Re: [PATCH v2] mm: shmem: fix the shmem large folio allocation for the i915 driver

[Patryk Kowalczyk <patryk@kowalczyk.ws>]

That patch solved problem with the i915 performance regression, so the
previous patch for the i915 driver shoudn't be merged.
best regards,
Patryk Kowalczyk

czw., 31 lip 2025 o 03:54 Baolin Wang <baolin.wang@linux.alibaba.com>
napisał(a):
>
> After commit acd7ccb284b8 ("mm: shmem: add large folio support for tmpfs"),
> we extend the 'huge=' option to allow any sized large folios for tmpfs,
> which means tmpfs will allow getting a highest order hint based on the size
> of write() and fallocate() paths, and then will try each allowable large order.
>
> However, when the i915 driver allocates shmem memory, it doesn't provide hint
> information about the size of the large folio to be allocated, resulting in
> the inability to allocate PMD-sized shmem, which in turn affects GPU performance.
>
> Patryk added:
>
> : In my tests, the performance drop ranges from a few percent up to 13%
> : in Unigine Superposition under heavy memory usage on the CPU Core Ultra
> : 155H with the Xe 128 EU GPU.  Other users have reported performance
> : impact up to 30% on certain workloads.  Please find more in the
> : regressions reports:
> : https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/14645
> : https://gitlab.freedesktop.org/drm/i915/kernel/-/issues/13845
> :
> : I believe the change should be backported to all active kernel branches
> : after version 6.12.
>
> To fix this issue, we can use the inode's size as a write size hint in
> shmem_read_folio_gfp() to help allocate PMD-sized large folios.
>
> Fixes: acd7ccb284b8 ("mm: shmem: add large folio support for tmpfs")
> Reported-by: Patryk Kowalczyk <patryk@kowalczyk.ws>
> Reported-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
> Tested-by: Patryk Kowalczyk <patryk@kowalczyk.ws>
> Suggested-by: Hugh Dickins <hughd@google.com>
> Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
> ---
> Changes from v1:
>  - Use inode size as the write size hint, per Hugh.
> ---
>  mm/shmem.c | 4 ++--
>  1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 41eb4aa60be5..e1e5d5f7f58d 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -5989,8 +5989,8 @@ struct folio *shmem_read_folio_gfp(struct address_space *mapping,
>         struct folio *folio;
>         int error;
>
> -       error = shmem_get_folio_gfp(inode, index, 0, &folio, SGP_CACHE,
> -                                   gfp, NULL, NULL);
> +       error = shmem_get_folio_gfp(inode, index, i_size_read(inode),
> +                                   &folio, SGP_CACHE, gfp, NULL, NULL);
>         if (error)
>                 return ERR_PTR(error);
>
> --
> 2.43.5
>