aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv6
diff options
context:
space:
mode:
authorMartin KaFai Lau <kafai@fb.com>2016-04-11 15:29:36 -0700
committerDavid S. Miller <davem@davemloft.net>2016-04-14 16:29:51 -0400
commit33c162a980fe03498fcecb917f618ad7e7c55e61 (patch)
treeb03155a858c516ef9be8770de7987bc652094b97 /net/ipv6
parentipv6: datagram: Refactor dst lookup and update codes to a new function (diff)
downloadlinux-dev-33c162a980fe03498fcecb917f618ad7e7c55e61.tar.xz
linux-dev-33c162a980fe03498fcecb917f618ad7e7c55e61.zip
ipv6: datagram: Update dst cache of a connected datagram sk during pmtu update
There is a case in connected UDP socket such that getsockopt(IPV6_MTU) will return a stale MTU value. The reproducible sequence could be the following: 1. Create a connected UDP socket 2. Send some datagrams out 3. Receive a ICMPV6_PKT_TOOBIG 4. No new outgoing datagrams to trigger the sk_dst_check() logic to update the sk->sk_dst_cache. 5. getsockopt(IPV6_MTU) returns the mtu from the invalid sk->sk_dst_cache instead of the newly created RTF_CACHE clone. This patch updates the sk->sk_dst_cache for a connected datagram sk during pmtu-update code path. Note that the sk->sk_v6_daddr is used to do the route lookup instead of skb->data (i.e. iph). It is because a UDP socket can become connected after sending out some datagrams in un-connected state. or It can be connected multiple times to different destinations. Hence, iph may not be related to where sk is currently connected to. It is done under '!sock_owned_by_user(sk)' condition because the user may make another ip6_datagram_connect() (i.e changing the sk->sk_v6_daddr) while dst lookup is happening in the pmtu-update code path. For the sock_owned_by_user(sk) == true case, the next patch will introduce a release_cb() which will update the sk->sk_dst_cache. Test: Server (Connected UDP Socket): ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ Route Details: [root@arch-fb-vm1 ~]# ip -6 r show | egrep '2fac' 2fac::/64 dev eth0 proto kernel metric 256 pref medium 2fac:face::/64 via 2fac::face dev eth0 metric 1024 pref medium A simple python code to create a connected UDP socket: import socket import errno HOST = '2fac::1' PORT = 8080 s = socket.socket(socket.AF_INET6, socket.SOCK_DGRAM) s.bind((HOST, PORT)) s.connect(('2fac:face::face', 53)) print("connected") while True: try: data = s.recv(1024) except socket.error as se: if se.errno == errno.EMSGSIZE: pmtu = s.getsockopt(41, 24) print("PMTU:%d" % pmtu) break s.close() Python program output after getting a ICMPV6_PKT_TOOBIG: [root@arch-fb-vm1 ~]# python2 ~/devshare/kernel/tasks/fib6/udp-connect-53-8080.py connected PMTU:1300 Cache routes after recieving TOOBIG: [root@arch-fb-vm1 ~]# ip -6 r show table cache 2fac:face::face via 2fac::face dev eth0 metric 0 cache expires 463sec mtu 1300 pref medium Client (Send the ICMPV6_PKT_TOOBIG): ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ scapy is used to generate the TOOBIG message. Here is the scapy script I have used: >>> p=Ether(src='da:75:4d:36:ac:32', dst='52:54:00:12:34:66', type=0x86dd)/IPv6(src='2fac::face', dst='2fac::1')/ICMPv6PacketTooBig(mtu=1300)/IPv6(src='2fac:: 1',dst='2fac:face::face', nh='UDP')/UDP(sport=8080,dport=53) >>> sendp(p, iface='qemubr0') Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception") Signed-off-by: Martin KaFai Lau <kafai@fb.com> Reported-by: Wei Wang <weiwan@google.com> Cc: Cong Wang <xiyou.wangcong@gmail.com> Cc: Eric Dumazet <edumazet@google.com> Cc: Wei Wang <weiwan@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/datagram.c20
-rw-r--r--net/ipv6/route.c12
2 files changed, 23 insertions, 9 deletions
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 669585e11294..59e01f27db9f 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -64,7 +64,7 @@ static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk)
security_sk_classify_flow(sk, flowi6_to_flowi(fl6));
}
-static int ip6_datagram_dst_update(struct sock *sk)
+int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr)
{
struct ip6_flowlabel *flowlabel = NULL;
struct in6_addr *final_p, final;
@@ -93,14 +93,16 @@ static int ip6_datagram_dst_update(struct sock *sk)
goto out;
}
- if (ipv6_addr_any(&np->saddr))
- np->saddr = fl6.saddr;
+ if (fix_sk_saddr) {
+ if (ipv6_addr_any(&np->saddr))
+ np->saddr = fl6.saddr;
- if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
- sk->sk_v6_rcv_saddr = fl6.saddr;
- inet->inet_rcv_saddr = LOOPBACK4_IPV6;
- if (sk->sk_prot->rehash)
- sk->sk_prot->rehash(sk);
+ if (ipv6_addr_any(&sk->sk_v6_rcv_saddr)) {
+ sk->sk_v6_rcv_saddr = fl6.saddr;
+ inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
+ }
}
ip6_dst_store(sk, dst,
@@ -221,7 +223,7 @@ ipv4_connected:
* destination cache for it.
*/
- err = ip6_datagram_dst_update(sk);
+ err = ip6_datagram_dst_update(sk, true);
if (err)
goto out;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 1d8871a5ed20..d916d6ab9ad2 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1418,8 +1418,20 @@ EXPORT_SYMBOL_GPL(ip6_update_pmtu);
void ip6_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, __be32 mtu)
{
+ struct dst_entry *dst;
+
ip6_update_pmtu(skb, sock_net(sk), mtu,
sk->sk_bound_dev_if, sk->sk_mark);
+
+ dst = __sk_dst_get(sk);
+ if (!dst || !dst->obsolete ||
+ dst->ops->check(dst, inet6_sk(sk)->dst_cookie))
+ return;
+
+ bh_lock_sock(sk);
+ if (!sock_owned_by_user(sk) && !ipv6_addr_v4mapped(&sk->sk_v6_daddr))
+ ip6_datagram_dst_update(sk, false);
+ bh_unlock_sock(sk);
}
EXPORT_SYMBOL_GPL(ip6_sk_update_pmtu);