Re: [PATCH 1/1] arm64: mm: swap: support THP_SWAP on hardware with MTE

[Ryan Roberts <ryan.roberts@arm.com>]

On 22/03/2024 11:41, Barry Song wrote:
> From: Barry Song <v-songbaohua@oppo.com>
> 
> Commit d0637c505f8a1 ("arm64: enable THP_SWAP for arm64") brings up
> THP_SWAP on ARM64, but it doesn't enable THP_SWP on hardware with
> MTE as the MTE code works with the assumption tags save/restore is
> always handling a folio with only one page.
> 
> The limitation should be removed as more and more ARM64 SoCs have
> this feature. Co-existence of MTE and THP_SWAP becomes more and
> more important.
> 
> This patch makes MTE tags saving support large folios, then we don't
> need to split large folios into base pages for swapping out on ARM64
> SoCs with MTE any more.
> 
> arch_prepare_to_swap() should take folio rather than page as parameter
> because we support THP swap-out as a whole. It saves tags for all
> pages in a large folio.
> 
> As now we are restoring tags based-on folio, in arch_swap_restore(),
> we may increase some extra loops and early-exitings while refaulting
> a large folio which is still in swapcache in do_swap_page(). In case
> a large folio has nr pages, do_swap_page() will only set the PTE of
> the particular page which is causing the page fault.
> Thus do_swap_page() runs nr times, and each time, arch_swap_restore()
> will loop nr times for those subpages in the folio. So right now the
> algorithmic complexity becomes O(nr^2).
> 
> Once we support mapping large folios in do_swap_page(), extra loops
> and early-exitings will decrease while not being completely removed
> as a large folio might get partially tagged in corner cases such as,
> 1. a large folio in swapcache can be partially unmapped, thus, MTE
> tags for the unmapped pages will be invalidated;
> 2. users might use mprotect() to set MTEs on a part of a large folio.
> 
> arch_thp_swp_supported() is dropped since ARM64 MTE was the only one
> who needed it.
> 
> Cc: Catalin Marinas <catalin.marinas@arm.com>
> Cc: Will Deacon <will@kernel.org>
> Cc: Ryan Roberts <ryan.roberts@arm.com>
> Cc: Mark Rutland <mark.rutland@arm.com>
> Cc: David Hildenbrand <david@redhat.com>
> Cc: Kemeng Shi <shikemeng@huaweicloud.com>
> Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>
> Cc: Anshuman Khandual <anshuman.khandual@arm.com>
> Cc: Peter Collingbourne <pcc@google.com>
> Cc: Steven Price <steven.price@arm.com>
> Cc: Yosry Ahmed <yosryahmed@google.com>
> Cc: Peter Xu <peterx@redhat.com>
> Cc: Lorenzo Stoakes <lstoakes@gmail.com>
> Cc: "Mike Rapoport (IBM)" <rppt@kernel.org>
> Cc: Hugh Dickins <hughd@google.com>
> CC: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>
> Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>
> Signed-off-by: Barry Song <v-songbaohua@oppo.com>
> Reviewed-by: Steven Price <steven.price@arm.com>
> Acked-by: Chris Li <chrisl@kernel.org>

Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>

It would be really great if we can get this in for v6.10!

