32 files changed, 4838 insertions, 1575 deletions

diff --git a/sys/ofed/include/rdma/ib.h b/sys/ofed/include/rdma/ib.h
new file mode 100644
index 000000000000..8d4aefcc9127
--- /dev/null
+++ b/sys/ofed/include/rdma/ib.h
@@ -0,0 +1,120 @@
+/*
+ * Copyright (c) 2010 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(_RDMA_IB_H)
+#define _RDMA_IB_H
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+
+/*
+ * Define a native infiniband address as in Linux upstream
+ * 8d36eb01da5d371feffa280e501377b5c450f5a5
+ */
+#define	AF_IB	41
+
+struct ib_addr {
+	union {
+		__u8		uib_addr8[16];
+		__be16		uib_addr16[8];
+		__be32		uib_addr32[4];
+		__be64		uib_addr64[2];
+	} ib_u;
+#define sib_addr8		ib_u.uib_addr8
+#define sib_addr16		ib_u.uib_addr16
+#define sib_addr32		ib_u.uib_addr32
+#define sib_addr64		ib_u.uib_addr64
+#define sib_raw			ib_u.uib_addr8
+#define sib_subnet_prefix	ib_u.uib_addr64[0]
+#define sib_interface_id	ib_u.uib_addr64[1]
+};
+
+static inline int ib_addr_any(const struct ib_addr *a)
+{
+	return ((a->sib_addr64[0] | a->sib_addr64[1]) == 0);
+}
+
+static inline int ib_addr_loopback(const struct ib_addr *a)
+{
+	return ((a->sib_addr32[0] | a->sib_addr32[1] |
+		 a->sib_addr32[2] | (a->sib_addr32[3] ^ htonl(1))) == 0);
+}
+
+static inline void ib_addr_set(struct ib_addr *addr,
+			       __be32 w1, __be32 w2, __be32 w3, __be32 w4)
+{
+	addr->sib_addr32[0] = w1;
+	addr->sib_addr32[1] = w2;
+	addr->sib_addr32[2] = w3;
+	addr->sib_addr32[3] = w4;
+}
+
+static inline int ib_addr_cmp(const struct ib_addr *a1, const struct ib_addr *a2)
+{
+	return memcmp(a1, a2, sizeof(struct ib_addr));
+}
+
+struct sockaddr_ib {
+	unsigned short int	sib_family;	/* AF_IB */
+	__be16			sib_pkey;
+	__be32			sib_flowinfo;
+	struct ib_addr		sib_addr;
+	__be64			sib_sid;
+	__be64			sib_sid_mask;
+	__u64			sib_scope_id;
+};
+
+/*
+ * The IB interfaces that use write() as bi-directional ioctl() are
+ * fundamentally unsafe, since there are lots of ways to trigger "write()"
+ * calls from various contexts with elevated privileges. That includes the
+ * traditional suid executable error message writes, but also various kernel
+ * interfaces that can write to file descriptors.
+ *
+ * This function provides protection for the legacy API by restricting the
+ * calling context.
+ */
+static inline bool ib_safe_file_access(struct file *filp)
+{
+	struct thread *td = curthread;
+
+	/*
+	 * Check if called from userspace through a devfs related
+	 * system call belonging to the given file:
+	 */
+	return (filp->_file != NULL &&
+		filp->_file == td->td_fpop &&
+		filp->_file->f_cred == td->td_ucred);
+}
+
+#endif /* _RDMA_IB_H */
diff --git a/sys/ofed/include/rdma/ib_addr.h b/sys/ofed/include/rdma/ib_addr.h
index c62f3ebba284..1dbe844cc8d0 100644
--- a/sys/ofed/include/rdma/ib_addr.h
+++ b/sys/ofed/include/rdma/ib_addr.h
@@ -31,7 +31,7 @@
  * SOFTWARE.
  */
 
-#ifndef IB_ADDR_H
+#if !defined(IB_ADDR_H)
 #define IB_ADDR_H
 
 #include <linux/in.h>
@@ -41,9 +41,11 @@
 #include <linux/inetdevice.h>
 #include <linux/socket.h>
 #include <linux/if_vlan.h>
+#include <net/ipv6.h>
+#include <net/if_inet6.h>
+#include <net/ip.h>
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
-#include <net/if_inet6.h>
 #include <net/ipv6.h>
 
 struct rdma_addr_client {
@@ -62,6 +64,17 @@ void rdma_addr_register_client(struct rdma_addr_client *client);
  */
 void rdma_addr_unregister_client(struct rdma_addr_client *client);
 
+/**
+ * struct rdma_dev_addr - Contains resolved RDMA hardware addresses
+ * @src_dev_addr:	Source MAC address.
+ * @dst_dev_addr:	Destination MAC address.
+ * @broadcast:		Broadcast address of the device.
+ * @dev_type:		The interface hardware type of the device.
+ * @bound_dev_if:	An optional device interface index.
+ * @transport:		The transport type used.
+ * @net:		Network namespace containing the bound_dev_if net_dev.
+ */
+struct vnet;
 struct rdma_dev_addr {
 	unsigned char src_dev_addr[MAX_ADDR_LEN];
 	unsigned char dst_dev_addr[MAX_ADDR_LEN];
@@ -69,14 +82,19 @@ struct rdma_dev_addr {
 	unsigned short dev_type;
 	int bound_dev_if;
 	enum rdma_transport_type transport;
+	struct vnet *net;
+	enum rdma_network_type network;
+	int hoplimit;
 };
 
 /**
  * rdma_translate_ip - Translate a local IP address to an RDMA hardware
  *   address.
+ *
+ * The dev_addr->net field must be initialized.
  */
-int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
-		      u16 *vlan_id);
+int rdma_translate_ip(const struct sockaddr *addr,
+		      struct rdma_dev_addr *dev_addr, u16 *vlan_id);
 
 /**
  * rdma_resolve_ip - Resolve source and destination IP addresses to
@@ -88,7 +106,7 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
  * @dst_addr: The destination address to resolve.
  * @addr: A reference to a data location that will receive the resolved
  *   addresses.  The data location must remain valid until the callback has
- *   been invoked.
+ *   been invoked. The net field of the addr struct must be valid.
  * @timeout_ms: Amount of time to wait for the address resolution to complete.
  * @callback: Call invoked once address resolution has completed, timed out,
  *   or been canceled.  A status of 0 indicates success.
@@ -101,20 +119,22 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
 				     struct rdma_dev_addr *addr, void *context),
 		    void *context);
 
+int rdma_resolve_ip_route(struct sockaddr *src_addr,
+			  const struct sockaddr *dst_addr,
+			  struct rdma_dev_addr *addr);
+
 void rdma_addr_cancel(struct rdma_dev_addr *addr);
 
 int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
 	      const unsigned char *dst_dev_addr);
-int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id,
-				u32 scope_id);
-int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac,
-			       u16 *vlan_id, u32 scope_id);
 
-static inline int ip_addr_size(struct sockaddr *addr)
-{
-	return addr->sa_family == AF_INET6 ?
-	       sizeof(struct sockaddr_in6) : sizeof(struct sockaddr_in);
-}
+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_l2_eth_by_grh(const union ib_gid *sgid,
+				 const union ib_gid *dgid,
+				 u8 *smac, u16 *vlan_id, int *if_index,
+				 int *hoplimit);
 
 static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
 {
@@ -147,16 +167,16 @@ static inline u16 rdma_vlan_dev_vlan_id(const struct net_device *dev)
 	return tag;
 }
 
-static inline int rdma_ip2gid(struct sockaddr *addr, union ib_gid *gid)
+static inline int rdma_ip2gid(const struct sockaddr *addr, union ib_gid *gid)
 {
 	switch (addr->sa_family) {
 	case AF_INET:
-		ipv6_addr_set_v4mapped(((struct sockaddr_in *)addr)->sin_addr.s_addr,
+		ipv6_addr_set_v4mapped(((const struct sockaddr_in *)
+					addr)->sin_addr.s_addr,
 				       (struct in6_addr *)gid);
 		break;
 	case AF_INET6:
-		memcpy(gid->raw, &((struct sockaddr_in6 *)addr)->sin6_addr,
-				   16);
+		memcpy(gid->raw, &((const struct sockaddr_in6 *)addr)->sin6_addr, 16);
 		break;
 	default:
 		return -EINVAL;
@@ -165,10 +185,9 @@ 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 int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid,
-    uint32_t scope_id)
+static inline void rdma_gid2ip(struct sockaddr *out, const union ib_gid *gid)
 {
-	if (ipv6_addr_v4mapped((struct in6_addr *)gid)) {
+	if (ipv6_addr_v4mapped((const struct in6_addr *)gid)) {
 		struct sockaddr_in *out_in = (struct sockaddr_in *)out;
 		memset(out_in, 0, sizeof(*out_in));
 		out_in->sin_len = sizeof(*out_in);
@@ -180,21 +199,28 @@ static inline int rdma_gid2ip(struct sockaddr *out, union ib_gid *gid,
 		out_in->sin6_len = sizeof(*out_in);
 		out_in->sin6_family = AF_INET6;
 		memcpy(&out_in->sin6_addr.s6_addr, gid->raw, 16);
-		if (scope_id < 256 &&
-		    IN6_IS_SCOPE_LINKLOCAL(&out_in->sin6_addr))
-			out_in->sin6_scope_id = scope_id;
 	}
-	return 0;
 }
 
-u32 rdma_get_ipv6_scope_id(struct ib_device *ib, u8 port_num);
-
-/* This func is called only in loopback ip address (127.0.0.1)
- * case in which sgid is not relevant
- */
 static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 				      union ib_gid *gid)
 {
+	struct net_device *dev;
+	struct ifaddr *ifa;
+
+	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+	if (dev) {
+		TAILQ_FOREACH(ifa, &dev->if_addrhead, ifa_link) {
+			if (ifa->ifa_addr == NULL ||
+			    ifa->ifa_addr->sa_family != AF_INET)
+				continue;
+			ipv6_addr_set_v4mapped(((struct sockaddr_in *)
+					       ifa->ifa_addr)->sin_addr.s_addr,
+					       (struct in6_addr *)gid);
+			break;
+		}
+		dev_put(dev);
+	}
 }
 
 static inline void rdma_addr_get_sgid(struct rdma_dev_addr *dev_addr, union ib_gid *gid)
@@ -246,13 +272,19 @@ static inline enum ib_mtu iboe_get_mtu(int mtu)
 
 static inline int iboe_get_rate(struct net_device *dev)
 {
-	if (dev->if_baudrate >= IF_Gbps(40))
+	uint64_t baudrate = dev->if_baudrate;
+#ifdef if_baudrate_pf
+	int exp;
+	for (exp = dev->if_baudrate_pf; exp > 0; exp--)
+		baudrate *= 10;
+#endif
+	if (baudrate >= IF_Gbps(40))
 		return IB_RATE_40_GBPS;
-	else if (dev->if_baudrate >= IF_Gbps(30))
+	else if (baudrate >= IF_Gbps(30))
 		return IB_RATE_30_GBPS;
-	else if (dev->if_baudrate >= IF_Gbps(20))
+	else if (baudrate >= IF_Gbps(20))
 		return IB_RATE_20_GBPS;
-	else if (dev->if_baudrate >= IF_Gbps(10))
+	else if (baudrate >= IF_Gbps(10))
 		return IB_RATE_10_GBPS;
 	else
 		return IB_RATE_PORT_CURRENT;
@@ -279,20 +311,6 @@ static inline int rdma_is_multicast_addr(struct in6_addr *addr)
 	return addr->s6_addr[0] == 0xff;
 }
 
-static inline void resolve_mcast_mac(struct in6_addr *addr, u8 *mac)
-{
-	if (addr->s6_addr[0] != 0xff)
-		return;
-
-#ifdef DUAL_MODE_MCAST_MAC
-	if (addr->s6_addr[1] == 0x0e) /* IPv4 */
-		ip_eth_mc_map(addr->s6_addr32[3], mac);
-	else
-#endif
-		ipv6_eth_mc_map(addr, mac);
-}
-
-
 static inline void rdma_get_mcast_mac(struct in6_addr *addr, u8 *mac)
 {
 	int i;
@@ -308,7 +326,7 @@ static inline u16 rdma_get_vlan_id(union ib_gid *dgid)
 	u16 vid;
 
 	vid = dgid->raw[11] << 8 | dgid->raw[12];
-	return vid < 0x1000 ? vid  : 0xffff;
+	return vid < 0x1000 ? vid : 0xffff;
 }
 
 static inline struct net_device *rdma_vlan_dev_real_dev(const struct net_device *dev)
diff --git a/sys/ofed/include/rdma/ib_cache.h b/sys/ofed/include/rdma/ib_cache.h
index ad9a3c280944..e30f19bd4a41 100644
--- a/sys/ofed/include/rdma/ib_cache.h
+++ b/sys/ofed/include/rdma/ib_cache.h
@@ -43,6 +43,8 @@
  * @port_num: The port number of the device to query.
  * @index: The index into the cached GID table to query.
  * @gid: The GID value found at the specified index.
+ * @attr: The GID attribute found at the specified index (only in RoCE).
+ *   NULL means ignore (output parameter).
  *
  * ib_get_cached_gid() fetches the specified GID table entry stored in
  * the local software cache.
@@ -50,13 +52,16 @@
 int ib_get_cached_gid(struct ib_device    *device,
 		      u8                   port_num,
 		      int                  index,
-		      union ib_gid        *gid);
+		      union ib_gid        *gid,
+		      struct ib_gid_attr  *attr);
 
 /**
  * ib_find_cached_gid - Returns the port number and GID table index where
  *   a specified GID value occurs.
  * @device: The device to query.
  * @gid: The GID value to search for.
+ * @gid_type: The GID type to search for.
+ * @ndev: In RoCE, the net device of the device. NULL means ignore.
  * @port_num: The port number of the device where the GID value was found.
  * @index: The index into the cached GID table where the GID was found.  This
  *   parameter may be NULL.
@@ -65,11 +70,42 @@ int ib_get_cached_gid(struct ib_device    *device,
  * the local software cache.
  */
 int ib_find_cached_gid(struct ib_device *device,
-		       union ib_gid	*gid,
+		       const union ib_gid *gid,
+		       enum ib_gid_type gid_type,
+		       struct net_device *ndev,
 		       u8               *port_num,
 		       u16              *index);
 
 /**
+ * ib_find_cached_gid_by_port - Returns the GID table index where a specified
+ * GID value occurs
+ * @device: The device to query.
+ * @gid: The GID value to search for.
+ * @gid_type: The GID type to search for.
+ * @port_num: The port number of the device where the GID value sould be
+ *   searched.
+ * @ndev: In RoCE, the net device of the device. Null means ignore.
+ * @index: The index into the cached GID table where the GID was found.  This
+ *   parameter may be NULL.
+ *
+ * ib_find_cached_gid() searches for the specified GID value in
+ * the local software cache.
+ */
+int ib_find_cached_gid_by_port(struct ib_device *device,
+			       const union ib_gid *gid,
+			       enum ib_gid_type gid_type,
+			       u8               port_num,
+			       struct net_device *ndev,
+			       u16              *index);
+
+int ib_find_gid_by_filter(struct ib_device *device,
+			  const union ib_gid *gid,
+			  u8 port_num,
+			  bool (*filter)(const union ib_gid *gid,
+					 const struct ib_gid_attr *,
+					 void *),
+			  void *context, u16 *index);
+/**
  * ib_get_cached_pkey - Returns a cached PKey table entry
  * @device: The device to query.
  * @port_num: The port number of the device to query.
diff --git a/sys/ofed/include/rdma/ib_cm.h b/sys/ofed/include/rdma/ib_cm.h
index a7ffaf950391..92a7d85917b4 100644
--- a/sys/ofed/include/rdma/ib_cm.h
+++ b/sys/ofed/include/rdma/ib_cm.h
@@ -105,13 +105,16 @@ enum ib_cm_data_size {
 	IB_CM_SIDR_REQ_PRIVATE_DATA_SIZE = 216,
 	IB_CM_SIDR_REP_PRIVATE_DATA_SIZE = 136,
 	IB_CM_SIDR_REP_INFO_LENGTH	 = 72,
-	IB_CM_COMPARE_SIZE		 = 64
 };
 
 struct ib_cm_id;
 
 struct ib_cm_req_event_param {
 	struct ib_cm_id		*listen_id;
+
+	/* P_Key that was used by the GMP's BTH header */
+	u16			bth_pkey;
+
 	u8			port;
 
 	struct ib_sa_path_rec	*primary_path;
@@ -222,6 +225,9 @@ struct ib_cm_apr_event_param {
 
 struct ib_cm_sidr_req_event_param {
 	struct ib_cm_id		*listen_id;
+	__be64			service_id;
+	/* P_Key that was used by the GMP's BTH header */
+	u16			bth_pkey;
 	u8			port;
 	u16			pkey;
 };
@@ -336,11 +342,6 @@ void ib_destroy_cm_id(struct ib_cm_id *cm_id);
 #define IB_SDP_SERVICE_ID	cpu_to_be64(0x0000000000010000ULL)
 #define IB_SDP_SERVICE_ID_MASK	cpu_to_be64(0xFFFFFFFFFFFF0000ULL)
 
-struct ib_cm_compare_data {
-	u8  data[IB_CM_COMPARE_SIZE];
-	u8  mask[IB_CM_COMPARE_SIZE];
-};
-
 /**
  * ib_cm_listen - Initiates listening on the specified service ID for
  *   connection and service ID resolution requests.
@@ -353,12 +354,13 @@ struct ib_cm_compare_data {
  *   range of service IDs.  If set to 0, the service ID is matched
  *   exactly.  This parameter is ignored if %service_id is set to
  *   IB_CM_ASSIGN_SERVICE_ID.
- * @compare_data: This parameter is optional.  It specifies data that must
- *   appear in the private data of a connection request for the specified
- *   listen request.
  */
-int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id, __be64 service_mask,
-		 struct ib_cm_compare_data *compare_data);
+int ib_cm_listen(struct ib_cm_id *cm_id, __be64 service_id,
+		 __be64 service_mask);
+
+struct ib_cm_id *ib_cm_insert_listen(struct ib_device *device,
+				     ib_cm_handler cm_handler,
+				     __be64 service_id);
 
 struct ib_cm_req_param {
 	struct ib_sa_path_rec	*primary_path;
@@ -601,6 +603,4 @@ struct ib_cm_sidr_rep_param {
 int ib_send_cm_sidr_rep(struct ib_cm_id *cm_id,
 			struct ib_cm_sidr_rep_param *param);
 
-int ib_update_cm_av(struct ib_cm_id *id, const u8 *smac, const u8 *alt_smac);
-
 #endif /* IB_CM_H */
diff --git a/sys/ofed/include/rdma/ib_hdrs.h b/sys/ofed/include/rdma/ib_hdrs.h
new file mode 100644
index 000000000000..408439fe911e
--- /dev/null
+++ b/sys/ofed/include/rdma/ib_hdrs.h
@@ -0,0 +1,178 @@
+/*
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * 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.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#ifndef IB_HDRS_H
+#define IB_HDRS_H
+
+#include <linux/types.h>
+#include <asm/unaligned.h>
+#include <rdma/ib_verbs.h>
+
+#define IB_SEQ_NAK	(3 << 29)
+
+/* AETH NAK opcode values */
+#define IB_RNR_NAK                      0x20
+#define IB_NAK_PSN_ERROR                0x60
+#define IB_NAK_INVALID_REQUEST          0x61
+#define IB_NAK_REMOTE_ACCESS_ERROR      0x62
+#define IB_NAK_REMOTE_OPERATIONAL_ERROR 0x63
+#define IB_NAK_INVALID_RD_REQUEST       0x64
+
+#define IB_BTH_REQ_ACK		BIT(31)
+#define IB_BTH_SOLICITED	BIT(23)
+#define IB_BTH_MIG_REQ		BIT(22)
+
+#define IB_GRH_VERSION		6
+#define IB_GRH_VERSION_MASK	0xF
+#define IB_GRH_VERSION_SHIFT	28
+#define IB_GRH_TCLASS_MASK	0xFF
+#define IB_GRH_TCLASS_SHIFT	20
+#define IB_GRH_FLOW_MASK	0xFFFFF
+#define IB_GRH_FLOW_SHIFT	0
+#define IB_GRH_NEXT_HDR		0x1B
+
+struct ib_reth {
+	__be64 vaddr;        /* potentially unaligned */
+	__be32 rkey;
+	__be32 length;
+} __packed;
+
+struct ib_atomic_eth {
+	__be64 vaddr;        /* potentially unaligned */
+	__be32 rkey;
+	__be64 swap_data;    /* potentially unaligned */
+	__be64 compare_data; /* potentially unaligned */
+} __packed;
+
+union ib_ehdrs {
+	struct {
+		__be32 deth[2];
+		__be32 imm_data;
+	} ud;
+	struct {
+		struct ib_reth reth;
+		__be32 imm_data;
+	} rc;
+	struct {
+		__be32 aeth;
+		__be64 atomic_ack_eth; /* potentially unaligned */
+	} __packed at;
+	__be32 imm_data;
+	__be32 aeth;
+	__be32 ieth;
+	struct ib_atomic_eth atomic_eth;
+}  __packed;
+
+struct ib_other_headers {
+	__be32 bth[3];
+	union ib_ehdrs u;
+} __packed;
+
+struct ib_header {
+	__be16 lrh[4];
+	union {
+		struct {
+			struct ib_grh grh;
+			struct ib_other_headers oth;
+		} l;
+		struct ib_other_headers oth;
+	} u;
+} __packed;
+
+/* accessors for unaligned __be64 items */
+
+static inline u64 ib_u64_get(__be64 *p)
+{
+	return get_unaligned_be64(p);
+}
+
+static inline void ib_u64_put(u64 val, __be64 *p)
+{
+	put_unaligned_be64(val, p);
+}
+
+static inline u64 get_ib_reth_vaddr(struct ib_reth *reth)
+{
+	return ib_u64_get(&reth->vaddr);
+}
+
+static inline void put_ib_reth_vaddr(u64 val, struct ib_reth *reth)
+{
+	ib_u64_put(val, &reth->vaddr);
+}
+
+static inline u64 get_ib_ateth_vaddr(struct ib_atomic_eth *ateth)
+{
+	return ib_u64_get(&ateth->vaddr);
+}
+
+static inline void put_ib_ateth_vaddr(u64 val, struct ib_atomic_eth *ateth)
+{
+	ib_u64_put(val, &ateth->vaddr);
+}
+
+static inline u64 get_ib_ateth_swap(struct ib_atomic_eth *ateth)
+{
+	return ib_u64_get(&ateth->swap_data);
+}
+
+static inline void put_ib_ateth_swap(u64 val, struct ib_atomic_eth *ateth)
+{
+	ib_u64_put(val, &ateth->swap_data);
+}
+
+static inline u64 get_ib_ateth_compare(struct ib_atomic_eth *ateth)
+{
+	return ib_u64_get(&ateth->compare_data);
+}
+
+static inline void put_ib_ateth_compare(u64 val, struct ib_atomic_eth *ateth)
+{
+	ib_u64_put(val, &ateth->compare_data);
+}
+
+#endif                          /* IB_HDRS_H */
diff --git a/sys/ofed/include/rdma/ib_mad.h b/sys/ofed/include/rdma/ib_mad.h
index 3d81b90cc315..9b02d1136404 100644
--- a/sys/ofed/include/rdma/ib_mad.h
+++ b/sys/ofed/include/rdma/ib_mad.h
@@ -40,9 +40,13 @@
 #include <linux/list.h>
 
 #include <rdma/ib_verbs.h>
+#include <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
@@ -123,6 +127,23 @@
 #define IB_DEFAULT_PKEY_PARTIAL 0x7FFF
 #define IB_DEFAULT_PKEY_FULL	0xFFFF
 
+/*
+ * Generic trap/notice types
+ */
+#define IB_NOTICE_TYPE_FATAL	0x80
+#define IB_NOTICE_TYPE_URGENT	0x81
+#define IB_NOTICE_TYPE_SECURITY	0x82
+#define IB_NOTICE_TYPE_SM	0x83
+#define IB_NOTICE_TYPE_INFO	0x84
+
+/*
+ * Generic trap/notice producers
+ */
+#define IB_NOTICE_PROD_CA		cpu_to_be16(1)
+#define IB_NOTICE_PROD_SWITCH		cpu_to_be16(2)
+#define IB_NOTICE_PROD_ROUTER		cpu_to_be16(3)
+#define IB_NOTICE_PROD_CLASS_MGR	cpu_to_be16(4)
+
 enum {
 	IB_MGMT_MAD_HDR = 24,
 	IB_MGMT_MAD_DATA = 232,
@@ -134,6 +155,10 @@ 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 {
@@ -180,12 +205,23 @@ 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;
@@ -201,12 +237,17 @@ struct ib_vendor_mad {
 	u8			data[IB_MGMT_VENDOR_DATA];
 };
 
+#define IB_MGMT_CLASSPORTINFO_ATTR_ID	cpu_to_be16(0x0001)
+
+#define IB_CLASS_PORT_INFO_RESP_TIME_MASK	0x1F
+#define IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE 5
+
 struct ib_class_port_info {
 	u8			base_version;
 	u8			class_version;
 	__be16			capability_mask;
-	u8			reserved[3];
-	u8			resp_time_value;
+	  /* 27 bits for cap_mask2, 5 bits for resp_time */
+	__be32			cap_mask2_resp_time;
 	u8			redirect_gid[16];
 	__be32			redirect_tcslfl;
 	__be16			redirect_lid;
@@ -222,6 +263,123 @@ struct ib_class_port_info {
 };
 
 /**
+ * ib_get_cpi_resp_time - Returns the resp_time value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u8 ib_get_cpi_resp_time(struct ib_class_port_info *cpi)
+{
+	return (u8)(be32_to_cpu(cpi->cap_mask2_resp_time) &
+		    IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_set_cpi_resptime - Sets the response time in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @rtime: The response time to set.
+ */
+static inline void ib_set_cpi_resp_time(struct ib_class_port_info *cpi,
+					u8 rtime)
+{
+	cpi->cap_mask2_resp_time =
+		(cpi->cap_mask2_resp_time &
+		 cpu_to_be32(~IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+		cpu_to_be32(rtime & IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_get_cpi_capmask2 - Returns the capmask2 value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u32 ib_get_cpi_capmask2(struct ib_class_port_info *cpi)
+{
+	return (be32_to_cpu(cpi->cap_mask2_resp_time) >>
+		IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
+/**
+ * ib_set_cpi_capmask2 - Sets the capmask2 in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @capmask2: The capmask2 to set.
+ */
+static inline void ib_set_cpi_capmask2(struct ib_class_port_info *cpi,
+				       u32 capmask2)
+{
+	cpi->cap_mask2_resp_time =
+		(cpi->cap_mask2_resp_time &
+		 cpu_to_be32(IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+		cpu_to_be32(capmask2 <<
+			    IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
+struct ib_mad_notice_attr {
+	u8 generic_type;
+	u8 prod_type_msb;
+	__be16 prod_type_lsb;
+	__be16 trap_num;
+	__be16 issuer_lid;
+	__be16 toggle_count;
+
+	union {
+		struct {
+			u8	details[54];
+		} raw_data;
+
+		struct {
+			__be16	reserved;
+			__be16	lid;		/* where violation happened */
+			u8	port_num;	/* where violation happened */
+		} __packed ntc_129_131;
+
+		struct {
+			__be16	reserved;
+			__be16	lid;		/* LID where change occurred */
+			u8	reserved2;
+			u8	local_changes;	/* low bit - local changes */
+			__be32	new_cap_mask;	/* new capability mask */
+			u8	reserved3;
+			u8	change_flags;	/* low 3 bits only */
+		} __packed ntc_144;
+
+		struct {
+			__be16	reserved;
+			__be16	lid;		/* lid where sys guid changed */
+			__be16	reserved2;
+			__be64	new_sys_guid;
+		} __packed ntc_145;
+
+		struct {
+			__be16	reserved;
+			__be16	lid;
+			__be16	dr_slid;
+			u8	method;
+			u8	reserved2;
+			__be16	attr_id;
+			__be32	attr_mod;
+			__be64	mkey;
+			u8	reserved3;
+			u8	dr_trunc_hop;
+			u8	dr_rtn_path[30];
+		} __packed ntc_256;
+
+		struct {
+			__be16		reserved;
+			__be16		lid1;
+			__be16		lid2;
+			__be32		key;
+			__be32		sl_qp1;	/* SL: high 4 bits */
+			__be32		qp2;	/* high 8 bits reserved */
+			union ib_gid	gid1;
+			union ib_gid	gid2;
+		} __packed ntc_257_258;
+
+	} details;
+};
+
+/**
  * ib_mad_send_buf - MAD data buffer and work request for sends.
  * @next: A pointer used to chain together MADs for posting.
  * @mad: References an allocated MAD data buffer for MADs that do not have
@@ -234,7 +392,10 @@ 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
@@ -254,6 +415,7 @@ struct ib_mad_send_buf {
 	int			data_len;
 	int			seg_count;
 	int			seg_size;
+	int			seg_rmpp_size;
 	int			timeout_ms;
 	int			retries;
 };
@@ -262,7 +424,7 @@ 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.
@@ -277,7 +439,7 @@ static inline u8 ib_get_rmpp_resptime(struct ib_rmpp_hdr *rmpp_hdr)
  * ib_get_rmpp_flags - Returns the RMPP flags.
  * @rmpp_hdr: An RMPP header.
  */
-static inline u8 ib_get_rmpp_flags(struct ib_rmpp_hdr *rmpp_hdr)
+static inline u8 ib_get_rmpp_flags(const struct ib_rmpp_hdr *rmpp_hdr)
 {
 	return rmpp_hdr->rmpp_rtime_flags & 0x7;
 }
@@ -318,11 +480,11 @@ typedef void (*ib_mad_send_handler)(struct ib_mad_agent *mad_agent,
 /**
  * ib_mad_snoop_handler - Callback handler for snooping sent MADs.
  * @mad_agent: MAD agent that snooped the MAD.
- * @send_wr: Work request information on the sent MAD.
+ * @send_buf: send MAD data buffer.
  * @mad_send_wc: Work completion information on the sent MAD.  Valid
  *   only for snooping that occurs on a send completion.
  *
- * Clients snooping MADs should not modify data referenced by the @send_wr
+ * Clients snooping MADs should not modify data referenced by the @send_buf
  * or @mad_send_wc.
  */
 typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent,
@@ -332,6 +494,7 @@ typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent,
 /**
  * ib_mad_recv_handler - callback handler for a received MAD.
  * @mad_agent: MAD agent requesting the received MAD.
+ * @send_buf: Send buffer if found, else NULL
  * @mad_recv_wc: Received work completion information on the received MAD.
  *
  * MADs received in response to a send request operation will be handed to
@@ -341,6 +504,7 @@ typedef void (*ib_mad_snoop_handler)(struct ib_mad_agent *mad_agent,
  * modify the data referenced by @mad_recv_wc.
  */
 typedef void (*ib_mad_recv_handler)(struct ib_mad_agent *mad_agent,
+				    struct ib_mad_send_buf *send_buf,
 				    struct ib_mad_recv_wc *mad_recv_wc);
 
 /**
@@ -355,18 +519,22 @@ typedef void (*ib_mad_recv_handler)(struct ib_mad_agent *mad_agent,
  * @hi_tid: Access layer assigned transaction ID for this client.
  *   Unsolicited MADs sent by this client will have the upper 32-bits
  *   of their TID set to this value.
+ * @flags: registration flags
  * @port_num: Port number on which QP is registered
  * @rmpp_version: If set, indicates the RMPP version used by this agent.
  */
+enum {
+	IB_MAD_USER_RMPP = IB_USER_MAD_USER_RMPP,
+};
 struct ib_mad_agent {
 	struct ib_device	*device;
 	struct ib_qp		*qp;
-	struct ib_mr		*mr;
 	ib_mad_recv_handler	recv_handler;
 	ib_mad_send_handler	send_handler;
 	ib_mad_snoop_handler	snoop_handler;
 	void			*context;
 	u32			hi_tid;
+	u32			flags;
 	u8			port_num;
 	u8			rmpp_version;
 };
@@ -395,7 +563,10 @@ 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;
+	};
 };
 
 /**
@@ -404,6 +575,7 @@ 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.
@@ -413,6 +585,7 @@ 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;
 };
 
 /**
@@ -426,6 +599,7 @@ struct ib_mad_recv_wc {
  *   in the range from 0x30 to 0x4f. Otherwise not used.
  * @method_mask: The caller will receive unsolicited MADs for any method
  *   where @method_mask = 1.
+ *
  */
 struct ib_mad_reg_req {
 	u8	mgmt_class;
@@ -451,6 +625,7 @@ struct ib_mad_reg_req {
  * @recv_handler: The completion callback routine invoked for a received
  *   MAD.
  * @context: User specified context associated with the registration.
+ * @registration_flags: Registration flags to set for this agent
  */
 struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
 					   u8 port_num,
@@ -459,7 +634,8 @@ struct ib_mad_agent *ib_register_mad_agent(struct ib_device *device,
 					   u8 rmpp_version,
 					   ib_mad_send_handler send_handler,
 					   ib_mad_recv_handler recv_handler,
-					   void *context);
+					   void *context,
+					   u32 registration_flags);
 
 enum ib_mad_snoop_flags {
 	/*IB_MAD_SNOOP_POSTED_SENDS	   = 1,*/
@@ -609,6 +785,7 @@ 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
@@ -624,7 +801,8 @@ 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
@@ -661,4 +839,11 @@ void *ib_get_rmpp_segment(struct ib_mad_send_buf *send_buf, int seg_num);
  */
 void ib_free_send_mad(struct ib_mad_send_buf *send_buf);
 
+/**
+ * ib_mad_kernel_rmpp_agent - Returns if the agent is performing RMPP.
+ * @agent: the agent in question
+ * @return: true if agent is performing rmpp, false otherwise.
+ */
+int ib_mad_kernel_rmpp_agent(const struct ib_mad_agent *agent);
+
 #endif /* IB_MAD_H */
diff --git a/sys/ofed/include/rdma/ib_pack.h b/sys/ofed/include/rdma/ib_pack.h
index 1678be7f047d..950aeebedc8a 100644
--- a/sys/ofed/include/rdma/ib_pack.h
+++ b/sys/ofed/include/rdma/ib_pack.h
@@ -40,6 +40,8 @@ enum {
 	IB_ETH_BYTES  = 14,
 	IB_VLAN_BYTES = 4,
 	IB_GRH_BYTES  = 40,
+	IB_IP4_BYTES  = 20,
+	IB_UDP_BYTES  = 8,
 	IB_BTH_BYTES  = 12,
 	IB_DETH_BYTES = 8
 };
@@ -75,6 +77,8 @@ enum {
 	IB_OPCODE_UC                                = 0x20,
 	IB_OPCODE_RD                                = 0x40,
 	IB_OPCODE_UD                                = 0x60,
+	/* per IBTA 1.3 vol 1 Table 38, A10.3.2 */
+	IB_OPCODE_CNP                               = 0x80,
 
