linux-kernel - Re: [PATCH v3 1/5] mm: Optimize mprotect() by batch-skipping PTEs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <912757c0-8a75-4307-a0bd-8755f6135b5a@redhat.com>
Date: Wed, 21 May 2025 14:06:08 +0200
From: David Hildenbrand <david@...hat.com>
To: Dev Jain <dev.jain@....com>, akpm@...ux-foundation.org
Cc: ryan.roberts@....com, willy@...radead.org, linux-mm@...ck.org,
 linux-kernel@...r.kernel.org, catalin.marinas@....com, will@...nel.org,
 Liam.Howlett@...cle.com, lorenzo.stoakes@...cle.com, vbabka@...e.cz,
 jannh@...gle.com, anshuman.khandual@....com, peterx@...hat.com,
 joey.gouly@....com, ioworker0@...il.com, baohua@...nel.org,
 kevin.brodsky@....com, quic_zhenhuah@...cinc.com,
 christophe.leroy@...roup.eu, yangyicong@...ilicon.com,
 linux-arm-kernel@...ts.infradead.org, hughd@...gle.com,
 yang@...amperecomputing.com, ziy@...dia.com
Subject: Re: [PATCH v3 1/5] mm: Optimize mprotect() by batch-skipping PTEs

On 19.05.25 09:48, Dev Jain wrote:

Please highlight in the subject that this is only about MM_CP_PROT_NUMA 
handling.

> In case of prot_numa, there are various cases in which we can skip to the
> next iteration. Since the skip condition is based on the folio and not
> the PTEs, we can skip a PTE batch.
> 
> Signed-off-by: Dev Jain <dev.jain@....com>
> ---
>   mm/mprotect.c | 36 +++++++++++++++++++++++++++++-------
>   1 file changed, 29 insertions(+), 7 deletions(-)
> 
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index 88608d0dc2c2..1ee160ed0b14 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -83,6 +83,18 @@ bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
>   	return pte_dirty(pte);
>   }
>   
> +static int mprotect_batch(struct folio *folio, unsigned long addr, pte_t *ptep,
> +		pte_t pte, int max_nr_ptes)
> +{
> +	const fpb_t flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
> +
> +	if (!folio_test_large(folio) || (max_nr_ptes == 1))
> +		return 1;
> +
> +	return folio_pte_batch(folio, addr, ptep, pte, max_nr_ptes, flags,
> +			       NULL, NULL, NULL);
> +}
> +
>   static long change_pte_range(struct mmu_gather *tlb,
>   		struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr,
>   		unsigned long end, pgprot_t newprot, unsigned long cp_flags)
> @@ -94,6 +106,7 @@ static long change_pte_range(struct mmu_gather *tlb,
>   	bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
>   	bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
>   	bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
> +	int nr_ptes;
>   
>   	tlb_change_page_size(tlb, PAGE_SIZE);
>   	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
> @@ -108,8 +121,10 @@ static long change_pte_range(struct mmu_gather *tlb,
>   	flush_tlb_batched_pending(vma->vm_mm);
>   	arch_enter_lazy_mmu_mode();
>   	do {
> +		nr_ptes = 1;
>   		oldpte = ptep_get(pte);
>   		if (pte_present(oldpte)) {
> +			int max_nr_ptes = (end - addr) >> PAGE_SHIFT;
>   			pte_t ptent;
>   
>   			/*
> @@ -126,15 +141,18 @@ static long change_pte_range(struct mmu_gather *tlb,
>   					continue;
>   
>   				folio = vm_normal_folio(vma, addr, oldpte);
> -				if (!folio || folio_is_zone_device(folio) ||
> -				    folio_test_ksm(folio))
> +				if (!folio)
>   					continue;
>   
> +				if (folio_is_zone_device(folio) ||
> +				    folio_test_ksm(folio))
> +					goto skip_batch;
> +
>   				/* Also skip shared copy-on-write pages */
>   				if (is_cow_mapping(vma->vm_flags) &&
>   				    (folio_maybe_dma_pinned(folio) ||
>   				     folio_maybe_mapped_shared(folio)))
> -					continue;
> +					goto skip_batch;
>   
>   				/*
>   				 * While migration can move some dirty pages,
> @@ -143,7 +161,7 @@ static long change_pte_range(struct mmu_gather *tlb,
>   				 */
>   				if (folio_is_file_lru(folio) &&
>   				    folio_test_dirty(folio))
> -					continue;
> +					goto skip_batch;
>   
>   				/*
>   				 * Don't mess with PTEs if page is already on the node
> @@ -151,7 +169,7 @@ static long change_pte_range(struct mmu_gather *tlb,
>   				 */
>   				nid = folio_nid(folio);
>   				if (target_node == nid)
> -					continue;
> +					goto skip_batch;
>   				toptier = node_is_toptier(nid);
>   
>   				/*
> @@ -159,8 +177,12 @@ static long change_pte_range(struct mmu_gather *tlb,
>   				 * balancing is disabled
>   				 */
>   				if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
> -				    toptier)
> +				    toptier) {
> +skip_batch:
> +					nr_ptes = mprotect_batch(folio, addr, pte,
> +								 oldpte, max_nr_ptes);
>   					continue;
> +				}


I suggest

a) not burying that skip_batch label in another if condition

b) looking into factoring out prot_numa handling into a separate 
function first.


Likely we want something like

if (prot_numa) {
	nr_ptes = prot_numa_pte_range_skip_ptes(vma, addr, oldpte);
	if (nr_ptes)
		continue;
}

... likely with a better function name,


-- 
Cheers,

David / dhildenb