From 5b0b9e4c2c895227c8852488b3f09839233bba54 Mon Sep 17 00:00:00 2001 From: Francesco Ruggeri Date: Wed, 20 Apr 2022 17:50:26 -0700 Subject: tcp: md5: incorrect tcp_header_len for incoming connections In tcp_create_openreq_child we adjust tcp_header_len for md5 using the remote address in newsk. But that address is still 0 in newsk at this point, and it is only set later by the callers (tcp_v[46]_syn_recv_sock). Use the address from the request socket instead. Fixes: cfb6eeb4c860 ("[TCP]: MD5 Signature Option (RFC2385) support.") Signed-off-by: Francesco Ruggeri Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20220421005026.686A45EC01F2@us226.sjc.aristanetworks.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_minisocks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6366df7aaf2a..6854bb1fb32b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -531,7 +531,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->tsoffset = treq->ts_off; #ifdef CONFIG_TCP_MD5SIG newtp->md5sig_info = NULL; /*XXX*/ - if (newtp->af_specific->md5_lookup(sk, newsk)) + if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req))) newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED; #endif if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len) -- cgit v1.2.3 From b253a0680ceadc5d7b4acca7aa2d870326cad8ad Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Wed, 20 Apr 2022 10:34:41 +0800 Subject: tcp: ensure to use the most recently sent skb when filling the rate sample If an ACK (s)acks multiple skbs, we favor the information from the most recently sent skb by choosing the skb with the highest prior_delivered count. But in the interval between receiving ACKs, we send multiple skbs with the same prior_delivered, because the tp->delivered only changes when we receive an ACK. We used RACK's solution, copying tcp_rack_sent_after() as tcp_skb_sent_after() helper to determine "which packet was sent last?". Later, we will use tcp_skb_sent_after() instead in RACK. Fixes: b9f64820fb22 ("tcp: track data delivery rate for a TCP connection") Signed-off-by: Pengcheng Yang Cc: Paolo Abeni Acked-by: Neal Cardwell Tested-by: Neal Cardwell Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/1650422081-22153-1-git-send-email-yangpc@wangsu.com Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 6 ++++++ net/ipv4/tcp_rate.c | 11 ++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index 70ca4a5e330a..be712fb9ddd7 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1042,6 +1042,7 @@ struct rate_sample { int losses; /* number of packets marked lost upon ACK */ u32 acked_sacked; /* number of packets newly (S)ACKed upon ACK */ u32 prior_in_flight; /* in flight before this ACK */ + u32 last_end_seq; /* end_seq of most recently ACKed packet */ bool is_app_limited; /* is sample from packet with bubble in pipe? */ bool is_retrans; /* is sample from retransmission? */ bool is_ack_delayed; /* is this (likely) a delayed ACK? */ @@ -1164,6 +1165,11 @@ void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost, bool is_sack_reneg, struct rate_sample *rs); void tcp_rate_check_app_limited(struct sock *sk); +static inline bool tcp_skb_sent_after(u64 t1, u64 t2, u32 seq1, u32 seq2) +{ + return t1 > t2 || (t1 == t2 && after(seq1, seq2)); +} + /* These functions determine how the current flow behaves in respect of SACK * handling. SACK is negotiated with the peer, and therefore it can vary * between different flows. diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c index fbab921670cc..9a8e014d9b5b 100644 --- a/net/ipv4/tcp_rate.c +++ b/net/ipv4/tcp_rate.c @@ -74,27 +74,32 @@ void tcp_rate_skb_sent(struct sock *sk, struct sk_buff *skb) * * If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is * called multiple times. We favor the