linux-kernel - Re: [PATCH v5 1/7] mm: Refactor MM_CP_PROT

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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <dc0b5e94-f5aa-407e-bad2-150814dc4885@arm.com>
Date: Tue, 22 Jul 2025 12:25:00 +0100
From: Ryan Roberts <ryan.roberts@....com>
To: Dev Jain <dev.jain@....com>, akpm@...ux-foundation.org
Cc: david@...hat.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 v5 1/7] mm: Refactor MM_CP_PROT_NUMA skipping case into
 new function

On 18/07/2025 10:02, Dev Jain wrote:
> Reduce indentation by refactoring the prot_numa case into a new function.
> No functional change intended.
> 
> Signed-off-by: Dev Jain <dev.jain@....com>
> ---
>  mm/mprotect.c | 101 +++++++++++++++++++++++++++-----------------------
>  1 file changed, 55 insertions(+), 46 deletions(-)
> 
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index 88709c01177b..2a9c73bd0778 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -83,6 +83,59 @@ bool can_change_pte_writable(struct vm_area_struct *vma, unsigned long addr,
>  	return pte_dirty(pte);
>  }
>  
> +static bool prot_numa_skip(struct vm_area_struct *vma, unsigned long addr,
> +			   pte_t oldpte, pte_t *pte, int target_node)
> +{
> +	struct folio *folio;
> +	bool toptier;
> +	int nid;
> +
> +	/* Avoid TLB flush if possible */
> +	if (pte_protnone(oldpte))
> +		return true;
> +
> +	folio = vm_normal_folio(vma, addr, oldpte);
> +	if (!folio)
> +		return true;
> +
> +	if (folio_is_zone_device(folio) || folio_test_ksm(folio))
> +		return true;
> +
> +	/* Also skip shared copy-on-write pages */
> +	if (is_cow_mapping(vma->vm_flags) &&
> +	    (folio_maybe_dma_pinned(folio) || folio_maybe_mapped_shared(folio)))
> +		return true;
> +
> +	/*
> +	 * While migration can move some dirty pages,
> +	 * it cannot move them all from MIGRATE_ASYNC
> +	 * context.
> +	 */
> +	if (folio_is_file_lru(folio) && folio_test_dirty(folio))
> +		return true;
> +
> +	/*
> +	 * Don't mess with PTEs if page is already on the node
> +	 * a single-threaded process is running on.
> +	 */
> +	nid = folio_nid(folio);
> +	if (target_node == nid)
> +		return true;
> +
> +	toptier = node_is_toptier(nid);
> +
> +	/*
> +	 * Skip scanning top tier node if normal numa
> +	 * balancing is disabled
> +	 */
> +	if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && toptier)
> +		return true;
> +
> +	if (folio_use_access_time(folio))
> +		folio_xchg_access_time(folio, jiffies_to_msecs(jiffies));

Perhaps this bit should be kept in the original location? It's got nothing to do
with determining if the pte should be skipped.

Thanks,
Ryan

> +	return false;
> +}
> +
>  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)
> @@ -117,53 +170,9 @@ static long change_pte_range(struct mmu_gather *tlb,
>  			 * pages. See similar comment in change_huge_pmd.
>  			 */
>  			if (prot_numa) {
> -				struct folio *folio;
> -				int nid;
> -				bool toptier;
> -
> -				/* Avoid TLB flush if possible */
> -				if (pte_protnone(oldpte))
> -					continue;
> -
> -				folio = vm_normal_folio(vma, addr, oldpte);
> -				if (!folio || folio_is_zone_device(folio) ||
> -				    folio_test_ksm(folio))
> -					continue;
> -
> -				/* 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;
> -
> -				/*
> -				 * While migration can move some dirty pages,
> -				 * it cannot move them all from MIGRATE_ASYNC
> -				 * context.
> -				 */
> -				if (folio_is_file_lru(folio) &&
> -				    folio_test_dirty(folio))
> -					continue;
> -
> -				/*
> -				 * Don't mess with PTEs if page is already on the node
> -				 * a single-threaded process is running on.
> -				 */
> -				nid = folio_nid(folio);
> -				if (target_node == nid)
> -					continue;
> -				toptier = node_is_toptier(nid);
> -
> -				/*
> -				 * Skip scanning top tier node if normal numa
> -				 * balancing is disabled
> -				 */
> -				if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) &&
> -				    toptier)
> +				if (prot_numa_skip(vma, addr, oldpte, pte,
> +						   target_node))
>  					continue;
> -				if (folio_use_access_time(folio))
> -					folio_xchg_access_time(folio,
> -						jiffies_to_msecs(jiffies));
>  			}
>  
>  			oldpte = ptep_modify_prot_start(vma, addr, pte);