linux_dsm_epyc7002/fs/char_dev.c
Will Deacon 68faa679b8 chardev: Avoid potential use-after-free in 'chrdev_open()'
'chrdev_open()' calls 'cdev_get()' to obtain a reference to the
'struct cdev *' stashed in the 'i_cdev' field of the target inode
structure. If the pointer is NULL, then it is initialised lazily by
looking up the kobject in the 'cdev_map' and so the whole procedure is
protected by the 'cdev_lock' spinlock to serialise initialisation of
the shared pointer.

Unfortunately, it is possible for the initialising thread to fail *after*
installing the new pointer, for example if the subsequent '->open()' call
on the file fails. In this case, 'cdev_put()' is called, the reference
count on the kobject is dropped and, if nobody else has taken a reference,
the release function is called which finally clears 'inode->i_cdev' from
'cdev_purge()' before potentially freeing the object. The problem here
is that a racing thread can happily take the 'cdev_lock' and see the
non-NULL pointer in the inode, which can result in a refcount increment
from zero and a warning:

  |  ------------[ cut here ]------------
  |  refcount_t: addition on 0; use-after-free.
  |  WARNING: CPU: 2 PID: 6385 at lib/refcount.c:25 refcount_warn_saturate+0x6d/0xf0
  |  Modules linked in:
  |  CPU: 2 PID: 6385 Comm: repro Not tainted 5.5.0-rc2+ 
  |  Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.12.0-1 04/01/2014
  |  RIP: 0010:refcount_warn_saturate+0x6d/0xf0
  |  Code: 05 55 9a 15 01 01 e8 9d aa c8 ff 0f 0b c3 80 3d 45 9a 15 01 00 75 ce 48 c7 c7 00 9c 62 b3 c6 08
  |  RSP: 0018:ffffb524c1b9bc70 EFLAGS: 00010282
  |  RAX: 0000000000000000 RBX: ffff9e9da1f71390 RCX: 0000000000000000
  |  RDX: ffff9e9dbbd27618 RSI: ffff9e9dbbd18798 RDI: ffff9e9dbbd18798
  |  RBP: 0000000000000000 R08: 000000000000095f R09: 0000000000000039
  |  R10: 0000000000000000 R11: ffffb524c1b9bb20 R12: ffff9e9da1e8c700
  |  R13: ffffffffb25ee8b0 R14: 0000000000000000 R15: ffff9e9da1e8c700
  |  FS:  00007f3b87d26700(0000) GS:ffff9e9dbbd00000(0000) knlGS:0000000000000000
  |  CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
  |  CR2: 00007fc16909c000 CR3: 000000012df9c000 CR4: 00000000000006e0
  |  DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
  |  DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
  |  Call Trace:
  |   kobject_get+0x5c/0x60
  |   cdev_get+0x2b/0x60
  |   chrdev_open+0x55/0x220
  |   ? cdev_put.part.3+0x20/0x20
  |   do_dentry_open+0x13a/0x390
  |   path_openat+0x2c8/0x1470
  |   do_filp_open+0x93/0x100
  |   ? selinux_file_ioctl+0x17f/0x220
  |   do_sys_open+0x186/0x220
  |   do_syscall_64+0x48/0x150
  |   entry_SYSCALL_64_after_hwframe+0x44/0xa9
  |  RIP: 0033:0x7f3b87efcd0e
  |  Code: 89 54 24 08 e8 a3 f4 ff ff 8b 74 24 0c 48 8b 3c 24 41 89 c0 44 8b 54 24 08 b8 01 01 00 00 89 f4
  |  RSP: 002b:00007f3b87d259f0 EFLAGS: 00000293 ORIG_RAX: 0000000000000101
  |  RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f3b87efcd0e
  |  RDX: 0000000000000000 RSI: 00007f3b87d25a80 RDI: 00000000ffffff9c
  |  RBP: 00007f3b87d25e90 R08: 0000000000000000 R09: 0000000000000000
  |  R10: 0000000000000000 R11: 0000000000000293 R12: 00007ffe188f504e
  |  R13: 00007ffe188f504f R14: 00007f3b87d26700 R15: 0000000000000000
  |  ---[ end trace 24f53ca58db8180a ]---

Since 'cdev_get()' can already fail to obtain a reference, simply move
it over to use 'kobject_get_unless_zero()' instead of 'kobject_get()',
which will cause the racing thread to return -ENXIO if the initialising
thread fails unexpectedly.

