8 files changed, 714 insertions, 211 deletions

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 26987d9d7e1c..edaae9f9853c 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -1,8 +1,7 @@
 infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_cm.o
 user_access-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_ucm.o
 
-obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_mad.o ib_sa.o \
-					ib_cm.o iw_cm.o ib_addr.o \
+obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_cm.o iw_cm.o \
 					$(infiniband-y)
 obj-$(CONFIG_INFINIBAND_USER_MAD) +=	ib_umad.o
 obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
@@ -10,14 +9,11 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 
 ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
-				roce_gid_mgmt.o mr_pool.o
+				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
+				multicast.o mad.o smi.o agent.o mad_rmpp.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 
-ib_mad-y :=			mad.o smi.o agent.o mad_rmpp.o
-
-ib_sa-y :=			sa_query.o multicast.o
-
 ib_cm-y :=			cm.o
 
 iw_cm-y :=			iwcm.o iwpm_util.o iwpm_msg.o
@@ -28,8 +24,6 @@ rdma_cm-$(CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS) += cma_configfs.o
 
 rdma_ucm-y :=			ucma.o
 
-ib_addr-y :=			addr.o
-
 ib_umad-y :=			user_mad.o
 
 ib_ucm-y :=			ucm.o
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 337353d86cfa..1374541a4528 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -46,10 +46,10 @@
 #include <net/ip6_route.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib.h>
+#include <rdma/rdma_netlink.h>
+#include <net/netlink.h>
 
-MODULE_AUTHOR("Sean Hefty");
-MODULE_DESCRIPTION("IB Address Translation");
-MODULE_LICENSE("Dual BSD/GPL");
+#include "core_priv.h"
 
 struct addr_req {
 	struct list_head list;
@@ -62,8 +62,11 @@ struct addr_req {
 			 struct rdma_dev_addr *addr, void *context);
 	unsigned long timeout;
 	int status;
+	u32 seq;
 };
 
+static atomic_t ib_nl_addr_request_seq = ATOMIC_INIT(0);
+
 static void process_req(struct work_struct *work);
 
 static DEFINE_MUTEX(lock);
@@ -71,6 +74,126 @@ static LIST_HEAD(req_list);
 static DECLARE_DELAYED_WORK(work, process_req);
 static struct workqueue_struct *addr_wq;
 
+static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = {
+	[LS_NLA_TYPE_DGID] = {.type = NLA_BINARY,
+		.len = sizeof(struct rdma_nla_ls_gid)},
+};
+
+static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
+{
+	struct nlattr *tb[LS_NLA_TYPE_MAX] = {};
+	int ret;
+
+	if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
+		return false;
+
+	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
+			nlmsg_len(nlh), ib_nl_addr_policy);
+	if (ret)
+		return false;
+
+	return true;
+}
+
+static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
+{
+	const struct nlattr *head, *curr;
+	union ib_gid gid;
+	struct addr_req *req;
+	int len, rem;
+	int found = 0;
+
+	head = (const struct nlattr *)nlmsg_data(nlh);
+	len = nlmsg_len(nlh);
+
+	nla_for_each_attr(curr, head, len, rem) {
+		if (curr->nla_type == LS_NLA_TYPE_DGID)
+			memcpy(&gid, nla_data(curr), nla_len(curr));
+	}
+
+	mutex_lock(&lock);
+	list_for_each_entry(req, &req_list, list) {
+		if (nlh->nlmsg_seq != req->seq)
+			continue;
+		/* We set the DGID part, the rest was set earlier */
+		rdma_addr_set_dgid(req->addr, &gid);
+		req->status = 0;
+		found = 1;
+		break;
+	}
+	mutex_unlock(&lock);
+
+	if (!found)
+		pr_info("Couldn't find request waiting for DGID: %pI6\n",
+			&gid);
+}
+
+int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
+			     struct netlink_callback *cb)
+{
+	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
+
+	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
+	    !(NETLINK_CB(skb).sk) ||
+	    !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (ib_nl_is_good_ip_resp(nlh))
+		ib_nl_process_good_ip_rsep(nlh);
+
+	return skb->len;
+}
+
+static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
+			     const void *daddr,
+			     u32 seq, u16 family)
+{
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	struct rdma_ls_ip_resolve_header *header;
+	void *data;
+	size_t size;
+	int attrtype;
+	int len;
+
+	if (family == AF_INET) {
+		size = sizeof(struct in_addr);
+		attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV4;
+	} else {
+		size = sizeof(struct in6_addr);
+		attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV6;
+	}
+
+	len = nla_total_size(sizeof(size));
+	len += NLMSG_ALIGN(sizeof(*header));
+
+	skb = nlmsg_new(len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	data = ibnl_put_msg(skb, &nlh, seq, 0, RDMA_NL_LS,
+			    RDMA_NL_LS_OP_IP_RESOLVE, NLM_F_REQUEST);
+	if (!data) {
+		nlmsg_free(skb);
+		return -ENODATA;
+	}
+
+	/* Construct the family header first */
+	header = (struct rdma_ls_ip_resolve_header *)
+		skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
+	header->ifindex = dev_addr->bound_dev_if;
+	nla_put(skb, attrtype, size, daddr);
+
+	/* Repair the nlmsg header length */
+	nlmsg_end(skb, nlh);
+	ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+
+	/* Make the request retry, so when we get the response from userspace
+	 * we will have something.
+	 */
+	return -ENODATA;
+}
+
 int rdma_addr_size(struct sockaddr *addr)
 {
 	switch (addr->sa_family) {
@@ -199,6 +322,17 @@ static void queue_req(struct addr_req *req)
 	mutex_unlock(&lock);
 }
 
