Re: [PATCH v6 01/23] mm: Introduce PTE_MARKER swap entry

[Alistair Popple <apopple@nvidia.com>]

On Monday, 15 November 2021 6:55:00 PM AEDT Peter Xu wrote:

[...]

> diff --git a/include/linux/swapops.h b/include/linux/swapops.h
> index d356ab4047f7..5103d2a4ae38 100644
> --- a/include/linux/swapops.h
> +++ b/include/linux/swapops.h
> @@ -247,6 +247,84 @@ static inline int is_writable_migration_entry(swp_entry_t entry)
>  
>  #endif
>  
> +typedef unsigned long pte_marker;
> +
> +#define  PTE_MARKER_MASK     (0)
> +
> +#ifdef CONFIG_PTE_MARKER
> +
> +static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
> +{
> +	return swp_entry(SWP_PTE_MARKER, marker);
> +}
> +
> +static inline bool is_pte_marker_entry(swp_entry_t entry)
> +{
> +	return swp_type(entry) == SWP_PTE_MARKER;
> +}
> +
> +static inline pte_marker pte_marker_get(swp_entry_t entry)
> +{
> +	return swp_offset(entry) & PTE_MARKER_MASK;

I'm not sure the PTE_MARKER_MASK adds much, especially as we only have one
user. I don't see a problem with open-coding these kind of checks (ie.
swp_offset(entry) & PTE_MARKER_UFFD_WP) as you kind of end up doing that anyway.
Alternatively if you want helper functions I think it would be better to define
them for each marker. Eg: is_pte_marker_uffd_wp().

> +}
> +
> +static inline bool is_pte_marker(pte_t pte)
> +{
> +	return is_swap_pte(pte) && is_pte_marker_entry(pte_to_swp_entry(pte));
> +}
> +
> +#else /* CONFIG_PTE_MARKER */
> +
> +static inline swp_entry_t make_pte_marker_entry(pte_marker marker)
> +{
> +	/* This should never be called if !CONFIG_PTE_MARKER */

Can we leave this function undefined then? That way we will get an obvious
build error.

Overall I'm liking the swap entry approach a lot more than the special pte
approach, but maybe that's just because I'm more familiar with special swap
entries :-)

> +	WARN_ON_ONCE(1);
> +	return swp_entry(0, 0);
> +}
> +
> +static inline bool is_pte_marker_entry(swp_entry_t entry)
> +{
> +	return false;
> +}
> +
> +static inline pte_marker pte_marker_get(swp_entry_t entry)
> +{
> +	return 0;
> +}
> +
> +static inline bool is_pte_marker(pte_t pte)
> +{
> +	return false;
> +}
> +
> +#endif /* CONFIG_PTE_MARKER */
> +
> +static inline pte_t make_pte_marker(pte_marker marker)
> +{
> +	return swp_entry_to_pte(make_pte_marker_entry(marker));
> +}
> +
> +/*
> + * This is a special version to check pte_none() just to cover the case when
> + * the pte is a pte marker.  It existed because in many cases the pte marker
> + * should be seen as a none pte; it's just that we have stored some information
> + * onto the none pte so it becomes not-none any more.
> + *
> + * It should be used when the pte is file-backed, ram-based and backing
> + * userspace pages, like shmem.  It is not needed upon pgtables that do not
> + * support pte markers at all.  For example, it's not needed on anonymous
> + * memory, kernel-only memory (including when the system is during-boot),
> + * non-ram based generic file-system.  It's fine to be used even there, but the
> + * extra pte marker check will be pure overhead.
> + *
> + * For systems configured with !CONFIG_PTE_MARKER this will be automatically
> + * optimized to pte_none().
> + */
> +static inline int pte_none_mostly(pte_t pte)
> +{
> +	return pte_none(pte) || is_pte_marker(pte);
> +}
> +
>  static inline struct page *pfn_swap_entry_to_page(swp_entry_t entry)
>  {
>  	struct page *p = pfn_to_page(swp_offset(entry));
> diff --git a/mm/Kconfig b/mm/Kconfig
> index 068ce591a13a..66f23c6c2032 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -897,6 +897,13 @@ config IO_MAPPING
>  config SECRETMEM
>  	def_bool ARCH_HAS_SET_DIRECT_MAP && !EMBEDDED
>  
> +config PTE_MARKER
> +	def_bool n
> +	bool "Marker PTEs support"
> +
> +	help
> +	  Allows to create marker PTEs for file-backed memory.
> +
>  source "mm/damon/Kconfig"
>  
>  endmenu
>