From 6d8b49c3a3a3e1f11b52edd3b9beb6693bb8061d Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 9 Nov 2016 10:24:40 -0800 Subject: netfilter: Update ip_route_me_harder to consider L3 domain ip_route_me_harder is not considering the L3 domain and sending lookups to the wrong table. For example consider the following output rule: iptables -I OUTPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset using perf to analyze lookups via the fib_table_lookup tracepoint shows: vrf-test 1187 [001] 46887.295927: fib:fib_table_lookup: table 255 oif 0 iif 0 src 0.0.0.0 dst 10.100.1.254 tos 0 scope 0 flags 0 ffffffff8143922c perf_trace_fib_table_lookup ([kernel.kallsyms]) ffffffff81493aac fib_table_lookup ([kernel.kallsyms]) ffffffff8148dda3 __inet_dev_addr_type ([kernel.kallsyms]) ffffffff8148ddf6 inet_addr_type ([kernel.kallsyms]) ffffffff8149e344 ip_route_me_harder ([kernel.kallsyms]) and vrf-test 1187 [001] 46887.295933: fib:fib_table_lookup: table 255 oif 0 iif 1 src 10.100.1.254 dst 10.100.1.2 tos 0 scope 0 flags ffffffff8143922c perf_trace_fib_table_lookup ([kernel.kallsyms]) ffffffff81493aac fib_table_lookup ([kernel.kallsyms]) ffffffff814998ff fib4_rule_action ([kernel.kallsyms]) ffffffff81437f35 fib_rules_lookup ([kernel.kallsyms]) ffffffff81499758 __fib_lookup ([kernel.kallsyms]) ffffffff8144f010 fib_lookup.constprop.34 ([kernel.kallsyms]) ffffffff8144f759 __ip_route_output_key_hash ([kernel.kallsyms]) ffffffff8144fc6a ip_route_output_flow ([kernel.kallsyms]) ffffffff8149e39b ip_route_me_harder ([kernel.kallsyms]) In both cases the lookups are directed to table 255 rather than the table associated with the device via the L3 domain. Update both lookups to pull the L3 domain from the dst currently attached to the skb. Signed-off-by: David Ahern Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index c3776ff6749f..b3cc1335adbc 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -24,10 +24,11 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t struct flowi4 fl4 = {}; __be32 saddr = iph->saddr; __u8 flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; + struct net_device *dev = skb_dst(skb)->dev; unsigned int hh_len; if (addr_type == RTN_UNSPEC) - addr_type = inet_addr_type(net, saddr); + addr_type = inet_addr_type_dev_table(net, dev, saddr); if (addr_type == RTN_LOCAL || addr_type == RTN_UNICAST) flags |= FLOWI_FLAG_ANYSRC; else @@ -40,6 +41,8 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t fl4.saddr = saddr; fl4.flowi4_tos = RT_TOS(iph->tos); fl4.flowi4_oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; + if (!fl4.flowi4_oif) + fl4.flowi4_oif = l3mdev_master_ifindex(dev); fl4.flowi4_mark = skb->mark; fl4.flowi4_flags = flags; rt = ip_route_output_key(net, &fl4); -- cgit v1.2.3 From 00b4422fe363cc7cadc51c50c5a0c3c510f0fa14 Mon Sep 17 00:00:00 2001 From: David Ahern Date: Wed, 9 Nov 2016 10:25:05 -0800 Subject: netfilter: Update nf_send_reset6 to consider L3 domain nf_send_reset6 is not considering the L3 domain and lookups are sent to the wrong table. For example consider the following output rule: ip6tables -A OUTPUT -p tcp --dport 12345 -j REJECT --reject-with tcp-reset using perf to analyze lookups via the fib6_table_lookup tracepoint shows: swapper 0 [001] 248.787816: fib6:fib6_table_lookup: table 255 oif 0 iif 1 src 2100:1::3 dst 2100:1: ffffffff81439cdc perf_trace_fib6_table_lookup ([kernel.kallsyms]) ffffffff814c1ce3 trace_fib6_table_lookup ([kernel.kallsyms]) ffffffff814c3e89 ip6_pol_route ([kernel.kallsyms]) ffffffff814c40d5 ip6_pol_route_output ([kernel.kallsyms]) ffffffff814e7b6f fib6_rule_action ([kernel.kallsyms]) ffffffff81437f60 fib_rules_lookup ([kernel.kallsyms]) ffffffff814e7c79 fib6_rule_lookup ([kernel.kallsyms]) ffffffff814c2541 ip6_route_output_flags ([kernel.kallsyms]) 528 nf_send_reset6 ([nf_reject_ipv6]) The lookup is directed to table 255 rather than the table associated with the device via the L3 domain. Update nf_send_reset6 to pull the L3 domain from the dst currently attached to the skb. Signed-off-by: David Ahern Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_reject_ipv6.