sock.h 38 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26
/*
 * 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
 *
 * Authors:	Ross Biro, <bir7@leland.Stanford.Edu>
 *		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
27 28 29 30 31
 *              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
32 33
 *              Pedro Hortas	:	New flags field for socket options
 *
Linus Torvalds's avatar
Linus Torvalds committed
34 35 36 37 38 39 40 41 42 43
 *
 *		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

#include <linux/config.h>
44
#include <linux/list.h>
Linus Torvalds's avatar
Linus Torvalds committed
45 46
#include <linux/timer.h>
#include <linux/cache.h>
47
#include <linux/module.h>
Linus Torvalds's avatar
Linus Torvalds committed
48 49
#include <linux/netdevice.h>
#include <linux/skbuff.h>	/* struct sk_buff */
50
#include <linux/security.h>
Linus Torvalds's avatar
Linus Torvalds committed
51 52 53 54 55

#include <linux/filter.h>

#include <asm/atomic.h>
#include <net/dst.h>
56
#include <net/checksum.h>
Linus Torvalds's avatar
Linus Torvalds committed
57 58 59 60 61 62 63

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

64
/* Define this to get the sk->sk_debug debugging facility. */
Linus Torvalds's avatar
Linus Torvalds committed
65 66
#define SOCK_DEBUGGING
#ifdef SOCK_DEBUGGING
67 68
#define SOCK_DEBUG(sk, msg...) do { if ((sk) && ((sk)->sk_debug)) \
					printk(KERN_DEBUG msg); } while (0)
Linus Torvalds's avatar
Linus Torvalds committed
69 70 71 72 73 74 75 76
#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.
 */
77
struct sock_iocb;
Linus Torvalds's avatar
Linus Torvalds committed
78 79
typedef struct {
	spinlock_t		slock;
80
	struct sock_iocb	*owner;
Linus Torvalds's avatar
Linus Torvalds committed
81 82 83 84
	wait_queue_head_t	wq;
} socket_lock_t;

#define sock_lock_init(__sk) \
85 86 87
do {	spin_lock_init(&((__sk)->sk_lock.slock)); \
	(__sk)->sk_lock.owner = NULL; \
	init_waitqueue_head(&((__sk)->sk_lock.wq)); \
88
} while(0)
Linus Torvalds's avatar
Linus Torvalds committed
89

90 91 92 93 94 95 96 97
struct sock;

/**
  *	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
98 99
  *	@skc_node - main hash linkage for various protocol lookup tables
  *	@skc_bind_node - bind hash linkage for various protocol lookup tables
100 101 102 103 104 105 106 107 108 109
  *	@skc_refcnt - reference count
  *
  *	This is the minimal network layer representation of sockets, the header
  *	for struct sock and struct tcp_tw_bucket.
  */
struct sock_common {
	unsigned short		skc_family;
	volatile unsigned char	skc_state;
	unsigned char		skc_reuse;
	int			skc_bound_dev_if;
110 111
	struct hlist_node	skc_node;
	struct hlist_node	skc_bind_node;
112 113 114
	atomic_t		skc_refcnt;
};

