RDMA netlink refactoring and RDMAtool code

index a0e7c16d8bd8..add99b92afdf 100644
@@ -174,7 +174,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto add_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;

@@ -251,7 +251,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto query_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";

@@ -312,7 +312,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 	if (ret)
 		goto remove_mapping_error;
 
-	ret = ibnl_unicast(skb, nlh, iwpm_user_pid);
+	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;

index 94931c474d41..0fc50e15ae22 100644
@@ -232,11 +232,21 @@ int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 {
 	int err;
 
-	err = netlink_unicast(nls, skb, pid, 0);
+	err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT);
 	return (err < 0) ? err : 0;
 }
 EXPORT_SYMBOL(ibnl_unicast);
 
+int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
+		      __u32 pid)
+{
+	int err;
+
+	err = netlink_unicast(nls, skb, pid, 0);
+	return (err < 0) ? err : 0;
+}
+EXPORT_SYMBOL(ibnl_unicast_wait);
+
 int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			unsigned int group, gfp_t flags)
 {

index 348c102cb5f6..5b1466770917 100644
@@ -63,6 +63,16 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			__u32 pid);
 
+/**
+ * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
+ * @skb: The netlink skb
+ * @nlh: Header of the netlink message to send
+ * @pid: Userspace netlink process ID
+ * Returns 0 on success or a negative error code.
+ */
+int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
+		      __u32 pid);
+
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb

index ca4135c596ba..2a16a559bdda 100644
@@ -4512,9 +4512,7 @@ static int __init cma_init(void)
 	if (ret)
 		goto err;
 
-	if (ibnl_add_client(RDMA_NL_RDMA_CM, ARRAY_SIZE(cma_cb_table),
-			    cma_cb_table))
-		pr_warn("RDMA CMA: failed to add netlink callback\n");
+	rdma_nl_register(RDMA_NL_RDMA_CM, cma_cb_table);
 	cma_configfs_init();
 
 	return 0;

@@ -4531,7 +4529,7 @@ static int __init cma_init(void)
 static void __exit cma_cleanup(void)
 {
 	cma_configfs_exit();
-	ibnl_remove_client(RDMA_NL_RDMA_CM);
+	rdma_nl_unregister(RDMA_NL_RDMA_CM);
 	ib_unregister_client(&cma_client);
 	unregister_netdevice_notifier(&cma_nb);
 	rdma_addr_unregister_client(&addr_client);

index 11ae67514e13..e759c27113cd 100644
@@ -179,8 +179,8 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
-int ibnl_init(void);
-void ibnl_cleanup(void);
+int rdma_nl_init(void);
+void rdma_nl_exit(void);
 
 /**
  * Check if there are any listeners to the netlink group

94 lines not on this page · raw message

index 31661b5c1743..8599271d8be6 100644
@@ -1175,12 +1175,8 @@ static int __init iw_cm_init(void)
 	ret = iwpm_init(RDMA_NL_IWCM);
 	if (ret)
 		pr_err("iw_cm: couldn't init iwpm\n");
-
-	ret = ibnl_add_client(RDMA_NL_IWCM, ARRAY_SIZE(iwcm_nl_cb_table),
-			      iwcm_nl_cb_table);
-	if (ret)
-		pr_err("iw_cm: couldn't register netlink callbacks\n");
-
+	else
+		rdma_nl_register(RDMA_NL_IWCM, iwcm_nl_cb_table);
 	iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", WQ_MEM_RECLAIM);
 	if (!iwcm_wq)
 		return -ENOMEM;

@@ -1200,7 +1196,7 @@ static void __exit iw_cm_cleanup(void)
 {
 	unregister_net_sysctl_table(iwcm_ctl_table_hdr);
 	destroy_workqueue(iwcm_wq);
-	ibnl_remove_client(RDMA_NL_IWCM);
+	rdma_nl_unregister(RDMA_NL_IWCM);
 	iwpm_exit(RDMA_NL_IWCM);
 }
 

250 lines not on this page · raw message

index 5b1466770917..aadf0ab963b2 100644
@@ -11,23 +11,18 @@ struct ibnl_client_cbs {
 };
 
 /**
- * Add a a client to the list of IB netlink exporters.
+ * Register client in RDMA netlink.
  * @index: Index of the added client
- * @nops: Number of supported ops by the added client.
  * @cb_table: A table for op->callback
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_add_client(int index, int nops,
-		    const struct ibnl_client_cbs cb_table[]);
+void rdma_nl_register(unsigned int index,
+		      const struct ibnl_client_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.
  * @index: Index of the removed IB client.
- *
- * Returns 0 on success or a negative error code.
  */
-int ibnl_remove_client(int index);
+void rdma_nl_unregister(unsigned int index);
 
 /**
  * Put a new message in a supplied skb.

index 2a16a559bdda..0c85f140e616 100644
@@ -4459,8 +4459,7 @@ static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb)
 }
 
 static const struct ibnl_client_cbs cma_cb_table[] = {
-	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats,
-				       .module = THIS_MODULE },
+	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 
 static int cma_init_net(struct net *net)

index 06f7ba31fbdd..cd9b7e7b7d2c 100644
@@ -180,12 +180,10 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cb.skb = skb;
 		cb.nlh = nlh;
 		cb.dump = rdma_nl_types[index].cb_table[op].dump;
-		cb.module = rdma_nl_types[index].cb_table[op].module;
 		return cb.dump(skb, &cb);
 	}
 
 	c.dump = rdma_nl_types[index].cb_table[op].dump;
-	c.module = rdma_nl_types[index].cb_table[op].module;
 	return netlink_dump_start(nls, skb, nlh, &c);
 }
 

index aadf0ab963b2..c124d8e43fc8 100644
@@ -7,7 +7,6 @@
 
 struct ibnl_client_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
-	struct module *module;
 };
 
 /**

index cd9b7e7b7d2c..826fbd612c7d 100644
@@ -159,8 +159,8 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 }
 EXPORT_SYMBOL(ibnl_put_attr);
 
-static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
-			struct netlink_ext_ack *extack)
+static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
+			   struct netlink_ext_ack *extack)
 {
 	int type = nlh->nlmsg_type;
 	unsigned int index = RDMA_NL_GET_CLIENT(type);

@@ -187,40 +187,66 @@ static int ibnl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	return netlink_dump_start(nls, skb, nlh, &c);
 }
 
-static void ibnl_rcv_reply_skb(struct sk_buff *skb)
+/*
+ * This function is similar to netlink_rcv_skb with one exception:
+ * It calls to the callback for the netlink messages without NLM_F_REQUEST
+ * flag. These messages are intended for RDMA_NL_LS consumer, so it is allowed
+ * for that consumer only.
+ */
+static int rdma_nl_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *,
+						   struct nlmsghdr *,
+						   struct netlink_ext_ack *))
 {
+	struct netlink_ext_ack extack = {};
 	struct nlmsghdr *nlh;
-	int msglen;
+	int err;
 
-	/*
-	 * Process responses until there is no more message or the first
-	 * request. Generally speaking, it is not recommended to mix responses
-	 * with requests.
-	 */
 	while (skb->len >= nlmsg_total_size(0)) {
+		int msglen;
+
 		nlh = nlmsg_hdr(skb);
+		err = 0;
 
 		if (nlh->nlmsg_len < NLMSG_HDRLEN || skb->len < nlh->nlmsg_len)
-			return;
+			return 0;
 
-		/* Handle response only */
-		if (nlh->nlmsg_flags & NLM_F_REQUEST)
-			return;
+		/*
+		 * Generally speaking, the only requests are handled
+		 * by the kernel, but RDMA_NL_LS is different, because it
+		 * runs backward netlink scheme. Kernel initiates messages
+		 * and waits for reply with data to keep pathrecord cache
+		 * in sync.
+		 */
+		if (!(nlh->nlmsg_flags & NLM_F_REQUEST) &&
+		    (RDMA_NL_GET_CLIENT(nlh->nlmsg_type) != RDMA_NL_LS))
+			goto ack;
+
+		/* Skip control messages */
+		if (nlh->nlmsg_type < NLMSG_MIN_TYPE)
+			goto ack;
 
