linux-kernel - Re: [PATCH v2 2/7] 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: Windows password security audit tool. GUI, reports in PDF.

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

Message-ID: <33e8d9fe-d30a-4cbb-b141-133b8989019e@arm.com>
Date: Tue, 29 Apr 2025 14:29:13 +0530
From: Dev Jain <dev.jain@....com>
To: Anshuman Khandual <anshuman.khandual@....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 2/7] mm: Optimize mprotect() by batch-skipping PTEs



On 29/04/25 12:44 pm, Anshuman Khandual wrote:
> On 4/29/25 10:53, Dev Jain wrote:
>> 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 | 27 ++++++++++++++++++++-------
>>   1 file changed, 20 insertions(+), 7 deletions(-)
>>
>> diff --git a/mm/mprotect.c b/mm/mprotect.c
>> index 70f59aa8c2a8..ec5d17af7650 100644
>> --- a/mm/mprotect.c
>> +++ b/mm/mprotect.c
>> @@ -91,6 +91,9 @@ static bool prot_numa_skip(struct vm_area_struct *vma, struct folio *folio,
>>   	bool toptier;
>>   	int nid;
>>   
>> +	if (folio_is_zone_device(folio) || folio_test_ksm(folio))
>> +		return true;
>> +
> 
> Moving these here from prot_numa_avoid_fault() could have been done
> earlier, while adding prot_numa_skip() itself in the previous patch
> (in case this helper is determined to be really required).

True. I'll do that.

> 
>>   	/* Also skip shared copy-on-write pages */
>>   	if (is_cow_mapping(vma->vm_flags) &&
>>   	    (folio_maybe_dma_pinned(folio) ||
>> @@ -126,8 +129,10 @@ static bool prot_numa_skip(struct vm_area_struct *vma, struct folio *folio,
>>   }
>>   
>>   static bool prot_numa_avoid_fault(struct vm_area_struct *vma,
>> -		unsigned long addr, pte_t oldpte, int target_node)
>> +		unsigned long addr, pte_t *pte, pte_t oldpte, int target_node,
>> +		int max_nr, int *nr)
>>   {
>> +	const fpb_t flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY;
> 
> Flags are all correct.
> 
>>   	struct folio *folio;
>>   	int ret;
>>   
>> @@ -136,12 +141,16 @@ static bool prot_numa_avoid_fault(struct vm_area_struct *vma,
>>   		return true;
>>   
>>   	folio = vm_normal_folio(vma, addr, oldpte);
>> -	if (!folio || folio_is_zone_device(folio) ||
>> -	    folio_test_ksm(folio))
>> +	if (!folio)
>>   		return true;
>> +
>>   	ret = prot_numa_skip(vma, folio, target_node);
>> -	if (ret)
>> +	if (ret) {
>> +		if (folio_test_large(folio) && max_nr != 1)
> 
> Conditional checks are all correct.
> 
>> +			*nr = folio_pte_batch(folio, addr, pte, oldpte,
>> +					      max_nr, flags, NULL, NULL, NULL);
>>   		return ret;
>> +	}
>>   	if (folio_use_access_time(folio))
>>   		folio_xchg_access_time(folio,
>>   			jiffies_to_msecs(jiffies));
>> @@ -159,6 +168,7 @@ 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;
>>   
>>   	tlb_change_page_size(tlb, PAGE_SIZE);
>>   	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
>> @@ -173,8 +183,10 @@ static long change_pte_range(struct mmu_gather *tlb,
>>   	flush_tlb_batched_pending(vma->vm_mm);
>>   	arch_enter_lazy_mmu_mode();
>>   	do {
>> +		nr = 1;
> 
> 'nr' resets each iteration.
> 
>>   		oldpte = ptep_get(pte);
>>   		if (pte_present(oldpte)) {
>> +			int max_nr = (end - addr) >> PAGE_SHIFT;
> 
> Small nit - 'max_nr' declaration could be moved earlier along with 'nr'.

Sure.

> 
>>   			pte_t ptent;
>>   
>>   			/*
>> @@ -182,8 +194,9 @@ static long change_pte_range(struct mmu_gather *tlb,
>>   			 * pages. See similar comment in change_huge_pmd.
>>   			 */
>>   			if (prot_numa &&
>> -			    prot_numa_avoid_fault(vma, addr,
>> -						  oldpte, target_node))
>> +			    prot_numa_avoid_fault(vma, addr, pte,
>> +						  oldpte, target_node,
>> +							  max_nr, &nr))
>>   					continue;
>>   
>>   			oldpte = ptep_modify_prot_start(vma, addr, pte);
>> @@ -300,7 +313,7 @@ static long change_pte_range(struct mmu_gather *tlb,
>>   				pages++;
>>   			}
>>   		}
>> -	} while (pte++, addr += PAGE_SIZE, addr != end);
>> +	} while (pte += nr, addr += nr * PAGE_SIZE, addr != end);
>>   	arch_leave_lazy_mmu_mode();
>>   	pte_unmap_unlock(pte - 1, ptl);
>>   
> 
> Otherwise LGTM