information from the most recently - * sent skb, i.e., the skb with the highest prior_delivered count. + * sent skb, i.e., the skb with the most recently sent time and the highest + * sequence. */ void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + u64 tx_tstamp; if (!scb->tx.delivered_mstamp) return; + tx_tstamp = tcp_skb_timestamp_us(skb); if (!rs->prior_delivered || - after(scb->tx.delivered, rs->prior_delivered)) { + tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp, + scb->end_seq, rs->last_end_seq)) { rs->prior_delivered_ce = scb->tx.delivered_ce; rs->prior_delivered = scb->tx.delivered; rs->prior_mstamp = scb->tx.delivered_mstamp; rs->is_app_limited = scb->tx.is_app_limited; rs->is_retrans = scb->sacked & TCPCB_RETRANS; + rs->last_end_seq = scb->end_seq; /* Record send time of most recently ACKed packet: */ - tp->first_tx_mstamp = tcp_skb_timestamp_us(skb); + tp->first_tx_mstamp = tx_tstamp; /* Find the duration of the "send phase" of this window: */ rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp, scb->tx.first_tx_mstamp); -- cgit v1.2.3 From b9b1e0da5800a41a537f3bd1c294e492dad5cc9e Mon Sep 17 00:00:00 2001 From: Rongguang Wei Date: Wed, 20 Apr 2022 10:38:04 +0800 Subject: netfilter: flowtable: Remove the empty file CONFIG_NF_FLOW_TABLE_IPV4 is already removed and the real user is also removed(nf_flow_table_ipv4.c is empty). Fixes: c42ba4290b2147aa ("netfilter: flowtable: remove ipv4/ipv6 modules") Signed-off-by: Pablo Neira Ayuso --- net/ipv4/netfilter/nf_flow_table_ipv4.c | 0 1 file changed, 0 insertions(+), 0 deletions(-) delete mode 100644 net/ipv4/netfilter/nf_flow_table_ipv4.c (limited to 'net/ipv4') diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c deleted file mode 100644 index e69de29bb2d1..000000000000 -- cgit v1.2.3 From ff827beb706ed719c766acf36449801ded0c17fc Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 21 Apr 2022 15:07:57 -0700 Subject: ip_gre: Make o_seqno start from 0 in native mode For GRE and GRETAP devices, currently o_seqno starts from 1 in native mode. According to RFC 2890 2.2., "The first datagram is sent with a sequence number of 0." Fix it. It is worth mentioning that o_seqno already starts from 0 in collect_md mode, see gre_fb_xmit(), where tunnel->o_seqno is passed to gre_build_header() before getting incremented. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Peilin Ye Acked-by: William Tu Signed-off-by: David S. Miller --- net/ipv4/ip_gre.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'net/ipv4') diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 365caebf51ab..21a8943f6fa4 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -459,14 +459,12 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - - if (tunnel->parms.o_flags & TUNNEL_SEQ) - tunnel->o_seqno++; + __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, - tunnel->parms.o_flags, proto, tunnel->parms.o_key, - htonl(tunnel->o_seqno)); + flags, proto, tunnel->parms.o_key, + (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } -- cgit v1.2.3 From 31c417c948d7f6909cb63f0ac3298f3c38f8ce20 Mon Sep 17 00:00:00 2001 From: Peilin Ye Date: Thu, 21 Apr 2022 15:09:02 -0700 Subject: ip_gre, ip6_gre: Fix race condition on o_seqno in collect_md mode As pointed out by Jakub Kicinski, currently using TUNNEL_SEQ in collect_md mode is racy for [IP6]GRE[TAP] devices. Consider the following sequence of events: 1. An [IP6]GRE[TAP] device is created in collect_md mode using "ip link add ... external". "ip" ignores "[o]seq" if "external" is specified, so TUNNEL_SEQ is off, and the device is marked as NETIF_F_LLTX (i.e. it uses lockless TX); 2. Someone sets TUNNEL_SEQ on outgoing skb's, using e.g. bpf_skb_set_tunnel_key() in an eBPF program attached to this device; 3. gre_fb_xmit() or __gre6_xmit() processes these skb's: gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); ^^^^^^^^^^^^^^^^^ Since we are not using the TX lock (&txq->_xmit_lock), multiple CPUs may try to do this tunnel->o_seqno++ in parallel, which is racy. Fix it by making o_seqno atomic_t. As mentioned by Eric Dumazet in commit b790e01aee74 ("ip_gre: lockless xmit"), making o_seqno atomic_t increases "chance for packets being out of order at receiver" when NETIF_F_LLTX is on. Maybe a better fix would be: 1. Do not ignore "oseq" in external mode. Users MUST specify "oseq" if they want the kernel to allow sequencing of outgoing packets; 2. Reject all outgoing TUNNEL_SEQ packets if the device was not created with "oseq". Unfortunately, that would break userspace. We could now make [IP6]GRE[TAP] devices always NETIF_F_LLTX, but let us do it in separate patches to keep this fix minimal. Suggested-by: Jakub Kicinski Fixes: 77a5196a804e ("gre: add sequence number for collect md mode.") Signed-off-by: Peilin Ye Acked-by: William Tu Signed-off-by: David S. Miller --- include/net/ip6_tunnel.h | 2 +- include/net/ip_tunnels.h | 2 +- net/ipv4/ip_gre.c | 6 +++--- net/ipv6/ip6_gre.c | 7 ++++--- 4 files changed, 9 insertions(+), 8 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h index a38c4f1e4e5c..74b369bddf49 100644 --- a/include/net/ip6_tunnel.h +++ b/include/net/ip6_tunnel.h @@ -58,7 +58,7 @@ struct ip6_tnl { /* These fields used only by GRE */ __u32 i_seqno; /* The last seen seqno */ - __u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int hlen; /* tun_hlen + encap_hlen */ int tun_hlen; /* Precalculated header length */ int encap_hlen; /* Encap header length (FOU,GUE) */ diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 88dee57eac8a..c24fa934221d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -116,7 +116,7 @@ struct ip_tunnel { /* These four fields used only by GRE */ u32 i_seqno; /* The last seen seqno */ - u32 o_seqno; /* The last output seqno */ + atomic_t o_seqno; /* The last output seqno */ int tun_hlen; /* Precalculated header length */ /* These four fields used only by ERSPAN */ diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 21a8943f6fa4..aacee9dd771b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -464,7 +464,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } @@ -502,7 +502,7 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); @@ -579,7 +579,7 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) } gre_build_header(skb, 8, TUNNEL_SEQ, - proto, 0, htonl(tunnel->o_seqno++)); + proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d9e4ac94eab4..5136959b3dc5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -766,7 +766,7 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tun_hlen, flags, protocol, tunnel_id_to_key32(tun_info->key.tun_id), - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); } else { @@ -777,7 +777,8 @@ static netdev_tx_t __gre6_xmit(struct sk_buff *skb, gre_build_header(skb, tunnel->tun_hlen, flags, protocol, tunnel->parms.o_key, - (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); + (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) + : 0); } return ip6_tnl_xmit(skb, dev, dsfield, fl6, encap_limit, pmtu, @@ -1055,7 +1056,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* Push GRE header. */ proto = (t->parms.erspan_ver == 1) ? htons(ETH_P_ERSPAN) : htons(ETH_P_ERSPAN2); - gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(t->o_seqno++)); + gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&t->o_seqno))); /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) -- cgit v1.2.3 From 4bfe744ff1644fbc0a991a2677dc874475dd6776 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 24 Apr 2022 17:34:07 -0700 Subject: tcp: fix potential