1 files changed, 166 insertions, 130 deletions

diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c
index 34f5bfaddfc..b4d5e1d97c1 100644
--- a/net/ipv6/fib6_rules.c
+++ b/net/ipv6/fib6_rules.c
@@ -13,185 +13,198 @@
  *	Ville Nuorvala		<vnuorval@tcs.hut.fi>
  */
 
-#include <linux/config.h>
 #include <linux/netdevice.h>
+#include <linux/export.h>
 
 #include <net/fib_rules.h>
 #include <net/ipv6.h>
+#include <net/addrconf.h>
 #include <net/ip6_route.h>
 #include <net/netlink.h>
 
-struct fib6_rule
-{
+struct fib6_rule {
 	struct fib_rule		common;
 	struct rt6key		src;
 	struct rt6key		dst;
-#ifdef CONFIG_IPV6_ROUTE_FWMARK
-	u32			fwmark;
-	u32			fwmask;
-#endif
 	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 dst_entry *fib6_rule_lookup(struct net *net, struct flowi6 *fl6,
+				   int flags, pol_lookup_t lookup)
 {
 	struct fib_lookup_arg arg = {
 		.lookup_ptr = lookup,
+		.flags = FIB_LOOKUP_NOREF,
 	};
 
-	fib_rules_lookup(&fib6_rules_ops, fl, flags, &arg);
-	if (arg.rule)
-		fib_rule_put(arg.rule);
+	fib_rules_lookup(net->ipv6.fib6_rules_ops,
+			 flowi6_to_flowi(fl6), flags, &arg);
 
 	if (arg.result)
-		return (struct dst_entry *) arg.result;
+		return arg.result;
 
-	dst_hold(&ip6_null_entry.u.dst);
-	return &ip6_null_entry.u.dst;
+	dst_hold(&net->ipv6.ip6_null_entry->dst);
+	return &net->ipv6.ip6_null_entry->dst;
 }
 
 static int fib6_rule_action(struct fib_rule *rule, struct flowi *flp,
 			    int flags, struct fib_lookup_arg *arg)
 {
+	struct flowi6 *flp6 = &flp->u.ip6;
 	struct rt6_info *rt = NULL;
 	struct fib6_table *table;
+	struct net *net = rule->fr_net;
 	pol_lookup_t lookup = arg->lookup_ptr;
+	int err = 0;
 
 	switch (rule->action) {
 	case FR_ACT_TO_TBL:
 		break;
 	case FR_ACT_UNREACHABLE:
-		rt = &ip6_null_entry;
+		err = -ENETUNREACH;
+		rt = net->ipv6.ip6_null_entry;
 		goto discard_pkt;
 	default:
 	case FR_ACT_BLACKHOLE:
-		rt = &ip6_blk_hole_entry;
+		err = -EINVAL;
+		rt = net->ipv6.ip6_blk_hole_entry;
 		goto discard_pkt;
 	case FR_ACT_PROHIBIT:
-		rt = &ip6_prohibit_entry;
+		err = -EACCES;
+		rt = net->ipv6.ip6_prohibit_entry;
 		goto discard_pkt;
 	}
 
-	table = fib6_get_table(rule->table);
-	if (table)
-		rt = lookup(table, flp, flags);
+	table = fib6_get_table(net, rule->table);
+	if (!table) {
+		err = -EAGAIN;
+		goto out;
+	}
 
-	if (rt != &ip6_null_entry)
+	rt = lookup(net, table, flp6, flags);
+	if (rt != net->ipv6.ip6_null_entry) {
+		struct fib6_rule *r = (struct fib6_rule *)rule;
+
+		/*
+		 * If we need to find a source address for this traffic,
+		 * we check the result if it meets requirement of the rule.
+		 */
+		if ((rule->flags & FIB_RULE_FIND_SADDR) &&
+		    r->src.plen && !(flags & RT6_LOOKUP_F_HAS_SADDR)) {
+			struct in6_addr saddr;
+
+			if (ipv6_dev_get_saddr(net,
+					       ip6_dst_idev(&rt->dst)->dev,
+					       &flp6->daddr,
+					       rt6_flags2srcprefs(flags),
+					       &saddr))
+				goto again;
+			if (!ipv6_prefix_equal(&saddr, &r->src.addr,
+					       r->src.plen))
+				goto again;
+			flp6->saddr = saddr;
+		}
 		goto out;
-	dst_release(&rt->u.dst);
+	}
+again:
+	ip6_rt_put(rt);
+	err = -EAGAIN;
 	rt = NULL;
 	goto out;
 
 discard_pkt:
-	dst_hold(&rt->u.dst);
+	dst_hold(&rt->dst);
 out:
 	arg->result = rt;
-	return rt == NULL ? -EAGAIN : 0;
+	return err;
 }
 
