OpenCloudOS-Kernel/net/dccp/timer.c

276 lines
7.3 KiB
C
Raw Normal View History

/*
* net/dccp/timer.c
*
* An implementation of the DCCP protocol
* Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/dccp.h>
#include <linux/skbuff.h>
#include <linux/export.h>
#include "dccp.h"
/* sysctl variables governing numbers of retransmission attempts */
int sysctl_dccp_request_retries __read_mostly = TCP_SYN_RETRIES;
int sysctl_dccp_retries1 __read_mostly = TCP_RETR1;
int sysctl_dccp_retries2 __read_mostly = TCP_RETR2;
static void dccp_write_err(struct sock *sk)
{
sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
sk->sk_error_report(sk);
dccp_send_reset(sk, DCCP_RESET_CODE_ABORTED);
dccp_done(sk);
__DCCP_INC_STATS(DCCP_MIB_ABORTONTIMEOUT);
}
/* A write timeout has occurred. Process the after effects. */
static int dccp_write_timeout(struct sock *sk)
{
const struct inet_connection_sock *icsk = inet_csk(sk);
int retry_until;
if (sk->sk_state == DCCP_REQUESTING || sk->sk_state == DCCP_PARTOPEN) {
if (icsk->icsk_retransmits != 0)
dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ?
: sysctl_dccp_request_retries;
} else {
if (icsk->icsk_retransmits >= sysctl_dccp_retries1) {
/* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu
black hole detection. :-(
It is place to make it. It is not made. I do not want
to make it. It is disguisting. It does not work in any
case. Let me to cite the same draft, which requires for
us to implement this:
"The one security concern raised by this memo is that ICMP black holes
are often caused by over-zealous security administrators who block
all ICMP messages. It is vitally important that those who design and
deploy security systems understand the impact of strict filtering on
upper-layer protocols. The safest web site in the world is worthless
if most TCP implementations cannot transfer data from it. It would
be far nicer to have all of the black holes fixed rather than fixing
all of the TCP implementations."
Golden words :-).
*/
dst_negative_advice(sk);
}
retry_until = sysctl_dccp_retries2;
/*
* FIXME: see tcp_write_timout and tcp_out_of_resources
*/
}
if (icsk->icsk_retransmits >= retry_until) {
/* Has it gone just too far? */
dccp_write_err(sk);
return 1;
}
return 0;
}
/*
* The DCCP retransmit timer.
*/
static void dccp_retransmit_timer(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
/*
* More than than 4MSL (8 minutes) has passed, a RESET(aborted) was
* sent, no need to retransmit, this sock is dead.
*/
if (dccp_write_timeout(sk))
return;
/*
* We want to know the number of packets retransmitted, not the
* total number of retransmissions of clones of original packets.
*/
if (icsk->icsk_retransmits == 0)
__DCCP_INC_STATS(DCCP_MIB_TIMEOUTS);
if (dccp_retransmit_skb(sk) != 0) {
/*
* Retransmission failed because of local congestion,
* do not backoff.
