From ce898ecb5a3c0027855dcee21ed99690b867d017 Mon Sep 17 00:00:00 2001 From: Patrick McHardy Date: Wed, 12 Feb 2014 21:13:16 +0000 Subject: netfilter: nft_reject_inet: fix unintended fall-through in switch-statatement For IPv4 packets, we call both IPv4 and IPv6 reject. Reported-by: Dave Jones Signed-off-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_reject_inet.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_reject_inet.c b/net/netfilter/nft_reject_inet.c index 8a310f2..b718a52 100644 --- a/net/netfilter/nft_reject_inet.c +++ b/net/netfilter/nft_reject_inet.c @@ -21,9 +21,9 @@ static void nft_reject_inet_eval(const struct nft_expr *expr, { switch (pkt->ops->pf) { case NFPROTO_IPV4: - nft_reject_ipv4_eval(expr, data, pkt); + return nft_reject_ipv4_eval(expr, data, pkt); case NFPROTO_IPV6: - nft_reject_ipv6_eval(expr, data, pkt); + return nft_reject_ipv6_eval(expr, data, pkt); } } -- cgit v1.1 From 06efbd6d5694b2e3cde176f724ba572d57709616 Mon Sep 17 00:00:00 2001 From: Paul Bolle Date: Wed, 12 Feb 2014 10:53:01 +0100 Subject: netfilter: nft_meta: fix typo "CONFIG_NET_CLS_ROUTE" There are two checks for CONFIG_NET_CLS_ROUTE, but the corresponding Kconfig symbol was dropped in v2.6.39. Since the code guards access to dst_entry.tclassid it seems CONFIG_IP_ROUTE_CLASSID should be used instead. Signed-off-by: Paul Bolle Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_meta.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index e8254ad..425cf39 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -116,7 +116,7 @@ static void nft_meta_get_eval(const struct nft_expr *expr, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); break; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: { const struct dst_entry *dst = skb_dst(skb); @@ -199,7 +199,7 @@ static int nft_meta_init_validate_get(uint32_t key) case NFT_META_OIFTYPE: case NFT_META_SKUID: case NFT_META_SKGID: -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID case NFT_META_RTCLASSID: #endif #ifdef CONFIG_NETWORK_SECMARK -- cgit v1.1 From 2b7a79bae2dc0327af2352e1d1793b9d752648aa Mon Sep 17 00:00:00 2001 From: FX Le Bail Date: Tue, 11 Feb 2014 15:49:25 +0100 Subject: netfilter: nf_nat_snmp_basic: fix duplicates in if/else branches The solution was found by Patrick in 2.4 kernel sources. Cc: Patrick McHardy Signed-off-by: Francois-Xavier Le Bail Acked-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_nat_snmp_basic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index d551e31..7c67667 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -1198,8 +1198,8 @@ static int snmp_translate(struct nf_conn *ct, map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); } else { /* DNAT replies */ - map.from = NOCT1(&ct->tuplehash[dir].tuple.src.u3.ip); - map.to = NOCT1(&ct->tuplehash[!dir].tuple.dst.u3.ip); + map.from = NOCT1(&ct->tuplehash[!dir].tuple.src.u3.ip); + map.to = NOCT1(&ct->tuplehash[dir].tuple.dst.u3.ip); } if (map.from == map.to) -- cgit v1.1 From 478b360a47b71f3b5030eacd3aae6acb1a32c2b6 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sat, 15 Feb 2014 23:48:45 +0100 Subject: netfilter: nf_tables: fix nf_trace always-on with XT_TRACE=n When using nftables with CONFIG_NETFILTER_XT_TARGET_TRACE=n, we get lots of "TRACE: filter:output:policy:1 IN=..." warnings as several places will leave skb->nf_trace uninitialised. Unlike iptables tracing functionality is not conditional in nftables, so always copy/zero nf_trace setting when nftables is enabled. Move this into __nf_copy() helper. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/skbuff.h | 5 ++++- net/core/skbuff.c | 3 --- net/ipv4/ip_output.c | 3 --- net/ipv6/ip6_output.c | 3 --- 4 files changed, 4 insertions(+), 10 deletions(-) diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index f589c9af..d40d40b 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2725,7 +2725,7 @@ static inline void nf_reset(struct sk_buff *skb) static inline void nf_reset_trace(struct sk_buff *skb) { -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) skb->nf_trace = 0; #endif } @@ -2742,6 +2742,9 @@ static inline void __nf_copy(struct sk_buff *dst, const struct sk_buff *src) dst->nf_bridge = src->nf_bridge; nf_bridge_get(src->nf_bridge); #endif +#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) || defined(CONFIG_NF_TABLES) + dst->nf_trace = src->nf_trace; +#endif } static inline void nf_copy(struct sk_buff *dst, const struct sk_buff *src) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5976ef0..5d6236d 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -707,9 +707,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->mark = old->mark; new->skb_iif = old->skb_iif; __nf_copy(new, old); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - new->nf_trace = old->nf_trace; -#endif #ifdef CONFIG_NET_SCHED new->tc_index = old->tc_index; #ifdef CONFIG_NET_CLS_ACT diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 8971780..73c6b63 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -422,9 +422,6 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE) to->ipvs_property = from->ipvs_property; #endif diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index ef02b26..4cfbe0f 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -517,9 +517,6 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from) to->tc_index = from->tc_index; #endif nf_copy(to, from); -#if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) - to->nf_trace = from->nf_trace; -#endif skb_copy_secmark(to, from); } -- cgit v1.1 From f627ed91d85ed7a189ec8b3b045a0d831e1655e2 Mon Sep 17 00:00:00 2001 From: Nikolay Aleksandrov Date: Sun, 16 Feb 2014 14:01:58 +0100 Subject: netfilter: nf_tables: check if payload length is a power of 2 Add a check if payload's length is a power of 2 when selecting ops. The fast ops were meant for well aligned loads, also this fixes a small bug when using a length of 3 with some offsets which causes only 1 byte to be loaded because the fast ops are chosen. Signed-off-by: Nikolay Aleksandrov Acked-by: Patrick McHardy Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_payload.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index a2aeb31..85daa84 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -135,7 +135,8 @@ nft_payload_select_ops(const struct nft_ctx *ctx, if (len == 0 || len > FIELD_SIZEOF(struct nft_data, data)) return ERR_PTR(-EINVAL); - if (len <= 4 && IS_ALIGNED(offset, len) && base != NFT_PAYLOAD_LL_HEADER) + if (len <= 4 && is_power_of_2(len) && IS_ALIGNED(offset, len) && + base != NFT_PAYLOAD_LL_HEADER) return &nft_payload_fast_ops; else return &nft_payload_ops; -- cgit v1.1 From 0eba801b64cc8284d9024c7ece30415a2b981a72 Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Sun, 16 Feb 2014 12:15:43 +0100 Subject: netfilter: ctnetlink: force null nat binding on insert Quoting Andrey Vagin: When a conntrack is created by kernel, it is initialized (sets IPS_{DST,SRC}_NAT_DONE_BIT bits in nf_nat_setup_info) and only then it is added in hashes (__nf_conntrack_hash_insert), so one conntract can't be initialized from a few threads concurrently. ctnetlink can add an uninitialized conntrack (w/o IPS_{DST,SRC}_NAT_DONE_BIT) in hashes, then a few threads can look up this conntrack and start initialize it concurrently. It's dangerous, because BUG can be triggered from nf_nat_setup_info. Fix this race by always setting up nat, even if no CTA_NAT_ attribute was requested before inserting the ct into the hash table. In absence of CTA_NAT_ attribute, a null binding is created. This alters current behaviour: Before this patch, the first packet matching the newly injected conntrack would be run through the nat table since nf_nat_initialized() returns false. IOW, this forces ctnetlink users to specify the desired nat transformation on ct creation time. Thanks for Florian Westphal, this patch is based on his original patch to address this problem, including this patch description. Reported-By: Andrey Vagin Signed-off-by: Pablo Neira Ayuso Acked-by: Florian Westphal --- net/netfilter/nf_conntrack_netlink.c | 35 +++++++++------------- net/netfilter/nf_nat_core.c | 56 ++++++++++++++++++++++-------------- 2 files changed, 49 insertions(+), 42 deletions(-) diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index bb322d0..b9f0e03 