[PATCH rdma-next 00/19] 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);
 

@@ -324,7 +324,7 @@ 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 */

@@ -46,13 +46,11 @@ 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(ibnl_chk_listeners);
+EXPORT_SYMBOL(rdma_nl_chk_listeners);
 
 static bool is_nl_msg_valid(unsigned int type, unsigned int op)
 {

@@ -1419,7 +1419,7 @@ 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;
 		}

@@ -78,6 +78,6 @@ int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
  * @group: the netlink group ID
  * Returns 0 on success or a negative for no listeners.
  */
-int ibnl_chk_listeners(unsigned int group);
+int rdma_nl_chk_listeners(unsigned int group);
 
 #endif /* _RDMA_NETLINK_H */

@@ -50,6 +50,45 @@ 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];
+	char name[IB_DEVICE_NAME_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return -EINVAL;
+
+	nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME], IB_DEVICE_NAME_MAX);
+
+	device = __ib_device_get_by_name(name);
+	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,

@@ -89,6 +128,7 @@ 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,
 	},
 };

@@ -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

@@ -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)

@@ -59,12 +59,10 @@ 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.

@@ -156,12 +156,15 @@ 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;
 

@@ -173,14 +176,14 @@ 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;
 
 }

@@ -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;

@@ -178,11 +178,14 @@ int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
 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_name(const char *name);
 #endif /* _CORE_PRIV_H */

@@ -1034,15 +1034,15 @@ 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,
 	},
 };

@@ -154,38 +154,30 @@ 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;
+	/* TODO: 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;

@@ -184,4 +184,5 @@ 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_name(const char *name);
 #endif /* _CORE_PRIV_H */

@@ -124,7 +124,7 @@ static int ib_device_check_mandatory(struct ib_device *device)
 	return 0;
 }
 
-static struct ib_device *__ib_device_get_by_name(const char *name)
+struct ib_device *__ib_device_get_by_name(const char *name)
 {
 	struct ib_device *device;
 

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

@@ -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

@@ -30,13 +30,72 @@
  * 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_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_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)

@@ -10,7 +10,9 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
 				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
-				multicast.o mad.o smi.o agent.o mad_rmpp.o
+				multicast.o mad.o smi.o agent.o mad_rmpp.o \
+				nldev.o
+
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 ib_core-$(CONFIG_CGROUP_RDMA) += cgroup.o

@@ -188,4 +188,8 @@ int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
 			     struct netlink_ext_ack *extack);
 
 struct ib_device *__ib_device_get_by_name(const char *name);
+
+/* RDMA device netlink */
+void nldev_init(void);
+void nldev_exit(void);
 #endif /* _CORE_PRIV_H */

@@ -1092,6 +1092,7 @@ static int __init ib_core_init(void)
 		goto err_mad;
 	}
 
+	nldev_init();
 	rdma_nl_register(RDMA_NL_LS, ibnl_ls_cb_table);
 	ib_cache_setup();
 

@@ -1115,6 +1116,7 @@ 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);
 	ib_sa_cleanup();
 	ib_mad_cleanup();

@@ -0,0 +1,45 @@
+/*
+ * Copyright (c) 2017 Mellanox Technologies. All rights reserved.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the names of the copyright holders nor the names of its
+ *    contributors may be used to endorse or promote products derived from
+ *    this software without specific prior written permission.
+ *
+ * Alternatively, this software may be distributed under the terms of the
+ * GNU General Public License ("GPL") version 2 as published by the Free
+ * Software Foundation.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
+ * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
+ * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+ * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+ * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+ * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+ * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+ * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+ * POSSIBILITY OF SUCH DAMAGE.
+ */
+
+#include <rdma/rdma_netlink.h>
+
+#include "core_priv.h"
+
+void __init nldev_init(void)
+{
+	rdma_nl_register(RDMA_NL_NLDEV, NULL);
+}
+
+void __exit nldev_exit(void)
+{
+	rdma_nl_unregister(RDMA_NL_NLDEV);
+}

@@ -136,6 +136,50 @@ 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];
+	char name[IB_DEVICE_NAME_MAX];
+	struct ib_device *device;
+	struct sk_buff *msg;
+	u32 port;
+	int err;
+
+	err = nlmsg_parse(nlh, 0, tb, RDMA_NLDEV_ATTR_MAX,
+			  nldev_policy, extack);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_NAME] ||
+	    !tb[RDMA_NLDEV_ATTR_PORT_INDEX])
+		return -EINVAL;
+
+	nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME], IB_DEVICE_NAME_MAX);
+	device = __ib_device_get_by_name(name);
+	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)
 {

@@ -189,6 +233,7 @@ 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,
 	},
 };

@@ -47,16 +47,35 @@ 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_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;
 }
 

@@ -262,6 +262,11 @@ 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 */

@@ -50,6 +50,16 @@ 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_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)
 {

@@ -126,11 +136,61 @@ 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];
+	char name[IB_DEVICE_NAME_MAX];
+	struct ib_device *device;
+	int start = cb->args[0];
+	struct nlmsghdr *nlh;
+	u32 idx = 0;
+	int err;
+	u32 p;
+
+	err = nlmsg_parse(cb->nlh, 0, tb, RDMA_NLDEV_ATTR_MAX,
+			  nldev_policy, NULL);
+	if (err || !tb[RDMA_NLDEV_ATTR_DEV_NAME])
+		return -EINVAL;
+
+	nla_strlcpy(name, tb[RDMA_NLDEV_ATTR_DEV_NAME], IB_DEVICE_NAME_MAX);
+
+	device = __ib_device_get_by_name(name);
+	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)