ip_vs_ctl.c 54.9 KB
Newer Older
L
Linus Torvalds 已提交
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
/*
 * IPVS         An implementation of the IP virtual server support for the
 *              LINUX operating system.  IPVS is now implemented as a module
 *              over the NetFilter framework. IPVS can be used to build a
 *              high-performance and highly available server based on a
 *              cluster of servers.
 *
 * Version:     $Id: ip_vs_ctl.c,v 1.36 2003/06/08 09:31:19 wensong Exp $
 *
 * Authors:     Wensong Zhang <wensong@linuxvirtualserver.org>
 *              Peter Kese <peter.kese@ijs.si>
 *              Julian Anastasov <ja@ssi.bg>
 *
 *              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.
 *
 * Changes:
 *
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
26
#include <linux/capability.h>
L
Linus Torvalds 已提交
27 28 29 30 31 32 33 34 35
#include <linux/fs.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/workqueue.h>
#include <linux/swap.h>
#include <linux/seq_file.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv4.h>
36
#include <linux/mutex.h>
L
Linus Torvalds 已提交
37

38
#include <net/net_namespace.h>
L
Linus Torvalds 已提交
39
#include <net/ip.h>
40
#include <net/route.h>
L
Linus Torvalds 已提交
41 42 43 44 45 46 47
#include <net/sock.h>

#include <asm/uaccess.h>

#include <net/ip_vs.h>

/* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */
48
static DEFINE_MUTEX(__ip_vs_mutex);
L
Linus Torvalds 已提交
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 94 95

/* lock for service table */
static DEFINE_RWLOCK(__ip_vs_svc_lock);

/* lock for table with the real services */
static DEFINE_RWLOCK(__ip_vs_rs_lock);

/* lock for state and timeout tables */
static DEFINE_RWLOCK(__ip_vs_securetcp_lock);

/* lock for drop entry handling */
static DEFINE_SPINLOCK(__ip_vs_dropentry_lock);

/* lock for drop packet handling */
static DEFINE_SPINLOCK(__ip_vs_droppacket_lock);

/* 1/rate drop and drop-entry variables */
int ip_vs_drop_rate = 0;
int ip_vs_drop_counter = 0;
static atomic_t ip_vs_dropentry = ATOMIC_INIT(0);

/* number of virtual services */
static int ip_vs_num_services = 0;

/* sysctl variables */
static int sysctl_ip_vs_drop_entry = 0;
static int sysctl_ip_vs_drop_packet = 0;
static int sysctl_ip_vs_secure_tcp = 0;
static int sysctl_ip_vs_amemthresh = 1024;
static int sysctl_ip_vs_am_droprate = 10;
int sysctl_ip_vs_cache_bypass = 0;
int sysctl_ip_vs_expire_nodest_conn = 0;
int sysctl_ip_vs_expire_quiescent_template = 0;
int sysctl_ip_vs_sync_threshold[2] = { 3, 50 };
int sysctl_ip_vs_nat_icmp_send = 0;


#ifdef CONFIG_IP_VS_DEBUG
static int sysctl_ip_vs_debug_level = 0;

int ip_vs_get_debug_level(void)
{
	return sysctl_ip_vs_debug_level;
}
#endif

/*
96 97
 *	update_defense_level is called from keventd and from sysctl,
 *	so it needs to protect itself from softirqs
L
Linus Torvalds 已提交
98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116
 */
static void update_defense_level(void)
{
	struct sysinfo i;
	static int old_secure_tcp = 0;
	int availmem;
	int nomem;
	int to_change = -1;

	/* we only count free and buffered memory (in pages) */
	si_meminfo(&i);
	availmem = i.freeram + i.bufferram;
	/* however in linux 2.5 the i.bufferram is total page cache size,
	   we need adjust it */
	/* si_swapinfo(&i); */
	/* availmem = availmem - (i.totalswap - i.freeswap); */

	nomem = (availmem < sysctl_ip_vs_amemthresh);

117 118
	local_bh_disable();

L
Linus Torvalds 已提交
119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214
	/* drop_entry */
	spin_lock(&__ip_vs_dropentry_lock);
	switch (sysctl_ip_vs_drop_entry) {
	case 0:
		atomic_set(&ip_vs_dropentry, 0);
		break;
	case 1:
		if (nomem) {
			atomic_set(&ip_vs_dropentry, 1);
			sysctl_ip_vs_drop_entry = 2;
		} else {
			atomic_set(&ip_vs_dropentry, 0);
		}
		break;
	case 2:
		if (nomem) {
			atomic_set(&ip_vs_dropentry, 1);
		} else {
			atomic_set(&ip_vs_dropentry, 0);
			sysctl_ip_vs_drop_entry = 1;
		};
		break;
	case 3:
		atomic_set(&ip_vs_dropentry, 1);
		break;
	}
	spin_unlock(&__ip_vs_dropentry_lock);

	/* drop_packet */
	spin_lock(&__ip_vs_droppacket_lock);
	switch (sysctl_ip_vs_drop_packet) {
	case 0:
		ip_vs_drop_rate = 0;
		break;
	case 1:
		if (nomem) {
			ip_vs_drop_rate = ip_vs_drop_counter
				= sysctl_ip_vs_amemthresh /
				(sysctl_ip_vs_amemthresh-availmem);
			sysctl_ip_vs_drop_packet = 2;
		} else {
			ip_vs_drop_rate = 0;
		}
		break;
	case 2:
		if (nomem) {
			ip_vs_drop_rate = ip_vs_drop_counter
				= sysctl_ip_vs_amemthresh /
				(sysctl_ip_vs_amemthresh-availmem);
		} else {
			ip_vs_drop_rate = 0;
			sysctl_ip_vs_drop_packet = 1;
		}
		break;
	case 3:
		ip_vs_drop_rate = sysctl_ip_vs_am_droprate;
		break;
	}
	spin_unlock(&__ip_vs_droppacket_lock);

	/* secure_tcp */
	write_lock(&__ip_vs_securetcp_lock);
	switch (sysctl_ip_vs_secure_tcp) {
	case 0:
		if (old_secure_tcp >= 2)
			to_change = 0;
		break;
	case 1:
		if (nomem) {
			if (old_secure_tcp < 2)
				to_change = 1;
			sysctl_ip_vs_secure_tcp = 2;
		} else {
			if (old_secure_tcp >= 2)
				to_change = 0;
		}
		break;
	case 2:
		if (nomem) {
			if (old_secure_tcp < 2)
				to_change = 1;
		} else {
			if (old_secure_tcp >= 2)
				to_change = 0;
			sysctl_ip_vs_secure_tcp = 1;
		}
		break;
	case 3:
		if (old_secure_tcp < 2)
			to_change = 1;
		break;
	}
	old_secure_tcp = sysctl_ip_vs_secure_tcp;
	if (to_change >= 0)
		ip_vs_protocol_timeout_change(sysctl_ip_vs_secure_tcp>1);
	write_unlock(&__ip_vs_securetcp_lock);
215 216

	local_bh_enable();
L
Linus Torvalds 已提交
217 218 219 220 221 222 223
}


/*
 *	Timer for checking the defense
 */
#define DEFENSE_TIMER_PERIOD	1*HZ
D
David Howells 已提交
224 225
static void defense_work_handler(struct work_struct *work);
static DECLARE_DELAYED_WORK(defense_work, defense_work_handler);
L
Linus Torvalds 已提交
226

D
David Howells 已提交
227
static void defense_work_handler(struct work_struct *work)
L
Linus Torvalds 已提交
228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285
{
	update_defense_level();
	if (atomic_read(&ip_vs_dropentry))
		ip_vs_random_dropentry();

	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);
}

int
ip_vs_use_count_inc(void)
{
	return try_module_get(THIS_MODULE);
}

void
ip_vs_use_count_dec(void)
{
	module_put(THIS_MODULE);
}


/*
 *	Hash table: for virtual service lookups
 */
#define IP_VS_SVC_TAB_BITS 8
#define IP_VS_SVC_TAB_SIZE (1 << IP_VS_SVC_TAB_BITS)
#define IP_VS_SVC_TAB_MASK (IP_VS_SVC_TAB_SIZE - 1)

/* the service table hashed by <protocol, addr, port> */
static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE];
/* the service table hashed by fwmark */
static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE];

/*
 *	Hash table: for real service lookups
 */
#define IP_VS_RTAB_BITS 4
#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS)
#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1)

static struct list_head ip_vs_rtable[IP_VS_RTAB_SIZE];

/*
 *	Trash for destinations
 */
static LIST_HEAD(ip_vs_dest_trash);

/*
 *	FTP & NULL virtual service counters
 */
static atomic_t ip_vs_ftpsvc_counter = ATOMIC_INIT(0);
static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0);