-		ibnl_rcv_msg(skb, nlh, NULL);
+		err = cb(skb, nlh, &extack);
+		if (err == -EINTR)
+			goto skip;
 
+ack:
+		if (nlh->nlmsg_flags & NLM_F_ACK || err)
+			netlink_ack(skb, nlh, err, &extack);
+
+skip:
 		msglen = NLMSG_ALIGN(nlh->nlmsg_len);
 		if (msglen > skb->len)
 			msglen = skb->len;
 		skb_pull(skb, msglen);
 	}
+
+	return 0;
 }
 
-static void ibnl_rcv(struct sk_buff *skb)
+static void rdma_nl_rcv(struct sk_buff *skb)
 {
 	mutex_lock(&rdma_nl_mutex);
-	ibnl_rcv_reply_skb(skb);
-	netlink_rcv_skb(skb, &ibnl_rcv_msg);
+	rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg);
 	mutex_unlock(&rdma_nl_mutex);
 }
 

@@ -254,7 +280,7 @@ EXPORT_SYMBOL(ibnl_multicast);
 int __init rdma_nl_init(void)
 {
 	struct netlink_kernel_cfg cfg = {
-		.input	= ibnl_rcv,
+		.input	= rdma_nl_rcv,
 	};
 
 	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);

index f13870e69ccd..32ca2aaa4e3b 100644
@@ -54,8 +54,6 @@ static struct iwpm_admin_data iwpm_admin;
 int iwpm_init(u8 nl_client)
 {
 	int ret = 0;
-	if (iwpm_valid_client(nl_client))
-		return -EINVAL;
 	mutex_lock(&iwpm_admin_lock);
 	if (atomic_read(&iwpm_admin.refcount) == 0) {
 		iwpm_hash_bucket = kzalloc(IWPM_MAPINFO_HASH_SIZE *

@@ -383,15 +381,11 @@ int iwpm_get_nlmsg_seq(void)
 
 int iwpm_valid_client(u8 nl_client)
 {
-	if (nl_client >= RDMA_NL_NUM_CLIENTS)
-		return 0;
 	return iwpm_admin.client_list[nl_client];
 }
 
 void iwpm_set_valid(u8 nl_client, int valid)
 {
-	if (nl_client >= RDMA_NL_NUM_CLIENTS)
-		return;
 	iwpm_admin.client_list[nl_client] = valid;
 }
 

index add99b92afdf..45de263305f5 100644
@@ -42,7 +42,6 @@ int iwpm_valid_pid(void)
 {
 	return iwpm_user_pid > 0;
 }
-EXPORT_SYMBOL(iwpm_valid_pid);
 
 /*
  * iwpm_register_pid - Send a netlink query to user space

@@ -122,7 +121,6 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_register_pid);
 
 /*
  * iwpm_add_mapping - Send a netlink add mapping message

@@ -191,7 +189,6 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_add_mapping);
 
 /*
  * iwpm_add_and_query_mapping - Send a netlink add and query

@@ -267,7 +264,6 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		iwpm_free_nlmsg_request(&nlmsg_request->kref);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_add_and_query_mapping);
 
 /*
  * iwpm_remove_mapping - Send a netlink remove mapping message

@@ -328,7 +324,6 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 		dev_kfree_skb_any(skb);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remove_mapping);
 
 /* netlink attribute policy for the received response to register pid request */
 static const struct nla_policy resp_reg_policy[IWPM_NLA_RREG_PID_MAX] = {

@@ -397,7 +392,6 @@ int iwpm_register_pid_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_register_pid_cb);
 
 /* netlink attribute policy for the received response to add mapping request */
 static const struct nla_policy resp_add_policy[IWPM_NLA_RMANAGE_MAPPING_MAX] = {

@@ -466,7 +460,6 @@ int iwpm_add_mapping_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_add_mapping_cb);
 
 /* netlink attribute policy for the response to add and query mapping request
  * and response with remote address info */

@@ -558,7 +551,6 @@ int iwpm_add_and_query_mapping_cb(struct sk_buff *skb,
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_add_and_query_mapping_cb);
 
 /*
  * iwpm_remote_info_cb - Process a port mapper message, containing

@@ -627,7 +619,6 @@ int iwpm_remote_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 			"remote_info: Mapped remote sockaddr:");
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remote_info_cb);
 
 /* netlink attribute policy for the received request for mapping info */
 static const struct nla_policy resp_mapinfo_policy[IWPM_NLA_MAPINFO_REQ_MAX] = {

@@ -677,7 +668,6 @@ int iwpm_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	ret = iwpm_send_mapinfo(nl_client, iwpm_user_pid);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_mapping_info_cb);
 
 /* netlink attribute policy for the received mapping info ack */
 static const struct nla_policy ack_mapinfo_policy[IWPM_NLA_MAPINFO_NUM_MAX] = {

@@ -707,7 +697,6 @@ int iwpm_ack_mapping_info_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	atomic_set(&echo_nlmsg_seq, cb->nlh->nlmsg_seq);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_ack_mapping_info_cb);
 
 /* netlink attribute policy for the received port mapper error message */
 static const struct nla_policy map_error_policy[IWPM_NLA_ERR_MAX] = {

@@ -751,4 +740,3 @@ int iwpm_mapping_error_cb(struct sk_buff *skb, struct netlink_callback *cb)
 	up(&nlmsg_request->sem);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_mapping_error_cb);

index 32ca2aaa4e3b..c46442ac71a2 100644
@@ -81,7 +81,6 @@ int iwpm_init(u8 nl_client)
 	}
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_init);
 
 static void free_hash_bucket(void);
 static void free_reminfo_bucket(void);

@@ -107,7 +106,6 @@ int iwpm_exit(u8 nl_client)
 	iwpm_set_registration(nl_client, IWPM_REG_UNDEF);
 	return 0;
 }
-EXPORT_SYMBOL(iwpm_exit);
 
 static struct hlist_head *get_mapinfo_hash_bucket(struct sockaddr_storage *,
 					       struct sockaddr_storage *);

@@ -146,7 +144,6 @@ int iwpm_create_mapinfo(struct sockaddr_storage *local_sockaddr,
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_create_mapinfo);
 
 int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr,
 			struct sockaddr_storage *mapped_local_addr)

@@ -182,7 +179,6 @@ int iwpm_remove_mapinfo(struct sockaddr_storage *local_sockaddr,
 	spin_unlock_irqrestore(&iwpm_mapinfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_remove_mapinfo);
 
 static void free_hash_bucket(void)
 {

@@ -295,7 +291,6 @@ int iwpm_get_remote_info(struct sockaddr_storage *mapped_loc_addr,
 	spin_unlock_irqrestore(&iwpm_reminfo_lock, flags);
 	return ret;
 }
-EXPORT_SYMBOL(iwpm_get_remote_info);
 
 struct iwpm_nlmsg_request *iwpm_get_nlmsg_request(__u32 nlmsg_seq,
 					u8 nl_client, gfp_t gfp)

index 01236cef7bfb..9f3339861ec5 100644
@@ -134,8 +134,7 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 	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))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	if (ib_nl_is_good_ip_resp(nlh))

index 298258c40d30..1c5276e6e7f6 100644
@@ -1088,11 +1088,17 @@ EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
 static const struct ibnl_client_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp},
+		.dump = ib_nl_handle_resolve_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout},
+		.dump = ib_nl_handle_set_timeout,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp},
+		.dump = ib_nl_handle_ip_res_resp,
+		.flags = RDMA_NL_ADMIN_PERM,
+	},
 };
 
 static int __init ib_core_init(void)

index 826fbd612c7d..c5ee62a24960 100644
@@ -171,6 +171,10 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
+	if ((rdma_nl_types[index].cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
+	    !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+
 	/*
 	 * For response or local service set_timeout request,
 	 * there is no need to use netlink_dump_start.

