Re: [PATCH] mm: avoid zeroing user movable page twice with init_on_alloc=1

[Geert Uytterhoeven <geert@linux-m68k.org>]

Hi Zi,

On Thu, Dec 5, 2024 at 6:33 PM Zi Yan <ziy@nvidia.com> wrote:
> Can you try the patch below (it compiles locally for mips and x86) to see
> if your issue is fixed? Can you please make THP always on in your config,
> since THP is also affected by the same issue? The patch you tested only
> fixed non THP config.

Thanks, this works both without THP, and with
CONFIG_TRANSPARENT_HUGEPAGE=y
CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS=y

Tested-by: Geert Uytterhoeven <geert+renesas@glider.be>

> Thanks. I appreciate your help. :)

Thanks, I appreciate your quick responses and solutions!

> --- a/include/linux/highmem.h
> +++ b/include/linux/highmem.h
> @@ -224,7 +224,13 @@ static inline
>  struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma,
>                                    unsigned long vaddr)
>  {
> -       return vma_alloc_folio(GFP_HIGHUSER_MOVABLE | __GFP_ZERO, 0, vma, vaddr);
> +       struct folio *folio;
> +
> +       folio = vma_alloc_folio(GFP_HIGHUSER_MOVABLE, 0, vma, vaddr);
> +       if (folio && alloc_need_zeroing())
> +               clear_user_highpage(&folio->page, vaddr);
> +
> +       return folio;
>  }
>  #endif
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index c39c4945946c..6ac0308c4380 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -4175,6 +4175,23 @@ static inline int do_mseal(unsigned long start, size_t len_in, unsigned long fla
>  }
>  #endif
>
> +/*
> + * alloc_need_zeroing checks if a user folio from page allocator needs to be
> + * zeroed or not.
> + */
> +static inline bool alloc_need_zeroing(void)
> +{
> +       /*
> +        * for user folios, arch with cache aliasing requires cache flush and
> +        * arc sets folio->flags, so always return false to make caller use
> +        * clear_user_page()/clear_user_highpage()
> +        */
> +       return (IS_ENABLED(CONFIG_ARCH_HAS_CPU_CACHE_ALIASING) ||
> +               IS_ENABLED(CONFIG_ARC)) ||
> +              !static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
> +                                  &init_on_alloc);
> +}
> +
>  int arch_get_shadow_stack_status(struct task_struct *t, unsigned long __user *status);
>  int arch_set_shadow_stack_status(struct task_struct *t, unsigned long status);
>  int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index ee335d96fc39..107130a5413a 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -1176,11 +1176,12 @@ static struct folio *vma_alloc_anon_folio_pmd(struct vm_area_struct *vma,
>         folio_throttle_swaprate(folio, gfp);
>
>         /*
> -       * When a folio is not zeroed during allocation (__GFP_ZERO not used),
> -       * folio_zero_user() is used to make sure that the page corresponding
> -       * to the faulting address will be hot in the cache after zeroing.
> +       * 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 (!alloc_zeroed())
> +       if (alloc_need_zeroing())
>                 folio_zero_user(folio, addr);
>         /*
>          * The memory barrier inside __folio_mark_uptodate makes sure that
> diff --git a/mm/internal.h b/mm/internal.h
> index cb8d8e8e3ffa..3bd08bafad04 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -1285,12 +1285,6 @@ void touch_pud(struct vm_area_struct *vma, unsigned long addr,
>  void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
>                pmd_t *pmd, bool write);
>
> -static inline bool alloc_zeroed(void)
> -{
> -       return static_branch_maybe(CONFIG_INIT_ON_ALLOC_DEFAULT_ON,
> -                       &init_on_alloc);
> -}
> -
>  /*
>   * Parses a string with mem suffixes into its order. Useful to parse kernel
>   * parameters.
> diff --git a/mm/memory.c b/mm/memory.c
> index 75c2dfd04f72..cf1611791856 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -4733,12 +4733,12 @@ static struct folio *alloc_anon_folio(struct vm_fault *vmf)
>                         folio_throttle_swaprate(folio, gfp);
>                         /*
>                          * When a folio is not zeroed during allocation
> -                        * (__GFP_ZERO not used), folio_zero_user() is used
> -                        * to make sure that the page corresponding to the
> -                        * faulting address will be hot in the cache after
> -                        * zeroing.
> +                        * (__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 (!alloc_zeroed())
> +                       if (alloc_need_zeroing())
>                                 folio_zero_user(folio, vmf->address);
>                         return folio;
>                 }

Gr{oetje,eeting}s,

                        Geert

-- 
Geert Uytterhoeven -- There's lots of Linux beyond ia32 -- geert@linux-m68k.org

In personal conversations with technical people, I call myself a hacker. But
when I'm talking to journalists I just say "programmer" or something like that.
                                -- Linus Torvalds