Re: [PATCH v3 6/6] mm: swap: entirely map large folios found in swapcache

[David Hildenbrand <david@redhat.com>]

On 03.05.24 02:50, Barry Song wrote:
> From: Chuanhua Han <hanchuanhua@oppo.com>
> 
> When a large folio is found in the swapcache, the current implementation
> requires calling do_swap_page() nr_pages times, resulting in nr_pages
> page faults. This patch opts to map the entire large folio at once to
> minimize page faults. Additionally, redundant checks and early exits
> for ARM64 MTE restoring are removed.
> 
> Signed-off-by: Chuanhua Han <hanchuanhua@oppo.com>
> Co-developed-by: Barry Song <v-songbaohua@oppo.com>
> Signed-off-by: Barry Song <v-songbaohua@oppo.com>
> ---
>   mm/memory.c | 60 ++++++++++++++++++++++++++++++++++++++++++-----------
>   1 file changed, 48 insertions(+), 12 deletions(-)
> 
> diff --git a/mm/memory.c b/mm/memory.c
> index 22e7c33cc747..940fdbe69fa1 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -3968,6 +3968,10 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>   	pte_t pte;
>   	vm_fault_t ret = 0;
>   	void *shadow = NULL;
> +	int nr_pages = 1;
> +	unsigned long page_idx = 0;
> +	unsigned long address = vmf->address;
> +	pte_t *ptep;
>   
>   	if (!pte_unmap_same(vmf))
>   		goto out;
> @@ -4166,6 +4170,36 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>   		goto out_nomap;
>   	}
>   
> +	ptep = vmf->pte;
> +	if (folio_test_large(folio) && folio_test_swapcache(folio)) {
> +		int nr = folio_nr_pages(folio);
> +		unsigned long idx = folio_page_idx(folio, page);
> +		unsigned long folio_start = vmf->address - idx * PAGE_SIZE;
> +		unsigned long folio_end = folio_start + nr * PAGE_SIZE;
> +		pte_t *folio_ptep;
> +		pte_t folio_pte;
> +
> +		if (unlikely(folio_start < max(vmf->address & PMD_MASK, vma->vm_start)))
> +			goto check_folio;
> +		if (unlikely(folio_end > pmd_addr_end(vmf->address, vma->vm_end)))
> +			goto check_folio;
> +
> +		folio_ptep = vmf->pte - idx;
> +		folio_pte = ptep_get(folio_ptep);
> +		if (!pte_same(folio_pte, pte_move_swp_offset(vmf->orig_pte, -idx)) ||
> +		    swap_pte_batch(folio_ptep, nr, folio_pte) != nr)
> +			goto check_folio;
> +
> +		page_idx = idx;
> +		address = folio_start;
> +		ptep = folio_ptep;
> +		nr_pages = nr;
> +		entry = folio->swap;
> +		page = &folio->page;
> +	}
> +
> +check_folio:
> +
>   	/*
>   	 * PG_anon_exclusive reuses PG_mappedtodisk for anon pages. A swap pte
>   	 * must never point at an anonymous page in the swapcache that is
> @@ -4225,12 +4259,13 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>   	 * We're already holding a reference on the page but haven't mapped it
>   	 * yet.
>   	 */
> -	swap_free_nr(entry, 1);
> +	swap_free_nr(entry, nr_pages);
>   	if (should_try_to_free_swap(folio, vma, vmf->flags))
>   		folio_free_swap(folio);
>   
> -	inc_mm_counter(vma->vm_mm, MM_ANONPAGES);
> -	dec_mm_counter(vma->vm_mm, MM_SWAPENTS);
> +	folio_ref_add(folio, nr_pages - 1);
> +	add_mm_counter(vma->vm_mm, MM_ANONPAGES, nr_pages);
> +	add_mm_counter(vma->vm_mm, MM_SWAPENTS, -nr_pages);
>   	pte = mk_pte(page, vma->vm_page_prot);
>   
>   	/*
> @@ -4240,34 +4275,35 @@ vm_fault_t do_swap_page(struct vm_fault *vmf)
>   	 * exclusivity.
>   	 */
>   	if (!folio_test_ksm(folio) &&
> -	    (exclusive || folio_ref_count(folio) == 1)) {
> +	    (exclusive || (folio_ref_count(folio) == nr_pages &&
> +			   folio_nr_pages(folio) == nr_pages))) {
>   		if (vmf->flags & FAULT_FLAG_WRITE) {
>   			pte = maybe_mkwrite(pte_mkdirty(pte), vma);
>   			vmf->flags &= ~FAULT_FLAG_WRITE;

I fail to convince myself that this change is correct, and if it is 
correct, it's confusing (I think there is a dependency on 
folio_free_swap() having been called and succeeding, such that we don't 
have a folio that is in the swapcache at this point).

Why can't we move the folio_ref_add() after this check and just leave 
the check as it is?

"folio_ref_count(folio) == 1" is as clear as it gets: we hold the single 
reference, so we can do with this thing whatever we want: it's certainly 
exclusive. No swapcache, no other people mapping it.


-- 
Cheers,

David / dhildenb