 	/* operations -- just used to define real constants */
 	IB_OPCODE_SEND_FIRST                        = 0x00,
@@ -98,6 +102,9 @@ enum {
 	IB_OPCODE_ATOMIC_ACKNOWLEDGE                = 0x12,
 	IB_OPCODE_COMPARE_SWAP                      = 0x13,
 	IB_OPCODE_FETCH_ADD                         = 0x14,
+	/* opcode 0x15 is reserved */
+	IB_OPCODE_SEND_LAST_WITH_INVALIDATE         = 0x16,
+	IB_OPCODE_SEND_ONLY_WITH_INVALIDATE         = 0x17,
 
 	/* real constants follow -- see comment about above IB_OPCODE()
 	   macro for more details */
@@ -124,6 +131,8 @@ enum {
 	IB_OPCODE(RC, ATOMIC_ACKNOWLEDGE),
 	IB_OPCODE(RC, COMPARE_SWAP),
 	IB_OPCODE(RC, FETCH_ADD),
+	IB_OPCODE(RC, SEND_LAST_WITH_INVALIDATE),
+	IB_OPCODE(RC, SEND_ONLY_WITH_INVALIDATE),
 
 	/* UC */
 	IB_OPCODE(UC, SEND_FIRST),
@@ -220,6 +229,27 @@ struct ib_unpacked_eth {
 	__be16	type;
 };
 
+struct ib_unpacked_ip4 {
+	u8	ver;
+	u8	hdr_len;
+	u8	tos;
+	__be16	tot_len;
+	__be16	id;
+	__be16	frag_off;
+	u8	ttl;
+	u8	protocol;
+	__sum16	check;
+	__be32	saddr;
+	__be32	daddr;
+};
+
+struct ib_unpacked_udp {
+	__be16	sport;
+	__be16	dport;
+	__be16	length;
+	__be16	csum;
+};
+
 struct ib_unpacked_vlan {
 	__be16  tag;
 	__be16  type;
@@ -228,16 +258,20 @@ struct ib_unpacked_vlan {
 struct ib_ud_header {
 	int                     lrh_present;
 	struct ib_unpacked_lrh  lrh;
-	int                     eth_present;
-	struct ib_unpacked_eth  eth;
+	int			eth_present;
+	struct ib_unpacked_eth	eth;
 	int                     vlan_present;
 	struct ib_unpacked_vlan vlan;
-	int                     grh_present;
-	struct ib_unpacked_grh  grh;
-	struct ib_unpacked_bth  bth;
+	int			grh_present;
+	struct ib_unpacked_grh	grh;
+	int			ipv4_present;
+	struct ib_unpacked_ip4	ip4;
+	int			udp_present;
+	struct ib_unpacked_udp	udp;
+	struct ib_unpacked_bth	bth;
 	struct ib_unpacked_deth deth;
-	int            		immediate_present;
-	__be32         		immediate_data;
+	int			immediate_present;
+	__be32			immediate_data;
 };
 
 void ib_pack(const struct ib_field        *desc,
@@ -250,13 +284,17 @@ void ib_unpack(const struct ib_field        *desc,
 	       void                         *buf,
 	       void                         *structure);
 
-void ib_ud_header_init(int     		    payload_bytes,
-		       int		    lrh_present,
-		       int		    eth_present,
-		       int		    vlan_present,
-		       int    		    grh_present,
-		       int		    immediate_present,
-		       struct ib_ud_header *header);
+__sum16 ib_ud_ip4_csum(struct ib_ud_header *header);
+
+int ib_ud_header_init(int		    payload_bytes,
+		      int		    lrh_present,
+		      int		    eth_present,
+		      int		    vlan_present,
+		      int		    grh_present,
+		      int		    ip_version,
+		      int		    udp_present,
+		      int		    immediate_present,
+		      struct ib_ud_header *header);
 
 int ib_ud_header_pack(struct ib_ud_header *header,
 		      void                *buf);
diff --git a/sys/ofed/include/rdma/ib_peer_mem.h b/sys/ofed/include/rdma/ib_peer_mem.h
deleted file mode 100644
index b2a8a4a3f246..000000000000
--- a/sys/ofed/include/rdma/ib_peer_mem.h
+++ /dev/null
@@ -1,59 +0,0 @@
-#if !defined(IB_PEER_MEM_H)
-#define IB_PEER_MEM_H
-
-#include <rdma/peer_mem.h>
-
-
-struct invalidation_ctx;
-struct ib_ucontext;
-
-struct ib_peer_memory_statistics {
-	unsigned long num_alloc_mrs;
-	unsigned long num_dealloc_mrs;
-	unsigned long num_reg_pages;
-	unsigned long num_dereg_pages;
-	unsigned long num_free_callbacks;
-};
-
-struct ib_peer_memory_client {
-	const struct peer_memory_client *peer_mem;
-
-	struct list_head	core_peer_list;
-	struct list_head    core_ticket_list;
-	unsigned long last_ticket;
-#ifdef __FreeBSD__
-	int holdcount;
-	int needwakeup;
-	struct cv peer_cv;
-#else
-	struct srcu_struct peer_srcu;
-#endif
-	struct mutex lock;
-	struct kobject *kobj;
-	struct attribute_group peer_mem_attr_group;
-	struct ib_peer_memory_statistics stats;
-};
-
-struct core_ticket {
-	unsigned long key;
-	void *context;
-	struct list_head   ticket_list;
-};
-
-struct ib_peer_memory_client *ib_get_peer_client(struct ib_ucontext *context, unsigned long addr,
-						  size_t size, void **peer_client_context,
-						  int *srcu_key);
-
-void ib_put_peer_client(struct ib_peer_memory_client *ib_peer_client,
-				void *peer_client_context,
-				int srcu_key);
-
-unsigned long ib_peer_insert_context(struct ib_peer_memory_client *ib_peer_client,
-				void *context);
-int ib_peer_remove_context(struct ib_peer_memory_client *ib_peer_client,
-				unsigned long key);
-struct core_ticket *ib_peer_search_context(struct ib_peer_memory_client *ib_peer_client,
-						unsigned long key);
-#endif
-
-
diff --git a/sys/ofed/include/rdma/ib_pma.h b/sys/ofed/include/rdma/ib_pma.h
index a2300cd276cd..2f8a65c1fca7 100644
--- a/sys/ofed/include/rdma/ib_pma.h
+++ b/sys/ofed/include/rdma/ib_pma.h
@@ -37,30 +37,12 @@
 
 #include <rdma/ib_mad.h>
 
-#define MAX_U32 0xffffffffULL
-#define MAX_U16 0xffffUL
-
-/* Counters should be saturate once they reach their maximum value */
-#define ASSIGN_32BIT_COUNTER(counter, value) do {	\
-	if ((value) > MAX_U32)				\
-		counter = cpu_to_be32(MAX_U32);		\
-	else						\
-		counter = cpu_to_be32(value);		\
-} while (0)
-
-/* Counters should be saturate once they reach their maximum value */
-#define ASSIGN_16BIT_COUNTER(counter, value) do {	\
-	if ((value) > MAX_U16)				\
-		counter = cpu_to_be16(MAX_U16);		\
-	else						\
-		counter = cpu_to_be16(value);		\
-} while (0)
-
 /*
  * PMA class portinfo capability mask bits
  */
 #define IB_PMA_CLASS_CAP_ALLPORTSELECT  cpu_to_be16(1 << 8)
 #define IB_PMA_CLASS_CAP_EXT_WIDTH      cpu_to_be16(1 << 9)
+#define IB_PMA_CLASS_CAP_EXT_WIDTH_NOIETF cpu_to_be16(1 << 10)
 #define IB_PMA_CLASS_CAP_XMIT_WAIT      cpu_to_be16(1 << 12)
 
 #define IB_PMA_CLASS_PORT_INFO          cpu_to_be16(0x0001)
diff --git a/sys/ofed/include/rdma/ib_sa.h b/sys/ofed/include/rdma/ib_sa.h
index 65f1a006ee52..4c3e2924e21d 100644
--- a/sys/ofed/include/rdma/ib_sa.h
+++ b/sys/ofed/include/rdma/ib_sa.h
@@ -37,8 +37,7 @@
 
 #include <linux/completion.h>
 #include <linux/compiler.h>
-
-#include <asm/atomic.h>
+#include <linux/netdevice.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_mad.h>
@@ -94,6 +93,21 @@ enum ib_sa_selector {
 };
 
 /*
+ * There are 4 types of join states:
+ * FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember.
+ * The order corresponds to JoinState bits in MCMemberRecord.
+ */
+enum ib_sa_mc_join_states {
+	FULLMEMBER_JOIN,
+	NONMEMBER_JOIN,
+	SENDONLY_NONMEBER_JOIN,
+	SENDONLY_FULLMEMBER_JOIN,
+	NUM_JOIN_MEMBERSHIP_TYPES,
+};
+
+#define IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT	BIT(12)
+
+/*
  * Structures for SA records are named "struct ib_sa_xxx_rec."  No
  * attempt is made to pack structures to match the physical layout of
  * SA records in SA MADs; all packing and unpacking is handled by the
@@ -154,11 +168,19 @@ struct ib_sa_path_rec {
 	u8           packet_life_time_selector;
 	u8           packet_life_time;
 	u8           preference;
-	u8           smac[ETH_ALEN];
-	u8           dmac[6];
-	__be16       vlan_id;
+	u8           dmac[ETH_ALEN];
+	/* ignored in IB */
+	int	     ifindex;
+	/* ignored in IB */
+	struct vnet  *net;
+	enum ib_gid_type gid_type;
 };
 
+static inline struct net_device *ib_get_ndev_from_path(struct ib_sa_path_rec *rec)
+{
+	return rec->net ? dev_get_by_index(rec->net, rec->ifindex) : NULL;
+}
+
 #define IB_SA_MCMEMBER_REC_MGID				IB_SA_COMP_MASK( 0)
 #define IB_SA_MCMEMBER_REC_PORT_GID			IB_SA_COMP_MASK( 1)
 #define IB_SA_MCMEMBER_REC_QKEY				IB_SA_COMP_MASK( 2)
@@ -394,6 +416,8 @@ int ib_sa_get_mcmember_rec(struct ib_device *device, u8 port_num,
  */
 int ib_init_ah_from_mcmember(struct ib_device *device, u8 port_num,
 			     struct ib_sa_mcmember_rec *rec,
+			     struct net_device *ndev,
+			     enum ib_gid_type gid_type,
 			     struct ib_ah_attr *ah_attr);
 
 /**
@@ -405,6 +429,12 @@ int ib_init_ah_from_path(struct ib_device *device, u8 port_num,
 			 struct ib_ah_attr *ah_attr);
 
 /**
+ * ib_sa_pack_path - Conert a path record from struct ib_sa_path_rec
+ * to IB MAD wire format.
+ */
+void ib_sa_pack_path(struct ib_sa_path_rec *rec, void *attribute);
+
+/**
  * ib_sa_unpack_path - Convert a path record from MAD format to struct
  * ib_sa_path_rec.
  */
@@ -412,13 +442,24 @@ void ib_sa_unpack_path(void *attribute, struct ib_sa_path_rec *rec);
 
 /* Support GuidInfoRecord */
 int ib_sa_guid_info_rec_query(struct ib_sa_client *client,
-                              struct ib_device *device, u8 port_num,
-                              struct ib_sa_guidinfo_rec *rec,
-                              ib_sa_comp_mask comp_mask, u8 method,
-                              int timeout_ms, gfp_t gfp_mask,
-                              void (*callback)(int status,
-                                               struct ib_sa_guidinfo_rec *resp,
-                                               void *context),
-                              void *context,
-                              struct ib_sa_query **sa_query);
+			      struct ib_device *device, u8 port_num,
+			      struct ib_sa_guidinfo_rec *rec,
+			      ib_sa_comp_mask comp_mask, u8 method,
+			      int timeout_ms, gfp_t gfp_mask,
+			      void (*callback)(int status,
+					       struct ib_sa_guidinfo_rec *resp,
+					       void *context),
+			      void *context,
+			      struct ib_sa_query **sa_query);
+
+/* Support get SA ClassPortInfo */
+int ib_sa_classport_info_rec_query(struct ib_sa_client *client,
+				   struct ib_device *device, u8 port_num,
+				   int timeout_ms, gfp_t gfp_mask,
+				   void (*callback)(int status,
+						    struct ib_class_port_info *resp,
+						    void *context),
+				   void *context,
+				   struct ib_sa_query **sa_query);
+
 #endif /* IB_SA_H */
diff --git a/sys/ofed/include/rdma/ib_smi.h b/sys/ofed/include/rdma/ib_smi.h
index 973c9a4efec8..15ac3d71c5ee 100644
--- a/sys/ofed/include/rdma/ib_smi.h
+++ b/sys/ofed/include/rdma/ib_smi.h
@@ -38,7 +38,6 @@
 #define IB_SMI_H
 
 #include <rdma/ib_mad.h>
-#include <asm/byteorder.h>
 
 #define IB_SMP_DATA_SIZE			64
 #define IB_SMP_MAX_PATH_HOPS			64
@@ -120,10 +119,57 @@ struct ib_port_info {
 	u8 link_roundtrip_latency[3];
 };
 
+struct ib_node_info {
+	u8 base_version;
+	u8 class_version;
+	u8 node_type;
+	u8 num_ports;
+	__be64 sys_guid;
+	__be64 node_guid;
+	__be64 port_guid;
+	__be16 partition_cap;
+	__be16 device_id;
+	__be32 revision;
+	u8 local_port_num;
+	u8 vendor_id[3];
+} __packed;
+
+struct ib_vl_weight_elem {
+	u8      vl;     /* IB: VL is low 4 bits, upper 4 bits reserved */
+                        /* OPA: VL is low 5 bits, upper 3 bits reserved */
+	u8      weight;
+};
+
 static inline u8
-ib_get_smp_direction(struct ib_smp *smp)
+ib_get_smp_direction(const struct ib_smp *smp)
 {
 	return ((smp->status & IB_SMP_DIRECTION) == IB_SMP_DIRECTION);
 }
 
+/*
+ * SM Trap/Notice numbers
+ */
+#define IB_NOTICE_TRAP_LLI_THRESH	cpu_to_be16(129)
+#define IB_NOTICE_TRAP_EBO_THRESH	cpu_to_be16(130)
+#define IB_NOTICE_TRAP_FLOW_UPDATE	cpu_to_be16(131)
+#define IB_NOTICE_TRAP_CAP_MASK_CHG	cpu_to_be16(144)
+#define IB_NOTICE_TRAP_SYS_GUID_CHG	cpu_to_be16(145)
+#define IB_NOTICE_TRAP_BAD_MKEY		cpu_to_be16(256)
+#define IB_NOTICE_TRAP_BAD_PKEY		cpu_to_be16(257)
+#define IB_NOTICE_TRAP_BAD_QKEY		cpu_to_be16(258)
+
+/*
+ * Other local changes flags (trap 144).
+ */
+#define IB_NOTICE_TRAP_LSE_CHG		0x04	/* Link Speed Enable changed */
+#define IB_NOTICE_TRAP_LWE_CHG		0x02	/* Link Width Enable changed */
+#define IB_NOTICE_TRAP_NODE_DESC_CHG	0x01
+
+/*
+ * M_Key volation flags in dr_trunc_hop (trap 256).
+ */
+#define IB_NOTICE_TRAP_DR_NOTICE	0x80
+#define IB_NOTICE_TRAP_DR_TRUNC		0x40
+
+
 #endif /* IB_SMI_H */
diff --git a/sys/ofed/include/rdma/ib_umem.h b/sys/ofed/include/rdma/ib_umem.h
index 82f6cfaa5b7a..6386d45c9cf2 100644
--- a/sys/ofed/include/rdma/ib_umem.h
+++ b/sys/ofed/include/rdma/ib_umem.h
@@ -36,58 +36,73 @@
 #include <linux/list.h>
 #include <linux/scatterlist.h>
 #include <linux/workqueue.h>
-#include <linux/dma-attrs.h>
-#include <linux/completion.h>
-#include <rdma/ib_peer_mem.h>
 
 struct ib_ucontext;
-struct ib_umem;
-
-typedef void (*umem_invalidate_func_t)(void *invalidation_cookie,
-					    struct ib_umem *umem,
-					    unsigned long addr, size_t size);
-
-struct invalidation_ctx {
-	struct ib_umem *umem;
-	umem_invalidate_func_t func;
-	void *cookie;
-	unsigned long context_ticket;
-	int peer_callback;
-	int inflight_invalidation;
-	int peer_invalidated;
-	struct completion comp;
-};
+struct ib_umem_odp;
 
 struct ib_umem {
 	struct ib_ucontext     *context;
 	size_t			length;
-	int			offset;
+	unsigned long		address;
 	int			page_size;
 	int                     writable;
-	int                     hugetlb;
 	struct work_struct	work;
+	pid_t			pid;
+	struct mm_struct       *mm;
 	unsigned long		diff;
-	unsigned long           start;
+	struct ib_umem_odp     *odp_data;
 	struct sg_table sg_head;
-	int                     nmap;
+	int             nmap;
 	int             npages;
-	/* peer memory that manages this umem*/
-	struct ib_peer_memory_client *ib_peer_mem;
-	struct invalidation_ctx *invalidation_ctx;
-	int peer_mem_srcu_key;
-	/* peer memory private context */
-	void *peer_mem_client_context;
 };
 
+/* Returns the offset of the umem start relative to the first page. */
+static inline int ib_umem_offset(struct ib_umem *umem)
+{
+	return umem->address & ((unsigned long)umem->page_size - 1);
+}
+
+/* Returns the first page of an ODP umem. */
+static inline unsigned long ib_umem_start(struct ib_umem *umem)
+{
+	return umem->address - ib_umem_offset(umem);
+}
+
+/* Returns the address of the page after the last one of an ODP umem. */
+static inline unsigned long ib_umem_end(struct ib_umem *umem)
+{
+	return PAGE_ALIGN(umem->address + umem->length);
+}
+
+static inline size_t ib_umem_num_pages(struct ib_umem *umem)
+{
+	return (ib_umem_end(umem) - ib_umem_start(umem)) >> PAGE_SHIFT;
+}
+
+#ifdef CONFIG_INFINIBAND_USER_MEM
+
 struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 			    size_t size, int access, int dmasync);
-struct ib_umem *ib_umem_get_ex(struct ib_ucontext *context, unsigned long addr,
-			    size_t size, int access, int dmasync,
-			    int invalidation_supported);
-void  ib_umem_activate_invalidation_notifier(struct ib_umem *umem,
-					       umem_invalidate_func_t func,
-					       void *cookie);
 void ib_umem_release(struct ib_umem *umem);
 int ib_umem_page_count(struct ib_umem *umem);
+int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
+		      size_t length);
+
+#else /* CONFIG_INFINIBAND_USER_MEM */
+
+#include <linux/err.h>
+
+static inline struct ib_umem *ib_umem_get(struct ib_ucontext *context,
+					  unsigned long addr, size_t size,
+					  int access, int dmasync) {
+	return ERR_PTR(-EINVAL);
+}
+static inline void ib_umem_release(struct ib_umem *umem) { }
+static inline int ib_umem_page_count(struct ib_umem *umem) { return 0; }
+static inline int ib_umem_copy_from(void *dst, struct ib_umem *umem, size_t offset,
+		      		    size_t length) {
+	return -EINVAL;
+}
+#endif /* CONFIG_INFINIBAND_USER_MEM */
 
 #endif /* IB_UMEM_H */
diff --git a/sys/ofed/include/rdma/ib_umem_odp.h b/sys/ofed/include/rdma/ib_umem_odp.h
new file mode 100644
index 000000000000..d2f0e6b1a8a5
--- /dev/null
+++ b/sys/ofed/include/rdma/ib_umem_odp.h
@@ -0,0 +1,161 @@
+/*
+ * Copyright (c) 2014 Mellanox Technologies. 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 IB_UMEM_ODP_H
+#define IB_UMEM_ODP_H
+
+#include <linux/rbtree.h>
+
+#include <rdma/ib_umem.h>
+#include <rdma/ib_verbs.h>
+
+struct umem_odp_node {
+	u64 __subtree_last;
+	struct rb_node rb;
+};
+
+struct ib_umem_odp {
+	/*
+	 * An array of the pages included in the on-demand paging umem.
+	 * Indices of pages that are currently not mapped into the device will
+	 * contain NULL.
+	 */
+	struct page		**page_list;
+	/*
+	 * An array of the same size as page_list, with DMA addresses mapped
+	 * for pages the pages in page_list. The lower two bits designate
+	 * access permissions. See ODP_READ_ALLOWED_BIT and
+	 * ODP_WRITE_ALLOWED_BIT.
+	 */
+	dma_addr_t		*dma_list;
+	/*
+	 * The umem_mutex protects the page_list and dma_list fields of an ODP
+	 * umem, allowing only a single thread to map/unmap pages. The mutex
+	 * also protects access to the mmu notifier counters.
+	 */
+	struct mutex		umem_mutex;
+	void			*private; /* for the HW driver to use. */
+
+	/* When false, use the notifier counter in the ucontext struct. */
+	bool mn_counters_active;
+	int notifiers_seq;
+	int notifiers_count;
+
+	/* A linked list of umems that don't have private mmu notifier
+	 * counters yet. */
+	struct list_head no_private_counters;
+	struct ib_umem		*umem;
+
+	/* Tree tracking */
+	struct umem_odp_node	interval_tree;
+
+	struct completion	notifier_completion;
+	int			dying;
+};
+
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+
+int ib_umem_odp_get(struct ib_ucontext *context, struct ib_umem *umem);
+
+void ib_umem_odp_release(struct ib_umem *umem);
+
+/*
+ * The lower 2 bits of the DMA address signal the R/W permissions for
+ * the entry. To upgrade the permissions, provide the appropriate
+ * bitmask to the map_dma_pages function.
+ *
+ * Be aware that upgrading a mapped address might result in change of
+ * the DMA address for the page.
+ */
+#define ODP_READ_ALLOWED_BIT  (1<<0ULL)
+#define ODP_WRITE_ALLOWED_BIT (1<<1ULL)
+
+#define ODP_DMA_ADDR_MASK (~(ODP_READ_ALLOWED_BIT | ODP_WRITE_ALLOWED_BIT))
+
+int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 start_offset, u64 bcnt,
+			      u64 access_mask, unsigned long current_seq);
+
+void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 start_offset,
+				 u64 bound);
+
+void rbt_ib_umem_insert(struct umem_odp_node *node, struct rb_root *root);
+void rbt_ib_umem_remove(struct umem_odp_node *node, struct rb_root *root);
+typedef int (*umem_call_back)(struct ib_umem *item, u64 start, u64 end,
+			      void *cookie);
+/*
+ * Call the callback on each ib_umem in the range. Returns the logical or of
+ * the return values of the functions called.
+ */
+int rbt_ib_umem_for_each_in_range(struct rb_root *root, u64 start, u64 end,
+				  umem_call_back cb, void *cookie);
+
+struct umem_odp_node *rbt_ib_umem_iter_first(struct rb_root *root,
+					     u64 start, u64 last);
+struct umem_odp_node *rbt_ib_umem_iter_next(struct umem_odp_node *node,
+					    u64 start, u64 last);
+
+static inline int ib_umem_mmu_notifier_retry(struct ib_umem *item,
+					     unsigned long mmu_seq)
+{
+	/*
+	 * This code is strongly based on the KVM code from
+	 * mmu_notifier_retry. Should be called with
+	 * the relevant locks taken (item->odp_data->umem_mutex
+	 * and the ucontext umem_mutex semaphore locked for read).
+	 */
+
+	/* Do not allow page faults while the new ib_umem hasn't seen a state
+	 * with zero notifiers yet, and doesn't have its own valid set of
+	 * private counters. */
+	if (!item->odp_data->mn_counters_active)
+		return 1;
+
+	if (unlikely(item->odp_data->notifiers_count))
+		return 1;
+	if (item->odp_data->notifiers_seq != mmu_seq)
+		return 1;
+	return 0;
+}
+
+#else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+
+static inline int ib_umem_odp_get(struct ib_ucontext *context,
+				  struct ib_umem *umem)
+{
+	return -EINVAL;
+}
+
+static inline void ib_umem_odp_release(struct ib_umem *umem) {}
+
+#endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
+
+#endif /* IB_UMEM_ODP_H */
diff --git a/sys/ofed/include/rdma/ib_user_mad.h b/sys/ofed/include/rdma/ib_user_mad.h
index 3595ae26c908..09f809f323ea 100644
--- a/sys/ofed/include/rdma/ib_user_mad.h
+++ b/sys/ofed/include/rdma/ib_user_mad.h
@@ -191,12 +191,55 @@ struct ib_user_mad_reg_req {
 	__u8	rmpp_version;
 };
 
+/**
+ * ib_user_mad_reg_req2 - MAD registration request
+ *
+ * @id                 - Set by the _kernel_; used by userspace to identify the
+ *                       registered agent in future requests.
+ * @qpn                - Queue pair number; must be 0 or 1.
+ * @mgmt_class         - Indicates which management class of MADs should be
+ *                       receive by the caller.  This field is only required if
+ *                       the user wishes to receive unsolicited MADs, otherwise
+ *                       it should be 0.
+ * @mgmt_class_version - Indicates which version of MADs for the given
+ *                       management class to receive.
+ * @res                - Ignored.
+ * @flags              - additional registration flags; Must be in the set of
+ *                       flags defined in IB_USER_MAD_REG_FLAGS_CAP
+ * @method_mask        - The caller wishes to receive unsolicited MADs for the
+ *                       methods whose bit(s) is(are) set.
+ * @oui                - Indicates IEEE OUI to use when mgmt_class is a vendor
+ *                       class in the range from 0x30 to 0x4f. Otherwise not
+ *                       used.
+ * @rmpp_version       - If set, indicates the RMPP version to use.
+ */
+enum {
+	IB_USER_MAD_USER_RMPP = (1 << 0),
+};
+#define IB_USER_MAD_REG_FLAGS_CAP (IB_USER_MAD_USER_RMPP)
+struct ib_user_mad_reg_req2 {
+	__u32	id;
+	__u32	qpn;
+	__u8	mgmt_class;
+	__u8	mgmt_class_version;
+	__u16   res;
+	__u32   flags;
+	__u64   method_mask[2];
+	__u32   oui;
+	__u8	rmpp_version;
+	__u8	reserved[3];
+};
+
 #define IB_IOCTL_MAGIC		0x1b
 
-#define IB_USER_MAD_REGISTER_AGENT	_IO(IB_IOCTL_MAGIC, 1)
+#define IB_USER_MAD_REGISTER_AGENT	_IOWR(IB_IOCTL_MAGIC, 1, \
+					      struct ib_user_mad_reg_req)
 
-#define IB_USER_MAD_UNREGISTER_AGENT	_IO(IB_IOCTL_MAGIC, 2)
+#define IB_USER_MAD_UNREGISTER_AGENT	_IOW(IB_IOCTL_MAGIC, 2, __u32)
 
 #define IB_USER_MAD_ENABLE_PKEY		_IO(IB_IOCTL_MAGIC, 3)
 
+#define IB_USER_MAD_REGISTER_AGENT2     _IOWR(IB_IOCTL_MAGIC, 4, \
+					      struct ib_user_mad_reg_req2)
+
 #endif /* IB_USER_MAD_H */
diff --git a/sys/ofed/include/rdma/ib_user_verbs.h b/sys/ofed/include/rdma/ib_user_verbs.h
index a07de88a5d0d..25225ebbc7d5 100644
--- a/sys/ofed/include/rdma/ib_user_verbs.h
+++ b/sys/ofed/include/rdma/ib_user_verbs.h
@@ -45,12 +45,6 @@
 #define IB_USER_VERBS_ABI_VERSION	6
 #define IB_USER_VERBS_CMD_THRESHOLD    50
 
-/*
- * To support 6 legacy commands using the old extension style
- */
-#define IB_USER_VERBS_LEGACY_CMD_FIRST   52
-#define IB_USER_VERBS_LEGACY_EX_CMD_LAST 56
-
 enum {
 	IB_USER_VERBS_CMD_GET_CONTEXT,
 	IB_USER_VERBS_CMD_QUERY_DEVICE,
@@ -92,15 +86,22 @@ enum {
 	IB_USER_VERBS_CMD_OPEN_XRCD,
 	IB_USER_VERBS_CMD_CLOSE_XRCD,
 	IB_USER_VERBS_CMD_CREATE_XSRQ,
-	IB_USER_VERBS_CMD_OPEN_QP
+	IB_USER_VERBS_CMD_OPEN_QP,
 };
 
 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_QP = IB_USER_VERBS_CMD_CREATE_QP,
 	IB_USER_VERBS_EX_CMD_CREATE_FLOW = IB_USER_VERBS_CMD_THRESHOLD,
-	IB_USER_VERBS_EX_CMD_DESTROY_FLOW
+	IB_USER_VERBS_EX_CMD_DESTROY_FLOW,
+	IB_USER_VERBS_EX_CMD_CREATE_WQ,
+	IB_USER_VERBS_EX_CMD_MODIFY_WQ,
+	IB_USER_VERBS_EX_CMD_DESTROY_WQ,
+	IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL,
+	IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL
 };
 
-
 /*
  * Make sure that all structs defined in this file remain laid out so
  * that they pack the same way on 32-bit and 64-bit architectures (to
@@ -130,14 +131,6 @@ struct ib_uverbs_comp_event_desc {
  * the rest of the command struct based on these value.
  */
 
-#define IBV_RESP_TO_VERBS_RESP_EX_RAW(ex_ptr, ex_type, ibv_type, field) \
-	((ibv_type *)((void *)(ex_ptr) + offsetof(ex_type,              \
-			field) + sizeof((ex_ptr)->field)))
-
-#define IBV_RESP_TO_VERBS_RESP_EX(ex_ptr, ex_type, ibv_type) \
-	IBV_RESP_TO_VERBS_RESP_EX_RAW(ex_ptr, ex_type, ibv_type, comp_mask)
-
-
 #define IB_USER_VERBS_CMD_COMMAND_MASK 0xff
 #define IB_USER_VERBS_CMD_FLAGS_MASK 0xff000000u
 #define IB_USER_VERBS_CMD_FLAGS_SHIFT 24
@@ -172,11 +165,6 @@ struct ib_uverbs_query_device {
 	__u64 driver_data[0];
 };
 
-struct ib_uverbs_query_device_ex {
-	__u64 comp_mask;
-	__u64 driver_data[0];
-};
-
 struct ib_uverbs_query_device_resp {
 	__u64 fw_ver;
 	__be64 node_guid;
@@ -221,6 +209,45 @@ struct ib_uverbs_query_device_resp {
 	__u8  reserved[4];
 };
 
+struct ib_uverbs_ex_query_device {
+	__u32 comp_mask;
+	__u32 reserved;
+};
+
+struct ib_uverbs_odp_caps {
+	__u64 general_caps;
+	struct {
+		__u32 rc_odp_caps;
+		__u32 uc_odp_caps;
+		__u32 ud_odp_caps;
+	} per_transport_caps;
+	__u32 reserved;
+};
+
+struct ib_uverbs_rss_caps {
+	/* Corresponding bit will be set if qp type from
+	 * 'enum ib_qp_type' is supported, e.g.
+	 * supported_qpts |= 1 << IB_QPT_UD
+	 */
+	__u32 supported_qpts;
+	__u32 max_rwq_indirection_tables;
+	__u32 max_rwq_indirection_table_size;
+	__u32 reserved;
+};
+
+struct ib_uverbs_ex_query_device_resp {
+	struct ib_uverbs_query_device_resp base;
+	__u32 comp_mask;
+	__u32 response_length;
+	struct ib_uverbs_odp_caps odp_caps;
+	__u64 timestamp_mask;
+	__u64 hca_core_clock; /* in KHZ */
+	__u64 device_cap_flags_ex;
+	struct ib_uverbs_rss_caps rss_caps;
+	__u32  max_wq_type_rq;
+	__u32 reserved;
+};
+
 struct ib_uverbs_query_port {
 	__u64 response;
 	__u8  port_num;
@@ -296,6 +323,22 @@ struct ib_uverbs_reg_mr_resp {
 	__u32 rkey;
 };
 
+struct ib_uverbs_rereg_mr {
+	__u64 response;
+	__u32 mr_handle;
+	__u32 flags;
+	__u64 start;
+	__u64 length;
+	__u64 hca_va;
+	__u32 pd_handle;
+	__u32 access_flags;
+};
+
+struct ib_uverbs_rereg_mr_resp {
+	__u32 lkey;
+	__u32 rkey;
+};
+
 struct ib_uverbs_dereg_mr {
 	__u32 mr_handle;
 };
@@ -334,33 +377,25 @@ struct ib_uverbs_create_cq {
 	__u64 driver_data[0];
 };
 
-struct ib_uverbs_create_cq_resp {
-	__u32 cq_handle;
-	__u32 cqe;
-};
-
-enum ib_uverbs_create_cq_ex_comp_mask {
-	IB_UVERBS_CREATE_CQ_EX_CAP_FLAGS	= (u64)1 << 0,
-};
-
-struct ib_uverbs_create_cq_ex {
-	__u64 comp_mask;
+struct ib_uverbs_ex_create_cq {
 	__u64 user_handle;
 	__u32 cqe;
 	__u32 comp_vector;
 	__s32 comp_channel;
+	__u32 comp_mask;
+	__u32 flags;
 	__u32 reserved;
-	__u64 create_flags;
-	__u64 driver_data[0];
 };
 
-struct ib_uverbs_modify_cq_ex {
-	__u64 comp_mask;
+struct ib_uverbs_create_cq_resp {
 	__u32 cq_handle;
-	__u32 attr_mask;
-	__u16 cq_count;
-	__u16 cq_period;
-	__u32 cq_cap_flags;
+	__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 {
@@ -502,6 +537,35 @@ struct ib_uverbs_create_qp {
 	__u64 driver_data[0];
 };
 
+enum ib_uverbs_create_qp_mask {
+	IB_UVERBS_CREATE_QP_MASK_IND_TABLE = 1UL << 0,
+};
+
+enum {
+	IB_UVERBS_CREATE_QP_SUP_COMP_MASK = IB_UVERBS_CREATE_QP_MASK_IND_TABLE,
+};
+
+struct ib_uverbs_ex_create_qp {
+	__u64 user_handle;
+	__u32 pd_handle;
+	__u32 send_cq_handle;
+	__u32 recv_cq_handle;
+	__u32 srq_handle;
+	__u32 max_send_wr;
+	__u32 max_recv_wr;
+	__u32 max_send_sge;
+	__u32 max_recv_sge;
+	__u32 max_inline_data;
+	__u8  sq_sig_all;
+	__u8  qp_type;
+	__u8  is_srq;
+	__u8 reserved;
+	__u32 comp_mask;
+	__u32 create_flags;
+	__u32 rwq_ind_tbl_handle;
+	__u32  reserved1;
+};
+
 struct ib_uverbs_open_qp {
 	__u64 response;
 	__u64 user_handle;
@@ -524,6 +588,12 @@ struct ib_uverbs_create_qp_resp {
 	__u32 reserved;
 };
 
