From 3a7b21eaf4fb3c971bdb47a98f570550ddfe4471 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Fri, 5 Apr 2013 08:13:30 +0000 Subject: [PATCH 1/4] netfilter: nf_ct_sip: don't drop packets with offsets pointing outside the packet Some Cisco phones create huge messages that are spread over multiple packets. After calculating the offset of the SIP body, it is validated to be within the packet and the packet is dropped otherwise. This breaks operation of these phones. Since connection tracking is supposed to be passive, just let those packets pass unmodified and untracked. Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_conntrack_sip.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 0e7d423324c3..e0c4373b4747 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1593,10 +1593,8 @@ static int sip_help_tcp(struct sk_buff *skb, unsigned int protoff, end += strlen("\r\n\r\n") + clen; msglen = origlen = end - dptr; - if (msglen > datalen) { - nf_ct_helper_log(skb, ct, "incomplete/bad SIP message"); - return NF_DROP; - } + if (msglen > datalen) + return NF_ACCEPT; ret = process_sip_msg(skb, ct, protoff, dataoff, &dptr, &msglen); From 02f815cb6d3f57914228be84df9613ee5a01c2e6 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 9 Apr 2013 08:57:19 +0000 Subject: [PATCH 2/4] netfilter: ipset: list:set: fix reference counter update The last element can be replaced or pushed off and in both cases the reference counter must be updated. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- net/netfilter/ipset/ip_set_list_set.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 8371c2bac2e4..09c744aa8982 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -174,9 +174,13 @@ list_set_add(struct list_set *map, u32 i, ip_set_id_t id, { const struct set_elem *e = list_set_elem(map, i); - if (i == map->size - 1 && e->id != IPSET_INVALID_ID) - /* Last element replaced: e.g. add new,before,last */ - ip_set_put_byindex(e->id); + if (e->id != IPSET_INVALID_ID) { + const struct set_elem *x = list_set_elem(map, map->size - 1); + + /* Last element replaced or pushed off */ + if (x->id != IPSET_INVALID_ID) + ip_set_put_byindex(x->id); + } if (with_timeout(map->timeout)) list_elem_tadd(map, i, id, ip_set_timeout_set(timeout)); else From 6eb4c7e96e19fd2c38a103472048fc0e0e0a3ec3 Mon Sep 17 00:00:00 2001 From: Jozsef Kadlecsik Date: Tue, 9 Apr 2013 08:57:20 +0000 Subject: [PATCH 3/4] netfilter: ipset: hash:*net*: nomatch flag not excluded on set resize If a resize is triggered the nomatch flag is not excluded at hashing, which leads to the element missed at lookup in the resized set. Signed-off-by: Jozsef Kadlecsik Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/ipset/ip_set_ahash.h | 30 +++++++++++++++----- net/netfilter/ipset/ip_set_hash_ipportnet.c | 18 ++++++++++++ net/netfilter/ipset/ip_set_hash_net.c | 22 ++++++++++++-- net/netfilter/ipset/ip_set_hash_netiface.c | 22 ++++++++++++-- net/netfilter/ipset/ip_set_hash_netport.c | 18 ++++++++++++ 5 files changed, 99 insertions(+), 11 deletions(-) diff --git a/include/linux/netfilter/ipset/ip_set_ahash.h b/include/linux/netfilter/ipset/ip_set_ahash.h index 01d25e6fc792..0214c4c146fa 100644 --- a/include/linux/netfilter/ipset/ip_set_ahash.h +++ b/include/linux/netfilter/ipset/ip_set_ahash.h @@ -291,6 +291,7 @@ ip_set_hash_destroy(struct ip_set *set) #define type_pf_data_tlist TOKEN(TYPE, PF, _data_tlist) #define type_pf_data_next TOKEN(TYPE, PF, _data_next) #define type_pf_data_flags TOKEN(TYPE, PF, _data_flags) +#define type_pf_data_reset_flags TOKEN(TYPE, PF, _data_reset_flags) #ifdef IP_SET_HASH_WITH_NETS #define type_pf_data_match TOKEN(TYPE, PF, _data_match) #else @@ -385,9 +386,9 @@ type_pf_resize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; retry: @@ -412,9 +413,16 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_data(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_add(m, data, AHASH_MAX(h), 0); + ret = type_pf_elem_add(m, data, AHASH_MAX(h), flags); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -836,9 +844,9 @@ type_pf_tresize(struct ip_set *set, bool retried) struct ip_set_hash *h = set->data; struct htable *t, *orig = h->table; u8 htable_bits = orig->htable_bits; - const struct type_pf_elem *data; + struct type_pf_elem *data; struct hbucket *n, *m; - u32 i, j; + u32 i, j, flags = 0; int ret; /* Try to cleanup once */ @@ -873,10 +881,17 @@ retry: n = hbucket(orig, i); for (j = 0; j < n->pos; j++) { data = ahash_tdata(n, j); +#ifdef IP_SET_HASH_WITH_NETS + flags = 0; + type_pf_data_reset_flags(data, &flags); +#endif m = hbucket(t, HKEY(data, h->initval, htable_bits)); - ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), 0, - ip_set_timeout_get(type_pf_data_timeout(data))); + ret = type_pf_elem_tadd(m, data, AHASH_MAX(h), flags, + ip_set_timeout_get(type_pf_data_timeout(data))); if (ret < 0) { +#ifdef IP_SET_HASH_WITH_NETS + type_pf_data_flags(data, flags); +#endif read_unlock_bh(&set->lock); ahash_destroy(t); if (ret == -EAGAIN) @@ -1187,6 +1202,7 @@ type_pf_gc_init(struct ip_set *set) #undef type_pf_data_tlist #undef type_pf_data_next #undef type_pf_data_flags +#undef type_pf_data_reset_flags #undef type_pf_data_match #undef type_pf_elem diff --git a/net/netfilter/ipset/ip_set_hash_ipportnet.c b/net/netfilter/ipset/ip_set_hash_ipportnet.c index f2627226a087..10a30b4fc7db 100644 --- a/net/netfilter/ipset/ip_set_hash_ipportnet.c +++ b/net/netfilter/ipset/ip_set_hash_ipportnet.c @@ -104,6 +104,15 @@ hash_ipportnet4_data_flags(struct hash_ipportnet4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_ipportnet4_data_reset_flags(struct hash_ipportnet4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_ipportnet4_data_match(const struct hash_ipportnet4_elem *elem) { @@ -414,6 +423,15 @@ hash_ipportnet6_data_flags(struct hash_ipportnet6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_ipportnet6_data_reset_flags(struct hash_ipportnet6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_ipportnet6_data_match(const struct hash_ipportnet6_elem *elem) { diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 4b677cf6bf7d..d6a59154d710 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -87,7 +87,16 @@ hash_net4_data_copy(struct hash_net4_elem *dst, static inline void hash_net4_data_flags(struct hash_net4_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_net4_data_reset_flags(struct hash_net4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int @@ -308,7 +317,16 @@ hash_net6_data_copy(struct hash_net6_elem *dst, static inline void hash_net6_data_flags(struct hash_net6_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_net6_data_reset_flags(struct hash_net6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int diff --git a/net/netfilter/ipset/ip_set_hash_netiface.c b/net/netfilter/ipset/ip_set_hash_netiface.c index 6ba985f1c96f..f2b0a3c30130 100644 --- a/net/netfilter/ipset/ip_set_hash_netiface.c +++ b/net/netfilter/ipset/ip_set_hash_netiface.c @@ -198,7 +198,16 @@ hash_netiface4_data_copy(struct hash_netiface4_elem *dst, static inline void hash_netiface4_data_flags(struct hash_netiface4_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); +} + +static inline void +hash_netiface4_data_reset_flags(struct hash_netiface4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } } static inline int @@ -494,7 +503,7 @@ hash_netiface6_data_copy(struct hash_netiface6_elem *dst, static inline void hash_netiface6_data_flags(struct hash_netiface6_elem *dst, u32 flags) { - dst->nomatch = flags & IPSET_FLAG_NOMATCH; + dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } static inline int @@ -503,6 +512,15 @@ hash_netiface6_data_match(const struct hash_netiface6_elem *elem) return elem->nomatch ? -ENOTEMPTY : 1; } +static inline void +hash_netiface6_data_reset_flags(struct hash_netiface6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline void hash_netiface6_data_zero_out(struct hash_netiface6_elem *elem) { diff --git a/net/netfilter/ipset/ip_set_hash_netport.c b/net/netfilter/ipset/ip_set_hash_netport.c index af20c0c5ced2..349deb672a2d 100644 --- a/net/netfilter/ipset/ip_set_hash_netport.c +++ b/net/netfilter/ipset/ip_set_hash_netport.c @@ -104,6 +104,15 @@ hash_netport4_data_flags(struct hash_netport4_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_netport4_data_reset_flags(struct hash_netport4_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_netport4_data_match(const struct hash_netport4_elem *elem) { @@ -375,6 +384,15 @@ hash_netport6_data_flags(struct hash_netport6_elem *dst, u32 flags) dst->nomatch = !!