linux_dsm_epyc7002/kernel/time/posix-clock.c
Vladis Dronov a33121e548 ptp: fix the race between the release of ptp_clock and cdev
In a case when a ptp chardev (like /dev/ptp0) is open but an underlying
device is removed, closing this file leads to a race. This reproduces
easily in a kvm virtual machine:

ts# cat openptp0.c
int main() { ... fp = fopen("/dev/ptp0", "r"); ... sleep(10); }
ts# uname -r
5.5.0-rc3-46cf053e
ts# cat /proc/cmdline
... slub_debug=FZP
ts# modprobe ptp_kvm
ts# ./openptp0 &
[1] 670
opened /dev/ptp0, sleeping 10s...
ts# rmmod ptp_kvm
ts# ls /dev/ptp*
ls: cannot access '/dev/ptp*': No such file or directory
ts# ...woken up
[   48.010809] general protection fault: 0000 [#1] SMP
[   48.012502] CPU: 6 PID: 658 Comm: openptp0 Not tainted 5.5.0-rc3-46cf053e #25
[   48.014624] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), ...
[   48.016270] RIP: 0010:module_put.part.0+0x7/0x80
[   48.017939] RSP: 0018:ffffb3850073be00 EFLAGS: 00010202
[   48.018339] RAX: 000000006b6b6b6b RBX: 6b6b6b6b6b6b6b6b RCX: ffff89a476c00ad0
[   48.018936] RDX: fffff65a08d3ea08 RSI: 0000000000000247 RDI: 6b6b6b6b6b6b6b6b
[   48.019470] ...                                              ^^^ a slub poison
[   48.023854] Call Trace:
[   48.024050]  __fput+0x21f/0x240
[   48.024288]  task_work_run+0x79/0x90
[   48.024555]  do_exit+0x2af/0xab0
[   48.024799]  ? vfs_write+0x16a/0x190
[   48.025082]  do_group_exit+0x35/0x90
[   48.025387]  __x64_sys_exit_group+0xf/0x10
[   48.025737]  do_syscall_64+0x3d/0x130
[   48.026056]  entry_SYSCALL_64_after_hwframe+0x44/0xa9
[   48.026479] RIP: 0033:0x7f53b12082f6
[   48.026792] ...
[   48.030945] Modules linked in: ptp i6300esb watchdog [last unloaded: ptp_kvm]
[   48.045001] Fixing recursive fault but reboot is needed!

This happens in:

static void __fput(struct file *file)
{   ...
    if (file->f_op->release)
        file->f_op->release(inode, file); <<< cdev is kfree'd here
    if (unlikely(S_ISCHR(inode->i_mode) && inode->i_cdev != NULL &&
             !(mode & FMODE_PATH))) {
        cdev_put(inode->i_cdev); <<< cdev fields are accessed here

Namely:

__fput()
  posix_clock_release()
    kref_put(&clk->kref, delete_clock) <<< the last reference
      delete_clock()
        delete_ptp_clock()
          kfree(ptp) <<< cdev is embedded in ptp
  cdev_put
    module_put(p->owner) <<< *p is kfree'd, bang!

Here cdev is embedded in posix_clock which is embedded in ptp_clock.
The race happens because ptp_clock's lifetime is controlled by two
refcounts: kref and cdev.kobj in posix_clock. This is wrong.

Make ptp_clock's sysfs device a parent of cdev with cdev_device_add()
created especially for such cases. This way the parent device with its
ptp_clock is not released until all references to the cdev are released.
This adds a requirement that an initialized but not exposed struct
device should be provided to posix_clock_register() by a caller instead
of a simple dev_t.

This approach was adopted from the commit 72139dfa24 ("watchdog: Fix
the race between the release of watchdog_core_data and cdev"). See
details of the implementation in the commit 233ed09d7f ("chardev: add
helper function to register char devs with a struct device").

Link: https://lore.kernel.org/linux-fsdevel/20191125125342.6189-1-vdronov@redhat.com/T/#u
Analyzed-by: Stephen Johnston <sjohnsto@redhat.com>
Analyzed-by: Vern Lovejoy <vlovejoy@redhat.com>
Signed-off-by: Vladis Dronov <vdronov@redhat.com>
Acked-by: Richard Cochran <richardcochran@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2019-12-30 20:19:27 -08:00