+struct ib_uverbs_ex_create_qp_resp {
+	struct ib_uverbs_create_qp_resp base;
+	__u32 comp_mask;
+	__u32 response_length;
+};
+
 /*
  * This struct needs to remain a multiple of 8 bytes to keep the
  * alignment of the modify QP parameters.
@@ -614,42 +684,6 @@ struct ib_uverbs_modify_qp {
 	__u64 driver_data[0];
 };
 
-enum ib_uverbs_modify_qp_ex_comp_mask {
-	IB_UVERBS_QP_ATTR_DCT_KEY	= 1ULL << 0,
-};
-
-struct ib_uverbs_modify_qp_ex {
-	__u32 comp_mask;
-	struct ib_uverbs_qp_dest dest;
-	struct ib_uverbs_qp_dest alt_dest;
-	__u32 qp_handle;
-	__u32 attr_mask;
-	__u32 qkey;
-	__u32 rq_psn;
-	__u32 sq_psn;
-	__u32 dest_qp_num;
-	__u32 qp_access_flags;
-	__u16 pkey_index;
-	__u16 alt_pkey_index;
-	__u8  qp_state;
-	__u8  cur_qp_state;
-	__u8  path_mtu;
-	__u8  path_mig_state;
-	__u8  en_sqd_async_notify;
-	__u8  max_rd_atomic;
-	__u8  max_dest_rd_atomic;
-	__u8  min_rnr_timer;
-	__u8  port_num;
-	__u8  timeout;
-	__u8  retry_cnt;
-	__u8  rnr_retry;
-	__u8  alt_port_num;
-	__u8  alt_timeout;
-	__u8  reserved[2];
-	__u64 dct_key;
-	__u64 driver_data[0];
-};
-
 struct ib_uverbs_modify_qp_resp {
 };
 
@@ -784,18 +818,18 @@ struct ib_uverbs_detach_mcast {
 };
 
 struct ib_uverbs_flow_spec_hdr {
-	__u32  type;
+	__u32 type;
 	__u16 size;
 	__u16 reserved;
 	/* followed by flow_spec */
 	__u64 flow_spec_data[0];
 };
 
-struct ib_kern_eth_filter {
-	__u8	dst_mac[6];
-	__u8	src_mac[6];
-	__be16	ether_type;
-	__be16	vlan_tag;
+struct ib_uverbs_flow_eth_filter {
+	__u8  dst_mac[6];
+	__u8  src_mac[6];
+	__be16 ether_type;
+	__be16 vlan_tag;
 };
 
 struct ib_uverbs_flow_spec_eth {
@@ -807,16 +841,20 @@ struct ib_uverbs_flow_spec_eth {
 			__u16 reserved;
 		};
 	};
-	struct ib_kern_eth_filter val;
-	struct ib_kern_eth_filter mask;
+	struct ib_uverbs_flow_eth_filter val;
+	struct ib_uverbs_flow_eth_filter mask;
 };
 
-struct ib_kern_ib_filter {
-	__be32	l3_type_qpn;
-	__u8	dst_gid[16];
+struct ib_uverbs_flow_ipv4_filter {
+	__be32 src_ip;
+	__be32 dst_ip;
+	__u8	proto;
+	__u8	tos;
+	__u8	ttl;
+	__u8	flags;
 };
 
-struct ib_uverbs_flow_spec_ib {
+struct ib_uverbs_flow_spec_ipv4 {
 	union {
 		struct ib_uverbs_flow_spec_hdr hdr;
 		struct {
@@ -825,16 +863,16 @@ struct ib_uverbs_flow_spec_ib {
 			__u16 reserved;
 		};
 	};
-	struct ib_kern_ib_filter val;
-	struct ib_kern_ib_filter mask;
+	struct ib_uverbs_flow_ipv4_filter val;
+	struct ib_uverbs_flow_ipv4_filter mask;
 };
 
-struct ib_kern_ipv4_filter {
-	__be32 src_ip;
-	__be32 dst_ip;
+struct ib_uverbs_flow_tcp_udp_filter {
+	__be16 dst_port;
+	__be16 src_port;
 };
 
-struct ib_uverbs_flow_spec_ipv4 {
+struct ib_uverbs_flow_spec_tcp_udp {
 	union {
 		struct ib_uverbs_flow_spec_hdr hdr;
 		struct {
@@ -843,16 +881,21 @@ struct ib_uverbs_flow_spec_ipv4 {
 			__u16 reserved;
 		};
 	};
-	struct ib_kern_ipv4_filter val;
-	struct ib_kern_ipv4_filter mask;
+	struct ib_uverbs_flow_tcp_udp_filter val;
+	struct ib_uverbs_flow_tcp_udp_filter mask;
 };
 
-struct ib_kern_tcp_udp_filter {
-	__be16 dst_port;
-	__be16	src_port;
+struct ib_uverbs_flow_ipv6_filter {
+	__u8    src_ip[16];
+	__u8    dst_ip[16];
+	__be32	flow_label;
+	__u8	next_hdr;
+	__u8	traffic_class;
+	__u8	hop_limit;
+	__u8	reserved;
 };
 
-struct ib_uverbs_flow_spec_tcp_udp {
+struct ib_uverbs_flow_spec_ipv6 {
 	union {
 		struct ib_uverbs_flow_spec_hdr hdr;
 		struct {
@@ -861,18 +904,18 @@ struct ib_uverbs_flow_spec_tcp_udp {
 			__u16 reserved;
 		};
 	};
-	struct ib_kern_tcp_udp_filter val;
-	struct ib_kern_tcp_udp_filter mask;
+	struct ib_uverbs_flow_ipv6_filter val;
+	struct ib_uverbs_flow_ipv6_filter mask;
 };
 
 struct ib_uverbs_flow_attr {
-	__u32	     type;
-	__u16	     size;
-	__u16	     priority;
-	__u8	     num_of_specs;
-	__u8   reserved[2];
-	__u8	     port;
-	__u32	     flags;
+	__u32 type;
+	__u16 size;
+	__u16 priority;
+	__u8  num_of_specs;
+	__u8  reserved[2];
+	__u8  port;
+	__u32 flags;
 	/* Following are the optional layers according to user request
 	 * struct ib_flow_spec_xxx
 	 * struct ib_flow_spec_yyy
@@ -959,22 +1002,66 @@ struct ib_uverbs_destroy_srq_resp {
 	__u32 events_reported;
 };
 
+struct ib_uverbs_ex_create_wq  {
+	__u32 comp_mask;
+	__u32 wq_type;
+	__u64 user_handle;
+	__u32 pd_handle;
+	__u32 cq_handle;
+	__u32 max_wr;
+	__u32 max_sge;
+};
 
-/*
- * Legacy extended verbs related structures
- */
-struct ib_uverbs_ex_cmd_hdr_legacy {
-	__u32 command;
-	__u16 in_words;
-	__u16 out_words;
-	__u16 provider_in_words;
-	__u16 provider_out_words;
-	__u32 cmd_hdr_reserved;
+struct ib_uverbs_ex_create_wq_resp {
+	__u32 comp_mask;
+	__u32 response_length;
+	__u32 wq_handle;
+	__u32 max_wr;
+	__u32 max_sge;
+	__u32 wqn;
 };
 
-struct ib_uverbs_ex_cmd_resp1_legacy {
-	__u64 comp_mask;
-	__u64 response;
+struct ib_uverbs_ex_destroy_wq  {
+	__u32 comp_mask;
+	__u32 wq_handle;
+};
+
+struct ib_uverbs_ex_destroy_wq_resp {
+	__u32 comp_mask;
+	__u32 response_length;
+	__u32 events_reported;
+	__u32 reserved;
+};
+
+struct ib_uverbs_ex_modify_wq  {
+	__u32 attr_mask;
+	__u32 wq_handle;
+	__u32 wq_state;
+	__u32 curr_wq_state;
+};
+
+/* Prevent memory allocation rather than max expected size */
+#define IB_USER_VERBS_MAX_LOG_IND_TBL_SIZE 0x0d
+struct ib_uverbs_ex_create_rwq_ind_table  {
+	__u32 comp_mask;
+	__u32 log_ind_tbl_size;
+	/* Following are the wq handles according to log_ind_tbl_size
+	 * wq_handle1
+	 * wq_handle2
+	 */
+	__u32 wq_handles[0];
+};
+
+struct ib_uverbs_ex_create_rwq_ind_table_resp {
+	__u32 comp_mask;
+	__u32 response_length;
+	__u32 ind_tbl_handle;
+	__u32 ind_tbl_num;
+};
+
+struct ib_uverbs_ex_destroy_rwq_ind_table  {
+	__u32 comp_mask;
+	__u32 ind_tbl_handle;
 };
 
 #endif /* IB_USER_VERBS_H */
diff --git a/sys/ofed/include/rdma/ib_user_verbs_exp.h b/sys/ofed/include/rdma/ib_user_verbs_exp.h
deleted file mode 100644
index 557d4ba7cece..000000000000
--- a/sys/ofed/include/rdma/ib_user_verbs_exp.h
+++ /dev/null
@@ -1,204 +0,0 @@
-/*
- * Copyright (c) 2005 Topspin Communications.  All rights reserved.
- * Copyright (c) 2005, 2006 Cisco Systems.  All rights reserved.
- * Copyright (c) 2005 PathScale, Inc.  All rights reserved.
- * Copyright (c) 2006 Mellanox Technologies.  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 IB_USER_VERBS_EXP_H
-#define IB_USER_VERBS_EXP_H
-
-#include <rdma/ib_user_verbs.h>
-
-enum {
-	IB_USER_VERBS_EXP_CMD_FIRST = 64
-};
-
-enum {
-	IB_USER_VERBS_EXP_CMD_CREATE_QP,
-	IB_USER_VERBS_EXP_CMD_MODIFY_CQ,
-	IB_USER_VERBS_EXP_CMD_MODIFY_QP,
-	IB_USER_VERBS_EXP_CMD_CREATE_CQ,
-	IB_USER_VERBS_EXP_CMD_QUERY_DEVICE,
-	IB_USER_VERBS_EXP_CMD_CREATE_DCT,
-	IB_USER_VERBS_EXP_CMD_DESTROY_DCT,
-	IB_USER_VERBS_EXP_CMD_QUERY_DCT,
-};
-
-/*
- * Make sure that all structs defined in this file remain laid out so
- * that they pack the same way on 32-bit and 64-bit architectures (to
- * avoid incompatibility between 32-bit userspace and 64-bit kernels).
- * Specifically:
- *  - Do not use pointer types -- pass pointers in __u64 instead.
- *  - Make sure that any structure larger than 4 bytes is padded to a
- *    multiple of 8 bytes.  Otherwise the structure size will be
- *    different between 32-bit and 64-bit architectures.
- */
-
-enum ib_uverbs_exp_create_qp_comp_mask {
-	IB_UVERBS_EXP_CREATE_QP_CAP_FLAGS          = (1ULL << 0),
-	IB_UVERBS_EXP_CREATE_QP_INL_RECV           = (1ULL << 1),
-	IB_UVERBS_EXP_CREATE_QP_QPG                = (1ULL << 2)
-};
-
-struct ib_uverbs_qpg_init_attrib {
-	__u32 tss_child_count;
-	__u32 rss_child_count;
-};
-
-struct ib_uverbs_qpg {
-	__u32 qpg_type;
-	union {
-		struct {
-			__u32 parent_handle;
-			__u32 reserved;
-		};
-		struct ib_uverbs_qpg_init_attrib parent_attrib;
-	};
-	__u32 reserved2;
-};
-
-struct ib_uverbs_exp_create_qp {
-	__u64 comp_mask;
-	__u64 user_handle;
-	__u32 pd_handle;
-	__u32 send_cq_handle;
-	__u32 recv_cq_handle;
-	__u32 srq_handle;
-	__u32 max_send_wr;
-	__u32 max_recv_wr;
-	__u32 max_send_sge;
-	__u32 max_recv_sge;
-	__u32 max_inline_data;
-	__u8  sq_sig_all;
-	__u8  qp_type;
-	__u8  is_srq;
-	__u8  reserved;
-	__u64 qp_cap_flags;
-	__u32 max_inl_recv;
-	__u32 reserved1;
-	struct ib_uverbs_qpg qpg;
-	__u64 driver_data[0];
-};
-
-enum ib_uverbs_exp_create_qp_resp_comp_mask {
-	IB_UVERBS_EXP_CREATE_QP_RESP_INL_RECV	= (1ULL << 0),
-};
-
-struct ib_uverbs_exp_create_qp_resp {
-	__u64 comp_mask;
-	__u32 qp_handle;
-	__u32 qpn;
-	__u32 max_send_wr;
-	__u32 max_recv_wr;
-	__u32 max_send_sge;
-	__u32 max_recv_sge;
-	__u32 max_inline_data;
-	__u32 max_inl_recv;
-};
-
-struct ib_uverbs_create_dct {
-	__u64	comp_mask;
-	__u64	user_handle;
-	__u32	pd_handle;
-	__u32	cq_handle;
-	__u32	srq_handle;
-	__u32	access_flags;
-	__u32	flow_label;
-	__u64	dc_key;
-	__u8	min_rnr_timer;
-	__u8	tclass;
-	__u8	port;
-	__u8	pkey_index;
-	__u8	gid_index;
-	__u8	hop_limit;
-	__u8	mtu;
-	__u8	rsvd;
-	__u32	create_flags;
-	__u64	driver_data[0];
-};
-
-struct ib_uverbs_create_dct_resp {
-	__u32 dct_handle;
-	__u32 dctn;
-};
-
-struct ib_uverbs_destroy_dct {
-	__u64 comp_mask;
-	__u64 user_handle;
-};
-
-struct ib_uverbs_destroy_dct_resp {
-	__u64	reserved;
-};
-
-struct ib_uverbs_query_dct {
-	__u64	comp_mask;
-	__u64	dct_handle;
-	__u64	driver_data[0];
-};
-
-struct ib_uverbs_query_dct_resp {
-	__u64	dc_key;
-	__u32	access_flags;
-	__u32	flow_label;
-	__u32	key_violations;
-	__u8	port;
-	__u8	min_rnr_timer;
-	__u8	tclass;
-	__u8	mtu;
-	__u8	pkey_index;
-	__u8	gid_index;
-	__u8	hop_limit;
-	__u8	state;
-	__u32	rsvd;
-	__u64	driver_data[0];
-};
-
-struct ib_uverbs_exp_query_device {
-	__u64 comp_mask;
-	__u64 driver_data[0];
-};
-
-struct ib_uverbs_exp_query_device_resp {
-	__u64					comp_mask;
-	struct ib_uverbs_query_device_resp	base;
-	__u64					timestamp_mask;
-	__u64					hca_core_clock;
-	__u64					device_cap_flags2;
-	__u32					dc_rd_req;
-	__u32					dc_rd_res;
-	__u32					inline_recv_sz;
-	__u32					max_rss_tbl_sz;
-};
-
-#endif /* IB_USER_VERBS_EXP_H */
diff --git a/sys/ofed/include/rdma/ib_verbs.h b/sys/ofed/include/rdma/ib_verbs.h
index 21fe2ffdb3bb..c96757d27af6 100644
--- a/sys/ofed/include/rdma/ib_verbs.h
+++ b/sys/ofed/include/rdma/ib_verbs.h
@@ -48,12 +48,24 @@
 #include <linux/rwsem.h>
 #include <linux/scatterlist.h>
 #include <linux/workqueue.h>
+#include <linux/socket.h>
 #include <linux/if_ether.h>
-#include <linux/mutex.h>
+#include <net/ipv6.h>
+#include <net/ip.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/rcupdate.h>
+#include <linux/netdevice.h>
+#include <netinet/ip.h>
 
+#include <asm/atomic.h>
 #include <asm/uaccess.h>
 
+struct ifla_vf_info;
+struct ifla_vf_stats;
+
 extern struct workqueue_struct *ib_wq;
+extern struct workqueue_struct *ib_comp_wq;
 
 union ib_gid {
 	u8	raw[16];
@@ -63,50 +75,116 @@ union ib_gid {
 	} global;
 };
 
+extern union ib_gid zgid;
+
+enum ib_gid_type {
+	/* If link layer is Ethernet, this is RoCE V1 */
+	IB_GID_TYPE_IB        = 0,
+	IB_GID_TYPE_ROCE      = 0,
+	IB_GID_TYPE_ROCE_UDP_ENCAP = 1,
+	IB_GID_TYPE_SIZE
+};
+
+#define ROCE_V2_UDP_DPORT      4791
+struct ib_gid_attr {
+	enum ib_gid_type	gid_type;
+	struct net_device	*ndev;
+};
+
 enum rdma_node_type {
 	/* IB values map to NodeInfo:NodeType. */
 	RDMA_NODE_IB_CA 	= 1,
 	RDMA_NODE_IB_SWITCH,
 	RDMA_NODE_IB_ROUTER,
 	RDMA_NODE_RNIC,
-	RDMA_NODE_MIC
+	RDMA_NODE_USNIC,
+	RDMA_NODE_USNIC_UDP,
+};
+
+enum {
+	/* set the local administered indication */
+	IB_SA_WELL_KNOWN_GUID	= BIT_ULL(57) | 2,
 };
 
 enum rdma_transport_type {
 	RDMA_TRANSPORT_IB,
 	RDMA_TRANSPORT_IWARP,
-	RDMA_TRANSPORT_SCIF
+	RDMA_TRANSPORT_USNIC,
+	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);
+
+enum rdma_network_type {
+	RDMA_NETWORK_IB,
+	RDMA_NETWORK_ROCE_V1 = RDMA_NETWORK_IB,
+	RDMA_NETWORK_IPV4,
+	RDMA_NETWORK_IPV6
 };
 
-enum rdma_transport_type
-rdma_node_get_transport(enum rdma_node_type node_type) __attribute_const__;
+static inline enum ib_gid_type ib_network_to_gid_type(enum rdma_network_type network_type)
+{
+	if (network_type == RDMA_NETWORK_IPV4 ||
+	    network_type == RDMA_NETWORK_IPV6)
+		return IB_GID_TYPE_ROCE_UDP_ENCAP;
+
+	/* IB_GID_TYPE_IB same as RDMA_NETWORK_ROCE_V1 */
+	return IB_GID_TYPE_IB;
+}
+
+static inline enum rdma_network_type ib_gid_to_network_type(enum ib_gid_type gid_type,
+							    union ib_gid *gid)
+{
+	if (gid_type == IB_GID_TYPE_IB)
+		return RDMA_NETWORK_IB;
+
+	if (ipv6_addr_v4mapped((struct in6_addr *)gid))
+		return RDMA_NETWORK_IPV4;
+	else
+		return RDMA_NETWORK_IPV6;
+}
 
 enum rdma_link_layer {
 	IB_LINK_LAYER_UNSPECIFIED,
 	IB_LINK_LAYER_INFINIBAND,
 	IB_LINK_LAYER_ETHERNET,
-	IB_LINK_LAYER_SCIF
 };
 
 enum ib_device_cap_flags {
-	IB_DEVICE_RESIZE_MAX_WR		= 1,
-	IB_DEVICE_BAD_PKEY_CNTR		= (1<<1),
-	IB_DEVICE_BAD_QKEY_CNTR		= (1<<2),
-	IB_DEVICE_RAW_MULTI		= (1<<3),
-	IB_DEVICE_AUTO_PATH_MIG		= (1<<4),
-	IB_DEVICE_CHANGE_PHY_PORT	= (1<<5),
-	IB_DEVICE_UD_AV_PORT_ENFORCE	= (1<<6),
-	IB_DEVICE_CURR_QP_STATE_MOD	= (1<<7),
-	IB_DEVICE_SHUTDOWN_PORT		= (1<<8),
-	IB_DEVICE_INIT_TYPE		= (1<<9),
-	IB_DEVICE_PORT_ACTIVE_EVENT	= (1<<10),
-	IB_DEVICE_SYS_IMAGE_GUID	= (1<<11),
-	IB_DEVICE_RC_RNR_NAK_GEN	= (1<<12),
-	IB_DEVICE_SRQ_RESIZE		= (1<<13),
-	IB_DEVICE_N_NOTIFY_CQ		= (1<<14),
-	IB_DEVICE_LOCAL_DMA_LKEY	= (1<<15),
-	IB_DEVICE_RESERVED		= (1<<16), /* old SEND_W_INV */
-	IB_DEVICE_MEM_WINDOW		= (1<<17),
+	IB_DEVICE_RESIZE_MAX_WR			= (1 << 0),
+	IB_DEVICE_BAD_PKEY_CNTR			= (1 << 1),
+	IB_DEVICE_BAD_QKEY_CNTR			= (1 << 2),
+	IB_DEVICE_RAW_MULTI			= (1 << 3),
+	IB_DEVICE_AUTO_PATH_MIG			= (1 << 4),
+	IB_DEVICE_CHANGE_PHY_PORT		= (1 << 5),
+	IB_DEVICE_UD_AV_PORT_ENFORCE		= (1 << 6),
+	IB_DEVICE_CURR_QP_STATE_MOD		= (1 << 7),
+	IB_DEVICE_SHUTDOWN_PORT			= (1 << 8),
+	IB_DEVICE_INIT_TYPE			= (1 << 9),
+	IB_DEVICE_PORT_ACTIVE_EVENT		= (1 << 10),
+	IB_DEVICE_SYS_IMAGE_GUID		= (1 << 11),
+	IB_DEVICE_RC_RNR_NAK_GEN		= (1 << 12),
+	IB_DEVICE_SRQ_RESIZE			= (1 << 13),
+	IB_DEVICE_N_NOTIFY_CQ			= (1 << 14),
+
+	/*
+	 * This device supports a per-device lkey or stag that can be
+	 * used without performing a memory registration for the local
+	 * memory.  Note that ULPs should never check this flag, but
+	 * instead of use the local_dma_lkey flag in the ib_pd structure,
+	 * which will always contain a usable lkey.
+	 */
+	IB_DEVICE_LOCAL_DMA_LKEY		= (1 << 15),
+	IB_DEVICE_RESERVED /* old SEND_W_INV */	= (1 << 16),
+	IB_DEVICE_MEM_WINDOW			= (1 << 17),
 	/*
 	 * Devices should set IB_DEVICE_UD_IP_SUM if they support
 	 * insertion of UDP and TCP checksum on outgoing UD IPoIB
@@ -114,27 +192,38 @@ enum ib_device_cap_flags {
 	 * incoming messages.  Setting this flag implies that the
 	 * IPoIB driver may set NETIF_F_IP_CSUM for datagram mode.
 	 */
-	IB_DEVICE_UD_IP_CSUM		= (1<<18),
-	IB_DEVICE_UD_TSO		= (1<<19),
-	IB_DEVICE_XRC			= (1<<20),
-	IB_DEVICE_MEM_MGT_EXTENSIONS	= (1<<21),
-	IB_DEVICE_BLOCK_MULTICAST_LOOPBACK = (1<<22),
-	IB_DEVICE_MR_ALLOCATE		= (1<<23),
-	IB_DEVICE_SHARED_MR             = (1<<24),
-	IB_DEVICE_QPG			= (1<<25),
-	IB_DEVICE_UD_RSS		= (1<<26),
-	IB_DEVICE_UD_TSS		= (1<<27),
-	IB_DEVICE_CROSS_CHANNEL		= (1<<28),
-	IB_DEVICE_MANAGED_FLOW_STEERING = (1<<29),
+	IB_DEVICE_UD_IP_CSUM			= (1 << 18),
+	IB_DEVICE_UD_TSO			= (1 << 19),
+	IB_DEVICE_XRC				= (1 << 20),
+
+	/*
+	 * This device supports the IB "base memory management extension",
+	 * which includes support for fast registrations (IB_WR_REG_MR,
+	 * IB_WR_LOCAL_INV and IB_WR_SEND_WITH_INV verbs).  This flag should
+	 * also be set by any iWarp device which must support FRs to comply
+	 * to the iWarp verbs spec.  iWarp devices also support the
+	 * IB_WR_RDMA_READ_WITH_INV verb for RDMA READs that invalidate the
+	 * stag.
+	 */
+	IB_DEVICE_MEM_MGT_EXTENSIONS		= (1 << 21),
+	IB_DEVICE_BLOCK_MULTICAST_LOOPBACK	= (1 << 22),
+	IB_DEVICE_MEM_WINDOW_TYPE_2A		= (1 << 23),
+	IB_DEVICE_MEM_WINDOW_TYPE_2B		= (1 << 24),
+	IB_DEVICE_RC_IP_CSUM			= (1 << 25),
+	IB_DEVICE_RAW_IP_CSUM			= (1 << 26),
 	/*
-	 * Devices can set either IB_DEVICE_MEM_WINDOW_TYPE_2A or
-	 * IB_DEVICE_MEM_WINDOW_TYPE_2B if it supports type 2A or type 2B
-	 * memory windows. It can set neither to indicate it doesn't support
-	 * type 2 windows at all.
+	 * Devices should set IB_DEVICE_CROSS_CHANNEL if they
+	 * support execution of WQEs that involve synchronization
+	 * of I/O operations with single completion queue managed
+	 * by hardware.
 	 */
-	IB_DEVICE_MEM_WINDOW_TYPE_2A	= (1<<30),
-	IB_DEVICE_MEM_WINDOW_TYPE_2B	= (1<<31),
-	IB_DEVICE_SIGNATURE_HANDOVER	= (1LL<<32)
+	IB_DEVICE_CROSS_CHANNEL		= (1 << 27),
+	IB_DEVICE_MANAGED_FLOW_STEERING		= (1 << 29),
+	IB_DEVICE_SIGNATURE_HANDOVER		= (1 << 30),
+	IB_DEVICE_ON_DEMAND_PAGING		= (1ULL << 31),
+	IB_DEVICE_SG_GAPS_REG			= (1ULL << 32),
+	IB_DEVICE_VIRTUAL_FUNCTION		= (1ULL << 33),
+	IB_DEVICE_RAW_SCATTER_FCS		= (1ULL << 34),
 };
 
 enum ib_signature_prot_cap {
@@ -154,10 +243,46 @@ enum ib_atomic_cap {
 	IB_ATOMIC_GLOB
 };
 
-enum ib_cq_create_flags {
-	IB_CQ_CREATE_CROSS_CHANNEL	= 1 << 0,
-	IB_CQ_TIMESTAMP			= 1 << 1,
-	IB_CQ_TIMESTAMP_TO_SYS_TIME	= 1 << 2
+enum ib_odp_general_cap_bits {
+	IB_ODP_SUPPORT = 1 << 0,
+};
+
+enum ib_odp_transport_cap_bits {
+	IB_ODP_SUPPORT_SEND	= 1 << 0,
+	IB_ODP_SUPPORT_RECV	= 1 << 1,
+	IB_ODP_SUPPORT_WRITE	= 1 << 2,
+	IB_ODP_SUPPORT_READ	= 1 << 3,
+	IB_ODP_SUPPORT_ATOMIC	= 1 << 4,
+};
+
+struct ib_odp_caps {
+	uint64_t general_caps;
+	struct {
+		uint32_t  rc_odp_caps;
+		uint32_t  uc_odp_caps;
+		uint32_t  ud_odp_caps;
+	} per_transport_caps;
+};
+
+struct ib_rss_caps {
+	/* Corresponding bit will be set if qp type from
+	 * 'enum ib_qp_type' is supported, e.g.
+	 * supported_qpts |= 1 << IB_QPT_UD
+	 */
+	u32 supported_qpts;
+	u32 max_rwq_indirection_tables;
+	u32 max_rwq_indirection_table_size;
+};
+
+enum ib_cq_creation_flags {
+	IB_CQ_FLAGS_TIMESTAMP_COMPLETION   = 1 << 0,
+	IB_CQ_FLAGS_IGNORE_OVERRUN	   = 1 << 1,
+};
+
+struct ib_cq_init_attr {
+	unsigned int	cqe;
+	int		comp_vector;
+	u32		flags;
 };
 
 struct ib_device_attr {
@@ -199,19 +324,15 @@ struct ib_device_attr {
 	int			max_srq_wr;
 	int			max_srq_sge;
 	unsigned int		max_fast_reg_page_list_len;
-	int			max_rss_tbl_sz;
 	u16			max_pkeys;
 	u8			local_ca_ack_delay;
-	int                     comp_mask;
-	uint64_t                timestamp_mask;
-	uint64_t                hca_core_clock;
-	unsigned int		sig_prot_cap;
-	unsigned int		sig_guard_cap;
-};
-
-enum ib_device_attr_comp_mask {
-	IB_DEVICE_ATTR_WITH_TIMESTAMP_MASK = 1ULL << 1,
-	IB_DEVICE_ATTR_WITH_HCA_CORE_CLOCK = 1ULL << 2
+	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 */
+	struct ib_rss_caps	rss_caps;
+	u32			max_wq_type_rq;
 };
 
 enum ib_mtu {
@@ -241,7 +362,7 @@ enum ib_port_state {
 	IB_PORT_ARMED		= 3,
 	IB_PORT_ACTIVE		= 4,
 	IB_PORT_ACTIVE_DEFER	= 5,
-	IB_PORT_DUMMY		= -1	/* force enum signed */
+	IB_PORT_DUMMY		= -1,	/* force enum signed */
 };
 
 enum ib_port_cap_flags {
@@ -267,7 +388,8 @@ enum ib_port_cap_flags {
 	IB_PORT_CAP_MASK_NOTICE_SUP		= 1 << 22,
 	IB_PORT_BOOT_MGMT_SUP			= 1 << 23,
 	IB_PORT_LINK_LATENCY_SUP		= 1 << 24,
-	IB_PORT_CLIENT_REG_SUP			= 1 << 25
+	IB_PORT_CLIENT_REG_SUP			= 1 << 25,
+	IB_PORT_IP_BASED_GIDS			= 1 << 26,
 };
 
 enum ib_port_width {
@@ -297,58 +419,101 @@ enum ib_port_speed {
 	IB_SPEED_EDR	= 32
 };
 
-struct ib_protocol_stats {
-	/* TBD... */
+/**
+ * struct rdma_hw_stats
+ * @timestamp - Used by the core code to track when the last update was
+ * @lifespan - Used by the core code to determine how old the counters
+ *   should be before being updated again.  Stored in jiffies, defaults
+ *   to 10 milliseconds, drivers can override the default be specifying
+ *   their own value during their allocation routine.
+ * @name - Array of pointers to static names used for the counters in
+ *   directory.
+ * @num_counters - How many hardware counters there are.  If name is
+ *   shorter than this number, a kernel oops will result.  Driver authors
+ *   are encouraged to leave BUILD_BUG_ON(ARRAY_SIZE(@name) < num_counters)
+ *   in their code to prevent this.
+ * @value - Array of u64 counters that are accessed by the sysfs code and
+ *   filled in by the drivers get_stats routine
+ */
+struct rdma_hw_stats {
+	unsigned long	timestamp;
+	unsigned long	lifespan;
+	const char * const *names;
+	int		num_counters;
+	u64		value[];
 };
 
-struct iw_protocol_stats {
-	u64	ipInReceives;
-	u64	ipInHdrErrors;
-	u64	ipInTooBigErrors;
-	u64	ipInNoRoutes;
-	u64	ipInAddrErrors;
-	u64	ipInUnknownProtos;
-	u64	ipInTruncatedPkts;
-	u64	ipInDiscards;
-	u64	ipInDelivers;
-	u64	ipOutForwDatagrams;
-	u64	ipOutRequests;
-	u64	ipOutDiscards;
-	u64	ipOutNoRoutes;
-	u64	ipReasmTimeout;
-	u64	ipReasmReqds;
-	u64	ipReasmOKs;
-	u64	ipReasmFails;
-	u64	ipFragOKs;
-	u64	ipFragFails;
-	u64	ipFragCreates;
-	u64	ipInMcastPkts;
-	u64	ipOutMcastPkts;
-	u64	ipInBcastPkts;
-	u64	ipOutBcastPkts;
+#define RDMA_HW_STATS_DEFAULT_LIFESPAN 10
+/**
+ * rdma_alloc_hw_stats_struct - Helper function to allocate dynamic struct
+ *   for drivers.
+ * @names - Array of static const char *
+ * @num_counters - How many elements in array
+ * @lifespan - How many milliseconds between updates
+ */
+static inline struct rdma_hw_stats *rdma_alloc_hw_stats_struct(
+		const char * const *names, int num_counters,
+		unsigned long lifespan)
+{
+	struct rdma_hw_stats *stats;
 
-	u64	tcpRtoAlgorithm;
-	u64	tcpRtoMin;
-	u64	tcpRtoMax;
-	u64	tcpMaxConn;
-	u64	tcpActiveOpens;
-	u64	tcpPassiveOpens;
-	u64	tcpAttemptFails;
-	u64	tcpEstabResets;
-	u64	tcpCurrEstab;
-	u64	tcpInSegs;
-	u64	tcpOutSegs;
-	u64	tcpRetransSegs;
-	u64	tcpInErrs;
-	u64	tcpOutRsts;
-};
+	stats = kzalloc(sizeof(*stats) + num_counters * sizeof(u64),
+			GFP_KERNEL);
+	if (!stats)
+		return NULL;
+	stats->names = names;
+	stats->num_counters = num_counters;
+	stats->lifespan = msecs_to_jiffies(lifespan);
 
-union rdma_protocol_stats {
-	struct ib_protocol_stats	ib;
-	struct iw_protocol_stats	iw;
-};
+	return stats;
+}
+
+
+/* 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_CAP_PROT_ROCE_UDP_ENCAP 0x00800000
+
+#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_IBA_ROCE_UDP_ENCAP			\
+					(RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP \
+					| 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 {
+	u64			subnet_prefix;
 	enum ib_port_state	state;
 	enum ib_mtu		max_mtu;
 	enum ib_mtu		active_mtu;
@@ -368,6 +533,7 @@ struct ib_port_attr {
 	u8			active_width;
 	u8			active_speed;
 	u8                      phys_state;
+	bool			grh_required;
 };
 
 enum ib_device_modify_flags {
@@ -375,9 +541,11 @@ enum ib_device_modify_flags {
 	IB_DEVICE_MODIFY_NODE_DESC	= 1 << 1
 };
 
+#define IB_DEVICE_NODE_DESC_MAX 64
+
 struct ib_device_modify {
 	u64	sys_image_guid;
-	char	node_desc[64];
+	char	node_desc[IB_DEVICE_NODE_DESC_MAX];
 };
 
 enum ib_port_modify_flags {
@@ -412,14 +580,18 @@ enum ib_event_type {
 	IB_EVENT_QP_LAST_WQE_REACHED,
 	IB_EVENT_CLIENT_REREGISTER,
 	IB_EVENT_GID_CHANGE,
+	IB_EVENT_WQ_FATAL,
 };
 
+const char *__attribute_const__ ib_event_msg(enum ib_event_type event);
+
 struct ib_event {
 	struct ib_device	*device;
 	union {
 		struct ib_cq	*cq;
 		struct ib_qp	*qp;
 		struct ib_srq	*srq;
+		struct ib_wq	*wq;
 		u8		port_num;
 	} element;
 	enum ib_event_type	event;
@@ -455,11 +627,23 @@ struct ib_grh {
 	union ib_gid	dgid;
 };
 