+static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
+			  const void *daddr, u32 seq, u16 family)
+{
+	if (ibnl_chk_listeners(RDMA_NL_GROUP_LS))
+		return -EADDRNOTAVAIL;
+
+	/* We fill in what we can, the response will fill the rest */
+	rdma_copy_addr(dev_addr, dst->dev, NULL);
+	return ib_nl_ip_send_msg(dev_addr, daddr, seq, family);
+}
+
 static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
 			const void *daddr)
 {
@@ -223,6 +357,39 @@ static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
 	return ret;
 }
 
+static bool has_gateway(struct dst_entry *dst, sa_family_t family)
+{
+	struct rtable *rt;
+	struct rt6_info *rt6;
+
+	if (family == AF_INET) {
+		rt = container_of(dst, struct rtable, dst);
+		return rt->rt_uses_gateway;
+	}
+
+	rt6 = container_of(dst, struct rt6_info, dst);
+	return rt6->rt6i_flags & RTF_GATEWAY;
+}
+
+static int fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
+		    const struct sockaddr *dst_in, u32 seq)
+{
+	const struct sockaddr_in *dst_in4 =
+		(const struct sockaddr_in *)dst_in;
+	const struct sockaddr_in6 *dst_in6 =
+		(const struct sockaddr_in6 *)dst_in;
+	const void *daddr = (dst_in->sa_family == AF_INET) ?
+		(const void *)&dst_in4->sin_addr.s_addr :
+		(const void *)&dst_in6->sin6_addr;
+	sa_family_t family = dst_in->sa_family;
+
+	/* Gateway + ARPHRD_INFINIBAND -> IB router */
+	if (has_gateway(dst, family) && dst->dev->type == ARPHRD_INFINIBAND)
+		return ib_nl_fetch_ha(dst, dev_addr, daddr, seq, family);
+	else
+		return dst_fetch_ha(dst, dev_addr, daddr);
+}
+
 static int addr4_resolve(struct sockaddr_in *src_in,
 			 const struct sockaddr_in *dst_in,
 			 struct rdma_dev_addr *addr,
@@ -246,10 +413,11 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 	src_in->sin_family = AF_INET;
 	src_in->sin_addr.s_addr = fl4.saddr;
 
-	/* If there's a gateway, we're definitely in RoCE v2 (as RoCE v1 isn't
-	 * routable) and we could set the network type accordingly.
+	/* If there's a gateway and type of device not ARPHRD_INFINIBAND, we're
+	 * definitely in RoCE v2 (as RoCE v1 isn't routable) set the network
+	 * type accordingly.
 	 */
-	if (rt->rt_uses_gateway)
+	if (rt->rt_uses_gateway && rt->dst.dev->type != ARPHRD_INFINIBAND)
 		addr->network = RDMA_NETWORK_IPV4;
 
 	addr->hoplimit = ip4_dst_hoplimit(&rt->dst);
@@ -291,10 +459,12 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 		src_in->sin6_addr = fl6.saddr;
 	}
 
-	/* If there's a gateway, we're definitely in RoCE v2 (as RoCE v1 isn't
-	 * routable) and we could set the network type accordingly.
+	/* If there's a gateway and type of device not ARPHRD_INFINIBAND, we're
+	 * definitely in RoCE v2 (as RoCE v1 isn't routable) set the network
+	 * type accordingly.
 	 */
-	if (rt->rt6i_flags & RTF_GATEWAY)
+	if (rt->rt6i_flags & RTF_GATEWAY &&
+	    ip6_dst_idev(dst)->dev->type != ARPHRD_INFINIBAND)
 		addr->network = RDMA_NETWORK_IPV6;
 
 	addr->hoplimit = ip6_dst_hoplimit(dst);
@@ -317,7 +487,8 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 
 static int addr_resolve_neigh(struct dst_entry *dst,
 			      const struct sockaddr *dst_in,
-			      struct rdma_dev_addr *addr)
+			      struct rdma_dev_addr *addr,
+			      u32 seq)
 {
 	if (dst->dev->flags & IFF_LOOPBACK) {
 		int ret;
@@ -331,17 +502,8 @@ static int addr_resolve_neigh(struct dst_entry *dst,
 	}
 
 	/* If the device doesn't do ARP internally */
-	if (!(dst->dev->flags & IFF_NOARP)) {
-		const struct sockaddr_in *dst_in4 =
-			(const struct sockaddr_in *)dst_in;
-		const struct sockaddr_in6 *dst_in6 =
-			(const struct sockaddr_in6 *)dst_in;
-
-		return dst_fetch_ha(dst, addr,
-				    dst_in->sa_family == AF_INET ?
-				    (const void *)&dst_in4->sin_addr.s_addr :
-				    (const void *)&dst_in6->sin6_addr);
-	}
+	if (!(dst->dev->flags & IFF_NOARP))
+		return fetch_ha(dst, addr, dst_in, seq);
 
 	return rdma_copy_addr(addr, dst->dev, NULL);
 }
@@ -349,7 +511,8 @@ static int addr_resolve_neigh(struct dst_entry *dst,
 static int addr_resolve(struct sockaddr *src_in,
 			const struct sockaddr *dst_in,
 			struct rdma_dev_addr *addr,
-			bool resolve_neigh)
+			bool resolve_neigh,
+			u32 seq)
 {
 	struct net_device *ndev;
 	struct dst_entry *dst;
@@ -366,7 +529,7 @@ static int addr_resolve(struct sockaddr *src_in,
 			return ret;
 
 		if (resolve_neigh)
-			ret = addr_resolve_neigh(&rt->dst, dst_in, addr);
+			ret = addr_resolve_neigh(&rt->dst, dst_in, addr, seq);
 
 		ndev = rt->dst.dev;
 		dev_hold(ndev);
@@ -383,7 +546,7 @@ static int addr_resolve(struct sockaddr *src_in,
 			return ret;
 
