Revision 7561cea5dbb97fecb952548a0fb74fb105bf4664 authored by Darrick J. Wong on 01 July 2022, 16:08:33 UTC, committed by Darrick J. Wong on 01 July 2022, 16:09:52 UTC
KASAN reported the following use after free bug when running
generic/475:

 XFS (dm-0): Mounting V5 Filesystem
 XFS (dm-0): Starting recovery (logdev: internal)
 XFS (dm-0): Ending recovery (logdev: internal)
 Buffer I/O error on dev dm-0, logical block 20639616, async page read
 Buffer I/O error on dev dm-0, logical block 20639617, async page read
 XFS (dm-0): log I/O error -5
 XFS (dm-0): Filesystem has been shut down due to log error (0x2).
 XFS (dm-0): Unmounting Filesystem
 XFS (dm-0): Please unmount the filesystem and rectify the problem(s).
 ==================================================================
 BUG: KASAN: use-after-free in do_raw_spin_lock+0x246/0x270
 Read of size 4 at addr ffff888109dd84c4 by task 3:1H/136

 CPU: 3 PID: 136 Comm: 3:1H Not tainted 5.19.0-rc4-xfsx #rc4 8e53ab5ad0fddeb31cee5e7063ff9c361915a9c4
 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014
 Workqueue: xfs-log/dm-0 xlog_ioend_work [xfs]
 Call Trace:
  <TASK>
  dump_stack_lvl+0x34/0x44
  print_report.cold+0x2b8/0x661
  ? do_raw_spin_lock+0x246/0x270
  kasan_report+0xab/0x120
  ? do_raw_spin_lock+0x246/0x270
  do_raw_spin_lock+0x246/0x270
  ? rwlock_bug.part.0+0x90/0x90
  xlog_force_shutdown+0xf6/0x370 [xfs 4ad76ae0d6add7e8183a553e624c31e9ed567318]
  xlog_ioend_work+0x100/0x190 [xfs 4ad76ae0d6add7e8183a553e624c31e9ed567318]
  process_one_work+0x672/0x1040
  worker_thread+0x59b/0xec0
  ? __kthread_parkme+0xc6/0x1f0
  ? process_one_work+0x1040/0x1040
  ? process_one_work+0x1040/0x1040
  kthread+0x29e/0x340
  ? kthread_complete_and_exit+0x20/0x20
  ret_from_fork+0x1f/0x30
  </TASK>

 Allocated by task 154099:
  kasan_save_stack+0x1e/0x40
  __kasan_kmalloc+0x81/0xa0
  kmem_alloc+0x8d/0x2e0 [xfs]
  xlog_cil_init+0x1f/0x540 [xfs]
  xlog_alloc_log+0xd1e/0x1260 [xfs]
  xfs_log_mount+0xba/0x640 [xfs]
  xfs_mountfs+0xf2b/0x1d00 [xfs]
  xfs_fs_fill_super+0x10af/0x1910 [xfs]
  get_tree_bdev+0x383/0x670
  vfs_get_tree+0x7d/0x240
  path_mount+0xdb7/0x1890
  __x64_sys_mount+0x1fa/0x270
  do_syscall_64+0x2b/0x80
  entry_SYSCALL_64_after_hwframe+0x46/0xb0

 Freed by task 154151:
  kasan_save_stack+0x1e/0x40
  kasan_set_track+0x21/0x30
  kasan_set_free_info+0x20/0x30
  ____kasan_slab_free+0x110/0x190
  slab_free_freelist_hook+0xab/0x180
  kfree+0xbc/0x310
  xlog_dealloc_log+0x1b/0x2b0 [xfs]
  xfs_unmountfs+0x119/0x200 [xfs]
  xfs_fs_put_super+0x6e/0x2e0 [xfs]
  generic_shutdown_super+0x12b/0x3a0
  kill_block_super+0x95/0xd0
  deactivate_locked_super+0x80/0x130
  cleanup_mnt+0x329/0x4d0
  task_work_run+0xc5/0x160
  exit_to_user_mode_prepare+0xd4/0xe0
  syscall_exit_to_user_mode+0x1d/0x40
  entry_SYSCALL_64_after_hwframe+0x46/0xb0

This appears to be a race between the unmount process, which frees the
CIL and waits for in-flight iclog IO; and the iclog IO completion.  When
generic/475 runs, it starts fsstress in the background, waits a few
seconds, and substitutes a dm-error device to simulate a disk falling
out of a machine.  If the fsstress encounters EIO on a pure data write,
it will exit but the filesystem will still be online.