+union rdma_network_hdr {
+	struct ib_grh ibgrh;
+	struct {
+		/* The IB spec states that if it's IPv4, the header
+		 * is located in the last 20 bytes of the header.
+		 */
+		u8		reserved[20];
+		struct ip	roce4grh;
+	};
+};
+
 enum {
 	IB_MULTICAST_QPN = 0xffffff
 };
 
 #define IB_LID_PERMISSIVE	cpu_to_be16(0xFFFF)
+#define IB_MULTICAST_LID_BASE	cpu_to_be16(0xC000)
 
 enum ib_ah_flags {
 	IB_AH_GRH	= 1
@@ -486,57 +670,48 @@ enum ib_rate {
 	IB_RATE_300_GBPS = 18
 };
 
-enum ib_mr_create_flags {
-		IB_MR_SIGNATURE_EN = 1,
-};
-
-/**
- * ib_mr_init_attr - Memory region init attributes passed to routine
- *     ib_create_mr.
- * @max_reg_descriptors: max number of registration descriptors that
- *     may be used with registration work requests.
- * @flags: MR creation flags bit mask.
- */
-struct ib_mr_init_attr {
-	int	    max_reg_descriptors;
-	u32	    flags;
-};
-
 /**
  * ib_rate_to_mult - Convert the IB rate enum to a multiple of the
  * base rate of 2.5 Gbit/sec.  For example, IB_RATE_5_GBPS will be
  * converted to 2, since 5 Gbit/sec is 2 * 2.5 Gbit/sec.
  * @rate: rate to convert.
  */
-int ib_rate_to_mult(enum ib_rate rate) __attribute_const__;
+__attribute_const__ int ib_rate_to_mult(enum ib_rate rate);
 
 /**
  * ib_rate_to_mbps - Convert the IB rate enum to Mbps.
  * For example, IB_RATE_2_5_GBPS will be converted to 2500.
  * @rate: rate to convert.
  */
-int ib_rate_to_mbps(enum ib_rate rate) __attribute_const__;
+__attribute_const__ int ib_rate_to_mbps(enum ib_rate rate);
 
-struct ib_cq_init_attr {
-	int	cqe;
-	int	comp_vector;
-	u32	flags;
-};
 
-enum ib_signature_type {
-	IB_SIG_TYPE_T10_DIF,
+/**
+ * enum ib_mr_type - memory region type
+ * @IB_MR_TYPE_MEM_REG:       memory region that is used for
+ *                            normal registration
+ * @IB_MR_TYPE_SIGNATURE:     memory region that is used for
+ *                            signature operations (data-integrity
+ *                            capable regions)
+ * @IB_MR_TYPE_SG_GAPS:       memory region that is capable to
+ *                            register any arbitrary sg lists (without
+ *                            the normal mr constraints - see
+ *                            ib_map_mr_sg)
+ */
+enum ib_mr_type {
+	IB_MR_TYPE_MEM_REG,
+	IB_MR_TYPE_SIGNATURE,
+	IB_MR_TYPE_SG_GAPS,
 };
 
 /**
- * T10-DIF Signature types
- * T10-DIF types are defined by SCSI
- * specifications.
+ * Signature types
+ * IB_SIG_TYPE_NONE: Unprotected.
+ * IB_SIG_TYPE_T10_DIF: Type T10-DIF
  */
-enum ib_t10_dif_type {
-	IB_T10DIF_NONE,
-	IB_T10DIF_TYPE1,
-	IB_T10DIF_TYPE2,
-	IB_T10DIF_TYPE3
+enum ib_signature_type {
+	IB_SIG_TYPE_NONE,
+	IB_SIG_TYPE_T10_DIF,
 };
 
 /**
@@ -552,24 +727,26 @@ enum ib_t10_dif_bg_type {
 /**
  * struct ib_t10_dif_domain - Parameters specific for T10-DIF
  *     domain.
- * @type: T10-DIF type (0|1|2|3)
  * @bg_type: T10-DIF block guard type (CRC|CSUM)
  * @pi_interval: protection information interval.
  * @bg: seed of guard computation.
  * @app_tag: application tag of guard block
  * @ref_tag: initial guard block reference tag.
- * @type3_inc_reftag: T10-DIF type 3 does not state
- *     about the reference tag, it is the user
- *     choice to increment it or not.
+ * @ref_remap: Indicate wethear the reftag increments each block
+ * @app_escape: Indicate to skip block check if apptag=0xffff
+ * @ref_escape: Indicate to skip block check if reftag=0xffffffff
+ * @apptag_check_mask: check bitmask of application tag.
  */
 struct ib_t10_dif_domain {
-	enum ib_t10_dif_type	type;
 	enum ib_t10_dif_bg_type bg_type;
-	u32			pi_interval;
+	u16			pi_interval;
 	u16			bg;
 	u16			app_tag;
 	u32			ref_tag;
-	bool			type3_inc_reftag;
+	bool			ref_remap;
+	bool			app_escape;
+	bool			ref_escape;
+	u16			apptag_check_mask;
 };
 
 /**
@@ -636,7 +813,7 @@ struct ib_mr_status {
  * enum.
  * @mult: multiple to convert.
  */
-enum ib_rate mult_to_ib_rate(int mult) __attribute_const__;
+__attribute_const__ enum ib_rate mult_to_ib_rate(int mult);
 
 struct ib_ah_attr {
 	struct ib_global_route	grh;
@@ -646,8 +823,7 @@ struct ib_ah_attr {
 	u8			static_rate;
 	u8			ah_flags;
 	u8			port_num;
-	u8			dmac[6];
-	u16			vlan_id;
+	u8			dmac[ETH_ALEN];
 };
 
 enum ib_wc_status {
@@ -675,16 +851,17 @@ enum ib_wc_status {
 	IB_WC_GENERAL_ERR
 };
 
+const char *__attribute_const__ ib_wc_status_msg(enum ib_wc_status status);
+
 enum ib_wc_opcode {
 	IB_WC_SEND,
 	IB_WC_RDMA_WRITE,
 	IB_WC_RDMA_READ,
 	IB_WC_COMP_SWAP,
 	IB_WC_FETCH_ADD,
-	IB_WC_BIND_MW,
 	IB_WC_LSO,
 	IB_WC_LOCAL_INV,
-	IB_WC_FAST_REG_MR,
+	IB_WC_REG_MR,
 	IB_WC_MASKED_COMP_SWAP,
 	IB_WC_MASKED_FETCH_ADD,
 /*
@@ -692,7 +869,8 @@ enum ib_wc_opcode {
  * receive by testing (opcode & IB_WC_RECV).
  */
 	IB_WC_RECV			= 1 << 7,
-	IB_WC_RECV_RDMA_WITH_IMM
+	IB_WC_RECV_RDMA_WITH_IMM,
+	IB_WC_DUMMY = -1,	/* force enum signed */
 };
 
 enum ib_wc_flags {
@@ -700,15 +878,16 @@ enum ib_wc_flags {
 	IB_WC_WITH_IMM		= (1<<1),
 	IB_WC_WITH_INVALIDATE	= (1<<2),
 	IB_WC_IP_CSUM_OK	= (1<<3),
-	IB_WC_WITH_SL		= (1<<4),
-	IB_WC_WITH_SLID		= (1<<5),
-	IB_WC_WITH_TIMESTAMP	= (1<<6),
-	IB_WC_WITH_SMAC		= (1<<7),
-	IB_WC_WITH_VLAN		= (1<<8),
+	IB_WC_WITH_SMAC		= (1<<4),
+	IB_WC_WITH_VLAN		= (1<<5),
+	IB_WC_WITH_NETWORK_HDR_TYPE	= (1<<6),
 };
 
 struct ib_wc {
-	u64			wr_id;
+	union {
+		u64		wr_id;
+		struct ib_cqe	*wr_cqe;
+	};
 	enum ib_wc_status	status;
 	enum ib_wc_opcode	opcode;
 	u32			vendor_err;
@@ -725,12 +904,9 @@ struct ib_wc {
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */
-	int			csum_ok;
-	struct {
-		uint64_t	timestamp; /* timestamp = 0 indicates error*/
-	} ts;
-	u8			smac[6];
+	u8			smac[ETH_ALEN];
 	u16			vlan_id;
+	u8			network_hdr_type;
 };
 
 enum ib_cq_notify_flags {
@@ -776,7 +952,13 @@ struct ib_qp_cap {
 	u32	max_send_sge;
 	u32	max_recv_sge;
 	u32	max_inline_data;
-	u32	qpg_tss_mask_sz;
+
+	/*
+	 * Maximum number of rdma_rw_ctx structures in flight at a time.
+	 * ib_create_qp() will calculate the right amount of neededed WRs
+	 * and MRs based on this.
+	 */
+	u32	max_rdma_ctxs;
 };
 
 enum ib_sig_type {
@@ -801,7 +983,6 @@ enum ib_qp_type {
 	IB_QPT_RAW_PACKET = 8,
 	IB_QPT_XRC_INI = 9,
 	IB_QPT_XRC_TGT,
-	IB_QPT_DC_INI,
 	IB_QPT_MAX,
 	/* Reserve a range for qp types internal to the low level driver.
 	 * These qp types will not be visible at the IB core layer, so the
@@ -822,27 +1003,22 @@ enum ib_qp_type {
 enum ib_qp_create_flags {
 	IB_QP_CREATE_IPOIB_UD_LSO		= 1 << 0,
 	IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK	= 1 << 1,
-	IB_QP_CREATE_CROSS_CHANNEL		= 1 << 2,
-	IB_QP_CREATE_MANAGED_SEND		= 1 << 3,
-	IB_QP_CREATE_MANAGED_RECV		= 1 << 4,
+	IB_QP_CREATE_CROSS_CHANNEL              = 1 << 2,
+	IB_QP_CREATE_MANAGED_SEND               = 1 << 3,
+	IB_QP_CREATE_MANAGED_RECV               = 1 << 4,
 	IB_QP_CREATE_NETIF_QP			= 1 << 5,
 	IB_QP_CREATE_SIGNATURE_EN		= 1 << 6,
+	IB_QP_CREATE_USE_GFP_NOIO		= 1 << 7,
+	IB_QP_CREATE_SCATTER_FCS		= 1 << 8,
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_QP_CREATE_RESERVED_START		= 1 << 26,
 	IB_QP_CREATE_RESERVED_END		= 1 << 31,
 };
 
-enum ib_qpg_type {
-	IB_QPG_NONE	= 0,
-	IB_QPG_PARENT	= (1<<0),
-	IB_QPG_CHILD_RX = (1<<1),
-	IB_QPG_CHILD_TX = (1<<2)
-};
-
-struct ib_qpg_init_attrib {
-	u32 tss_child_count;
-	u32 rss_child_count;
-};
+/*
+ * Note: users may not call ib_close_qp or ib_destroy_qp from the event_handler
+ * callback to destroy the passed in QP.
+ */
 
 struct ib_qp_init_attr {
 	void                  (*event_handler)(struct ib_event *, void *);
@@ -852,52 +1028,15 @@ struct ib_qp_init_attr {
 	struct ib_srq	       *srq;
 	struct ib_xrcd	       *xrcd;     /* XRC TGT QPs only */
 	struct ib_qp_cap	cap;
-	union {
-		struct ib_qp *qpg_parent; /* see qpg_type */
-		struct ib_qpg_init_attrib parent_attrib;
-	};
 	enum ib_sig_type	sq_sig_type;
 	enum ib_qp_type		qp_type;
 	enum ib_qp_create_flags	create_flags;
-	enum ib_qpg_type	qpg_type;
-	u8			port_num; /* special QP types only */
-};
 
-enum {
-	IB_DCT_CREATE_FLAG_RCV_INLINE		= 1 << 0,
-	IB_DCT_CREATE_FLAGS_MASK		= IB_DCT_CREATE_FLAG_RCV_INLINE,
-};
-
-struct ib_dct_init_attr {
-	struct ib_pd	       *pd;
-	struct ib_cq	       *cq;
-	struct ib_srq	       *srq;
-	u64			dc_key;
-	u8			port;
-	u32			access_flags;
-	u8			min_rnr_timer;
-	u8			tclass;
-	u32			flow_label;
-	enum ib_mtu		mtu;
-	u8			pkey_index;
-	u8			gid_index;
-	u8			hop_limit;
-	u32			create_flags;
-};
-
-struct ib_dct_attr {
-	u64			dc_key;
-	u8			port;
-	u32			access_flags;
-	u8			min_rnr_timer;
-	u8			tclass;
-	u32			flow_label;
-	enum ib_mtu		mtu;
-	u8			pkey_index;
-	u8			gid_index;
-	u8			hop_limit;
-	u32			key_violations;
-	u8			state;
+	/*
+	 * Only needed for special QP types, or when using the RW API.
+	 */
+	u8			port_num;
+	struct ib_rwq_ind_table *rwq_ind_tbl;
 };
 
 struct ib_qp_open_attr {
@@ -964,12 +1103,10 @@ enum ib_qp_attr_mask {
 	IB_QP_PATH_MIG_STATE		= (1<<18),
 	IB_QP_CAP			= (1<<19),
 	IB_QP_DEST_QPN			= (1<<20),
-	IB_QP_GROUP_RSS			= (1<<21),
-	IB_QP_DC_KEY			= (1<<22),
-	IB_QP_SMAC			= (1<<23),
-	IB_QP_ALT_SMAC			= (1<<24),
-	IB_QP_VID			= (1<<25),
-	IB_QP_ALT_VID			= (1<<26)
+	IB_QP_RESERVED1			= (1<<21),
+	IB_QP_RESERVED2			= (1<<22),
+	IB_QP_RESERVED3			= (1<<23),
+	IB_QP_RESERVED4			= (1<<24),
 };
 
 enum ib_qp_state {
@@ -980,7 +1117,7 @@ enum ib_qp_state {
 	IB_QPS_SQD,
 	IB_QPS_SQE,
 	IB_QPS_ERR,
-	IB_QPS_DUMMY = -1	/* force enum signed */
+	IB_QPS_DUMMY = -1,	/* force enum signed */
 };
 
 enum ib_mig_state {
@@ -1020,40 +1157,6 @@ struct ib_qp_attr {
 	u8			rnr_retry;
 	u8			alt_port_num;
 	u8			alt_timeout;
-	u8                      smac[ETH_ALEN];
-	u8                      alt_smac[ETH_ALEN];
-	u16                     vlan_id;
-	u16                     alt_vlan_id;
-
-};
-
-struct ib_qp_attr_ex {
-	enum ib_qp_state	qp_state;
-	enum ib_qp_state	cur_qp_state;
-	enum ib_mtu		path_mtu;
-	enum ib_mig_state	path_mig_state;
-	u32			qkey;
-	u32			rq_psn;
-	u32			sq_psn;
-	u32			dest_qp_num;
-	int			qp_access_flags;
-	struct ib_qp_cap	cap;
-	struct ib_ah_attr	ah_attr;
-	struct ib_ah_attr	alt_ah_attr;
-	u16			pkey_index;
-	u16			alt_pkey_index;
-	u8			en_sqd_async_notify;
-	u8			sq_draining;
-	u8			max_rd_atomic;
-	u8			max_dest_rd_atomic;
-	u8			min_rnr_timer;
-	u8			port_num;
-	u8			timeout;
-	u8			retry_cnt;
-	u8			rnr_retry;
-	u8			alt_port_num;
-	u8			alt_timeout;
-	u64			dct_key;
 };
 
 enum ib_wr_opcode {
@@ -1068,10 +1171,9 @@ enum ib_wr_opcode {
 	IB_WR_SEND_WITH_INV,
 	IB_WR_RDMA_READ_WITH_INV,
 	IB_WR_LOCAL_INV,
-	IB_WR_FAST_REG_MR,
+	IB_WR_REG_MR,
 	IB_WR_MASKED_ATOMIC_CMP_AND_SWP,
 	IB_WR_MASKED_ATOMIC_FETCH_AND_ADD,
-	IB_WR_BIND_MW,
 	IB_WR_REG_SIG_MR,
 	/* reserve values for low level drivers' internal use.
 	 * These values will not be used at all in the ib core layer.
@@ -1086,6 +1188,7 @@ enum ib_wr_opcode {
 	IB_WR_RESERVED8,
 	IB_WR_RESERVED9,
 	IB_WR_RESERVED10,
+	IB_WR_DUMMY = -1,	/* force enum signed */
 };
 
 enum ib_send_flags {
@@ -1098,7 +1201,6 @@ enum ib_send_flags {
 	/* reserve bits 26-31 for low level drivers' internal use */
 	IB_SEND_RESERVED_START	= (1 << 26),
 	IB_SEND_RESERVED_END	= (1 << 31),
-	IB_SEND_UMR_UNREG       = (1<<5)
 };
 
 struct ib_sge {
@@ -1107,32 +1209,16 @@ struct ib_sge {
 	u32	lkey;
 };
 
-struct ib_fast_reg_page_list {
-	struct ib_device       *device;
-	u64		       *page_list;
-	unsigned int		max_page_list_len;
-};
-
-/**
- * struct ib_mw_bind_info - Parameters for a memory window bind operation.
- * @mr: A memory region to bind the memory window to.
- * @addr: The address where the memory window should begin.
- * @length: The length of the memory window, in bytes.
- * @mw_access_flags: Access flags from enum ib_access_flags for the window.
- *
- * This struct contains the shared parameters for type 1 and type 2
- * memory window bind operations.
- */
-struct ib_mw_bind_info {
-	struct ib_mr   *mr;
-	u64		addr;
-	u64		length;
-	int		mw_access_flags;
+struct ib_cqe {
+	void (*done)(struct ib_cq *cq, struct ib_wc *wc);
 };
 
 struct ib_send_wr {
 	struct ib_send_wr      *next;
-	u64			wr_id;
+	union {
+		u64		wr_id;
+		struct ib_cqe	*wr_cqe;
+	};
 	struct ib_sge	       *sg_list;
 	int			num_sge;
 	enum ib_wr_opcode	opcode;
@@ -1141,66 +1227,82 @@ struct ib_send_wr {
 		__be32		imm_data;
 		u32		invalidate_rkey;
 	} ex;
-	union {
-		struct {
-			u64	remote_addr;
-			u32	rkey;
-		} rdma;
-		struct {
-			u64	remote_addr;
-			u64	compare_add;
-			u64	swap;
-			u64	compare_add_mask;
-			u64	swap_mask;
-			u32	rkey;
-		} atomic;
-		struct {
-			struct ib_ah *ah;
-			void   *header;
-			int     hlen;
-			int     mss;
-			u32	remote_qpn;
-			u32	remote_qkey;
-			u16	pkey_index; /* valid for GSI only */
-			u8	port_num;   /* valid for DR SMPs on switch only */
-		} ud;
-		struct {
-			u64				iova_start;
-			struct ib_fast_reg_page_list   *page_list;
-			unsigned int			page_shift;
-			unsigned int			page_list_len;
-			u32				length;
-			int				access_flags;
-			u32				rkey;
-		} fast_reg;
-		struct {
-			int		npages;
-			int		access_flags;
-			u32		mkey;
-			struct ib_pd   *pd;
-			u64		virt_addr;
-			u64		length;
-			int		page_shift;
-		} umr;
-		struct {
-			struct ib_mw            *mw;
-			/* The new rkey for the memory window. */
-			u32                      rkey;
-			struct ib_mw_bind_info   bind_info;
-		} bind_mw;
-		struct {
-			struct ib_sig_attrs    *sig_attrs;
-			struct ib_mr	       *sig_mr;
-			int			access_flags;
-			struct ib_sge	       *prot;
-		} sig_handover;
-	} wr;
-	u32			xrc_remote_srq_num;	/* XRC TGT QPs only */
 };
 
+struct ib_rdma_wr {
+	struct ib_send_wr	wr;
+	u64			remote_addr;
+	u32			rkey;
+};
+
+static inline struct ib_rdma_wr *rdma_wr(struct ib_send_wr *wr)
+{
+	return container_of(wr, struct ib_rdma_wr, wr);
+}
+
+struct ib_atomic_wr {
+	struct ib_send_wr	wr;
+	u64			remote_addr;
+	u64			compare_add;
+	u64			swap;
+	u64			compare_add_mask;
+	u64			swap_mask;
+	u32			rkey;
+};
+
+static inline struct ib_atomic_wr *atomic_wr(struct ib_send_wr *wr)
+{
+	return container_of(wr, struct ib_atomic_wr, wr);
+}
+
+struct ib_ud_wr {
+	struct ib_send_wr	wr;
+	struct ib_ah		*ah;
+	void			*header;
+	int			hlen;
+	int			mss;
+	u32			remote_qpn;
+	u32			remote_qkey;
+	u16			pkey_index; /* valid for GSI only */
+	u8			port_num;   /* valid for DR SMPs on switch only */
+};
+
+static inline struct ib_ud_wr *ud_wr(struct ib_send_wr *wr)
+{
+	return container_of(wr, struct ib_ud_wr, wr);
+}
+
+struct ib_reg_wr {
+	struct ib_send_wr	wr;
+	struct ib_mr		*mr;
+	u32			key;
+	int			access;
+};
+
+static inline struct ib_reg_wr *reg_wr(struct ib_send_wr *wr)
+{
+	return container_of(wr, struct ib_reg_wr, wr);
+}
+
+struct ib_sig_handover_wr {
+	struct ib_send_wr	wr;
+	struct ib_sig_attrs    *sig_attrs;
+	struct ib_mr	       *sig_mr;
+	int			access_flags;
+	struct ib_sge	       *prot;
+};
+
+static inline struct ib_sig_handover_wr *sig_handover_wr(struct ib_send_wr *wr)
+{
+	return container_of(wr, struct ib_sig_handover_wr, wr);
+}
+
 struct ib_recv_wr {
 	struct ib_recv_wr      *next;
-	u64			wr_id;
+	union {
+		u64		wr_id;
+		struct ib_cqe	*wr_cqe;
+	};
 	struct ib_sge	       *sg_list;
 	int			num_sge;
 };
@@ -1211,40 +1313,19 @@ enum ib_access_flags {
 	IB_ACCESS_REMOTE_READ	= (1<<2),
 	IB_ACCESS_REMOTE_ATOMIC	= (1<<3),
 	IB_ACCESS_MW_BIND	= (1<<4),
-	IB_ACCESS_ALLOCATE_MR	= (1<<5),
-	IB_ZERO_BASED		= (1<<13)
-};
-
-struct ib_phys_buf {
-	u64      addr;
-	u64      size;
-};
-
-struct ib_mr_attr {
-	struct ib_pd	*pd;
-	u64		device_virt_addr;
-	u64		size;
-	int		mr_access_flags;
-	u32		lkey;
-	u32		rkey;
+	IB_ZERO_BASED		= (1<<5),
+	IB_ACCESS_ON_DEMAND     = (1<<6),
 };
 
+/*
+ * XXX: these are apparently used for ->rereg_user_mr, no idea why they
+ * are hidden here instead of a uapi header!
+ */
 enum ib_mr_rereg_flags {
 	IB_MR_REREG_TRANS	= 1,
 	IB_MR_REREG_PD		= (1<<1),
-	IB_MR_REREG_ACCESS	= (1<<2)
-};
-
-/**
- * struct ib_mw_bind - Parameters for a type 1 memory window bind operation.
- * @wr_id:      Work request id.
- * @send_flags: Flags from ib_send_flags enum.
- * @bind_info:  More parameters of the bind operation.
- */
-struct ib_mw_bind {
-	u64		wr_id;
-	int		send_flags;
-	struct ib_mw_bind_info bind_info;
+	IB_MR_REREG_ACCESS	= (1<<2),
+	IB_MR_REREG_SUPPORTED	= ((IB_MR_REREG_ACCESS << 1) - 1)
 };
 
 struct ib_fmr_attr {
@@ -1253,6 +1334,8 @@ struct ib_fmr_attr {
 	u8	page_shift;
 };
 
+struct ib_umem;
+
 struct ib_ucontext {
 	struct ib_device       *device;
 	struct list_head	pd_list;
@@ -1264,10 +1347,27 @@ struct ib_ucontext {
 	struct list_head	ah_list;
 	struct list_head	xrcd_list;
 	struct list_head	rule_list;
-	struct list_head	dct_list;
+	struct list_head	wq_list;
+	struct list_head	rwq_ind_tbl_list;
 	int			closing;
-	void		 *peer_mem_private_data;
-	char		 *peer_mem_name;
+
+	pid_t			tgid;
+#ifdef CONFIG_INFINIBAND_ON_DEMAND_PAGING
+	struct rb_root      umem_tree;
+	/*
+	 * Protects .umem_rbroot and tree, as well as odp_mrs_count and
+	 * mmu notifiers registration.
+	 */
+	struct rw_semaphore	umem_rwsem;
+	void (*invalidate_range)(struct ib_umem *umem,
+				 unsigned long start, unsigned long end);
+
+	struct mmu_notifier	mn;
+	atomic_t		notifier_count;
+	/* A list of umems that don't have private mmu notifier counters yet. */
+	struct list_head	no_private_counters;
+	int                     odp_mrs_count;
+#endif
 };
 
 struct ib_uobject {
@@ -1278,36 +1378,37 @@ struct ib_uobject {
 	int			id;		/* index into kernel idr */
 	struct kref		ref;
 	struct rw_semaphore	mutex;		/* protects .live */
+	struct rcu_head		rcu;		/* kfree_rcu() overhead */
 	int			live;
 };
 
-struct ib_udata;
-struct ib_udata_ops {
-	int		      (*copy_from)(void *dest, struct ib_udata *udata,
-					   size_t len);
-	int		      (*copy_to)(struct ib_udata *udata, void *src,
-					 size_t len);
-};
-
 struct ib_udata {
-	struct ib_udata_ops    *ops;
-	void __user *inbuf;
+	const void __user *inbuf;
 	void __user *outbuf;
 	size_t       inlen;
 	size_t       outlen;
 };
 
 struct ib_pd {
+	u32			local_dma_lkey;
+	u32			flags;
 	struct ib_device       *device;
 	struct ib_uobject      *uobject;
 	atomic_t          	usecnt; /* count all resources */
+
+	u32			unsafe_global_rkey;
+
+	/*
+	 * Implementation details of the RDMA core, don't use in drivers:
+	 */
+	struct ib_mr	       *__internal_mr;
 };
 
 struct ib_xrcd {
 	struct ib_device       *device;
 	atomic_t		usecnt; /* count all exposed resources */
 	struct inode	       *inode;
-	
+
 	struct mutex		tgt_qp_mutex;
 	struct list_head	tgt_qp_list;
 };
@@ -1318,25 +1419,14 @@ struct ib_ah {
 	struct ib_uobject	*uobject;
 };
 
-enum ib_cq_attr_mask {
-	IB_CQ_MODERATION               = (1 << 0),
-	IB_CQ_CAP_FLAGS                = (1 << 1)
-};
-
-enum ib_cq_cap_flags {
-	IB_CQ_IGNORE_OVERRUN           = (1 << 0)
-};
+typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);
 
-struct ib_cq_attr {
-	struct {
-		u16     cq_count;
-		u16     cq_period;
-	} moderation;
-	u32     cq_cap_flags;
+enum ib_poll_context {
+	IB_POLL_DIRECT,		/* caller context, no hw completions */
+	IB_POLL_SOFTIRQ,	/* poll from softirq context */
+	IB_POLL_WORKQUEUE,	/* poll from workqueue */
 };
 
-typedef void (*ib_comp_handler)(struct ib_cq *cq, void *cq_context);
-
 struct ib_cq {
 	struct ib_device       *device;
 	struct ib_uobject      *uobject;
@@ -1345,6 +1435,8 @@ struct ib_cq {
 	void                   *cq_context;
 	int               	cqe;
 	atomic_t          	usecnt; /* count number of work queues */
+	enum ib_poll_context	poll_ctx;
+	struct work_struct	work;
 };
 
 struct ib_srq {
@@ -1365,14 +1457,77 @@ struct ib_srq {
 	} ext;
 };
 
+enum ib_wq_type {
+	IB_WQT_RQ
+};
+
+enum ib_wq_state {
+	IB_WQS_RESET,
+	IB_WQS_RDY,
+	IB_WQS_ERR
+};
+
+struct ib_wq {
+	struct ib_device       *device;
+	struct ib_uobject      *uobject;
+	void		    *wq_context;
+	void		    (*event_handler)(struct ib_event *, void *);
+	struct ib_pd	       *pd;
+	struct ib_cq	       *cq;
+	u32		wq_num;
+	enum ib_wq_state       state;
+	enum ib_wq_type	wq_type;
+	atomic_t		usecnt;
+};
+
+struct ib_wq_init_attr {
+	void		       *wq_context;
+	enum ib_wq_type	wq_type;
+	u32		max_wr;
+	u32		max_sge;
+	struct	ib_cq	       *cq;
+	void		    (*event_handler)(struct ib_event *, void *);
+};
+
+enum ib_wq_attr_mask {
+	IB_WQ_STATE	= 1 << 0,
+	IB_WQ_CUR_STATE	= 1 << 1,
+};
+
+struct ib_wq_attr {
+	enum	ib_wq_state	wq_state;
+	enum	ib_wq_state	curr_wq_state;
+};
+
+struct ib_rwq_ind_table {
+	struct ib_device	*device;
+	struct ib_uobject      *uobject;
+	atomic_t		usecnt;
+	u32		ind_tbl_num;
+	u32		log_ind_tbl_size;
+	struct ib_wq	**ind_tbl;
+};
+
+struct ib_rwq_ind_table_init_attr {
+	u32		log_ind_tbl_size;
+	/* Each entry is a pointer to Receive Work Queue */
+	struct ib_wq	**ind_tbl;
+};
+
+/*
+ * @max_write_sge: Maximum SGE elements per RDMA WRITE request.
+ * @max_read_sge:  Maximum SGE elements per RDMA READ request.
+ */
 struct ib_qp {
 	struct ib_device       *device;
 	struct ib_pd	       *pd;
 	struct ib_cq	       *send_cq;
 	struct ib_cq	       *recv_cq;
+	spinlock_t		mr_lock;
 	struct ib_srq	       *srq;
 	struct ib_xrcd	       *xrcd; /* XRC TGT QPs only */
 	struct list_head	xrcd_list;
+
 	/* count times opened, mcast attaches, flow attaches */
 	atomic_t		usecnt;
 	struct list_head	open_list;
@@ -1381,27 +1536,25 @@ struct ib_qp {
 	void                  (*event_handler)(struct ib_event *, void *);
 	void		       *qp_context;
 	u32			qp_num;
+	u32			max_write_sge;
+	u32			max_read_sge;
 	enum ib_qp_type		qp_type;
-	enum ib_qpg_type	qpg_type;
-	u8			port_num;
-};
-
-struct ib_dct {
-	struct ib_device       *device;
-	struct ib_uobject      *uobject;
-	struct ib_pd	       *pd;
-	struct ib_cq	       *cq;
-	struct ib_srq	       *srq;
-	u32			dct_num;
+	struct ib_rwq_ind_table *rwq_ind_tbl;
 };
 
 struct ib_mr {
 	struct ib_device  *device;
 	struct ib_pd	  *pd;
-	struct ib_uobject *uobject;
 	u32		   lkey;
 	u32		   rkey;
-	atomic_t	   usecnt; /* count number of MWs */
+	u64		   iova;
+	u32		   length;
+	unsigned int	   page_size;
+	bool		   need_inval;
+	union {
+		struct ib_uobject	*uobject;	/* user */
+		struct list_head	qp_entry;	/* FR */
+	};
 };
 
 struct ib_mw {
@@ -1440,14 +1593,15 @@ enum ib_flow_attr_type {
 enum ib_flow_spec_type {
 	/* L2 headers*/
 	IB_FLOW_SPEC_ETH	= 0x20,
-	IB_FLOW_SPEC_IB		= 0x21,
+	IB_FLOW_SPEC_IB		= 0x22,
 	/* L3 header*/
 	IB_FLOW_SPEC_IPV4	= 0x30,
+	IB_FLOW_SPEC_IPV6	= 0x31,
 	/* L4 headers*/
 	IB_FLOW_SPEC_TCP	= 0x40,
 	IB_FLOW_SPEC_UDP	= 0x41
 };
-
+#define IB_FLOW_SPEC_LAYER_MASK	0xF0
 #define IB_FLOW_SPEC_SUPPORT_LAYERS 4
 
 /* Flow steering rule priority is set according to it's domain.
@@ -1462,7 +1616,8 @@ enum ib_flow_domain {
 };
 
 enum ib_flow_flags {
-	IB_FLOW_ATTR_FLAGS_ALLOW_LOOP_BACK = 1
+	IB_FLOW_ATTR_FLAGS_DONT_TRAP = 1UL << 1, /* Continue match, no steal */
+	IB_FLOW_ATTR_FLAGS_RESERVED  = 1UL << 2  /* Must be last */
 };
 
 struct ib_flow_eth_filter {
@@ -1470,6 +1625,8 @@ struct ib_flow_eth_filter {
 	u8	src_mac[6];
 	__be16	ether_type;
 	__be16	vlan_tag;
+	/* Must be last */
+	u8	real_sz[0];
 };
 
 struct ib_flow_spec_eth {
@@ -1480,8 +1637,10 @@ struct ib_flow_spec_eth {
 };
 
 struct ib_flow_ib_filter {
-	__be32	l3_type_qpn;
-	u8	dst_gid[16];
+	__be16 dlid;
+	__u8   sl;
+	/* Must be last */
+	u8	real_sz[0];
 };
 
 struct ib_flow_spec_ib {
@@ -1491,9 +1650,22 @@ struct ib_flow_spec_ib {
 	struct ib_flow_ib_filter mask;
 };
 
+/* IPv4 header flags */
+enum ib_ipv4_flags {
+	IB_IPV4_DONT_FRAG = 0x2, /* Don't enable packet fragmentation */
+	IB_IPV4_MORE_FRAG = 0X4  /* For All fragmented packets except the
+				    last have this flag set */
+};
+
 struct ib_flow_ipv4_filter {
-	__be32 src_ip;
-	__be32 dst_ip;
+	__be32	src_ip;
+	__be32	dst_ip;
+	u8	proto;
+	u8	tos;
+	u8	ttl;
+	u8	flags;
+	/* Must be last */
+	u8	real_sz[0];
 };
 
 struct ib_flow_spec_ipv4 {
@@ -1503,9 +1675,29 @@ struct ib_flow_spec_ipv4 {
 	struct ib_flow_ipv4_filter mask;
 };
 
