inet_diag.c 22.6 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 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 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951
/*
 * inet_diag.c	Module for monitoring INET transport protocols sockets.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 *	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.
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/random.h>
#include <linux/slab.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/time.h>

#include <net/icmp.h>
#include <net/tcp.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/inet_connection_sock.h>
#include <net/inet_hashtables.h>
#include <net/inet_timewait_sock.h>
#include <net/inet6_hashtables.h>
#include <net/netlink.h>

#include <linux/inet.h>
#include <linux/stddef.h>

#include <linux/inet_diag.h>

static const struct inet_diag_handler **inet_diag_table;

struct inet_diag_entry {
	__be32 *saddr;
	__be32 *daddr;
	u16 sport;
	u16 dport;
	u16 family;
	u16 userlocks;
};

static struct sock *idiagnl;

#define INET_DIAG_PUT(skb, attrtype, attrlen) \
	RTA_DATA(__RTA_PUT(skb, attrtype, attrlen))

static DEFINE_MUTEX(inet_diag_table_mutex);

static const struct inet_diag_handler *inet_diag_lock_handler(int type)
{
	if (!inet_diag_table[type])
		request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
			       NETLINK_INET_DIAG, type);

	mutex_lock(&inet_diag_table_mutex);
	if (!inet_diag_table[type])
		return ERR_PTR(-ENOENT);

	return inet_diag_table[type];
}

static inline void inet_diag_unlock_handler(
	const struct inet_diag_handler *handler)
{
	mutex_unlock(&inet_diag_table_mutex);
}

static int inet_csk_diag_fill(struct sock *sk,
			      struct sk_buff *skb,
			      int ext, u32 pid, u32 seq, u16 nlmsg_flags,
			      const struct nlmsghdr *unlh)
{
	const struct inet_sock *inet = inet_sk(sk);
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct inet_diag_msg *r;
	struct nlmsghdr  *nlh;
	void *info = NULL;
	struct inet_diag_meminfo  *minfo = NULL;
	unsigned char	 *b = skb_tail_pointer(skb);
	const struct inet_diag_handler *handler;

	handler = inet_diag_table[unlh->nlmsg_type];
	BUG_ON(handler == NULL);

	nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
	nlh->nlmsg_flags = nlmsg_flags;

	r = NLMSG_DATA(nlh);
	BUG_ON(sk->sk_state == TCP_TIME_WAIT);

	if (ext & (1 << (INET_DIAG_MEMINFO - 1)))
		minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo));

	if (ext & (1 << (INET_DIAG_INFO - 1)))
		info = INET_DIAG_PUT(skb, INET_DIAG_INFO,
				     handler->idiag_info_size);

	if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) {
		const size_t len = strlen(icsk->icsk_ca_ops->name);

		strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1),
		       icsk->icsk_ca_ops->name);
	}

	r->idiag_family = sk->sk_family;
	r->idiag_state = sk->sk_state;
	r->idiag_timer = 0;
	r->idiag_retrans = 0;

	r->id.idiag_if = sk->sk_bound_dev_if;
	r->id.idiag_cookie[0] = (u32)(unsigned long)sk;
	r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);

	r->id.idiag_sport = inet->inet_sport;
	r->id.idiag_dport = inet->inet_dport;
	r->id.idiag_src[0] = inet->inet_rcv_saddr;
	r->id.idiag_dst[0] = inet->inet_daddr;

#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	if (r->idiag_family == AF_INET6) {
		const struct ipv6_pinfo *np = inet6_sk(sk);

		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
			       &np->rcv_saddr);
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
			       &np->daddr);
	}
#endif

