sock.c 48.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11
/*
 * 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.
 *
 *		Generic socket support routines. Memory allocators, socket lock/release
 *		handler for protocols to use and generic option handler.
 *
 *
 * Version:	$Id: sock.c,v 1.117 2002/02/01 22:01:03 davem Exp $
 *
12
 * Authors:	Ross Biro
L
Linus Torvalds 已提交
13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93
 *		Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *		Florian La Roche, <flla@stud.uni-sb.de>
 *		Alan Cox, <A.Cox@swansea.ac.uk>
 *
 * Fixes:
 *		Alan Cox	: 	Numerous verify_area() problems
 *		Alan Cox	:	Connecting on a connecting socket
 *					now returns an error for tcp.
 *		Alan Cox	:	sock->protocol is set correctly.
 *					and is not sometimes left as 0.
 *		Alan Cox	:	connect handles icmp errors on a
 *					connect properly. Unfortunately there
 *					is a restart syscall nasty there. I
 *					can't match BSD without hacking the C
 *					library. Ideas urgently sought!
 *		Alan Cox	:	Disallow bind() to addresses that are
 *					not ours - especially broadcast ones!!
 *		Alan Cox	:	Socket 1024 _IS_ ok for users. (fencepost)
 *		Alan Cox	:	sock_wfree/sock_rfree don't destroy sockets,
 *					instead they leave that for the DESTROY timer.
 *		Alan Cox	:	Clean up error flag in accept
 *		Alan Cox	:	TCP ack handling is buggy, the DESTROY timer
 *					was buggy. Put a remove_sock() in the handler
 *					for memory when we hit 0. Also altered the timer
 *					code. The ACK stuff can wait and needs major 
 *					TCP layer surgery.
 *		Alan Cox	:	Fixed TCP ack bug, removed remove sock
 *					and fixed timer/inet_bh race.
 *		Alan Cox	:	Added zapped flag for TCP
 *		Alan Cox	:	Move kfree_skb into skbuff.c and tidied up surplus code
 *		Alan Cox	:	for new sk_buff allocations wmalloc/rmalloc now call alloc_skb
 *		Alan Cox	:	kfree_s calls now are kfree_skbmem so we can track skb resources
 *		Alan Cox	:	Supports socket option broadcast now as does udp. Packet and raw need fixing.
 *		Alan Cox	:	Added RCVBUF,SNDBUF size setting. It suddenly occurred to me how easy it was so...
 *		Rick Sladkey	:	Relaxed UDP rules for matching packets.
 *		C.E.Hawkins	:	IFF_PROMISC/SIOCGHWADDR support
 *	Pauline Middelink	:	identd support
 *		Alan Cox	:	Fixed connect() taking signals I think.
 *		Alan Cox	:	SO_LINGER supported
 *		Alan Cox	:	Error reporting fixes
 *		Anonymous	:	inet_create tidied up (sk->reuse setting)
 *		Alan Cox	:	inet sockets don't set sk->type!
 *		Alan Cox	:	Split socket option code
 *		Alan Cox	:	Callbacks
 *		Alan Cox	:	Nagle flag for Charles & Johannes stuff
 *		Alex		:	Removed restriction on inet fioctl
 *		Alan Cox	:	Splitting INET from NET core
 *		Alan Cox	:	Fixed bogus SO_TYPE handling in getsockopt()
 *		Adam Caldwell	:	Missing return in SO_DONTROUTE/SO_DEBUG code
 *		Alan Cox	:	Split IP from generic code
 *		Alan Cox	:	New kfree_skbmem()
 *		Alan Cox	:	Make SO_DEBUG superuser only.
 *		Alan Cox	:	Allow anyone to clear SO_DEBUG
 *					(compatibility fix)
 *		Alan Cox	:	Added optimistic memory grabbing for AF_UNIX throughput.
 *		Alan Cox	:	Allocator for a socket is settable.
 *		Alan Cox	:	SO_ERROR includes soft errors.
 *		Alan Cox	:	Allow NULL arguments on some SO_ opts
 *		Alan Cox	: 	Generic socket allocation to make hooks
 *					easier (suggested by Craig Metz).
 *		Michael Pall	:	SO_ERROR returns positive errno again
 *              Steve Whitehouse:       Added default destructor to free
 *                                      protocol private data.
 *              Steve Whitehouse:       Added various other default routines
 *                                      common to several socket families.
 *              Chris Evans     :       Call suser() check last on F_SETOWN
 *		Jay Schulist	:	Added SO_ATTACH_FILTER and SO_DETACH_FILTER.
 *		Andi Kleen	:	Add sock_kmalloc()/sock_kfree_s()
 *		Andi Kleen	:	Fix write_space callback
 *		Chris Evans	:	Security fixes - signedness again
 *		Arnaldo C. Melo :       cleanups, use skb_queue_purge
 *
 * To Fix:
 *
 *
 *		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.
 */

94
#include <linux/capability.h>
L
Linus Torvalds 已提交
95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/sched.h>
#include <linux/timer.h>
#include <linux/string.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/poll.h>
#include <linux/tcp.h>
#include <linux/init.h>

#include <asm/uaccess.h>
#include <asm/system.h>

#include <linux/netdevice.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
121
#include <net/request_sock.h>
L
Linus Torvalds 已提交
122 123 124 125 126 127 128 129 130 131
#include <net/sock.h>
#include <net/xfrm.h>
#include <linux/ipsec.h>

#include <linux/filter.h>

#ifdef CONFIG_INET
#include <net/tcp.h>
#endif

132 133 134 135
/*
 * Each address family might have different locking rules, so we have
 * one slock key per address family:
 */
I
Ingo Molnar 已提交
136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171
static struct lock_class_key af_family_keys[AF_MAX];
static struct lock_class_key af_family_slock_keys[AF_MAX];

#ifdef CONFIG_DEBUG_LOCK_ALLOC
/*
 * Make lock validator output more readable. (we pre-construct these
 * strings build-time, so that runtime initialization of socket
 * locks is fast):
 */
static const char *af_family_key_strings[AF_MAX+1] = {
  "sk_lock-AF_UNSPEC", "sk_lock-AF_UNIX"     , "sk_lock-AF_INET"     ,
  "sk_lock-AF_AX25"  , "sk_lock-AF_IPX"      , "sk_lock-AF_APPLETALK",
  "sk_lock-AF_NETROM", "sk_lock-AF_BRIDGE"   , "sk_lock-AF_ATMPVC"   ,
  "sk_lock-AF_X25"   , "sk_lock-AF_INET6"    , "sk_lock-AF_ROSE"     ,
  "sk_lock-AF_DECnet", "sk_lock-AF_NETBEUI"  , "sk_lock-AF_SECURITY" ,
  "sk_lock-AF_KEY"   , "sk_lock-AF_NETLINK"  , "sk_lock-AF_PACKET"   ,
  "sk_lock-AF_ASH"   , "sk_lock-AF_ECONET"   , "sk_lock-AF_ATMSVC"   ,
  "sk_lock-21"       , "sk_lock-AF_SNA"      , "sk_lock-AF_IRDA"     ,
  "sk_lock-AF_PPPOX" , "sk_lock-AF_WANPIPE"  , "sk_lock-AF_LLC"      ,
  "sk_lock-27"       , "sk_lock-28"          , "sk_lock-29"          ,
  "sk_lock-AF_TIPC"  , "sk_lock-AF_BLUETOOTH", "sk_lock-AF_MAX"
};
static const char *af_family_slock_key_strings[AF_MAX+1] = {
  "slock-AF_UNSPEC", "slock-AF_UNIX"     , "slock-AF_INET"     ,
  "slock-AF_AX25"  , "slock-AF_IPX"      , "slock-AF_APPLETALK",
  "slock-AF_NETROM", "slock-AF_BRIDGE"   , "slock-AF_ATMPVC"   ,
  "slock-AF_X25"   , "slock-AF_INET6"    , "slock-AF_ROSE"     ,
  "slock-AF_DECnet", "slock-AF_NETBEUI"  , "slock-AF_SECURITY" ,
  "slock-AF_KEY"   , "slock-AF_NETLINK"  , "slock-AF_PACKET"   ,
  "slock-AF_ASH"   , "slock-AF_ECONET"   , "slock-AF_ATMSVC"   ,
  "slock-21"       , "slock-AF_SNA"      , "slock-AF_IRDA"     ,
  "slock-AF_PPPOX" , "slock-AF_WANPIPE"  , "slock-AF_LLC"      ,
  "slock-27"       , "slock-28"          , "slock-29"          ,
  "slock-AF_TIPC"  , "slock-AF_BLUETOOTH", "slock-AF_MAX"
};
#endif
172 173 174 175 176 177 178

