From 920a46115ca3fa88990276d98520abab85495b2d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sat, 1 Nov 2008 21:22:23 -0700 Subject: udp: multicast packets need to check namespace Current UDP multicast delivery is not namespace aware. Signed-off-by: Eric Dumazet Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- net/ipv6/udp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index e51da8c092f..71e259e866a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -328,7 +328,7 @@ drop: return -1; } -static struct sock *udp_v6_mcast_next(struct sock *sk, +static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, __be16 loc_port, struct in6_addr *loc_addr, __be16 rmt_port, struct in6_addr *rmt_addr, int dif) @@ -340,7 +340,7 @@ static struct sock *udp_v6_mcast_next(struct sock *sk, sk_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); - if (sock_net(s) != sock_net(sk)) + if (!net_eq(sock_net(s), net)) continue; if (s->sk_hash == num && s->sk_family == PF_INET6) { @@ -383,14 +383,14 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, read_lock(&udp_hash_lock); sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]); dif = inet6_iif(skb); - sk = udp_v6_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); + sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); if (!sk) { kfree_skb(skb); goto out; } sk2 = sk; - while ((sk2 = udp_v6_mcast_next(sk_next(sk2), uh->dest, daddr, + while ((sk2 = udp_v6_mcast_next(net, sk_next(sk2), uh->dest, daddr, uh->source, saddr, dif))) { struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); if (buff) { -- cgit v1.2.3 From f26ba1751145edbf52b2c89a40e389f2fbdfc1af Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 2 Nov 2008 16:11:01 +0000 Subject: udp: Fix the SNMP counter of UDP_MIB_INDATAGRAMS If UDP echo is sent to xinetd/echo-dgram, the UDP reply will be received at the sender. But the SNMP counter of UDP_MIB_INDATAGRAMS will be not increased, UDP6_MIB_INDATAGRAMS will be increased instead. Endpoint A Endpoint B UDP Echo request -----------> (IPv4, Dst port=7) <---------- UDP Echo Reply (IPv4, Src port=7) This bug is come from this patch cb75994ec311b2cd50e5205efdcc0696abd6675d. It do counter UDP[6]_MIB_INDATAGRAMS until udp[v6]_recvmsg. Because xinetd used IPv6 socket to receive UDP messages, thus, when received UDP packet, the UDP6_MIB_INDATAGRAMS will be increased in function udpv6_recvmsg() even if the packet is a IPv4 UDP packet. This patch fixed the problem. Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- net/ipv6/udp.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 71e259e866a..18696af106d 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -138,6 +138,7 @@ int udpv6_recvmsg(struct kiocb *iocb, struct sock *sk, int peeked; int err; int is_udplite = IS_UDPLITE(sk); + int is_udp4; if (addr_len) *addr_len=sizeof(struct sockaddr_in6); @@ -158,6 +159,8 @@ try_again: else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; + is_udp4 = (skb->protocol == htons(ETH_P_IP)); + /* * If checksum is needed at all, try to do it while copying the * data. If the data is truncated, or if we only want a partial @@ -180,9 +183,14 @@ try_again: if (err) goto out_free; - if (!peeked) - UDP6_INC_STATS_USER(sock_net(sk), - UDP_MIB_INDATAGRAMS, is_udplite); + if (!peeked) { + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); + } sock_recv_timestamp(msg, sk, skb); @@ -196,7 +204,7 @@ try_again: sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; - if (skb->protocol == htons(ETH_P_IP)) + if (is_udp4) ipv6_addr_set(&sin6->sin6_addr, 0, 0, htonl(0xffff), ip_hdr(skb)->saddr); else { @@ -207,7 +215,7 @@ try_again: } } - if (skb->protocol == htons(ETH_P_IP)) { + if (is_udp4) { if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } else { -- cgit v1.2.3 From 0856f93958c488f0cc656be53c26dfd20663bdb3 Mon Sep 17 00:00:00 2001 From: Wei Yongjun Date: Sun, 2 Nov 2008 16:14:27 +0000 Subject: udp: Fix the SNMP counter of UDP_MIB_INERRORS UDP packets received in udpv6_recvmsg() are not only IPv6 UDP packets, but also have IPv4 UDP packets, so when do the counter of UDP_MIB_INERRORS in udpv6_recvmsg(), we should check whether the packet is a IPv6 UDP packet or a IPv4 UDP packet. Signed-off-by: Wei Yongjun Signed-off-by: David S. Miller --- net/ipv6/udp.