kernel_optimize_test/net/dccp/timer.c
Eric Dumazet a8d7aa17bb 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: dc841e30ea ("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>
2018-05-03 15:14:57 -04:00

276 lines
7.3 KiB
C

/*
* 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_write_xmit(sk);
bh_unlock_sock(sk);
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();
}