib_query_protocol(struct ib_device *device, u8 port_num);
 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);
@@ -44,9 +47,10 @@ struct ib_qp *usnic_ib_create_qp(struct ib_pd *pd,
 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);
+struct ib_cq *usnic_ib_create_cq(struct ib_device *ibdev,
+				 const struct ib_cq_init_attr *attr,
+				 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,

drivers/infiniband/hw/usnic/usnic_uiom.c

@@ -472,11 +472,10 @@ struct usnic_uiom_pd *usnic_uiom_alloc_pd(void)
 		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));
+	if (!domain) {
+		usnic_err("Failed to allocate IOMMU domain");
 		kfree(pd);
-		return ERR_PTR(domain ? PTR_ERR(domain) : -ENOMEM);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	iommu_set_fault_handler(pd->domain, usnic_uiom_dma_fault, NULL);

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -1128,7 +1128,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 {
 	struct ipoib_neigh_table *ntbl = &priv->ntbl;
 	struct ipoib_neigh_hash *htbl;
-	struct ipoib_neigh **buckets;
+	struct ipoib_neigh __rcu **buckets;
 	u32 size;
 
 	clear_bit(IPOIB_NEIGH_TBL_FLUSH, &priv->flags);
@@ -1146,7 +1146,7 @@ static int ipoib_neigh_hash_init(struct ipoib_dev_priv *priv)
 	htbl->size = size;
 	htbl->mask = (size - 1);
 	htbl->buckets = buckets;
-	ntbl->htbl = htbl;
+	RCU_INIT_POINTER(ntbl->htbl, htbl);
 	htbl->ntbl = ntbl;
 	atomic_set(&ntbl->entries, 0);
 
@@ -1685,9 +1685,7 @@ static void ipoib_add_one(struct ib_device *device)
 	struct net_device *dev;
 	struct ipoib_dev_priv *priv;
 	int s, e, p;
-
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
+	int count = 0;
 
 	dev_list = kmalloc(sizeof *dev_list, GFP_KERNEL);
 	if (!dev_list)
@@ -1704,15 +1702,21 @@ static void ipoib_add_one(struct ib_device *device)
 	}
 
 	for (p = s; p <= e; ++p) {
-		if (rdma_port_get_link_layer(device, p) != IB_LINK_LAYER_INFINIBAND)
+		if (!rdma_protocol_ib(device, p))
 			continue;
 		dev = ipoib_add_port("ib%d", device, p);
 		if (!IS_ERR(dev)) {
 			priv = netdev_priv(dev);
 			list_add_tail(&priv->list, dev_list);
+			count++;
 		}
 	}
 
+	if (!count) {
+		kfree(dev_list);
+		return;
+	}
+
 	ib_set_client_data(device, &ipoib_client, dev_list);
 }
 
@@ -1721,9 +1725,6 @@ static void ipoib_remove_one(struct ib_device *device)
 	struct ipoib_dev_priv *priv, *tmp;
 	struct list_head *dev_list;
 
-	if (rdma_node_get_transport(device->node_type) != RDMA_TRANSPORT_IB)
-		return;
-
 	dev_list = ib_get_client_data(device, &ipoib_client);
 	if (!dev_list)
 		return;

drivers/infiniband/ulp/ipoib/ipoib_verbs.c

@@ -141,6 +141,7 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 		.sq_sig_type = IB_SIGNAL_ALL_WR,
 		.qp_type     = IB_QPT_UD
 	};
+	struct ib_cq_init_attr cq_attr = {};
 
 	int ret, size;
 	int i;
@@ -178,14 +179,17 @@ int ipoib_transport_dev_init(struct net_device *dev, struct ib_device *ca)
 	} else
 		goto out_free_wq;
 
-	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL, dev, size, 0);
+	cq_attr.cqe = size;
+	priv->recv_cq = ib_create_cq(priv->ca, ipoib_ib_completion, NULL,
+				     dev, &cq_attr);
 	if (IS_ERR(priv->recv_cq)) {
 		printk(KERN_WARNING "%s: failed to create receive CQ\n", ca->name);
 		goto out_cm_dev_cleanup;
 	}
 
+	cq_attr.cqe = ipoib_sendq_size;
 	priv->send_cq = ib_create_cq(priv->ca, ipoib_send_comp_handler, NULL,
-				     dev, ipoib_sendq_size, 0);
+				     dev, &cq_attr);
 	if (IS_ERR(priv->send_cq)) {
 		printk(KERN_WARNING "%s: failed to create send CQ\n", ca->name);
 		goto out_free_recv_cq;

drivers/infiniband/ulp/iser/iser_verbs.c

@@ -51,19 +51,22 @@ static void iser_cq_callback(struct ib_cq *cq, void *cq_context);
 
 static void iser_cq_event_callback(struct ib_event *cause, void *context)
 {
-	iser_err("got cq event %d \n", cause->event);
+	iser_err("cq event %s (%d)\n",
+		 ib_event_msg(cause->event), cause->event);
 }
 
 static void iser_qp_event_callback(struct ib_event *cause, void *context)
 {
-	iser_err("got qp event %d\n",cause->event);
+	iser_err("qp event %s (%d)\n",
+		 ib_event_msg(cause->event), cause->event);
 }
 
 static void iser_event_handler(struct ib_event_handler *handler,
 				struct ib_event *event)
 {
-	iser_err("async event %d on device %s port %d\n", event->event,
-		event->device->name, event->element.port_num);
+	iser_err("async event %s (%d) on device %s port %d\n",
+		 ib_event_msg(event->event), event->event,
+		 event->device->name, event->element.port_num);
 }
 
 /**
@@ -123,14 +126,17 @@ static int iser_create_device_ib_res(struct iser_device *device)
 		goto pd_err;
 
 	for (i = 0; i < device->comps_used; i++) {
+		struct ib_cq_init_attr cq_attr = {};
 		struct iser_comp *comp = &device->comps[i];
 
 		comp->device = device;
+		cq_attr.cqe = max_cqe;
+		cq_attr.comp_vector = i;
 		comp->cq = ib_create_cq(device->ib_device,
 					iser_cq_callback,
 					iser_cq_event_callback,
 					(void *)comp,
-					max_cqe, i);
+					&cq_attr);
 		if (IS_ERR(comp->cq)) {
 			comp->cq = NULL;
 			goto cq_err;
@@ -873,8 +879,9 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve
 	int ret = 0;
 
 	iser_conn = (struct iser_conn *)cma_id->context;
-	iser_info("event %d status %d conn %p id %p\n",
-		  event->event, event->status, cma_id->context, cma_id);
+	iser_info("%s (%d): status %d conn %p id %p\n",
+		  rdma_event_msg(event->event), event->event,
+		  event->status, cma_id->context, cma_id);
 
 	mutex_lock(&iser_conn->state_mutex);
 	switch (event->event) {
@@ -913,7 +920,8 @@ static int iser_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *eve
 		}
 		break;
 	default:
-		iser_err("Unexpected RDMA CM event (%d)\n", event->event);
+		iser_err("Unexpected RDMA CM event: %s (%d)\n",
+			 rdma_event_msg(event->event), event->event);
 		break;
 	}
 	mutex_unlock(&iser_conn->state_mutex);
@@ -1173,10 +1181,13 @@ static void iser_handle_wc(struct ib_wc *wc)
 		}
 	} else {
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
-			iser_err("wr id %llx status %d vend_err %x\n",
-				 wc->wr_id, wc->status, wc->vendor_err);
+			iser_err("%s (%d): wr id %llx vend_err %x\n",
+				 ib_wc_status_msg(wc->status), wc->status,
+				 wc->wr_id, wc->vendor_err);
 		else
-			iser_dbg("flush error: wr id %llx\n", wc->wr_id);
+			iser_dbg("%s (%d): wr id %llx\n",
+				 ib_wc_status_msg(wc->status), wc->status,
+				 wc->wr_id);
 
 		if (wc->wr_id == ISER_BEACON_WRID)
 			/* all flush errors were consumed */

drivers/infiniband/ulp/isert/ib_isert.c

@@ -80,7 +80,9 @@ isert_qp_event_callback(struct ib_event *e, void *context)
 {
 	struct isert_conn *isert_conn = context;
 
-	isert_err("conn %p event: %d\n", isert_conn, e->event);
+	isert_err("%s (%d): conn %p\n",
+		  ib_event_msg(e->event), e->event, isert_conn);
+
 	switch (e->event) {
 	case IB_EVENT_COMM_EST:
 		rdma_notify(isert_conn->cm_id, IB_EVENT_COMM_EST);
@@ -318,15 +320,18 @@ isert_alloc_comps(struct isert_device *device,
 	max_cqe = min(ISER_MAX_CQ_LEN, attr->max_cqe);
 
 	for (i = 0; i < device->comps_used; i++) {
+		struct ib_cq_init_attr cq_attr = {};
 		struct isert_comp *comp = &device->comps[i];
 
 		comp->device = device;
 		INIT_WORK(&comp->work, isert_cq_work);
+		cq_attr.cqe = max_cqe;
+		cq_attr.comp_vector = i;
 		comp->cq = ib_create_cq(device->ib_device,
 					isert_cq_callback,
 					isert_cq_event_callback,
 					(void *)comp,
-					max_cqe, i);
+					&cq_attr);
 		if (IS_ERR(comp->cq)) {
 			isert_err("Unable to allocate cq\n");
 			ret = PTR_ERR(comp->cq);
@@ -900,7 +905,8 @@ static int
 isert_np_cma_handler(struct isert_np *isert_np,
 		     enum rdma_cm_event_type event)
 {
-	isert_dbg("isert np %p, handling event %d\n", isert_np, event);
+	isert_dbg("%s (%d): isert np %p\n",
+		  rdma_event_msg(event), event, isert_np);
 
 	switch (event) {
 	case RDMA_CM_EVENT_DEVICE_REMOVAL:
@@ -974,7 +980,8 @@ isert_cma_handler(struct rdma_cm_id *cma_id, struct rdma_cm_event *event)
 {
 	int ret = 0;
 