+struct ib_flow_ipv6_filter {
+	u8	src_ip[16];
+	u8	dst_ip[16];
+	__be32	flow_label;
+	u8	next_hdr;
+	u8	traffic_class;
+	u8	hop_limit;
+	/* Must be last */
+	u8	real_sz[0];
+};
+
+struct ib_flow_spec_ipv6 {
+	enum ib_flow_spec_type	   type;
+	u16			   size;
+	struct ib_flow_ipv6_filter val;
+	struct ib_flow_ipv6_filter mask;
+};
+
 struct ib_flow_tcp_udp_filter {
-	__be16 dst_port;
+	__be16	dst_port;
 	__be16	src_port;
+	/* Must be last */
+	u8	real_sz[0];
 };
 
 struct ib_flow_spec_tcp_udp {
@@ -1520,19 +1712,20 @@ union ib_flow_spec {
 		enum ib_flow_spec_type	type;
 		u16			size;
 	};
-	struct ib_flow_spec_ib ib;
-	struct ib_flow_spec_eth eth;
-	struct ib_flow_spec_ipv4 ipv4;
-	struct ib_flow_spec_tcp_udp tcp_udp;
+	struct ib_flow_spec_eth		eth;
+	struct ib_flow_spec_ib		ib;
+	struct ib_flow_spec_ipv4        ipv4;
+	struct ib_flow_spec_tcp_udp	tcp_udp;
+	struct ib_flow_spec_ipv6        ipv6;
 };
 
 struct ib_flow_attr {
 	enum ib_flow_attr_type type;
 	u16	     size;
 	u16	     priority;
+	u32	     flags;
 	u8	     num_of_specs;
 	u8	     port;
-	u32	     flags;
 	/* Following are the optional layers according to user request
 	 * struct ib_flow_spec_xxx
 	 * struct ib_flow_spec_yyy
@@ -1544,7 +1737,7 @@ struct ib_flow {
 	struct ib_uobject	*uobject;
 };
 
-struct ib_mad;
+struct ib_mad_hdr;
 struct ib_grh;
 
 enum ib_process_mad_flags {
@@ -1566,19 +1759,10 @@ struct ib_cache {
 	rwlock_t                lock;
 	struct ib_event_handler event_handler;
 	struct ib_pkey_cache  **pkey_cache;
-	struct ib_gid_cache   **gid_cache;
+	struct ib_gid_table   **gid_cache;
 	u8                     *lmc_cache;
 };
 
-enum verbs_values_mask {
-	IBV_VALUES_HW_CLOCK = 1 << 0
-};
-
-struct ib_device_values {
-	int values_mask;
-	uint64_t hwclock;
-};
-
 struct ib_dma_mapping_ops {
 	int		(*mapping_error)(struct ib_device *dev,
 					 u64 dma_addr);
@@ -1601,10 +1785,14 @@ struct ib_dma_mapping_ops {
 	void		(*unmap_sg)(struct ib_device *dev,
 				    struct scatterlist *sg, int nents,
 				    enum dma_data_direction direction);
-	u64		(*dma_address)(struct ib_device *dev,
-				       struct scatterlist *sg);
-	unsigned int	(*dma_len)(struct ib_device *dev,
-				   struct scatterlist *sg);
+	int		(*map_sg_attrs)(struct ib_device *dev,
+					struct scatterlist *sg, int nents,
+					enum dma_data_direction direction,
+					struct dma_attrs *attrs);
+	void		(*unmap_sg_attrs)(struct ib_device *dev,
+					  struct scatterlist *sg, int nents,
+					  enum dma_data_direction direction,
+					  struct dma_attrs *attrs);
 	void		(*sync_single_for_cpu)(struct ib_device *dev,
 					       u64 dma_handle,
 					       size_t size,
@@ -1623,8 +1811,13 @@ struct ib_dma_mapping_ops {
 };
 
 struct iw_cm_verbs;
-struct ib_exp_device_attr;
-struct ib_exp_qp_init_attr;
+
+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;
@@ -1636,36 +1829,92 @@ struct ib_device {
 
 	spinlock_t                    client_data_lock;
 	struct list_head              core_list;
+	/* Access to the client_data_list is protected by the client_data_lock
+	 * spinlock and the lists_rwsem read-write semaphore */
 	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;
 
 	struct iw_cm_verbs	     *iwcm;
 
-	int		           (*get_protocol_stats)(struct ib_device *device,
-							 union rdma_protocol_stats *stats);
+	/**
+	 * alloc_hw_stats - Allocate a struct rdma_hw_stats and fill in the
+	 *   driver initialized data.  The struct is kfree()'ed by the sysfs
+	 *   core when the device is removed.  A lifespan of -1 in the return
+	 *   struct tells the core to set a default lifespan.
+	 */
+	struct rdma_hw_stats      *(*alloc_hw_stats)(struct ib_device *device,
+						     u8 port_num);
+	/**
+	 * get_hw_stats - Fill in the counter value(s) in the stats struct.
+	 * @index - The index in the value array we wish to have updated, or
+	 *   num_counters if we want all stats updated
+	 * Return codes -
+	 *   < 0 - Error, no counters updated
+	 *   index - Updated the single counter pointed to by index
+	 *   num_counters - Updated all counters (will reset the timestamp
+	 *     and prevent further calls for lifespan milliseconds)
+	 * Drivers are allowed to update all counters in leiu of just the
+	 *   one given in index at their option
+	 */
+	int		           (*get_hw_stats)(struct ib_device *device,
+						   struct rdma_hw_stats *stats,
+						   u8 port, int index);
 	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);
 	enum rdma_link_layer	   (*get_link_layer)(struct ib_device *device,
 						     u8 port_num);
 	/* When calling get_netdev, the HW vendor's driver should return the
-	 * net device of device @device at port @port_num. The function
-	 * is called in rtnl_lock. The HW vendor's device driver must guarantee
-	 * to return NULL before the net device has reached
+	 * net device of device @device at port @port_num or NULL if such
+	 * a net device doesn't exist. The vendor driver should call dev_hold
+	 * on this net device. The HW vendor's device driver must guarantee
+	 * that this function returns NULL before the net device reaches
 	 * NETDEV_UNREGISTER_FINAL state.
 	 */
-	struct net_device	*(*get_netdev)(struct ib_device *device,
-					       u8 port_num);
+	struct net_device	  *(*get_netdev)(struct ib_device *device,
+						 u8 port_num);
 	int		           (*query_gid)(struct ib_device *device,
 						u8 port_num, int index,
 						union ib_gid *gid);
+	/* When calling add_gid, the HW vendor's driver should
+	 * add the gid of device @device at gid index @index of
+	 * port @port_num to be @gid. Meta-info of that gid (for example,
+	 * the network device related to this gid is available
+	 * at @attr. @context allows the HW vendor driver to store extra
+	 * information together with a GID entry. The HW vendor may allocate
+	 * memory to contain this information and store it in @context when a
+	 * new GID entry is written to. Params are consistent until the next
+	 * call of add_gid or delete_gid. The function should return 0 on
+	 * success or error otherwise. The function could be called
+	 * concurrently for different ports. This function is only called
+	 * when roce_gid_table is used.
+	 */
+	int		           (*add_gid)(struct ib_device *device,
+					      u8 port_num,
+					      unsigned int index,
+					      const union ib_gid *gid,
+					      const struct ib_gid_attr *attr,
+					      void **context);
+	/* When calling del_gid, the HW vendor's driver should delete the
+	 * gid of device @device at gid index @index of port @port_num.
+	 * Upon the deletion of a GID entry, the HW vendor must free any
+	 * allocated memory. The caller will clear @context afterwards.
+	 * This function is only called when roce_gid_table is used.
+	 */
+	int		           (*del_gid)(struct ib_device *device,
+					      u8 port_num,
+					      unsigned int index,
+					      void **context);
 	int		           (*query_pkey)(struct ib_device *device,
 						 u8 port_num, u16 index, u16 *pkey);
 	int		           (*modify_device)(struct ib_device *device,
@@ -1722,12 +1971,11 @@ struct ib_device {
 						struct ib_recv_wr *recv_wr,
 						struct ib_recv_wr **bad_recv_wr);
 	struct ib_cq *             (*create_cq)(struct ib_device *device,
-						struct ib_cq_init_attr *attr,
+						const struct ib_cq_init_attr *attr,
 						struct ib_ucontext *context,
 						struct ib_udata *udata);
-	int                        (*modify_cq)(struct ib_cq *cq,
-						struct ib_cq_attr *cq_attr,
-						int cq_attr_mask);
+	int                        (*modify_cq)(struct ib_cq *cq, u16 cq_count,
+						u16 cq_period);
 	int                        (*destroy_cq)(struct ib_cq *cq);
 	int                        (*resize_cq)(struct ib_cq *cq, int cqe,
 						struct ib_udata *udata);
@@ -1740,40 +1988,29 @@ struct ib_device {
 						      int wc_cnt);
 	struct ib_mr *             (*get_dma_mr)(struct ib_pd *pd,
 						 int mr_access_flags);
-	struct ib_mr *             (*reg_phys_mr)(struct ib_pd *pd,
-						  struct ib_phys_buf *phys_buf_array,
-						  int num_phys_buf,
-						  int mr_access_flags,
-						  u64 *iova_start);
 	struct ib_mr *             (*reg_user_mr)(struct ib_pd *pd,
 						  u64 start, u64 length,
 						  u64 virt_addr,
 						  int mr_access_flags,
-						  struct ib_udata *udata,
-							int mr_id);
-	int                        (*query_mr)(struct ib_mr *mr,
-					       struct ib_mr_attr *mr_attr);
-	int                        (*dereg_mr)(struct ib_mr *mr);
-	int                        (*destroy_mr)(struct ib_mr *mr);
-	struct ib_mr *		   (*create_mr)(struct ib_pd *pd,
-						struct ib_mr_init_attr *mr_init_attr);
-	struct ib_mr *		   (*alloc_fast_reg_mr)(struct ib_pd *pd,
-					       int max_page_list_len);
-	struct ib_fast_reg_page_list * (*alloc_fast_reg_page_list)(struct ib_device *device,
-								   int page_list_len);
-	void			   (*free_fast_reg_page_list)(struct ib_fast_reg_page_list *page_list);
-	int                        (*rereg_phys_mr)(struct ib_mr *mr,
-						    int mr_rereg_mask,
-						    struct ib_pd *pd,
-						    struct ib_phys_buf *phys_buf_array,
-						    int num_phys_buf,
+						  struct ib_udata *udata);
+	int			   (*rereg_user_mr)(struct ib_mr *mr,
+						    int flags,
+						    u64 start, u64 length,
+						    u64 virt_addr,
 						    int mr_access_flags,
-						    u64 *iova_start);
+						    struct ib_pd *pd,
+						    struct ib_udata *udata);
+	int                        (*dereg_mr)(struct ib_mr *mr);
+	struct ib_mr *		   (*alloc_mr)(struct ib_pd *pd,
+					       enum ib_mr_type mr_type,
+					       u32 max_num_sg);
+	int                        (*map_mr_sg)(struct ib_mr *mr,
+						struct scatterlist *sg,
+						int sg_nents,
+						unsigned int *sg_offset);
 	struct ib_mw *             (*alloc_mw)(struct ib_pd *pd,
-					       enum ib_mw_type type);
-	int                        (*bind_mw)(struct ib_qp *qp,
-					      struct ib_mw *mw,
-					      struct ib_mw_bind *mw_bind);
+					       enum ib_mw_type type,
+					       struct ib_udata *udata);
 	int                        (*dealloc_mw)(struct ib_mw *mw);
 	struct ib_fmr *	           (*alloc_fmr)(struct ib_pd *pd,
 						int mr_access_flags,
@@ -1792,10 +2029,13 @@ 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);
@@ -1807,17 +2047,29 @@ struct ib_device {
 	int			   (*destroy_flow)(struct ib_flow *flow_id);
 	int			   (*check_mr_status)(struct ib_mr *mr, u32 check_mask,
 						      struct ib_mr_status *mr_status);
-
-	unsigned long		   (*get_unmapped_area)(struct file *file,
-					unsigned long addr,
-					unsigned long len, unsigned long pgoff,
-					unsigned long flags);
-	int			   (*ioctl)(struct ib_ucontext *context,
-					    unsigned int cmd,
-					    unsigned long arg);
-	int			   (*query_values)(struct ib_device *device,
-					    int q_values,
-					    struct ib_device_values *values);
+	void			   (*disassociate_ucontext)(struct ib_ucontext *ibcontext);
+	void			   (*drain_rq)(struct ib_qp *qp);
+	void			   (*drain_sq)(struct ib_qp *qp);
+	int			   (*set_vf_link_state)(struct ib_device *device, int vf, u8 port,
+							int state);
+	int			   (*get_vf_config)(struct ib_device *device, int vf, u8 port,
+						   struct ifla_vf_info *ivf);
+	int			   (*get_vf_stats)(struct ib_device *device, int vf, u8 port,
+						   struct ifla_vf_stats *stats);
+	int			   (*set_vf_guid)(struct ib_device *device, int vf, u8 port, u64 guid,
+						  int type);
+	struct ib_wq *		   (*create_wq)(struct ib_pd *pd,
+						struct ib_wq_init_attr *init_attr,
+						struct ib_udata *udata);
+	int			   (*destroy_wq)(struct ib_wq *wq);
+	int			   (*modify_wq)(struct ib_wq *wq,
+						struct ib_wq_attr *attr,
+						u32 wq_attr_mask,
+						struct ib_udata *udata);
+	struct ib_rwq_ind_table *  (*create_rwq_ind_table)(struct ib_device *device,
+							   struct ib_rwq_ind_table_init_attr *init_attr,
+							   struct ib_udata *udata);
+	int                        (*destroy_rwq_ind_table)(struct ib_rwq_ind_table *wq_ind_table);
 	struct ib_dma_mapping_ops   *dma_ops;
 
 	struct module               *owner;
@@ -1835,44 +2087,61 @@ struct ib_device {
 	u64			     uverbs_cmd_mask;
 	u64			     uverbs_ex_cmd_mask;
 
-	char			     node_desc[64];
+	char			     node_desc[IB_DEVICE_NODE_DESC_MAX];
 	__be64			     node_guid;
 	u32			     local_dma_lkey;
+	u16                          is_switch:1;
 	u8                           node_type;
 	u8                           phys_port_cnt;
-	int			     cmd_perf;
-	u64			     cmd_avg;
-	u32			     cmd_n;
-	spinlock_t		     cmd_perf_lock;
+	struct ib_device_attr        attrs;
+	struct attribute_group	     *hw_stats_ag;
+	struct rdma_hw_stats         *hw_stats;
 
-	/*
-	 * Experimental data and functions
+	/**
+	 * 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			(*exp_query_device)(struct ib_device *device,
-						    struct ib_exp_device_attr *device_attr);
-	struct ib_qp *		(*exp_create_qp)(struct ib_pd *pd,
-						 struct ib_exp_qp_init_attr *qp_init_attr,
-						 struct ib_udata *udata);
-	struct ib_dct *		(*exp_create_dct)(struct ib_pd *pd,
-					      struct ib_dct_init_attr *attr,
-					      struct ib_udata *udata);
-	int			(*exp_destroy_dct)(struct ib_dct *dct);
-	int			(*exp_query_dct)(struct ib_dct *dct, struct ib_dct_attr *attr);
-
-	u64			uverbs_exp_cmd_mask;
+	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
+	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
 };
 
 struct ib_client {
 	char  *name;
 	void (*add)   (struct ib_device *);
-	void (*remove)(struct ib_device *);
+	void (*remove)(struct ib_device *, void *client_data);
 
+	/* Returns the net_dev belonging to this ib_client and matching the
+	 * given parameters.
+	 * @dev:	 An RDMA device that the net_dev use for communication.
+	 * @port:	 A physical port number on the RDMA device.
+	 * @pkey:	 P_Key that the net_dev uses if applicable.
+	 * @gid:	 A GID that the net_dev uses to communicate.
+	 * @addr:	 An IP address the net_dev is configured with.
+	 * @client_data: The device's client data set by ib_set_client_data().
+	 *
+	 * An ib_client that implements a net_dev on top of RDMA devices
+	 * (such as IP over IB) should implement this callback, allowing the
+	 * rdma_cm module to find the right net_dev for a given request.
+	 *
+	 * The caller is responsible for calling dev_put on the returned
+	 * netdev. */
+	struct net_device *(*get_net_dev_by_params)(
+			struct ib_device *dev,
+			u8 port,
+			u16 pkey,
+			const union ib_gid *gid,
+			const struct sockaddr *addr,
+			void *client_data);
 	struct list_head list;
 };
 
 struct ib_device *ib_alloc_device(size_t size);
 void ib_dealloc_device(struct ib_device *device);
 
+void ib_get_device_fw_str(struct ib_device *device, char *str, size_t str_len);
+
 int ib_register_device(struct ib_device *device,
 		       int (*port_callback)(struct ib_device *,
 					    u8, struct kobject *));
@@ -1887,12 +2156,32 @@ void  ib_set_client_data(struct ib_device *device, struct ib_client *client,
 
 static inline int ib_copy_from_udata(void *dest, struct ib_udata *udata, size_t len)
 {
-	return udata->ops->copy_from(dest, udata, len);
+	return copy_from_user(dest, udata->inbuf, len) ? -EFAULT : 0;
 }
 
 static inline int ib_copy_to_udata(struct ib_udata *udata, void *src, size_t len)
 {
-	return udata->ops->copy_to(udata, src, len);
+	return copy_to_user(udata->outbuf, src, len) ? -EFAULT : 0;
+}
+
+static inline bool ib_is_udata_cleared(struct ib_udata *udata,
+				       size_t offset,
+				       size_t len)
+{
+	const void __user *p = (const char __user *)udata->inbuf + offset;
+	bool ret;
+	u8 *buf;
+
+	if (len > USHRT_MAX)
+		return false;
+
+	buf = memdup_user(p, len);
+	if (IS_ERR(buf))
+		return false;
+
+	ret = !memchr_inv(buf, 0, len);
+	kfree(buf);
+	return ret;
 }
 
 /**
@@ -1919,17 +2208,330 @@ int ib_register_event_handler  (struct ib_event_handler *event_handler);
 int ib_unregister_event_handler(struct ib_event_handler *event_handler);
 void ib_dispatch_event(struct ib_event *event);
 
-int ib_query_device(struct ib_device *device,
-		    struct ib_device_attr *device_attr);
-
 int ib_query_port(struct ib_device *device,
 		  u8 port_num, struct ib_port_attr *port_attr);
 
 enum rdma_link_layer rdma_port_get_link_layer(struct ib_device *device,
 					       u8 port_num);
 
+/**
+ * rdma_cap_ib_switch - Check if the device is IB switch
+ * @device: Device to check
+ *
+ * Device driver is responsible for setting is_switch bit on
+ * in ib_device structure at init time.
+ *
+ * Return: true if the device is IB switch.
+ */
+static inline bool rdma_cap_ib_switch(const struct ib_device *device)
+{
+	return device->is_switch;
+}
+
+/**
+ * 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 rdma_cap_ib_switch(device) ? 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 rdma_cap_ib_switch(device) ? 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 | RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP);
+}
+
+static inline bool rdma_protocol_roce_udp_encap(const struct ib_device *device, u8 port_num)
+{
+	return device->port_immutable[port_num].core_cap_flags & RDMA_CORE_CAP_PROT_ROCE_UDP_ENCAP;
+}
+
+static inline bool rdma_protocol_roce_eth_encap(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 rdma_protocol_ib(device, port_num) ||
+		rdma_protocol_roce(device, port_num);
+}
+
+/**
+ * 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_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;
+}
+
+/**
+ * rdma_cap_roce_gid_table - Check if the port of device uses roce_gid_table
+ * @device: Device to check
+ * @port_num: Port number to check
+ *
+ * RoCE GID table mechanism manages the various GIDs for a device.
+ *
+ * NOTE: if allocating the port's GID table has failed, this call will still
+ * return true, but any RoCE GID table API will fail.
+ *
+ * Return: true if the port uses RoCE GID table mechanism in order to manage
+ * its GIDs.
+ */
+static inline bool rdma_cap_roce_gid_table(const struct ib_device *device,
+					   u8 port_num)
+{
+	return rdma_protocol_roce(device, port_num) &&
+		device->add_gid && device->del_gid;
+}
+
+/*
+ * Check if the device supports READ W/ INVALIDATE.
+ */
+static inline bool rdma_cap_read_inv(struct ib_device *dev, u32 port_num)
+{
+	/*
+	 * iWarp drivers must support READ W/ INVALIDATE.  No other protocol
+	 * has support for it yet.
+	 */
+	return rdma_protocol_iwarp(dev, port_num);
+}
+
 int ib_query_gid(struct ib_device *device,
-		 u8 port_num, int index, union ib_gid *gid);
+		 u8 port_num, int index, union ib_gid *gid,
+		 struct ib_gid_attr *attr);
+
+int ib_set_vf_link_state(struct ib_device *device, int vf, u8 port,
+			 int state);
+int ib_get_vf_config(struct ib_device *device, int vf, u8 port,
+		     struct ifla_vf_info *info);
+int ib_get_vf_stats(struct ib_device *device, int vf, u8 port,
+		    struct ifla_vf_stats *stats);
+int ib_set_vf_guid(struct ib_device *device, int vf, u8 port, u64 guid,
+		   int type);
 
 int ib_query_pkey(struct ib_device *device,
 		  u8 port_num, u16 index, u16 *pkey);
@@ -1943,25 +2545,30 @@ int ib_modify_port(struct ib_device *device,
 		   struct ib_port_modify *port_modify);
 
 int ib_find_gid(struct ib_device *device, union ib_gid *gid,
+		enum ib_gid_type gid_type, struct net_device *ndev,
 		u8 *port_num, u16 *index);
 
 int ib_find_pkey(struct ib_device *device,
 		 u8 port_num, u16 pkey, u16 *index);
 
-/**
- * ib_alloc_pd - Allocates an unused protection domain.
- * @device: The device on which to allocate the protection domain.
- *
- * A protection domain object provides an association between QPs, shared
- * receive queues, address handles, memory regions, and memory windows.
- */
-struct ib_pd *ib_alloc_pd(struct ib_device *device);
+enum ib_pd_flags {
+	/*
+	 * Create a memory registration for all memory in the system and place
+	 * the rkey for it into pd->unsafe_global_rkey.  This can be used by
+	 * ULPs to avoid the overhead of dynamic MRs.
+	 *
+	 * This flag is generally considered unsafe and must only be used in
+	 * extremly trusted environments.  Every use of it will log a warning
+	 * in the kernel log.
+	 */
+	IB_PD_UNSAFE_GLOBAL_RKEY	= 0x01,
+};
 
-/**
- * ib_dealloc_pd - Deallocates a protection domain.
- * @pd: The protection domain to deallocate.
- */
-int ib_dealloc_pd(struct ib_pd *pd);
+struct ib_pd *__ib_alloc_pd(struct ib_device *device, unsigned int flags,
+		const char *caller);
+#define ib_alloc_pd(device, flags) \
+	__ib_alloc_pd((device), (flags), __func__)
+void ib_dealloc_pd(struct ib_pd *pd);
 
 /**
  * ib_create_ah - Creates an address handle for the given address vector.
@@ -1984,8 +2591,9 @@ 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
@@ -1999,8 +2607,8 @@ 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
@@ -2187,6 +2795,10 @@ static inline int ib_post_recv(struct ib_qp *qp,
 	return qp->device->post_recv(qp, recv_wr, bad_recv_wr);
 }
 
+struct ib_cq *ib_alloc_cq(struct ib_device *dev, void *private,
+		int nr_cqe, int comp_vector, enum ib_poll_context poll_ctx);
+void ib_free_cq(struct ib_cq *cq);
+
 /**
  * ib_create_cq - Creates a CQ on the specified device.
  * @device: The device on which to create the CQ.
@@ -2196,16 +2808,15 @@ 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.
@@ -2217,16 +2828,13 @@ struct ib_cq *ib_create_cq(struct ib_device *device,
 int ib_resize_cq(struct ib_cq *cq, int cqe);
 
 /**
- * ib_modify_cq - Modifies the attributes for the specified CQ and then
- *   transitions the CQ to the given state.
+ * ib_modify_cq - Modifies moderation params of the CQ
  * @cq: The CQ to modify.
- * @cq_attr: specifies the CQ attributes to modify.
- * @cq_attr_mask: A bit-mask used to specify which attributes of the CQ
- *   are being modified.
+ * @cq_count: number of CQEs that will trigger an event
+ * @cq_period: max period of time in usec before triggering an event
+ *
  */
-int ib_modify_cq(struct ib_cq *cq,
-		 struct ib_cq_attr *cq_attr,
-		 int cq_attr_mask);
+int ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period);
 
 /**
  * ib_destroy_cq - Destroys the specified CQ.
@@ -2312,18 +2920,6 @@ static inline int ib_req_ncomp_notif(struct ib_cq *cq, int wc_cnt)
 }
 
 /**
- * ib_get_dma_mr - Returns a memory region for system memory that is
- *   usable for DMA.
- * @pd: The protection domain associated with the memory region.
- * @mr_access_flags: Specifies the memory access rights.
- *
- * Note that the ib_dma_*() functions defined below must be used
- * to create/destroy addresses used with the Lkey or Rkey returned
- * by ib_get_dma_mr().
- */
-struct ib_mr *ib_get_dma_mr(struct ib_pd *pd, int mr_access_flags);
-
-/**
  * ib_dma_mapping_error - check a DMA addr for error
  * @dev: The device for which the dma_addr was created
  * @dma_addr: The DMA address to check
@@ -2371,19 +2967,19 @@ static inline void ib_dma_unmap_single(struct ib_device *dev,
 static inline u64 ib_dma_map_single_attrs(struct ib_device *dev,
 					  void *cpu_addr, size_t size,
 					  enum dma_data_direction direction,
-					  struct dma_attrs *attrs)
+					  struct dma_attrs *dma_attrs)
 {
 	return dma_map_single_attrs(dev->dma_device, cpu_addr, size,
-				    direction, attrs);
+				    direction, dma_attrs);
 }
 
 static inline void ib_dma_unmap_single_attrs(struct ib_device *dev,
 					     u64 addr, size_t size,
 					     enum dma_data_direction direction,
-					     struct dma_attrs *attrs)
+					     struct dma_attrs *dma_attrs)
 {
 	return dma_unmap_single_attrs(dev->dma_device, addr, size,
-				      direction, attrs);
+				      direction, dma_attrs);
 }
 
 /**
@@ -2458,28 +3054,39 @@ static inline void ib_dma_unmap_sg(struct ib_device *dev,
 static inline int ib_dma_map_sg_attrs(struct ib_device *dev,
 				      struct scatterlist *sg, int nents,
 				      enum dma_data_direction direction,
-				      struct dma_attrs *attrs)
+				      struct dma_attrs *dma_attrs)
 {
-	return dma_map_sg_attrs(dev->dma_device, sg, nents, direction, attrs);
+	if (dev->dma_ops)
+		return dev->dma_ops->map_sg_attrs(dev, sg, nents, direction,
+						  dma_attrs);
+	else
+		return dma_map_sg_attrs(dev->dma_device, sg, nents, direction,
+					dma_attrs);
 }
 
 static inline void ib_dma_unmap_sg_attrs(struct ib_device *dev,
 					 struct scatterlist *sg, int nents,
 					 enum dma_data_direction direction,
-					 struct dma_attrs *attrs)
+					 struct dma_attrs *dma_attrs)
 {
-	dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction, attrs);
+	if (dev->dma_ops)
+		return dev->dma_ops->unmap_sg_attrs(dev, sg, nents, direction,
+						  dma_attrs);
+	else
+		dma_unmap_sg_attrs(dev->dma_device, sg, nents, direction,
+				   dma_attrs);
 }
 /**
  * ib_sg_dma_address - Return the DMA address from a scatter/gather entry
  * @dev: The device for which the DMA addresses were created
  * @sg: The scatter/gather entry
+ *
+ * Note: this function is obsolete. To do: change all occurrences of
+ * ib_sg_dma_address() into sg_dma_address().
  */
 static inline u64 ib_sg_dma_address(struct ib_device *dev,
 				    struct scatterlist *sg)
 {
-	if (dev->dma_ops)
-		return dev->dma_ops->dma_address(dev, sg);
 	return sg_dma_address(sg);
 }
 
@@ -2487,12 +3094,13 @@ static inline u64 ib_sg_dma_address(struct ib_device *dev,
  * ib_sg_dma_len - Return the DMA length from a scatter/gather entry
  * @dev: The device for which the DMA addresses were created
  * @sg: The scatter/gather entry
+ *
+ * Note: this function is obsolete. To do: change all occurrences of
+ * ib_sg_dma_len() into sg_dma_len().
  */
 static inline unsigned int ib_sg_dma_len(struct ib_device *dev,
 					 struct scatterlist *sg)
 {
-	if (dev->dma_ops)
-		return dev->dma_ops->dma_len(dev, sg);
 	return sg_dma_len(sg);
 }
 
@@ -2574,59 +3182,6 @@ static inline void ib_dma_free_coherent(struct ib_device *dev,
 }
 
 /**
- * ib_reg_phys_mr - Prepares a virtually addressed memory region for use
- *   by an HCA.
- * @pd: The protection domain associated assigned to the registered region.
- * @phys_buf_array: Specifies a list of physical buffers to use in the
- *   memory region.
- * @num_phys_buf: Specifies the size of the phys_buf_array.
- * @mr_access_flags: Specifies the memory access rights.
- * @iova_start: The offset of the region's starting I/O virtual address.
- */
-struct ib_mr *ib_reg_phys_mr(struct ib_pd *pd,
-			     struct ib_phys_buf *phys_buf_array,
-			     int num_phys_buf,
-			     int mr_access_flags,
-			     u64 *iova_start);
-
-/**
- * ib_rereg_phys_mr - Modifies the attributes of an existing memory region.
- *   Conceptually, this call performs the functions deregister memory region
- *   followed by register physical memory region.  Where possible,
- *   resources are reused instead of deallocated and reallocated.
- * @mr: The memory region to modify.
- * @mr_rereg_mask: A bit-mask used to indicate which of the following
- *   properties of the memory region are being modified.
- * @pd: If %IB_MR_REREG_PD is set in mr_rereg_mask, this field specifies
- *   the new protection domain to associated with the memory region,
- *   otherwise, this parameter is ignored.
- * @phys_buf_array: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
- *   field specifies a list of physical buffers to use in the new
- *   translation, otherwise, this parameter is ignored.
- * @num_phys_buf: If %IB_MR_REREG_TRANS is set in mr_rereg_mask, this
- *   field specifies the size of the phys_buf_array, otherwise, this
- *   parameter is ignored.
- * @mr_access_flags: If %IB_MR_REREG_ACCESS is set in mr_rereg_mask, this
- *   field specifies the new memory access rights, otherwise, this
- *   parameter is ignored.
- * @iova_start: The offset of the region's starting I/O virtual address.
- */
-int ib_rereg_phys_mr(struct ib_mr *mr,
-		     int mr_rereg_mask,
-		     struct ib_pd *pd,
-		     struct ib_phys_buf *phys_buf_array,
-		     int num_phys_buf,
-		     int mr_access_flags,
-		     u64 *iova_start);
-
-/**
- * ib_query_mr - Retrieves information about a specific memory region.
- * @mr: The memory region to retrieve information about.
- * @mr_attr: The attributes of the specified memory region.
- */
-int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
-
-/**
  * ib_dereg_mr - Deregisters a memory region and removes it from the
  *   HCA translation table.
  * @mr: The memory region to deregister.
@@ -2635,60 +3190,9 @@ int ib_query_mr(struct ib_mr *mr, struct ib_mr_attr *mr_attr);
  */
 int ib_dereg_mr(struct ib_mr *mr);
 
-
-/**
- * ib_create_mr - Allocates a memory region that may be used for
- *     signature handover operations.
- * @pd: The protection domain associated with the region.
- * @mr_init_attr: memory region init attributes.
- */
-struct ib_mr *ib_create_mr(struct ib_pd *pd,
-			   struct ib_mr_init_attr *mr_init_attr);
-
-/**
- * ib_destroy_mr - Destroys a memory region that was created using
- *     ib_create_mr and removes it from HW translation tables.
- * @mr: The memory region to destroy.
- *
- * This function can fail, if the memory region has memory windows bound to it.
- */
-int ib_destroy_mr(struct ib_mr *mr);
-
-/**
- * ib_alloc_fast_reg_mr - Allocates memory region usable with the
- *   IB_WR_FAST_REG_MR send work request.
- * @pd: The protection domain associated with the region.
- * @max_page_list_len: requested max physical buffer list length to be
- *   used with fast register work requests for this MR.
- */
-struct ib_mr *ib_alloc_fast_reg_mr(struct ib_pd *pd, int max_page_list_len);
-
-/**
- * ib_alloc_fast_reg_page_list - Allocates a page list array
- * @device - ib device pointer.
- * @page_list_len - size of the page list array to be allocated.
- *
- * This allocates and returns a struct ib_fast_reg_page_list * and a
- * page_list array that is at least page_list_len in size.  The actual
- * size is returned in max_page_list_len.  The caller is responsible
- * for initializing the contents of the page_list array before posting
- * a send work request with the IB_WC_FAST_REG_MR opcode.
- *
- * The page_list array entries must be translated using one of the
- * ib_dma_*() functions just like the addresses passed to
- * ib_map_phys_fmr().  Once the ib_post_send() is issued, the struct
- * ib_fast_reg_page_list must not be modified by the caller until the
- * IB_WC_FAST_REG_MR work request completes.
- */
-struct ib_fast_reg_page_list *ib_alloc_fast_reg_page_list(
-				struct ib_device *device, int page_list_len);
-
-/**
- * ib_free_fast_reg_page_list - Deallocates a previously allocated
- *   page list array.
- * @page_list - struct ib_fast_reg_page_list pointer to be deallocated.
- */
-void ib_free_fast_reg_page_list(struct ib_fast_reg_page_list *page_list);
+struct ib_mr *ib_alloc_mr(struct ib_pd *pd,
+			  enum ib_mr_type mr_type,
+			  u32 max_num_sg);
 
 /**
  * ib_update_fast_reg_key - updates the key portion of the fast_reg MR
@@ -2714,42 +3218,6 @@ static inline u32 ib_inc_rkey(u32 rkey)
 }
 
 /**
- * ib_alloc_mw - Allocates a memory window.
- * @pd: The protection domain associated with the memory window.
- * @type: The type of the memory window (1 or 2).
- */
-struct ib_mw *ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type);
-
-/**
- * ib_bind_mw - Posts a work request to the send queue of the specified
- *   QP, which binds the memory window to the given address range and
- *   remote access attributes.
- * @qp: QP to post the bind work request on.
- * @mw: The memory window to bind.
- * @mw_bind: Specifies information about the memory window, including
- *   its address range, remote access rights, and associated memory region.
- *
- * If there is no immediate error, the function will update the rkey member
- * of the mw parameter to its new value. The bind operation can still fail
- * asynchronously.
- */
-static inline int ib_bind_mw(struct ib_qp *qp,
-			     struct ib_mw *mw,
-			     struct ib_mw_bind *mw_bind)
-{
-	/* XXX reference counting in corresponding MR? */
-	return mw->device->bind_mw ?
-		mw->device->bind_mw(qp, mw, mw_bind) :
-		-ENOSYS;
-}
-
-/**
- * ib_dealloc_mw - Deallocates a memory window.
- * @mw: The memory window to deallocate.
- */
-int ib_dealloc_mw(struct ib_mw *mw);
-
-/**
  * ib_alloc_fmr - Allocates a unmapped fast memory region.
  * @pd: The protection domain associated with the unmapped region.
  * @mr_access_flags: Specifies the memory access rights.
@@ -2826,47 +3294,6 @@ struct ib_flow *ib_create_flow(struct ib_qp *qp,
 			       struct ib_flow_attr *flow_attr, int domain);
 int ib_destroy_flow(struct ib_flow *flow_id);
 
