Axel,

On Mon, May 03, 2021 at 11:07:33AM -0700, Axel Rasmussen wrote:

In a previous commit, we added the mfill_atomic_install_pte() helper.
This helper does the job of setting up PTEs for an existing page, to map
it into a given VMA. It deals with both the anon and shmem cases, as
well as the shared and private cases.

In other words, shmem_mfill_atomic_pte() duplicates a case it already
handles. So, expose it, and let shmem_mfill_atomic_pte() use it
directly, to reduce code duplication.

This requires that we refactor shmem_mfill_atomic_pte() a bit:

Instead of doing accounting (shmem_recalc_inode() et al) part-way
through the PTE setup, do it afterward. This frees up
mfill_atomic_install_pte() from having to care about this accounting,
and means we don't need to e.g. shmem_uncharge() in the error path.

A side effect is this switches shmem_mfill_atomic_pte() to use
lru_cache_add_inactive_or_unevictable() instead of just lru_cache_add().
This wrapper does some extra accounting in an exceptional case, if
appropriate, so it's actually the more correct thing to use.

Signed-off-by: Axel Rasmussen <axelrasmussen@google.com>

(The moving of "ret = -ENOMEM" seems unnecessary, but not a big deal I think)

Reviewed-by: Peter Xu <peterx@redhat.com>

Thanks,

-- 
Peter Xu