From nobody Tue Dec 2 01:05:43 2025 Received: from out30-131.freemail.mail.aliyun.com (out30-131.freemail.mail.aliyun.com [115.124.30.131]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 0355520458A for ; Tue, 25 Nov 2025 00:57:10 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.131 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1764032233; cv=none; b=KoSe42Uis00IbUpoMg1Q5UsgRy0AVWg4RJ3DJHAcMvcP5K1wCE40vat7MtvcRklrgrESMyNCpuDTtE7zTdXEKCjbHh0zFiC8hYfBn0riCBycdeoj91Km/2aXPgT8gF0wvvKyqToQhbirHbb6mWutVxLpzuam+mLqh2vvpjcptR8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1764032233; c=relaxed/simple; bh=3lkazJCDp6HrfJoMu/11N1eQ3CzqGGvLY4xLRZ4FzDc=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=NUTaKddcDiiidEvZrDOlusHvNpUtSUp1jDf+cw6jWFPBM8Y3j5BNxtx5EVz+9cjw3dMVjvLVn9P5bMZHUV/mYeZ9+EuBIr4/btJ7AJCnka3ouG4C8w1P3ZT2SIt4sygNBmJrnkoFMLm6Xkezix6cYtsa+IZrh+/WH/R8mX1cgfI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=F6yqIj/R; arc=none smtp.client-ip=115.124.30.131 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="F6yqIj/R" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1764032223; h=From:To:Subject:Date:Message-ID:MIME-Version; bh=OXtn3K8Eq0WVSir81qSgpoCSJ7ob/sT7KbPkVXVRj10=; b=F6yqIj/RKVxnEkl2m3Y/jK275JW3UBDFcYefKofnBVR031KEiqdkNaZVtiawkMbnQMeHcye+feidJ4Ks+jcz68LeZ0lQIgC7N8onJH5bzDXa+zvTCdEJ6i1t8O+uM+k6NRIcgj/naoawJjrZREo14CDvUve5F14DUo+W7iorxS4= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WtL74.V_1764032220 cluster:ay36) by smtp.aliyun-inc.com; Tue, 25 Nov 2025 08:57:01 +0800 From: Baolin Wang To: akpm@linux-foundation.org, david@kernel.org, catalin.marinas@arm.com, will@kernel.org Cc: lorenzo.stoakes@oracle.com, ryan.roberts@arm.com, Liam.Howlett@oracle.com, vbabka@suse.cz, rppt@kernel.org, surenb@google.com, mhocko@suse.com, riel@surriel.com, harry.yoo@oracle.com, jannh@google.com, willy@infradead.org, baohua@kernel.org, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH 2/2] mm: rmap: support batched checks of the references for large folios Date: Tue, 25 Nov 2025 08:56:51 +0800 Message-ID: X-Mailer: git-send-email 2.43.7 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" 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 alr= eady 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 oper= ations for the entire large folio (which might exceed the contiguous range: CONT_P= TE_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 obser= ve 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 --- 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/pgta= ble.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_a= rea_struct *vma, return contpte_clear_flush_young_ptes(vma, addr, ptep, CONT_PTES); } =20 +#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 =3D=3D 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 =3D owner; } =20 -#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 =3D __vma; \ unsigned long ___address =3D __address; \ - __young =3D ptep_clear_flush_young(___vma, ___address, __ptep); \ + unsigned int ___nr =3D __nr; \ + __young =3D clear_flush_young_ptes(___vma, ___address, __ptep, ___nr); \ __young |=3D mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ - PAGE_SIZE); \ + nr * PAGE_SIZE); \ __young; \ }) =20 @@ -650,7 +651,7 @@ static inline void mmu_notifier_subscriptions_destroy(s= truct mm_struct *mm) =20 #define mmu_notifier_range_update_to_read_only(r) false =20 -#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 =20 +#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 =3D 0; + + for (;;) { + young |=3D ptep_clear_flush_young(vma, addr, ptep); + if (--nr =3D=3D 0) + break; + ptep++; + addr +=3D PAGE_SIZE; + } + + return young; +} +#endif + /* * On some architectures hardware does not set page access bit when access= ing * memory page, it is responsibility of software setting this bit. It brin= gs diff --git a/mm/rmap.c b/mm/rmap.c index f955f02d570e..3833b8557a6f 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 =3D arg; DEFINE_FOLIO_VMA_WALK(pvmw, folio, vma, address, 0); int ptes =3D 0, referenced =3D 0; + unsigned int nr; =20 while (page_vma_mapped_walk(&pvmw)) { address =3D pvmw.address; + nr =3D 1; =20 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 =3D pmd_addr_end(address, vma->vm_end); + unsigned int max_nr =3D (end_addr - address) >> PAGE_SHIFT; + pte_t pteval =3D ptep_get(pvmw.pte); + + nr =3D folio_pte_batch(folio, pvmw.pte, pteval, max_nr); + } + + ptes +=3D nr; if (ptep_clear_flush_young_notify(vma, address, - pvmw.pte)) + pvmw.pte, nr)) referenced++; + /* Skip the batched PTEs */ + pvmw.pte +=3D nr - 1; + pvmw.address +=3D (nr - 1) * PAGE_SIZE; } else if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) { if (pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) @@ -886,7 +900,11 @@ static bool folio_referenced_one(struct folio *folio, WARN_ON_ONCE(1); } =20 - pra->mapcount--; + pra->mapcount -=3D nr; + if (ptes =3D=3D pvmw.nr_pages) { + page_vma_mapped_walk_done(&pvmw); + break; + } } =20 if (referenced) --=20 2.47.3