summaryrefslogtreecommitdiffstats
path: root/include/linux/sctp.h
Commit message (Collapse)AuthorAgeFilesLines
* sctp: implement definition for SACK-IMMEDIATELY extensionWei Yongjun2009-11-231-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch implement the definition for SACK-IMMEDIATELY extension. Section 3. The I-bit in the DATA Chunk Header The following Figure 1 shows the extended DATA chunk. 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Type = 0 | Res |I|U|B|E| Length | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | TSN | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Stream Identifier | Stream Sequence Number | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Payload Protocol Identifier | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ \ \ / User Data / \ \ +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ Figure 1 The only difference between the DATA chunk in Figure 1 and the DATA chunk defined in [RFC4960] is the addition of the I-bit in the flags field of the chunk header. Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com> Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
* sctp: fix error cause codes of ADD-IP extensionWei Yongjun2009-06-031-10/+10
| | | | | | | | | | | | | | | | | | | RFC5061 had changed the error cause codes for Dynamic Address Reconfiguration As the following: Cause Code Value Cause Code --------- ---------------- 0x00A0 Request to Delete Last Remaining IP Address 0x00A1 Operation Refused Due to Resource Shortage 0x00A2 Request to Delete Source IP Address 0x00A3 Association Aborted Due to Illegal ASCONF-ACK 0x00A4 Request Refused - No Authorization This patch fix the error cause codes. Signed-off-by: Wei Yongjun <yjwei@cn.fujitsu.com> Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
* sctp: Clean up sctp checksumming codeVlad Yasevich2009-02-161-1/+1
| | | | | | | | | | | The sctp crc32c checksum is always generated in little endian. So, we clean up the code to treat it as little endian and remove all the __force casts. Suggested by Herbert Xu. Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* net: replace __constant_{endian} uses in net headersHarvey Harrison2009-02-151-45/+45
| | | | | | | | Base versions handle constant folding now. For headers exposed to userspace, we must only expose the __ prefixed versions. Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [SCTP]: Stop claiming that this is a "reference implementation"Vlad Yasevich2008-02-051-2/+2
| | | | | | | | | | | I was notified by Randy Stewart that lksctp claims to be "the reference implementation". First of all, "the refrence implementation" was the original implementation of SCTP in usersapce written ty Randy and a few others. Second, after looking at the definiton of 'reference implementation', we don't really meet the requirements. Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com>
* [SCTP]: protocol definitions for SCTP-AUTH implementationVlad Yasevich2007-10-111-1/+99
| | | | | Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [SCTP]: Implement the Supported Extensions ParameterVlad Yasevich2007-10-111-0/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | SCTP Supported Extenions parameter is specified in Section 4.2.7 of the ADD-IP draft (soon to be RFC). The parameter is encoded as: 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | Parameter Type = 0x8008 | Parameter Length | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | CHUNK TYPE 1 | CHUNK TYPE 2 | CHUNK TYPE 3 | CHUNK TYPE 4 | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | .... | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | CHUNK TYPE N | PAD | PAD | PAD | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ It contains a list of chunks that a particular SCTP extension uses. Current extensions supported are Partial Reliability (FWD-TSN) and ADD-IP (ASCONF and ASCONF-ACK). When implementing new extensions (AUTH, PKT-DROP, etc..), new chunks need to be added to this parameter. Parameter processing would be modified to negotiate support for these new features. Signed-off-by: Vlad Yasevich <vladislav.yasevich@hp.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [SK_BUFF]: Introduce skb_transport_header(skb)Arnaldo Carvalho de Melo2007-04-261-1/+1
| | | | | | | | | For the places where we need a pointer to the transport header, it is still legal to touch skb->h.raw directly if just adding to, subtracting from or setting it to another layer header. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [SCTP]: Introduce sctp_hdr()Arnaldo Carvalho de Melo2007-04-261-0/+9
| | | | | | | For consistency with all the other skb->h.raw accessors. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [SCTP]: Fix typo adaption -> adaptation as per the latest API draft.Ivan Skytte Jorgensen2006-12-221-5/+5
| | | | | | Signed-off-by: Ivan Skytte Jorgensen <isj-sctp@i1.dk> Signed-off-by: Sridhar Samudrala <sri@us.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
* [SCTP]: Annotate SCTP headers.Al Viro2006-12-031-36/+36
| | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
* Linux-2.6.12-rc2Linus Torvalds2005-04-171-0/+594
Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-09-12 19:52:21 +0200
#n516'>516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 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 
/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		IPv4 Forwarding Information Base: semantics.
 *
 * Version:	$Id: fib_semantics.c,v 1.19 2002/01/12 07:54:56 davem Exp $
 *
 * 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 <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/jiffies.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/init.h>

#include <net/arp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/ip_mp_alg.h>
#include <net/netlink.h>
#include <net/nexthop.h>