 		if (resolve_neigh)
-			ret = addr_resolve_neigh(dst, dst_in, addr);
+			ret = addr_resolve_neigh(dst, dst_in, addr, seq);
 
 		ndev = dst->dev;
 		dev_hold(ndev);
@@ -412,7 +575,7 @@ static void process_req(struct work_struct *work)
 			src_in = (struct sockaddr *) &req->src_addr;
 			dst_in = (struct sockaddr *) &req->dst_addr;
 			req->status = addr_resolve(src_in, dst_in, req->addr,
-						   true);
+						   true, req->seq);
 			if (req->status && time_after_eq(jiffies, req->timeout))
 				req->status = -ETIMEDOUT;
 			else if (req->status == -ENODATA)
@@ -471,8 +634,9 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
 	req->context = context;
 	req->client = client;
 	atomic_inc(&client->refcount);
+	req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq);
 
-	req->status = addr_resolve(src_in, dst_in, addr, true);
+	req->status = addr_resolve(src_in, dst_in, addr, true, req->seq);
 	switch (req->status) {
 	case 0:
 		req->timeout = jiffies;
@@ -510,7 +674,7 @@ int rdma_resolve_ip_route(struct sockaddr *src_addr,
 		src_in->sa_family = dst_addr->sa_family;
 	}
 
-	return addr_resolve(src_in, dst_addr, addr, false);
+	return addr_resolve(src_in, dst_addr, addr, false, 0);
 }
 EXPORT_SYMBOL(rdma_resolve_ip_route);
 
@@ -634,7 +798,7 @@ static struct notifier_block nb = {
 	.notifier_call = netevent_callback
 };
 
-static int __init addr_init(void)
+int addr_init(void)
 {
 	addr_wq = create_singlethread_workqueue("ib_addr");
 	if (!addr_wq)
@@ -642,15 +806,13 @@ static int __init addr_init(void)
 
 	register_netevent_notifier(&nb);
 	rdma_addr_register_client(&self);
+
 	return 0;
 }
 
-static void __exit addr_cleanup(void)
+void addr_cleanup(void)
 {
 	rdma_addr_unregister_client(&self);
 	unregister_netevent_notifier(&nb);
 	destroy_workqueue(addr_wq);
 }
-
-module_init(addr_init);
-module_exit(addr_cleanup);
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index eab32215756b..19d499dcab76 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -137,4 +137,20 @@ static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
 	return _upper == upper;
 }
 
+int addr_init(void);
+void addr_cleanup(void);
+
+int ib_mad_init(void);
+void ib_mad_cleanup(void);
+
+int ib_sa_init(void);
+void ib_sa_cleanup(void);
+
+int ib_nl_handle_resolve_resp(struct sk_buff *skb,
+			      struct netlink_callback *cb);
+int ib_nl_handle_set_timeout(struct sk_buff *skb,
+			     struct netlink_callback *cb);
+int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
+			     struct netlink_callback *cb);
+
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 10979844026a..5516fb070344 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -955,6 +955,29 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
+static struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+	[RDMA_NL_LS_OP_RESOLVE] = {
+		.dump = ib_nl_handle_resolve_resp,
+		.module = THIS_MODULE },
+	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
+		.dump = ib_nl_handle_set_timeout,
+		.module = THIS_MODULE },
+	[RDMA_NL_LS_OP_IP_RESOLVE] = {
+		.dump = ib_nl_handle_ip_res_resp,
+		.module = THIS_MODULE },
+};
+
+static int ib_add_ibnl_clients(void)
+{
+	return ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ibnl_ls_cb_table),
+			       ibnl_ls_cb_table);
+}
+
+static void ib_remove_ibnl_clients(void)
+{
+	ibnl_remove_client(RDMA_NL_LS);
+}
+
 static int __init ib_core_init(void)
 {
 	int ret;
@@ -983,10 +1006,41 @@ static int __init ib_core_init(void)
 		goto err_sysfs;
 	}
 
+	ret = addr_init();
+	if (ret) {
+		pr_warn("Could't init IB address resolution\n");
+		goto err_ibnl;
+	}
+
+	ret = ib_mad_init();
+	if (ret) {
+		pr_warn("Couldn't init IB MAD\n");
+		goto err_addr;
+	}
+
+	ret = ib_sa_init();
+	if (ret) {
+		pr_warn("Couldn't init SA\n");
+		goto err_mad;
+	}
+
+	if (ib_add_ibnl_clients()) {
+		pr_warn("Couldn't register ibnl clients\n");
+		goto err_sa;
+	}
+
 	ib_cache_setup();
 
 	return 0;
 
+err_sa:
+	ib_sa_cleanup();
+err_mad:
+	ib_mad_cleanup();
+err_addr:
+	addr_cleanup();
+err_ibnl:
+	ibnl_cleanup();
 err_sysfs:
 	class_unregister(&ib_class);
 err_comp:
@@ -999,6 +1053,10 @@ err:
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	ib_remove_ibnl_clients();
+	ib_sa_cleanup();
+	ib_mad_cleanup();
+	addr_cleanup();
 	ibnl_cleanup();
 	class_unregister(&ib_class);
 	destroy_workqueue(ib_comp_wq);
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 9fa5bf33f5a3..82fb511112da 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -47,11 +47,7 @@
 #include "smi.h"
 #include "opa_smi.h"
 #include "agent.h"
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("kernel IB MAD API");
-MODULE_AUTHOR("Hal Rosenstock");
-MODULE_AUTHOR("Sean Hefty");
+#include "core_priv.h"
 
 static int mad_sendq_size = IB_MAD_QP_SEND_SIZE;
 static int mad_recvq_size = IB_MAD_QP_RECV_SIZE;
@@ -3316,7 +3312,7 @@ static struct ib_client mad_client = {
 	.remove = ib_mad_remove_device
 };
 
