On 3/24/26 16:43, Pedro Falcato wrote:
> The common order-0 case is important enough to want its own branch, and
> avoids the hairy, large loop logic that the CPU does not seem to handle
> particularly well.
> 
> While at it, encourage the compiler to inline batch PTE logic and resolve
> constant branches by adding __always_inline strategically.
> 
> Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
> Signed-off-by: Pedro Falcato <pfalcato@suse.de>
> ---
>  mm/mprotect.c | 17 ++++++++++++-----
>  1 file changed, 12 insertions(+), 5 deletions(-)
> 
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index 2eaf862e5734..2fda26107066 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -103,7 +103,7 @@ bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
>  	return can_change_shared_pte_writable(vma, pte);
>  }
> 
> -static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
> +static __always_inline int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
>  				    pte_t pte, int max_nr_ptes, fpb_t flags)
>  {
>  	/* No underlying folio, so cannot batch */
> @@ -117,9 +117,9 @@ static int mprotect_folio_pte_batch(struct folio *folio, pte_t *ptep,
>  }
> 
>  /* Set nr_ptes number of ptes, starting from idx */
> -static void prot_commit_flush_ptes(struct vm_area_struct *vma, unsigned long addr,
> -		pte_t *ptep, pte_t oldpte, pte_t ptent, int nr_ptes,
> -		int idx, bool set_write, struct mmu_gather *tlb)
> +static __always_inline void prot_commit_flush_ptes(struct vm_area_struct *vma,
> +		unsigned long addr, pte_t *ptep, pte_t oldpte, pte_t ptent,
> +		int nr_ptes, int idx, bool set_write, struct mmu_gather *tlb)
>  {
>  	/*
>  	 * Advance the position in the batch by idx; note that if idx > 0,
> @@ -169,7 +169,7 @@ static int page_anon_exclusive_sub_batch(int start_idx, int max_len,
>   * pte of the batch. Therefore, we must individually check all pages and
>   * retrieve sub-batches.
>   */
> -static void commit_anon_folio_batch(struct vm_area_struct *vma,
> +static __always_inline void commit_anon_folio_batch(struct vm_area_struct *vma,
>  		struct folio *folio, struct page *first_page, unsigned long addr, pte_t *ptep,
>  		pte_t oldpte, pte_t ptent, int nr_ptes, struct mmu_gather *tlb)
>  {
> @@ -177,6 +177,13 @@ static void commit_anon_folio_batch(struct vm_area_struct *vma,
>  	int sub_batch_idx = 0;
>  	int len;
> 
> +	/* Optimize for the common order-0 case. */
> +	if (likely(nr_ptes == 1)) {
> +		prot_commit_flush_ptes(vma, addr, ptep, oldpte, ptent, 1,
> +				       0, PageAnonExclusive(first_page), tlb);

To optimize that one, inlining prot_commit_flush_ptes() would be
sufficient. Does inlining the other two really help? I don't think we
can optimize out loops etc. for them?

I would have thought that specializing on nr_ptes==0 on an even higher
level--where we call
set_write_prot_commit_flush_ptes/prot_commit_flush_ptes() would allow
for optimizing the loops entirely for nr_ptes==0?

-- 
Cheers,

David