#include "fib_lookup.h"

#define FSprintk(a...)

static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
static unsigned int fib_hash_size;
static unsigned int fib_info_cnt;

#define DEVINDEX_HASHBITS 8
#define DEVINDEX_HASHSIZE (1U << DEVINDEX_HASHBITS)
static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];

#ifdef CONFIG_IP_ROUTE_MULTIPATH

static DEFINE_SPINLOCK(fib_multipath_lock);

#define for_nexthops(fi) { int nhsel; const struct fib_nh * nh; \
for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++)

#define change_nexthops(fi) { int nhsel; struct fib_nh * nh; \
for (nhsel=0, nh = (struct fib_nh*)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++)

#else /* CONFIG_IP_ROUTE_MULTIPATH */

/* Hope, that gcc will optimize it to get rid of dummy loop */

#define for_nexthops(fi) { int nhsel=0; const struct fib_nh * nh = (fi)->fib_nh; \
for (nhsel=0; nhsel < 1; nhsel++)

#define change_nexthops(fi) { int nhsel=0; struct fib_nh * nh = (struct fib_nh*)((fi)->fib_nh); \
for (nhsel=0; nhsel < 1; nhsel++)

#endif /* CONFIG_IP_ROUTE_MULTIPATH */

#define endfor_nexthops(fi) }


static const struct
{
	int	error;
	u8	scope;
} fib_props[RTN_MAX + 1] = {
	{
		.error	= 0,
		.scope	= RT_SCOPE_NOWHERE,
	},	/* RTN_UNSPEC */
	{
		.error	= 0,
		.scope	= RT_SCOPE_UNIVERSE,
	},	/* RTN_UNICAST */
	{
		.error	= 0,
		.scope	= RT_SCOPE_HOST,
	},	/* RTN_LOCAL */
	{
		.error	= 0,
		.scope	= RT_SCOPE_LINK,
	},	/* RTN_BROADCAST */
	{
		.error	= 0,
		.scope	= RT_SCOPE_LINK,
	},	/* RTN_ANYCAST */
	{
		.error	= 0,
		.scope	= RT_SCOPE_UNIVERSE,
	},	/* RTN_MULTICAST */
	{
		.error	= -EINVAL,
		.scope	= RT_SCOPE_UNIVERSE,
	},	/* RTN_BLACKHOLE */
	{
		.error	= -EHOSTUNREACH,
		.scope	= RT_SCOPE_UNIVERSE,
	},	/* RTN_UNREACHABLE */
	{
		.error	= -EACCES,
		.scope	= RT_SCOPE_UNIVERSE,
	},	/* RTN_PROHIBIT */
	{
		.error	= -EAGAIN,
		.scope	= RT_SCOPE_UNIVERSE,
	},	/* RTN_THROW */
	{
		.error	= -EINVAL,
		.scope	= RT_SCOPE_NOWHERE,
	},	/* RTN_NAT */
	{
		.error	= -EINVAL,
		.scope	= RT_SCOPE_NOWHERE,
	},	/* RTN_XRESOLVE */
};


/* Release a nexthop info record */

void free_fib_info(struct fib_info *fi)
{
	if (fi->fib_dead == 0) {
		printk("Freeing alive fib_info %p\n", fi);
		return;
	}
	change_nexthops(fi) {
		if (nh->nh_dev)
			dev_put(nh->nh_dev);
		nh->nh_dev = NULL;
	} endfor_nexthops(fi);
	fib_info_cnt--;
	kfree(fi);
}

void fib_release_info(struct fib_info *fi)
{
	spin_lock_bh(&fib_info_lock);
	if (fi && --fi->fib_treeref == 0) {
		hlist_del(&fi->fib_hash);
		if (fi->fib_prefsrc)
			hlist_del(&fi->fib_lhash);
		change_nexthops(fi) {
			if (!nh->nh_dev)
				continue;
			hlist_del(&nh->nh_hash);
		} endfor_nexthops(fi)
		fi->fib_dead = 1;
		fib_info_put(fi);
	}
	spin_unlock_bh(&fib_info_lock);
}

static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
{
	const struct fib_nh *onh = ofi->fib_nh;

	for_nexthops(fi) {
		if (nh->nh_oif != onh->nh_oif ||
		    nh->nh_gw  != onh->nh_gw ||
		    nh->nh_scope != onh->nh_scope ||
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		    nh->nh_weight != onh->nh_weight ||
#endif
#ifdef CONFIG_NET_CLS_ROUTE
		    nh->nh_tclassid != onh->nh_tclassid ||
#endif
		    ((nh->nh_flags^onh->nh_flags)&~RTNH_F_DEAD))
			return -1;
		onh++;
	} endfor_nexthops(fi);
	return 0;
}

static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
{
	unsigned int mask = (fib_hash_size - 1);
	unsigned int val = fi->fib_nhs;

	val ^= fi->fib_protocol;
	val ^= (__force u32)fi->fib_prefsrc;
	val ^= fi->fib_priority;

	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
}

static struct fib_info *fib_find_info(const struct fib_info *nfi)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct fib_info *fi;
	unsigned int hash;

	hash = fib_info_hashfn(nfi);
	head = &fib_info_hash[hash];

	hlist_for_each_entry(fi, node, head, fib_hash) {
		if (fi->fib_nhs != nfi->fib_nhs)
			continue;
		if (nfi->fib_protocol == fi->fib_protocol &&
		    nfi->fib_prefsrc == fi->fib_prefsrc &&
		    nfi->fib_priority == fi->fib_priority &&
		    memcmp(nfi->fib_metrics, fi->fib_metrics,
			   sizeof(fi->fib_metrics)) == 0 &&
		    ((nfi->fib_flags^fi->fib_flags)&~RTNH_F_DEAD) == 0 &&
		    (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
			return fi;
	}

	return NULL;
}

static inline unsigned int fib_devindex_hashfn(unsigned int val)
{
	unsigned int mask = DEVINDEX_HASHSIZE - 1;

	return (val ^
		(val >> DEVINDEX_HASHBITS) ^
		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
}

/* Check, that the gateway is already configured.
   Used only by redirect accept routine.
 */

int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
	struct hlist_head *head;
	struct hlist_node *node;
	struct fib_nh *nh;
	unsigned int hash;

	spin_lock(&fib_info_lock);

	hash = fib_devindex_hashfn(dev->ifindex);
	head = &fib_info_devhash[hash];
	hlist_for_each_entry(nh, node, head, nh_hash) {
		if (nh->nh_dev == dev &&
		    nh->nh_gw == gw &&
		    !(nh->nh_flags&RTNH_F_DEAD)) {
			spin_unlock(&fib_info_lock);
			return 0;
		}
	}

	spin_unlock(&fib_info_lock);

	return -1;
}

static inline size_t fib_nlmsg_size(struct fib_info *fi)
{
	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
			 + nla_total_size(4) /* RTA_TABLE */
			 + nla_total_size(4) /* RTA_DST */
			 + nla_total_size(4) /* RTA_PRIORITY */
			 + nla_total_size(4); /* RTA_PREFSRC */

	/* space for nested metrics */
	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));

	if (fi->fib_nhs) {
		/* Also handles the special case fib_nhs == 1 */

		/* each nexthop is packed in an attribute */
		size_t nhsize = nla_total_size(sizeof(struct rtnexthop));

		/* may contain flow and gateway attribute */
		nhsize += 2 * nla_total_size(4);

		/* all nexthops are packed in a nested attribute */
		payload += nla_total_size(fi->fib_nhs * nhsize);
	}

	return payload;
}

void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
	       int dst_len, u32 tb_id, struct nl_info *info)
{
	struct sk_buff *skb;
	u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
	int err = -ENOBUFS;

	skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
	if (skb == NULL)
		goto errout;

	err = fib_dump_info(skb, info->pid, seq, event, tb_id,
			    fa->fa_type, fa->fa_scope, key, dst_len,
			    fa->fa_tos, fa->fa_info, 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	err = rtnl_notify(skb, info->pid, RTNLGRP_IPV4_ROUTE,
			  info->nlh, GFP_KERNEL);
errout:
	if (err < 0)
		rtnl_set_sk_err(RTNLGRP_IPV4_ROUTE, err);
}

/* Return the first fib alias matching TOS with
 * priority less than or equal to PRIO.
 */
struct fib_alias *fib_find_alias(struct list_head *fah, u8 tos, u32 prio)
{
	if (fah) {
		struct fib_alias *fa;
		list_for_each_entry(fa, fah, fa_list) {
			if (fa->fa_tos > tos)
				continue;
			if (fa->fa_info->fib_priority >= prio ||
			    fa->fa_tos < tos)
				return fa;
		}
	}
	return NULL;
}

int fib_detect_death(struct fib_info *fi, int order,
		     struct fib_info **last_resort, int *last_idx, int *dflt)
{
	struct neighbour *n;
	int state = NUD_NONE;

	n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
	if (n) {
		state = n->nud_state;
		neigh_release(n);
	}
	if (state==NUD_REACHABLE)
		return 0;
	if ((state&NUD_VALID) && order != *dflt)
		return 0;
	if ((state&NUD_VALID) ||
	    (*last_idx<0 && order > *dflt)) {
		*last_resort = fi;
		*last_idx = order;
	}
	return 1;
}