115 116
/**
  *	struct sock - network layer representation of sockets
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
  *	@__sk_common - shared layout with tcp_tw_bucket
  *	@sk_zapped - ax25 & ipx means !linked
  *	@sk_shutdown - mask of %SEND_SHUTDOWN and/or %RCV_SHUTDOWN
  *	@sk_use_write_queue - wheter to call sk->sk_write_space in sock_wfree
  *	@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
  *	@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
  *	@sk_flags - %SO_LINGER (l_onoff), %SO_BROADCAST, %SO_KEEPALIVE, %SO_OOBINLINE settings
  *	@sk_no_check - %SO_NO_CHECK setting, wether or not checkup packets
  *	@sk_debug - %SO_DEBUG setting
  *	@sk_rcvtstamp - %SO_TIMESTAMP setting
  *	@sk_no_largesend - whether to sent large segments or not
  *	@sk_route_caps - route capabilities (e.g. %NETIF_F_TSO)
  *	@sk_lingertime - %SO_LINGER l_linger setting
  *	@sk_hashent - hash entry in several tables (e.g. tcp_ehash)
  *	@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
  *	@sk_prot - protocol handlers inside a network family
  *	@sk_err - last error
  *	@sk_err_soft - errors that don't cause failure but are the cause of a persistent failure not just 'timed out'
  *	@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_localroute - route locally only, %SO_DONTROUTE setting
  *	@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_slab - the slabcache this instance was allocated from
  *	@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_owner - module that owns this socket
169 170
  *	@sk_sndmsg_page - cached page for sendmsg
  *	@sk_sndmsg_off - cached offset for sendmsg
171
  *	@sk_send_head - front of stuff to transmit
172
  *	@sk_write_pending - a write to stream socket waits to start
173
  *	@sk_queue_shrunk - write queue has been shrunk recently
174 175 176 177 178 179
  *	@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
180
 */
Linus Torvalds's avatar
Linus Torvalds committed
181
struct sock {
182 183 184 185 186 187 188 189 190
	/*
	 * Now struct tcp_tw_bucket also uses sock_common, so please just
	 * 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
191 192
#define sk_node			__sk_common.skc_node
#define sk_bind_node		__sk_common.skc_bind_node
193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220
#define sk_refcnt		__sk_common.skc_refcnt
	volatile unsigned char	sk_zapped;
	unsigned char		sk_shutdown;
	unsigned char		sk_use_write_queue;
	unsigned char		sk_userlocks;
	socket_lock_t		sk_lock;
	int			sk_rcvbuf;
	wait_queue_head_t	*sk_sleep;
	struct dst_entry	*sk_dst_cache;
	rwlock_t		sk_dst_lock;
	struct xfrm_policy	*sk_policy[2];
	atomic_t		sk_rmem_alloc;
	struct sk_buff_head	sk_receive_queue;
	atomic_t		sk_wmem_alloc;
	struct sk_buff_head	sk_write_queue;
	atomic_t		sk_omem_alloc;
	int			sk_wmem_queued;
	int			sk_forward_alloc;
	unsigned int		sk_allocation;
	int			sk_sndbuf;
	unsigned long 		sk_flags;
	char		 	sk_no_check;
	unsigned char		sk_debug;
	unsigned char		sk_rcvtstamp;
	unsigned char		sk_no_largesend;
	int			sk_route_caps;
	unsigned long	        sk_lingertime;
	int			sk_hashent;
221 222
	/*
	 * The backlog queue is special, it is always used with
Linus Torvalds's avatar
Linus Torvalds committed
223
	 * the per-socket spinlock held and requires low latency
224
	 * access. Therefore we special case it's implementation.
Linus Torvalds's avatar
Linus Torvalds committed
225 226 227 228
	 */
	struct {
		struct sk_buff *head;
		struct sk_buff *tail;
229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252
	} sk_backlog;
	rwlock_t		sk_callback_lock;
	struct sk_buff_head	sk_error_queue;
	struct proto		*sk_prot;
	int			sk_err,
				sk_err_soft;
	unsigned short		sk_ack_backlog;
	unsigned short		sk_max_ack_backlog;
	__u32			sk_priority;
	unsigned short		sk_type;
	unsigned char		sk_localroute;
	unsigned char		sk_protocol;
	struct ucred		sk_peercred;
	int			sk_rcvlowat;
	long			sk_rcvtimeo;
	long			sk_sndtimeo;
	struct sk_filter      	*sk_filter;
	void			*sk_protinfo;
	kmem_cache_t		*sk_slab;
	struct timer_list	sk_timer;
	struct timeval		sk_stamp;
	struct socket		*sk_socket;
	void			*sk_user_data;
	struct module		*sk_owner;
253 254 255
	struct page		*sk_sndmsg_page;
	__u32			sk_sndmsg_off;
	struct sk_buff		*sk_send_head;
256
	int			sk_write_pending;
257
	void			*sk_security;
258 259
	__u8			sk_queue_shrunk;
	/* three bytes hole, try to pack */
260 261 262 263 264 265 266
	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);
Linus Torvalds's avatar
Linus Torvalds committed
267 268
};

269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302
/*
 * Hashed lists helper routines
 */
static inline struct sock *__sk_head(struct hlist_head *head)
{
	return hlist_entry(head->first, struct sock, sk_node);
}

static inline struct sock *sk_head(struct hlist_head *head)
{
	return hlist_empty(head) ? NULL : __sk_head(head);
}

static inline struct sock *sk_next(struct sock *sk)
{
	return sk->sk_node.next ?
		hlist_entry(sk->sk_node.next, struct sock, sk_node) : NULL;
}

static inline int sk_unhashed(struct sock *sk)
{
	return hlist_unhashed(&sk->sk_node);
}

static inline int sk_hashed(struct sock *sk)
{
	return sk->sk_node.pprev != NULL;
}

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

303 304 305 306 307 308
static __inline__ void __sk_del_node(struct sock *sk)
{
	__hlist_del(&sk->sk_node);
}

static __inline__ int __sk_del_node_init(struct sock *sk)
309 310
{
	if (sk_hashed(sk)) {
311
		__sk_del_node(sk);
312 313 314 315 316 317
		sk_node_init(&sk->sk_node);
		return 1;
	}
	return 0;
}

318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335
/* 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);
}
336 337 338 339 340 341 342 343 344 345 346 347 348 349

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)
350 351 352 353
{
	hlist_add_head(&sk->sk_node, list);
}

354 355 356 357 358 359 360 361 362 363 364
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);
}

365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383
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)