The next thing the test does is unmount the filesystem, which tries to
clean the log, free the CIL, and wait for iclog IO completion.  If an
iclog was being written when the dm-error switch occurred, it can race
with log unmounting as follows:

Thread 1				Thread 2

					xfs_log_unmount
					xfs_log_clean
					xfs_log_quiesce
xlog_ioend_work
<observe error>
xlog_force_shutdown
test_and_set_bit(XLOG_IOERROR)
					xfs_log_force
					<log is shut down, nop>
					xfs_log_umount_write
					<log is shut down, nop>
					xlog_dealloc_log
					xlog_cil_destroy
					<wait for iclogs>
spin_lock(&log->l_cilp->xc_push_lock)
<KABOOM>

Therefore, free the CIL after waiting for the iclogs to complete.  I
/think/ this race has existed for quite a few years now, though I don't
remember the ~2014 era logging code well enough to know if it was a real
threat then or if the actual race was exposed only more recently.

Fixes: ac983517ec59 ("xfs: don't sleep in xlog_cil_force_lsn on shutdown")
Signed-off-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Dave Chinner <dchinner@redhat.com>
1 parent 8944c6f
Raw File
fhandle.c
// SPDX-License-Identifier: GPL-2.0
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/exportfs.h>
#include <linux/fs_struct.h>
#include <linux/fsnotify.h>
#include <linux/personality.h>
#include <linux/uaccess.h>
#include <linux/compat.h>
#include "internal.h"
#include "mount.h"

static long do_sys_name_to_handle(struct path *path,
				  struct file_handle __user *ufh,
				  int __user *mnt_id)
{
	long retval;
	struct file_handle f_handle;
	int handle_dwords, handle_bytes;
	struct file_handle *handle = NULL;

	/*
	 * We need to make sure whether the file system
	 * support decoding of the file handle
	 */
	if (!path->dentry->d_sb->s_export_op ||
	    !path->dentry->d_sb->s_export_op->fh_to_dentry)
		return -EOPNOTSUPP;

	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle)))
		return -EFAULT;

	if (f_handle.handle_bytes > MAX_HANDLE_SZ)
		return -EINVAL;

	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
			 GFP_KERNEL);
	if (!handle)
		return -ENOMEM;

	/* convert handle size to multiple of sizeof(u32) */
	handle_dwords = f_handle.handle_bytes >> 2;

	/* we ask for a non connected handle */
	retval = exportfs_encode_fh(path->dentry,
				    (struct fid *)handle->f_handle,
				    &handle_dwords,  0);
	handle->handle_type = retval;
	/* convert handle size to bytes */
	handle_bytes = handle_dwords * sizeof(u32);
	handle->handle_bytes = handle_bytes;
	if ((handle->handle_bytes > f_handle.handle_bytes) ||
	    (retval == FILEID_INVALID) || (retval == -ENOSPC)) {
		/* As per old exportfs_encode_fh documentation
		 * we could return ENOSPC to indicate overflow
		 * But file system returned 255 always. So handle
		 * both the values
		 */
		/*
		 * set the handle size to zero so we copy only
		 * non variable part of the file_handle
		 */
		handle_bytes = 0;
		retval = -EOVERFLOW;
	} else
		retval = 0;
	/* copy the mount id */
	if (put_user(real_mount(path->mnt)->mnt_id, mnt_id) ||
	    copy_to_user(ufh, handle,
			 sizeof(struct file_handle) + handle_bytes))
		retval = -EFAULT;
	kfree(handle);
	return retval;
}

/**
 * sys_name_to_handle_at: convert name to handle
 * @dfd: directory relative to which name is interpreted if not absolute
 * @name: name that should be converted to handle.
 * @handle: resulting file handle
 * @mnt_id: mount id of the file system containing the file
 * @flag: flag value to indicate whether to follow symlink or not
 *
 * @handle->handle_size indicate the space available to store the
 * variable part of the file handle in bytes. If there is not
 * enough space, the field is updated to return the minimum
 * value required.
 */
SYSCALL_DEFINE5(name_to_handle_at, int, dfd, const char __user *, name,
		struct file_handle __user *, handle, int __user *, mnt_id,
		int, flag)
{
	struct path path;
	int lookup_flags;
	int err;

	if ((flag & ~(AT_SYMLINK_FOLLOW | AT_EMPTY_PATH)) != 0)
		return -EINVAL;

	lookup_flags = (flag & AT_SYMLINK_FOLLOW) ? LOOKUP_FOLLOW : 0;
	if (flag & AT_EMPTY_PATH)
		lookup_flags |= LOOKUP_EMPTY;
	err = user_path_at(dfd, name, lookup_flags, &path);
	if (!err) {
		err = do_sys_name_to_handle(&path, handle, mnt_id);
		path_put(&path);
	}
	return err;
}

