[PATCH rdma-next V2 00/27] RDMA Netlink Device Client

@@ -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);
 

@@ -185,7 +185,7 @@ 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.

@@ -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;

@@ -247,12 +247,11 @@ int rdma_nl_unicast(struct sk_buff *skb, u32 pid)
 }
 EXPORT_SYMBOL(rdma_nl_unicast);
 
-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)
 {

@@ -862,7 +862,7 @@ 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

@@ -64,12 +64,10 @@ int rdma_nl_unicast(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 */

@@ -4476,7 +4476,7 @@ 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},
 };
 

@@ -1008,7 +1008,7 @@ 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,

@@ -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},

@@ -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)) {

@@ -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.

@@ -92,6 +92,14 @@ 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

@@ -815,6 +815,31 @@ void ib_enum_all_roce_netdevs(roce_netdev_filter filter,
 }
 
 /**
+ * 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
  * @port_num:Port number to query

@@ -194,4 +194,8 @@ int ib_nl_handle_set_timeout(struct sk_buff *skb,
 int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 			     struct netlink_callback *cb);
 
+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 */

@@ -124,6 +124,17 @@ 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;

@@ -135,7 +146,6 @@ static struct ib_device *__ib_device_get_by_name(const char *name)
 	return NULL;
 }
 
-
 static int alloc_name(char *name)
 {
 	unsigned long *inuse;

@@ -326,6 +336,30 @@ void ib_get_device_fw_str(struct ib_device *dev, char *str, size_t str_len)
 EXPORT_SYMBOL(ib_get_device_fw_str);
 
 /**
+ *	__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
  *

@@ -417,6 +451,7 @@ 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);

@@ -2237,6 +2237,8 @@ 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

@@ -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);
 }
 
 /*

@@ -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;
 };

@@ -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;
 
 }

@@ -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(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast(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(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast(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(skb, nlh, iwpm_user_pid);
+	ret = rdma_nl_unicast(skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;

@@ -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;

@@ -241,12 +241,11 @@ 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)
 {
 	return nlmsg_unicast(nls, skb, pid);
 }
-EXPORT_SYMBOL(ibnl_unicast);
+EXPORT_SYMBOL(rdma_nl_unicast);
 
 int ibnl_multicast(struct sk_buff *skb, struct nlmsghdr *nlh,
 			unsigned int group, gfp_t flags)

@@ -56,12 +56,10 @@ 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 the supplied skb to a netlink group.

@@ -48,6 +48,8 @@ static const struct nla_policy nldev_policy[RDMA_NLDEV_ATTR_MAX] = {
 	[RDMA_NLDEV_ATTR_LID]		= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_SM_LID]	= { .type = NLA_U32 },
 	[RDMA_NLDEV_ATTR_LMC]		= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_PORT_STATE]	= { .type = NLA_U8 },
+	[RDMA_NLDEV_ATTR_PORT_PHYS_STATE] = { .type = NLA_U8 },
 };
 
 static int fill_dev_info(struct sk_buff *msg, struct ib_device *device)

@@ -113,6 +115,10 @@ static int fill_port_info(struct sk_buff *msg,
 		if (nla_put_u8(msg, RDMA_NLDEV_ATTR_LMC, attr.lmc))
 			return -EMSGSIZE;
 	}
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_STATE, attr.state))
+		return -EMSGSIZE;
+	if (nla_put_u8(msg, RDMA_NLDEV_ATTR_PORT_PHYS_STATE, attr.phys_state))
+		return -EMSGSIZE;
 	return 0;
 }
 

@@ -297,6 +297,9 @@ enum rdma_nldev_attr {
 	 */
 	RDMA_NLDEV_ATTR_LMC,			/* u8 */
 
+	RDMA_NLDEV_ATTR_PORT_STATE,		/* u8 */
+	RDMA_NLDEV_ATTR_PORT_PHYS_STATE,	/* u8 */
+
 	RDMA_NLDEV_ATTR_MAX
 };
 #endif /* _UAPI_RDMA_NETLINK_H */

@@ -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;

@@ -188,11 +188,14 @@ 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);
 
 struct ib_device *__ib_device_get_by_index(u32 ifindex);
 /* RDMA device netlink */

@@ -1070,15 +1070,15 @@ 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,
 	},
 };

@@ -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;
 }
 
 /*

@@ -1022,9 +1022,9 @@ 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;

@@ -1098,9 +1098,9 @@ 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;

@@ -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,
 	},
 };

@@ -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)

@@ -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;
 }
 

@@ -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 */

@@ -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;
 }
 

@@ -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 */

@@ -326,10 +326,10 @@ 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';
 }

@@ -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);
 }
 

@@ -1337,8 +1337,7 @@ 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;

@@ -1346,7 +1345,7 @@ 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)

@@ -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),