summaryrefslogtreecommitdiffstats
path: root/include/net/inet_sock.h
blob: f0faf9d0e7fb7cc3b53cc2d58983f6fbb3446a61 (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
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		Definitions for inet_sock
 *
 * Authors:	Many, reorganised here by
 * 		Arnaldo Carvalho de Melo <acme@mandriva.com>
 */
#ifndef _INET_SOCK_H
#define _INET_SOCK_H

#include <linux/bitops.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/jhash.h>
#include <linux/netdevice.h>

#include <net/flow.h>
#include <net/sock.h>
#include <net/request_sock.h>
#include <net/netns/hash.h>
#include <net/tcp_states.h>
#include <net/l3mdev.h>

/** struct ip_options - IP Options
 *
 * @faddr - Saved first hop address
 * @nexthop - Saved nexthop address in LSRR and SSRR
 * @is_strictroute - Strict source route
 * @srr_is_hit - Packet destination addr was our one
 * @is_changed - IP checksum more not valid
 * @rr_needaddr - Need to record addr of outgoing dev
 * @ts_needtime - Need to record timestamp
 * @ts_needaddr - Need to record addr of outgoing dev
 */
struct ip_options {
	__be32		faddr;
	__be32		nexthop;
	unsigned char	optlen;
	unsigned char	srr;
	unsigned char	rr;
	unsigned char	ts;
	unsigned char	is_strictroute:1,
			srr_is_hit:1,
			is_changed:1,
			rr_needaddr:1,
			ts_needtime:1,
			ts_needaddr:1;
	unsigned char	router_alert;
	unsigned char	cipso;
	unsigned char	__pad2;
	unsigned char	__data[];
};

struct ip_options_rcu {
	struct rcu_head rcu;
	struct ip_options opt;
};

struct ip_options_data {
	struct ip_options_rcu	opt;
	char			data[40];
};

struct inet_request_sock {
	struct request_sock	req;
#define ir_loc_addr		req.__req_common.skc_rcv_saddr
#define ir_rmt_addr		req.__req_common.skc_daddr
#define ir_num			req.__req_common.skc_num
#define ir_rmt_port		req.__req_common.skc_dport
#define ir_v6_rmt_addr		req.__req_common.skc_v6_daddr
#define ir_v6_loc_addr		req.__req_common.skc_v6_rcv_saddr
#define ir_iif			req.__req_common.skc_bound_dev_if
#define ir_cookie		req.__req_common.skc_cookie
#define ireq_net		req.__req_common.skc_net
#define ireq_state		req.__req_common.skc_state
#define ireq_family		req.__req_common.skc_family

	u16			snd_wscale : 4,
				rcv_wscale : 4,
				tstamp_ok  : 1,
				sack_ok	   : 1,
				wscale_ok  : 1,
				ecn_ok	   : 1,
				acked	   : 1,
				no_srccheck: 1,
				smc_ok	   : 1;
	u32                     ir_mark;
	union {
		struct ip_options_rcu __rcu	*ireq_opt;
#if IS_ENABLED(CONFIG_IPV6)
		struct {
			struct ipv6_txoptions	*ipv6_opt;
			struct sk_buff		*pktopts;
		};
#endif
	};
};

static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
{
	return (struct inet_request_sock *)sk;
}

static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
{
	if (!sk->sk_mark &&
	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept))
		return skb->mark;

	return sk->sk_mark;
}

static inline int inet_request_bound_dev_if(const struct sock *sk,
					    struct sk_buff *skb)
{
	int bound_dev_if = READ_ONCE(sk->sk_bound_dev_if);
#ifdef CONFIG_NET_L3_MASTER_DEV
	struct net *net = sock_net(sk);

	if (!bound_dev_if && READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept))
		return l3mdev_master_ifindex_by_index(net, skb->skb_iif);
#endif

