sock.h 38 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1
2
3
4
5
6
7
8
9
/*
 * 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 the AF_INET socket handler.
 *
 * Version:	@(#)sock.h	1.0.4	05/13/93
 *
10
 * Authors:	Ross Biro
Linus Torvalds's avatar
Linus Torvalds committed
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
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Corey Minyard <wf-rch!minyard@relay.EU.net>
 *		Florian La Roche <flla@stud.uni-sb.de>
 *
 * Fixes:
 *		Alan Cox	:	Volatiles in skbuff pointers. See
 *					skbuff comments. May be overdone,
 *					better to prove they can be removed
 *					than the reverse.
 *		Alan Cox	:	Added a zapped field for tcp to note
 *					a socket is reset and must stay shut up
 *		Alan Cox	:	New fields for options
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Eliminate low level recv/recvfrom
 *		David S. Miller	:	New socket lookup architecture.
 *              Steve Whitehouse:       Default routines for sock_ops
 *              Arnaldo C. Melo :	removed net_pinfo, tp_pinfo and made
 *              			protinfo be just a void pointer, as the
 *              			protocol specific parts were moved to
 *              			respective headers and ipv4/v6, etc now
 *              			use private slabcaches for its socks
 *              Pedro Hortas	:	New flags field for socket options
 *
 *
 *		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 _SOCK_H
#define _SOCK_H

43
#include <linux/kernel.h>
Linus Torvalds's avatar
Linus Torvalds committed
44
45
46
47
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/module.h>
48
#include <linux/lockdep.h>
Linus Torvalds's avatar
Linus Torvalds committed
49
50
#include <linux/netdevice.h>
#include <linux/skbuff.h>	/* struct sk_buff */
Al Viro's avatar
Al Viro committed
51
#include <linux/mm.h>
Linus Torvalds's avatar
Linus Torvalds committed
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
#include <linux/security.h>

#include <linux/filter.h>

#include <asm/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>

/*
 * This structure really needs to be cleaned up.
 * Most of it is for TCP, and not used by any of
 * the other protocols.
 */

/* Define this to get the SOCK_DBG debugging facility. */
#define SOCK_DEBUGGING
#ifdef SOCK_DEBUGGING
#define SOCK_DEBUG(sk, msg...) do { if ((sk) && sock_flag((sk), SOCK_DBG)) \
					printk(KERN_DEBUG msg); } while (0)
#else
72
73
74
75
76
/* Validate arguments and do nothing */
static void inline int __attribute__ ((format (printf, 2, 3)))
SOCK_DEBUG(struct sock *sk, const char *msg, ...)
{
}
Linus Torvalds's avatar
Linus Torvalds committed
77
78
79
80
81
82
83
84
#endif

/* This is the per-socket lock.  The spinlock provides a synchronization
 * between user contexts and software interrupt processing, whereas the
 * mini-semaphore synchronizes multiple users amongst themselves.
 */
typedef struct {
	spinlock_t		slock;
85
	int			owned;
Linus Torvalds's avatar
Linus Torvalds committed
86
	wait_queue_head_t	wq;
87
88
89
90
91
92
93
94
95
	/*
	 * We express the mutex-alike socket_lock semantics
	 * to the lock validator by explicitly managing
	 * the slock as a lock variant (in addition to
	 * the slock itself):
	 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
	struct lockdep_map dep_map;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
96
97
98
} socket_lock_t;

struct sock;
99
struct proto;
100
struct net;
Linus Torvalds's avatar
Linus Torvalds committed
101
102

/**
103
104
105
106
107
108
109
110
 *	struct sock_common - minimal network layer representation of sockets
 *	@skc_family: network address family
 *	@skc_state: Connection state
 *	@skc_reuse: %SO_REUSEADDR setting
 *	@skc_bound_dev_if: bound device index if != 0
 *	@skc_node: main hash linkage for various protocol lookup tables
 *	@skc_bind_node: bind hash linkage for various protocol lookup tables
 *	@skc_refcnt: reference count
111
 *	@skc_hash: hash value used with various protocol lookup tables
112
 *	@skc_prot: protocol handlers inside a network family
113
 *	@skc_net: reference to the network namespace of this socket
114
115
 *
 *	This is the minimal network layer representation of sockets, the header
116
117
 *	for struct sock and struct inet_timewait_sock.
 */
Linus Torvalds's avatar
Linus Torvalds committed
118
119
120
121
122
123
124
125
struct sock_common {
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
	struct hlist_node	skc_node;
	struct hlist_node	skc_bind_node;
	atomic_t		skc_refcnt;
126
	unsigned int		skc_hash;
127
	struct proto		*skc_prot;
128
#ifdef CONFIG_NET_NS
129
	struct net	 	*skc_net;
130
#endif
Linus Torvalds's avatar
Linus Torvalds committed
131
132
133
134
};

