From c71099acce933455123ee505cc75964610a209ad Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 23:20:06 -0700 Subject: [IPV6]: Multiple Routing Tables Adds the framework to support multiple IPv6 routing tables. Currently all automatically generated routes are put into the same table. This could be changed at a later point after considering the produced locking overhead. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/ip6_route.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/net/ip6_route.h') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 96b0e66406ec..d49c8c90eb68 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -58,7 +58,8 @@ extern int ipv6_route_ioctl(unsigned int cmd, void __user *arg); extern int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *, void *rtattr, - struct netlink_skb_parms *req); + struct netlink_skb_parms *req, + u32 table_id); extern int ip6_ins_rt(struct rt6_info *, struct nlmsghdr *, void *rtattr, -- cgit v1.2.3 From 101367c2f8c464ea96643192673aa18d88e6336d Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Fri, 4 Aug 2006 03:39:02 -0700 Subject: [IPV6]: Policy Routing Rules Adds support for policy routing rules including a new local table for routes with a local destination. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rtnetlink.h | 2 + include/net/ip6_fib.h | 9 +- include/net/ip6_route.h | 5 + net/ipv6/Kconfig | 1 + net/ipv6/Makefile | 1 + net/ipv6/addrconf.c | 1 + net/ipv6/fib6_rules.c | 251 ++++++++++++++++++++++++++++++++++++++++++++++ net/ipv6/ip6_fib.c | 21 ++-- net/ipv6/route.c | 50 +++++++++ 9 files changed, 329 insertions(+), 12 deletions(-) create mode 100644 net/ipv6/fib6_rules.c (limited to 'include/net/ip6_route.h') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index facd9ee37b76..bf353538ae93 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -889,6 +889,8 @@ enum rtnetlink_groups { RTNLGRP_NOP4, RTNLGRP_IPV6_PREFIX, #define RTNLGRP_IPV6_PREFIX RTNLGRP_IPV6_PREFIX + RTNLGRP_IPV6_RULE, +#define RTNLGRP_IPV6_RULE RTNLGRP_IPV6_RULE __RTNLGRP_MAX }; #define RTNLGRP_MAX (__RTNLGRP_MAX - 1) diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 818411519c89..7b47e8d5a765 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -155,7 +155,6 @@ struct fib6_table { #define RT6_TABLE_UNSPEC RT_TABLE_UNSPEC #define RT6_TABLE_MAIN RT_TABLE_MAIN -#define RT6_TABLE_LOCAL RT6_TABLE_MAIN #define RT6_TABLE_DFLT RT6_TABLE_MAIN #define RT6_TABLE_INFO RT6_TABLE_MAIN #define RT6_TABLE_PREFIX RT6_TABLE_MAIN @@ -163,9 +162,11 @@ struct fib6_table { #ifdef CONFIG_IPV6_MULTIPLE_TABLES #define FIB6_TABLE_MIN 1 #define FIB6_TABLE_MAX RT_TABLE_MAX +#define RT6_TABLE_LOCAL RT_TABLE_LOCAL #else #define FIB6_TABLE_MIN RT_TABLE_MAIN #define FIB6_TABLE_MAX FIB6_TABLE_MIN +#define RT6_TABLE_LOCAL RT6_TABLE_MAIN #endif #define RT6_F_STRICT 1 @@ -221,5 +222,11 @@ extern void fib6_run_gc(unsigned long dummy); extern void fib6_gc_cleanup(void); extern void fib6_init(void); + +extern void fib6_rules_init(void); +extern void fib6_rules_cleanup(void); +extern int fib6_rules_dump(struct sk_buff *, + struct netlink_callback *); + #endif #endif diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index d49c8c90eb68..9bfa3cc6cedb 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -41,6 +41,11 @@ struct pol_chain { extern struct rt6_info ip6_null_entry; +#ifdef CONFIG_IPV6_MULTIPLE_TABLES +extern struct rt6_info ip6_prohibit_entry; +extern struct rt6_info ip6_blk_hole_entry; +#endif + extern int ip6_rt_gc_interval; extern void ip6_route_input(struct sk_buff *skb); diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 159c63d99c81..36a6c2b79889 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -139,6 +139,7 @@ config IPV6_TUNNEL config IPV6_MULTIPLE_TABLES bool "IPv6: Multiple Routing Tables" depends on IPV6 && EXPERIMENTAL + select FIB_RULES ---help--- Support multiple routing tables. diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 386e0a626948..9eebf6091279 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -13,6 +13,7 @@ ipv6-objs := af_inet6.o anycast.o ip6_output.o ip6_input.o addrconf.o sit.o \ ipv6-$(CONFIG_XFRM) += xfrm6_policy.o xfrm6_state.o xfrm6_input.o \ xfrm6_output.o ipv6-$(CONFIG_NETFILTER) += netfilter.o +ipv6-$(CONFIG_IPV6_MULTIPLE_TABLES) += fib6_rules.o ipv6-objs += $(ipv6-y) obj-$(CONFIG_INET6_AH) += ah6.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 318767fcefdc..ed766eebc022 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3528,6 +3528,7 @@ static struct rtnetlink_link inet6_rtnetlink_table[RTM_NR_MSGTYPES] = { [RTM_DELROUTE - RTM_BASE] = { .doit = inet6_rtm_delroute, }, [RTM_GETROUTE - RTM_BASE] = { .doit = inet6_rtm_getroute, .dumpit = inet6_dump_fib, }, + [RTM_GETRULE - RTM_BASE] = { .dumpit = fib6_rules_dump, }, }; static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c new file mode 100644 index 000000000000..c3c8195744ee --- /dev/null +++ b/net/ipv6/fib6_rules.c @@ -0,0 +1,251 @@ +/* + * net/ipv6/fib6_rules.c IPv6 Routing Policy Rules + * + * Copyright (C)2003-2006 Helsinki University of Technology + * Copyright (C)2003-2006 USAGI/WIDE Project + * + * 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, version 2. + * + * Authors + * Thomas Graf + * Ville Nuorvala + */ + +#include +#include + +#include +#include +#include +#include + +struct fib6_rule +{ + struct fib_rule common; + struct rt6key src; + struct rt6key dst; + u8 tclass; +}; + +static struct fib_rules_ops fib6_rules_ops; + +static struct fib6_rule main_rule = { + .common = { + .refcnt = ATOMIC_INIT(2), + .pref = 0x7FFE, + .action = FR_ACT_TO_TBL, + .table = RT6_TABLE_MAIN, + }, +}; + +static struct fib6_rule local_rule = { + .common = { + .refcnt = ATOMIC_INIT(2), + .pref = 0, + .action = FR_ACT_TO_TBL, + .table = RT6_TABLE_LOCAL, + .flags = FIB_RULE_PERMANENT, + }, +}; + +static LIST_HEAD(fib6_rules); + +struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags, + pol_lookup_t lookup) +{ + struct fib_lookup_arg arg = { + .lookup_ptr = lookup, + }; + + fib_rules_lookup(&fib6_rules_ops, fl, flags, &arg); + if (arg.rule) + fib_rule_put(arg.rule); + + return (struct dst_entry *) arg.result; +} + +int fib6_rule_action(struct fib_rule *rule, struct flowi *flp, + int flags, struct fib_lookup_arg *arg) +{ + struct rt6_info *rt = NULL; + struct fib6_table *table; + pol_lookup_t lookup = arg->lookup_ptr; + + switch (rule->action) { + case FR_ACT_TO_TBL: + break; + case FR_ACT_UNREACHABLE: + rt = &ip6_null_entry; + goto discard_pkt; + default: + case FR_ACT_BLACKHOLE: + rt = &ip6_blk_hole_entry; + goto discard_pkt; + case FR_ACT_PROHIBIT: + rt = &ip6_prohibit_entry; + goto discard_pkt; + } + + table = fib6_get_table(rule->table); + if (table) + rt = lookup(table, flp, flags); + + if (rt != &ip6_null_entry) + goto out; + + dst_release(&rt->u.dst); +discard_pkt: + dst_hold(&rt->u.dst); +out: + arg->result = rt; + return rt == NULL ? -EAGAIN : 0; +} + + +static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) +{ + struct fib6_rule *r = (struct fib6_rule *) rule; + + if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) + return 0; + + if ((flags & RT6_F_HAS_SADDR) && + !