1 files changed, 438 insertions, 106 deletions

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index 1df6cd4568d..185c341fafb 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -10,22 +10,67 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/slab.h>
 #include <linux/list.h>
+#include <linux/module.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
 #include <net/fib_rules.h>
 
-static LIST_HEAD(rules_ops);
-static DEFINE_SPINLOCK(rules_mod_lock);
+int fib_default_rule_add(struct fib_rules_ops *ops,
+			 u32 pref, u32 table, u32 flags)
+{
+	struct fib_rule *r;
+
+	r = kzalloc(ops->rule_size, GFP_KERNEL);
+	if (r == NULL)
+		return -ENOMEM;
+
+	atomic_set(&r->refcnt, 1);
+	r->action = FR_ACT_TO_TBL;
+	r->pref = pref;
+	r->table = table;
+	r->flags = flags;
+	r->fr_net = hold_net(ops->fro_net);
+
+	r->suppress_prefixlen = -1;
+	r->suppress_ifgroup = -1;
+
+	/* The lock is not required here, the list in unreacheable
+	 * at the moment this function is called */
+	list_add_tail(&r->list, &ops->rules_list);
+	return 0;
+}
+EXPORT_SYMBOL(fib_default_rule_add);
+
+u32 fib_default_rule_pref(struct fib_rules_ops *ops)
+{
+	struct list_head *pos;
+	struct fib_rule *rule;
+
+	if (!list_empty(&ops->rules_list)) {
+		pos = ops->rules_list.next;
+		if (pos->next != &ops->rules_list) {
+			rule = list_entry(pos->next, struct fib_rule, list);
+			if (rule->pref)
+				return rule->pref - 1;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(fib_default_rule_pref);
 
 static void notify_rule_change(int event, struct fib_rule *rule,
 			       struct fib_rules_ops *ops, struct nlmsghdr *nlh,
 			       u32 pid);
 
-static struct fib_rules_ops *lookup_rules_ops(int family)
+static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family)
 {
 	struct fib_rules_ops *ops;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(ops, &rules_ops, list) {
+	list_for_each_entry_rcu(ops, &net->rules_ops, list) {
 		if (ops->family == family) {
 			if (!try_module_get(ops->owner))
 				ops = NULL;
@@ -44,10 +89,19 @@ static void rules_ops_put(struct fib_rules_ops *ops)
 		module_put(ops->owner);
 }
 
-int fib_rules_register(struct fib_rules_ops *ops)
+static void flush_route_cache(struct fib_rules_ops *ops)
+{
+	if (ops->flush_cache)
+		ops->flush_cache(ops);
+}
+
+static int __fib_rules_register(struct fib_rules_ops *ops)
 {
 	int err = -EEXIST;
 	struct fib_rules_ops *o;
+	struct net *net;
+
+	net = ops->fro_net;
 
 	if (ops->rule_size < sizeof(struct fib_rule))
 		return -EINVAL;
@@ -57,54 +111,75 @@ int fib_rules_register(struct fib_rules_ops *ops)
 	    ops->action == NULL)
 		return -EINVAL;
 
-	spin_lock(&rules_mod_lock);
-	list_for_each_entry(o, &rules_ops, list)
+	spin_lock(&net->rules_mod_lock);
+	list_for_each_entry(o, &net->rules_ops, list)
 		if (ops->family == o->family)
 			goto errout;
 
-	list_add_tail_rcu(&ops->list, &rules_ops);
+	hold_net(net);
+	list_add_tail_rcu(&ops->list, &net->rules_ops);
 	err = 0;
 errout:
-	spin_unlock(&rules_mod_lock);
+	spin_unlock(&net->rules_mod_lock);
 
 	return err;
 }
 
+struct fib_rules_ops *
+fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net)
+{
+	struct fib_rules_ops *ops;
+	int err;
+
+	ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL);
+	if (ops == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&ops->rules_list);
+	ops->fro_net = net;
+
+	err = __fib_rules_register(ops);
+	if (err) {
+		kfree(ops);
+		ops = ERR_PTR(err);
+	}
+
+	return ops;
+}
 EXPORT_SYMBOL_GPL(fib_rules_register);
 
-static void cleanup_ops(struct fib_rules_ops *ops)
+static void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
 {
 	struct fib_rule *rule, *tmp;
 
