diff options
Diffstat (limited to 'net/ipv4/tcp_timer.c')
| -rw-r--r-- | net/ipv4/tcp_timer.c | 718 |
1 files changed, 486 insertions, 232 deletions
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 4b85e6f636c9..160080c9021d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket @@ -21,74 +22,135 @@ #include <linux/module.h> #include <linux/gfp.h> #include <net/tcp.h> +#include <net/rstreason.h> -int sysctl_tcp_syn_retries __read_mostly = TCP_SYN_RETRIES; -int sysctl_tcp_synack_retries __read_mostly = TCP_SYNACK_RETRIES; -int sysctl_tcp_keepalive_time __read_mostly = TCP_KEEPALIVE_TIME; -int sysctl_tcp_keepalive_probes __read_mostly = TCP_KEEPALIVE_PROBES; -int sysctl_tcp_keepalive_intvl __read_mostly = TCP_KEEPALIVE_INTVL; -int sysctl_tcp_retries1 __read_mostly = TCP_RETR1; -int sysctl_tcp_retries2 __read_mostly = TCP_RETR2; -int sysctl_tcp_orphan_retries __read_mostly; -int sysctl_tcp_thin_linear_timeouts __read_mostly; +static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_sock *tp = tcp_sk(sk); + u32 elapsed, user_timeout; + s32 remaining; -static void tcp_write_err(struct sock *sk) + user_timeout = READ_ONCE(icsk->icsk_user_timeout); + if (!user_timeout) + return icsk->icsk_rto; + + elapsed = tcp_time_stamp_ts(tp) - tp->retrans_stamp; + if (tp->tcp_usec_ts) + elapsed /= USEC_PER_MSEC; + + remaining = user_timeout - elapsed; + if (remaining <= 0) + return 1; /* user timeout has passed; fire ASAP */ + + return min_t(u32, icsk->icsk_rto, msecs_to_jiffies(remaining)); +} + +u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when) { - sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT; - sk->sk_error_report(sk); + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 remaining, user_timeout; + s32 elapsed; - tcp_done(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); + user_timeout = READ_ONCE(icsk->icsk_user_timeout); + if (!user_timeout || !icsk->icsk_probes_tstamp) + return when; + + elapsed = tcp_jiffies32 - icsk->icsk_probes_tstamp; + if (unlikely(elapsed < 0)) + elapsed = 0; + remaining = msecs_to_jiffies(user_timeout) - elapsed; + remaining = max_t(u32, remaining, TCP_TIMEOUT_MIN); + + return min_t(u32, remaining, when); } -/* Do not allow orphaned sockets to eat all our resources. - * This is direct violation of TCP specs, but it is required - * to prevent DoS attacks. It is called when a retransmission timeout - * or zero probe timeout occurs on orphaned socket. +/** + * tcp_write_err() - close socket and save error info + * @sk: The socket the error has appeared on. + * + * Returns: Nothing (void) + */ + +static void tcp_write_err(struct sock *sk) +{ + tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT); +} + +/** + * tcp_out_of_resources() - Close socket if out of resources + * @sk: pointer to current socket + * @do_reset: send a last packet with reset flag + * + * Do not allow orphaned sockets to eat all our resources. + * This is direct violation of TCP specs, but it is required + * to prevent DoS attacks. It is called when a retransmission timeout + * or zero probe timeout occurs on orphaned socket. + * + * Also close if our net namespace is exiting; in that case there is no + * hope of ever communicating again since all netns interfaces are already + * down (or about to be down), and we need to release our dst references, + * which have been moved to the netns loopback interface, so the namespace + * can finish exiting. This condition is only possible if we are a kernel + * socket, as those do not hold references to the namespace. * - * Criteria is still not confirmed experimentally and may change. - * We kill the socket, if: - * 1. If number of orphaned sockets exceeds an administratively configured - * limit. - * 2. If we have strong memory pressure. + * Criteria is still not confirmed experimentally and may change. + * We kill the socket, if: + * 1. If number of orphaned sockets exceeds an administratively configured + * limit. + * 2. If we have strong memory pressure. + * 3. If our net namespace is exiting. */ -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; /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset) + if ((s32)(tcp_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset) shift++; /* If