1 files changed, 191 insertions, 73 deletions

diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c
index bd309384f8b..185c341fafb 100644
--- a/net/core/fib_rules.c
+++ b/net/core/fib_rules.c
@@ -10,7 +10,9 @@
 
 #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>
@@ -31,6 +33,9 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 	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);
@@ -38,6 +43,24 @@ int fib_default_rule_add(struct fib_rules_ops *ops,
 }
 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);
@@ -72,7 +95,7 @@ static void flush_route_cache(struct fib_rules_ops *ops)
 		ops->flush_cache(ops);
 }
 
-int fib_rules_register(struct fib_rules_ops *ops)
+static int __fib_rules_register(struct fib_rules_ops *ops)
 {
 	int err = -EEXIST;
 	struct fib_rules_ops *o;
@@ -102,18 +125,49 @@ errout:
 	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);
 
-void fib_rules_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_del_rcu(&rule->list);
+		if (ops->delete)
+			ops->delete(rule);
 		fib_rule_put(rule);
 	}
 }
-EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops);
+
+static void fib_rules_put_rcu(struct rcu_head *head)
+{
+	struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu);
+	struct net *net = ops->fro_net;
+
+	release_net(net);
+	kfree(ops);
+}
 
 void fib_rules_unregister(struct fib_rules_ops *ops)
 {
@@ -124,10 +178,8 @@ void fib_rules_unregister(struct fib_rules_ops *ops)
 	fib_rules_cleanup_ops(ops);
 	spin_unlock(&net->rules_mod_lock);
 
-	synchronize_rcu();
-	release_net(net);
+	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,
@@ -135,10 +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);
@@ -174,10 +229,16 @@ jumped:
 		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;
 		}
 	}
 
@@ -187,7 +248,6 @@ out:
 
 	return err;
 }
-
 EXPORT_SYMBOL_GPL(fib_rules_lookup);
 
 static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb,
@@ -212,7 +272,7 @@ errout:
 	return err;
 }
 
-static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
+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);
@@ -248,14 +308,24 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	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->iifindex = -1;
+		nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+		dev = __dev_get_by_name(net, rule->iifname);
+		if (dev)
+			rule->iifindex = dev->ifindex;
+	}
+
+	if (tb[FRA_OIFNAME]) {
 		struct net_device *dev;
 
-		rule->ifindex = -1;
-		nla_strlcpy(rule->ifname, tb[FRA_IFNAME], IFNAMSIZ);
-		dev = __dev_get_by_name(net, rule->ifname);
+		rule->oifindex = -1;
+		nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+		dev = __dev_get_by_name(net, rule->oifname);
 		if (dev)
-			rule->ifindex = dev->ifindex;
+			rule->oifindex = dev->ifindex;
 	}
 
 	if (tb[FRA_FWMARK]) {
@@ -273,8 +343,17 @@ static 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 (tb[FRA_SUPPRESS_IFGROUP])
+		rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]);
+	else
+		rule->suppress_ifgroup = -1;
 
-	if (!rule->pref && ops->default_pref)
+	if (!tb[FRA_PRIORITY] && ops->default_pref)
 		rule->pref = ops->default_pref(ops);
 
 	err = -EINVAL;
@@ -289,12 +368,12 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 
 		list_for_each_entry(r, &ops->rules_list, list) {
 			if (r->pref == rule->target) {
-				rule->ctarget = r;
+				RCU_INIT_POINTER(rule->ctarget, r);
 				break;
 			}
 		}
 
-		if (rule->ctarget == NULL)
+		if (rcu_dereference_protected(rule->ctarget, 1) == NULL)
 			unresolved = 1;
 	} else if (rule->action == FR_ACT_GOTO)
 		goto errout_free;
@@ -311,6 +390,11 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 
 	fib_rule_get(rule);
 
