| 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
| ||
|
Message-ID: <753ee7bd-8c9a-4242-a216-98defcd8280f@linux.alibaba.com>
Date: Wed, 17 Dec 2025 15:09:47 +0800
From: Baolin Wang <baolin.wang@...ux.alibaba.com>
To: Dev Jain <dev.jain@....com>, akpm@...ux-foundation.org, david@...nel.org,
catalin.marinas@....com, will@...nel.org
Cc: lorenzo.stoakes@...cle.com, ryan.roberts@....com,
Liam.Howlett@...cle.com, vbabka@...e.cz, rppt@...nel.org, surenb@...gle.com,
mhocko@...e.com, riel@...riel.com, harry.yoo@...cle.com, jannh@...gle.com,
willy@...radead.org, baohua@...nel.org, linux-mm@...ck.org,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 2/3] mm: rmap: support batched checks of the references
for large folios
On 2025/12/17 14:49, Dev Jain wrote:
>
> On 11/12/25 1:46 pm, Baolin Wang wrote:
>> Currently, folio_referenced_one() always checks the young flag for each PTE
>> sequentially, which is inefficient for large folios. This inefficiency is
>> especially noticeable when reclaiming clean file-backed large folios, where
>> folio_referenced() is observed as a significant performance hotspot.
>>
>> Moreover, on Arm architecture, which supports contiguous PTEs, there is already
>> an optimization to clear the young flags for PTEs within a contiguous range.
>> However, this is not sufficient. We can extend this to perform batched operations
>> for the entire large folio (which might exceed the contiguous range: CONT_PTE_SIZE).
>>
>> Introduce a new API: clear_flush_young_ptes() to facilitate batched checking
>> of the young flags and flushing TLB entries, thereby improving performance
>> during large folio reclamation.
>>
>> Performance testing:
>> Allocate 10G clean file-backed folios by mmap() in a memory cgroup, and try to
>> reclaim 8G file-backed folios via the memory.reclaim interface. I can observe
>> 33% performance improvement on my Arm64 32-core server (and 10%+ improvement
>> on my X86 machine). Meanwhile, the hotspot folio_check_references() dropped
>> from approximately 35% to around 5%.
>>
>> W/o patchset:
>> real 0m1.518s
>> user 0m0.000s
>> sys 0m1.518s
>>
>> W/ patchset:
>> real 0m1.018s
>> user 0m0.000s
>> sys 0m1.018s
>>
>> Signed-off-by: Baolin Wang <baolin.wang@...ux.alibaba.com>
>> ---
>> arch/arm64/include/asm/pgtable.h | 11 +++++++++++
>> include/linux/mmu_notifier.h | 9 +++++----
>> include/linux/pgtable.h | 19 +++++++++++++++++++
>> mm/rmap.c | 22 ++++++++++++++++++++--
>> 4 files changed, 55 insertions(+), 6 deletions(-)
>>
>> diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
>> index e03034683156..a865bd8c46a3 100644
>> --- a/arch/arm64/include/asm/pgtable.h
>> +++ b/arch/arm64/include/asm/pgtable.h
>> @@ -1869,6 +1869,17 @@ static inline int ptep_clear_flush_young(struct vm_area_struct *vma,
>> return contpte_clear_flush_young_ptes(vma, addr, ptep, CONT_PTES);
>> }
>>
>> +#define clear_flush_young_ptes clear_flush_young_ptes
>> +static inline int clear_flush_young_ptes(struct vm_area_struct *vma,
>> + unsigned long addr, pte_t *ptep,
>> + unsigned int nr)
>> +{
>> + if (likely(nr == 1))
>> + return __ptep_clear_flush_young(vma, addr, ptep);
>> +
>> + return contpte_clear_flush_young_ptes(vma, addr, ptep, nr);
>> +}
>> +
>> #define wrprotect_ptes wrprotect_ptes
>> static __always_inline void wrprotect_ptes(struct mm_struct *mm,
>> unsigned long addr, pte_t *ptep, unsigned int nr)
>> diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
>> index d1094c2d5fb6..be594b274729 100644
>> --- a/include/linux/mmu_notifier.h
>> +++ b/include/linux/mmu_notifier.h
