sock.h 40 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
#include <linux/security.h>

#include <linux/filter.h>

#include <asm/atomic.h>
#include <net/dst.h>
#include <net/checksum.h>
59
#include <net/net_namespace.h>
Linus Torvalds's avatar
Linus Torvalds committed
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81

/*
 * 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
#define SOCK_DEBUG(sk, msg...) do { } while (0)
#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;
82
	int			owned;
Linus Torvalds's avatar
Linus Torvalds committed
83
	wait_queue_head_t	wq;
84
85
86
87
88
89
90
91
92
	/*
	 * 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
93
94
95
} socket_lock_t;

struct sock;
96
struct proto;
Linus Torvalds's avatar
Linus Torvalds committed
97
98

/**
99
100
101
102
103
104
105
106
 *	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
107
 *	@skc_hash: hash value used with various protocol lookup tables
108
 *	@skc_prot: protocol handlers inside a network family
109
 *	@skc_net: reference to the network namespace of this socket
110
111
 *
 *	This is the minimal network layer representation of sockets, the header
112
113
 *	for struct sock and struct inet_timewait_sock.
 */
Linus Torvalds's avatar
Linus Torvalds committed
114
115
116
117
118
119
120
121
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;
122
	unsigned int		skc_hash;
123
	struct proto		*skc_prot;
124
	struct net	 	*skc_net;
Linus Torvalds's avatar
Linus Torvalds committed
125
126
127
128
};

/**
  *	struct sock - network layer representation of sockets
129
  *	@__sk_common: shared layout with inet_timewait_sock
130
131
132
133
134
135
136
137
138
139
140
141
  *	@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
142
  *	@sk_async_wait_queue: DMA copied packets
143
144
145
146
147
  *	@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
148
149
  *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
  *		   %SO_OOBINLINE settings
150
151
  *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
  *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
152
  *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
153
154
155
156
  *	@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
157
158
  *	@sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
  *			  IPV6_ADDRFORM for instance)
159
  *	@sk_err: last error
Wang Chen's avatar
Wang Chen committed
160
161
162
  *	@sk_err_soft: errors that don't cause failure but are the cause of a
  *		      persistent failure not just 'timed out'
  *	@sk_drops: raw drops counter
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
  *	@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
181
  *	@sk_security: used by security modules
182
183
184
185
186
187
188
  *	@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
189
190
191
 */
struct sock {
	/*
192
	 * Now struct inet_timewait_sock also uses sock_common, so please just
Linus Torvalds's avatar
Linus Torvalds committed
193
194
195
196
197
198
199
200
201
202
	 * 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
203
#define sk_hash			__sk_common.skc_hash
204
#define sk_prot			__sk_common.skc_prot
205
#define sk_net			__sk_common.skc_net
Linus Torvalds's avatar
Linus Torvalds committed
206
207
208
209
210
211
212
	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;
213
214
215
216
217
218
219
220
221
	/*
	 * 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
222
223
224
225
226
227
228
	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;
229
	int			sk_sndbuf;
Linus Torvalds's avatar
Linus Torvalds committed
230
231
	struct sk_buff_head	sk_receive_queue;
	struct sk_buff_head	sk_write_queue;
232
	struct sk_buff_head	sk_async_wait_queue;
Linus Torvalds's avatar
Linus Torvalds committed
233
234
	int			sk_wmem_queued;
	int			sk_forward_alloc;
Al Viro's avatar
Al Viro committed
235
	gfp_t			sk_allocation;
Linus Torvalds's avatar
Linus Torvalds committed
236
	int			sk_route_caps;
237
	int			sk_gso_type;
238
	int			sk_rcvlowat;
Linus Torvalds's avatar
Linus Torvalds committed
239
240
241
	unsigned long 		sk_flags;
	unsigned long	        sk_lingertime;
	struct sk_buff_head	sk_error_queue;
242
	struct proto		*sk_prot_creator;
Linus Torvalds's avatar
Linus Torvalds committed
243
244
245
	rwlock_t		sk_callback_lock;
	int			sk_err,
				sk_err_soft;
Wang Chen's avatar
Wang Chen committed
246
	atomic_t		sk_drops;
Linus Torvalds's avatar
Linus Torvalds committed
247
248
249
250
251
252
253
254
255
	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;
256
	ktime_t			sk_stamp;
Linus Torvalds's avatar
Linus Torvalds committed
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
	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;
	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
 */
276
static inline struct sock *__sk_head(const struct hlist_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
277
278
279
280
{
	return hlist_entry(head->first, struct sock, sk_node);
}

281
static inline struct sock *sk_head(const struct hlist_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
282
283
284
285
{
	return hlist_empty(head) ? NULL : __sk_head(head);
}

286
static inline struct sock *sk_next(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
287
288
289
290
291
{
	return sk->sk_node.next ?
		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}

292
static inline int sk_unhashed(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
293
294
295
296
{
	return hlist_unhashed(&sk->sk_node);
}