384 385 386 387 388 389 390 391 392
/* Sock flags */
enum sock_flags {
	SOCK_DEAD,
	SOCK_DONE,
	SOCK_URGINLINE,
	SOCK_KEEPOPEN,
	SOCK_LINGER,
	SOCK_DESTROY,
	SOCK_BROADCAST,
393
	SOCK_TIMESTAMP,
394 395 396 397
};

static inline void sock_set_flag(struct sock *sk, enum sock_flags flag)
{
398
	__set_bit(flag, &sk->sk_flags);
399 400 401 402
}

static inline void sock_reset_flag(struct sock *sk, enum sock_flags flag)
{
403
	__clear_bit(flag, &sk->sk_flags);
404 405 406 407
}

static inline int sock_flag(struct sock *sk, enum sock_flags flag)
{
408
	return test_bit(flag, &sk->sk_flags);
409 410
}

411 412 413 414 415 416 417 418 419 420 421 422 423 424 425
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)
{
	return sk->sk_ack_backlog > sk->sk_max_ack_backlog;
}

426 427 428 429 430 431 432 433 434 435 436 437 438 439 440
/*
 * 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);

441 442 443 444 445
static inline int sk_stream_memory_free(struct sock *sk)
{
	return sk->sk_wmem_queued < sk->sk_sndbuf;
}

446 447 448 449 450 451 452 453 454 455
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;
}

456 457 458 459 460 461 462 463
static inline void sk_stream_free_skb(struct sock *sk, struct sk_buff *skb)
{
	sk->sk_queue_shrunk   = 1;
	sk->sk_wmem_queued   -= skb->truesize;
	sk->sk_forward_alloc += skb->truesize;
	__kfree_skb(skb);
}

Linus Torvalds's avatar
Linus Torvalds committed
464
/* The per-socket spinlock must be held here. */
465 466 467 468 469 470 471 472 473
#define sk_add_backlog(__sk, __skb)				\
do {	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
474 475
} while(0)

476 477 478 479 480 481 482 483 484 485 486 487
#define sk_wait_event(__sk, __timeo, __condition)		\
({	int rc;							\
	release_sock(__sk);					\
	rc = __condition;					\
	if (!rc) {						\
		*(__timeo) = schedule_timeout(*(__timeo));	\
		rc = __condition;				\
	}							\
	lock_sock(__sk);					\
	rc;							\
})

488
extern int sk_stream_wait_connect(struct sock *sk, long *timeo_p);
489
extern int sk_stream_wait_memory(struct sock *sk, long *timeo_p);
490
extern void sk_stream_wait_close(struct sock *sk, long timeo_p);
491
extern int sk_stream_error(struct sock *sk, int flags, int err);
492
extern void sk_stream_kill_queues(struct sock *sk);
493

494 495
extern int sk_wait_data(struct sock *sk, long *timeo);

496
/* Networking protocol blocks we attach to sockets.
Linus Torvalds's avatar
Linus Torvalds committed
497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515
 * 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, 
516 517
					int optname, char __user *optval,
					int optlen);
Linus Torvalds's avatar
Linus Torvalds committed
518
	int			(*getsockopt)(struct sock *sk, int level, 
519 520
					int optname, char __user *optval, 
					int __user *option);  	 
Benjamin LaHaise's avatar
Benjamin LaHaise committed
521
	int			(*sendmsg)(struct kiocb *iocb, struct sock *sk,
522
					   struct msghdr *msg, size_t len);
Benjamin LaHaise's avatar
Benjamin LaHaise committed
523 524
	int			(*recvmsg)(struct kiocb *iocb, struct sock *sk,
					   struct msghdr *msg,
525
					size_t len, int noblock, int flags, 
Linus Torvalds's avatar
Linus Torvalds committed
526
					int *addr_len);
527 528
	int			(*sendpage)(struct sock *sk, struct page *page,
					int offset, size_t size, int flags);
Linus Torvalds's avatar
Linus Torvalds committed
529 530 531 532 533 534 535 536 537 538 539
	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);

540 541
	/* Memory pressure */
	void			(*enter_memory_pressure)(void);
542 543
	atomic_t		*memory_allocated;	/* Current allocated memory. */
	atomic_t		*sockets_allocated;	/* Current number of sockets. */
544 545 546 547 548 549
	/*
	 * 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.
	 */
550 551 552 553
	int			*memory_pressure;
	int			*sysctl_mem;
	int			*sysctl_wmem;
	int			*sysctl_rmem;
554
	int			max_header;
555

556 557 558
	kmem_cache_t		*slab;
	int			slab_obj_size;

Linus Torvalds's avatar
Linus Torvalds committed
559 560 561 562 563 564 565 566
	char			name[32];

	struct {
		int inuse;
		u8  __pad[SMP_CACHE_BYTES - sizeof(int)];
	} stats[NR_CPUS];
};

567 568 569 570 571 572 573 574
extern int sk_alloc_slab(struct proto *prot, char *name);
extern void sk_free_slab(struct proto *prot);

static inline void sk_alloc_slab_error(struct proto *proto)
{
	printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n", proto->name);
}