-	isert_info("event %d status %d id %p np %p\n", event->event,
+	isert_info("%s (%d): status %d id %p np %p\n",
+		   rdma_event_msg(event->event), event->event,
 		   event->status, cma_id, cma_id->context);
 
 	switch (event->event) {
@@ -2108,10 +2115,13 @@ isert_handle_wc(struct ib_wc *wc)
 		}
 	} else {
 		if (wc->status != IB_WC_WR_FLUSH_ERR)
-			isert_err("wr id %llx status %d vend_err %x\n",
-				  wc->wr_id, wc->status, wc->vendor_err);
+			isert_err("%s (%d): wr id %llx vend_err %x\n",
+				  ib_wc_status_msg(wc->status), wc->status,
+				  wc->wr_id, wc->vendor_err);
 		else
-			isert_dbg("flush error: wr id %llx\n", wc->wr_id);
+			isert_dbg("%s (%d): wr id %llx\n",
+				  ib_wc_status_msg(wc->status), wc->status,
+				  wc->wr_id);
 
 		if (wc->wr_id != ISER_FASTREG_LI_WRID)
 			isert_cq_comp_err(isert_conn, wc);

drivers/infiniband/ulp/srp/ib_srp.c

@@ -59,9 +59,10 @@
 #define DRV_RELDATE	"July 1, 2013"
 
 MODULE_AUTHOR("Roland Dreier");
-MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator "
-		   "v" DRV_VERSION " (" DRV_RELDATE ")");
+MODULE_DESCRIPTION("InfiniBand SCSI RDMA Protocol initiator");
 MODULE_LICENSE("Dual BSD/GPL");
+MODULE_VERSION(DRV_VERSION);
+MODULE_INFO(release_date, DRV_RELDATE);
 
 static unsigned int srp_sg_tablesize;
 static unsigned int cmd_sg_entries;
@@ -253,7 +254,8 @@ static void srp_free_iu(struct srp_host *host, struct srp_iu *iu)
 
 static void srp_qp_event(struct ib_event *event, void *context)
 {
-	pr_debug("QP event %d\n", event->event);
+	pr_debug("QP event %s (%d)\n",
+		 ib_event_msg(event->event), event->event);
 }
 
 static int srp_init_qp(struct srp_target_port *target,
@@ -465,14 +467,13 @@ static struct srp_fr_pool *srp_alloc_fr_pool(struct srp_target_port *target)
  */
 static void srp_destroy_qp(struct srp_rdma_ch *ch)
 {
-	struct srp_target_port *target = ch->target;
 	static struct ib_qp_attr attr = { .qp_state = IB_QPS_ERR };
 	static struct ib_recv_wr wr = { .wr_id = SRP_LAST_WR_ID };
 	struct ib_recv_wr *bad_wr;
 	int ret;
 
 	/* Destroying a QP and reusing ch->done is only safe if not connected */
-	WARN_ON_ONCE(target->connected);
+	WARN_ON_ONCE(ch->connected);
 
 	ret = ib_modify_qp(ch->qp, &attr, IB_QP_STATE);
 	WARN_ONCE(ret, "ib_cm_init_qp_attr() returned %d\n", ret);
@@ -499,6 +500,7 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch)
 	struct ib_fmr_pool *fmr_pool = NULL;
 	struct srp_fr_pool *fr_pool = NULL;
 	const int m = 1 + dev->use_fast_reg;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	init_attr = kzalloc(sizeof *init_attr, GFP_KERNEL);
@@ -506,15 +508,19 @@ static int srp_create_ch_ib(struct srp_rdma_ch *ch)
 		return -ENOMEM;
 
 	/* + 1 for SRP_LAST_WR_ID */
+	cq_attr.cqe = target->queue_size + 1;
+	cq_attr.comp_vector = ch->comp_vector;
 	recv_cq = ib_create_cq(dev->dev, srp_recv_completion, NULL, ch,
-			       target->queue_size + 1, ch->comp_vector);
+			       &cq_attr);
 	if (IS_ERR(recv_cq)) {
 		ret = PTR_ERR(recv_cq);
 		goto err;
 	}
 
+	cq_attr.cqe = m * target->queue_size;
+	cq_attr.comp_vector = ch->comp_vector;
 	send_cq = ib_create_cq(dev->dev, srp_send_completion, NULL, ch,
-			       m * target->queue_size, ch->comp_vector);
+			       &cq_attr);
 	if (IS_ERR(send_cq)) {
 		ret = PTR_ERR(send_cq);
 		goto err_recv_cq;
@@ -781,7 +787,7 @@ static int srp_send_req(struct srp_rdma_ch *ch, bool multich)
 		shost_printk(KERN_DEBUG, target->scsi_host,
 			     PFX "Topspin/Cisco initiator port ID workaround "
 			     "activated for target GUID %016llx\n",
-			     (unsigned long long) be64_to_cpu(target->ioc_guid));
+			     be64_to_cpu(target->ioc_guid));
 		memset(req->priv.initiator_port_id, 0, 8);
 		memcpy(req->priv.initiator_port_id + 8,
 		       &target->srp_host->srp_dev->dev->node_guid, 8);
@@ -811,35 +817,19 @@ static bool srp_queue_remove_work(struct srp_target_port *target)
 	return changed;
 }
 
-static bool srp_change_conn_state(struct srp_target_port *target,
-				  bool connected)
-{
-	bool changed = false;
-
-	spin_lock_irq(&target->lock);
-	if (target->connected != connected) {
-		target->connected = connected;
-		changed = true;
-	}
-	spin_unlock_irq(&target->lock);
-
-	return changed;
-}
-
 static void srp_disconnect_target(struct srp_target_port *target)
 {
 	struct srp_rdma_ch *ch;
 	int i;
 
-	if (srp_change_conn_state(target, false)) {
-		/* XXX should send SRP_I_LOGOUT request */
+	/* XXX should send SRP_I_LOGOUT request */
 
-		for (i = 0; i < target->ch_count; i++) {
-			ch = &target->ch[i];
-			if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) {
-				shost_printk(KERN_DEBUG, target->scsi_host,
-					     PFX "Sending CM DREQ failed\n");
-			}
+	for (i = 0; i < target->ch_count; i++) {
+		ch = &target->ch[i];
+		ch->connected = false;
+		if (ch->cm_id && ib_send_cm_dreq(ch->cm_id, NULL, 0)) {
+			shost_printk(KERN_DEBUG, target->scsi_host,
+				     PFX "Sending CM DREQ failed\n");
 		}
 	}
 }
@@ -852,7 +842,7 @@ static void srp_free_req_data(struct srp_target_port *target,
 	struct srp_request *req;
 	int i;
 
-	if (!ch->target || !ch->req_ring)
+	if (!ch->req_ring)
 		return;
 
 	for (i = 0; i < target->req_ring_size; ++i) {
@@ -986,14 +976,26 @@ static void srp_rport_delete(struct srp_rport *rport)
 	srp_queue_remove_work(target);
 }
 
+/**
+ * srp_connected_ch() - number of connected channels
+ * @target: SRP target port.
+ */
+static int srp_connected_ch(struct srp_target_port *target)
+{
+	int i, c = 0;
+
+	for (i = 0; i < target->ch_count; i++)
+		c += target->ch[i].connected;
+
+	return c;
+}
+
 static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
 {
 	struct srp_target_port *target = ch->target;
 	int ret;
 
-	WARN_ON_ONCE(!multich && target->connected);
-
-	target->qp_in_error = false;
+	WARN_ON_ONCE(!multich && srp_connected_ch(target) > 0);
 
 	ret = srp_lookup_path(ch);
 	if (ret)
@@ -1016,7 +1018,7 @@ static int srp_connect_ch(struct srp_rdma_ch *ch, bool multich)
 		 */
 		switch (ch->status) {
 		case 0:
-			srp_change_conn_state(target, true);
+			ch->connected = true;
 			return 0;
 
 		case SRP_PORT_REDIRECT:
@@ -1214,14 +1216,10 @@ static int srp_rport_reconnect(struct srp_rport *rport)
 	 */
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (!ch->target)
-			break;
 		ret += srp_new_cm_id(ch);
 	}
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (!ch->target)
-			break;
 		for (j = 0; j < target->req_ring_size; ++j) {
 			struct srp_request *req = &ch->req_ring[j];
 
@@ -1230,8 +1228,6 @@ static int srp_rport_reconnect(struct srp_rport *rport)
 	}
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (!ch->target)
-			break;
 		/*
 		 * Whether or not creating a new CM ID succeeded, create a new
 		 * QP. This guarantees that all completion callback function
@@ -1243,13 +1239,13 @@ static int srp_rport_reconnect(struct srp_rport *rport)
 		for (j = 0; j < target->queue_size; ++j)
 			list_add(&ch->tx_ring[j]->list, &ch->free_tx);
 	}
+
+	target->qp_in_error = false;
+
 	for (i = 0; i < target->ch_count; i++) {
 		ch = &target->ch[i];
-		if (ret || !ch->target) {
-			if (i > 1)
-				ret = 0;
+		if (ret)
 			break;
-		}
 		ret = srp_connect_ch(ch, multich);
 		multich = true;
 	}
@@ -1842,7 +1838,7 @@ static void srp_process_aer_req(struct srp_rdma_ch *ch,
 	s32 delta = be32_to_cpu(req->req_lim_delta);
 
 	shost_printk(KERN_ERR, target->scsi_host, PFX
-		     "ignoring AER for LUN %llu\n", be64_to_cpu(req->lun));
+		     "ignoring AER for LUN %llu\n", scsilun_to_int(&req->lun));
 
 	if (srp_response_common(ch, delta, &rsp, sizeof(rsp)))
 		shost_printk(KERN_ERR, target->scsi_host, PFX
@@ -1929,20 +1925,21 @@ static void srp_handle_qp_err(u64 wr_id, enum ib_wc_status wc_status,
 		return;
 	}
 