/*
 *	Returns hash value for virtual service
 */
static __inline__ unsigned
A
Al Viro 已提交
286
ip_vs_svc_hashkey(unsigned proto, __be32 addr, __be16 port)
L
Linus Torvalds 已提交
287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367
{
	register unsigned porth = ntohs(port);

	return (proto^ntohl(addr)^(porth>>IP_VS_SVC_TAB_BITS)^porth)
		& IP_VS_SVC_TAB_MASK;
}

/*
 *	Returns hash value of fwmark for virtual service lookup
 */
static __inline__ unsigned ip_vs_svc_fwm_hashkey(__u32 fwmark)
{
	return fwmark & IP_VS_SVC_TAB_MASK;
}

/*
 *	Hashes a service in the ip_vs_svc_table by <proto,addr,port>
 *	or in the ip_vs_svc_fwm_table by fwmark.
 *	Should be called with locked tables.
 */
static int ip_vs_svc_hash(struct ip_vs_service *svc)
{
	unsigned hash;

	if (svc->flags & IP_VS_SVC_F_HASHED) {
		IP_VS_ERR("ip_vs_svc_hash(): request for already hashed, "
			  "called from %p\n", __builtin_return_address(0));
		return 0;
	}

	if (svc->fwmark == 0) {
		/*
		 *  Hash it by <protocol,addr,port> in ip_vs_svc_table
		 */
		hash = ip_vs_svc_hashkey(svc->protocol, svc->addr, svc->port);
		list_add(&svc->s_list, &ip_vs_svc_table[hash]);
	} else {
		/*
		 *  Hash it by fwmark in ip_vs_svc_fwm_table
		 */
		hash = ip_vs_svc_fwm_hashkey(svc->fwmark);
		list_add(&svc->f_list, &ip_vs_svc_fwm_table[hash]);
	}

	svc->flags |= IP_VS_SVC_F_HASHED;
	/* increase its refcnt because it is referenced by the svc table */
	atomic_inc(&svc->refcnt);
	return 1;
}


/*
 *	Unhashes a service from ip_vs_svc_table/ip_vs_svc_fwm_table.
 *	Should be called with locked tables.
 */
static int ip_vs_svc_unhash(struct ip_vs_service *svc)
{
	if (!(svc->flags & IP_VS_SVC_F_HASHED)) {
		IP_VS_ERR("ip_vs_svc_unhash(): request for unhash flagged, "
			  "called from %p\n", __builtin_return_address(0));
		return 0;
	}

	if (svc->fwmark == 0) {
		/* Remove it from the ip_vs_svc_table table */
		list_del(&svc->s_list);
	} else {
		/* Remove it from the ip_vs_svc_fwm_table table */
		list_del(&svc->f_list);
	}

	svc->flags &= ~IP_VS_SVC_F_HASHED;
	atomic_dec(&svc->refcnt);
	return 1;
}


/*
 *	Get service by {proto,addr,port} in the service table.
 */
static __inline__ struct ip_vs_service *
A
Al Viro 已提交
368
__ip_vs_service_get(__u16 protocol, __be32 vaddr, __be16 vport)
L
Linus Torvalds 已提交
369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412
{
	unsigned hash;
	struct ip_vs_service *svc;

	/* Check for "full" addressed entries */
	hash = ip_vs_svc_hashkey(protocol, vaddr, vport);

	list_for_each_entry(svc, &ip_vs_svc_table[hash], s_list){
		if ((svc->addr == vaddr)
		    && (svc->port == vport)
		    && (svc->protocol == protocol)) {
			/* HIT */
			atomic_inc(&svc->usecnt);
			return svc;
		}
	}

	return NULL;
}


/*
 *	Get service by {fwmark} in the service table.
 */
static __inline__ struct ip_vs_service *__ip_vs_svc_fwm_get(__u32 fwmark)
{
	unsigned hash;
	struct ip_vs_service *svc;

	/* Check for fwmark addressed entries */
	hash = ip_vs_svc_fwm_hashkey(fwmark);

	list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) {
		if (svc->fwmark == fwmark) {
			/* HIT */
			atomic_inc(&svc->usecnt);
			return svc;
		}
	}

	return NULL;
}

struct ip_vs_service *
A
Al Viro 已提交
413
ip_vs_service_get(__u32 fwmark, __u16 protocol, __be32 vaddr, __be16 vport)
L
Linus Torvalds 已提交
414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452
{
	struct ip_vs_service *svc;

	read_lock(&__ip_vs_svc_lock);

	/*
	 *	Check the table hashed by fwmark first
	 */
	if (fwmark && (svc = __ip_vs_svc_fwm_get(fwmark)))
		goto out;

	/*
	 *	Check the table hashed by <protocol,addr,port>
	 *	for "full" addressed entries
	 */
	svc = __ip_vs_service_get(protocol, vaddr, vport);

	if (svc == NULL
	    && protocol == IPPROTO_TCP
	    && atomic_read(&ip_vs_ftpsvc_counter)
	    && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) {
		/*
		 * Check if ftp service entry exists, the packet
		 * might belong to FTP data connections.
		 */
		svc = __ip_vs_service_get(protocol, vaddr, FTPPORT);
	}

	if (svc == NULL
	    && atomic_read(&ip_vs_nullsvc_counter)) {
		/*
		 * Check if the catch-all port (port zero) exists
		 */
		svc = __ip_vs_service_get(protocol, vaddr, 0);
	}

  out:
	read_unlock(&__ip_vs_svc_lock);

453
	IP_VS_DBG(9, "lookup service: fwm %u %s %u.%u.%u.%u:%u %s\n",
L
Linus Torvalds 已提交
454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482
		  fwmark, ip_vs_proto_name(protocol),
		  NIPQUAD(vaddr), ntohs(vport),
		  svc?"hit":"not hit");

	return svc;
}


static inline void
__ip_vs_bind_svc(struct ip_vs_dest *dest, struct ip_vs_service *svc)
{
	atomic_inc(&svc->refcnt);
	dest->svc = svc;
}

static inline void
__ip_vs_unbind_svc(struct ip_vs_dest *dest)
{
	struct ip_vs_service *svc = dest->svc;

	dest->svc = NULL;
	if (atomic_dec_and_test(&svc->refcnt))
		kfree(svc);
}


/*
 *	Returns hash value for real service
 */
A
Al Viro 已提交
483
static __inline__ unsigned ip_vs_rs_hashkey(__be32 addr, __be16 port)
L
Linus Torvalds 已提交
484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533
{
	register unsigned porth = ntohs(port);

	return (ntohl(addr)^(porth>>IP_VS_RTAB_BITS)^porth)
		& IP_VS_RTAB_MASK;
}

/*
 *	Hashes ip_vs_dest in ip_vs_rtable by <proto,addr,port>.
 *	should be called with locked tables.
 */
static int ip_vs_rs_hash(struct ip_vs_dest *dest)
{
	unsigned hash;

	if (!list_empty(&dest->d_list)) {
		return 0;
	}

	/*
	 *	Hash by proto,addr,port,
	 *	which are the parameters of the real service.
	 */
	hash = ip_vs_rs_hashkey(dest->addr, dest->port);
	list_add(&dest->d_list, &ip_vs_rtable[hash]);

	return 1;
}

/*
 *	UNhashes ip_vs_dest from ip_vs_rtable.
 *	should be called with locked tables.
 */
static int ip_vs_rs_unhash(struct ip_vs_dest *dest)
{
	/*
	 * Remove it from the ip_vs_rtable table.
	 */
	if (!list_empty(&dest->d_list)) {
		list_del(&dest->d_list);
		INIT_LIST_HEAD(&dest->d_list);
	}

	return 1;
}

/*
 *	Lookup real service by <proto,addr,port> in the real service table.
 */
struct ip_vs_dest *
A
Al Viro 已提交
534
ip_vs_lookup_real_service(__u16 protocol, __be32 daddr, __be16 dport)
L
Linus Torvalds 已提交
535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564
{
	unsigned hash;
	struct ip_vs_dest *dest;

	/*
	 *	Check for "full" addressed entries
	 *	Return the first found entry
	 */
	hash = ip_vs_rs_hashkey(daddr, dport);

	read_lock(&__ip_vs_rs_lock);
	list_for_each_entry(dest, &ip_vs_rtable[hash], d_list) {
		if ((dest->addr == daddr)
		    && (dest->port == dport)
		    && ((dest->protocol == protocol) ||
			dest->vfwmark)) {
			/* HIT */
			read_unlock(&__ip_vs_rs_lock);
			return dest;
		}
	}
	read_unlock(&__ip_vs_rs_lock);

	return NULL;
}

/*
 *	Lookup destination by {addr,port} in the given service
 */
static struct ip_vs_dest *
A
Al Viro 已提交
565
ip_vs_lookup_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport)
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
{
	struct ip_vs_dest *dest;