297
static inline int sk_hashed(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
298
{
Akinobu Mita's avatar
Akinobu Mita committed
299
	return !sk_unhashed(sk);
Linus Torvalds's avatar
Linus Torvalds committed
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
390
391
392
393
394
395
396
397
398
399
400
401
}

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 */
402
	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
Linus Torvalds's avatar
Linus Torvalds committed
403
404
405
406
	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
};

Ralf Baechle's avatar
Ralf Baechle committed
407
408
409
410
411
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
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
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)
{
439
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
Linus Torvalds's avatar
Linus Torvalds committed
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
}

/*
 * Compute minimal free write space needed to queue new packets.
 */
static inline int sk_stream_min_wspace(struct sock *sk)
{
	return sk->sk_wmem_queued / 2;
}

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;
}

extern void sk_stream_rfree(struct sk_buff *skb);

static inline void sk_stream_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb->sk = sk;
	skb->destructor = sk_stream_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
	sk->sk_forward_alloc -= skb->truesize;
}

static inline void sk_stream_free_skb(struct sock *sk, struct sk_buff *skb)
{
474
	skb_truesize_check(skb);
Linus Torvalds's avatar
Linus Torvalds committed
475
476
477
478
479
480
481
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
	sk->sk_wmem_queued   -= skb->truesize;
	sk->sk_forward_alloc += skb->truesize;
	__kfree_skb(skb);
}

/* The per-socket spinlock must be held here. */
482
483
484
485
486
487
488
489
490
491
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
492

493
494
495
496
497
498
499
500
501
502
503
#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
504
505
506
507
508
509
510
511
512

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);

513
struct request_sock_ops;
514
struct timewait_sock_ops;
515

Linus Torvalds's avatar
Linus Torvalds committed
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
/* 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);
	int			(*destroy)(struct sock *sk);
	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);  	 
541
542
543
544
545
546
547
548
	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
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
	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);

568
569
570
571
572
573
574
575
#ifdef CONFIG_SMP
	/* Keeping track of sockets in use */
	void			(*inuse_add)(struct proto *prot, int inc);
	int			(*inuse_getval)(const struct proto *prot);
	int			*inuse_ptr;
#else
	int			inuse;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
	/* 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.
	 * All the sk_stream_mem_schedule() is of this nature: accounting
	 * is strict, actions are advisory and have some latency.
	 */
	int			*memory_pressure;
	int			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
	int			max_header;

592
	struct kmem_cache		*slab;
Linus Torvalds's avatar
Linus Torvalds committed
593
594
	unsigned int		obj_size;

595
	atomic_t		*orphan_count;
596

597
	struct request_sock_ops	*rsk_prot;
598
	struct timewait_sock_ops *twsk_prot;
599

Linus Torvalds's avatar
Linus Torvalds committed
600
601
602
603
604
	struct module		*owner;

	char			name[32];

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

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
635
636
637
638
639
/*
 * Special macros to let protos use a fast version of inuse{get|add}
 * using a static percpu variable per proto instead of an allocated one,
 * saving one dereference.
 * This might be changed if/when dynamic percpu vars become fast.
 */
#ifdef CONFIG_SMP
# define DEFINE_PROTO_INUSE(NAME)			\
static DEFINE_PER_CPU(int, NAME##_inuse);		\
static void NAME##_inuse_add(struct proto *prot, int inc)	\
{							\
	__get_cpu_var(NAME##_inuse) += inc;		\
}							\
							\
static int NAME##_inuse_getval(const struct proto *prot)\
{							\
	int res = 0, cpu;				\
							\
	for_each_possible_cpu(cpu)			\
		res += per_cpu(NAME##_inuse, cpu);	\
	return res;					\
}
# define REF_PROTO_INUSE(NAME)				\
	.inuse_add = NAME##_inuse_add,			\
	.inuse_getval = NAME##_inuse_getval,
#else
# define DEFINE_PROTO_INUSE(NAME)
# define REF_PROTO_INUSE(NAME)
#endif

Linus Torvalds's avatar
Linus Torvalds committed
640
641
642
extern int proto_register(struct proto *prot, int alloc_slab);
extern void proto_unregister(struct proto *prot);

643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
#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 */

Linus Torvalds's avatar
Linus Torvalds committed
668
669
670
/* Called with local bh disabled */
static __inline__ void sock_prot_inc_use(struct proto *prot)
{
671
672
673
674
675
#ifdef CONFIG_SMP
	prot->inuse_add(prot, 1);
#else
	prot->inuse++;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
676
677
678
679
}

static __inline__ void sock_prot_dec_use(struct proto *prot)
{
680
681
682
683
684
685
686
687
688
689
690
691
692
693
#ifdef CONFIG_SMP
	prot->inuse_add(prot, -1);
#else
	prot->inuse--;
#endif
}

static __inline__ int sock_prot_inuse(struct proto *proto)
{
#ifdef CONFIG_SMP
	return proto->inuse_getval(proto);
#else
	return proto->inuse;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
694
695
}

696
697
698
699
700
701
702
703
704
/* 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
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
/* 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;
}

extern void __sk_stream_mem_reclaim(struct sock *sk);
extern int sk_stream_mem_schedule(struct sock *sk, int size, int kind);