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index a5400223fd74..10090400c72f 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -156,6 +156,7 @@ void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook) fl6.daddr = oip6h->saddr; fl6.fl6_sport = otcph->dest; fl6.fl6_dport = otcph->source; + fl6.flowi6_oif = l3mdev_master_ifindex(skb_dst(oldskb)->dev); security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6)); dst = ip6_route_output(net, NULL, &fl6); if (dst->error) { -- cgit v1.2.3 From 486dcf43da7815baa615822f3e46883ccca5400f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 10 Nov 2016 14:24:40 +0100 Subject: netfilter: fix nf_conntrack_helper documentation Since kernel 4.7 this defaults to off. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- Documentation/networking/nf_conntrack-sysctl.txt | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/Documentation/networking/nf_conntrack-sysctl.txt b/Documentation/networking/nf_conntrack-sysctl.txt index 399e4e866a9c..433b6724797a 100644 --- a/Documentation/networking/nf_conntrack-sysctl.txt +++ b/Documentation/networking/nf_conntrack-sysctl.txt @@ -62,10 +62,13 @@ nf_conntrack_generic_timeout - INTEGER (seconds) protocols. nf_conntrack_helper - BOOLEAN - 0 - disabled - not 0 - enabled (default) + 0 - disabled (default) + not 0 - enabled Enable automatic conntrack helper assignment. + If disabled it is required to set up iptables rules to assign + helpers to connections. See the CT target description in the + iptables-extensions(8) man page for further information. nf_conntrack_icmp_timeout - INTEGER (seconds) default 30 -- cgit v1.2.3 From abd66e9f3cc50c9c3ba4cf609749374090a2f215 Mon Sep 17 00:00:00 2001 From: Laura Garcia Liebana Date: Mon, 14 Nov 2016 22:33:34 +0100 Subject: netfilter: nft_hash: validate maximum value of u32 netlink hash attribute Use the function nft_parse_u32_check() to fetch the value and validate the u32 attribute into the hash len u8 field. This patch revisits 4da449ae1df9 ("netfilter: nft_exthdr: Add size check on u8 nft_exthdr attributes"). Fixes: cb1b69b0b15b ("netfilter: nf_tables: add hash expression") Signed-off-by: Laura Garcia Liebana Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_hash.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index baf694de3935..d5447a22275c 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -53,6 +53,7 @@ static int nft_hash_init(const struct nft_ctx *ctx, { struct nft_hash *priv = nft_expr_priv(expr); u32 len; + int err; if (!tb[NFTA_HASH_SREG] || !tb[NFTA_HASH_DREG] || @@ -67,8 +68,10 @@ static int nft_hash_init(const struct nft_ctx *ctx, priv->sreg = nft_parse_register(tb[NFTA_HASH_SREG]); priv->dreg = nft_parse_register(tb[NFTA_HASH_DREG]); - len = ntohl(nla_get_be32(tb[NFTA_HASH_LEN])); - if (len == 0 || len > U8_MAX) + err = nft_parse_u32_check(tb[NFTA_HASH_LEN], U8_MAX, &len); + if (err < 0) + return err; + if (len == 0) return -ERANGE; priv->len = len; -- cgit v1.2.3 From 728e87b49605f7ee02c0415c8255d3d185a36154 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 16 Nov 2016 15:13:35 +0100 Subject: netfilter: nat: fix cmp return value The comparator works like memcmp, i.e. 0 means objects are equal. In other words, when objects are distinct they are treated as identical, when they are distinct they are allegedly the same. The first case is rare (distinct objects are unlikely to get hashed to same bucket). The second case results in unneeded port conflict resolutions attempts. Fixes: 870190a9ec907 ("netfilter: nat: convert nat bysrc hash to rhashtable") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_nat_core.