	/*
	 * Find the destination for the given service
	 */
	list_for_each_entry(dest, &svc->destinations, n_list) {
		if ((dest->addr == daddr) && (dest->port == dport)) {
			/* HIT */
			return dest;
		}
	}

	return NULL;
}


/*
 *  Lookup dest by {svc,addr,port} in the destination trash.
 *  The destination trash is used to hold the destinations that are removed
 *  from the service table but are still referenced by some conn entries.
 *  The reason to add the destination trash is when the dest is temporary
 *  down (either by administrator or by monitor program), the dest can be
 *  picked back from the trash, the remaining connections to the dest can
 *  continue, and the counting information of the dest is also useful for
 *  scheduling.
 */
static struct ip_vs_dest *
A
Al Viro 已提交
594
ip_vs_trash_get_dest(struct ip_vs_service *svc, __be32 daddr, __be16 dport)
L
Linus Torvalds 已提交
595 596 597 598 599 600 601 602
{
	struct ip_vs_dest *dest, *nxt;

	/*
	 * Find the destination in trash
	 */
	list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) {
		IP_VS_DBG(3, "Destination %u/%u.%u.%u.%u:%u still in trash, "
603
			  "dest->refcnt=%d\n",
L
Linus Torvalds 已提交
604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737
			  dest->vfwmark,
			  NIPQUAD(dest->addr), ntohs(dest->port),
			  atomic_read(&dest->refcnt));
		if (dest->addr == daddr &&
		    dest->port == dport &&
		    dest->vfwmark == svc->fwmark &&
		    dest->protocol == svc->protocol &&
		    (svc->fwmark ||
		     (dest->vaddr == svc->addr &&
		      dest->vport == svc->port))) {
			/* HIT */
			return dest;
		}

		/*
		 * Try to purge the destination from trash if not referenced
		 */
		if (atomic_read(&dest->refcnt) == 1) {
			IP_VS_DBG(3, "Removing destination %u/%u.%u.%u.%u:%u "
				  "from trash\n",
				  dest->vfwmark,
				  NIPQUAD(dest->addr), ntohs(dest->port));
			list_del(&dest->n_list);
			ip_vs_dst_reset(dest);
			__ip_vs_unbind_svc(dest);
			kfree(dest);
		}
	}

	return NULL;
}


/*
 *  Clean up all the destinations in the trash
 *  Called by the ip_vs_control_cleanup()
 *
 *  When the ip_vs_control_clearup is activated by ipvs module exit,
 *  the service tables must have been flushed and all the connections
 *  are expired, and the refcnt of each destination in the trash must
 *  be 1, so we simply release them here.
 */
static void ip_vs_trash_cleanup(void)
{
	struct ip_vs_dest *dest, *nxt;

	list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) {
		list_del(&dest->n_list);
		ip_vs_dst_reset(dest);
		__ip_vs_unbind_svc(dest);
		kfree(dest);
	}
}


static void
ip_vs_zero_stats(struct ip_vs_stats *stats)
{
	spin_lock_bh(&stats->lock);
	memset(stats, 0, (char *)&stats->lock - (char *)stats);
	spin_unlock_bh(&stats->lock);
	ip_vs_zero_estimator(stats);
}

/*
 *	Update a destination in the given service
 */
static void
__ip_vs_update_dest(struct ip_vs_service *svc,
		    struct ip_vs_dest *dest, struct ip_vs_dest_user *udest)
{
	int conn_flags;

	/* set the weight and the flags */
	atomic_set(&dest->weight, udest->weight);
	conn_flags = udest->conn_flags | IP_VS_CONN_F_INACTIVE;

	/* check if local node and update the flags */
	if (inet_addr_type(udest->addr) == RTN_LOCAL) {
		conn_flags = (conn_flags & ~IP_VS_CONN_F_FWD_MASK)
			| IP_VS_CONN_F_LOCALNODE;
	}

	/* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */
	if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != 0) {
		conn_flags |= IP_VS_CONN_F_NOOUTPUT;
	} else {
		/*
		 *    Put the real service in ip_vs_rtable if not present.
		 *    For now only for NAT!
		 */
		write_lock_bh(&__ip_vs_rs_lock);
		ip_vs_rs_hash(dest);
		write_unlock_bh(&__ip_vs_rs_lock);
	}
	atomic_set(&dest->conn_flags, conn_flags);

	/* bind the service */
	if (!dest->svc) {
		__ip_vs_bind_svc(dest, svc);
	} else {
		if (dest->svc != svc) {
			__ip_vs_unbind_svc(dest);
			ip_vs_zero_stats(&dest->stats);
			__ip_vs_bind_svc(dest, svc);
		}
	}

	/* set the dest status flags */
	dest->flags |= IP_VS_DEST_F_AVAILABLE;

	if (udest->u_threshold == 0 || udest->u_threshold > dest->u_threshold)
		dest->flags &= ~IP_VS_DEST_F_OVERLOAD;
	dest->u_threshold = udest->u_threshold;
	dest->l_threshold = udest->l_threshold;
}


/*
 *	Create a destination for the given service
 */
static int
ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest,
	       struct ip_vs_dest **dest_p)
{
	struct ip_vs_dest *dest;
	unsigned atype;

	EnterFunction(2);

	atype = inet_addr_type(udest->addr);
	if (atype != RTN_LOCAL && atype != RTN_UNICAST)
		return -EINVAL;

738
	dest = kzalloc(sizeof(struct ip_vs_dest), GFP_ATOMIC);
L
Linus Torvalds 已提交
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
	if (dest == NULL) {
		IP_VS_ERR("ip_vs_new_dest: kmalloc failed.\n");
		return -ENOMEM;
	}

	dest->protocol = svc->protocol;
	dest->vaddr = svc->addr;
	dest->vport = svc->port;
	dest->vfwmark = svc->fwmark;
	dest->addr = udest->addr;
	dest->port = udest->port;

	atomic_set(&dest->activeconns, 0);
	atomic_set(&dest->inactconns, 0);
	atomic_set(&dest->persistconns, 0);
	atomic_set(&dest->refcnt, 0);

	INIT_LIST_HEAD(&dest->d_list);
	spin_lock_init(&dest->dst_lock);
	spin_lock_init(&dest->stats.lock);
	__ip_vs_update_dest(svc, dest, udest);
	ip_vs_new_estimator(&dest->stats);

	*dest_p = dest;

	LeaveFunction(2);
	return 0;
}


/*
 *	Add a destination into an existing service
 */
static int
ip_vs_add_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest)
{
	struct ip_vs_dest *dest;
A
Al Viro 已提交
776 777
	__be32 daddr = udest->addr;
	__be16 dport = udest->port;
L
Linus Torvalds 已提交
778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808
	int ret;

	EnterFunction(2);

	if (udest->weight < 0) {
		IP_VS_ERR("ip_vs_add_dest(): server weight less than zero\n");
		return -ERANGE;
	}

	if (udest->l_threshold > udest->u_threshold) {
		IP_VS_ERR("ip_vs_add_dest(): lower threshold is higher than "
			  "upper threshold\n");
		return -ERANGE;
	}

	/*
	 * Check if the dest already exists in the list
	 */
	dest = ip_vs_lookup_dest(svc, daddr, dport);
	if (dest != NULL) {
		IP_VS_DBG(1, "ip_vs_add_dest(): dest already exists\n");
		return -EEXIST;
	}

	/*
	 * Check if the dest already exists in the trash and
	 * is from the same service
	 */
	dest = ip_vs_trash_get_dest(svc, daddr, dport);
	if (dest != NULL) {
		IP_VS_DBG(3, "Get destination %u.%u.%u.%u:%u from trash, "
809
			  "dest->refcnt=%d, service %u/%u.%u.%u.%u:%u\n",
L
Linus Torvalds 已提交
810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881
			  NIPQUAD(daddr), ntohs(dport),
			  atomic_read(&dest->refcnt),
			  dest->vfwmark,
			  NIPQUAD(dest->vaddr),
			  ntohs(dest->vport));
		__ip_vs_update_dest(svc, dest, udest);

		/*
		 * Get the destination from the trash
		 */
		list_del(&dest->n_list);

		ip_vs_new_estimator(&dest->stats);

		write_lock_bh(&__ip_vs_svc_lock);

		/*
		 * Wait until all other svc users go away.
		 */
		IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1);

		list_add(&dest->n_list, &svc->destinations);
		svc->num_dests++;

		/* call the update_service function of its scheduler */
		svc->scheduler->update_service(svc);

		write_unlock_bh(&__ip_vs_svc_lock);
		return 0;
	}

	/*
	 * Allocate and initialize the dest structure
	 */
	ret = ip_vs_new_dest(svc, udest, &dest);
	if (ret) {
		return ret;
	}

	/*
	 * Add the dest entry into the list
	 */
	atomic_inc(&dest->refcnt);

	write_lock_bh(&__ip_vs_svc_lock);

	/*
	 * Wait until all other svc users go away.
	 */
	IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1);

	list_add(&dest->n_list, &svc->destinations);
	svc->num_dests++;

	/* call the update_service function of its scheduler */
	svc->scheduler->update_service(svc);

	write_unlock_bh(&__ip_vs_svc_lock);