xmit stalls caused by TCP_NOTSENT_LOWAT I had this bug sitting for too long in my pile, it is time to fix it. Thanks to Doug Porter for reminding me of it! We had various attempts in the past, including commit 0cbe6a8f089e ("tcp: remove SOCK_QUEUE_SHRUNK"), but the issue is that TCP stack currently only generates EPOLLOUT from input path, when tp->snd_una has advanced and skb(s) cleaned from rtx queue. If a flow has a big RTT, and/or receives SACKs, it is possible that the notsent part (tp->write_seq - tp->snd_nxt) reaches 0 and no more data can be sent until tp->snd_una finally advances. What is needed is to also check if POLLOUT needs to be generated whenever tp->snd_nxt is advanced, from output path. This bug triggers more often after an idle period, as we do not receive ACK for at least one RTT. tcp_notsent_lowat could be a fraction of what CWND and pacing rate would allow to send during this RTT. In a followup patch, I will remove the bogus call to tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED) from tcp_check_space(). Fact that we have decided to generate an EPOLLOUT does not mean the application has immediately refilled the transmit queue. This optimistic call might have been the reason the bug seemed not too serious. Tested: 200 ms rtt, 1% packet loss, 32 MB tcp_rmem[2] and tcp_wmem[2] $ echo 500000 >/proc/sys/net/ipv4/tcp_notsent_lowat $ cat bench_rr.sh SUM=0 for i in {1..10} do V=`netperf -H remote_host -l30 -t TCP_RR -- -r 10000000,10000 -o LOCAL_BYTES_SENT | egrep -v "MIGRATED|Bytes"` echo $V SUM=$(($SUM + $V)) done echo SUM=$SUM Before patch: $ bench_rr.sh 130000000 80000000 140000000 140000000 140000000 140000000 130000000 40000000 90000000 110000000 SUM=1140000000 After patch: $ bench_rr.sh 430000000 590000000 530000000 450000000 450000000 350000000 450000000 490000000 480000000 460000000 SUM=4680000000 # This is 410 % of the value before patch. Fixes: c9bee3b7fdec ("tcp: TCP_NOTSENT_LOWAT socket option") Signed-off-by: Eric Dumazet Reported-by: Doug Porter Cc: Soheil Hassas Yeganeh Cc: Neal Cardwell Acked-by: Soheil Hassas Yeganeh Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/tcp_input.c | 12 +++++++++++- net/ipv4/tcp_output.c | 1 + 3 files changed, 13 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index be712fb9ddd7..b99d9d9cbd99 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -620,6 +620,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk, struct sk_buff *skb); void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); void tcp_fin(struct sock *sk); +void tcp_check_space(struct sock *sk); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2088f93fa37b..48f607522860 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -5454,7 +5454,17 @@ static void tcp_new_space(struct sock *sk) INDIRECT_CALL_1(sk->sk_write_space, sk_stream_write_space, sk); } -static void tcp_check_space(struct sock *sk) +/* Caller made space either from: + * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced) + * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt) + * + * We might be able to generate EPOLLOUT to the application if: + * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2 + * 2) notsent amount (tp->write_seq - tp->snd_nxt) became + * small enough that tcp_stream_memory_free() decides it + * is time to generate EPOLLOUT. + */ +void tcp_check_space(struct sock *sk) { /* pairs with tcp_poll() */ smp_mb(); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9ede847f4199..1ca2f28c9981 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -82,6 +82,7 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT, tcp_skb_pcount(skb)); + tcp_check_space(sk); } /* SND.NXT, if window was not shrunk or the amount of shrunk was less than one -- cgit v1.2.3 From ba5a4fdd63ae0c575707030db0b634b160baddd7 