575 576 577 578 579 580 581 582 583 584 585
static __inline__ void sk_set_owner(struct sock *sk, struct module *owner)
{
	/*
	 * One should use sk_set_owner just once, after struct sock creation,
	 * be it shortly after sk_alloc or after a function that returns a new
	 * struct sock (and that down the call chain called sk_alloc), e.g. the
	 * IPv4 and IPv6 modules share tcp_create_openreq_child, so if
	 * tcp_create_openreq_child called sk_set_owner IPv6 would have to
	 * change the ownership of this struct sock, with one not needed
	 * transient sk_set_owner call.
	 */
586 587
	BUG_ON(sk->sk_owner != NULL);

588
	sk->sk_owner = owner;
589 590 591
	__module_get(owner);
}

Linus Torvalds's avatar
Linus Torvalds committed
592
/* Called with local bh disabled */
Linus Torvalds's avatar
Linus Torvalds committed
593
static __inline__ void sock_prot_inc_use(struct proto *prot)
Linus Torvalds's avatar
Linus Torvalds committed
594 595 596 597
{
	prot->stats[smp_processor_id()].inuse++;
}

Linus Torvalds's avatar
Linus Torvalds committed
598
static __inline__ void sock_prot_dec_use(struct proto *prot)
Linus Torvalds's avatar
Linus Torvalds committed
599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617
{
	prot->stats[smp_processor_id()].inuse--;
}

/* 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

Benjamin LaHaise's avatar
Benjamin LaHaise committed
618 619 620 621 622 623 624 625
/* 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;
626
	struct scm_cookie	*scm;
Benjamin LaHaise's avatar
Benjamin LaHaise committed
627 628
	struct msghdr		*msg, async_msg;
	struct iovec		async_iov;
629
	struct kiocb		*kiocb;
Benjamin LaHaise's avatar
Benjamin LaHaise committed
630 631 632 633 634 635 636 637 638
};

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)
{
639
	return si->kiocb;
Benjamin LaHaise's avatar
Benjamin LaHaise committed
640
}
Linus Torvalds's avatar
Linus Torvalds committed
641

642 643 644 645 646 647 648 649 650 651 652 653 654 655 656
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;
}

657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672
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)
{
	return (amt + SK_STREAM_MEM_QUANTUM - 1) / SK_STREAM_MEM_QUANTUM;
}

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

673 674 675 676 677 678 679 680 681 682 683 684 685 686 687
static inline void sk_stream_writequeue_purge(struct sock *sk)
{
	struct sk_buff *skb;

	while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
		sk_stream_free_skb(sk, skb);
	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);
}

Linus Torvalds's avatar
Linus Torvalds committed
688 689 690 691 692 693 694 695 696 697 698 699 700 701 702
/* 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.
 */
extern void __lock_sock(struct sock *sk);
extern void __release_sock(struct sock *sk);
703
#define sock_owned_by_user(sk)	((sk)->sk_lock.owner)
Linus Torvalds's avatar
Linus Torvalds committed
704

705 706
extern void FASTCALL(lock_sock(struct sock *sk));
extern void FASTCALL(release_sock(struct sock *sk));
Linus Torvalds's avatar
Linus Torvalds committed
707 708

/* BH context may only use the following locking interface. */
709 710
#define bh_lock_sock(__sk)	spin_lock(&((__sk)->sk_lock.slock))
#define bh_unlock_sock(__sk)	spin_unlock(&((__sk)->sk_lock.slock))
Linus Torvalds's avatar
Linus Torvalds committed
711

712 713
extern struct sock *		sk_alloc(int family, int priority, int zero_it,
					 kmem_cache_t *slab);
Linus Torvalds's avatar
Linus Torvalds committed
714 715 716 717 718 719 720 721 722 723 724 725
extern void			sk_free(struct sock *sk);

extern struct sk_buff		*sock_wmalloc(struct sock *sk,
					      unsigned long size, int force,
					      int priority);
extern struct sk_buff		*sock_rmalloc(struct sock *sk,
					      unsigned long size, int force,
					      int priority);
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,
726
						int op, char __user *optval,
Linus Torvalds's avatar
Linus Torvalds committed
727 728 729
						int optlen);

extern int			sock_getsockopt(struct socket *sock, int level,
730 731
						int op, char __user *optval, 
						int __user *optlen);
Linus Torvalds's avatar
Linus Torvalds committed
732 733 734 735
extern struct sk_buff 		*sock_alloc_send_skb(struct sock *sk,
						     unsigned long size,
						     int noblock,
						     int *errcode);
Linus Torvalds's avatar
Linus Torvalds committed
736 737 738 739 740
extern struct sk_buff 		*sock_alloc_send_pskb(struct sock *sk,
						      unsigned long header_len,
						      unsigned long data_len,
						      int noblock,
						      int *errcode);
Linus Torvalds's avatar
Linus Torvalds committed
741 742
extern void *sock_kmalloc(struct sock *sk, int size, int priority);
extern void sock_kfree_s(struct sock *sk, void *mem, int size);
743
extern void sk_send_sigurg(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766