/*
 * sk_callback_lock locking rules are per-address-family,
 * so split the lock classes by using a per-AF key:
 */
static struct lock_class_key af_callback_keys[AF_MAX];

L
Linus Torvalds 已提交
179 180 181 182 183 184 185 186 187 188 189
/* Take into consideration the size of the struct sk_buff overhead in the
 * determination of these values, since that is non-constant across
 * platforms.  This makes socket queueing behavior and performance
 * not depend upon such differences.
 */
#define _SK_MEM_PACKETS		256
#define _SK_MEM_OVERHEAD	(sizeof(struct sk_buff) + 256)
#define SK_WMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)
#define SK_RMEM_MAX		(_SK_MEM_OVERHEAD * _SK_MEM_PACKETS)

/* Run time adjustable parameters. */
190 191 192 193
__u32 sysctl_wmem_max __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_max __read_mostly = SK_RMEM_MAX;
__u32 sysctl_wmem_default __read_mostly = SK_WMEM_MAX;
__u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX;
L
Linus Torvalds 已提交
194 195

/* Maximal space eaten by iovec or ancilliary data plus some space */
196
int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512);
L
Linus Torvalds 已提交
197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235

static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen)
{
	struct timeval tv;

	if (optlen < sizeof(tv))
		return -EINVAL;
	if (copy_from_user(&tv, optval, sizeof(tv)))
		return -EFAULT;

	*timeo_p = MAX_SCHEDULE_TIMEOUT;
	if (tv.tv_sec == 0 && tv.tv_usec == 0)
		return 0;
	if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1))
		*timeo_p = tv.tv_sec*HZ + (tv.tv_usec+(1000000/HZ-1))/(1000000/HZ);
	return 0;
}

static void sock_warn_obsolete_bsdism(const char *name)
{
	static int warned;
	static char warncomm[TASK_COMM_LEN];
	if (strcmp(warncomm, current->comm) && warned < 5) { 
		strcpy(warncomm,  current->comm); 
		printk(KERN_WARNING "process `%s' is using obsolete "
		       "%s SO_BSDCOMPAT\n", warncomm, name);
		warned++;
	}
}

static void sock_disable_timestamp(struct sock *sk)
{	
	if (sock_flag(sk, SOCK_TIMESTAMP)) { 
		sock_reset_flag(sk, SOCK_TIMESTAMP);
		net_disable_timestamp();
	}
}


236 237 238 239 240 241 242 243 244 245 246 247 248 249
int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
	int err = 0;
	int skb_len;

	/* 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) {
		err = -ENOMEM;
		goto out;
	}

250
	err = sk_filter(sk, skb);
251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276
	if (err)
		goto out;

	skb->dev = NULL;
	skb_set_owner_r(skb, sk);

	/* 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;

	skb_queue_tail(&sk->sk_receive_queue, skb);

	if (!sock_flag(sk, SOCK_DEAD))
		sk->sk_data_ready(sk, skb_len);
out:
	return err;
}
EXPORT_SYMBOL(sock_queue_rcv_skb);

int sk_receive_skb(struct sock *sk, struct sk_buff *skb)
{
	int rc = NET_RX_SUCCESS;

277
	if (sk_filter(sk, skb))
278 279 280 281 282
		goto discard_and_relse;

	skb->dev = NULL;

	bh_lock_sock(sk);
I
Ingo Molnar 已提交
283 284 285 286 287 288
	if (!sock_owned_by_user(sk)) {
		/*
		 * trylock + unlock semantics:
		 */
		mutex_acquire(&sk->sk_lock.dep_map, 0, 1, _RET_IP_);

289
		rc = sk->sk_backlog_rcv(sk, skb);
I
Ingo Molnar 已提交
290 291 292

		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
	} else
293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);
out:
	sock_put(sk);
	return rc;
discard_and_relse:
	kfree_skb(skb);
	goto out;
}
EXPORT_SYMBOL(sk_receive_skb);

struct dst_entry *__sk_dst_check(struct sock *sk, u32 cookie)
{
	struct dst_entry *dst = sk->sk_dst_cache;

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

	return dst;
}
EXPORT_SYMBOL(__sk_dst_check);

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);
		dst_release(dst);
		return NULL;
	}

	return dst;
}
EXPORT_SYMBOL(sk_dst_check);

L
Linus Torvalds 已提交
332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351
/*
 *	This is meant for all protocols to use and covers goings on
 *	at the socket level. Everything here is generic.
 */

int sock_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int optlen)
{
	struct sock *sk=sock->sk;
	struct sk_filter *filter;
	int val;
	int valbool;
	struct linger ling;
	int ret = 0;
	
	/*
	 *	Options without arguments
	 */

#ifdef SO_DONTLINGER		/* Compatibility item... */
K
Kyle Moffett 已提交
352 353 354 355 356
	if (optname == SO_DONTLINGER) {
		lock_sock(sk);
		sock_reset_flag(sk, SOCK_LINGER);
		release_sock(sk);
		return 0;
L
Linus Torvalds 已提交
357
	}
K
Kyle Moffett 已提交
358 359
#endif
	
L
Linus Torvalds 已提交
360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405
  	if(optlen<sizeof(int))
  		return(-EINVAL);
  	
	if (get_user(val, (int __user *)optval))
		return -EFAULT;
	
  	valbool = val?1:0;

	lock_sock(sk);

  	switch(optname) 
  	{
		case SO_DEBUG:	
			if(val && !capable(CAP_NET_ADMIN))
			{
				ret = -EACCES;
			}
			else if (valbool)
				sock_set_flag(sk, SOCK_DBG);
			else
				sock_reset_flag(sk, SOCK_DBG);
			break;
		case SO_REUSEADDR:
			sk->sk_reuse = valbool;
			break;
		case SO_TYPE:
		case SO_ERROR:
			ret = -ENOPROTOOPT;
		  	break;
		case SO_DONTROUTE:
			if (valbool)
				sock_set_flag(sk, SOCK_LOCALROUTE);
			else
				sock_reset_flag(sk, SOCK_LOCALROUTE);
			break;
		case SO_BROADCAST:
			sock_valbool_flag(sk, SOCK_BROADCAST, valbool);
			break;
		case SO_SNDBUF:
			/* Don't error on this BSD doesn't and if you think
			   about it this is right. Otherwise apps have to
			   play 'guess the biggest size' games. RCVBUF/SNDBUF
			   are treated in BSD as hints */
			   
			if (val > sysctl_wmem_max)
				val = sysctl_wmem_max;
406
set_sndbuf:
L
Linus Torvalds 已提交
407 408 409 410 411 412 413 414 415 416 417 418 419
			sk->sk_userlocks |= SOCK_SNDBUF_LOCK;
			if ((val * 2) < SOCK_MIN_SNDBUF)
				sk->sk_sndbuf = SOCK_MIN_SNDBUF;
			else
				sk->sk_sndbuf = val * 2;

			/*
			 *	Wake up sending tasks if we
			 *	upped the value.
			 */
			sk->sk_write_space(sk);
			break;

420 421 422 423 424 425 426
		case SO_SNDBUFFORCE:
			if (!capable(CAP_NET_ADMIN)) {
				ret = -EPERM;
				break;
			}
			goto set_sndbuf;