index 70fa4cabe48e..b499f4422f41 100644
@@ -1033,8 +1033,7 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 	int ret;
 
 	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),

@@ -1109,8 +1108,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb,
 	int ret;
 
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    !(NETLINK_CB(skb).sk) ||
-	    !netlink_capable(skb, CAP_NET_ADMIN))
+	    !(NETLINK_CB(skb).sk))
 		return -EPERM;
 
 	spin_lock_irqsave(&ib_nl_request_lock, flags);

index c124d8e43fc8..6ea36ec45401 100644
@@ -7,6 +7,12 @@
 
 struct ibnl_client_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
+	u8 flags;
+};
+
+enum rdma_nl_flags {
+	/* Require CAP_NET_ADMIN */
+	RDMA_NL_ADMIN_PERM	= 1 << 0,
 };
 
 /**

index c5ee62a24960..fc8b45d4140a 100644
@@ -126,36 +126,23 @@ EXPORT_SYMBOL(rdma_nl_unregister);
 void *ibnl_put_msg(struct sk_buff *skb, struct nlmsghdr **nlh, int seq,
 		   int len, int client, int op, int flags)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op),
-			 len, flags);
-	if (!*nlh)
-		goto out_nlmsg_trim;
-	(*nlh)->nlmsg_len = skb_tail_pointer(skb) - prev_tail;
+	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), len, flags);
+	if (!*nlh) {
+		nlmsg_cancel(skb, *nlh);
+		return NULL;
+	}
 	return nlmsg_data(*nlh);
-
-out_nlmsg_trim:
-	nlmsg_trim(skb, prev_tail);
-	return NULL;
 }
 EXPORT_SYMBOL(ibnl_put_msg);
 
 int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 		  int len, void *data, int type)
 {
-	unsigned char *prev_tail;
-
-	prev_tail = skb_tail_pointer(skb);
-	if (nla_put(skb, type, len, data))
-		goto nla_put_failure;
-	nlh->nlmsg_len += skb_tail_pointer(skb) - prev_tail;
+	if (nla_put(skb, type, len, data)) {
+		nlmsg_cancel(skb, nlh);
+		return -EMSGSIZE;
+	}
 	return 0;
-
-nla_put_failure:
-	nlmsg_trim(skb, prev_tail - nlh->nlmsg_len);
-	return -EMSGSIZE;
 }
 EXPORT_SYMBOL(ibnl_put_attr);
 

index 45de263305f5..ca3c160bb9da 100644
@@ -172,7 +172,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto add_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;

@@ -248,7 +248,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 		goto query_mapping_error;
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";

@@ -308,7 +308,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 	if (ret)
 		goto remove_mapping_error;
 
-	ret = ibnl_unicast_wait(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;

index c46442ac71a2..c81c55942626 100644
@@ -597,7 +597,7 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
 				&mapping_num, IWPM_NLA_MAPINFO_SEND_NUM);
 	if (ret)
 		goto mapinfo_num_error;
-	ret = ibnl_unicast(skb, nlh, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";

@@ -626,7 +626,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
 		return -ENOMEM;
 	}
 	nlh->nlmsg_type = NLMSG_DONE;
-	ret = ibnl_unicast(skb, (struct nlmsghdr *)skb->data, iwpm_pid);
+	ret = rdma_nl_unicast(skb, iwpm_pid);
 	if (ret)
 		pr_warn("%s Unable to send a nlmsg\n", __func__);
 	return ret;

index fc8b45d4140a..0e0d0820cbac 100644
@@ -241,25 +241,23 @@ static void rdma_nl_rcv(struct sk_buff *skb)
 	mutex_unlock(&rdma_nl_mutex);
 }
 
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid)
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid)
 {
 	int err;
 
 	err = netlink_unicast(nls, skb, pid, MSG_DONTWAIT);
 	return (err < 0) ? err : 0;
 }
-EXPORT_SYMBOL(ibnl_unicast);
+EXPORT_SYMBOL(rdma_nl_unicast);
 
-int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
-		      __u32 pid)
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid)
 {
 	int err;
 
 	err = netlink_unicast(nls, skb, pid, 0);
 	return (err < 0) ? err : 0;
 }
-EXPORT_SYMBOL(ibnl_unicast_wait);
+EXPORT_SYMBOL(rdma_nl_unicast_wait);
 
 int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			unsigned int group, gfp_t flags)

index 6ea36ec45401..e7b0779385e9 100644
@@ -56,22 +56,18 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 /**
  * Send the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			__u32 pid);
+int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
 
 /**
  * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int ibnl_unicast_wait(struct sk_buff *skb, struct nlmsghdr *nlh,
-		      __u32 pid);
+int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.

index 9f3339861ec5..30cf764824ec 100644
@@ -184,7 +184,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
 
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
-	ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
 
 	/* Make the request retry, so when we get the response from userspace
 	 * we will have something.

index ca3c160bb9da..30825bb9b8e9 100644
@@ -103,7 +103,7 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
 		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNAVAILABLE;

index 0e0d0820cbac..83c32713f401 100644
@@ -259,12 +259,11 @@ int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid)
 }
 EXPORT_SYMBOL(rdma_nl_unicast_wait);
 
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags)
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags)
 {
 	return nlmsg_multicast(nls, skb, 0, group, flags);
 }
-EXPORT_SYMBOL(ibnl_multicast);
+EXPORT_SYMBOL(rdma_nl_multicast);
 
 int __init rdma_nl_init(void)
 {

index b499f4422f41..977f64d0e983 100644
@@ -861,7 +861,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	ret = ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, gfp_mask);
+	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
 	if (!ret)
 		ret = len;
 	else

index e7b0779385e9..16a94c425938 100644
@@ -72,12 +72,10 @@ int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
 /**
  * Send the supplied skb to a netlink group.
  * @skb: The netlink skb
- * @nlh: Header of the netlink message to send
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
-			unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
 #endif /* _RDMA_NETLINK_H */

index 30cf764824ec..7310ece99cd9 100644
@@ -325,7 +325,7 @@ static void queue_req(struct addr_req *req)
 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))
+	if (rdma_nl_chk_listeners(RDMA_NL_GROUP_LS))
 		return -EADDRNOTAVAIL;
 
 	/* We fill in what we can, the response will fill the rest */

index 83c32713f401..b027b6ecd2b3 100644
@@ -47,12 +47,11 @@ static struct {
 	const struct ibnl_client_cbs   *cb_table;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
-int ibnl_chk_listeners(unsigned int group)
+int rdma_nl_chk_listeners(unsigned int group)
 {
-	if (netlink_has_listeners(nls, group) == 0)
-		return -1;
-	return 0;
+	return (netlink_has_listeners(nls, group)) ? 0 : -1;
 }
+EXPORT_SYMBOL(rdma_nl_chk_listeners);
 
 static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 {

index 977f64d0e983..2cc85c2b74b7 100644
@@ -1418,7 +1418,7 @@ static int send_mad(struct ib_sa_query *query, int timeout_ms, gfp_t gfp_mask)
 
 	if ((query->flags & IB_SA_ENABLE_LOCAL_SERVICE) &&
 	    (!(query->flags & IB_SA_QUERY_OPA))) {
-		if (!ibnl_chk_listeners(RDMA_NL_GROUP_LS)) {
+		if (!rdma_nl_chk_listeners(RDMA_NL_GROUP_LS)) {
 			if (!ib_nl_make_request(query, gfp_mask))
 				return id;
 		}

index 16a94c425938..348e0bbe0fc9 100644
@@ -78,4 +78,10 @@ int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
  */
 int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
 
