summaryrefslogtreecommitdiff
path: root/net/mptcp/mptcp_diag.c
blob: 7f9a7178043739a4d2aa1832810a3823483616b8 (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
// SPDX-License-Identifier: GPL-2.0
/* MPTCP socket monitoring support
 *
 * Copyright (c) 2020 Red Hat
 *
 * Author: Paolo Abeni <pabeni@redhat.com>
 */

#include <linux/kernel.h>
#include <linux/net.h>
#include <linux/inet_diag.h>
#include <net/netlink.h>
#include <uapi/linux/mptcp.h>
#include "protocol.h"

static int sk_diag_dump(struct sock *sk, struct sk_buff *skb,
			struct netlink_callback *cb,
			const struct inet_diag_req_v2 *req,
			struct nlattr *bc, bool net_admin)
{
	if (!inet_diag_bc_sk(bc, sk))
		return 0;

	return inet_sk_diag_fill(sk, inet_csk(sk), skb, cb, req, NLM_F_MULTI,
				 net_admin);
}

static int mptcp_diag_dump_one(struct netlink_callback *cb,
			       const struct inet_diag_req_v2 *req)
{
	struct sk_buff *in_skb = cb->skb;
	struct mptcp_sock *msk = NULL;
	struct sk_buff *rep;
	int err = -ENOENT;
	struct net *net;
	struct sock *sk;

	net = sock_net(in_skb->sk);
	msk = mptcp_token_get_sock(net, req->id.idiag_cookie[0]);
	if (!msk)
		goto out_nosk;

	err = -ENOMEM;
	sk = (struct sock *)msk;
	rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) +
			inet_diag_msg_attrs_size() +
			nla_total_size(sizeof(struct mptcp_info)) +
			nla_total_size(sizeof(struct inet_diag_meminfo)) + 64,
			GFP_KERNEL);
	if (!rep)
		goto out;

	err = inet_sk_diag_fill(sk, inet_csk(sk), rep, cb, req, 0,
				netlink_net_capable(in_skb, CAP_NET_ADMIN));
	if (err < 0) {
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(rep);
		goto out;
	}
	err = nlmsg_unicast(net->diag_nlsk, rep, NETLINK_CB(in_skb).portid);

out:
	sock_put(sk);

out_nosk:
	return err;
}

struct mptcp_diag_ctx {
	long s_slot;
	long s_num;
	unsigned int l_slot;
	unsigned int l_num;
};

static void mptcp_diag_dump_listeners(struct sk_buff *skb, struct netlink_callback *cb,
				      const struct inet_diag_req_v2 *r,
				      bool net_admin)
{
	struct inet_diag_dump_data *cb_data = cb->data;
	struct mptcp_diag_ctx *diag_ctx = (void *)cb->ctx;
	struct nlattr *bc = cb_data->inet_diag_nla_bc;
	struct net *net = sock_net(skb->sk);
	int i;

	for (i = diag_ctx->l_slot; i <= tcp_hashinfo.lhash2_mask; i++) {
		struct inet_listen_hashbucket *ilb;
		struct hlist_nulls_node *node;
		struct sock *sk;
		int num = 0;

		ilb = &tcp_hashinfo.lhash2[i];

		rcu_read_lock();
		spin_lock(&ilb->lock);
		sk_nulls_for_each(sk, node, &ilb->nulls_head) {
			const struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(sk);
			struct inet_sock *inet = inet_sk(sk);
			int ret;

			if (num < diag_ctx->l_num)
				goto next_listen;

			if (!ctx || strcmp(inet_csk(sk)->icsk_ulp_ops->name, "mptcp"))
				goto next_listen;

			sk = ctx->conn;
			if (!sk || !net_eq(sock_net(sk), net))
				goto next_listen;

			if (r->sdiag_family != AF_UNSPEC &&
			    sk->sk_family != r->sdiag_family)
				goto next_listen;

			if (r->id.idiag_sport != inet->inet_sport &&
			    r->id.idiag_sport)
				goto next_listen;

