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
apm-power.c
/*
* Input Power Event -> APM Bridge
*
* Copyright (c) 2007 Richard Purdie
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/module.h>
#include <linux/input.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/tty.h>
#include <linux/delay.h>
#include <linux/pm.h>
#include <linux/apm-emulation.h>
static void system_power_event(unsigned int keycode)
{
switch (keycode) {
case KEY_SUSPEND:
apm_queue_event(APM_USER_SUSPEND);
pr_info("Requesting system suspend...\n");
break;
default:
break;
}
}
static void apmpower_event(struct input_handle *handle, unsigned int type,
unsigned int code, int value)
{
/* only react on key down events */
if (value != 1)
return;
switch (type) {
case EV_PWR:
system_power_event(code);
break;
default:
break;
}
}
static int apmpower_connect(struct input_handler *handler,
struct input_dev *dev,
const struct input_device_id *id)
{
struct input_handle *handle;
int error;
handle = kzalloc(sizeof(struct input_handle), GFP_KERNEL);
if (!handle)
return -ENOMEM;
handle->dev = dev;
handle->handler = handler;
handle->name = "apm-power";
error = input_register_handle(handle);
if (error) {
pr_err("Failed to register input power handler, error %d\n",
error);
kfree(handle);
return error;
}
error = input_open_device(handle);
if (error) {
pr_err("Failed to open input power device, error %d\n", error);
input_unregister_handle(handle);
kfree(handle);
return error;
}
return 0;
}
static void apmpower_disconnect(struct input_handle *handle)
{
input_close_device(handle);
input_unregister_handle(handle);
kfree(handle);
}
static const struct input_device_id apmpower_ids[] = {
{
.flags = INPUT_DEVICE_ID_MATCH_EVBIT,
.evbit = { BIT_MASK(EV_PWR) },
},
{ },
};
MODULE_DEVICE_TABLE(input, apmpower_ids);
static struct input_handler apmpower_handler = {
.event = apmpower_event,
.connect = apmpower_connect,
.disconnect = apmpower_disconnect,
.name = "apm-power",
.id_table = apmpower_ids,
};
static int __init apmpower_init(void)
{
return input_register_handler(&apmpower_handler);
}
static void __exit apmpower_exit(void)
{
input_unregister_handler(&apmpower_handler);
}
module_init(apmpower_init);
module_exit(apmpower_exit);
MODULE_AUTHOR("Richard Purdie <rpurdie@rpsys.net>");
MODULE_DESCRIPTION("Input Power Event -> APM Bridge");
MODULE_LICENSE("GPL");
Computing file changes ...