Cc: Hillf Danton <hdanton@sina.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Reported-by: syzbot+82defefbbd8527e1c2cb@syzkaller.appspotmail.com
Signed-off-by: Will Deacon <will@kernel.org>
Cc: stable <stable@vger.kernel.org>
Link: https://lore.kernel.org/r/20191219120203.32691-1-will@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2020-01-06 20:10:26 +01:00

683 lines
16 KiB
C

// SPDX-License-Identifier: GPL-2.0
/*
* linux/fs/char_dev.c
*
* Copyright (C) 1991, 1992 Linus Torvalds
*/
#include <linux/init.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/major.h>
#include <linux/errno.h>
#include <linux/module.h>
#include <linux/seq_file.h>
#include <linux/kobject.h>
#include <linux/kobj_map.h>
#include <linux/cdev.h>
#include <linux/mutex.h>
#include <linux/backing-dev.h>
#include <linux/tty.h>
#include "internal.h"
static struct kobj_map *cdev_map;
static DEFINE_MUTEX(chrdevs_lock);
#define CHRDEV_MAJOR_HASH_SIZE 255
static struct char_device_struct {
struct char_device_struct *next;
unsigned int major;
unsigned int baseminor;
int minorct;
char name[64];
struct cdev *cdev; /* will die */
} *chrdevs[CHRDEV_MAJOR_HASH_SIZE];
/* index in the above */
static inline int major_to_index(unsigned major)
{
return major % CHRDEV_MAJOR_HASH_SIZE;
}
#ifdef CONFIG_PROC_FS
void chrdev_show(struct seq_file *f, off_t offset)
{
struct char_device_struct *cd;
mutex_lock(&chrdevs_lock);
for (cd = chrdevs[major_to_index(offset)]; cd; cd = cd->next) {
if (cd->major == offset)
seq_printf(f, "%3d %s\n", cd->major, cd->name);
}
mutex_unlock(&chrdevs_lock);
}
#endif /* CONFIG_PROC_FS */
static int find_dynamic_major(void)
{
int i;
struct char_device_struct *cd;
for (i = ARRAY_SIZE(chrdevs)-1; i >= CHRDEV_MAJOR_DYN_END; i--) {
if (chrdevs[i] == NULL)
return i;
}
for (i = CHRDEV_MAJOR_DYN_EXT_START;
i >= CHRDEV_MAJOR_DYN_EXT_END; i--) {
for (cd = chrdevs[major_to_index(i)]; cd; cd = cd->next)
if (cd->major == i)
break;
if (cd == NULL)
return i;
}
return -EBUSY;
}
/*
* Register a single major with a specified minor range.
*
* If major == 0 this function will dynamically allocate an unused major.
* If major > 0 this function will attempt to reserve the range of minors
* with given major.