>> @@ -515,16 +515,17 @@ static inline void mmu_notifier_range_init_owner(
>> range->owner = owner;
>> }
>>
>> -#define ptep_clear_flush_young_notify(__vma, __address, __ptep) \
>> +#define ptep_clear_flush_young_notify(__vma, __address, __ptep, __nr) \
>> ({ \
>> int __young; \
>> struct vm_area_struct *___vma = __vma; \
>> unsigned long ___address = __address; \
>> - __young = ptep_clear_flush_young(___vma, ___address, __ptep); \
>> + unsigned int ___nr = __nr; \
>> + __young = clear_flush_young_ptes(___vma, ___address, __ptep, ___nr); \
>> __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \
>> ___address, \
>> ___address + \
>> - PAGE_SIZE); \
>> + nr * PAGE_SIZE); \
>> __young; \
>> })
>>
>> @@ -650,7 +651,7 @@ static inline void mmu_notifier_subscriptions_destroy(struct mm_struct *mm)
>>
>> #define mmu_notifier_range_update_to_read_only(r) false
>>
>> -#define ptep_clear_flush_young_notify ptep_clear_flush_young
>> +#define ptep_clear_flush_young_notify clear_flush_young_ptes
>> #define pmdp_clear_flush_young_notify pmdp_clear_flush_young
>> #define ptep_clear_young_notify ptep_test_and_clear_young
>> #define pmdp_clear_young_notify pmdp_test_and_clear_young
>> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
>> index b13b6f42be3c..c7d0fd228cb7 100644
>> --- a/include/linux/pgtable.h
>> +++ b/include/linux/pgtable.h
>> @@ -947,6 +947,25 @@ static inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr,
>> }
>> #endif
>>
>> +#ifndef clear_flush_young_ptes
>> +static inline int clear_flush_young_ptes(struct vm_area_struct *vma,
>> + unsigned long addr, pte_t *ptep,
>> + unsigned int nr)
>> +{
>> + int young = 0;
>> +
>> + for (;;) {
>> + young |= ptep_clear_flush_young(vma, addr, ptep);
>> + if (--nr == 0)
>> + break;
>> + ptep++;
>> + addr += PAGE_SIZE;
>> + }
>> +
>> + return young;
>> +}
>> +#endif
>> +
>> /*
>> * On some architectures hardware does not set page access bit when accessing
>> * memory page, it is responsibility of software setting this bit. It brings
>> diff --git a/mm/rmap.c b/mm/rmap.c
>> index d6799afe1114..ec232165c47d 100644
>> --- a/mm/rmap.c
>> +++ b/mm/rmap.c
>> @@ -827,9 +827,11 @@ static bool folio_referenced_one(struct folio *folio,
>> struct folio_referenced_arg *pra = arg;
>> DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0);
>> int ptes = 0, referenced = 0;
>> + unsigned int nr;
>>
>> while (page_vma_mapped_walk(&pvmw)) {
>> address = pvmw.address;
>> + nr = 1;
>>
>> if (vma->vm_flags & VM_LOCKED) {
>> ptes++;
>> @@ -874,9 +876,21 @@ static bool folio_referenced_one(struct folio *folio,
>> if (lru_gen_look_around(&pvmw))
>> referenced++;
>> } else if (pvmw.pte) {
>> + if (folio_test_large(folio)) {
>> + unsigned long end_addr = pmd_addr_end(address, vma->vm_end);
>
> I may be hallucinating here but I am just trying to recall things - is this a bug in
> folio_pte_batch_flags()? A folio may not be naturally aligned in virtual space and hence
> we may cross the PTE table while batching across it, which can be fixed by taking into
> account pmd_addr_end() while computing max_nr.
IMHO, the comments for the folio_pte_batch_flags() function have already
made clear requirements for the caller to avoid such situations:
"
* @ptep must map any page of the folio. max_nr must be at least one and
* must be limited by the caller so scanning cannot exceed a single VMA and
* a single page table.
"
Additionally, Lance recently fixed a similar issue, see commit
ddd05742b45b ("mm/rmap: fix potential out-of-bounds page table access
during batched unmap").
Powered by blists - more mailing lists