From 80fbdb208f37740774652ba095a5b2045205ed59 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 11 Apr 2016 15:29:34 -0700 Subject: ipv6: datagram: Refactor flowi6 init codes to a new function Move flowi6 init codes for connected datagram sk to a newly created function ip6_datagram_flow_key_init(). Notes: 1. fl6_flowlabel is used instead of fl6.flowlabel in __ip6_datagram_connect 2. ipv6_addr_is_multicast(&fl6->daddr) is used instead of (addr_type & IPV6_ADDR_MULTICAST) in ip6_datagram_flow_key_init() This new function will be reused during pmtu update in the later patch. Signed-off-by: Martin KaFai Lau Cc: Cong Wang Cc: Eric Dumazet Cc: Wei Wang Signed-off-by: David S. Miller --- net/ipv6/datagram.c | 50 ++++++++++++++++++++++++++++++-------------------- 1 file changed, 30 insertions(+), 20 deletions(-) (limited to 'net/ipv6/datagram.c') diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 428162155280..f07c1ddb5cac 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -40,6 +40,30 @@ static bool ipv6_mapped_addr_any(const struct in6_addr *a) return ipv6_addr_v4mapped(a) && (a->s6_addr32[3] == 0); } +static void ip6_datagram_flow_key_init(struct flowi6 *fl6, struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + + memset(fl6, 0, sizeof(*fl6)); + fl6->flowi6_proto = sk->sk_protocol; + fl6->daddr = sk->sk_v6_daddr; + fl6->saddr = np->saddr; + fl6->flowi6_oif = sk->sk_bound_dev_if; + fl6->flowi6_mark = sk->sk_mark; + fl6->fl6_dport = inet->inet_dport; + fl6->fl6_sport = inet->inet_sport; + fl6->flowlabel = np->flow_label; + + if (!fl6->flowi6_oif) + fl6->flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; + + if (!fl6->flowi6_oif && ipv6_addr_is_multicast(&fl6->daddr)) + fl6->flowi6_oif = np->mcast_oif; + + security_sk_classify_flow(sk, flowi6_to_flowi(fl6)); +} + static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; @@ -52,6 +76,7 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a struct ipv6_txoptions *opt; int addr_type; int err; + __be32 fl6_flowlabel = 0; if (usin->sin6_family == AF_INET) { if (__ipv6_only_sock(sk)) @@ -66,11 +91,10 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; - memset(&fl6, 0, sizeof(fl6)); if (np->sndflow) { - fl6.flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK; - if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); + fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; + if (fl6_flowlabel & IPV6_FLOWLABEL_MASK) { + flowlabel = fl6_sock_lookup(sk, fl6_flowlabel); if (!flowlabel) return -EINVAL; } @@ -145,7 +169,7 @@ ipv4_connected: } sk->sk_v6_daddr = *daddr; - np->flow_label = fl6.flowlabel; + np->flow_label = fl6_flowlabel; inet->inet_dport = usin->sin6_port; @@ -154,21 +178,7 @@ ipv4_connected: * destination cache for it. */ - fl6.flowi6_proto = sk->sk_protocol; - fl6.daddr = sk->sk_v6_daddr; - fl6.saddr = np->saddr; - fl6.flowi6_oif = sk->sk_bound_dev_if; - fl6.flowi6_mark = sk->sk_mark; - fl6.fl6_dport = inet->inet_dport; - fl6.fl6_sport = inet->inet_sport; - - if (!fl6.flowi6_oif) - fl6.flowi6_oif = np->sticky_pktinfo.ipi6_ifindex; - - if (!fl6.flowi6_oif && (addr_type&IPV6_ADDR_MULTICAST)) - fl6.flowi6_oif = np->mcast_oif; - - security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); + ip6_datagram_flow_key_init(&fl6, sk); rcu_read_lock(); opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); -- cgit v1.2.3-59-g8ed1b From 7e2040db1539a904924b997a14ebd3de53172100 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 11 Apr 2016 15:29:35 -0700 Subject: ipv6: datagram: Refactor dst lookup and update codes to a new function This patch moves the route lookup and update codes for connected datagram sk to a newly created function ip6_datagram_dst_update() It will be reused during the pmtu update in the later patch. Signed-off-by: Martin KaFai Lau Cc: Cong Wang Cc: Eric Dumazet Cc: Wei Wang Signed-off-by: David S. Miller --- net/ipv6/datagram.c | 103 +++++++++++++++++++++++++++++----------------------- 1 file changed, 57 insertions(+), 46 deletions(-) (limited to 'net/ipv6/datagram.c') diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index f07c1ddb5cac..669585e11294 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -64,16 +64,65 @@ 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) +{ + struct ip6_flowlabel *flowlabel = NULL; + struct in6_addr *final_p, final; + struct ipv6_txoptions *opt; + struct dst_entry *dst; + struct inet_sock *inet = inet_sk(sk); + struct ipv6_pinfo *np = inet6_sk(sk); + struct flowi6 fl6; + int err = 0; + + if (np->sndflow && (np->flow_label & IPV6_FLOWLABEL_MASK)) { + flowlabel = fl6_sock_lookup(sk, np->flow_label); + if (!flowlabel) + return -EINVAL; + } + ip6_datagram_flow_key_init(&fl6, sk); + + rcu_read_lock(); + opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); + final_p = fl6_update_dst(&fl6, opt, &final); + rcu_read_unlock(); + + dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + if (IS_ERR(dst)) { + err = PTR_ERR(dst); + goto out; + } + + 