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen)) + return 0; + + return 1; +} + +static struct nla_policy fib6_rule_policy[RTA_MAX+1] __read_mostly = { + [FRA_IFNAME] = { .type = NLA_STRING }, + [FRA_PRIORITY] = { .type = NLA_U32 }, + [FRA_SRC] = { .minlen = sizeof(struct in6_addr) }, + [FRA_DST] = { .minlen = sizeof(struct in6_addr) }, +}; + +static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + int err = -EINVAL; + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + if (frh->src_len > 128 || frh->dst_len > 128 || + (frh->tos & ~IPV6_FLOWINFO_MASK)) + goto errout; + + if (rule->action == FR_ACT_TO_TBL) { + if (rule->table == RT6_TABLE_UNSPEC) + goto errout; + + if (fib6_new_table(rule->table) == NULL) { + err = -ENOBUFS; + goto errout; + } + } + + if (tb[FRA_SRC]) + nla_memcpy(&rule6->src.addr, tb[FRA_SRC], + sizeof(struct in6_addr)); + + if (tb[FRA_DST]) + nla_memcpy(&rule6->dst.addr, tb[FRA_DST], + sizeof(struct in6_addr)); + + rule6->src.plen = frh->src_len; + rule6->dst.plen = frh->dst_len; + rule6->tclass = frh->tos; + + err = 0; +errout: + return err; +} + +static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, + struct nlattr **tb) +{ + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + if (frh->src_len && (rule6->src.plen != frh->src_len)) + return 0; + + if (frh->dst_len && (rule6->dst.plen != frh->dst_len)) + return 0; + + if (frh->tos && (rule6->tclass != frh->tos)) + return 0; + + if (tb[FRA_SRC] && + nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr))) + return 0; + + if (tb[FRA_DST] && + nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr))) + return 0; + + return 1; +} + +static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb, + struct nlmsghdr *nlh, struct fib_rule_hdr *frh) +{ + struct fib6_rule *rule6 = (struct fib6_rule *) rule; + + frh->family = AF_INET6; + frh->dst_len = rule6->dst.plen; + frh->src_len = rule6->src.plen; + frh->tos = rule6->tclass; + + if (rule6->dst.plen) + NLA_PUT(skb, FRA_DST, sizeof(struct in6_addr), + &rule6->dst.addr); + + if (rule6->src.plen) + NLA_PUT(skb, FRA_SRC, sizeof(struct in6_addr), + &rule6->src.addr); + + return 0; + +nla_put_failure: + return -ENOBUFS; +} + +int fib6_rules_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + return fib_rules_dump(skb, cb, AF_INET6); +} + +static u32 fib6_rule_default_pref(void) +{ + return 0x3FFF; +} + +static struct fib_rules_ops fib6_rules_ops = { + .family = AF_INET6, + .rule_size = sizeof(struct fib6_rule), + .action = fib6_rule_action, + .match = fib6_rule_match, + .configure = fib6_rule_configure, + .compare = fib6_rule_compare, + .fill = fib6_rule_fill, + .default_pref = fib6_rule_default_pref, + .nlgroup = RTNLGRP_IPV6_RULE, + .policy = fib6_rule_policy, + .rules_list = &fib6_rules, + .owner = THIS_MODULE, +}; + +void __init fib6_rules_init(void) +{ + list_add_tail(&local_rule.common.list, &fib6_rules); + list_add_tail(&main_rule.common.list, &fib6_rules); + + fib_rules_register(&fib6_rules_ops); +} + +void fib6_rules_cleanup(void) +{ + fib_rules_unregister(&fib6_rules_ops); +} diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index fcd7da830aca..ce226c14bef5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -159,6 +159,15 @@ static struct fib6_table fib6_main_tbl = { #ifdef CONFIG_IPV6_MULTIPLE_TABLES +static struct fib6_table fib6_local_tbl = { + .tb6_id = RT6_TABLE_LOCAL, + .tb6_lock = RW_LOCK_UNLOCKED, + .tb6_root = { + .leaf = &ip6_null_entry, + .fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO, + }, +}; + #define FIB_TABLE_HASHSZ 256 static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; @@ -228,20 +237,10 @@ struct fib6_table *fib6_get_table(u32 id) return NULL; } -struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags, - pol_lookup_t lookup) -{ - /* - * TODO: Add rule lookup - */ - struct fib6_table *table = fib6_get_table(RT6_TABLE_MAIN); - - return (struct dst_entry *) lookup(table, fl, flags); -} - static void __init fib6_tables_init(void) { fib6_link_table(&fib6_main_tbl); + fib6_link_table(&fib6_local_tbl); } #else diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 73efdadb9ab8..438977e2085d 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -140,6 +140,50 @@ struct rt6_info ip6_null_entry = { .rt6i_ref = ATOMIC_INIT(1), }; +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + +struct rt6_info ip6_prohibit_entry = { + .u = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .dev = &loopback_dev, + .obsolete = -1, + .error = -EACCES, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = ip6_pkt_discard, + .output = ip6_pkt_discard_out, + .ops = &ip6_dst_ops, + .path = (struct dst_entry*)&ip6_prohibit_entry, + } + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; + +struct rt6_info ip6_blk_hole_entry = { + .u = { + .dst = { + .__refcnt = ATOMIC_INIT(1), + .__use = 1, + .dev = &loopback_dev, + .obsolete = -1, + .error = -EINVAL, + .metrics = { [RTAX_HOPLIMIT - 1] = 255, }, + .input = ip6_pkt_discard, + .output = ip6_pkt_discard_out, + .ops = &ip6_dst_ops, + .path = (struct dst_entry*)&ip6_blk_hole_entry, + } + }, + .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), + .rt6i_metric = ~(u32) 0, + .rt6i_ref = ATOMIC_INIT(1), +}; + +#endif + /* allocate dst with ip6_dst_ops */ static __inline__ struct rt6_info *ip6_dst_alloc(void) { @@ -2408,10 +2452,16 @@ void __init ip6_route_init(void) #ifdef CONFIG_XFRM xfrm6_init(); #endif +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + fib6_rules_init(); +#endif } void ip6_route_cleanup(void) { +#ifdef CONFIG_IPV6_MULTIPLE_TABLES + fib6_rules_cleanup(); +#endif #ifdef CONFIG_PROC_FS proc_net_remove("ipv6_route"); proc_net_remove("rt6_stats"); -- cgit v1.2.3 From 1b43af5480c351dbcb2eef478bafe179cbeb6e83 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Thu, 10 Aug 2006 23:11:17 -0700 Subject: [IPV6]: Increase number of possible routing tables to 2^32 Increase number of possible routing tables to 2^32 by replacing iterations over all possible table IDs by hash table walking. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/net/ip6_route.h | 7 ++ net/ipv6/ip6_fib.c | 171 ++++++++++++++++++++++++++++++++++++++++++------ net/ipv6/route.c | 128 +----------------------------------- 3 files changed, 159 insertions(+), 147 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 9bfa3cc6cedb..01bfe404784f 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -137,6 +137,13 @@ extern int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *a extern int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg); extern int inet6_rtm_getroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg); +struct rt6_rtnl_dump_arg +{ + struct sk_buff *skb; + struct netlink_callback *cb; +}; + +extern int rt6_dump_route(struct rt6_info *rt, void *p_arg); extern void rt6_ifdown(struct net_device *dev); extern void rt6_mtu_change(struct net_device *dev, unsigned mtu); diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 1f2316187ca4..bececbe9dd2c 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -158,7 +158,26 @@ static struct fib6_table fib6_main_tbl = { }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES +#define FIB_TABLE_HASHSZ 256 +#else +#define FIB_TABLE_HASHSZ 1 +#endif +static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; + +static void fib6_link_table(struct fib6_table *tb) +{ + unsigned int h; + + h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1); + /* + * No protection necessary, this is the only list mutatation + * operation, tables never disappear once they exist. + */ + hlist_add_head_rcu(&tb->tb6_hlist, &fib_table_hash[h]); +} + +#ifdef CONFIG_IPV6_MULTIPLE_TABLES static struct fib6_table fib6_local_tbl = { .tb6_id = RT6_TABLE_LOCAL, .tb6_lock = RW_LOCK_UNLOCKED, @@ -168,9 +187,6 @@ static struct fib6_table fib6_local_tbl = { }, }; -#define FIB_TABLE_HASHSZ 256 -static struct hlist_head fib_table_hash[FIB_TABLE_HASHSZ]; - static struct fib6_table *fib6_alloc_table(u32 id) { struct fib6_table *table; @@ -186,19 +202,6 @@ static struct fib6_table *fib6_alloc_table(u32 id) return table; } -static void fib6_link_table(struct fib6_table *tb) -{ - unsigned int h; - - h = tb->tb6_id & (FIB_TABLE_HASHSZ - 1); - - /* - * No protection necessary, this is the only list mutatation - * operation, tables never disappear once they exist. - */ - hlist_add_head_rcu(&tb->tb6_hlist, &fib_table_hash[h]); -} - struct fib6_table *fib6_new_table(u32 id) { struct fib6_table *tb; @@ -263,10 +266,135 @@ struct dst_entry *fib6_rule_lookup(struct flowi *fl, int flags, static void __init fib6_tables_init(void) { + fib6_link_table(&fib6_main_tbl); } #endif +static int fib6_dump_node(struct fib6_walker_t *w) +{ + int res; + struct rt6_info *rt; + + for (rt = w->leaf; rt; rt = rt->u.next) { + res = rt6_dump_route(rt, w->args); + if (res < 0) { + /* Frame is full, suspend walking */ + w->leaf = rt; + return 1; + } + BUG_TRAP(res!