summaryrefslogtreecommitdiff
path: root/drivers/infiniband/core/netlink.c
blob: 1fb72c356e36ccc77fc3d97e384a238d9fa6d2f9 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
/*
 * 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
 * licenses.  You may choose to be licensed under the terms of the GNU
 * General Public License (GPL) Version 2, available from the file
 * COPYING in the main directory of this source tree, or the
 * OpenIB.org BSD license below:
 *
 *     Redistribution and use in source and binary forms, with or
 *     without modification, are permitted provided that the following
 *     conditions are met:
 *
 *      - Redistributions of source code must retain the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer.
 *
 *      - Redistributions in binary form must reproduce the above
 *        copyright notice, this list of conditions and the following
 *        disclaimer in the documentation and/or other materials
 *        provided with the distribution.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 * SOFTWARE.
 */

#define pr_fmt(fmt) "%s:%s: " fmt, KBUILD_MODNAME, __func__

#include <linux/export.h>
#include <net/netlink.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <rdma/rdma_netlink.h>
#include <linux/module.h>
#include "core_priv.h"

#include "core_priv.h"

static DEFINE_MUTEX(rdma_nl_mutex);
static struct sock *nls;
static struct {
	const struct rdma_nl_cbs   *cb_table;
} rdma_nl_types[RDMA_NL_NUM_CLIENTS];

int rdma_nl_chk_listeners(unsigned int group)
{
	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)
{
	static const unsigned int max_num_ops[RDMA_NL_NUM_CLIENTS] = {
		[RDMA_NL_RDMA_CM] = RDMA_NL_RDMA_CM_NUM_OPS,
		[RDMA_NL_IWCM] = RDMA_NL_IWPM_NUM_OPS,
		[RDMA_NL_LS] = RDMA_NL_LS_NUM_OPS,
		[RDMA_NL_NLDEV] = RDMA_NLDEV_NUM_OPS,
	};

	/*
	 * This BUILD_BUG_ON is intended to catch addition of new
	 * RDMA netlink protocol without updating the array above.
	 */
	BUILD_BUG_ON(RDMA_NL_NUM_CLIENTS != 6);

	if (type >= RDMA_NL_NUM_CLIENTS)
		return false;

	return (op < max_num_ops[type]) ? true : false;
}

static bool is_nl_valid(unsigned int type, unsigned int op)
{
	const struct rdma_nl_cbs *cb_table;

	if (!is_nl_msg_valid(type, op))
		return false;

	cb_table = rdma_nl_types[type].cb_table;
#ifdef CONFIG_MODULES
	if (!cb_table) {
		mutex_unlock(&rdma_nl_mutex);
		request_module("rdma-netlink-subsys-%d", type);
		mutex_lock(&rdma_nl_mutex);
		cb_table = rdma_nl_types[type].cb_table;
	}
#endif

	if (!cb_table || (!cb_table[op].dump && !cb_table[op].doit))
		return false;
	return true;
}

void rdma_nl_register(unsigned int index,
		      const struct rdma_nl_cbs cb_table[])
{
	mutex_lock(&rdma_nl_mutex);
	if (!is_nl_msg_valid(index, 0)) {
		/*
		 * All clients are not interesting in success/failure of
		 * this call. They want to see the print to error log and
		 * continue their initialization. Print warning for them,
		 * because it is programmer's error to be here.
		 */
		mutex_unlock(&rdma_nl_mutex);
		WARN(true,
		     "The not-valid %u index was supplied to RDMA netlink\n",
		     index);
		return;
	}

	if (rdma_nl_types[index].cb_table) {
		mutex_unlock(&rdma_nl_mutex);
		WARN(true,
		     "The %u index is already registered in RDMA netlink\n",
		     index);
		return;
	}

	rdma_nl_types[index].cb_table = cb_table;
	mutex_unlock(&rdma_nl_mutex);
}
EXPORT_SYMBOL(rdma_nl_register);

void rdma_nl_unregister(unsigned int index)
{
	mutex_lock(&rdma_nl_mutex);
	rdma_nl_types[index].cb_table = NULL;
	mutex_unlock(&rdma_nl_mutex);
}
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)
{
	*nlh = nlmsg_put(skb, 0, seq, RDMA_NL_GET_TYPE(client, op), len, flags);
	if (!*nlh)
		return NULL;
	return nlmsg_data(*nlh);
}
EXPORT_SYMBOL(ibnl_put_msg);

int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
		  int len, void *data, int type)
{
	if (nla_put(skb, type, len, data)) {
		nlmsg_cancel(skb, nlh);
		return -EMSGSIZE;
	}
	return 0;
}
EXPORT_SYMBOL(ibnl_put_attr);

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);
	unsigned int op = RDMA_NL_GET_OP(type);
	const struct rdma_nl_cbs *cb_table;

	if (!is_nl_valid(index, op))
		return -EINVAL;

	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;

	/*
	 * LS responses overload the 0x100 (NLM_F_ROOT) flag.  Don't
	 * mistakenly call the .dump() function.
	 */
	if (index == RDMA_NL_LS) {
		if (cb_table[op].doit)
			return cb_table[op].doit(skb, nlh, extack);
		return -EINVAL;
	}
	/* 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,
		};
		if (c.dump)
			return netlink_dump_start(nls, skb, nlh, &c);
		return -EINVAL;
	}

	if (cb_table[op].doit)
		return cb_table[op].doit(skb, nlh, extack);

	return 0;
}

/*
 * 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 err;

	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 0;

		/*
		 * 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;

		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 rdma_nl_rcv(struct sk_buff *skb)
{
	mutex_lock(&rdma_nl_mutex);
	rdma_nl_rcv_skb(skb, &rdma_nl_rcv_msg);
	mutex_unlock(&rdma_nl_mutex);
}

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(rdma_nl_unicast);

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(rdma_nl_unicast_wait);

int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags)
{
	return nlmsg_multicast(nls, skb, 0, group, flags);
}
EXPORT_SYMBOL(rdma_nl_multicast);

int __init rdma_nl_init(void)
{
	struct netlink_kernel_cfg cfg = {
		.input	= rdma_nl_rcv,
	};

	nls = netlink_kernel_create(&init_net, NETLINK_RDMA, &cfg);
	if (!nls)
		return -ENOMEM;

	nls->sk_sndtimeo = 10 * HZ;
	return 0;
}

void rdma_nl_exit(void)
{
	int idx;

	for (idx = 0; idx < RDMA_NL_NUM_CLIENTS; idx++)
		rdma_nl_unregister(idx);

	netlink_kernel_release(nls);
}

MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_RDMA);