sock.h 45.2 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
#include <linux/list.h>
45
#include <linux/list_nulls.h>
Linus Torvalds's avatar
Linus Torvalds committed
46
47
48
#include <linux/timer.h>
#include <linux/cache.h>
#include <linux/module.h>
49
#include <linux/lockdep.h>
Linus Torvalds's avatar
Linus Torvalds committed
50
51
#include <linux/netdevice.h>
#include <linux/skbuff.h>	/* struct sk_buff */
Al Viro's avatar
Al Viro committed
52
#include <linux/mm.h>
Linus Torvalds's avatar
Linus Torvalds committed
53
54
55
#include <linux/security.h>

#include <linux/filter.h>
56
#include <linux/rculist_nulls.h>
57
#include <linux/poll.h>
Linus Torvalds's avatar
Linus Torvalds committed
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74

#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
75
76
77
78
79
/* 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
80
81
82
83
84
85
86
87
#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;
88
	int			owned;
Linus Torvalds's avatar
Linus Torvalds committed
89
	wait_queue_head_t	wq;
90
91
92
93
94
95
96
97
98
	/*
	 * 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
99
100
101
} socket_lock_t;

struct sock;
102
struct proto;
103
struct net;
Linus Torvalds's avatar
Linus Torvalds committed
104
105

/**
106
107
108
109
110
111
 *	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
112
 *	@skc_nulls_node: main hash linkage for UDP/UDP-Lite protocol
113
114
 *	@skc_bind_node: bind hash linkage for various protocol lookup tables
 *	@skc_refcnt: reference count
115
 *	@skc_hash: hash value used with various protocol lookup tables
116
 *	@skc_prot: protocol handlers inside a network family
117
 *	@skc_net: reference to the network namespace of this socket
118
119
 *
 *	This is the minimal network layer representation of sockets, the header
120
121
 *	for struct sock and struct inet_timewait_sock.
 */
Linus Torvalds's avatar
Linus Torvalds committed
122
123
124
125
126
struct sock_common {
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
127
128
129
130
	union {
		struct hlist_node	skc_node;
		struct hlist_nulls_node skc_nulls_node;
	};
Linus Torvalds's avatar
Linus Torvalds committed
131
132
	struct hlist_node	skc_bind_node;
	atomic_t		skc_refcnt;
133
	unsigned int		skc_hash;
134
	struct proto		*skc_prot;
135
#ifdef CONFIG_NET_NS
136
	struct net	 	*skc_net;
137
#endif
Linus Torvalds's avatar
Linus Torvalds committed
138
139
140
141
};