			if (!refcount_inc_not_zero(&sk->sk_refcnt))
				goto next_listen;

			ret = sk_diag_dump(sk, skb, cb, r, bc, net_admin);

			sock_put(sk);

			if (ret < 0) {
				spin_unlock(&ilb->lock);
				rcu_read_unlock();
				diag_ctx->l_slot = i;
				diag_ctx->l_num = num;
				return;
			}
			diag_ctx->l_num = num + 1;
			num = 0;
next_listen:
			++num;
		}
		spin_unlock(&ilb->lock);
		rcu_read_unlock();

		cond_resched();
		diag_ctx->l_num = 0;
	}

	diag_ctx->l_num = 0;
	diag_ctx->l_slot = i;
}

static void mptcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
			    const struct inet_diag_req_v2 *r)
{
	bool net_admin = netlink_net_capable(cb->skb, CAP_NET_ADMIN);
	struct mptcp_diag_ctx *diag_ctx = (void *)cb->ctx;
	struct net *net = sock_net(skb->sk);
	struct inet_diag_dump_data *cb_data;
	struct mptcp_sock *msk;
	struct nlattr *bc;

	BUILD_BUG_ON(sizeof(cb->ctx) < sizeof(*diag_ctx));

	cb_data = cb->data;
	bc = cb_data->inet_diag_nla_bc;

	while ((msk = mptcp_token_iter_next(net, &diag_ctx->s_slot,
					    &diag_ctx->s_num)) != NULL) {
		struct inet_sock *inet = (struct inet_sock *)msk;
		struct sock *sk = (struct sock *)msk;
		int ret = 0;

		if (!(r->idiag_states & (1 << sk->sk_state)))
			goto next;
		if (r->sdiag_family != AF_UNSPEC &&
		    sk->sk_family != r->sdiag_family)
			goto next;
		if (r->id.idiag_sport != inet->inet_sport &&
		    r->id.idiag_sport)
			goto next;
		if (r->id.idiag_dport != inet->inet_dport &&
		    r->id.idiag_dport)
			goto next;

		ret = sk_diag_dump(sk, skb, cb, r, bc, net_admin);
next:
		sock_put(sk);
		if (ret < 0) {
			/* will retry on the same position */
			diag_ctx->s_num--;
			break;
		}
		cond_resched();
	}

	if ((r->idiag_states & TCPF_LISTEN) && r->id.idiag_dport == 0)
		mptcp_diag_dump_listeners(skb, cb, r, net_admin);
}

static void mptcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
				void *_info)
{
	struct mptcp_sock *msk = mptcp_sk(sk);
	struct mptcp_info *info = _info;

	r->idiag_rqueue = sk_rmem_alloc_get(sk);
	r->idiag_wqueue = sk_wmem_alloc_get(sk);

	if (inet_sk_state_load(sk) == TCP_LISTEN) {
		struct sock *lsk = READ_ONCE(msk->first);

		if (lsk) {
			/* override with settings from tcp listener,
			 * so Send-Q will show accept queue.
			 */
			r->idiag_rqueue = READ_ONCE(lsk->sk_ack_backlog);
			r->idiag_wqueue = READ_ONCE(lsk->sk_max_ack_backlog);
		}
	}

	if (!info)
		return;

	mptcp_diag_fill_info(msk, info);
}

static const struct inet_diag_handler mptcp_diag_handler = {
	.dump		 = mptcp_diag_dump,
	.dump_one	 = mptcp_diag_dump_one,
	.idiag_get_info  = mptcp_diag_get_info,
	.idiag_type	 = IPPROTO_MPTCP,
	.idiag_info_size = sizeof(struct mptcp_info),
};

static int __init mptcp_diag_init(void)
{
	return inet_diag_register(&mptcp_diag_handler);
}

static void __exit mptcp_diag_exit(void)
{
	inet_diag_unregister(&mptcp_diag_handler);
}

module_init(mptcp_diag_init);
module_exit(mptcp_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-262 /* AF_INET - IPPROTO_MPTCP */);