L
Linus Torvalds 已提交
427 428 429 430 431 432 433 434
		case SO_RCVBUF:
			/* Don't error on this BSD doesn't and if you think
			   about it this is right. Otherwise apps have to
			   play 'guess the biggest size' games. RCVBUF/SNDBUF
			   are treated in BSD as hints */
			  
			if (val > sysctl_rmem_max)
				val = sysctl_rmem_max;
435
set_rcvbuf:
L
Linus Torvalds 已提交
436
			sk->sk_userlocks |= SOCK_RCVBUF_LOCK;
A
Andrew Morton 已提交
437 438 439 440 441 442 443 444 445 446 447 448 449 450 451
			/*
			 * We double it on the way in to account for
			 * "struct sk_buff" etc. overhead.   Applications
			 * assume that the SO_RCVBUF setting they make will
			 * allow that much actual data to be received on that
			 * socket.
			 *
			 * Applications are unaware that "struct sk_buff" and
			 * other overheads allocate from the receive buffer
			 * during socket buffer allocation.
			 *
			 * And after considering the possible alternatives,
			 * returning the value we actually used in getsockopt
			 * is the most desirable behavior.
			 */
L
Linus Torvalds 已提交
452 453 454 455 456 457
			if ((val * 2) < SOCK_MIN_RCVBUF)
				sk->sk_rcvbuf = SOCK_MIN_RCVBUF;
			else
				sk->sk_rcvbuf = val * 2;
			break;

458 459 460 461 462 463 464
		case SO_RCVBUFFORCE:
			if (!capable(CAP_NET_ADMIN)) {
				ret = -EPERM;
				break;
			}
			goto set_rcvbuf;

L
Linus Torvalds 已提交
465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500
		case SO_KEEPALIVE:
#ifdef CONFIG_INET
			if (sk->sk_protocol == IPPROTO_TCP)
				tcp_set_keepalive(sk, valbool);
#endif
			sock_valbool_flag(sk, SOCK_KEEPOPEN, valbool);
			break;

	 	case SO_OOBINLINE:
			sock_valbool_flag(sk, SOCK_URGINLINE, valbool);
			break;

	 	case SO_NO_CHECK:
			sk->sk_no_check = valbool;
			break;

		case SO_PRIORITY:
			if ((val >= 0 && val <= 6) || capable(CAP_NET_ADMIN)) 
				sk->sk_priority = val;
			else
				ret = -EPERM;
			break;

		case SO_LINGER:
			if(optlen<sizeof(ling)) {
				ret = -EINVAL;	/* 1003.1g */
				break;
			}
			if (copy_from_user(&ling,optval,sizeof(ling))) {
				ret = -EFAULT;
				break;
			}
			if (!ling.l_onoff)
				sock_reset_flag(sk, SOCK_LINGER);
			else {
#if (BITS_PER_LONG == 32)
501
				if ((unsigned int)ling.l_linger >= MAX_SCHEDULE_TIMEOUT/HZ)
L
Linus Torvalds 已提交
502 503 504
					sk->sk_lingertime = MAX_SCHEDULE_TIMEOUT;
				else
#endif
505
					sk->sk_lingertime = (unsigned int)ling.l_linger * HZ;
L
Linus Torvalds 已提交
506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562
				sock_set_flag(sk, SOCK_LINGER);
			}
			break;

		case SO_BSDCOMPAT:
			sock_warn_obsolete_bsdism("setsockopt");
			break;

		case SO_PASSCRED:
			if (valbool)
				set_bit(SOCK_PASSCRED, &sock->flags);
			else
				clear_bit(SOCK_PASSCRED, &sock->flags);
			break;

		case SO_TIMESTAMP:
			if (valbool)  {
				sock_set_flag(sk, SOCK_RCVTSTAMP);
				sock_enable_timestamp(sk);
			} else
				sock_reset_flag(sk, SOCK_RCVTSTAMP);
			break;

		case SO_RCVLOWAT:
			if (val < 0)
				val = INT_MAX;
			sk->sk_rcvlowat = val ? : 1;
			break;

		case SO_RCVTIMEO:
			ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen);
			break;

		case SO_SNDTIMEO:
			ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen);
			break;

#ifdef CONFIG_NETDEVICES
		case SO_BINDTODEVICE:
		{
			char devname[IFNAMSIZ]; 

			/* Sorry... */ 
			if (!capable(CAP_NET_RAW)) {
				ret = -EPERM;
				break;
			}

			/* Bind this socket to a particular device like "eth0",
			 * as specified in the passed interface name. If the
			 * name is "" or the option length is zero the socket 
			 * is not bound. 
			 */ 

			if (!valbool) {
				sk->sk_bound_dev_if = 0;
			} else {
563 564 565
				if (optlen > IFNAMSIZ - 1)
					optlen = IFNAMSIZ - 1;
				memset(devname, 0, sizeof(devname));
L
Linus Torvalds 已提交
566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604
				if (copy_from_user(devname, optval, optlen)) {
					ret = -EFAULT;
					break;
				}

				/* Remove any cached route for this socket. */
				sk_dst_reset(sk);

				if (devname[0] == '\0') {
					sk->sk_bound_dev_if = 0;
				} else {
					struct net_device *dev = dev_get_by_name(devname);
					if (!dev) {
						ret = -ENODEV;
						break;
					}
					sk->sk_bound_dev_if = dev->ifindex;
					dev_put(dev);
				}
			}
			break;
		}
#endif


		case SO_ATTACH_FILTER:
			ret = -EINVAL;
			if (optlen == sizeof(struct sock_fprog)) {
				struct sock_fprog fprog;

				ret = -EFAULT;
				if (copy_from_user(&fprog, optval, sizeof(fprog)))
					break;

				ret = sk_attach_filter(&fprog, sk);
			}
			break;

		case SO_DETACH_FILTER:
605 606
			rcu_read_lock_bh();
			filter = rcu_dereference(sk->sk_filter);
L
Linus Torvalds 已提交
607
                        if (filter) {
608
				rcu_assign_pointer(sk->sk_filter, NULL);
L
Linus Torvalds 已提交
609
				sk_filter_release(sk, filter);
610
				rcu_read_unlock_bh();
L
Linus Torvalds 已提交
611 612
				break;
			}
613
			rcu_read_unlock_bh();
L
Linus Torvalds 已提交
614 615 616
			ret = -ENONET;
			break;

C
Catherine Zhang 已提交
617 618 619 620 621 622 623
		case SO_PASSSEC:
			if (valbool)
				set_bit(SOCK_PASSSEC, &sock->flags);
			else
				clear_bit(SOCK_PASSSEC, &sock->flags);
			break;

L
Linus Torvalds 已提交
624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781
		/* We implement the SO_SNDLOWAT etc to
		   not be settable (1003.1g 5.3) */
		default:
		  	ret = -ENOPROTOOPT;
			break;
  	}
	release_sock(sk);
	return ret;
}


int sock_getsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;
	
	union
	{
  		int val;
  		struct linger ling;
		struct timeval tm;
	} v;
	
	unsigned int lv = sizeof(int);
	int len;
  	
  	if(get_user(len,optlen))
  		return -EFAULT;
	if(len < 0)
		return -EINVAL;
		
  	switch(optname) 
  	{
		case SO_DEBUG:		
			v.val = sock_flag(sk, SOCK_DBG);
			break;
		
		case SO_DONTROUTE:
			v.val = sock_flag(sk, SOCK_LOCALROUTE);
			break;
		
		case SO_BROADCAST:
			v.val = !!sock_flag(sk, SOCK_BROADCAST);
			break;

		case SO_SNDBUF:
			v.val = sk->sk_sndbuf;
			break;
		
		case SO_RCVBUF:
			v.val = sk->sk_rcvbuf;
			break;

		case SO_REUSEADDR:
			v.val = sk->sk_reuse;
			break;

		case SO_KEEPALIVE:
			v.val = !!sock_flag(sk, SOCK_KEEPOPEN);
			break;

		case SO_TYPE:
			v.val = sk->sk_type;		  		
			break;

		case SO_ERROR:
			v.val = -sock_error(sk);
			if(v.val==0)
				v.val = xchg(&sk->sk_err_soft, 0);
			break;

		case SO_OOBINLINE:
			v.val = !!sock_flag(sk, SOCK_URGINLINE);
			break;
	
		case SO_NO_CHECK:
			v.val = sk->sk_no_check;
			break;

		case SO_PRIORITY:
			v.val = sk->sk_priority;
			break;
		