	return bound_dev_if;
}

static inline int inet_sk_bound_l3mdev(const struct sock *sk)
{
#ifdef CONFIG_NET_L3_MASTER_DEV
	struct net *net = sock_net(sk);

	if (!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept))
		return l3mdev_master_ifindex_by_index(net,
						      sk->sk_bound_dev_if);
#endif

	return 0;
}

static inline bool inet_bound_dev_eq(bool l3mdev_accept, int bound_dev_if,
				     int dif, int sdif)
{
	if (!bound_dev_if)
		return !sdif || l3mdev_accept;
	return bound_dev_if == dif || bound_dev_if == sdif;
}

static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
					int dif, int sdif)
{
#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
	return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept),
				 bound_dev_if, dif, sdif);
#else
	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
#endif
}

struct inet_cork {
	unsigned int		flags;
	__be32			addr;
	struct ip_options	*opt;
	unsigned int		fragsize;
	int			length; /* Total length of all frames */
	struct dst_entry	*dst;
	u8			tx_flags;
	__u8			ttl;
	__s16			tos;
	char			priority;
	__u16			gso_size;
	u64			transmit_time;
	u32			mark;
};

struct inet_cork_full {
	struct inet_cork	base;
	struct flowi		fl;
};

struct ip_mc_socklist;
struct ipv6_pinfo;
struct rtable;

/** struct inet_sock - representation of INET sockets
 *
 * @sk - ancestor class
 * @pinet6 - pointer to IPv6 control block
 * @inet_daddr - Foreign IPv4 addr
 * @inet_rcv_saddr - Bound local IPv4 addr
 * @inet_dport - Destination port
 * @inet_num - Local port
 * @inet_saddr - Sending source
 * @uc_ttl - Unicast TTL
 * @inet_sport - Source port
 * @inet_id - ID counter for DF pkts
 * @tos - TOS
 * @mc_ttl - Multicasting TTL
 * @is_icsk - is this an inet_connection_sock?
 * @uc_index - Unicast outgoing device index
 * @mc_index - Multicast device index
 * @mc_list - Group array
 * @cork - info to build ip hdr on each ip frag while socket is corked
 */
struct inet_sock {
	/* sk and pinet6 has to be the first two members of inet_sock */
	struct sock		sk;
#if IS_ENABLED(CONFIG_IPV6)
	struct ipv6_pinfo	*pinet6;
#endif
	/* Socket demultiplex comparisons on incoming packets. */
#define inet_daddr		sk.__sk_common.skc_daddr
#define inet_rcv_saddr		sk.__sk_common.skc_rcv_saddr
#define inet_dport		sk.__sk_common.skc_dport
#define inet_num		sk.__sk_common.skc_num

	__be32			inet_saddr;
	__s16			uc_ttl;
	__u16			cmsg_flags;
	__be16			inet_sport;
	__u16			inet_id;

	struct ip_options_rcu __rcu	*inet_opt;
	int			rx_dst_ifindex;
	__u8			tos;
	__u8			min_ttl;
	__u8			mc_ttl;
	__u8			pmtudisc;
	__u8			recverr:1,
				is_icsk:1,
				freebind:1,
				hdrincl:1,
				mc_loop:1,
				transparent:1,
				mc_all:1,
				nodefrag:1;
	__u8			bind_address_no_port:1,
				recverr_rfc4884:1,
				defer_connect:1; /* Indicates that fastopen_connect is set
						  * and cookie exists so we defer connect
						  * until first data frame is written
						  */
	__u8			rcv_tos;
	__u8			convert_csum;
	int			uc_index;
	int			mc_index;
	__be32			mc_addr;
	struct ip_mc_socklist __rcu	*mc_list;
	struct inet_cork_full	cork;
};

#define IPCORK_OPT	1	/* ip-options has been held in ipcork.opt */
#define IPCORK_ALLFRAG	2	/* always fragment (for ipv6 for now) */