+	if (last)
+		list_add_rcu(&rule->list, &last->list);
+	else
+		list_add_rcu(&rule->list, &ops->rules_list);
+
 	if (ops->unresolved_rules) {
 		/*
 		 * There are unresolved goto rules in the list, check if
@@ -318,8 +402,8 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 		 */
 		list_for_each_entry(r, &ops->rules_list, list) {
 			if (r->action == FR_ACT_GOTO &&
-			    r->target == rule->pref) {
-				BUG_ON(r->ctarget != NULL);
+			    r->target == rule->pref &&
+			    rtnl_dereference(r->ctarget) == NULL) {
 				rcu_assign_pointer(r->ctarget, rule);
 				if (--ops->unresolved_rules == 0)
 					break;
@@ -333,12 +417,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	if (unresolved)
 		ops->unresolved_rules++;
 
-	if (last)
-		list_add_rcu(&rule->list, &last->list);
-	else
-		list_add_rcu(&rule->list, &ops->rules_list);
-
-	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;
@@ -351,7 +430,7 @@ errout:
 	return err;
 }
 
-static 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);
@@ -381,15 +460,20 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 		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] &&
@@ -410,8 +494,11 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 
 		list_del_rcu(&rule->list);
 
-		if (rule->action == FR_ACT_GOTO)
+		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,
@@ -421,16 +508,17 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 		 */
 		if (ops->nr_goto_rules > 0) {
 			list_for_each_entry(tmp, &ops->rules_list, list) {
-				if (tmp->ctarget == rule) {
-					rcu_assign_pointer(tmp->ctarget, NULL);
+				if (rtnl_dereference(tmp->ctarget) == rule) {
+					RCU_INIT_POINTER(tmp->ctarget, NULL);
 					ops->unresolved_rules++;
 				}
 			}
 		}
 
-		synchronize_rcu();
 		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);
@@ -447,9 +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 */
 
@@ -471,34 +562,49 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
 		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->action == FR_ACT_GOTO && rule->ctarget == NULL)
+	if (rule->action == FR_ACT_GOTO &&
+	    rcu_access_pointer(rule->ctarget) == NULL)
 		frh->flags |= FIB_RULE_UNRESOLVED;
 
-	if (rule->ifname[0]) {
-		NLA_PUT_STRING(skb, FRA_IFNAME, rule->ifname);
-
-		if (rule->ifindex == -1)
-			frh->flags |= FIB_RULE_DEV_DETACHED;
+	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->pref)
-		NLA_PUT_U32(skb, FRA_PRIORITY, rule->pref);
-
-	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 (rule->target)
-		NLA_PUT_U32(skb, FRA_GOTO, rule->target);
+	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;
@@ -516,17 +622,19 @@ static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
 	int idx = 0;
 	struct fib_rule *rule;
 
-	list_for_each_entry(rule, &ops->rules_list, list) {
+	rcu_read_lock();
+	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;
 skip:
 		idx++;
 	}
+	rcu_read_unlock();
 	cb->args[1] = idx;
 	rules_ops_put(ops);
 
@@ -558,7 +666,7 @@ static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
 			break;
 
 		cb->args[1] = 0;
-	skip:
+skip:
 		idx++;
 	}
 	rcu_read_unlock();
@@ -600,9 +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;
 	}
 }
 
@@ -610,21 +721,23 @@ 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:
@@ -632,14 +745,19 @@ static int fib_rules_event(struct notifier_block *this, unsigned long event,
 			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, &net->rules_ops, list)
 			detach_rules(&ops->rules_list, dev);
 		break;
 	}
 
-	rcu_read_unlock();
-
 	return NOTIFY_DONE;
 }
 
@@ -647,7 +765,7 @@ static struct notifier_block fib_rules_notifier = {
 	.notifier_call = fib_rules_event,
 };
 
-static int fib_rules_net_init(struct net *net)
+static int __net_init fib_rules_net_init(struct net *net)
 {
 	INIT_LIST_HEAD(&net->rules_ops);
 	spin_lock_init(&net->rules_mod_lock);
@@ -661,9 +779,9 @@ static struct pernet_operations fib_rules_net_ops = {
 static int __init fib_rules_init(void)
 {
 	int err;
-	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL);
-	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule);
+	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)