-	if (target->connected && !target->qp_in_error) {
+	if (ch->connected && !target->qp_in_error) {
 		if (wr_id & LOCAL_INV_WR_ID_MASK) {
 			shost_printk(KERN_ERR, target->scsi_host, PFX
-				     "LOCAL_INV failed with status %d\n",
-				     wc_status);
+				     "LOCAL_INV failed with status %s (%d)\n",
+				     ib_wc_status_msg(wc_status), wc_status);
 		} else if (wr_id & FAST_REG_WR_ID_MASK) {
 			shost_printk(KERN_ERR, target->scsi_host, PFX
-				     "FAST_REG_MR failed status %d\n",
-				     wc_status);
+				     "FAST_REG_MR failed status %s (%d)\n",
+				     ib_wc_status_msg(wc_status), wc_status);
 		} else {
 			shost_printk(KERN_ERR, target->scsi_host,
-				     PFX "failed %s status %d for iu %p\n",
+				     PFX "failed %s status %s (%d) for iu %p\n",
 				     send_err ? "send" : "receive",
-				     wc_status, (void *)(uintptr_t)wr_id);
+				     ib_wc_status_msg(wc_status), wc_status,
+				     (void *)(uintptr_t)wr_id);
 		}
 		queue_work(system_long_wq, &target->tl_err_work);
 	}
@@ -2034,7 +2031,7 @@ static int srp_queuecommand(struct Scsi_Host *shost, struct scsi_cmnd *scmnd)
 	memset(cmd, 0, sizeof *cmd);
 
 	cmd->opcode = SRP_CMD;
-	cmd->lun    = cpu_to_be64((u64) scmnd->device->lun << 48);
+	int_to_scsilun(scmnd->device->lun, &cmd->lun);
 	cmd->tag    = tag;
 	memcpy(cmd->cdb, scmnd->cmnd, scmnd->cmd_len);
 
@@ -2367,7 +2364,7 @@ static int srp_cm_handler(struct ib_cm_id *cm_id, struct ib_cm_event *event)
 	case IB_CM_DREQ_RECEIVED:
 		shost_printk(KERN_WARNING, target->scsi_host,
 			     PFX "DREQ received - connection closed\n");
-		srp_change_conn_state(target, false);
+		ch->connected = false;
 		if (ib_send_cm_drep(cm_id, NULL, 0))
 			shost_printk(KERN_ERR, target->scsi_host,
 				     PFX "Sending CM DREP failed\n");
@@ -2414,8 +2411,8 @@ srp_change_queue_depth(struct scsi_device *sdev, int qdepth)
 	return scsi_change_queue_depth(sdev, qdepth);
 }
 
-static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag,
-			     unsigned int lun, u8 func)
+static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag, u64 lun,
+			     u8 func)
 {
 	struct srp_target_port *target = ch->target;
 	struct srp_rport *rport = target->rport;
@@ -2423,7 +2420,7 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag,
 	struct srp_iu *iu;
 	struct srp_tsk_mgmt *tsk_mgmt;
 
-	if (!target->connected || target->qp_in_error)
+	if (!ch->connected || target->qp_in_error)
 		return -1;
 
 	init_completion(&ch->tsk_mgmt_done);
@@ -2449,7 +2446,7 @@ static int srp_send_tsk_mgmt(struct srp_rdma_ch *ch, u64 req_tag,
 	memset(tsk_mgmt, 0, sizeof *tsk_mgmt);
 
 	tsk_mgmt->opcode 	= SRP_TSK_MGMT;
-	tsk_mgmt->lun		= cpu_to_be64((u64) lun << 48);
+	int_to_scsilun(lun, &tsk_mgmt->lun);
 	tsk_mgmt->tag		= req_tag | SRP_TAG_TSK_MGMT;
 	tsk_mgmt->tsk_mgmt_func = func;
 	tsk_mgmt->task_tag	= req_tag;
@@ -2563,8 +2560,7 @@ static ssize_t show_id_ext(struct device *dev, struct device_attribute *attr,
 {
 	struct srp_target_port *target = host_to_target(class_to_shost(dev));
 
-	return sprintf(buf, "0x%016llx\n",
-		       (unsigned long long) be64_to_cpu(target->id_ext));
+	return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->id_ext));
 }
 
 static ssize_t show_ioc_guid(struct device *dev, struct device_attribute *attr,
@@ -2572,8 +2568,7 @@ static ssize_t show_ioc_guid(struct device *dev, struct device_attribute *attr,
 {
 	struct srp_target_port *target = host_to_target(class_to_shost(dev));
 
-	return sprintf(buf, "0x%016llx\n",
-		       (unsigned long long) be64_to_cpu(target->ioc_guid));
+	return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->ioc_guid));
 }
 
 static ssize_t show_service_id(struct device *dev,
@@ -2581,8 +2576,7 @@ static ssize_t show_service_id(struct device *dev,
 {
 	struct srp_target_port *target = host_to_target(class_to_shost(dev));
 
-	return sprintf(buf, "0x%016llx\n",
-		       (unsigned long long) be64_to_cpu(target->service_id));
+	return sprintf(buf, "0x%016llx\n", be64_to_cpu(target->service_id));
 }
 
 static ssize_t show_pkey(struct device *dev, struct device_attribute *attr,
@@ -2773,7 +2767,7 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 
 	target->state = SRP_TARGET_SCANNING;
 	sprintf(target->target_name, "SRP.T10:%016llX",
-		 (unsigned long long) be64_to_cpu(target->id_ext));
+		be64_to_cpu(target->id_ext));
 
 	if (scsi_add_host(target->scsi_host, host->srp_dev->dev->dma_device))
 		return -ENODEV;
@@ -2797,7 +2791,8 @@ static int srp_add_target(struct srp_host *host, struct srp_target_port *target)
 	scsi_scan_target(&target->scsi_host->shost_gendev,
 			 0, target->scsi_id, SCAN_WILD_CARD, 0);
 
-	if (!target->connected || target->qp_in_error) {
+	if (srp_connected_ch(target) < target->ch_count ||
+	    target->qp_in_error) {
 		shost_printk(KERN_INFO, target->scsi_host,
 			     PFX "SCSI scan failed - removing SCSI host\n");
 		srp_queue_remove_work(target);
@@ -3146,7 +3141,7 @@ static ssize_t srp_create_target(struct device *dev,
 	target_host->transportt  = ib_srp_transport_template;
 	target_host->max_channel = 0;
 	target_host->max_id      = 1;
-	target_host->max_lun     = SRP_MAX_LUN;
+	target_host->max_lun     = -1LL;
 	target_host->max_cmd_len = sizeof ((struct srp_cmd *) (void *) 0L)->cdb;
 
 	target = host_to_target(target_host);
@@ -3172,11 +3167,11 @@ static ssize_t srp_create_target(struct device *dev,
 
 	ret = srp_parse_options(buf, target);
 	if (ret)
-		goto err;
+		goto out;
 
 	ret = scsi_init_shared_tag_map(target_host, target_host->can_queue);
 	if (ret)
-		goto err;
+		goto out;
 
 	target->req_ring_size = target->queue_size - SRP_TSK_MGMT_SQ_SIZE;
 
@@ -3187,7 +3182,7 @@ static ssize_t srp_create_target(struct device *dev,
 			     be64_to_cpu(target->ioc_guid),
 			     be64_to_cpu(target->initiator_ext));
 		ret = -EEXIST;
-		goto err;
+		goto out;
 	}
 
 	if (!srp_dev->has_fmr && !srp_dev->has_fr && !target->allow_ext_sg &&
@@ -3208,7 +3203,7 @@ static ssize_t srp_create_target(struct device *dev,
 	spin_lock_init(&target->lock);
 	ret = ib_query_gid(ibdev, host->port, 0, &target->sgid);
 	if (ret)
-		goto err;
+		goto out;
 
 	ret = -ENOMEM;
 	target->ch_count = max_t(unsigned, num_online_nodes(),
@@ -3219,7 +3214,7 @@ static ssize_t srp_create_target(struct device *dev,
 	target->ch = kcalloc(target->ch_count, sizeof(*target->ch),
 			     GFP_KERNEL);
 	if (!target->ch)
-		goto err;
+		goto out;
 
 	node_idx = 0;
 	for_each_online_node(node) {
@@ -3315,9 +3310,6 @@ err_disconnect:
 	}
 
 	kfree(target->ch);
-
-err:
-	scsi_host_put(target_host);
 	goto out;
 }
 

drivers/infiniband/ulp/srp/ib_srp.h

@@ -54,7 +54,6 @@ enum {
 	SRP_DLID_REDIRECT	= 2,
 	SRP_STALE_CONN		= 3,
 
-	SRP_MAX_LUN		= 512,
 	SRP_DEF_SG_TABLESIZE	= 12,
 
 	SRP_DEFAULT_QUEUE_SIZE	= 1 << 6,
@@ -170,6 +169,7 @@ struct srp_rdma_ch {
 
 	struct completion	tsk_mgmt_done;
 	u8			tsk_mgmt_status;
+	bool			connected;
 };
 
 /**
@@ -214,7 +214,6 @@ struct srp_target_port {
 	__be16			pkey;
 
 	u32			rq_tmo_jiffies;
-	bool			connected;
 
 	int			zero_req_lim;
 

drivers/infiniband/ulp/srpt/ib_srpt.c

@@ -476,7 +476,8 @@ static void srpt_mad_recv_handler(struct ib_mad_agent *mad_agent,
 	rsp = ib_create_send_mad(mad_agent, mad_wc->wc->src_qp,
 				 mad_wc->wc->pkey_index, 0,
 				 IB_MGMT_DEVICE_HDR, IB_MGMT_DEVICE_DATA,
-				 GFP_KERNEL);
+				 GFP_KERNEL,
+				 IB_MGMT_BASE_VERSION);
 	if (IS_ERR(rsp))
 		goto err_rsp;
 
@@ -2080,6 +2081,7 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 	struct srpt_port *sport = ch->sport;
 	struct srpt_device *sdev = sport->sdev;
 	u32 srp_sq_size = sport->port_attrib.srp_sq_size;
+	struct ib_cq_init_attr cq_attr = {};
 	int ret;
 
 	WARN_ON(ch->rq_size < 1);
@@ -2090,8 +2092,9 @@ static int srpt_create_ch_ib(struct srpt_rdma_ch *ch)
 		goto out;
 
 retry:
+	cq_attr.cqe = ch->rq_size + srp_sq_size;
 	ch->cq = ib_create_cq(sdev->device, srpt_completion, NULL, ch,
-			      ch->rq_size + srp_sq_size, 0);
+			      &cq_attr);
 	if (IS_ERR(ch->cq)) {
 		ret = PTR_ERR(ch->cq);
 		pr_err("failed to create CQ cqe= %d ret= %d\n",

drivers/net/ethernet/chelsio/cxgb4/cxgb4.h

@@ -1185,6 +1185,7 @@ enum t4_bar2_qtype { T4_BAR2_QTYPE_EGRESS, T4_BAR2_QTYPE_INGRESS };
 int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter,
 		      unsigned int qid,
 		      enum t4_bar2_qtype qtype,
+		      int user,
 		      u64 *pbar2_qoffset,
 		      unsigned int *pbar2_qid);
 

drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c

@@ -2145,6 +2145,7 @@ EXPORT_SYMBOL(cxgb4_read_sge_timestamp);
 int cxgb4_bar2_sge_qregs(struct net_device *dev,
 			 unsigned int qid,
 			 enum cxgb4_bar2_qtype qtype,
+			 int user,
 			 u64 *pbar2_qoffset,
 			 unsigned int *pbar2_qid)
 {
@@ -2153,6 +2154,7 @@ int cxgb4_bar2_sge_qregs(struct net_device *dev,
 				 (qtype == CXGB4_BAR2_QTYPE_EGRESS
 				  ? T4_BAR2_QTYPE_EGRESS
 				  : T4_BAR2_QTYPE_INGRESS),
+				 user,
 				 pbar2_qoffset,
 				 pbar2_qid);
 }
@@ -2351,7 +2353,7 @@ static void process_db_drop(struct work_struct *work)
 		int ret;
 
 		ret = cxgb4_t4_bar2_sge_qregs(adap, qid, T4_BAR2_QTYPE_EGRESS,
-					&bar2_qoffset, &bar2_qid);
+					      0, &bar2_qoffset, &bar2_qid);
 		if (ret)
 			dev_err(adap->pdev_dev, "doorbell drop recovery: "
 				"qid=%d, pidx_inc=%d\n", qid, pidx_inc);

drivers/net/ethernet/chelsio/cxgb4/cxgb4_uld.h

@@ -306,6 +306,7 @@ enum cxgb4_bar2_qtype { CXGB4_BAR2_QTYPE_EGRESS, CXGB4_BAR2_QTYPE_INGRESS };
 int cxgb4_bar2_sge_qregs(struct net_device *dev,
 			 unsigned int qid,
 			 enum cxgb4_bar2_qtype qtype,
+			 int user,
 			 u64 *pbar2_qoffset,
 			 unsigned int *pbar2_qid);
 

drivers/net/ethernet/chelsio/cxgb4/sge.c

@@ -2429,8 +2429,8 @@ static void __iomem *bar2_address(struct adapter *adapter,
 	u64 bar2_qoffset;
 	int ret;
 
-	ret = cxgb4_t4_bar2_sge_qregs(adapter, qid, qtype,
-				&bar2_qoffset, pbar2_qid);
+	ret = cxgb4_t4_bar2_sge_qregs(adapter, qid, qtype, 0,
+				      &bar2_qoffset, pbar2_qid);
 	if (ret)
 		return NULL;
 

drivers/net/ethernet/chelsio/cxgb4/t4_hw.c

@@ -5102,6 +5102,7 @@ int t4_prep_adapter(struct adapter *adapter)
  *	@adapter: the adapter
  *	@qid: the Queue ID
  *	@qtype: the Ingress or Egress type for @qid
+ *	@user: true if this request is for a user mode queue
  *	@pbar2_qoffset: BAR2 Queue Offset
  *	@pbar2_qid: BAR2 Queue ID or 0 for Queue ID inferred SGE Queues
  *
@@ -5125,6 +5126,7 @@ int t4_prep_adapter(struct adapter *adapter)
 int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter,
 		      unsigned int qid,
 		      enum t4_bar2_qtype qtype,
+		      int user,
 		      u64 *pbar2_qoffset,
 		      unsigned int *pbar2_qid)
 {
@@ -5132,9 +5134,8 @@ int cxgb4_t4_bar2_sge_qregs(struct adapter *adapter,
 	u64 bar2_page_offset, bar2_qoffset;
 	unsigned int bar2_qid, bar2_qid_offset, bar2_qinferred;
 
-	/* T4 doesn't support BAR2 SGE Queue registers.
-	 */
-	if (is_t4(adapter->params.chip))
+	/* T4 doesn't support BAR2 SGE Queue registers for kernel mode queues */
+	if (!user && is_t4(adapter->params.chip))
 		return -EINVAL;
 
 	/* Get our SGE Page Size parameters.

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

@@ -1674,6 +1674,25 @@ static int map_internal_clock(struct mlx4_dev *dev)
 	return 0;
 }
 
+int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
+				   struct mlx4_clock_params *params)
+{
+	struct mlx4_priv *priv = mlx4_priv(dev);
+
+	if (mlx4_is_slave(dev))
+		return -ENOTSUPP;
+
+	if (!params)
+		return -EINVAL;
+
+	params->bar = priv->fw.clock_bar;
+	params->offset = priv->fw.clock_offset;
+	params->size = MLX4_CLOCK_SIZE;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_get_internal_clock_params);
+
 static void unmap_internal_clock(struct mlx4_dev *dev)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);

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

@@ -36,7 +36,7 @@
 #include <linux/mlx5/cmd.h>
 #include "mlx5_core.h"
 
-int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, void *inb, void *outb,
+int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
 		      u16 opmod, u8 port)
 {
 	struct mlx5_mad_ifc_mbox_in *in = NULL;

drivers/scsi/ibmvscsi/ibmvscsi.c

@@ -1053,7 +1053,7 @@ static int ibmvscsi_queuecommand_lck(struct scsi_cmnd *cmnd,
 	memset(srp_cmd, 0x00, SRP_MAX_IU_LEN);
 	srp_cmd->opcode = SRP_CMD;
 	memcpy(srp_cmd->cdb, cmnd->cmnd, sizeof(srp_cmd->cdb));
-	srp_cmd->lun = cpu_to_be64(((u64)lun) << 48);
+	int_to_scsilun(lun, &srp_cmd->lun);
 
 	if (!map_data_for_srp_cmd(cmnd, evt_struct, srp_cmd, hostdata->dev)) {
 		if (!firmware_has_feature(FW_FEATURE_CMO))
@@ -1529,7 +1529,7 @@ static int ibmvscsi_eh_abort_handler(struct scsi_cmnd *cmd)
 		/* Set up an abort SRP command */
 		memset(tsk_mgmt, 0x00, sizeof(*tsk_mgmt));
 		tsk_mgmt->opcode = SRP_TSK_MGMT;
-		tsk_mgmt->lun = cpu_to_be64(((u64) lun) << 48);
+		int_to_scsilun(lun, &tsk_mgmt->lun);
 		tsk_mgmt->tsk_mgmt_func = SRP_TSK_ABORT_TASK;
 		tsk_mgmt->task_tag = (u64) found_evt;
 
@@ -1652,7 +1652,7 @@ static int ibmvscsi_eh_device_reset_handler(struct scsi_cmnd *cmd)
 		/* Set up a lun reset SRP command */
 		memset(tsk_mgmt, 0x00, sizeof(*tsk_mgmt));
 		tsk_mgmt->opcode = SRP_TSK_MGMT;
-		tsk_mgmt->lun = cpu_to_be64(((u64) lun) << 48);
+		int_to_scsilun(lun, &tsk_mgmt->lun);
 		tsk_mgmt->tsk_mgmt_func = SRP_TSK_LUN_RESET;
 
 		evt->sync_srp = &srp_rsp;

drivers/scsi/scsi_transport_srp.c

@@ -61,6 +61,11 @@ static inline struct Scsi_Host *rport_to_shost(struct srp_rport *r)
 	return dev_to_shost(r->dev.parent);
 }
 
+static inline struct srp_rport *shost_to_rport(struct Scsi_Host *shost)
+{
+	return transport_class_to_srp_rport(&shost->shost_gendev);
+}
+
 /**
  * srp_tmo_valid() - check timeout combination validity
  * @reconnect_delay: Reconnect delay in seconds.
@@ -396,6 +401,36 @@ static void srp_reconnect_work(struct work_struct *work)
 	}
 }
 