/**
  *	struct sock - network layer representation of sockets
142
  *	@__sk_common: shared layout with inet_timewait_sock
143
144
145
146
147
148
149
150
151
152
153
154
  *	@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
155
  *	@sk_async_wait_queue: DMA copied packets
156
157
158
159
160
  *	@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
161
  *	@sk_flags: %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE,
162
  *		   %SO_OOBINLINE settings, %SO_TIMESTAMPING settings
163
164
  *	@sk_no_check: %SO_NO_CHECK setting, wether or not checkup packets
  *	@sk_route_caps: route capabilities (e.g. %NETIF_F_TSO)
165
  *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)
166
  *	@sk_gso_max_size: Maximum GSO segment size to build
167
168
169
170
  *	@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
171
172
  *	@sk_prot_creator: sk_prot of original sock creator (see ipv6_setsockopt,
  *			  IPV6_ADDRFORM for instance)
173
  *	@sk_err: last error
Wang Chen's avatar
Wang Chen committed
174
175
  *	@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
176
  *	@sk_drops: raw/udp drops counter
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
  *	@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
195
  *	@sk_security: used by security modules
196
  *	@sk_mark: generic packet mark
197
198
199
200
201
202
203
  *	@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
204
205
206
 */
struct sock {
	/*
207
	 * Now struct inet_timewait_sock also uses sock_common, so please just
Linus Torvalds's avatar
Linus Torvalds committed
208
209
210
211
212
213
214
215
	 * 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
216
#define sk_nulls_node		__sk_common.skc_nulls_node
Linus Torvalds's avatar
Linus Torvalds committed
217
218
#define sk_bind_node		__sk_common.skc_bind_node
#define sk_refcnt		__sk_common.skc_refcnt
219
#define sk_hash			__sk_common.skc_hash
220
#define sk_prot			__sk_common.skc_prot
221
#define sk_net			__sk_common.skc_net
222
	kmemcheck_bitfield_begin(flags);
Linus Torvalds's avatar
Linus Torvalds committed
223
224
225
	unsigned char		sk_shutdown : 2,
				sk_no_check : 2,
				sk_userlocks : 4;
226
	kmemcheck_bitfield_end(flags);
Linus Torvalds's avatar
Linus Torvalds committed
227
228
229
230
	unsigned char		sk_protocol;
	unsigned short		sk_type;
	int			sk_rcvbuf;
	socket_lock_t		sk_lock;
231
232
233
234
235
236
237
238
239
	/*
	 * 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
240
241
	wait_queue_head_t	*sk_sleep;
	struct dst_entry	*sk_dst_cache;
242
#ifdef CONFIG_XFRM
Linus Torvalds's avatar
Linus Torvalds committed
243
	struct xfrm_policy	*sk_policy[2];
244
#endif
Linus Torvalds's avatar
Linus Torvalds committed
245
246
247
248
	rwlock_t		sk_dst_lock;
	atomic_t		sk_rmem_alloc;
	atomic_t		sk_wmem_alloc;
	atomic_t		sk_omem_alloc;
249
	int			sk_sndbuf;
Linus Torvalds's avatar
Linus Torvalds committed
250
251
	struct sk_buff_head	sk_receive_queue;
	struct sk_buff_head	sk_write_queue;
252
#ifdef CONFIG_NET_DMA
253
	struct sk_buff_head	sk_async_wait_queue;
254
#endif
Linus Torvalds's avatar
Linus Torvalds committed
255
256
	int			sk_wmem_queued;
	int			sk_forward_alloc;
Al Viro's avatar
Al Viro committed
257
	gfp_t			sk_allocation;
Linus Torvalds's avatar
Linus Torvalds committed
258
	int			sk_route_caps;
259
	int			sk_gso_type;
260
	unsigned int		sk_gso_max_size;
261
	int			sk_rcvlowat;
Linus Torvalds's avatar
Linus Torvalds committed
262
263
264
	unsigned long 		sk_flags;
	unsigned long	        sk_lingertime;
	struct sk_buff_head	sk_error_queue;
265
	struct proto		*sk_prot_creator;
Linus Torvalds's avatar
Linus Torvalds committed
266
267
268
	rwlock_t		sk_callback_lock;
	int			sk_err,
				sk_err_soft;
Wang Chen's avatar
Wang Chen committed
269
	atomic_t		sk_drops;
Linus Torvalds's avatar
Linus Torvalds committed
270
271
272
273
274
275
276
277
278
	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;
279
	ktime_t			sk_stamp;
Linus Torvalds's avatar
Linus Torvalds committed
280
281
282
283
284
285
	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;
Alexey Dobriyan's avatar
Alexey Dobriyan committed
286
#ifdef CONFIG_SECURITY
Linus Torvalds's avatar
Linus Torvalds committed
287
	void			*sk_security;
Alexey Dobriyan's avatar
Alexey Dobriyan committed
288
#endif
289
290
	__u32			sk_mark;
	/* XXX 4 bytes hole on 64 bit */
Linus Torvalds's avatar
Linus Torvalds committed
291
292
293
294
295
296
297
298
299
300
301
302
	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
 */
303
static inline struct sock *__sk_head(const struct hlist_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
304
305
306
307
{
	return hlist_entry(head->first, struct sock, sk_node);
}

308
static inline struct sock *sk_head(const struct hlist_head *head)
Linus Torvalds's avatar
Linus Torvalds committed
309
310
311
312
{
	return hlist_empty(head) ? NULL : __sk_head(head);
}

313
314
315
316
317
318
319
320
321
322
static inline struct sock *__sk_nulls_head(const struct hlist_nulls_head *head)
{
	return hlist_nulls_entry(head->first, struct sock, sk_nulls_node);
}

static inline struct sock *sk_nulls_head(const struct hlist_nulls_head *head)
{
	return hlist_nulls_empty(head) ? NULL : __sk_nulls_head(head);
}

323
static inline struct sock *sk_next(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
324
325
326
327
328
{
	return sk->sk_node.next ?
		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}

329
330
331
332
333
334
335
336
static inline struct sock *sk_nulls_next(const struct sock *sk)
{
	return (!is_a_nulls(sk->sk_nulls_node.next)) ?
		hlist_nulls_entry(sk->sk_nulls_node.next,
				  struct sock, sk_nulls_node) :
		NULL;
}

337
static inline int sk_unhashed(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
338
339
340
341
{
	return hlist_unhashed(&sk->sk_node);
}