-static int __init ib_mad_init_module(void)
+int ib_mad_init(void)
 {
 	mad_recvq_size = min(mad_recvq_size, IB_MAD_QP_MAX_SIZE);
 	mad_recvq_size = max(mad_recvq_size, IB_MAD_QP_MIN_SIZE);
@@ -3334,10 +3330,7 @@ static int __init ib_mad_init_module(void)
 	return 0;
 }
 
-static void __exit ib_mad_cleanup_module(void)
+void ib_mad_cleanup(void)
 {
 	ib_unregister_client(&mad_client);
 }
-
-module_init(ib_mad_init_module);
-module_exit(ib_mad_cleanup_module);
diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index 250937cb9a1a..a83ec28a147b 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -93,6 +93,18 @@ enum {
 
 struct mcast_member;
 
+/*
+* There are 4 types of join states:
+* FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember.
+*/
+enum {
+	FULLMEMBER_JOIN,
+	NONMEMBER_JOIN,
+	SENDONLY_NONMEBER_JOIN,
+	SENDONLY_FULLMEMBER_JOIN,
+	NUM_JOIN_MEMBERSHIP_TYPES,
+};
+
 struct mcast_group {
 	struct ib_sa_mcmember_rec rec;
 	struct rb_node		node;
@@ -102,7 +114,7 @@ struct mcast_group {
 	struct list_head	pending_list;
 	struct list_head	active_list;
 	struct mcast_member	*last_join;
-	int			members[3];
+	int			members[NUM_JOIN_MEMBERSHIP_TYPES];
 	atomic_t		refcount;
 	enum mcast_group_state	state;
 	struct ib_sa_query	*query;
@@ -220,8 +232,9 @@ static void queue_join(struct mcast_member *member)
 }
 
 /*
- * A multicast group has three types of members: full member, non member, and
- * send only member.  We need to keep track of the number of members of each
+ * A multicast group has four types of members: full member, non member,
+ * sendonly non member and sendonly full member.
+ * We need to keep track of the number of members of each
  * type based on their join state.  Adjust the number of members the belong to
  * the specified join states.
  */
@@ -229,7 +242,7 @@ static void adjust_membership(struct mcast_group *group, u8 join_state, int inc)
 {
 	int i;
 
-	for (i = 0; i < 3; i++, join_state >>= 1)
+	for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++, join_state >>= 1)
 		if (join_state & 0x1)
 			group->members[i] += inc;
 }
@@ -245,7 +258,7 @@ static u8 get_leave_state(struct mcast_group *group)
 	u8 leave_state = 0;
 	int i;
 
-	for (i = 0; i < 3; i++)
+	for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++)
 		if (!group->members[i])
 			leave_state |= (0x1 << i);
 
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 3ebd108bcc5f..e95538650dc6 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -53,10 +53,6 @@
 #include "sa.h"
 #include "core_priv.h"
 
-MODULE_AUTHOR("Roland Dreier");
-MODULE_DESCRIPTION("InfiniBand subnet administration query support");
-MODULE_LICENSE("Dual BSD/GPL");
-
 #define IB_SA_LOCAL_SVC_TIMEOUT_MIN		100
 #define IB_SA_LOCAL_SVC_TIMEOUT_DEFAULT		2000
 #define IB_SA_LOCAL_SVC_TIMEOUT_MAX		200000
@@ -119,6 +115,12 @@ struct ib_sa_guidinfo_query {
 	struct ib_sa_query sa_query;
 };
 
+struct ib_sa_classport_info_query {
+	void (*callback)(int, struct ib_class_port_info *, void *);
+	void *context;
+	struct ib_sa_query sa_query;
+};
+
 struct ib_sa_mcmember_query {
 	void (*callback)(int, struct ib_sa_mcmember_rec *, void *);
 	void *context;
@@ -392,6 +394,82 @@ static const struct ib_field service_rec_table[] = {
 	  .size_bits    = 2*64 },
 };
 
+#define CLASSPORTINFO_REC_FIELD(field) \
+	.struct_offset_bytes = offsetof(struct ib_class_port_info, field),	\
+	.struct_size_bytes   = sizeof((struct ib_class_port_info *)0)->field,	\
+	.field_name          = "ib_class_port_info:" #field
+
+static const struct ib_field classport_info_rec_table[] = {
+	{ CLASSPORTINFO_REC_FIELD(base_version),
+	  .offset_words = 0,
+	  .offset_bits  = 0,
+	  .size_bits    = 8 },
+	{ CLASSPORTINFO_REC_FIELD(class_version),
+	  .offset_words = 0,
+	  .offset_bits  = 8,
+	  .size_bits    = 8 },
+	{ CLASSPORTINFO_REC_FIELD(capability_mask),
+	  .offset_words = 0,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 },
+	{ CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time),
+	  .offset_words = 1,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_gid),
+	  .offset_words = 2,
+	  .offset_bits  = 0,
+	  .size_bits    = 128 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_tcslfl),
+	  .offset_words = 6,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_lid),
+	  .offset_words = 7,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_pkey),
+	  .offset_words = 7,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 },
+
+	{ CLASSPORTINFO_REC_FIELD(redirect_qp),
+	  .offset_words = 8,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_qkey),
+	  .offset_words = 9,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+
+	{ CLASSPORTINFO_REC_FIELD(trap_gid),
+	  .offset_words = 10,
+	  .offset_bits  = 0,
+	  .size_bits    = 128 },
+	{ CLASSPORTINFO_REC_FIELD(trap_tcslfl),
+	  .offset_words = 14,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+
+	{ CLASSPORTINFO_REC_FIELD(trap_lid),
+	  .offset_words = 15,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ CLASSPORTINFO_REC_FIELD(trap_pkey),
+	  .offset_words = 15,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 },
+
+	{ CLASSPORTINFO_REC_FIELD(trap_hlqp),
+	  .offset_words = 16,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(trap_qkey),
+	  .offset_words = 17,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+};
+
 #define GUIDINFO_REC_FIELD(field) \
 	.struct_offset_bytes = offsetof(struct ib_sa_guidinfo_rec, field),	\
 	.struct_size_bytes   = sizeof((struct ib_sa_guidinfo_rec *) 0)->field,	\
@@ -705,8 +783,8 @@ static void ib_nl_request_timeout(struct work_struct *work)
 	spin_unlock_irqrestore(&ib_nl_request_lock, flags);
 }
 
