From 70789d7052239992824628db8133de08dc78e593 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 3 Sep 2010 05:13:05 +0000 Subject: ipv6: discard overlapping fragment RFC5722 prohibits reassembling fragments when some data overlaps. Bug spotted by Zhang Zuotao . Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/reassembly.c | 71 +++++++++++---------------------------------------- 1 file changed, 15 insertions(+), 56 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 545c414..64cfef1 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -149,13 +149,6 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a) } EXPORT_SYMBOL(ip6_frag_match); -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf->mem); - kfree_skb(skb); -} - void ip6_frag_init(struct inet_frag_queue *q, void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); @@ -346,58 +339,22 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, } found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. + /* RFC5722, Section 4: + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments, including those not yet received) MUST be silently + * discarded. */ - if (prev) { - int i = (FRAG6_CB(prev)->offset + prev->len) - offset; - if (i > 0) { - offset += i; - if (end <= offset) - goto err; - if (!pskb_pull(skb, i)) - goto err; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } + /* Check for overlap with preceding fragment. */ + if (prev && + (FRAG6_CB(prev)->offset + prev->len) - offset > 0) + goto discard_fq; - /* Look for overlap with succeeding segments. - * If we can merge fragments, do it. - */ - while (next && FRAG6_CB(next)->offset < end) { - int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */ - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - if (!pskb_pull(next, i)) - goto err; - FRAG6_CB(next)->offset += i; /* next fragment */ - fq->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragment is completely overridden with - * new one drop it. - */ - next = next->next; - - if (prev) - prev->next = next; - else - fq->q.fragments = next; - - fq->q.meat -= free_it->len; - frag_kfree_skb(fq->q.net, free_it); - } - } + /* Look for overlap with succeeding segment. */ + if (next && FRAG6_CB(next)->offset < end) + goto discard_fq; FRAG6_CB(skb)->offset = offset; @@ -436,6 +393,8 @@ found: write_unlock(&ip6_frags.lock); return -1; +discard_fq: + fq_kill(fq); err: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); -- cgit v1.1 From 1ee89bd0fe72e381c8e4ef887d53c19c8adc6c93 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Fri, 3 Sep 2010 05:13:07 +0000 Subject: netfilter: discard overlapping IPv6 fragment RFC5722 prohibits reassembling IPv6 fragments when some data overlaps. Bug spotted by Zhang Zuotao . Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- net/ipv6/netfilter/nf_conntrack_reasm.c | 80 +++++++-------------------------- 1 file changed, 15 insertions(+), 65 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 13ef5bc..578f3c1 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb) kfree_skb(NFCT_FRAG6_CB(skb)->orig); } -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf_init_frags.mem); - nf_skb_free(skb); - kfree_skb(skb); -} - /* Destruction primitives. */ static __inline__ void fq_put(struct nf_ct_frag6_queue *fq) @@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, } found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. - */ - if (prev) { - int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset; - - if (i > 0) { - offset += i; - if (end <= offset) { - pr_debug("overlap\n"); - goto err; - } - if (!pskb_pull(skb, i)) { - pr_debug("Can't pull\n"); - goto err; - } - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } - - /* Look for overlap with succeeding segments. - * If we can merge fragments, do it. + /* RFC5722, Section 4: + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments, including those not yet received) MUST be silently + * discarded. */ - while (next && NFCT_FRAG6_CB(next)->offset < end) { - /* overlap is 'i' bytes */ - int i = end - NFCT_FRAG6_CB(next)->offset; - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - pr_debug("Eat head of the overlapped parts.: %d", i); - if (!pskb_pull(next, i)) - goto err; - /* next fragment */ - NFCT_FRAG6_CB(next)->offset += i; - fq->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragmnet is completely overridden with - * new one drop it. - */ - next = next->next; + /* Check for overlap with preceding fragment. */ + if (prev && + (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0) + goto discard_fq; - if (prev) - prev->next = next; - else - fq->q.fragments = next; - - fq->q.meat -= free_it->len; - frag_kfree_skb(free_it); - } - } + /* Look for overlap with succeeding segment. */ + if (next && NFCT_FRAG6_CB(next)->offset < end) + goto discard_fq; NFCT_FRAG6_CB(skb)->offset = offset; @@ -371,6 +319,8 @@ found: write_unlock(&nf_frags.lock); return 0; +discard_fq: + fq_kill(fq); err: return -1; } -- cgit v1.1 From 719f835853a92f6090258114a72ffe41f09155cd Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Wed, 