-	list_for_each_entry_safe(rule, tmp, ops->rules_list, list) {
+	list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) {
 		list_del_rcu(&rule->list);
+		if (ops->delete)
+			ops->delete(rule);
 		fib_rule_put(rule);
 	}
 }
 
-int fib_rules_unregister(struct fib_rules_ops *ops)
+static void fib_rules_put_rcu(struct rcu_head *head)
 {
-	int err = 0;
-	struct fib_rules_ops *o;
+	struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu);
+	struct net *net = ops->fro_net;
 
-	spin_lock(&rules_mod_lock);
-	list_for_each_entry(o, &rules_ops, list) {
-		if (o == ops) {
-			list_del_rcu(&o->list);
-			cleanup_ops(ops);
-			goto out;
-		}
-	}
+	release_net(net);
+	kfree(ops);
+}
 
-	err = -ENOENT;
-out:
-	spin_unlock(&rules_mod_lock);
+void fib_rules_unregister(struct fib_rules_ops *ops)
+{
+	struct net *net = ops->fro_net;
 
-	synchronize_rcu();
+	spin_lock(&net->rules_mod_lock);
+	list_del_rcu(&ops->list);
+	fib_rules_cleanup_ops(ops);
+	spin_unlock(&net->rules_mod_lock);
 
-	return err;
+	call_rcu(&ops->rcu, fib_rules_put_rcu);
 }
-
 EXPORT_SYMBOL_GPL(fib_rules_unregister);
 
 static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
@@ -112,10 +187,13 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
 {
 	int ret = 0;
 
-	if (rule->ifindex && (rule->ifindex != fl->iif))
+	if (rule->iifindex && (rule->iifindex != fl->flowi_iif))
 		goto out;
 
-	if ((rule->mark ^ fl->mark) & rule->mark_mask)
+	if (rule->oifindex && (rule->oifindex != fl->flowi_oif))
+		goto out;
+
+	if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
 		goto out;
 
 	ret = ops->match(rule, fl, flags);
@@ -131,41 +209,84 @@ int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl,
 
 	rcu_read_lock();
 
-	list_for_each_entry_rcu(rule, ops->rules_list, list) {
+	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+jumped:
 		if (!fib_rule_match(rule, ops, fl, flags))
 			continue;
 
-		err = ops->action(rule, fl, flags, arg);
+		if (rule->action == FR_ACT_GOTO) {
+			struct fib_rule *target;
+
+			target = rcu_dereference(rule->ctarget);
+			if (target == NULL) {
+				continue;
+			} else {
+				rule = target;
+				goto jumped;
+			}
+		} else if (rule->action == FR_ACT_NOP)
+			continue;
+		else
+			err = ops->action(rule, fl, flags, arg);
+
+		if (!err && ops->suppress && ops->suppress(rule, arg))
+			continue;
+
 		if (err != -EAGAIN) {
-			fib_rule_get(rule);
-			arg->rule = rule;
-			goto out;
+			if ((arg->flags & FIB_LOOKUP_NOREF) ||
+			    likely(atomic_inc_not_zero(&rule->refcnt))) {
+				arg->rule = rule;
+				goto out;
+			}
+			break;
 		}
 	}
 
-	err = -ENETUNREACH;
+	err = -ESRCH;
 out:
 	rcu_read_unlock();
 
 	return err;
 }
-
 EXPORT_SYMBOL_GPL(fib_rules_lookup);
 
-int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb,
+			    struct fib_rules_ops *ops)
+{
+	int err = -EINVAL;
+
+	if (frh->src_len)
+		if (tb[FRA_SRC] == NULL ||
+		    frh->src_len > (ops->addr_size * 8) ||
+		    nla_len(tb[FRA_SRC]) != ops->addr_size)
+			goto errout;
+
+	if (frh->dst_len)
+		if (tb[FRA_DST] == NULL ||
+		    frh->dst_len > (ops->addr_size * 8) ||
+		    nla_len(tb[FRA_DST]) != ops->addr_size)
+			goto errout;
+
+	err = 0;
+errout:
+	return err;
+}
+
+static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 {
+	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
 	struct fib_rules_ops *ops = NULL;
 	struct fib_rule *rule, *r, *last = NULL;
 	struct nlattr *tb[FRA_MAX+1];
-	int err = -EINVAL;
+	int err = -EINVAL, unresolved = 0;
 
 	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
 		goto errout;
 
