From b428336676dbca363262cc134b6218205df4f530 Mon Sep 17 00:00:00 2001 From: Stephen Suryaputra Date: Tue, 4 Aug 2020 17:44:09 -0400 Subject: netfilter: nf_tables: nft_exthdr: the presence return value should be little-endian On big-endian machine, the returned register data when the exthdr is present is not being compared correctly because little-endian is assumed. The function nft_cmp_fast_mask(), called by nft_cmp_fast_eval() and nft_cmp_fast_init(), calls cpu_to_le32(). The following dump also shows that little endian is assumed: $ nft --debug=netlink add rule ip recordroute forward ip option rr exists counter ip [ exthdr load ipv4 1b @ 7 + 0 present => reg 1 ] [ cmp eq reg 1 0x01000000 ] [ counter pkts 0 bytes 0 ] Lastly, debug print in nft_cmp_fast_init() and nft_cmp_fast_eval() when RR option exists in the packet shows that the comparison fails because the assumption: nft_cmp_fast_init:189 priv->sreg=4 desc.len=8 mask=0xff000000 data.data[0]=0x10003e0 nft_cmp_fast_eval:57 regs->data[priv->sreg=4]=0x1 mask=0xff000000 priv->data=0x1000000 v2: use nft_reg_store8() instead (Florian Westphal). Also to avoid the warnings reported by kernel test robot. Fixes: dbb5281a1f84 ("netfilter: nf_tables: add support for matching IPv4 options") Fixes: c078ca3b0c5b ("netfilter: nft_exthdr: Add support for existence check") Signed-off-by: Stephen Suryaputra Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_exthdr.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 07782836fad6..3c48cdc8935d 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -44,7 +44,7 @@ static void nft_exthdr_ipv6_eval(const struct nft_expr *expr, err = ipv6_find_hdr(pkt->skb, &offset, priv->type, NULL, NULL); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; @@ -141,7 +141,7 @@ static void nft_exthdr_ipv4_eval(const struct nft_expr *expr, err = ipv4_find_option(nft_net(pkt), skb, &offset, priv->type); if (priv->flags & NFT_EXTHDR_F_PRESENT) { - *dest = (err >= 0); + nft_reg_store8(dest, err >= 0); return; } else if (err < 0) { goto err; -- cgit v1.2.3 From 2f941622fd88328ca75806c45c9e9709286a0609 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Sun, 9 Aug 2020 20:28:01 +0200 Subject: netfilter: nft_compat: remove flush counter optimization WARNING: CPU: 1 PID: 16059 at lib/refcount.c:31 refcount_warn_saturate+0xdf/0xf [..] __nft_mt_tg_destroy+0x42/0x50 [nft_compat] nft_target_destroy+0x63/0x80 [nft_compat] nf_tables_expr_destroy+0x1b/0x30 [nf_tables] nf_tables_rule_destroy+0x3a/0x70 [nf_tables] nf_tables_exit_net+0x186/0x3d0 [nf_tables] Happens when a compat expr is destoyed from abort path. There is no functional impact; after this work queue is flushed unconditionally if its pending. This removes the waitcount optimization. Test of repeated iptables-restore of a ~60k kubernetes ruleset doesn't indicate a slowdown. In case the counter is needed after all for some workloads we can revert this and increment the refcount for the != NFT_PREPARE_TRANS case to avoid the increment/decrement imbalance. While at it, also flush for match case, this was an oversight in the original patch. Fixes: ffe8923f109b7e ("netfilter: nft_compat: make sure xtables destructors have run") Reported-by: kernel test robot Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nft_compat.c | 37 ++++++++++++++----------------------- 1 file changed, 14 insertions(+), 23 deletions(-) (limited to 'net') diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index 6428856ccbec..8e56f353ff35 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -27,8 +27,6 @@ struct nft_xt_match_priv { void *info; }; -static refcount_t nft_compat_pending_destroy = REFCOUNT_INIT(1); - static int nft_compat_chain_validate_dependency(const struct nft_ctx *ctx, const char *tablename) { @@ -215,6 +213,17 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return 0; } +static void nft_compat_wait_for_destructors(void) +{ + /* xtables matches or targets can have side effects, e.g. + * creation/destruction of /proc files. + * The xt ->destroy functions are run asynchronously from + * work queue. If we have pending invocations we thus + * need to wait for those to finish. + */ + nf_tables_trans_destroy_flush_work(); +} + static int nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -238,14 +247,7 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_target_set_tgchk_param(&par, ctx, target, info, &e, proto, inv); - /* xtables matches or targets can have side effects, e.g. - * creation/destruction of /proc files. - * The xt ->destroy functions