Re: [RFC 0/4] fs: provide per-filesystem options to disable fscrypt

[Niels de Vos]

On Tue, Nov 15, 2022 at 06:10:59PM -0800, Eric Biggers wrote:
> On Thu, Nov 10, 2022 at 03:12:21PM +0100, Niels de Vos wrote:
> > While more filesystems are getting support for fscrypt, it is useful to
> > be able to disable fscrypt for a selection of filesystems, while
> > enabling it for others.
> > 
> > The new USE_FS_ENCRYPTION define gets picked up in
> > include/linux/fscrypt.h. This allows filesystems to choose to use the
> > empty function definitions, or the functional ones when fscrypt is to be
> > used with the filesystem.
> > 
> > Using USE_FS_ENCRYPTION is a relatively clean approach, and requires
> > minimal changes to the filesystems supporting fscrypt. This RFC is
> > mostly for checking the acceptance of this solution, or if an other
> > direction is preferred.
> > 
> > ---
> > 
> > Niels de Vos (4):
> >   fscrypt: introduce USE_FS_ENCRYPTION
> >   fs: make fscrypt support an ext4 config option
> >   fs: make fscrypt support a f2fs config option
> >   fs: make fscrypt support a UBIFS config option
> 
> So as others have pointed out, it doesn't seem worth the complexity to do this.
> 
> For a bit of historical context, before Linux v5.1, we did have per-filesystem
> options for this: CONFIG_EXT4_ENCRYPTION, CONFIG_F2FS_FS_ENCRYPTION, and
> CONFIG_UBIFS_FS_ENCRYPTION.  If you enabled one of these, it selected
> CONFIG_FS_ENCRYPTION to get the code in fs/crypto/.  CONFIG_FS_ENCRYPTION was a
> tristate, so the code in fs/crypto/ could be built as a loadable module if it
> was only needed by filesystems that were loadable modules themselves.
> 
> Having fs/crypto/ possibly be a loadable module was problematic, though, because
> it made it impossible to call into fs/crypto/ from built-in code such as
> fs/buffer.c, fs/ioctl.c, fs/libfs.c, fs/super.c, fs/iomap/direct-io.c, etc.  So
> that's why we made CONFIG_FS_ENCRYPTION into a bool.  At the same time, we
> decided to simplify the kconfig options by removing the per-filesystem options
> so that it worked like CONFIG_QUOTA, CONFIG_FS_DAX, CONFIG_FS_POSIX_ACL, etc.
> 
> I suppose we *could* have *just* changed CONFIG_FS_ENCRYPTION to a bool to solve
> the first problem, and kept the per-filesystem options.  I think that wouldn't
> have made a lot of sense, though, for the reasons that Ted has already covered.

Yes, it seems that there is a move to reduce the Kconfig options and
(re)adding per-filesystem encryption support would be counterproductive.

> A further point, beyond what Ted has already covered, is that
> non-filesystem-specific code can't honor filesystem-specific options.  So e.g.
> if you had a filesystem with encryption disabled by kconfig, that then called
> into fs/iomap/direct-io.c to process an I/O request, it could potentially still
> call into fs/crypto/ to enable encryption on that I/O request, since
> fs/iomap/direct-io.c would think that encryption support is enabled.
> 
> Granted, that *should* never actually happen, because this would only make a
> difference on encrypted files, and the filesystem shouldn't have allowed an
> encrypted file to be opened if it doesn't have encryption support enabled.  But
> it does seem a bit odd, given that it would go against the goal of compiling out
> all encryption code for a filesystem.

Ah, yes, indeed! The boundaries between the options would be less clear,
and potential changes to shared functions under fs/ could have incorrect
assumptions about CONFIG_FS_ENCRYPTION. Even if this is not the case
now, optimizations/enhancements in the future might be more complicated
because of this.

Thanks for the additional details! Have a good weekend,
Niels