+/**
+ * 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.
+ *
+ * To do: add support for scsi-mq in this function.
+ */
+static int scsi_request_fn_active(struct Scsi_Host *shost)
+{
+	struct scsi_device *sdev;
+	struct request_queue *q;
+	int request_fn_active = 0;
+
+	shost_for_each_device(sdev, shost) {
+		q = sdev->request_queue;
+
+		spin_lock_irq(q->queue_lock);
+		request_fn_active += q->request_fn_active;
+		spin_unlock_irq(q->queue_lock);
+	}
+
+	return request_fn_active;
+}
+
+/* Wait until ongoing shost->hostt->queuecommand() calls have finished. */
+static void srp_wait_for_queuecommand(struct Scsi_Host *shost)
+{
+	while (scsi_request_fn_active(shost))
+		msleep(20);
+}
+
 static void __rport_fail_io_fast(struct srp_rport *rport)
 {
 	struct Scsi_Host *shost = rport_to_shost(rport);
@@ -409,8 +444,10 @@ static void __rport_fail_io_fast(struct srp_rport *rport)
 
 	/* Involve the LLD if possible to terminate all I/O on the rport. */
 	i = to_srp_internal(shost->transportt);
-	if (i->f->terminate_rport_io)
+	if (i->f->terminate_rport_io) {
+		srp_wait_for_queuecommand(shost);
 		i->f->terminate_rport_io(rport);
+	}
 }
 
 /**
@@ -503,27 +540,6 @@ void srp_start_tl_fail_timers(struct srp_rport *rport)
 }
 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)
-{
-	struct scsi_device *sdev;
-	struct request_queue *q;
-	int request_fn_active = 0;
-
-	shost_for_each_device(sdev, shost) {
-		q = sdev->request_queue;
-
-		spin_lock_irq(q->queue_lock);
-		request_fn_active += q->request_fn_active;
-		spin_unlock_irq(q->queue_lock);
-	}
-
-	return request_fn_active;
-}
-
 /**
  * srp_reconnect_rport() - reconnect to an SRP target port
  * @rport: SRP target port.
@@ -559,8 +575,7 @@ int srp_reconnect_rport(struct srp_rport *rport)
 	if (res)
 		goto out;
 	scsi_target_block(&shost->shost_gendev);
-	while (scsi_request_fn_active(shost))
-		msleep(20);
+	srp_wait_for_queuecommand(shost);
 	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);
@@ -618,9 +633,11 @@ static enum blk_eh_timer_return srp_timed_out(struct scsi_cmnd *scmd)
 	struct scsi_device *sdev = scmd->device;
 	struct Scsi_Host *shost = sdev->host;
 	struct srp_internal *i = to_srp_internal(shost->transportt);
+	struct srp_rport *rport = shost_to_rport(shost);
 
 	pr_debug("timeout for sdev %s\n", dev_name(&sdev->sdev_gendev));
-	return i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
+	return rport->fast_io_fail_tmo < 0 && rport->dev_loss_tmo < 0 &&
+		i->f->reset_timer_if_blocked && scsi_device_blocked(sdev) ?
 		BLK_EH_RESET_TIMER : BLK_EH_NOT_HANDLED;
 }
 

drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.c

@@ -647,6 +647,7 @@ kib_conn_t *kiblnd_create_conn(kib_peer_t *peer, struct rdma_cm_id *cmid,
 	kib_dev_t	      *dev;
 	struct ib_qp_init_attr *init_qp_attr;
 	struct kib_sched_info	*sched;
+	struct ib_cq_init_attr  cq_attr = {};
 	kib_conn_t		*conn;
 	struct ib_cq		*cq;
 	unsigned long		flags;
@@ -742,10 +743,11 @@ kib_conn_t *kiblnd_create_conn(kib_peer_t *peer, struct rdma_cm_id *cmid,
 
 	kiblnd_map_rx_descs(conn);
 
+	cq_attr.cqe = IBLND_CQ_ENTRIES(version);
+	cq_attr.comp_vector = kiblnd_get_completion_vector(conn, cpt);
 	cq = ib_create_cq(cmid->device,
 			  kiblnd_cq_completion, kiblnd_cq_event, conn,
-			  IBLND_CQ_ENTRIES(version),
-			  kiblnd_get_completion_vector(conn, cpt));
+			  &cq_attr);
 	if (IS_ERR(cq)) {
 		CERROR("Can't create CQ: %ld, cqe: %d\n",
 		       PTR_ERR(cq), IBLND_CQ_ENTRIES(version));

include/linux/mlx4/device.h

@@ -829,6 +829,12 @@ struct mlx4_dev {
 	struct mlx4_vf_dev     *dev_vfs;
 };
 
+struct mlx4_clock_params {
+	u64 offset;
+	u8 bar;
+	u8 size;
+};
+
 struct mlx4_eqe {
 	u8			reserved1;
 	u8			type;
@@ -1485,4 +1491,7 @@ int mlx4_ACCESS_PTYS_REG(struct mlx4_dev *dev,
 			 enum mlx4_access_reg_method method,
 			 struct mlx4_ptys_reg *ptys_reg);
 
+int mlx4_get_internal_clock_params(struct mlx4_dev *dev,
+				   struct mlx4_clock_params *params);
+
 #endif /* MLX4_DEVICE_H */

include/linux/mlx5/driver.h

@@ -696,7 +696,7 @@ int mlx5_core_dump_fill_mkey(struct mlx5_core_dev *dev, struct mlx5_core_mr *mr,
 			     u32 *mkey);
 int mlx5_core_alloc_pd(struct mlx5_core_dev *dev, u32 *pdn);
 int mlx5_core_dealloc_pd(struct mlx5_core_dev *dev, u32 pdn);
-int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, void *inb, void *outb,
+int mlx5_core_mad_ifc(struct mlx5_core_dev *dev, const void *inb, void *outb,
 		      u16 opmod, u8 port);
 void mlx5_pagealloc_init(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_cleanup(struct mlx5_core_dev *dev);

include/rdma/ib_addr.h

@@ -111,8 +111,8 @@ 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);
+int rdma_addr_find_dmac_by_grh(const union ib_gid *sgid, const union ib_gid *dgid,
+			       u8 *smac, u16 *vlan_id);
 
 static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
 {
@@ -160,7 +160,7 @@ static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
 }
 
 /* Important - sockaddr should be a union of sockaddr_in and sockaddr_in6 */
-static inline void rdma_gid2ip(struct sockaddr *out, union ib_gid *gid)
+static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid)
 {
 	if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
 		struct sockaddr_in *out_in = (struct sockaddr_in *)out;

include/rdma/ib_cache.h

@@ -64,10 +64,10 @@ int ib_get_cached_gid(struct ib_device    *device,
  * ib_find_cached_gid() searches for the specified GID value in
  * the local software cache.
  */
-int ib_find_cached_gid(struct ib_device *device,
-		       union ib_gid	*gid,
-		       u8               *port_num,
-		       u16              *index);
+int ib_find_cached_gid(struct ib_device   *device,
+		       const union ib_gid *gid,
+		       u8                 *port_num,
+		       u16                *index);
 
 /**
  * ib_get_cached_pkey - Returns a cached PKey table entry

include/rdma/ib_mad.h

@@ -42,8 +42,11 @@
 #include <rdma/ib_verbs.h>
 #include <uapi/rdma/ib_user_mad.h>
 
-/* Management base version */
+/* Management base versions */
 #define IB_MGMT_BASE_VERSION			1
+#define OPA_MGMT_BASE_VERSION			0x80
+
+#define OPA_SMP_CLASS_VERSION			0x80
 
 /* Management classes */
 #define IB_MGMT_CLASS_SUBN_LID_ROUTED		0x01
@@ -135,6 +138,10 @@ enum {
 	IB_MGMT_SA_DATA = 200,
 	IB_MGMT_DEVICE_HDR = 64,
 	IB_MGMT_DEVICE_DATA = 192,
+	IB_MGMT_MAD_SIZE = IB_MGMT_MAD_HDR + IB_MGMT_MAD_DATA,
+	OPA_MGMT_MAD_DATA = 2024,
+	OPA_MGMT_RMPP_DATA = 2012,
+	OPA_MGMT_MAD_SIZE = IB_MGMT_MAD_HDR + OPA_MGMT_MAD_DATA,
 };
 
 struct ib_mad_hdr {
@@ -181,12 +188,23 @@ struct ib_mad {
 	u8			data[IB_MGMT_MAD_DATA];
 };
 
+struct opa_mad {
+	struct ib_mad_hdr	mad_hdr;
+	u8			data[OPA_MGMT_MAD_DATA];
+};
+
 struct ib_rmpp_mad {
 	struct ib_mad_hdr	mad_hdr;
 	struct ib_rmpp_hdr	rmpp_hdr;
 	u8			data[IB_MGMT_RMPP_DATA];
 };
 
+struct opa_rmpp_mad {
+	struct ib_mad_hdr	mad_hdr;
+	struct ib_rmpp_hdr	rmpp_hdr;
+	u8			data[OPA_MGMT_RMPP_DATA];
+};
+
 struct ib_sa_mad {
 	struct ib_mad_hdr	mad_hdr;
 	struct ib_rmpp_hdr	rmpp_hdr;
@@ -235,7 +253,10 @@ struct ib_class_port_info {
  *   includes the common MAD, RMPP, and class specific headers.
  * @data_len: Indicates the total size of user-transferred data.
  * @seg_count: The number of RMPP segments allocated for this send.
- * @seg_size: Size of each RMPP segment.
+ * @seg_size: Size of the data in each RMPP segment.  This does not include
+ *   class specific headers.
+ * @seg_rmpp_size: Size of each RMPP segment including the class specific
+ *   headers.
  * @timeout_ms: Time to wait for a response.
  * @retries: Number of times to retry a request for a response.  For MADs
  *   using RMPP, this applies per window.  On completion, returns the number
@@ -255,6 +276,7 @@ struct ib_mad_send_buf {
 	int			data_len;
 	int			seg_count;
 	int			seg_size;
+	int			seg_rmpp_size;
 	int			timeout_ms;
 	int			retries;
 };
@@ -263,7 +285,7 @@ struct ib_mad_send_buf {
  * ib_response_mad - Returns if the specified MAD has been generated in
  *   response to a sent request or trap.
  */
-int ib_response_mad(struct ib_mad *mad);
+int ib_response_mad(const struct ib_mad_hdr *hdr);
 
