From nobody Tue Dec 2 01:05:42 2025 Received: from out30-97.freemail.mail.aliyun.com (out30-97.freemail.mail.aliyun.com [115.124.30.97]) (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 1715E1EB5FD for ; Tue, 25 Nov 2025 00:57:08 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.97 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1764032231; cv=none; b=VOU1f52zODcBBbF4BCDihft8a7XiTCNlT0gYHGzw79PxIe4mmlGYAPYuK+Hd7JdWCKKUQQ652LjeSKUnUCjyT0XcBVdffF7CelgXK6Hu9vqE65iV8dKRThDMbuWb1sqxF236IvK/OOOPs+BnQq2j7kXrfjxobljEZw/BUaPwSD4= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1764032231; c=relaxed/simple; bh=HhZ/mm7RhM5IXzy10VA6jzwSOJRfN9g+3VLUyg6Zps4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Ll9CZrPUVCi7vTV2rmRE698rYPNB7sXDJvIpyyWOLEpAW0kjmHoFIc7I8NXJrsXjNe2BPbK4PdADRwxXXcpeC8E6qSjFPXf7/fhZzsZ3iJvUoqWT6sQbK8uvYdZFRGucqZLkTbfvA73yXoZHXwA6+K4ooPTpbUUpkzEU3jbOlIo= 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=egCjUtvq; arc=none smtp.client-ip=115.124.30.97 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="egCjUtvq" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1764032221; h=From:To:Subject:Date:Message-ID:MIME-Version; bh=/ea6etQCpReM0Dd5R3qfwP463Goog5MVH76oxL1v2kk=; b=egCjUtvqAvX9qvvEpsZTTuumyfx+fx/5gdtMtb9hbiqUvp63Z73BlnmVem06JngLYlBofR19l80RjzZiQC/ISVR7SERlXWbBjlm8AnqaApDo2q4W4uvT/MchIPyR+fvP2dbdITprjYGRPNmMspzZBILOSUNOkLHdruYLECl89uw= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WtL1wub_1764032219 cluster:ay36) by smtp.aliyun-inc.com; Tue, 25 Nov 2025 08:56:59 +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 1/2] arm64: mm: support batch clearing of the young flag for large folios Date: Tue, 25 Nov 2025 08:56:50 +0800 Message-ID: <1d71cf419726188dfc41c292dfac066be5cb1e33.1763976541.git.baolin.wang@linux.alibaba.com> 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, contpte_ptep_test_and_clear_young() and contpte_ptep_clear_flush= _young() only clear the young flag and flush TLBs for PTEs within the contiguous ran= ge. To support batch PTE operations for other sized large folios in the followi= ng patches, adding a new parameter to specify the number of PTEs. While we are at it, rename the functions to maintain consistency with other contpte_*() functions. Signed-off-by: Baolin Wang --- arch/arm64/include/asm/pgtable.h | 12 ++++----- arch/arm64/mm/contpte.c | 44 ++++++++++++++++++++++---------- 2 files changed, 37 insertions(+), 19 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgta= ble.h index 0944e296dd4a..e03034683156 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1679,10 +1679,10 @@ extern void contpte_clear_full_ptes(struct mm_struc= t *mm, unsigned long addr, extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); -extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); -extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep); +extern int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr); +extern int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr); extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long add= r, pte_t *ptep, unsigned int nr); extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, @@ -1854,7 +1854,7 @@ static inline int ptep_test_and_clear_young(struct vm= _area_struct *vma, if (likely(!pte_valid_cont(orig_pte))) return __ptep_test_and_clear_young(vma, addr, ptep); =20 - return contpte_ptep_test_and_clear_young(vma, addr, ptep); + return contpte_test_and_clear_young_ptes(vma, addr, ptep, CONT_PTES); } =20 #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH @@ -1866,7 +1866,7 @@ static inline int ptep_clear_flush_young(struct vm_ar= ea_struct *vma, if (likely(!pte_valid_cont(orig_pte))) return __ptep_clear_flush_young(vma, addr, ptep); =20 - return contpte_ptep_clear_flush_young(vma, addr, ptep); + return contpte_clear_flush_young_ptes(vma, addr, ptep, CONT_PTES); } =20 #define wrprotect_ptes wrprotect_ptes diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index c0557945939c..19b122441be3 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -488,8 +488,9 @@ pte_t contpte_get_and_clear_full_ptes(struct mm_struct = *mm, } EXPORT_SYMBOL_GPL(contpte_get_and_clear_full_ptes); =20 -int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr) { /* * ptep_clear_flush_young() technically requires us to clear the access @@ -500,39 +501,56 @@ int contpte_ptep_test_and_clear_young(struct vm_area_= struct *vma, * having to unfold. */ =20 + unsigned long start =3D addr; + unsigned long end =3D start + nr * PAGE_SIZE; int young =3D 0; int i; =20 - ptep =3D contpte_align_down(ptep); - addr =3D ALIGN_DOWN(addr, CONT_PTE_SIZE); + if (pte_cont(__ptep_get(ptep + nr - 1))) + end =3D ALIGN(end, CONT_PTE_SIZE); =20 - for (i =3D 0; i < CONT_PTES; i++, ptep++, addr +=3D PAGE_SIZE) - young |=3D __ptep_test_and_clear_young(vma, addr, ptep); + if (pte_cont(__ptep_get(ptep))) { + start =3D ALIGN_DOWN(start, CONT_PTE_SIZE); + ptep =3D contpte_align_down(ptep); + } + + nr =3D (end - start) / PAGE_SIZE; + for (i =3D 0; i < nr; i++, ptep++, start +=3D PAGE_SIZE) + young |=3D __ptep_test_and_clear_young(vma, start, ptep); =20 return young; } -EXPORT_SYMBOL_GPL(contpte_ptep_test_and_clear_young); +EXPORT_SYMBOL_GPL(contpte_test_and_clear_young_ptes); =20 -int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) +int contpte_clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr) { int young; =20 - young =3D contpte_ptep_test_and_clear_young(vma, addr, ptep); + young =3D contpte_test_and_clear_young_ptes(vma, addr, ptep, nr); =20 if (young) { + unsigned long start =3D addr; + unsigned long end =3D start + nr * PAGE_SIZE; + + if (pte_cont(__ptep_get(ptep + nr - 1))) + end =3D ALIGN(end, CONT_PTE_SIZE); + + if (pte_cont(__ptep_get(ptep))) + start =3D ALIGN_DOWN(start, CONT_PTE_SIZE); + /* * See comment in __ptep_clear_flush_young(); same rationale for * eliding the trailing DSB applies here. */ - addr =3D ALIGN_DOWN(addr, CONT_PTE_SIZE); - __flush_tlb_range_nosync(vma->vm_mm, addr, addr + CONT_PTE_SIZE, + __flush_tlb_range_nosync(vma->vm_mm, start, end, PAGE_SIZE, true, 3); } =20 return young; } -EXPORT_SYMBOL_GPL(contpte_ptep_clear_flush_young); +EXPORT_SYMBOL_GPL(contpte_clear_flush_young_ptes); =20 void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) --=20 2.47.3