Re: [PATCH 06/13] mm: add PMD swap entry splitting support

[Dev Jain]

On 27/04/26 3:31 pm, Usama Arif wrote:
> Add a swap branch in __split_huge_pmd_locked() that splits a PMD swap
> entry into 512 PTE swap entries.  Unlike migration splits, no folio
> reference is needed because swap entries point to swap slots, not
> pages.  Each PTE inherits the correct sub-slot offset and preserves
> soft_dirty, uffd_wp, and exclusive flags.
> 
> This branch is reached from the explicit __split_huge_pmd() callers
> that hit a non-present PMD: partial-range mprotect / munmap, the
> wp_huge_pmd() PMD-COW fallback, and the swap-in / swapoff fallbacks
> added in later patches when the cached folio is no longer PMD-sized.
> page_vma_mapped_walk() does not iterate PMD swap entries, so
> try_to_unmap_one() and try_to_migrate_one() do not reach this branch
> and freeze=true cannot occur in this branch today.  page and folio
> are therefore left uninitialized in the swap branch; a
> VM_WARN_ON_ONCE(freeze) catches any future caller that breaks this
> invariant before the freeze path dereferences page_to_pfn(page + i)
> or put_page(page).
> 
> Signed-off-by: Usama Arif <usama.arif@xxxxxxxxx>
> ---
>  include/linux/leafops.h |  6 +++---
>  mm/huge_memory.c        | 27 ++++++++++++++++++++++++++-
>  2 files changed, 29 insertions(+), 4 deletions(-)
> 
> diff --git a/include/linux/leafops.h b/include/linux/leafops.h
> index 79e04db45bfb..2c0dfce6d0f0 100644
> --- a/include/linux/leafops.h
> +++ b/include/linux/leafops.h
> @@ -657,9 +657,9 @@ static inline bool pmd_is_swap_entry(pmd_t pmd)
>   * pmd_is_valid_softleaf() - Is this PMD entry a valid softleaf entry?
>   * @pmd: PMD entry.
>   *
> - * PMD leaf entries are valid only if they are device private or migration
> - * entries. This function asserts that a PMD leaf entry is valid in this
> - * respect.
> + * PMD leaf entries are valid only if they are device private, migration,
> + * or swap entries. This function asserts that a PMD leaf entry is valid
> + * in this respect.
>   *

The commentary change can go in the previous patch right?


>   * Returns: true if the PMD entry is a valid leaf entry, otherwise false.
>   */
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index d82a19b5e276..9f67638e43c8 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -3201,6 +3201,12 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  			folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR,
>  						 vma, haddr, rmap_flags);
>  		}
> +	} else if (pmd_is_swap_entry(*pmd)) {
> +		VM_WARN_ON_ONCE(freeze);
> +		old_pmd = *pmd;
> +		soft_dirty = pmd_swp_soft_dirty(old_pmd);
> +		uffd_wp = pmd_swp_uffd_wp(old_pmd);
> +		anon_exclusive = pmd_swp_exclusive(old_pmd);
>  	} else {
>  		/*
>  		 * Up to this point the pmd is present and huge and userland has
> @@ -3337,6 +3343,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  			VM_WARN_ON(!pte_none(ptep_get(pte + i)));
>  			set_pte_at(mm, addr, pte + i, entry);
>  		}
> +	} else if (pmd_is_swap_entry(old_pmd)) {
> +		softleaf_t sl_entry = softleaf_from_pmd(old_pmd);
> +		pte_t swp_pte;
> +		swp_entry_t sub_entry;
> +
> +		for (i = 0, addr = haddr; i < HPAGE_PMD_NR;
> +		     i++, addr += PAGE_SIZE) {
> +			sub_entry = swp_entry(swp_type(sl_entry),
> +					      swp_offset(sl_entry) + i);
> +			swp_pte = swp_entry_to_pte(sub_entry);
> +			if (soft_dirty)
> +				swp_pte = pte_swp_mksoft_dirty(swp_pte);
> +			if (uffd_wp)
> +				swp_pte = pte_swp_mkuffd_wp(swp_pte);
> +			if (anon_exclusive)
> +				swp_pte = pte_swp_mkexclusive(swp_pte);
> +			VM_WARN_ON(!pte_none(ptep_get(pte + i)));
> +			set_pte_at(mm, addr, pte + i, swp_pte);
> +		}
>  	} else {
>  		pte_t entry;
>  
> @@ -3360,7 +3385,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
>  	}
>  	pte_unmap(pte);
>  
> -	if (!pmd_is_migration_entry(*pmd))
> +	if (!pmd_is_migration_entry(*pmd) && !pmd_is_swap_entry(*pmd))
>  		folio_remove_rmap_pmd(folio, page, vma);
>  	if (freeze)
>  		put_page(page);