/**
  *	struct sock - network layer representation of sockets
135
  *	@__sk_common: shared layout with inet_timewait_sock
136
137
138
139
140
141
142
143
144
145
146
147
  *	@sk_shutdown: mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
  *	@sk_userlocks: %SO_SNDBUF and %SO_RCVBUF settings
  *	@sk_lock:	synchronizer
  *	@sk_rcvbuf: size of receive buffer in bytes
  *	@sk_sleep: sock wait queue
  *	@sk_dst_cache: destination cache
  *	@sk_dst_lock: destination cache lock
  *	@sk_policy: flow policy
  *	@sk_rmem_alloc: receive queue bytes committed
  *	@sk_receive_queue: incoming packets
  *	@sk_wmem_alloc: transmit queue bytes committed
  *	@sk_write_queue: Packet sending queue
148
  *	@sk_async_wait_queue: DMA copied packets
149
150
151
152
153
  *	@sk_omem_alloc: "o" is "option" or "other"
  *	@sk_wmem_queued: persistent queue size
  *	@sk_forward_alloc: space allocated forward
  *	@sk_allocation: allocation mode
  *	@sk_sndbuf: size of send buffer in bytes
Wang Chen's avatar
Wang Chen committed
154
155
  *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		   %SO_OOBINLINE settings
156
157
  *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
  *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
158
  *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
159
  *	@sk_gso_max_size: Maximum GSO segment size to build
160
161
162
163
  *	@sk_lingertime: %SO_LINGER l_linger setting
  *	@sk_backlog: always used with the per-socket spinlock held
  *	@sk_callback_lock: used with the callbacks in the end of this struct
  *	@sk_error_queue: rarely used
Wang Chen's avatar
Wang Chen committed
164
165
  *	@sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
  *			  IPV6_ADDRFORM for instance)
166
  *	@sk_err: last error
Wang Chen's avatar
Wang Chen committed
167
168
  *	@sk_err_soft: errors that don't cause failure but are the cause of a
  *		      persistent failure not just 'timed out'
Eric Dumazet's avatar
Eric Dumazet committed
169
  *	@sk_drops: raw/udp drops counter
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
  *	@sk_ack_backlog: current listen backlog
  *	@sk_max_ack_backlog: listen backlog set in listen()
  *	@sk_priority: %SO_PRIORITY setting
  *	@sk_type: socket type (%SOCK_STREAM, etc)
  *	@sk_protocol: which protocol this socket belongs in this network family
  *	@sk_peercred: %SO_PEERCRED setting
  *	@sk_rcvlowat: %SO_RCVLOWAT setting
  *	@sk_rcvtimeo: %SO_RCVTIMEO setting
  *	@sk_sndtimeo: %SO_SNDTIMEO setting
  *	@sk_filter: socket filtering instructions
  *	@sk_protinfo: private area, net family specific, when not using slab
  *	@sk_timer: sock cleanup timer
  *	@sk_stamp: time stamp of last packet received
  *	@sk_socket: Identd and reporting IO signals
  *	@sk_user_data: RPC layer private data
  *	@sk_sndmsg_page: cached page for sendmsg
  *	@sk_sndmsg_off: cached offset for sendmsg
  *	@sk_send_head: front of stuff to transmit
188
  *	@sk_security: used by security modules
189
  *	@sk_mark: generic packet mark
190
191
192
193
194
195
196
  *	@sk_write_pending: a write to stream socket waits to start
  *	@sk_state_change: callback to indicate change in the state of the sock
  *	@sk_data_ready: callback to indicate there is data to be processed
  *	@sk_write_space: callback to indicate there is bf sending space available
  *	@sk_error_report: callback to indicate errors (e.g. %MSG_ERRQUEUE)
  *	@sk_backlog_rcv: callback to process the backlog
  *	@sk_destruct: called at sock freeing time, i.e. when all refcnt == 0
Linus Torvalds's avatar
Linus Torvalds committed
197
198