+static bool fib6_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
+{
+	struct rt6_info *rt = (struct rt6_info *) arg->result;
+	struct net_device *dev = NULL;
+
+	if (rt->rt6i_idev)
+		dev = rt->rt6i_idev->dev;
+
+	/* do not accept result if the route does
+	 * not meet the required prefix length
+	 */
+	if (rt->rt6i_dst.plen <= rule->suppress_prefixlen)
+		goto suppress_route;
+
+	/* do not accept result if the route uses a device
+	 * belonging to a forbidden interface group
+	 */
+	if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup)
+		goto suppress_route;
+
+	return false;
+
+suppress_route:
+	ip6_rt_put(rt);
+	return true;
+}
 
 static int fib6_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
 {
 	struct fib6_rule *r = (struct fib6_rule *) rule;
+	struct flowi6 *fl6 = &fl->u.ip6;
 
-	if (!ipv6_prefix_equal(&fl->fl6_dst, &r->dst.addr, r->dst.plen))
-		return 0;
-
-	if ((flags & RT6_LOOKUP_F_HAS_SADDR) &&
-	    !ipv6_prefix_equal(&fl->fl6_src, &r->src.addr, r->src.plen))
+	if (r->dst.plen &&
+	    !ipv6_prefix_equal(&fl6->daddr, &r->dst.addr, r->dst.plen))
 		return 0;
 
-	if (r->tclass && r->tclass != ((ntohl(fl->fl6_flowlabel) >> 20) & 0xff))
-		return 0;
+	/*
+	 * If FIB_RULE_FIND_SADDR is set and we do not have a
+	 * source address for the traffic, we defer check for
+	 * source address.
+	 */
+	if (r->src.plen) {
+		if (flags & RT6_LOOKUP_F_HAS_SADDR) {
+			if (!ipv6_prefix_equal(&fl6->saddr, &r->src.addr,
+					       r->src.plen))
+				return 0;
+		} else if (!(r->common.flags & FIB_RULE_FIND_SADDR))
+			return 0;
+	}
 
-#ifdef CONFIG_IPV6_ROUTE_FWMARK
-	if ((r->fwmark ^ fl->fl6_fwmark) & r->fwmask)
+	if (r->tclass && r->tclass != ip6_tclass(fl6->flowlabel))
 		return 0;
-#endif
 
 	return 1;
 }
 
-static struct nla_policy fib6_rule_policy[FRA_MAX+1] __read_mostly = {
-	[FRA_IFNAME]	= { .type = NLA_STRING, .len = IFNAMSIZ - 1 },
-	[FRA_PRIORITY]	= { .type = NLA_U32 },
-	[FRA_SRC]	= { .len = sizeof(struct in6_addr) },
-	[FRA_DST]	= { .len = sizeof(struct in6_addr) },
-	[FRA_FWMARK]	= { .type = NLA_U32 },
-	[FRA_FWMASK]	= { .type = NLA_U32 },
-	[FRA_TABLE]	= { .type = NLA_U32 },
+static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = {
+	FRA_GENERIC_POLICY,
 };
 
 static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
-			       struct nlmsghdr *nlh, struct fib_rule_hdr *frh,
+			       struct fib_rule_hdr *frh,
 			       struct nlattr **tb)
 {
 	int err = -EINVAL;
+	struct net *net = sock_net(skb->sk);
 	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) {
+		if (fib6_new_table(net, rule->table) == NULL) {
 			err = -ENOBUFS;
 			goto errout;
 		}
 	}
 
-	if (tb[FRA_SRC])
+	if (frh->src_len)
 		nla_memcpy(&rule6->src.addr, tb[FRA_SRC],
 			   sizeof(struct in6_addr));
 
-	if (tb[FRA_DST])
+	if (frh->dst_len)
 		nla_memcpy(&rule6->dst.addr, tb[FRA_DST],
 			   sizeof(struct in6_addr));
 
-#ifdef CONFIG_IPV6_ROUTE_FWMARK
-	if (tb[FRA_FWMARK]) {
-		rule6->fwmark = nla_get_u32(tb[FRA_FWMARK]);
-		if (rule6->fwmark) {
-			/*
-			 * if the mark value is non-zero,
-			 * all bits are compared by default
-			 * unless a mask is explicitly specified.
-			 */
-			rule6->fwmask = 0xFFFFFFFF;
-		}
-	}
-
-	if (tb[FRA_FWMASK])
-		rule6->fwmask = nla_get_u32(tb[FRA_FWMASK]);
-#endif
-
 	rule6->src.plen = frh->src_len;
 	rule6->dst.plen = frh->dst_len;
 	rule6->tclass = frh->tos;
@@ -215,91 +228,114 @@ static int fib6_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh,
 	if (frh->tos && (rule6->tclass != frh->tos))
 		return 0;
 
-	if (tb[FRA_SRC] &&
+	if (frh->src_len &&
 	    nla_memcmp(tb[FRA_SRC], &rule6->src.addr, sizeof(struct in6_addr)))
 		return 0;
 