=0); + } + w->leaf = NULL; + return 0; +} + +static void fib6_dump_end(struct netlink_callback *cb) +{ + struct fib6_walker_t *w = (void*)cb->args[2]; + + if (w) { + cb->args[2] = 0; + kfree(w); + } + cb->done = (void*)cb->args[3]; + cb->args[1] = 3; +} + +static int fib6_dump_done(struct netlink_callback *cb) +{ + fib6_dump_end(cb); + return cb->done ? cb->done(cb) : 0; +} + +static int fib6_dump_table(struct fib6_table *table, struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct fib6_walker_t *w; + int res; + + w = (void *)cb->args[2]; + w->root = &table->tb6_root; + + if (cb->args[4] == 0) { + read_lock_bh(&table->tb6_lock); + res = fib6_walk(w); + read_unlock_bh(&table->tb6_lock); + if (res > 0) + cb->args[4] = 1; + } else { + read_lock_bh(&table->tb6_lock); + res = fib6_walk_continue(w); + read_unlock_bh(&table->tb6_lock); + if (res != 0) { + if (res < 0) + fib6_walker_unlink(w); + goto end; + } + fib6_walker_unlink(w); + cb->args[4] = 0; + } +end: + return res; +} + +int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) +{ + unsigned int h, s_h; + unsigned int e = 0, s_e; + struct rt6_rtnl_dump_arg arg; + struct fib6_walker_t *w; + struct fib6_table *tb; + struct hlist_node *node; + int res = 0; + + s_h = cb->args[0]; + s_e = cb->args[1]; + + w = (void *)cb->args[2]; + if (w == NULL) { + /* New dump: + * + * 1. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + + /* + * 2. allocate and initialize walker. + */ + w = kzalloc(sizeof(*w), GFP_ATOMIC); + if (w == NULL) + return -ENOMEM; + w->func = fib6_dump_node; + cb->args[2] = (long)w; + } + + arg.skb = skb; + arg.cb = cb; + w->args = &arg; + + for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) { + e = 0; + hlist_for_each_entry(tb, node, &fib_table_hash[h], tb6_hlist) { + if (e < s_e) + goto next; + res = fib6_dump_table(tb, skb, cb); + if (res != 0) + goto out; +next: + e++; + } + } +out: + cb->args[1] = e; + cb->args[0] = h; + + res = res < 0 ? res : skb->len; + if (res <= 0) + fib6_dump_end(cb); + return res; +} /* * Routing Table @@ -1187,17 +1315,20 @@ static void fib6_clean_tree(struct fib6_node *root, void fib6_clean_all(int (*func)(struct rt6_info *, void *arg), int prune, void *arg) { - int i; struct fib6_table *table; + struct hlist_node *node; + unsigned int h; - for (i = FIB6_TABLE_MIN; i <= FIB6_TABLE_MAX; i++) { - table = fib6_get_table(i); - if (table != NULL) { + rcu_read_lock(); + for (h = 0; h < FIB_TABLE_HASHSZ; h++) { + hlist_for_each_entry_rcu(table, node, &fib_table_hash[h], + tb6_hlist) { write_lock_bh(&table->tb6_lock); fib6_clean_tree(&table->tb6_root, func, prune, arg); write_unlock_bh(&table->tb6_lock); } } + rcu_read_unlock(); } static int fib6_prune_clone(struct rt6_info *rt, void *arg) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 843c5509fced..9ce28277f47f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1874,12 +1874,6 @@ int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) rtm_get_table(arg, r->rtm_table)); } -struct rt6_rtnl_dump_arg -{ - struct sk_buff *skb; - struct netlink_callback *cb; -}; - static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, struct in6_addr *dst, struct in6_addr *src, int iif, int type, u32 pid, u32 seq, @@ -1976,7 +1970,7 @@ rtattr_failure: return -1; } -static int rt6_dump_route(struct rt6_info *rt, void *p_arg) +int rt6_dump_route(struct rt6_info *rt, void *p_arg) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; int prefix; @@ -1992,126 +1986,6 @@ static int rt6_dump_route(struct rt6_info *rt, void *p_arg) prefix, NLM_F_MULTI); } -static int fib6_dump_node(struct fib6_walker_t *w) -{ - int res; - struct rt6_info *rt; - - for (rt = w->leaf; rt; rt = rt->u.next) { - res = rt6_dump_route(rt, w->args); - if (res < 0) { - /* Frame is full, suspend walking */ - w->leaf = rt; - return 1; - } - BUG_TRAP(res!=0); - } - w->leaf = NULL; - return 0; -} - -static void fib6_dump_end(struct netlink_callback *cb) -{ - struct fib6_walker_t *w = (void*)cb->args[0]; - - if (w) { - cb->args[0] = 0; - kfree(w); - } - cb->done = (void*)cb->args[1]; - cb->args[1] = 0; -} - -static int fib6_dump_done(struct netlink_callback *cb) -{ - fib6_dump_end(cb); - return cb->done ? cb->done(cb) : 0; -} - -int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) -{ - struct fib6_table *table; - struct rt6_rtnl_dump_arg arg; - struct fib6_walker_t *w; - int i, res = 0; - - arg.skb = skb; - arg.cb = cb; - - /* - * cb->args[0] = pointer to walker structure - * cb->args[1] = saved cb->done() pointer - * cb->args[2] = current table being dumped - */ - - w = (void*)cb->args[0]; - if (w == NULL) { - /* New dump: - * - * 1. hook callback destructor. - */ - cb->args[1] = (long)cb->done; - cb->done = fib6_dump_done; - - /* - * 2. allocate and initialize walker. - */ - w = kzalloc(sizeof(*w), GFP_ATOMIC); - if (w == NULL) - return -ENOMEM; - w->func = fib6_dump_node; - w->args = &arg; - cb->args[0] = (long)w; - cb->args[2] = FIB6_TABLE_MIN; - } else { - w->args = &arg; - i = cb->args[2]; - if (i > FIB6_TABLE_MAX) - goto end; - - table = fib6_get_table(i); - if (table != NULL) { - read_lock_bh(&table->tb6_lock); - w->root = &table->tb6_root; - res = fib6_walk_continue(w); - read_unlock_bh(&table->tb6_lock); - if (res != 0) { - if (res < 0) - fib6_walker_unlink(w); - goto end; - } - } - - fib6_walker_unlink(w); - cb->args[2] = ++i; - } - - for (i = cb->args[2]; i <= FIB6_TABLE_MAX; i++) { - table = fib6_get_table(i); - if (table == NULL) - continue; - - read_lock_bh(&table->tb6_lock); - w->root = &table->tb6_root; - res = fib6_walk(w); - read_unlock_bh(&table->tb6_lock); - if (res) - break; - } -end: - cb->args[2] = i; - - res = res < 0 ? res : skb->len; - /* res < 0 is an error. (really, impossible) - res == 0 means that dump is complete, but skb still can contain data. - res > 0 dump is not complete, but frame is full. - */ - /* Destroy walker, if dump of this table is complete. */ - if (res <= 0) - fib6_dump_end(cb); - return res; -} - int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg) { struct rtattr **rta = arg; -- cgit v1.2.3 From e0a1ad73d34fd6dfdb630479400511e9879069c0 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 22 Aug 2006 00:00:21 -0700 Subject: [IPv6] route: Simplify ip6_del_rt() Provide a simple ip6_del_rt() for the majority of users and an alternative for the exception via netlink. Avoids code obfuscation. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/ip6_route.h | 5 +---- net/ipv6/addrconf.c | 6 +++--- net/ipv6/ndisc.c | 4 ++-- net/ipv6/route.c | 18 ++++++++++++------ 4 files changed, 18 insertions(+), 15 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 01bfe404784f..a7e6086a2bd4 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -69,10 +69,7 @@ extern int ip6_ins_rt(struct rt6_info *, struct nlmsghdr *, void *rtattr, struct netlink_skb_parms *req); -extern int ip6_del_rt(struct rt6_info *, - struct nlmsghdr *, - void *rtattr, - struct netlink_skb_parms *req); +extern int ip6_del_rt(struct rt6_info *); extern int ip6_rt_addr_add(struct in6_addr *addr, struct net_device *dev, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f1ede9004887..27f2e3309598 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -736,7 +736,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { if (onlink == 0) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } else if (!(rt->rt6i_flags & RTF_EXPIRES)) { rt->rt6i_expires = expires; @@ -1662,7 +1662,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len) if (rt && ((rt->rt6i_flags & (RTF_GATEWAY | RTF_DEFAULT)) == 0)) { if (rt->rt6i_flags&RTF_EXPIRES) { if (valid_lft == 0) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } else { rt->rt6i_expires = jiffies + rt_expires; @@ -3557,7 +3557,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); dst_hold(&ifp->rt->u.dst); - if (ip6_del_rt(ifp->rt, NULL, NULL, NULL)) + if (ip6_del_rt(ifp->rt)) dst_free(&ifp->rt->u.dst); break; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 5743e8bffefd..419d65163819 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -961,7 +961,7 @@ static void ndisc_recv_na(struct sk_buff *skb) struct rt6_info *rt; rt = rt6_get_dflt_router(saddr, dev); if (rt) - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); } out: @@ -1114,7 +1114,7 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (rt && lifetime == 0) { neigh_clone(neigh); - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 1aca787ead85..8d511de0db1b 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -457,7 +457,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, rt = rt6_get_route_info(prefix, rinfo->prefix_len, gwaddr, dev->ifindex); if (rt && !lifetime) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); rt = NULL; } @@ -813,7 +813,7 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) if (rt) { if (rt->rt6i_flags & RTF_CACHE) - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); else dst_release(dst); } @@ -1218,7 +1218,8 @@ out: return err; } -int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, + void *_rtattr, struct netlink_skb_parms *req) { int err; struct fib6_table *table; @@ -1237,6 +1238,11 @@ int ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct return err; } +int ip6_del_rt(struct rt6_info *rt) +{ + return __ip6_del_rt(rt, NULL, NULL, NULL); +} + static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req, u32 table_id) @@ -1271,7 +1277,7 @@ static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, dst_hold(&rt->u.dst); read_unlock_bh(&table->tb6_lock); - return ip6_del_rt(rt, nlh, _rtattr, req); + return __ip6_del_rt(rt, nlh, _rtattr, req); } } read_unlock_bh(&table->tb6_lock); @@ -1395,7 +1401,7 @@ restart: call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); if (rt->rt6i_flags&RTF_CACHE) { - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); return; } @@ -1631,7 +1637,7 @@ restart: if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) { dst_hold(&rt->u.dst); read_unlock_bh(&table->tb6_lock); - ip6_del_rt(rt, NULL, NULL, NULL); + ip6_del_rt(rt); goto restart; } } -- cgit v1.2.3 From 40e22e8f3d4d4f1ff68fb03683f007c53ee8b348 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 22 Aug 2006 00:00:45 -0700 Subject: [IPv6] route: Simplify ip6_ins_rt() Provide a simple ip6_ins_rt() for the majority of users and an alternative for the exception via netlink. Avoids code obfuscation. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/ip6_route.h | 5 +---- net/ipv6/addrconf.c | 2 +- net/ipv6/anycast.c | 2 +- net/ipv6/route.c | 19 ++++++++++++------- 4 files changed, 15 insertions(+), 13 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index a7e6086a2bd4..172c4761e2bf 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -65,10 +65,7 @@ extern int ip6_route_add(struct in6_rtmsg *rtmsg, void *rtattr, struct netlink_skb_parms *req, u32 table_id); -extern int ip6_ins_rt(struct rt6_info *, - struct nlmsghdr *, - void *rtattr, - struct netlink_skb_parms *req); +extern int ip6_ins_rt(struct rt6_info *); extern int ip6_del_rt(struct rt6_info *); extern int ip6_rt_addr_add(struct in6_addr *addr, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 27f2e3309598..aafba9ea9cb6 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3548,7 +3548,7 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) switch (event) { case RTM_NEWADDR: - ip6_ins_rt(ifp->rt, NULL, NULL, NULL); + ip6_ins_rt(ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); break; diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index f6881d7a0385..abbc35a13e08 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -335,7 +335,7 @@ int ipv6_dev_ac_inc(struct net_device *dev, struct in6_addr *addr) write_unlock_bh(&idev->lock); dst_hold(&rt->u.dst); - if (ip6_ins_rt(rt, NULL, NULL, NULL)) + if (ip6_ins_rt(rt)) dst_release(&rt->u.dst); addrconf_join_solict(dev, &aca->aca_addr); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 8d511de0db1b..9ec348a72a95 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -546,8 +546,8 @@ struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, be destroyed. */ -int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, + void *_rtattr, struct netlink_skb_parms *req) { int err; struct fib6_table *table; @@ -560,6 +560,11 @@ int ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, return err; } +int ip6_ins_rt(struct rt6_info *rt) +{ + return __ip6_ins_rt(rt, NULL, NULL, NULL); +} + static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr, struct in6_addr *saddr) { @@ -657,7 +662,7 @@ restart: dst_hold(&rt->u.dst); if (nrt) { - err = ip6_ins_rt(nrt, NULL, NULL, NULL); + err = ip6_ins_rt(nrt); if (!err) goto out2; } @@ -752,7 +757,7 @@ restart: dst_hold(&rt->u.dst); if (nrt) { - err = ip6_ins_rt(nrt, NULL, NULL, NULL); + err = ip6_ins_rt(nrt); if (!err) goto out2; } @@ -1206,7 +1211,7 @@ install_route: rt->u.dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; - return ip6_ins_rt(rt, nlh, _rtattr, req); + return __ip6_ins_rt(rt, nlh, _rtattr, req); out: if (dev) @@ -1393,7 +1398,7 @@ restart: nrt->u.dst.metrics[RTAX_MTU-1] = ipv6_get_mtu(neigh->dev); nrt->u.dst.metrics[RTAX_ADVMSS-1] = ipv6_advmss(dst_mtu(&nrt->u.dst)); - if (ip6_ins_rt(nrt, NULL, NULL, NULL)) + if (ip6_ins_rt(nrt)) goto out; netevent.old = &rt->u.dst; @@ -1483,7 +1488,7 @@ void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr, dst_set_expires(&nrt->u.dst, ip6_rt_mtu_expires); nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES; - ip6_ins_rt(nrt, NULL, NULL, NULL); + ip6_ins_rt(nrt); } out: dst_release(&rt->u.dst); -- cgit v1.2.3 From 86872cb57925c46a6499887d77afb880a892c0ec Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 22 Aug 2006 00:01:08 -0700 Subject: [IPv6] route: FIB6 configuration using struct fib6_config Replaces the struct in6_rtmsg based interface orignating from the ioctl interface with a struct fib6_config based on. Allows changing the interface without breaking the ioctl interface and avoids passing on tons of parameters. The recently introduced struct nl_info is used to pass on netlink authorship information for notifications. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/ip6_fib.h | 38 ++++-- include/net/ip6_route.h | 6 +- net/ipv6/addrconf.c | 65 +++++----- net/ipv6/ip6_fib.c | 19 ++- net/ipv6/route.c | 331 ++++++++++++++++++++++++++++-------------------- 5 files changed, 259 insertions(+), 200 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 69c444209781..9610b887ffb5 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -16,14 +16,35 @@ #ifdef __KERNEL__ #include - -#include -#include #include #include +#include +#include +#include struct rt6_info; +struct fib6_config +{ + u32 fc_table; + u32 fc_metric; + int fc_dst_len; + int fc_src_len; + int fc_ifindex; + u32 fc_flags; + u32 fc_protocol; + + struct in6_addr fc_dst; + struct in6_addr fc_src; + struct in6_addr fc_gateway; + + unsigned long fc_expires; + struct nlattr *fc_mx; + int fc_mx_len; + + struct nl_info fc_nlinfo; +}; + struct fib6_node { struct fib6_node *parent; @@ -175,18 +196,13 @@ extern void fib6_clean_all(int (*func)(struct rt6_info *, void *arg), extern int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nlmsghdr *nlh, - void *rtattr, - struct netlink_skb_parms *req); + struct nl_info *info); extern int fib6_del(struct rt6_info *rt, - struct nlmsghdr *nlh, - void *rtattr, - struct netlink_skb_parms *req); + struct nl_info *info); extern void inet6_rt_notify(int event, struct rt6_info *rt, - struct nlmsghdr *nlh, - struct netlink_skb_parms *req); + struct nl_info *info); extern void fib6_run_gc(unsigned long dummy); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 172c4761e2bf..3f170f667c7b 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -60,11 +60,7 @@ extern void ip6_route_cleanup(void); extern int ipv6_route_ioctl(unsigned int cmd, void __user *arg); -extern int ip6_route_add(struct in6_rtmsg *rtmsg, - struct nlmsghdr *, - void *rtattr, - struct netlink_skb_parms *req, - u32 table_id); +extern int ip6_route_add(struct fib6_config *cfg); extern int ip6_ins_rt(struct rt6_info *); extern int ip6_del_rt(struct rt6_info *); diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index aafba9ea9cb6..fc9cff3426c4 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1509,59 +1509,56 @@ static void addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, unsigned long expires, u32 flags) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_PREFIX, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_expires = expires, + .fc_dst_len = plen, + .fc_flags = RTF_UP | flags, + }; - memset(&rtmsg, 0, sizeof(rtmsg)); - ipv6_addr_copy(&rtmsg.rtmsg_dst, pfx); - rtmsg.rtmsg_dst_len = plen; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; - rtmsg.rtmsg_ifindex = dev->ifindex; - rtmsg.rtmsg_info = expires; - rtmsg.rtmsg_flags = RTF_UP|flags; - rtmsg.rtmsg_type = RTMSG_NEWROUTE; + ipv6_addr_copy(&cfg.fc_dst, pfx); /* Prevent useless cloning on PtP SIT. This thing is done here expecting that the whole class of non-broadcast devices need not cloning. */ - if (dev->type == ARPHRD_SIT && (dev->flags&IFF_POINTOPOINT)) - rtmsg.rtmsg_flags |= RTF_NONEXTHOP; + if (dev->type == ARPHRD_SIT && (dev->flags & IFF_POINTOPOINT)) + cfg.fc_flags |= RTF_NONEXTHOP; - ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_PREFIX); + ip6_route_add(&cfg); } /* Create "default" multicast route to the interface */ static void addrconf_add_mroute(struct net_device *dev) { - struct in6_rtmsg rtmsg; - - memset(&rtmsg, 0, sizeof(rtmsg)); - ipv6_addr_set(&rtmsg.rtmsg_dst, - htonl(0xFF000000), 0, 0, 0); - rtmsg.rtmsg_dst_len = 8; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; - rtmsg.rtmsg_ifindex = dev->ifindex; - rtmsg.rtmsg_flags = RTF_UP; - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_LOCAL); + struct fib6_config cfg = { + .fc_table = RT6_TABLE_LOCAL, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_dst_len = 8, + .fc_flags = RTF_UP, + }; + + ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); + + ip6_route_add(&cfg); } static void sit_route_add(struct net_device *dev) { - struct in6_rtmsg rtmsg; - - memset(&rtmsg, 0, sizeof(rtmsg)); - - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - rtmsg.rtmsg_metric = IP6_RT_PRIO_ADDRCONF; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_MAIN, + .fc_metric = IP6_RT_PRIO_ADDRCONF, + .fc_ifindex = dev->ifindex, + .fc_dst_len = 96, + .fc_flags = RTF_UP | RTF_NONEXTHOP, + }; /* prefix length - 96 bits "::d.d.d.d" */ - rtmsg.rtmsg_dst_len = 96; - rtmsg.rtmsg_flags = RTF_UP|RTF_NONEXTHOP; - rtmsg.rtmsg_ifindex = dev->ifindex; - - ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_MAIN); + ip6_route_add(&cfg); } static void addrconf_add_lroute(struct net_device *dev) diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index be36f4acda94..667b1b1ea25d 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -610,7 +610,7 @@ insert_above: */ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nlmsghdr *nlh, struct netlink_skb_parms *req) + struct nl_info *info) { struct rt6_info *iter = NULL; struct rt6_info **ins; @@ -665,7 +665,7 @@ out: *ins = rt; rt->rt6i_node = fn; atomic_inc(&rt->rt6i_ref); - inet6_rt_notify(RTM_NEWROUTE, rt, nlh, req); + inet6_rt_notify(RTM_NEWROUTE, rt, info); rt6_stats.fib_rt_entries++; if ((fn->fn_flags & RTN_RTINFO) == 0) { @@ -695,8 +695,7 @@ void fib6_force_start_gc(void) * with source addr info in sub-trees */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int fib6_add(struct fib6_node *root, struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn; int err = -ENOMEM; @@ -769,7 +768,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } #endif - err = fib6_add_rt2node(fn, rt, nlh, req); + err = fib6_add_rt2node(fn, rt, info); if (err == 0) { fib6_start_gc(rt); @@ -1076,7 +1075,7 @@ static struct fib6_node * fib6_repair_tree(struct fib6_node *fn) } static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, - struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) + struct nl_info *info) { struct fib6_walker_t *w; struct rt6_info *rt = *rtp; @@ -1132,11 +1131,11 @@ static void fib6_del_route(struct fib6_node *fn, struct rt6_info **rtp, if (atomic_read(&rt->rt6i_ref) != 1) BUG(); } - inet6_rt_notify(RTM_DELROUTE, rt, nlh, req); + inet6_rt_notify(RTM_DELROUTE, rt, info); rt6_release(rt); } -int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct netlink_skb_parms *req) +int fib6_del(struct rt6_info *rt, struct nl_info *info) { struct fib6_node *fn = rt->rt6i_node; struct rt6_info **rtp; @@ -1161,7 +1160,7 @@ int fib6_del(struct rt6_info *rt, struct nlmsghdr *nlh, void *_rtattr, struct ne for (rtp = &fn->leaf; *rtp; rtp = &(*rtp)->u.next) { if (*rtp == rt) { - fib6_del_route(fn, rtp, nlh, _rtattr, req); + fib6_del_route(fn, rtp, info); return 0; } } @@ -1290,7 +1289,7 @@ static int fib6_clean_node(struct fib6_walker_t *w) res = c->func(rt, c->arg); if (res < 0) { w->leaf = rt; - res = fib6_del(rt, NULL, NULL, NULL); + res = fib6_del(rt, NULL); if (res) { #if RT6_DEBUG >= 2 printk(KERN_DEBUG "fib6_clean_node: del failed: rt=%p@%p err=%d\n", rt, rt->rt6i_node, res); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 9ec348a72a95..7bcffa6ddba3 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -546,15 +546,14 @@ struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, be destroyed. */ -static int __ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info) { int err; struct fib6_table *table; table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, nlh, _rtattr, req); + err = fib6_add(&table->tb6_root, rt, info); write_unlock_bh(&table->tb6_lock); return err; @@ -562,7 +561,7 @@ static int __ip6_ins_rt(struct rt6_info *rt, struct nlmsghdr *nlh, int ip6_ins_rt(struct rt6_info *rt) { - return __ip6_ins_rt(rt, NULL, NULL, NULL); + return __ip6_ins_rt(rt, NULL); } static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr, @@ -1014,30 +1013,24 @@ int ipv6_get_hoplimit(struct net_device *dev) * */ -int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req, - u32 table_id) +int ip6_route_add(struct fib6_config *cfg) { int err; - struct rtmsg *r; - struct rtattr **rta; struct rt6_info *rt = NULL; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; int addr_type; - rta = (struct rtattr **) _rtattr; - - if (rtmsg->rtmsg_dst_len > 128 || rtmsg->rtmsg_src_len > 128) + if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128) return -EINVAL; #ifndef CONFIG_IPV6_SUBTREES - if (rtmsg->rtmsg_src_len) + if (cfg->fc_src_len) return -EINVAL; #endif - if (rtmsg->rtmsg_ifindex) { + if (cfg->fc_ifindex) { err = -ENODEV; - dev = dev_get_by_index(rtmsg->rtmsg_ifindex); + dev = dev_get_by_index(cfg->fc_ifindex); if (!dev) goto out; idev = in6_dev_get(dev); @@ -1045,10 +1038,10 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto out; } - if (rtmsg->rtmsg_metric == 0) - rtmsg->rtmsg_metric = IP6_RT_PRIO_USER; + if (cfg->fc_metric == 0) + cfg->fc_metric = IP6_RT_PRIO_USER; - table = fib6_new_table(table_id); + table = fib6_new_table(cfg->fc_table); if (table == NULL) { err = -ENOBUFS; goto out; @@ -1062,14 +1055,13 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, } rt->u.dst.obsolete = -1; - rt->rt6i_expires = jiffies + clock_t_to_jiffies(rtmsg->rtmsg_info); - if (nlh && (r = NLMSG_DATA(nlh))) { - rt->rt6i_protocol = r->rtm_protocol; - } else { - rt->rt6i_protocol = RTPROT_BOOT; - } + rt->rt6i_expires = jiffies + clock_t_to_jiffies(cfg->fc_expires); + + if (cfg->fc_protocol == RTPROT_UNSPEC) + cfg->fc_protocol = RTPROT_BOOT; + rt->rt6i_protocol = cfg->fc_protocol; - addr_type = ipv6_addr_type(&rtmsg->rtmsg_dst); + addr_type = ipv6_addr_type(&cfg->fc_dst); if (addr_type & IPV6_ADDR_MULTICAST) rt->u.dst.input = ip6_mc_input; @@ -1078,24 +1070,22 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, rt->u.dst.output = ip6_output; - ipv6_addr_prefix(&rt->rt6i_dst.addr, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len); - rt->rt6i_dst.plen = rtmsg->rtmsg_dst_len; + ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); + rt->rt6i_dst.plen = cfg->fc_dst_len; if (rt->rt6i_dst.plen == 128) rt->u.dst.flags = DST_HOST; #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_prefix(&rt->rt6i_src.addr, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); - rt->rt6i_src.plen = rtmsg->rtmsg_src_len; + ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); + rt->rt6i_src.plen = cfg->fc_src_len; #endif - rt->rt6i_metric = rtmsg->rtmsg_metric; + rt->rt6i_metric = cfg->fc_metric; /* We cannot add true routes via loopback here, they would result in kernel looping; promote them to reject routes */ - if ((rtmsg->rtmsg_flags&RTF_REJECT) || + if ((cfg->fc_flags & RTF_REJECT) || (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK))) { /* hold loopback dev/idev if we haven't done so. */ if (dev != &loopback_dev) { @@ -1118,12 +1108,12 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, goto install_route; } - if (rtmsg->rtmsg_flags & RTF_GATEWAY) { + if (cfg->fc_flags & RTF_GATEWAY) { struct in6_addr *gw_addr; int gwa_type; - gw_addr = &rtmsg->rtmsg_gateway; - ipv6_addr_copy(&rt->rt6i_gateway, &rtmsg->rtmsg_gateway); + gw_addr = &cfg->fc_gateway; + ipv6_addr_copy(&rt->rt6i_gateway, gw_addr); gwa_type = ipv6_addr_type(gw_addr); if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) { @@ -1140,7 +1130,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, if (!