From 58d3aade20cdddbac6c9707ac0f3f5f8c1278b74 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 4 Dec 2023 17:08:05 +0100 Subject: tcp: fix mid stream window clamp. After the blamed commit below, if the user-space application performs window clamping when tp->rcv_wnd is 0, the TCP socket will never be able to announce a non 0 receive window, even after completely emptying the receive buffer and re-setting the window clamp to higher values. Refactor tcp_set_window_clamp() to address the issue: when the user decreases the current clamp value, set rcv_ssthresh according to the same logic used at buffer initialization, but ensuring reserved mem provisioning. To avoid code duplication factor-out the relevant bits from tcp_adjust_rcv_ssthresh() in a new helper and reuse it in the above scenario. When increasing the clamp value, give the rcv_ssthresh a chance to grow according to previously implemented heuristic. Fixes: 3aa7857fe1d7 ("tcp: enable mid stream window clamp") Reported-by: David Gibson Reported-by: Stefano Brivio Signed-off-by: Paolo Abeni Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/705dad54e6e6e9a010e571bf58e0b35a8ae70503.1701706073.git.pabeni@redhat.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp.c | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 53bcc17c91e4..c9f078224569 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3368,9 +3368,25 @@ int tcp_set_window_clamp(struct sock *sk, int val) return -EINVAL; tp->window_clamp = 0; } else { - tp->window_clamp = val < SOCK_MIN_RCVBUF / 2 ? - SOCK_MIN_RCVBUF / 2 : val; - tp->rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + u32 new_rcv_ssthresh, old_window_clamp = tp->window_clamp; + u32 new_window_clamp = val < SOCK_MIN_RCVBUF / 2 ? + SOCK_MIN_RCVBUF / 2 : val; + + if (new_window_clamp == old_window_clamp) + return 0; + + tp->window_clamp = new_window_clamp; + if (new_window_clamp < old_window_clamp) { + /* need to apply the reserved mem provisioning only + * when shrinking the window clamp + */ + __tcp_adjust_rcv_ssthresh(sk, tp->window_clamp); + + } else { + new_rcv_ssthresh = min(tp->rcv_wnd, tp->window_clamp); + tp->rcv_ssthresh = max(new_rcv_ssthresh, + tp->rcv_ssthresh); + } } return 0; } -- cgit v1.2.3 From 80d875cfc9d3711a029f234ef7d680db79e8fa4b Mon Sep 17 00:00:00 2001 From: Shigeru Yoshida Date: Sun, 3 Dec 2023 01:14:41 +0900 Subject: ipv4: ip_gre: Avoid skb_pull() failure in ipgre_xmit() In ipgre_xmit(), skb_pull() may fail even if pskb_inet_may_pull() returns true. For example, applications can use PF_PACKET to create a malformed packet with no IP header. This type of packet causes a problem such as uninit-value access. This patch ensures that skb_pull() can pull the required size by checking the skb with pskb_network_may_pull() before skb_pull(). Fixes: c54419321455 ("GRE: Refactor GRE tunneling code.") Signed-off-by: Shigeru Yoshida Reviewed-by: Eric Dumazet Reviewed-by: Suman Ghosh Link: https://lore.kernel.org/r/20231202161441.221135-1-syoshida@redhat.com Signed-off-by: Paolo Abeni --- net/ipv4/ip_gre.c | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 22a26d1d29a0..5169c3c72cff 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -635,15 +635,18 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, } if (dev->header_ops) { + int pull_len = tunnel->hlen + sizeof(struct iphdr); + if (skb_cow_head(skb, 0)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; - /* Pull skb since ip_tunnel_xmit() needs skb->data pointing - * to gre header. - */ - skb_pull(skb, tunnel->hlen + sizeof(struct iphdr)); + if (!pskb_network_may_pull(skb, pull_len)) + goto free_skb; + + /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ + skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && -- cgit v1.2.3 From da7dfaa6d6f731c30eca6ffa808b83634d43e26f Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 