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 18696af106d..8b48512ebf6 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -236,8 +236,14 @@ out: csum_copy_err: lock_sock(sk); - if (!skb_kill_datagram(sk, skb, flags)) - UDP6_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + if (!skb_kill_datagram(sk, skb, flags)) { + if (is_udp4) + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + else + UDP6_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + } release_sock(sk); if (flags & MSG_DONTWAIT) -- cgit v1.2.3 From 79654a7698195fa043063092f5c1ca5245276fba Mon Sep 17 00:00:00 2001 From: Andreas Steffen Date: Tue, 4 Nov 2008 14:49:19 -0800 Subject: xfrm: Have af-specific init_tempsel() initialize family field of temporary selector While adding MIGRATE support to strongSwan, Andreas Steffen noticed that the selectors provided in XFRM_MSG_ACQUIRE have their family field uninitialized (those in MIGRATE do have their family set). Looking at the code, this is because the af-specific init_tempsel() (called via afinfo->init_tempsel() in xfrm_init_tempsel()) do not set the value. Reported-by: Andreas Steffen Acked-by: Herbert Xu Signed-off-by: Arnaud Ebalard --- net/ipv6/xfrm6_state.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/ipv6') diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 89884a4f23a..60c78cfc273 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -34,6 +34,7 @@ __xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, x->sel.dport_mask = htons(0xffff); x->sel.sport = xfrm_flowi_sport(fl); x->sel.sport_mask = htons(0xffff); + x->sel.family = AF_INET6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->sel.proto = fl->proto; -- cgit v1.2.3 From e3ec6cfc260e2322834e200c2fa349cdf104fd13 Mon Sep 17 00:00:00 2001 From: Benjamin Thery Date: Wed, 5 Nov 2008 01:43:57 -0800 Subject: ipv6: fix run pending DAD when interface becomes ready With some net devices types, an IPv6 address configured while the interface was down can stay 'tentative' forever, even after the interface is set up. In some case, pending IPv6 DADs are not executed when the device becomes ready. I observed this while doing some tests with kvm. If I assign an IPv6 address to my interface eth0 (kvm driver rtl8139) when it is still down then the address is flagged tentative (IFA_F_TENTATIVE). Then, I set eth0 up, and to my surprise, the address stays 'tentative', no DAD is executed and the address can't be pinged. I also observed the same behaviour, without kvm, with virtual interfaces types macvlan and veth. Some easy steps to reproduce the issue with macvlan: 1. ip link add link eth0 type macvlan 2. ip -6 addr add 2003::ab32/64 dev macvlan0 3. ip addr show dev macvlan0 ... inet6 2003::ab32/64 scope global tentative ... 4. ip link set macvlan0 up 5. ip addr show dev macvlan0 ... inet6 2003::ab32/64 scope global tentative ... Address is still tentative I think there's a bug in net/ipv6/addrconf.c, addrconf_notify(): addrconf_dad_run() is not always run when the interface is flagged IF_READY. Currently it is only run when receiving NETDEV_CHANGE event. Looks like some (virtual) devices doesn't send this event when becoming up. For both NETDEV_UP and NETDEV_CHANGE events, when the interface becomes ready, run_pending should be set to 1. Patch below. 'run_pending = 1' could be moved below the if/else block but it makes the code less readable. Signed-off-by: Benjamin Thery Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index eea9542728c..d9da5eb9dcb 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -2483,8 +2483,10 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (!idev && dev->mtu >= IPV6_MIN_MTU) idev = ipv6_add_dev(dev); - if (idev) + if (idev) { idev->if_flags |= IF_READY; + run_pending = 1; + } } else { if (!addrconf_qdisc_ok(dev)) { /* device is still not ready. */ -- cgit v1.2.3