From 7faee5c0d514162853a343d93e4a0b6bb8bfec21 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 5 Sep 2014 15:33:33 -0700 Subject: tcp: remove TCP_SKB_CB(skb)->when After commit 740b0f1841f6 ("tcp: switch rtt estimations to usec resolution"), we no longer need to maintain timestamps in two different fields. TCP_SKB_CB(skb)->when can be removed, as same information sits in skb_mstamp.stamp_jiffies Signed-off-by: Eric Dumazet Acked-by: Yuchung Cheng Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index df90cd1ce37..a339e7ba05a 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -135,10 +135,9 @@ static bool retransmits_timed_out(struct sock *sk, if (!inet_csk(sk)->icsk_retransmits) return false; - if (unlikely(!tcp_sk(sk)->retrans_stamp)) - start_ts = TCP_SKB_CB(tcp_write_queue_head(sk))->when; - else - start_ts = tcp_sk(sk)->retrans_stamp; + start_ts = tcp_sk(sk)->retrans_stamp; + if (unlikely(!start_ts)) + start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk)); if (likely(timeout == 0)) { linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); -- cgit v1.2.3-70-g09d2 From fcdd1cf4dd63aecf86c987d7f4ec7187be5c2fbc Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 22 Sep 2014 13:19:44 -0700 Subject: tcp: avoid possible arithmetic overflows icsk_rto is a 32bit field, and icsk_backoff can reach 15 by default, or more if some sysctl (eg tcp_retries2) are changed. Better use 64bit to perform icsk_rto << icsk_backoff operations As Joe Perches suggested, add a helper for this. Yuchung spotted the tcp_v4_err() case. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/inet_connection_sock.h | 9 +++++++++ net/ipv4/tcp_input.c | 5 +++-- net/ipv4/tcp_ipv4.c | 6 +++--- net/ipv4/tcp_output.c | 13 ++++++------- net/ipv4/tcp_timer.c | 4 ++-- 5 files changed, 23 insertions(+), 14 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 5fbe6568c3c..848e85cb5c6 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -242,6 +242,15 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, #endif } +static inline unsigned long +inet_csk_rto_backoff(const struct inet_connection_sock *icsk, + unsigned long max_when) +{ + u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff; + + return (unsigned long)min_t(u64, when, max_when); +} + struct sock *inet_csk_accept(struct sock *sk, int flags, int *err); struct request_sock *inet_csk_search_req(const struct sock *sk, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 02fb66d4a01..13f3da4762e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3208,9 +3208,10 @@ static void tcp_ack_probe(struct sock *sk) * This function is not for random using! */ } else { + unsigned long when = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); + inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX), - TCP_RTO_MAX); + when, TCP_RTO_MAX); } } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 006b045716d..3b2e49cb2b6 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -430,9 +430,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) break; icsk->icsk_backoff--; - inet_csk(sk)->icsk_rto = (tp->srtt_us ? __tcp_set_rto(tp) : - TCP_TIMEOUT_INIT) << icsk->icsk_backoff; - tcp_bound_rto(sk); + icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : + TCP_TIMEOUT_INIT; + icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); skb = tcp_write_queue_head(sk); BUG_ON(!skb); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7f1280dcad5..8c61a7c0c88 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -3279,6 +3279,7 @@ void tcp_send_probe0(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + unsigned long probe_max; int err; err = tcp_write_wakeup(sk); @@ -3294,9 +3295,7 @@ void tcp_send_probe0(struct sock *sk) if (icsk->icsk_backoff < sysctl_tcp_retries2) icsk->icsk_backoff++; icsk->icsk_probes_out++; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - min(icsk->icsk_rto << icsk->icsk_backoff, TCP_RTO_MAX), - TCP_RTO_MAX); + probe_max = TCP_RTO_MAX; } else { /* If packet was not sent due to local congestion, * do not backoff and do not remember icsk_probes_out. @@ -3306,11 +3305,11 @@ void tcp_send_probe0(struct sock *sk) */ if (!icsk->icsk_probes_out) icsk->icsk_probes_out = 1; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - min(icsk->icsk_rto << icsk->icsk_backoff, - TCP_RESOURCE_PROBE_INTERVAL), - TCP_RTO_MAX); + probe_max = TCP_RESOURCE_PROBE_INTERVAL; } + inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0, + inet_csk_rto_backoff(icsk, probe_max), + TCP_RTO_MAX); } int tcp_rtx_synack(struct sock *sk, struct request_sock *req) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index a339e7ba05a..b24360f6e29 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -180,7 +180,7 @@ static int tcp_write_timeout(struct sock *sk) retry_until = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { - const int alive = (icsk->icsk_rto < TCP_RTO_MAX); + const int alive = icsk->icsk_rto < TCP_RTO_MAX; retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || @@ -294,7 +294,7 @@ static void tcp_probe_timer(struct sock *sk) max_probes = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { - const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX); + const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; max_probes = tcp_orphan_retries(sk, alive); -- cgit v1.2.3-70-g09d2 From b248230c34970a6c1c17c591d63b464e8d2cfc33 Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Mon, 29 Sep 2014 13:20:38 -0700 Subject: tcp: abort orphan sockets stalling on zero window probes Currently we have two different policies for orphan sockets that repeatedly stall on zero window ACKs. If a socket gets a zero window ACK when it is transmitting data, the RTO is used to probe the window. The socket is aborted after roughly tcp_orphan_retries() retries (as in tcp_write_timeout()). But if the socket was idle when it received the zero window ACK, and later wants to send more data, we use the probe timer to probe the window. If the receiver always returns zero window ACKs, icsk_probes keeps getting reset in tcp_ack() and the orphan socket can stall forever until the system reaches the orphan limit (as commented in tcp_probe_timer()). This opens up a simple attack to create lots of hanging orphan sockets to burn the memory and the CPU, as demonstrated in the recent netdev post "TCP connection will hang in FIN_WAIT1 after closing if zero window is advertised." http://www.spinics.net/lists/netdev/msg296539.html This patch follows the design in RTO-based probe: we abort an orphan socket stalling on zero window when the probe timer reaches both the maximum backoff and the maximum RTO. For example, an 100ms RTT connection will timeout after roughly 153 seconds (0.3 + 0.6 + .... + 76.8) if the receiver keeps the window shut. If the orphan socket passes this check, but the system already has too many orphans (as in tcp_out_of_resources()), we still abort it but we'll also send an RST packet as the connection may still be active. In addition, we change TCP_USER_TIMEOUT to cover (life or dead) sockets stalled on zero-window probes. This changes the semantics of TCP_USER_TIMEOUT slightly because it previously only applies when the socket has pending transmission. Signed-off-by: Yuchung Cheng Signed-off-by: Eric Dumazet Signed-off-by: Neal Cardwell Reported-by: Andrey Dmitrov Signed-off-by: David S. Miller --- net/ipv4/tcp.c | 2 +- net/ipv4/tcp_timer.c | 41 +++++++++++++++++++++-------------------- 2 files changed, 22 insertions(+), 21 deletions(-) (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5c170340f68..26a6f113f00 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2693,7 +2693,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, break; #endif case TCP_USER_TIMEOUT: - /* Cap the max timeout in ms TCP will retry/retrans + /* Cap the max time in ms TCP will retry or probe the window * before giving up and aborting (ETIMEDOUT) a connection. */ if (val < 0) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index b24360f6e29..9b21ae8b2e3 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -52,7 +52,7 @@ static void tcp_write_err(struct sock *sk) * limit. * 2. If we have strong memory pressure. */ -static int tcp_out_of_resources(struct sock *sk, int do_reset) +static int tcp_out_of_resources(struct sock *sk, bool do_reset) { struct tcp_sock *tp = tcp_sk(sk); int shift = 0; @@ -72,7 +72,7 @@ static int tcp_out_of_resources(struct sock *sk, int do_reset) if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || /* 2. Window is closed. */ (!tp->snd_wnd && !tp->packets_out)) - do_reset = 1; + do_reset = true; if (do_reset) tcp_send_active_reset(sk, GFP_ATOMIC); tcp_done(sk); @@ -270,40 +270,41 @@ static void tcp_probe_timer(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; + u32 start_ts; if (tp->packets_out || !tcp_send_head(sk)) { icsk->icsk_probes_out = 0; return; } - /* *WARNING* RFC 1122 forbids this - * - * It doesn't AFAIK, because we kill the retransmit timer -AK - * - * FIXME: We ought not to do it, Solaris 2.5 actually has fixing - * this behaviour in Solaris down as a bug fix. [AC] - * - * Let me to explain. icsk_probes_out is zeroed by incoming ACKs - * even if they advertise zero window. Hence, connection is killed only - * if we received no ACKs for normal connection timeout. It is not killed - * only because window stays zero for some time, window may be zero - * until armageddon and even later. We are in full accordance - * with RFCs, only probe timer combines both retransmission timeout - * and probe timeout in one bottle. --ANK + /* 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. But if the + * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we + * kill the socket when the retry count and the time exceeds the + * corresponding system limit. We also implement similar policy when + * we use RTO to probe window in tcp_retransmit_timer(). */ - max_probes = sysctl_tcp_retries2; + start_ts = tcp_skb_timestamp(tcp_send_head(sk)); + if (!start_ts) + skb_mstamp_get(&tcp_send_head(sk)->skb_mstamp); + else if (icsk->icsk_user_timeout && + (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout) + goto abort; + max_probes = sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { const int alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; max_probes = tcp_orphan_retries(sk, alive); - - if (tcp_out_of_resources(sk, alive || icsk->icsk_probes_out <= max_probes)) + if (!alive && icsk->icsk_backoff >= max_probes) + goto abort; + if (tcp_out_of_resources(sk, true)) return; } if (icsk->icsk_probes_out > max_probes) { - tcp_write_err(sk); +abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ tcp_send_probe0(sk); -- cgit v1.2.3-70-g09d2