		case SO_LINGER:	
			lv		= sizeof(v.ling);
			v.ling.l_onoff	= !!sock_flag(sk, SOCK_LINGER);
 			v.ling.l_linger	= sk->sk_lingertime / HZ;
			break;
					
		case SO_BSDCOMPAT:
			sock_warn_obsolete_bsdism("getsockopt");
			break;

		case SO_TIMESTAMP:
			v.val = sock_flag(sk, SOCK_RCVTSTAMP);
			break;

		case SO_RCVTIMEO:
			lv=sizeof(struct timeval);
			if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) {
				v.tm.tv_sec = 0;
				v.tm.tv_usec = 0;
			} else {
				v.tm.tv_sec = sk->sk_rcvtimeo / HZ;
				v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * 1000000) / HZ;
			}
			break;

		case SO_SNDTIMEO:
			lv=sizeof(struct timeval);
			if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) {
				v.tm.tv_sec = 0;
				v.tm.tv_usec = 0;
			} else {
				v.tm.tv_sec = sk->sk_sndtimeo / HZ;
				v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * 1000000) / HZ;
			}
			break;

		case SO_RCVLOWAT:
			v.val = sk->sk_rcvlowat;
			break;

		case SO_SNDLOWAT:
			v.val=1;
			break; 

		case SO_PASSCRED:
			v.val = test_bit(SOCK_PASSCRED, &sock->flags) ? 1 : 0;
			break;

		case SO_PEERCRED:
			if (len > sizeof(sk->sk_peercred))
				len = sizeof(sk->sk_peercred);
			if (copy_to_user(optval, &sk->sk_peercred, len))
				return -EFAULT;
			goto lenout;

		case SO_PEERNAME:
		{
			char address[128];

			if (sock->ops->getname(sock, (struct sockaddr *)address, &lv, 2))
				return -ENOTCONN;
			if (lv < len)
				return -EINVAL;
			if (copy_to_user(optval, address, len))
				return -EFAULT;
			goto lenout;
		}

		/* Dubious BSD thing... Probably nobody even uses it, but
		 * the UNIX standard wants it for whatever reason... -DaveM
		 */
		case SO_ACCEPTCONN:
			v.val = sk->sk_state == TCP_LISTEN;
			break;

C
Catherine Zhang 已提交
782 783 784 785
		case SO_PASSSEC:
			v.val = test_bit(SOCK_PASSSEC, &sock->flags) ? 1 : 0;
			break;

L
Linus Torvalds 已提交
786
		case SO_PEERSEC:
C
Catherine Zhang 已提交
787
			return security_socket_getpeersec_stream(sock, optval, optlen, len);
L
Linus Torvalds 已提交
788 789 790 791 792 793 794 795 796 797 798 799 800 801

		default:
			return(-ENOPROTOOPT);
	}
	if (len > lv)
		len = lv;
	if (copy_to_user(optval, &v, len))
		return -EFAULT;
lenout:
  	if (put_user(len, optlen))
  		return -EFAULT;
  	return 0;
}

I
Ingo Molnar 已提交
802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825
/*
 * Initialize an sk_lock.
 *
 * (We also register the sk_lock with the lock validator.)
 */
static void inline sock_lock_init(struct sock *sk)
{
	spin_lock_init(&sk->sk_lock.slock);
	sk->sk_lock.owner = NULL;
	init_waitqueue_head(&sk->sk_lock.wq);
	/*
	 * Make sure we are not reinitializing a held lock:
	 */
	debug_check_no_locks_freed((void *)&sk->sk_lock, sizeof(sk->sk_lock));

	/*
	 * Mark both the sk_lock and the sk_lock.slock as a
	 * per-address-family lock class:
	 */
	lockdep_set_class_and_name(&sk->sk_lock.slock,
				   af_family_slock_keys + sk->sk_family,
				   af_family_slock_key_strings[sk->sk_family]);
	lockdep_init_map(&sk->sk_lock.dep_map,
			 af_family_key_strings[sk->sk_family],
826
			 af_family_keys + sk->sk_family, 0);
I
Ingo Molnar 已提交
827 828
}

L
Linus Torvalds 已提交
829 830
/**
 *	sk_alloc - All socket objects are allocated here
831 832 833 834
 *	@family: protocol family
 *	@priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc)
 *	@prot: struct proto associated with this new sock instance
 *	@zero_it: if we should zero the newly allocated sock
L
Linus Torvalds 已提交
835
 */
A
Al Viro 已提交
836
struct sock *sk_alloc(int family, gfp_t priority,
V
Victor Fusco 已提交
837
		      struct proto *prot, int zero_it)
L
Linus Torvalds 已提交
838 839 840 841 842 843 844 845 846 847 848 849 850
{
	struct sock *sk = NULL;
	kmem_cache_t *slab = prot->slab;

	if (slab != NULL)
		sk = kmem_cache_alloc(slab, priority);
	else
		sk = kmalloc(prot->obj_size, priority);

	if (sk) {
		if (zero_it) {
			memset(sk, 0, prot->obj_size);
			sk->sk_family = family;
851 852 853 854 855
			/*
			 * See comment in struct sock definition to understand
			 * why we need sk_prot_creator -acme
			 */
			sk->sk_prot = sk->sk_prot_creator = prot;
L
Linus Torvalds 已提交
856 857 858
			sock_lock_init(sk);
		}
		
859 860 861 862 863
		if (security_sk_alloc(sk, family, priority))
			goto out_free;

		if (!try_module_get(prot->owner))
			goto out_free;
L
Linus Torvalds 已提交
864 865
	}
	return sk;
866 867 868 869 870 871 872

out_free:
	if (slab != NULL)
		kmem_cache_free(slab, sk);
	else
		kfree(sk);
	return NULL;
L
Linus Torvalds 已提交
873 874 875 876 877
}

void sk_free(struct sock *sk)
{
	struct sk_filter *filter;
878
	struct module *owner = sk->sk_prot_creator->owner;
L
Linus Torvalds 已提交
879 880 881 882

	if (sk->sk_destruct)
		sk->sk_destruct(sk);

883
	filter = rcu_dereference(sk->sk_filter);
L
Linus Torvalds 已提交
884 885
	if (filter) {
		sk_filter_release(sk, filter);
886
		rcu_assign_pointer(sk->sk_filter, NULL);
L
Linus Torvalds 已提交
887 888 889 890 891 892 893 894 895
	}

	sock_disable_timestamp(sk);

	if (atomic_read(&sk->sk_omem_alloc))
		printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n",
		       __FUNCTION__, atomic_read(&sk->sk_omem_alloc));

	security_sk_free(sk);
896 897
	if (sk->sk_prot_creator->slab != NULL)
		kmem_cache_free(sk->sk_prot_creator->slab, sk);
L
Linus Torvalds 已提交
898 899 900 901 902
	else
		kfree(sk);
	module_put(owner);
}

A
Al Viro 已提交
903
struct sock *sk_clone(const struct sock *sk, const gfp_t priority)
904 905 906 907 908 909
{
	struct sock *newsk = sk_alloc(sk->sk_family, priority, sk->sk_prot, 0);

	if (newsk != NULL) {
		struct sk_filter *filter;

910
		sock_copy(newsk, sk);
911 912 913 914 915 916 917 918 919 920 921

		/* SANITY */
		sk_node_init(&newsk->sk_node);
		sock_lock_init(newsk);
		bh_lock_sock(newsk);

		atomic_set(&newsk->sk_rmem_alloc, 0);
		atomic_set(&newsk->sk_wmem_alloc, 0);
		atomic_set(&newsk->sk_omem_alloc, 0);
		skb_queue_head_init(&newsk->sk_receive_queue);
		skb_queue_head_init(&newsk->sk_write_queue);
922 923 924
#ifdef CONFIG_NET_DMA
		skb_queue_head_init(&newsk->sk_async_wait_queue);
#endif
925 926 927

		rwlock_init(&newsk->sk_dst_lock);
		rwlock_init(&newsk->sk_callback_lock);
928 929
		lockdep_set_class(&newsk->sk_callback_lock,
				   af_callback_keys + newsk->sk_family);
930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981

		newsk->sk_dst_cache	= NULL;
		newsk->sk_wmem_queued	= 0;
		newsk->sk_forward_alloc = 0;
		newsk->sk_send_head	= NULL;
		newsk->sk_backlog.head	= newsk->sk_backlog.tail = NULL;
		newsk->sk_userlocks	= sk->sk_userlocks & ~SOCK_BINDPORT_LOCK;

		sock_reset_flag(newsk, SOCK_DONE);
		skb_queue_head_init(&newsk->sk_error_queue);

		filter = newsk->sk_filter;
		if (filter != NULL)
			sk_filter_charge(newsk, filter);

		if (unlikely(xfrm_sk_clone_policy(newsk))) {
			/* It is still raw copy of parent, so invalidate
			 * destructor and make plain sk_free() */
			newsk->sk_destruct = NULL;
			sk_free(newsk);
			newsk = NULL;
			goto out;
		}

		newsk->sk_err	   = 0;
		newsk->sk_priority = 0;
		atomic_set(&newsk->sk_refcnt, 2);