 /**
  * ib_get_rmpp_resptime - Returns the RMPP response time.
@@ -401,7 +423,10 @@ struct ib_mad_send_wc {
 struct ib_mad_recv_buf {
 	struct list_head	list;
 	struct ib_grh		*grh;
-	struct ib_mad		*mad;
+	union {
+		struct ib_mad	*mad;
+		struct opa_mad	*opa_mad;
+	};
 };
 
 /**
@@ -410,6 +435,7 @@ struct ib_mad_recv_buf {
  * @recv_buf: Specifies the location of the received data buffer(s).
  * @rmpp_list: Specifies a list of RMPP reassembled received MAD buffers.
  * @mad_len: The length of the received MAD, without duplicated headers.
+ * @mad_seg_size: The size of individual MAD segments
  *
  * For received response, the wr_id contains a pointer to the ib_mad_send_buf
  *   for the corresponding send request.
@@ -419,6 +445,7 @@ struct ib_mad_recv_wc {
 	struct ib_mad_recv_buf	recv_buf;
 	struct list_head	rmpp_list;
 	int			mad_len;
+	size_t			mad_seg_size;
 };
 
 /**
@@ -618,6 +645,7 @@ int ib_process_mad_wc(struct ib_mad_agent *mad_agent,
  *   automatically adjust the allocated buffer size to account for any
  *   additional padding that may be necessary.
  * @gfp_mask: GFP mask used for the memory allocation.
+ * @base_version: Base Version of this MAD
  *
  * This routine allocates a MAD for sending.  The returned MAD send buffer
  * will reference a data buffer usable for sending a MAD, along
@@ -633,7 +661,8 @@ struct ib_mad_send_buf *ib_create_send_mad(struct ib_mad_agent *mad_agent,
 					   u32 remote_qpn, u16 pkey_index,
 					   int rmpp_active,
 					   int hdr_len, int data_len,
-					   gfp_t gfp_mask);
+					   gfp_t gfp_mask,
+					   u8 base_version);
 
 /**
  * ib_is_mad_class_rmpp - returns whether given management class
@@ -675,6 +704,6 @@ void ib_free_send_mad(struct ib_mad_send_buf *send_buf);
  * @agent: the agent in question
  * @return: true if agent is performing rmpp, false otherwise.
  */
-int ib_mad_kernel_rmpp_agent(struct ib_mad_agent *agent);
+int ib_mad_kernel_rmpp_agent(const struct ib_mad_agent *agent);
 
 #endif /* IB_MAD_H */

include/rdma/ib_verbs.h

@@ -81,6 +81,13 @@ enum rdma_transport_type {
 	RDMA_TRANSPORT_USNIC_UDP
 };
 
+enum rdma_protocol_type {
+	RDMA_PROTOCOL_IB,
+	RDMA_PROTOCOL_IBOE,
+	RDMA_PROTOCOL_IWARP,
+	RDMA_PROTOCOL_USNIC_UDP
+};
+
 __attribute_const__ enum rdma_transport_type
 rdma_node_get_transport(enum rdma_node_type node_type);
 
@@ -166,6 +173,16 @@ struct ib_odp_caps {
 	} per_transport_caps;
 };
 
+enum ib_cq_creation_flags {
+	IB_CQ_FLAGS_TIMESTAMP_COMPLETION   = 1 << 0,
+};
+
+struct ib_cq_init_attr {
+	unsigned int	cqe;
+	int		comp_vector;
+	u32		flags;
+};
+
 struct ib_device_attr {
 	u64			fw_ver;
 	__be64			sys_image_guid;
@@ -210,6 +227,8 @@ struct ib_device_attr {
 	int			sig_prot_cap;
 	int			sig_guard_cap;
 	struct ib_odp_caps	odp_caps;
+	uint64_t		timestamp_mask;
+	uint64_t		hca_core_clock; /* in KHZ */
 };
 
 enum ib_mtu {
@@ -346,6 +365,42 @@ union rdma_protocol_stats {
 	struct iw_protocol_stats	iw;
 };
 
+/* Define bits for the various functionality this port needs to be supported by
+ * the core.
+ */
+/* Management                           0x00000FFF */
+#define RDMA_CORE_CAP_IB_MAD            0x00000001
+#define RDMA_CORE_CAP_IB_SMI            0x00000002
+#define RDMA_CORE_CAP_IB_CM             0x00000004
+#define RDMA_CORE_CAP_IW_CM             0x00000008
+#define RDMA_CORE_CAP_IB_SA             0x00000010
+#define RDMA_CORE_CAP_OPA_MAD           0x00000020
+
+/* Address format                       0x000FF000 */
+#define RDMA_CORE_CAP_AF_IB             0x00001000
+#define RDMA_CORE_CAP_ETH_AH            0x00002000
+
+/* Protocol                             0xFFF00000 */
+#define RDMA_CORE_CAP_PROT_IB           0x00100000
+#define RDMA_CORE_CAP_PROT_ROCE         0x00200000
+#define RDMA_CORE_CAP_PROT_IWARP        0x00400000
+
+#define RDMA_CORE_PORT_IBA_IB          (RDMA_CORE_CAP_PROT_IB  \
+					| RDMA_CORE_CAP_IB_MAD \
+					| RDMA_CORE_CAP_IB_SMI \
+					| RDMA_CORE_CAP_IB_CM  \
+					| RDMA_CORE_CAP_IB_SA  \
+					| RDMA_CORE_CAP_AF_IB)
+#define RDMA_CORE_PORT_IBA_ROCE        (RDMA_CORE_CAP_PROT_ROCE \
+					| RDMA_CORE_CAP_IB_MAD  \
+					| RDMA_CORE_CAP_IB_CM   \
+					| RDMA_CORE_CAP_AF_IB   \
+					| RDMA_CORE_CAP_ETH_AH)
+#define RDMA_CORE_PORT_IWARP           (RDMA_CORE_CAP_PROT_IWARP \
+					| RDMA_CORE_CAP_IW_CM)
+#define RDMA_CORE_PORT_INTEL_OPA       (RDMA_CORE_PORT_IBA_IB  \
+					| RDMA_CORE_CAP_OPA_MAD)
+
 struct ib_port_attr {
 	enum ib_port_state	state;
 	enum ib_mtu		max_mtu;
@@ -412,6 +467,8 @@ enum ib_event_type {
 	IB_EVENT_GID_CHANGE,
 };
 
+__attribute_const__ const char *ib_event_msg(enum ib_event_type event);
+
 struct ib_event {
 	struct ib_device	*device;
 	union {
@@ -663,6 +720,8 @@ enum ib_wc_status {
 	IB_WC_GENERAL_ERR
 };
 
+__attribute_const__ const char *ib_wc_status_msg(enum ib_wc_status status);
+
 enum ib_wc_opcode {
 	IB_WC_SEND,
 	IB_WC_RDMA_WRITE,
@@ -1407,7 +1466,7 @@ struct ib_flow {
 	struct ib_uobject	*uobject;
 };
 
-struct ib_mad;
+struct ib_mad_hdr;
 struct ib_grh;
 
 enum ib_process_mad_flags {
@@ -1474,6 +1533,13 @@ struct ib_dma_mapping_ops {
 
 struct iw_cm_verbs;
 
+struct ib_port_immutable {
+	int                           pkey_tbl_len;
+	int                           gid_tbl_len;
+	u32                           core_cap_flags;
+	u32                           max_mad_size;
+};
+
 struct ib_device {
 	struct device                *dma_device;
 
@@ -1487,8 +1553,10 @@ struct ib_device {
 	struct list_head              client_data_list;
 
 	struct ib_cache               cache;
-	int                          *pkey_tbl_len;
-	int                          *gid_tbl_len;
+	/**
+	 * port_immutable is indexed by port number
+	 */
+	struct ib_port_immutable     *port_immutable;
 
 	int			      num_comp_vectors;
 
@@ -1497,7 +1565,8 @@ struct ib_device {
 	int		           (*get_protocol_stats)(struct ib_device *device,
 							 union rdma_protocol_stats *stats);
 	int		           (*query_device)(struct ib_device *device,
-						   struct ib_device_attr *device_attr);
+						   struct ib_device_attr *device_attr,
+						   struct ib_udata *udata);
 	int		           (*query_port)(struct ib_device *device,
 						 u8 port_num,
 						 struct ib_port_attr *port_attr);
@@ -1561,8 +1630,8 @@ struct ib_device {
 	int                        (*post_recv)(struct ib_qp *qp,
 						struct ib_recv_wr *recv_wr,
 						struct ib_recv_wr **bad_recv_wr);
-	struct ib_cq *             (*create_cq)(struct ib_device *device, int cqe,
-						int comp_vector,
+	struct ib_cq *             (*create_cq)(struct ib_device *device,
+						const struct ib_cq_init_attr *attr,
 						struct ib_ucontext *context,
 						struct ib_udata *udata);
 	int                        (*modify_cq)(struct ib_cq *cq, u16 cq_count,
@@ -1637,10 +1706,13 @@ struct ib_device {
 	int                        (*process_mad)(struct ib_device *device,
 						  int process_mad_flags,
 						  u8 port_num,
-						  struct ib_wc *in_wc,
-						  struct ib_grh *in_grh,
-						  struct ib_mad *in_mad,
-						  struct ib_mad *out_mad);
+						  const struct ib_wc *in_wc,
+						  const struct ib_grh *in_grh,
+						  const struct ib_mad_hdr *in_mad,
+						  size_t in_mad_size,
+						  struct ib_mad_hdr *out_mad,
+						  size_t *out_mad_size,
+						  u16 *out_mad_pkey_index);
 	struct ib_xrcd *	   (*alloc_xrcd)(struct ib_device *device,
 						 struct ib_ucontext *ucontext,
 						 struct ib_udata *udata);
@@ -1675,6 +1747,14 @@ struct ib_device {
 	u32			     local_dma_lkey;
 	u8                           node_type;
 	u8                           phys_port_cnt;
+
+	/**
+	 * The following mandatory functions are used only at device
+	 * registration.  Keep functions such as these at the end of this
+	 * structure to avoid cache line misses when accessing struct ib_device
+	 * in fast paths.
+	 */
+	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
 };
 
 struct ib_client {
@@ -1743,6 +1823,284 @@ int ib_query_port(struct ib_device *device,
 enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
 					       u8 port_num);
 
