summaryrefslogtreecommitdiff
path: root/include/net/request_sock.h
blob: b07b1cd14e9f4d41d2b4fbad6015bbfae4190636 (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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * NET		Generic infrastructure for Network protocols.
 *
 *		Definitions for request_sock
 *
 * Authors:	Arnaldo Carvalho de Melo <acme@conectiva.com.br>
 *
 * 		From code originally in include/net/tcp.h
 */
#ifndef _REQUEST_SOCK_H
#define _REQUEST_SOCK_H

#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/bug.h>
#include <linux/refcount.h>

#include <net/sock.h>
#include <net/rstreason.h>

struct request_sock;
struct sk_buff;
struct dst_entry;
struct proto;

struct request_sock_ops {
	int		family;
	unsigned int	obj_size;
	struct kmem_cache	*slab;
	char		*slab_name;
	int		(*rtx_syn_ack)(const struct sock *sk,
				       struct request_sock *req);
	void		(*send_ack)(const struct sock *sk, struct sk_buff *skb,
				    struct request_sock *req);
	void		(*send_reset)(const struct sock *sk,
				      struct sk_buff *skb,
				      enum sk_rst_reason reason);
	void		(*destructor)(struct request_sock *req);
	void		(*syn_ack_timeout)(const struct request_sock *req);
};

int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);

struct saved_syn {
	u32 mac_hdrlen;
	u32 network_hdrlen;
	u32 tcp_hdrlen;
	u8 data[];
};

/* struct request_sock - mini sock to represent a connection request
 */
struct request_sock {
	struct sock_common		__req_common;
#define rsk_refcnt			__req_common.skc_refcnt
#define rsk_hash			__req_common.skc_hash
#define rsk_listener			__req_common.skc_listener
#define rsk_window_clamp		__req_common.skc_window_clamp
#define rsk_rcv_wnd			__req_common.skc_rcv_wnd

	struct request_sock		*dl_next;
	u16				mss;
	u8				num_retrans; /* number of retransmits */
	u8				syncookie:1; /* True if
						      * 1) tcpopts needs to be encoded in
						      *    TS of SYN+ACK
						      * 2) ACK is validated by BPF kfunc.
						      */
	u8				num_timeout:7; /* number of timeouts */
	u32				ts_recent;
	struct timer_list		rsk_timer;
	const struct request_sock_ops	*rsk_ops;
	struct sock			*sk;
	struct saved_syn		*saved_syn;
	u32				secid;
	u32				peer_secid;
	u32				timeout;
};

static inline struct request_sock *inet_reqsk(const struct sock *sk)
{
	return (struct request_sock *)sk;
}

static inline struct sock *req_to_sk(struct request_sock *req)
{
	return (struct sock *)req;
}

/**
 * skb_steal_sock - steal a socket from an sk_buff
 * @skb: sk_buff to steal the socket from
 * @refcounted: is set to true if the socket is reference-counted
 * @prefetched: is set to true if the socket was assigned from bpf
 */
static inline struct sock *skb_steal_sock(struct sk_buff *skb,
					  bool *refcounted, bool *prefetched)
{
	struct sock *sk = skb->sk;

	if (!sk) {
		*prefetched = false;
		*refcounted = false;
		return NULL;
	}

	*prefetched = skb_sk_is_prefetched(skb);
	if (*prefetched) {
#if IS_ENABLED(CONFIG_SYN_COOKIES)
		if (sk->sk_state == TCP_NEW_SYN_RECV && inet_reqsk(sk)->syncookie) {
			struct request_sock *req = inet_reqsk(sk);

			*refcounted = false;
			sk = req->rsk_listener;
			req->rsk_listener = NULL;
			return sk;
		}
#endif
		*refcounted = sk_is_refcounted(sk);
	} else {
		*refcounted = true;
	}

	skb->destructor = NULL;
	skb->sk = NULL;
	return sk;
}

static inline void __reqsk_free(struct request_sock *req)
{
	req->rsk_ops->destructor(req);
	if (req->rsk_listener)
		sock_put(req->rsk_listener);
	kfree(req->saved_syn);
	kmem_cache_free(req->rsk_ops->slab, req);
}

static inline void reqsk_free(struct request_sock *req)
{
	DEBUG_NET_WARN_ON_ONCE(refcount_read(&req->rsk_refcnt) != 0);
	__reqsk_free(req);
}

static inline void reqsk_put(struct request_sock *req)
{
	if (refcount_dec_and_test(&req->rsk_refcnt))
		__reqsk_free(req);
}