199
 */
struct sock {
	/*
200
	 * Now struct inet_timewait_sock also uses sock_common, so please just
Linus Torvalds's avatar
Linus Torvalds committed
201
202
203
204
205
206
207
208
209
210
	 * don't add nothing before this first member (__sk_common) --acme
	 */
	struct sock_common	__sk_common;
#define sk_family		__sk_common.skc_family
#define sk_state		__sk_common.skc_state
#define sk_reuse		__sk_common.skc_reuse
#define sk_bound_dev_if		__sk_common.skc_bound_dev_if
#define sk_node			__sk_common.skc_node
#define sk_bind_node		__sk_common.skc_bind_node
#define sk_refcnt		__sk_common.skc_refcnt
211
#define sk_hash			__sk_common.skc_hash
212
#define sk_prot			__sk_common.skc_prot
213
#define sk_net			__sk_common.skc_net
Linus Torvalds's avatar
Linus Torvalds committed
214
215
216
217
218
219
220
	unsigned char		sk_shutdown : 2,
				sk_no_check : 2,
				sk_userlocks : 4;
	unsigned char		sk_protocol;
	unsigned short		sk_type;
	int			sk_rcvbuf;
	socket_lock_t		sk_lock;
221
222
223
224
225
226
227
228
229
	/*
	 * The backlog queue is special, it is always used with
	 * the per-socket spinlock held and requires low latency
	 * access. Therefore we special case it's implementation.
	 */
	struct {
		struct sk_buff *head;
		struct sk_buff *tail;
	} sk_backlog;
Linus Torvalds's avatar
Linus Torvalds committed
230
231
232
233
234
235
236
	wait_queue_head_t	*sk_sleep;
	struct dst_entry	*sk_dst_cache;
	struct xfrm_policy	*sk_policy[2];
	rwlock_t		sk_dst_lock;
	atomic_t		sk_rmem_alloc;
	atomic_t		sk_wmem_alloc;
	atomic_t		sk_omem_alloc;
237
	int			sk_sndbuf;
Linus Torvalds's avatar
Linus Torvalds committed
238
239
	struct sk_buff_head	sk_receive_queue;
	struct sk_buff_head	sk_write_queue;
240
	struct sk_buff_head	sk_async_wait_queue;
Linus Torvalds's avatar
Linus Torvalds committed
241
242
	int			sk_wmem_queued;
	int			sk_forward_alloc;
Al Viro's avatar
Al Viro committed
243
	gfp_t			sk_allocation;
Linus Torvalds's avatar
Linus Torvalds committed
244
	int			sk_route_caps;
245
	int			sk_gso_type;
246
	unsigned int		sk_gso_max_size;
247
	int			sk_rcvlowat;
Linus Torvalds's avatar
Linus Torvalds committed
248
249
250
	unsigned long 		sk_flags;
	unsigned long	        sk_lingertime;
	struct sk_buff_head	sk_error_queue;
251
	struct proto		*sk_prot_creator;
Linus Torvalds's avatar
Linus Torvalds committed
252
253
254
	rwlock_t		sk_callback_lock;
	int			sk_err,
				sk_err_soft;
Wang Chen's avatar
Wang Chen committed
255
	atomic_t		sk_drops;
Linus Torvalds's avatar
Linus Torvalds committed
256
257
258
259
260
261
262
263
264
	unsigned short		sk_ack_backlog;
	unsigned short		sk_max_ack_backlog;
	__u32			sk_priority;
	struct ucred		sk_peercred;
	long			sk_rcvtimeo;
	long			sk_sndtimeo;
	struct sk_filter      	*sk_filter;
	void			*sk_protinfo;
	struct timer_list	sk_timer;
265
	ktime_t			sk_stamp;
Linus Torvalds's avatar
Linus Torvalds committed
266
267
268
269
270
271
272
	struct socket		*sk_socket;
	void			*sk_user_data;
	struct page		*sk_sndmsg_page;
	struct sk_buff		*sk_send_head;
	__u32			sk_sndmsg_off;
	int			sk_write_pending;
	void			*sk_security;
273
274
	__u32			sk_mark;
	/* XXX 4 bytes hole on 64 bit */
Linus Torvalds's avatar
Linus Torvalds committed
275
276
277
278
279
280
281
282
283
284
285
286
	void			(*sk_state_change)(struct sock *sk);
	void			(*sk_data_ready)(struct sock *sk, int bytes);
	void			(*sk_write_space)(struct sock *sk);
	void			(*sk_error_report)(struct sock *sk);
  	int			(*sk_backlog_rcv)(struct sock *sk,
						  struct sk_buff *skb);  
	void                    (*sk_destruct)(struct sock *sk);
};