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index bbb8f3df79f7..c632429706eb 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -193,9 +193,12 @@ static int nf_nat_bysource_cmp(struct rhashtable_compare_arg *arg, const struct nf_nat_conn_key *key = arg->key; const struct nf_conn *ct = obj; - return same_src(ct, key->tuple) && - net_eq(nf_ct_net(ct), key->net) && - nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL); + if (!same_src(ct, key->tuple) || + !net_eq(nf_ct_net(ct), key->net) || + !nf_ct_zone_equal(ct, key->zone, IP_CT_DIR_ORIGINAL)) + return 1; + + return 0; } static struct rhashtable_params nf_nat_bysource_params = { -- cgit v1.2.3 From 7223ecd4669921cb2a709193521967aaa2b06862 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 16 Nov 2016 15:13:36 +0100 Subject: netfilter: nat: switch to new rhlist interface I got offlist bug report about failing connections and high cpu usage. This happens because we hit 'elasticity' checks in rhashtable that refuses bucket list exceeding 16 entries. The nat bysrc hash unfortunately needs to insert distinct objects that share same key and are identical (have same source tuple), this cannot be avoided. Switch to the rhlist interface which is designed for this. The nulls_base is removed here, I don't think its needed: A (unlikely) false positive results in unneeded port clash resolution, a false negative results in packet drop during conntrack confirmation, when we try to insert the duplicate into main conntrack hash table. Tested by adding multiple ip addresses to host, then adding iptables -t nat -A POSTROUTING -o eth0 -j MASQUERADE ... and then creating multiple connections, from same source port but different addresses: for i in $(seq 2000 2032);do nc -p 1234 192.168.7.1 $i > /dev/null & done (all of these then get hashed to same bysource slot) Then, to test that nat conflict resultion is working: nc -s 10.0.0.1 -p 1234 192.168.7.1 2000 nc -s 10.0.0.2 -p 1234 192.168.7.1 2000 tcp .. src=10.0.0.1 dst=192.168.7.1 sport=1234 dport=2000 src=192.168.7.1 dst=192.168.7.10 sport=2000 dport=1024 [ASSURED] tcp .. src=10.0.0.2 dst=192.168.7.1 sport=1234 dport=2000 src=192.168.7.1 dst=192.168.7.10 sport=2000 dport=1025 [ASSURED] tcp .. src=192.168.7.10 dst=192.168.7.1 sport=1234 dport=2000 src=192.168.7.1 dst=192.168.7.10 sport=2000 dport=1234 [ASSURED] tcp .. src=192.168.7.10 dst=192.168.7.1 sport=1234 dport=2001 src=192.168.7.1 dst=192.168.7.10 sport=2001 dport=1234 [ASSURED] [..] -> nat altered source ports to 1024 and 1025, respectively. This can also be confirmed on destination host which shows ESTAB 0 0 192.168.7.1:2000 192.168.7.10:1024 ESTAB 0 0 192.168.7.1:2000 192.168.7.10:1025 ESTAB 0 0 192.168.7.1:2000 192.168.7.10:1234 Cc: Herbert Xu Fixes: 870190a9ec907 ("netfilter: nat: convert nat bysrc hash to rhashtable") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 2 +- net/netfilter/nf_nat_core.c | 40 +++++++++++++++++++++--------------- 2 files changed, 25 insertions(+), 17 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index 50418052a520..dc143ada9762 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -118,7 +118,7 @@ struct nf_conn { struct nf_ct_ext *ext; #if IS_ENABLED(CONFIG_NF_NAT) - struct rhash_head nat_bysource; + struct rhlist_head nat_bysource; #endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index c632429706eb..5b9c884a452e 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -42,7 +42,7 @@ struct nf_nat_conn_key { const struct nf_conntrack_zone *zone; }; -static struct rhashtable nf_nat_bysource_table; +static struct rhltable nf_nat_bysource_table; inline const struct nf_nat_l3proto * __nf_nat_l3proto_find(u8 family) @@ -207,7 +207,6 @@ static struct rhashtable_params nf_nat_bysource_params = { .obj_cmpfn = nf_nat_bysource_cmp, .nelem_hint = 256, .min_size = 1024, - .nulls_base = (1U << RHT_BASE_SHIFT), }; /* Only called for SRC manip */ @@ -226,12 +225,15 @@ find_appropriate_src(struct net *net, .tuple = tuple, .zone = zone }; + struct rhlist_head *hl; - ct = rhashtable_lookup_fast(&nf_nat_bysource_table, &key, - nf_nat_bysource_params); - if (!ct) + hl = rhltable_lookup(&nf_nat_bysource_table, &key, + nf_nat_bysource_params); + if (!hl) return 0; + ct = container_of(hl, typeof(*ct), nat_bysource); + nf_ct_invert_tuplepr(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); result->dst = tuple->dst; @@ -449,11 +451,17 @@ nf_nat_setup_info(struct nf_conn *ct, } if (maniptype == NF_NAT_MANIP_SRC) { + struct nf_nat_conn_key key = { + .net = nf_ct_net(ct), + .tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple, + .zone = nf_ct_zone(ct), + }; int err; - err = rhashtable_insert_fast(&nf_nat_bysource_table, - &ct->nat_bysource, - nf_nat_bysource_params); + err = rhltable_insert_key(&nf_nat_bysource_table, + &key, + &ct->nat_bysource, + nf_nat_bysource_params); if (err) return NF_DROP; } @@ -570,8 +578,8 @@ static int nf_nat_proto_clean(struct nf_conn *ct, void *data) * will delete entry from already-freed table. */ ct->status &= ~IPS_NAT_DONE_MASK; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); /* don't delete conntrack. Although that would make things a lot * simpler, we'd end up flushing all conntracks on nat rmmod. @@ -701,8 +709,8 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) if (!nat) return; - rhashtable_remove_fast(&nf_nat_bysource_table, &ct->nat_bysource, - nf_nat_bysource_params); + rhltable_remove(&nf_nat_bysource_table, &ct->nat_bysource, + nf_nat_bysource_params); } static struct nf_ct_ext_type nat_extend __read_mostly = { @@ -837,13 +845,13 @@ static int __init nf_nat_init(void) { int ret; - ret = rhashtable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); + ret = rhltable_init(&nf_nat_bysource_table, &nf_nat_bysource_params); if (ret) return ret; ret = nf_ct_extend_register(&nat_extend); if (ret < 0) { - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); printk(KERN_ERR "nf_nat_core: Unable to register extension\n"); return ret; } @@ -867,7 +875,7 @@ static int __init nf_nat_init(void) return 0; cleanup_extend: - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); nf_ct_extend_unregister(&nat_extend); return ret; } @@ -886,7 +894,7 @@ static void __exit nf_nat_cleanup(void) for (i = 0; i < NFPROTO_NUMPROTO; i++) kfree(nf_nat_l4protos[i]); - rhashtable_destroy(&nf_nat_bysource_table); + rhltable_destroy(&nf_nat_bysource_table); } MODULE_LICENSE("GPL"); -- cgit v1.2.3 From d3e2a1110cae6ee5eeb1f9a97addf03e974f12e6 Mon Sep 17 00:00:00 2001 From: "Anders K. Pedersen" Date: Sun, 20 Nov 2016 16:38:47 +0000 Subject: netfilter: nf_tables: fix inconsistent element expiration calculation As Liping Zhang reports, after commit a8b1e36d0d1d ("netfilter: nft_dynset: fix element timeout for HZ != 1000"), priv->timeout was stored in jiffies, while set->timeout was stored in milliseconds. This is inconsistent and incorrect. Firstly, we already call msecs_to_jiffies in nft_set_elem_init, so priv->timeout will be converted to jiffies twice. Secondly, if the user did not specify the NFTA_DYNSET_TIMEOUT attr, set->timeout will be used, but we forget to call msecs_to_jiffies when do update elements. Fix this by using jiffies internally for traditional sets and doing the conversions to/from msec when interacting with userspace - as dynset already does. This is preferable to doing the conversions, when elements are inserted or updated, because this can happen very frequently on busy dynsets. Fixes: a8b1e36d0d1d ("netfilter: nft_dynset: fix element timeout for HZ != 1000") Reported-by: Liping Zhang Signed-off-by: Anders K. Pedersen Acked-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 2 +- net/netfilter/nf_tables_api.c | 14 +++++++++----- 2 files changed, 10 insertions(+), 6 deletions(-) diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index d79d1e9b9546..b02af0bf5777 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -313,7 +313,7 @@ void nft_unregister_set(struct nft_set_ops *ops); * @size: maximum set size * @nelems: number of elements * @ndeact: number