/*
 * Functions to fill in entries in struct proto_ops when a protocol
 * does not implement a particular function.
 */
extern int                      sock_no_release(struct socket *);
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,
767
						   char __user *, int __user *);
Linus Torvalds's avatar
Linus Torvalds committed
768
extern int			sock_no_setsockopt(struct socket *, int, int,
769
						   char __user *, int);
Benjamin LaHaise's avatar
Benjamin LaHaise committed
770
extern int                      sock_no_sendmsg(struct kiocb *, struct socket *,
771
						struct msghdr *, size_t);
Benjamin LaHaise's avatar
Benjamin LaHaise committed
772
extern int                      sock_no_recvmsg(struct kiocb *, struct socket *,
773
						struct msghdr *, size_t, int);
Linus Torvalds's avatar
Linus Torvalds committed
774 775 776
extern int			sock_no_mmap(struct file *file,
					     struct socket *sock,
					     struct vm_area_struct *vma);
Linus Torvalds's avatar
Linus Torvalds committed
777 778 779 780
extern ssize_t			sock_no_sendpage(struct socket *sock,
						struct page *page,
						int offset, size_t size, 
						int flags);
Linus Torvalds's avatar
Linus Torvalds committed
781

782 783 784 785 786 787 788 789 790 791 792 793 794
/*
 * 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);

extern void sk_common_release(struct sock *sk);

Linus Torvalds's avatar
Linus Torvalds committed
795 796 797 798 799 800 801 802 803 804
/*
 *	Default socket callbacks and setup code
 */
 
extern void sock_def_destruct(struct sock *);

/* Initialise core socket variables */
extern void sock_init_data(struct socket *sock, struct sock *sk);

/**
Chris Wright's avatar
Chris Wright committed
805
 *	sk_filter - run a packet through a socket filter
806
 *	@sk: sock associated with &sk_buff
Linus Torvalds's avatar
Linus Torvalds committed
807
 *	@skb: buffer to filter
808
 *	@needlock: set to 1 if the sock is not locked by caller.
Linus Torvalds's avatar
Linus Torvalds committed
809 810 811 812 813
 *
 * 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
814 815
 * be accepted or -EPERM if the packet should be tossed.
 *
Linus Torvalds's avatar
Linus Torvalds committed
816 817
 */

Chris Wright's avatar
Chris Wright committed
818
static inline int sk_filter(struct sock *sk, struct sk_buff *skb, int needlock)
819
{
Chris Wright's avatar
Chris Wright committed
820 821 822 823 824 825
	int err;
	
	err = security_sock_rcv_skb(sk, skb);
	if (err)
		return err;
	
826
	if (sk->sk_filter) {
827 828 829 830 831
		struct sk_filter *filter;
		
		if (needlock)
			bh_lock_sock(sk);
		
832
		filter = sk->sk_filter;
833 834 835 836 837 838 839 840 841 842 843 844 845
		if (filter) {
			int pkt_len = sk_run_filter(skb, filter->insns,
						    filter->len);
			if (!pkt_len)
				err = -EPERM;
			else
				skb_trim(skb, pkt_len);
		}

		if (needlock)
			bh_unlock_sock(sk);
	}
	return err;
Linus Torvalds's avatar
Linus Torvalds committed
846 847 848 849 850 851 852 853 854 855 856 857 858 859
}

/**
 *	sk_filter_release: Release a socket filter
 *	@sk: socket
 *	@fp: filter to remove
 *
 *	Remove a filter from a socket and release its resources.
 */
 
static inline void sk_filter_release(struct sock *sk, struct sk_filter *fp)
{
	unsigned int size = sk_filter_len(fp);

860
	atomic_sub(size, &sk->sk_omem_alloc);
Linus Torvalds's avatar
Linus Torvalds committed
861 862 863 864 865 866 867 868

	if (atomic_dec_and_test(&fp->refcnt))
		kfree(fp);
}

static inline void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
	atomic_inc(&fp->refcnt);
869
	atomic_add(sk_filter_len(fp), &sk->sk_omem_alloc);
Linus Torvalds's avatar
Linus Torvalds committed
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
}

/*
 * 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)
{
900
	if (atomic_dec_and_test(&sk->sk_refcnt))
Linus Torvalds's avatar
Linus Torvalds committed
901 902 903 904 905 906 907 908 909 910 911 912
		sk_free(sk);
}

/* 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)
{
913
	write_lock_bh(&sk->sk_callback_lock);
914
	sock_set_flag(sk, SOCK_DEAD);
915 916 917
	sk->sk_socket = NULL;
	sk->sk_sleep  = NULL;
	write_unlock_bh(&sk->sk_callback_lock);
Linus Torvalds's avatar
Linus Torvalds committed
918 919 920 921
}

static inline void sock_graft(struct sock *sk, struct socket *parent)
{
922 923
	write_lock_bh(&sk->sk_callback_lock);
	sk->sk_sleep = &parent->wait;
Linus Torvalds's avatar
Linus Torvalds committed
924
	parent->sk = sk;
925 926
	sk->sk_socket = parent;
	write_unlock_bh(&sk->sk_callback_lock);
Linus Torvalds's avatar
Linus Torvalds committed
927 928
}

