When the last process closes /dev/mdX sync_blockdev will be called so
that all buffers get flushed.
So if it is then opened for the STOP_ARRAY ioctl to be sent there will
be nothing to flush.
However if we open /dev/mdX in order to send the STOP_ARRAY ioctl just
moments before some other process which was writing closes their file
descriptor, then there won't be a 'last close' and the buffers might
not get flushed.
So do_md_stop() calls sync_blockdev(). However at this point it is
holding ->reconfig_mutex. So if the array is currently 'clean' then
the writes from sync_blockdev() will not complete until the array
can be marked dirty and that won't happen until some other thread
can get ->reconfig_mutex. So we deadlock.
We need to move the sync_blockdev() call to before we take
->reconfig_mutex.
However then some other thread could open /dev/mdX and write to it
after we call sync_blockdev() and before we actually stop the array.
This can leave dirty data in the page cache which is awkward.
So introduce new flag MD_STILL_CLOSED. Set it before calling
sync_blockdev(), clear it if anyone does open the file, and abort the
STOP_ARRAY attempt if it gets set before we lock against further
opens.
It is still possible to get problems if you open /dev/mdX, write to
it, then issue the STOP_ARRAY ioctl. Just don't do that.
Signed-off-by: NeilBrown <neilb@suse.de>
err = -EBUSY;
goto out;
}
err = -EBUSY;
goto out;
}
- if (bdev)
- sync_blockdev(bdev);
+ if (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags)) {
+ /* Someone opened the device since we flushed it
+ * so page cache could be dirty and it is too late
+ * to flush. So abort
+ */
+ mutex_unlock(&mddev->open_mutex);
+ return -EBUSY;
+ }
if (mddev->pers) {
__md_stop_writes(mddev);
if (mddev->pers) {
__md_stop_writes(mddev);
mutex_unlock(&mddev->open_mutex);
return -EBUSY;
}
mutex_unlock(&mddev->open_mutex);
return -EBUSY;
}
- if (bdev)
- /* It is possible IO was issued on some other
- * open file which was closed before we took ->open_mutex.
- * As that was not the last close __blkdev_put will not
- * have called sync_blockdev, so we must.
+ if (bdev && !test_bit(MD_STILL_CLOSED, &mddev->flags)) {
+ /* Someone opened the device since we flushed it
+ * so page cache could be dirty and it is too late
+ * to flush. So abort
+ mutex_unlock(&mddev->open_mutex);
+ return -EBUSY;
+ }
if (mddev->pers) {
if (mddev->ro)
set_disk_ro(disk, 0);
if (mddev->pers) {
if (mddev->ro)
set_disk_ro(disk, 0);
!test_bit(MD_RECOVERY_NEEDED,
&mddev->flags),
msecs_to_jiffies(5000));
!test_bit(MD_RECOVERY_NEEDED,
&mddev->flags),
msecs_to_jiffies(5000));
+ if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) {
+ /* Need to flush page cache, and ensure no-one else opens
+ * and writes
+ */
+ mutex_lock(&mddev->open_mutex);
+ if (atomic_read(&mddev->openers) > 1) {
+ mutex_unlock(&mddev->open_mutex);
+ err = -EBUSY;
+ goto abort;
+ }
+ set_bit(MD_STILL_CLOSED, &mddev->flags);
+ mutex_unlock(&mddev->open_mutex);
+ sync_blockdev(bdev);
+ }
err = mddev_lock(mddev);
if (err) {
printk(KERN_INFO
err = mddev_lock(mddev);
if (err) {
printk(KERN_INFO
err = 0;
atomic_inc(&mddev->openers);
err = 0;
atomic_inc(&mddev->openers);
+ clear_bit(MD_STILL_CLOSED, &mddev->flags);
mutex_unlock(&mddev->open_mutex);
check_disk_change(bdev);
mutex_unlock(&mddev->open_mutex);
check_disk_change(bdev);
#define MD_CHANGE_PENDING 2 /* switch from 'clean' to 'active' in progress */
#define MD_UPDATE_SB_FLAGS (1 | 2 | 4) /* If these are set, md_update_sb needed */
#define MD_ARRAY_FIRST_USE 3 /* First use of array, needs initialization */
#define MD_CHANGE_PENDING 2 /* switch from 'clean' to 'active' in progress */
#define MD_UPDATE_SB_FLAGS (1 | 2 | 4) /* If these are set, md_update_sb needed */
#define MD_ARRAY_FIRST_USE 3 /* First use of array, needs initialization */
+#define MD_STILL_CLOSED 4 /* If set, then array has not been opened since
+ * md_ioctl checked on it.
+ */
int suspended;
atomic_t active_io;
int suspended;
atomic_t active_io;