*
*/
static struct char_device_struct *
__register_chrdev_region(unsigned int major, unsigned int baseminor,
int minorct, const char *name)
{
struct char_device_struct *cd, *curr, *prev = NULL;
int ret;
int i;
if (major >= CHRDEV_MAJOR_MAX) {
pr_err("CHRDEV \"%s\" major requested (%u) is greater than the maximum (%u)\n",
name, major, CHRDEV_MAJOR_MAX-1);
return ERR_PTR(-EINVAL);
}
if (minorct > MINORMASK + 1 - baseminor) {
pr_err("CHRDEV \"%s\" minor range requested (%u-%u) is out of range of maximum range (%u-%u) for a single major\n",
name, baseminor, baseminor + minorct - 1, 0, MINORMASK);
return ERR_PTR(-EINVAL);
}
cd = kzalloc(sizeof(struct char_device_struct), GFP_KERNEL);
if (cd == NULL)
return ERR_PTR(-ENOMEM);
mutex_lock(&chrdevs_lock);
if (major == 0) {
ret = find_dynamic_major();
if (ret < 0) {
pr_err("CHRDEV \"%s\" dynamic allocation region is full\n",
name);
goto out;
}
major = ret;
}
ret = -EBUSY;
i = major_to_index(major);
for (curr = chrdevs[i]; curr; prev = curr, curr = curr->next) {
if (curr->major < major)
continue;
if (curr->major > major)
break;
if (curr->baseminor + curr->minorct <= baseminor)
continue;
if (curr->baseminor >= baseminor + minorct)
break;
goto out;
}
cd->major = major;
cd->baseminor = baseminor;
cd->minorct = minorct;
strlcpy(cd->name, name, sizeof(cd->name));
if (!prev) {
cd->next = curr;
chrdevs[i] = cd;
} else {
cd->next = prev->next;
prev->next = cd;
}
mutex_unlock(&chrdevs_lock);
return cd;
out:
mutex_unlock(&chrdevs_lock);
kfree(cd);
return ERR_PTR(ret);
}
static struct char_device_struct *
__unregister_chrdev_region(unsigned major, unsigned baseminor, int minorct)
{
struct char_device_struct *cd = NULL, **cp;
int i = major_to_index(major);
mutex_lock(&chrdevs_lock);
for (cp = &chrdevs[i]; *cp; cp = &(*cp)->next)
if ((*cp)->major == major &&
(*cp)->baseminor == baseminor &&
(*cp)->minorct == minorct)
break;
if (*cp) {
cd = *cp;
*cp = cd->next;
}
mutex_unlock(&chrdevs_lock);
return cd;
}
/**
* register_chrdev_region() - register a range of device numbers
* @from: the first in the desired range of device numbers; must include
* the major number.
* @count: the number of consecutive device numbers required
* @name: the name of the device or driver.
*
* Return value is zero on success, a negative error code on failure.
*/
int register_chrdev_region(dev_t from, unsigned count, const char *name)
{
struct char_device_struct *cd;
dev_t to = from + count;
dev_t n, next;
for (n = from; n < to; n = next) {
next = MKDEV(MAJOR(n)+1, 0);
if (next > to)
next = to;
cd = __register_chrdev_region(MAJOR(n), MINOR(n),
next - n, name);
if (IS_ERR(cd))
goto fail;
}
return 0;
fail:
to = n;
for (n = from; n < to; n = next) {
next = MKDEV(MAJOR(n)+1, 0);
kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n));
}
return PTR_ERR(cd);
}
/**
* alloc_chrdev_region() - register a range of char device numbers
* @dev: output parameter for first assigned number
* @baseminor: first of the requested range of minor numbers
* @count: the number of minor numbers required
* @name: the name of the associated device or driver
*
* Allocates a range of char device numbers. The major number will be
* chosen dynamically, and returned (along with the first minor number)
* in @dev. Returns zero or a negative error code.
*/
int alloc_chrdev_region(dev_t *dev, unsigned baseminor, unsigned count,
const char *name)
{
struct char_device_struct *cd;
cd = __register_chrdev_region(0, baseminor, count, name);
if (IS_ERR(cd))
return PTR_ERR(cd);
*dev = MKDEV(cd->major, cd->baseminor);
return 0;
}
/**
* __register_chrdev() - create and register a cdev occupying a range of minors
* @major: major device number or 0 for dynamic allocation
* @baseminor: first of the requested range of minor numbers
* @count: the number of minor numbers required
* @name: name of this range of devices
* @fops: file operations associated with this devices
*
* If @major == 0 this functions will dynamically allocate a major and return
* its number.