8 Sep 2010 05:08:44 +0000 Subject: udp: add rehash on connect() commit 30fff923 introduced in linux-2.6.33 (udp: bind() optimisation) added a secondary hash on UDP, hashed on (local addr, local port). Problem is that following sequence : fd = socket(...) connect(fd, &remote, ...) not only selects remote end point (address and port), but also sets local address, while UDP stack stored in secondary hash table the socket while its local address was INADDR_ANY (or ipv6 equivalent) Sequence is : - autobind() : choose a random local port, insert socket in hash tables [while local address is INADDR_ANY] - connect() : set remote address and port, change local address to IP given by a route lookup. When an incoming UDP frame comes, if more than 10 sockets are found in primary hash table, we switch to secondary table, and fail to find socket because its local address changed. One solution to this problem is to rehash datagram socket if needed. We add a new rehash(struct socket *) method in "struct proto", and implement this method for UDP v4 & v6, using a common helper. This rehashing only takes care of secondary hash table, since primary hash (based on local port only) is not changed. Reported-by: Krzysztof Piotr Oledzki Signed-off-by: Eric Dumazet Tested-by: Krzysztof Piotr Oledzki Signed-off-by: David S. Miller --- net/ipv6/datagram.c | 7 ++++++- net/ipv6/udp.c | 10 ++++++++++ 2 files changed, 16 insertions(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 7d929a2..ef371aa 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -105,9 +105,12 @@ ipv4_connected: if (ipv6_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } goto out; } @@ -181,6 +184,8 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); inet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1dd1aff..5acb356 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } +static void udp_v6_rehash(struct sock *sk) +{ + u16 new_hash = udp6_portaddr_hash(sock_net(sk), + &inet6_sk(sk)->rcv_saddr, + inet_sk(sk)->inet_num); + + udp_lib_rehash(sk, new_hash); +} + static inline int compute_score(struct sock *sk, struct net *net, unsigned short hnum, struct in6_addr *saddr, __be16 sport, @@ -1447,6 +1456,7 @@ struct proto udpv6_prot = { .backlog_rcv = udpv6_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, -- cgit v1.1 From 8444cf712c5f71845cba9dc30d8f530ff0d5ff83 Mon Sep 17 00:00:00 2001 From: Thomas Egerer Date: Mon, 20 Sep 2010 11:11:38 -0700 Subject: xfrm: Allow different selector family in temporary state The family parameter xfrm_state_find is used to find a state matching a certain policy. This value is set to the template's family (encap_family) right before xfrm_state_find is called. The family parameter is however also used to construct a temporary state in xfrm_state_find itself which is wrong for inter-family scenarios because it produces a selector for the wrong family. Since this selector is included in the xfrm_user_acquire structure, user space programs misinterpret IPv6 addresses as IPv4 and vice versa. This patch splits up the original init_tempsel function into a part that initializes the selector respectively the props and id of the temporary state, to allow for differing ip address families whithin the state. Signed-off-by: Thomas Egerer Signed-off-by: Steffen Klassert Signed-off-by: David S. Miller --- net/ipv6/xfrm6_state.c | 33 +++++++++++++++++++-------------- 1 file changed, 19 insertions(+), 14 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index f417b77..a67575d 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -20,23 +20,27 @@ #include static void -__xfrm6_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) { /* Initialize temporary selector matching only * to current session. */ - ipv6_addr_copy((struct in6_addr *)&x->sel.daddr, &fl->fl6_dst); - ipv6_addr_copy((struct in6_addr *)&x->sel.saddr, &fl->fl6_src); - x->sel.dport = xfrm_flowi_dport(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; - x->sel.ifindex = fl->oif; + ipv6_addr_copy((struct in6_addr *)&sel->daddr, &fl->fl6_dst); + ipv6_addr_copy((struct in6_addr *)&sel->saddr, &fl->fl6_src); + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET6; + sel->prefixlen_d = 128; + sel->prefixlen_s = 128; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) +{ x->id = tmpl->id; if (ipv6_addr_any((struct in6_addr*)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); @@ -168,6 +172,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .eth_proto = htons(ETH_P_IPV6), .owner = THIS_MODULE, .init_tempsel = __xfrm6_init_tempsel, + .init_temprop = xfrm6_init_temprop, .