of deactivated elements queued for removal - * @timeout: default timeout value in msecs + * @timeout: default timeout value in jiffies * @gc_int: garbage collection interval in msecs * @policy: set parameterization (see enum nft_set_policies) * @udlen: user data length diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 026581b04ea8..e5194f6f906c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2570,7 +2570,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, } if (set->timeout && - nla_put_be64(skb, NFTA_SET_TIMEOUT, cpu_to_be64(set->timeout), + nla_put_be64(skb, NFTA_SET_TIMEOUT, + cpu_to_be64(jiffies_to_msecs(set->timeout)), NFTA_SET_PAD)) goto nla_put_failure; if (set->gc_int && @@ -2859,7 +2860,8 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_TIMEOUT]))); } gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { @@ -3178,7 +3180,8 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - cpu_to_be64(*nft_set_ext_timeout(ext)), + cpu_to_be64(jiffies_to_msecs( + *nft_set_ext_timeout(ext))), NFTA_SET_ELEM_PAD)) goto nla_put_failure; @@ -3447,7 +3450,7 @@ void *nft_set_elem_init(const struct nft_set *set, memcpy(nft_set_ext_data(ext), data, set->dlen); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) *nft_set_ext_expiration(ext) = - jiffies + msecs_to_jiffies(timeout); + jiffies + timeout; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) *nft_set_ext_timeout(ext) = timeout; @@ -3535,7 +3538,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = be64_to_cpu(nla_get_be64(nla[NFTA_SET_ELEM_TIMEOUT])); + timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( + nla[NFTA_SET_ELEM_TIMEOUT]))); } else if (set->flags & NFT_SET_TIMEOUT) { timeout = set->timeout; } -- cgit v1.2.3 From 49cdc4c74918a5576cb93b679629714d8a9ef399 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Mon, 21 Nov 2016 21:18:23 +0800 Subject: netfilter: nft_range: add the missing NULL pointer check Otherwise, kernel panic will happen if the user does not specify the related attributes. Fixes: 0f3cd9b36977 ("netfilter: nf_tables: add range expression") Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_range.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index fbc88009ca2e..8f0aaaea1376 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -59,6 +59,12 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr int err; u32 op; + if (!tb[NFTA_RANGE_SREG] || + !tb[NFTA_RANGE_OP] || + !tb[NFTA_RANGE_FROM_DATA] || + !tb[NFTA_RANGE_TO_DATA]) + return -EINVAL; + err = nft_data_init(NULL, &priv->data_from, sizeof(priv->data_from), &desc_from, tb[NFTA_RANGE_FROM_DATA]); if (err < 0) -- cgit v1.2.3 From 5173bc679dec881120df109a6a2b39143235382c Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Wed, 23 Nov 2016 01:11:03 +0100 Subject: netfilter: nat: fix crash when conntrack entry is re-used Stas Nichiporovich reports oops in nf_nat_bysource_cmp(), trying to access nf_conn struct at address 0xffffffffffffff50. This is the result of fetching a null rhash list (struct embedded at offset 176; 0 - 176 gets us ...fff50). The problem is that conntrack entries are allocated from a SLAB_DESTROY_BY_RCU cache, i.e. entries can be free'd and reused on another cpu while nf nat bysource hash access the same conntrack entry. Freeing is fine (we hold rcu read lock); zeroing rhlist_head isn't. -> Move the rhlist struct outside of the memset()-inited area. Fixes: 7c9664351980aaa6a ("netfilter: move nat hlist_head to nf_conn") Reported-by: Stas Nichiporovich Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_conntrack.