mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-05 17:16:41 +07:00
144d56e910
Commit 6f458dfb40
(tcp: improve latencies of timer triggered events)
added bug leading to following trace :
[ 2866.131281] IPv4: Attempt to release TCP socket in state 1 ffff880019ec0000
[ 2866.131726]
[ 2866.132188] =========================
[ 2866.132281] [ BUG: held lock freed! ]
[ 2866.132281] 3.6.0-rc1+ #622 Not tainted
[ 2866.132281] -------------------------
[ 2866.132281] kworker/0:1/652 is freeing memory ffff880019ec0000-ffff880019ec0a1f, with a lock still held there!
[ 2866.132281] (sk_lock-AF_INET-RPC){+.+...}, at: [<ffffffff81903619>] tcp_sendmsg+0x29/0xcc6
[ 2866.132281] 4 locks held by kworker/0:1/652:
[ 2866.132281] #0: (rpciod){.+.+.+}, at: [<ffffffff81083567>] process_one_work+0x1de/0x47f
[ 2866.132281] #1: ((&task->u.tk_work)){+.+.+.}, at: [<ffffffff81083567>] process_one_work+0x1de/0x47f
[ 2866.132281] #2: (sk_lock-AF_INET-RPC){+.+...}, at: [<ffffffff81903619>] tcp_sendmsg+0x29/0xcc6
[ 2866.132281] #3: (&icsk->icsk_retransmit_timer){+.-...}, at: [<ffffffff81078017>] run_timer_softirq+0x1ad/0x35f
[ 2866.132281]
[ 2866.132281] stack backtrace:
[ 2866.132281] Pid: 652, comm: kworker/0:1 Not tainted 3.6.0-rc1+ #622
[ 2866.132281] Call Trace:
[ 2866.132281] <IRQ> [<ffffffff810bc527>] debug_check_no_locks_freed+0x112/0x159
[ 2866.132281] [<ffffffff818a0839>] ? __sk_free+0xfd/0x114
[ 2866.132281] [<ffffffff811549fa>] kmem_cache_free+0x6b/0x13a
[ 2866.132281] [<ffffffff818a0839>] __sk_free+0xfd/0x114
[ 2866.132281] [<ffffffff818a08c0>] sk_free+0x1c/0x1e
[ 2866.132281] [<ffffffff81911e1c>] tcp_write_timer+0x51/0x56
[ 2866.132281] [<ffffffff81078082>] run_timer_softirq+0x218/0x35f
[ 2866.132281] [<ffffffff81078017>] ? run_timer_softirq+0x1ad/0x35f
[ 2866.132281] [<ffffffff810f5831>] ? rb_commit+0x58/0x85
[ 2866.132281] [<ffffffff81911dcb>] ? tcp_write_timer_handler+0x148/0x148
[ 2866.132281] [<ffffffff81070bd6>] __do_softirq+0xcb/0x1f9
[ 2866.132281] [<ffffffff81a0a00c>] ? _raw_spin_unlock+0x29/0x2e
[ 2866.132281] [<ffffffff81a1227c>] call_softirq+0x1c/0x30
[ 2866.132281] [<ffffffff81039f38>] do_softirq+0x4a/0xa6
[ 2866.132281] [<ffffffff81070f2b>] irq_exit+0x51/0xad
[ 2866.132281] [<ffffffff81a129cd>] do_IRQ+0x9d/0xb4
[ 2866.132281] [<ffffffff81a0a3ef>] common_interrupt+0x6f/0x6f
[ 2866.132281] <EOI> [<ffffffff8109d006>] ? sched_clock_cpu+0x58/0xd1
[ 2866.132281] [<ffffffff81a0a172>] ? _raw_spin_unlock_irqrestore+0x4c/0x56
[ 2866.132281] [<ffffffff81078692>] mod_timer+0x178/0x1a9
[ 2866.132281] [<ffffffff818a00aa>] sk_reset_timer+0x19/0x26
[ 2866.132281] [<ffffffff8190b2cc>] tcp_rearm_rto+0x99/0xa4
[ 2866.132281] [<ffffffff8190dfba>] tcp_event_new_data_sent+0x6e/0x70