/*
 * Hashed lists helper routines
 */
287
static inline struct sock *__sk_head(const struct hlist_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
288
289
290
291
{
	return hlist_entry(head->first, struct sock, sk_node);
}

292
static inline struct sock *sk_head(const struct hlist_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
293
294
295
296
{
	return hlist_empty(head) ? NULL : __sk_head(head);
}

297
static inline struct sock *sk_next(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
298
299
300
301
302
{
	return sk->sk_node.next ?
		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}

303
static inline int sk_unhashed(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
304
305
306
307
{
	return hlist_unhashed(&sk->sk_node);
}

308
static inline int sk_hashed(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
309
{
Akinobu Mita's avatar
Akinobu Mita committed
310
	return !sk_unhashed(sk);
Linus Torvalds's avatar
Linus Torvalds committed
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
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
}

static __inline__ void sk_node_init(struct hlist_node *node)
{
	node->pprev = NULL;
}

static __inline__ void __sk_del_node(struct sock *sk)
{
	__hlist_del(&sk->sk_node);
}

static __inline__ int __sk_del_node_init(struct sock *sk)
{
	if (sk_hashed(sk)) {
		__sk_del_node(sk);
		sk_node_init(&sk->sk_node);
		return 1;
	}
	return 0;
}

/* Grab socket reference count. This operation is valid only
   when sk is ALREADY grabbed f.e. it is found in hash table
   or a list and the lookup is made under lock preventing hash table
   modifications.
 */

static inline void sock_hold(struct sock *sk)
{
	atomic_inc(&sk->sk_refcnt);
}

/* Ungrab socket in the context, which assumes that socket refcnt
   cannot hit zero, f.e. it is true in context of any socketcall.
 */
static inline void __sock_put(struct sock *sk)
{
	atomic_dec(&sk->sk_refcnt);
}

static __inline__ int sk_del_node_init(struct sock *sk)
{
	int rc = __sk_del_node_init(sk);

	if (rc) {
		/* paranoid for a while -acme */
		WARN_ON(atomic_read(&sk->sk_refcnt) == 1);
		__sock_put(sk);
	}
	return rc;
}

static __inline__ void __sk_add_node(struct sock *sk, struct hlist_head *list)
{
	hlist_add_head(&sk->sk_node, list);
}

static __inline__ void sk_add_node(struct sock *sk, struct hlist_head *list)
{
	sock_hold(sk);
	__sk_add_node(sk, list);
}

static __inline__ void __sk_del_bind_node(struct sock *sk)
{
	__hlist_del(&sk->sk_bind_node);
}

static __inline__ void sk_add_bind_node(struct sock *sk,
					struct hlist_head *list)
{
	hlist_add_head(&sk->sk_bind_node, list);
}

#define sk_for_each(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_node)
#define sk_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
		hlist_for_each_entry_from(__sk, node, sk_node)
#define sk_for_each_continue(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
		hlist_for_each_entry_continue(__sk, node, sk_node)
#define sk_for_each_safe(__sk, node, tmp, list) \
	hlist_for_each_entry_safe(__sk, node, tmp, list, sk_node)
#define sk_for_each_bound(__sk, node, list) \
	hlist_for_each_entry(__sk, node, list, sk_bind_node)

/* Sock flags */
enum sock_flags {
	SOCK_DEAD,
	SOCK_DONE,
	SOCK_URGINLINE,
	SOCK_KEEPOPEN,
	SOCK_LINGER,
	SOCK_DESTROY,
	SOCK_BROADCAST,
	SOCK_TIMESTAMP,
	SOCK_ZAPPED,
	SOCK_USE_WRITE_QUEUE, /* whether to call sk->sk_write_space in sock_wfree */
	SOCK_DBG, /* %SO_DEBUG setting */
	SOCK_RCVTSTAMP, /* %SO_TIMESTAMP setting */
413
	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
Linus Torvalds's avatar
Linus Torvalds committed
414
415
416
417
	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
};

Ralf Baechle's avatar
Ralf Baechle committed
418
419
420
421
422
static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
{
	nsk->sk_flags = osk->sk_flags;
}

Linus Torvalds's avatar
Linus Torvalds committed
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
{
	__set_bit(flag, &sk->sk_flags);
}

static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
{
	__clear_bit(flag, &sk->sk_flags);
}

static inline int sock_flag(struct sock *sk, enum sock_flags flag)
{
	return test_bit(flag, &sk->sk_flags);
}

static inline void sk_acceptq_removed(struct sock *sk)
{
	sk->sk_ack_backlog--;
}

static inline void sk_acceptq_added(struct sock *sk)
{
	sk->sk_ack_backlog++;
}

static inline int sk_acceptq_is_full(struct sock *sk)
{
450
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
Linus Torvalds's avatar
Linus Torvalds committed
451
452
453
454
455
456
457
}

/*
 * Compute minimal free write space needed to queue new packets.
 */
static inline int sk_stream_min_wspace(struct sock *sk)
{
458
	return sk->sk_wmem_queued >> 1;
Linus Torvalds's avatar
Linus Torvalds committed
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
}

static inline int sk_stream_wspace(struct sock *sk)
{
	return sk->sk_sndbuf - sk->sk_wmem_queued;
}

extern void sk_stream_write_space(struct sock *sk);

static inline int sk_stream_memory_free(struct sock *sk)
{
	return sk->sk_wmem_queued < sk->sk_sndbuf;
}

/* The per-socket spinlock must be held here. */
474
475
476
477
478
479
480
481
482
483
static inline void sk_add_backlog(struct sock *sk, struct sk_buff *skb)
{
	if (!sk->sk_backlog.tail) {
		sk->sk_backlog.head = sk->sk_backlog.tail = skb;
	} else {
		sk->sk_backlog.tail->next = skb;
		sk->sk_backlog.tail = skb;
	}
	skb->next = NULL;
}
Linus Torvalds's avatar
Linus Torvalds committed
484