#define SK_STREAM_MEM_QUANTUM ((int)PAGE_SIZE)

static inline int sk_stream_pages(int amt)
{
765
	return DIV_ROUND_UP(amt, SK_STREAM_MEM_QUANTUM);
Linus Torvalds's avatar
Linus Torvalds committed
766
767
768
769
770
771
772
773
774
775
776
777
778
779
}

static inline void sk_stream_mem_reclaim(struct sock *sk)
{
	if (sk->sk_forward_alloc >= SK_STREAM_MEM_QUANTUM)
		__sk_stream_mem_reclaim(sk);
}

static inline int sk_stream_rmem_schedule(struct sock *sk, struct sk_buff *skb)
{
	return (int)skb->truesize <= sk->sk_forward_alloc ||
		sk_stream_mem_schedule(sk, skb->truesize, 1);
}

780
781
782
783
784
785
static inline int sk_stream_wmem_schedule(struct sock *sk, int size)
{
	return size <= sk->sk_forward_alloc ||
	       sk_stream_mem_schedule(sk, size, 0);
}

Linus Torvalds's avatar
Linus Torvalds committed
786
787
788
789
790
791
792
793
794
795
796
797
798
/* 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.
 */
799
#define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
Linus Torvalds's avatar
Linus Torvalds committed
800

801
802
803
804
805
806
807
808
809
/*
 * 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 {									\
810
	sk->sk_lock.owned = 0;					\
811
812
813
814
815
816
817
818
819
	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)

820
821
822
823
824
825
826
extern void FASTCALL(lock_sock_nested(struct sock *sk, int subclass));

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

Linus Torvalds's avatar
Linus Torvalds committed
827
828
829
830
extern void FASTCALL(release_sock(struct sock *sk));

/* BH context may only use the following locking interface. */
#define bh_lock_sock(__sk)	spin_lock(&((__sk)->sk_lock.slock))
831
832
833
#define bh_lock_sock_nested(__sk) \
				spin_lock_nested(&((__sk)->sk_lock.slock), \
				SINGLE_DEPTH_NESTING)
Linus Torvalds's avatar
Linus Torvalds committed
834
835
#define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))

836
extern struct sock		*sk_alloc(struct net *net, int family,
837
					  gfp_t priority,
838
					  struct proto *prot);
Linus Torvalds's avatar
Linus Torvalds committed
839
extern void			sk_free(struct sock *sk);
840
extern struct sock		*sk_clone(const struct sock *sk,
841
					  const gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
842
843
844

extern struct sk_buff		*sock_wmalloc(struct sock *sk,
					      unsigned long size, int force,
845
					      gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
846
847
extern struct sk_buff		*sock_rmalloc(struct sock *sk,
					      unsigned long size, int force,
848
					      gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
849
850
851
852
853
854
855
856
857
858
859
860
861
862
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
863
extern void *sock_kmalloc(struct sock *sk, int size,
864
			  gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
865
866
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
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);
914
915
916
917
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
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941

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);

/**
 *	sk_filter - run a packet through a socket filter
 *	@sk: sock associated with &sk_buff
 *	@skb: buffer to filter
 *	@needlock: set to 1 if the sock is not locked by caller.
 *
 * Run the filter code and then cut skb->data to correct size returned by
 * sk_run_filter. If pkt_len is 0 we toss packet. If skb->len is smaller
 * than pkt_len we keep whole skb->data. This is the socket level
 * wrapper to sk_run_filter. It returns 0 if the packet should
 * be accepted or -EPERM if the packet should be tossed.
 *
 */

942
static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
Linus Torvalds's avatar
Linus Torvalds committed
943
944
{
	int err;
945
	struct sk_filter *filter;
Linus Torvalds's avatar
Linus Torvalds committed
946
947
948
949
950
	
	err = security_sock_rcv_skb(sk, skb);
	if (err)
		return err;
	
951
	rcu_read_lock_bh();
952
	filter = rcu_dereference(sk->sk_filter);
953
954
955
956
	if (filter) {
		unsigned int pkt_len = sk_run_filter(skb, filter->insns,
				filter->len);
		err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM;
Linus Torvalds's avatar
Linus Torvalds committed
957
	}
958
959
 	rcu_read_unlock_bh();

Linus Torvalds's avatar
Linus Torvalds committed
960
961
962
	return err;
}

963
964
965
966
967
968
969
970
/**
 *	sk_filter_release: Release a socket filter
 *	@sk: socket
 *	@fp: filter to remove
 *
 *	Remove a filter from a socket and release its resources.
 */

971
972
973
static inline void sk_filter_release(struct sk_filter *fp)
{
	if (atomic_dec_and_test(&fp->refcnt))
974
		kfree(fp);
975
976
977
}

static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
Linus Torvalds's avatar
Linus Torvalds committed
978
979
980
981
{
	unsigned int size = sk_filter_len(fp);

	atomic_sub(size, &sk->sk_omem_alloc);
982
	sk_filter_release(fp);
Linus Torvalds's avatar
Linus Torvalds committed
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
}

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.