Revision 73223e4e2e3867ebf033a5a8eb2e5df0158ccc99 authored by zhong jiang on 18 August 2017, 22:16:24 UTC, committed by Linus Torvalds on 18 August 2017, 22:32:02 UTC
I hit a use after free issue when executing trinity and repoduced it with KASAN enabled. The related call trace is as follows. BUG: KASan: use after free in SyS_get_mempolicy+0x3c8/0x960 at addr ffff8801f582d766 Read of size 2 by task syz-executor1/798 INFO: Allocated in mpol_new.part.2+0x74/0x160 age=3 cpu=1 pid=799 __slab_alloc+0x768/0x970 kmem_cache_alloc+0x2e7/0x450 mpol_new.part.2+0x74/0x160 mpol_new+0x66/0x80 SyS_mbind+0x267/0x9f0 system_call_fastpath+0x16/0x1b INFO: Freed in __mpol_put+0x2b/0x40 age=4 cpu=1 pid=799 __slab_free+0x495/0x8e0 kmem_cache_free+0x2f3/0x4c0 __mpol_put+0x2b/0x40 SyS_mbind+0x383/0x9f0 system_call_fastpath+0x16/0x1b INFO: Slab 0xffffea0009cb8dc0 objects=23 used=8 fp=0xffff8801f582de40 flags=0x200000000004080 INFO: Object 0xffff8801f582d760 @offset=5984 fp=0xffff8801f582d600 Bytes b4 ffff8801f582d750: ae 01 ff ff 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ Object ffff8801f582d760: 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b 6b kkkkkkkkkkkkkkkk Object ffff8801f582d770: 6b 6b 6b 6b 6b 6b 6b a5 kkkkkkk. Redzone ffff8801f582d778: bb bb bb bb bb bb bb bb ........ Padding ffff8801f582d8b8: 5a 5a 5a 5a 5a 5a 5a 5a ZZZZZZZZ Memory state around the buggy address: ffff8801f582d600: fb fb fb fc fc fc fc fc fc fc fc fc fc fc fc fc ffff8801f582d680: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc >ffff8801f582d700: fc fc fc fc fc fc fc fc fc fc fc fc fb fb fb fc !shared memory policy is not protected against parallel removal by other thread which is normally protected by the mmap_sem. do_get_mempolicy, however, drops the lock midway while we can still access it later. Early premature up_read is a historical artifact from times when put_user was called in this path see https://lwn.net/Articles/124754/ but that is gone since 8bccd85ffbaf ("[PATCH] Implement sys_* do_* layering in the memory policy layer."). but when we have the the current mempolicy ref count model. The issue was introduced accordingly. Fix the issue by removing the premature release. Link: http://lkml.kernel.org/r/1502950924-27521-1-git-send-email-zhongjiang@huawei.com Signed-off-by: zhong jiang <zhongjiang@huawei.com> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: David Rientjes <rientjes@google.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: <stable@vger.kernel.org> [2.6+] Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
1 parent da094e4
timer.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(unsigned long data)
{
struct sock *sk = (struct sock *)data;
struct inet_connection_sock *icsk = inet_csk(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(unsigned long data)
{
struct sock *sk = (struct sock *)data;
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(unsigned long data)
{
struct sock *sk = (struct sock *)data;
struct inet_connection_sock *icsk = inet_csk(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);
}
static void dccp_write_xmit_timer(unsigned long data)
{
dccp_write_xmitlet(data);
sock_put((struct sock *)data);
}
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);
setup_timer(&dp->dccps_xmit_timer, dccp_write_xmit_timer,
(unsigned long)sk);
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();
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...