are run asynchronously from - * work queue. If we have pending invocations we thus - * need to wait for those to finish. - */ - if (refcount_read(&nft_compat_pending_destroy) > 1) - nf_tables_trans_destroy_flush_work(); + nft_compat_wait_for_destructors(); ret = xt_check_target(&par, size, proto, inv); if (ret < 0) @@ -260,7 +262,6 @@ nft_target_init(const struct nft_ctx *ctx, const struct nft_expr *expr, static void __nft_mt_tg_destroy(struct module *me, const struct nft_expr *expr) { - refcount_dec(&nft_compat_pending_destroy); module_put(me); kfree(expr->ops); } @@ -468,6 +469,8 @@ __nft_match_init(const struct nft_ctx *ctx, const struct nft_expr *expr, nft_match_set_mtchk_param(&par, ctx, match, info, &e, proto, inv); + nft_compat_wait_for_destructors(); + return xt_check_match(&par, size, proto, inv); } @@ -716,14 +719,6 @@ static const struct nfnetlink_subsystem nfnl_compat_subsys = { static struct nft_expr_type nft_match_type; -static void nft_mt_tg_deactivate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - enum nft_trans_phase phase) -{ - if (phase == NFT_TRANS_COMMIT) - refcount_inc(&nft_compat_pending_destroy); -} - static const struct nft_expr_ops * nft_match_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -762,7 +757,6 @@ nft_match_select_ops(const struct nft_ctx *ctx, ops->type = &nft_match_type; ops->eval = nft_match_eval; ops->init = nft_match_init; - ops->deactivate = nft_mt_tg_deactivate, ops->destroy = nft_match_destroy; ops->dump = nft_match_dump; ops->validate = nft_match_validate; @@ -853,7 +847,6 @@ nft_target_select_ops(const struct nft_ctx *ctx, ops->size = NFT_EXPR_SIZE(XT_ALIGN(target->targetsize)); ops->init = nft_target_init; ops->destroy = nft_target_destroy; - ops->deactivate = nft_mt_tg_deactivate, ops->dump = nft_target_dump; ops->validate = nft_target_validate; ops->data = target; @@ -917,8 +910,6 @@ static void __exit nft_compat_module_exit(void) nfnetlink_subsys_unregister(&nfnl_compat_subsys); nft_unregister_expr(&nft_target_type); nft_unregister_expr(&nft_match_type); - - WARN_ON_ONCE(refcount_read(&nft_compat_pending_destroy) != 1); } MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_NFT_COMPAT); -- cgit v1.2.3 From 2404b73c3f1a5f15726c6ecd226b56f6f992767f Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 10 Aug 2020 13:52:15 +0200 Subject: netfilter: avoid ipv6 -> nf_defrag_ipv6 module dependency nf_ct_frag6_gather is part of nf_defrag_ipv6.ko, not ipv6 core. The current use of the netfilter ipv6 stub indirections causes a module dependency between ipv6 and nf_defrag_ipv6. This prevents nf_defrag_ipv6 module from being removed because ipv6 can't be unloaded. Remove the indirection and always use a direct call. This creates a depency from nf_conntrack_bridge to nf_defrag_ipv6 instead: modinfo nf_conntrack depends: nf_conntrack,nf_defrag_ipv6,bridge .. and nf_conntrack already depends on nf_defrag_ipv6 anyway. Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6.h | 18 ------------------ net/bridge/netfilter/nf_conntrack_bridge.c | 8 ++++++-- net/ipv6/netfilter.c | 3 --- 3 files changed, 6 insertions(+), 23 deletions(-) (limited to 'net') diff --git a/include/linux/netfilter_ipv6.h b/include/linux/netfilter_ipv6.h index aac42c28fe62..9b67394471e1 100644 --- a/include/linux/netfilter_ipv6.h +++ b/include/linux/netfilter_ipv6.h @@ -58,7 +58,6 @@ struct nf_ipv6_ops { int (*output)(struct net *, struct sock *, struct sk_buff *)); int (*reroute)(struct sk_buff *skb, const struct nf_queue_entry *entry); #if IS_MODULE(CONFIG_IPV6) - int (*br_defrag)(struct net *net, struct sk_buff *skb, u32 user); int (*br_fragment)(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, @@ -117,23 +116,6 @@ static inline int nf_ip6_route(struct net *net, struct dst_entry **dst, #include -static inline int nf_ipv6_br_defrag(struct net *net, struct sk_buff *skb, - u32 user) -{ -#if IS_MODULE(CONFIG_IPV6) - const struct nf_ipv6_ops *v6_ops = nf_get_ipv6_ops(); - - if (!v6_ops) - return 1; - - return v6_ops->br_defrag(net, skb, user); -#elif IS_BUILTIN(CONFIG_IPV6) - return nf_ct_frag6_gather(net, skb, user); -#else - return 1; -#endif -} - int br_ip6_fragment(struct net *net, struct sock *sk, struct sk_buff *skb, struct nf_bridge_frag_data *data, int (*output)(struct net *, struct sock *sk, diff --git a/net/bridge/netfilter/nf_conntrack_bridge.c b/net/bridge/netfilter/nf_conntrack_bridge.c index 809673222382..8d033a75a766 100644 --- a/net/bridge/netfilter/nf_conntrack_bridge.c +++ b/net/bridge/netfilter/nf_conntrack_bridge.c @@ -168,6 +168,7 @@ static unsigned int nf_ct_br_defrag4(struct sk_buff *skb, static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, const struct nf_hook_state *state) { +#if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) u16 zone_id = NF_CT_DEFAULT_ZONE_ID; enum ip_conntrack_info ctinfo; struct br_input_skb_cb cb; @@ -180,14 +181,17 @@ static unsigned int nf_ct_br_defrag6(struct sk_buff *skb, br_skb_cb_save(skb, &cb, sizeof(struct inet6_skb_parm)); - err = nf_ipv6_br_defrag(state->net, skb, - IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); + err = nf_ct_frag6_gather(state->net, skb, + IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id); /* queued */ if (err == -EINPROGRESS) return NF_STOLEN; br_skb_cb_restore(skb, &cb, IP6CB(skb)->frag_max_size); return err == 0 ? NF_ACCEPT : NF_DROP; +#else + return NF_ACCEPT; +#endif } static int nf_ct_br_ip_check(const struct sk_buff *skb) diff --git a/net/ipv6/netfilter.c b/net/ipv6/netfilter.c index 409e79b84a83..6d0e942d082d 100644 --- a/net/ipv6/netfilter.c +++ b/net/ipv6/netfilter.c @@ -245,9 +245,6 @@ static const struct nf_ipv6_ops ipv6ops = { .route_input = ip6_route_input, .fragment = ip6_fragment, .reroute = nf_ip6_reroute, -#if IS_MODULE(CONFIG_IPV6) && IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) - .br_defrag = nf_ct_frag6_gather, -#endif #if IS_MODULE(CONFIG_IPV6) .br_fragment = br_ip6_fragment, #endif -- cgit v1.2.3 From 59136aa3b2649796a3a1fd90158675f1f640ce0e Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Tue, 11 Aug 2020 19:39:09 +0200 Subject: netfilter: nf_tables: free chain context when BINDING flag is missing syzbot found a memory leak in nf_tables_addchain() because the chain object is not free'd correctly on error. Fixes: d0e2c7de92c7 ("netfilter: nf_tables: add NFT_CHAIN_BINDING") Reported-by: syzbot+c99868fde67014f7e9f5@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- net/netfilter/nf_tables_api.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) (limited to 'net') diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index d878e34e3354..fd814e514f94 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2018,8 +2018,10 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, if (nla[NFTA_CHAIN_NAME]) { chain->name = nla_strdup(nla[NFTA_CHAIN_NAME], GFP_KERNEL); } else { - if (!(flags & NFT_CHAIN_BINDING)) - return -EINVAL; + if (!(flags & NFT_CHAIN_BINDING)) { + err = -EINVAL; + goto err1; + } snprintf(name, sizeof(name), "__chain%llu", ++chain_id); chain->name = kstrdup(name, GFP_KERNEL); -- cgit v1.2.3 From 5c04da55c754c44937b3d19c6522f9023fd5c5d5 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Thu, 13 Aug 2020 09:46:11 +0200 Subject: netfilter: ebtables: reject bogus getopt len value syzkaller reports splat: ------------[ cut here ]------------ Buffer overflow detected (80 < 137)! Call Trace: do_ebt_get_ctl+0x2b4/0x790 net/bridge/netfilter/ebtables.c:2317 nf_getsockopt+0x72/0xd0 net/netfilter/nf_sockopt.c:116 ip_getsockopt net/ipv4/ip_sockglue.c:1778 [inline] caused by a copy-to-user with a too-large "*len" value. This adds a argument check on *len just like in the non-compat version of the handler. Before the "Fixes" commit, the reproducer fails with -EINVAL as expected: 1. core calls the "compat" getsockopt version 2. compat getsockopt version detects the *len value is possibly in 64-bit layout (*len != compat_len) 3. compat getsockopt version delegates everything to native getsockopt version 4. native getsockopt rejects invalid *len -> compat handler only sees len == sizeof(compat_struct) for GET_ENTRIES. After the refactor, event sequence is: 1. getsockopt calls "compat" version (len != native_len) 2. compat version attempts to copy *len bytes, where *len is random value from userspace Fixes: fc66de8e16ec ("netfilter/ebtables: clean up compat {get, set}sockopt handling") Reported-by: syzbot+5accb5c62faa1d346480@syzkaller.appspotmail.com Signed-off-by: Florian Westphal Reviewed-by: Christoph Hellwig Signed-off-by: Pablo Neira Ayuso --- net/bridge/netfilter/ebtables.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 1641f414d1ba..ebe33b60efd6 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -2238,6 +2238,10 @@ static int compat_do_ebt_get_ctl(struct sock *sk, int cmd, struct ebt_table *t; struct net *net = sock_net(sk); + if ((cmd == EBT_SO_GET_INFO || cmd == EBT_SO_GET_INIT_INFO) && + *len != sizeof(struct compat_ebt_replace)) + return -EINVAL; + if (copy_from_user(&tmp, user, sizeof(tmp))) return -EFAULT; -- cgit v1.2.3