*
* If @major > 0 this function will attempt to reserve a device with the given
* major number and will return zero on success.
*
* Returns a -ve errno on failure.
*
* The name of this device has nothing to do with the name of the device in
* /dev. It only helps to keep track of the different owners of devices. If
* your module name has only one type of devices it's ok to use e.g. the name
* of the module here.
*/
int __register_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name,
const struct file_operations *fops)
{
struct char_device_struct *cd;
struct cdev *cdev;
int err = -ENOMEM;
cd = __register_chrdev_region(major, baseminor, count, name);
if (IS_ERR(cd))
return PTR_ERR(cd);
cdev = cdev_alloc();
if (!cdev)
goto out2;
cdev->owner = fops->owner;
cdev->ops = fops;
kobject_set_name(&cdev->kobj, "%s", name);
err = cdev_add(cdev, MKDEV(cd->major, baseminor), count);
if (err)
goto out;
cd->cdev = cdev;
return major ? 0 : cd->major;
out:
kobject_put(&cdev->kobj);
out2:
kfree(__unregister_chrdev_region(cd->major, baseminor, count));
return err;
}
/**
* unregister_chrdev_region() - unregister a range of device numbers
* @from: the first in the range of numbers to unregister
* @count: the number of device numbers to unregister
*
* This function will unregister a range of @count device numbers,
* starting with @from. The caller should normally be the one who
* allocated those numbers in the first place...
*/
void unregister_chrdev_region(dev_t from, unsigned count)
{
dev_t to = from + count;
dev_t n, next;
for (n = from; n < to; n = next) {
next = MKDEV(MAJOR(n)+1, 0);
if (next > to)
next = to;
kfree(__unregister_chrdev_region(MAJOR(n), MINOR(n), next - n));
}
}
/**
* __unregister_chrdev - unregister and destroy a cdev
* @major: major device number
* @baseminor: first of the range of minor numbers
* @count: the number of minor numbers this cdev is occupying
* @name: name of this range of devices
*
* Unregister and destroy the cdev occupying the region described by
* @major, @baseminor and @count. This function undoes what
* __register_chrdev() did.
*/
void __unregister_chrdev(unsigned int major, unsigned int baseminor,
unsigned int count, const char *name)
{
struct char_device_struct *cd;
cd = __unregister_chrdev_region(major, baseminor, count);
if (cd && cd->cdev)
cdev_del(cd->cdev);
kfree(cd);
}
static DEFINE_SPINLOCK(cdev_lock);
static struct kobject *cdev_get(struct cdev *p)
{
struct module *owner = p->owner;
struct kobject *kobj;
if (owner && !try_module_get(owner))
return NULL;
kobj = kobject_get_unless_zero(&p->kobj);
if (!kobj)
module_put(owner);
return kobj;
}
void cdev_put(struct cdev *p)
{
if (p) {
struct module *owner = p->owner;
kobject_put(&p->kobj);
module_put(owner);
}
}
/*
* Called every time a character special file is opened
*/
static int chrdev_open(struct inode *inode, struct file *filp)
{
const struct file_operations *fops;
struct cdev *p;
struct cdev *new = NULL;
int ret = 0;
spin_lock(&cdev_lock);
p = inode->i_cdev;
if (!p) {
struct kobject *kobj;
int idx;
spin_unlock(&cdev_lock);
kobj = kobj_lookup(cdev_map, inode->i_rdev, &idx);
if (!kobj)
return -ENXIO;
new = container_of(kobj, struct cdev, kobj);
spin_lock(&cdev_lock);
/* Check i_cdev again in case somebody beat us to it while
we dropped the lock. */
p = inode->i_cdev;
if (!p) {
inode->i_cdev = p = new;
list_add(&inode->i_devices, &p->list);
new = NULL;
} else if (!cdev_get(p))
ret = -ENXIO;
} else if (!cdev_get(p))
ret = -ENXIO;
spin_unlock(&cdev_lock);
cdev_put(new);
if (ret)
return ret;
ret = -ENXIO;
fops = fops_get(p->ops);
if (!fops)
goto out_cdev_put;
