This is a note to let you know that I've just added the patch titled
brd: defer automatic disk creation until module initialization succeeds
to the 5.15-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
brd-defer-automatic-disk-creation-until-module-initi.patch
and it can be found in the queue-5.15 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 71b1a8f0ff3b2d340c8a11235c30cd0387b28b5b
Author: Yang Erkun <yangerkun@xxxxxxxxxx>
Date: Wed Oct 30 11:49:14 2024 +0800
brd: defer automatic disk creation until module initialization succeeds
[ Upstream commit 826cc42adf44930a633d11a5993676d85ddb0842 ]
My colleague Wupeng found the following problems during fault injection:
BUG: unable to handle page fault for address: fffffbfff809d073
PGD 6e648067 P4D 123ec8067 PUD 123ec4067 PMD 100e38067 PTE 0
Oops: Oops: 0000 [#1] PREEMPT SMP KASAN NOPTI
CPU: 5 UID: 0 PID: 755 Comm: modprobe Not tainted 6.12.0-rc3+ #17
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS
1.16.1-2.fc37 04/01/2014
RIP: 0010:__asan_load8+0x4c/0xa0
...
Call Trace:
<TASK>
blkdev_put_whole+0x41/0x70
bdev_release+0x1a3/0x250
blkdev_release+0x11/0x20
__fput+0x1d7/0x4a0
task_work_run+0xfc/0x180
syscall_exit_to_user_mode+0x1de/0x1f0
do_syscall_64+0x6b/0x170
entry_SYSCALL_64_after_hwframe+0x76/0x7e
loop_init() is calling loop_add() after __register_blkdev() succeeds and
is ignoring disk_add() failure from loop_add(), for loop_add() failure
is not fatal and successfully created disks are already visible to
bdev_open().
brd_init() is currently calling brd_alloc() before __register_blkdev()
succeeds and is releasing successfully created disks when brd_init()
returns an error. This can cause UAF for the latter two case:
case 1:
T1:
modprobe brd
brd_init
brd_alloc(0) // success
add_disk
disk_scan_partitions
bdev_file_open_by_dev // alloc file
fput // won't free until back to userspace
brd_alloc(1) // failed since mem alloc error inject
// error path for modprobe will release code segment
// back to userspace
__fput
blkdev_release
bdev_release
blkdev_put_whole
bdev->bd_disk->fops->release // fops is freed now, UAF!
case 2:
T1: T2:
modprobe brd
brd_init
brd_alloc(0) // success
open(/dev/ram0)
brd_alloc(1) // fail
// error path for modprobe
close(/dev/ram0)
...
/* UAF! */
bdev->bd_disk->fops->release
Fix this problem by following what loop_init() does. Besides,
reintroduce brd_devices_mutex to help serialize modifications to
brd_list.
Fixes: 7f9b348cb5e9 ("brd: convert to blk_alloc_disk/blk_cleanup_disk")
Reported-by: Wupeng Ma <mawupeng1@xxxxxxxxxx>
Signed-off-by: Yang Erkun <yangerkun@xxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Link: https://lore.kernel.org/r/20241030034914.907829-1-yangerkun@xxxxxxxxxxxxxxx
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/drivers/block/brd.c b/drivers/block/brd.c
index db816baca5567..e4f470cc702f9 100644
--- a/drivers/block/brd.c
+++ b/drivers/block/brd.c
@@ -362,8 +362,40 @@ __setup("ramdisk_size=", ramdisk_size);
* (should share code eventually).
*/
static LIST_HEAD(brd_devices);
+static DEFINE_MUTEX(brd_devices_mutex);
static struct dentry *brd_debugfs_dir;
+static struct brd_device *brd_find_or_alloc_device(int i)
+{
+ struct brd_device *brd;
+
+ mutex_lock(&brd_devices_mutex);
+ list_for_each_entry(brd, &brd_devices, brd_list) {
+ if (brd->brd_number == i) {
+ mutex_unlock(&brd_devices_mutex);
+ return ERR_PTR(-EEXIST);
+ }
+ }
+
+ brd = kzalloc(sizeof(*brd), GFP_KERNEL);
+ if (!brd) {
+ mutex_unlock(&brd_devices_mutex);
+ return ERR_PTR(-ENOMEM);
+ }
+ brd->brd_number = i;
+ list_add_tail(&brd->brd_list, &brd_devices);
+ mutex_unlock(&brd_devices_mutex);
+ return brd;
+}
+
+static void brd_free_device(struct brd_device *brd)
+{
+ mutex_lock(&brd_devices_mutex);
+ list_del(&brd->brd_list);
+ mutex_unlock(&brd_devices_mutex);
+ kfree(brd);
+}
+
static int brd_alloc(int i)
{
struct brd_device *brd;
@@ -371,14 +403,9 @@ static int brd_alloc(int i)
char buf[DISK_NAME_LEN];
int err = -ENOMEM;
- list_for_each_entry(brd, &brd_devices, brd_list)
- if (brd->brd_number == i)
- return -EEXIST;
- brd = kzalloc(sizeof(*brd), GFP_KERNEL);
- if (!brd)
- return -ENOMEM;
- brd->brd_number = i;
- list_add_tail(&brd->brd_list, &brd_devices);
+ brd = brd_find_or_alloc_device(i);
+ if (IS_ERR(brd))
+ return PTR_ERR(brd);
spin_lock_init(&brd->brd_lock);
INIT_RADIX_TREE(&brd->brd_pages, GFP_ATOMIC);
@@ -423,8 +450,7 @@ static int brd_alloc(int i)
out_cleanup_disk:
blk_cleanup_disk(disk);
out_free_dev:
- list_del(&brd->brd_list);
- kfree(brd);
+ brd_free_device(brd);
return err;
}
@@ -443,8 +469,7 @@ static void brd_cleanup(void)
del_gendisk(brd->brd_disk);
blk_cleanup_disk(brd->brd_disk);
brd_free_pages(brd);
- list_del(&brd->brd_list);
- kfree(brd);
+ brd_free_device(brd);
}
}
@@ -471,16 +496,6 @@ static int __init brd_init(void)
{
int err, i;
- brd_check_and_reset_par();
-
- brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL);
-
- for (i = 0; i < rd_nr; i++) {
- err = brd_alloc(i);
- if (err)
- goto out_free;
- }
-
/*
* brd module now has a feature to instantiate underlying device
* structure on-demand, provided that there is an access dev node.
@@ -496,11 +511,18 @@ static int __init brd_init(void)
* dynamically.
*/
+ brd_check_and_reset_par();
+
+ brd_debugfs_dir = debugfs_create_dir("ramdisk_pages", NULL);
+
if (__register_blkdev(RAMDISK_MAJOR, "ramdisk", brd_probe)) {
err = -EIO;
goto out_free;
}
+ for (i = 0; i < rd_nr; i++)
+ brd_alloc(i);
+
pr_info("brd: module loaded\n");
return 0;