some dubious ICMP arrived, penalize even more. */ - if (sk->sk_err_soft) + if (READ_ONCE(sk->sk_err_soft)) shift++; if (tcp_check_oom(sk, shift)) { /* Catch exceptional cases, when connection requires reset. * 1. Last segment was sent recently. */ - if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN || + if ((s32)(tcp_jiffies32 - 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_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_TCP_ABORT_ON_MEMORY); tcp_done(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY); return 1; } + + if (!check_net(sock_net(sk))) { + /* Not possible to send reset; just close */ + tcp_done(sk); + return 1; + } + return 0; } -/* Calculate maximal number or retries on an orphaned socket. */ -static int tcp_orphan_retries(struct sock *sk, int alive) +/** + * tcp_orphan_retries() - Returns maximal number of retries on an orphaned socket + * @sk: Pointer to the current socket. + * @alive: bool, socket alive state + */ +static int tcp_orphan_retries(struct sock *sk, bool alive) { - int retries = sysctl_tcp_orphan_retries; /* May be zero. */ + int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ - if (sk->sk_err_soft && !alive) + if (READ_ONCE(sk->sk_err_soft) && !alive) retries = 0; /* However, if socket sent something recently, select some safe @@ -101,262 +163,397 @@ static int tcp_orphan_retries(struct sock *sk, int alive) static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) { + const struct net *net = sock_net(sk); + int mss; + /* Black hole detection */ - if (sysctl_tcp_mtu_probing) { - if (!icsk->icsk_mtup.enabled) { - icsk->icsk_mtup.enabled = 1; - tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); - } else { - struct tcp_sock *tp = tcp_sk(sk); - int mss; - - mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; - mss = min(sysctl_tcp_base_mss, mss); - mss = max(mss, 68 - tp->tcp_header_len); - icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); - tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); - } + if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) + return; + + if (!icsk->icsk_mtup.enabled) { + icsk->icsk_mtup.enabled = 1; + icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; + } else { + mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; + mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } + tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } -/* This function calculates a "timeout" which is equivalent to the timeout of a - * TCP connection after "boundary" unsuccessful, exponentially backed-off - * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if - * syn_set flag is set. +static unsigned int tcp_model_timeout(struct sock *sk, + unsigned int boundary, + unsigned int rto_base) +{ + unsigned int linear_backoff_thresh, timeout; + + linear_backoff_thresh = ilog2(tcp_rto_max(sk) / rto_base); + if (boundary <= linear_backoff_thresh) + timeout = ((2 << boundary) - 1) * rto_base; + else + timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + + (boundary - linear_backoff_thresh) * tcp_rto_max(sk); + return jiffies_to_msecs(timeout); +} +/** + * retransmits_timed_out() - returns true if this connection has timed out + * @sk: The current socket + * @boundary: max number of retransmissions + * @timeout: A custom timeout value. + * If set to 0 the default timeout is calculated and used. + * Using TCP_RTO_MIN and the number of unsuccessful retransmits. + * + * The default "timeout" value this function can calculate and use + * is equivalent to the timeout of a TCP Connection + * after "boundary" unsuccessful, exponentially backed-off + * retransmissions with an initial RTO of TCP_RTO_MIN. */ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, - unsigned int timeout, - bool syn_set) + unsigned int timeout) { - unsigned int linear_backoff_thresh, start_ts; - unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; + struct tcp_sock *tp = tcp_sk(sk); + unsigned int start_ts, delta; 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 = tp->retrans_stamp; if (likely(timeout == 0)) { - linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); + unsigned int rto_base = TCP_RTO_MIN; + + if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) + rto_base = tcp_timeout_init(sk); + timeout = tcp_model_timeout(sk, boundary, rto_base); + } - if (boundary <= linear_backoff_thresh) - timeout = ((2 << boundary) - 1) * rto_base; - else - timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + - (boundary - linear_backoff_thresh) * TCP_RTO_MAX; + if (tp->tcp_usec_ts) { + /* delta maybe off up to a jiffy due to timer granularity. */ + delta = tp->tcp_mstamp - start_ts + jiffies_to_usecs(1); + return (s32)(delta - timeout * USEC_PER_MSEC) >= 0; } - return (tcp_time_stamp - start_ts) >= timeout; + return (s32)(tcp_time_stamp_ts(tp) - start_ts - timeout) >= 0; } /* A write timeout has occurred. Process the after effects. */ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); - int retry_until; - bool do_reset, syn_set = false; + struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); + bool expired = false, do_reset; + int retry_until, max_retransmits; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) - dst_negative_advice(sk); - retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; - syn_set = true; + __dst_negative_advice(sk); + /* Paired with WRITE_ONCE() in tcp_sock_set_syncnt() */ + retry_until = READ_ONCE(icsk->icsk_syn_retries) ? : + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); + + max_retransmits = retry_until; + if (sk->sk_state == TCP_SYN_SENT) + max_retransmits += READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts); + + expired = icsk->icsk_retransmits >= max_retransmits; } else { - if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) { + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); - dst_negative_advice(sk); + __dst_negative_advice(sk); } - retry_until = sysctl_tcp_retries2; + retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { - const int alive = (icsk->icsk_rto < TCP_RTO_MAX); + const bool alive = icsk->icsk_rto < tcp_rto_max(sk); retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || - !retransmits_timed_out(sk, retry_until, 0, 0); + !retransmits_timed_out(sk, retry_until, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } } - - if (retransmits_timed_out(sk, retry_until, - syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) { + if (!expired) + expired = retransmits_timed_out(sk, retry_until, + READ_ONCE(icsk->icsk_user_timeout)); + tcp_fastopen_active_detect_blackhole(sk, expired); + mptcp_active_detect_blackhole(sk, expired); + + if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG)) + tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB, + icsk->icsk_retransmits, + icsk->icsk_rto, (int)expired); + + if (expired) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; } + + if (sk_rethink_txhash(sk)) { + tp->timeout_rehash++; + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); + } + return 0; } +/* Called with BH disabled */ void tcp_delack_timer_handler(struct sock *sk) { - struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); - sk_mem_reclaim_partial(sk); - - if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) - goto out; + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; - if (time_after(icsk->icsk_ack.timeout, jiffies)) { - sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); - goto out; + /* Handling the sack compression case */ + if (tp->compressed_ack) { + tcp_mstamp_refresh(tp); + tcp_sack_compress_send_ack(sk); + return; } - icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; - if (!skb_queue_empty(&tp->ucopy.prequeue)) { - struct sk_buff *skb; - - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPSCHEDULERFAILED); - - while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL) - sk_backlog_rcv(sk, skb); + if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + return; - tp->ucopy.memory = 0; + if (time_after(icsk_delack_timeout(icsk), jiffies)) { + sk_reset_timer(sk, &icsk->icsk_delack_timer, + icsk_delack_timeout(icsk)); + return; } + icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { - if (!icsk->icsk_ack.pingpong) { + if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ - icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); + icsk->icsk_ack.ato = min_t(u32, icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } + tcp_mstamp_refresh(tp); tcp_send_ack(sk); - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKS); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); } - -out: - if (sk_under_memory_pressure(sk)) - sk_mem_reclaim(sk); } -static void tcp_delack_timer(unsigned long data) + +/** + * tcp_delack_timer() - The TCP delayed ACK timeout handler + * @t: Pointer to the timer. (gets casted to struct sock *) + * + * This function gets (indirectly) called when the kernel timer for a TCP packet + * of this socket expires. Calls tcp_delack_timer_handler() to do the actual work. + * + * Returns: Nothing (void) + */ +static void tcp_delack_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct inet_connection_sock *icsk = + timer_container_of(icsk, t, icsk_delack_timer); + struct sock *sk = &icsk->icsk_inet.sk; + + /* Avoid taking socket spinlock if there is no ACK to send. + * The compressed_ack check is racy, but a separate hrtimer + * will take care of it eventually. + */ + if (!(smp_load_acquire(&icsk->icsk_ack.pending) & ICSK_ACK_TIMER) && + !READ_ONCE(tcp_sk(sk)->compressed_ack)) + goto out; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_delack_timer_handler(sk); } else { - inet_csk(sk)->icsk_ack.blocked = 1; - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED); /* deleguate our work to tcp_release_cb() */ - if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags)) + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); +out: sock_put(sk); } static void tcp_probe_timer(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; - if (tp->packets_out || !tcp_send_head(sk)) { - icsk->icsk_probes_out = 0; + if (tp->packets_out || !skb) { + WRITE_ONCE(icsk->icsk_probes_out, 0); + icsk->icsk_probes_tstamp = 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; + if (!icsk->icsk_probes_tstamp) { + icsk->icsk_probes_tstamp = tcp_jiffies32; + } else { + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); + if (user_timeout && + (s32)(tcp_jiffies32 - icsk->icsk_probes_tstamp) >= + msecs_to_jiffies(user_timeout)) + goto abort; + } + max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { - const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX); + unsigned int rto_max = tcp_rto_max(sk); + const bool alive = inet_csk_rto_backoff(icsk, rto_max) < 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); + if (icsk->icsk_probes_out >= max_probes) { +abort: tcp_write_err(sk); } else { /* Only send another probe if we didn't close things up. */ tcp_send_probe0(sk); } } +static void tcp_update_rto_stats(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (!icsk->icsk_retransmits) { + tp->total_rto_recoveries++; + tp->rto_stamp = tcp_time_stamp_ms(tp); + } + WRITE_ONCE(icsk->icsk_retransmits, icsk->icsk_retransmits + 1); + tp->total_rto++; +} + /* * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ -static void tcp_fastopen_synack_timer(struct sock *sk) +static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); - int max_retries = icsk->icsk_syn_retries ? : - sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ - struct request_sock *req; + struct tcp_sock *tp = tcp_sk(sk); + int max_retries; - req = tcp_sk(sk)->fastopen_rsk; - req->rsk_ops->syn_ack_timeout(sk, req); + tcp_syn_ack_timeout(req); + + /* Add one more retry for fastopen. + * Paired with WRITE_ONCE() in tcp_sock_set_syncnt() + */ + max_retries = READ_ONCE(icsk->icsk_syn_retries) ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; } + /* Lower cwnd after certain SYNACK timeout like tcp_init_transfer() */ + if (icsk->icsk_retransmits == 1) + tcp_enter_loss(sk); /* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error * returned from rtx_syn_ack() to make it more persistent like * regular retransmit because if the child socket has been accepted * it's not good to give up too easily. */ - inet_rtx_syn_ack(sk, req); + tcp_rtx_synack(sk, req); req->num_timeout++; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); + tcp_update_rto_stats(sk); + if (!tp->retrans_stamp) + tp->retrans_stamp = tcp_time_stamp_ts(tp); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + req->timeout << req->num_timeout, false); } -/* - * The