	LeaveFunction(2);

	return 0;
}


/*
 *	Edit a destination in the given service
 */
static int
ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user *udest)
{
	struct ip_vs_dest *dest;
A
Al Viro 已提交
882 883
	__be32 daddr = udest->addr;
	__be16 dport = udest->port;
L
Linus Torvalds 已提交
884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911

	EnterFunction(2);

	if (udest->weight < 0) {
		IP_VS_ERR("ip_vs_edit_dest(): server weight less than zero\n");
		return -ERANGE;
	}

	if (udest->l_threshold > udest->u_threshold) {
		IP_VS_ERR("ip_vs_edit_dest(): lower threshold is higher than "
			  "upper threshold\n");
		return -ERANGE;
	}

	/*
	 *  Lookup the destination list
	 */
	dest = ip_vs_lookup_dest(svc, daddr, dport);
	if (dest == NULL) {
		IP_VS_DBG(1, "ip_vs_edit_dest(): dest doesn't exist\n");
		return -ENOENT;
	}

	__ip_vs_update_dest(svc, dest, udest);

	write_lock_bh(&__ip_vs_svc_lock);

	/* Wait until all other svc users go away */
912
	IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1);
L
Linus Torvalds 已提交
913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953

	/* call the update_service, because server weight may be changed */
	svc->scheduler->update_service(svc);

	write_unlock_bh(&__ip_vs_svc_lock);

	LeaveFunction(2);

	return 0;
}


/*
 *	Delete a destination (must be already unlinked from the service)
 */
static void __ip_vs_del_dest(struct ip_vs_dest *dest)
{
	ip_vs_kill_estimator(&dest->stats);

	/*
	 *  Remove it from the d-linked list with the real services.
	 */
	write_lock_bh(&__ip_vs_rs_lock);
	ip_vs_rs_unhash(dest);
	write_unlock_bh(&__ip_vs_rs_lock);

	/*
	 *  Decrease the refcnt of the dest, and free the dest
	 *  if nobody refers to it (refcnt=0). Otherwise, throw
	 *  the destination into the trash.
	 */
	if (atomic_dec_and_test(&dest->refcnt)) {
		ip_vs_dst_reset(dest);
		/* simply decrease svc->refcnt here, let the caller check
		   and release the service if nobody refers to it.
		   Only user context can release destination and service,
		   and only one user context can update virtual service at a
		   time, so the operation here is OK */
		atomic_dec(&dest->svc->refcnt);
		kfree(dest);
	} else {
954 955
		IP_VS_DBG(3, "Moving dest %u.%u.%u.%u:%u into trash, "
			  "dest->refcnt=%d\n",
L
Linus Torvalds 已提交
956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993
			  NIPQUAD(dest->addr), ntohs(dest->port),
			  atomic_read(&dest->refcnt));
		list_add(&dest->n_list, &ip_vs_dest_trash);
		atomic_inc(&dest->refcnt);
	}
}


/*
 *	Unlink a destination from the given service
 */
static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
				struct ip_vs_dest *dest,
				int svcupd)
{
	dest->flags &= ~IP_VS_DEST_F_AVAILABLE;

	/*
	 *  Remove it from the d-linked destination list.
	 */
	list_del(&dest->n_list);
	svc->num_dests--;
	if (svcupd) {
		/*
		 *  Call the update_service function of its scheduler
		 */
		svc->scheduler->update_service(svc);
	}
}


/*
 *	Delete a destination server in the given service
 */
static int
ip_vs_del_dest(struct ip_vs_service *svc,struct ip_vs_dest_user *udest)
{
	struct ip_vs_dest *dest;
A
Al Viro 已提交
994 995
	__be32 daddr = udest->addr;
	__be16 dport = udest->port;
L
Linus Torvalds 已提交
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 1048 1049 1050 1051

	EnterFunction(2);

	dest = ip_vs_lookup_dest(svc, daddr, dport);
	if (dest == NULL) {
		IP_VS_DBG(1, "ip_vs_del_dest(): destination not found!\n");
		return -ENOENT;
	}

	write_lock_bh(&__ip_vs_svc_lock);

	/*
	 *	Wait until all other svc users go away.
	 */
	IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1);

	/*
	 *	Unlink dest from the service
	 */
	__ip_vs_unlink_dest(svc, dest, 1);

	write_unlock_bh(&__ip_vs_svc_lock);

	/*
	 *	Delete the destination
	 */
	__ip_vs_del_dest(dest);

	LeaveFunction(2);

	return 0;
}


/*
 *	Add a service into the service hash table
 */
static int
ip_vs_add_service(struct ip_vs_service_user *u, struct ip_vs_service **svc_p)
{
	int ret = 0;
	struct ip_vs_scheduler *sched = NULL;
	struct ip_vs_service *svc = NULL;

	/* increase the module use count */
	ip_vs_use_count_inc();

	/* Lookup the scheduler by 'u->sched_name' */
	sched = ip_vs_scheduler_get(u->sched_name);
	if (sched == NULL) {
		IP_VS_INFO("Scheduler module ip_vs_%s not found\n",
			   u->sched_name);
		ret = -ENOENT;
		goto out_mod_dec;
	}

1052
	svc = kzalloc(sizeof(struct ip_vs_service), GFP_ATOMIC);
L
Linus Torvalds 已提交
1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 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 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 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 1275 1276 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 1446 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 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 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 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 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
	if (svc == NULL) {
		IP_VS_DBG(1, "ip_vs_add_service: kmalloc failed.\n");
		ret = -ENOMEM;
		goto out_err;
	}

	/* I'm the first user of the service */
	atomic_set(&svc->usecnt, 1);
	atomic_set(&svc->refcnt, 0);

	svc->protocol = u->protocol;
	svc->addr = u->addr;
	svc->port = u->port;
	svc->fwmark = u->fwmark;
	svc->flags = u->flags;
	svc->timeout = u->timeout * HZ;
	svc->netmask = u->netmask;

	INIT_LIST_HEAD(&svc->destinations);
	rwlock_init(&svc->sched_lock);
	spin_lock_init(&svc->stats.lock);

	/* Bind the scheduler */
	ret = ip_vs_bind_scheduler(svc, sched);
	if (ret)
		goto out_err;
	sched = NULL;

	/* Update the virtual service counters */
	if (svc->port == FTPPORT)
		atomic_inc(&ip_vs_ftpsvc_counter);
	else if (svc->port == 0)
		atomic_inc(&ip_vs_nullsvc_counter);

	ip_vs_new_estimator(&svc->stats);
	ip_vs_num_services++;

	/* Hash the service into the service table */
	write_lock_bh(&__ip_vs_svc_lock);
	ip_vs_svc_hash(svc);
	write_unlock_bh(&__ip_vs_svc_lock);

	*svc_p = svc;
	return 0;

  out_err:
	if (svc != NULL) {
		if (svc->scheduler)
			ip_vs_unbind_scheduler(svc);
		if (svc->inc) {
			local_bh_disable();
			ip_vs_app_inc_put(svc->inc);
			local_bh_enable();
		}
		kfree(svc);
	}
	ip_vs_scheduler_put(sched);

  out_mod_dec:
	/* decrease the module use count */
	ip_vs_use_count_dec();

	return ret;
}


/*
 *	Edit a service and bind it with a new scheduler
 */
static int
ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user *u)
{
	struct ip_vs_scheduler *sched, *old_sched;
	int ret = 0;

	/*
	 * Lookup the scheduler, by 'u->sched_name'
	 */
	sched = ip_vs_scheduler_get(u->sched_name);
	if (sched == NULL) {
		IP_VS_INFO("Scheduler module ip_vs_%s not found\n",
			   u->sched_name);
		return -ENOENT;
	}
	old_sched = sched;

	write_lock_bh(&__ip_vs_svc_lock);

	/*
	 * Wait until all other svc users go away.
	 */
	IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1);

	/*
	 * Set the flags and timeout value
	 */
	svc->flags = u->flags | IP_VS_SVC_F_HASHED;
	svc->timeout = u->timeout * HZ;
	svc->netmask = u->netmask;

	old_sched = svc->scheduler;
	if (sched != old_sched) {
		/*
		 * Unbind the old scheduler
		 */
		if ((ret = ip_vs_unbind_scheduler(svc))) {
			old_sched = sched;
			goto out;
		}

		/*
		 * Bind the new scheduler
		 */
		if ((ret = ip_vs_bind_scheduler(svc, sched))) {
			/*
			 * If ip_vs_bind_scheduler fails, restore the old
			 * scheduler.
			 * The main reason of failure is out of memory.
			 *
			 * The question is if the old scheduler can be
			 * restored all the time. TODO: if it cannot be
			 * restored some time, we must delete the service,
			 * otherwise the system may crash.
			 */
			ip_vs_bind_scheduler(svc, old_sched);
			old_sched = sched;
			goto out;
		}
	}

  out:
	write_unlock_bh(&__ip_vs_svc_lock);

	if (old_sched)
		ip_vs_scheduler_put(old_sched);

	return ret;
}


/*
 *	Delete a service from the service list
 *	- The service must be unlinked, unlocked and not referenced!
 *	- We are called under _bh lock
 */
static void __ip_vs_del_service(struct ip_vs_service *svc)
{
	struct ip_vs_dest *dest, *nxt;
	struct ip_vs_scheduler *old_sched;

	ip_vs_num_services--;
	ip_vs_kill_estimator(&svc->stats);

