From 9d9b1ee0b2d1c9e02b2338c4a4b0a062d2d3edac Mon Sep 17 00:00:00 2001 From: Enke Chen Date: Fri, 15 Jan 2021 14:30:58 -0800 Subject: tcp: fix TCP_USER_TIMEOUT with zero window 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 --- net/ipv4/tcp_timer.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 6c62b9ea1320..454732ecc8f3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -349,6 +349,7 @@ static void tcp_probe_timer(struct sock *sk) if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; + icsk->icsk_probes_tstamp = 0; return; } @@ -360,13 +361,12 @@ 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)) { -- cgit From 9c30ae8398b0813e237bde387d67a7f74ab2db2d Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Tue, 19 Jan 2021 11:26:19 -0800 Subject: tcp: fix TCP socket rehash stats mis-accounting The previous commit 32efcc06d2a1 ("tcp: export count for rehash attempts") would mis-account rehashing SNMP and socket stats: a. During handshake of an active open, only counts the first SYN timeout b. After handshake of passive and active open, stop updating after (roughly) TCP_RETRIES1 recurring RTOs c. After the socket aborts, over count timeout_rehash by 1 This patch fixes this by checking the rehash result from sk_rethink_txhash. Fixes: 32efcc06d2a1 ("tcp: export count for rehash attempts") Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Link: https://lore.kernel.org/r/20210119192619.1848270-1-ycheng@google.com Signed-off-by: Jakub Kicinski --- net/ipv4/tcp_timer.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 454732ecc8f3..faa92948441b 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -219,14 +219,8 @@ static int tcp_write_timeout(struct sock *sk) int retry_until; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { - if (icsk->icsk_retransmits) { - dst_negative_advice(sk); - } else { - sk_rethink_txhash(sk); - tp->timeout_rehash++; - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPTIMEOUTREHASH); - } + if (icsk->icsk_retransmits) + __dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; expired = icsk->icsk_retransmits >= retry_until; } else { @@ -234,12 +228,7 @@ static int tcp_write_timeout(struct sock *sk) /* Black hole detection */ tcp_mtu_probing(icsk, sk); - dst_negative_advice(sk); - } else { - sk_rethink_txhash(sk); - tp->timeout_rehash++; - __NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPTIMEOUTREHASH); + __dst_negative_advice(sk); } retry_until = net->ipv4.sysctl_tcp_retries2; @@ -270,6 +259,11 @@ static int tcp_write_timeout(struct sock *sk) return 1; } + if (sk_rethink_txhash(sk)) { + tp->timeout_rehash++; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); + } + return 0; } -- cgit