TCP retransmit timer. - */ +static bool tcp_rtx_probe0_timed_out(const struct sock *sk, + const struct sk_buff *skb, + u32 rtx_delta) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); + const struct tcp_sock *tp = tcp_sk(sk); + int timeout = tcp_rto_max(sk) * 2; + s32 rcv_delta; + + if (user_timeout) { + /* If user application specified a TCP_USER_TIMEOUT, + * it does not want win 0 packets to 'reset the timer' + * while retransmits are not making progress. + */ + if (rtx_delta > user_timeout) + return true; + timeout = min_t(u32, timeout, msecs_to_jiffies(user_timeout)); + } + /* Note: timer interrupt might have been delayed by at least one jiffy, + * and tp->rcv_tstamp might very well have been written recently. + * rcv_delta can thus be negative. + */ + rcv_delta = tcp_timeout_expires(sk) - tp->rcv_tstamp; + if (rcv_delta <= timeout) + return false; + return msecs_to_jiffies(rtx_delta) > timeout; +} + +/** + * tcp_retransmit_timer() - The TCP retransmit timeout handler + * @sk: Pointer to the current socket. + * + * This function gets called when the kernel timer for a TCP packet + * of this socket expires. + * + * It handles retransmission, timer adjustment and other necessary measures. + * + * Returns: Nothing (void) + */ void tcp_retransmit_timer(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); + struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; + struct sk_buff *skb; - if (tp->fastopen_rsk) { + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - tcp_fastopen_synack_timer(sk); + tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ return; } - if (!tp->packets_out) - goto out; - WARN_ON(tcp_write_queue_empty(sk)); + if (!tp->packets_out) + return; - tp->tlp_high_seq = 0; + skb = tcp_rtx_queue_head(sk); + if (WARN_ON_ONCE(!skb)) + return; if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) && !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) { @@ -366,36 +563,45 @@ void tcp_retransmit_timer(struct sock *sk) * we cannot allow such beasts to hang infinitely. */ struct inet_sock *inet = inet_sk(sk); + u32 rtx_delta; + + rtx_delta = tcp_time_stamp_ts(tp) - (tp->retrans_stamp ?: + tcp_skb_timestamp_ts(tp->tcp_usec_ts, skb)); + if (tp->tcp_usec_ts) + rtx_delta /= USEC_PER_MSEC; + if (sk->sk_family == AF_INET) { - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), - &inet->inet_daddr, - ntohs(inet->inet_dport), inet->inet_num, - tp->snd_una, tp->snd_nxt); + net_dbg_ratelimited("Probing zero-window on %pI4:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n", + &inet->inet_daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt, + jiffies_to_msecs(jiffies - tp->rcv_tstamp), + rtx_delta); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n"), - &np->daddr, - ntohs(inet->inet_dport), inet->inet_num, - tp->snd_una, tp->snd_nxt); + net_dbg_ratelimited("Probing zero-window on %pI6:%u/%u, seq=%u:%u, recv %ums ago, lasting %ums\n", + &sk->sk_v6_daddr, ntohs(inet->inet_dport), + inet->inet_num, tp->snd_una, tp->snd_nxt, + jiffies_to_msecs(jiffies - tp->rcv_tstamp), + rtx_delta); } #endif - if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) { + if (tcp_rtx_probe0_timed_out(sk, skb, rtx_delta)) { tcp_write_err(sk); goto out; } - tcp_enter_loss(sk, 0); - tcp_retransmit_skb(sk, tcp_write_queue_head(sk)); + tcp_enter_loss(sk); + tcp_retransmit_skb(sk, skb, 1); __sk_dst_reset(sk); goto out_reset_timer; } + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); if (tcp_write_timeout(sk)) goto out; if (icsk->icsk_retransmits == 0) { - int mib_idx; + int mib_idx = 0; if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) @@ -410,23 +616,21 @@ void tcp_retransmit_timer(struct sock *sk) mib_idx = LINUX_MIB_TCPSACKFAILURES; else mib_idx = LINUX_MIB_TCPRENOFAILURES; - } else { - mib_idx = LINUX_MIB_TCPTIMEOUTS; } - NET_INC_STATS_BH(sock_net(sk), mib_idx); + if (mib_idx) + __NET_INC_STATS(sock_net(sk), mib_idx); } - tcp_enter_loss(sk, 0); + tcp_enter_loss(sk); - if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk)) > 0) { + tcp_update_rto_stats(sk); + if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, - * do not backoff. + * Let senders fight for local resources conservatively. */ - if (!icsk->icsk_retransmits) - icsk->icsk_retransmits = 1; - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL), - TCP_RTO_MAX); + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + TCP_RESOURCE_PROBE_INTERVAL, + false); goto out; } @@ -445,8 +649,6 @@ void tcp_retransmit_timer(struct sock *sk) * implemented ftp to mars will work nicely. We will have to fix * the 120 second clamps though! */ - icsk->icsk_backoff++; - icsk->icsk_retransmits++; out_reset_timer: /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is @@ -459,89 +661,105 @@ out_reset_timer: * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && - (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) && + (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; - icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX); - } else { - /* Use normal (exponential) backoff */ - icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); + icsk->icsk_rto = clamp(__tcp_set_rto(tp), + tcp_rto_min(sk), + tcp_rto_max(sk)); + } else if (sk->sk_state != TCP_SYN_SENT || + tp->total_rto > + READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) { + /* Use normal (exponential) backoff unless linear timeouts are + * activated. + */ + icsk->icsk_backoff++; + icsk->icsk_rto = min(icsk->icsk_rto << 1, tcp_rto_max(sk)); } - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0)) + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + tcp_clamp_rto_to_user_timeout(sk), false); + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; } +/* Called with bottom-half processing disabled. + * Called by tcp_write_timer() and tcp_release_cb(). + */ void tcp_write_timer_handler(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int event; - if (sk->sk_state == TCP_CLOSE || !icsk->icsk_pending) - goto out; + if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !icsk->icsk_pending) + return; - if (time_after(icsk->icsk_timeout, jiffies)) { - sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout); - goto out; + if (time_after(tcp_timeout_expires(sk), jiffies)) { + sk_reset_timer(sk, &sk->tcp_retransmit_timer, + tcp_timeout_expires(sk)); + return; } - + tcp_mstamp_refresh(tcp_sk(sk)); event = icsk->icsk_pending; switch (event) { - case ICSK_TIME_EARLY_RETRANS: - tcp_resume_early_retransmit(sk); + case ICSK_TIME_REO_TIMEOUT: + tcp_rack_reo_timeout(sk); break; case ICSK_TIME_LOSS_PROBE: tcp_send_loss_probe(sk); break; case ICSK_TIME_RETRANS: - icsk->icsk_pending = 0; + smp_store_release(&icsk->icsk_pending, 0); tcp_retransmit_timer(sk); break; case ICSK_TIME_PROBE0: - icsk->icsk_pending = 0; + smp_store_release(&icsk->icsk_pending, 0); tcp_probe_timer(sk); break; } - -out: - sk_mem_reclaim(sk); } -static void tcp_write_timer(unsigned long data) +static void tcp_write_timer(struct timer_list *t) { - struct sock *sk = (struct sock *)data; + struct sock *sk = timer_container_of(sk, t, tcp_retransmit_timer); + + /* Avoid locking the socket when there is no pending event. */ + if (!smp_load_acquire(&inet_csk(sk)->icsk_pending)) + goto out; bh_lock_sock(sk); if (!sock_owned_by_user(sk)) { tcp_write_timer_handler(sk); } else { - /* deleguate our work to tcp_release_cb() */ - if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags)) + /* delegate our work to tcp_release_cb() */ + if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } bh_unlock_sock(sk); +out: sock_put(sk); } -/* - * Timer for listening sockets - */ +void tcp_syn_ack_timeout(const struct request_sock *req) +{ + struct net *net = read_pnet(&inet_rsk(req)->ireq_net); -static void tcp_synack_timer(struct sock *sk) + __NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS); +} + +void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len) { - inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL, - TCP_TIMEOUT_INIT, TCP_RTO_MAX); + sk_reset_timer(sk, &inet_csk(sk)->icsk_keepalive_timer, jiffies + len); } -void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req) +static void tcp_delete_keepalive_timer(struct sock *sk) { - NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS); + sk_stop_timer(sk, &inet_csk(sk)->icsk_keepalive_timer); } -EXPORT_SYMBOL(tcp_syn_ack_timeout); void tcp_set_keepalive(struct