-	ops = lookup_rules_ops(frh->family);
+	ops = lookup_rules_ops(net, frh->family);
 	if (ops == NULL) {
-		err = EAFNOSUPPORT;
+		err = -EAFNOSUPPORT;
 		goto errout;
 	}
 
@@ -173,23 +294,38 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	if (err < 0)
 		goto errout;
 
+	err = validate_rulemsg(frh, tb, ops);
+	if (err < 0)
+		goto errout;
+
 	rule = kzalloc(ops->rule_size, GFP_KERNEL);
 	if (rule == NULL) {
 		err = -ENOMEM;
 		goto errout;
 	}
+	rule->fr_net = hold_net(net);
 
 	if (tb[FRA_PRIORITY])
 		rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
 
-	if (tb[FRA_IFNAME]) {
+	if (tb[FRA_IIFNAME]) {
 		struct net_device *dev;
 
-		rule->ifindex = -1;
-		nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ);
-		dev = __dev_get_by_name(rule->ifname);
+		rule->iifindex = -1;
+		nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+		dev = __dev_get_by_name(net, rule->iifname);
 		if (dev)
-			rule->ifindex = dev->ifindex;
+			rule->iifindex = dev->ifindex;
+	}
+
+	if (tb[FRA_OIFNAME]) {
+		struct net_device *dev;
+
+		rule->oifindex = -1;
+		nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+		dev = __dev_get_by_name(net, rule->oifname);
+		if (dev)
+			rule->oifindex = dev->ifindex;
 	}
 
 	if (tb[FRA_FWMARK]) {
@@ -207,15 +343,46 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	rule->action = frh->action;
 	rule->flags = frh->flags;
 	rule->table = frh_get_table(frh, tb);
+	if (tb[FRA_SUPPRESS_PREFIXLEN])
+		rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]);
+	else
+		rule->suppress_prefixlen = -1;
 
-	if (!rule->pref && ops->default_pref)
-		rule->pref = ops->default_pref();
+	if (tb[FRA_SUPPRESS_IFGROUP])
+		rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]);
+	else
+		rule->suppress_ifgroup = -1;
+
+	if (!tb[FRA_PRIORITY] && ops->default_pref)
+		rule->pref = ops->default_pref(ops);
+
+	err = -EINVAL;
+	if (tb[FRA_GOTO]) {
+		if (rule->action != FR_ACT_GOTO)
+			goto errout_free;
+
+		rule->target = nla_get_u32(tb[FRA_GOTO]);
+		/* Backward jumps are prohibited to avoid endless loops */
+		if (rule->target <= rule->pref)
+			goto errout_free;
+
+		list_for_each_entry(r, &ops->rules_list, list) {
+			if (r->pref == rule->target) {
+				RCU_INIT_POINTER(rule->ctarget, r);
+				break;
+			}
+		}
 
-	err = ops->configure(rule, skb, nlh, frh, tb);
+		if (rcu_dereference_protected(rule->ctarget, 1) == NULL)
+			unresolved = 1;
+	} else if (rule->action == FR_ACT_GOTO)
+		goto errout_free;
+
+	err = ops->configure(rule, skb, frh, tb);
 	if (err < 0)
 		goto errout_free;
 
-	list_for_each_entry(r, ops->rules_list, list) {
+	list_for_each_entry(r, &ops->rules_list, list) {
 		if (r->pref > rule->pref)
 			break;
 		last = r;
@@ -226,33 +393,58 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	if (last)
 		list_add_rcu(&rule->list, &last->list);
 	else
-		list_add_rcu(&rule->list, ops->rules_list);
+		list_add_rcu(&rule->list, &ops->rules_list);
+
+	if (ops->unresolved_rules) {
+		/*
+		 * There are unresolved goto rules in the list, check if
+		 * any of them are pointing to this new rule.
+		 */
+		list_for_each_entry(r, &ops->rules_list, list) {
+			if (r->action == FR_ACT_GOTO &&
+			    r->target == rule->pref &&
+			    rtnl_dereference(r->ctarget) == NULL) {
+				rcu_assign_pointer(r->ctarget, rule);
+				if (--ops->unresolved_rules == 0)
+					break;
+			}
+		}
+	}
+
+	if (rule->action == FR_ACT_GOTO)
+		ops->nr_goto_rules++;
+
+	if (unresolved)
+		ops->unresolved_rules++;
 