485
486
487
488
489
490
491
492
493
494
495
#define sk_wait_event(__sk, __timeo, __condition)			\
	({	int __rc;						\
		release_sock(__sk);					\
		__rc = __condition;					\
		if (!__rc) {						\
			*(__timeo) = schedule_timeout(*(__timeo));	\
		}							\
		lock_sock(__sk);					\
		__rc = __condition;					\
		__rc;							\
	})
Linus Torvalds's avatar
Linus Torvalds committed
496
497
498
499
500
501
502
503
504

extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
extern int sk_stream_error(struct sock *sk, int flags, int err);
extern void sk_stream_kill_queues(struct sock *sk);

extern int sk_wait_data(struct sock *sk, long *timeo);

505
struct request_sock_ops;
506
struct timewait_sock_ops;
507
struct inet_hashinfo;
508
struct raw_hashinfo;
509

Linus Torvalds's avatar
Linus Torvalds committed
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
/* Networking protocol blocks we attach to sockets.
 * socket layer -> transport layer interface
 * transport -> network interface is defined by struct inet_proto
 */
struct proto {
	void			(*close)(struct sock *sk, 
					long timeout);
	int			(*connect)(struct sock *sk,
				        struct sockaddr *uaddr, 
					int addr_len);
	int			(*disconnect)(struct sock *sk, int flags);

	struct sock *		(*accept) (struct sock *sk, int flags, int *err);

	int			(*ioctl)(struct sock *sk, int cmd,
					 unsigned long arg);
	int			(*init)(struct sock *sk);
527
	void			(*destroy)(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
528
529
530
531
532
533
534
	void			(*shutdown)(struct sock *sk, int how);
	int			(*setsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval,
					int optlen);
	int			(*getsockopt)(struct sock *sk, int level, 
					int optname, char __user *optval, 
					int __user *option);  	 
535
536
537
538
539
540
541
542
	int			(*compat_setsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					int optlen);
	int			(*compat_getsockopt)(struct sock *sk,
					int level,
					int optname, char __user *optval,
					int __user *option);
Linus Torvalds's avatar
Linus Torvalds committed
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
	int			(*sendmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg, size_t len);
	int			(*recvmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg,
					size_t len, int noblock, int flags, 
					int *addr_len);
	int			(*sendpage)(struct sock *sk, struct page *page,
					int offset, size_t size, int flags);
	int			(*bind)(struct sock *sk, 
					struct sockaddr *uaddr, int addr_len);

	int			(*backlog_rcv) (struct sock *sk, 
						struct sk_buff *skb);

	/* Keeping track of sk's, looking them up, and port selection methods. */
	void			(*hash)(struct sock *sk);
	void			(*unhash)(struct sock *sk);
	int			(*get_port)(struct sock *sk, unsigned short snum);

562
	/* Keeping track of sockets in use */
563
#ifdef CONFIG_PROC_FS
564
	unsigned int		inuse_idx;
565
#endif
566

Linus Torvalds's avatar
Linus Torvalds committed
567
568
569
570
571
572
573
	/* Memory pressure */
	void			(*enter_memory_pressure)(void);
	atomic_t		*memory_allocated;	/* Current allocated memory. */
	atomic_t		*sockets_allocated;	/* Current number of sockets. */
	/*
	 * Pressure flag: try to collapse.
	 * Technical note: it is used by multiple contexts non atomically.
574
	 * All the __sk_mem_schedule() is of this nature: accounting
Linus Torvalds's avatar
Linus Torvalds committed
575
576
577
578
579
580
581
582
	 * is strict, actions are advisory and have some latency.
	 */
	int			*memory_pressure;
	int			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
	int			max_header;

583
	struct kmem_cache		*slab;
Linus Torvalds's avatar
Linus Torvalds committed
584
585
	unsigned int		obj_size;

586
	atomic_t		*orphan_count;
587

588
	struct request_sock_ops	*rsk_prot;
589
	struct timewait_sock_ops *twsk_prot;
590

591
592
593
	union {
		struct inet_hashinfo	*hashinfo;
		struct hlist_head	*udp_hash;
594
		struct raw_hashinfo	*raw_hash;
595
	} h;
596

Linus Torvalds's avatar
Linus Torvalds committed
597
598
599
600
601
	struct module		*owner;

	char			name[32];

	struct list_head	node;
602
603
604
#ifdef SOCK_REFCNT_DEBUG
	atomic_t		socks;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
605
606
607
608
609
};

extern int proto_register(struct proto *prot, int alloc_slab);
extern void proto_unregister(struct proto *prot);