+/**
+ * Check if there are any listeners to the netlink group
+ * @group: the netlink group ID
+ * Returns 0 on success or a negative for no listeners.
+ */
+int rdma_nl_chk_listeners(unsigned int group);
 #endif /* _RDMA_NETLINK_H */

index 0c85f140e616..d8edd8b11561 100644
@@ -4458,7 +4458,7 @@ static int cma_get_id_stats(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static const struct ibnl_client_cbs cma_cb_table[] = {
+static const struct rdma_nl_cbs cma_cb_table[] = {
 	[RDMA_NL_RDMA_CM_ID_STATS] = { .dump = cma_get_id_stats},
 };
 

index 1c5276e6e7f6..a1d5798fa4d7 100644
@@ -1086,7 +1086,7 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
-static const struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
 		.dump = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,

index 8599271d8be6..452a3115e3e6 100644
@@ -80,7 +80,7 @@ const char *__attribute_const__ iwcm_reject_msg(int reason)
 }
 EXPORT_SYMBOL(iwcm_reject_msg);
 
-static struct ibnl_client_cbs iwcm_nl_cb_table[] = {
+static struct rdma_nl_cbs iwcm_nl_cb_table[] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},

index b027b6ecd2b3..2a88f92657fc 100644
@@ -44,7 +44,7 @@
 static DEFINE_MUTEX(rdma_nl_mutex);
 static struct sock *nls;
 static struct {
-	const struct ibnl_client_cbs   *cb_table;
+	const struct rdma_nl_cbs   *cb_table;
 } rdma_nl_types[RDMA_NL_NUM_CLIENTS];
 
 int rdma_nl_chk_listeners(unsigned int group)

@@ -84,7 +84,7 @@ static bool is_nl_valid(unsigned int type, unsigned int op)
 }
 
 void rdma_nl_register(unsigned int index,
-		      const struct ibnl_client_cbs cb_table[])
+		      const struct rdma_nl_cbs cb_table[])
 {
 	mutex_lock(&rdma_nl_mutex);
 	if (!is_nl_msg_valid(index, 0)) {

index 348e0bbe0fc9..92f8832297ab 100644
@@ -5,7 +5,7 @@
 #include <linux/netlink.h>
 #include <uapi/rdma/rdma_netlink.h>
 
-struct ibnl_client_cbs {
+struct rdma_nl_cbs {
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
 	u8 flags;
 };

@@ -21,7 +21,7 @@ enum rdma_nl_flags {
  * @cb_table: A table for op->callback
  */
 void rdma_nl_register(unsigned int index,
-		      const struct ibnl_client_cbs cb_table[]);
+		      const struct rdma_nl_cbs cb_table[]);
 
 /**
  * Remove a client from IB netlink.

index e759c27113cd..0c175590cf92 100644
@@ -102,6 +102,14 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 			      roce_netdev_callback cb,
 			      void *cookie);
 
+typedef int (*nldev_callback)(struct ib_device *device,
+			      struct sk_buff *skb,
+			      struct netlink_callback *cb,
+			      unsigned int idx);
+
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb);
+
 enum ib_cache_gid_default_mode {
 	IB_CACHE_GID_DEFAULT_MODE_SET,
 	IB_CACHE_GID_DEFAULT_MODE_DELETE

index a1d5798fa4d7..54143476a020 100644
@@ -892,6 +892,31 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 	up_read(&lists_rwsem);
 }
 
+/**
+ * ib_enum_all_devs - enumerate all ib_devices
+ * @cb: Callback to call for each found ib_device
+ *
+ * Enumerates all ib_devices and calls callback() on each device.
+ */
+int ib_enum_all_devs(nldev_callback nldev_cb, struct sk_buff *skb,
+		     struct netlink_callback *cb)
+{
+	struct ib_device *dev;
+	unsigned int idx = 0;
+	int ret = 0;
+
+	down_read(&lists_rwsem);
+	list_for_each_entry(dev, &device_list, core_list) {
+		ret = nldev_cb(dev, skb, cb, idx);
+		if (ret)
+			break;
+		idx++;
+	}
+
+	up_read(&lists_rwsem);
+	return ret;
+}
+
 /**
  * ib_query_pkey - Get P_Key table entry
  * @device:Device to query

index 0c175590cf92..cbdcc81e1df8 100644
@@ -309,4 +309,9 @@ static inline int ib_mad_enforce_security(struct ib_mad_agent_private *map,
 	return 0;
 }
 #endif
+
+struct ib_device *__ib_device_get_by_index(u32 ifindex);
+/* RDMA device netlink */
+void nldev_init(void);
+void nldev_exit(void);
 #endif /* _CORE_PRIV_H */

index 54143476a020..41eebd6ca0ff 100644
@@ -134,6 +134,17 @@ static int ib_device_check_mandatory(struct ib_device *device)
 	return 0;
 }
 
+struct ib_device *__ib_device_get_by_index(u32 index)
+{
+	struct ib_device *device;
+
+	list_for_each_entry(device, &device_list, core_list)
+		if (device->index == index)
+			return device;
+
+	return NULL;
+}
+
 static struct ib_device *__ib_device_get_by_name(const char *name)
 {
 	struct ib_device *device;

@@ -145,7 +156,6 @@ static struct ib_device *__ib_device_get_by_name(const char *name)
 	return NULL;
 }
 
-
 static int alloc_name(char *name)
 {
 	unsigned long *inuse;

@@ -394,6 +404,30 @@ static int ib_security_change(struct notifier_block *nb, unsigned long event,
 	return NOTIFY_OK;
 }
 
+/**
+ *	__dev_new_index	-	allocate an device index
+ *
+ *	Returns a suitable unique value for a new device interface
+ *	number.  It assumes that there are less than 2^32-1 ib devices
+ *	will be present in the system.
+ */
+static u32 __dev_new_index(void)
+{
+	/*
+	 * The device index to allow stable naming.
+	 * Similar to struct net -> ifindex.
+	 */
+	static u32 index;
+
+	for (;;) {
+		if (!(++index))
+			index = 1;
+
+		if (!__ib_device_get_by_index(index))
+			return index;
+	}
+}
+
 /**
  * ib_register_device - Register an IB device with IB core
  * @device:Device to register

@@ -492,6 +526,7 @@ int ib_register_device(struct ib_device *device,
 		if (client->add && !add_client_context(device, client))
 			client->add(device);
 
+	device->index = __dev_new_index();
 	down_write(&lists_rwsem);
 	list_add_tail(&device->core_list, &device_list);
 	up_write(&lists_rwsem);

index 1082b4c81b2c..3391df5fdc9c 100644
@@ -2298,6 +2298,8 @@ struct ib_device {
 	struct rdmacg_device         cg_device;
 #endif
 
+	u32                          index;
+
 	/**
 	 * The following mandatory functions are used only at device
 	 * registration.  Keep functions such as these at the end of this

index 2a88f92657fc..a5276bfc5909 100644
@@ -76,9 +76,13 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 
 static bool is_nl_valid(unsigned int type, unsigned int op)
 {
-	if (!is_nl_msg_valid(type, op) ||
-	    !rdma_nl_types[type].cb_table ||
-	    !rdma_nl_types[type].cb_table[op].dump)
+	const struct rdma_nl_cbs *cb_table;
+
+	if (!is_nl_msg_valid(type, op))
+		return false;
+
+	cb_table = rdma_nl_types[type].cb_table;
+	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
 		return false;
 	return true;
 }

@@ -153,6 +157,7 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int op = RDMA_NL_GET_OP(type);
 	struct netlink_callback cb = {};
 	struct netlink_dump_control c = {};
+	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;

@@ -171,10 +176,14 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 		cb.nlh = nlh;
 		cb.dump = rdma_nl_types[index].cb_table[op].dump;
 		return cb.dump(skb, &cb);
+	} else {
+		c.dump = rdma_nl_types[index].cb_table[op].dump;
+		return netlink_dump_start(nls, skb, nlh, &c);
 	}
+	if (rdma_nl_types[index].cb_table[op].doit)
+		ret = rdma_nl_types[index].cb_table[op].doit(skb, nlh, extack);
+	return ret;
 
