summaryrefslogtreecommitdiff
path: root/include/net/inet_sock.h
blob: b487bc1b99ab749d2d0501c7f6041e630b738673 (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
/*
 * 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>
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */
#ifndef _INET_SOCK_H
#define _INET_SOCK_H


#include <linux/kmemcheck.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>

/** struct ip_options - IP Options
 *
 * @faddr - Saved first hop address
 * @is_data - Options in __data, rather than skb
 * @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;
	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[0];
};

#define optlength(opt) (sizeof(struct ip_options) + opt->optlen)

struct inet_request_sock {
	struct request_sock	req;
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	u16			inet6_rsk_offset;
#endif
	__be16			loc_port;
	__be32			loc_addr;
	__be32			rmt_addr;
	__be16			rmt_port;
	kmemcheck_bitfield_begin(flags);
	u16			snd_wscale : 4,
				rcv_wscale : 4,
				tstamp_ok  : 1,
				sack_ok	   : 1,
				wscale_ok  : 1,
				ecn_ok	   : 1,
				acked	   : 1,
				no_srccheck: 1;
	kmemcheck_bitfield_end(flags);
	struct ip_options	*opt;
};

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

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
 * @rxhash - flow hash received from netif layer
 * @tos - TOS
 * @mc_ttl - Multicasting TTL
 * @is_icsk - is this an inet_connection_sock?
 * @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 defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
	struct ipv6_pinfo	*pinet6;
#endif
	/* Socket demultiplex comparisons on incoming packets. */
	__be32			inet_daddr;
	__be32			inet_rcv_saddr;
	__be16			inet_dport;
	__u16			inet_num;
	__be32			inet_saddr;
	__s16			uc_ttl;
	__u16			cmsg_flags;
	__be16			inet_sport;
	__u16			inet_id;
#ifdef CONFIG_RPS
	__u32			rxhash;
#endif

	struct ip_options	*opt;
	__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;
	int			mc_index;
	__be32			mc_addr;
	struct ip_mc_socklist	*mc_list;
	struct {
		unsigned int		flags;
		unsigned int		fragsize;
		struct ip_options	*opt;
		struct dst_entry	*dst;
		int			length; /* Total length of all frames */
		__be32			addr;
		struct flowi		fl;
	} cork;
};

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

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);
}
#if !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE))
static inline void inet_sk_copy_descendant(struct sock *sk_to,
					   const struct sock *sk_from)
{
	__inet_sk_copy_descendant(sk_to, sk_from, sizeof(struct inet_sock));
}
#endif

extern int inet_sk_rebuild_header(struct sock *sk);

extern u32 inet_ehash_secret;
extern void build_ehash_secret(void);

static inline unsigned int inet_ehashfn(struct net *net,
					const __be32 laddr, const __u16 lport,
					const __be32 faddr, const __be16 fport)
{
	return jhash_3words((__force __u32) laddr,
			    (__force __u32) faddr,
			    ((__u32) lport) << 16 | (__force __u32)fport,
			    inet_ehash_secret + net_hash_mix(net));
}

static inline int inet_sk_ehashfn(const struct sock *sk)
{
	const struct inet_sock *inet = inet_sk(sk);
	const __be32 laddr = inet->inet_rcv_saddr;
	const __u16 lport = inet->inet_num;
	const __be32 faddr = inet->inet_daddr;
	const __be16 fport = inet->inet_dport;
	struct net *net = sock_net(sk);

	return inet_ehashfn(net, laddr, lport, faddr, fport);
}

static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops)
{
	struct request_sock *req = reqsk_alloc(ops);
	struct inet_request_sock *ireq = inet_rsk(req);

	if (req != NULL) {
		kmemcheck_annotate_bitfield(ireq, flags);
		ireq->opt = NULL;
	}

	return req;
}

static inline __u8 inet_sk_flowi_flags(const struct sock *sk)
{
	return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0;
}

static inline void inet_rps_record_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
	struct rps_sock_flow_table *sock_flow_table;

	rcu_read_lock();
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	rps_record_sock_flow(sock_flow_table, inet_sk(sk)->rxhash);
	rcu_read_unlock();
#endif
}

static inline void inet_rps_reset_flow(const struct sock *sk)
{
#ifdef CONFIG_RPS
	struct rps_sock_flow_table *sock_flow_table;

	rcu_read_lock();
	sock_flow_table = rcu_dereference(rps_sock_flow_table);
	rps_reset_sock_flow(sock_flow_table, inet_sk(sk)->rxhash);
	rcu_read_unlock();
#endif
}

static inline void inet_rps_save_rxhash(const struct sock *sk, u32 rxhash)
{
#ifdef CONFIG_RPS
	if (unlikely(inet_sk(sk)->rxhash != rxhash)) {
		inet_rps_reset_flow(sk);
		inet_sk(sk)->rxhash = rxhash;
	}
#endif
}
#endif	/* _INET_SOCK_H */