610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
#ifdef SOCK_REFCNT_DEBUG
static inline void sk_refcnt_debug_inc(struct sock *sk)
{
	atomic_inc(&sk->sk_prot->socks);
}

static inline void sk_refcnt_debug_dec(struct sock *sk)
{
	atomic_dec(&sk->sk_prot->socks);
	printk(KERN_DEBUG "%s socket %p released, %d are still alive\n",
	       sk->sk_prot->name, sk, atomic_read(&sk->sk_prot->socks));
}

static inline void sk_refcnt_debug_release(const struct sock *sk)
{
	if (atomic_read(&sk->sk_refcnt) != 1)
		printk(KERN_DEBUG "Destruction of the %s socket %p delayed, refcnt=%d\n",
		       sk->sk_prot->name, sk, atomic_read(&sk->sk_refcnt));
}
#else /* SOCK_REFCNT_DEBUG */
#define sk_refcnt_debug_inc(sk) do { } while (0)
#define sk_refcnt_debug_dec(sk) do { } while (0)
#define sk_refcnt_debug_release(sk) do { } while (0)
#endif /* SOCK_REFCNT_DEBUG */

635
636

#ifdef CONFIG_PROC_FS
Linus Torvalds's avatar
Linus Torvalds committed
637
/* Called with local bh disabled */
638
639
extern void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc);
extern int sock_prot_inuse_get(struct net *net, struct proto *proto);
640
#else
641
642
static void inline sock_prot_inuse_add(struct net *net, struct proto *prot,
		int inc)
643
644
645
646
{
}
#endif

Linus Torvalds's avatar
Linus Torvalds committed
647

648
649
650
651
652
653
654
655
656
/* With per-bucket locks this operation is not-atomic, so that
 * this version is not worse.
 */
static inline void __sk_prot_rehash(struct sock *sk)
{
	sk->sk_prot->unhash(sk);
	sk->sk_prot->hash(sk);
}

Linus Torvalds's avatar
Linus Torvalds committed
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
/* About 10 seconds */
#define SOCK_DESTROY_TIME (10*HZ)

/* Sockets 0-1023 can't be bound to unless you are superuser */
#define PROT_SOCK	1024

#define SHUTDOWN_MASK	3
#define RCV_SHUTDOWN	1
#define SEND_SHUTDOWN	2

#define SOCK_SNDBUF_LOCK	1
#define SOCK_RCVBUF_LOCK	2
#define SOCK_BINDADDR_LOCK	4
#define SOCK_BINDPORT_LOCK	8

/* sock_iocb: used to kick off async processing of socket ios */
struct sock_iocb {
	struct list_head	list;

	int			flags;
	int			size;
	struct socket		*sock;
	struct sock		*sk;
	struct scm_cookie	*scm;
	struct msghdr		*msg, async_msg;
	struct kiocb		*kiocb;
};

static inline struct sock_iocb *kiocb_to_siocb(struct kiocb *iocb)
{
	return (struct sock_iocb *)iocb->private;
}

static inline struct kiocb *siocb_to_kiocb(struct sock_iocb *si)
{
	return si->kiocb;
}

struct socket_alloc {
	struct socket socket;
	struct inode vfs_inode;
};

static inline struct socket *SOCKET_I(struct inode *inode)
{
	return &container_of(inode, struct socket_alloc, vfs_inode)->socket;
}

static inline struct inode *SOCK_INODE(struct socket *socket)
{
	return &container_of(socket, struct socket_alloc, socket)->vfs_inode;
}

710
711
712
713
714
/*
 * Functions for memory accounting
 */
extern int __sk_mem_schedule(struct sock *sk, int size, int kind);
extern void __sk_mem_reclaim(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
715

716
717
718
719
#define SK_MEM_QUANTUM ((int)PAGE_SIZE)
#define SK_MEM_QUANTUM_SHIFT ilog2(SK_MEM_QUANTUM)
#define SK_MEM_SEND	0
#define SK_MEM_RECV	1
Linus Torvalds's avatar
Linus Torvalds committed
720

721
static inline int sk_mem_pages(int amt)
Linus Torvalds's avatar
Linus Torvalds committed
722
{
723
	return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
Linus Torvalds's avatar
Linus Torvalds committed
724
725
}

726
static inline int sk_has_account(struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
727
{
728
729
	/* return true if protocol supports memory accounting */
	return !!sk->sk_prot->memory_allocated;
Linus Torvalds's avatar
Linus Torvalds committed
730
731
}

732
static inline int sk_wmem_schedule(struct sock *sk, int size)
Linus Torvalds's avatar
Linus Torvalds committed
733
{
734
735
736
737
	if (!sk_has_account(sk))
		return 1;
	return size <= sk->sk_forward_alloc ||
		__sk_mem_schedule(sk, size, SK_MEM_SEND);
Linus Torvalds's avatar
Linus Torvalds committed
738
739
}

740
static inline int sk_rmem_schedule(struct sock *sk, int size)
741
{
742
743
	if (!sk_has_account(sk))
		return 1;
744
	return size <= sk->sk_forward_alloc ||
745
746
747
748
749
750
751
752
753
754
755
		__sk_mem_schedule(sk, size, SK_MEM_RECV);
}

static inline void sk_mem_reclaim(struct sock *sk)
{
	if (!sk_has_account(sk))
		return;
	if (sk->sk_forward_alloc >= SK_MEM_QUANTUM)
		__sk_mem_reclaim(sk);
}