929 930
extern int sock_i_uid(struct sock *sk);
extern unsigned long sock_i_ino(struct sock *sk);
Linus Torvalds's avatar
Linus Torvalds committed
931 932 933 934

static inline struct dst_entry *
__sk_dst_get(struct sock *sk)
{
935
	return sk->sk_dst_cache;
Linus Torvalds's avatar
Linus Torvalds committed
936 937 938 939 940 941 942
}

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

943 944
	read_lock(&sk->sk_dst_lock);
	dst = sk->sk_dst_cache;
Linus Torvalds's avatar
Linus Torvalds committed
945 946
	if (dst)
		dst_hold(dst);
947
	read_unlock(&sk->sk_dst_lock);
Linus Torvalds's avatar
Linus Torvalds committed
948 949 950 951 952 953 954 955
	return dst;
}

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

956 957
	old_dst = sk->sk_dst_cache;
	sk->sk_dst_cache = dst;
Linus Torvalds's avatar
Linus Torvalds committed
958 959 960 961 962 963
	dst_release(old_dst);
}

static inline void
sk_dst_set(struct sock *sk, struct dst_entry *dst)
{
964
	write_lock(&sk->sk_dst_lock);
Linus Torvalds's avatar
Linus Torvalds committed
965
	__sk_dst_set(sk, dst);
966
	write_unlock(&sk->sk_dst_lock);
Linus Torvalds's avatar
Linus Torvalds committed
967 968 969 970 971 972 973
}

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

974 975
	old_dst = sk->sk_dst_cache;
	sk->sk_dst_cache = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
976 977 978 979 980 981
	dst_release(old_dst);
}

static inline void
sk_dst_reset(struct sock *sk)
{
982
	write_lock(&sk->sk_dst_lock);
Linus Torvalds's avatar
Linus Torvalds committed
983
	__sk_dst_reset(sk);
984
	write_unlock(&sk->sk_dst_lock);
Linus Torvalds's avatar
Linus Torvalds committed
985 986 987 988 989
}

static inline struct dst_entry *
__sk_dst_check(struct sock *sk, u32 cookie)
{
990
	struct dst_entry *dst = sk->sk_dst_cache;
Linus Torvalds's avatar
Linus Torvalds committed
991 992

	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
993
		sk->sk_dst_cache = NULL;
Linus Torvalds's avatar
Linus Torvalds committed
994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012
		return NULL;
	}

	return dst;
}

static inline struct dst_entry *
sk_dst_check(struct sock *sk, u32 cookie)
{
	struct dst_entry *dst = sk_dst_get(sk);

	if (dst && dst->obsolete && dst->ops->check(dst, cookie) == NULL) {
		sk_dst_reset(sk);
		return NULL;
	}

	return dst;
}

1013 1014 1015 1016 1017
static inline void sk_charge_skb(struct sock *sk, struct sk_buff *skb)
{
	sk->sk_wmem_queued   += skb->truesize;
	sk->sk_forward_alloc -= skb->truesize;
}
Linus Torvalds's avatar
Linus Torvalds committed
1018

1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041
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;
		unsigned int csum = csum_and_copy_from_user(from,
						     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;
	sk->sk_forward_alloc -= copy;
	return 0;
}

Linus Torvalds's avatar
Linus Torvalds committed
1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055
/*
 * 	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)
{
	sock_hold(sk);
	skb->sk = sk;
	skb->destructor = sock_wfree;
1056
	atomic_add(skb->truesize, &sk->sk_wmem_alloc);
Linus Torvalds's avatar
Linus Torvalds committed
1057 1058 1059 1060 1061 1062
}

static inline void skb_set_owner_r(struct sk_buff *skb, struct sock *sk)
{
	skb->sk = sk;
	skb->destructor = sock_rfree;
1063
	atomic_add(skb->truesize, &sk->sk_rmem_alloc);
Linus Torvalds's avatar
Linus Torvalds committed
1064 1065
}

1066 1067 1068 1069 1070
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);

Linus Torvalds's avatar
Linus Torvalds committed
1071 1072
static inline int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
1073
	int err = 0;
1074
	int skb_len;
1075

Linus Torvalds's avatar
Linus Torvalds committed
1076 1077 1078
	/* Cast skb->rcvbuf to unsigned... It's pointless, but reduces
	   number of warnings when compiling with -W --ANK
	 */
1079 1080
	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
	    (unsigned)sk->sk_rcvbuf) {
1081 1082
		err = -ENOMEM;
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed
1083
	}
1084 1085 1086 1087 1088 1089 1090 1091