/* cmsg flags for inet */
#define IP_CMSG_PKTINFO		BIT(0)
#define IP_CMSG_TTL		BIT(1)
#define IP_CMSG_TOS		BIT(2)
#define IP_CMSG_RECVOPTS	BIT(3)
#define IP_CMSG_RETOPTS		BIT(4)
#define IP_CMSG_PASSSEC		BIT(5)
#define IP_CMSG_ORIGDSTADDR	BIT(6)
#define IP_CMSG_CHECKSUM	BIT(7)
#define IP_CMSG_RECVFRAGSIZE	BIT(8)

/**
 * sk_to_full_sk - Access to a full socket
 * @sk: pointer to a socket
 *
 * SYNACK messages might be attached to request sockets.
 * Some places want to reach the listener in this case.
 */
static inline struct sock *sk_to_full_sk(struct sock *sk)
{
#ifdef CONFIG_INET
	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
		sk = inet_reqsk(sk)->rsk_listener;
#endif
	return sk;
}

/* sk_to_full_sk() variant with a const argument */
static inline const struct sock *sk_const_to_full_sk(const struct sock *sk)
{
#ifdef CONFIG_INET
	if (sk && sk->sk_state == TCP_NEW_SYN_RECV)
		sk = ((const struct request_sock *)sk)->rsk_listener;
#endif
	return sk;
}

static inline struct sock *skb_to_full_sk(const struct sk_buff *skb)
{
	return sk_to_full_sk(skb->sk);
}

static inline struct inet_sock *inet_sk(const struct sock *sk)
{
	return (struct inet_sock *)sk;
}

static inline void __inet_sk_copy_descendant(struct sock *sk_to,
					     const struct sock *sk_from,
					     const int ancestor_size)
{
	memcpy(inet_sk(sk_to) + 1, inet_sk(sk_from) + 1,
	       sk_from->sk_prot->obj_size - ancestor_size);
}

int inet_sk_rebuild_header(struct sock *sk);

/**
 * inet_sk_state_load - read sk->sk_state for lockless contexts
 * @sk: socket pointer
 *
 * Paired with inet_sk_state_store(). Used in places we don't hold socket lock:
 * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ...
 */
static inline int inet_sk_state_load(const struct sock *sk)
{
	/* state change might impact lockless readers. */
	return smp_load_acquire(&sk->sk_state);
}

/**
 * inet_sk_state_store - update sk->sk_state
 * @sk: socket pointer
 * @newstate: new state
 *
 * Paired with inet_sk_state_load(). Should be used in contexts where
 * state change might impact lockless readers.
 */
void inet_sk_state_store(struct sock *sk, int newstate);

void inet_sk_set_state(struct sock *sk, int state);

static inline unsigned int __inet_ehashfn(const __be32 laddr,
					  const __u16 lport,
					  const __be32 faddr,
					  const __be16 fport,
					  u32 initval)
{
	return jhash_3words((__force __u32) laddr,
			    (__force __u32) faddr,
			    ((__u32) lport) << 16 | (__force __u32)fport,
			    initval);
}

struct request_sock *inet_reqsk_alloc(const struct request_sock_ops *ops,
				      struct sock *sk_listener,
				      bool attach_listener);

static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
{
	__u8 flags = 0;

	if (inet_sk(sk)->transparent || inet_sk(sk)->hdrincl)
		flags |= FLOWI_FLAG_ANYSRC;
	return flags;
}

static inline void inet_inc_convert_csum(struct sock *sk)
{
	inet_sk(sk)->convert_csum++;
}

static inline void inet_dec_convert_csum(struct sock *sk)
{
	if (inet_sk(sk)->convert_csum > 0)
		inet_sk(sk)->convert_csum--;
}

static inline bool inet_get_convert_csum(struct sock *sk)
{
	return !!inet_sk(sk)->convert_csum;
}


static inline bool inet_can_nonlocal_bind(struct net *net,
					  struct inet_sock *inet)
{
	return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) ||
		inet->freebind || inet->transparent;
}

#endif	/* _INET_SOCK_H */