replace_fops(filp, fops);
if (filp->f_op->open) {
ret = filp->f_op->open(inode, filp);
if (ret)
goto out_cdev_put;
}
return 0;
out_cdev_put:
cdev_put(p);
return ret;
}
void cd_forget(struct inode *inode)
{
spin_lock(&cdev_lock);
list_del_init(&inode->i_devices);
inode->i_cdev = NULL;
inode->i_mapping = &inode->i_data;
spin_unlock(&cdev_lock);
}
static void cdev_purge(struct cdev *cdev)
{
spin_lock(&cdev_lock);
while (!list_empty(&cdev->list)) {
struct inode *inode;
inode = container_of(cdev->list.next, struct inode, i_devices);
list_del_init(&inode->i_devices);
inode->i_cdev = NULL;
}
spin_unlock(&cdev_lock);
}
/*
* Dummy default file-operations: the only thing this does
* is contain the open that then fills in the correct operations
* depending on the special file...
*/
const struct file_operations def_chr_fops = {
.open = chrdev_open,
.llseek = noop_llseek,
};
static struct kobject *exact_match(dev_t dev, int *part, void *data)
{
struct cdev *p = data;
return &p->kobj;
}
static int exact_lock(dev_t dev, void *data)
{
struct cdev *p = data;
return cdev_get(p) ? 0 : -1;
}
/**
* cdev_add() - add a char device to the system
* @p: the cdev structure for the device
* @dev: the first device number for which this device is responsible
* @count: the number of consecutive minor numbers corresponding to this
* device
*
* cdev_add() adds the device represented by @p to the system, making it
* live immediately. A negative error code is returned on failure.
*/
int cdev_add(struct cdev *p, dev_t dev, unsigned count)
{
int error;
p->dev = dev;
p->count = count;
error = kobj_map(cdev_map, dev, count, NULL,
exact_match, exact_lock, p);
if (error)
return error;
kobject_get(p->kobj.parent);
return 0;
}
/**
* cdev_set_parent() - set the parent kobject for a char device
* @p: the cdev structure
* @kobj: the kobject to take a reference to
*
* cdev_set_parent() sets a parent kobject which will be referenced
* appropriately so the parent is not freed before the cdev. This
* should be called before cdev_add.
*/
void cdev_set_parent(struct cdev *p, struct kobject *kobj)
{
WARN_ON(!kobj->state_initialized);
p->kobj.parent = kobj;
}
/**
* cdev_device_add() - add a char device and it's corresponding
* struct device, linkink
* @dev: the device structure
* @cdev: the cdev structure
*
* cdev_device_add() adds the char device represented by @cdev to the system,
* just as cdev_add does. It then adds @dev to the system using device_add
* The dev_t for the char device will be taken from the struct device which
* needs to be initialized first. This helper function correctly takes a
* reference to the parent device so the parent will not get released until
* all references to the cdev are released.
*
* This helper uses dev->devt for the device number. If it is not set
* it will not add the cdev and it will be equivalent to device_add.
*
* This function should be used whenever the struct cdev and the
* struct device are members of the same structure whose lifetime is
* managed by the struct device.
*
* NOTE: Callers must assume that userspace was able to open the cdev and
* can call cdev fops callbacks at any time, even if this function fails.
*/
int cdev_device_add(struct cdev *cdev, struct device *dev)
{
int rc = 0;
if (dev->devt) {
cdev_set_parent(cdev, &dev->kobj);
rc = cdev_add(cdev, dev->devt, 1);
if (rc)
return rc;
}
rc = device_add(dev);
if (rc)
cdev_del(cdev);
return rc;
}
/**
* cdev_device_del() - inverse of cdev_device_add
* @dev: the device structure
* @cdev: the cdev structure
*
* cdev_device_del() is a helper function to call cdev_del and device_del.