-	notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid);
+	notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
+	flush_route_cache(ops);
 	rules_ops_put(ops);
 	return 0;
 
 errout_free:
+	release_net(rule->fr_net);
 	kfree(rule);
 errout:
 	rules_ops_put(ops);
 	return err;
 }
 
-int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
 {
+	struct net *net = sock_net(skb->sk);
 	struct fib_rule_hdr *frh = nlmsg_data(nlh);
 	struct fib_rules_ops *ops = NULL;
-	struct fib_rule *rule;
+	struct fib_rule *rule, *tmp;
 	struct nlattr *tb[FRA_MAX+1];
 	int err = -EINVAL;
 
 	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
 		goto errout;
 
-	ops = lookup_rules_ops(frh->family);
+	ops = lookup_rules_ops(net, frh->family);
 	if (ops == NULL) {
-		err = EAFNOSUPPORT;
+		err = -EAFNOSUPPORT;
 		goto errout;
 	}
 
@@ -260,19 +452,28 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	if (err < 0)
 		goto errout;
 
-	list_for_each_entry(rule, ops->rules_list, list) {
+	err = validate_rulemsg(frh, tb, ops);
+	if (err < 0)
+		goto errout;
+
+	list_for_each_entry(rule, &ops->rules_list, list) {
 		if (frh->action && (frh->action != rule->action))
 			continue;
 
-		if (frh->table && (frh_get_table(frh, tb) != rule->table))
+		if (frh_get_table(frh, tb) &&
+		    (frh_get_table(frh, tb) != rule->table))
 			continue;
 
 		if (tb[FRA_PRIORITY] &&
 		    (rule->pref != nla_get_u32(tb[FRA_PRIORITY])))
 			continue;
 
-		if (tb[FRA_IFNAME] &&
-		    nla_strcmp(tb[FRA_IFNAME], rule->ifname))
+		if (tb[FRA_IIFNAME] &&
+		    nla_strcmp(tb[FRA_IIFNAME], rule->iifname))
+			continue;
+
+		if (tb[FRA_OIFNAME] &&
+		    nla_strcmp(tb[FRA_OIFNAME], rule->oifname))
 			continue;
 
 		if (tb[FRA_FWMARK] &&
@@ -292,10 +493,34 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 		}
 
 		list_del_rcu(&rule->list);
-		synchronize_rcu();
+
+		if (rule->action == FR_ACT_GOTO) {
+			ops->nr_goto_rules--;
+			if (rtnl_dereference(rule->ctarget) == NULL)
+				ops->unresolved_rules--;
+		}
+
+		/*
+		 * Check if this rule is a target to any of them. If so,
+		 * disable them. As this operation is eventually very
+		 * expensive, it is only performed if goto rules have
+		 * actually been added.
+		 */
+		if (ops->nr_goto_rules > 0) {
+			list_for_each_entry(tmp, &ops->rules_list, list) {
+				if (rtnl_dereference(tmp->ctarget) == rule) {
+					RCU_INIT_POINTER(tmp->ctarget, NULL);
+					ops->unresolved_rules++;
+				}
+			}
+		}
+
 		notify_rule_change(RTM_DELRULE, rule, ops, nlh,
-				   NETLINK_CB(skb).pid);
+				   NETLINK_CB(skb).portid);
+		if (ops->delete)
+			ops->delete(rule);
 		fib_rule_put(rule);
+		flush_route_cache(ops);
 		rules_ops_put(ops);
 		return 0;
 	}
@@ -310,9 +535,12 @@ static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
 					 struct fib_rule *rule)
 {
 	size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr))
-			 + nla_total_size(IFNAMSIZ) /* FRA_IFNAME */
+			 + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */
+			 + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */
 			 + nla_total_size(4) /* FRA_PRIORITY */
 			 + nla_total_size(4) /* FRA_TABLE */
+			 + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */
+			 + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
 			 + nla_total_size(4) /* FRA_FWMARK */
 			 + nla_total_size(4); /* FRA_FWMASK */
 
@@ -331,53 +559,75 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 
 	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags);
 	if (nlh == NULL)
-		return -1;
+		return -EMSGSIZE;
 
 	frh = nlmsg_data(nlh);
+	frh->family = ops->family;
 	frh->table = rule->table;
-	NLA_PUT_U32(skb, FRA_TABLE, rule->table);
+	if (nla_put_u32(skb, FRA_TABLE, rule->table))
+		goto nla_put_failure;
+	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
+		goto nla_put_failure;
 	frh->res1 = 0;
 	frh->res2 = 0;
 	frh->action = rule->action;
 	frh->flags = rule->flags;
 