#define EXPIRES_IN_MS(tmo)  DIV_ROUND_UP((tmo - jiffies) * 1000, HZ)

	if (icsk->icsk_pending == ICSK_TIME_RETRANS) {
		r->idiag_timer = 1;
		r->idiag_retrans = icsk->icsk_retransmits;
		r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
	} else if (icsk->icsk_pending == ICSK_TIME_PROBE0) {
		r->idiag_timer = 4;
		r->idiag_retrans = icsk->icsk_probes_out;
		r->idiag_expires = EXPIRES_IN_MS(icsk->icsk_timeout);
	} else if (timer_pending(&sk->sk_timer)) {
		r->idiag_timer = 2;
		r->idiag_retrans = icsk->icsk_probes_out;
		r->idiag_expires = EXPIRES_IN_MS(sk->sk_timer.expires);
	} else {
		r->idiag_timer = 0;
		r->idiag_expires = 0;
	}
#undef EXPIRES_IN_MS

	r->idiag_uid = sock_i_uid(sk);
	r->idiag_inode = sock_i_ino(sk);

	if (minfo) {
		minfo->idiag_rmem = sk_rmem_alloc_get(sk);
		minfo->idiag_wmem = sk->sk_wmem_queued;
		minfo->idiag_fmem = sk->sk_forward_alloc;
		minfo->idiag_tmem = sk_wmem_alloc_get(sk);
	}

	handler->idiag_get_info(sk, r, info);

	if (sk->sk_state < TCP_TIME_WAIT &&
	    icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info)
		icsk->icsk_ca_ops->get_info(sk, ext, skb);

	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
	return skb->len;

rtattr_failure:
nlmsg_failure:
	nlmsg_trim(skb, b);
	return -EMSGSIZE;
}

static int inet_twsk_diag_fill(struct inet_timewait_sock *tw,
			       struct sk_buff *skb, int ext, u32 pid,
			       u32 seq, u16 nlmsg_flags,
			       const struct nlmsghdr *unlh)
{
	long tmo;
	struct inet_diag_msg *r;
	const unsigned char *previous_tail = skb_tail_pointer(skb);
	struct nlmsghdr *nlh = NLMSG_PUT(skb, pid, seq,
					 unlh->nlmsg_type, sizeof(*r));

	r = NLMSG_DATA(nlh);
	BUG_ON(tw->tw_state != TCP_TIME_WAIT);

	nlh->nlmsg_flags = nlmsg_flags;

	tmo = tw->tw_ttd - jiffies;
	if (tmo < 0)
		tmo = 0;

	r->idiag_family	      = tw->tw_family;
	r->idiag_retrans      = 0;
	r->id.idiag_if	      = tw->tw_bound_dev_if;
	r->id.idiag_cookie[0] = (u32)(unsigned long)tw;
	r->id.idiag_cookie[1] = (u32)(((unsigned long)tw >> 31) >> 1);
	r->id.idiag_sport     = tw->tw_sport;
	r->id.idiag_dport     = tw->tw_dport;
	r->id.idiag_src[0]    = tw->tw_rcv_saddr;
	r->id.idiag_dst[0]    = tw->tw_daddr;
	r->idiag_state	      = tw->tw_substate;
	r->idiag_timer	      = 3;
	r->idiag_expires      = DIV_ROUND_UP(tmo * 1000, HZ);
	r->idiag_rqueue	      = 0;
	r->idiag_wqueue	      = 0;
	r->idiag_uid	      = 0;
	r->idiag_inode	      = 0;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	if (tw->tw_family == AF_INET6) {
		const struct inet6_timewait_sock *tw6 =
						inet6_twsk((struct sock *)tw);

		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
			       &tw6->tw_v6_rcv_saddr);
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
			       &tw6->tw_v6_daddr);
	}
#endif
	nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail;
	return skb->len;
nlmsg_failure:
	nlmsg_trim(skb, previous_tail);
	return -EMSGSIZE;
}

static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
			int ext, u32 pid, u32 seq, u16 nlmsg_flags,
			const struct nlmsghdr *unlh)
{
	if (sk->sk_state == TCP_TIME_WAIT)
		return inet_twsk_diag_fill((struct inet_timewait_sock *)sk,
					   skb, ext, pid, seq, nlmsg_flags,
					   unlh);
	return inet_csk_diag_fill(sk, skb, ext, pid, seq, nlmsg_flags, unlh);
}

static int inet_diag_get_exact(struct sk_buff *in_skb,
			       const struct nlmsghdr *nlh)
{
	int err;
	struct sock *sk;
	struct inet_diag_req *req = NLMSG_DATA(nlh);
	struct sk_buff *rep;
	struct inet_hashinfo *hashinfo;
	const struct inet_diag_handler *handler;