756
757
758
759
760
761
762
763
static inline void sk_mem_reclaim_partial(struct sock *sk)
{
	if (!sk_has_account(sk))
		return;
	if (sk->sk_forward_alloc > SK_MEM_QUANTUM)
		__sk_mem_reclaim(sk);
}

764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
static inline void sk_mem_charge(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return;
	sk->sk_forward_alloc -= size;
}

static inline void sk_mem_uncharge(struct sock *sk, int size)
{
	if (!sk_has_account(sk))
		return;
	sk->sk_forward_alloc += size;
}

static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
{
	skb_truesize_check(skb);
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
	sk->sk_wmem_queued -= skb->truesize;
	sk_mem_uncharge(sk, skb->truesize);
	__kfree_skb(skb);
785
786
}

Linus Torvalds's avatar
Linus Torvalds committed
787
788
789
790
791
792
793
794
795
796
797
798
799
/* Used by processes to "lock" a socket state, so that
 * interrupts and bottom half handlers won't change it
 * from under us. It essentially blocks any incoming
 * packets, so that we won't get any new data or any
 * packets that change the state of the socket.
 *
 * While locked, BH processing will add new packets to
 * the backlog queue.  This queue is processed by the
 * owner of the socket lock right before it is released.
 *
 * Since ~2.3.5 it is also exclusive sleep lock serializing
 * accesses from user process context.
 */
800
#define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
Linus Torvalds's avatar
Linus Torvalds committed
801

802
803
804
805
806
807
808
809
810
/*
 * Macro so as to not evaluate some arguments when
 * lockdep is not enabled.
 *
 * Mark both the sk_lock and the sk_lock.slock as a
 * per-address-family lock class.
 */
#define sock_lock_init_class_and_name(sk, sname, skey, name, key) 	\
do {									\
811
	sk->sk_lock.owned = 0;					\
812
813
814
815
816
817
818
819
820
	init_waitqueue_head(&sk->sk_lock.wq);				\
	spin_lock_init(&(sk)->sk_lock.slock);				\
	debug_check_no_locks_freed((void *)&(sk)->sk_lock,		\
			sizeof((sk)->sk_lock));				\
	lockdep_set_class_and_name(&(sk)->sk_lock.slock,		\
		       	(skey), (sname));				\
	lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0);	\
} while (0)

Harvey Harrison's avatar
Harvey Harrison committed
821
extern void lock_sock_nested(struct sock *sk, int subclass);
822
823
824
825
826
827

static inline void lock_sock(struct sock *sk)
{
	lock_sock_nested(sk, 0);
}

Harvey Harrison's avatar
Harvey Harrison committed
828
extern void release_sock(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
829
830
831

/* BH context may only use the following locking interface. */
#define bh_lock_sock(__sk)	spin_lock(&((__sk)->sk_lock.slock))
832
833
834
#define bh_lock_sock_nested(__sk) \
				spin_lock_nested(&((__sk)->sk_lock.slock), \
				SINGLE_DEPTH_NESTING)
Linus Torvalds's avatar
Linus Torvalds committed
835
836
#define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))

837
extern struct sock		*sk_alloc(struct net *net, int family,
838
					  gfp_t priority,
839
					  struct proto *prot);
Linus Torvalds's avatar
Linus Torvalds committed
840
extern void			sk_free(struct sock *sk);
841
extern void			sk_release_kernel(struct sock *sk);
842
extern struct sock		*sk_clone(const struct sock *sk,
843
					  const gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
844
845
846

extern struct sk_buff		*sock_wmalloc(struct sock *sk,
					      unsigned long size, int force,
847
					      gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
848
849
extern struct sk_buff		*sock_rmalloc(struct sock *sk,
					      unsigned long size, int force,
850
					      gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
851
852
853
854
855
856
857
858
859
860
861
862
863
864
extern void			sock_wfree(struct sk_buff *skb);
extern void			sock_rfree(struct sk_buff *skb);

extern int			sock_setsockopt(struct socket *sock, int level,
						int op, char __user *optval,
						int optlen);

extern int			sock_getsockopt(struct socket *sock, int level,
						int op, char __user *optval, 
						int __user *optlen);
extern struct sk_buff 		*sock_alloc_send_skb(struct sock *sk,
						     unsigned long size,
						     int noblock,
						     int *errcode);
Victor Fusco's avatar
Victor Fusco committed
865
extern void *sock_kmalloc(struct sock *sk, int size,
866
			  gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
extern void sock_kfree_s(struct sock *sk, void *mem, int size);
extern void sk_send_sigurg(struct sock *sk);