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1310,27 +1310,22 @@ ctnetlink_change_status(struct nf_conn *ct, const struct nlattr * const cda[]) } static int -ctnetlink_change_nat(struct nf_conn *ct, const struct nlattr * const cda[]) +ctnetlink_setup_nat(struct nf_conn *ct, const struct nlattr * const cda[]) { #ifdef CONFIG_NF_NAT_NEEDED int ret; - if (cda[CTA_NAT_DST]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_DST, - cda[CTA_NAT_DST]); - if (ret < 0) - return ret; - } - if (cda[CTA_NAT_SRC]) { - ret = ctnetlink_parse_nat_setup(ct, - NF_NAT_MANIP_SRC, - cda[CTA_NAT_SRC]); - if (ret < 0) - return ret; - } - return 0; + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_DST, + cda[CTA_NAT_DST]); + if (ret < 0) + return ret; + + ret = ctnetlink_parse_nat_setup(ct, NF_NAT_MANIP_SRC, + cda[CTA_NAT_SRC]); + return ret; #else + if (!cda[CTA_NAT_DST] && !cda[CTA_NAT_SRC]) + return 0; return -EOPNOTSUPP; #endif } @@ -1659,11 +1654,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, goto err2; } - if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) { - err = ctnetlink_change_nat(ct, cda); - if (err < 0) - goto err2; - } + err = ctnetlink_setup_nat(ct, cda); + if (err < 0) + goto err2; nf_ct_acct_ext_add(ct, GFP_ATOMIC); nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d3f5cd6..52ca952 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -432,15 +432,15 @@ nf_nat_setup_info(struct nf_conn *ct, } EXPORT_SYMBOL(nf_nat_setup_info); -unsigned int -nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +static unsigned int +__nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip) { /* Force range to this IP; let proto decide mapping for * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). * Use reply in case it's already been mangled (eg local packet). */ union nf_inet_addr ip = - (HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? + (manip == NF_NAT_MANIP_SRC ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3); struct nf_nat_range range = { @@ -448,7 +448,13 @@ nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) .min_addr = ip, .max_addr = ip, }; - return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); + return nf_nat_setup_info(ct, &range, manip); +} + +unsigned int +nf_nat_alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) +{ + return __nf_nat_alloc_null_binding(ct, HOOK2MANIP(hooknum)); } EXPORT_SYMBOL_GPL(nf_nat_alloc_null_binding); @@ -702,9 +708,9 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range *range) + const struct nf_conn *ct, struct nf_nat_range *range, + const struct nf_nat_l3proto *l3proto) { - const struct nf_nat_l3proto *l3proto; struct nlattr *tb[CTA_NAT_MAX+1]; int err; @@ -714,38 +720,46 @@ nfnetlink_parse_nat(const struct nlattr *nat, if (err < 0) return err; - rcu_read_lock(); - l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); - if (l3proto == NULL) { - err = -EAGAIN; - goto out; - } err = l3proto->nlattr_to_range(tb, range); if (err < 0) - goto out; + return err; if (!tb[CTA_NAT_PROTO]) - goto out; + return 0; - err = nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); -out: - rcu_read_unlock(); - return err; + return nfnetlink_parse_nat_proto(tb[CTA_NAT_PROTO], ct, range); } +/* This function is called under rcu_read_lock() */ static int nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { struct nf_nat_range range; + const struct nf_nat_l3proto *l3proto; int err; - err = nfnetlink_parse_nat(attr, ct, &range); + /* Should not happen, restricted to creating new conntracks + * via ctnetlink. + */ + if (WARN_ON_ONCE(nf_nat_initialized(ct, manip))) + return -EEXIST; + + /* Make sure that L3 NAT is there by when we call nf_nat_setup_info to + * attach the null binding, otherwise this may oops. + */ + l3proto = __nf_nat_l3proto_find(nf_ct_l3num(ct)); + if (l3proto == NULL) + return -EAGAIN; + + /* No NAT information has been passed, allocate the null-binding */ + if (attr == NULL) + return __nf_nat_alloc_null_binding(ct, manip); + + err = nfnetlink_parse_nat(attr, ct, &range, l3proto); if (err < 0) return err; - if (nf_nat_initialized(ct, manip)) - return -EEXIST; return nf_nat_setup_info(ct, &range, manip); } -- cgit v1.1