(gwa_type&IPV6_ADDR_UNICAST)) goto out; - grt = rt6_lookup(gw_addr, NULL, rtmsg->rtmsg_ifindex, 1); + grt = rt6_lookup(gw_addr, NULL, cfg->fc_ifindex, 1); err = -EHOSTUNREACH; if (grt == NULL) @@ -1172,7 +1162,7 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, if (dev == NULL) goto out; - if (rtmsg->rtmsg_flags & (RTF_GATEWAY|RTF_NONEXTHOP)) { + if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) { rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev); if (IS_ERR(rt->rt6i_nexthop)) { err = PTR_ERR(rt->rt6i_nexthop); @@ -1181,24 +1171,24 @@ int ip6_route_add(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, } } - rt->rt6i_flags = rtmsg->rtmsg_flags; + rt->rt6i_flags = cfg->fc_flags; install_route: - if (rta && rta[RTA_METRICS-1]) { - int attrlen = RTA_PAYLOAD(rta[RTA_METRICS-1]); - struct rtattr *attr = RTA_DATA(rta[RTA_METRICS-1]); - - while (RTA_OK(attr, attrlen)) { - unsigned flavor = attr->rta_type; - if (flavor) { - if (flavor > RTAX_MAX) { + 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) { err = -EINVAL; goto out; } - rt->u.dst.metrics[flavor-1] = - *(u32 *)RTA_DATA(attr); + + rt->u.dst.metrics[type - 1] = nla_get_u32(nla); } - attr = RTA_NEXT(attr, attrlen); } } @@ -1211,7 +1201,7 @@ install_route: rt->u.dst.dev = dev; rt->rt6i_idev = idev; rt->rt6i_table = table; - return __ip6_ins_rt(rt, nlh, _rtattr, req); + return __ip6_ins_rt(rt, &cfg->fc_nlinfo); out: if (dev) @@ -1223,8 +1213,7 @@ out: return err; } -static int __ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req) +static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) { int err; struct fib6_table *table; @@ -1235,7 +1224,7 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, table = rt->rt6i_table; write_lock_bh(&table->tb6_lock); - err = fib6_del(rt, nlh, _rtattr, req); + err = fib6_del(rt, info); dst_release(&rt->u.dst); write_unlock_bh(&table->tb6_lock); @@ -1245,44 +1234,41 @@ static int __ip6_del_rt(struct rt6_info *rt, struct nlmsghdr *nlh, int ip6_del_rt(struct rt6_info *rt) { - return __ip6_del_rt(rt, NULL, NULL, NULL); + return __ip6_del_rt(rt, NULL); } -static int ip6_route_del(struct in6_rtmsg *rtmsg, struct nlmsghdr *nlh, - void *_rtattr, struct netlink_skb_parms *req, - u32 table_id) +static int ip6_route_del(struct fib6_config *cfg) { struct fib6_table *table; struct fib6_node *fn; struct rt6_info *rt; int err = -ESRCH; - table = fib6_get_table(table_id); + table = fib6_get_table(cfg->fc_table); if (table == NULL) return err; read_lock_bh(&table->tb6_lock); fn = fib6_locate(&table->tb6_root, - &rtmsg->rtmsg_dst, rtmsg->rtmsg_dst_len, - &rtmsg->rtmsg_src, rtmsg->rtmsg_src_len); + &cfg->fc_dst, cfg->fc_dst_len, + &cfg->fc_src, cfg->fc_src_len); if (fn) { for (rt = fn->leaf; rt; rt = rt->u.next) { - if (rtmsg->rtmsg_ifindex && + if (cfg->fc_ifindex && (rt->rt6i_dev == NULL || - rt->rt6i_dev->ifindex != rtmsg->rtmsg_ifindex)) + rt->rt6i_dev->ifindex != cfg->fc_ifindex)) continue; - if (rtmsg->rtmsg_flags&RTF_GATEWAY && - !ipv6_addr_equal(&rtmsg->rtmsg_gateway, &rt->rt6i_gateway)) + if (cfg->fc_flags & RTF_GATEWAY && + !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) continue; - if (rtmsg->rtmsg_metric && - rtmsg->rtmsg_metric != rt->rt6i_metric) + if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) continue; dst_hold(&rt->u.dst); read_unlock_bh(&table->tb6_lock); - return __ip6_del_rt(rt, nlh, _rtattr, req); + return __ip6_del_rt(rt, &cfg->fc_nlinfo); } } read_unlock_bh(&table->tb6_lock); @@ -1565,21 +1551,23 @@ static struct rt6_info *rt6_add_route_info(struct in6_addr *prefix, int prefixle struct in6_addr *gwaddr, int ifindex, unsigned pref) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_INFO, + .fc_metric = 1024, + .fc_ifindex = ifindex, + .fc_dst_len = prefixlen, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | + RTF_UP | RTF_PREF(pref), + }; + + ipv6_addr_copy(&cfg.fc_dst, prefix); + ipv6_addr_copy(&cfg.fc_gateway, gwaddr); - memset(&rtmsg, 0, sizeof(rtmsg)); - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - ipv6_addr_copy(&rtmsg.rtmsg_dst, prefix); - rtmsg.rtmsg_dst_len = prefixlen; - ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr); - rtmsg.rtmsg_metric = 1024; - rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref); /* We should treat it as a default route if prefix length is 0. */ if (!prefixlen) - rtmsg.rtmsg_flags |= RTF_DEFAULT; - rtmsg.rtmsg_ifindex = ifindex; + cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_INFO); + ip6_route_add(&cfg); return rt6_get_route_info(prefix, prefixlen, gwaddr, ifindex); } @@ -1611,18 +1599,18 @@ struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { - struct in6_rtmsg rtmsg; + struct fib6_config cfg = { + .fc_table = RT6_TABLE_DFLT, + .fc_metric = 1024, + .fc_ifindex = dev->ifindex, + .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | + RTF_UP | RTF_EXPIRES | RTF_PREF(pref), + }; - memset(&rtmsg, 0, sizeof(struct in6_rtmsg)); - rtmsg.rtmsg_type = RTMSG_NEWROUTE; - ipv6_addr_copy(&rtmsg.rtmsg_gateway, gwaddr); - rtmsg.rtmsg_metric = 1024; - rtmsg.rtmsg_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | - RTF_PREF(pref); + ipv6_addr_copy(&cfg.fc_gateway, gwaddr); - rtmsg.rtmsg_ifindex = dev->ifindex; + ip6_route_add(&cfg); - ip6_route_add(&rtmsg, NULL, NULL, NULL, RT6_TABLE_DFLT); return rt6_get_dflt_router(gwaddr, dev); } @@ -1649,8 +1637,27 @@ restart: read_unlock_bh(&table->tb6_lock); } +static void rtmsg_to_fib6_config(struct in6_rtmsg *rtmsg, + struct fib6_config *cfg) +{ + memset(cfg, 0, sizeof(*cfg)); + + cfg->fc_table = RT6_TABLE_MAIN; + cfg->fc_ifindex = rtmsg->rtmsg_ifindex; + cfg->fc_metric = rtmsg->rtmsg_metric; + cfg->fc_expires = rtmsg->rtmsg_info; + cfg->fc_dst_len = rtmsg->rtmsg_dst_len; + cfg->fc_src_len = rtmsg->rtmsg_src_len; + cfg->fc_flags = rtmsg->rtmsg_flags; + + ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst); + ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src); + ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway); +} + int ipv6_route_ioctl(unsigned int cmd, void __user *arg) { + struct fib6_config cfg; struct in6_rtmsg rtmsg; int err; @@ -1663,16 +1670,16 @@ int ipv6_route_ioctl(unsigned int cmd, void __user *arg) sizeof(struct in6_rtmsg)); if (err) return -EFAULT; - + + rtmsg_to_fib6_config(&rtmsg, &cfg); + rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&rtmsg, NULL, NULL, NULL, - RT6_TABLE_MAIN); + err = ip6_route_add(&cfg); break; case SIOCDELRT: - err = ip6_route_del(&rtmsg, NULL, NULL, NULL, - RT6_TABLE_MAIN); + err = ip6_route_del(&cfg); break; default: err = -EINVAL; @@ -1823,66 +1830,104 @@ void rt6_mtu_change(struct net_device *dev, unsigned mtu) fib6_clean_all(rt6_mtu_change_route, 0, &arg); } -static int inet6_rtm_to_rtmsg(struct rtmsg *r, struct rtattr **rta, - struct in6_rtmsg *rtmsg) +static struct nla_policy rtm_ipv6_policy[RTA_MAX+1] __read_mostly = { + [RTA_GATEWAY] = { .minlen = sizeof(struct in6_addr) }, + [RTA_OIF] = { .type = NLA_U32 }, + [RTA_PRIORITY] = { .type = NLA_U32 }, + [RTA_METRICS] = { .type = NLA_NESTED }, +}; + +static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, + struct fib6_config *cfg) { - memset(rtmsg, 0, sizeof(*rtmsg)); + struct rtmsg *rtm; + struct nlattr *tb[RTA_MAX+1]; + int err; + + err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy); + if (err < 0) + goto errout; - rtmsg->rtmsg_dst_len = r->rtm_dst_len; - rtmsg->rtmsg_src_len = r->rtm_src_len; - rtmsg->rtmsg_flags = RTF_UP; - if (r->rtm_type == RTN_UNREACHABLE) - rtmsg->rtmsg_flags |= RTF_REJECT; + err = -EINVAL; + rtm = nlmsg_data(nlh); + memset(cfg, 0, sizeof(*cfg)); - if (rta[RTA_GATEWAY-1]) { - if (rta[RTA_GATEWAY-1]->rta_len != RTA_LENGTH(16)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_gateway, RTA_DATA(rta[RTA_GATEWAY-1]), 16); - rtmsg->rtmsg_flags |= RTF_GATEWAY; - } - if (rta[RTA_DST-1]) { - if (RTA_PAYLOAD(rta[RTA_DST-1]) < ((r->rtm_dst_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_dst, RTA_DATA(rta[RTA_DST-1]), ((r->rtm_dst_len+7)>>3)); + cfg->fc_table = rtm->rtm_table; + cfg->fc_dst_len = rtm->rtm_dst_len; + cfg->fc_src_len = rtm->rtm_src_len; + cfg->fc_flags = RTF_UP; + cfg->fc_protocol = rtm->rtm_protocol; + + if (rtm->rtm_type == RTN_UNREACHABLE) + cfg->fc_flags |= RTF_REJECT; + + cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid; + cfg->fc_nlinfo.nlh = nlh; + + if (tb[RTA_GATEWAY]) { + nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16); + cfg->fc_flags |= RTF_GATEWAY; } - if (rta[RTA_SRC-1]) { - if (RTA_PAYLOAD(rta[RTA_SRC-1]) < ((r->rtm_src_len+7)>>3)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_src, RTA_DATA(rta[RTA_SRC-1]), ((r->rtm_src_len+7)>>3)); + + if (tb[RTA_DST]) { + int plen = (rtm->rtm_dst_len + 7) >> 3; + + if (nla_len(tb[RTA_DST]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen); } - if (rta[RTA_OIF-1]) { - if (rta[RTA_OIF-1]->rta_len != RTA_LENGTH(sizeof(int))) - return -EINVAL; - memcpy(&rtmsg->rtmsg_ifindex, RTA_DATA(rta[RTA_OIF-1]), sizeof(int)); + + if (tb[RTA_SRC]) { + int plen = (rtm->rtm_src_len + 7) >> 3; + + if (nla_len(tb[RTA_SRC]) < plen) + goto errout; + + nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen); } - if (rta[RTA_PRIORITY-1]) { - if (rta[RTA_PRIORITY-1]->rta_len != RTA_LENGTH(4)) - return -EINVAL; - memcpy(&rtmsg->rtmsg_metric, RTA_DATA(rta[RTA_PRIORITY-1]), 4); + + if (tb[RTA_OIF]) + cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]); + + if (tb[RTA_PRIORITY]) + cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]); + + if (tb[RTA_METRICS]) { + cfg->fc_mx = nla_data(tb[RTA_METRICS]); + cfg->fc_mx_len = nla_len(tb[RTA_METRICS]); } - return 0; + + if (tb[RTA_TABLE]) + cfg->fc_table = nla_get_u32(tb[RTA_TABLE]); + + err = 0; +errout: + return err; } int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_del(&rtmsg, nlh, arg, &NETLINK_CB(skb), - rtm_get_table(arg, r->rtm_table)); + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; + + return ip6_route_del(&cfg); } int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) { - struct rtmsg *r = NLMSG_DATA(nlh); - struct in6_rtmsg rtmsg; + struct fib6_config cfg; + int err; - if (inet6_rtm_to_rtmsg(r, arg, &rtmsg)) - return -EINVAL; - return ip6_route_add(&rtmsg, nlh, arg, &NETLINK_CB(skb), - rtm_get_table(arg, r->rtm_table)); + err = rtm_to_fib6_config(skb, nlh, &cfg); + if (err < 0) + return err; + + return ip6_route_add(&cfg); } static int rt6_fill_node(struct sk_buff *skb, struct rt6_info *rt, @@ -2063,15 +2108,21 @@ out_free: goto out; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nlmsghdr *nlh, - struct netlink_skb_parms *req) +void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info) { struct sk_buff *skb; - u32 pid = req ? req->pid : 0; - u32 seq = nlh ? nlh->nlmsg_seq : 0; + u32 pid = 0, seq = 0; + struct nlmsghdr *nlh = NULL; int payload = sizeof(struct rtmsg) + 256; int err = -ENOBUFS; + if (info) { + pid = info->pid; + nlh = info->nlh; + if (nlh) + seq = nlh->nlmsg_seq; + } + skb = nlmsg_new(nlmsg_total_size(payload), gfp_any()); if (skb == NULL) goto errout; -- cgit v1.2.3 From 5e032e32ecc2e6cb0385dc115ca9bfe5e19a9539 Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 23 Aug 2006 17:12:24 -0700 Subject: [IPV6] NDISC: Take source address into account for redirects. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: Ville Nuorvala Signed-off-by: David S. Miller --- include/net/ip6_route.h | 1 + net/ipv6/ndisc.c | 3 ++- net/ipv6/route.c | 5 +++-- 3 files changed, 6 insertions(+), 3 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 3f170f667c7b..249ce4545ef0 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -110,6 +110,7 @@ extern int rt6_route_rcv(struct net_device *dev, struct in6_addr *gwaddr); extern void rt6_redirect(struct in6_addr *dest, + struct in6_addr *src, struct in6_addr *saddr, struct neighbour *neigh, u8 *lladdr, diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 419d65163819..32f28dec399e 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1346,7 +1346,8 @@ static void ndisc_redirect_rcv(struct sk_buff *skb) neigh = __neigh_lookup(&nd_tbl, target, skb->dev, 1); if (neigh) { - rt6_redirect(dest, &skb->nh.ipv6h->saddr, neigh, lladdr, + rt6_redirect(dest, &skb->nh.ipv6h->daddr, + &skb->nh.ipv6h->saddr, neigh, lladdr, on_link); neigh_release(neigh); } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 5d6e9083ca2c..a9b08a2422e0 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1279,7 +1279,8 @@ static int ip6_route_del(struct fib6_config *cfg) /* * Handle redirects */ -void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, +void rt6_redirect(struct in6_addr *dest, struct in6_addr *src, + struct in6_addr *saddr, struct neighbour *neigh, u8 *lladdr, int on_link) { struct rt6_info *rt, *nrt = NULL; @@ -1304,7 +1305,7 @@ void rt6_redirect(struct in6_addr *dest, struct in6_addr *saddr, */ read_lock_bh(&table->tb6_lock); - fn = fib6_lookup(&table->tb6_root, dest, NULL); + fn = fib6_lookup(&table->tb6_root, dest, src); restart: for (rt = fn->leaf; rt; rt = rt->u.next) { /* -- cgit v1.2.3 From 8e1ef0a95b87e8b4292b2ba733e8cb854ea2d2fe Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Tue, 29 Aug 2006 17:15:09 -0700 Subject: [IPV6]: Cache source address as well in ipv6_pinfo{}. Based on MIPL2 kernel patch. Signed-off-by: YOSHIFUJI Hideaki Signed-off-by: Ville Nuorvala Signed-off-by: David S. Miller --- include/linux/ipv6.h | 3 +++ include/net/ip6_route.h | 9 ++++++--- net/dccp/ipv6.c | 4 ++-- net/ipv6/af_inet6.c | 2 +- net/ipv6/datagram.c | 7 ++++++- net/ipv6/inet6_connection_sock.c | 2 +- net/ipv6/ip6_output.c | 3 +++ net/ipv6/tcp_ipv6.c | 4 ++-- net/ipv6/udp.c | 7 ++++++- 9 files changed, 30 insertions(+), 11 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 297853c841b4..02d14a3ff2af 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -242,6 +242,9 @@ struct ipv6_pinfo { struct in6_addr rcv_saddr; struct in6_addr daddr; struct in6_addr *daddr_cache; +#ifdef CONFIG_IPV6_SUBTREES + struct in6_addr *saddr_cache; +#endif __u32 flow_label; __u32 frag_size; diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 249ce4545ef0..0d40f84df21b 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -144,21 +144,24 @@ extern rwlock_t rt6_lock; * Store a destination cache entry in a socket */ static inline void __ip6_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr) + struct in6_addr *daddr, struct in6_addr *saddr) { struct ipv6_pinfo *np = inet6_sk(sk); struct rt6_info *rt = (struct rt6_info *) dst; sk_setup_caps(sk, dst); np->daddr_cache = daddr; +#ifdef CONFIG_IPV6_SUBTREES + np->saddr_cache = saddr; +#endif np->dst_cookie = rt->rt6i_node ? rt->rt6i_node->fn_sernum : 0; } static inline void ip6_dst_store(struct sock *sk, struct dst_entry *dst, - struct in6_addr *daddr) + struct in6_addr *daddr, struct in6_addr *saddr) { write_lock(&sk->sk_dst_lock); - __ip6_dst_store(sk, dst, daddr); + __ip6_dst_store(sk, dst, daddr, saddr); write_unlock(&sk->sk_dst_lock); } diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 231bc7c7e749..f9c5e12d7038 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -231,7 +231,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ipv6_addr_copy(&np->saddr, saddr); inet->rcv_saddr = LOOPBACK4_IPV6; - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (np->opt != NULL) @@ -872,7 +872,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk, * comment in that function for the gory details. -acme */ - __ip6_dst_store(newsk, dst, NULL); + __ip6_dst_store(newsk, dst, NULL, NULL); newsk->sk_route_caps = dst->dev->features & ~(NETIF_F_IP_CSUM | NETIF_F_TSO); newdp6 = (struct dccp6_sock *)newsk; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 2ff600cfe3a4..57ee5ddea96f 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -659,7 +659,7 @@ int inet6_sk_rebuild_header(struct sock *sk) return err; } - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); } return 0; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index c73508e090a6..8561b9da6db6 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -193,7 +193,12 @@ ipv4_connected: ip6_dst_store(sk, dst, ipv6_addr_equal(&fl.fl6_dst, &np->daddr) ? - &np->daddr : NULL); + &np->daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl.fl6_src, &np->saddr) ? + &np->saddr : +#endif + NULL); sk->sk_state = TCP_ESTABLISHED; out: diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 7a51a258615d..827f41d1478b 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -186,7 +186,7 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) return err; } - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); } skb->dst = dst_clone(dst); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 0a18cb6b1cbb..2a376b7d91b4 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -762,6 +762,9 @@ static struct dst_entry *ip6_sk_dst_check(struct sock *sk, * 2. oif also should be the same. */ if (ip6_rt_check(&rt->rt6i_dst, &fl->fl6_dst, np->daddr_cache) || +#ifdef CONFIG_IPV6_SUBTREES + ip6_rt_check(&rt->rt6i_src, &fl->fl6_src, np->saddr_cache) || +#endif (fl->oif && fl->oif != dst->dev->ifindex)) { dst_release(dst); dst = NULL; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7f1b660493b7..2b18918f3011 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -272,7 +272,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, inet->rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(sk, dst, NULL); + __ip6_dst_store(sk, dst, NULL, NULL); icsk->icsk_ext_hdr_len = 0; if (np->opt) @@ -954,7 +954,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, */ newsk->sk_gso_type = SKB_GSO_TCPV6; - __ip6_dst_store(newsk, dst, NULL); + __ip6_dst_store(newsk, dst, NULL, NULL); newtcp6sk = (struct tcp6_sock *)newsk; inet_sk(newsk)->pinet6 = &newtcp6sk->inet6; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index eb9e1b39c8f8..b9cc55ccb000 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -847,7 +847,12 @@ do_append_data: if (connected) { ip6_dst_store(sk, dst, ipv6_addr_equal(&fl->fl6_dst, &np->daddr) ? - &np->daddr : NULL); + &np->daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl->fl6_src, &np->saddr) ? + &np->saddr : +#endif + NULL); } else { dst_release(dst); } -- cgit v1.2.3 From 77d16f450ae0452d7d4b009f78debb1294fb435c Mon Sep 17 00:00:00 2001 From: YOSHIFUJI Hideaki Date: Wed, 23 Aug 2006 17:25:05 -0700 Subject: [IPV6] ROUTE: Unify RT6_F_xxx and RT6_SELECT_F_xxx flags Unify RT6_F_xxx and RT6_SELECT_F_xxx flags into RT6_LOOKUP_F_xxx flags, and put them into ip6_route.h Signed-off-by: YOSHIFUJI Hideaki Acked-by: Ville Nuorvala --- include/net/ip6_fib.h | 3 --- include/net/ip6_route.h | 4 ++++ net/ipv6/fib6_rules.c | 2 +- net/ipv6/route.c | 32 ++++++++++++-------------------- 4 files changed, 17 insertions(+), 24 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 6a3f26a04509..e4438de3bd6b 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -173,9 +173,6 @@ struct fib6_table { #define RT6_TABLE_LOCAL RT6_TABLE_MAIN #endif -#define RT6_F_STRICT 1 -#define RT6_F_HAS_SADDR 2 - typedef struct rt6_info *(*pol_lookup_t)(struct fib6_table *, struct flowi *, int); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 0d40f84df21b..297909570041 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -32,6 +32,10 @@ struct route_info { #include #include +#define RT6_LOOKUP_F_IFACE 0x1 +#define RT6_LOOKUP_F_REACHABLE 0x2 +#define RT6_LOOKUP_F_HAS_SADDR 0x4 + struct pol_chain { int type; int priority; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 2c4fbc855e6c..7b4908cc52b3 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -117,7 +117,7 @@ static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen)) return 0; - if ((flags & RT6_F_HAS_SADDR) && + if ((flags & RT6_LOOKUP_F_HAS_SADDR) && !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen)) return 0; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index fd6f2ec4fa09..20691285aee5 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -76,9 +76,6 @@ #define CLONE_OFFLINK_ROUTE 0 -#define RT6_SELECT_F_IFACE 0x1 -#define RT6_SELECT_F_REACHABLE 0x2 - static int ip6_rt_max_size = 4096; static int ip6_rt_gc_min_interval = HZ / 2; static int ip6_rt_gc_timeout = 60*HZ; @@ -340,7 +337,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, int m, n; m = rt6_check_dev(rt, oif); - if (!m && (strict & RT6_SELECT_F_IFACE)) + if (!m && (strict & RT6_LOOKUP_F_IFACE)) return -1; #ifdef CONFIG_IPV6_ROUTER_PREF m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; @@ -348,7 +345,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, n = rt6_check_neigh(rt); if (n > 1) m |= 16; - else if (!n && strict & RT6_SELECT_F_REACHABLE) + else if (!n && strict & RT6_LOOKUP_F_REACHABLE) return -1; return m; } @@ -388,7 +385,7 @@ static struct rt6_info *rt6_select(struct rt6_info **head, int oif, } if (!match && - (strict & RT6_SELECT_F_REACHABLE) && + (strict & RT6_LOOKUP_F_REACHABLE) && last && last != rt0) { /* no entries matched; do round-robin */ static DEFINE_SPINLOCK(lock); @@ -511,7 +508,7 @@ static struct rt6_info *ip6_pol_route_lookup(struct fib6_table *table, fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src); restart: rt = fn->leaf; - rt = rt6_device_match(rt, fl->oif, flags & RT6_F_STRICT); + rt = rt6_device_match(rt, fl->oif, flags); BACKTRACK(&fl->fl6_src); dst_hold(&rt->u.dst); out: @@ -537,7 +534,7 @@ struct rt6_info *rt6_lookup(struct in6_addr *daddr, struct in6_addr *saddr, }, }; struct dst_entry *dst; - int flags = strict ? RT6_F_STRICT : 0; + int flags = strict ? RT6_LOOKUP_F_IFACE : 0; dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_lookup); if (dst->error == 0) @@ -633,10 +630,9 @@ static struct rt6_info *ip6_pol_route_input(struct fib6_table *table, int strict = 0; int attempts = 3; int err; - int reachable = RT6_SELECT_F_REACHABLE; + int reachable = RT6_LOOKUP_F_REACHABLE; - if (flags & RT6_F_STRICT) - strict = RT6_SELECT_F_IFACE; + strict |= flags & RT6_LOOKUP_F_IFACE; relookup: read_lock_bh(&table->tb6_lock); @@ -712,10 +708,7 @@ void ip6_route_input(struct sk_buff *skb) }, .proto = iph->nexthdr, }; - int flags = 0; - - if (rt6_need_strict(&iph->daddr)) - flags |= RT6_F_STRICT; + int flags = rt6_need_strict(&iph->daddr) ? RT6_LOOKUP_F_IFACE : 0; skb->dst = fib6_rule_lookup(&fl, flags, ip6_pol_route_input); } @@ -728,10 +721,9 @@ static struct rt6_info *ip6_pol_route_output(struct fib6_table *table, int strict = 0; int attempts = 3; int err; - int reachable = RT6_SELECT_F_REACHABLE; + int reachable = RT6_LOOKUP_F_REACHABLE; - if (flags & RT6_F_STRICT) - strict = RT6_SELECT_F_IFACE; + strict |= flags & RT6_LOOKUP_F_IFACE; relookup: read_lock_bh(&table->tb6_lock); @@ -797,7 +789,7 @@ struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl) int flags = 0; if (rt6_need_strict(&fl->fl6_dst)) - flags |= RT6_F_STRICT; + flags |= RT6_LOOKUP_F_IFACE; return fib6_rule_lookup(fl, flags, ip6_pol_route_output); } @@ -1362,7 +1354,7 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, }, .gateway = *gateway, }; - int flags = rt6_need_strict(dest) ? RT6_F_STRICT : 0; + int flags = rt6_need_strict(dest) ? RT6_LOOKUP_F_IFACE : 0; return (struct rt6_info *)fib6_rule_lookup((struct flowi *)&rdfl, flags, __ip6_route_redirect); } -- cgit v1.2.3 From 9123de2c043996050bacf77031cad845f5976f5d Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 20 Sep 2006 11:59:42 -0700 Subject: [NETFILTER]: ip6table_mangle: reroute when nfmark changes in NF_IP6_LOCAL_OUT Now that IPv6 supports policy routing we need to reroute in NF_IP6_LOCAL_OUT when the mark value changes. Signed-off-by: Patrick McHardy Signed-off-by: David S. Miller --- include/linux/netfilter_ipv6.h | 1 + include/net/ip6_route.h | 2 -- net/ipv6/netfilter/ip6table_mangle.c | 8 ++------ 3 files changed, 3 insertions(+), 8 deletions(-) (limited to 'include/net/ip6_route.h') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index 52a7b9e76428..d97e268cdfe5 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -73,6 +73,7 @@ enum nf_ip6_hook_priorities { }; #ifdef CONFIG_NETFILTER +extern int ip6_route_me_harder(struct sk_buff *skb); extern unsigned int nf_ip6_checksum(struct sk_buff *skb, unsigned int hook, unsigned int dataoff, u_int8_t protocol); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 297909570041..6ca6b71dfe0f 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -57,8 +57,6 @@ extern void ip6_route_input(struct sk_buff *skb); extern struct dst_entry * ip6_route_output(struct sock *sk, struct flowi *fl); -extern int ip6_route_me_harder(struct sk_buff *skb); - extern void ip6_route_init(void); extern void ip6_route_cleanup(void); diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 32db04fd8310..386ea260e767 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -180,12 +180,8 @@ ip6t_local_hook(unsigned int hook, && (memcmp(&(*pskb)->nh.ipv6h->saddr, &saddr, sizeof(saddr)) || memcmp(&(*pskb)->nh.ipv6h->daddr, &daddr, sizeof(daddr)) || (*pskb)->nfmark != nfmark - || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) { - - /* something which could affect routing has changed */ - - DEBUGP("ip6table_mangle: we'd need to re-route a packet\n"); - } + || (*pskb)->nh.ipv6h->hop_limit != hop_limit)) + return ip6_route_me_harder(*pskb) == 0 ? ret : NF_DROP; return ret; } -- cgit v1.2.3