	handler = inet_diag_lock_handler(nlh->nlmsg_type);
	if (IS_ERR(handler)) {
		err = PTR_ERR(handler);
		goto unlock;
	}

	hashinfo = handler->idiag_hashinfo;
	err = -EINVAL;

	if (req->idiag_family == AF_INET) {
		sk = inet_lookup(&init_net, hashinfo, req->id.idiag_dst[0],
				 req->id.idiag_dport, req->id.idiag_src[0],
				 req->id.idiag_sport, req->id.idiag_if);
	}
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	else if (req->idiag_family == AF_INET6) {
		sk = inet6_lookup(&init_net, hashinfo,
				  (struct in6_addr *)req->id.idiag_dst,
				  req->id.idiag_dport,
				  (struct in6_addr *)req->id.idiag_src,
				  req->id.idiag_sport,
				  req->id.idiag_if);
	}
#endif
	else {
		goto unlock;
	}

	err = -ENOENT;
	if (sk == NULL)
		goto unlock;

	err = -ESTALE;
	if ((req->id.idiag_cookie[0] != INET_DIAG_NOCOOKIE ||
	     req->id.idiag_cookie[1] != INET_DIAG_NOCOOKIE) &&
	    ((u32)(unsigned long)sk != req->id.idiag_cookie[0] ||
	     (u32)((((unsigned long)sk) >> 31) >> 1) != req->id.idiag_cookie[1]))
		goto out;

	err = -ENOMEM;
	rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) +
				     sizeof(struct inet_diag_meminfo) +
				     handler->idiag_info_size + 64)),
			GFP_KERNEL);
	if (!rep)
		goto out;

	err = sk_diag_fill(sk, rep, req->idiag_ext,
			   NETLINK_CB(in_skb).pid,
			   nlh->nlmsg_seq, 0, nlh);
	if (err < 0) {
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(rep);
		goto out;
	}
	err = netlink_unicast(idiagnl, rep, NETLINK_CB(in_skb).pid,
			      MSG_DONTWAIT);
	if (err > 0)
		err = 0;

out:
	if (sk) {
		if (sk->sk_state == TCP_TIME_WAIT)
			inet_twsk_put((struct inet_timewait_sock *)sk);
		else
			sock_put(sk);
	}
unlock:
	inet_diag_unlock_handler(handler);
	return err;
}

static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits)
{
	int words = bits >> 5;

	bits &= 0x1f;

	if (words) {
		if (memcmp(a1, a2, words << 2))
			return 0;
	}
	if (bits) {
		__be32 w1, w2;
		__be32 mask;

		w1 = a1[words];
		w2 = a2[words];

		mask = htonl((0xffffffff) << (32 - bits));

		if ((w1 ^ w2) & mask)
			return 0;
	}

	return 1;
}


static int inet_diag_bc_run(const void *bc, int len,
			    const struct inet_diag_entry *entry)
{
	while (len > 0) {
		int yes = 1;
		const struct inet_diag_bc_op *op = bc;

		switch (op->code) {
		case INET_DIAG_BC_NOP:
			break;
		case INET_DIAG_BC_JMP:
			yes = 0;
			break;
		case INET_DIAG_BC_S_GE:
			yes = entry->sport >= op[1].no;
			break;
		case INET_DIAG_BC_S_LE:
			yes = entry->sport <= op[1].no;
			break;
		case INET_DIAG_BC_D_GE:
			yes = entry->dport >= op[1].no;
			break;
		case INET_DIAG_BC_D_LE:
			yes = entry->dport <= op[1].no;
			break;
		case INET_DIAG_BC_AUTO:
			yes = !(entry->userlocks & SOCK_BINDPORT_LOCK);
			break;
		case INET_DIAG_BC_S_COND:
		case INET_DIAG_BC_D_COND: {
			struct inet_diag_hostcond *cond;
			__be32 *addr;