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Sun, 24 Apr 2022 13:35:09 -0700 Subject: tcp: make sure treq->af_specific is initialized syzbot complained about a recent change in TCP stack, hitting a NULL pointer [1] tcp request sockets have an af_specific pointer, which was used before the blamed change only for SYNACK generation in non SYNCOOKIE mode. tcp requests sockets momentarily created when third packet coming from client in SYNCOOKIE mode were not using treq->af_specific. Make sure this field is populated, in the same way normal TCP requests sockets do in tcp_conn_request(). [1] TCP: request_sock_TCPv6: Possible SYN flooding on port 20002. Sending cookies. Check SNMP counters. general protection fault, probably for non-canonical address 0xdffffc0000000001: 0000 [#1] PREEMPT SMP KASAN KASAN: null-ptr-deref in range [0x0000000000000008-0x000000000000000f] CPU: 1 PID: 3695 Comm: syz-executor864 Not tainted 5.18.0-rc3-syzkaller-00224-g5fd1fe4807f9 #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:tcp_create_openreq_child+0xe16/0x16b0 net/ipv4/tcp_minisocks.c:534 Code: 48 c1 ea 03 80 3c 02 00 0f 85 e5 07 00 00 4c 8b b3 28 01 00 00 48 b8 00 00 00 00 00 fc ff df 49 8d 7e 08 48 89 fa 48 c1 ea 03 <80> 3c 02 00 0f 85 c9 07 00 00 48 8b 3c 24 48 89 de 41 ff 56 08 48 RSP: 0018:ffffc90000de0588 EFLAGS: 00010202 RAX: dffffc0000000000 RBX: ffff888076490330 RCX: 0000000000000100 RDX: 0000000000000001 RSI: ffffffff87d67ff0 RDI: 0000000000000008 RBP: ffff88806ee1c7f8 R08: 0000000000000000 R09: 0000000000000000 R10: ffffffff87d67f00 R11: 0000000000000000 R12: ffff88806ee1bfc0 R13: ffff88801b0e0368 R14: 0000000000000000 R15: 0000000000000000 FS: 00007f517fe58700(0000) GS:ffff8880b9d00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffcead76960 CR3: 000000006f97b000 CR4: 00000000003506e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tcp_v6_syn_recv_sock+0x199/0x23b0 net/ipv6/tcp_ipv6.c:1267 tcp_get_cookie_sock+0xc9/0x850 net/ipv4/syncookies.c:207 cookie_v6_check+0x15c3/0x2340 net/ipv6/syncookies.c:258 tcp_v6_cookie_check net/ipv6/tcp_ipv6.c:1131 [inline] tcp_v6_do_rcv+0x1148/0x13b0 net/ipv6/tcp_ipv6.c:1486 tcp_v6_rcv+0x3305/0x3840 net/ipv6/tcp_ipv6.c:1725 ip6_protocol_deliver_rcu+0x2e9/0x1900 net/ipv6/ip6_input.c:422 ip6_input_finish+0x14c/0x2c0 net/ipv6/ip6_input.c:464 NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ip6_input+0x9c/0xd0 net/ipv6/ip6_input.c:473 dst_input include/net/dst.h:461 [inline] ip6_rcv_finish net/ipv6/ip6_input.c:76 [inline] NF_HOOK include/linux/netfilter.h:307 [inline] NF_HOOK include/linux/netfilter.h:301 [inline] ipv6_rcv+0x27f/0x3b0 net/ipv6/ip6_input.c:297 __netif_receive_skb_one_core+0x114/0x180 net/core/dev.c:5405 __netif_receive_skb+0x24/0x1b0 net/core/dev.c:5519 process_backlog+0x3a0/0x7c0 net/core/dev.c:5847 __napi_poll+0xb3/0x6e0 net/core/dev.c:6413 napi_poll net/core/dev.c:6480 [inline] net_rx_action+0x8ec/0xc60 net/core/dev.c:6567 __do_softirq+0x29b/0x9c2 kernel/softirq.c:558 invoke_softirq kernel/softirq.c:432 [inline] __irq_exit_rcu+0x123/0x180 kernel/softirq.c:637 irq_exit_rcu+0x5/0x20 kernel/softirq.c:649 sysvec_apic_timer_interrupt+0x93/0xc0 arch/x86/kernel/apic/apic.c:1097 Fixes: 5b0b9e4c2c89 ("tcp: md5: incorrect tcp_header_len for incoming connections") Signed-off-by: Eric Dumazet Cc: Francesco Ruggeri Signed-off-by: David S. Miller --- include/net/tcp.h | 1 + net/ipv4/syncookies.c | 8 +++++++- net/ipv6/syncookies.c | 3 ++- 3 files changed, 10 insertions(+), 2 deletions(-) (limited to 'net/ipv4') diff --git a/include/net/tcp.h b/include/net/tcp.h index b99d9d9cbd99..cc1295037533 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -480,6 +480,7 @@ int __cookie_v4_check(const struct iphdr *iph, const struct tcphdr *th, u32 