-	c.dump = rdma_nl_types[index].cb_table[op].dump;
-	return netlink_dump_start(nls, skb, nlh, &c);
 }
 
 /*

index 92f8832297ab..e25bf1988846 100644
@@ -6,6 +6,8 @@
 #include <uapi/rdma/rdma_netlink.h>
 
 struct rdma_nl_cbs {
+	int (*doit)(struct sk_buff *skb, struct nlmsghdr *nlh,
+		    struct netlink_ext_ack *extack);
 	int (*dump)(struct sk_buff *skb, struct netlink_callback *nlcb);
 	u8 flags;
 };

index a5276bfc5909..61216e410492 100644
@@ -157,12 +157,15 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	unsigned int op = RDMA_NL_GET_OP(type);
 	struct netlink_callback cb = {};
 	struct netlink_dump_control c = {};
+	const struct rdma_nl_cbs *cb_table;
 	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
-	if ((rdma_nl_types[index].cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
+	cb_table = rdma_nl_types[type].cb_table;
+
+	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 

@@ -174,14 +177,14 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	    (index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
 		cb.skb = skb;
 		cb.nlh = nlh;
-		cb.dump = rdma_nl_types[index].cb_table[op].dump;
+		cb.dump = cb_table[op].dump;
 		return cb.dump(skb, &cb);
 	} else {
-		c.dump = rdma_nl_types[index].cb_table[op].dump;
+		c.dump = cb_table[op].dump;
 		return netlink_dump_start(nls, skb, nlh, &c);
 	}
-	if (rdma_nl_types[index].cb_table[op].doit)
-		ret = rdma_nl_types[index].cb_table[op].doit(skb, nlh, extack);
+	if (cb_table[op].doit)
+		ret = cb_table[op].doit(skb, nlh, extack);
 	return ret;
 
 }

index 7310ece99cd9..16b3bdffeb96 100644
@@ -129,10 +129,9 @@ static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
-
 	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
 	    !(NETLINK_CB(skb).sk))
 		return -EPERM;

index cbdcc81e1df8..57beb1cceda3 100644
@@ -198,11 +198,14 @@ void rdma_nl_exit(void);
 int ibnl_chk_listeners(unsigned int group);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb);
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack);
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
-			     struct netlink_callback *cb);
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack);
 
 int ib_get_cached_subnet_prefix(struct ib_device *device,
 				u8                port_num,

index 41eebd6ca0ff..5a3ff941c86c 100644
@@ -1148,15 +1148,15 @@ EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
 static const struct rdma_nl_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp,
+		.doit = ib_nl_handle_resolve_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout,
+		.doit = ib_nl_handle_set_timeout,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 	[RDMA_NL_LS_OP_IP_RESOLVE] = {
-		.dump = ib_nl_handle_ip_res_resp,
+		.doit = ib_nl_handle_ip_res_resp,
 		.flags = RDMA_NL_ADMIN_PERM,
 	},
 };

index 61216e410492..71bbf351e91c 100644
@@ -155,38 +155,30 @@ static int rdma_nl_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh,
 	int type = nlh->nlmsg_type;
 	unsigned int index = RDMA_NL_GET_CLIENT(type);
 	unsigned int op = RDMA_NL_GET_OP(type);
-	struct netlink_callback cb = {};
-	struct netlink_dump_control c = {};
 	const struct rdma_nl_cbs *cb_table;
-	int ret;
 
 	if (!is_nl_valid(index, op))
 		return -EINVAL;
 
-	cb_table = rdma_nl_types[type].cb_table;
+	cb_table = rdma_nl_types[index].cb_table;
 
 	if ((cb_table[op].flags & RDMA_NL_ADMIN_PERM) &&
 	    !netlink_capable(skb, CAP_NET_ADMIN))
 		return -EPERM;
 
-	/*
-	 * For response or local service set_timeout request,
-	 * there is no need to use netlink_dump_start.
-	 */
-	if (!(nlh->nlmsg_flags & NLM_F_REQUEST) ||
-	    (index == RDMA_NL_LS && op == RDMA_NL_LS_OP_SET_TIMEOUT)) {
-		cb.skb = skb;
-		cb.nlh = nlh;
-		cb.dump = cb_table[op].dump;
-		return cb.dump(skb, &cb);
-	} else {
-		c.dump = cb_table[op].dump;
+	/* FIXME: Convert IWCM to properly handle doit callbacks */
+	if ((nlh->nlmsg_flags & NLM_F_DUMP) || index == RDMA_NL_RDMA_CM ||
+	    index == RDMA_NL_IWCM) {
+		struct netlink_dump_control c = {
+			.dump = cb_table[op].dump,
+		};
 		return netlink_dump_start(nls, skb, nlh, &c);
 	}
+
 	if (cb_table[op].doit)
-		ret = cb_table[op].doit(skb, nlh, extack);
-	return ret;
+		return cb_table[op].doit(skb, nlh, extack);
 
+	return 0;
 }
 
 /*

index 2cc85c2b74b7..da29e2863c84 100644
@@ -1021,9 +1021,9 @@ static void ib_nl_request_timeout(struct work_struct *work)
 }
 
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
-			     struct netlink_callback *cb)
+			     struct nlmsghdr *nlh,
+			     struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	int timeout, delta, abs_delta;
 	const struct nlattr *attr;
 	unsigned long flags;

@@ -1097,9 +1097,9 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 }
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-			      struct netlink_callback *cb)
+			      struct nlmsghdr *nlh,
+			      struct netlink_ext_ack *extack)
 {
-	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	unsigned long flags;
 	struct ib_sa_query *query;
 	struct ib_mad_send_buf *send_buf;

index 71bbf351e91c..1c80e7ec1730 100644
@@ -1,4 +1,5 @@
 /*
+ * Copyright (c) 2017 Mellanox Technologies Inc.  All rights reserved.
  * Copyright (c) 2010 Voltaire Inc.  All rights reserved.
  *
  * This software is available to you under a choice of one of two

index 1c80e7ec1730..911c71706c16 100644
@@ -61,7 +61,7 @@ static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 				  RDMA_NL_IWPM_NUM_OPS,
 				  0,
 				  RDMA_NL_LS_NUM_OPS,
-				  0 };
+				  RDMA_NLDEV_NUM_OPS };
 
 	/*
 	 * This BUILD_BUG_ON is intended to catch addition of new

index 02fe8390c18f..1d064fedfa9a 100644
@@ -8,7 +8,7 @@ enum {
 	RDMA_NL_IWCM,
 	RDMA_NL_RSVD,
 	RDMA_NL_LS,	/* RDMA Local Services */
-	RDMA_NL_I40IW,
+	RDMA_NL_NLDEV,	/* RDMA device interface */
 	RDMA_NL_NUM_CLIENTS
 };
 

@@ -222,4 +222,41 @@ struct rdma_nla_ls_gid {
 	__u8		gid[16];
 };
 
+enum rdma_nldev_command {
+	RDMA_NLDEV_CMD_UNSPEC,
+
+	RDMA_NLDEV_CMD_GET, /* can dump */
+	RDMA_NLDEV_CMD_SET,
+	RDMA_NLDEV_CMD_NEW,
+	RDMA_NLDEV_CMD_DEL,
+
+	RDMA_NLDEV_CMD_PORT_GET, /* can dump */
+	RDMA_NLDEV_CMD_PORT_SET,
+	RDMA_NLDEV_CMD_PORT_NEW,
+	RDMA_NLDEV_CMD_PORT_DEL,
+
+	RDMA_NLDEV_NUM_OPS
+};
+
+enum rdma_nldev_attr {
+	/* don't change the order or add anything between, this is ABI! */
+	RDMA_NLDEV_ATTR_UNSPEC,
+
+	/* Identifier for ib_device */
+	RDMA_NLDEV_ATTR_DEV_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_DEV_NAME,		/* string */
+	/*
+	 * Device index together with port index are identifiers
+	 * for port/link properties.
+	 *
+	 * For RDMA_NLDEV_CMD_GET comamnd, port index will return number
+	 * of available ports in ib_device, while for port specific operations,
+	 * it will be real port index as it appears in sysfs. Port index follows
+	 * sysfs notation and starts from 1 for the first port.
+	 */
+	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
+
+	RDMA_NLDEV_ATTR_MAX
+};
 #endif /* _UAPI_RDMA_NETLINK_H */

index 5a3ff941c86c..fca126aa001b 100644
@@ -1212,6 +1212,7 @@ static int __init ib_core_init(void)
 		goto err_sa;
 	}
 