-struct ib_dct *ib_create_dct(struct ib_pd *pd, struct ib_dct_init_attr *attr,
-			     struct ib_udata *udata);
-int ib_destroy_dct(struct ib_dct *dct);
-int ib_query_dct(struct ib_dct *dct, struct ib_dct_attr *attr);
-
-int ib_query_values(struct ib_device *device,
-                   int q_values, struct ib_device_values *values);
-
-static inline void ib_active_speed_enum_to_rate(u8 active_speed,
-						int *rate,
-						char **speed)
-{
-	switch (active_speed) {
-	case IB_SPEED_DDR:
-		*speed = " DDR";
-		*rate = 50;
-		break;
-	case IB_SPEED_QDR:
-		*speed = " QDR";
-		*rate = 100;
-		break;
-	case IB_SPEED_FDR10:
-		*speed = " FDR10";
-		*rate = 100;
-		break;
-	case IB_SPEED_FDR:
-		*speed = " FDR";
-		*rate = 140;
-		break;
-	case IB_SPEED_EDR:
-		*speed = " EDR";
-		*rate = 250;
-		break;
-	case IB_SPEED_SDR:
-	default:		/* default to SDR for invalid rates */
-		*rate = 25;
-		break;
-	}
-
-}
-
 static inline int ib_check_mr_access(int flags)
 {
 	/*
@@ -2895,4 +3322,38 @@ static inline int ib_check_mr_access(int flags)
 int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
 		       struct ib_mr_status *mr_status);
 
+struct net_device *ib_get_net_dev_by_params(struct ib_device *dev, u8 port,
+					    u16 pkey, const union ib_gid *gid,
+					    const struct sockaddr *addr);
+struct ib_wq *ib_create_wq(struct ib_pd *pd,
+			   struct ib_wq_init_attr *init_attr);
+int ib_destroy_wq(struct ib_wq *wq);
+int ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *attr,
+		 u32 wq_attr_mask);
+struct ib_rwq_ind_table *ib_create_rwq_ind_table(struct ib_device *device,
+						 struct ib_rwq_ind_table_init_attr*
+						 wq_ind_table_init_attr);
+int ib_destroy_rwq_ind_table(struct ib_rwq_ind_table *wq_ind_table);
+
+int ib_map_mr_sg(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
+		 unsigned int *sg_offset, unsigned int page_size);
+
+static inline int
+ib_map_mr_sg_zbva(struct ib_mr *mr, struct scatterlist *sg, int sg_nents,
+		  unsigned int *sg_offset, unsigned int page_size)
+{
+	int n;
+
+	n = ib_map_mr_sg(mr, sg, sg_nents, sg_offset, page_size);
+	mr->iova = 0;
+
+	return n;
+}
+
+int ib_sg_to_pages(struct ib_mr *mr, struct scatterlist *sgl, int sg_nents,
+		unsigned int *sg_offset, int (*set_page)(struct ib_mr *, u64));
+
+void ib_drain_rq(struct ib_qp *qp);
+void ib_drain_sq(struct ib_qp *qp);
+void ib_drain_qp(struct ib_qp *qp);
 #endif /* IB_VERBS_H */
diff --git a/sys/ofed/include/rdma/ib_verbs_exp.h b/sys/ofed/include/rdma/ib_verbs_exp.h
deleted file mode 100644
index ca5b84b5c76d..000000000000
--- a/sys/ofed/include/rdma/ib_verbs_exp.h
+++ /dev/null
@@ -1,100 +0,0 @@
-/*
- * Copyright (c) 2004 Mellanox Technologies Ltd.  All rights reserved.
- * Copyright (c) 2004 Infinicon Corporation.  All rights reserved.
- * Copyright (c) 2004 Intel Corporation.  All rights reserved.
- * Copyright (c) 2004 Topspin Corporation.  All rights reserved.
- * Copyright (c) 2004 Voltaire Corporation.  All rights reserved.
- * Copyright (c) 2005 Sun Microsystems, Inc. All rights reserved.
- * Copyright (c) 2005, 2006, 2007 Cisco Systems.  All rights reserved.
- *
- * This software is available to you under a choice of one of two
- * licenses.  You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- *     Redistribution and use in source and binary forms, with or
- *     without modification, are permitted provided that the following
- *     conditions are met:
- *
- *      - Redistributions of source code must retain the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer.
- *
- *      - Redistributions in binary form must reproduce the above
- *        copyright notice, this list of conditions and the following
- *        disclaimer in the documentation and/or other materials
- *        provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#ifndef IB_VERBS_EXP_H
-#define IB_VERBS_EXP_H
-
-#include <rdma/ib_verbs.h>
-
-
-enum ib_exp_device_cap_flags2 {
-	IB_EXP_DEVICE_DC_TRANSPORT		= 1 << 0,
-	IB_EXP_DEVICE_QPG			= 1 << 1,
-	IB_EXP_DEVICE_UD_RSS			= 1 << 2,
-	IB_EXP_DEVICE_UD_TSS			= 1 << 3
-};
-
-enum ib_exp_device_attr_comp_mask {
-	IB_EXP_DEVICE_ATTR_WITH_TIMESTAMP_MASK	= 1ULL << 1,
-	IB_EXP_DEVICE_ATTR_WITH_HCA_CORE_CLOCK	= 1ULL << 2,
-	IB_EXP_DEVICE_ATTR_CAP_FLAGS2		= 1ULL << 3,
-	IB_EXP_DEVICE_ATTR_DC_REQ_RD		= 1ULL << 4,
-	IB_EXP_DEVICE_ATTR_DC_RES_RD		= 1ULL << 5,
-	IB_EXP_DEVICE_ATTR_INLINE_RECV_SZ	= 1ULL << 6,
-	IB_EXP_DEVICE_ATTR_RSS_TBL_SZ		= 1ULL << 7,
-};
-
-struct ib_exp_device_attr {
-	struct ib_device_attr	base;
-	/* Use IB_EXP_DEVICE_ATTR_... for exp_comp_mask */
-	uint32_t		exp_comp_mask;
-	uint64_t		device_cap_flags2;
-	uint32_t		dc_rd_req;
-	uint32_t		dc_rd_res;
-	uint32_t		inline_recv_sz;
-	uint32_t		max_rss_tbl_sz;
-};
-
-struct ib_exp_qp_init_attr {
-	void                  (*event_handler)(struct ib_event *, void *);
-	void		       *qp_context;
-	struct ib_cq	       *send_cq;
-	struct ib_cq	       *recv_cq;
-	struct ib_srq	       *srq;
-	struct ib_xrcd	       *xrcd;     /* XRC TGT QPs only */
-	struct ib_qp_cap	cap;
-	union {
-		struct ib_qp *qpg_parent; /* see qpg_type */
-		struct ib_qpg_init_attrib parent_attrib;
-	};
-	enum ib_sig_type	sq_sig_type;
-	enum ib_qp_type		qp_type;
-	enum ib_qp_create_flags	create_flags;
-	enum ib_qpg_type	qpg_type;
-	u8			port_num; /* special QP types only */
-	u32			max_inl_recv;
-};
-
-
-int ib_exp_query_device(struct ib_device *device,
-			struct ib_exp_device_attr *device_attr);
-
-
-
-
-#endif /* IB_VERBS_EXP_H */
diff --git a/sys/ofed/include/rdma/iw_cm.h b/sys/ofed/include/rdma/iw_cm.h
index a246e6176c6c..1a919be827a7 100644
--- a/sys/ofed/include/rdma/iw_cm.h
+++ b/sys/ofed/include/rdma/iw_cm.h
@@ -1,7 +1,6 @@
 /*
  * Copyright (c) 2005 Network Appliance, Inc. All rights reserved.
  * Copyright (c) 2005 Open Grid Computing, Inc. All rights reserved.
- * Copyright (c) 2016 Chelsio Communications.  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
@@ -50,12 +49,11 @@ enum iw_cm_event_type {
 struct iw_cm_event {
 	enum iw_cm_event_type event;
 	int			 status;
-	struct sockaddr_in local_addr;
-	struct sockaddr_in remote_addr;
+	struct sockaddr_storage local_addr;
+	struct sockaddr_storage remote_addr;
 	void *private_data;
 	void *provider_data;
 	u8 private_data_len;
-	struct socket *so;
 	u8 ord;
 	u8 ird;
 };
@@ -85,15 +83,17 @@ struct iw_cm_id {
 	iw_cm_handler		cm_handler;      /* client callback function */
 	void		        *context;	 /* client cb context */
 	struct ib_device	*device;
-	struct sockaddr_in      local_addr;
-	struct sockaddr_in	remote_addr;
+	struct sockaddr_storage local_addr;      /* local addr */
+	struct sockaddr_storage	remote_addr;
+	struct sockaddr_storage m_local_addr;	 /* nmapped local addr */
+	struct sockaddr_storage	m_remote_addr;	 /* nmapped rem addr */
 	void			*provider_data;	 /* provider private data */
 	iw_event_handler        event_handler;   /* cb for provider
 						    events */
 	/* 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 *);
-	struct socket           *so;
+	u8  tos;
 };
 
 struct iw_cm_conn_param {
@@ -121,13 +121,11 @@ struct iw_cm_verbs {
 	int		(*reject)(struct iw_cm_id *cm_id,
 				  const void *pdata, u8 pdata_len);
 
-	int		(*create_listen_ep)(struct iw_cm_id *cm_id,
+	int		(*create_listen)(struct iw_cm_id *cm_id,
 					 int backlog);
 
-	void		(*destroy_listen_ep)(struct iw_cm_id *cm_id);
-
-	void		(*newconn)(struct iw_cm_id *parent_cm_id,
-						struct socket *so);
+	int		(*destroy_listen)(struct iw_cm_id *cm_id);
+	char		ifname[IFNAMSIZ];
 };
 
 /**
@@ -138,7 +136,7 @@ struct iw_cm_verbs {
  *   returned IW CM identifier.
  * @context: User specified context associated with the id.
  */
-struct iw_cm_id *iw_create_cm_id(struct ib_device *device, struct socket *so,
+struct iw_cm_id *iw_create_cm_id(struct ib_device *device,
 				 iw_cm_handler cm_handler, void *context);
 
 /**
diff --git a/sys/ofed/include/rdma/iw_portmap.h b/sys/ofed/include/rdma/iw_portmap.h
new file mode 100644
index 000000000000..9393f50b6e4e
--- /dev/null
+++ b/sys/ofed/include/rdma/iw_portmap.h
@@ -0,0 +1,70 @@
+/*
+ * Copyright (c) 2014 Intel Corporation. All rights reserved.
+ * Copyright (c) 2014 Chelsio, Inc. 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 _IW_PORTMAP_H
+#define _IW_PORTMAP_H
+
+#define IWPM_ULIBNAME_SIZE	32
+#define IWPM_DEVNAME_SIZE	32
+#define IWPM_IFNAME_SIZE	16
+#define IWPM_IPADDR_SIZE	16
+
+enum {
+	IWPM_INVALID_NLMSG_ERR = 10,
+	IWPM_CREATE_MAPPING_ERR,
+	IWPM_DUPLICATE_MAPPING_ERR,
+	IWPM_UNKNOWN_MAPPING_ERR,
+	IWPM_CLIENT_DEV_INFO_ERR,
+	IWPM_USER_LIB_INFO_ERR,
+	IWPM_REMOTE_QUERY_REJECT
+};
+
+struct iwpm_dev_data {
+	char dev_name[IWPM_DEVNAME_SIZE];
+	char if_name[IWPM_IFNAME_SIZE];
+};
+
+struct iwpm_sa_data {
+	struct sockaddr_storage loc_addr;
+	struct sockaddr_storage mapped_loc_addr;
+	struct sockaddr_storage rem_addr;
+	struct sockaddr_storage mapped_rem_addr;
+};
+
+/**
+ * iwpm_valid_pid - Check if the userspace iwarp port mapper pid is valid
+ *
+ * Returns true if the pid is greater than zero, otherwise returns false
+ */
+int iwpm_valid_pid(void);
+
+#endif /* _IW_PORTMAP_H */
diff --git a/sys/ofed/include/rdma/opa_port_info.h b/sys/ofed/include/rdma/opa_port_info.h
new file mode 100644
index 000000000000..9303e0e4f508
--- /dev/null
+++ b/sys/ofed/include/rdma/opa_port_info.h
@@ -0,0 +1,417 @@
+/*
+ * 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_PORT_INFO_H)
+#define OPA_PORT_INFO_H
+
+#define OPA_PORT_LINK_MODE_NOP	0		/* No change */
+#define OPA_PORT_LINK_MODE_OPA	4		/* Port mode is OPA */
+
+#define OPA_PORT_PACKET_FORMAT_NOP	0		/* No change */
+#define OPA_PORT_PACKET_FORMAT_8B	1		/* Format 8B */
+#define OPA_PORT_PACKET_FORMAT_9B	2		/* Format 9B */
+#define OPA_PORT_PACKET_FORMAT_10B	4		/* Format 10B */
+#define OPA_PORT_PACKET_FORMAT_16B	8		/* Format 16B */
+
+#define OPA_PORT_LTP_CRC_MODE_NONE	0	/* No change */
+#define OPA_PORT_LTP_CRC_MODE_14	1	/* 14-bit LTP CRC mode (optional) */
+#define OPA_PORT_LTP_CRC_MODE_16	2	/* 16-bit LTP CRC mode */
+#define OPA_PORT_LTP_CRC_MODE_48	4	/* 48-bit LTP CRC mode (optional) */
+#define OPA_PORT_LTP_CRC_MODE_PER_LANE  8	/* 12/16-bit per lane LTP CRC mode */
+
+/* Link Down / Neighbor Link Down Reason; indicated as follows: */
+#define OPA_LINKDOWN_REASON_NONE				0	/* No specified reason */
+#define OPA_LINKDOWN_REASON_RCV_ERROR_0				1
+#define OPA_LINKDOWN_REASON_BAD_PKT_LEN				2
+#define OPA_LINKDOWN_REASON_PKT_TOO_LONG			3
+#define OPA_LINKDOWN_REASON_PKT_TOO_SHORT			4
+#define OPA_LINKDOWN_REASON_BAD_SLID				5
+#define OPA_LINKDOWN_REASON_BAD_DLID				6
+#define OPA_LINKDOWN_REASON_BAD_L2				7
+#define OPA_LINKDOWN_REASON_BAD_SC				8
+#define OPA_LINKDOWN_REASON_RCV_ERROR_8				9
+#define OPA_LINKDOWN_REASON_BAD_MID_TAIL			10
+#define OPA_LINKDOWN_REASON_RCV_ERROR_10			11
+#define OPA_LINKDOWN_REASON_PREEMPT_ERROR			12
+#define OPA_LINKDOWN_REASON_PREEMPT_VL15			13
+#define OPA_LINKDOWN_REASON_BAD_VL_MARKER			14
+#define OPA_LINKDOWN_REASON_RCV_ERROR_14			15
+#define OPA_LINKDOWN_REASON_RCV_ERROR_15			16
+#define OPA_LINKDOWN_REASON_BAD_HEAD_DIST			17
+#define OPA_LINKDOWN_REASON_BAD_TAIL_DIST			18
+#define OPA_LINKDOWN_REASON_BAD_CTRL_DIST			19
+#define OPA_LINKDOWN_REASON_BAD_CREDIT_ACK			20
+#define OPA_LINKDOWN_REASON_UNSUPPORTED_VL_MARKER		21
+#define OPA_LINKDOWN_REASON_BAD_PREEMPT				22
+#define OPA_LINKDOWN_REASON_BAD_CONTROL_FLIT			23
+#define OPA_LINKDOWN_REASON_EXCEED_MULTICAST_LIMIT		24
+#define OPA_LINKDOWN_REASON_RCV_ERROR_24			25
+#define OPA_LINKDOWN_REASON_RCV_ERROR_25			26
+#define OPA_LINKDOWN_REASON_RCV_ERROR_26			27
+#define OPA_LINKDOWN_REASON_RCV_ERROR_27			28
+#define OPA_LINKDOWN_REASON_RCV_ERROR_28			29
+#define OPA_LINKDOWN_REASON_RCV_ERROR_29			30
+#define OPA_LINKDOWN_REASON_RCV_ERROR_30			31
+#define OPA_LINKDOWN_REASON_EXCESSIVE_BUFFER_OVERRUN		32
+#define OPA_LINKDOWN_REASON_UNKNOWN				33
+/* 34 -reserved */
+#define OPA_LINKDOWN_REASON_REBOOT				35
+#define OPA_LINKDOWN_REASON_NEIGHBOR_UNKNOWN			36
+/* 37-38 reserved */
+#define OPA_LINKDOWN_REASON_FM_BOUNCE				39
+#define OPA_LINKDOWN_REASON_SPEED_POLICY			40
+#define OPA_LINKDOWN_REASON_WIDTH_POLICY			41
+/* 42-48 reserved */
+#define OPA_LINKDOWN_REASON_DISCONNECTED			49
+#define OPA_LINKDOWN_REASON_LOCAL_MEDIA_NOT_INSTALLED		50
+#define OPA_LINKDOWN_REASON_NOT_INSTALLED			51
+#define OPA_LINKDOWN_REASON_CHASSIS_CONFIG			52
+/* 53 reserved */
+#define OPA_LINKDOWN_REASON_END_TO_END_NOT_INSTALLED		54
+/* 55 reserved */
+#define OPA_LINKDOWN_REASON_POWER_POLICY			56
+#define OPA_LINKDOWN_REASON_LINKSPEED_POLICY			57
+#define OPA_LINKDOWN_REASON_LINKWIDTH_POLICY			58
+/* 59 reserved */
+#define OPA_LINKDOWN_REASON_SWITCH_MGMT				60
+#define OPA_LINKDOWN_REASON_SMA_DISABLED			61
+/* 62 reserved */
+#define OPA_LINKDOWN_REASON_TRANSIENT				63
+/* 64-255 reserved */
+
+/* OPA Link Init reason; indicated as follows: */
+/* 3-7; 11-15 reserved; 8-15 cleared on Polling->LinkUp */
+#define OPA_LINKINIT_REASON_NOP                 0
+#define OPA_LINKINIT_REASON_LINKUP              (1 << 4)
+#define OPA_LINKINIT_REASON_FLAPPING            (2 << 4)
+#define OPA_LINKINIT_REASON_CLEAR               (8 << 4)
+#define OPA_LINKINIT_OUTSIDE_POLICY             (8 << 4)
+#define OPA_LINKINIT_QUARANTINED                (9 << 4)
+#define OPA_LINKINIT_INSUFIC_CAPABILITY         (10 << 4)
+
+#define OPA_LINK_SPEED_NOP              0x0000  /*  Reserved (1-5 Gbps) */
+#define OPA_LINK_SPEED_12_5G            0x0001  /*  12.5 Gbps */
+#define OPA_LINK_SPEED_25G              0x0002  /*  25.78125?  Gbps (EDR) */
+
+#define OPA_LINK_WIDTH_1X            0x0001
+#define OPA_LINK_WIDTH_2X            0x0002
+#define OPA_LINK_WIDTH_3X            0x0004
+#define OPA_LINK_WIDTH_4X            0x0008
+
+#define OPA_CAP_MASK3_IsSnoopSupported            (1 << 7)
+#define OPA_CAP_MASK3_IsAsyncSC2VLSupported       (1 << 6)
+#define OPA_CAP_MASK3_IsAddrRangeConfigSupported  (1 << 5)
+#define OPA_CAP_MASK3_IsPassThroughSupported      (1 << 4)
+#define OPA_CAP_MASK3_IsSharedSpaceSupported      (1 << 3)
+/* reserved (1 << 2) */
+#define OPA_CAP_MASK3_IsVLMarkerSupported         (1 << 1)
+#define OPA_CAP_MASK3_IsVLrSupported              (1 << 0)
+
+/**
+ * new MTU values
+ */
+enum {
+	OPA_MTU_8192  = 6,
+	OPA_MTU_10240 = 7,
+};
+
+enum {
+	OPA_PORT_PHYS_CONF_DISCONNECTED = 0,
+	OPA_PORT_PHYS_CONF_STANDARD     = 1,
+	OPA_PORT_PHYS_CONF_FIXED        = 2,
+	OPA_PORT_PHYS_CONF_VARIABLE     = 3,
+	OPA_PORT_PHYS_CONF_SI_PHOTO     = 4
+};
+
+enum port_info_field_masks {
+	/* vl.cap */
+	OPA_PI_MASK_VL_CAP                        = 0x1F,
+	/* port_states.ledenable_offlinereason */
+	OPA_PI_MASK_OFFLINE_REASON                = 0x0F,
+	OPA_PI_MASK_LED_ENABLE                    = 0x40,
+	/* port_states.unsleepstate_downdefstate */
+	OPA_PI_MASK_UNSLEEP_STATE                 = 0xF0,
+	OPA_PI_MASK_DOWNDEF_STATE                 = 0x0F,
+	/* port_states.portphysstate_portstate */
+	OPA_PI_MASK_PORT_PHYSICAL_STATE           = 0xF0,
+	OPA_PI_MASK_PORT_STATE                    = 0x0F,
+	/* port_phys_conf */
+	OPA_PI_MASK_PORT_PHYSICAL_CONF            = 0x0F,
+	/* collectivemask_multicastmask */
+	OPA_PI_MASK_COLLECT_MASK                  = 0x38,
+	OPA_PI_MASK_MULTICAST_MASK                = 0x07,
+	/* mkeyprotect_lmc */
+	OPA_PI_MASK_MKEY_PROT_BIT                 = 0xC0,
+	OPA_PI_MASK_LMC                           = 0x0F,
+	/* smsl */
+	OPA_PI_MASK_SMSL                          = 0x1F,
+	/* partenforce_filterraw */
+	/* Filter Raw In/Out bits 1 and 2 were removed */
+	OPA_PI_MASK_LINKINIT_REASON               = 0xF0,
+	OPA_PI_MASK_PARTITION_ENFORCE_IN          = 0x08,
+	OPA_PI_MASK_PARTITION_ENFORCE_OUT         = 0x04,
+	/* operational_vls */
+	OPA_PI_MASK_OPERATIONAL_VL                = 0x1F,
+	/* sa_qp */
+	OPA_PI_MASK_SA_QP                         = 0x00FFFFFF,
+	/* sm_trap_qp */
+	OPA_PI_MASK_SM_TRAP_QP                    = 0x00FFFFFF,
+	/* localphy_overrun_errors */
+	OPA_PI_MASK_LOCAL_PHY_ERRORS              = 0xF0,
+	OPA_PI_MASK_OVERRUN_ERRORS                = 0x0F,
+	/* clientrereg_subnettimeout */
+	OPA_PI_MASK_CLIENT_REREGISTER             = 0x80,
+	OPA_PI_MASK_SUBNET_TIMEOUT                = 0x1F,
+	/* port_link_mode */
+	OPA_PI_MASK_PORT_LINK_SUPPORTED           = (0x001F << 10),
+	OPA_PI_MASK_PORT_LINK_ENABLED             = (0x001F <<  5),
+	OPA_PI_MASK_PORT_LINK_ACTIVE              = (0x001F <<  0),
+	/* port_link_crc_mode */
+	OPA_PI_MASK_PORT_LINK_CRC_SUPPORTED       = 0x0F00,
+	OPA_PI_MASK_PORT_LINK_CRC_ENABLED         = 0x00F0,
+	OPA_PI_MASK_PORT_LINK_CRC_ACTIVE          = 0x000F,
+	/* port_mode */
+	OPA_PI_MASK_PORT_MODE_SECURITY_CHECK      = 0x0001,
+	OPA_PI_MASK_PORT_MODE_16B_TRAP_QUERY      = 0x0002,
+	OPA_PI_MASK_PORT_MODE_PKEY_CONVERT        = 0x0004,
+	OPA_PI_MASK_PORT_MODE_SC2SC_MAPPING       = 0x0008,
+	OPA_PI_MASK_PORT_MODE_VL_MARKER           = 0x0010,
+	OPA_PI_MASK_PORT_PASS_THROUGH             = 0x0020,
+	OPA_PI_MASK_PORT_ACTIVE_OPTOMIZE          = 0x0040,
+	/* flit_control.interleave */
+	OPA_PI_MASK_INTERLEAVE_DIST_SUP           = (0x0003 << 12),
+	OPA_PI_MASK_INTERLEAVE_DIST_ENABLE        = (0x0003 << 10),
+	OPA_PI_MASK_INTERLEAVE_MAX_NEST_TX        = (0x001F <<  5),
+	OPA_PI_MASK_INTERLEAVE_MAX_NEST_RX        = (0x001F <<  0),
+
+	/* port_error_action */
+	OPA_PI_MASK_EX_BUFFER_OVERRUN                  = 0x80000000,
+		/* 7 bits reserved */
+	OPA_PI_MASK_FM_CFG_ERR_EXCEED_MULTICAST_LIMIT  = 0x00800000,
+	OPA_PI_MASK_FM_CFG_BAD_CONTROL_FLIT            = 0x00400000,
+	OPA_PI_MASK_FM_CFG_BAD_PREEMPT                 = 0x00200000,
+	OPA_PI_MASK_FM_CFG_UNSUPPORTED_VL_MARKER       = 0x00100000,
+	OPA_PI_MASK_FM_CFG_BAD_CRDT_ACK                = 0x00080000,
+	OPA_PI_MASK_FM_CFG_BAD_CTRL_DIST               = 0x00040000,
+	OPA_PI_MASK_FM_CFG_BAD_TAIL_DIST               = 0x00020000,
+	OPA_PI_MASK_FM_CFG_BAD_HEAD_DIST               = 0x00010000,
+		/* 2 bits reserved */
+	OPA_PI_MASK_PORT_RCV_BAD_VL_MARKER             = 0x00002000,
+	OPA_PI_MASK_PORT_RCV_PREEMPT_VL15              = 0x00001000,
+	OPA_PI_MASK_PORT_RCV_PREEMPT_ERROR             = 0x00000800,
+		/* 1 bit reserved */
+	OPA_PI_MASK_PORT_RCV_BAD_MidTail               = 0x00000200,
+		/* 1 bit reserved */
+	OPA_PI_MASK_PORT_RCV_BAD_SC                    = 0x00000080,
+	OPA_PI_MASK_PORT_RCV_BAD_L2                    = 0x00000040,
+	OPA_PI_MASK_PORT_RCV_BAD_DLID                  = 0x00000020,
+	OPA_PI_MASK_PORT_RCV_BAD_SLID                  = 0x00000010,
+	OPA_PI_MASK_PORT_RCV_PKTLEN_TOOSHORT           = 0x00000008,
+	OPA_PI_MASK_PORT_RCV_PKTLEN_TOOLONG            = 0x00000004,
+	OPA_PI_MASK_PORT_RCV_BAD_PKTLEN                = 0x00000002,
+	OPA_PI_MASK_PORT_RCV_BAD_LT                    = 0x00000001,
+
+	/* pass_through.res_drctl */
+	OPA_PI_MASK_PASS_THROUGH_DR_CONTROL       = 0x01,
+
+	/* buffer_units */
+	OPA_PI_MASK_BUF_UNIT_VL15_INIT            = (0x00000FFF  << 11),
+	OPA_PI_MASK_BUF_UNIT_VL15_CREDIT_RATE     = (0x0000001F  <<  6),
+	OPA_PI_MASK_BUF_UNIT_CREDIT_ACK           = (0x00000003  <<  3),
+	OPA_PI_MASK_BUF_UNIT_BUF_ALLOC            = (0x00000003  <<  0),
+
+	/* neigh_mtu.pvlx_to_mtu */
+	OPA_PI_MASK_NEIGH_MTU_PVL0                = 0xF0,
+	OPA_PI_MASK_NEIGH_MTU_PVL1                = 0x0F,
+
+	/* neigh_mtu.vlstall_hoq_life */
+	OPA_PI_MASK_VL_STALL                      = (0x03 << 5),
+	OPA_PI_MASK_HOQ_LIFE                      = (0x1F << 0),
+
+	/* port_neigh_mode */
+	OPA_PI_MASK_NEIGH_MGMT_ALLOWED            = (0x01 << 3),
+	OPA_PI_MASK_NEIGH_FW_AUTH_BYPASS          = (0x01 << 2),
+	OPA_PI_MASK_NEIGH_NODE_TYPE               = (0x03 << 0),
+
+	/* resptime_value */
+	OPA_PI_MASK_RESPONSE_TIME_VALUE           = 0x1F,
+
+	/* mtucap */
+	OPA_PI_MASK_MTU_CAP                       = 0x0F,
+};
+
+struct opa_port_states {
+	u8     reserved;
+	u8     ledenable_offlinereason;   /* 1 res, 1 bit, 6 bits */
+	u8     reserved2;
+	u8     portphysstate_portstate;   /* 4 bits, 4 bits */
+};
+
+struct opa_port_state_info {
+	struct opa_port_states port_states;
+	__be16 link_width_downgrade_tx_active;
+	__be16 link_width_downgrade_rx_active;
+};
+
+struct opa_port_info {
+	__be32 lid;
+	__be32 flow_control_mask;
+
+	struct {
+		u8     res;                       /* was inittype */
+		u8     cap;                       /* 3 res, 5 bits */
+		__be16 high_limit;
+		__be16 preempt_limit;
+		u8     arb_high_cap;
+		u8     arb_low_cap;
+	} vl;
+
+	struct opa_port_states  port_states;
+	u8     port_phys_conf;                    /* 4 res, 4 bits */
+	u8     collectivemask_multicastmask;      /* 2 res, 3, 3 */
+	u8     mkeyprotect_lmc;                   /* 2 bits, 2 res, 4 bits */
+	u8     smsl;                              /* 3 res, 5 bits */
+
+	u8     partenforce_filterraw;             /* bit fields */
+	u8     operational_vls;                    /* 3 res, 5 bits */
+	__be16 pkey_8b;
+	__be16 pkey_10b;
+	__be16 mkey_violations;
+
+	__be16 pkey_violations;
+	__be16 qkey_violations;
+	__be32 sm_trap_qp;                        /* 8 bits, 24 bits */
+
+	__be32 sa_qp;                             /* 8 bits, 24 bits */
+	u8     neigh_port_num;
+	u8     link_down_reason;
+	u8     neigh_link_down_reason;
+	u8     clientrereg_subnettimeout;	  /* 1 bit, 2 bits, 5 */
+
+	struct {
+		__be16 supported;
+		__be16 enabled;
+		__be16 active;
+	} link_speed;
+	struct {
+		__be16 supported;
+		__be16 enabled;
+		__be16 active;
+	} link_width;
+	struct {
+		__be16 supported;
+		__be16 enabled;
+		__be16 tx_active;
+		__be16 rx_active;
+	} link_width_downgrade;
+	__be16 port_link_mode;                  /* 1 res, 5 bits, 5 bits, 5 bits */
+	__be16 port_ltp_crc_mode;               /* 4 res, 4 bits, 4 bits, 4 bits */
+
+	__be16 port_mode;                       /* 9 res, bit fields */
+	struct {
+		__be16 supported;
+		__be16 enabled;
+	} port_packet_format;
+	struct {
+		__be16 interleave;  /* 2 res, 2,2,5,5 */
+		struct {
+			__be16 min_initial;
+			__be16 min_tail;
+			u8     large_pkt_limit;
+			u8     small_pkt_limit;
+			u8     max_small_pkt_limit;
+			u8     preemption_limit;
+		} preemption;
+	} flit_control;
+
+	__be32 reserved4;
+	__be32 port_error_action; /* bit field */
+
+	struct {
+		u8 egress_port;
+		u8 res_drctl;                    /* 7 res, 1 */
+	} pass_through;
+	__be16 mkey_lease_period;
+	__be32 buffer_units;                     /* 9 res, 12, 5, 3, 3 */
+
+	__be32 reserved5;
+	__be32 sm_lid;
+
+	__be64 mkey;
+
+	__be64 subnet_prefix;
+
+	struct {
+		u8 pvlx_to_mtu[OPA_MAX_VLS/2]; /* 4 bits, 4 bits */
+	} neigh_mtu;
+
+	struct {
+		u8 vlstall_hoqlife;             /* 3 bits, 5 bits */
+	} xmit_q[OPA_MAX_VLS];
+
+	struct {
+		u8 addr[16];
+	} ipaddr_ipv6;
+
+	struct {
+		u8 addr[4];
+	} ipaddr_ipv4;
+
+	u32    reserved6;
+	u32    reserved7;
+	u32    reserved8;
+
+	__be64 neigh_node_guid;
+
+	__be32 ib_cap_mask;
+	__be16 reserved9;                    /* was ib_cap_mask2 */
+	__be16 opa_cap_mask;
+
+	__be32 reserved10;                   /* was link_roundtrip_latency */
+	__be16 overall_buffer_space;
+	__be16 reserved11;                   /* was max_credit_hint */
+
+	__be16 diag_code;
+	struct {
+		u8 buffer;
+		u8 wire;
+	} replay_depth;
+	u8     port_neigh_mode;
+	u8     mtucap;                          /* 4 res, 4 bits */
+
+	u8     resptimevalue;		        /* 3 res, 5 bits */
+	u8     local_port_num;
+	u8     reserved12;
+	u8     reserved13;                       /* was guid_cap */
+} __attribute__ ((packed));
+
+#endif /* OPA_PORT_INFO_H */
diff --git a/sys/ofed/include/rdma/opa_smi.h b/sys/ofed/include/rdma/opa_smi.h
new file mode 100644
index 000000000000..3c21923d5209
--- /dev/null
+++ b/sys/ofed/include/rdma/opa_smi.h
@@ -0,0 +1,153 @@
+/*
+ * 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_MAX_VLS				32
+#define OPA_MAX_SLS				32
+#define OPA_MAX_SCS				32
+
+#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;
+
+
+/* Subnet management attributes */
+/* ... */
+#define OPA_ATTRIB_ID_NODE_DESCRIPTION		cpu_to_be16(0x0010)
+#define OPA_ATTRIB_ID_NODE_INFO			cpu_to_be16(0x0011)
+#define OPA_ATTRIB_ID_PORT_INFO			cpu_to_be16(0x0015)
+#define OPA_ATTRIB_ID_PARTITION_TABLE		cpu_to_be16(0x0016)
+#define OPA_ATTRIB_ID_SL_TO_SC_MAP		cpu_to_be16(0x0017)
+#define OPA_ATTRIB_ID_VL_ARBITRATION		cpu_to_be16(0x0018)
+#define OPA_ATTRIB_ID_SM_INFO			cpu_to_be16(0x0020)
+#define OPA_ATTRIB_ID_CABLE_INFO		cpu_to_be16(0x0032)
+#define OPA_ATTRIB_ID_AGGREGATE			cpu_to_be16(0x0080)
+#define OPA_ATTRIB_ID_SC_TO_SL_MAP		cpu_to_be16(0x0082)
+#define OPA_ATTRIB_ID_SC_TO_VLR_MAP		cpu_to_be16(0x0083)
+#define OPA_ATTRIB_ID_SC_TO_VLT_MAP		cpu_to_be16(0x0084)
+#define OPA_ATTRIB_ID_SC_TO_VLNT_MAP		cpu_to_be16(0x0085)
+/* ... */
+#define OPA_ATTRIB_ID_PORT_STATE_INFO		cpu_to_be16(0x0087)
+/* ... */
+#define OPA_ATTRIB_ID_BUFFER_CONTROL_TABLE	cpu_to_be16(0x008A)
+/* ... */
+
+struct opa_node_description {
+	u8 data[64];
+} __attribute__ ((packed));
+
+struct opa_node_info {
+	u8      base_version;
+	u8      class_version;
+	u8      node_type;
+	u8      num_ports;
+	__be32  reserved;
+	__be64  system_image_guid;
+	__be64  node_guid;
+	__be64  port_guid;
+	__be16  partition_cap;
+	__be16  device_id;
+	__be32  revision;
+	u8      local_port_num;
+	u8      vendor_id[3];   /* network byte order */
+} __attribute__ ((packed));
+
+#define OPA_PARTITION_TABLE_BLK_SIZE 32
+
+static inline u8
+opa_get_smp_direction(const struct opa_smp *smp)
+{
+	return ib_get_smp_direction((const 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(const 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(const 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 */
diff --git a/sys/ofed/include/rdma/peer_mem.h b/sys/ofed/include/rdma/peer_mem.h
deleted file mode 100644
index 85658831299c..000000000000
--- a/sys/ofed/include/rdma/peer_mem.h
+++ /dev/null
@@ -1,73 +0,0 @@
-/*
- * Copyright (c) 2013,  Mellanox Technologies. 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(PEER_MEM_H)
-#define PEER_MEM_H
-
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/errno.h>
-#include <linux/scatterlist.h>
-#include <linux/mutex.h>
-
-
-#define IB_PEER_MEMORY_NAME_MAX 64
-#define IB_PEER_MEMORY_VER_MAX 16
-
-struct peer_memory_client {
-	char	name[IB_PEER_MEMORY_NAME_MAX];
-	char	version[IB_PEER_MEMORY_VER_MAX];
-	/* acquire return code: 1 mine, 0 - not mine */
-	int (*acquire) (unsigned long addr, size_t size, void *peer_mem_private_data,
-					char *peer_mem_name, void **client_context);
-	int (*get_pages) (unsigned long addr,
-			  size_t size, int write, int force,
-			  struct sg_table *sg_head,
-			  void *client_context, void *core_context);
-	int (*dma_map) (struct sg_table *sg_head, void *client_context,
-			struct device *dma_device, int dmasync, int *nmap);
-	int (*dma_unmap) (struct sg_table *sg_head, void *client_context,
-			   struct device  *dma_device);
-	void (*put_pages) (struct sg_table *sg_head, void *client_context);
-	unsigned long (*get_page_size) (void *client_context);
-	void (*release) (void *client_context);
-
-};
-
-typedef int (*invalidate_peer_memory)(void *reg_handle,
-					  void *core_context);
-
-void *ib_register_peer_memory_client(struct peer_memory_client *peer_client,
-					  invalidate_peer_memory *invalidate_callback);
-void ib_unregister_peer_memory_client(void *reg_handle);
-
-#endif
diff --git a/sys/ofed/include/rdma/rdma_cm.h b/sys/ofed/include/rdma/rdma_cm.h
index 33be95784d54..7fee12cb36a8 100644
--- a/sys/ofed/include/rdma/rdma_cm.h
+++ b/sys/ofed/include/rdma/rdma_cm.h
@@ -1,7 +1,6 @@
 /*
  * Copyright (c) 2005 Voltaire Inc.  All rights reserved.
  * Copyright (c) 2005 Intel Corporation.  All rights reserved.
- * Copyright (c) 2016 Chelsio Communications.  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
@@ -60,13 +59,11 @@ enum rdma_cm_event_type {
 	RDMA_CM_EVENT_MULTICAST_JOIN,
 	RDMA_CM_EVENT_MULTICAST_ERROR,
 	RDMA_CM_EVENT_ADDR_CHANGE,
-	RDMA_CM_EVENT_TIMEWAIT_EXIT,
-	RDMA_CM_EVENT_ALT_ROUTE_RESOLVED,
-	RDMA_CM_EVENT_ALT_ROUTE_ERROR,
-	RDMA_CM_EVENT_LOAD_ALT_PATH,
-	RDMA_CM_EVENT_ALT_PATH_LOADED,
+	RDMA_CM_EVENT_TIMEWAIT_EXIT
 };
 