342
static inline int sk_hashed(const struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
343
{
Akinobu Mita's avatar
Akinobu Mita committed
344
	return !sk_unhashed(sk);
Linus Torvalds's avatar
Linus Torvalds committed
345
346
347
348
349
350
351
}

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

352
353
354
355
356
static __inline__ void sk_nulls_node_init(struct hlist_nulls_node *node)
{
	node->pprev = NULL;
}

Linus Torvalds's avatar
Linus Torvalds committed
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
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;
}

403
static __inline__ int __sk_nulls_del_node_init_rcu(struct sock *sk)
404
405
{
	if (sk_hashed(sk)) {
406
		hlist_nulls_del_init_rcu(&sk->sk_nulls_node);
407
408
409
410
411
		return 1;
	}
	return 0;
}

412
static __inline__ int sk_nulls_del_node_init_rcu(struct sock *sk)
413
{
414
	int rc = __sk_nulls_del_node_init_rcu(sk);
415
416
417
418
419
420
421
422
423

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

Linus Torvalds's avatar
Linus Torvalds committed
424
425
426
427
428
429
430
431
432
433
434
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);
}

435
static __inline__ void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
436
{
437
	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
438
439
}

440
static __inline__ void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
441
442
{
	sock_hold(sk);
443
	__sk_nulls_add_node_rcu(sk, list);
444
445
}

Linus Torvalds's avatar
Linus Torvalds committed
446
447
448
449
450
451
452
453
454
455
456
457
458
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)
459
460
461
462
#define sk_nulls_for_each(__sk, node, list) \
	hlist_nulls_for_each_entry(__sk, node, list, sk_nulls_node)
#define sk_nulls_for_each_rcu(__sk, node, list) \
	hlist_nulls_for_each_entry_rcu(__sk, node, list, sk_nulls_node)
Linus Torvalds's avatar
Linus Torvalds committed
463
464
465
#define sk_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_node; 1; })) \
		hlist_for_each_entry_from(__sk, node, sk_node)
466
467
468
#define sk_nulls_for_each_from(__sk, node) \
	if (__sk && ({ node = &(__sk)->sk_nulls_node; 1; })) \
		hlist_nulls_for_each_entry_from(__sk, node, sk_nulls_node)
Linus Torvalds's avatar
Linus Torvalds committed
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
#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 */
491
	SOCK_RCVTSTAMPNS, /* %SO_TIMESTAMPNS setting */
Linus Torvalds's avatar
Linus Torvalds committed
492
493
	SOCK_LOCALROUTE, /* route locally only, %SO_DONTROUTE setting */
	SOCK_QUEUE_SHRUNK, /* write queue has been shrunk recently */
494
495
496
497
498
499
500
	SOCK_TIMESTAMPING_TX_HARDWARE,  /* %SOF_TIMESTAMPING_TX_HARDWARE */
	SOCK_TIMESTAMPING_TX_SOFTWARE,  /* %SOF_TIMESTAMPING_TX_SOFTWARE */
	SOCK_TIMESTAMPING_RX_HARDWARE,  /* %SOF_TIMESTAMPING_RX_HARDWARE */
	SOCK_TIMESTAMPING_RX_SOFTWARE,  /* %SOF_TIMESTAMPING_RX_SOFTWARE */
	SOCK_TIMESTAMPING_SOFTWARE,     /* %SOF_TIMESTAMPING_SOFTWARE */
	SOCK_TIMESTAMPING_RAW_HARDWARE, /* %SOF_TIMESTAMPING_RAW_HARDWARE */
	SOCK_TIMESTAMPING_SYS_HARDWARE, /* %SOF_TIMESTAMPING_SYS_HARDWARE */
Linus Torvalds's avatar
Linus Torvalds committed
501
502
};

Ralf Baechle's avatar
Ralf Baechle committed
503
504
505
506
507
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
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
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)
{
535
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
Linus Torvalds's avatar
Linus Torvalds committed
536
537
538
539
540
541
542
}

/*
 * Compute minimal free write space needed to queue new packets.
 */
static inline int sk_stream_min_wspace(struct sock *sk)
{
543
	return sk->sk_wmem_queued >> 1;
Linus Torvalds's avatar
Linus Torvalds committed
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
}

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. */
559
560
561
562
563
564
565
566
567
568
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
569

570
571
572
573
574
static inline int sk_backlog_rcv(struct sock *sk, struct sk_buff *skb)
{
	return sk->sk_backlog_rcv(sk, skb);
}

575
576
577
578
579
580
581
582
583
584
585
#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
586
587
588
589
590
591
592
593
594

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);