[ 2866.132281] [<ffffffff8190f7ea>] tcp_write_xmit+0x7de/0x8e4
[ 2866.132281] [<ffffffff818a565d>] ? __alloc_skb+0xa0/0x1a1
[ 2866.132281] [<ffffffff8190f952>] __tcp_push_pending_frames+0x2e/0x8a
[ 2866.132281] [<ffffffff81904122>] tcp_sendmsg+0xb32/0xcc6
[ 2866.132281] [<ffffffff819229c2>] inet_sendmsg+0xaa/0xd5
[ 2866.132281] [<ffffffff81922918>] ? inet_autobind+0x5f/0x5f
[ 2866.132281] [<ffffffff810ee7f1>] ? trace_clock_local+0x9/0xb
[ 2866.132281] [<ffffffff8189adab>] sock_sendmsg+0xa3/0xc4
[ 2866.132281] [<ffffffff810f5de6>] ? rb_reserve_next_event+0x26f/0x2d5
[ 2866.132281] [<ffffffff8103e6a9>] ? native_sched_clock+0x29/0x6f
[ 2866.132281] [<ffffffff8103e6f8>] ? sched_clock+0x9/0xd
[ 2866.132281] [<ffffffff810ee7f1>] ? trace_clock_local+0x9/0xb
[ 2866.132281] [<ffffffff8189ae03>] kernel_sendmsg+0x37/0x43
[ 2866.132281] [<ffffffff8199ce49>] xs_send_kvec+0x77/0x80
[ 2866.132281] [<ffffffff8199cec1>] xs_sendpages+0x6f/0x1a0
[ 2866.132281] [<ffffffff8107826d>] ? try_to_del_timer_sync+0x55/0x61
[ 2866.132281] [<ffffffff8199d0d2>] xs_tcp_send_request+0x55/0xf1
[ 2866.132281] [<ffffffff8199bb90>] xprt_transmit+0x89/0x1db
[ 2866.132281] [<ffffffff81999bcd>] ? call_connect+0x3c/0x3c
[ 2866.132281] [<ffffffff81999d92>] call_transmit+0x1c5/0x20e
[ 2866.132281] [<ffffffff819a0d55>] __rpc_execute+0x6f/0x225
[ 2866.132281] [<ffffffff81999bcd>] ? call_connect+0x3c/0x3c
[ 2866.132281] [<ffffffff819a0f33>] rpc_async_schedule+0x28/0x34
[ 2866.132281] [<ffffffff810835d6>] process_one_work+0x24d/0x47f
[ 2866.132281] [<ffffffff81083567>] ? process_one_work+0x1de/0x47f
[ 2866.132281] [<ffffffff819a0f0b>] ? __rpc_execute+0x225/0x225
[ 2866.132281] [<ffffffff81083a6d>] worker_thread+0x236/0x317
[ 2866.132281] [<ffffffff81083837>] ? process_scheduled_works+0x2f/0x2f
[ 2866.132281] [<ffffffff8108b7b8>] kthread+0x9a/0xa2
[ 2866.132281] [<ffffffff81a12184>] kernel_thread_helper+0x4/0x10
[ 2866.132281] [<ffffffff81a0a4b0>] ? retint_restore_args+0x13/0x13
[ 2866.132281] [<ffffffff8108b71e>] ? __init_kthread_worker+0x5a/0x5a
[ 2866.132281] [<ffffffff81a12180>] ? gs_change+0x13/0x13
[ 2866.308506] IPv4: Attempt to release TCP socket in state 1 ffff880019ec0000
[ 2866.309689] =============================================================================
[ 2866.310254] BUG TCP (Not tainted): Object already free
[ 2866.310254] -----------------------------------------------------------------------------
[ 2866.310254]
The bug comes from the fact that timer set in sk_reset_timer() can run
before we actually do the sock_hold(). socket refcount reaches zero and
we free the socket too soon.
timer handler is not allowed to reduce socket refcnt if socket is owned
by the user, or we need to change sk_reset_timer() implementation.