	/* Unbind scheduler */
	old_sched = svc->scheduler;
	ip_vs_unbind_scheduler(svc);
	if (old_sched)
		ip_vs_scheduler_put(old_sched);

	/* Unbind app inc */
	if (svc->inc) {
		ip_vs_app_inc_put(svc->inc);
		svc->inc = NULL;
	}

	/*
	 *    Unlink the whole destination list
	 */
	list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) {
		__ip_vs_unlink_dest(svc, dest, 0);
		__ip_vs_del_dest(dest);
	}

	/*
	 *    Update the virtual service counters
	 */
	if (svc->port == FTPPORT)
		atomic_dec(&ip_vs_ftpsvc_counter);
	else if (svc->port == 0)
		atomic_dec(&ip_vs_nullsvc_counter);

	/*
	 *    Free the service if nobody refers to it
	 */
	if (atomic_read(&svc->refcnt) == 0)
		kfree(svc);

	/* decrease the module use count */
	ip_vs_use_count_dec();
}

/*
 *	Delete a service from the service list
 */
static int ip_vs_del_service(struct ip_vs_service *svc)
{
	if (svc == NULL)
		return -EEXIST;

	/*
	 * Unhash it from the service table
	 */
	write_lock_bh(&__ip_vs_svc_lock);

	ip_vs_svc_unhash(svc);

	/*
	 * Wait until all the svc users go away.
	 */
	IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 1);

	__ip_vs_del_service(svc);

	write_unlock_bh(&__ip_vs_svc_lock);

	return 0;
}


/*
 *	Flush all the virtual services
 */
static int ip_vs_flush(void)
{
	int idx;
	struct ip_vs_service *svc, *nxt;

	/*
	 * Flush the service table hashed by <protocol,addr,port>
	 */
	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], s_list) {
			write_lock_bh(&__ip_vs_svc_lock);
			ip_vs_svc_unhash(svc);
			/*
			 * Wait until all the svc users go away.
			 */
			IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);
			__ip_vs_del_service(svc);
			write_unlock_bh(&__ip_vs_svc_lock);
		}
	}

	/*
	 * Flush the service table hashed by fwmark
	 */
	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry_safe(svc, nxt,
					 &ip_vs_svc_fwm_table[idx], f_list) {
			write_lock_bh(&__ip_vs_svc_lock);
			ip_vs_svc_unhash(svc);
			/*
			 * Wait until all the svc users go away.
			 */
			IP_VS_WAIT_WHILE(atomic_read(&svc->usecnt) > 0);
			__ip_vs_del_service(svc);
			write_unlock_bh(&__ip_vs_svc_lock);
		}
	}

	return 0;
}


/*
 *	Zero counters in a service or all services
 */
static int ip_vs_zero_service(struct ip_vs_service *svc)
{
	struct ip_vs_dest *dest;

	write_lock_bh(&__ip_vs_svc_lock);
	list_for_each_entry(dest, &svc->destinations, n_list) {
		ip_vs_zero_stats(&dest->stats);
	}
	ip_vs_zero_stats(&svc->stats);
	write_unlock_bh(&__ip_vs_svc_lock);
	return 0;
}

static int ip_vs_zero_all(void)
{
	int idx;
	struct ip_vs_service *svc;

	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
			ip_vs_zero_service(svc);
		}
	}

	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
			ip_vs_zero_service(svc);
		}
	}

	ip_vs_zero_stats(&ip_vs_stats);
	return 0;
}


static int
proc_do_defense_mode(ctl_table *table, int write, struct file * filp,
		     void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int *valp = table->data;
	int val = *valp;
	int rc;

	rc = proc_dointvec(table, write, filp, buffer, lenp, ppos);
	if (write && (*valp != val)) {
		if ((*valp < 0) || (*valp > 3)) {
			/* Restore the correct value */
			*valp = val;
		} else {
			update_defense_level();
		}
	}
	return rc;
}


static int
proc_do_sync_threshold(ctl_table *table, int write, struct file *filp,
		       void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int *valp = table->data;
	int val[2];
	int rc;

	/* backup the value first */
	memcpy(val, valp, sizeof(val));

	rc = proc_dointvec(table, write, filp, buffer, lenp, ppos);
	if (write && (valp[0] < 0 || valp[1] < 0 || valp[0] >= valp[1])) {
		/* Restore the correct value */
		memcpy(valp, val, sizeof(val));
	}
	return rc;
}


/*
 *	IPVS sysctl table (under the /proc/sys/net/ipv4/vs/)
 */

static struct ctl_table vs_vars[] = {
	{
		.ctl_name	= NET_IPV4_VS_AMEMTHRESH,
		.procname	= "amemthresh",
		.data		= &sysctl_ip_vs_amemthresh,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#ifdef CONFIG_IP_VS_DEBUG
	{
		.ctl_name	= NET_IPV4_VS_DEBUG_LEVEL,
		.procname	= "debug_level",
		.data		= &sysctl_ip_vs_debug_level,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
#endif
	{
		.ctl_name	= NET_IPV4_VS_AMDROPRATE,
		.procname	= "am_droprate",
		.data		= &sysctl_ip_vs_am_droprate,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_VS_DROP_ENTRY,
		.procname	= "drop_entry",
		.data		= &sysctl_ip_vs_drop_entry,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_do_defense_mode,
	},
	{
		.ctl_name	= NET_IPV4_VS_DROP_PACKET,
		.procname	= "drop_packet",
		.data		= &sysctl_ip_vs_drop_packet,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_do_defense_mode,
	},
	{
		.ctl_name	= NET_IPV4_VS_SECURE_TCP,
		.procname	= "secure_tcp",
		.data		= &sysctl_ip_vs_secure_tcp,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_do_defense_mode,
	},
#if 0
	{
		.ctl_name	= NET_IPV4_VS_TO_ES,
		.procname	= "timeout_established",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_ESTABLISHED],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_SS,
		.procname	= "timeout_synsent",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_SYN_SENT],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_SR,
		.procname	= "timeout_synrecv",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_SYN_RECV],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_FW,
		.procname	= "timeout_finwait",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_FIN_WAIT],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_TW,
		.procname	= "timeout_timewait",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_TIME_WAIT],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_CL,
		.procname	= "timeout_close",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_CLOSE],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_CW,
		.procname	= "timeout_closewait",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_CLOSE_WAIT],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_LA,
		.procname	= "timeout_lastack",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_LAST_ACK],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_LI,
		.procname	= "timeout_listen",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_LISTEN],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_SA,
		.procname	= "timeout_synack",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_SYNACK],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_UDP,
		.procname	= "timeout_udp",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_UDP],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
	{
		.ctl_name	= NET_IPV4_VS_TO_ICMP,
		.procname	= "timeout_icmp",
		.data	= &vs_timeout_table_dos.timeout[IP_VS_S_ICMP],
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_jiffies,
	},
#endif
	{
		.ctl_name	= NET_IPV4_VS_CACHE_BYPASS,
		.procname	= "cache_bypass",
		.data		= &sysctl_ip_vs_cache_bypass,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_VS_EXPIRE_NODEST_CONN,
		.procname	= "expire_nodest_conn",
		.data		= &sysctl_ip_vs_expire_nodest_conn,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_VS_EXPIRE_QUIESCENT_TEMPLATE,
		.procname	= "expire_quiescent_template",
		.data		= &sysctl_ip_vs_expire_quiescent_template,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{
		.ctl_name	= NET_IPV4_VS_SYNC_THRESHOLD,
		.procname	= "sync_threshold",
		.data		= &sysctl_ip_vs_sync_threshold,
		.maxlen		= sizeof(sysctl_ip_vs_sync_threshold),
		.mode		= 0644,
		.proc_handler	= &proc_do_sync_threshold,
	},
	{
		.ctl_name	= NET_IPV4_VS_NAT_ICMP_SEND,
		.procname	= "nat_icmp_send",
		.data		= &sysctl_ip_vs_nat_icmp_send,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec,
	},
	{ .ctl_name = 0 }
};

static ctl_table vs_table[] = {
	{
		.ctl_name	= NET_IPV4_VS,
		.procname	= "vs",
		.mode		= 0555,
		.child		= vs_vars
	},
	{ .ctl_name = 0 }
};

1602
static ctl_table ipvs_ipv4_table[] = {
L
Linus Torvalds 已提交
1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616
	{
		.ctl_name	= NET_IPV4,
		.procname	= "ipv4",
		.mode		= 0555,
		.child		= vs_table,
	},
	{ .ctl_name = 0 }
};

static ctl_table vs_root_table[] = {
	{
		.ctl_name	= CTL_NET,
		.procname	= "net",
		.mode		= 0555,
1617
		.child		= ipvs_ipv4_table,
L
Linus Torvalds 已提交
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 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 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 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785
	},
	{ .ctl_name = 0 }
};

static struct ctl_table_header * sysctl_header;