cookie); struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb); #ifdef CONFIG_SYN_COOKIES diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 2cb3b852d148..f33c31dd7366 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -281,6 +281,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, EXPORT_SYMBOL(cookie_ecn_ok); struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, + const struct tcp_request_sock_ops *af_ops, struct sock *sk, struct sk_buff *skb) { @@ -297,6 +298,10 @@ struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops, return NULL; treq = tcp_rsk(req); + + /* treq->af_specific might be used to perform TCP_MD5 lookup */ + treq->af_specific = af_ops; + treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield; #if IS_ENABLED(CONFIG_MPTCP) treq->is_mptcp = sk_is_mptcp(sk); @@ -364,7 +369,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, + &tcp_request_sock_ipv4_ops, sk, skb); if (!req) goto out; diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index d1b61d00368e..9cc123f000fb 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -170,7 +170,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out; ret = NULL; - req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, sk, skb); + req = cookie_tcp_reqsk_alloc(&tcp6_request_sock_ops, + &tcp_request_sock_ipv6_ops, sk, skb); if (!req) goto out; -- cgit v1.2.3 From d9157f6806d1499e173770df1f1b234763de5c79 Mon Sep 17 00:00:00 2001 From: Pengcheng Yang Date: Tue, 26 Apr 2022 18:03:39 +0800 Subject: tcp: fix F-RTO may not work correctly when receiving DSACK Currently DSACK is regarded as a dupack, which may cause F-RTO to incorrectly enter "loss was real" when receiving DSACK. Packetdrill to demonstrate: // Enable F-RTO and TLP 0 `sysctl -q net.ipv4.tcp_frto=2` 0 `sysctl -q net.ipv4.tcp_early_retrans=3` 0 `sysctl -q net.ipv4.tcp_congestion_control=cubic` // Establish a connection +0 socket(..., SOCK_STREAM, IPPROTO_TCP) = 3 +0 setsockopt(3, SOL_SOCKET, SO_REUSEADDR, [1], 4) = 0 +0 bind(3, ..., ...) = 0 +0 listen(3, 1) = 0 // RTT 10ms, RTO 210ms +.1 < S 0:0(0) win 32792 +0 > S. 0:0(0) ack 1 <...> +.01 < . 1:1(0) ack 1 win 257 +0 accept(3, ..., ...) = 4 // Send 2 data segments +0 write(4, ..., 2000) = 2000 +0 > P. 1:2001(2000) ack 1 // TLP +.022 > P. 1001:2001(1000) ack 1 // Continue to send 8 data segments +0 write(4, ..., 10000) = 10000 +0 > P. 2001:10001(8000) ack 1 // RTO +.188 > . 1:1001(1000) ack 1 // The original data is acked and new data is sent(F-RTO step 2.b) +0 < . 1:1(0) ack 2001 win 257 +0 > P. 10001:12001(2000) ack 1 // D-SACK caused by TLP is regarded as a dupack, this results in // the incorrect judgment of "loss was real"(F-RTO step 3.a) +.022 < . 1:1(0) ack 2001 win 257 // Never-retransmitted data(3001:4001) are acked and // expect to switch to open state(F-RTO step 3.b) +0 < . 1:1(0) ack 4001 win 257 +0 %{ assert tcpi_ca_state == 0, tcpi_ca_state }% Fixes: e33099f96d99 ("tcp: implement RFC5682 F-RTO") Signed-off-by: Pengcheng Yang Acked-by: Neal Cardwell Tested-by: Neal Cardwell Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/1650967419-2150-1-git-send-email-yangpc@wangsu.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_input.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/ipv4') diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 48f607522860..60f99e9fb6d1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3867,7 +3867,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_process_tlp_ack(sk, ack, flag); if (tcp_ack_is_dubious(sk, flag)) { - if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) { + if (!(flag & (FLAG_SND_UNA_ADVANCED | + FLAG_NOT_DUP | FLAG_DSACKING_ACK))) { num_dupack = 1; /* Consider if pure acks were aggregated in tcp_add_backlog() */ if (!(flag & FLAG_DATA)) -- cgit v1.2.3