/*
 * For a TCP Fast Open listener -
 *	lock - protects the access to all the reqsk, which is co-owned by
 *		the listener and the child socket.
 *	qlen - pending TFO requests (still in TCP_SYN_RECV).
 *	max_qlen - max TFO reqs allowed before TFO is disabled.
 *
 *	XXX (TFO) - ideally these fields can be made as part of "listen_sock"
 *	structure above. But there is some implementation difficulty due to
 *	listen_sock being part of request_sock_queue hence will be freed when
 *	a listener is stopped. But TFO related fields may continue to be
 *	accessed even after a listener is closed, until its sk_refcnt drops
 *	to 0 implying no more outstanding TFO reqs. One solution is to keep
 *	listen_opt around until	sk_refcnt drops to 0. But there is some other
 *	complexity that needs to be resolved. E.g., a listener can be disabled
 *	temporarily through shutdown()->tcp_disconnect(), and re-enabled later.
 */
struct fastopen_queue {
	struct request_sock	*rskq_rst_head; /* Keep track of past TFO */
	struct request_sock	*rskq_rst_tail; /* requests that caused RST.
						 * This is part of the defense
						 * against spoofing attack.
						 */
	spinlock_t	lock;
	int		qlen;		/* # of pending (TCP_SYN_RECV) reqs */
	int		max_qlen;	/* != 0 iff TFO is currently enabled */

	struct tcp_fastopen_context __rcu *ctx; /* cipher context for cookie */
};

/** struct request_sock_queue - queue of request_socks
 *
 * @rskq_accept_head - FIFO head of established children
 * @rskq_accept_tail - FIFO tail of established children
 * @rskq_defer_accept - User waits for some data after accept()
 *
 */
struct request_sock_queue {
	spinlock_t		rskq_lock;
	u8			rskq_defer_accept;

	u32			synflood_warned;
	atomic_t		qlen;
	atomic_t		young;

	struct request_sock	*rskq_accept_head;
	struct request_sock	*rskq_accept_tail;
	struct fastopen_queue	fastopenq;  /* Check max_qlen != 0 to determine
					     * if TFO is enabled.
					     */
};

void reqsk_queue_alloc(struct request_sock_queue *queue);

void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
			   bool reset);

static inline bool reqsk_queue_empty(const struct request_sock_queue *queue)
{
	return READ_ONCE(queue->rskq_accept_head) == NULL;
}

static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue,
						      struct sock *parent)
{
	struct request_sock *req;

	spin_lock_bh(&queue->rskq_lock);
	req = queue->rskq_accept_head;
	if (req) {
		sk_acceptq_removed(parent);
		WRITE_ONCE(queue->rskq_accept_head, req->dl_next);
		if (queue->rskq_accept_head == NULL)
			queue->rskq_accept_tail = NULL;
	}
	spin_unlock_bh(&queue->rskq_lock);
	return req;
}

static inline void reqsk_queue_removed(struct request_sock_queue *queue,
				       const struct request_sock *req)
{
	if (req->num_timeout == 0)
		atomic_dec(&queue->young);
	atomic_dec(&queue->qlen);
}

static inline void reqsk_queue_added(struct request_sock_queue *queue)
{
	atomic_inc(&queue->young);
	atomic_inc(&queue->qlen);
}

static inline int reqsk_queue_len(const struct request_sock_queue *queue)
{
	return atomic_read(&queue->qlen);
}

static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
{
	return atomic_read(&queue->young);
}

/* RFC 7323 2.3 Using the Window Scale Option
 *  The window field (SEG.WND) of every outgoing segment, with the
 *  exception of <SYN> segments, MUST be right-shifted by
 *  Rcv.Wind.Shift bits.
 *
 * This means the SEG.WND carried in SYNACK can not exceed 65535.
 * We use this property to harden TCP stack while in NEW_SYN_RECV state.
 */
static inline u32 tcp_synack_window(const struct request_sock *req)
{
	return min(req->rsk_rcv_wnd, 65535U);
}
#endif /* _REQUEST_SOCK_H */