> ---
>  arch/arm64/include/asm/pgtable.h | 19 ++------------
>  arch/arm64/mm/mteswap.c          | 45 ++++++++++++++++++++++++++++++++
>  include/linux/huge_mm.h          | 12 ---------
>  include/linux/pgtable.h          |  2 +-
>  mm/internal.h                    | 14 ++++++++++
>  mm/memory.c                      |  2 +-
>  mm/page_io.c                     |  2 +-
>  mm/shmem.c                       |  2 +-
>  mm/swap_slots.c                  |  2 +-
>  mm/swapfile.c                    |  2 +-
>  10 files changed, 67 insertions(+), 35 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
> index afdd56d26ad7..259325e6b7e8 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -49,12 +49,6 @@
>  	__flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1)
>  #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
>  
> -static inline bool arch_thp_swp_supported(void)
> -{
> -	return !system_supports_mte();
> -}
> -#define arch_thp_swp_supported arch_thp_swp_supported
> -
>  /*
>   * Outside of a few very special situations (e.g. hibernation), we always
>   * use broadcast TLB invalidation instructions, therefore a spurious page
> @@ -1280,12 +1274,7 @@ static inline pmd_t pmdp_establish(struct vm_area_struct *vma,
>  #ifdef CONFIG_ARM64_MTE
>  
>  #define __HAVE_ARCH_PREPARE_TO_SWAP
> -static inline int arch_prepare_to_swap(struct page *page)
> -{
> -	if (system_supports_mte())
> -		return mte_save_tags(page);
> -	return 0;
> -}
> +extern int arch_prepare_to_swap(struct folio *folio);
>  
>  #define __HAVE_ARCH_SWAP_INVALIDATE
>  static inline void arch_swap_invalidate_page(int type, pgoff_t offset)
> @@ -1301,11 +1290,7 @@ static inline void arch_swap_invalidate_area(int type)
>  }
>  
>  #define __HAVE_ARCH_SWAP_RESTORE
> -static inline void arch_swap_restore(swp_entry_t entry, struct folio *folio)
> -{
> -	if (system_supports_mte())
> -		mte_restore_tags(entry, &folio->page);
> -}
> +extern void arch_swap_restore(swp_entry_t entry, struct folio *folio);
>  
>  #endif /* CONFIG_ARM64_MTE */
>  
> diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c
> index a31833e3ddc5..63e8d72f202a 100644
> --- a/arch/arm64/mm/mteswap.c
> +++ b/arch/arm64/mm/mteswap.c
> @@ -68,6 +68,13 @@ void mte_invalidate_tags(int type, pgoff_t offset)
>  	mte_free_tag_storage(tags);
>  }
>  
> +static inline void __mte_invalidate_tags(struct page *page)
> +{
> +	swp_entry_t entry = page_swap_entry(page);
> +
> +	mte_invalidate_tags(swp_type(entry), swp_offset(entry));
> +}
> +
>  void mte_invalidate_tags_area(int type)
>  {
>  	swp_entry_t entry = swp_entry(type, 0);
> @@ -83,3 +90,41 @@ void mte_invalidate_tags_area(int type)
>  	}
>  	xa_unlock(&mte_pages);
>  }
> +
> +int arch_prepare_to_swap(struct folio *folio)
> +{
> +	long i, nr;
> +	int err;
> +
> +	if (!system_supports_mte())
> +		return 0;
> +
> +	nr = folio_nr_pages(folio);
> +
> +	for (i = 0; i < nr; i++) {
> +		err = mte_save_tags(folio_page(folio, i));
> +		if (err)
> +			goto out;
> +	}
> +	return 0;
> +
> +out:
> +	while (i--)
> +		__mte_invalidate_tags(folio_page(folio, i));
> +	return err;
> +}
> +
> +void arch_swap_restore(swp_entry_t entry, struct folio *folio)
> +{
> +	long i, nr;
> +
> +	if (!system_supports_mte())
> +		return;
> +
> +	nr = folio_nr_pages(folio);
> +
> +	for (i = 0; i < nr; i++) {
> +		mte_restore_tags(entry, folio_page(folio, i));
> +		entry.val++;
> +	}
> +}
> diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
> index de0c89105076..e04b93c43965 100644
> --- a/include/linux/huge_mm.h
> +++ b/include/linux/huge_mm.h
> @@ -535,16 +535,4 @@ static inline int split_folio_to_order(struct folio *folio, int new_order)
>  #define split_folio_to_list(f, l) split_folio_to_list_to_order(f, l, 0)
>  #define split_folio(f) split_folio_to_order(f, 0)
>  
> -/*
> - * archs that select ARCH_WANTS_THP_SWAP but don't support THP_SWP due to
> - * limitations in the implementation like arm64 MTE can override this to
> - * false
> - */
> -#ifndef arch_thp_swp_supported