4 Dec 2023 19:00:41 +0000 Subject: net/tcp: Consistently align TCP-AO option in the header Currently functions that pre-calculate TCP header options length use unaligned TCP-AO header + MAC-length for skb reservation. And the functions that actually write TCP-AO options into skb do align the header. Nothing good can come out of this for ((maclen % 4) != 0). Provide tcp_ao_len_aligned() helper and use it everywhere for TCP header options space calculations. Fixes: 1e03d32bea8e ("net/tcp: Add TCP-AO sign to outgoing packets") Signed-off-by: Dmitry Safonov Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- include/net/tcp_ao.h | 6 ++++++ net/ipv4/tcp_ao.c | 4 ++-- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv4/tcp_minisocks.c | 2 +- net/ipv4/tcp_output.c | 6 +++--- net/ipv6/tcp_ipv6.c | 2 +- 6 files changed, 15 insertions(+), 9 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp_ao.h b/include/net/tcp_ao.h index b56be10838f0..647781080613 100644 --- a/include/net/tcp_ao.h +++ b/include/net/tcp_ao.h @@ -62,11 +62,17 @@ static inline int tcp_ao_maclen(const struct tcp_ao_key *key) return key->maclen; } +/* Use tcp_ao_len_aligned() for TCP header calculations */ static inline int tcp_ao_len(const struct tcp_ao_key *key) { return tcp_ao_maclen(key) + sizeof(struct tcp_ao_hdr); } +static inline int tcp_ao_len_aligned(const struct tcp_ao_key *key) +{ + return round_up(tcp_ao_len(key), 4); +} + static inline unsigned int tcp_ao_digest_size(struct tcp_ao_key *key) { return key->digest_size; diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 7696417d0640..c8be1d526eac 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1100,7 +1100,7 @@ void tcp_ao_connect_init(struct sock *sk) ao_info->current_key = key; if (!ao_info->rnext_key) ao_info->rnext_key = key; - tp->tcp_header_len += tcp_ao_len(key); + tp->tcp_header_len += tcp_ao_len_aligned(key); ao_info->lisn = htonl(tp->write_seq); ao_info->snd_sne = 0; @@ -1346,7 +1346,7 @@ static int tcp_ao_parse_crypto(struct tcp_ao_add *cmd, struct tcp_ao_key *key) syn_tcp_option_space -= TCPOLEN_MSS_ALIGNED; syn_tcp_option_space -= TCPOLEN_TSTAMP_ALIGNED; syn_tcp_option_space -= TCPOLEN_WSCALE_ALIGNED; - if (tcp_ao_len(key) > syn_tcp_option_space) { + if (tcp_ao_len_aligned(key) > syn_tcp_option_space) { err = -EMSGSIZE; goto err_kfree; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5f693bbd578d..0c50c5a32b84 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -690,7 +690,7 @@ static bool tcp_v4_ao_sign_reset(const struct sock *sk, struct sk_buff *skb, reply_options[0] = htonl((TCPOPT_AO << 24) | (tcp_ao_len(key) << 16) | (aoh->rnext_keyid << 8) | keyid); - arg->iov[0].iov_len += round_up(tcp_ao_len(key), 4); + arg->iov[0].iov_len += tcp_ao_len_aligned(key); reply->doff = arg->iov[0].iov_len / 4; if (tcp_ao_hash_hdr(AF_INET, (char *)&reply_options[1], @@ -978,7 +978,7 @@ static void tcp_v4_send_ack(const struct sock *sk, (tcp_ao_len(key->ao_key) << 16) | (key->ao_key->sndid << 8) | key->rcv_next); - arg.iov[0].iov_len += round_up(tcp_ao_len(key->ao_key), 4); + arg.iov[0].iov_len += tcp_ao_len_aligned(key->ao_key); rep.th.doff = arg.iov[0].iov_len / 4; tcp_ao_hash_hdr(AF_INET, (char *)&rep.opt[offset], diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index a9807eeb311c..9e85f2a0bddd 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -615,7 +615,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, ao_key = treq->af_specific->ao_lookup(sk, req, tcp_rsk(req)->ao_keyid, -1); if (ao_key) - newtp->tcp_header_len += tcp_ao_len(ao_key); + newtp->tcp_header_len += tcp_ao_len_aligned(ao_key); #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index eb13a55d660c..93eef1dbbc55 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -825,7 +825,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, timestamps = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps); if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - remaining -= tcp_ao_len(key->ao_key); + remaining -= tcp_ao_len_aligned(key->ao_key); } } @@ -915,7 +915,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, ireq->tstamp_ok &= !ireq->sack_ok; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - remaining -= tcp_ao_len(key->ao_key); + remaining -= tcp_ao_len_aligned(key->ao_key); ireq->tstamp_ok &= !ireq->sack_ok; } @@ -982,7 +982,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb size += TCPOLEN_MD5SIG_ALIGNED; } else if (tcp_key_is_ao(key)) { opts->options |= OPTION_AO; - size += tcp_ao_len(key->ao_key); + size += tcp_ao_len_aligned(key->ao_key); } if (likely(tp->rx_opt.tstamp_ok)) { diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 937a02c2e534..8c6623496dd7 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -881,7 +881,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 if (tcp_key_is_md5(key)) tot_len += TCPOLEN_MD5SIG_ALIGNED; if (tcp_key_is_ao(key)) - tot_len += tcp_ao_len(key->ao_key); + tot_len += tcp_ao_len_aligned(key->ao_key); #ifdef CONFIG_MPTCP if (rst && !tcp_key_is_md5(key)) { -- cgit v1.2.3 From 965c00e4ea2e4df986ecd73c2fe9d3a00a2858db Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 4 Dec 2023 19:00:42 +0000 Subject: net/tcp: Limit TCP_AO_REPAIR to non-listen sockets Listen socket is not an established TCP connection, so setsockopt(TCP_AO_REPAIR) doesn't have any impact. Restrict this uAPI for listen sockets. Fixes: faadfaba5e01 ("net/tcp: Add TCP_AO_REPAIR") Signed-off-by: Dmitry Safonov Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- net/ipv4/tcp.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c9f078224569..ff6838ca2e58 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3610,6 +3610,10 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, break; case TCP_AO_REPAIR: + if (!tcp_can_repair_sock(sk)) { + err = -EPERM; + break; + } err = tcp_ao_set_repair(sk, optval, optlen); break; #ifdef CONFIG_TCP_AO @@ -4309,6 +4313,8 @@ zerocopy_rcv_out: } #endif case TCP_AO_REPAIR: + if (!tcp_can_repair_sock(sk)) + return -EPERM; return tcp_ao_get_repair(sk, optval, optlen); case TCP_AO_GET_KEYS: case TCP_AO_INFO: { -- cgit v1.2.3 From 12083d728213285c2d4347fa0ed3b556449703ce Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 4 Dec 2023 19:00:43 +0000 Subject: net/tcp: Don't add key with non-matching VRF on connected sockets If the connection was established, don't allow adding TCP-AO keys that don't match the peer. Currently, there are checks for ip-address matching, but L3 index check is missing. Add it to restrict userspace shooting itself somewhere. Yet, nothing restricts the CAP_NET_RAW user from trying to shoot themselves by performing setsockopt(SO_BINDTODEVICE) or setsockopt(SO_BINDTOIFINDEX) over an established TCP-AO connection. So, this is just "minimum effort" to potentially save someone's debugging time, rather than a full restriction on doing weird things. Fixes: 248411b8cb89 ("net/tcp: Wire up l3index to TCP-AO") Signed-off-by: Dmitry Safonov Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- net/ipv4/tcp_ao.c | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index c8be1d526eac..18dacfef7a07 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -1608,6 +1608,15 @@ static int tcp_ao_add_cmd(struct sock *sk, unsigned short int family, if (!dev || !l3index) return -EINVAL; + if (!bound_dev_if || bound_dev_if != cmd.ifindex) { + /* tcp_ao_established_key() doesn't expect having + * non peer-matching key on an established TCP-AO + * connection. + */ + if (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))) + return -EINVAL; + } + /* It's still possible to bind after adding keys or even * re-bind to a different