		/*
		 * Increment the counter in the same struct proto as the master
		 * sock (sk_refcnt_debug_inc uses newsk->sk_prot->socks, that
		 * is the same as sk->sk_prot->socks, as this field was copied
		 * with memcpy).
		 *
		 * This _changes_ the previous behaviour, where
		 * tcp_create_openreq_child always was incrementing the
		 * equivalent to tcp_prot->socks (inet_sock_nr), so this have
		 * to be taken into account in all callers. -acme
		 */
		sk_refcnt_debug_inc(newsk);
		newsk->sk_socket = NULL;
		newsk->sk_sleep	 = NULL;

		if (newsk->sk_prot->sockets_allocated)
			atomic_inc(newsk->sk_prot->sockets_allocated);
	}
out:
	return newsk;
}

EXPORT_SYMBOL_GPL(sk_clone);

L
Linus Torvalds 已提交
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 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047
void __init sk_init(void)
{
	if (num_physpages <= 4096) {
		sysctl_wmem_max = 32767;
		sysctl_rmem_max = 32767;
		sysctl_wmem_default = 32767;
		sysctl_rmem_default = 32767;
	} else if (num_physpages >= 131072) {
		sysctl_wmem_max = 131071;
		sysctl_rmem_max = 131071;
	}
}

/*
 *	Simple resource managers for sockets.
 */


/* 
 * Write buffer destructor automatically called from kfree_skb. 
 */
void sock_wfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	/* In case it might be waiting for more memory. */
	atomic_sub(skb->truesize, &sk->sk_wmem_alloc);
	if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE))
		sk->sk_write_space(sk);
	sock_put(sk);
}

/* 
 * Read buffer destructor automatically called from kfree_skb. 
 */
void sock_rfree(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;

	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
}


int sock_i_uid(struct sock *sk)
{
	int uid;

	read_lock(&sk->sk_callback_lock);
	uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0;
	read_unlock(&sk->sk_callback_lock);
	return uid;
}

unsigned long sock_i_ino(struct sock *sk)
{
	unsigned long ino;

	read_lock(&sk->sk_callback_lock);
	ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0;
	read_unlock(&sk->sk_callback_lock);
	return ino;
}

/*
 * Allocate a skb from the socket's send buffer.
 */
V
Victor Fusco 已提交
1048
struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
A
Al Viro 已提交
1049
			     gfp_t priority)
L
Linus Torvalds 已提交
1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063
{
	if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
		struct sk_buff * skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_w(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/*
 * Allocate a skb from the socket's receive buffer.
 */ 
V
Victor Fusco 已提交
1064
struct sk_buff *sock_rmalloc(struct sock *sk, unsigned long size, int force,
A
Al Viro 已提交
1065
			     gfp_t priority)
L
Linus Torvalds 已提交
1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079
{
	if (force || atomic_read(&sk->sk_rmem_alloc) < sk->sk_rcvbuf) {
		struct sk_buff *skb = alloc_skb(size, priority);
		if (skb) {
			skb_set_owner_r(skb, sk);
			return skb;
		}
	}
	return NULL;
}

/* 
 * Allocate a memory block from the socket's option memory buffer.
 */ 
A
Al Viro 已提交
1080
void *sock_kmalloc(struct sock *sk, int size, gfp_t priority)
L
Linus Torvalds 已提交
1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 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
{
	if ((unsigned)size <= sysctl_optmem_max &&
	    atomic_read(&sk->sk_omem_alloc) + size < sysctl_optmem_max) {
		void *mem;
		/* First do the add, to avoid the race if kmalloc
 		 * might sleep.
		 */
		atomic_add(size, &sk->sk_omem_alloc);
		mem = kmalloc(size, priority);
		if (mem)
			return mem;
		atomic_sub(size, &sk->sk_omem_alloc);
	}
	return NULL;
}

/*
 * Free an option memory block.
 */
void sock_kfree_s(struct sock *sk, void *mem, int size)
{
	kfree(mem);
	atomic_sub(size, &sk->sk_omem_alloc);
}

/* It is almost wait_for_tcp_memory minus release_sock/lock_sock.
   I think, these locks should be removed for datagram sockets.
 */
static long sock_wait_for_wmem(struct sock * sk, long timeo)
{
	DEFINE_WAIT(wait);

	clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
	for (;;) {
		if (!timeo)
			break;
		if (signal_pending(current))
			break;
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf)
			break;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			break;
		if (sk->sk_err)
			break;
		timeo = schedule_timeout(timeo);
	}
	finish_wait(sk->sk_sleep, &wait);
	return timeo;
}


/*
 *	Generic send/receive buffer handlers
 */

static struct sk_buff *sock_alloc_send_pskb(struct sock *sk,
					    unsigned long header_len,
					    unsigned long data_len,
					    int noblock, int *errcode)
{
	struct sk_buff *skb;
A
Al Viro 已提交
1144
	gfp_t gfp_mask;
L
Linus Torvalds 已提交
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 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 1205 1206 1207 1208 1209 1210 1211 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 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 1274
	long timeo;
	int err;

	gfp_mask = sk->sk_allocation;
	if (gfp_mask & __GFP_WAIT)
		gfp_mask |= __GFP_REPEAT;

	timeo = sock_sndtimeo(sk, noblock);
	while (1) {
		err = sock_error(sk);
		if (err != 0)
			goto failure;

		err = -EPIPE;
		if (sk->sk_shutdown & SEND_SHUTDOWN)
			goto failure;

		if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
			skb = alloc_skb(header_len, sk->sk_allocation);
			if (skb) {
				int npages;
				int i;

				/* No pages, we're done... */
				if (!data_len)
					break;

				npages = (data_len + (PAGE_SIZE - 1)) >> PAGE_SHIFT;
				skb->truesize += data_len;
				skb_shinfo(skb)->nr_frags = npages;
				for (i = 0; i < npages; i++) {
					struct page *page;
					skb_frag_t *frag;

					page = alloc_pages(sk->sk_allocation, 0);
					if (!page) {
						err = -ENOBUFS;
						skb_shinfo(skb)->nr_frags = i;
						kfree_skb(skb);
						goto failure;
					}

					frag = &skb_shinfo(skb)->frags[i];
					frag->page = page;
					frag->page_offset = 0;
					frag->size = (data_len >= PAGE_SIZE ?
						      PAGE_SIZE :
						      data_len);
					data_len -= PAGE_SIZE;
				}

				/* Full success... */
				break;
			}
			err = -ENOBUFS;
			goto failure;
		}
		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
		err = -EAGAIN;
		if (!timeo)
			goto failure;
		if (signal_pending(current))
			goto interrupted;
		timeo = sock_wait_for_wmem(sk, timeo);
	}

	skb_set_owner_w(skb, sk);
	return skb;

interrupted:
	err = sock_intr_errno(timeo);
failure:
	*errcode = err;
	return NULL;
}

struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, 
				    int noblock, int *errcode)
{
	return sock_alloc_send_pskb(sk, size, 0, noblock, errcode);
}

static void __lock_sock(struct sock *sk)
{
	DEFINE_WAIT(wait);

	for(;;) {
		prepare_to_wait_exclusive(&sk->sk_lock.wq, &wait,
					TASK_UNINTERRUPTIBLE);
		spin_unlock_bh(&sk->sk_lock.slock);
		schedule();
		spin_lock_bh(&sk->sk_lock.slock);
		if(!sock_owned_by_user(sk))
			break;
	}
	finish_wait(&sk->sk_lock.wq, &wait);
}

static void __release_sock(struct sock *sk)
{
	struct sk_buff *skb = sk->sk_backlog.head;

	do {
		sk->sk_backlog.head = sk->sk_backlog.tail = NULL;
		bh_unlock_sock(sk);

		do {
			struct sk_buff *next = skb->next;

			skb->next = NULL;
			sk->sk_backlog_rcv(sk, skb);