> -static inline bool arch_thp_swp_supported(void)
> -{
> -	return true;
> -}
> -#endif
> -
>  #endif /* _LINUX_HUGE_MM_H */
> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> index 85fc7554cd52..b10a7dd615bd 100644
> --- a/include/linux/pgtable.h
> +++ b/include/linux/pgtable.h
> @@ -1052,7 +1052,7 @@ static inline int arch_unmap_one(struct mm_struct *mm,
>   * prototypes must be defined in the arch-specific asm/pgtable.h file.
>   */
>  #ifndef __HAVE_ARCH_PREPARE_TO_SWAP
> -static inline int arch_prepare_to_swap(struct page *page)
> +static inline int arch_prepare_to_swap(struct folio *folio)
>  {
>  	return 0;
>  }
> diff --git a/mm/internal.h b/mm/internal.h
> index 7e486f2c502c..2551e93dd885 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -76,6 +76,20 @@ static inline int folio_nr_pages_mapped(struct folio *folio)
>  	return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED;
>  }
>  
> +/*
> + * Retrieve the first entry of a folio based on a provided entry within the
> + * folio. We cannot rely on folio->swap as there is no guarantee that it has
> + * been initialized. Used for calling arch_swap_restore()
> + */
> +static inline swp_entry_t folio_swap(swp_entry_t entry, struct folio *folio)
> +{
> +	swp_entry_t swap = {
> +		.val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)),
> +	};
> +
> +	return swap;
> +}
> +
>  static inline void *folio_raw_mapping(struct folio *folio)
>  {
>  	unsigned long mapping = (unsigned long)folio->mapping;
> diff --git a/mm/memory.c b/mm/memory.c
> index f2bc6dd15eb8..b7cab8be8632 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -4188,7 +4188,7 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>  	 * when reading from swap. This metadata may be indexed by swap entry
>  	 * so this must be called before swap_free().
>  	 */
> -	arch_swap_restore(entry, folio);
> +	arch_swap_restore(folio_swap(entry, folio), folio);
>  
>  	/*
>  	 * Remove the swap entry and conditionally try to free up the swapcache.
> diff --git a/mm/page_io.c b/mm/page_io.c
> index ae2b49055e43..a9a7c236aecc 100644
> --- a/mm/page_io.c
> +++ b/mm/page_io.c
> @@ -189,7 +189,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
>  	 * Arch code may have to preserve more data than just the page
>  	 * contents, e.g. memory tags.
>  	 */
> -	ret = arch_prepare_to_swap(&folio->page);
> +	ret = arch_prepare_to_swap(folio);
>  	if (ret) {
>  		folio_mark_dirty(folio);
>  		folio_unlock(folio);
> diff --git a/mm/shmem.c b/mm/shmem.c
> index 0aad0d9a621b..44c1519ba881 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -1913,7 +1913,7 @@ static int shmem_swapin_folio(struct inode *inode, pgoff_t index,
>  	 * Some architectures may have to restore extra metadata to the
>  	 * folio after reading from swap.
>  	 */
> -	arch_swap_restore(swap, folio);
> +	arch_swap_restore(folio_swap(swap, folio), folio);
>  
>  	if (shmem_should_replace_folio(folio, gfp)) {
>  		error = shmem_replace_folio(&folio, gfp, info, index);
> diff --git a/mm/swap_slots.c b/mm/swap_slots.c
> index 90973ce7881d..53abeaf1371d 100644
> --- a/mm/swap_slots.c
> +++ b/mm/swap_slots.c
> @@ -310,7 +310,7 @@ swp_entry_t folio_alloc_swap(struct folio *folio)
>  	entry.val = 0;
>  
>  	if (folio_test_large(folio)) {
> -		if (IS_ENABLED(CONFIG_THP_SWAP) && arch_thp_swp_supported())
> +		if (IS_ENABLED(CONFIG_THP_SWAP))
>  			get_swap_pages(1, &entry, folio_nr_pages(folio));
>  		goto out;
>  	}
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 4919423cce76..5e6d2304a2a4 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -1806,7 +1806,7 @@ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd,
>  	 * when reading from swap. This metadata may be indexed by swap entry
>  	 * so this must be called before swap_free().
>  	 */
> -	arch_swap_restore(entry, folio);
> +	arch_swap_restore(folio_swap(entry, folio), folio);
>  
>  	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
>  	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);