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
sync.c
// SPDX-License-Identifier: GPL-2.0
/*
* High-level sync()-related operations
*/
#include <linux/blkdev.h>
#include <linux/kernel.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/export.h>
#include <linux/namei.h>
#include <linux/sched.h>
#include <linux/writeback.h>
#include <linux/syscalls.h>
#include <linux/linkage.h>
#include <linux/pagemap.h>
#include <linux/quotaops.h>
#include <linux/backing-dev.h>
#include "internal.h"
#define VALID_FLAGS (SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE| \
SYNC_FILE_RANGE_WAIT_AFTER)
/*
* Write out and wait upon all dirty data associated with this
* superblock. Filesystem data as well as the underlying block
* device. Takes the superblock lock.
*/
int sync_filesystem(struct super_block *sb)
{
int ret = 0;
/*
* We need to be protected against the filesystem going from
* r/o to r/w or vice versa.
*/
WARN_ON(!rwsem_is_locked(&sb->s_umount));
/*
* No point in syncing out anything if the filesystem is read-only.
*/
if (sb_rdonly(sb))
return 0;
/*
* Do the filesystem syncing work. For simple filesystems
* writeback_inodes_sb(sb) just dirties buffers with inodes so we have
* to submit I/O for these buffers via sync_blockdev(). This also
* speeds up the wait == 1 case since in that case write_inode()
* methods call sync_dirty_buffer() and thus effectively write one block
* at a time.
*/
writeback_inodes_sb(sb, WB_REASON_SYNC);
if (sb->s_op->sync_fs) {
ret = sb->s_op->sync_fs(sb, 0);
if (ret)
return ret;
}
ret = sync_blockdev_nowait(sb->s_bdev);
if (ret)
return ret;
sync_inodes_sb(sb);
if (sb->s_op->sync_fs) {
ret = sb->s_op->sync_fs(sb, 1);
if (ret)
return ret;
}
return sync_blockdev(sb->s_bdev);
}
EXPORT_SYMBOL(sync_filesystem);
static void sync_inodes_one_sb(struct super_block *sb, void *arg)
{
if (!sb_rdonly(sb))
sync_inodes_sb(sb);
}
static void sync_fs_one_sb(struct super_block *sb, void *arg)
{
if (!sb_rdonly(sb) && !(sb->s_iflags & SB_I_SKIP_SYNC) &&
sb->s_op->sync_fs)
sb->s_op->sync_fs(sb, *(int *)arg);
}
/*
* Sync everything. We start by waking flusher threads so that most of
* writeback runs on all devices in parallel. Then we sync all inodes reliably
* which effectively also waits for all flusher threads to finish doing
* writeback. At this point all data is on disk so metadata should be stable
* and we tell filesystems to sync their metadata via ->sync_fs() calls.
* Finally, we writeout all block devices because some filesystems (e.g. ext2)
* just write metadata (such as inodes or bitmaps) to block device page cache
* and do not sync it on their own in ->sync_fs().
*/
void ksys_sync(void)
{
int nowait = 0, wait = 1;
wakeup_flusher_threads(WB_REASON_SYNC);
iterate_supers(sync_inodes_one_sb, NULL);
iterate_supers(sync_fs_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &wait);
sync_bdevs(false);
sync_bdevs(true);
if (unlikely(laptop_mode))
laptop_sync_completion();
}
SYSCALL_DEFINE0(sync)
{
ksys_sync();
return 0;
}
static void do_sync_work(struct work_struct *work)
{
int nowait = 0;
/*
* Sync twice to reduce the possibility we skipped some inodes / pages
* because they were temporarily locked
*/
iterate_supers(sync_inodes_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &nowait);
sync_bdevs(false);
iterate_supers(sync_inodes_one_sb, &nowait);
iterate_supers(sync_fs_one_sb, &nowait);
sync_bdevs(false);
printk("Emergency Sync complete\n");
kfree(work);
}
void emergency_sync(void)
{
struct work_struct *work;
work = kmalloc(sizeof(*work), GFP_ATOMIC);
if (work) {
INIT_WORK(work, do_sync_work);
schedule_work(work);
}
}
/*
* sync a single super
*/
SYSCALL_DEFINE1(syncfs, int, fd)
{
struct fd f = fdget(fd);
struct super_block *sb;
int ret, ret2;
if (!f.file)
return -EBADF;
sb = f.file->f_path.dentry->d_sb;
down_read(&sb->s_umount);
ret = sync_filesystem(sb);
up_read(&sb->s_umount);
ret2 = errseq_check_and_advance(&sb->s_wb_err, &f.file->f_sb_err);
fdput(f);
return ret ? ret : ret2;
}
/**
* vfs_fsync_range - helper to sync a range of data & metadata to disk
* @file: file to sync
* @start: offset in bytes of the beginning of data range to sync
* @end: offset in bytes of the end of data range (inclusive)
* @datasync: perform only datasync
*
* Write back data in range @start..@end and metadata for @file to disk. If
* @datasync is set only metadata needed to access modified file data is
* written.