			/*
			 * We are in process context here with softirqs
			 * disabled, use cond_resched_softirq() to preempt.
			 * This is safe to do because we've taken the backlog
			 * queue private:
			 */
			cond_resched_softirq();

			skb = next;
		} while (skb != NULL);

		bh_lock_sock(sk);
	} while((skb = sk->sk_backlog.head) != NULL);
}

/**
 * sk_wait_data - wait for data to arrive at sk_receive_queue
1275 1276
 * @sk:    sock to wait on
 * @timeo: for how long
L
Linus Torvalds 已提交
1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 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 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 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 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445
 *
 * Now socket state including sk->sk_err is changed only under lock,
 * hence we may omit checks after joining wait queue.
 * We check receive queue before schedule() only as optimization;
 * it is very likely that release_sock() added new data.
 */
int sk_wait_data(struct sock *sk, long *timeo)
{
	int rc;
	DEFINE_WAIT(wait);

	prepare_to_wait(sk->sk_sleep, &wait, TASK_INTERRUPTIBLE);
	set_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	rc = sk_wait_event(sk, timeo, !skb_queue_empty(&sk->sk_receive_queue));
	clear_bit(SOCK_ASYNC_WAITDATA, &sk->sk_socket->flags);
	finish_wait(sk->sk_sleep, &wait);
	return rc;
}

EXPORT_SYMBOL(sk_wait_data);

/*
 * Set of default routines for initialising struct proto_ops when
 * the protocol does not support a particular function. In certain
 * cases where it makes no sense for a protocol to have a "do nothing"
 * function, some default processing is provided.
 */

int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len)
{
	return -EOPNOTSUPP;
}

int sock_no_connect(struct socket *sock, struct sockaddr *saddr, 
		    int len, int flags)
{
	return -EOPNOTSUPP;
}

int sock_no_socketpair(struct socket *sock1, struct socket *sock2)
{
	return -EOPNOTSUPP;
}

int sock_no_accept(struct socket *sock, struct socket *newsock, int flags)
{
	return -EOPNOTSUPP;
}

int sock_no_getname(struct socket *sock, struct sockaddr *saddr, 
		    int *len, int peer)
{
	return -EOPNOTSUPP;
}

unsigned int sock_no_poll(struct file * file, struct socket *sock, poll_table *pt)
{
	return 0;
}

int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
{
	return -EOPNOTSUPP;
}

int sock_no_listen(struct socket *sock, int backlog)
{
	return -EOPNOTSUPP;
}

int sock_no_shutdown(struct socket *sock, int how)
{
	return -EOPNOTSUPP;
}

int sock_no_setsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int optlen)
{
	return -EOPNOTSUPP;
}

int sock_no_getsockopt(struct socket *sock, int level, int optname,
		    char __user *optval, int __user *optlen)
{
	return -EOPNOTSUPP;
}

int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
		    size_t len)
{
	return -EOPNOTSUPP;
}

int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m,
		    size_t len, int flags)
{
	return -EOPNOTSUPP;
}

int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma)
{
	/* Mirror missing mmap method error code */
	return -ENODEV;
}

ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags)
{
	ssize_t res;
	struct msghdr msg = {.msg_flags = flags};
	struct kvec iov;
	char *kaddr = kmap(page);
	iov.iov_base = kaddr + offset;
	iov.iov_len = size;
	res = kernel_sendmsg(sock, &msg, &iov, 1, size);
	kunmap(page);
	return res;
}

/*
 *	Default Socket Callbacks
 */

static void sock_def_wakeup(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible_all(sk->sk_sleep);
	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_error_report(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
	sk_wake_async(sk,0,POLL_ERR); 
	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_readable(struct sock *sk, int len)
{
	read_lock(&sk->sk_callback_lock);
	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
		wake_up_interruptible(sk->sk_sleep);
	sk_wake_async(sk,1,POLL_IN);
	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_write_space(struct sock *sk)
{
	read_lock(&sk->sk_callback_lock);

	/* Do not wake up a writer until he can make "significant"
	 * progress.  --DaveM
	 */
	if((atomic_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) {
		if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
			wake_up_interruptible(sk->sk_sleep);

		/* Should agree with poll, otherwise some programs break */
		if (sock_writeable(sk))
			sk_wake_async(sk, 2, POLL_OUT);
	}

	read_unlock(&sk->sk_callback_lock);
}

static void sock_def_destruct(struct sock *sk)
{
J
Jesper Juhl 已提交
1446
	kfree(sk->sk_protinfo);
L
Linus Torvalds 已提交
1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477
}

void sk_send_sigurg(struct sock *sk)
{
	if (sk->sk_socket && sk->sk_socket->file)
		if (send_sigurg(&sk->sk_socket->file->f_owner))
			sk_wake_async(sk, 3, POLL_PRI);
}

void sk_reset_timer(struct sock *sk, struct timer_list* timer,
		    unsigned long expires)
{
	if (!mod_timer(timer, expires))
		sock_hold(sk);
}

EXPORT_SYMBOL(sk_reset_timer);

void sk_stop_timer(struct sock *sk, struct timer_list* timer)
{
	if (timer_pending(timer) && del_timer(timer))
		__sock_put(sk);
}

EXPORT_SYMBOL(sk_stop_timer);

void sock_init_data(struct socket *sock, struct sock *sk)
{
	skb_queue_head_init(&sk->sk_receive_queue);
	skb_queue_head_init(&sk->sk_write_queue);
	skb_queue_head_init(&sk->sk_error_queue);
1478 1479 1480
#ifdef CONFIG_NET_DMA
	skb_queue_head_init(&sk->sk_async_wait_queue);
#endif
L
Linus Torvalds 已提交
1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503

	sk->sk_send_head	=	NULL;

	init_timer(&sk->sk_timer);
	
	sk->sk_allocation	=	GFP_KERNEL;
	sk->sk_rcvbuf		=	sysctl_rmem_default;
	sk->sk_sndbuf		=	sysctl_wmem_default;
	sk->sk_state		=	TCP_CLOSE;
	sk->sk_socket		=	sock;

	sock_set_flag(sk, SOCK_ZAPPED);

	if(sock)
	{
		sk->sk_type	=	sock->type;
		sk->sk_sleep	=	&sock->wait;
		sock->sk	=	sk;
	} else
		sk->sk_sleep	=	NULL;

	rwlock_init(&sk->sk_dst_lock);
	rwlock_init(&sk->sk_callback_lock);
1504 1505
	lockdep_set_class(&sk->sk_callback_lock,
			   af_callback_keys + sk->sk_family);
L
Linus Torvalds 已提交
1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532

	sk->sk_state_change	=	sock_def_wakeup;
	sk->sk_data_ready	=	sock_def_readable;
	sk->sk_write_space	=	sock_def_write_space;
	sk->sk_error_report	=	sock_def_error_report;
	sk->sk_destruct		=	sock_def_destruct;

	sk->sk_sndmsg_page	=	NULL;
	sk->sk_sndmsg_off	=	0;

	sk->sk_peercred.pid 	=	0;
	sk->sk_peercred.uid	=	-1;
	sk->sk_peercred.gid	=	-1;
	sk->sk_write_pending	=	0;
	sk->sk_rcvlowat		=	1;
	sk->sk_rcvtimeo		=	MAX_SCHEDULE_TIMEOUT;
	sk->sk_sndtimeo		=	MAX_SCHEDULE_TIMEOUT;

	sk->sk_stamp.tv_sec     = -1L;
	sk->sk_stamp.tv_usec    = -1L;

	atomic_set(&sk->sk_refcnt, 1);
}

void fastcall lock_sock(struct sock *sk)
{
	might_sleep();
I
Ingo Molnar 已提交
1533
	spin_lock_bh(&sk->sk_lock.slock);
L
Linus Torvalds 已提交
1534 1535 1536
	if (sk->sk_lock.owner)
		__lock_sock(sk);
	sk->sk_lock.owner = (void *)1;
I
Ingo Molnar 已提交
1537 1538 1539 1540 1541 1542
	spin_unlock(&sk->sk_lock.slock);
	/*
	 * The sk_lock has mutex_lock() semantics here:
	 */
	mutex_acquire(&sk->sk_lock.dep_map, 0, 0, _RET_IP_);
	local_bh_enable();
L
Linus Torvalds 已提交
1543 1544 1545 1546 1547 1548
}