+const char *__attribute_const__ rdma_event_msg(enum rdma_cm_event_type event);
+
 enum rdma_port_space {
 	RDMA_PS_SDP   = 0x0001,
 	RDMA_PS_IPOIB = 0x0002,
@@ -75,12 +72,10 @@ enum rdma_port_space {
 	RDMA_PS_UDP   = 0x0111,
 };
 
-enum alt_path_type {
-	RDMA_ALT_PATH_NONE,
-	RDMA_ALT_PATH_PORT,
-	RDMA_ALT_PATH_LID,
-	RDMA_ALT_PATH_BEST
-};
+#define RDMA_IB_IP_PS_MASK   0xFFFFFFFFFFFF0000ULL
+#define RDMA_IB_IP_PS_TCP    0x0000000001060000ULL
+#define RDMA_IB_IP_PS_UDP    0x0000000001110000ULL
+#define RDMA_IB_IP_PS_IB     0x00000000013F0000ULL
 
 struct rdma_addr {
 	struct sockaddr_storage src_addr;
@@ -105,6 +100,7 @@ struct rdma_conn_param {
 	/* Fields below ignored if a QP is created on the rdma_cm_id. */
 	u8 srq;
 	u32 qp_num;
+	u32 qkey;
 };
 
 struct rdma_ud_param {
@@ -113,7 +109,6 @@ struct rdma_ud_param {
 	struct ib_ah_attr ah_attr;
 	u32 qp_num;
 	u32 qkey;
-	u8 alt_path_index;
 };
 
 struct rdma_cm_event {
@@ -160,19 +155,22 @@ struct rdma_cm_id {
 	enum rdma_port_space	 ps;
 	enum ib_qp_type		 qp_type;
 	u8			 port_num;
-	void			 *ucontext;
 };
 
 /**
  * rdma_create_id - Create an RDMA identifier.
  *
+ * @net: The network namespace in which to create the new id.
  * @event_handler: User callback invoked to report events associated with the
  *   returned rdma_id.
  * @context: User specified context associated with the id.
  * @ps: RDMA port space.
  * @qp_type: type of queue pair associated with the id.
+ *
+ * The id holds a reference on the network namespace until it is destroyed.
  */
-struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
+struct rdma_cm_id *rdma_create_id(struct vnet *net,
+				  rdma_cm_event_handler event_handler,
 				  void *context, enum rdma_port_space ps,
 				  enum ib_qp_type qp_type);
 
@@ -223,19 +221,6 @@ int rdma_resolve_addr(struct rdma_cm_id *id, struct sockaddr *src_addr,
 int rdma_resolve_route(struct rdma_cm_id *id, int timeout_ms);
 
 /**
- * rdma_enable_apm - Get ready to use APM for the given ID.
- * Actual Alternate path discovery and load will take place only
- * after a connection has been established.
- *
- * Calling this function only has an effect on the connection's client side.
- * It should be called after rdma_resolve_route and before rdma_connect.
- *
- * @id: RDMA identifier.
- * @alt_type: Alternate path type to resolve.
- */
-int rdma_enable_apm(struct rdma_cm_id *id, enum alt_path_type alt_type);
-
-/**
  * rdma_create_qp - Allocate a QP and associate it with the specified RDMA
  * identifier.
  *
@@ -348,11 +333,13 @@ int rdma_disconnect(struct rdma_cm_id *id);
  *   address.
  * @id: Communication identifier associated with the request.
  * @addr: Multicast address identifying the group to join.
+ * @join_state: Multicast JoinState bitmap requested by port.
+ *		Bitmap is based on IB_SA_MCMEMBER_REC_JOIN_STATE bits.
  * @context: User-defined context associated with the join request, returned
  * to the user through the private_data pointer in multicast events.
  */
 int rdma_join_multicast(struct rdma_cm_id *id, struct sockaddr *addr,
-			void *context);
+			u8 join_state, void *context);
 
 /**
  * rdma_leave_multicast - Leave the multicast group specified by the given
@@ -394,14 +381,11 @@ int rdma_set_reuseaddr(struct rdma_cm_id *id, int reuse);
  */
 int rdma_set_afonly(struct rdma_cm_id *id, int afonly);
 
-/**
- * rdma_set_timeout - Set the QP timeout associated with a connection
- * identifier.
- * @id: Communication identifier to associated with service type.
- * @timeout: QP timeout
+ /**
+ * rdma_get_service_id - Return the IB service ID for a specified address.
+ * @id: Communication identifier associated with the address.
+ * @addr: Address for the service ID.
  */
-void rdma_set_timeout(struct rdma_cm_id *id, int timeout);
-int rdma_cma_any_addr(struct sockaddr *addr);
-int rdma_find_cmid_laddr(struct sockaddr_in *local_addr,
-		unsigned short dev_type, void **cm_id);
+__be64 rdma_get_service_id(struct rdma_cm_id *id, struct sockaddr *addr);
+
 #endif /* RDMA_CM_H */
diff --git a/sys/ofed/include/rdma/rdma_user_cm.h b/sys/ofed/include/rdma/rdma_user_cm.h
index 4d9909994ddd..01923d463673 100644
--- a/sys/ofed/include/rdma/rdma_user_cm.h
+++ b/sys/ofed/include/rdma/rdma_user_cm.h
@@ -34,6 +34,7 @@
 #define RDMA_USER_CM_H
 
 #include <linux/types.h>
+#include <linux/socket.h>
 #include <linux/in6.h>
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_user_sa.h>
@@ -45,8 +46,8 @@
 enum {
 	RDMA_USER_CM_CMD_CREATE_ID,
 	RDMA_USER_CM_CMD_DESTROY_ID,
-	RDMA_USER_CM_CMD_BIND_ADDR,
-	RDMA_USER_CM_CMD_RESOLVE_ADDR,
+	RDMA_USER_CM_CMD_BIND_IP,
+	RDMA_USER_CM_CMD_RESOLVE_IP,
 	RDMA_USER_CM_CMD_RESOLVE_ROUTE,
 	RDMA_USER_CM_CMD_QUERY_ROUTE,
 	RDMA_USER_CM_CMD_CONNECT,
@@ -59,9 +60,13 @@ enum {
 	RDMA_USER_CM_CMD_GET_OPTION,
 	RDMA_USER_CM_CMD_SET_OPTION,
 	RDMA_USER_CM_CMD_NOTIFY,
-	RDMA_USER_CM_CMD_JOIN_MCAST,
+	RDMA_USER_CM_CMD_JOIN_IP_MCAST,
 	RDMA_USER_CM_CMD_LEAVE_MCAST,
-	RDMA_USER_CM_CMD_MIGRATE_ID
+	RDMA_USER_CM_CMD_MIGRATE_ID,
+	RDMA_USER_CM_CMD_QUERY,
+	RDMA_USER_CM_CMD_BIND,
+	RDMA_USER_CM_CMD_RESOLVE_ADDR,
+	RDMA_USER_CM_CMD_JOIN_MCAST
 };
 
 /*
@@ -95,28 +100,51 @@ struct rdma_ucm_destroy_id_resp {
 	__u32 events_reported;
 };
 
-struct rdma_ucm_bind_addr {
+struct rdma_ucm_bind_ip {
 	__u64 response;
 	struct sockaddr_in6 addr;
 	__u32 id;
 };
 
-struct rdma_ucm_resolve_addr {
+struct rdma_ucm_bind {
+	__u32 id;
+	__u16 addr_size;
+	__u16 reserved;
+	struct sockaddr_storage addr;
+};
+
+struct rdma_ucm_resolve_ip {
 	struct sockaddr_in6 src_addr;
 	struct sockaddr_in6 dst_addr;
 	__u32 id;
 	__u32 timeout_ms;
 };
 
+struct rdma_ucm_resolve_addr {
+	__u32 id;
+	__u32 timeout_ms;
+	__u16 src_size;
+	__u16 dst_size;
+	__u32 reserved;
+	struct sockaddr_storage src_addr;
+	struct sockaddr_storage dst_addr;
+};
+
 struct rdma_ucm_resolve_route {
 	__u32 id;
 	__u32 timeout_ms;
 };
 
-struct rdma_ucm_query_route {
+enum {
+	RDMA_USER_CM_QUERY_ADDR,
+	RDMA_USER_CM_QUERY_PATH,
+	RDMA_USER_CM_QUERY_GID
+};
+
+struct rdma_ucm_query {
 	__u64 response;
 	__u32 id;
-	__u32 reserved;
+	__u32 option;
 };
 
 struct rdma_ucm_query_route_resp {
@@ -129,9 +157,26 @@ struct rdma_ucm_query_route_resp {
 	__u8 reserved[3];
 };
 
+struct rdma_ucm_query_addr_resp {
+	__u64 node_guid;
+	__u8  port_num;
+	__u8  reserved;
+	__u16 pkey;
+	__u16 src_size;
+	__u16 dst_size;
+	struct sockaddr_storage src_addr;
+	struct sockaddr_storage dst_addr;
+};
+
+struct rdma_ucm_query_path_resp {
+	__u32 num_paths;
+	__u32 reserved;
+	struct ib_path_rec_data path_data[0];
+};
+
 struct rdma_ucm_conn_param {
 	__u32 qp_num;
-	__u32 reserved;
+	__u32 qkey;
 	__u8  private_data[RDMA_MAX_PRIVATE_DATA];
 	__u8  private_data_len;
 	__u8  srq;
@@ -192,13 +237,29 @@ struct rdma_ucm_notify {
 	__u32 event;
 };
 
-struct rdma_ucm_join_mcast {
+struct rdma_ucm_join_ip_mcast {
 	__u64 response;		/* rdma_ucm_create_id_resp */
 	__u64 uid;
 	struct sockaddr_in6 addr;
 	__u32 id;
 };
 
+/* Multicast join flags */
+enum {
+	RDMA_MC_JOIN_FLAG_FULLMEMBER,
+	RDMA_MC_JOIN_FLAG_SENDONLY_FULLMEMBER,
+	RDMA_MC_JOIN_FLAG_RESERVED,
+};
+
+struct rdma_ucm_join_mcast {
+	__u64 response;		/* rdma_ucma_create_id_resp */
+	__u64 uid;
+	__u32 id;
+	__u16 addr_size;
+	__u16 join_flags;
+	struct sockaddr_storage addr;
+};
+
 struct rdma_ucm_get_event {
 	__u64 response;
 };
@@ -222,12 +283,10 @@ enum {
 
 /* Option details */
 enum {
-	RDMA_OPTION_ID_TOS	= 0,
+	RDMA_OPTION_ID_TOS	 = 0,
 	RDMA_OPTION_ID_REUSEADDR = 1,
 	RDMA_OPTION_ID_AFONLY	 = 2,
-
-	RDMA_OPTION_IB_PATH	 = 1,
-	RDMA_OPTION_IB_APM	 = 2,
+	RDMA_OPTION_IB_PATH	 = 1
 };
 