+/**
+ * rdma_start_port - Return the first valid port number for the device
+ * specified
+ *
+ * @device: Device to be checked
+ *
+ * Return start port number
+ */
+static inline u8 rdma_start_port(const struct ib_device *device)
+{
+	return (device->node_type == RDMA_NODE_IB_SWITCH) ? 0 : 1;
+}
+
+/**
+ * rdma_end_port - Return the last valid port number for the device
+ * specified
+ *
+ * @device: Device to be checked
+ *
+ * Return last port number
+ */
+static inline u8 rdma_end_port(const struct ib_device *device)
+{
+	return (device->node_type == RDMA_NODE_IB_SWITCH) ?
+		0 : device->phys_port_cnt;
+}
+
+static inline bool rdma_protocol_ib(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IB;
+}
+
+static inline bool rdma_protocol_roce(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE;
+}
+
+static inline bool rdma_protocol_iwarp(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IWARP;
+}
+
+static inline bool rdma_ib_or_roce(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags &
+		(RDMA_CORE_CAP_PROT_IB | RDMA_CORE_CAP_PROT_ROCE);
+}
+
+/**
+ * rdma_cap_ib_mad - Check if the port of a device supports Infiniband
+ * Management Datagrams.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Management Datagrams (MAD) are a required part of the InfiniBand
+ * specification and are supported on all InfiniBand devices.  A slightly
+ * extended version are also supported on OPA interfaces.
+ *
+ * Return: true if the port supports sending/receiving of MAD packets.
+ */
+static inline bool rdma_cap_ib_mad(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_MAD;
+}
+
+/**
+ * rdma_cap_opa_mad - Check if the port of device provides support for OPA
+ * Management Datagrams.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Intel OmniPath devices extend and/or replace the InfiniBand Management
+ * datagrams with their own versions.  These OPA MADs share many but not all of
+ * the characteristics of InfiniBand MADs.
+ *
+ * OPA MADs differ in the following ways:
+ *
+ *    1) MADs are variable size up to 2K
+ *       IBTA defined MADs remain fixed at 256 bytes
+ *    2) OPA SMPs must carry valid PKeys
+ *    3) OPA SMP packets are a different format
+ *
+ * Return: true if the port supports OPA MAD packet formats.
+ */
+static inline bool rdma_cap_opa_mad(struct ib_device *device, u8 port_num)
+{
+	return (device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_OPA_MAD)
+		== RDMA_CORE_CAP_OPA_MAD;
+}
+
+/**
+ * rdma_cap_ib_smi - Check if the port of a device provides an Infiniband
+ * Subnet Management Agent (SMA) on the Subnet Management Interface (SMI).
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Each InfiniBand node is required to provide a Subnet Management Agent
+ * that the subnet manager can access.  Prior to the fabric being fully
+ * configured by the subnet manager, the SMA is accessed via a well known
+ * interface called the Subnet Management Interface (SMI).  This interface
+ * uses directed route packets to communicate with the SM to get around the
+ * chicken and egg problem of the SM needing to know what's on the fabric
+ * in order to configure the fabric, and needing to configure the fabric in
+ * order to send packets to the devices on the fabric.  These directed
+ * route packets do not need the fabric fully configured in order to reach
+ * their destination.  The SMI is the only method allowed to send
+ * directed route packets on an InfiniBand fabric.
+ *
+ * Return: true if the port provides an SMI.
+ */
+static inline bool rdma_cap_ib_smi(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SMI;
+}
+
+/**
+ * rdma_cap_ib_cm - Check if the port of device has the capability Infiniband
+ * Communication Manager.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * The InfiniBand Communication Manager is one of many pre-defined General
+ * Service Agents (GSA) that are accessed via the General Service
+ * Interface (GSI).  It's role is to facilitate establishment of connections
+ * between nodes as well as other management related tasks for established
+ * connections.
+ *
+ * Return: true if the port supports an IB CM (this does not guarantee that
+ * a CM is actually running however).
+ */
+static inline bool rdma_cap_ib_cm(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_CM;
+}
+
+/**
+ * rdma_cap_iw_cm - Check if the port of device has the capability IWARP
+ * Communication Manager.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * Similar to above, but specific to iWARP connections which have a different
+ * managment protocol than InfiniBand.
+ *
+ * Return: true if the port supports an iWARP CM (this does not guarantee that
+ * a CM is actually running however).
+ */
+static inline bool rdma_cap_iw_cm(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IW_CM;
+}
+
+/**
+ * rdma_cap_ib_sa - Check if the port of device has the capability Infiniband
+ * Subnet Administration.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * An InfiniBand Subnet Administration (SA) service is a pre-defined General
+ * Service Agent (GSA) provided by the Subnet Manager (SM).  On InfiniBand
+ * fabrics, devices should resolve routes to other hosts by contacting the
+ * SA to query the proper route.
+ *
+ * Return: true if the port should act as a client to the fabric Subnet
+ * Administration interface.  This does not imply that the SA service is
+ * running locally.
+ */
+static inline bool rdma_cap_ib_sa(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_IB_SA;
+}
+
+/**
+ * rdma_cap_ib_mcast - Check if the port of device has the capability Infiniband
+ * Multicast.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * InfiniBand multicast registration is more complex than normal IPv4 or
+ * IPv6 multicast registration.  Each Host Channel Adapter must register
+ * with the Subnet Manager when it wishes to join a multicast group.  It
+ * should do so only once regardless of how many queue pairs it subscribes
+ * to this group.  And it should leave the group only after all queue pairs
+ * attached to the group have been detached.
+ *
+ * Return: true if the port must undertake the additional adminstrative
+ * overhead of registering/unregistering with the SM and tracking of the
+ * total number of queue pairs attached to the multicast group.
+ */
+static inline bool rdma_cap_ib_mcast(const struct ib_device *device, u8 port_num)
+{
+	return rdma_cap_ib_sa(device, port_num);
+}
+
+/**
+ * rdma_cap_af_ib - Check if the port of device has the capability
+ * Native Infiniband Address.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * InfiniBand addressing uses a port's GUID + Subnet Prefix to make a default
+ * GID.  RoCE uses a different mechanism, but still generates a GID via
+ * a prescribed mechanism and port specific data.
+ *
+ * Return: true if the port uses a GID address to identify devices on the
+ * network.
+ */
+static inline bool rdma_cap_af_ib(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_AF_IB;
+}
+
+/**
+ * rdma_cap_eth_ah - Check if the port of device has the capability
+ * Ethernet Address Handle.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * RoCE is InfiniBand over Ethernet, and it uses a well defined technique
+ * to fabricate GIDs over Ethernet/IP specific addresses native to the
+ * port.  Normally, packet headers are generated by the sending host
+ * adapter, but when sending connectionless datagrams, we must manually
+ * inject the proper headers for the fabric we are communicating over.
+ *
+ * Return: true if we are running as a RoCE port and must force the
+ * addition of a Global Route Header built from our Ethernet Address
+ * Handle into our header list for connectionless packets.
+ */
+static inline bool rdma_cap_eth_ah(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_ETH_AH;
+}
+
+/**
+ * rdma_cap_read_multi_sge - Check if the port of device has the capability
+ * RDMA Read Multiple Scatter-Gather Entries.
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * iWARP has a restriction that RDMA READ requests may only have a single
+ * Scatter/Gather Entry (SGE) in the work request.
+ *
+ * NOTE: although the linux kernel currently assumes all devices are either
+ * single SGE RDMA READ devices or identical SGE maximums for RDMA READs and
+ * WRITEs, according to Tom Talpey, this is not accurate.  There are some
+ * devices out there that support more than a single SGE on RDMA READ
+ * requests, but do not support the same number of SGEs as they do on
+ * RDMA WRITE requests.  The linux kernel would need rearchitecting to
+ * support these imbalanced READ/WRITE SGEs allowed devices.  So, for now,
+ * suffice with either the device supports the same READ/WRITE SGEs, or
+ * it only gets one READ sge.
+ *
+ * Return: true for any device that allows more than one SGE in RDMA READ
+ * requests.
+ */
+static inline bool rdma_cap_read_multi_sge(struct ib_device *device,
+					   u8 port_num)
+{
+	return !(device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_IWARP);
+}
+
+/**
+ * rdma_max_mad_size - Return the max MAD size required by this RDMA Port.
+ *
+ * @device: Device
+ * @port_num: Port number
+ *
+ * This MAD size includes the MAD headers and MAD payload.  No other headers
+ * are included.
+ *
+ * Return the max MAD size required by the Port.  Will return 0 if the port
+ * does not support MADs
+ */
+static inline size_t rdma_max_mad_size(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].max_mad_size;
+}
+
 int ib_query_gid(struct ib_device *device,
 		 u8 port_num, int index, union ib_gid *gid);
 