EXPORT_SYMBOL(lock_sock);

void fastcall release_sock(struct sock *sk)
{
I
Ingo Molnar 已提交
1549 1550 1551 1552 1553 1554
	/*
	 * The sk_lock has mutex_unlock() semantics:
	 */
	mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);

	spin_lock_bh(&sk->sk_lock.slock);
L
Linus Torvalds 已提交
1555 1556 1557
	if (sk->sk_backlog.tail)
		__release_sock(sk);
	sk->sk_lock.owner = NULL;
I
Ingo Molnar 已提交
1558 1559 1560
	if (waitqueue_active(&sk->sk_lock.wq))
		wake_up(&sk->sk_lock.wq);
	spin_unlock_bh(&sk->sk_lock.slock);
L
Linus Torvalds 已提交
1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602
}
EXPORT_SYMBOL(release_sock);

int sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp)
{ 
	if (!sock_flag(sk, SOCK_TIMESTAMP))
		sock_enable_timestamp(sk);
	if (sk->sk_stamp.tv_sec == -1) 
		return -ENOENT;
	if (sk->sk_stamp.tv_sec == 0)
		do_gettimeofday(&sk->sk_stamp);
	return copy_to_user(userstamp, &sk->sk_stamp, sizeof(struct timeval)) ?
		-EFAULT : 0; 
} 
EXPORT_SYMBOL(sock_get_timestamp);

void sock_enable_timestamp(struct sock *sk)
{	
	if (!sock_flag(sk, SOCK_TIMESTAMP)) { 
		sock_set_flag(sk, SOCK_TIMESTAMP);
		net_enable_timestamp();
	}
}
EXPORT_SYMBOL(sock_enable_timestamp); 

/*
 *	Get a socket option on an socket.
 *
 *	FIX: POSIX 1003.1g is very ambiguous here. It states that
 *	asynchronous errors should be reported by getsockopt. We assume
 *	this means if you specify SO_ERROR (otherwise whats the point of it).
 */
int sock_common_getsockopt(struct socket *sock, int level, int optname,
			   char __user *optval, int __user *optlen)
{
	struct sock *sk = sock->sk;

	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL(sock_common_getsockopt);

1603
#ifdef CONFIG_COMPAT
1604 1605
int compat_sock_common_getsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int __user *optlen)
1606 1607 1608
{
	struct sock *sk = sock->sk;

1609 1610 1611
	if (sk->sk_prot->compat_setsockopt != NULL)
		return sk->sk_prot->compat_getsockopt(sk, level, optname,
						      optval, optlen);
1612 1613 1614 1615 1616
	return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_getsockopt);
#endif

L
Linus Torvalds 已提交
1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645
int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock,
			struct msghdr *msg, size_t size, int flags)
{
	struct sock *sk = sock->sk;
	int addr_len = 0;
	int err;

	err = sk->sk_prot->recvmsg(iocb, sk, msg, size, flags & MSG_DONTWAIT,
				   flags & ~MSG_DONTWAIT, &addr_len);
	if (err >= 0)
		msg->msg_namelen = addr_len;
	return err;
}

EXPORT_SYMBOL(sock_common_recvmsg);

/*
 *	Set socket options on an inet socket.
 */
int sock_common_setsockopt(struct socket *sock, int level, int optname,
			   char __user *optval, int optlen)
{
	struct sock *sk = sock->sk;

	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}

EXPORT_SYMBOL(sock_common_setsockopt);

1646
#ifdef CONFIG_COMPAT
1647 1648
int compat_sock_common_setsockopt(struct socket *sock, int level, int optname,
				  char __user *optval, int optlen)
1649 1650 1651
{
	struct sock *sk = sock->sk;

1652 1653 1654
	if (sk->sk_prot->compat_setsockopt != NULL)
		return sk->sk_prot->compat_setsockopt(sk, level, optname,
						      optval, optlen);
1655 1656 1657 1658 1659
	return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen);
}
EXPORT_SYMBOL(compat_sock_common_setsockopt);
#endif

L
Linus Torvalds 已提交
1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690
void sk_common_release(struct sock *sk)
{
	if (sk->sk_prot->destroy)
		sk->sk_prot->destroy(sk);

	/*
	 * Observation: when sock_common_release is called, processes have
	 * no access to socket. But net still has.
	 * Step one, detach it from networking:
	 *
	 * A. Remove from hash tables.
	 */

	sk->sk_prot->unhash(sk);

	/*
	 * In this point socket cannot receive new packets, but it is possible
	 * that some packets are in flight because some CPU runs receiver and
	 * did hash table lookup before we unhashed socket. They will achieve
	 * receive queue and will be purged by socket destructor.
	 *
	 * Also we still have packets pending on receive queue and probably,
	 * our own packets waiting in device queues. sock_destroy will drain
	 * receive queue, but transmitted packets will delay socket destruction
	 * until the last reference will be released.
	 */

	sock_orphan(sk);

	xfrm_sk_free_policy(sk);

1691
	sk_refcnt_debug_release(sk);
L
Linus Torvalds 已提交
1692 1693 1694 1695 1696 1697 1698 1699 1700 1701
	sock_put(sk);
}

EXPORT_SYMBOL(sk_common_release);

static DEFINE_RWLOCK(proto_list_lock);
static LIST_HEAD(proto_list);

int proto_register(struct proto *prot, int alloc_slab)
{
1702 1703
	char *request_sock_slab_name = NULL;
	char *timewait_sock_slab_name;
L
Linus Torvalds 已提交
1704 1705 1706 1707 1708 1709 1710 1711 1712
	int rc = -ENOBUFS;

	if (alloc_slab) {
		prot->slab = kmem_cache_create(prot->name, prot->obj_size, 0,
					       SLAB_HWCACHE_ALIGN, NULL, NULL);

		if (prot->slab == NULL) {
			printk(KERN_CRIT "%s: Can't create sock SLAB cache!\n",
			       prot->name);
1713
			goto out;
L
Linus Torvalds 已提交
1714
		}
1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733

		if (prot->rsk_prot != NULL) {
			static const char mask[] = "request_sock_%s";

			request_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL);
			if (request_sock_slab_name == NULL)
				goto out_free_sock_slab;

			sprintf(request_sock_slab_name, mask, prot->name);
			prot->rsk_prot->slab = kmem_cache_create(request_sock_slab_name,
								 prot->rsk_prot->obj_size, 0,
								 SLAB_HWCACHE_ALIGN, NULL, NULL);

			if (prot->rsk_prot->slab == NULL) {
				printk(KERN_CRIT "%s: Can't create request sock SLAB cache!\n",
				       prot->name);
				goto out_free_request_sock_slab_name;
			}
		}
1734

1735
		if (prot->twsk_prot != NULL) {
1736 1737 1738 1739 1740 1741 1742 1743
			static const char mask[] = "tw_sock_%s";

			timewait_sock_slab_name = kmalloc(strlen(prot->name) + sizeof(mask) - 1, GFP_KERNEL);

			if (timewait_sock_slab_name == NULL)
				goto out_free_request_sock_slab;

			sprintf(timewait_sock_slab_name, mask, prot->name);
1744 1745 1746 1747 1748 1749
			prot->twsk_prot->twsk_slab =
				kmem_cache_create(timewait_sock_slab_name,
						  prot->twsk_prot->twsk_obj_size,
						  0, SLAB_HWCACHE_ALIGN,
						  NULL, NULL);
			if (prot->twsk_prot->twsk_slab == NULL)
1750 1751
				goto out_free_timewait_sock_slab_name;
		}
L
Linus Torvalds 已提交
1752 1753
	}