-	if (rule->ifname[0])
-		NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname);
+	if (rule->action == FR_ACT_GOTO &&
+	    rcu_access_pointer(rule->ctarget) == NULL)
+		frh->flags |= FIB_RULE_UNRESOLVED;
 
-	if (rule->pref)
-		NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref);
+	if (rule->iifname[0]) {
+		if (nla_put_string(skb, FRA_IIFNAME, rule->iifname))
+			goto nla_put_failure;
+		if (rule->iifindex == -1)
+			frh->flags |= FIB_RULE_IIF_DETACHED;
+	}
 
-	if (rule->mark)
-		NLA_PUT_U32(skb, FRA_FWMARK, rule->mark);
+	if (rule->oifname[0]) {
+		if (nla_put_string(skb, FRA_OIFNAME, rule->oifname))
+			goto nla_put_failure;
+		if (rule->oifindex == -1)
+			frh->flags |= FIB_RULE_OIF_DETACHED;
+	}
 
-	if (rule->mark_mask || rule->mark)
-		NLA_PUT_U32(skb, FRA_FWMASK, rule->mark_mask);
+	if ((rule->pref &&
+	     nla_put_u32(skb, FRA_PRIORITY, rule->pref)) ||
+	    (rule->mark &&
+	     nla_put_u32(skb, FRA_FWMARK, rule->mark)) ||
+	    ((rule->mark_mask || rule->mark) &&
+	     nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
+	    (rule->target &&
+	     nla_put_u32(skb, FRA_GOTO, rule->target)))
+		goto nla_put_failure;
 
-	if (ops->fill(rule, skb, nlh, frh) < 0)
+	if (rule->suppress_ifgroup != -1) {
+		if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup))
+			goto nla_put_failure;
+	}
+
+	if (ops->fill(rule, skb, frh) < 0)
 		goto nla_put_failure;
 
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
-	return nlmsg_cancel(skb, nlh);
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
 }
 
-int fib_rules_dump(struct sk_buff *skb, struct netlink_callback *cb, int family)
+static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
+		      struct fib_rules_ops *ops)
 {
 	int idx = 0;
 	struct fib_rule *rule;
-	struct fib_rules_ops *ops;
-
-	ops = lookup_rules_ops(family);
-	if (ops == NULL)
-		return -EAFNOSUPPORT;
 
 	rcu_read_lock();
-	list_for_each_entry(rule, ops->rules_list, list) {
-		if (idx < cb->args[0])
+	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+		if (idx < cb->args[1])
 			goto skip;
 
-		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).pid,
+		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
 				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
 				     NLM_F_MULTI, ops) < 0)
 			break;
@@ -385,33 +635,72 @@ skip:
 		idx++;
 	}
 	rcu_read_unlock();
-	cb->args[0] = idx;
+	cb->args[1] = idx;
 	rules_ops_put(ops);
 
 	return skb->len;
 }
 
-EXPORT_SYMBOL_GPL(fib_rules_dump);
+static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct fib_rules_ops *ops;
+	int idx = 0, family;
+
+	family = rtnl_msg_family(cb->nlh);
+	if (family != AF_UNSPEC) {
+		/* Protocol specific dump request */
+		ops = lookup_rules_ops(net, family);
+		if (ops == NULL)
+			return -EAFNOSUPPORT;
+
+		return dump_rules(skb, cb, ops);
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ops, &net->rules_ops, list) {
+		if (idx < cb->args[0] || !try_module_get(ops->owner))
+			goto skip;
+
+		if (dump_rules(skb, cb, ops) < 0)
+			break;
+
+		cb->args[1] = 0;
+skip:
+		idx++;
+	}
+	rcu_read_unlock();
+	cb->args[0] = idx;
+
+	return skb->len;
+}
 
 static void notify_rule_change(int event, struct fib_rule *rule,
 			       struct fib_rules_ops *ops, struct nlmsghdr *nlh,
 			       u32 pid)
 {
+	struct net *net;
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
+	net = ops->fro_net;
 	skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL);
 	if (skb == NULL)
 		goto errout;
 
 	err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops);
-	/* failure implies BUG in fib_rule_nlmsg_size() */
-	BUG_ON(err < 0);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
 
