[PATCH v1 11/11] mm/memory: ignore writable bit in folio_pte_batch()

[Ryan Roberts]

On 22/01/2024 19:42, David Hildenbrand wrote:
> ... and conditionally return to the caller if any pte except the first one
> is writable. fork() has to make sure to properly write-protect in case any
> PTE is writable. Other users (e.g., page unmaping) won't care.
> 
> Signed-off-by: David Hildenbrand <david at redhat.com>

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

> ---
>  mm/memory.c | 26 +++++++++++++++++++++-----
>  1 file changed, 21 insertions(+), 5 deletions(-)
> 
> diff --git a/mm/memory.c b/mm/memory.c
> index 341b2be845b6e..a26fd0669016b 100644
> --- a/mm/memory.c
> +++ b/mm/memory.c
> @@ -955,7 +955,7 @@ static __always_inline void __copy_present_ptes(struct vm_area_struct *dst_vma,
>  
>  static inline pte_t __pte_batch_clear_ignored(pte_t pte)
>  {
> -	return pte_clear_soft_dirty(pte_mkclean(pte_mkold(pte)));
> +	return pte_wrprotect(pte_clear_soft_dirty(pte_mkclean(pte_mkold(pte))));
>  }
>  
>  /*
> @@ -963,20 +963,29 @@ static inline pte_t __pte_batch_clear_ignored(pte_t pte)
>   * pages of the same folio.
>   *
>   * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN.
> - * the accessed bit, dirty bit and soft-dirty bit.
> + * the accessed bit, dirty bit, soft-dirty bit and writable bit.
> + . If "any_writable" is set, it will indicate if any other PTE besides the
> + * first (given) PTE is writable.
>   */
>  static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
> -		pte_t *start_ptep, pte_t pte, int max_nr)
> +		pte_t *start_ptep, pte_t pte, int max_nr, bool *any_writable)
>  {
>  	unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio);
>  	const pte_t *end_ptep = start_ptep + max_nr;
>  	pte_t expected_pte = __pte_batch_clear_ignored(pte_next_pfn(pte));
>  	pte_t *ptep = start_ptep + 1;
> +	bool writable;
> +
> +	if (any_writable)
> +		*any_writable = false;
>  
>  	VM_WARN_ON_FOLIO(!pte_present(pte), folio);
>  
>  	while (ptep != end_ptep) {
> -		pte = __pte_batch_clear_ignored(ptep_get(ptep));
> +		pte = ptep_get(ptep);
> +		if (any_writable)
> +			writable = !!pte_write(pte);
> +		pte = __pte_batch_clear_ignored(pte);
>  
>  		if (!pte_same(pte, expected_pte))
>  			break;
> @@ -989,6 +998,9 @@ static inline int folio_pte_batch(struct folio *folio, unsigned long addr,
>  		if (pte_pfn(pte) == folio_end_pfn)
>  			break;
>  
> +		if (any_writable)
> +			*any_writable |= writable;
> +
>  		expected_pte = pte_next_pfn(expected_pte);
>  		ptep++;
>  	}
> @@ -1010,6 +1022,7 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
>  {
>  	struct page *page;
>  	struct folio *folio;
> +	bool any_writable;
>  	int err, nr;
>  
>  	page = vm_normal_page(src_vma, addr, pte);
> @@ -1024,7 +1037,8 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
>  	 * by keeping the batching logic separate.
>  	 */
>  	if (unlikely(!*prealloc && folio_test_large(folio) && max_nr != 1)) {
> -		nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr);
> +		nr = folio_pte_batch(folio, addr, src_pte, pte, max_nr,
> +				     &any_writable);
>  		if (folio_test_anon(folio)) {
>  			folio_ref_add(folio, nr);
>  			if (unlikely(folio_try_dup_anon_rmap_ptes(folio, page,
> @@ -1039,6 +1053,8 @@ copy_present_ptes(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma
>  			folio_dup_file_rmap_ptes(folio, page, nr);
>  			rss[mm_counter_file(page)] += nr;
>  		}
> +		if (any_writable)
> +			pte = pte_mkwrite(pte, src_vma);
>  		__copy_present_ptes(dst_vma, src_vma, dst_pte, src_pte, pte,
>  				    addr, nr);
>  		return nr;