595
struct request_sock_ops;
596
struct timewait_sock_ops;
597
struct inet_hashinfo;
598
struct raw_hashinfo;
599

Linus Torvalds's avatar
Linus Torvalds committed
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
/* 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);
617
	void			(*destroy)(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
618
619
620
621
622
623
624
	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);  	 
625
#ifdef CONFIG_COMPAT
626
627
628
629
630
631
632
633
	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);
634
#endif
Linus Torvalds's avatar
Linus Torvalds committed
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
	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);

654
	/* Keeping track of sockets in use */
655
#ifdef CONFIG_PROC_FS
656
	unsigned int		inuse_idx;
657
#endif
658

Linus Torvalds's avatar
Linus Torvalds committed
659
	/* Memory pressure */
660
	void			(*enter_memory_pressure)(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
661
	atomic_t		*memory_allocated;	/* Current allocated memory. */
662
	struct percpu_counter	*sockets_allocated;	/* Current number of sockets. */
Linus Torvalds's avatar
Linus Torvalds committed
663
664
665
	/*
	 * Pressure flag: try to collapse.
	 * Technical note: it is used by multiple contexts non atomically.
666
	 * All the __sk_mem_schedule() is of this nature: accounting
Linus Torvalds's avatar
Linus Torvalds committed
667
668
669
670
671
672
673
674
	 * is strict, actions are advisory and have some latency.
	 */
	int			*memory_pressure;
	int			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
	int			max_header;

675
	struct kmem_cache	*slab;
Linus Torvalds's avatar
Linus Torvalds committed
676
	unsigned int		obj_size;
677
	int			slab_flags;
Linus Torvalds's avatar
Linus Torvalds committed
678

679
	struct percpu_counter	*orphan_count;
680

681
	struct request_sock_ops	*rsk_prot;
682
	struct timewait_sock_ops *twsk_prot;
683

684
685
	union {
		struct inet_hashinfo	*hashinfo;
686
		struct udp_table	*udp_table;
687
		struct raw_hashinfo	*raw_hash;
688
	} h;
689

Linus Torvalds's avatar
Linus Torvalds committed
690
691
692
693
694
	struct module		*owner;

	char			name[32];

	struct list_head	node;
695
696
697
#ifdef SOCK_REFCNT_DEBUG
	atomic_t		socks;
#endif
Linus Torvalds's avatar
Linus Torvalds committed
698
699
700
701
702
};

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

703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
#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 */

728
729

#ifdef CONFIG_PROC_FS
Linus Torvalds's avatar
Linus Torvalds committed
730
/* Called with local bh disabled */
731
732
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);
733
#else
734
735
static void inline sock_prot_inuse_add(struct net *net, struct proto *prot,
		int inc)
736
737
738
739
{
}
#endif

Linus Torvalds's avatar
Linus Torvalds committed
740

741
742
743
744
745
746
747
748
749
/* 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
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
/* 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;
}

803
804
805
806
807
/*
 * 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
808

809
810
811
812
#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
813

814
static inline int sk_mem_pages(int amt)
Linus Torvalds's avatar
Linus Torvalds committed
815
{
816
	return (amt + SK_MEM_QUANTUM - 1) >> SK_MEM_QUANTUM_SHIFT;
Linus Torvalds's avatar
Linus Torvalds committed
817
818
}

819
static inline int sk_has_account(struct sock *sk)
Linus Torvalds's avatar
Linus Torvalds committed
820
{
821
822
	/* return true if protocol supports memory accounting */
	return !!sk->sk_prot->memory_allocated;
Linus Torvalds's avatar
Linus Torvalds committed
823
824
}

825
static inline int sk_wmem_schedule(struct sock *sk, int size)
Linus Torvalds's avatar
Linus Torvalds committed
826
{
827
828
829
830
	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
831
832
}

833
static inline int sk_rmem_schedule(struct sock *sk, int size)
834
{
835
836
	if (!sk_has_account(sk))
		return 1;
837
	return size <= sk->sk_forward_alloc ||
838
839
840
841
842
843
844
845
846
847
848
		__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);
}

849
850
851
852
853
854
855
856
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);
}

857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
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)
{
	sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
	sk->sk_wmem_queued -= skb->truesize;
	sk_mem_uncharge(sk, skb->truesize);
	__kfree_skb(skb);
877
878
}

Linus Torvalds's avatar
Linus Torvalds committed
879
880
881
882
883
884
885
886
887
888
889
890
891
/* 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.
 */
892
#define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
Linus Torvalds's avatar
Linus Torvalds committed
893

