To restore fsnotify's watches on files we need to find paths for each
of them using handle we have in /proc/<pid>/fdinfo/<fsnotifyfd>.
These handle is valid to open the file with open_by_handle_at if
you have mount fd where the file lays. So we try open_by_handle_at
for all possible mount fds we have.

But we can not do so for 'file' bind-mounts, as the way we open
mount fd opens file instead and can hang on fifos or fail on sockets.
(see check_open_handle->open_handle->open_mount code path, imagine
lookup_mnt_sdev() found 'file' bind-mount, open_mount() failed(hanged)
in __open_mountpoint() and if irmap_lookup() also was not successful the
whole dump fails too)

So if we have file bindmount of fifo file, and we restore some
inotify on other file on other mount with same s_dev, we hang forever
on open.

So just skip non-directory mounts from inotify search we will find
path for them on other mount(e.g. non-bindmount) with same s_dev.

v2: remove isdir hashing, improve commit message
v3: make lookup_mnt_sdev handle only nondir mounts, add comment,
move more expensive notdir_mountpoint check after s_dev
v4: inverse notdir_mountpoint to be mnt_is_dir, now on error
in mnt_is_dir mount is also skipped
Signed-off-by: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Signed-off-by: Andrei Vagin <avagin@virtuozzo.com>