-static int ib_nl_handle_set_timeout(struct sk_buff *skb,
-				    struct netlink_callback *cb)
+int ib_nl_handle_set_timeout(struct sk_buff *skb,
+			     struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	int timeout, delta, abs_delta;
@@ -782,8 +860,8 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 	return 1;
 }
 
-static int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-				     struct netlink_callback *cb)
+int ib_nl_handle_resolve_resp(struct sk_buff *skb,
+			      struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	unsigned long flags;
@@ -838,15 +916,6 @@ resp_out:
 	return skb->len;
 }
 
-static struct ibnl_client_cbs ib_sa_cb_table[] = {
-	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp,
-		.module = THIS_MODULE },
-	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout,
-		.module = THIS_MODULE },
-};
-
 static void free_sm_ah(struct kref *kref)
 {
 	struct ib_sa_sm_ah *sm_ah = container_of(kref, struct ib_sa_sm_ah, ref);
@@ -1645,6 +1714,97 @@ err1:
 }
 EXPORT_SYMBOL(ib_sa_guid_info_rec_query);
 
+/* Support get SA ClassPortInfo */
+static void ib_sa_classport_info_rec_callback(struct ib_sa_query *sa_query,
+					      int status,
+					      struct ib_sa_mad *mad)
+{
+	struct ib_sa_classport_info_query *query =
+		container_of(sa_query, struct ib_sa_classport_info_query, sa_query);
+
+	if (mad) {
+		struct ib_class_port_info rec;
+
+		ib_unpack(classport_info_rec_table,
+			  ARRAY_SIZE(classport_info_rec_table),
+			  mad->data, &rec);
+		query->callback(status, &rec, query->context);
+	} else {
+		query->callback(status, NULL, query->context);
+	}
+}
+
+static void ib_sa_portclass_info_rec_release(struct ib_sa_query *sa_query)
+{
+	kfree(container_of(sa_query, struct ib_sa_classport_info_query,
+			   sa_query));
+}
+
+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)
+{
+	struct ib_sa_classport_info_query *query;
+	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
+	struct ib_sa_port *port;
+	struct ib_mad_agent *agent;
+	struct ib_sa_mad *mad;
+	int ret;
+
+	if (!sa_dev)
+		return -ENODEV;
+
+	port  = &sa_dev->port[port_num - sa_dev->start_port];
+	agent = port->agent;
+
+	query = kzalloc(sizeof(*query), gfp_mask);
+	if (!query)
+		return -ENOMEM;
+
+	query->sa_query.port = port;
+	ret = alloc_mad(&query->sa_query, gfp_mask);
+	if (ret)
+		goto err1;
+
+	ib_sa_client_get(client);
+	query->sa_query.client = client;
+	query->callback        = callback;
+	query->context         = context;
+
+	mad = query->sa_query.mad_buf->mad;
+	init_mad(mad, agent);
+
+	query->sa_query.callback = callback ? ib_sa_classport_info_rec_callback : NULL;
+
+	query->sa_query.release  = ib_sa_portclass_info_rec_release;
+	/* support GET only */
+	mad->mad_hdr.method	 = IB_MGMT_METHOD_GET;
+	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_CLASS_PORTINFO);
+	mad->sa_hdr.comp_mask	 = 0;
+	*sa_query = &query->sa_query;
+
+	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
+	if (ret < 0)
+		goto err2;
+
+	return ret;
+
+err2:
+	*sa_query = NULL;
+	ib_sa_client_put(query->sa_query.client);
+	free_mad(&query->sa_query);
+
+err1:
+	kfree(query);
+	return ret;
+}
+EXPORT_SYMBOL(ib_sa_classport_info_rec_query);
+
 static void send_handler(struct ib_mad_agent *agent,
 			 struct ib_mad_send_wc *mad_send_wc)
 {
@@ -1794,7 +1954,7 @@ static void ib_sa_remove_one(struct ib_device *device, void *client_data)
 	kfree(sa_dev);
 }
 
-static int __init ib_sa_init(void)
+int ib_sa_init(void)
 {
 	int ret;
 
@@ -1820,17 +1980,10 @@ static int __init ib_sa_init(void)
 		goto err3;
 	}
 
-	if (ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ib_sa_cb_table),
-			    ib_sa_cb_table)) {
-		pr_err("Failed to add netlink callback\n");
-		ret = -EINVAL;
-		goto err4;
-	}
 	INIT_DELAYED_WORK(&ib_nl_timed_work, ib_nl_request_timeout);
 
 	return 0;
-err4:
-	destroy_workqueue(ib_nl_wq);
+
 err3:
 	mcast_cleanup();
 err2:
@@ -1839,9 +1992,8 @@ err1:
 	return ret;
 }
 