#ifdef CONFIG_IP_ROUTE_MULTIPATH

static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining)
{
	int nhs = 0;

	while (rtnh_ok(rtnh, remaining)) {
		nhs++;
		rtnh = rtnh_next(rtnh, &remaining);
	}

	/* leftover implies invalid nexthop configuration, discard it */
	return remaining > 0 ? 0 : nhs;
}

static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
		       int remaining, struct fib_config *cfg)
{
	change_nexthops(fi) {
		int attrlen;

		if (!rtnh_ok(rtnh, remaining))
			return -EINVAL;

		nh->nh_flags = (cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
		nh->nh_oif = rtnh->rtnh_ifindex;
		nh->nh_weight = rtnh->rtnh_hops + 1;

		attrlen = rtnh_attrlen(rtnh);
		if (attrlen > 0) {
			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);

			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
			nh->nh_gw = nla ? nla_get_be32(nla) : 0;
#ifdef CONFIG_NET_CLS_ROUTE
			nla = nla_find(attrs, attrlen, RTA_FLOW);
			nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
#endif
		}

		rtnh = rtnh_next(rtnh, &remaining);
	} endfor_nexthops(fi);

	return 0;
}

#endif

int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	struct rtnexthop *rtnh;
	int remaining;
#endif

	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
		return 1;

	if (cfg->fc_oif || cfg->fc_gw) {
		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->nh_gw))
			return 0;
		return 1;
	}

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (cfg->fc_mp == NULL)
		return 0;

	rtnh = cfg->fc_mp;
	remaining = cfg->fc_mp_len;

	for_nexthops(fi) {
		int attrlen;

		if (!rtnh_ok(rtnh, remaining))
			return -EINVAL;

		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif)
			return 1;

		attrlen = rtnh_attrlen(rtnh);
		if (attrlen < 0) {
			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);

			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
			if (nla && nla_get_be32(nla) != nh->nh_gw)
				return 1;
#ifdef CONFIG_NET_CLS_ROUTE
			nla = nla_find(attrs, attrlen, RTA_FLOW);
			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
				return 1;
#endif
		}

		rtnh = rtnh_next(rtnh, &remaining);
	} endfor_nexthops(fi);
#endif
	return 0;
}


/*
   Picture
   -------

   Semantics of nexthop is very messy by historical reasons.
   We have to take into account, that:
   a) gateway can be actually local interface address,
      so that gatewayed route is direct.
   b) gateway must be on-link address, possibly
      described not by an ifaddr, but also by a direct route.
   c) If both gateway and interface are specified, they should not
      contradict.
   d) If we use tunnel routes, gateway could be not on-link.

   Attempt to reconcile all of these (alas, self-contradictory) conditions
   results in pretty ugly and hairy code with obscure logic.

   I chose to generalized it instead, so that the size
   of code does not increase practically, but it becomes
   much more general.
   Every prefix is assigned a "scope" value: "host" is local address,
   "link" is direct route,
   [ ... "site" ... "interior" ... ]
   and "universe" is true gateway route with global meaning.

   Every prefix refers to a set of "nexthop"s (gw, oif),
   where gw must have narrower scope. This recursion stops
   when gw has LOCAL scope or if "nexthop" is declared ONLINK,
   which means that gw is forced to be on link.

   Code is still hairy, but now it is apparently logically
   consistent and very flexible. F.e. as by-product it allows
   to co-exists in peace independent exterior and interior
   routing processes.

   Normally it looks as following.

   {universe prefix}  -> (gw, oif) [scope link]
			  |
			  |-> {link prefix} -> (gw, oif) [scope local]
						|
						|-> {local prefix} (terminal node)
 */

static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
			struct fib_nh *nh)
{
	int err;

	if (nh->nh_gw) {
		struct fib_result res;

#ifdef CONFIG_IP_ROUTE_PERVASIVE
		if (nh->nh_flags&RTNH_F_PERVASIVE)
			return 0;
#endif
		if (nh->nh_flags&RTNH_F_ONLINK) {
			struct net_device *dev;

			if (cfg->fc_scope >= RT_SCOPE_LINK)
				return -EINVAL;
			if (inet_addr_type(nh->nh_gw) != RTN_UNICAST)
				return -EINVAL;
			if ((dev = __dev_get_by_index(nh->nh_oif)) == NULL)
				return -ENODEV;
			if (!(dev->flags&IFF_UP))
				return -ENETDOWN;
			nh->nh_dev = dev;
			dev_hold(dev);
			nh->nh_scope = RT_SCOPE_LINK;
			return 0;
		}
		{
			struct flowi fl = {
				.nl_u = {
					.ip4_u = {
						.daddr = nh->nh_gw,
						.scope = cfg->fc_scope + 1,
					},
				},
				.oif = nh->nh_oif,
			};

