Revision 8aef18845266f5c05904c610088f2d1ed58f6be3 authored by Al Viro on 16 June 2011, 14:10:06 UTC, committed by Al Viro on 16 June 2011, 15:28:16 UTC
[Kudos to dhowells for tracking that crap down]
If two processes attempt to cause automounting on the same mountpoint at the
same time, the vfsmount holding the mountpoint will be left with one too few
references on it, causing a BUG when the kernel tries to clean up.
The problem is that lock_mount() drops the caller's reference to the
mountpoint's vfsmount in the case where it finds something already mounted on
the mountpoint as it transits to the mounted filesystem and replaces path->mnt
with the new mountpoint vfsmount.
During a pathwalk, however, we don't take a reference on the vfsmount if it is
the same as the one in the nameidata struct, but do_add_mount() doesn't know
this.
The fix is to make sure we have a ref on the vfsmount of the mountpoint before
calling do_add_mount(). However, if lock_mount() doesn't transit, we're then
left with an extra ref on the mountpoint vfsmount which needs releasing.
We can handle that in follow_managed() by not making assumptions about what
we can and what we cannot get from lookup_mnt() as the current code does.
The callers of follow_managed() expect that reference to path->mnt will be
grabbed iff path->mnt has been changed. follow_managed() and follow_automount()
keep track of whether such reference has been grabbed and assume that it'll
happen in those and only those cases that'll have us return with changed
path->mnt. That assumption is almost correct - it breaks in case of
racing automounts and in even harder to hit race between following a mountpoint
and a couple of mount --move. The thing is, we don't need to make that
assumption at all - after the end of loop in follow_manage() we can check
if path->mnt has ended up unchanged and do mntput() if needed.
The BUG can be reproduced with the following test program:
#include <stdio.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <sys/wait.h>
int main(int argc, char **argv)
{
int pid, ws;
struct stat buf;
pid = fork();
stat(argv[1], &buf);
if (pid > 0) wait(&ws);
return 0;
}
and the following procedure:
(1) Mount an NFS volume that on the server has something else mounted on a
subdirectory. For instance, I can mount / from my server:
mount warthog:/ /mnt -t nfs4 -r
On the server /data has another filesystem mounted on it, so NFS will see
a change in FSID as it walks down the path, and will mark /mnt/data as
being a mountpoint. This will cause the automount code to be triggered.
!!! Do not look inside the mounted fs at this point !!!
(2) Run the above program on a file within the submount to generate two
simultaneous automount requests:
/tmp/forkstat /mnt/data/testfile
(3) Unmount the automounted submount:
umount /mnt/data
(4) Unmount the original mount:
umount /mnt
At this point the kernel should throw a BUG with something like the
following:
BUG: Dentry ffff880032e3c5c0{i=2,n=} still in use (1) [unmount of nfs4 0:12]
Note that the bug appears on the root dentry of the original mount, not the
mountpoint and not the submount because sys_umount() hasn't got to its final
mntput_no_expire() yet, but this isn't so obvious from the call trace:
[<ffffffff8117cd82>] shrink_dcache_for_umount+0x69/0x82
[<ffffffff8116160e>] generic_shutdown_super+0x37/0x15b
[<ffffffffa00fae56>] ? nfs_super_return_all_delegations+0x2e/0x1b1 [nfs]
[<ffffffff811617f3>] kill_anon_super+0x1d/0x7e
[<ffffffffa00d0be1>] nfs4_kill_super+0x60/0xb6 [nfs]
[<ffffffff81161c17>] deactivate_locked_super+0x34/0x83
[<ffffffff811629ff>] deactivate_super+0x6f/0x7b
[<ffffffff81186261>] mntput_no_expire+0x18d/0x199
[<ffffffff811862a8>] mntput+0x3b/0x44
[<ffffffff81186d87>] release_mounts+0xa2/0xbf
[<ffffffff811876af>] sys_umount+0x47a/0x4ba
[<ffffffff8109e1ca>] ? trace_hardirqs_on_caller+0x1fd/0x22f
[<ffffffff816ea86b>] system_call_fastpath+0x16/0x1b
as do_umount() is inlined. However, you can see release_mounts() in there.