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * does not implement a particular function.
 */
extern int                      sock_no_bind(struct socket *, 
					     struct sockaddr *, int);
extern int                      sock_no_connect(struct socket *,
						struct sockaddr *, int, int);
extern int                      sock_no_socketpair(struct socket *,
						   struct socket *);
extern int                      sock_no_accept(struct socket *,
					       struct socket *, int);
extern int                      sock_no_getname(struct socket *,
						struct sockaddr *, int *, int);
extern unsigned int             sock_no_poll(struct file *, struct socket *,
					     struct poll_table_struct *);
extern int                      sock_no_ioctl(struct socket *, unsigned int,
					      unsigned long);
extern int			sock_no_listen(struct socket *, int);
extern int                      sock_no_shutdown(struct socket *, int);
extern int			sock_no_getsockopt(struct socket *, int , int,
						   char __user *, int __user *);
extern int			sock_no_setsockopt(struct socket *, int, int,
						   char __user *, int);
extern int                      sock_no_sendmsg(struct kiocb *, struct socket *,
						struct msghdr *, size_t);
extern int                      sock_no_recvmsg(struct kiocb *, struct socket *,
						struct msghdr *, size_t, int);
extern int			sock_no_mmap(struct file *file,
					     struct socket *sock,
					     struct vm_area_struct *vma);
extern ssize_t			sock_no_sendpage(struct socket *sock,
						struct page *page,
						int offset, size_t size, 
						int flags);

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * uses the inet style.
 */
extern int sock_common_getsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int __user *optlen);
extern int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
			       struct msghdr *msg, size_t size, int flags);
extern int sock_common_setsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int optlen);
916
917
918
919
extern int compat_sock_common_getsockopt(struct socket *sock, int level,
		int optname, char __user *optval, int __user *optlen);
extern int compat_sock_common_setsockopt(struct socket *sock, int level,
		int optname, char __user *optval, int optlen);
Linus Torvalds's avatar
Linus Torvalds committed
920
921
922
923
924
925
926
927
928
929

extern void sk_common_release(struct sock *sk);

/*
 *	Default socket callbacks and setup code
 */
 
/* Initialise core socket variables */
extern void sock_init_data(struct socket *sock, struct sock *sk);

930
931
932
933
934
935
936
937
/**
 *	sk_filter_release: Release a socket filter
 *	@sk: socket
 *	@fp: filter to remove
 *
 *	Remove a filter from a socket and release its resources.
 */

938
939
940
static inline void sk_filter_release(struct sk_filter *fp)
{
	if (atomic_dec_and_test(&fp->refcnt))
941
		kfree(fp);
942
943
944
}

static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
Linus Torvalds's avatar
Linus Torvalds committed
945
946
947
948
{
	unsigned int size = sk_filter_len(fp);

	atomic_sub(size, &sk->sk_omem_alloc);
949
	sk_filter_release(fp);
Linus Torvalds's avatar
Linus Torvalds committed
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
}

static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
	atomic_inc(&fp->refcnt);
	atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc);
}

/*
 * Socket reference counting postulates.
 *
 * * Each user of socket SHOULD hold a reference count.
 * * Each access point to socket (an hash table bucket, reference from a list,
 *   running timer, skb in flight MUST hold a reference count.
 * * When reference count hits 0, it means it will never increase back.
 * * When reference count hits 0, it means that no references from
 *   outside exist to this socket and current process on current CPU
 *   is last user and may/should destroy this socket.
 * * sk_free is called from any context: process, BH, IRQ. When
 *   it is called, socket has no references from outside -> sk_free
 *   may release descendant resources allocated by the socket, but
 *   to the time when it is called, socket is NOT referenced by any
 *   hash tables, lists etc.
 * * Packets, delivered from outside (from network or from another process)
 *   and enqueued on receive/error queues SHOULD NOT grab reference count,
 *   when they sit in queue. Otherwise, packets will leak to hole, when
 *   socket is looked up by one cpu and unhasing is made by another CPU.
 *   It is true for udp/raw, netlink (leak to receive and error queues), tcp
 *   (leak to backlog). Packet socket does all the processing inside
 *   BR_NETPROTO_LOCK, so that it has not this race condition. UNIX sockets
 *   use separate SMP lock, so that they are prone too.
 */

/* Ungrab socket and destroy it, if it was the last reference. */
static inline void sock_put(struct sock *sk)
{
	if (atomic_dec_and_test(&sk->sk_refcnt))
		sk_free(sk);
}

990
991
extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
			  const int nested);
992

Linus Torvalds's avatar
Linus Torvalds committed
993
994
995
996
997
998
999
1000
/* Detach socket from process context.
 * Announce socket dead, detach it from wait queue and inode.
 * Note that parent inode held reference count on this struct sock,
 * we do not release it in this function, because protocol
 * probably wants some additional cleanups or even continuing
 * to work with this socket (TCP).
 */
static inline void sock_orphan(struct sock *sk)