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, -- cgit v1.1 From 3d13008e7345fa7a79d8f6438150dc15d6ba6e9d Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 21 Sep 2010 08:47:45 +0000 Subject: ip: fix truesize mismatch in ip fragmentation Special care should be taken when slow path is hit in ip_fragment() : When walking through frags, we transfert truesize ownership from skb to frags. Then if we hit a slow_path condition, we must undo this or risk uncharging frags->truesize twice, and in the end, having negative socket sk_wmem_alloc counter, or even freeing socket sooner than expected. Many thanks to Nick Bowler, who provided a very clean bug report and test program. Thanks to Jarek for reviewing my first patch and providing a V2 While Nick bisection pointed to commit 2b85a34e911 (net: No more expensive sock_hold()/sock_put() on each tx), underlying bug is older (2.6.12-rc5) A side effect is to extend work done in commit b2722b1c3a893e (ip_fragment: also adjust skb->truesize for packets not owned by a socket) to ipv6 as well. Reported-and-bisected-by: Nick Bowler Tested-by: Nick Bowler Signed-off-by: Eric Dumazet CC: Jarek Poplawski CC: Patrick McHardy Signed-off-by: David S. Miller --- net/ipv6/ip6_output.c | 18 +++++++++++++----- 1 file changed, 13 insertions(+), 5 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index d40b330..980912e 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -639,7 +639,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (skb_has_frags(skb)) { int first_len = skb_pagelen(skb); - int truesizes = 0; + struct sk_buff *frag2; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -651,18 +651,18 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; - truesizes += frag->truesize; } + skb->truesize -= frag->truesize; } err = 0; @@ -693,7 +693,6 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) first_len = skb_pagelen(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; ipv6_hdr(skb)->payload_len = htons(first_len - sizeof(struct ipv6hdr)); @@ -756,6 +755,15 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) IPSTATS_MIB_FRAGFAILS); dst_release(&rt->dst); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: -- cgit v1.1 From 2cc6d2bf3d6195fabcf0febc192c01f99519a8f3 Mon Sep 17 00:00:00 2001 From: Neil Horman Date: Fri, 24 Sep 2010 09:55:52 +0000 Subject: ipv6: add a missing unregister_pernet_subsys call Clean up a missing exit path in the ipv6 module init routines. In addrconf_init we call ipv6_addr_label_init which calls register_pernet_subsys for the ipv6_addr_label_ops structure. But if module loading fails, or if the ipv6 module is removed, there is no corresponding unregister_pernet_subsys call, which leaves a now-bogus address on the pernet_list, leading to oopses in subsequent registrations. This patch cleans up both the failed load path and the unload path. Tested by myself with good results. Signed-off-by: Neil Horman include/net/addrconf.h | 1 + net/ipv6/addrconf.c | 11 ++++++++--- net/ipv6/addrlabel.c | 5 +++++ 3 files changed, 14 insertions(+), 3 deletions(-) Signed-off-by: David S. Miller --- net/ipv6/addrconf.c | 11 ++++++++--- net/ipv6/addrlabel.c | 5 +++++ 2 files changed, 13 insertions(+), 3 deletions(-) (limited to 'net/ipv6') diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index ab70a3f..324fac3 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -4637,10 +4637,12 @@ int __init addrconf_init(void) if (err < 0) { printk(KERN_CRIT "IPv6 Addrconf:" " cannot initialize default policy table: %d.\n", err); - return err; + goto out; } - register_pernet_subsys(&addrconf_ops); + err = register_pernet_subsys(&addrconf_ops); + if (err < 0) + goto out_addrlabel; /* The addrconf netdev notifier requires that loopback_dev * has it's ipv6 private information allocated and setup @@ -4692,7 +4694,9 @@ errout: unregister_netdevice_notifier(&ipv6_dev_notf); errlo: unregister_pernet_subsys(&addrconf_ops); - +out_addrlabel: + ipv6_addr_label_cleanup(); +out: return err; } @@ -4703,6 +4707,7 @@ void addrconf_cleanup(void) unregister_netdevice_notifier(&ipv6_dev_notf); unregister_pernet_subsys(&addrconf_ops); + ipv6_addr_label_cleanup(); rtnl_lock(); diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index f0e774c..8175f80 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -393,6 +393,11 @@ int __init ipv6_addr_label_init(void) return register_pernet_subsys(&ipv6_addr_label_ops); } +void ipv6_addr_label_cleanup(void) +{ + unregister_pernet_subsys(&ipv6_addr_label_ops); +} + static const struct nla_policy ifal_policy[IFAL_MAX+1] = { [IFAL_ADDRESS] = { .len = sizeof(struct in6_addr), }, [IFAL_LABEL] = { .len = sizeof(u32), }, -- cgit v1.1 From 7e1b33e5ea392dfc984fc63b76ca75acbf249dcd Mon Sep 17 00:00:00 2001 From: Ulrich Weber Date: Mon, 27 Sep 2010 15:02:18 -0700 Subject: ipv6: add IPv6 to neighbour table overflow warning IPv4 and IPv6 have separate neighbour tables, so the warning messages should be distinguishable. [ Add a suitable message prefix on the ipv4 side as well -DaveM ] Signed-off-by: Ulrich Weber Signed-off-by: David S. Miller --- net/ipv6/route.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv6') diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d126365..8323136 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -670,7 +670,7 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *dad if (net_ratelimit()) printk(KERN_WARNING - "Neighbour table overflow.\n"); + "ipv6: Neighbour table overflow.\n"); dst_free(&rt->dst); return NULL; } -- cgit v1.1