We should take a reference on the socket in case TCP_DELACK_TIMER_DEFERRED
or TCP_DELACK_TIMER_DEFERRED bit are set in tsq_flags
Also fix a typo in tcp_delack_timer(), where TCP_WRITE_TIMER_DEFERRED
was used instead of TCP_DELACK_TIMER_DEFERRED.
For consistency, use same socket refcount change for TCP_MTU_REDUCED_DEFERRED,
even if not fired from a timer.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Tested-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
611 lines
17 KiB
C
611 lines
17 KiB
C
/*
|
|
* 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, <waltje@uWalt.NL.Mugnet.ORG>
|
|
* Mark Evans, <evansmp@uhura.aston.ac.uk>
|
|
* Corey Minyard <wf-rch!minyard@relay.EU.net>
|
|
* Florian La Roche, <flla@stud.uni-sb.de>
|
|
* Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
|
|
* Linus Torvalds, <torvalds@cs.helsinki.fi>
|
|
* Alan Cox, <gw4pts@gw4pts.ampr.org>
|
|
* Matthew Dillon, <dillon@apollo.west.oic.com>
|
|
* Arnt Gulbrandsen, <agulbra@nvg.unit.no>
|
|
* Jorge Cwik, <jorge@laser.satlink.net>
|
|
*/
|
|
|
|
#include <linux/module.h>
|
|
#include <linux/gfp.h>
|
|
#include <net/tcp.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 void tcp_write_err(struct sock *sk)
|
|
{
|
|
sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
|
|
sk->sk_error_report(sk);
|
|
|
|
tcp_done(sk);
|
|
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
|
|
}
|
|
|
|
/* 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.
|
|
*
|
|
* 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.
|
|
*/
|
|
static int tcp_out_of_resources(struct sock *sk, int 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)
|
|
shift++;
|
|
|
|
/* If some dubious ICMP arrived, penalize even more. */
|
|
if (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 ||
|
|
/* 2. Window is closed. */
|
|
(!tp->snd_wnd && !tp->packets_out))
|
|
do_reset = 1;
|
|
if (do_reset)
|
|
tcp_send_active_reset(sk, GFP_ATOMIC);
|
|
tcp_done(sk);
|
|
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Calculate maximal number or retries on an orphaned socket. */
|
|
static int tcp_orphan_retries(struct sock *sk, int alive)
|
|
{
|
|
int retries = sysctl_tcp_orphan_retries; /* May be zero. */
|
|
|
|
/* We know from an ICMP that something is wrong. */
|
|
if (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)
|
|
{
|
|
/* 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);
|
|
}
|
|
}
|
|
}
|
|
|
|
/* 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 bool retransmits_timed_out(struct sock *sk,
|
|
unsigned int boundary,
|
|
unsigned int timeout,
|
|
bool syn_set)
|
|
{
|
|
unsigned int linear_backoff_thresh, start_ts;
|
|
unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;
|
|
|
|
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;
|
|
|
|
if (likely(timeout == 0)) {
|
|
linear_backoff_thresh = ilog2(TCP_RTO_MAX/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;
|
|
}
|
|
return (tcp_time_stamp - start_ts) >= timeout;
|
|
}
|
|
|
|
/* 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;
|
|
|
|
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;
|
|
} else {
|
|
if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) {
|
|
/* Black hole detection */
|
|
tcp_mtu_probing(icsk, sk);
|
|
|
|
dst_negative_advice(sk);
|
|
}
|
|
|
|
retry_until = sysctl_tcp_retries2;
|
|
if (sock_flag(sk, SOCK_DEAD)) {
|
|
const int alive = (icsk->icsk_rto < TCP_RTO_MAX);
|
|
|
|
retry_until = tcp_orphan_retries(sk, alive);
|
|
do_reset = alive ||
|
|
!retransmits_timed_out(sk, retry_until, 0, 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)) {
|
|
/* Has it gone just too far? */
|
|
tcp_write_err(sk);
|
|
return 1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
void tcp_delack_timer_handler(struct sock *sk)
|
|
{
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
sk_mem_reclaim_partial(sk);
|
|
|
|
if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
|
|
goto out;
|
|
|
|
if (time_after(icsk->icsk_ack.timeout, jiffies)) {
|
|
sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
|
|
goto out;
|
|
}
|
|
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);
|
|
|
|
tp->ucopy.memory = 0;
|
|
}
|
|
|
|
if (inet_csk_ack_scheduled(sk)) {
|
|
if (!icsk->icsk_ack.pingpong) {
|
|
/* Delayed ACK missed: inflate ATO. */
|
|
icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto);
|
|
} else {
|
|
/* Delayed ACK missed: leave pingpong mode and
|
|
* deflate ATO.