			cond = (struct inet_diag_hostcond *)(op + 1);
			if (cond->port != -1 &&
			    cond->port != (op->code == INET_DIAG_BC_S_COND ?
					     entry->sport : entry->dport)) {
				yes = 0;
				break;
			}

			if (cond->prefix_len == 0)
				break;

			if (op->code == INET_DIAG_BC_S_COND)
				addr = entry->saddr;
			else
				addr = entry->daddr;

			if (bitstring_match(addr, cond->addr,
					    cond->prefix_len))
				break;
			if (entry->family == AF_INET6 &&
			    cond->family == AF_INET) {
				if (addr[0] == 0 && addr[1] == 0 &&
				    addr[2] == htonl(0xffff) &&
				    bitstring_match(addr + 3, cond->addr,
						    cond->prefix_len))
					break;
			}
			yes = 0;
			break;
		}
		}

		if (yes) {
			len -= op->yes;
			bc += op->yes;
		} else {
			len -= op->no;
			bc += op->no;
		}
	}
	return len == 0;
}

static int valid_cc(const void *bc, int len, int cc)
{
	while (len >= 0) {
		const struct inet_diag_bc_op *op = bc;

		if (cc > len)
			return 0;
		if (cc == len)
			return 1;
		if (op->yes < 4 || op->yes & 3)
			return 0;
		len -= op->yes;
		bc  += op->yes;
	}
	return 0;
}

static int inet_diag_bc_audit(const void *bytecode, int bytecode_len)
{
	const void *bc = bytecode;
	int  len = bytecode_len;

	while (len > 0) {
		const struct inet_diag_bc_op *op = bc;

//printk("BC: %d %d %d {%d} / %d\n", op->code, op->yes, op->no, op[1].no, len);
		switch (op->code) {
		case INET_DIAG_BC_AUTO:
		case INET_DIAG_BC_S_COND:
		case INET_DIAG_BC_D_COND:
		case INET_DIAG_BC_S_GE:
		case INET_DIAG_BC_S_LE:
		case INET_DIAG_BC_D_GE:
		case INET_DIAG_BC_D_LE:
		case INET_DIAG_BC_JMP:
			if (op->no < 4 || op->no > len + 4 || op->no & 3)
				return -EINVAL;
			if (op->no < len &&
			    !valid_cc(bytecode, bytecode_len, len - op->no))
				return -EINVAL;
			break;
		case INET_DIAG_BC_NOP:
			break;
		default:
			return -EINVAL;
		}
		if (op->yes < 4 || op->yes > len + 4 || op->yes & 3)
			return -EINVAL;
		bc  += op->yes;
		len -= op->yes;
	}
	return len == 0 ? 0 : -EINVAL;
}

static int inet_csk_diag_dump(struct sock *sk,
			      struct sk_buff *skb,
			      struct netlink_callback *cb)
{
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);

	if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
		struct inet_diag_entry entry;
		const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
							  sizeof(*r),
							  INET_DIAG_REQ_BYTECODE);
		struct inet_sock *inet = inet_sk(sk);

		entry.family = sk->sk_family;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		if (entry.family == AF_INET6) {
			struct ipv6_pinfo *np = inet6_sk(sk);

			entry.saddr = np->rcv_saddr.s6_addr32;
			entry.daddr = np->daddr.s6_addr32;
		} else
#endif
		{
			entry.saddr = &inet->inet_rcv_saddr;
			entry.daddr = &inet->inet_daddr;
		}
		entry.sport = inet->inet_num;
		entry.dport = ntohs(inet->inet_dport);
		entry.userlocks = sk->sk_userlocks;

		if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
			return 0;
	}

	return inet_csk_diag_fill(sk, skb, r->idiag_ext,
				  NETLINK_CB(cb->skb).pid,
				  cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}

static int inet_twsk_diag_dump(struct inet_timewait_sock *tw,
			       struct sk_buff *skb,
			       struct netlink_callback *cb)
{
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);

	if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
		struct inet_diag_entry entry;
		const struct nlattr *bc = nlmsg_find_attr(cb->nlh,
							  sizeof(*r),
							  INET_DIAG_REQ_BYTECODE);

