linux-kernel - Re: [PATCH v2 1/7] mm: Refactor code in mprotect

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: <43dc2d0b-1ce9-4d56-a260-d1dfc4545c99@arm.com>
Date: Tue, 29 Apr 2025 12:11:30 +0530
From: Anshuman Khandual <anshuman.khandual@....com>
To: Dev Jain <dev.jain@....com>, akpm@...ux-foundation.org
Cc: ryan.roberts@....com, 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, 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,
 namit@...are.com, hughd@...gle.com, yang@...amperecomputing.com,
 ziy@...dia.com
Subject: Re: [PATCH v2 1/7] mm: Refactor code in mprotect



On 4/29/25 10:53, Dev Jain wrote:
> Reduce indentation in change_pte_range() by refactoring some of the code
> into a new function. No functional change.
> 
> Signed-off-by: Dev Jain <dev.jain@....com>
> ---
>  mm/mprotect.c | 116 +++++++++++++++++++++++++++++---------------------
>  1 file changed, 68 insertions(+), 48 deletions(-)
> 
> diff --git a/mm/mprotect.c b/mm/mprotect.c
> index 88608d0dc2c2..70f59aa8c2a8 100644
> --- a/mm/mprotect.c
> +++ b/mm/mprotect.c
> @@ -83,6 +83,71 @@ 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, struct folio *folio,
> +		int target_node)
> +{
> +	bool toptier;
> +	int nid;
> +
> +	/* 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;
> +	return false;
> +}
> +
> +static bool prot_numa_avoid_fault(struct vm_area_struct *vma,
> +		unsigned long addr, pte_t oldpte, int target_node)
> +{
> +	struct folio *folio;
> +	int ret;
> +
> +	/* Avoid TLB flush if possible */
> +	if (pte_protnone(oldpte))
> +		return true;
> +
> +	folio = vm_normal_folio(vma, addr, oldpte);
> +	if (!folio || folio_is_zone_device(folio) ||
> +	    folio_test_ksm(folio))
> +		return true;
> +	ret = prot_numa_skip(vma, folio, target_node);

What purpose does it solve to create additional helper prot_numa_skip().
IOW - why cannot all of these be inside prot_numa_avoid_fault() itself.

> +	if (ret)
> +		return ret;
> +	if (folio_use_access_time(folio))
> +		folio_xchg_access_time(folio,
> +			jiffies_to_msecs(jiffies));
> +	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)
> @@ -116,56 +181,11 @@ static long change_pte_range(struct mmu_gather *tlb,
>  			 * Avoid trapping faults against the zero or KSM
>  			 * 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))
> +			if (prot_numa &&
> +			    prot_numa_avoid_fault(vma, addr,
> +						  oldpte, target_node))
>  					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)
> -					continue;
> -				if (folio_use_access_time(folio))
> -					folio_xchg_access_time(folio,
> -						jiffies_to_msecs(jiffies));
> -			}
> -
>  			oldpte = ptep_modify_prot_start(vma, addr, pte);
>  			ptent = pte_modify(oldpte, newprot);
>