894
895
896
897
898
899
900
901
902
/*
 * 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 {									\
903
	sk->sk_lock.owned = 0;						\
904
905
906
907
908
909
910
911
912
	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
913
extern void lock_sock_nested(struct sock *sk, int subclass);
914
915
916
917
918
919

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

Harvey Harrison's avatar
Harvey Harrison committed
920
extern void release_sock(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
921
922
923

/* BH context may only use the following locking interface. */
#define bh_lock_sock(__sk)	spin_lock(&((__sk)->sk_lock.slock))
924
925
926
#define bh_lock_sock_nested(__sk) \
				spin_lock_nested(&((__sk)->sk_lock.slock), \
				SINGLE_DEPTH_NESTING)
Linus Torvalds's avatar
Linus Torvalds committed
927
928
#define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))

929
extern struct sock		*sk_alloc(struct net *net, int family,
930
					  gfp_t priority,
931
					  struct proto *prot);
Linus Torvalds's avatar
Linus Torvalds committed
932
extern void			sk_free(struct sock *sk);
933
extern void			sk_release_kernel(struct sock *sk);
934
extern struct sock		*sk_clone(const struct sock *sk,
935
					  const gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
936
937
938

extern struct sk_buff		*sock_wmalloc(struct sock *sk,
					      unsigned long size, int force,
939
					      gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
940
941
extern struct sk_buff		*sock_rmalloc(struct sock *sk,
					      unsigned long size, int force,
942
					      gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
943
944
945
946
947
948
949
950
951
952
953
954
955
956
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);
957
958
959
960
961
extern struct sk_buff 		*sock_alloc_send_pskb(struct sock *sk,
						      unsigned long header_len,
						      unsigned long data_len,
						      int noblock,
						      int *errcode);
Victor Fusco's avatar
Victor Fusco committed
962
extern void *sock_kmalloc(struct sock *sk, int size,
963
			  gfp_t priority);
Linus Torvalds's avatar
Linus Torvalds committed
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
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
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);
1013
1014
1015
1016
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
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026

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);

1027
1028
1029
1030
1031
1032
1033
/**
 *	sk_filter_release: Release a socket filter
 *	@fp: filter to remove
 *
 *	Remove a filter from a socket and release its resources.
 */

1034
1035
1036
static inline void sk_filter_release(struct sk_filter *fp)
{
	if (atomic_dec_and_test(&fp->refcnt))
1037
		kfree(fp);
1038
1039
1040
}

static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
Linus Torvalds's avatar
Linus Torvalds committed
1041
1042
1043
1044
{
	unsigned int size = sk_filter_len(fp);

	atomic_sub(size, &sk->sk_omem_alloc);
1045
	sk_filter_release(fp);
Linus Torvalds's avatar
Linus Torvalds committed
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
}

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);
}

1086
1087
extern int sk_receive_skb(struct sock *sk, struct sk_buff *skb,
			  const int nested);
1088

1089
1090
1091
1092
1093
static inline void sk_set_socket(struct sock *sk, struct socket *sock)
{
	sk->sk_socket = sock;
}

Linus Torvalds's avatar
Linus Torvalds committed
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
/* 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)
{
	write_lock_bh(&sk->sk_callback_lock);
	sock_set_flag(sk, SOCK_DEAD);
1105
	sk_set_socket(sk, NULL);
Linus Torvalds's avatar
Linus Torvalds committed
1106
1107
1108
1109
1110
1111
1112
1113
1114
	sk->sk_sleep  = NULL;
	write_unlock_bh(&sk->sk_callback_lock);
}

static inline void sock_graft(struct sock *sk, struct socket *parent)
{
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_sleep = &parent->wait;
	parent->sk = sk;
1115
	sk_set_socket(sk, parent);
1116
	security_sock_graft(sk, parent);
Linus Torvalds's avatar
Linus Torvalds committed
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
	write_unlock_bh(&sk->sk_callback_lock);
}

extern int sock_i_uid(struct sock *sk);
extern unsigned long sock_i_ino(struct sock *sk);

static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
{
	return sk->sk_dst_cache;
}

static inline struct dst_entry *
sk_dst_get(struct sock *sk)
{
	struct dst_entry *dst;

	read_lock(&sk->sk_dst_lock);
	dst = sk->sk_dst_cache;
	if (dst)
		dst_hold(dst);
	read_unlock(&sk->sk_dst_lock);
	return dst;
}

static inline void
__sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
	struct dst_entry *old_dst;

	old_dst = sk->sk_dst_cache;
	sk->sk_dst_cache = dst;
	dst_release(old_dst);
}

static inline void
sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
	write_lock(&sk->sk_dst_lock);
	__sk_dst_set(sk, dst);
	write_unlock(&sk->sk_dst_lock);
}

static inline void
__sk_dst_reset(struct sock *sk)
{
	struct dst_entry *old_dst;

	old_dst = sk->sk_dst_cache;
	sk->sk_dst_cache = NULL;
	dst_release(old_dst);
}

static inline void
sk_dst_reset(struct sock *sk)
{
	write_lock(&sk->sk_dst_lock);
	__sk_dst_reset(sk);
	write_unlock(&sk->sk_dst_lock);
}