-static void __exit ib_sa_cleanup(void)
+void ib_sa_cleanup(void)
 {
-	ibnl_remove_client(RDMA_NL_LS);
 	cancel_delayed_work(&ib_nl_timed_work);
 	flush_workqueue(ib_nl_wq);
 	destroy_workqueue(ib_nl_wq);
@@ -1849,6 +2001,3 @@ static void __exit ib_sa_cleanup(void)
 	ib_unregister_client(&sa_client);
 	idr_destroy(&query_idr);
 }
-
-module_init(ib_sa_init);
-module_exit(ib_sa_cleanup);
diff --git a/drivers/infiniband/core/sysfs.c b/drivers/infiniband/core/sysfs.c
index 14606afbfaa8..5e573bb18660 100644
--- a/drivers/infiniband/core/sysfs.c
+++ b/drivers/infiniband/core/sysfs.c
@@ -56,8 +56,10 @@ struct ib_port {
 	struct gid_attr_group *gid_attr_group;
 	struct attribute_group gid_group;
 	struct attribute_group pkey_group;
-	u8                     port_num;
 	struct attribute_group *pma_table;
+	struct attribute_group *hw_stats_ag;
+	struct rdma_hw_stats   *hw_stats;
+	u8                     port_num;
 };
 
 struct port_attribute {
@@ -80,6 +82,18 @@ struct port_table_attribute {
 	__be16			attr_id;
 };
 
+struct hw_stats_attribute {
+	struct attribute	attr;
+	ssize_t			(*show)(struct kobject *kobj,
+					struct attribute *attr, char *buf);
+	ssize_t			(*store)(struct kobject *kobj,
+					 struct attribute *attr,
+					 const char *buf,
+					 size_t count);
+	int			index;
+	u8			port_num;
+};
+
 static ssize_t port_attr_show(struct kobject *kobj,
 			      struct attribute *attr, char *buf)
 {
@@ -733,6 +747,212 @@ static struct attribute_group *get_counter_table(struct ib_device *dev,
 	return &pma_group;
 }
 
+static int update_hw_stats(struct ib_device *dev, struct rdma_hw_stats *stats,
+			   u8 port_num, int index)
+{
+	int ret;
+
+	if (time_is_after_eq_jiffies(stats->timestamp + stats->lifespan))
+		return 0;
+	ret = dev->get_hw_stats(dev, stats, port_num, index);
+	if (ret < 0)
+		return ret;
+	if (ret == stats->num_counters)
+		stats->timestamp = jiffies;
+
+	return 0;
+}
+
+static ssize_t print_hw_stat(struct rdma_hw_stats *stats, int index, char *buf)
+{
+	return sprintf(buf, "%llu\n", stats->value[index]);
+}
+
+static ssize_t show_hw_stats(struct kobject *kobj, struct attribute *attr,
+			     char *buf)
+{
+	struct ib_device *dev;
+	struct ib_port *port;
+	struct hw_stats_attribute *hsa;
+	struct rdma_hw_stats *stats;
+	int ret;
+
+	hsa = container_of(attr, struct hw_stats_attribute, attr);
+	if (!hsa->port_num) {
+		dev = container_of((struct device *)kobj,
+				   struct ib_device, dev);
+		stats = dev->hw_stats;
+	} else {
+		port = container_of(kobj, struct ib_port, kobj);
+		dev = port->ibdev;
+		stats = port->hw_stats;
+	}
+	ret = update_hw_stats(dev, stats, hsa->port_num, hsa->index);
+	if (ret)
+		return ret;
+	return print_hw_stat(stats, hsa->index, buf);
+}
+
+static ssize_t show_stats_lifespan(struct kobject *kobj,
+				   struct attribute *attr,
+				   char *buf)
+{
+	struct hw_stats_attribute *hsa;
+	int msecs;
+
+	hsa = container_of(attr, struct hw_stats_attribute, attr);
+	if (!hsa->port_num) {
+		struct ib_device *dev = container_of((struct device *)kobj,
+						     struct ib_device, dev);
+		msecs = jiffies_to_msecs(dev->hw_stats->lifespan);
+	} else {
+		struct ib_port *p = container_of(kobj, struct ib_port, kobj);
+		msecs = jiffies_to_msecs(p->hw_stats->lifespan);
+	}
+	return sprintf(buf, "%d\n", msecs);
+}
+
+static ssize_t set_stats_lifespan(struct kobject *kobj,
+				  struct attribute *attr,
