Re: [PATCH] mm: add mmap_prepare() compatibility layer for nested file systems

[Lorenzo Stoakes <lorenzo.stoakes@oracle.com>]

Andrew - to be clear, this should be a hotfix against 6.16-rc1 :>) Thanks!

On Mon, Jun 09, 2025 at 12:18:40PM +0200, Vlastimil Babka wrote:
> On 6/9/25 11:24 AM, Lorenzo Stoakes wrote:
> > Nested file systems, that is those which invoke call_mmap() within their
> > own f_op->mmap() handlers, may encounter underlying file systems which
> > provide the f_op->mmap_prepare() hook introduced by commit
> > c84bf6dd2b83 ("mm: introduce new .mmap_prepare() file callback").
> >
> > We have a chicken-and-egg scenario here - until all file systems are
> > converted to using .mmap_prepare(), we cannot convert these nested
> > handlers, as we can't call f_op->mmap from an .mmap_prepare() hook.
> >
> > So we have to do it the other way round - invoke the .mmap_prepare() hook
> > from an .mmap() one.
> >
> > in order to do so, we need to convert VMA state into a struct vm_area_desc
> > descriptor, invoking the underlying file system's f_op->mmap_prepare()
> > callback passing a pointer to this, and then setting VMA state accordingly
> > and safely.
> >
> > This patch achieves this via the compat_vma_mmap_prepare() function, which
> > we invoke from call_mmap() if f_op->mmap_prepare() is specified in the
> > passed in file pointer.
> >
> > We place the fundamental logic into mm/vma.c where VMA manipulation
> > belongs. We also update the VMA userland tests to accommodate the changes.
> >
> > The compat_vma_mmap_prepare() function and its associated machinery is
> > temporary, and will be removed once the conversion of file systems is
> > complete.
> >
> > Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
> > Reported-by: Jann Horn <jannh@google.com>
> > Closes: https://lore.kernel.org/linux-mm/CAG48ez04yOEVx1ekzOChARDDBZzAKwet8PEoPM4Ln3_rk91AzQ@mail.gmail.com/
> > Fixes: c84bf6dd2b83 ("mm: introduce new .mmap_prepare() file callback").
>
> So this is a hotfix for 6.16-rc1 but doesn't need cc: stable.
> Also probably nothing wraps yet the filesystems with .mmap_prepare? But
> good to have this handled within 6.16.

Only secretmem uses this so unaffected BUT I want to make changes to filesystems
in 6.17 which is blocked by this problem (I actually have a bunch of changes
queued up ready), so it's really important to get this hotfixed.

Also, given the change in use of callback is going to touch a ton of filesystems
this is important for backporting purposes, in case anything needs
backporting there.

So from that point of view it's important to have it in 6.16 also.

>
> Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
>

Thanks!