From ff46e3b4421923937b7f6e44ffcd3549a074f321 Mon Sep 17 00:00:00 2001 From: luoxuanqiang Date: Fri, 21 Jun 2024 09:39:29 +0800 Subject: Fix race for duplicate reqsk on identical SYN When bonding is configured in BOND_MODE_BROADCAST mode, if two identical SYN packets are received at the same time and processed on different CPUs, it can potentially create the same sk (sock) but two different reqsk (request_sock) in tcp_conn_request(). These two different reqsk will respond with two SYNACK packets, and since the generation of the seq (ISN) incorporates a timestamp, the final two SYNACK packets will have different seq values. The consequence is that when the Client receives and replies with an ACK to the earlier SYNACK packet, we will reset(RST) it. ======================================================================== This behavior is consistently reproducible in my local setup, which comprises: | NETA1 ------ NETB1 | PC_A --- bond --- | | --- bond --- PC_B | NETA2 ------ NETB2 | - PC_A is the Server and has two network cards, NETA1 and NETA2. I have bonded these two cards using BOND_MODE_BROADCAST mode and configured them to be handled by different CPU. - PC_B is the Client, also equipped with two network cards, NETB1 and NETB2, which are also bonded and configured in BOND_MODE_BROADCAST mode. If the client attempts a TCP connection to the server, it might encounter a failure. Capturing packets from the server side reveals: 10.10.10.10.45182 > localhost: Flags [S], seq 320236027, 10.10.10.10.45182 > localhost: Flags [S], seq 320236027, localhost > 10.10.10.10.45182: Flags [S.], seq 2967855116, localhost > 10.10.10.10.45182: Flags [S.], seq 2967855123, <== 10.10.10.10.45182 > localhost: Flags [.], ack 4294967290, 10.10.10.10.45182 > localhost: Flags [.], ack 4294967290, localhost > 10.10.10.10.45182: Flags [R], seq 2967855117, <== localhost > 10.10.10.10.45182: Flags [R], seq 2967855117, Two SYNACKs with different seq numbers are sent by localhost, resulting in an anomaly. ======================================================================== The attempted solution is as follows: Add a return value to inet_csk_reqsk_queue_hash_add() to confirm if the ehash insertion is successful (Up to now, the reason for unsuccessful insertion is that a reqsk for the same connection has already been inserted). If the insertion fails, release the reqsk. Due to the refcnt, Kuniyuki suggests also adding a return value check for the DCCP module; if ehash insertion fails, indicating a successful insertion of the same connection, simply release the reqsk as well. Simultaneously, In the reqsk_queue_hash_req(), the start of the req->rsk_timer is adjusted to be after successful insertion. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: luoxuanqiang Reviewed-by: Kuniyuki Iwashima Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20240621013929.1386815-1-luoxuanqiang@kylinos.cn Signed-off-by: Paolo Abeni --- include/net/inet_connection_sock.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 7d6b1254c92d..c0deaafebfdc 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -263,7 +263,7 @@ struct dst_entry *inet_csk_route_child_sock(const struct sock *sk, struct sock *inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req, struct sock *child); -void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, +bool inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, unsigned long timeout); struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child, struct request_sock *req, -- cgit v1.2.3 From 7931d32955e09d0a11b1fe0b6aac1bfa061c005c Mon Sep 17 00:00:00 2001 From: Pablo Neira Ayuso Date: Wed, 26 Jun 2024 23:15:38 +0200 Subject: netfilter: nf_tables: fully validate NFT_DATA_VALUE on store to data registers register store validation for NFT_DATA_VALUE is conditional, however, the datatype is always either NFT_DATA_VALUE or NFT_DATA_VERDICT. This only requires a new helper function to infer the register type from the set datatype so this conditional check can be removed. Otherwise, pointer to chain object can be leaked through the registers. Fixes: 96518518cc41 ("netfilter: add nftables") Reported-by: Linus Torvalds Signed-off-by: Pablo Neira Ayuso --- include/net/netfilter/nf_tables.h | 5 +++++ net/netfilter/nf_tables_api.c | 8 ++++---- net/netfilter/nft_lookup.c | 3 ++- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'include/net') diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index 2796153b03da..188d41da1a40 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -619,6 +619,11 @@ static inline void *nft_set_priv(const struct nft_set *set) return (void *)set->data; } +static inline enum nft_data_types nft_set_datatype(const struct nft_set *set) +{ + return set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE; +} + static inline bool nft_set_gc_is_pending(const struct nft_set *s) { return refcount_read(&s->refs) != 1; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index be3b4c90d2ed..e8dcf41d360d 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -5740,8 +5740,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_DATA) && nft_data_dump(skb, NFTA_SET_ELEM_DATA, nft_set_ext_data(ext), - set->dtype == NFT_DATA_VERDICT ? NFT_DATA_VERDICT : NFT_DATA_VALUE, - set->dlen) < 0) + nft_set_datatype(set), set->dlen) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPRESSIONS) && @@ -11073,6 +11072,9 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, return 0; default: + if (type != NFT_DATA_VALUE) + return -EINVAL; + if (reg < NFT_REG_1 * NFT_REG_SIZE / NFT_REG32_SIZE) return -EINVAL; if (len == 0) @@ -11081,8 +11083,6 @@ static int nft_validate_register_store(const struct nft_ctx *ctx, sizeof_field(struct nft_regs, data)) return -ERANGE; - if (data != NULL && type != NFT_DATA_VALUE) - return -EINVAL; return 0; } } diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c index b314ca728a29..f3080fa1b226 100644 --- a/net/netfilter/nft_lookup.c +++ b/net/netfilter/nft_lookup.c @@ -132,7 +132,8 @@ static int nft_lookup_init(const struct nft_ctx *ctx, return -EINVAL; err = nft_parse_register_store(ctx, tb[NFTA_LOOKUP_DREG], - &priv->dreg, NULL, set->dtype, + &priv->dreg, NULL, + nft_set_datatype(set), set->dlen); if (err < 0) return err; -- cgit v1.2.3