*/
int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync)
{
struct inode *inode = file->f_mapping->host;
if (!file->f_op->fsync)
return -EINVAL;
if (!datasync && (inode->i_state & I_DIRTY_TIME))
mark_inode_dirty_sync(inode);
return file->f_op->fsync(file, start, end, datasync);
}
EXPORT_SYMBOL(vfs_fsync_range);
/**
* vfs_fsync - perform a fsync or fdatasync on a file
* @file: file to sync
* @datasync: only perform a fdatasync operation
*
* Write back data and metadata for @file to disk. If @datasync is
* set only metadata needed to access modified file data is written.
*/
int vfs_fsync(struct file *file, int datasync)
{
return vfs_fsync_range(file, 0, LLONG_MAX, datasync);
}
EXPORT_SYMBOL(vfs_fsync);
static int do_fsync(unsigned int fd, int datasync)
{
struct fd f = fdget(fd);
int ret = -EBADF;
if (f.file) {
ret = vfs_fsync(f.file, datasync);
fdput(f);
}
return ret;
}
SYSCALL_DEFINE1(fsync, unsigned int, fd)
{
return do_fsync(fd, 0);
}
SYSCALL_DEFINE1(fdatasync, unsigned int, fd)
{
return do_fsync(fd, 1);
}
int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
unsigned int flags)
{
int ret;
struct address_space *mapping;
loff_t endbyte; /* inclusive */
umode_t i_mode;
ret = -EINVAL;
if (flags & ~VALID_FLAGS)
goto out;
endbyte = offset + nbytes;
if ((s64)offset < 0)
goto out;
if ((s64)endbyte < 0)
goto out;
if (endbyte < offset)
goto out;
if (sizeof(pgoff_t) == 4) {
if (offset >= (0x100000000ULL << PAGE_SHIFT)) {
/*
* The range starts outside a 32 bit machine's
* pagecache addressing capabilities. Let it "succeed"
*/
ret = 0;
goto out;
}
if (endbyte >= (0x100000000ULL << PAGE_SHIFT)) {
/*
* Out to EOF
*/
nbytes = 0;
}
}
if (nbytes == 0)
endbyte = LLONG_MAX;
else
endbyte--; /* inclusive */
i_mode = file_inode(file)->i_mode;
ret = -ESPIPE;
if (!S_ISREG(i_mode) && !S_ISBLK(i_mode) && !S_ISDIR(i_mode) &&
!S_ISLNK(i_mode))
goto out;
mapping = file->f_mapping;
ret = 0;
if (flags & SYNC_FILE_RANGE_WAIT_BEFORE) {
ret = file_fdatawait_range(file, offset, endbyte);
if (ret < 0)
goto out;
}
if (flags & SYNC_FILE_RANGE_WRITE) {
int sync_mode = WB_SYNC_NONE;
if ((flags & SYNC_FILE_RANGE_WRITE_AND_WAIT) ==
SYNC_FILE_RANGE_WRITE_AND_WAIT)
sync_mode = WB_SYNC_ALL;
ret = __filemap_fdatawrite_range(mapping, offset, endbyte,
sync_mode);
if (ret < 0)
goto out;
}
if (flags & SYNC_FILE_RANGE_WAIT_AFTER)
ret = file_fdatawait_range(file, offset, endbyte);
out:
return ret;
}
/*
* ksys_sync_file_range() permits finely controlled syncing over a segment of
* a file in the range offset .. (offset+nbytes-1) inclusive. If nbytes is
* zero then ksys_sync_file_range() will operate from offset out to EOF.