-	if (tb[FRA_DST] &&
+	if (frh->dst_len &&
 	    nla_memcmp(tb[FRA_DST], &rule6->dst.addr, sizeof(struct in6_addr)))
 		return 0;
 
-#ifdef CONFIG_IPV6_ROUTE_FWMARK
-	if (tb[FRA_FWMARK] && (rule6->fwmark != nla_get_u32(tb[FRA_FWMARK])))
-		return 0;
-
-	if (tb[FRA_FWMASK] && (rule6->fwmask != nla_get_u32(tb[FRA_FWMASK])))
-		return 0;
-#endif
-
 	return 1;
 }
 
 static int fib6_rule_fill(struct fib_rule *rule, struct sk_buff *skb,
-			  struct nlmsghdr *nlh, struct fib_rule_hdr *frh)
+			  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);
-
-#ifdef CONFIG_IPV6_ROUTE_FWMARK
-	if (rule6->fwmark)
-		NLA_PUT_U32(skb, FRA_FWMARK, rule6->fwmark);
-
-	if (rule6->fwmask || rule6->fwmark)
-		NLA_PUT_U32(skb, FRA_FWMASK, rule6->fwmask);
-#endif
-
+	if ((rule6->dst.plen &&
+	     nla_put(skb, FRA_DST, sizeof(struct in6_addr),
+		     &rule6->dst.addr)) ||
+	    (rule6->src.plen &&
+	     nla_put(skb, FRA_SRC, sizeof(struct in6_addr),
+		     &rule6->src.addr)))
+		goto nla_put_failure;
 	return 0;
 
 nla_put_failure:
 	return -ENOBUFS;
 }
 
-int fib6_rules_dump(struct sk_buff *skb, struct netlink_callback *cb)
+static u32 fib6_rule_default_pref(struct fib_rules_ops *ops)
 {
-	return fib_rules_dump(skb, cb, AF_INET6);
+	return 0x3FFF;
 }
 
-static u32 fib6_rule_default_pref(void)
+static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule)
 {
-	return 0x3FFF;
+	return nla_total_size(16) /* dst */
+	       + nla_total_size(16); /* src */
 }
 
-static struct fib_rules_ops fib6_rules_ops = {
+static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = {
 	.family			= AF_INET6,
 	.rule_size		= sizeof(struct fib6_rule),
+	.addr_size		= sizeof(struct in6_addr),
 	.action			= fib6_rule_action,
 	.match			= fib6_rule_match,
+	.suppress		= fib6_rule_suppress,
 	.configure		= fib6_rule_configure,
 	.compare		= fib6_rule_compare,
 	.fill			= fib6_rule_fill,
 	.default_pref		= fib6_rule_default_pref,
+	.nlmsg_payload		= fib6_rule_nlmsg_payload,
 	.nlgroup		= RTNLGRP_IPV6_RULE,
 	.policy			= fib6_rule_policy,
-	.rules_list		= &fib6_rules,
 	.owner			= THIS_MODULE,
+	.fro_net		= &init_net,
 };
 
-void __init fib6_rules_init(void)
+static int __net_init fib6_rules_net_init(struct net *net)
 {
-	list_add_tail(&local_rule.common.list, &fib6_rules);
-	list_add_tail(&main_rule.common.list, &fib6_rules);
+	struct fib_rules_ops *ops;
+	int err = -ENOMEM;
+
+	ops = fib_rules_register(&fib6_rules_ops_template, net);
+	if (IS_ERR(ops))
+		return PTR_ERR(ops);
+	net->ipv6.fib6_rules_ops = ops;
+
+
+	err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0,
+				   RT6_TABLE_LOCAL, 0);
+	if (err)
+		goto out_fib6_rules_ops;
+
+	err = fib_default_rule_add(net->ipv6.fib6_rules_ops,
+				   0x7FFE, RT6_TABLE_MAIN, 0);
+	if (err)
+		goto out_fib6_rules_ops;
 
-	fib_rules_register(&fib6_rules_ops);
+out:
+	return err;
+
+out_fib6_rules_ops:
+	fib_rules_unregister(ops);
+	goto out;
+}
+
+static void __net_exit fib6_rules_net_exit(struct net *net)
+{
+	fib_rules_unregister(net->ipv6.fib6_rules_ops);
 }
 
+static struct pernet_operations fib6_rules_net_ops = {
+	.init = fib6_rules_net_init,
+	.exit = fib6_rules_net_exit,
+};
+
+int __init fib6_rules_init(void)
+{
+	return register_pernet_subsys(&fib6_rules_net_ops);
+}
+
+
 void fib6_rules_cleanup(void)
 {
-	fib_rules_unregister(&fib6_rules_ops);
+	unregister_pernet_subsys(&fib6_rules_net_ops);
 }