+	nldev_init();
 	rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
 	ib_cache_setup();
 

@@ -1237,6 +1238,7 @@ static int __init ib_core_init(void)
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	nldev_exit();
 	rdma_nl_unregister(RDMA_NL_LS);
 	unregister_lsm_notifier(&ibdev_lsm_nb);
 	ib_sa_cleanup();

45 lines not on this page · raw message

index 1d1e4f214874..4b8b0f5d5344 100644
@@ -30,13 +30,75 @@
  * POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <net/netlink.h>
 #include <rdma/rdma_netlink.h>
 
 #include "core_priv.h"
 
+static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
+	[RDMA_NLDEV_ATTR_DEV_INDEX]     = { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_DEV_NAME]	= { .type = NLA_NUL_STRING,
+					    .len = IB_DEVICE_NAME_MAX - 1},
+	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
+};
+
+static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
+{
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device)))
+		return -EMSGSIZE;
+	return 0;
+}
+
+static int _nldev_get_dumpit(struct ib_device *device,
+			     struct sk_buff *skb,
+			     struct netlink_callback *cb,
+			     unsigned int idx)
+{
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+
+	if (idx < start)
+		return 0;
+
+	nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, NLM_F_MULTI);
+
+	if (fill_dev_info(skb, device)) {
+		nlmsg_cancel(skb, nlh);
+		goto out;
+	}
+
+	nlmsg_end(skb, nlh);
+
+	idx++;
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
+static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	/*
+	 * There is no need to take lock, because
+	 * we are relying on ib_core's lists_rwsem
+	 */
+	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
+}
+
+static const struct rdma_nl_cbs nldev_cb_table[] = {
+	[RDMA_NLDEV_CMD_GET] = {
+		.dump = nldev_get_dumpit,
+	},
+};
+
 void __init nldev_init(void)
 {
-	rdma_nl_register(RDMA_NL_NLDEV, NULL);
+	rdma_nl_register(RDMA_NL_NLDEV, nldev_cb_table);
 }
 
 void __exit nldev_exit(void)

index 4b8b0f5d5344..666940f2b49a 100644
@@ -53,6 +53,45 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	return 0;
 }
 
+static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			  struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_dev_info(msg, device);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
 static int _nldev_get_dumpit(struct ib_device *device,
 			     struct sk_buff *skb,
 			     struct netlink_callback *cb,

@@ -92,6 +131,7 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 
 static const struct rdma_nl_cbs nldev_cb_table[] = {
 	[RDMA_NLDEV_CMD_GET] = {
+		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
 	},
 };

index 666940f2b49a..4413eda8c435 100644
@@ -53,6 +53,18 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	return 0;
 }
 
+static int fill_port_info(struct sk_buff *msg,
+			  struct ib_device *device, u32 port)
+{
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
+		return -EMSGSIZE;
+	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
+		return -EMSGSIZE;
+	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
+		return -EMSGSIZE;
+	return 0;
+}
+
 static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 			  struct netlink_ext_ack *extack)
 {

@@ -129,11 +141,60 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
 }
 
+static int nldev_port_get_dumpit(struct sk_buff *skb,
+				 struct netlink_callback *cb)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+	u32 idx = 0;
+	u32 ifindex;
+	int err;
+	u32 p;
+
+	err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, NULL);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_INDEX])
+		return -EINVAL;
+
+	ifindex = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(ifindex);
+	if (!device)
+		return -EINVAL;
+
+	for (p = rdma_start_port(device); p <= rdma_end_port(device); ++p) {
+		if (idx < start) {
+			idx++;
+			continue;
+		}
+
+		nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid,
+				cb->nlh->nlmsg_seq,
+				RDMA_NL_GET_TYPE(RDMA_NL_NLDEV,
+						 RDMA_NLDEV_CMD_PORT_GET),
+				0, NLM_F_MULTI);
+
+		if (fill_port_info(skb, device, p)) {
+			nlmsg_cancel(skb, nlh);
+			goto out;
+		}
+		idx++;
+		nlmsg_end(skb, nlh);
+	}
+
+out:	cb->args[0] = idx;
+	return skb->len;
+}
+
 static const struct rdma_nl_cbs nldev_cb_table[] = {
 	[RDMA_NLDEV_CMD_GET] = {
 		.doit = nldev_get_doit,
 		.dump = nldev_get_dumpit,
 	},
+	[RDMA_NLDEV_CMD_PORT_GET] = {
+		.dump = nldev_port_get_dumpit,
+	},
 };
 
 void __init nldev_init(void)

index 4413eda8c435..533ac72a05b8 100644
@@ -141,6 +141,49 @@ static int nldev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 	return ib_enum_all_devs(_nldev_get_dumpit, skb, cb);
 }
 
+static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
+			       struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[RDMA_NLDEV_ATTR_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 index;
+	u32 port;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX - 1,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+		return -EINVAL;
+
+	index = nla_get_u32(tb[RDMA_NLDEV_ATTR_DEV_INDEX]);
+	device = __ib_device_get_by_index(index);
+	if (!device)
+		return -EINVAL;
+
+	port = nla_get_u32(tb[RDMA_NLDEV_ATTR_PORT_INDEX]);
+	if (!rdma_is_port_valid(device, port))
+		return -EINVAL;
+
+	msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(msg, NETLINK_CB(skb).portid, nlh->nlmsg_seq,
+			RDMA_NL_GET_TYPE(RDMA_NL_NLDEV, RDMA_NLDEV_CMD_GET),
+			0, 0);
+
+	err = fill_port_info(msg, device, port);
+	if (err) {
+		nlmsg_free(msg);
+		return err;
+	}
+
+	nlmsg_end(msg, nlh);
+
+	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+}
+
 static int nldev_port_get_dumpit(struct sk_buff *skb,
 				 struct netlink_callback *cb)
 {

@@ -193,6 +236,7 @@ static const struct rdma_nl_cbs nldev_cb_table[] = {
 		.dump = nldev_get_dumpit,
 	},
 	[RDMA_NLDEV_CMD_PORT_GET] = {
+		.doit = nldev_port_get_doit,
 		.dump = nldev_port_get_dumpit,
 	},
 };

index 533ac72a05b8..21e75928400c 100644
@@ -50,18 +50,37 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 		return -EMSGSIZE;
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, rdma_end_port(device)))
 		return -EMSGSIZE;
+
+	BUILD_BUG_ON(sizeof(device->attrs.device_cap_flags) != sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      device->attrs.device_cap_flags, 0))
+		return -EMSGSIZE;
+
 	return 0;
 }
 
 static int fill_port_info(struct sk_buff *msg,
 			  struct ib_device *device, u32 port)
 {
+	struct ib_port_attr attr;
+	int ret;
+
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
 		return -EMSGSIZE;
 	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))
 		return -EMSGSIZE;
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_PORT_INDEX, port))
 		return -EMSGSIZE;
+
+	ret = ib_query_port(device, port, &attr);
+	if (ret)
+		return ret;
+
+	BUILD_BUG_ON(sizeof(attr.port_cap_flags) > sizeof(u64));
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
+			      (u64)attr.port_cap_flags, 0))
+		return -EMSGSIZE;
+
 	return 0;
 }
 

index 1d064fedfa9a..8fc5278d07d6 100644
@@ -257,6 +257,11 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_PORT_INDEX,		/* u32 */
 