			/* It is not necessary, but requires a bit of thinking */
			if (fl.fl4_scope < RT_SCOPE_LINK)
				fl.fl4_scope = RT_SCOPE_LINK;
			if ((err = fib_lookup(&fl, &res)) != 0)
				return err;
		}
		err = -EINVAL;
		if (res.type != RTN_UNICAST && res.type != RTN_LOCAL)
			goto out;
		nh->nh_scope = res.scope;
		nh->nh_oif = FIB_RES_OIF(res);
		if ((nh->nh_dev = FIB_RES_DEV(res)) == NULL)
			goto out;
		dev_hold(nh->nh_dev);
		err = -ENETDOWN;
		if (!(nh->nh_dev->flags & IFF_UP))
			goto out;
		err = 0;
out:
		fib_res_put(&res);
		return err;
	} else {
		struct in_device *in_dev;

		if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK))
			return -EINVAL;

		in_dev = inetdev_by_index(nh->nh_oif);
		if (in_dev == NULL)
			return -ENODEV;
		if (!(in_dev->dev->flags&IFF_UP)) {
			in_dev_put(in_dev);
			return -ENETDOWN;
		}
		nh->nh_dev = in_dev->dev;
		dev_hold(nh->nh_dev);
		nh->nh_scope = RT_SCOPE_HOST;
		in_dev_put(in_dev);
	}
	return 0;
}

static inline unsigned int fib_laddr_hashfn(__be32 val)
{
	unsigned int mask = (fib_hash_size - 1);

	return ((__force u32)val ^ ((__force u32)val >> 7) ^ ((__force u32)val >> 14)) & mask;
}

static struct hlist_head *fib_hash_alloc(int bytes)
{
	if (bytes <= PAGE_SIZE)
		return kmalloc(bytes, GFP_KERNEL);
	else
		return (struct hlist_head *)
			__get_free_pages(GFP_KERNEL, get_order(bytes));
}

static void fib_hash_free(struct hlist_head *hash, int bytes)
{
	if (!hash)
		return;

	if (bytes <= PAGE_SIZE)
		kfree(hash);
	else
		free_pages((unsigned long) hash, get_order(bytes));
}

static void fib_hash_move(struct hlist_head *new_info_hash,
			  struct hlist_head *new_laddrhash,
			  unsigned int new_size)
{
	struct hlist_head *old_info_hash, *old_laddrhash;
	unsigned int old_size = fib_hash_size;
	unsigned int i, bytes;

	spin_lock_bh(&fib_info_lock);
	old_info_hash = fib_info_hash;
	old_laddrhash = fib_info_laddrhash;
	fib_hash_size = new_size;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *head = &fib_info_hash[i];
		struct hlist_node *node, *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, node, n, head, fib_hash) {
			struct hlist_head *dest;
			unsigned int new_hash;

			hlist_del(&fi->fib_hash);

			new_hash = fib_info_hashfn(fi);
			dest = &new_info_hash[new_hash];
			hlist_add_head(&fi->fib_hash, dest);
		}
	}
	fib_info_hash = new_info_hash;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *lhead = &fib_info_laddrhash[i];
		struct hlist_node *node, *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, node, n, lhead, fib_lhash) {
			struct hlist_head *ldest;
			unsigned int new_hash;

			hlist_del(&fi->fib_lhash);

			new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
			ldest = &new_laddrhash[new_hash];
			hlist_add_head(&fi->fib_lhash, ldest);
		}
	}
	fib_info_laddrhash = new_laddrhash;

	spin_unlock_bh(&fib_info_lock);

	bytes = old_size * sizeof(struct hlist_head *);
	fib_hash_free(old_info_hash, bytes);
	fib_hash_free(old_laddrhash, bytes);
}

struct fib_info *fib_create_info(struct fib_config *cfg)
{
	int err;
	struct fib_info *fi = NULL;
	struct fib_info *ofi;
	int nhs = 1;

	/* Fast check to catch the most weird cases */
	if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
		goto err_inval;

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (cfg->fc_mp) {
		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
		if (nhs == 0)
			goto err_inval;
	}
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
	if (cfg->fc_mp_alg) {
		if (cfg->fc_mp_alg < IP_MP_ALG_NONE ||
		    cfg->fc_mp_alg > IP_MP_ALG_MAX)
			goto err_inval;
	}
#endif

	err = -ENOBUFS;
	if (fib_info_cnt >= fib_hash_size) {
		unsigned int new_size = fib_hash_size << 1;
		struct hlist_head *new_info_hash;
		struct hlist_head *new_laddrhash;
		unsigned int bytes;

		if (!new_size)
			new_size = 1;
		bytes = new_size * sizeof(struct hlist_head *);
		new_info_hash = fib_hash_alloc(bytes);
		new_laddrhash = fib_hash_alloc(bytes);
		if (!new_info_hash || !new_laddrhash) {
			fib_hash_free(new_info_hash, bytes);
			fib_hash_free(new_laddrhash, bytes);
		} else {
			memset(new_info_hash, 0, bytes);
			memset(new_laddrhash, 0, bytes);