*/
if (--icsk->icsk_retransmits == 0)
icsk->icsk_retransmits = 1;
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
min(icsk->icsk_rto,
TCP_RESOURCE_PROBE_INTERVAL),
DCCP_RTO_MAX);
return;
}
icsk->icsk_backoff++;
icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX);
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto,
DCCP_RTO_MAX);
if (icsk->icsk_retransmits > sysctl_dccp_retries1)
__sk_dst_reset(sk);
}
static void dccp_write_timer(struct timer_list *t)
{
struct inet_connection_sock *icsk =
from_timer(icsk, t, icsk_retransmit_timer);
struct sock *sk = &icsk->icsk_inet.sk;
int event = 0;
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
/* Try again later */
sk_reset_timer(sk, &icsk->icsk_retransmit_timer,
jiffies + (HZ / 20));
goto out;
}
if (sk->sk_state == DCCP_CLOSED || !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:
dccp_retransmit_timer(sk);
break;
}
out:
bh_unlock_sock(sk);
sock_put(sk);
}
static void dccp_keepalive_timer(struct timer_list *t)
{
struct sock *sk = from_timer(sk, t, sk_timer);
pr_err("dccp should not use a keepalive timer !\n");
sock_put(sk);
}
/* This is the same as tcp_delack_timer, sans prequeue & mem_reclaim stuff */
static void dccp_delack_timer(struct timer_list *t)
{
struct inet_connection_sock *icsk =
from_timer(icsk, t, icsk_delack_timer);
struct sock *sk = &icsk->icsk_inet.sk;
bh_lock_sock(sk);
if (sock_owned_by_user(sk)) {
/* Try again later. */
icsk->icsk_ack.blocked = 1;
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
sk_reset_timer(sk, &icsk->icsk_delack_timer,
jiffies + TCP_DELACK_MIN);
goto out;
}
if (sk->sk_state == DCCP_CLOSED ||
!(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 (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;
}
dccp_send_ack(sk);
__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
}
out:
bh_unlock_sock(sk);
sock_put(sk);
}
/**
* dccp_write_xmitlet - Workhorse for CCID packet dequeueing interface
* See the comments above %ccid_dequeueing_decision for supported modes.
*/
static void dccp_write_xmitlet(unsigned long data)
{
struct sock *sk = (struct sock *)data;
bh_lock_sock(sk);
if (sock_owned_by_user(sk))
sk_reset_timer(sk, &dccp_sk(sk)->dccps_xmit_timer, jiffies + 1);
else
dccp: Refine the wait-for-ccid mechanism This extends the existing wait-for-ccid routine so that it may be used with different types of CCID, addressing the following problems: 1) The queue-drain mechanism only works with rate-based CCIDs. If CCID-2 for example has a full TX queue and becomes network-limited just as the application wants to close, then waiting for CCID-2 to become unblocked could lead to an indefinite delay (i.e., application "hangs"). 2) Since each TX CCID in turn uses a feedback mechanism, there may be changes in its sending policy while the queue is being drained. This can lead to further delays during which the application will not be able to terminate. 3) The minimum wait time for CCID-3/4 can be expected to be the queue length times the current inter-packet delay. For example if tx_qlen=100 and a delay of 15 ms is used for each packet, then the application would have to wait for a minimum of 1.5 seconds before being allowed to exit. 4) There is no way for the user/application to control this behaviour. It would be good to use the timeout argument of dccp_close() as an upper bound. Then the maximum time that an application is willing to wait for its CCIDs to can be set via the SO_LINGER option. These problems are addressed by giving the CCID a grace period of up to the `timeout' value. The wait-for-ccid function is, as before, used when the application (a) has read all the data in its receive buffer and (b) if SO_LINGER was set with a non-zero linger time, or (c) the socket is either in the OPEN (active close) or in the PASSIVE_CLOSEREQ state (client application closes after receiving CloseReq). In addition, there is a catch-all case of __skb_queue_purge() after waiting for the CCID. This is necessary since the write queue may still have data when (a) the host has been passively-closed, (b) abnormal termination (unread data, zero linger time), (c) wait-for-ccid could not finish within the given time limit. Signed-off-by: Gerrit Renker <gerrit@erg.abdn.ac.uk> Signed-off-by: David S. Miller <davem@davemloft.net>