+				  const char *buf, size_t count)
+{
+	struct hw_stats_attribute *hsa;
+	int msecs;
+	int jiffies;
+	int ret;
+
+	ret = kstrtoint(buf, 10, &msecs);
+	if (ret)
+		return ret;
+	if (msecs < 0 || msecs > 10000)
+		return -EINVAL;
+	jiffies = msecs_to_jiffies(msecs);
+	hsa = container_of(attr, struct hw_stats_attribute, attr);
+	if (!hsa->port_num) {
+		struct ib_device *dev = container_of((struct device *)kobj,
+						     struct ib_device, dev);
+		dev->hw_stats->lifespan = jiffies;
+	} else {
+		struct ib_port *p = container_of(kobj, struct ib_port, kobj);
+		p->hw_stats->lifespan = jiffies;
+	}
+	return count;
+}
+
+static void free_hsag(struct kobject *kobj, struct attribute_group *attr_group)
+{
+	struct attribute **attr;
+
+	sysfs_remove_group(kobj, attr_group);
+
+	for (attr = attr_group->attrs; *attr; attr++)
+		kfree(*attr);
+	kfree(attr_group);
+}
+
+static struct attribute *alloc_hsa(int index, u8 port_num, const char *name)
+{
+	struct hw_stats_attribute *hsa;
+
+	hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
+	if (!hsa)
+		return NULL;
+
+	hsa->attr.name = (char *)name;
+	hsa->attr.mode = S_IRUGO;
+	hsa->show = show_hw_stats;
+	hsa->store = NULL;
+	hsa->index = index;
+	hsa->port_num = port_num;
+
+	return &hsa->attr;
+}
+
+static struct attribute *alloc_hsa_lifespan(char *name, u8 port_num)
+{
+	struct hw_stats_attribute *hsa;
+
+	hsa = kmalloc(sizeof(*hsa), GFP_KERNEL);
+	if (!hsa)
+		return NULL;
+
+	hsa->attr.name = name;
+	hsa->attr.mode = S_IWUSR | S_IRUGO;
+	hsa->show = show_stats_lifespan;
+	hsa->store = set_stats_lifespan;
+	hsa->index = 0;
+	hsa->port_num = port_num;
+
+	return &hsa->attr;
+}
+
+static void setup_hw_stats(struct ib_device *device, struct ib_port *port,
+			   u8 port_num)
+{
+	struct attribute_group *hsag = NULL;
+	struct rdma_hw_stats *stats;
+	int i = 0, ret;
+
+	stats = device->alloc_hw_stats(device, port_num);
+
+	if (!stats)
+		return;
+
+	if (!stats->names || stats->num_counters <= 0)
+		goto err;
+
+	hsag = kzalloc(sizeof(*hsag) +
+		       // 1 extra for the lifespan config entry
+		       sizeof(void *) * (stats->num_counters + 1),
+		       GFP_KERNEL);
+	if (!hsag)
+		return;
+
+	ret = device->get_hw_stats(device, stats, port_num,
+				   stats->num_counters);
+	if (ret != stats->num_counters)
+		goto err;
+
+	stats->timestamp = jiffies;
+
+	hsag->name = "hw_counters";
+	hsag->attrs = (void *)hsag + sizeof(*hsag);
+
+	for (i = 0; i < stats->num_counters; i++) {
+		hsag->attrs[i] = alloc_hsa(i, port_num, stats->names[i]);
+		if (!hsag->attrs[i])
+			goto err;
+	}
+
+	/* treat an error here as non-fatal */
+	hsag->attrs[i] = alloc_hsa_lifespan("lifespan", port_num);
+
+	if (port) {
+		struct kobject *kobj = &port->kobj;
+		ret = sysfs_create_group(kobj, hsag);
+		if (ret)
+			goto err;
+		port->hw_stats_ag = hsag;
+		port->hw_stats = stats;
+	} else {
+		struct kobject *kobj = &device->dev.kobj;
+		ret = sysfs_create_group(kobj, hsag);
+		if (ret)
+			goto err;
+		device->hw_stats_ag = hsag;
+		device->hw_stats = stats;
+	}
+
+	return;
+
+err:
+	kfree(stats);
+	for (; i >= 0; i--)
+		kfree(hsag->attrs[i]);
+	kfree(hsag);
+	return;
+}
+
 static int add_port(struct ib_device *device, int port_num,
 		    int (*port_callback)(struct ib_device *,
 					 u8, struct kobject *))
@@ -835,6 +1055,14 @@ static int add_port(struct ib_device *device, int port_num,
 			goto err_remove_pkey;
 	}
 
