lwtunnel: fix autoload of lwt modules

Trying to add an mpls encap route when the MPLS modules are not loaded
hangs. For example:

    CONFIG_MPLS=y
    CONFIG_NET_MPLS_GSO=m
    CONFIG_MPLS_ROUTING=m
    CONFIG_MPLS_IPTUNNEL=m

    $ ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2

The ip command hangs:
root       880   826  0 21:25 pts/0    00:00:00 ip route add 10.10.10.10/32 encap mpls 100 via inet 10.100.1.2

    $ cat /proc/880/stack
    [<ffffffff81065a9b>] call_usermodehelper_exec+0xd6/0x134
    [<ffffffff81065efc>] __request_module+0x27b/0x30a
    [<ffffffff814542f6>] lwtunnel_build_state+0xe4/0x178
    [<ffffffff814aa1e4>] fib_create_info+0x47f/0xdd4
    [<ffffffff814ae451>] fib_table_insert+0x90/0x41f
    [<ffffffff814a8010>] inet_rtm_newroute+0x4b/0x52
    ...

modprobe is trying to load rtnl-lwt-MPLS:

root       881     5  0 21:25 ?        00:00:00 /sbin/modprobe -q -- rtnl-lwt-MPLS

and it hangs after loading mpls_router:

    $ cat /proc/881/stack
    [<ffffffff81441537>] rtnl_lock+0x12/0x14
    [<ffffffff8142ca2a>] register_netdevice_notifier+0x16/0x179
    [<ffffffffa0033025>] mpls_init+0x25/0x1000 [mpls_router]
    [<ffffffff81000471>] do_one_initcall+0x8e/0x13f
    [<ffffffff81119961>] do_init_module+0x5a/0x1e5
    [<ffffffff810bd070>] load_module+0x13bd/0x17d6
    ...

The problem is that lwtunnel_build_state is called with rtnl lock
held preventing mpls_init from registering.

Given the potential references held by the time lwtunnel_build_state it
can not drop the rtnl lock to the load module. So, extract the module
loading code from lwtunnel_build_state into a new function to validate
the encap type. The new function is called while converting the user
request into a fib_config which is well before any table, device or
fib entries are examined.

Fixes: 745041e2aaf1 ("lwtunnel: autoload of lwt modules")
Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 75 insertions, 7 deletions

diff --git a/net/core/lwtunnel.c b/net/core/lwtunnel.c
index a5d4e866ce88..47b1dd65947b 100644
--- a/net/core/lwtunnel.c
+++ b/net/core/lwtunnel.c
@@ -26,6 +26,7 @@
 #include <net/lwtunnel.h>
 #include <net/rtnetlink.h>
 #include <net/ip6_fib.h>
+#include <net/nexthop.h>
 
 #ifdef CONFIG_MODULES
 
@@ -114,25 +115,74 @@ int lwtunnel_build_state(struct net_device *dev, u16 encap_type,
 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
 	ops = rcu_dereference(lwtun_encaps[encap_type]);
+	if (likely(ops && ops->build_state))
+		ret = ops->build_state(dev, encap, family, cfg, lws);
+	rcu_read_unlock();
+
+	return ret;
+}
+EXPORT_SYMBOL(lwtunnel_build_state);
+
+int lwtunnel_valid_encap_type(u16 encap_type)
+{
+	const struct lwtunnel_encap_ops *ops;
+	int ret = -EINVAL;
+
+	if (encap_type == LWTUNNEL_ENCAP_NONE ||
+	    encap_type > LWTUNNEL_ENCAP_MAX)
+		return ret;
+
+	rcu_read_lock();
+	ops = rcu_dereference(lwtun_encaps[encap_type]);
+	rcu_read_unlock();
 #ifdef CONFIG_MODULES
 	if (!ops) {
 		const char *encap_type_str = lwtunnel_encap_str(encap_type);
 
 		if (encap_type_str) {
-			rcu_read_unlock();
+			__rtnl_unlock();
 			request_module("rtnl-lwt-%s", encap_type_str);
+			rtnl_lock();
+
 			rcu_read_lock();
 			ops = rcu_dereference(lwtun_encaps[encap_type]);
+			rcu_read_unlock();
 		}
 	}
 #endif
-	if (likely(ops && ops->build_state))
-		ret = ops->build_state(dev, encap, family, cfg, lws);
-	rcu_read_unlock();
+	return ops ? 0 : -EOPNOTSUPP;
+}
+EXPORT_SYMBOL(lwtunnel_valid_encap_type);
 