			fib_hash_move(new_info_hash, new_laddrhash, new_size);
		}

		if (!fib_hash_size)
			goto failure;
	}

	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
	if (fi == NULL)
		goto failure;
	fib_info_cnt++;

	fi->fib_protocol = cfg->fc_protocol;
	fi->fib_flags = cfg->fc_flags;
	fi->fib_priority = cfg->fc_priority;
	fi->fib_prefsrc = cfg->fc_prefsrc;

	fi->fib_nhs = nhs;
	change_nexthops(fi) {
		nh->nh_parent = fi;
	} endfor_nexthops(fi)

	if (cfg->fc_mx) {
		struct nlattr *nla;
		int remaining;

		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
			int type = nla->nla_type;

			if (type) {
				if (type > RTAX_MAX)
					goto err_inval;
				fi->fib_metrics[type - 1] = nla_get_u32(nla);
			}
		}
	}

	if (cfg->fc_mp) {
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg);
		if (err != 0)
			goto failure;
		if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif)
			goto err_inval;
		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
			goto err_inval;
#ifdef CONFIG_NET_CLS_ROUTE
		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
			goto err_inval;
#endif
#else
		goto err_inval;
#endif
	} else {
		struct fib_nh *nh = fi->fib_nh;

		nh->nh_oif = cfg->fc_oif;
		nh->nh_gw = cfg->fc_gw;
		nh->nh_flags = cfg->fc_flags;
#ifdef CONFIG_NET_CLS_ROUTE
		nh->nh_tclassid = cfg->fc_flow;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		nh->nh_weight = 1;
#endif
	}

#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
	fi->fib_mp_alg = cfg->fc_mp_alg;
#endif

	if (fib_props[cfg->fc_type].error) {
		if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
			goto err_inval;
		goto link_it;
	}

	if (cfg->fc_scope > RT_SCOPE_HOST)
		goto err_inval;

	if (cfg->fc_scope == RT_SCOPE_HOST) {
		struct fib_nh *nh = fi->fib_nh;

		/* Local address is added. */
		if (nhs != 1 || nh->nh_gw)
			goto err_inval;
		nh->nh_scope = RT_SCOPE_NOWHERE;
		nh->nh_dev = dev_get_by_index(fi->fib_nh->nh_oif);
		err = -ENODEV;
		if (nh->nh_dev == NULL)
			goto failure;
	} else {
		change_nexthops(fi) {
			if ((err = fib_check_nh(cfg, fi, nh)) != 0)
				goto failure;
		} endfor_nexthops(fi)
	}

	if (fi->fib_prefsrc) {
		if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
		    fi->fib_prefsrc != cfg->fc_dst)
			if (inet_addr_type(fi->fib_prefsrc) != RTN_LOCAL)
				goto err_inval;
	}

link_it:
	if ((ofi = fib_find_info(fi)) != NULL) {
		fi->fib_dead = 1;
		free_fib_info(fi);
		ofi->fib_treeref++;
		return ofi;
	}

	fi->fib_treeref++;
	atomic_inc(&fi->fib_clntref);
	spin_lock_bh(&fib_info_lock);
	hlist_add_head(&fi->fib_hash,
		       &fib_info_hash[fib_info_hashfn(fi)]);
	if (fi->fib_prefsrc) {
		struct hlist_head *head;

		head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
		hlist_add_head(&fi->fib_lhash, head);
	}
	change_nexthops(fi) {
		struct hlist_head *head;
		unsigned int hash;

		if (!nh->nh_dev)
			continue;
		hash = fib_devindex_hashfn(nh->nh_dev->ifindex);
		head = &fib_info_devhash[hash];
		hlist_add_head(&nh->nh_hash, head);
	} endfor_nexthops(fi)
	spin_unlock_bh(&fib_info_lock);
	return fi;

err_inval:
	err = -EINVAL;

failure:
	if (fi) {
		fi->fib_dead = 1;
		free_fib_info(fi);
	}

	return ERR_PTR(err);
}

/* Note! fib_semantic_match intentionally uses  RCU list functions. */
int fib_semantic_match(struct list_head *head, const struct flowi *flp,
		       struct fib_result *res, __be32 zone, __be32 mask,
			int prefixlen)
{
	struct fib_alias *fa;
	int nh_sel = 0;

	list_for_each_entry_rcu(fa, head, fa_list) {
		int err;

		if (fa->fa_tos &&
		    fa->fa_tos != flp->fl4_tos)
			continue;

		if (fa->fa_scope < flp->fl4_scope)
			continue;

		fa->fa_state |= FA_S_ACCESSED;

		err = fib_props[fa->fa_type].error;
		if (err == 0) {
			struct fib_info *fi = fa->fa_info;

			if (fi->fib_flags & RTNH_F_DEAD)
				continue;

			switch (fa->fa_type) {
			case RTN_UNICAST:
			case RTN_LOCAL:
			case RTN_BROADCAST:
			case RTN_ANYCAST:
			case RTN_MULTICAST:
				for_nexthops(fi) {
					if (nh->nh_flags&RTNH_F_DEAD)
						continue;
					if (!flp->oif || flp->oif == nh->nh_oif)
						break;
				}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
				if (nhsel < fi->fib_nhs) {
					nh_sel = nhsel;
					goto out_fill_res;
				}
#else
				if (nhsel < 1) {
					goto out_fill_res;
				}
#endif
				endfor_nexthops(fi);
				continue;

			default:
				printk(KERN_DEBUG "impossible 102\n");
				return -EINVAL;
			}
		}
		return err;
	}
	return 1;

out_fill_res:
	res->prefixlen = prefixlen;
	res->nh_sel = nh_sel;
	res->type = fa->fa_type;
	res->scope = fa->fa_scope;
	res->fi = fa->fa_info;
#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
	res->netmask = mask;
	res->network = zone & inet_make_mask(prefixlen);
#endif
	atomic_inc(&res->fi->fib_clntref);
	return 0;
}

/* Find appropriate source address to this destination */

__be32 __fib_res_prefsrc(struct fib_result *res)
{
	return inet_select_addr(FIB_RES_DEV(*res), FIB_RES_GW(*res), res->scope);
}

int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event,
		  u32 tb_id, u8 type, u8 scope, __be32 dst, int dst_len, u8 tos,
		  struct fib_info *fi, unsigned int flags)
{
	struct nlmsghdr *nlh;
	struct rtmsg *rtm;

	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*rtm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	rtm = nlmsg_data(nlh);
	rtm->rtm_family = AF_INET;
	rtm->rtm_dst_len = dst_len;
	rtm->rtm_src_len = 0;
	rtm->rtm_tos = tos;
	rtm->rtm_table = tb_id;
	NLA_PUT_U32(skb, RTA_TABLE, tb_id);
	rtm->rtm_type = type;
	rtm->rtm_flags = fi->fib_flags;
	rtm->rtm_scope = scope;
	rtm->rtm_protocol = fi->fib_protocol;

	if (rtm->rtm_dst_len)
		NLA_PUT_BE32(skb, RTA_DST, dst);

	if (fi->fib_priority)
		NLA_PUT_U32(skb, RTA_PRIORITY, fi->fib_priority);

	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
		goto nla_put_failure;

	if (fi->fib_prefsrc)
		NLA_PUT_BE32(skb, RTA_PREFSRC, fi->fib_prefsrc);

	if (fi->fib_nhs == 1) {
		if (fi->fib_nh->nh_gw)
			NLA_PUT_BE32(skb, RTA_GATEWAY, fi->fib_nh->nh_gw);

		if (fi->fib_nh->nh_oif)
			NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif);
#ifdef CONFIG_NET_CLS_ROUTE
		if (fi->fib_nh[0].nh_tclassid)
			NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid);
#endif
	}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (fi->fib_nhs > 1) {
		struct rtnexthop *rtnh;
		struct nlattr *mp;

		mp = nla_nest_start(skb, RTA_MULTIPATH);
		if (mp == NULL)
			goto nla_put_failure;

		for_nexthops(fi) {
			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
			if (rtnh == NULL)
				goto nla_put_failure;

			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
			rtnh->rtnh_hops = nh->nh_weight - 1;
			rtnh->rtnh_ifindex = nh->nh_oif;

			if (nh->nh_gw)
				NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw);
#ifdef CONFIG_NET_CLS_ROUTE
			if (nh->nh_tclassid)
				NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid);
#endif
			/* length of rtnetlink header + attributes */
			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
		} endfor_nexthops(fi);

		nla_nest_end(skb, mp);
	}
#endif
	return nlmsg_end(skb, nlh);

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

/*
   Update FIB if:
   - local address disappeared -> we must delete all the entries
     referring to it.
   - device went down -> we must shutdown all nexthops going via it.
 */

int fib_sync_down(__be32 local, struct net_device *dev, int force)
{
	int ret = 0;
	int scope = RT_SCOPE_NOWHERE;

	if (force)
		scope = -1;

	if (local && fib_info_laddrhash) {
		unsigned int hash = fib_laddr_hashfn(local);
		struct hlist_head *head = &fib_info_laddrhash[hash];
		struct hlist_node *node;
		struct fib_info *fi;

		hlist_for_each_entry(fi, node, head, fib_lhash) {
			if (fi->fib_prefsrc == local) {
				fi->fib_flags |= RTNH_F_DEAD;
				ret++;
			}
		}
	}

	if (dev) {
		struct fib_info *prev_fi = NULL;
		unsigned int hash = fib_devindex_hashfn(dev->ifindex);
		struct hlist_head *head = &fib_info_devhash[hash];
		struct hlist_node *node;
		struct fib_nh *nh;

		hlist_for_each_entry(nh, node, head, nh_hash) {
			struct fib_info *fi = nh->nh_parent;
			int dead;