#ifdef CONFIG_PROC_FS

struct ip_vs_iter {
	struct list_head *table;
	int bucket;
};

/*
 *	Write the contents of the VS rule table to a PROCfs file.
 *	(It is kept just for backward compatibility)
 */
static inline const char *ip_vs_fwd_name(unsigned flags)
{
	switch (flags & IP_VS_CONN_F_FWD_MASK) {
	case IP_VS_CONN_F_LOCALNODE:
		return "Local";
	case IP_VS_CONN_F_TUNNEL:
		return "Tunnel";
	case IP_VS_CONN_F_DROUTE:
		return "Route";
	default:
		return "Masq";
	}
}


/* Get the Nth entry in the two lists */
static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos)
{
	struct ip_vs_iter *iter = seq->private;
	int idx;
	struct ip_vs_service *svc;

	/* look in hash by protocol */
	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
			if (pos-- == 0){
				iter->table = ip_vs_svc_table;
				iter->bucket = idx;
				return svc;
			}
		}
	}

	/* keep looking in fwmark */
	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
			if (pos-- == 0) {
				iter->table = ip_vs_svc_fwm_table;
				iter->bucket = idx;
				return svc;
			}
		}
	}

	return NULL;
}

static void *ip_vs_info_seq_start(struct seq_file *seq, loff_t *pos)
{

	read_lock_bh(&__ip_vs_svc_lock);
	return *pos ? ip_vs_info_array(seq, *pos - 1) : SEQ_START_TOKEN;
}


static void *ip_vs_info_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
	struct list_head *e;
	struct ip_vs_iter *iter;
	struct ip_vs_service *svc;

	++*pos;
	if (v == SEQ_START_TOKEN)
		return ip_vs_info_array(seq,0);

	svc = v;
	iter = seq->private;

	if (iter->table == ip_vs_svc_table) {
		/* next service in table hashed by protocol */
		if ((e = svc->s_list.next) != &ip_vs_svc_table[iter->bucket])
			return list_entry(e, struct ip_vs_service, s_list);


		while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
			list_for_each_entry(svc,&ip_vs_svc_table[iter->bucket],
					    s_list) {
				return svc;
			}
		}

		iter->table = ip_vs_svc_fwm_table;
		iter->bucket = -1;
		goto scan_fwmark;
	}

	/* next service in hashed by fwmark */
	if ((e = svc->f_list.next) != &ip_vs_svc_fwm_table[iter->bucket])
		return list_entry(e, struct ip_vs_service, f_list);

 scan_fwmark:
	while (++iter->bucket < IP_VS_SVC_TAB_SIZE) {
		list_for_each_entry(svc, &ip_vs_svc_fwm_table[iter->bucket],
				    f_list)
			return svc;
	}

	return NULL;
}

static void ip_vs_info_seq_stop(struct seq_file *seq, void *v)
{
	read_unlock_bh(&__ip_vs_svc_lock);
}


static int ip_vs_info_seq_show(struct seq_file *seq, void *v)
{
	if (v == SEQ_START_TOKEN) {
		seq_printf(seq,
			"IP Virtual Server version %d.%d.%d (size=%d)\n",
			NVERSION(IP_VS_VERSION_CODE), IP_VS_CONN_TAB_SIZE);
		seq_puts(seq,
			 "Prot LocalAddress:Port Scheduler Flags\n");
		seq_puts(seq,
			 "  -> RemoteAddress:Port Forward Weight ActiveConn InActConn\n");
	} else {
		const struct ip_vs_service *svc = v;
		const struct ip_vs_iter *iter = seq->private;
		const struct ip_vs_dest *dest;

		if (iter->table == ip_vs_svc_table)
			seq_printf(seq, "%s  %08X:%04X %s ",
				   ip_vs_proto_name(svc->protocol),
				   ntohl(svc->addr),
				   ntohs(svc->port),
				   svc->scheduler->name);
		else
			seq_printf(seq, "FWM  %08X %s ",
				   svc->fwmark, svc->scheduler->name);

		if (svc->flags & IP_VS_SVC_F_PERSISTENT)
			seq_printf(seq, "persistent %d %08X\n",
				svc->timeout,
				ntohl(svc->netmask));
		else
			seq_putc(seq, '\n');

		list_for_each_entry(dest, &svc->destinations, n_list) {
			seq_printf(seq,
				   "  -> %08X:%04X      %-7s %-6d %-10d %-10d\n",
				   ntohl(dest->addr), ntohs(dest->port),
				   ip_vs_fwd_name(atomic_read(&dest->conn_flags)),
				   atomic_read(&dest->weight),
				   atomic_read(&dest->activeconns),
				   atomic_read(&dest->inactconns));
		}
	}
	return 0;
}

1786
static const struct seq_operations ip_vs_info_seq_ops = {
L
Linus Torvalds 已提交
1787 1788 1789 1790 1791 1792 1793 1794 1795 1796
	.start = ip_vs_info_seq_start,
	.next  = ip_vs_info_seq_next,
	.stop  = ip_vs_info_seq_stop,
	.show  = ip_vs_info_seq_show,
};

static int ip_vs_info_open(struct inode *inode, struct file *file)
{
	struct seq_file *seq;
	int rc = -ENOMEM;
1797
	struct ip_vs_iter *s = kzalloc(sizeof(*s), GFP_KERNEL);
L
Linus Torvalds 已提交
1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814

	if (!s)
		goto out;

	rc = seq_open(file, &ip_vs_info_seq_ops);
	if (rc)
		goto out_kfree;

	seq	     = file->private_data;
	seq->private = s;
out:
	return rc;
out_kfree:
	kfree(s);
	goto out;
}

1815
static const struct file_operations ip_vs_info_fops = {
L
Linus Torvalds 已提交
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
	.owner	 = THIS_MODULE,
	.open    = ip_vs_info_open,
	.read    = seq_read,
	.llseek  = seq_lseek,
	.release = seq_release_private,
};

#endif

struct ip_vs_stats ip_vs_stats;

#ifdef CONFIG_PROC_FS
static int ip_vs_stats_show(struct seq_file *seq, void *v)
{

/*               01234567 01234567 01234567 0123456701234567 0123456701234567 */
	seq_puts(seq,
		 "   Total Incoming Outgoing         Incoming         Outgoing\n");
	seq_printf(seq,
		   "   Conns  Packets  Packets            Bytes            Bytes\n");

	spin_lock_bh(&ip_vs_stats.lock);
	seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", ip_vs_stats.conns,
		   ip_vs_stats.inpkts, ip_vs_stats.outpkts,
		   (unsigned long long) ip_vs_stats.inbytes,
		   (unsigned long long) ip_vs_stats.outbytes);

/*                 01234567 01234567 01234567 0123456701234567 0123456701234567 */
	seq_puts(seq,
		   " Conns/s   Pkts/s   Pkts/s          Bytes/s          Bytes/s\n");
	seq_printf(seq,"%8X %8X %8X %16X %16X\n",
			ip_vs_stats.cps,
			ip_vs_stats.inpps,
			ip_vs_stats.outpps,
			ip_vs_stats.inbps,
			ip_vs_stats.outbps);
	spin_unlock_bh(&ip_vs_stats.lock);

	return 0;
}

static int ip_vs_stats_seq_open(struct inode *inode, struct file *file)
{
	return single_open(file, ip_vs_stats_show, NULL);
}

1862
static const struct file_operations ip_vs_stats_fops = {
L
Linus Torvalds 已提交
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
	.owner = THIS_MODULE,
	.open = ip_vs_stats_seq_open,
	.read = seq_read,
	.llseek = seq_lseek,
	.release = single_release,
};

#endif

/*
 *	Set timeout values for tcp tcpfin udp in the timeout_table.
 */
static int ip_vs_set_timeout(struct ip_vs_timeout_user *u)
{
	IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n",
		  u->tcp_timeout,
		  u->tcp_fin_timeout,
		  u->udp_timeout);

#ifdef CONFIG_IP_VS_PROTO_TCP
	if (u->tcp_timeout) {
		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED]
			= u->tcp_timeout * HZ;
	}

	if (u->tcp_fin_timeout) {
		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT]
			= u->tcp_fin_timeout * HZ;
	}
#endif

#ifdef CONFIG_IP_VS_PROTO_UDP
	if (u->udp_timeout) {
		ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL]
			= u->udp_timeout * HZ;
	}
#endif
	return 0;
}


#define SET_CMDID(cmd)		(cmd - IP_VS_BASE_CTL)
#define SERVICE_ARG_LEN		(sizeof(struct ip_vs_service_user))
#define SVCDEST_ARG_LEN		(sizeof(struct ip_vs_service_user) +	\
				 sizeof(struct ip_vs_dest_user))
#define TIMEOUT_ARG_LEN		(sizeof(struct ip_vs_timeout_user))
#define DAEMON_ARG_LEN		(sizeof(struct ip_vs_daemon_user))
#define MAX_ARG_LEN		SVCDEST_ARG_LEN