|
|
*/
|
|
icsk->icsk_ack.pingpong = 0;
|
|
icsk->icsk_ack.ato = TCP_ATO_MIN;
|
|
}
|
|
tcp_send_ack(sk);
|
|
NET_INC_STATS_BH(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)
|
|
{
|
|
struct sock *sk = (struct sock *)data;
|
|
|
|
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);
|
|
/* deleguate our work to tcp_release_cb() */
|
|
if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &tcp_sk(sk)->tsq_flags))
|
|
sock_hold(sk);
|
|
}
|
|
bh_unlock_sock(sk);
|
|
sock_put(sk);
|
|
}
|
|
|
|
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;
|
|
|
|
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
|
|
*/
|
|
max_probes = sysctl_tcp_retries2;
|
|
|
|
if (sock_flag(sk, SOCK_DEAD)) {
|
|
const int alive = ((icsk->icsk_rto << icsk->icsk_backoff) < TCP_RTO_MAX);
|
|
|
|
max_probes = tcp_orphan_retries(sk, alive);
|
|
|
|
if (tcp_out_of_resources(sk, alive || icsk->icsk_probes_out <= max_probes))
|
|
return;
|
|
}
|
|
|
|
if (icsk->icsk_probes_out > max_probes) {
|
|
tcp_write_err(sk);
|
|
} else {
|
|
/* Only send another probe if we didn't close things up. */
|
|
tcp_send_probe0(sk);
|
|
}
|
|
}
|
|
|
|
/*
|
|
* The TCP retransmit timer.
|
|
*/
|
|
|
|
void tcp_retransmit_timer(struct sock *sk)
|
|
{
|
|
struct tcp_sock *tp = tcp_sk(sk);
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
if (tp->early_retrans_delayed) {
|
|
tcp_resume_early_retransmit(sk);
|
|
return;
|
|
}
|
|
|
|
if (!tp->packets_out)
|
|
goto out;
|
|
|
|
WARN_ON(tcp_write_queue_empty(sk));
|
|
|
|
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);
|
|
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);
|
|
}
|
|
#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);
|
|
}
|
|
#endif
|
|
if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
|
|
tcp_write_err(sk);
|
|
goto out;
|
|
}
|
|
tcp_enter_loss(sk, 0);
|
|
tcp_retransmit_skb(sk, tcp_write_queue_head(sk));
|
|
__sk_dst_reset(sk);
|
|
goto out_reset_timer;
|
|
}
|
|
|
|
if (tcp_write_timeout(sk))
|
|
goto out;
|
|
|
|
if (icsk->icsk_retransmits == 0) {
|
|
int mib_idx;
|
|
|
|
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;
|
|
} else {
|
|
mib_idx = LINUX_MIB_TCPTIMEOUTS;
|
|
}
|
|
NET_INC_STATS_BH(sock_net(sk), mib_idx);
|
|
}
|
|
|
|
if (tcp_use_frto(sk)) {
|
|
tcp_enter_frto(sk);
|
|
} else {
|
|
tcp_enter_loss(sk, 0);
|
|
}
|
|
|
|
if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk)) > 0) {
|
|
/* Retransmission failed because of local congestion,
|
|
* do not backoff.
|
|
*/
|
|
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);
|
|
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!