dev (with CAP_NET_RAW). * So, no reason to return error here, rather try to be -- cgit v1.2.3 From 9396c4ee93f9ac03cd0cea0bb345fbc657772943 Mon Sep 17 00:00:00 2001 From: Dmitry Safonov Date: Mon, 4 Dec 2023 19:00:44 +0000 Subject: net/tcp: Don't store TCP-AO maclen on reqsk This extra check doesn't work for a handshake when SYN segment has (current_key.maclen != rnext_key.maclen). It could be amended to preserve rnext_key.maclen instead of current_key.maclen, but that requires a lookup on listen socket. Originally, this extra maclen check was introduced just because it was cheap. Drop it and convert tcp_request_sock::maclen into boolean tcp_request_sock::used_tcp_ao. Fixes: 06b22ef29591 ("net/tcp: Wire TCP-AO to request sockets") Signed-off-by: Dmitry Safonov Reviewed-by: Eric Dumazet Signed-off-by: Paolo Abeni --- include/linux/tcp.h | 8 ++------ net/ipv4/tcp_ao.c | 4 ++-- net/ipv4/tcp_input.c | 5 +++-- net/ipv4/tcp_output.c | 9 +++------ 4 files changed, 10 insertions(+), 16 deletions(-) (limited to 'net/ipv4') diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 68f3d315d2e1..b646b574b060 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -169,7 +169,7 @@ struct tcp_request_sock { #ifdef CONFIG_TCP_AO u8 ao_keyid; u8 ao_rcv_next; - u8 maclen; + bool used_tcp_ao; #endif }; @@ -180,14 +180,10 @@ static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req) static inline bool tcp_rsk_used_ao(const struct request_sock *req) { - /* The real length of MAC is saved in the request socket, - * signing anything with zero-length makes no sense, so here is - * a little hack.. - */ #ifndef CONFIG_TCP_AO return false; #else - return tcp_rsk(req)->maclen != 0; + return tcp_rsk(req)->used_tcp_ao; #endif } diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c index 18dacfef7a07..f8308d3f565e 100644 --- a/net/ipv4/tcp_ao.c +++ b/net/ipv4/tcp_ao.c @@ -851,7 +851,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, const struct tcp_ao_hdr *aoh; struct tcp_ao_key *key; - treq->maclen = 0; + treq->used_tcp_ao = false; if (tcp_parse_auth_options(th, NULL, &aoh) || !aoh) return; @@ -863,7 +863,7 @@ void tcp_ao_syncookie(struct sock *sk, const struct sk_buff *skb, treq->ao_rcv_next = aoh->keyid; treq->ao_keyid = aoh->rnext_keyid; - treq->maclen = tcp_ao_maclen(key); + treq->used_tcp_ao = true; } static enum skb_drop_reason diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bcb55d98004c..337c8bb07ccc 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -7182,11 +7182,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, if (tcp_parse_auth_options(tcp_hdr(skb), NULL, &aoh)) goto drop_and_release; /* Invalid TCP options */ if (aoh) { - tcp_rsk(req)->maclen = aoh->length - sizeof(struct tcp_ao_hdr); + tcp_rsk(req)->used_tcp_ao = true; tcp_rsk(req)->ao_rcv_next = aoh->keyid; tcp_rsk(req)->ao_keyid = aoh->rnext_keyid; + } else { - tcp_rsk(req)->maclen = 0; + tcp_rsk(req)->used_tcp_ao = false; } #endif tcp_rsk(req)->snt_isn = isn; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 93eef1dbbc55..f5ef15e1d9ac 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3720,7 +3720,6 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, if (tcp_rsk_used_ao(req)) { #ifdef CONFIG_TCP_AO struct tcp_ao_key *ao_key = NULL; - u8 maclen = tcp_rsk(req)->maclen; u8 keyid = tcp_rsk(req)->ao_keyid; ao_key = tcp_sk(sk)->af_specific->ao_lookup(sk, req_to_sk(req), @@ -3730,13 +3729,11 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, * for another peer-matching key, but the peer has requested * ao_keyid (RFC5925 RNextKeyID), so let's keep it simple here. */ - if (unlikely(!ao_key || tcp_ao_maclen(ao_key) != maclen)) { - u8 key_maclen = ao_key ? tcp_ao_maclen(ao_key) : 0; - + if (unlikely(!ao_key)) { rcu_read_unlock(); kfree_skb(skb); - net_warn_ratelimited("TCP-AO: the keyid %u with