From f7020c437e138507d50c3f167342870f24d2432f Mon Sep 17 00:00:00 2001 From: Enke Chen Date: Fri, 15 Jan 2021 14:30:58 -0800 Subject: [PATCH] tcp: fix TCP_USER_TIMEOUT with zero window commit 9d9b1ee0b2d1c9e02b2338c4a4b0a062d2d3edac upstream. The TCP session does not terminate with TCP_USER_TIMEOUT when data remain untransmitted due to zero window. The number of unanswered zero-window probes (tcp_probes_out) is reset to zero with incoming acks irrespective of the window size, as described in tcp_probe_timer(): RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as long as the receiver continues to respond probes. We support this by default and reset icsk_probes_out with incoming ACKs. This counter, however, is the wrong one to be used in calculating the duration that the window remains closed and data remain untransmitted. Thanks to Jonathan Maxwell for diagnosing the actual issue. In this patch a new timestamp is introduced for the socket in order to track the elapsed time for the zero-window probes that have not been answered with any non-zero window ack. Fixes: 9721e709fa68 ("tcp: simplify window probe aborting on USER_TIMEOUT") Reported-by: William McCall Co-developed-by: Neal Cardwell Signed-off-by: Neal Cardwell Signed-off-by: Enke Chen Reviewed-by: Yuchung Cheng Reviewed-by: Eric Dumazet Link: https://lore.kernel.org/r/20210115223058.GA39267@localhost.localdomain Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/inet_connection_sock.h | 3 +++ net/ipv4/inet_connection_sock.c | 1 + net/ipv4/tcp.c | 1 + net/ipv4/tcp_input.c | 1 + net/ipv4/tcp_output.c | 1 + net/ipv4/tcp_timer.c | 14 +++++++------- 6 files changed, 14 insertions(+), 7 deletions(-) diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index c71eb294da95..6c8f8e5e33c3 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -83,6 +83,8 @@ struct inet_connection_sock_af_ops { * @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options) * @icsk_ack: Delayed ACK control data * @icsk_mtup; MTU probing control data + * @icsk_probes_tstamp: Probe timestamp (cleared by non-zero window ack) + * @icsk_user_timeout: TCP_USER_TIMEOUT value */ struct inet_connection_sock { /* inet_sock has to be the first member! */ @@ -133,6 +135,7 @@ struct inet_connection_sock { u32 probe_timestamp; } icsk_mtup; + u32 icsk_probes_tstamp; u32 icsk_user_timeout; u64 icsk_ca_priv[104 / sizeof(u64)]; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 9745c52f49ca..ac5c4f6cdefe 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -840,6 +840,7 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, newicsk->icsk_retransmits = 0; newicsk->icsk_backoff = 0; newicsk->icsk_probes_out = 0; + newicsk->icsk_probes_tstamp = 0; /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d3ced6a39bcf..6ddec8a23942 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2627,6 +2627,7 @@ int tcp_disconnect(struct sock *sk, int flags) icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; + icsk->icsk_probes_tstamp = 0; icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd = TCP_INIT_CWND; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index adace90f49fa..7411a4313462 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3286,6 +3286,7 @@ static void tcp_ack_probe(struct sock *sk) return; if (!after(TCP_SKB_CB(head)->end_seq, tcp_wnd_end(tp))) { icsk->icsk_backoff = 0; + icsk->icsk_probes_tstamp = 0; inet_csk_clear_xmit_timer(sk, ICSK_TIME_PROBE0); /* Socket must be waked up by subsequent tcp_data_snd_check(). * This function is not for random using! diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 5e311e6a31d5..5da6ffce390c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3835,6 +3835,7 @@ void tcp_send_probe0(struct sock *sk) /* Cancel probe timer, if it is not required. */ icsk->icsk_probes_out = 0; icsk->icsk_backoff = 0; + icsk->icsk_probes_tstamp = 0; return; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index dd5a6317a801..7fcd116fbd37 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -344,6 +344,7 @@ static void tcp_probe_timer(struct sock *sk) if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; + icsk->icsk_probes_tstamp = 0; return; } @@ -355,13 +356,12 @@ static void tcp_probe_timer(struct sock *sk) * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ - if (icsk->icsk_user_timeout) { - u32 elapsed = tcp_model_timeout(sk, icsk->icsk_probes_out, - tcp_probe0_base(sk)); - - if (elapsed >= icsk->icsk_user_timeout) - goto abort; - } + if (!icsk->icsk_probes_tstamp) + icsk->icsk_probes_tstamp = tcp_jiffies32; + else if (icsk->icsk_user_timeout && + (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= + msecs_to_jiffies(icsk->icsk_user_timeout)) + goto abort; max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) {