+	/*
+	 * If port == 0, it means we have only one port and the parent
+	 * device, not this port device, should be the holder of the
+	 * hw_counters
+	 */
+	if (device->alloc_hw_stats && port_num)
+		setup_hw_stats(device, p, port_num);
+
 	list_add_tail(&p->kobj.entry, &device->port_list);
 
 	kobject_uevent(&p->kobj, KOBJ_ADD);
@@ -972,120 +1200,6 @@ static struct device_attribute *ib_class_attributes[] = {
 	&dev_attr_node_desc
 };
 
-/* Show a given an attribute in the statistics group */
-static ssize_t show_protocol_stat(const struct device *device,
-			    struct device_attribute *attr, char *buf,
-			    unsigned offset)
-{
-	struct ib_device *dev = container_of(device, struct ib_device, dev);
-	union rdma_protocol_stats stats;
-	ssize_t ret;
-
-	ret = dev->get_protocol_stats(dev, &stats);
-	if (ret)
-		return ret;
-
-	return sprintf(buf, "%llu\n",
-		       (unsigned long long) ((u64 *) &stats)[offset]);
-}
-
-/* generate a read-only iwarp statistics attribute */
-#define IW_STATS_ENTRY(name)						\
-static ssize_t show_##name(struct device *device,			\
-			   struct device_attribute *attr, char *buf)	\
-{									\
-	return show_protocol_stat(device, attr, buf,			\
-				  offsetof(struct iw_protocol_stats, name) / \
-				  sizeof (u64));			\
-}									\
-static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL)
-
-IW_STATS_ENTRY(ipInReceives);
-IW_STATS_ENTRY(ipInHdrErrors);
-IW_STATS_ENTRY(ipInTooBigErrors);
-IW_STATS_ENTRY(ipInNoRoutes);
-IW_STATS_ENTRY(ipInAddrErrors);
-IW_STATS_ENTRY(ipInUnknownProtos);
-IW_STATS_ENTRY(ipInTruncatedPkts);
-IW_STATS_ENTRY(ipInDiscards);
-IW_STATS_ENTRY(ipInDelivers);
-IW_STATS_ENTRY(ipOutForwDatagrams);
-IW_STATS_ENTRY(ipOutRequests);
-IW_STATS_ENTRY(ipOutDiscards);
-IW_STATS_ENTRY(ipOutNoRoutes);
-IW_STATS_ENTRY(ipReasmTimeout);
-IW_STATS_ENTRY(ipReasmReqds);
-IW_STATS_ENTRY(ipReasmOKs);
-IW_STATS_ENTRY(ipReasmFails);
-IW_STATS_ENTRY(ipFragOKs);
-IW_STATS_ENTRY(ipFragFails);
-IW_STATS_ENTRY(ipFragCreates);
-IW_STATS_ENTRY(ipInMcastPkts);
-IW_STATS_ENTRY(ipOutMcastPkts);
-IW_STATS_ENTRY(ipInBcastPkts);
-IW_STATS_ENTRY(ipOutBcastPkts);
-IW_STATS_ENTRY(tcpRtoAlgorithm);
-IW_STATS_ENTRY(tcpRtoMin);
-IW_STATS_ENTRY(tcpRtoMax);
-IW_STATS_ENTRY(tcpMaxConn);
-IW_STATS_ENTRY(tcpActiveOpens);
-IW_STATS_ENTRY(tcpPassiveOpens);
-IW_STATS_ENTRY(tcpAttemptFails);
-IW_STATS_ENTRY(tcpEstabResets);
-IW_STATS_ENTRY(tcpCurrEstab);
-IW_STATS_ENTRY(tcpInSegs);
-IW_STATS_ENTRY(tcpOutSegs);
-IW_STATS_ENTRY(tcpRetransSegs);
-IW_STATS_ENTRY(tcpInErrs);
-IW_STATS_ENTRY(tcpOutRsts);
-
-static struct attribute *iw_proto_stats_attrs[] = {
-	&dev_attr_ipInReceives.attr,
-	&dev_attr_ipInHdrErrors.attr,
-	&dev_attr_ipInTooBigErrors.attr,
-	&dev_attr_ipInNoRoutes.attr,
-	&dev_attr_ipInAddrErrors.attr,
-	&dev_attr_ipInUnknownProtos.attr,
-	&dev_attr_ipInTruncatedPkts.attr,
-	&dev_attr_ipInDiscards.attr,
-	&dev_attr_ipInDelivers.attr,
-	&dev_attr_ipOutForwDatagrams.attr,
-	&dev_attr_ipOutRequests.attr,
-	&dev_attr_ipOutDiscards.attr,
-	&dev_attr_ipOutNoRoutes.attr,
-	&dev_attr_ipReasmTimeout.attr,
-	&dev_attr_ipReasmReqds.attr,
-	&dev_attr_ipReasmOKs.attr,
-	&dev_attr_ipReasmFails.attr,
-	&dev_attr_ipFragOKs.attr,
-	&dev_attr_ipFragFails.attr,
-	&dev_attr_ipFragCreates.attr,
-	&dev_attr_ipInMcastPkts.attr,
-	&dev_attr_ipOutMcastPkts.attr,
-	&dev_attr_ipInBcastPkts.attr,
-	&dev_attr_ipOutBcastPkts.attr,
-	&dev_attr_tcpRtoAlgorithm.attr,
-	&dev_attr_tcpRtoMin.attr,
-	&dev_attr_tcpRtoMax.attr,
-	&dev_attr_tcpMaxConn.attr,
-	&dev_attr_tcpActiveOpens.attr,
-	&dev_attr_tcpPassiveOpens.attr,
-	&dev_attr_tcpAttemptFails.attr,
-	&dev_attr_tcpEstabResets.attr,
-	&dev_attr_tcpCurrEstab.attr,
-	&dev_attr_tcpInSegs.attr,
-	&dev_attr_tcpOutSegs.attr,
-	&dev_attr_tcpRetransSegs.attr,
-	&dev_attr_tcpInErrs.attr,
-	&dev_attr_tcpOutRsts.attr,
-	NULL
-};
-
-static struct attribute_group iw_stats_group = {
-	.name	= "proto_stats",
-	.attrs	= iw_proto_stats_attrs,
-};
-
 static void free_port_list_attributes(struct ib_device *device)
 {
 	struct kobject *p, *t;
@@ -1093,6 +1207,10 @@ static void free_port_list_attributes(struct ib_device *device)
 	list_for_each_entry_safe(p, t, &device->port_list, entry) {
 		struct ib_port *port = container_of(p, struct ib_port, kobj);
 		list_del(&p->entry);
+		if (port->hw_stats) {
+			kfree(port->hw_stats);
+			free_hsag(&port->kobj, port->hw_stats_ag);
+		}
 		sysfs_remove_group(p, port->pma_table);
 		sysfs_remove_group(p, &port->pkey_group);
 		sysfs_remove_group(p, &port->gid_group);
@@ -1149,11 +1267,8 @@ int ib_device_register_sysfs(struct ib_device *device,
 		}
 	}
 
-	if (device->node_type == RDMA_NODE_RNIC && device->get_protocol_stats) {
-		ret = sysfs_create_group(&class_dev->kobj, &iw_stats_group);
-		if (ret)
-			goto err_put;
-	}
+	if (device->alloc_hw_stats)
+		setup_hw_stats(device, NULL, 0);
 
 	return 0;
 
@@ -1169,15 +1284,18 @@ err:
 
 void ib_device_unregister_sysfs(struct ib_device *device)
 {
-	/* Hold kobject until ib_dealloc_device() */
-	struct kobject *kobj_dev = kobject_get(&device->dev.kobj);
 	int i;
 
-	if (device->node_type == RDMA_NODE_RNIC && device->get_protocol_stats)
-		sysfs_remove_group(kobj_dev, &iw_stats_group);
+	/* Hold kobject until ib_dealloc_device() */
+	kobject_get(&device->dev.kobj);
 
 	free_port_list_attributes(device);
 
+	if (device->hw_stats) {
+		kfree(device->hw_stats);
+		free_hsag(&device->dev.kobj, device->hw_stats_ag);
+	}
+
 	for (i = 0; i < ARRAY_SIZE(ib_class_attributes); ++i)
 		device_remove_file(&device->dev, ib_class_attributes[i]);