Note also that it may be necessary to have multiple CPU cores to be able to
trigger this bug.
Tested-by: Jeff Layton <jlayton@redhat.com>
Tested-by: Ian Kent <raven@themaw.net>
Signed-off-by: David Howells <dhowells@redhat.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
1 parent 50338b8
sysctl_net_netrom.c
/*
* 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.
*
* Copyright (C) 1996 Mike Shaver (shaver@zeroknowledge.com)
*/
#include <linux/mm.h>
#include <linux/sysctl.h>
#include <linux/init.h>
#include <net/ax25.h>
#include <net/netrom.h>
/*
* Values taken from NET/ROM documentation.
*/
static int min_quality[] = {0}, max_quality[] = {255};
static int min_obs[] = {0}, max_obs[] = {255};
static int min_ttl[] = {0}, max_ttl[] = {255};
static int min_t1[] = {5 * HZ};
static int max_t1[] = {600 * HZ};
static int min_n2[] = {2}, max_n2[] = {127};
static int min_t2[] = {1 * HZ};
static int max_t2[] = {60 * HZ};
static int min_t4[] = {1 * HZ};
static int max_t4[] = {1000 * HZ};
static int min_window[] = {1}, max_window[] = {127};
static int min_idle[] = {0 * HZ};
static int max_idle[] = {65535 * HZ};
static int min_route[] = {0}, max_route[] = {1};
static int min_fails[] = {1}, max_fails[] = {10};
static int min_reset[] = {0}, max_reset[] = {1};
static struct ctl_table_header *nr_table_header;
static ctl_table nr_table[] = {
{
.procname = "default_path_quality",
.data = &sysctl_netrom_default_path_quality,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_quality,
.extra2 = &max_quality
},
{
.procname = "obsolescence_count_initialiser",
.data = &sysctl_netrom_obsolescence_count_initialiser,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_obs,
.extra2 = &max_obs
},
{
.procname = "network_ttl_initialiser",
.data = &sysctl_netrom_network_ttl_initialiser,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_ttl,
.extra2 = &max_ttl
},
{
.procname = "transport_timeout",
.data = &sysctl_netrom_transport_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_t1,
.extra2 = &max_t1
},
{
.procname = "transport_maximum_tries",
.data = &sysctl_netrom_transport_maximum_tries,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_n2,
.extra2 = &max_n2
},
{
.procname = "transport_acknowledge_delay",
.data = &sysctl_netrom_transport_acknowledge_delay,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_t2,
.extra2 = &max_t2
},
{
.procname = "transport_busy_delay",
.data = &sysctl_netrom_transport_busy_delay,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_t4,
.extra2 = &max_t4
},
{
.procname = "transport_requested_window_size",
.data = &sysctl_netrom_transport_requested_window_size,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_window,
.extra2 = &max_window
},
{
.procname = "transport_no_activity_timeout",
.data = &sysctl_netrom_transport_no_activity_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_idle,
.extra2 = &max_idle
},
{
.procname = "routing_control",
.data = &sysctl_netrom_routing_control,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_route,
.extra2 = &max_route
},
{
.procname = "link_fails_count",
.data = &sysctl_netrom_link_fails_count,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_fails,
.extra2 = &max_fails
},
{
.procname = "reset",
.data = &sysctl_netrom_reset_circuit,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_minmax,
.extra1 = &min_reset,
.extra2 = &max_reset
},
{ }
};
static struct ctl_path nr_path[] = {
{ .procname = "net", },
{ .procname = "netrom", },
{ }
};
void __init nr_register_sysctl(void)
{
nr_table_header = register_sysctl_paths(nr_path, nr_table);
}
void nr_unregister_sysctl(void)
{
unregister_sysctl_table(nr_table_header);
}
Computing file changes ...