	/* It would be deadlock, if sock_queue_rcv_skb is used
	   with socket lock! We assume that users of this
	   function are lock free.
	*/
	err = sk_filter(sk, skb, 1);
	if (err)
		goto out;
Linus Torvalds's avatar
Linus Torvalds committed
1092 1093 1094

	skb->dev = NULL;
	skb_set_owner_r(skb, sk);
1095 1096 1097 1098 1099 1100 1101 1102

	/* Cache the SKB length before we tack it onto the receive
	 * queue.  Once it is added it no longer belongs to us and
	 * may be freed by other threads of control pulling packets
	 * from the queue.
	 */
	skb_len = skb->len;

1103
	skb_queue_tail(&sk->sk_receive_queue, skb);
1104

1105
	if (!sock_flag(sk, SOCK_DEAD))
1106
		sk->sk_data_ready(sk, skb_len);
1107 1108
out:
	return err;
Linus Torvalds's avatar
Linus Torvalds committed
1109 1110 1111 1112 1113 1114 1115
}

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
	 */
1116 1117
	if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >=
	    (unsigned)sk->sk_rcvbuf)
Linus Torvalds's avatar
Linus Torvalds committed
1118 1119
		return -ENOMEM;
	skb_set_owner_r(skb, sk);
1120
	skb_queue_tail(&sk->sk_error_queue, skb);
1121
	if (!sock_flag(sk, SOCK_DEAD))
1122
		sk->sk_data_ready(sk, skb->len);
Linus Torvalds's avatar
Linus Torvalds committed
1123 1124 1125 1126 1127 1128 1129 1130 1131
	return 0;
}

/*
 *	Recover an error report and clear atomically
 */
 
static inline int sock_error(struct sock *sk)
{
1132
	int err = xchg(&sk->sk_err, 0);
Linus Torvalds's avatar
Linus Torvalds committed
1133 1134 1135 1136 1137 1138 1139
	return -err;
}

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

1140 1141
	if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {
		amt = sk->sk_sndbuf - atomic_read(&sk->sk_wmem_alloc);
Linus Torvalds's avatar
Linus Torvalds committed
1142 1143 1144 1145 1146 1147 1148 1149
		if (amt < 0) 
			amt = 0;
	}
	return amt;
}

static inline void sk_wake_async(struct sock *sk, int how, int band)
{
1150 1151
	if (sk->sk_socket && sk->sk_socket->fasync_list)
		sock_wake_async(sk->sk_socket, how, band);
Linus Torvalds's avatar
Linus Torvalds committed
1152 1153 1154 1155 1156
}

#define SOCK_MIN_SNDBUF 2048
#define SOCK_MIN_RCVBUF 256

1157 1158 1159 1160 1161 1162 1163 1164
static inline void sk_stream_moderate_sndbuf(struct sock *sk)
{
	if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) {
		sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued / 2);
		sk->sk_sndbuf = max(sk->sk_sndbuf, SOCK_MIN_SNDBUF);
	}
}

1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204
static inline struct sk_buff *sk_stream_alloc_pskb(struct sock *sk,
						   int size, int mem, int gfp)
{
	struct sk_buff *skb = alloc_skb(size + sk->sk_prot->max_header, gfp);

	if (skb) {
		skb->truesize += mem;
		if (sk->sk_forward_alloc >= (int)skb->truesize ||
		    sk_stream_mem_schedule(sk, skb->truesize, 0)) {
			skb_reserve(skb, sk->sk_prot->max_header);
			return skb;
		}
		__kfree_skb(skb);
	} else {
		sk->sk_prot->enter_memory_pressure();
		sk_stream_moderate_sndbuf(sk);
	}
	return NULL;
}

static inline struct sk_buff *sk_stream_alloc_skb(struct sock *sk,
						  int size, int gfp)
{
	return sk_stream_alloc_pskb(sk, size, 0, gfp);
}

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

	if (sk->sk_forward_alloc >= (int)PAGE_SIZE ||
	    sk_stream_mem_schedule(sk, PAGE_SIZE, 0))
		page = alloc_pages(sk->sk_allocation, 0);
	else {
		sk->sk_prot->enter_memory_pressure();
		sk_stream_moderate_sndbuf(sk);
	}
	return page;
}

1205 1206 1207 1208 1209 1210
#define sk_stream_for_retrans_queue(skb, sk)				\
		for (skb = (sk)->sk_write_queue.next;			\
		     (skb != (sk)->sk_send_head) &&			\
		     (skb != (struct sk_buff *)&(sk)->sk_write_queue);	\
		     skb = skb->next)

Linus Torvalds's avatar
Linus Torvalds committed
1211 1212 1213
/*
 *	Default write policy as shown to user space via poll/select/SIGIO
 */
1214
static inline int sock_writeable(const struct sock *sk) 
Linus Torvalds's avatar
Linus Torvalds committed
1215
{
1216
	return atomic_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf / 2);
Linus Torvalds's avatar
Linus Torvalds committed
1217 1218 1219 1220 1221 1222 1223
}

static inline int gfp_any(void)
{
	return in_softirq() ? GFP_ATOMIC : GFP_KERNEL;
}