1178
extern struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie);
Linus Torvalds's avatar
Linus Torvalds committed
1179

1180
extern struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie);
Linus Torvalds's avatar
Linus Torvalds committed
1181

1182
1183
1184
1185
1186
static inline int sk_can_gso(const struct sock *sk)
{
	return net_gso_ok(sk->sk_route_caps, sk->sk_gso_type);
}

1187
extern void sk_setup_caps(struct sock *sk, struct dst_entry *dst);
1188

Linus Torvalds's avatar
Linus Torvalds committed
1189
1190
1191
1192
1193
1194
static inline int skb_copy_to_page(struct sock *sk, char __user *from,
				   struct sk_buff *skb, struct page *page,
				   int off, int copy)
{
	if (skb->ip_summed == CHECKSUM_NONE) {
		int err = 0;
1195
		__wsum csum = csum_and_copy_from_user(from,
Linus Torvalds's avatar
Linus Torvalds committed
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
						     page_address(page) + off,
							    copy, 0, &err);
		if (err)
			return err;
		skb->csum = csum_block_add(skb->csum, csum, skb->len);
	} else if (copy_from_user(page_address(page) + off, from, copy))
		return -EFAULT;

	skb->len	     += copy;
	skb->data_len	     += copy;
	skb->truesize	     += copy;
	sk->sk_wmem_queued   += copy;
1208
	sk_mem_charge(sk, copy);
Linus Torvalds's avatar
Linus Torvalds committed
1209
1210
1211
	return 0;
}

1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
/**
 * sk_wmem_alloc_get - returns write allocations
 * @sk: socket
 *
 * Returns sk_wmem_alloc minus initial offset of one
 */
static inline int sk_wmem_alloc_get(const struct sock *sk)
{
	return atomic_read(&sk->sk_wmem_alloc) - 1;
}

/**
 * sk_rmem_alloc_get - returns read allocations
 * @sk: socket
 *
 * Returns sk_rmem_alloc
 */
static inline int sk_rmem_alloc_get(const struct sock *sk)
{
	return atomic_read(&sk->sk_rmem_alloc);
}

/**
 * sk_has_allocations - check if allocations are outstanding
 * @sk: socket
 *
 * Returns true if socket has write or read allocations
 */
static inline int sk_has_allocations(const struct sock *sk)
{
	return sk_wmem_alloc_get(sk) || sk_rmem_alloc_get(sk);
}

1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
/**
 * sk_has_sleeper - check if there are any waiting processes
 * @sk: socket
 *
 * Returns true if socket has waiting processes
 *
 * The purpose of the sk_has_sleeper and sock_poll_wait is to wrap the memory
 * barrier call. They were added due to the race found within the tcp code.
 *
 * Consider following tcp code paths:
 *
 * CPU1                  CPU2
 *
 * sys_select            receive packet
 *   ...                 ...
 *   __add_wait_queue    update tp->rcv_nxt
 *   ...                 ...
 *   tp->rcv_nxt check   sock_def_readable
 *   ...                 {
 *   schedule               ...
 *                          if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
 *                              wake_up_interruptible(sk->sk_sleep)
 *                          ...
 *                       }
 *
 * The race for tcp fires when the __add_wait_queue changes done by CPU1 stay
 * in its cache, and so does the tp->rcv_nxt update on CPU2 side.  The CPU1
 * could then endup calling schedule and sleep forever if there are no more
 * data on the socket.
1274
1275
1276
 *
 * The sk_has_sleeper is always called right after a call to read_lock, so we
 * can use smp_mb__after_lock barrier.
1277
1278
1279
1280
1281
1282
1283
1284
1285
 */
static inline int sk_has_sleeper(struct sock *sk)
{
	/*
	 * We need to be sure we are in sync with the
	 * add_wait_queue modifications to the wait queue.
	 *
	 * This memory barrier is paired in the sock_poll_wait.
	 */
1286
	smp_mb__after_lock();
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
	return sk->sk_sleep && waitqueue_active(sk->sk_sleep);
}