-	err = rtnl_notify(skb, pid, ops->nlgroup, nlh, GFP_KERNEL);
+	rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL);
+	return;
 errout:
 	if (err < 0)
-		rtnl_set_sk_err(ops->nlgroup, err);
+		rtnl_set_sk_err(net, ops->nlgroup, err);
 }
 
 static void attach_rules(struct list_head *rules, struct net_device *dev)
@@ -419,9 +708,12 @@ static void attach_rules(struct list_head *rules, struct net_device *dev)
 	struct fib_rule *rule;
 
 	list_for_each_entry(rule, rules, list) {
-		if (rule->ifindex == -1 &&
-		    strcmp(dev->name, rule->ifname) == 0)
-			rule->ifindex = dev->ifindex;
+		if (rule->iifindex == -1 &&
+		    strcmp(dev->name, rule->iifname) == 0)
+			rule->iifindex = dev->ifindex;
+		if (rule->oifindex == -1 &&
+		    strcmp(dev->name, rule->oifname) == 0)
+			rule->oifindex = dev->ifindex;
 	}
 }
 
@@ -429,35 +721,43 @@ static void detach_rules(struct list_head *rules, struct net_device *dev)
 {
 	struct fib_rule *rule;
 
-	list_for_each_entry(rule, rules, list)
-		if (rule->ifindex == dev->ifindex)
-			rule->ifindex = -1;
+	list_for_each_entry(rule, rules, list) {
+		if (rule->iifindex == dev->ifindex)
+			rule->iifindex = -1;
+		if (rule->oifindex == dev->ifindex)
+			rule->oifindex = -1;
+	}
 }
 
 
 static int fib_rules_event(struct notifier_block *this, unsigned long event,
-			    void *ptr)
+			   void *ptr)
 {
-	struct net_device *dev = ptr;
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
 	struct fib_rules_ops *ops;
 
 	ASSERT_RTNL();
-	rcu_read_lock();
 
 	switch (event) {
 	case NETDEV_REGISTER:
-		list_for_each_entry(ops, &rules_ops, list)
-			attach_rules(ops->rules_list, dev);
+		list_for_each_entry(ops, &net->rules_ops, list)
+			attach_rules(&ops->rules_list, dev);
+		break;
+
+	case NETDEV_CHANGENAME:
+		list_for_each_entry(ops, &net->rules_ops, list) {
+			detach_rules(&ops->rules_list, dev);
+			attach_rules(&ops->rules_list, dev);
+		}
 		break;
 
 	case NETDEV_UNREGISTER:
-		list_for_each_entry(ops, &rules_ops, list)
-			detach_rules(ops->rules_list, dev);
+		list_for_each_entry(ops, &net->rules_ops, list)
+			detach_rules(&ops->rules_list, dev);
 		break;
 	}
 
-	rcu_read_unlock();
-
 	return NOTIFY_DONE;
 }
 
@@ -465,9 +765,41 @@ static struct notifier_block fib_rules_notifier = {
 	.notifier_call = fib_rules_event,
 };
 
+static int __net_init fib_rules_net_init(struct net *net)
+{
+	INIT_LIST_HEAD(&net->rules_ops);
+	spin_lock_init(&net->rules_mod_lock);
+	return 0;
+}
+
+static struct pernet_operations fib_rules_net_ops = {
+	.init = fib_rules_net_init,
+};
+
 static int __init fib_rules_init(void)
 {
-	return register_netdevice_notifier(&fib_rules_notifier);
+	int err;
+	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL);
+
+	err = register_pernet_subsys(&fib_rules_net_ops);
+	if (err < 0)
+		goto fail;
+
+	err = register_netdevice_notifier(&fib_rules_notifier);
+	if (err < 0)
+		goto fail_unregister;
+
+	return 0;
+
+fail_unregister:
+	unregister_pernet_subsys(&fib_rules_net_ops);
+fail:
+	rtnl_unregister(PF_UNSPEC, RTM_NEWRULE);
+	rtnl_unregister(PF_UNSPEC, RTM_DELRULE);
+	rtnl_unregister(PF_UNSPEC, RTM_GETRULE);
+	return err;
 }
 
 subsys_initcall(fib_rules_init);