sock *sk, int val) { @@ -549,16 +767,17 @@ void tcp_set_keepalive(struct sock *sk, int val) return; if (val && !sock_flag(sk, SOCK_KEEPOPEN)) - inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk))); + tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk))); else if (!val) - inet_csk_delete_keepalive_timer(sk); + tcp_delete_keepalive_timer(sk); } +EXPORT_IPV6_MOD_GPL(tcp_set_keepalive); - -static void tcp_keepalive_timer (unsigned long data) +static void tcp_keepalive_timer(struct timer_list *t) { - struct sock *sk = (struct sock *) data; - struct inet_connection_sock *icsk = inet_csk(sk); + struct inet_connection_sock *icsk = + timer_container_of(icsk, t, icsk_keepalive_timer); + struct sock *sk = &icsk->icsk_inet.sk; struct tcp_sock *tp = tcp_sk(sk); u32 elapsed; @@ -566,17 +785,18 @@ static void tcp_keepalive_timer (unsigned long data) bh_lock_sock(sk); if (sock_owned_by_user(sk)) { /* Try again later. */ - inet_csk_reset_keepalive_timer (sk, HZ/20); + tcp_reset_keepalive_timer(sk, HZ/20); goto out; } if (sk->sk_state == TCP_LISTEN) { - tcp_synack_timer(sk); + pr_err("Hmm... keepalive on a LISTEN ???\n"); goto out; } + tcp_mstamp_refresh(tp); if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) { - if (tp->linger2 >= 0) { + if (READ_ONCE(tp->linger2) >= 0) { const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN; if (tmo > 0) { @@ -584,36 +804,40 @@ static void tcp_keepalive_timer (unsigned long data) goto out; } } - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); goto death; } - if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE) + if (!sock_flag(sk, SOCK_KEEPOPEN) || + ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT))) goto out; elapsed = keepalive_time_when(tp); /* It is alive without keepalive 8) */ - if (tp->packets_out || tcp_send_head(sk)) + if (tp->packets_out || !tcp_write_queue_empty(sk)) goto resched; elapsed = keepalive_time_elapsed(tp); if (elapsed >= keepalive_time_when(tp)) { + u32 user_timeout = READ_ONCE(icsk->icsk_user_timeout); + /* If the TCP_USER_TIMEOUT option is enabled, use that * to determine when to timeout instead. */ - if ((icsk->icsk_user_timeout != 0 && - elapsed >= icsk->icsk_user_timeout && + if ((user_timeout != 0 && + elapsed >= msecs_to_jiffies(user_timeout) && icsk->icsk_probes_out > 0) || - (icsk->icsk_user_timeout == 0 && + (user_timeout == 0 && icsk->icsk_probes_out >= keepalive_probes(tp))) { - tcp_send_active_reset(sk, GFP_ATOMIC); + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); tcp_write_err(sk); goto out; } - if (tcp_write_wakeup(sk) <= 0) { - icsk->icsk_probes_out++; + if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) { + WRITE_ONCE(icsk->icsk_probes_out, icsk->icsk_probes_out + 1); elapsed = keepalive_intvl_when(tp); } else { /* If keepalive was lost due to local congestion, @@ -626,10 +850,8 @@ static void tcp_keepalive_timer (unsigned long data) elapsed = keepalive_time_when(tp) - elapsed; } - sk_mem_reclaim(sk); - resched: - inet_csk_reset_keepalive_timer (sk, elapsed); + tcp_reset_keepalive_timer(sk, elapsed); goto out; death: @@ -640,9 +862,41 @@ out: sock_put(sk); } +static enum hrtimer_restart tcp_compressed_ack_kick(struct hrtimer *timer) +{ + struct tcp_sock *tp = container_of(timer, struct tcp_sock, compressed_ack_timer); + struct sock *sk = (struct sock *)tp; + + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) { + if (tp->compressed_ack) { + /* Since we have to send one ack finally, + * subtract one from tp->compressed_ack to keep + * LINUX_MIB_TCPACKCOMPRESSED accurate. + */ + tp->compressed_ack--; + tcp_mstamp_refresh(tp); + tcp_send_ack(sk); + } + } else { + if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, + &sk->sk_tsq_flags)) + sock_hold(sk); + } + bh_unlock_sock(sk); + + sock_put(sk); + + return HRTIMER_NORESTART; +} + void tcp_init_xmit_timers(struct sock *sk) { inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); + hrtimer_setup(&tcp_sk(sk)->pacing_timer, tcp_pace_kick, CLOCK_MONOTONIC, + HRTIMER_MODE_ABS_PINNED_SOFT); + + hrtimer_setup(&tcp_sk(sk)->compressed_ack_timer, tcp_compressed_ack_kick, CLOCK_MONOTONIC, + HRTIMER_MODE_REL_PINNED_SOFT); } -EXPORT_SYMBOL(tcp_init_xmit_timers); |