1224
static inline long sock_rcvtimeo(const struct sock *sk, int noblock)
Linus Torvalds's avatar
Linus Torvalds committed
1225
{
1226
	return noblock ? 0 : sk->sk_rcvtimeo;
Linus Torvalds's avatar
Linus Torvalds committed
1227 1228
}

1229
static inline long sock_sndtimeo(const struct sock *sk, int noblock)
Linus Torvalds's avatar
Linus Torvalds committed
1230
{
1231
	return noblock ? 0 : sk->sk_sndtimeo;
Linus Torvalds's avatar
Linus Torvalds committed
1232 1233
}

1234
static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len)
Linus Torvalds's avatar
Linus Torvalds committed
1235
{
1236
	return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1;
Linus Torvalds's avatar
Linus Torvalds committed
1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249
}

/* 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;
}

static __inline__ void
sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
{
1250 1251 1252 1253 1254 1255 1256 1257 1258 1259
	struct timeval *stamp = &skb->stamp;
	if (sk->sk_rcvtstamp) { 
		/* Race occurred between timestamp enabling and packet
		   receiving.  Fill in the current time for now. */
		if (stamp->tv_sec == 0)
			do_gettimeofday(stamp);
		put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP, sizeof(struct timeval),
			 stamp);
	} else
		sk->sk_stamp = *stamp;
Linus Torvalds's avatar
Linus Torvalds committed
1260 1261
}

1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275
/**
 * sk_eat_skb - Release a skb if it is no longer needed
 * @sk - socket to eat this skb from
 * @skb - socket buffer to eat
 *
 * This routine must be called with interrupts disabled or with the socket
 * locked so that the sk_buff queue operation is ok.
*/
static inline void sk_eat_skb(struct sock *sk, struct sk_buff *skb)
{
	__skb_unlink(skb, &sk->sk_receive_queue);
	__kfree_skb(skb);
}

1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289
extern atomic_t netstamp_needed;
extern void sock_enable_timestamp(struct sock *sk);
extern void sock_disable_timestamp(struct sock *sk);

static inline void net_timestamp(struct timeval *stamp) 
{ 
	if (atomic_read(&netstamp_needed)) 
		do_gettimeofday(stamp);
	else {
		stamp->tv_sec = 0;
		stamp->tv_usec = 0;
	}		
} 

1290
extern int sock_get_timestamp(struct sock *, struct timeval __user *);
1291

Linus Torvalds's avatar
Linus Torvalds committed
1292 1293 1294 1295 1296 1297
/* 
 *	Enable debug/info messages 
 */

#if 0
#define NETDEBUG(x)	do { } while (0)
1298
#define LIMIT_NETDEBUG(x) do {} while(0)
Linus Torvalds's avatar
Linus Torvalds committed
1299 1300
#else
#define NETDEBUG(x)	do { x; } while (0)
1301
#define LIMIT_NETDEBUG(x) do { if (net_ratelimit()) { x; } } while(0)
Linus Torvalds's avatar
Linus Torvalds committed
1302 1303 1304 1305 1306 1307 1308 1309 1310 1311
#endif

/*
 * Macros for sleeping on a socket. Use them like this:
 *
 * SOCK_SLEEP_PRE(sk)
 * if (condition)
 * 	schedule();
 * SOCK_SLEEP_POST(sk)
 *
1312 1313 1314
 * N.B. These are now obsolete and were, afaik, only ever used in DECnet
 * and when the last use of them in DECnet has gone, I'm intending to
 * remove them.
Linus Torvalds's avatar
Linus Torvalds committed
1315 1316 1317 1318 1319
 */

#define SOCK_SLEEP_PRE(sk) 	{ struct task_struct *tsk = current; \
				DECLARE_WAITQUEUE(wait, tsk); \
				tsk->state = TASK_INTERRUPTIBLE; \
1320
				add_wait_queue((sk)->sk_sleep, &wait); \
Linus Torvalds's avatar
Linus Torvalds committed
1321 1322 1323
				release_sock(sk);

#define SOCK_SLEEP_POST(sk)	tsk->state = TASK_RUNNING; \
1324
				remove_wait_queue((sk)->sk_sleep, &wait); \
Linus Torvalds's avatar
Linus Torvalds committed
1325 1326 1327
				lock_sock(sk); \
				}

1328 1329 1330
static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
{
	if (valbool)
1331
		sock_set_flag(sk, bit);
1332
	else
1333
		sock_reset_flag(sk, bit);
1334 1335
}

Linus Torvalds's avatar
Linus Torvalds committed
1336 1337 1338
extern __u32 sysctl_wmem_max;
extern __u32 sysctl_rmem_max;

1339 1340
int siocdevprivate_ioctl(unsigned int fd, unsigned int cmd, unsigned long arg);

Linus Torvalds's avatar
Linus Torvalds committed
1341
#endif	/* _SOCK_H */