*
* The flag bits are:
*
* SYNC_FILE_RANGE_WAIT_BEFORE: wait upon writeout of all pages in the range
* before performing the write.
*
* SYNC_FILE_RANGE_WRITE: initiate writeout of all those dirty pages in the
* range which are not presently under writeback. Note that this may block for
* significant periods due to exhaustion of disk request structures.
*
* SYNC_FILE_RANGE_WAIT_AFTER: wait upon writeout of all pages in the range
* after performing the write.
*
* Useful combinations of the flag bits are:
*
* SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE: ensures that all pages
* in the range which were dirty on entry to ksys_sync_file_range() are placed
* under writeout. This is a start-write-for-data-integrity operation.
*
* SYNC_FILE_RANGE_WRITE: start writeout of all dirty pages in the range which
* are not presently under writeout. This is an asynchronous flush-to-disk
* operation. Not suitable for data integrity operations.
*
* SYNC_FILE_RANGE_WAIT_BEFORE (or SYNC_FILE_RANGE_WAIT_AFTER): wait for
* completion of writeout of all pages in the range. This will be used after an
* earlier SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE operation to wait
* for that operation to complete and to return the result.
*
* SYNC_FILE_RANGE_WAIT_BEFORE|SYNC_FILE_RANGE_WRITE|SYNC_FILE_RANGE_WAIT_AFTER
* (a.k.a. SYNC_FILE_RANGE_WRITE_AND_WAIT):
* a traditional sync() operation. This is a write-for-data-integrity operation
* which will ensure that all pages in the range which were dirty on entry to
* ksys_sync_file_range() are written to disk. It should be noted that disk
* caches are not flushed by this call, so there are no guarantees here that the
* data will be available on disk after a crash.
*
*
* SYNC_FILE_RANGE_WAIT_BEFORE and SYNC_FILE_RANGE_WAIT_AFTER will detect any
* I/O errors or ENOSPC conditions and will return those to the caller, after
* clearing the EIO and ENOSPC flags in the address_space.
*
* It should be noted that none of these operations write out the file's
* metadata. So unless the application is strictly performing overwrites of
* already-instantiated disk blocks, there are no guarantees here that the data
* will be available after a crash.
*/
int ksys_sync_file_range(int fd, loff_t offset, loff_t nbytes,
unsigned int flags)
{
int ret;
struct fd f;
ret = -EBADF;
f = fdget(fd);
if (f.file)
ret = sync_file_range(f.file, offset, nbytes, flags);
fdput(f);
return ret;
}
SYSCALL_DEFINE4(sync_file_range, int, fd, loff_t, offset, loff_t, nbytes,
unsigned int, flags)
{
return ksys_sync_file_range(fd, offset, nbytes, flags);
}
#if defined(CONFIG_COMPAT) && defined(__ARCH_WANT_COMPAT_SYNC_FILE_RANGE)
COMPAT_SYSCALL_DEFINE6(sync_file_range, int, fd, compat_arg_u64_dual(offset),
compat_arg_u64_dual(nbytes), unsigned int, flags)
{
return ksys_sync_file_range(fd, compat_arg_u64_glue(offset),
compat_arg_u64_glue(nbytes), flags);
}
#endif
/* It would be nice if people remember that not all the world's an i386
when they introduce new system calls */
SYSCALL_DEFINE4(sync_file_range2, int, fd, unsigned int, flags,
loff_t, offset, loff_t, nbytes)
{
return ksys_sync_file_range(fd, offset, nbytes, flags);
}
![swh spinner](/static/img/swh-spinner.gif)
Computing file changes ...