+	/*
+	 * Device and port capabilities
+	 */
+	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */

index fca126aa001b..75220569b00e 100644
@@ -336,10 +336,10 @@ static int read_port_immutable(struct ib_device *device)
 	return 0;
 }
 
-void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len)
+void ib_get_device_fw_str(struct ib_device *dev, char *str)
 {
 	if (dev->get_dev_fw_str)
-		dev->get_dev_fw_str(dev, str, str_len);
+		dev->get_dev_fw_str(dev, str);
 	else
 		str[0] = '\0';
 }

index 7ebe1ef23652..abc5ab581f82 100644
@@ -1210,8 +1210,8 @@ static ssize_t show_fw_ver(struct device *device, struct device_attribute *attr,
 {
 	struct ib_device *dev = container_of(device, struct ib_device, dev);
 
-	ib_get_device_fw_str(dev, buf, PAGE_SIZE);
-	strlcat(buf, "\n", PAGE_SIZE);
+	ib_get_device_fw_str(dev, buf);
+	strlcat(buf, "\n", IB_FW_VERSION_NAME_MAX);
 	return strlen(buf);
 }
 

index 0cd0c1fa27d4..099e76f3758a 100644
@@ -1336,8 +1336,7 @@ static int iwch_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str,
-			       size_t str_len)
+static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str)
 {
 	struct iwch_dev *iwch_dev = to_iwch_dev(ibdev);
 	struct ethtool_drvinfo info;

@@ -1345,7 +1344,7 @@ static void get_dev_fw_ver_str(struct ib_device *ibdev, char *str,
 
 	pr_debug("%s dev 0x%p\n", __func__, iwch_dev);
 	lldev->ethtool_ops->get_drvinfo(lldev, &info);
-	snprintf(str, str_len, "%s", info.fw_version);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version);
 }
 
 int iwch_register_device(struct iwch_dev *dev)

index 0771e9a4d061..346e8334279a 100644
@@ -517,14 +517,13 @@ static int c4iw_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *dev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	struct c4iw_dev *c4iw_dev = container_of(dev, struct c4iw_dev,
 						 ibdev);
 	pr_debug("%s dev 0x%p\n", __func__, dev);
 
-	snprintf(str, str_len, "%u.%u.%u.%u",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u.%u",
 		 FW_HDR_FW_VER_MAJOR_G(c4iw_dev->rdev.lldi.fw_vers),
 		 FW_HDR_FW_VER_MINOR_G(c4iw_dev->rdev.lldi.fw_vers),
 		 FW_HDR_FW_VER_MICRO_G(c4iw_dev->rdev.lldi.fw_vers),

index dc51bf247006..c88c03c11555 100644
@@ -1561,14 +1561,13 @@ static void init_ibport(struct hfi1_pportdata *ppd)
 	RCU_INIT_POINTER(ibp->rvp.qp[1], NULL);
 }
 
-static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str,
-				size_t str_len)
+static void hfi1_get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct rvt_dev_info *rdi = ib_to_rvt(ibdev);
 	struct hfi1_ibdev *dev = dev_from_rdi(rdi);
 	u32 ver = dd_from_dev(dev)->dc8051_ver;
 
-	snprintf(str, str_len, "%u.%u.%u", dc8051_ver_maj(ver),
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u.%u", dc8051_ver_maj(ver),
 		 dc8051_ver_min(ver), dc8051_ver_patch(ver));
 }
 

index 02d871db7ca5..1aa411034a27 100644
@@ -2584,13 +2584,12 @@ static const char * const i40iw_hw_stat_names[] = {
 		"iwRdmaInv"
 };
 
-static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str,
-				 size_t str_len)
+static void i40iw_get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	u32 firmware_version = I40IW_FW_VERSION;
 
-	snprintf(str, str_len, "%u.%u", firmware_version,
-		       (firmware_version & 0x000000ff));
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u", firmware_version,
+		 (firmware_version & 0x000000ff));
 }
 
 /**

index 1f25a37eb056..c636842c5be0 100644
@@ -2587,12 +2587,11 @@ static int mlx4_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_fw_ver_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_fw_ver_str(struct ib_device *device, char *str)
 {
 	struct mlx4_ib_dev *dev =
 		container_of(device, struct mlx4_ib_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
 		 (int) (dev->dev->caps.fw_ver >> 32),
 		 (int) (dev->dev->caps.fw_ver >> 16) & 0xffff,
 		 (int) dev->dev->caps.fw_ver & 0xffff);

index 9279631d8da0..0a5a4e3fa66d 100644
@@ -3285,13 +3285,13 @@ static int mlx5_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *ibdev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct mlx5_ib_dev *dev =
 		container_of(ibdev, struct mlx5_ib_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%04d", fw_rev_maj(dev->mdev),
-		       fw_rev_min(dev->mdev), fw_rev_sub(dev->mdev));
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%04d",
+		 fw_rev_maj(dev->mdev), fw_rev_min(dev->mdev),
+		 fw_rev_sub(dev->mdev));
 }
 
 static int mlx5_eth_lag_init(struct mlx5_ib_dev *dev)

index c197cd9b193f..eae9bffd45d4 100644
@@ -1178,12 +1178,11 @@ static int mthca_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct mthca_dev *dev =
 		container_of(device, struct mthca_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d",
 		 (int) (dev->fw_ver >> 32),
 		 (int) (dev->fw_ver >> 16) & 0xffff,
 		 (int) dev->fw_ver & 0xffff);

index 25dcd7573df9..c2943e39d2f9 100644
@@ -3672,15 +3672,14 @@ static int nes_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *dev, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *dev, char *str)
 {
 	struct nes_ib_device *nesibdev =
 			container_of(dev, struct nes_ib_device, ibdev);
 	struct nes_vnic *nesvnic = nesibdev->nesvnic;
 
 	nes_debug(NES_DBG_INIT, "\n");
-	snprintf(str, str_len, "%u.%u",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%u.%u",
 		 (nesvnic->nesdev->nesadapter->firmware_version >> 16),
 		 (nesvnic->nesdev->nesadapter->firmware_version & 0x000000ff));
 }

index 757c65816295..fbfbd9e96147 100644
@@ -107,12 +107,11 @@ static int ocrdma_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void get_dev_fw_str(struct ib_device *device, char *str,
-			   size_t str_len)
+static void get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct ocrdma_dev *dev = get_ocrdma_dev(device);
 
-	snprintf(str, str_len, "%s", &dev->attr.fw_ver[0]);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", &dev->attr.fw_ver[0]);
 }
 
 static int ocrdma_register_device(struct ocrdma_dev *dev)

index 199b6edbef92..97d033f51dc9 100644
@@ -68,13 +68,12 @@ static enum rdma_link_layer qedr_link_layer(struct ib_device *device,
 	return IB_LINK_LAYER_ETHERNET;
 }
 
-static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str,
-				size_t str_len)
+static void qedr_get_dev_fw_str(struct ib_device *ibdev, char *str)
 {
 	struct qedr_dev *qedr = get_qedr_dev(ibdev);
 	u32 fw_ver = (u32)qedr->attr.fw_ver;
 
-	snprintf(str, str_len, "%d. %d. %d. %d",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d. %d. %d. %d",
 		 (fw_ver >> 24) & 0xFF, (fw_ver >> 16) & 0xFF,
 		 (fw_ver >> 8) & 0xFF, fw_ver & 0xFF);
 }

index e69c8e476a2b..e86700f994cb 100644
@@ -333,9 +333,7 @@ static int usnic_port_immutable(struct ib_device *ibdev, u8 port_num,
 	return 0;
 }
 