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); + } + + ip6_dst_store(sk, dst, + ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? + &sk->sk_v6_daddr : NULL, +#ifdef CONFIG_IPV6_SUBTREES + ipv6_addr_equal(&fl6.saddr, &np->saddr) ? + &np->saddr : +#endif + NULL); + +out: + fl6_sock_release(flowlabel); + return err; +} + static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); - struct in6_addr *daddr, *final_p, final; - struct dst_entry *dst; - struct flowi6 fl6; - struct ip6_flowlabel *flowlabel = NULL; - struct ipv6_txoptions *opt; + struct in6_addr *daddr; int addr_type; int err; __be32 fl6_flowlabel = 0; @@ -91,14 +140,8 @@ static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int a if (usin->sin6_family != AF_INET6) return -EAFNOSUPPORT; - if (np->sndflow) { + if (np->sndflow) fl6_flowlabel = usin->sin6_flowinfo & IPV6_FLOWINFO_MASK; - if (fl6_flowlabel & IPV6_FLOWLABEL_MASK) { - flowlabel = fl6_sock_lookup(sk, fl6_flowlabel); - if (!flowlabel) - return -EINVAL; - } - } addr_type = ipv6_addr_type(&usin->sin6_addr); @@ -178,45 +221,13 @@ ipv4_connected: * destination cache for it. */ - ip6_datagram_flow_key_init(&fl6, sk); - - rcu_read_lock(); - opt = flowlabel ? flowlabel->opt : rcu_dereference(np->opt); - final_p = fl6_update_dst(&fl6, opt, &final); - rcu_read_unlock(); - - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); - err = 0; - if (IS_ERR(dst)) { - err = PTR_ERR(dst); + err = ip6_datagram_dst_update(sk); + if (err) goto out; - } - - /* source address lookup done in ip6_dst_lookup */ - - 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); - } - - ip6_dst_store(sk, dst, - ipv6_addr_equal(&fl6.daddr, &sk->sk_v6_daddr) ? - &sk->sk_v6_daddr : NULL, -#ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_equal(&fl6.saddr, &np->saddr) ? - &np->saddr : -#endif - NULL); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); out: - fl6_sock_release(flowlabel); return err; } -- cgit v1.2.3-59-g8ed1b From 33c162a980fe03498fcecb917f618ad7e7c55e61 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 11 Apr 2016 15:29:36 -0700 Subject: 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 Reported-by: Wei Wang Cc: Cong Wang Cc: Eric Dumazet Cc: Wei Wang Signed-off-by: David S. Miller --- include/net/ipv6.h | 1 + net/ipv6/datagram.c | 20 +++++++++++--------- net/ipv6/route.c | 12 ++++++++++++ 3 files changed, 24 insertions(+), 9 deletions(-) (limited to 'net/ipv6/datagram.c') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index d0aeb97aec5d..fd02e90b1289 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -959,6 +959,7 @@ int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); +int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); 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); -- cgit v1.2.3-59-g8ed1b From e646b657f6983017783914a951039e323120dc55 Mon Sep 17 00:00:00 2001 From: Martin KaFai Lau Date: Mon, 11 Apr 2016 15:29:37 -0700 Subject: ipv6: udp: Do a route lookup and update during release_cb This patch adds a release_cb for UDPv6. It does a route lookup and updates sk->sk_dst_cache if it is needed. It picks up the left-over job from ip6_sk_update_pmtu() if the sk was owned by user during the pmtu update. It takes a rcu_read_lock to protect the __sk_dst_get() operations because another thread may do ip6_dst_store() without taking the sk lock (e.g. sendmsg). Fixes: 45e4fd26683c ("ipv6: Only create RTF_CACHE routes after encountering pmtu exception") Signed-off-by: Martin KaFai Lau Reported-by: Wei Wang Cc: Cong Wang Cc: Eric Dumazet Cc: Wei Wang Signed-off-by: David S. Miller --- include/net/ipv6.h | 1 + net/ipv6/datagram.c | 20 ++++++++++++++++++++ net/ipv6/udp.c | 1 + 3 files changed, 22 insertions(+) (limited to 'net/ipv6/datagram.c') diff --git a/include/net/ipv6.h b/include/net/ipv6.h index fd02e90b1289..1be050ada8c5 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -960,6 +960,7 @@ int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); +void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 59e01f27db9f..9dd3882fe6bf 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -119,6 +119,26 @@ out: return err; } +void ip6_datagram_release_cb(struct sock *sk) +{ + struct dst_entry *dst; + + if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) + return; + + rcu_read_lock(); + dst = __sk_dst_get(sk); + if (!dst || !dst->obsolete || + dst->ops->check(dst, inet6_sk(sk)->dst_cookie)) { + rcu_read_unlock(); + return; + } + rcu_read_unlock(); + + ip6_datagram_dst_update(sk, false); +} +EXPORT_SYMBOL_GPL(ip6_datagram_release_cb); + static int __ip6_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr; diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 8125931106be..6bc5c664fa46 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1539,6 +1539,7 @@ struct proto udpv6_prot = { .sendmsg = udpv6_sendmsg, .recvmsg = udpv6_recvmsg, .backlog_rcv = __udpv6_queue_rcv_skb, + .release_cb = ip6_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v6_rehash, -- cgit v1.2.3-59-g8ed1b