maclen %u|%u from SYN packet is not present - not sending SYNACK\n", - keyid, maclen, key_maclen); + net_warn_ratelimited("TCP-AO: the keyid %u from SYN packet is not present - not sending SYNACK\n", + keyid); return NULL; } key.ao_key = ao_key; -- cgit v1.2.3 From 3d501dd326fb1c73f1b8206d4c6e1d7b15c07e27 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Dec 2023 16:18:41 +0000 Subject: tcp: do not accept ACK of bytes we never sent This patch is based on a detailed report and ideas from Yepeng Pan and Christian Rossow. ACK seq validation is currently following RFC 5961 5.2 guidelines: The ACK value is considered acceptable only if it is in the range of ((SND.UNA - MAX.SND.WND) <= SEG.ACK <= SND.NXT). All incoming segments whose ACK value doesn't satisfy the above condition MUST be discarded and an ACK sent back. It needs to be noted that RFC 793 on page 72 (fifth check) says: "If the ACK is a duplicate (SEG.ACK < SND.UNA), it can be ignored. If the ACK acknowledges something not yet sent (SEG.ACK > SND.NXT) then send an ACK, drop the segment, and return". The "ignored" above implies that the processing of the incoming data segment continues, which means the ACK value is treated as acceptable. This mitigation makes the ACK check more stringent since any ACK < SND.UNA wouldn't be accepted, instead only ACKs that are in the range ((SND.UNA - MAX.SND.WND) <= SEG.ACK <= SND.NXT) get through. This can be refined for new (and possibly spoofed) flows, by not accepting ACK for bytes that were never sent. This greatly improves TCP security at a little cost. I added a Fixes: tag to make sure this patch will reach stable trees, even if the 'blamed' patch was adhering to the RFC. tp->bytes_acked was added in linux-4.2 Following packetdrill test (courtesy of Yepeng Pan) shows the issue at hand: 0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1024) = 0 // ---------------- Handshake ------------------- // // when window scale is set to 14 the window size can be extended to // 65535 * (2^14) = 1073725440. Linux would accept an ACK packet // with ack number in (Server_ISN+1-1073725440. Server_ISN+1) // ,though this ack number acknowledges some data never // sent by the server. +0 < S 0:0(0) win 65535 +0 > S. 0:0(0) ack 1 <...> +0 < . 1:1(0) ack 1 win 65535 +0 accept(3, ..., ...) = 4 // For the established connection, we send an ACK packet, // the ack packet uses ack number 1 - 1073725300 + 2^32, // where 2^32 is used to wrap around. // Note: we used 1073725300 instead of 1073725440 to avoid possible // edge cases. // 1 - 1073725300 + 2^32 = 3221241997 // Oops, old kernels happily accept this packet. +0 < . 1:1001(1000) ack 3221241997 win 65535 // After the kernel fix the following will be replaced by a challenge ACK, // and prior malicious frame would be dropped. +0 > . 1:1(0) ack 1001 Fixes: 354e4aa391ed ("tcp: RFC 5961 5.2 Blind Data Injection Attack Mitigation") Signed-off-by: Eric Dumazet Reported-by: Yepeng Pan Reported-by: Christian Rossow Acked-by: Neal Cardwell Link: https://lore.kernel.org/r/20231205161841.2702925-1-edumazet@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_input.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 337c8bb07ccc..90de838a2745 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3871,8 +3871,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) * then we can probably ignore it. */ if (before(ack, prior_snd_una)) { + u32 max_window; + + /* do not accept ACK for bytes we never sent. */ + max_window = min_t(u64, tp->max_window, tp->bytes_acked); /* RFC 5961 5.2 [Blind Data Injection Attack].[Mitigation] */ - if (before(ack, prior_snd_una - tp->max_window)) { + if (before(ack, prior_snd_una - max_window)) { if (!(flag & FLAG_NO_CHALLENGE_ACK)) tcp_send_challenge_ack(sk); return -SKB_DROP_REASON_TCP_TOO_OLD_ACK; -- cgit v1.2.3