 struct rdma_ucm_set_option {
diff --git a/sys/ofed/include/rdma/rdma_vt.h b/sys/ofed/include/rdma/rdma_vt.h
new file mode 100644
index 000000000000..e31502107a58
--- /dev/null
+++ b/sys/ofed/include/rdma/rdma_vt.h
@@ -0,0 +1,500 @@
+#ifndef DEF_RDMA_VT_H
+#define DEF_RDMA_VT_H
+
+/*
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * 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.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+/*
+ * Structure that low level drivers will populate in order to register with the
+ * rdmavt layer.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/list.h>
+#include <linux/hash.h>
+#include <rdma/ib_verbs.h>
+#include <rdma/rdmavt_mr.h>
+#include <rdma/rdmavt_qp.h>
+
+#define RVT_MAX_PKEY_VALUES 16
+
+struct rvt_ibport {
+	struct rvt_qp __rcu *qp[2];
+	struct ib_mad_agent *send_agent;	/* agent for SMI (traps) */
+	struct rb_root mcast_tree;
+	spinlock_t lock;		/* protect changes in this struct */
+
+	/* non-zero when timer is set */
+	unsigned long mkey_lease_timeout;
+	unsigned long trap_timeout;
+	__be64 gid_prefix;      /* in network order */
+	__be64 mkey;
+	u64 tid;
+	u32 port_cap_flags;
+	u32 pma_sample_start;
+	u32 pma_sample_interval;
+	__be16 pma_counter_select[5];
+	u16 pma_tag;
+	u16 mkey_lease_period;
+	u16 sm_lid;
+	u8 sm_sl;
+	u8 mkeyprot;
+	u8 subnet_timeout;
+	u8 vl_high_limit;
+
+	/*
+	 * Driver is expected to keep these up to date. These
+	 * counters are informational only and not required to be
+	 * completely accurate.
+	 */
+	u64 n_rc_resends;
+	u64 n_seq_naks;
+	u64 n_rdma_seq;
+	u64 n_rnr_naks;
+	u64 n_other_naks;
+	u64 n_loop_pkts;
+	u64 n_pkt_drops;
+	u64 n_vl15_dropped;
+	u64 n_rc_timeouts;
+	u64 n_dmawait;
+	u64 n_unaligned;
+	u64 n_rc_dupreq;
+	u64 n_rc_seqnak;
+	u16 pkey_violations;
+	u16 qkey_violations;
+	u16 mkey_violations;
+
+	/* Hot-path per CPU counters to avoid cacheline trading to update */
+	u64 z_rc_acks;
+	u64 z_rc_qacks;
+	u64 z_rc_delayed_comp;
+	u64 __percpu *rc_acks;
+	u64 __percpu *rc_qacks;
+	u64 __percpu *rc_delayed_comp;
+
+	void *priv; /* driver private data */
+
+	/*
+	 * The pkey table is allocated and maintained by the driver. Drivers
+	 * need to have access to this before registering with rdmav. However
+	 * rdmavt will need access to it so drivers need to proviee this during
+	 * the attach port API call.
+	 */
+	u16 *pkey_table;
+
+	struct rvt_ah *sm_ah;
+};
+
+#define RVT_CQN_MAX 16 /* maximum length of cq name */
+
+/*
+ * Things that are driver specific, module parameters in hfi1 and qib
+ */
+struct rvt_driver_params {
+	struct ib_device_attr props;
+
+	/*
+	 * Anything driver specific that is not covered by props
+	 * For instance special module parameters. Goes here.
+	 */
+	unsigned int lkey_table_size;
+	unsigned int qp_table_size;
+	int qpn_start;
+	int qpn_inc;
+	int qpn_res_start;
+	int qpn_res_end;
+	int nports;
+	int npkeys;
+	char cq_name[RVT_CQN_MAX];
+	int node;
+	int psn_mask;
+	int psn_shift;
+	int psn_modify_mask;
+	u32 core_cap_flags;
+	u32 max_mad_size;
+	u8 qos_shift;
+	u8 max_rdma_atomic;
+	u8 reserved_operations;
+};
+
+/* Protection domain */
+struct rvt_pd {
+	struct ib_pd ibpd;
+	int user;               /* non-zero if created from user space */
+};
+
+/* Address handle */
+struct rvt_ah {
+	struct ib_ah ibah;
+	struct ib_ah_attr attr;
+	atomic_t refcount;
+	u8 vl;
+	u8 log_pmtu;
+};
+
+struct rvt_dev_info;
+struct rvt_swqe;
+struct rvt_driver_provided {
+	/*
+	 * Which functions are required depends on which verbs rdmavt is
+	 * providing and which verbs the driver is overriding. See
+	 * check_support() for details.
+	 */
+
+	/* Passed to ib core registration. Callback to create syfs files */
+	int (*port_callback)(struct ib_device *, u8, struct kobject *);
+
+	/*
+	 * Returns a string to represent the device for which is being
+	 * registered. This is primarily used for error and debug messages on
+	 * the console.
+	 */
+	const char * (*get_card_name)(struct rvt_dev_info *rdi);
+
+	/*
+	 * Returns a pointer to the undelying hardware's PCI device. This is
+	 * used to display information as to what hardware is being referenced
+	 * in an output message
+	 */
+	struct pci_dev * (*get_pci_dev)(struct rvt_dev_info *rdi);
+
+	/*
+	 * Allocate a private queue pair data structure for driver specific
+	 * information which is opaque to rdmavt.  Errors are returned via
+	 * ERR_PTR(err).  The driver is free to return NULL or a valid
+	 * pointer.
+	 */
+	void * (*qp_priv_alloc)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+				gfp_t gfp);
+
+	/*
+	 * Free the driver's private qp structure.
+	 */
+	void (*qp_priv_free)(struct rvt_dev_info *rdi, struct rvt_qp *qp);
+
+	/*
+	 * Inform the driver the particular qp in quesiton has been reset so
+	 * that it can clean up anything it needs to.
+	 */
+	void (*notify_qp_reset)(struct rvt_qp *qp);
+
+	/*
+	 * Give the driver a notice that there is send work to do. It is up to
+	 * the driver to generally push the packets out, this just queues the
+	 * work with the driver. There are two variants here. The no_lock
+	 * version requires the s_lock not to be held. The other assumes the
+	 * s_lock is held.
+	 */
+	void (*schedule_send)(struct rvt_qp *qp);
+	void (*schedule_send_no_lock)(struct rvt_qp *qp);
+
+	/*
+	 * Sometimes rdmavt needs to kick the driver's send progress. That is
+	 * done by this call back.
+	 */
+	void (*do_send)(struct rvt_qp *qp);
+
+	/*
+	 * Get a path mtu from the driver based on qp attributes.
+	 */
+	int (*get_pmtu_from_attr)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+				  struct ib_qp_attr *attr);
+
+	/*
+	 * Notify driver that it needs to flush any outstanding IO requests that
+	 * are waiting on a qp.
+	 */
+	void (*flush_qp_waiters)(struct rvt_qp *qp);
+
+	/*
+	 * Notify driver to stop its queue of sending packets. Nothing else
+	 * should be posted to the queue pair after this has been called.
+	 */
+	void (*stop_send_queue)(struct rvt_qp *qp);
+
+	/*
+	 * Have the drivr drain any in progress operations
+	 */
+	void (*quiesce_qp)(struct rvt_qp *qp);
+
+	/*
+	 * Inform the driver a qp has went to error state.
+	 */
+	void (*notify_error_qp)(struct rvt_qp *qp);
+
+	/*
+	 * Get an MTU for a qp.
+	 */
+	u32 (*mtu_from_qp)(struct rvt_dev_info *rdi, struct rvt_qp *qp,
+			   u32 pmtu);
+	/*
+	 * Convert an mtu to a path mtu
+	 */
+	int (*mtu_to_path_mtu)(u32 mtu);
+
+	/*
+	 * Get the guid of a port in big endian byte order
+	 */
+	int (*get_guid_be)(struct rvt_dev_info *rdi, struct rvt_ibport *rvp,
+			   int guid_index, __be64 *guid);
+
+	/*
+	 * Query driver for the state of the port.
+	 */
+	int (*query_port_state)(struct rvt_dev_info *rdi, u8 port_num,
+				struct ib_port_attr *props);
+
+	/*
+	 * Tell driver to shutdown a port
+	 */
+	int (*shut_down_port)(struct rvt_dev_info *rdi, u8 port_num);
+
+	/* Tell driver to send a trap for changed  port capabilities */
+	void (*cap_mask_chg)(struct rvt_dev_info *rdi, u8 port_num);
+
+	/*
+	 * The following functions can be safely ignored completely. Any use of
+	 * these is checked for NULL before blindly calling. Rdmavt should also
+	 * be functional if drivers omit these.
+	 */
+
+	/* Called to inform the driver that all qps should now be freed. */
+	unsigned (*free_all_qps)(struct rvt_dev_info *rdi);
+
+	/* Driver specific AH validation */
+	int (*check_ah)(struct ib_device *, struct ib_ah_attr *);
+
+	/* Inform the driver a new AH has been created */
+	void (*notify_new_ah)(struct ib_device *, struct ib_ah_attr *,
+			      struct rvt_ah *);
+
+	/* Let the driver pick the next queue pair number*/
+	int (*alloc_qpn)(struct rvt_dev_info *rdi, struct rvt_qpn_table *qpt,
+			 enum ib_qp_type type, u8 port_num, gfp_t gfp);
+
+	/* Determine if its safe or allowed to modify the qp */
+	int (*check_modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr,
+			       int attr_mask, struct ib_udata *udata);
+
+	/* Driver specific QP modification/notification-of */
+	void (*modify_qp)(struct rvt_qp *qp, struct ib_qp_attr *attr,
+			  int attr_mask, struct ib_udata *udata);
+
+	/* Driver specific work request checking */
+	int (*check_send_wqe)(struct rvt_qp *qp, struct rvt_swqe *wqe);
+
+	/* Notify driver a mad agent has been created */
+	void (*notify_create_mad_agent)(struct rvt_dev_info *rdi, int port_idx);
+
+	/* Notify driver a mad agent has been removed */
+	void (*notify_free_mad_agent)(struct rvt_dev_info *rdi, int port_idx);
+
+};
+
+struct rvt_dev_info {
+	struct ib_device ibdev; /* Keep this first. Nothing above here */
+
+	/*
+	 * Prior to calling for registration the driver will be responsible for
+	 * allocating space for this structure.
+	 *
+	 * The driver will also be responsible for filling in certain members of
+	 * dparms.props. The driver needs to fill in dparms exactly as it would
+	 * want values reported to a ULP. This will be returned to the caller
+	 * in rdmavt's device. The driver should also therefore refrain from
+	 * modifying this directly after registration with rdmavt.
+	 */
+
+	/* Driver specific properties */
+	struct rvt_driver_params dparms;
+
+	/* post send table */
+	const struct rvt_operation_params *post_parms;
+
+	struct rvt_mregion __rcu *dma_mr;
+	struct rvt_lkey_table lkey_table;
+
+	/* Driver specific helper functions */
+	struct rvt_driver_provided driver_f;
+
+	/* Internal use */
+	int n_pds_allocated;
+	spinlock_t n_pds_lock; /* Protect pd allocated count */
+
+	int n_ahs_allocated;
+	spinlock_t n_ahs_lock; /* Protect ah allocated count */
+
+	u32 n_srqs_allocated;
+	spinlock_t n_srqs_lock; /* Protect srqs allocated count */
+
+	int flags;
+	struct rvt_ibport **ports;
+
+	/* QP */
+	struct rvt_qp_ibdev *qp_dev;
+	u32 n_qps_allocated;    /* number of QPs allocated for device */
+	u32 n_rc_qps;		/* number of RC QPs allocated for device */
+	u32 busy_jiffies;	/* timeout scaling based on RC QP count */
+	spinlock_t n_qps_lock;	/* protect qps, rc qps and busy jiffy counts */
+
+	/* memory maps */
+	struct list_head pending_mmaps;
+	spinlock_t mmap_offset_lock; /* protect mmap_offset */
+	u32 mmap_offset;
+	spinlock_t pending_lock; /* protect pending mmap list */
+
+	/* CQ */
+	struct kthread_worker *worker; /* per device cq worker */
+	u32 n_cqs_allocated;    /* number of CQs allocated for device */
+	spinlock_t n_cqs_lock; /* protect count of in use cqs */
+
+	/* Multicast */
+	u32 n_mcast_grps_allocated; /* number of mcast groups allocated */
+	spinlock_t n_mcast_grps_lock;
+
+};
+
+static inline struct rvt_pd *ibpd_to_rvtpd(struct ib_pd *ibpd)
+{
+	return container_of(ibpd, struct rvt_pd, ibpd);
+}
+
+static inline struct rvt_ah *ibah_to_rvtah(struct ib_ah *ibah)
+{
+	return container_of(ibah, struct rvt_ah, ibah);
+}
+
+static inline struct rvt_dev_info *ib_to_rvt(struct ib_device *ibdev)
+{
+	return  container_of(ibdev, struct rvt_dev_info, ibdev);
+}
+
+static inline struct rvt_srq *ibsrq_to_rvtsrq(struct ib_srq *ibsrq)
+{
+	return container_of(ibsrq, struct rvt_srq, ibsrq);
+}
+
+static inline struct rvt_qp *ibqp_to_rvtqp(struct ib_qp *ibqp)
+{
+	return container_of(ibqp, struct rvt_qp, ibqp);
+}
+
+static inline unsigned rvt_get_npkeys(struct rvt_dev_info *rdi)
+{
+	/*
+	 * All ports have same number of pkeys.
+	 */
+	return rdi->dparms.npkeys;
+}
+
+/*
+ * Return the max atomic suitable for determining
+ * the size of the ack ring buffer in a QP.
+ */
+static inline unsigned int rvt_max_atomic(struct rvt_dev_info *rdi)
+{
+	return rdi->dparms.max_rdma_atomic + 1;
+}
+
+/*
+ * Return the indexed PKEY from the port PKEY table.
+ */
+static inline u16 rvt_get_pkey(struct rvt_dev_info *rdi,
+			       int port_index,
+			       unsigned index)
+{
+	if (index >= rvt_get_npkeys(rdi))
+		return 0;
+	else
+		return rdi->ports[port_index]->pkey_table[index];
+}
+
+/**
+ * rvt_lookup_qpn - return the QP with the given QPN
+ * @ibp: the ibport
+ * @qpn: the QP number to look up
+ *
+ * The caller must hold the rcu_read_lock(), and keep the lock until
+ * the returned qp is no longer in use.
+ */
+/* TODO: Remove this and put in rdmavt/qp.h when no longer needed by drivers */
+static inline struct rvt_qp *rvt_lookup_qpn(struct rvt_dev_info *rdi,
+					    struct rvt_ibport *rvp,
+					    u32 qpn) __must_hold(RCU)
+{
+	struct rvt_qp *qp = NULL;
+
+	if (unlikely(qpn <= 1)) {
+		qp = rcu_dereference(rvp->qp[qpn]);
+	} else {
+		u32 n = hash_32(qpn, rdi->qp_dev->qp_table_bits);
+
+		for (qp = rcu_dereference(rdi->qp_dev->qp_table[n]); qp;
+			qp = rcu_dereference(qp->next))
+			if (qp->ibqp.qp_num == qpn)
+				break;
+	}
+	return qp;
+}
+
+struct rvt_dev_info *rvt_alloc_device(size_t size, int nports);
+void rvt_dealloc_device(struct rvt_dev_info *rdi);
+int rvt_register_device(struct rvt_dev_info *rvd);
+void rvt_unregister_device(struct rvt_dev_info *rvd);
+int rvt_check_ah(struct ib_device *ibdev, struct ib_ah_attr *ah_attr);
+int rvt_init_port(struct rvt_dev_info *rdi, struct rvt_ibport *port,
+		  int port_index, u16 *pkey_table);
+int rvt_fast_reg_mr(struct rvt_qp *qp, struct ib_mr *ibmr, u32 key,
+		    int access);
+int rvt_invalidate_rkey(struct rvt_qp *qp, u32 rkey);
+int rvt_rkey_ok(struct rvt_qp *qp, struct rvt_sge *sge,
+		u32 len, u64 vaddr, u32 rkey, int acc);
+int rvt_lkey_ok(struct rvt_lkey_table *rkt, struct rvt_pd *pd,
+		struct rvt_sge *isge, struct ib_sge *sge, int acc);
+struct rvt_mcast *rvt_mcast_find(struct rvt_ibport *ibp, union ib_gid *mgid);
+
+#endif          /* DEF_RDMA_VT_H */
diff --git a/sys/ofed/include/rdma/rdmavt_cq.h b/sys/ofed/include/rdma/rdmavt_cq.h
new file mode 100644
index 000000000000..51fd00b243d0
--- /dev/null
+++ b/sys/ofed/include/rdma/rdmavt_cq.h
@@ -0,0 +1,99 @@
+#ifndef DEF_RDMAVT_INCCQ_H
+#define DEF_RDMAVT_INCCQ_H
+
+/*
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * Copyright(c) 2015 Intel Corporation.
+ *
+ * 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.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#include <linux/kthread.h>
+#include <rdma/ib_user_verbs.h>
+
+/*
+ * Define an ib_cq_notify value that is not valid so we know when CQ
+ * notifications are armed.
+ */
+#define RVT_CQ_NONE      (IB_CQ_NEXT_COMP + 1)
+
+/*
+ * This structure is used to contain the head pointer, tail pointer,
+ * and completion queue entries as a single memory allocation so
+ * it can be mmap'ed into user space.
+ */
+struct rvt_cq_wc {
+	u32 head;               /* index of next entry to fill */
+	u32 tail;               /* index of next ib_poll_cq() entry */
+	union {
+		/* these are actually size ibcq.cqe + 1 */
+		struct ib_uverbs_wc uqueue[0];
+		struct ib_wc kqueue[0];
+	};
+};
+
+/*
+ * The completion queue structure.
+ */
+struct rvt_cq {
+	struct ib_cq ibcq;
+	struct kthread_work comptask;
+	spinlock_t lock; /* protect changes in this struct */
+	u8 notify;
+	u8 triggered;
+	struct rvt_dev_info *rdi;
+	struct rvt_cq_wc *queue;
+	struct rvt_mmap_info *ip;
+};
+
+static inline struct rvt_cq *ibcq_to_rvtcq(struct ib_cq *ibcq)
+{
+	return container_of(ibcq, struct rvt_cq, ibcq);
+}
+
+void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited);
+
+#endif          /* DEF_RDMAVT_INCCQH */
diff --git a/sys/ofed/include/rdma/rdmavt_mr.h b/sys/ofed/include/rdma/rdmavt_mr.h
new file mode 100644
index 000000000000..6b3c6c8b6b77
--- /dev/null
+++ b/sys/ofed/include/rdma/rdmavt_mr.h
@@ -0,0 +1,140 @@
+#ifndef DEF_RDMAVT_INCMR_H
+#define DEF_RDMAVT_INCMR_H
+
+/*
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * 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.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+/*
+ * For Memory Regions. This stuff should probably be moved into rdmavt/mr.h once
+ * drivers no longer need access to the MR directly.
+ */
+
+/*
+ * A segment is a linear region of low physical memory.
+ * Used by the verbs layer.
+ */
+struct rvt_seg {
+	void *vaddr;
+	size_t length;
+};
+
+/* The number of rvt_segs that fit in a page. */
+#define RVT_SEGSZ     (PAGE_SIZE / sizeof(struct rvt_seg))
+
+struct rvt_segarray {
+	struct rvt_seg segs[RVT_SEGSZ];
+};
+
+struct rvt_mregion {
+	struct ib_pd *pd;       /* shares refcnt of ibmr.pd */
+	u64 user_base;          /* User's address for this region */
+	u64 iova;               /* IB start address of this region */
+	size_t length;
+	u32 lkey;
+	u32 offset;             /* offset (bytes) to start of region */
+	int access_flags;
+	u32 max_segs;           /* number of rvt_segs in all the arrays */
+	u32 mapsz;              /* size of the map array */
+	u8  page_shift;         /* 0 - non unform/non powerof2 sizes */
+	u8  lkey_published;     /* in global table */
+	atomic_t lkey_invalid;	/* true if current lkey is invalid */
+	struct completion comp; /* complete when refcount goes to zero */
+	atomic_t refcount;
+	struct rvt_segarray *map[0];    /* the segments */
+};
+
+#define RVT_MAX_LKEY_TABLE_BITS 23
+
+struct rvt_lkey_table {
+	spinlock_t lock; /* protect changes in this struct */
+	u32 next;               /* next unused index (speeds search) */
+	u32 gen;                /* generation count */
+	u32 max;                /* size of the table */
+	struct rvt_mregion __rcu **table;
+};
+
+/*
+ * These keep track of the copy progress within a memory region.
+ * Used by the verbs layer.
+ */
+struct rvt_sge {
+	struct rvt_mregion *mr;
+	void *vaddr;            /* kernel virtual address of segment */
+	u32 sge_length;         /* length of the SGE */
+	u32 length;             /* remaining length of the segment */
+	u16 m;                  /* current index: mr->map[m] */
+	u16 n;                  /* current index: mr->map[m]->segs[n] */
+};
+
+struct rvt_sge_state {
+	struct rvt_sge *sg_list;      /* next SGE to be used if any */
+	struct rvt_sge sge;   /* progress state for the current SGE */
+	u32 total_len;
+	u8 num_sge;
+};
+
+static inline void rvt_put_mr(struct rvt_mregion *mr)
+{
+	if (unlikely(atomic_dec_and_test(&mr->refcount)))
+		complete(&mr->comp);
+}
+
+static inline void rvt_get_mr(struct rvt_mregion *mr)
+{
+	atomic_inc(&mr->refcount);
+}
+
+static inline void rvt_put_ss(struct rvt_sge_state *ss)
+{
+	while (ss->num_sge) {
+		rvt_put_mr(ss->sge.mr);
+		if (--ss->num_sge)
+			ss->sge = *ss->sg_list++;
+	}
+}
+
+#endif          /* DEF_RDMAVT_INCMRH */
diff --git a/sys/ofed/include/rdma/rdmavt_qp.h b/sys/ofed/include/rdma/rdmavt_qp.h
new file mode 100644
index 000000000000..2c5183ef0243
--- /dev/null
+++ b/sys/ofed/include/rdma/rdmavt_qp.h
@@ -0,0 +1,535 @@
+#ifndef DEF_RDMAVT_INCQP_H
+#define DEF_RDMAVT_INCQP_H
+
+/*
+ * Copyright(c) 2016 Intel Corporation.
+ *
+ * This file is provided under a dual BSD/GPLv2 license.  When using or
+ * redistributing this file, you may do so under either license.
+ *
+ * GPL LICENSE SUMMARY
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * BSD LICENSE
+ *
+ * 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.
+ *  - Neither the name of Intel Corporation nor the names of its
+ *    contributors may be used to endorse or promote products derived
+ *    from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+ * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+ * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+ * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+ * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+ * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+ * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+ * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+ * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+ * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ *
+ */
+
+#include <rdma/rdma_vt.h>
+#include <rdma/ib_pack.h>
+#include <rdma/ib_verbs.h>
+/*
+ * Atomic bit definitions for r_aflags.
+ */
+#define RVT_R_WRID_VALID        0
+#define RVT_R_REWIND_SGE        1
+
+/*
+ * Bit definitions for r_flags.
+ */
+#define RVT_R_REUSE_SGE 0x01
+#define RVT_R_RDMAR_SEQ 0x02
+#define RVT_R_RSP_NAK   0x04
+#define RVT_R_RSP_SEND  0x08
+#define RVT_R_COMM_EST  0x10
+
+/*
+ * Bit definitions for s_flags.
+ *
+ * RVT_S_SIGNAL_REQ_WR - set if QP send WRs contain completion signaled
+ * RVT_S_BUSY - send tasklet is processing the QP
+ * RVT_S_TIMER - the RC retry timer is active
+ * RVT_S_ACK_PENDING - an ACK is waiting to be sent after RDMA read/atomics
+ * RVT_S_WAIT_FENCE - waiting for all prior RDMA read or atomic SWQEs
+ *                         before processing the next SWQE
+ * RVT_S_WAIT_RDMAR - waiting for a RDMA read or atomic SWQE to complete
+ *                         before processing the next SWQE
+ * RVT_S_WAIT_RNR - waiting for RNR timeout
+ * RVT_S_WAIT_SSN_CREDIT - waiting for RC credits to process next SWQE
+ * RVT_S_WAIT_DMA - waiting for send DMA queue to drain before generating
+ *                  next send completion entry not via send DMA
+ * RVT_S_WAIT_PIO - waiting for a send buffer to be available
+ * RVT_S_WAIT_PIO_DRAIN - waiting for a qp to drain pio packets
+ * RVT_S_WAIT_TX - waiting for a struct verbs_txreq to be available
+ * RVT_S_WAIT_DMA_DESC - waiting for DMA descriptors to be available
+ * RVT_S_WAIT_KMEM - waiting for kernel memory to be available
+ * RVT_S_WAIT_PSN - waiting for a packet to exit the send DMA queue
+ * RVT_S_WAIT_ACK - waiting for an ACK packet before sending more requests
+ * RVT_S_SEND_ONE - send one packet, request ACK, then wait for ACK
+ * RVT_S_ECN - a BECN was queued to the send engine
+ */
+#define RVT_S_SIGNAL_REQ_WR	0x0001
+#define RVT_S_BUSY		0x0002
+#define RVT_S_TIMER		0x0004
+#define RVT_S_RESP_PENDING	0x0008
+#define RVT_S_ACK_PENDING	0x0010
+#define RVT_S_WAIT_FENCE	0x0020
+#define RVT_S_WAIT_RDMAR	0x0040
+#define RVT_S_WAIT_RNR		0x0080
+#define RVT_S_WAIT_SSN_CREDIT	0x0100
+#define RVT_S_WAIT_DMA		0x0200
+#define RVT_S_WAIT_PIO		0x0400
+#define RVT_S_WAIT_PIO_DRAIN    0x0800
+#define RVT_S_WAIT_TX		0x1000
+#define RVT_S_WAIT_DMA_DESC	0x2000
+#define RVT_S_WAIT_KMEM		0x4000
+#define RVT_S_WAIT_PSN		0x8000
+#define RVT_S_WAIT_ACK		0x10000
+#define RVT_S_SEND_ONE		0x20000
+#define RVT_S_UNLIMITED_CREDIT	0x40000
+#define RVT_S_AHG_VALID		0x80000
+#define RVT_S_AHG_CLEAR		0x100000
+#define RVT_S_ECN		0x200000
+
+/*
+ * Wait flags that would prevent any packet type from being sent.
+ */
+#define RVT_S_ANY_WAIT_IO \
+	(RVT_S_WAIT_PIO | RVT_S_WAIT_PIO_DRAIN | RVT_S_WAIT_TX | \
+	 RVT_S_WAIT_DMA_DESC | RVT_S_WAIT_KMEM)
+
+/*
+ * Wait flags that would prevent send work requests from making progress.
+ */
+#define RVT_S_ANY_WAIT_SEND (RVT_S_WAIT_FENCE | RVT_S_WAIT_RDMAR | \
+	RVT_S_WAIT_RNR | RVT_S_WAIT_SSN_CREDIT | RVT_S_WAIT_DMA | \
+	RVT_S_WAIT_PSN | RVT_S_WAIT_ACK)
+
+#define RVT_S_ANY_WAIT (RVT_S_ANY_WAIT_IO | RVT_S_ANY_WAIT_SEND)
+
+/* Number of bits to pay attention to in the opcode for checking qp type */
+#define RVT_OPCODE_QP_MASK 0xE0
+
+/* Flags for checking QP state (see ib_rvt_state_ops[]) */
+#define RVT_POST_SEND_OK                0x01
+#define RVT_POST_RECV_OK                0x02
+#define RVT_PROCESS_RECV_OK             0x04
+#define RVT_PROCESS_SEND_OK             0x08
+#define RVT_PROCESS_NEXT_SEND_OK        0x10
+#define RVT_FLUSH_SEND			0x20
+#define RVT_FLUSH_RECV			0x40
+#define RVT_PROCESS_OR_FLUSH_SEND \
+	(RVT_PROCESS_SEND_OK | RVT_FLUSH_SEND)
+
+/*
+ * Internal send flags
+ */
+#define RVT_SEND_RESERVE_USED           IB_SEND_RESERVED_START
+#define RVT_SEND_COMPLETION_ONLY	(IB_SEND_RESERVED_START << 1)
+
+/*
+ * Send work request queue entry.
+ * The size of the sg_list is determined when the QP is created and stored
+ * in qp->s_max_sge.
+ */
+struct rvt_swqe {
+	union {
+		struct ib_send_wr wr;   /* don't use wr.sg_list */
+		struct ib_ud_wr ud_wr;
+		struct ib_reg_wr reg_wr;
+		struct ib_rdma_wr rdma_wr;
+		struct ib_atomic_wr atomic_wr;
+	};
+	u32 psn;                /* first packet sequence number */
+	u32 lpsn;               /* last packet sequence number */
+	u32 ssn;                /* send sequence number */
+	u32 length;             /* total length of data in sg_list */
+	struct rvt_sge sg_list[0];
+};
+
+/*
+ * Receive work request queue entry.
+ * The size of the sg_list is determined when the QP (or SRQ) is created
+ * and stored in qp->r_rq.max_sge (or srq->rq.max_sge).
+ */
+struct rvt_rwqe {
+	u64 wr_id;
+	u8 num_sge;
+	struct ib_sge sg_list[0];
+};
+
+/*
+ * This structure is used to contain the head pointer, tail pointer,
+ * and receive work queue entries as a single memory allocation so
+ * it can be mmap'ed into user space.
+ * Note that the wq array elements are variable size so you can't
+ * just index into the array to get the N'th element;
+ * use get_rwqe_ptr() instead.
+ */
+struct rvt_rwq {
+	u32 head;               /* new work requests posted to the head */
+	u32 tail;               /* receives pull requests from here. */
+	struct rvt_rwqe wq[0];
+};
+
+struct rvt_rq {
+	struct rvt_rwq *wq;
+	u32 size;               /* size of RWQE array */
+	u8 max_sge;
+	/* protect changes in this struct */
+	spinlock_t lock ____cacheline_aligned_in_smp;
+};
+
+/*
+ * This structure is used by rvt_mmap() to validate an offset
+ * when an mmap() request is made.  The vm_area_struct then uses
+ * this as its vm_private_data.
+ */
+struct rvt_mmap_info {
+	struct list_head pending_mmaps;
+	struct ib_ucontext *context;
+	void *obj;
+	__u64 offset;
+	struct kref ref;
+	unsigned size;
+};
+
+/*
+ * This structure holds the information that the send tasklet needs
+ * to send a RDMA read response or atomic operation.
+ */
+struct rvt_ack_entry {
+	struct rvt_sge rdma_sge;
+	u64 atomic_data;
+	u32 psn;
+	u32 lpsn;
+	u8 opcode;
+	u8 sent;
+};
+
+#define	RC_QP_SCALING_INTERVAL	5
+
+#define RVT_OPERATION_PRIV        0x00000001
+#define RVT_OPERATION_ATOMIC      0x00000002
+#define RVT_OPERATION_ATOMIC_SGE  0x00000004
+#define RVT_OPERATION_LOCAL       0x00000008
+#define RVT_OPERATION_USE_RESERVE 0x00000010
+
+#define RVT_OPERATION_MAX (IB_WR_RESERVED10 + 1)
+
+/**
+ * rvt_operation_params - op table entry
+ * @length - the length to copy into the swqe entry
+ * @qpt_support - a bit mask indicating QP type support
+ * @flags - RVT_OPERATION flags (see above)
+ *
+ * This supports table driven post send so that
+ * the driver can have differing an potentially
+ * different sets of operations.
+ *
+ **/
+
+struct rvt_operation_params {
+	size_t length;
+	u32 qpt_support;
+	u32 flags;
+};
+
+/*
+ * Common variables are protected by both r_rq.lock and s_lock in that order
+ * which only happens in modify_qp() or changing the QP 'state'.
+ */
+struct rvt_qp {
+	struct ib_qp ibqp;
+	void *priv; /* Driver private data */
+	/* read mostly fields above and below */
+	struct ib_ah_attr remote_ah_attr;
+	struct ib_ah_attr alt_ah_attr;
+	struct rvt_qp __rcu *next;           /* link list for QPN hash table */
+	struct rvt_swqe *s_wq;  /* send work queue */
+	struct rvt_mmap_info *ip;
+
+	unsigned long timeout_jiffies;  /* computed from timeout */
+
+	enum ib_mtu path_mtu;
+	int srate_mbps;		/* s_srate (below) converted to Mbit/s */
+	pid_t pid;		/* pid for user mode QPs */
+	u32 remote_qpn;
+	u32 qkey;               /* QKEY for this QP (for UD or RD) */
+	u32 s_size;             /* send work queue size */
+	u32 s_ahgpsn;           /* set to the psn in the copy of the header */
+
+	u16 pmtu;		/* decoded from path_mtu */
+	u8 log_pmtu;		/* shift for pmtu */
+	u8 state;               /* QP state */
+	u8 allowed_ops;		/* high order bits of allowed opcodes */
+	u8 qp_access_flags;
+	u8 alt_timeout;         /* Alternate path timeout for this QP */
+	u8 timeout;             /* Timeout for this QP */
+	u8 s_srate;
+	u8 s_mig_state;
+	u8 port_num;
+	u8 s_pkey_index;        /* PKEY index to use */
+	u8 s_alt_pkey_index;    /* Alternate path PKEY index to use */
+	u8 r_max_rd_atomic;     /* max number of RDMA read/atomic to receive */
+	u8 s_max_rd_atomic;     /* max number of RDMA read/atomic to send */
+	u8 s_retry_cnt;         /* number of times to retry */
+	u8 s_rnr_retry_cnt;
+	u8 r_min_rnr_timer;     /* retry timeout value for RNR NAKs */
+	u8 s_max_sge;           /* size of s_wq->sg_list */
+	u8 s_draining;
+
+	/* start of read/write fields */
+	atomic_t refcount ____cacheline_aligned_in_smp;
+	wait_queue_head_t wait;
+
+	struct rvt_ack_entry *s_ack_queue;
+	struct rvt_sge_state s_rdma_read_sge;
+
+	spinlock_t r_lock ____cacheline_aligned_in_smp;      /* used for APM */
+	u32 r_psn;              /* expected rcv packet sequence number */
+	unsigned long r_aflags;
+	u64 r_wr_id;            /* ID for current receive WQE */
+	u32 r_ack_psn;          /* PSN for next ACK or atomic ACK */
+	u32 r_len;              /* total length of r_sge */
+	u32 r_rcv_len;          /* receive data len processed */
+	u32 r_msn;              /* message sequence number */
+
+	u8 r_state;             /* opcode of last packet received */
+	u8 r_flags;
+	u8 r_head_ack_queue;    /* index into s_ack_queue[] */
+
+	struct list_head rspwait;       /* link for waiting to respond */
+
+	struct rvt_sge_state r_sge;     /* current receive data */
+	struct rvt_rq r_rq;             /* receive work queue */
+
+	/* post send line */
+	spinlock_t s_hlock ____cacheline_aligned_in_smp;
+	u32 s_head;             /* new entries added here */
+	u32 s_next_psn;         /* PSN for next request */
+	u32 s_avail;            /* number of entries avail */
+	u32 s_ssn;              /* SSN of tail entry */
+	atomic_t s_reserved_used; /* reserved entries in use */
+
+	spinlock_t s_lock ____cacheline_aligned_in_smp;
+	u32 s_flags;
+	struct rvt_sge_state *s_cur_sge;
+	struct rvt_swqe *s_wqe;
+	struct rvt_sge_state s_sge;     /* current send request data */
+	struct rvt_mregion *s_rdma_mr;
+	u32 s_cur_size;         /* size of send packet in bytes */
+	u32 s_len;              /* total length of s_sge */
+	u32 s_rdma_read_len;    /* total length of s_rdma_read_sge */
+	u32 s_last_psn;         /* last response PSN processed */
+	u32 s_sending_psn;      /* lowest PSN that is being sent */
+	u32 s_sending_hpsn;     /* highest PSN that is being sent */
+	u32 s_psn;              /* current packet sequence number */
+	u32 s_ack_rdma_psn;     /* PSN for sending RDMA read responses */
+	u32 s_ack_psn;          /* PSN for acking sends and RDMA writes */
+	u32 s_tail;             /* next entry to process */
+	u32 s_cur;              /* current work queue entry */
+	u32 s_acked;            /* last un-ACK'ed entry */
+	u32 s_last;             /* last completed entry */
+	u32 s_lsn;              /* limit sequence number (credit) */
+	u16 s_hdrwords;         /* size of s_hdr in 32 bit words */
+	u16 s_rdma_ack_cnt;
+	s8 s_ahgidx;
+	u8 s_state;             /* opcode of last packet sent */
+	u8 s_ack_state;         /* opcode of packet to ACK */
+	u8 s_nak_state;         /* non-zero if NAK is pending */
+	u8 r_nak_state;         /* non-zero if NAK is pending */
+	u8 s_retry;             /* requester retry counter */
+	u8 s_rnr_retry;         /* requester RNR retry counter */
+	u8 s_num_rd_atomic;     /* number of RDMA read/atomic pending */
+	u8 s_tail_ack_queue;    /* index into s_ack_queue[] */
+
+	struct rvt_sge_state s_ack_rdma_sge;
+	struct timer_list s_timer;
+
+	atomic_t local_ops_pending; /* number of fast_reg/local_inv reqs */
+
+	/*
+	 * This sge list MUST be last. Do not add anything below here.
+	 */
+	struct rvt_sge r_sg_list[0] /* verified SGEs */
+		____cacheline_aligned_in_smp;
+};
+
+struct rvt_srq {
+	struct ib_srq ibsrq;
+	struct rvt_rq rq;
+	struct rvt_mmap_info *ip;
+	/* send signal when number of RWQEs < limit */
+	u32 limit;
+};
+
+#define RVT_QPN_MAX                 BIT(24)
+#define RVT_QPNMAP_ENTRIES          (RVT_QPN_MAX / PAGE_SIZE / BITS_PER_BYTE)
+#define RVT_BITS_PER_PAGE           (PAGE_SIZE * BITS_PER_BYTE)
+#define RVT_BITS_PER_PAGE_MASK      (RVT_BITS_PER_PAGE - 1)
+#define RVT_QPN_MASK		    0xFFFFFF
+
+/*
+ * QPN-map pages start out as NULL, they get allocated upon
+ * first use and are never deallocated. This way,
+ * large bitmaps are not allocated unless large numbers of QPs are used.
+ */
+struct rvt_qpn_map {
+	void *page;
+};
+
+struct rvt_qpn_table {
+	spinlock_t lock; /* protect changes to the qp table */
+	unsigned flags;         /* flags for QP0/1 allocated for each port */
+	u32 last;               /* last QP number allocated */
+	u32 nmaps;              /* size of the map table */
+	u16 limit;
+	u8  incr;
+	/* bit map of free QP numbers other than 0/1 */
+	struct rvt_qpn_map map[RVT_QPNMAP_ENTRIES];
+};
+
+struct rvt_qp_ibdev {
+	u32 qp_table_size;
+	u32 qp_table_bits;
+	struct rvt_qp __rcu **qp_table;
+	spinlock_t qpt_lock; /* qptable lock */
+	struct rvt_qpn_table qpn_table;
+};
+
+/*
+ * There is one struct rvt_mcast for each multicast GID.
+ * All attached QPs are then stored as a list of
+ * struct rvt_mcast_qp.
+ */
+struct rvt_mcast_qp {
+	struct list_head list;
+	struct rvt_qp *qp;
+};
+
+struct rvt_mcast {
+	struct rb_node rb_node;
+	union ib_gid mgid;
+	struct list_head qp_list;
+	wait_queue_head_t wait;
+	atomic_t refcount;
+	int n_attached;
+};
+
+/*
+ * Since struct rvt_swqe is not a fixed size, we can't simply index into
+ * struct rvt_qp.s_wq.  This function does the array index computation.
+ */
+static inline struct rvt_swqe *rvt_get_swqe_ptr(struct rvt_qp *qp,
+						unsigned n)
+{
+	return (struct rvt_swqe *)((char *)qp->s_wq +
+				     (sizeof(struct rvt_swqe) +
+				      qp->s_max_sge *
+				      sizeof(struct rvt_sge)) * n);
+}
+
+/*
+ * Since struct rvt_rwqe is not a fixed size, we can't simply index into
+ * struct rvt_rwq.wq.  This function does the array index computation.
+ */
+static inline struct rvt_rwqe *rvt_get_rwqe_ptr(struct rvt_rq *rq, unsigned n)
+{
+	return (struct rvt_rwqe *)
+		((char *)rq->wq->wq +
+		 (sizeof(struct rvt_rwqe) +
+		  rq->max_sge * sizeof(struct ib_sge)) * n);
+}
+
+/**
+ * rvt_get_qp - get a QP reference
+ * @qp - the QP to hold
+ */
+static inline void rvt_get_qp(struct rvt_qp *qp)
+{
+	atomic_inc(&qp->refcount);
+}
+
+/**
+ * rvt_put_qp - release a QP reference
+ * @qp - the QP to release
+ */
+static inline void rvt_put_qp(struct rvt_qp *qp)
+{
+	if (qp && atomic_dec_and_test(&qp->refcount))
+		wake_up(&qp->wait);
+}
+
+/**
+ * rvt_qp_wqe_reserve - reserve operation
+ * @qp - the rvt qp
+ * @wqe - the send wqe
+ *
+ * This routine used in post send to record
+ * a wqe relative reserved operation use.
+ */
+static inline void rvt_qp_wqe_reserve(
+	struct rvt_qp *qp,
+	struct rvt_swqe *wqe)
+{
+	wqe->wr.send_flags |= RVT_SEND_RESERVE_USED;
+	atomic_inc(&qp->s_reserved_used);
+}
+
+/**
+ * rvt_qp_wqe_unreserve - clean reserved operation
+ * @qp - the rvt qp
+ * @wqe - the send wqe
+ *
+ * This decrements the reserve use count.
+ *
+ * This call MUST precede the change to
+ * s_last to insure that post send sees a stable
+ * s_avail.
+ *
+ * An smp_mp__after_atomic() is used to insure
+ * the compiler does not juggle the order of the s_last
+ * ring index and the decrementing of s_reserved_used.
+ */
+static inline void rvt_qp_wqe_unreserve(
+	struct rvt_qp *qp,
+	struct rvt_swqe *wqe)
+{
+	if (unlikely(wqe->wr.send_flags & RVT_SEND_RESERVE_USED)) {
+		wqe->wr.send_flags &= ~RVT_SEND_RESERVE_USED;
+		atomic_dec(&qp->s_reserved_used);
+		/* insure no compiler re-order up to s_last change */
+		smp_mb__after_atomic();
+	}
+}
+
+extern const int  ib_rvt_state_ops[];
+
+struct rvt_dev_info;
+int rvt_error_qp(struct rvt_qp *qp, enum ib_wc_status err);
+
+#endif          /* DEF_RDMAVT_INCQP_H */
diff --git a/sys/ofed/include/rdma/sdp_socket.h b/sys/ofed/include/rdma/sdp_socket.h
deleted file mode 100644
index 6b075892968e..000000000000
--- a/sys/ofed/include/rdma/sdp_socket.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* Stuff that should go into include/linux/socket.h */
-
-#ifndef SDP_SOCKET_H
-#define SDP_SOCKET_H
-
-#ifndef __FreeBSD__
-#ifndef AF_INET_SDP
-#define AF_INET_SDP 27
-#define PF_INET_SDP AF_INET_SDP
-#endif
-#endif
-
-#ifndef SDP_ZCOPY_THRESH
-#define SDP_ZCOPY_THRESH 80
-#endif
-
-#ifndef SDP_LAST_BIND_ERR
-#define SDP_LAST_BIND_ERR 81
-#endif
-
-/* TODO: AF_INET6_SDP ? */
-
-#endif
diff --git a/sys/ofed/include/uapi/rdma/mlx4-abi.h b/sys/ofed/include/uapi/rdma/mlx4-abi.h
new file mode 100644
index 000000000000..af431752655c
--- /dev/null
+++ b/sys/ofed/include/uapi/rdma/mlx4-abi.h
@@ -0,0 +1,107 @@
+/*
+ * Copyright (c) 2007 Cisco Systems, Inc. All rights reserved.
+ * Copyright (c) 2007, 2008 Mellanox Technologies. 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 MLX4_ABI_USER_H
+#define MLX4_ABI_USER_H
+
+#include <linux/types.h>
+
+/*
+ * Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+
+#define MLX4_IB_UVERBS_NO_DEV_CAPS_ABI_VERSION	3
+#define MLX4_IB_UVERBS_ABI_VERSION		4
+
+/*
+ * Make sure that all structs defined in this file remain laid out so
+ * that they pack the same way on 32-bit and 64-bit architectures (to
+ * avoid incompatibility between 32-bit userspace and 64-bit kernels).
+ * In particular do not use pointer types -- pass pointers in __u64
+ * instead.
+ */
+
+struct mlx4_ib_alloc_ucontext_resp_v3 {
+	__u32	qp_tab_size;
+	__u16	bf_reg_size;
+	__u16	bf_regs_per_page;
+};
+
+struct mlx4_ib_alloc_ucontext_resp {
+	__u32	dev_caps;
+	__u32	qp_tab_size;
+	__u16	bf_reg_size;
+	__u16	bf_regs_per_page;
+	__u32	cqe_size;
+};
+
+struct mlx4_ib_alloc_pd_resp {
+	__u32	pdn;
+	__u32	reserved;
+};
+
+struct mlx4_ib_create_cq {
+	__u64	buf_addr;
+	__u64	db_addr;
+};
+
+struct mlx4_ib_create_cq_resp {
+	__u32	cqn;
+	__u32	reserved;
+};
+
+struct mlx4_ib_resize_cq {
+	__u64	buf_addr;
+};
+
+struct mlx4_ib_create_srq {
+	__u64	buf_addr;
+	__u64	db_addr;
+};
+
+struct mlx4_ib_create_srq_resp {
+	__u32	srqn;
+	__u32	reserved;
+};
+
+struct mlx4_ib_create_qp {
+	__u64	buf_addr;
+	__u64	db_addr;
+	__u8	log_sq_bb_count;
+	__u8	log_sq_stride;
+	__u8	sq_no_prefetch;
+	__u8	reserved[5];
+};
+
+#endif /* MLX4_ABI_USER_H */
diff --git a/sys/ofed/include/uapi/rdma/mlx5-abi.h b/sys/ofed/include/uapi/rdma/mlx5-abi.h
new file mode 100644
index 000000000000..f5d0f4e83b59
--- /dev/null
+++ b/sys/ofed/include/uapi/rdma/mlx5-abi.h
@@ -0,0 +1,249 @@
+/*
+ * Copyright (c) 2013-2015, Mellanox Technologies. 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 MLX5_ABI_USER_H
+#define MLX5_ABI_USER_H
+
+#include <linux/types.h>
+
+enum {
+	MLX5_QP_FLAG_SIGNATURE		= 1 << 0,
+	MLX5_QP_FLAG_SCATTER_CQE	= 1 << 1,
+};
+
+enum {
+	MLX5_SRQ_FLAG_SIGNATURE		= 1 << 0,
+};
+
+enum {
+	MLX5_WQ_FLAG_SIGNATURE		= 1 << 0,
+};
+
+/* Increment this value if any changes that break userspace ABI
+ * compatibility are made.
+ */
+#define MLX5_IB_UVERBS_ABI_VERSION	1
+
+/* Make sure that all structs defined in this file remain laid out so
+ * that they pack the same way on 32-bit and 64-bit architectures (to
+ * avoid incompatibility between 32-bit userspace and 64-bit kernels).
+ * In particular do not use pointer types -- pass pointers in __u64
+ * instead.
+ */
+
+struct mlx5_ib_alloc_ucontext_req {
+	__u32	total_num_uuars;
+	__u32	num_low_latency_uuars;
+};
+
+struct mlx5_ib_alloc_ucontext_req_v2 {
+	__u32	total_num_uuars;
+	__u32	num_low_latency_uuars;
+	__u32	flags;
+	__u32	comp_mask;
+	__u8	max_cqe_version;
+	__u8	reserved0;
+	__u16	reserved1;
+	__u32	reserved2;
+};
+
+enum mlx5_ib_alloc_ucontext_resp_mask {
+	MLX5_IB_ALLOC_UCONTEXT_RESP_MASK_CORE_CLOCK_OFFSET = 1UL << 0,
+};
+
+enum mlx5_user_cmds_supp_uhw {
+	MLX5_USER_CMDS_SUPP_UHW_QUERY_DEVICE = 1 << 0,
+};
+
+struct mlx5_ib_alloc_ucontext_resp {
+	__u32	qp_tab_size;
+	__u32	bf_reg_size;
+	__u32	tot_uuars;
+	__u32	cache_line_size;
+	__u16	max_sq_desc_sz;
+	__u16	max_rq_desc_sz;
+	__u32	max_send_wqebb;
+	__u32	max_recv_wr;
+	__u32	max_srq_recv_wr;
+	__u16	num_ports;
+	__u16	reserved1;
+	__u32	comp_mask;
+	__u32	response_length;
+	__u8	cqe_version;
+	__u8	cmds_supp_uhw;
+	__u16	reserved2;
+	__u64	hca_core_clock_offset;
+};
+
+struct mlx5_ib_alloc_pd_resp {
+	__u32	pdn;
+};
+
+struct mlx5_ib_tso_caps {
+	__u32 max_tso; /* Maximum tso payload size in bytes */
+
+	/* Corresponding bit will be set if qp type from
+	 * 'enum ib_qp_type' is supported, e.g.
+	 * supported_qpts |= 1 << IB_QPT_UD
+	 */
+	__u32 supported_qpts;
+};
+
+struct mlx5_ib_rss_caps {
+	__u64 rx_hash_fields_mask; /* enum mlx5_rx_hash_fields */
+	__u8 rx_hash_function; /* enum mlx5_rx_hash_function_flags */
+	__u8 reserved[7];
+};
+
+struct mlx5_ib_query_device_resp {
+	__u32	comp_mask;
+	__u32	response_length;
+	struct	mlx5_ib_tso_caps tso_caps;
+	struct	mlx5_ib_rss_caps rss_caps;
+};
+
+struct mlx5_ib_create_cq {
+	__u64	buf_addr;
+	__u64	db_addr;
+	__u32	cqe_size;
+	__u32	reserved; /* explicit padding (optional on i386) */
+};
+
+struct mlx5_ib_create_cq_resp {
+	__u32	cqn;
+	__u32	reserved;
+};
+
+struct mlx5_ib_resize_cq {
+	__u64	buf_addr;
+	__u16	cqe_size;
+	__u16	reserved0;
+	__u32	reserved1;
+};
+
+struct mlx5_ib_create_srq {
+	__u64	buf_addr;
+	__u64	db_addr;
+	__u32	flags;
+	__u32	reserved0; /* explicit padding (optional on i386) */
+	__u32	uidx;
+	__u32	reserved1;
+};
+
+struct mlx5_ib_create_srq_resp {
+	__u32	srqn;
+	__u32	reserved;
+};
+
+struct mlx5_ib_create_qp {
+	__u64	buf_addr;
+	__u64	db_addr;
+	__u32	sq_wqe_count;
+	__u32	rq_wqe_count;
+	__u32	rq_wqe_shift;
+	__u32	flags;
+	__u32	uidx;
+	__u32	reserved0;
+	__u64	sq_buf_addr;
+};
+
+/* RX Hash function flags */
+enum mlx5_rx_hash_function_flags {
+	MLX5_RX_HASH_FUNC_TOEPLITZ	= 1 << 0,
+};
+
+/*
+ * RX Hash flags, these flags allows to set which incoming packet's field should
+ * participates in RX Hash. Each flag represent certain packet's field,
+ * when the flag is set the field that is represented by the flag will
+ * participate in RX Hash calculation.
+ * Note: *IPV4 and *IPV6 flags can't be enabled together on the same QP
+ * and *TCP and *UDP flags can't be enabled together on the same QP.
+*/
+enum mlx5_rx_hash_fields {
+	MLX5_RX_HASH_SRC_IPV4	= 1 << 0,
+	MLX5_RX_HASH_DST_IPV4	= 1 << 1,
+	MLX5_RX_HASH_SRC_IPV6	= 1 << 2,
+	MLX5_RX_HASH_DST_IPV6	= 1 << 3,
+	MLX5_RX_HASH_SRC_PORT_TCP	= 1 << 4,
+	MLX5_RX_HASH_DST_PORT_TCP	= 1 << 5,
+	MLX5_RX_HASH_SRC_PORT_UDP	= 1 << 6,
+	MLX5_RX_HASH_DST_PORT_UDP	= 1 << 7
+};
+
+struct mlx5_ib_create_qp_rss {
+	__u64 rx_hash_fields_mask; /* enum mlx5_rx_hash_fields */
+	__u8 rx_hash_function; /* enum mlx5_rx_hash_function_flags */
+	__u8 rx_key_len; /* valid only for Toeplitz */
+	__u8 reserved[6];
+	__u8 rx_hash_key[128]; /* valid only for Toeplitz */
+	__u32   comp_mask;
+	__u32   reserved1;
+};
+
+struct mlx5_ib_create_qp_resp {
+	__u32	uuar_index;
+};
+
+struct mlx5_ib_alloc_mw {
+	__u32	comp_mask;
+	__u8	num_klms;
+	__u8	reserved1;
+	__u16	reserved2;
+};
+
+struct mlx5_ib_create_wq {
+	__u64   buf_addr;
+	__u64   db_addr;
+	__u32   rq_wqe_count;
+	__u32   rq_wqe_shift;
+	__u32   user_index;
+	__u32   flags;
+	__u32   comp_mask;
+	__u32   reserved;
+};
+
+struct mlx5_ib_create_wq_resp {
+	__u32	response_length;
+	__u32	reserved;
+};
+
+struct mlx5_ib_create_rwq_ind_tbl_resp {
+	__u32	response_length;
+	__u32	reserved;
+};
+
+struct mlx5_ib_modify_wq {
+	__u32	comp_mask;
+	__u32	reserved;
+};
+#endif /* MLX5_ABI_USER_H */