318 lines
5.6 KiB
C

// SPDX-License-Identifier: GPL-2.0+
/*
* Support for dynamic clock devices
*
* Copyright (C) 2010 OMICRON electronics GmbH
*/
#include <linux/device.h>
#include <linux/export.h>
#include <linux/file.h>
#include <linux/posix-clock.h>
#include <linux/slab.h>
#include <linux/syscalls.h>
#include <linux/uaccess.h>
#include "posix-timers.h"
/*
* Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
*/
static struct posix_clock *get_posix_clock(struct file *fp)
{
struct posix_clock *clk = fp->private_data;
down_read(&clk->rwsem);
if (!clk->zombie)
return clk;
up_read(&clk->rwsem);
return NULL;
}
static void put_posix_clock(struct posix_clock *clk)
{
up_read(&clk->rwsem);
}
static ssize_t posix_clock_read(struct file *fp, char __user *buf,
size_t count, loff_t *ppos)
{
struct posix_clock *clk = get_posix_clock(fp);
int err = -EINVAL;
if (!clk)
return -ENODEV;
if (clk->ops.read)
err = clk->ops.read(clk, fp->f_flags, buf, count);
put_posix_clock(clk);
return err;
}
static __poll_t posix_clock_poll(struct file *fp, poll_table *wait)
{
struct posix_clock *clk = get_posix_clock(fp);
__poll_t result = 0;
if (!clk)
return EPOLLERR;
if (clk->ops.poll)
result = clk->ops.poll(clk, fp, wait);
put_posix_clock(clk);
return result;
}
static long posix_clock_ioctl(struct file *fp,
unsigned int cmd, unsigned long arg)
{
struct posix_clock *clk = get_posix_clock(fp);
int err = -ENOTTY;
if (!clk)
return -ENODEV;
if (clk->ops.ioctl)
err = clk->ops.ioctl(clk, cmd, arg);
put_posix_clock(clk);
return err;
}
#ifdef CONFIG_COMPAT
static long posix_clock_compat_ioctl(struct file *fp,
unsigned int cmd, unsigned long arg)
{
struct posix_clock *clk = get_posix_clock(fp);
int err = -ENOTTY;
if (!clk)
return -ENODEV;
if (clk->ops.ioctl)
err = clk->ops.ioctl(clk, cmd, arg);
put_posix_clock(clk);
return err;
}
#endif
static int posix_clock_open(struct inode *inode, struct file *fp)
{
int err;
struct posix_clock *clk =
container_of(inode->i_cdev, struct posix_clock, cdev);
down_read(&clk->rwsem);
if (clk->zombie) {
err = -ENODEV;
goto out;
}
if (clk->ops.open)
err = clk->ops.open(clk, fp->f_mode);
else
err = 0;
if (!err) {
get_device(clk->dev);
fp->private_data = clk;
}
out:
up_read(&clk->rwsem);
return err;
}
static int posix_clock_release(struct inode *inode, struct file *fp)
{
struct posix_clock *clk = fp->private_data;
int err = 0;
if (clk->ops.release)
err = clk->ops.release(clk);
put_device(clk->dev);
fp->private_data = NULL;
return err;
}
static const struct file_operations posix_clock_file_operations = {
.owner = THIS_MODULE,
.llseek = no_llseek,
.read = posix_clock_read,
.poll = posix_clock_poll,
.unlocked_ioctl = posix_clock_ioctl,
.open = posix_clock_open,
.release = posix_clock_release,
#ifdef CONFIG_COMPAT
.compat_ioctl = posix_clock_compat_ioctl,
#endif
};
int posix_clock_register(struct posix_clock *clk, struct device *dev)
{
int err;
init_rwsem(&clk->rwsem);
cdev_init(&clk->cdev, &posix_clock_file_operations);
err = cdev_device_add(&clk->cdev, dev);
if (err) {
pr_err("%s unable to add device %d:%d\n",
dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
return err;
}
clk->cdev.owner = clk->ops.owner;
clk->dev = dev;
return 0;
}
EXPORT_SYMBOL_GPL(posix_clock_register);
void posix_clock_unregister(struct posix_clock *clk)
{
cdev_device_del(&clk->cdev, clk->dev);
down_write(&clk->rwsem);
clk->zombie = true;
up_write(&clk->rwsem);
put_device(clk->dev);
}
EXPORT_SYMBOL_GPL(posix_clock_unregister);
struct posix_clock_desc {
struct file *fp;
struct posix_clock *clk;
};
static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
{
struct file *fp = fget(clockid_to_fd(id));
int err = -EINVAL;
if (!fp)
return err;
if (fp->f_op->open != posix_clock_open || !fp->private_data)
goto out;
cd->fp = fp;
cd->clk = get_posix_clock(fp);
err = cd->clk ? 0 : -ENODEV;
out:
if (err)
fput(fp);
return err;
}
static void put_clock_desc(struct posix_clock_desc *cd)
{
put_posix_clock(cd->clk);
fput(cd->fp);
}
static int pc_clock_adjtime(clockid_t id, struct __kernel_timex *tx)
{
struct posix_clock_desc cd;
int err;
err = get_clock_desc(id, &cd);
if (err)
return err;
if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
err = -EACCES;
goto out;
}
if (cd.clk->ops.clock_adjtime)
err = cd.clk->ops.clock_adjtime(cd.clk, tx);
else
err = -EOPNOTSUPP;
out:
put_clock_desc(&cd);
return err;
}
static int pc_clock_gettime(clockid_t id, struct timespec64 *ts)
{
struct posix_clock_desc cd;
int err;
err = get_clock_desc(id, &cd);
if (err)
return err;
if (cd.clk->ops.clock_gettime)
err = cd.clk->ops.clock_gettime(cd.clk, ts);
else
err = -EOPNOTSUPP;
put_clock_desc(&cd);
return err;
}
static int pc_clock_getres(clockid_t id, struct timespec64 *ts)
{
struct posix_clock_desc cd;
int err;
err = get_clock_desc(id, &cd);
if (err)
return err;
if (cd.clk->ops.clock_getres)
err = cd.clk->ops.clock_getres(cd.clk, ts);
else
err = -EOPNOTSUPP;
put_clock_desc(&cd);
return err;
}
static int pc_clock_settime(clockid_t id, const struct timespec64 *ts)
{
struct posix_clock_desc cd;
int err;
err = get_clock_desc(id, &cd);
if (err)
return err;
if ((cd.fp->f_mode & FMODE_WRITE) == 0) {
err = -EACCES;
goto out;
}
if (cd.clk->ops.clock_settime)
err = cd.clk->ops.clock_settime(cd.clk, ts);
else
err = -EOPNOTSUPP;
out:
put_clock_desc(&cd);
return err;
}
const struct k_clock clock_posix_dynamic = {
.clock_getres = pc_clock_getres,
.clock_set = pc_clock_settime,
.clock_get = pc_clock_gettime,
.clock_adj = pc_clock_adjtime,
};