		entry.family = tw->tw_family;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
		if (tw->tw_family == AF_INET6) {
			struct inet6_timewait_sock *tw6 =
						inet6_twsk((struct sock *)tw);
			entry.saddr = tw6->tw_v6_rcv_saddr.s6_addr32;
			entry.daddr = tw6->tw_v6_daddr.s6_addr32;
		} else
#endif
		{
			entry.saddr = &tw->tw_rcv_saddr;
			entry.daddr = &tw->tw_daddr;
		}
		entry.sport = tw->tw_num;
		entry.dport = ntohs(tw->tw_dport);
		entry.userlocks = 0;

		if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry))
			return 0;
	}

	return inet_twsk_diag_fill(tw, skb, r->idiag_ext,
				   NETLINK_CB(cb->skb).pid,
				   cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh);
}

static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk,
			      struct request_sock *req, u32 pid, u32 seq,
			      const struct nlmsghdr *unlh)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct inet_sock *inet = inet_sk(sk);
	unsigned char *b = skb_tail_pointer(skb);
	struct inet_diag_msg *r;
	struct nlmsghdr *nlh;
	long tmo;

	nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r));
	nlh->nlmsg_flags = NLM_F_MULTI;
	r = NLMSG_DATA(nlh);

	r->idiag_family = sk->sk_family;
	r->idiag_state = TCP_SYN_RECV;
	r->idiag_timer = 1;
	r->idiag_retrans = req->retrans;

	r->id.idiag_if = sk->sk_bound_dev_if;
	r->id.idiag_cookie[0] = (u32)(unsigned long)req;
	r->id.idiag_cookie[1] = (u32)(((unsigned long)req >> 31) >> 1);

	tmo = req->expires - jiffies;
	if (tmo < 0)
		tmo = 0;

	r->id.idiag_sport = inet->inet_sport;
	r->id.idiag_dport = ireq->rmt_port;
	r->id.idiag_src[0] = ireq->loc_addr;
	r->id.idiag_dst[0] = ireq->rmt_addr;
	r->idiag_expires = jiffies_to_msecs(tmo);
	r->idiag_rqueue = 0;
	r->idiag_wqueue = 0;
	r->idiag_uid = sock_i_uid(sk);
	r->idiag_inode = 0;
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
	if (r->idiag_family == AF_INET6) {
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_src,
			       &inet6_rsk(req)->loc_addr);
		ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst,
			       &inet6_rsk(req)->rmt_addr);
	}
#endif
	nlh->nlmsg_len = skb_tail_pointer(skb) - b;

	return skb->len;

nlmsg_failure:
	nlmsg_trim(skb, b);
	return -1;
}

static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk,
			       struct netlink_callback *cb)
{
	struct inet_diag_entry entry;
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct listen_sock *lopt;
	const struct nlattr *bc = NULL;
	struct inet_sock *inet = inet_sk(sk);
	int j, s_j;
	int reqnum, s_reqnum;
	int err = 0;

	s_j = cb->args[3];
	s_reqnum = cb->args[4];

	if (s_j > 0)
		s_j--;

	entry.family = sk->sk_family;

	read_lock_bh(&icsk->icsk_accept_queue.syn_wait_lock);

	lopt = icsk->icsk_accept_queue.listen_opt;
	if (!lopt || !lopt->qlen)
		goto out;

	if (nlmsg_attrlen(cb->nlh, sizeof(*r))) {
		bc = nlmsg_find_attr(cb->nlh, sizeof(*r),
				     INET_DIAG_REQ_BYTECODE);
		entry.sport = inet->inet_num;
		entry.userlocks = sk->sk_userlocks;
	}

	for (j = s_j; j < lopt->nr_table_entries; j++) {
		struct request_sock *req, *head = lopt->syn_table[j];

		reqnum = 0;
		for (req = head; req; reqnum++, req = req->dl_next) {
			struct inet_request_sock *ireq = inet_rsk(req);

			if (reqnum < s_reqnum)
				continue;
			if (r->id.idiag_dport != ireq->rmt_port &&
			    r->id.idiag_dport)
				continue;

