Re: [PATCH v1 06/12] mm: use single SWP_DEVICE_EXCLUSIVE entry type

[Alistair Popple <apopple@nvidia.com>]

On Wed, Jan 29, 2025 at 12:54:04PM +0100, David Hildenbrand wrote:
> There is no need for the distinction anymore; let's merge the readable
> and writable device-exclusive entries into a single device-exclusive
> entry type.
> 
> Signed-off-by: David Hildenbrand <david@redhat.com>
> ---
>  include/linux/swap.h    |  7 +++----
>  include/linux/swapops.h | 27 ++++-----------------------
>  mm/mprotect.c           |  8 --------
>  mm/page_table_check.c   |  5 ++---
>  mm/rmap.c               |  2 +-
>  5 files changed, 10 insertions(+), 39 deletions(-)
> 
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 91b30701274e..9a48e79a0a52 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -74,14 +74,13 @@ static inline int current_is_kswapd(void)
>   * to a special SWP_DEVICE_{READ|WRITE} entry.
>   *
>   * When a page is mapped by the device for exclusive access we set the CPU page
> - * table entries to special SWP_DEVICE_EXCLUSIVE_* entries.
> + * table entries to a special SWP_DEVICE_EXCLUSIVE entry.
>   */
>  #ifdef CONFIG_DEVICE_PRIVATE
> -#define SWP_DEVICE_NUM 4
> +#define SWP_DEVICE_NUM 3
>  #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM)
>  #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1)
> -#define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2)
> -#define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3)
> +#define SWP_DEVICE_EXCLUSIVE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2)
>  #else
>  #define SWP_DEVICE_NUM 0
>  #endif
> diff --git a/include/linux/swapops.h b/include/linux/swapops.h
> index 96f26e29fefe..64ea151a7ae3 100644
> --- a/include/linux/swapops.h
> +++ b/include/linux/swapops.h
> @@ -186,26 +186,16 @@ static inline bool is_writable_device_private_entry(swp_entry_t entry)
>  	return unlikely(swp_type(entry) == SWP_DEVICE_WRITE);
>  }
>  
> -static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset)
> +static inline swp_entry_t make_device_exclusive_entry(pgoff_t offset)
>  {
> -	return swp_entry(SWP_DEVICE_EXCLUSIVE_READ, offset);
> -}
> -
> -static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset)
> -{
> -	return swp_entry(SWP_DEVICE_EXCLUSIVE_WRITE, offset);
> +	return swp_entry(SWP_DEVICE_EXCLUSIVE, offset);
>  }
>  
>  static inline bool is_device_exclusive_entry(swp_entry_t entry)
>  {
> -	return swp_type(entry) == SWP_DEVICE_EXCLUSIVE_READ ||
> -		swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE;
> +	return swp_type(entry) == SWP_DEVICE_EXCLUSIVE;
>  }
>  
> -static inline bool is_writable_device_exclusive_entry(swp_entry_t entry)
> -{
> -	return unlikely(swp_type(entry) == SWP_DEVICE_EXCLUSIVE_WRITE);
> -}
>  #else /* CONFIG_DEVICE_PRIVATE */
>  static inline swp_entry_t make_readable_device_private_entry(pgoff_t offset)
>  {
> @@ -227,12 +217,7 @@ static inline bool is_writable_device_private_entry(swp_entry_t entry)
>  	return false;
>  }
>  
> -static inline swp_entry_t make_readable_device_exclusive_entry(pgoff_t offset)
> -{
> -	return swp_entry(0, 0);
> -}
> -
> -static inline swp_entry_t make_writable_device_exclusive_entry(pgoff_t offset)
> +static inline swp_entry_t make_device_exclusive_entry(pgoff_t offset)
>  {
>  	return swp_entry(0, 0);
>  }
> @@ -242,10 +227,6 @@ static inline bool is_device_exclusive_entry(swp_entry_t entry)
>  	return false;
>  }
>  
> -static inline bool is_writable_device_exclusive_entry(swp_entry_t entry)
> -{
> -	return false;
> -}
>  #endif /* CONFIG_DEVICE_PRIVATE */
>  
>  #ifdef CONFIG_MIGRATION
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index 516b1d847e2c..9cb6ab7c4048 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -225,14 +225,6 @@ static long change_pte_range(struct mmu_gather *tlb,
>  				newpte = swp_entry_to_pte(entry);
>  				if (pte_swp_uffd_wp(oldpte))
>  					newpte = pte_swp_mkuffd_wp(newpte);
> -			} else if (is_writable_device_exclusive_entry(entry)) {
> -				entry = make_readable_device_exclusive_entry(
> -							swp_offset(entry));
> -				newpte = swp_entry_to_pte(entry);
> -				if (pte_swp_soft_dirty(oldpte))
> -					newpte = pte_swp_mksoft_dirty(newpte);
> -				if (pte_swp_uffd_wp(oldpte))
> -					newpte = pte_swp_mkuffd_wp(newpte);

So just to check my understanding the idea is we now check vma->vm_flags in
restore_exclusive_pte() to restore them as read-only in the case of mprotect()
write protecting the range? That makes sense to me, so assuming that's true:

Reviewed-by: Alistair Popple <apopple@nvidia.com>

>  			} else if (is_pte_marker_entry(entry)) {
>  				/*
>  				 * Ignore error swap entries unconditionally,
> diff --git a/mm/page_table_check.c b/mm/page_table_check.c
> index 509c6ef8de40..c2b3600429a0 100644
> --- a/mm/page_table_check.c
> +++ b/mm/page_table_check.c
> @@ -196,9 +196,8 @@ EXPORT_SYMBOL(__page_table_check_pud_clear);
>  /* Whether the swap entry cached writable information */
>  static inline bool swap_cached_writable(swp_entry_t entry)
>  {
> -	return is_writable_device_exclusive_entry(entry) ||
> -	    is_writable_device_private_entry(entry) ||
> -	    is_writable_migration_entry(entry);
> +	return is_writable_device_private_entry(entry) ||
> +	       is_writable_migration_entry(entry);
>  }
>  
>  static inline void page_table_check_pte_flags(pte_t pte)
> diff --git a/mm/rmap.c b/mm/rmap.c
> index 49ffac6d27f8..65d9bbea16d0 100644
> --- a/mm/rmap.c
> +++ b/mm/rmap.c
> @@ -2470,7 +2470,7 @@ struct page *make_device_exclusive(struct mm_struct *mm, unsigned long addr,
>  	 * do_swap_page() will trigger the conversion back while holding the
>  	 * folio lock.
>  	 */
> -	entry = make_writable_device_exclusive_entry(page_to_pfn(page));
> +	entry = make_device_exclusive_entry(page_to_pfn(page));
>  	swp_pte = swp_entry_to_pte(entry);
>  	if (pte_soft_dirty(fw.pte))
>  		swp_pte = pte_swp_mksoft_dirty(swp_pte);
> -- 
> 2.48.1
>