Re: [PATCH v10 25/37] mm: use __GFP_ZERO in alloc_anon_folio

[Lorenzo Stoakes <ljs@kernel.org>]

On Mon, Jun 08, 2026 at 04:39:02AM -0400, Michael S. Tsirkin wrote:
> Convert alloc_anon_folio() to pass __GFP_ZERO instead of zeroing
> at the callsite. post_alloc_hook uses the fault address passed
> through vma_alloc_folio for cache-friendly zeroing.
>
> Note: before this series, replacing clear_user_highpage() with
> __GFP_ZERO was unsafe on cache-aliasing architectures because
> __GFP_ZERO uses clear_page() without a dcache flush. With this
> series, it is safe if the caller passes a valid user address
> (not USER_ADDR_NONE) to vma_alloc_folio() etc., which delivers
> it to post_alloc_hook() for the dcache flush via
> folio_zero_user(). It is only unsafe if USER_ADDR_NONE is passed.
>
> Note: with __GFP_ZERO, the folio is zeroed before
> mem_cgroup_charge().  If the charge fails, the zeroing work is
> wasted.  Previously zeroing was done after a successful charge.
> This is inherent to moving zeroing into the allocator.
> Charge failures are rare (only at cgroup limits).
>
> Use folio_put_zeroed() on charge failure so the zeroed hint
> propagates to the buddy allocator, avoiding redundant re-zeroing
> on the next allocation attempt.

Is this even worth the effort? This is surely not a hotpath...

>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
> Reviewed-by: Gregory Price <gourry@gourry.net>
> Assisted-by: Claude:claude-opus-4-6
> ---
>  mm/memory.c | 13 ++-----------
>  1 file changed, 2 insertions(+), 11 deletions(-)
>
> diff --git a/mm/memory.c b/mm/memory.c
> index 6c14b90f558e..6d6a3e1a02c1 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -5265,25 +5265,16 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
>  		goto fallback;
>
>  	/* Try allocating the highest of the remaining orders. */
> -	gfp = vma_thp_gfp_mask(vma);
> +	gfp = vma_thp_gfp_mask(vma) | __GFP_ZERO;
>  	while (orders) {
>  		folio = vma_alloc_folio(gfp, order, vma, vmf->address);
>  		if (folio) {
>  			if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) {
>  				count_mthp_stat(order, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
> -				folio_put(folio);
> +				folio_put_zeroed(folio);

You just allocated the folio as zeroed above, should PG_zeroed not be set thus
making it unnecessary to add folio_put_zeroed()?

>  				goto next;
>  			}
>  			folio_throttle_swaprate(folio, gfp);
> -			/*
> -			 * When a folio is not zeroed during allocation
> -			 * (__GFP_ZERO not used) or user folios require special
> -			 * handling, folio_zero_user() is used to make sure
> -			 * that the page corresponding to the faulting address
> -			 * will be hot in the cache after zeroing.
> -			 */
> -			if (user_alloc_needs_zeroing())
> -				folio_zero_user(folio, vmf->address);
>  			return folio;
>  		}
>  next:
> --
> MST
>

Thanks, Lorenzo