			if (bc) {
				entry.saddr =
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
					(entry.family == AF_INET6) ?
					inet6_rsk(req)->loc_addr.s6_addr32 :
#endif
					&ireq->loc_addr;
				entry.daddr =
#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE)
					(entry.family == AF_INET6) ?
					inet6_rsk(req)->rmt_addr.s6_addr32 :
#endif
					&ireq->rmt_addr;
				entry.dport = ntohs(ireq->rmt_port);

				if (!inet_diag_bc_run(nla_data(bc),
						      nla_len(bc), &entry))
					continue;
			}

			err = inet_diag_fill_req(skb, sk, req,
					       NETLINK_CB(cb->skb).pid,
					       cb->nlh->nlmsg_seq, cb->nlh);
			if (err < 0) {
				cb->args[3] = j + 1;
				cb->args[4] = reqnum;
				goto out;
			}
		}

		s_reqnum = 0;
	}

out:
	read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock);

	return err;
}

static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
	int i, num;
	int s_i, s_num;
	struct inet_diag_req *r = NLMSG_DATA(cb->nlh);
	const struct inet_diag_handler *handler;
	struct inet_hashinfo *hashinfo;

	handler = inet_diag_lock_handler(cb->nlh->nlmsg_type);
	if (IS_ERR(handler))
		goto unlock;

	hashinfo = handler->idiag_hashinfo;

	s_i = cb->args[1];
	s_num = num = cb->args[2];

	if (cb->args[0] == 0) {
		if (!(r->idiag_states & (TCPF_LISTEN | TCPF_SYN_RECV)))
			goto skip_listen_ht;

		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
			struct sock *sk;
			struct hlist_nulls_node *node;
			struct inet_listen_hashbucket *ilb;

			num = 0;
			ilb = &hashinfo->listening_hash[i];
			spin_lock_bh(&ilb->lock);
			sk_nulls_for_each(sk, node, &ilb->head) {
				struct inet_sock *inet = inet_sk(sk);

				if (num < s_num) {
					num++;
					continue;
				}

				if (r->id.idiag_sport != inet->inet_sport &&
				    r->id.idiag_sport)
					goto next_listen;

				if (!(r->idiag_states & TCPF_LISTEN) ||
				    r->id.idiag_dport ||
				    cb->args[3] > 0)
					goto syn_recv;

				if (inet_csk_diag_dump(sk, skb, cb) < 0) {
					spin_unlock_bh(&ilb->lock);
					goto done;
				}

syn_recv:
				if (!(r->idiag_states & TCPF_SYN_RECV))
					goto next_listen;

				if (inet_diag_dump_reqs(skb, sk, cb) < 0) {
					spin_unlock_bh(&ilb->lock);
					goto done;
				}

next_listen:
				cb->args[3] = 0;
				cb->args[4] = 0;
				++num;
			}
			spin_unlock_bh(&ilb->lock);

			s_num = 0;
			cb->args[3] = 0;
			cb->args[4] = 0;
		}
skip_listen_ht:
		cb->args[0] = 1;
		s_i = num = s_num = 0;
	}

	if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV)))
		goto unlock;

	for (i = s_i; i <= hashinfo->ehash_mask; i++) {
		struct inet_ehash_bucket *head = &hashinfo->ehash[i];
		spinlock_t *lock = inet_ehash_lockp(hashinfo, i);
		struct sock *sk;
		struct hlist_nulls_node *node;

		num = 0;

		if (hlist_nulls_empty(&head->chain) &&
			hlist_nulls_empty(&head->twchain))
			continue;

		if (i > s_i)
			s_num = 0;

		spin_lock_bh(lock);
		sk_nulls_for_each(sk, node, &head->chain) {
			struct inet_sock *inet = inet_sk(sk);

			if (num < s_num)
				goto next_normal;
			if (!(r->idiag_states & (1 << sk->sk_state)))
				goto next_normal;
			if (r->id.idiag_sport != inet->inet_sport &&
			    r->id.idiag_sport)
				goto next_normal;
			if (r->id.idiag_dport != inet->inet_dport &&
			    r->id.idiag_dport)
				goto next_normal;
			if (inet_csk_diag_dump(sk, skb, cb) < 0) {
				spin_unlock_bh(lock);
				goto done;
			}
next_normal:
			++num;
		}