1912
static const unsigned char set_arglen[SET_CMDID(IP_VS_SO_SET_MAX)+1] = {
L
Linus Torvalds 已提交
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
	[SET_CMDID(IP_VS_SO_SET_ADD)]		= SERVICE_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_EDIT)]		= SERVICE_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_DEL)]		= SERVICE_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_FLUSH)]		= 0,
	[SET_CMDID(IP_VS_SO_SET_ADDDEST)]	= SVCDEST_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_DELDEST)]	= SVCDEST_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_EDITDEST)]	= SVCDEST_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_TIMEOUT)]	= TIMEOUT_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_STARTDAEMON)]	= DAEMON_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_STOPDAEMON)]	= DAEMON_ARG_LEN,
	[SET_CMDID(IP_VS_SO_SET_ZERO)]		= SERVICE_ARG_LEN,
};

static int
do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len)
{
	int ret;
	unsigned char arg[MAX_ARG_LEN];
	struct ip_vs_service_user *usvc;
	struct ip_vs_service *svc;
	struct ip_vs_dest_user *udest;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	if (len != set_arglen[SET_CMDID(cmd)]) {
		IP_VS_ERR("set_ctl: len %u != %u\n",
			  len, set_arglen[SET_CMDID(cmd)]);
		return -EINVAL;
	}

	if (copy_from_user(arg, user, len) != 0)
		return -EFAULT;

	/* increase the module use count */
	ip_vs_use_count_inc();

1950
	if (mutex_lock_interruptible(&__ip_vs_mutex)) {
L
Linus Torvalds 已提交
1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040
		ret = -ERESTARTSYS;
		goto out_dec;
	}

	if (cmd == IP_VS_SO_SET_FLUSH) {
		/* Flush the virtual service */
		ret = ip_vs_flush();
		goto out_unlock;
	} else if (cmd == IP_VS_SO_SET_TIMEOUT) {
		/* Set timeout values for (tcp tcpfin udp) */
		ret = ip_vs_set_timeout((struct ip_vs_timeout_user *)arg);
		goto out_unlock;
	} else if (cmd == IP_VS_SO_SET_STARTDAEMON) {
		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
		ret = start_sync_thread(dm->state, dm->mcast_ifn, dm->syncid);
		goto out_unlock;
	} else if (cmd == IP_VS_SO_SET_STOPDAEMON) {
		struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg;
		ret = stop_sync_thread(dm->state);
		goto out_unlock;
	}

	usvc = (struct ip_vs_service_user *)arg;
	udest = (struct ip_vs_dest_user *)(usvc + 1);

	if (cmd == IP_VS_SO_SET_ZERO) {
		/* if no service address is set, zero counters in all */
		if (!usvc->fwmark && !usvc->addr && !usvc->port) {
			ret = ip_vs_zero_all();
			goto out_unlock;
		}
	}

	/* Check for valid protocol: TCP or UDP, even for fwmark!=0 */
	if (usvc->protocol!=IPPROTO_TCP && usvc->protocol!=IPPROTO_UDP) {
		IP_VS_ERR("set_ctl: invalid protocol: %d %d.%d.%d.%d:%d %s\n",
			  usvc->protocol, NIPQUAD(usvc->addr),
			  ntohs(usvc->port), usvc->sched_name);
		ret = -EFAULT;
		goto out_unlock;
	}

	/* Lookup the exact service by <protocol, addr, port> or fwmark */
	if (usvc->fwmark == 0)
		svc = __ip_vs_service_get(usvc->protocol,
					  usvc->addr, usvc->port);
	else
		svc = __ip_vs_svc_fwm_get(usvc->fwmark);

	if (cmd != IP_VS_SO_SET_ADD
	    && (svc == NULL || svc->protocol != usvc->protocol)) {
		ret = -ESRCH;
		goto out_unlock;
	}

	switch (cmd) {
	case IP_VS_SO_SET_ADD:
		if (svc != NULL)
			ret = -EEXIST;
		else
			ret = ip_vs_add_service(usvc, &svc);
		break;
	case IP_VS_SO_SET_EDIT:
		ret = ip_vs_edit_service(svc, usvc);
		break;
	case IP_VS_SO_SET_DEL:
		ret = ip_vs_del_service(svc);
		if (!ret)
			goto out_unlock;
		break;
	case IP_VS_SO_SET_ZERO:
		ret = ip_vs_zero_service(svc);
		break;
	case IP_VS_SO_SET_ADDDEST:
		ret = ip_vs_add_dest(svc, udest);
		break;
	case IP_VS_SO_SET_EDITDEST:
		ret = ip_vs_edit_dest(svc, udest);
		break;
	case IP_VS_SO_SET_DELDEST:
		ret = ip_vs_del_dest(svc, udest);
		break;
	default:
		ret = -EINVAL;
	}

	if (svc)
		ip_vs_service_put(svc);

  out_unlock:
2041
	mutex_unlock(&__ip_vs_mutex);
L
Linus Torvalds 已提交
2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064
  out_dec:
	/* decrease the module use count */
	ip_vs_use_count_dec();

	return ret;
}


static void
ip_vs_copy_stats(struct ip_vs_stats_user *dst, struct ip_vs_stats *src)
{
	spin_lock_bh(&src->lock);
	memcpy(dst, src, (char*)&src->lock - (char*)src);
	spin_unlock_bh(&src->lock);
}

static void
ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src)
{
	dst->protocol = src->protocol;
	dst->addr = src->addr;
	dst->port = src->port;
	dst->fwmark = src->fwmark;
P
pageexec 已提交
2065
	strlcpy(dst->sched_name, src->scheduler->name, sizeof(dst->sched_name));
L
Linus Torvalds 已提交
2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085
	dst->flags = src->flags;
	dst->timeout = src->timeout / HZ;
	dst->netmask = src->netmask;
	dst->num_dests = src->num_dests;
	ip_vs_copy_stats(&dst->stats, &src->stats);
}

static inline int
__ip_vs_get_service_entries(const struct ip_vs_get_services *get,
			    struct ip_vs_get_services __user *uptr)
{
	int idx, count=0;
	struct ip_vs_service *svc;
	struct ip_vs_service_entry entry;
	int ret = 0;

	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) {
			if (count >= get->num_services)
				goto out;
P
pageexec 已提交
2086
			memset(&entry, 0, sizeof(entry));
L
Linus Torvalds 已提交
2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100
			ip_vs_copy_service(&entry, svc);
			if (copy_to_user(&uptr->entrytable[count],
					 &entry, sizeof(entry))) {
				ret = -EFAULT;
				goto out;
			}
			count++;
		}
	}

	for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) {
		list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) {
			if (count >= get->num_services)
				goto out;
P
pageexec 已提交
2101
			memset(&entry, 0, sizeof(entry));
L
Linus Torvalds 已提交
2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182
			ip_vs_copy_service(&entry, svc);
			if (copy_to_user(&uptr->entrytable[count],
					 &entry, sizeof(entry))) {
				ret = -EFAULT;
				goto out;
			}
			count++;
		}
	}
  out:
	return ret;
}

static inline int
__ip_vs_get_dest_entries(const struct ip_vs_get_dests *get,
			 struct ip_vs_get_dests __user *uptr)
{
	struct ip_vs_service *svc;
	int ret = 0;

	if (get->fwmark)
		svc = __ip_vs_svc_fwm_get(get->fwmark);
	else
		svc = __ip_vs_service_get(get->protocol,
					  get->addr, get->port);
	if (svc) {
		int count = 0;
		struct ip_vs_dest *dest;
		struct ip_vs_dest_entry entry;

		list_for_each_entry(dest, &svc->destinations, n_list) {
			if (count >= get->num_dests)
				break;

			entry.addr = dest->addr;
			entry.port = dest->port;
			entry.conn_flags = atomic_read(&dest->conn_flags);
			entry.weight = atomic_read(&dest->weight);
			entry.u_threshold = dest->u_threshold;
			entry.l_threshold = dest->l_threshold;
			entry.activeconns = atomic_read(&dest->activeconns);
			entry.inactconns = atomic_read(&dest->inactconns);
			entry.persistconns = atomic_read(&dest->persistconns);
			ip_vs_copy_stats(&entry.stats, &dest->stats);
			if (copy_to_user(&uptr->entrytable[count],
					 &entry, sizeof(entry))) {
				ret = -EFAULT;
				break;
			}
			count++;
		}
		ip_vs_service_put(svc);
	} else
		ret = -ESRCH;
	return ret;
}

static inline void
__ip_vs_get_timeouts(struct ip_vs_timeout_user *u)
{
#ifdef CONFIG_IP_VS_PROTO_TCP
	u->tcp_timeout =
		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ;
	u->tcp_fin_timeout =
		ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ;
#endif
#ifdef CONFIG_IP_VS_PROTO_UDP
	u->udp_timeout =
		ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL] / HZ;
#endif
}