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index dc143ada9762..d9d52c020a70 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -100,6 +100,9 @@ struct nf_conn { possible_net_t ct_net; +#if IS_ENABLED(CONFIG_NF_NAT) + struct rhlist_head nat_bysource; +#endif /* all members below initialized via memset */ u8 __nfct_init_offset[0]; @@ -117,9 +120,6 @@ struct nf_conn { /* Extensions */ struct nf_ct_ext *ext; -#if IS_ENABLED(CONFIG_NF_NAT) - struct rhlist_head nat_bysource; -#endif /* Storage reserved for other modules, must be the last member */ union nf_conntrack_proto proto; }; -- cgit v1.2.3 From 9b57da0630c9fd36ed7a20fc0f98dc82cc0777fa Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 29 Nov 2016 02:17:34 +0100 Subject: netfilter: ipv6: nf_defrag: drop mangled skb on ream error Dmitry Vyukov reported GPF in network stack that Andrey traced down to negative nh offset in nf_ct_frag6_queue(). Problem is that all network headers before fragment header are pulled. Normal ipv6 reassembly will drop the skb when errors occur further down the line. netfilter doesn't do this, and instead passed the original fragment along. That was also fine back when netfilter ipv6 defrag worked with cloned fragments, as the original, pristine fragment was passed on. So we either have to undo the pull op, or discard such fragments. Since they're malformed after all (e.g. overlapping fragment) it seems preferrable to just drop them. Same for temporary errors -- it doesn't make sense to accept (and perhaps forward!) only some fragments of same datagram. Fixes: 029f7f3b8701cc7ac ("netfilter: ipv6: nf_defrag: avoid/free clone operations") Reported-by: Dmitry Vyukov Debugged-by: Andrey Konovalov Diagnosed-by: Eric Dumazet Signed-off-by: Florian Westphal Acked-by: Eric Dumazet Signed-off-by: Pablo Neira Ayuso --- net/ipv6/netfilter/nf_conntrack_reasm.c | 4 ++-- net/ipv6/netfilter/nf_defrag_ipv6_hooks.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index e4347aeb2e65..9948b5ce52da 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -576,11 +576,11 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); - return -EINVAL; + return 0; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) - return -EINVAL; + return 0; if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) return -ENOMEM; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index f7aab5ab93a5..f06b0471f39f 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -69,7 +69,7 @@ static unsigned int ipv6_defrag(void *priv, if (err == -EINPROGRESS) return NF_STOLEN; - return NF_ACCEPT; + return err == 0 ? NF_ACCEPT : NF_DROP; } static struct nf_hook_ops ipv6_defrag_ops[] = { -- cgit v1.2.3 From 17a49cd549d9dc8707dc9262210166455c612dde Mon Sep 17 00:00:00 2001 From: Hongxu Jia Date: Tue, 29 Nov 2016 21:56:26 -0500 Subject: netfilter: arp_tables: fix invoking 32bit "iptable -P INPUT ACCEPT" failed in 64bit kernel Since 09d9686047db ("netfilter: x_tables: do compat validation via translate_table"), it used compatr structure to assign newinfo structure. In translate_compat_table of ip_tables.c and ip6_tables.c, it used compatr->hook_entry to replace info->hook_entry and compatr->underflow to replace info->underflow, but not do the same replacement in arp_tables.c. It caused invoking 32-bit "arptbale -P INPUT ACCEPT" failed in 64bit kernel. -------------------------------------- root@qemux86-64:~# arptables -P INPUT ACCEPT root@qemux86-64:~# arptables -P INPUT ACCEPT ERROR: Policy for `INPUT' offset 448 != underflow 0 arptables: Incompatible with this kernel -------------------------------------- Fixes: 09d9686047db ("netfilter: x_tables: do compat validation via translate_table") Signed-off-by: Hongxu Jia Acked-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/arp_tables.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index b31df597fd37..697538464e6e 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1201,8 +1201,8 @@ static int translate_compat_table(struct xt_table_info **pinfo, newinfo->number = compatr->num_entries; for (i = 0; i < NF_ARP_NUMHOOKS; i++) { - newinfo->hook_entry[i] = info->hook_entry[i]; - newinfo->underflow[i] = info->underflow[i]; + newinfo->hook_entry[i] = compatr->hook_entry[i]; + newinfo->underflow[i] = compatr->underflow[i]; } entry1 = newinfo->entries; pos = entry1; -- cgit v1.2.3