|
|
*/
|
|
icsk->icsk_backoff++;
|
|
icsk->icsk_retransmits++;
|
|
|
|
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 || 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);
|
|
}
|
|
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))
|
|
__sk_dst_reset(sk);
|
|
|
|
out:;
|
|
}
|
|
|
|
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 (time_after(icsk->icsk_timeout, jiffies)) {
|
|
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
|
|
goto out;
|
|
}
|
|
|
|
event = icsk->icsk_pending;
|
|
icsk->icsk_pending = 0;
|
|
|
|
switch (event) {
|
|
case ICSK_TIME_RETRANS:
|
|
tcp_retransmit_timer(sk);
|
|
break;
|
|
case ICSK_TIME_PROBE0:
|
|
tcp_probe_timer(sk);
|
|
break;
|
|
}
|
|
|
|
out:
|
|
sk_mem_reclaim(sk);
|
|
}
|
|
|
|
static void tcp_write_timer(unsigned long data)
|
|
{
|
|
struct sock *sk = (struct sock *)data;
|
|
|
|
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))
|
|
sock_hold(sk);
|
|
}
|
|
bh_unlock_sock(sk);
|
|
sock_put(sk);
|
|
}
|
|
|
|
/*
|
|
* Timer for listening sockets
|
|
*/
|
|
|
|
static void tcp_synack_timer(struct sock *sk)
|
|
{
|
|
inet_csk_reqsk_queue_prune(sk, TCP_SYNQ_INTERVAL,
|
|
TCP_TIMEOUT_INIT, TCP_RTO_MAX);
|
|
}
|
|
|
|
void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req)
|
|
{
|
|
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEOUTS);
|
|
}
|
|
EXPORT_SYMBOL(tcp_syn_ack_timeout);
|
|
|
|
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))
|
|
inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
|
|
else if (!val)
|
|
inet_csk_delete_keepalive_timer(sk);
|
|
}
|
|
|
|
|
|
static void tcp_keepalive_timer (unsigned long data)
|
|
{
|
|
struct sock *sk = (struct sock *) data;
|
|
struct inet_connection_sock *icsk = inet_csk(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. */
|
|
inet_csk_reset_keepalive_timer (sk, HZ/20);
|
|
goto out;
|
|
}
|
|
|
|
if (sk->sk_state == TCP_LISTEN) {
|
|
tcp_synack_timer(sk);
|
|
goto out;
|
|
}
|
|
|
|
if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
|
|
if (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);
|
|
goto death;
|
|
}
|
|
|
|
if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
|
|
goto out;
|
|
|
|
elapsed = keepalive_time_when(tp);
|
|
|
|
/* It is alive without keepalive 8) */
|
|
if (tp->packets_out || tcp_send_head(sk))
|
|
goto resched;
|
|
|
|
elapsed = keepalive_time_elapsed(tp);
|
|
|
|
if (elapsed >= keepalive_time_when(tp)) {
|
|
/* 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 &&
|
|
icsk->icsk_probes_out > 0) ||
|
|
(icsk->icsk_user_timeout == 0 &&
|
|
icsk->icsk_probes_out >= keepalive_probes(tp))) {
|
|
tcp_send_active_reset(sk, GFP_ATOMIC);
|
|
tcp_write_err(sk);
|
|
goto out;
|
|
}
|
|
if (tcp_write_wakeup(sk) <= 0) {
|
|
icsk->icsk_probes_out++;
|
|
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;
|
|
}
|
|
|
|
sk_mem_reclaim(sk);
|
|
|
|
resched:
|
|
inet_csk_reset_keepalive_timer (sk, elapsed);
|
|
goto out;
|
|
|
|
death:
|
|
tcp_done(sk);
|
|
|
|
out:
|
|
bh_unlock_sock(sk);
|
|
sock_put(sk);
|
|
}
|
|
|
|
void tcp_init_xmit_timers(struct sock *sk)
|
|
{
|
|
inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
|
|
&tcp_keepalive_timer);
|
|
}
|
|
EXPORT_SYMBOL(tcp_init_xmit_timers);
|