			BUG_ON(!fi->fib_nhs);
			if (nh->nh_dev != dev || fi == prev_fi)
				continue;
			prev_fi = fi;
			dead = 0;
			change_nexthops(fi) {
				if (nh->nh_flags&RTNH_F_DEAD)
					dead++;
				else if (nh->nh_dev == dev &&
					 nh->nh_scope != scope) {
					nh->nh_flags |= RTNH_F_DEAD;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
					spin_lock_bh(&fib_multipath_lock);
					fi->fib_power -= nh->nh_power;
					nh->nh_power = 0;
					spin_unlock_bh(&fib_multipath_lock);
#endif
					dead++;
				}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
				if (force > 1 && nh->nh_dev == dev) {
					dead = fi->fib_nhs;
					break;
				}
#endif
			} endfor_nexthops(fi)
			if (dead == fi->fib_nhs) {
				fi->fib_flags |= RTNH_F_DEAD;
				ret++;
			}
		}
	}

	return ret;
}

#ifdef CONFIG_IP_ROUTE_MULTIPATH

/*
   Dead device goes up. We wake up dead nexthops.
   It takes sense only on multipath routes.
 */

int fib_sync_up(struct net_device *dev)
{
	struct fib_info *prev_fi;
	unsigned int hash;
	struct hlist_head *head;
	struct hlist_node *node;
	struct fib_nh *nh;
	int ret;

	if (!(dev->flags&IFF_UP))
		return 0;

	prev_fi = NULL;
	hash = fib_devindex_hashfn(dev->ifindex);
	head = &fib_info_devhash[hash];
	ret = 0;

	hlist_for_each_entry(nh, node, head, nh_hash) {
		struct fib_info *fi = nh->nh_parent;
		int alive;

		BUG_ON(!fi->fib_nhs);
		if (nh->nh_dev != dev || fi == prev_fi)
			continue;

		prev_fi = fi;
		alive = 0;
		change_nexthops(fi) {
			if (!(nh->nh_flags&RTNH_F_DEAD)) {
				alive++;
				continue;
			}
			if (nh->nh_dev == NULL || !(nh->nh_dev->flags&IFF_UP))
				continue;
			if (nh->nh_dev != dev || !__in_dev_get_rtnl(dev))
				continue;
			alive++;
			spin_lock_bh(&fib_multipath_lock);
			nh->nh_power = 0;
			nh->nh_flags &= ~RTNH_F_DEAD;
			spin_unlock_bh(&fib_multipath_lock);
		} endfor_nexthops(fi)

		if (alive > 0) {
			fi->fib_flags &= ~RTNH_F_DEAD;
			ret++;
		}
	}

	return ret;
}

/*
   The algorithm is suboptimal, but it provides really
   fair weighted route distribution.
 */

void fib_select_multipath(const struct flowi *flp, struct fib_result *res)
{
	struct fib_info *fi = res->fi;
	int w;

	spin_lock_bh(&fib_multipath_lock);
	if (fi->fib_power <= 0) {
		int power = 0;
		change_nexthops(fi) {
			if (!(nh->nh_flags&RTNH_F_DEAD)) {
				power += nh->nh_weight;
				nh->nh_power = nh->nh_weight;
			}
		} endfor_nexthops(fi);
		fi->fib_power = power;
		if (power <= 0) {
			spin_unlock_bh(&fib_multipath_lock);
			/* Race condition: route has just become dead. */
			res->nh_sel = 0;
			return;
		}
	}


	/* w should be random number [0..fi->fib_power-1],
	   it is pretty bad approximation.
	 */

	w = jiffies % fi->fib_power;

	change_nexthops(fi) {
		if (!(nh->nh_flags&RTNH_F_DEAD) && nh->nh_power) {
			if ((w -= nh->nh_power) <= 0) {
				nh->nh_power--;
				fi->fib_power--;
				res->nh_sel = nhsel;
				spin_unlock_bh(&fib_multipath_lock);
				return;
			}
		}
	} endfor_nexthops(fi);

	/* Race condition: route has just become dead. */
	res->nh_sel = 0;
	spin_unlock_bh(&fib_multipath_lock);
}
#endif
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2024-09-12 19:52:12 +0200