(flags & IPSET_FLAG_NOMATCH); } +static inline void +hash_netport6_data_reset_flags(struct hash_netport6_elem *dst, u32 *flags) +{ + if (dst->nomatch) { + *flags = IPSET_FLAG_NOMATCH; + dst->nomatch = 0; + } +} + static inline int hash_netport6_data_match(const struct hash_netport6_elem *elem) { From c2d421e171868586939c328dfb91bab840fe4c49 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 11 Apr 2013 04:22:39 +0000 Subject: [PATCH 4/4] netfilter: nf_nat: fix race when unloading protocol modules following oops was reported: RIP: 0010:[] [] nf_nat_cleanup_conntrack+0x42/0x70 [nf_nat] RSP: 0018:ffff880202c63d40 EFLAGS: 00010246 RAX: 0000000000000000 RBX: ffff8801ac7bec28 RCX: ffff8801d0eedbe0 RDX: dead000000200200 RSI: 0000000000000011 RDI: ffffffffa03265b8 [..] Call Trace: [..] [] destroy_conntrack+0xbd/0x110 [nf_conntrack] Happens when a conntrack timeout expires right after first part of the nat cleanup has completed (bysrc hash removal), but before part 2 has completed (re-initialization of nat area). [ destroy callback tries to delete bysrc again ] Patrick suggested to just remove the affected conntracks -- the connections won't work properly anyway without nat transformation. So, lets do that. Reported-by: CAI Qian Cc: Patrick McHardy Signed-off-by: Florian Westphal Acked-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 40 +++++++------------------------------ 1 file changed, 7 insertions(+), 33 deletions(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 8d5769c6d16e..ad24be070e53 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -467,33 +467,22 @@ EXPORT_SYMBOL_GPL(nf_nat_packet); struct nf_nat_proto_clean { u8 l3proto; u8 l4proto; - bool hash; }; -/* Clear NAT section of all conntracks, in case we're loaded again. */ -static int nf_nat_proto_clean(struct nf_conn *i, void *data) +/* kill conntracks with affected NAT section */ +static int nf_nat_proto_remove(struct nf_conn *i, void *data) { const struct nf_nat_proto_clean *clean = data; struct nf_conn_nat *nat = nfct_nat(i); if (!nat) return 0; - if (!(i->status & IPS_SRC_NAT_DONE)) - return 0; + if ((clean->l3proto && nf_ct_l3num(i) != clean->l3proto) || (clean->l4proto && nf_ct_protonum(i) != clean->l4proto)) return 0; - if (clean->hash) { - spin_lock_bh(&nf_nat_lock); - hlist_del_rcu(&nat->bysource); - spin_unlock_bh(&nf_nat_lock); - } else { - memset(nat, 0, sizeof(*nat)); - i->status &= ~(IPS_NAT_MASK | IPS_NAT_DONE_MASK | - IPS_SEQ_ADJUST); - } - return 0; + return i->status & IPS_NAT_MASK ? 1 : 0; } static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) @@ -505,16 +494,8 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto) struct net *net; rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu(); - - /* Step 2 - clean NAT section */ - clean.hash = false; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); } @@ -526,16 +507,9 @@ static void nf_nat_l3proto_clean(u8 l3proto) struct net *net; rtnl_lock(); - /* Step 1 - remove from bysource hash */ - clean.hash = true; - for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); - synchronize_rcu(); - /* Step 2 - clean NAT section */ - clean.hash = false; for_each_net(net) - nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean); rtnl_unlock(); } @@ -773,7 +747,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { struct nf_nat_proto_clean clean = {}; - nf_ct_iterate_cleanup(net, &nf_nat_proto_clean, &clean); + nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean); synchronize_rcu(); nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size); }