-	return ret;
+int lwtunnel_valid_encap_type_attr(struct nlattr *attr, int remaining)
+{
+	struct rtnexthop *rtnh = (struct rtnexthop *)attr;
+	struct nlattr *nla_entype;
+	struct nlattr *attrs;
+	struct nlattr *nla;
+	u16 encap_type;
+	int attrlen;
+
+	while (rtnh_ok(rtnh, remaining)) {
+		attrlen = rtnh_attrlen(rtnh);
+		if (attrlen > 0) {
+			attrs = rtnh_attrs(rtnh);
+			nla = nla_find(attrs, attrlen, RTA_ENCAP);
+			nla_entype = nla_find(attrs, attrlen, RTA_ENCAP_TYPE);
+
+			if (nla_entype) {
+				encap_type = nla_get_u16(nla_entype);
+
+				if (lwtunnel_valid_encap_type(encap_type) != 0)
+					return -EOPNOTSUPP;
+			}
+		}
+		rtnh = rtnh_next(rtnh, &remaining);
+	}
+
+	return 0;
 }
-EXPORT_SYMBOL(lwtunnel_build_state);
+EXPORT_SYMBOL(lwtunnel_valid_encap_type_attr);
 
 void lwtstate_free(struct lwtunnel_state *lws)
 {
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index eae0332b0e8c..7db2ad2e82d3 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -46,6 +46,7 @@
 #include <net/rtnetlink.h>
 #include <net/xfrm.h>
 #include <net/l3mdev.h>
+#include <net/lwtunnel.h>
 #include <trace/events/fib.h>
 
 #ifndef CONFIG_IP_MULTIPLE_TABLES
@@ -677,6 +678,10 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			cfg->fc_mx_len = nla_len(attr);
 			break;
 		case RTA_MULTIPATH:
+			err = lwtunnel_valid_encap_type_attr(nla_data(attr),
+							     nla_len(attr));
+			if (err < 0)
+				goto errout;
 			cfg->fc_mp = nla_data(attr);
 			cfg->fc_mp_len = nla_len(attr);
 			break;
@@ -691,6 +696,9 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
 			break;
 		case RTA_ENCAP_TYPE:
 			cfg->fc_encap_type = nla_get_u16(attr);
+			err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+			if (err < 0)
+				goto errout;
 			break;
 		}
 	}
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4f6b067c8753..7ea85370c11c 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2896,6 +2896,11 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_MULTIPATH]) {
 		cfg->fc_mp = nla_data(tb[RTA_MULTIPATH]);
 		cfg->fc_mp_len = nla_len(tb[RTA_MULTIPATH]);
+
+		err = lwtunnel_valid_encap_type_attr(cfg->fc_mp,
+						     cfg->fc_mp_len);
+		if (err < 0)
+			goto errout;
 	}
 
 	if (tb[RTA_PREF]) {
@@ -2909,9 +2914,14 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
 	if (tb[RTA_ENCAP])
 		cfg->fc_encap = tb[RTA_ENCAP];
 
-	if (tb[RTA_ENCAP_TYPE])
+	if (tb[RTA_ENCAP_TYPE]) {
 		cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]);
 
+		err = lwtunnel_valid_encap_type(cfg->fc_encap_type);
+		if (err < 0)
+			goto errout;
+	}
+
 	if (tb[RTA_EXPIRES]) {
 		unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ);