[PATCH v4 04/23] mm: devmap: refactor 1-based refcounting for ZONE_DEVICE pages

[Dan Williams]

On Tue, Nov 12, 2019 at 8:27 PM John Hubbard <jhubbard at nvidia.com> wrote:
>
> An upcoming patch changes and complicates the refcounting and
> especially the "put page" aspects of it. In order to keep
> everything clean, refactor the devmap page release routines:
>
> * Rename put_devmap_managed_page() to page_is_devmap_managed(),
>   and limit the functionality to "read only": return a bool,
>   with no side effects.
>
> * Add a new routine, put_devmap_managed_page(), to handle checking
>   what kind of page it is, and what kind of refcount handling it
>   requires.
>
> * Rename __put_devmap_managed_page() to free_devmap_managed_page(),
>   and limit the functionality to unconditionally freeing a devmap
>   page.
>
> This is originally based on a separate patch by Ira Weiny, which
> applied to an early version of the put_user_page() experiments.
> Since then, Jérôme Glisse suggested the refactoring described above.
>
> Suggested-by: Jérôme Glisse <jglisse at redhat.com>
> Signed-off-by: Ira Weiny <ira.weiny at intel.com>
> Signed-off-by: John Hubbard <jhubbard at nvidia.com>
> ---
>  include/linux/mm.h | 27 ++++++++++++++++---
>  mm/memremap.c      | 67 ++++++++++++++++++++--------------------------
>  2 files changed, 53 insertions(+), 41 deletions(-)
>
> diff --git a/include/linux/mm.h b/include/linux/mm.h
> index a2adf95b3f9c..96228376139c 100644
> --- a/include/linux/mm.h
> +++ b/include/linux/mm.h
> @@ -967,9 +967,10 @@ static inline bool is_zone_device_page(const struct page *page)
>  #endif
>
>  #ifdef CONFIG_DEV_PAGEMAP_OPS
> -void __put_devmap_managed_page(struct page *page);
> +void free_devmap_managed_page(struct page *page);
>  DECLARE_STATIC_KEY_FALSE(devmap_managed_key);
> -static inline bool put_devmap_managed_page(struct page *page)
> +
> +static inline bool page_is_devmap_managed(struct page *page)
>  {
>         if (!static_branch_unlikely(&devmap_managed_key))
>                 return false;
> @@ -978,7 +979,6 @@ static inline bool put_devmap_managed_page(struct page *page)
>         switch (page->pgmap->type) {
>         case MEMORY_DEVICE_PRIVATE:
>         case MEMORY_DEVICE_FS_DAX:
> -               __put_devmap_managed_page(page);
>                 return true;
>         default:
>                 break;
> @@ -986,6 +986,27 @@ static inline bool put_devmap_managed_page(struct page *page)
>         return false;
>  }
>
> +static inline bool put_devmap_managed_page(struct page *page)
> +{
> +       bool is_devmap = page_is_devmap_managed(page);
> +
> +       if (is_devmap) {
> +               int count = page_ref_dec_return(page);
> +
> +               /*
> +                * devmap page refcounts are 1-based, rather than 0-based: if
> +                * refcount is 1, then the page is free and the refcount is
> +                * stable because nobody holds a reference on the page.
> +                */
> +               if (count == 1)
> +                       free_devmap_managed_page(page);
> +               else if (!count)
> +                       __put_page(page);
> +       }
> +
> +       return is_devmap;
> +}
> +
>  #else /* CONFIG_DEV_PAGEMAP_OPS */
>  static inline bool put_devmap_managed_page(struct page *page)
>  {
> diff --git a/mm/memremap.c b/mm/memremap.c
> index 03ccbdfeb697..bc7e2a27d025 100644
> --- a/mm/memremap.c
> +++ b/mm/memremap.c
> @@ -410,48 +410,39 @@ struct dev_pagemap *get_dev_pagemap(unsigned long pfn,
>  EXPORT_SYMBOL_GPL(get_dev_pagemap);
>
>  #ifdef CONFIG_DEV_PAGEMAP_OPS
> -void __put_devmap_managed_page(struct page *page)
> +void free_devmap_managed_page(struct page *page)
>  {
> -       int count = page_ref_dec_return(page);
> +       /* Clear Active bit in case of parallel mark_page_accessed */
> +       __ClearPageActive(page);
> +       __ClearPageWaiters(page);
> +
> +       mem_cgroup_uncharge(page);

Ugh, when did all this HMM specific manipulation sneak into the
generic ZONE_DEVICE path? It used to be gated by pgmap type with its
own put_zone_device_private_page(). For example it's certainly
unnecessary and might be broken (would need to check) to call
mem_cgroup_uncharge() on a DAX page. ZONE_DEVICE users are not a
monolith and the HMM use case leaks pages into code paths that DAX
explicitly avoids.