2010-10-28 03:16:27 +08:00
dccp_write_xmit(sk);
bh_unlock_sock(sk);
dccp: fix tasklet usage syzbot reported a crash in tasklet_action_common() caused by dccp. dccp needs to make sure socket wont disappear before tasklet handler has completed. This patch takes a reference on the socket when arming the tasklet, and moves the sock_put() from dccp_write_xmit_timer() to dccp_write_xmitlet() kernel BUG at kernel/softirq.c:514! invalid opcode: 0000 [#1] SMP KASAN Dumping ftrace buffer: (ftrace buffer empty) Modules linked in: CPU: 1 PID: 17 Comm: ksoftirqd/1 Not tainted 4.17.0-rc3+ #30 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:tasklet_action_common.isra.19+0x6db/0x700 kernel/softirq.c:515 RSP: 0018:ffff8801d9b3faf8 EFLAGS: 00010246 dccp_close: ABORT with 65423 bytes unread RAX: 1ffff1003b367f6b RBX: ffff8801daf1f3f0 RCX: 0000000000000000 RDX: ffff8801cf895498 RSI: 0000000000000004 RDI: 0000000000000000 RBP: ffff8801d9b3fc40 R08: ffffed0039f12a95 R09: ffffed0039f12a94 dccp_close: ABORT with 65423 bytes unread R10: ffffed0039f12a94 R11: ffff8801cf8954a3 R12: 0000000000000000 R13: ffff8801d9b3fc18 R14: dffffc0000000000 R15: ffff8801cf895490 FS: 0000000000000000(0000) GS:ffff8801daf00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000001b2bc28000 CR3: 00000001a08a9000 CR4: 00000000001406e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: tasklet_action+0x1d/0x20 kernel/softirq.c:533 __do_softirq+0x2e0/0xaf5 kernel/softirq.c:285 dccp_close: ABORT with 65423 bytes unread run_ksoftirqd+0x86/0x100 kernel/softirq.c:646 smpboot_thread_fn+0x417/0x870 kernel/smpboot.c:164 kthread+0x345/0x410 kernel/kthread.c:238 ret_from_fork+0x3a/0x50 arch/x86/entry/entry_64.S:412 Code: 48 8b 85 e8 fe ff ff 48 8b 95 f0 fe ff ff e9 94 fb ff ff 48 89 95 f0 fe ff ff e8 81 53 6e 00 48 8b 95 f0 fe ff ff e9 62 fb ff ff <0f> 0b 48 89 cf 48 89 8d e8 fe ff ff e8 64 53 6e 00 48 8b 8d e8 RIP: tasklet_action_common.isra.19+0x6db/0x700 kernel/softirq.c:515 RSP: ffff8801d9b3faf8 Fixes: dc841e30eaea ("dccp: Extend CCID packet dequeueing interface") Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: syzbot <syzkaller@googlegroups.com> Cc: Gerrit Renker <gerrit@erg.abdn.ac.uk> Cc: dccp@vger.kernel.org Signed-off-by: David S. Miller <davem@davemloft.net>
2018-05-04 00:39:20 +08:00
sock_put(sk);
}
static void dccp_write_xmit_timer(struct timer_list *t)
{
struct dccp_sock *dp = from_timer(dp, t, dccps_xmit_timer);
struct sock *sk = &dp->dccps_inet_connection.icsk_inet.sk;
dccp_write_xmitlet((unsigned long)sk);
}
void dccp_init_xmit_timers(struct sock *sk)
{
struct dccp_sock *dp = dccp_sk(sk);
tasklet_init(&dp->dccps_xmitlet, dccp_write_xmitlet, (unsigned long)sk);
timer_setup(&dp->dccps_xmit_timer, dccp_write_xmit_timer, 0);
inet_csk_init_xmit_timers(sk, &dccp_write_timer, &dccp_delack_timer,
&dccp_keepalive_timer);
}
static ktime_t dccp_timestamp_seed;
/**
* dccp_timestamp - 10s of microseconds time source
* Returns the number of 10s of microseconds since loading DCCP. This is native
* DCCP time difference format (RFC 4340, sec. 13).
* Please note: This will wrap around about circa every 11.9 hours.
*/
u32 dccp_timestamp(void)
{
u64 delta = (u64)ktime_us_delta(ktime_get_real(), dccp_timestamp_seed);
do_div(delta, 10);
return delta;
}
EXPORT_SYMBOL_GPL(dccp_timestamp);
void __init dccp_timestamping_init(void)
{
dccp_timestamp_seed = ktime_get_real();
}