From 034dd340b08be1f2f0477ad16131d609f9dbd53c Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Sun, 30 Aug 2026 09:22:00 -0700 Subject: Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull tracing fixes from Steven Rostedt: - Fix error output of boot instance creation failure Currently if a boot instance creation fails, instead of printing out the name of the instance that failed, it prints "(null)". That is because it prints "cur_str" that had already been processed by strsep(). Print the saved name instead. While at it, print the error code of the failure. - Fix use-after-free for same named historgrams Histograms can be named so that they can be used in multiple events. But if the named histogram has a variable attached, the second event that uses the named histogram which duplicates it and needs to free the original after duplication leaves the old variable in place and still visible. If another histogram uses than variable, it will use the stale one which will try to reference the freed duplicate histogram and crash the kernel. Free the duplicate variables along with the duplicated histogram data. - Check return value of kthread_run() in event self test The events self tests uses a kthread for testing but does not check if it succeeded in creating a kthread. If the kthread creation were to fail, the code will still try to call kthread_stop() on the error returned. - Fix race between reading trace_pipe and updating subbuffer size If a user is reading the trace_pipe file at the same time they update the ring buffer sub-buffer size, can cause the trace_pipe read to read stale data. Add trace_access_lock() around updating the ring buffer sub-buffer size. - Fix eventfs_inode on failure path in creation of the events directory In the creation of the "events" directory, if after allocating the eventfs_inode a failure is detected, it calls cleanup_ei() which calls free_ei(). The free_ei() will test if eventfs_inode being freed has no children. It is a bug if it does. But on the failure case of the creation of the "events" directory, the children lists have not yet been initialized and the free will trigger a warning because list_empty() on an uninitialized list returns false. Move the initialization into init_ei() where it makes more sense and makes sure that a created eventfs_inode has its lists initialized upon creation. - Check return value of kthread_run() in ftrace direct sample code The sample code that shows how to use the ftrace direct calls does not test the return of kthread_run() to see if it succeeds. Return a failure if the kthread_run() doesn't succeed. - Clear user events state on fork in case of alloc failure On fork, the child gets a pointer to the parent's user events state. It makes a copy of it then updates the child's pointer to it. But if the allocation fails, the duplication function leaves the child with a pointer to its parent's descriptor. When the child cleans up its data, it will free the parent's descriptor while the parent is still using it. In the duplication function, set the child's user_event_mm to NULL before testing if the allocation succeeded, and when it exits it will not free the parent's descriptor. - Fix retry exhaustion in simple ring buffer reader swap simple_ring_buffer_swap_reader_page() starts with retry set to 8 and post-decrements it only after a failed link replacement. On the final attempt, a successful replacement leaves retry at zero, while a failed replacement leaves it at -1. But the check for success expects the retry value to be non-zero and exits with an error on zero. This is the opposite result. Fix it. - Fail nicely when the remote swap_reader_page() returns an error Currently, if the swap_reader_page() of a remote buffer fails, it triggers a WARN_ON_ONCE() and continues normally. Instead, have it exit with an error and a pr_warn() print instead of a full WARNING. * tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: ring-buffer: Stop remote reader update when page swap fails tracing: Fix retry exhaustion in simple ring buffer reader swap tracing/user_events: Clear copied tracing state before fork duplication samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify eventfs: Initialize ei->children and ei->list in init_ei() tracing: Fix use-after-free in trace_pipe read on sub-buffer order change tracing: Fix crash passing ERR_PTR to kthread_stop() tracing: Fix use-after-free with same-name named triggers tracing: Fix logged instance name on creation failure --- net/ipv4/tcp_timer.c | 907 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 907 insertions(+) create mode 100644 net/ipv4/tcp_timer.c (limited to 'net/ipv4/tcp_timer.c') diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c new file mode 100644 index 000000000..1038e7ba9 --- /dev/null +++ b/net/ipv4/tcp_timer.c @@ -0,0 +1,907 @@ +// 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 + * interface as the means of communication with the user level. + * + * Implementation of the Transmission Control Protocol(TCP). + * + * Authors: Ross Biro + * Fred N. van Kempen, + * Mark Evans, + * Corey Minyard + * Florian La Roche, + * Charles Hedrick, + * Linus Torvalds, + * Alan Cox, + * Matthew Dillon, + * Arnt Gulbrandsen, + * Jorge Cwik, + */ + +#include +#include +#include +#include +#include + +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; + + 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) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + u32 user_timeout; + s32 remaining; + s32 elapsed; + + 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(int, remaining, TCP_TIMEOUT_MIN); + + return min_t(u32, remaining, when); +} + +/** + * 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. + * 3. If our net namespace is exiting. + */ +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_jiffies32 - tp->lsndtime) > 2*tcp_rto_max(sk) || !do_reset) + shift++; + + /* If some dubious ICMP arrived, penalize even more. */ + 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_jiffies32 - tp->lsndtime) <= TCP_TIMEWAIT_LEN || + /* 2. Window is closed. */ + (!tp->snd_wnd && !tp->packets_out)) + do_reset = true; + if (do_reset) + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_TCP_ABORT_ON_MEMORY); + tcp_done(sk); + __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; +} + +/** + * 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 = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ + + /* We know from an ICMP that something is wrong. */ + if (READ_ONCE(sk->sk_err_soft) && !alive) + retries = 0; + + /* However, if socket sent something recently, select some safe + * number of retries. 8 corresponds to >100 seconds with minimal + * RTO of 200msec. */ + if (retries == 0 && alive) + retries = 8; + return retries; +} + +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 (!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); +} + +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) +{ + struct tcp_sock *tp = tcp_sk(sk); + unsigned int start_ts, delta; + + if (!inet_csk(sk)->icsk_retransmits) + return false; + + start_ts = tp->retrans_stamp; + if (likely(timeout == 0)) { + 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 (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 (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); + 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); + /* 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, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { + /* Black hole detection */ + tcp_mtu_probing(icsk, sk); + + __dst_negative_advice(sk); + } + + retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); + if (sock_flag(sk, SOCK_DEAD)) { + 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); + + if (tcp_out_of_resources(sk, do_reset)) + return 1; + } + } + 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_reset_dst(sk)) { + WRITE_ONCE(tp->timeout_rehash, tp->timeout_rehash + 1); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPTIMEOUTREHASH); + } + + return 0; +} + +/* Called with BH disabled */ +void tcp_delack_timer_handler(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; + + /* Handling the sack compression case */ + if (tp->compressed_ack) { + tcp_mstamp_refresh(tp); + tcp_sack_compress_send_ack(sk); + return; + } + + if (!(icsk->icsk_ack.pending & ICSK_ACK_TIMER)) + return; + + 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 (!inet_csk_in_pingpong_mode(sk)) { + /* Delayed ACK missed: inflate ATO. */ + icsk->icsk_ack.ato = min3((u32)icsk->icsk_ack.ato << 1, + icsk->icsk_rto, + (u32)TCP_DELACK_MAX); + } else { + /* Delayed ACK missed: leave pingpong mode and + * deflate ATO. + */ + inet_csk_exit_pingpong_mode(sk); + icsk->icsk_ack.ato = TCP_ATO_MIN; + } + tcp_mstamp_refresh(tp); + tcp_send_ack(sk); + __NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS); + } +} + + +/** + * 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 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 { + __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, &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 || !skb) { + WRITE_ONCE(icsk->icsk_probes_out, 0); + icsk->icsk_probes_tstamp = 0; + return; + } + + /* 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(). + */ + 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)) { + 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 (!alive && icsk->icsk_backoff >= max_probes) + goto abort; + if (tcp_out_of_resources(sk, true)) + return; + } + + 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, struct request_sock *req) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + int max_retries; + + 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. + */ + tcp_rtx_synack(sk, req); + if (req->num_retrans > 1 && tcp_rsk(req)->accecn_ok) + tcp_rsk(req)->accecn_fail_mode |= TCP_ACCECN_ACE_FAIL_SEND; + req->num_timeout++; + 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); +} + +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; + + 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, 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) + return; + + 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))) { + /* Receiver dastardly shrinks window. Our retransmits + * become zero probes, but we should not timeout this + * connection. If the socket is an orphan, time it out, + * 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) { + 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) { + 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_rtx_probe0_timed_out(sk, skb, rtx_delta)) { + tcp_write_err(sk); + goto out; + } + 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 = 0; + + if (icsk->icsk_ca_state == TCP_CA_Recovery) { + if (tcp_is_sack(tp)) + mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL; + else + mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL; + } else if (icsk->icsk_ca_state == TCP_CA_Loss) { + mib_idx = LINUX_MIB_TCPLOSSFAILURES; + } else if ((icsk->icsk_ca_state == TCP_CA_Disorder) || + tp->sacked_out) { + if (tcp_is_sack(tp)) + mib_idx = LINUX_MIB_TCPSACKFAILURES; + else + mib_idx = LINUX_MIB_TCPRENOFAILURES; + } + if (mib_idx) + __NET_INC_STATS(sock_net(sk), mib_idx); + } + + tcp_enter_loss(sk); + + tcp_update_rto_stats(sk); + if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { + /* Retransmission failed because of local congestion, + * Let senders fight for local resources conservatively. + */ + tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, + TCP_RESOURCE_PROBE_INTERVAL, + false); + goto out; + } + + /* Increase the timeout each time we retransmit. Note that + * we do not increase the rtt estimate. rto is initialized + * from rtt, but increases here. Jacobson (SIGCOMM 88) suggests + * that doubling rto each time is the least we can get away with. + * In KA9Q, Karn uses this for the first few times, and then + * goes to quadratic. netBSD doubles, but only goes up to *64, + * and clamps at 1 to 64 sec afterwards. Note that 120 sec is + * defined in the protocol as the maximum possible RTT. I guess + * we'll have to use something other than TCP to talk to the + * University of Mars. + * + * PAWS allows us longer timeouts and large windows, so once + * implemented ftp to mars will work nicely. We will have to fix + * the 120 second clamps though! + */ + +out_reset_timer: + /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is + * used to reset timer, set to 0. Recalculate 'icsk_rto' as this + * might be increased if the stream oscillates between thin and thick, + * thus the old value might already be too high compared to the value + * set by 'tcp_set_rto' in tcp_input.c which resets the rto without + * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating + * exponential backoff behaviour to avoid continue hammering + * linear-timeout retransmissions into a black hole + */ + if (sk->sk_state == TCP_ESTABLISHED && + (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 = 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)); + } + 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 (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) || + !icsk->icsk_pending) + return; + + 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_REO_TIMEOUT: + tcp_rack_reo_timeout(sk); + break; + case ICSK_TIME_LOSS_PROBE: + tcp_send_loss_probe(sk); + break; + case ICSK_TIME_RETRANS: + smp_store_release(&icsk->icsk_pending, 0); + tcp_retransmit_timer(sk); + break; + case ICSK_TIME_PROBE0: + smp_store_release(&icsk->icsk_pending, 0); + tcp_probe_timer(sk); + break; + } +} + +static void tcp_write_timer(struct timer_list *t) +{ + 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 { + /* 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); +} + +noinline_for_tracing void tcp_syn_ack_timeout(const struct request_sock *req) +{ + struct net *net = read_pnet(&inet_rsk(req)->ireq_net); + + __NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS); +} + +void tcp_reset_keepalive_timer(struct sock *sk, unsigned long len) +{ + sk_reset_timer(sk, &inet_csk(sk)->icsk_keepalive_timer, jiffies + len); +} + +static void tcp_delete_keepalive_timer(struct sock *sk) +{ + sk_stop_timer(sk, &inet_csk(sk)->icsk_keepalive_timer); +} + +void tcp_set_keepalive(struct sock *sk, int val) +{ + if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) + return; + + if (val && !sock_flag(sk, SOCK_KEEPOPEN)) + tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk))); + else if (!val) + tcp_delete_keepalive_timer(sk); +} + +static void tcp_keepalive_timer(struct timer_list *t) +{ + 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; + + /* Only process if socket is not in use. */ + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) { + /* Try again later. */ + tcp_reset_keepalive_timer(sk, HZ/20); + goto out; + } + + if (sk->sk_state == TCP_LISTEN) { + 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 (READ_ONCE(tp->linger2) >= 0) { + const int tmo = tcp_fin_time(sk) - TCP_TIMEWAIT_LEN; + + if (tmo > 0) { + tcp_time_wait(sk, TCP_FIN_WAIT2, tmo); + goto out; + } + } + tcp_send_active_reset(sk, GFP_ATOMIC, SK_RST_REASON_TCP_STATE); + goto death; + } + + 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_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 ((user_timeout != 0 && + elapsed >= msecs_to_jiffies(user_timeout) && + icsk->icsk_probes_out > 0) || + (user_timeout == 0 && + icsk->icsk_probes_out >= keepalive_probes(tp))) { + tcp_send_active_reset(sk, GFP_ATOMIC, + SK_RST_REASON_TCP_KEEPALIVE_TIMEOUT); + tcp_write_err(sk); + goto 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, + * try harder. + */ + elapsed = TCP_RESOURCE_PROBE_INTERVAL; + } + } else { + /* It is tp->rcv_tstamp + keepalive_time_when(tp) */ + elapsed = keepalive_time_when(tp) - elapsed; + } + +resched: + tcp_reset_keepalive_timer(sk, elapsed); + goto out; + +death: + tcp_done(sk); + +out: + bh_unlock_sock(sk); + 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); +} -- cgit v1.3.1