1754
	write_lock(&proto_list_lock);
L
Linus Torvalds 已提交
1755 1756
	list_add(&prot->node, &proto_list);
	write_unlock(&proto_list_lock);
1757 1758
	rc = 0;
out:
L
Linus Torvalds 已提交
1759
	return rc;
1760 1761 1762 1763 1764 1765 1766
out_free_timewait_sock_slab_name:
	kfree(timewait_sock_slab_name);
out_free_request_sock_slab:
	if (prot->rsk_prot && prot->rsk_prot->slab) {
		kmem_cache_destroy(prot->rsk_prot->slab);
		prot->rsk_prot->slab = NULL;
	}
1767 1768 1769 1770 1771 1772
out_free_request_sock_slab_name:
	kfree(request_sock_slab_name);
out_free_sock_slab:
	kmem_cache_destroy(prot->slab);
	prot->slab = NULL;
	goto out;
L
Linus Torvalds 已提交
1773 1774 1775 1776 1777 1778 1779
}

EXPORT_SYMBOL(proto_register);

void proto_unregister(struct proto *prot)
{
	write_lock(&proto_list_lock);
1780 1781
	list_del(&prot->node);
	write_unlock(&proto_list_lock);
L
Linus Torvalds 已提交
1782 1783 1784 1785 1786 1787

	if (prot->slab != NULL) {
		kmem_cache_destroy(prot->slab);
		prot->slab = NULL;
	}

1788 1789 1790 1791 1792 1793 1794 1795
	if (prot->rsk_prot != NULL && prot->rsk_prot->slab != NULL) {
		const char *name = kmem_cache_name(prot->rsk_prot->slab);

		kmem_cache_destroy(prot->rsk_prot->slab);
		kfree(name);
		prot->rsk_prot->slab = NULL;
	}

1796 1797
	if (prot->twsk_prot != NULL && prot->twsk_prot->twsk_slab != NULL) {
		const char *name = kmem_cache_name(prot->twsk_prot->twsk_slab);
1798

1799
		kmem_cache_destroy(prot->twsk_prot->twsk_slab);
1800
		kfree(name);
1801
		prot->twsk_prot->twsk_slab = NULL;
1802
	}
L
Linus Torvalds 已提交
1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969
}

EXPORT_SYMBOL(proto_unregister);

#ifdef CONFIG_PROC_FS
static inline struct proto *__proto_head(void)
{
	return list_entry(proto_list.next, struct proto, node);
}

static inline struct proto *proto_head(void)
{
	return list_empty(&proto_list) ? NULL : __proto_head();
}

static inline struct proto *proto_next(struct proto *proto)
{
	return proto->node.next == &proto_list ? NULL :
		list_entry(proto->node.next, struct proto, node);
}

static inline struct proto *proto_get_idx(loff_t pos)
{
	struct proto *proto;
	loff_t i = 0;

	list_for_each_entry(proto, &proto_list, node)
		if (i++ == pos)
			goto out;

	proto = NULL;
out:
	return proto;
}

static void *proto_seq_start(struct seq_file *seq, loff_t *pos)
{
	read_lock(&proto_list_lock);
	return *pos ? proto_get_idx(*pos - 1) : SEQ_START_TOKEN;
}

static void *proto_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	++*pos;
	return v == SEQ_START_TOKEN ? proto_head() : proto_next(v);
}

static void proto_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock(&proto_list_lock);
}

static char proto_method_implemented(const void *method)
{
	return method == NULL ? 'n' : 'y';
}

static void proto_seq_printf(struct seq_file *seq, struct proto *proto)
{
	seq_printf(seq, "%-9s %4u %6d  %6d   %-3s %6u   %-3s  %-10s "
			"%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n",
		   proto->name,
		   proto->obj_size,
		   proto->sockets_allocated != NULL ? atomic_read(proto->sockets_allocated) : -1,
		   proto->memory_allocated != NULL ? atomic_read(proto->memory_allocated) : -1,
		   proto->memory_pressure != NULL ? *proto->memory_pressure ? "yes" : "no" : "NI",
		   proto->max_header,
		   proto->slab == NULL ? "no" : "yes",
		   module_name(proto->owner),
		   proto_method_implemented(proto->close),
		   proto_method_implemented(proto->connect),
		   proto_method_implemented(proto->disconnect),
		   proto_method_implemented(proto->accept),
		   proto_method_implemented(proto->ioctl),
		   proto_method_implemented(proto->init),
		   proto_method_implemented(proto->destroy),
		   proto_method_implemented(proto->shutdown),
		   proto_method_implemented(proto->setsockopt),
		   proto_method_implemented(proto->getsockopt),
		   proto_method_implemented(proto->sendmsg),
		   proto_method_implemented(proto->recvmsg),
		   proto_method_implemented(proto->sendpage),
		   proto_method_implemented(proto->bind),
		   proto_method_implemented(proto->backlog_rcv),
		   proto_method_implemented(proto->hash),
		   proto_method_implemented(proto->unhash),
		   proto_method_implemented(proto->get_port),
		   proto_method_implemented(proto->enter_memory_pressure));
}

static int proto_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN)
		seq_printf(seq, "%-9s %-4s %-8s %-6s %-5s %-7s %-4s %-10s %s",
			   "protocol",
			   "size",
			   "sockets",
			   "memory",
			   "press",
			   "maxhdr",
			   "slab",
			   "module",
			   "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n");
	else
		proto_seq_printf(seq, v);
	return 0;
}

static struct seq_operations proto_seq_ops = {
	.start  = proto_seq_start,
	.next   = proto_seq_next,
	.stop   = proto_seq_stop,
	.show   = proto_seq_show,
};

static int proto_seq_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &proto_seq_ops);
}

static struct file_operations proto_seq_fops = {
	.owner		= THIS_MODULE,
	.open		= proto_seq_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static int __init proto_init(void)
{
	/* register /proc/net/protocols */
	return proc_net_fops_create("protocols", S_IRUGO, &proto_seq_fops) == NULL ? -ENOBUFS : 0;
}

subsys_initcall(proto_init);

#endif /* PROC_FS */

EXPORT_SYMBOL(sk_alloc);
EXPORT_SYMBOL(sk_free);
EXPORT_SYMBOL(sk_send_sigurg);
EXPORT_SYMBOL(sock_alloc_send_skb);
EXPORT_SYMBOL(sock_init_data);
EXPORT_SYMBOL(sock_kfree_s);
EXPORT_SYMBOL(sock_kmalloc);
EXPORT_SYMBOL(sock_no_accept);
EXPORT_SYMBOL(sock_no_bind);
EXPORT_SYMBOL(sock_no_connect);
EXPORT_SYMBOL(sock_no_getname);
EXPORT_SYMBOL(sock_no_getsockopt);
EXPORT_SYMBOL(sock_no_ioctl);
EXPORT_SYMBOL(sock_no_listen);
EXPORT_SYMBOL(sock_no_mmap);
EXPORT_SYMBOL(sock_no_poll);
EXPORT_SYMBOL(sock_no_recvmsg);
EXPORT_SYMBOL(sock_no_sendmsg);
EXPORT_SYMBOL(sock_no_sendpage);
EXPORT_SYMBOL(sock_no_setsockopt);
EXPORT_SYMBOL(sock_no_shutdown);
EXPORT_SYMBOL(sock_no_socketpair);
EXPORT_SYMBOL(sock_rfree);
EXPORT_SYMBOL(sock_setsockopt);
EXPORT_SYMBOL(sock_wfree);
EXPORT_SYMBOL(sock_wmalloc);
EXPORT_SYMBOL(sock_i_uid);
EXPORT_SYMBOL(sock_i_ino);
EXPORT_SYMBOL(sysctl_optmem_max);
1970
#ifdef CONFIG_SYSCTL
L
Linus Torvalds 已提交
1971 1972 1973
EXPORT_SYMBOL(sysctl_rmem_max);
EXPORT_SYMBOL(sysctl_wmem_max);
#endif