#define GET_CMDID(cmd)		(cmd - IP_VS_BASE_CTL)
#define GET_INFO_ARG_LEN	(sizeof(struct ip_vs_getinfo))
#define GET_SERVICES_ARG_LEN	(sizeof(struct ip_vs_get_services))
#define GET_SERVICE_ARG_LEN	(sizeof(struct ip_vs_service_entry))
#define GET_DESTS_ARG_LEN	(sizeof(struct ip_vs_get_dests))
#define GET_TIMEOUT_ARG_LEN	(sizeof(struct ip_vs_timeout_user))
#define GET_DAEMON_ARG_LEN	(sizeof(struct ip_vs_daemon_user) * 2)

2183
static const unsigned char get_arglen[GET_CMDID(IP_VS_SO_GET_MAX)+1] = {
L
Linus Torvalds 已提交
2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210
	[GET_CMDID(IP_VS_SO_GET_VERSION)]	= 64,
	[GET_CMDID(IP_VS_SO_GET_INFO)]		= GET_INFO_ARG_LEN,
	[GET_CMDID(IP_VS_SO_GET_SERVICES)]	= GET_SERVICES_ARG_LEN,
	[GET_CMDID(IP_VS_SO_GET_SERVICE)]	= GET_SERVICE_ARG_LEN,
	[GET_CMDID(IP_VS_SO_GET_DESTS)]		= GET_DESTS_ARG_LEN,
	[GET_CMDID(IP_VS_SO_GET_TIMEOUT)]	= GET_TIMEOUT_ARG_LEN,
	[GET_CMDID(IP_VS_SO_GET_DAEMON)]	= GET_DAEMON_ARG_LEN,
};

static int
do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
	unsigned char arg[128];
	int ret = 0;

	if (!capable(CAP_NET_ADMIN))
		return -EPERM;

	if (*len < get_arglen[GET_CMDID(cmd)]) {
		IP_VS_ERR("get_ctl: len %u < %u\n",
			  *len, get_arglen[GET_CMDID(cmd)]);
		return -EINVAL;
	}

	if (copy_from_user(arg, user, get_arglen[GET_CMDID(cmd)]) != 0)
		return -EFAULT;

2211
	if (mutex_lock_interruptible(&__ip_vs_mutex))
L
Linus Torvalds 已提交
2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311
		return -ERESTARTSYS;

	switch (cmd) {
	case IP_VS_SO_GET_VERSION:
	{
		char buf[64];

		sprintf(buf, "IP Virtual Server version %d.%d.%d (size=%d)",
			NVERSION(IP_VS_VERSION_CODE), IP_VS_CONN_TAB_SIZE);
		if (copy_to_user(user, buf, strlen(buf)+1) != 0) {
			ret = -EFAULT;
			goto out;
		}
		*len = strlen(buf)+1;
	}
	break;

	case IP_VS_SO_GET_INFO:
	{
		struct ip_vs_getinfo info;
		info.version = IP_VS_VERSION_CODE;
		info.size = IP_VS_CONN_TAB_SIZE;
		info.num_services = ip_vs_num_services;
		if (copy_to_user(user, &info, sizeof(info)) != 0)
			ret = -EFAULT;
	}
	break;

	case IP_VS_SO_GET_SERVICES:
	{
		struct ip_vs_get_services *get;
		int size;

		get = (struct ip_vs_get_services *)arg;
		size = sizeof(*get) +
			sizeof(struct ip_vs_service_entry) * get->num_services;
		if (*len != size) {
			IP_VS_ERR("length: %u != %u\n", *len, size);
			ret = -EINVAL;
			goto out;
		}
		ret = __ip_vs_get_service_entries(get, user);
	}
	break;

	case IP_VS_SO_GET_SERVICE:
	{
		struct ip_vs_service_entry *entry;
		struct ip_vs_service *svc;

		entry = (struct ip_vs_service_entry *)arg;
		if (entry->fwmark)
			svc = __ip_vs_svc_fwm_get(entry->fwmark);
		else
			svc = __ip_vs_service_get(entry->protocol,
						  entry->addr, entry->port);
		if (svc) {
			ip_vs_copy_service(entry, svc);
			if (copy_to_user(user, entry, sizeof(*entry)) != 0)
				ret = -EFAULT;
			ip_vs_service_put(svc);
		} else
			ret = -ESRCH;
	}
	break;

	case IP_VS_SO_GET_DESTS:
	{
		struct ip_vs_get_dests *get;
		int size;

		get = (struct ip_vs_get_dests *)arg;
		size = sizeof(*get) +
			sizeof(struct ip_vs_dest_entry) * get->num_dests;
		if (*len != size) {
			IP_VS_ERR("length: %u != %u\n", *len, size);
			ret = -EINVAL;
			goto out;
		}
		ret = __ip_vs_get_dest_entries(get, user);
	}
	break;

	case IP_VS_SO_GET_TIMEOUT:
	{
		struct ip_vs_timeout_user t;

		__ip_vs_get_timeouts(&t);
		if (copy_to_user(user, &t, sizeof(t)) != 0)
			ret = -EFAULT;
	}
	break;

	case IP_VS_SO_GET_DAEMON:
	{
		struct ip_vs_daemon_user d[2];

		memset(&d, 0, sizeof(d));
		if (ip_vs_sync_state & IP_VS_STATE_MASTER) {
			d[0].state = IP_VS_STATE_MASTER;
P
pageexec 已提交
2312
			strlcpy(d[0].mcast_ifn, ip_vs_master_mcast_ifn, sizeof(d[0].mcast_ifn));
L
Linus Torvalds 已提交
2313 2314 2315 2316
			d[0].syncid = ip_vs_master_syncid;
		}
		if (ip_vs_sync_state & IP_VS_STATE_BACKUP) {
			d[1].state = IP_VS_STATE_BACKUP;
P
pageexec 已提交
2317
			strlcpy(d[1].mcast_ifn, ip_vs_backup_mcast_ifn, sizeof(d[1].mcast_ifn));
L
Linus Torvalds 已提交
2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329
			d[1].syncid = ip_vs_backup_syncid;
		}
		if (copy_to_user(user, &d, sizeof(d)) != 0)
			ret = -EFAULT;
	}
	break;

	default:
		ret = -EINVAL;
	}

  out:
2330
	mutex_unlock(&__ip_vs_mutex);
L
Linus Torvalds 已提交
2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342
	return ret;
}


static struct nf_sockopt_ops ip_vs_sockopts = {
	.pf		= PF_INET,
	.set_optmin	= IP_VS_BASE_CTL,
	.set_optmax	= IP_VS_SO_SET_MAX+1,
	.set		= do_ip_vs_set_ctl,
	.get_optmin	= IP_VS_BASE_CTL,
	.get_optmax	= IP_VS_SO_GET_MAX+1,
	.get		= do_ip_vs_get_ctl,
2343
	.owner		= THIS_MODULE,
L
Linus Torvalds 已提交
2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359
};


int ip_vs_control_init(void)
{
	int ret;
	int idx;

	EnterFunction(2);

	ret = nf_register_sockopt(&ip_vs_sockopts);
	if (ret) {
		IP_VS_ERR("cannot register sockopt.\n");
		return ret;
	}

2360 2361
	proc_net_fops_create(&init_net, "ip_vs", 0, &ip_vs_info_fops);
	proc_net_fops_create(&init_net, "ip_vs_stats",0, &ip_vs_stats_fops);
L
Linus Torvalds 已提交
2362

2363
	sysctl_header = register_sysctl_table(vs_root_table);
L
Linus Torvalds 已提交
2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390

	/* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */
	for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++)  {
		INIT_LIST_HEAD(&ip_vs_svc_table[idx]);
		INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]);
	}
	for(idx = 0; idx < IP_VS_RTAB_SIZE; idx++)  {
		INIT_LIST_HEAD(&ip_vs_rtable[idx]);
	}

	memset(&ip_vs_stats, 0, sizeof(ip_vs_stats));
	spin_lock_init(&ip_vs_stats.lock);
	ip_vs_new_estimator(&ip_vs_stats);

	/* Hook the defense timer */
	schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD);

	LeaveFunction(2);
	return 0;
}


void ip_vs_control_cleanup(void)
{
	EnterFunction(2);
	ip_vs_trash_cleanup();
	cancel_rearming_delayed_work(&defense_work);
2391
	cancel_work_sync(&defense_work.work);
L
Linus Torvalds 已提交
2392 2393
	ip_vs_kill_estimator(&ip_vs_stats);
	unregister_sysctl_table(sysctl_header);
2394 2395
	proc_net_remove(&init_net, "ip_vs_stats");
	proc_net_remove(&init_net, "ip_vs");
L
Linus Torvalds 已提交
2396 2397 2398
	nf_unregister_sockopt(&ip_vs_sockopts);
	LeaveFunction(2);
}