* It should be used whenever cdev_device_add is used.
*
* If dev->devt is not set it will not remove the cdev and will be equivalent
* to device_del.
*
* NOTE: This guarantees that associated sysfs callbacks are not running
* or runnable, however any cdevs already open will remain and their fops
* will still be callable even after this function returns.
*/
void cdev_device_del(struct cdev *cdev, struct device *dev)
{
device_del(dev);
if (dev->devt)
cdev_del(cdev);
}
static void cdev_unmap(dev_t dev, unsigned count)
{
kobj_unmap(cdev_map, dev, count);
}
/**
* cdev_del() - remove a cdev from the system
* @p: the cdev structure to be removed
*
* cdev_del() removes @p from the system, possibly freeing the structure
* itself.
*
* NOTE: This guarantees that cdev device will no longer be able to be
* opened, however any cdevs already open will remain and their fops will
* still be callable even after cdev_del returns.
*/
void cdev_del(struct cdev *p)
{
cdev_unmap(p->dev, p->count);
kobject_put(&p->kobj);
}
static void cdev_default_release(struct kobject *kobj)
{
struct cdev *p = container_of(kobj, struct cdev, kobj);
struct kobject *parent = kobj->parent;
cdev_purge(p);
kobject_put(parent);
}
static void cdev_dynamic_release(struct kobject *kobj)
{
struct cdev *p = container_of(kobj, struct cdev, kobj);
struct kobject *parent = kobj->parent;
cdev_purge(p);
kfree(p);
kobject_put(parent);
}
static struct kobj_type ktype_cdev_default = {
.release = cdev_default_release,
};
static struct kobj_type ktype_cdev_dynamic = {
.release = cdev_dynamic_release,
};
/**
* cdev_alloc() - allocate a cdev structure
*
* Allocates and returns a cdev structure, or NULL on failure.
*/
struct cdev *cdev_alloc(void)
{
struct cdev *p = kzalloc(sizeof(struct cdev), GFP_KERNEL);
if (p) {
INIT_LIST_HEAD(&p->list);
kobject_init(&p->kobj, &ktype_cdev_dynamic);
}
return p;
}
/**
* cdev_init() - initialize a cdev structure
* @cdev: the structure to initialize
* @fops: the file_operations for this device
*
* Initializes @cdev, remembering @fops, making it ready to add to the
* system with cdev_add().
*/
void cdev_init(struct cdev *cdev, const struct file_operations *fops)
{
memset(cdev, 0, sizeof *cdev);
INIT_LIST_HEAD(&cdev->list);
kobject_init(&cdev->kobj, &ktype_cdev_default);
cdev->ops = fops;
}
static struct kobject *base_probe(dev_t dev, int *part, void *data)
{
if (request_module("char-major-%d-%d", MAJOR(dev), MINOR(dev)) > 0)
/* Make old-style 2.4 aliases work */
request_module("char-major-%d", MAJOR(dev));
return NULL;
}
void __init chrdev_init(void)
{
cdev_map = kobj_map_init(base_probe, &chrdevs_lock);
}
/* Let modules do char dev stuff */
EXPORT_SYMBOL(register_chrdev_region);
EXPORT_SYMBOL(unregister_chrdev_region);
EXPORT_SYMBOL(alloc_chrdev_region);
EXPORT_SYMBOL(cdev_init);
EXPORT_SYMBOL(cdev_alloc);
EXPORT_SYMBOL(cdev_del);
EXPORT_SYMBOL(cdev_add);
EXPORT_SYMBOL(cdev_set_parent);
EXPORT_SYMBOL(cdev_device_add);
EXPORT_SYMBOL(cdev_device_del);
EXPORT_SYMBOL(__register_chrdev);
EXPORT_SYMBOL(__unregister_chrdev);