@@ -1799,8 +2157,9 @@ struct ib_ah *ib_create_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr);
  * @ah_attr: Returned attributes that can be used when creating an address
  *   handle for replying to the message.
  */
-int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
-		       struct ib_grh *grh, struct ib_ah_attr *ah_attr);
+int ib_init_ah_from_wc(struct ib_device *device, u8 port_num,
+		       const struct ib_wc *wc, const struct ib_grh *grh,
+		       struct ib_ah_attr *ah_attr);
 
 /**
  * ib_create_ah_from_wc - Creates an address handle associated with the
@@ -1814,8 +2173,8 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
  * The address handle is used to reference a local or global destination
  * in all UD QP post sends.
  */
-struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, struct ib_wc *wc,
-				   struct ib_grh *grh, u8 port_num);
+struct ib_ah *ib_create_ah_from_wc(struct ib_pd *pd, const struct ib_wc *wc,
+				   const struct ib_grh *grh, u8 port_num);
 
 /**
  * ib_modify_ah - Modifies the address vector associated with an address
@@ -2011,16 +2370,15 @@ static inline int ib_post_recv(struct ib_qp *qp,
  *   asynchronous event not associated with a completion occurs on the CQ.
  * @cq_context: Context associated with the CQ returned to the user via
  *   the associated completion and event handlers.
- * @cqe: The minimum size of the CQ.
- * @comp_vector - Completion vector used to signal completion events.
- *     Must be >= 0 and < context->num_comp_vectors.
+ * @cq_attr: The attributes the CQ should be created upon.
  *
  * Users can examine the cq structure to determine the actual CQ size.
  */
 struct ib_cq *ib_create_cq(struct ib_device *device,
 			   ib_comp_handler comp_handler,
 			   void (*event_handler)(struct ib_event *, void *),
-			   void *cq_context, int cqe, int comp_vector);
+			   void *cq_context,
+			   const struct ib_cq_init_attr *cq_attr);
 
 /**
  * ib_resize_cq - Modifies the capacity of the CQ.

include/rdma/iw_cm.h

@@ -91,6 +91,7 @@ struct iw_cm_id {
 	/* Used by provider to add and remove refs on IW cm_id */
 	void (*add_ref)(struct iw_cm_id *);
 	void (*rem_ref)(struct iw_cm_id *);
+	u8  tos;
 };
 
 struct iw_cm_conn_param {

include/rdma/opa_smi.h

@@ -0,0 +1,106 @@
+/*
+ * Copyright (c) 2014 Intel Corporation.  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.
+ */
+
+#if !defined(OPA_SMI_H)
+#define OPA_SMI_H
+
+#include <rdma/ib_mad.h>
+#include <rdma/ib_smi.h>
+
+#define OPA_SMP_LID_DATA_SIZE			2016
+#define OPA_SMP_DR_DATA_SIZE			1872
+#define OPA_SMP_MAX_PATH_HOPS			64
+
+#define OPA_SMI_CLASS_VERSION			0x80
+
+#define OPA_LID_PERMISSIVE			cpu_to_be32(0xFFFFFFFF)
+
+struct opa_smp {
+	u8	base_version;
+	u8	mgmt_class;
+	u8	class_version;
+	u8	method;
+	__be16	status;
+	u8	hop_ptr;
+	u8	hop_cnt;
+	__be64	tid;
+	__be16	attr_id;
+	__be16	resv;
+	__be32	attr_mod;
+	__be64	mkey;
+	union {
+		struct {
+			uint8_t data[OPA_SMP_LID_DATA_SIZE];
+		} lid;
+		struct {
+			__be32	dr_slid;
+			__be32	dr_dlid;
+			u8	initial_path[OPA_SMP_MAX_PATH_HOPS];
+			u8	return_path[OPA_SMP_MAX_PATH_HOPS];
+			u8	reserved[8];
+			u8	data[OPA_SMP_DR_DATA_SIZE];
+		} dr;
+	} route;
+} __packed;
+
+
+static inline u8
+opa_get_smp_direction(struct opa_smp *smp)
+{
+	return ib_get_smp_direction((struct ib_smp *)smp);
+}
+
+static inline u8 *opa_get_smp_data(struct opa_smp *smp)
+{
+	if (smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+		return smp->route.dr.data;
+
+	return smp->route.lid.data;
+}
+
+static inline size_t opa_get_smp_data_size(struct opa_smp *smp)
+{
+	if (smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+		return sizeof(smp->route.dr.data);
+
+	return sizeof(smp->route.lid.data);
+}
+
+static inline size_t opa_get_smp_header_size(struct opa_smp *smp)
+{
+	if (smp->mgmt_class == IB_MGMT_CLASS_SUBN_DIRECTED_ROUTE)
+		return sizeof(*smp) - sizeof(smp->route.dr.data);
+
+	return sizeof(*smp) - sizeof(smp->route.lid.data);
+}
+
+#endif /* OPA_SMI_H */

include/rdma/rdma_cm.h

@@ -62,6 +62,8 @@ enum rdma_cm_event_type {
 	RDMA_CM_EVENT_TIMEWAIT_EXIT
 };
 
+__attribute_const__ const char *rdma_event_msg(enum rdma_cm_event_type event);
+
 enum rdma_port_space {
 	RDMA_PS_SDP   = 0x0001,
 	RDMA_PS_IPOIB = 0x0002,

include/scsi/srp.h

@@ -42,6 +42,7 @@
  */
 
 #include <linux/types.h>
+#include <scsi/scsi.h>
 
 enum {
 	SRP_LOGIN_REQ	= 0x00,
@@ -179,7 +180,7 @@ struct srp_tsk_mgmt {
 	u8	reserved1[6];
 	u64	tag;
 	u8	reserved2[4];
-	__be64	lun __attribute__((packed));
+	struct scsi_lun	lun;
 	u8	reserved3[2];
 	u8	tsk_mgmt_func;
 	u8	reserved4;
@@ -200,7 +201,7 @@ struct srp_cmd {
 	u8	data_in_desc_cnt;
 	u64	tag;
 	u8	reserved2[4];
-	__be64	lun __attribute__((packed));
+	struct scsi_lun	lun;
 	u8	reserved3;
 	u8	task_attr;
 	u8	reserved4;
@@ -265,7 +266,7 @@ struct srp_aer_req {
 	__be32	req_lim_delta;
 	u64	tag;
 	u32	reserved2;
-	__be64	lun;
+	struct scsi_lun	lun;
 	__be32	sense_data_len;
 	u32	reserved3;
 	u8	sense_data[0];

include/uapi/rdma/ib_user_verbs.h

@@ -91,6 +91,7 @@ enum {
 
 enum {
 	IB_USER_VERBS_EX_CMD_QUERY_DEVICE = IB_USER_VERBS_CMD_QUERY_DEVICE,
+	IB_USER_VERBS_EX_CMD_CREATE_CQ = IB_USER_VERBS_CMD_CREATE_CQ,
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
 	IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
 };
@@ -222,6 +223,8 @@ struct ib_uverbs_ex_query_device_resp {
 	__u32 comp_mask;
 	__u32 response_length;
 	struct ib_uverbs_odp_caps odp_caps;
+	__u64 timestamp_mask;
+	__u64 hca_core_clock; /* in KHZ */
 };
 
 struct ib_uverbs_query_port {
@@ -353,11 +356,27 @@ struct ib_uverbs_create_cq {
 	__u64 driver_data[0];
 };
 
+struct ib_uverbs_ex_create_cq {
+	__u64 user_handle;
+	__u32 cqe;
+	__u32 comp_vector;
+	__s32 comp_channel;
+	__u32 comp_mask;
+	__u32 flags;
+	__u32 reserved;
+};
+
 struct ib_uverbs_create_cq_resp {
 	__u32 cq_handle;
 	__u32 cqe;
 };
 
+struct ib_uverbs_ex_create_cq_resp {
+	struct ib_uverbs_create_cq_resp base;
+	__u32 comp_mask;
+	__u32 response_length;
+};
+
 struct ib_uverbs_resize_cq {
 	__u64 response;
 	__u32 cq_handle;

net/9p/trans_rdma.c

@@ -648,6 +648,7 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
 	struct rdma_conn_param conn_param;
 	struct ib_qp_init_attr qp_attr;
 	struct ib_device_attr devattr;
+	struct ib_cq_init_attr cq_attr = {};
 
 	/* Parse the transport specific mount options */
 	err = parse_opts(args, &opts);
@@ -705,9 +706,10 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
 		goto error;
 
 	/* Create the Completion Queue */
+	cq_attr.cqe = opts.sq_depth + opts.rq_depth + 1;
 	rdma->cq = ib_create_cq(rdma->cm_id->device, cq_comp_handler,
 				cq_event_handler, client,
-				opts.sq_depth + opts.rq_depth + 1, 0);
+				&cq_attr);
 	if (IS_ERR(rdma->cq))
 		goto error;
 	ib_req_notify_cq(rdma->cq, IB_CQ_NEXT_COMP);

net/rds/af_rds.c

@@ -40,15 +40,6 @@
 
 #include "rds.h"
 
-char *rds_str_array(char **array, size_t elements, size_t index)
-{
-	if ((index < elements) && array[index])
-		return array[index];
-	else
-		return "unknown";
-}
-EXPORT_SYMBOL(rds_str_array);
-
 /* this is just used for stats gathering :/ */
 static DEFINE_SPINLOCK(rds_sock_lock);
 static unsigned long rds_sock_count;