/**
 * sock_poll_wait - place memory barrier behind the poll_wait call.
 * @filp:           file
 * @wait_address:   socket wait queue
 * @p:              poll_table
 *
 * See the comments in the sk_has_sleeper function.
 */
static inline void sock_poll_wait(struct file *filp,
		wait_queue_head_t *wait_address, poll_table *p)
{
	if (p && wait_address) {
		poll_wait(filp, wait_address, p);
		/*
		 * We need to be sure we are in sync with the
		 * socket flags modification.
		 *
		 * This memory barrier is paired in the sk_has_sleeper.
		*/
		smp_mb();
	}
}

Linus Torvalds's avatar
Linus Torvalds committed
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
/*
 * 	Queue a received datagram if it will fit. Stream and sequenced
 *	protocols can't normally use this as they need to fit buffers in
 *	and play with them.
 *
 * 	Inlined as it's very short and called for pretty much every
 *	packet ever received.
 */

static inline void skb_set_owner_w(struct sk_buff *skb, struct sock *sk)
{
1324
	skb_orphan(skb);
Linus Torvalds's avatar
Linus Torvalds committed
1325
1326
	skb->sk = sk;
	skb->destructor = sock_wfree;
1327
1328
1329
1330
1331
	/*
	 * We used to take a refcount on sk, but following operation
	 * is enough to guarantee sk_free() wont free this sock until
	 * all in-flight packets are completed
	 */
Linus Torvalds's avatar
Linus Torvalds committed
1332
1333
1334
1335
1336
	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
}

static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
1337
	skb_orphan(skb);
Linus Torvalds's avatar
Linus Torvalds committed
1338
1339
1340
	skb->sk = sk;
	skb->destructor = sock_rfree;
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
1341
	sk_mem_charge(sk, skb->truesize);
Linus Torvalds's avatar
Linus Torvalds committed
1342
1343
1344
1345
1346
1347
1348
}

extern void sk_reset_timer(struct sock *sk, struct timer_list* timer,
			   unsigned long expires);

extern void sk_stop_timer(struct sock *sk, struct timer_list* timer);

1349
extern int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
Linus Torvalds's avatar
Linus Torvalds committed
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371

static inline int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb)
{
	/* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
	   number of warnings when compiling with -W --ANK
	 */
	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
	    (unsigned)sk->sk_rcvbuf)
		return -ENOMEM;
	skb_set_owner_r(skb, sk);
	skb_queue_tail(&sk->sk_error_queue, skb);
	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_data_ready(sk, skb->len);
	return 0;
}

/*
 *	Recover an error report and clear atomically
 */
 
static inline int sock_error(struct sock *sk)
{
1372
1373
1374
1375
	int err;
	if (likely(!sk->sk_err))
		return 0;
	err = xchg(&sk->sk_err, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
	return -err;
}

static inline unsigned long sock_wspace(struct sock *sk)
{
	int amt = 0;

	if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
		amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
		if (amt < 0) 
			amt = 0;
	}
	return amt;
}

static inline void sk_wake_async(struct sock *sk, int how, int band)
{
	if (sk->sk_socket && sk->sk_socket->fasync_list)
		sock_wake_async(sk->sk_socket, how, band);
}

#define SOCK_MIN_SNDBUF 2048
#define SOCK_MIN_RCVBUF 256

static inline void sk_stream_moderate_sndbuf(struct sock *sk)
{
	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
1403
		sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1);
Linus Torvalds's avatar
Linus Torvalds committed
1404
1405
1406
1407
		sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF);
	}
}

1408
struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp);
Linus Torvalds's avatar
Linus Torvalds committed
1409
1410
1411
1412
1413

static inline struct page *sk_stream_alloc_page(struct sock *sk)
{
	struct page *page = NULL;

1414
1415
	page = alloc_pages(sk->sk_allocation, 0);
	if (!page) {
1416
		sk->sk_prot->enter_memory_pressure(sk);
Linus Torvalds's avatar
Linus Torvalds committed
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
		sk_stream_moderate_sndbuf(sk);
	}
	return page;
}

/*
 *	Default write policy as shown to user space via poll/select/SIGIO
 */
static inline int sock_writeable(const struct sock *sk) 
{
1427
	return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1);
Linus Torvalds's avatar
Linus Torvalds committed
1428
1429
}