		if (r->idiag_states & TCPF_TIME_WAIT) {
			struct inet_timewait_sock *tw;

			inet_twsk_for_each(tw, node,
				    &head->twchain) {

				if (num < s_num)
					goto next_dying;
				if (r->id.idiag_sport != tw->tw_sport &&
				    r->id.idiag_sport)
					goto next_dying;
				if (r->id.idiag_dport != tw->tw_dport &&
				    r->id.idiag_dport)
					goto next_dying;
				if (inet_twsk_diag_dump(tw, skb, cb) < 0) {
					spin_unlock_bh(lock);
					goto done;
				}
next_dying:
				++num;
			}
		}
		spin_unlock_bh(lock);
	}

done:
	cb->args[1] = i;
	cb->args[2] = num;
unlock:
	inet_diag_unlock_handler(handler);
	return skb->len;
}

static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
{
	int hdrlen = sizeof(struct inet_diag_req);

	if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX ||
	    nlmsg_len(nlh) < hdrlen)
		return -EINVAL;

	if (nlh->nlmsg_flags & NLM_F_DUMP) {
		if (nlmsg_attrlen(nlh, hdrlen)) {
			struct nlattr *attr;

			attr = nlmsg_find_attr(nlh, hdrlen,
					       INET_DIAG_REQ_BYTECODE);
			if (attr == NULL ||
			    nla_len(attr) < sizeof(struct inet_diag_bc_op) ||
			    inet_diag_bc_audit(nla_data(attr), nla_len(attr)))
				return -EINVAL;
		}

		return netlink_dump_start(idiagnl, skb, nlh,
					  inet_diag_dump, NULL, 0);
	}

	return inet_diag_get_exact(skb, nlh);
}

static DEFINE_MUTEX(inet_diag_mutex);

static void inet_diag_rcv(struct sk_buff *skb)
{
	mutex_lock(&inet_diag_mutex);
	netlink_rcv_skb(skb, &inet_diag_rcv_msg);
	mutex_unlock(&inet_diag_mutex);
}

int inet_diag_register(const struct inet_diag_handler *h)
{
	const __u16 type = h->idiag_type;
	int err = -EINVAL;

	if (type >= INET_DIAG_GETSOCK_MAX)
		goto out;

	mutex_lock(&inet_diag_table_mutex);
	err = -EEXIST;
	if (inet_diag_table[type] == NULL) {
		inet_diag_table[type] = h;
		err = 0;
	}
	mutex_unlock(&inet_diag_table_mutex);
out:
	return err;
}
EXPORT_SYMBOL_GPL(inet_diag_register);

void inet_diag_unregister(const struct inet_diag_handler *h)
{
	const __u16 type = h->idiag_type;

	if (type >= INET_DIAG_GETSOCK_MAX)
		return;

	mutex_lock(&inet_diag_table_mutex);
	inet_diag_table[type] = NULL;
	mutex_unlock(&inet_diag_table_mutex);
}
EXPORT_SYMBOL_GPL(inet_diag_unregister);

static int __init inet_diag_init(void)
{
	const int inet_diag_table_size = (INET_DIAG_GETSOCK_MAX *
					  sizeof(struct inet_diag_handler *));
	int err = -ENOMEM;

	inet_diag_table = kzalloc(inet_diag_table_size, GFP_KERNEL);
	if (!inet_diag_table)
		goto out;

	idiagnl = netlink_kernel_create(&init_net, NETLINK_INET_DIAG, 0,
					inet_diag_rcv, NULL, THIS_MODULE);
	if (idiagnl == NULL)
		goto out_free_table;
	err = 0;
out:
	return err;
out_free_table:
	kfree(inet_diag_table);
	goto out;
}

static void __exit inet_diag_exit(void)
{
	netlink_kernel_release(idiagnl);
	kfree(inet_diag_table);
}

module_init(inet_diag_init);
module_exit(inet_diag_exit);
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_INET_DIAG);