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
twl4030-pwrbutton.c
/**
* twl4030-pwrbutton.c - TWL4030 Power Button Input Driver
*
* Copyright (C) 2008-2009 Nokia Corporation
*
* Written by Peter De Schrijver <peter.de-schrijver@nokia.com>
* Several fixes by Felipe Balbi <felipe.balbi@nokia.com>
*
* This file is subject to the terms and conditions of the GNU General
* Public License. See the file "COPYING" in the main directory of this
* archive for more details.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*
* You should have received a copy of the GNU General Public License
* along with this program; if not, write to the Free Software
* Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
*/
#include <linux/module.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/input.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
#include <linux/i2c/twl.h>
#define PWR_PWRON_IRQ (1 << 0)
#define STS_HW_CONDITIONS 0xf
static irqreturn_t powerbutton_irq(int irq, void *_pwr)
{
struct input_dev *pwr = _pwr;
int err;
u8 value;
err = twl_i2c_read_u8(TWL4030_MODULE_PM_MASTER, &value,
STS_HW_CONDITIONS);
if (!err) {
input_report_key(pwr, KEY_POWER, value & PWR_PWRON_IRQ);
input_sync(pwr);
} else {
dev_err(pwr->dev.parent, "twl4030: i2c error %d while reading"
" TWL4030 PM_MASTER STS_HW_CONDITIONS register\n", err);
}
return IRQ_HANDLED;
}
static int __init twl4030_pwrbutton_probe(struct platform_device *pdev)
{
struct input_dev *pwr;
int irq = platform_get_irq(pdev, 0);
int err;
pwr = input_allocate_device();
if (!pwr) {
dev_dbg(&pdev->dev, "Can't allocate power button\n");
return -ENOMEM;
}
pwr->evbit[0] = BIT_MASK(EV_KEY);
pwr->keybit[BIT_WORD(KEY_POWER)] = BIT_MASK(KEY_POWER);
pwr->name = "twl4030_pwrbutton";
pwr->phys = "twl4030_pwrbutton/input0";
pwr->dev.parent = &pdev->dev;
err = request_threaded_irq(irq, NULL, powerbutton_irq,
IRQF_TRIGGER_FALLING | IRQF_TRIGGER_RISING,
"twl4030_pwrbutton", pwr);
if (err < 0) {
dev_dbg(&pdev->dev, "Can't get IRQ for pwrbutton: %d\n", err);
goto free_input_dev;
}
err = input_register_device(pwr);
if (err) {
dev_dbg(&pdev->dev, "Can't register power button: %d\n", err);
goto free_irq;
}
platform_set_drvdata(pdev, pwr);
return 0;
free_irq:
free_irq(irq, pwr);
free_input_dev:
input_free_device(pwr);
return err;
}
static int __exit twl4030_pwrbutton_remove(struct platform_device *pdev)
{
struct input_dev *pwr = platform_get_drvdata(pdev);
int irq = platform_get_irq(pdev, 0);
free_irq(irq, pwr);
input_unregister_device(pwr);
return 0;
}
static struct platform_driver twl4030_pwrbutton_driver = {
.remove = __exit_p(twl4030_pwrbutton_remove),
.driver = {
.name = "twl4030_pwrbutton",
.owner = THIS_MODULE,
},
};
static int __init twl4030_pwrbutton_init(void)
{
return platform_driver_probe(&twl4030_pwrbutton_driver,
twl4030_pwrbutton_probe);
}
module_init(twl4030_pwrbutton_init);
static void __exit twl4030_pwrbutton_exit(void)
{
platform_driver_unregister(&twl4030_pwrbutton_driver);
}
module_exit(twl4030_pwrbutton_exit);
MODULE_ALIAS("platform:twl4030_pwrbutton");
MODULE_DESCRIPTION("Triton2 Power Button");
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Peter De Schrijver <peter.de-schrijver@nokia.com>");
MODULE_AUTHOR("Felipe Balbi <felipe.balbi@nokia.com>");
Computing file changes ...