1430
static inline gfp_t gfp_any(void)
Linus Torvalds's avatar
Linus Torvalds committed
1431
{
1432
	return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
Linus Torvalds's avatar
Linus Torvalds committed
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
}

static inline long sock_rcvtimeo(const struct sock *sk, int noblock)
{
	return noblock ? 0 : sk->sk_rcvtimeo;
}

static inline long sock_sndtimeo(const struct sock *sk, int noblock)
{
	return noblock ? 0 : sk->sk_sndtimeo;
}

static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
{
	return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
}

/* Alas, with timeout socket operations are not restartable.
 * Compare this to poll().
 */
static inline int sock_intr_errno(long timeo)
{
	return timeo == MAX_SCHEDULE_TIMEOUT ? -ERESTARTSYS : -EINTR;
}

1458
1459
1460
extern void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
	struct sk_buff *skb);

Linus Torvalds's avatar
Linus Torvalds committed
1461
1462
1463
static __inline__ void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
1464
	ktime_t kt = skb->tstamp;
1465
	struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
1466

1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
	/*
	 * generate control messages if
	 * - receive time stamping in software requested (SOCK_RCVTSTAMP
	 *   or SOCK_TIMESTAMPING_RX_SOFTWARE)
	 * - software time stamp available and wanted
	 *   (SOCK_TIMESTAMPING_SOFTWARE)
	 * - hardware time stamps available and wanted
	 *   (SOCK_TIMESTAMPING_SYS_HARDWARE or
	 *   SOCK_TIMESTAMPING_RAW_HARDWARE)
	 */
	if (sock_flag(sk, SOCK_RCVTSTAMP) ||
	    sock_flag(sk, SOCK_TIMESTAMPING_RX_SOFTWARE) ||
	    (kt.tv64 && sock_flag(sk, SOCK_TIMESTAMPING_SOFTWARE)) ||
	    (hwtstamps->hwtstamp.tv64 &&
	     sock_flag(sk, SOCK_TIMESTAMPING_RAW_HARDWARE)) ||
	    (hwtstamps->syststamp.tv64 &&
	     sock_flag(sk, SOCK_TIMESTAMPING_SYS_HARDWARE)))
1484
1485
		__sock_recv_timestamp(msg, sk, skb);
	else
1486
		sk->sk_stamp = kt;
Linus Torvalds's avatar
Linus Torvalds committed
1487
1488
}

1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
/**
 * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
 * @msg:	outgoing packet
 * @sk:		socket sending this packet
 * @shtx:	filled with instructions for time stamping
 *
 * Currently only depends on SOCK_TIMESTAMPING* flags. Returns error code if
 * parameters are invalid.
 */
extern int sock_tx_timestamp(struct msghdr *msg,
			     struct sock *sk,
			     union skb_shared_tx *shtx);


Linus Torvalds's avatar
Linus Torvalds committed
1503
1504
/**
 * sk_eat_skb - Release a skb if it is no longer needed
1505
1506
 * @sk: socket to eat this skb from
 * @skb: socket buffer to eat
Randy Dunlap's avatar
Randy Dunlap committed
1507
 * @copied_early: flag indicating whether DMA operations copied this data early
Linus Torvalds's avatar
Linus Torvalds committed
1508
1509
1510
1511
 *
 * This routine must be called with interrupts disabled or with the socket
 * locked so that the sk_buff queue operation is ok.
*/
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
#ifdef CONFIG_NET_DMA
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	if (!copied_early)
		__kfree_skb(skb);
	else
		__skb_queue_tail(&sk->sk_async_wait_queue, skb);
}
#else
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb, int copied_early)
Linus Torvalds's avatar
Linus Torvalds committed
1523
1524
1525
1526
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	__kfree_skb(skb);
}
1527
#endif
Linus Torvalds's avatar
Linus Torvalds committed
1528

1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
static inline
struct net *sock_net(const struct sock *sk)
{
#ifdef CONFIG_NET_NS
	return sk->sk_net;
#else
	return &init_net;
#endif
}

static inline
1540
void sock_net_set(struct sock *sk, struct net *net)
1541
1542
1543
1544
1545
1546
{
#ifdef CONFIG_NET_NS
	sk->sk_net = net;
#endif
}

1547
1548
1549
1550
1551
1552
1553
1554
/*
 * Kernel sockets, f.e. rtnl or icmp_socket, are a part of a namespace.
 * They should not hold a referrence to a namespace in order to allow
 * to stop it.
 * Sockets after sk_change_net should be released using sk_release_kernel
 */
static inline void sk_change_net(struct sock *sk, struct net *net)
{
1555
	put_net(sock_net(sk));
1556
	sock_net_set(sk, hold_net(net));
Denis V. Lunev's avatar