-static void usnic_get_dev_fw_str(struct ib_device *device,
-				 char *str,
-				 size_t str_len)
+static void usnic_get_dev_fw_str(struct ib_device *device, char *str)
 {
 	struct usnic_ib_dev *us_ibdev =
 		container_of(device, struct usnic_ib_dev, ib_dev);

@@ -345,7 +343,7 @@ static void usnic_get_dev_fw_str(struct ib_device *device,
 	us_ibdev->netdev->ethtool_ops->get_drvinfo(us_ibdev->netdev, &info);
 	mutex_unlock(&us_ibdev->usdev_lock);
 
-	snprintf(str, str_len, "%s", info.fw_version);
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%s", info.fw_version);
 }
 
 /* Start of PF discovery section */

index e76565280afa..7f29e4db28a1 100644
@@ -102,12 +102,11 @@ static struct device_attribute *pvrdma_class_attributes[] = {
 	&dev_attr_board_id
 };
 
-static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str,
-				  size_t str_len)
+static void pvrdma_get_fw_ver_str(struct ib_device *device, char *str)
 {
 	struct pvrdma_dev *dev =
 		container_of(device, struct pvrdma_dev, ib_dev);
-	snprintf(str, str_len, "%d.%d.%d\n",
+	snprintf(str, IB_FW_VERSION_NAME_MAX, "%d.%d.%d\n",
 		 (int) (dev->dsr->caps.fw_ver >> 32),
 		 (int) (dev->dsr->caps.fw_ver >> 16) & 0xffff,
 		 (int) dev->dsr->caps.fw_ver & 0xffff);

index 7871379342f4..98e30b41e436 100644
@@ -62,8 +62,7 @@ static void ipoib_get_drvinfo(struct net_device *netdev,
 {
 	struct ipoib_dev_priv *priv = ipoib_priv(netdev);
 
-	ib_get_device_fw_str(priv->ca, drvinfo->fw_version,
-			     sizeof(drvinfo->fw_version));
+	ib_get_device_fw_str(priv->ca, drvinfo->fw_version);
 
 	strlcpy(drvinfo->bus_info, dev_name(priv->ca->dev.parent),
 		sizeof(drvinfo->bus_info));

index 3391df5fdc9c..e0e87a1f66fb 100644
@@ -64,6 +64,8 @@
 #include <linux/cgroup_rdma.h>
 #include <uapi/rdma/ib_user_verbs.h>
 
+#define IB_FW_VERSION_NAME_MAX	ETHTOOL_FWVERS_LEN
+
 extern struct workqueue_struct *ib_wq;
 extern struct workqueue_struct *ib_comp_wq;
 

@@ -2307,7 +2309,7 @@ struct ib_device {
 	 * in fast paths.
 	 */
 	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);
+	void (*get_dev_fw_str)(struct ib_device *, char *str);
 };
 
 struct ib_client {

@@ -2343,7 +2345,7 @@ struct ib_client {
 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);
+void ib_get_device_fw_str(struct ib_device *device, char *str);
 
 int ib_register_device(struct ib_device *device,
 		       int (*port_callback)(struct ib_device *,

index 21e75928400c..40d5f0eb16f5 100644
@@ -40,10 +40,14 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_DEV_NAME]	= { .type = NLA_NUL_STRING,
 					    .len = IB_DEVICE_NAME_MAX - 1},
 	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_FW_VERSION]	= { .type = NLA_NUL_STRING,
+					    .len = IB_FW_VERSION_NAME_MAX - 1},
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 {
+	char fw[IB_FW_VERSION_NAME_MAX];
+
 	if (nla_put_u32(msg, RDMA_NLDEV_ATTR_DEV_INDEX, device->index))
 		return -EMSGSIZE;
 	if (nla_put_string(msg, RDMA_NLDEV_ATTR_DEV_NAME, device->name))

@@ -56,6 +60,11 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 			      device->attrs.device_cap_flags, 0))
 		return -EMSGSIZE;
 
+	ib_get_device_fw_str(device, fw);
+	/* Device without FW has strlen(fw) */
+	if (strlen(fw) && nla_put_string(msg, RDMA_NLDEV_ATTR_FW_VERSION, fw))
+		return -EMSGSIZE;
+
 	return 0;
 }
 

index 8fc5278d07d6..fec735f73eee 100644
@@ -262,6 +262,10 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_CAP_FLAGS,		/* u64 */
 
+	/*
+	 * FW version
+	 */
+	RDMA_NLDEV_ATTR_FW_VERSION,		/* string */
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */

index 40d5f0eb16f5..fde0138fff5f 100644
@@ -42,6 +42,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_PORT_INDEX]	= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_FW_VERSION]	= { .type = NLA_NUL_STRING,
 					    .len = IB_FW_VERSION_NAME_MAX - 1},
+	[RDMA_NLDEV_ATTR_NODE_GUID]	= { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)

@@ -65,6 +67,12 @@ static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)
 	if (strlen(fw) && nla_put_string(msg, RDMA_NLDEV_ATTR_FW_VERSION, fw))
 		return -EMSGSIZE;
 
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_NODE_GUID,
+			      be64_to_cpu(device->node_guid), 0))
+		return -EMSGSIZE;
+	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,
+			      be64_to_cpu(device->attrs.sys_image_guid), 0))
+		return -EMSGSIZE;
 	return 0;
 }
 

index fec735f73eee..b34f7745daf0 100644
@@ -266,6 +266,19 @@ enum rdma_nldev_attr {
 	 * FW version
 	 */
 	RDMA_NLDEV_ATTR_FW_VERSION,		/* string */
+
+	/*
+	 * Node GUID (in host byte order) associated with the RDMA device.
+	 */
+	RDMA_NLDEV_ATTR_NODE_GUID,			/* u64 */
+
+	/*
+	 * System image GUID (in host byte order) associated with
+	 * this RDMA device and other devices which are part of a
+	 * single system.
+	 */
+	RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */

index fde0138fff5f..c4884841e2fe 100644
@@ -44,6 +44,7 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 					    .len = IB_FW_VERSION_NAME_MAX - 1},
 	[RDMA_NLDEV_ATTR_NODE_GUID]	= { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_SUBNET_PREFIX]	= { .type = NLA_U64 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)

@@ -97,6 +98,10 @@ static int fill_port_info(struct sk_buff *msg,
 	if (nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_CAP_FLAGS,
 			      (u64)attr.port_cap_flags, 0))
 		return -EMSGSIZE;
+	if (rdma_protocol_ib(device, port) &&
+	    nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX,
+			      attr.subnet_prefix, 0))
+		return -EMSGSIZE;
 
 	return 0;
 }

index b34f7745daf0..24712d810dca 100644
@@ -279,6 +279,11 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_SYS_IMAGE_GUID,		/* u64 */
 
+	/*
+	 * Subnet prefix (in host byte order)
+	 */
+	RDMA_NLDEV_ATTR_SUBNET_PREFIX,		/* u64 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */

index c4884841e2fe..ce733bf33ed9 100644
@@ -45,6 +45,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_NODE_GUID]	= { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_SYS_IMAGE_GUID] = { .type = NLA_U64 },
 	[RDMA_NLDEV_ATTR_SUBNET_PREFIX]	= { .type = NLA_U64 },
+	[RDMA_NLDEV_ATTR_LID]		= { .type = NLA_U32 },
+	[RDMA_NLDEV_ATTR_SM_LID]	= { .type = NLA_U32 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)

@@ -102,7 +104,12 @@ static int fill_port_info(struct sk_buff *msg,
 	    nla_put_u64_64bit(msg, RDMA_NLDEV_ATTR_SUBNET_PREFIX,
 			      attr.subnet_prefix, 0))
 		return -EMSGSIZE;
-
+	if (rdma_protocol_ib(device, port)) {
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_LID, attr.lid))
+			return -EMSGSIZE;
+		if (nla_put_u32(msg, RDMA_NLDEV_ATTR_SM_LID, attr.sm_lid))
+			return -EMSGSIZE;
+	}
 	return 0;
 }