static struct vfsmount *get_vfsmount_from_fd(int fd)
{
	struct vfsmount *mnt;

	if (fd == AT_FDCWD) {
		struct fs_struct *fs = current->fs;
		spin_lock(&fs->lock);
		mnt = mntget(fs->pwd.mnt);
		spin_unlock(&fs->lock);
	} else {
		struct fd f = fdget(fd);
		if (!f.file)
			return ERR_PTR(-EBADF);
		mnt = mntget(f.file->f_path.mnt);
		fdput(f);
	}
	return mnt;
}

static int vfs_dentry_acceptable(void *context, struct dentry *dentry)
{
	return 1;
}

static int do_handle_to_path(int mountdirfd, struct file_handle *handle,
			     struct path *path)
{
	int retval = 0;
	int handle_dwords;

	path->mnt = get_vfsmount_from_fd(mountdirfd);
	if (IS_ERR(path->mnt)) {
		retval = PTR_ERR(path->mnt);
		goto out_err;
	}
	/* change the handle size to multiple of sizeof(u32) */
	handle_dwords = handle->handle_bytes >> 2;
	path->dentry = exportfs_decode_fh(path->mnt,
					  (struct fid *)handle->f_handle,
					  handle_dwords, handle->handle_type,
					  vfs_dentry_acceptable, NULL);
	if (IS_ERR(path->dentry)) {
		retval = PTR_ERR(path->dentry);
		goto out_mnt;
	}
	return 0;
out_mnt:
	mntput(path->mnt);
out_err:
	return retval;
}

static int handle_to_path(int mountdirfd, struct file_handle __user *ufh,
		   struct path *path)
{
	int retval = 0;
	struct file_handle f_handle;
	struct file_handle *handle = NULL;

	/*
	 * With handle we don't look at the execute bit on the
	 * directory. Ideally we would like CAP_DAC_SEARCH.
	 * But we don't have that
	 */
	if (!capable(CAP_DAC_READ_SEARCH)) {
		retval = -EPERM;
		goto out_err;
	}
	if (copy_from_user(&f_handle, ufh, sizeof(struct file_handle))) {
		retval = -EFAULT;
		goto out_err;
	}
	if ((f_handle.handle_bytes > MAX_HANDLE_SZ) ||
	    (f_handle.handle_bytes == 0)) {
		retval = -EINVAL;
		goto out_err;
	}
	handle = kmalloc(sizeof(struct file_handle) + f_handle.handle_bytes,
			 GFP_KERNEL);
	if (!handle) {
		retval = -ENOMEM;
		goto out_err;
	}
	/* copy the full handle */
	*handle = f_handle;
	if (copy_from_user(&handle->f_handle,
			   &ufh->f_handle,
			   f_handle.handle_bytes)) {
		retval = -EFAULT;
		goto out_handle;
	}

	retval = do_handle_to_path(mountdirfd, handle, path);

out_handle:
	kfree(handle);
out_err:
	return retval;
}

static long do_handle_open(int mountdirfd, struct file_handle __user *ufh,
			   int open_flag)
{
	long retval = 0;
	struct path path;
	struct file *file;
	int fd;

	retval = handle_to_path(mountdirfd, ufh, &path);
	if (retval)
		return retval;

	fd = get_unused_fd_flags(open_flag);
	if (fd < 0) {
		path_put(&path);
		return fd;
	}
	file = file_open_root(&path, "", open_flag, 0);
	if (IS_ERR(file)) {
		put_unused_fd(fd);
		retval =  PTR_ERR(file);
	} else {
		retval = fd;
		fsnotify_open(file);
		fd_install(fd, file);
	}
	path_put(&path);
	return retval;
}

/**
 * sys_open_by_handle_at: Open the file handle
 * @mountdirfd: directory file descriptor
 * @handle: file handle to be opened
 * @flags: open flags.
 *
 * @mountdirfd indicate the directory file descriptor
 * of the mount point. file handle is decoded relative
 * to the vfsmount pointed by the @mountdirfd. @flags
 * value is same as the open(2) flags.
 */
SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
		struct file_handle __user *, handle,
		int, flags)
{
	long ret;

	if (force_o_largefile())
		flags |= O_LARGEFILE;

	ret = do_handle_open(mountdirfd, handle, flags);
	return ret;
}

#ifdef CONFIG_COMPAT
/*
 * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
 * doesn't set the O_LARGEFILE flag.
 */
COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
			     struct file_handle __user *, handle, int, flags)
{
	return do_handle_open(mountdirfd, handle, flags);
}
#endif
back to top