From nobody Sat Feb 7 21:53:15 2026 Received: from out30-111.freemail.mail.aliyun.com (out30-111.freemail.mail.aliyun.com [115.124.30.111]) (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 E508D25393E for ; Tue, 23 Dec 2025 05:54:08 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.111 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766469254; cv=none; b=rcgj7LQhhZ12JgqiC1CKQabB5CogRNuhYrQHp+AQWw6Y8oUOIpD0l08vEfy9WCuO+Qj6cT/JUgV6sc79ffQ/+i1WmhH1/baPre85wC4sJgEjEi2DjBkJZ0oO5MRkW68ALp7VFN03E7FUaEen+D2DbDMeh16eX4YD2R+GiLOeTqs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766469254; c=relaxed/simple; bh=mPyX/3tsCchvnKZZmrzfwqNAy3u7q97O4neROMVe1a0=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=hH+oLJIco1taSpc4jJlcPQ1G39t4pb0g9wP35Vonb8YRqVTJKkz5mouYYn3R6PEVn7Saw3p/2Ihjy6j0VGRWD0uACArNQQMfZWBCU0vepCAC9cJ+s2Rg4iNYqq+mMrdrtIdJY0EMpc9S/DXxxPhEwAgpfP0e3oTWa2jJurCaxx4= 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=d1TRrJC6; arc=none smtp.client-ip=115.124.30.111 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="d1TRrJC6" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1766469245; h=From:To:Subject:Date:Message-ID:MIME-Version; bh=MSFx6Rnw8Uesz11I46fNYvPpzwOjE58x5E7aQ6mIcqg=; b=d1TRrJC61E5OYsw/mYuv3jyK6x1CIxVikRNGSDB2IT7+3YlV08Sr9kGUZGGGyIAPTX2cHcuua3r/R0f19w9vJeW19buwN718fytQdCRB83sM95SafS8k0Y07zL2jL7We4bWKJNelJ8wupQMmC5zsJTPYEOLJbPDIKVWPxJV3uBw= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WvWSzFR_1766468925 cluster:ay36) by smtp.aliyun-inc.com; Tue, 23 Dec 2025 13:48:45 +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, dev.jain@arm.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH v4 1/5] mm: rmap: support batched checks of the references for large folios Date: Tue, 23 Dec 2025 13:48:35 +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 Arm64 architecture, which supports contiguous PTEs, there is a= lready 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. And it will be overridden by the architectu= re that implements a more efficient batch operation in the following patches. Signed-off-by: Baolin Wang Reviewed-by: Ryan Roberts --- include/linux/mmu_notifier.h | 9 +++++---- include/linux/pgtable.h | 35 +++++++++++++++++++++++++++++++++++ mm/rmap.c | 29 +++++++++++++++++++++++++++-- 3 files changed, 67 insertions(+), 6 deletions(-) diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index d1094c2d5fb6..dbbdcef4abf1 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 2f0dd3a4ace1..fcf7a7820061 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1087,6 +1087,41 @@ static inline void wrprotect_ptes(struct mm_struct *= mm, unsigned long addr, } #endif =20 +#ifndef clear_flush_young_ptes +/** + * clear_flush_young_ptes - Clear the access bit and perform a TLB flush f= or PTEs + * that map consecutive pages of the same folio. + * @vma: The virtual memory area the pages are mapped into. + * @addr: Address the first page is mapped at. + * @ptep: Page table pointer for the first entry. + * @nr: Number of entries to clear access bit. + * + * May be overridden by the architecture; otherwise, implemented as a simp= le + * loop over ptep_clear_flush_young(). + * + * Note that PTE bits in the PTE range besides the PFN can differ. For exa= mple, + * some PTEs might be write-protected. + * + * Context: The caller holds the page table lock. The PTEs map consecutive + * pages that belong to the same folio. The PTEs are all in the same PMD. + */ +static inline int clear_flush_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, + unsigned int nr) +{ + int young; + + young =3D ptep_clear_flush_young(vma, addr, ptep); + while (--nr) { + ptep++; + addr +=3D PAGE_SIZE; + young |=3D ptep_clear_flush_young(vma, addr, ptep); + } + + 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 d6799afe1114..a0fc05f5966f 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 +876,24 @@ 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 +903,15 @@ static bool folio_referenced_one(struct folio *folio, WARN_ON_ONCE(1); } =20 - pra->mapcount--; + pra->mapcount -=3D nr; + /* + * If we are sure that we batched the entire folio, + * we can just optimize and stop right here. + */ + if (ptes =3D=3D pvmw.nr_pages) { + page_vma_mapped_walk_done(&pvmw); + break; + } } =20 if (referenced) --=20 2.47.3 From nobody Sat Feb 7 21:53:15 2026 Received: from out30-98.freemail.mail.aliyun.com (out30-98.freemail.mail.aliyun.com [115.124.30.98]) (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 7EC9917A303 for ; Tue, 23 Dec 2025 05:48:50 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.98 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766468935; cv=none; b=shAaBRdDR9zqg3MavA0uiAWhcqza1gfgP8CB6mf0qik9T0TPjwZNzfL9sJnF/dwLAPoPUuOyB30HCqglJdDYuLN92E8umViAO94YWA5LhqYXP4PcM/PANgRUeKiR41XPH2LrqCamerSzh/vv5nmx/FdTVI1AC30NIT8VDd1+waA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766468935; c=relaxed/simple; bh=NKI5nbUjfI6CU3Y3XlRYxpndvWz8/a7qjNELYOTUh/k=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=eZHglitu2zfkiymIK/RK+KrSCaSGKgszF3dD/4G02GrcjBCf3kkIr9CB+U+lh0fbFIYF8EHA1EqKebEUrDhTZ55d91FrH4wXsuyjYjDFBSRiVlmx5BlGEEYN3QMZb1XAkUpmEHCWI5BOnKBeRWhshT+GCyW7IwoEY3Mo8W/TvME= 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=lccI3o52; arc=none smtp.client-ip=115.124.30.98 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="lccI3o52" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1766468929; h=From:To:Subject:Date:Message-ID:MIME-Version; bh=+a78DMtklkrNbj5wKq84JjELX4bL639or56rrqyDL8M=; b=lccI3o52wq33fTkG6PUxq+hAgd5UzvDf6wJxQy6PMOK+O7RchlrQNVMUGnZFMEpyK/PKoA5Uxv2bwiaxuuLFaVo0kH1gY4D/USksoLiah5Yn5aeoMep+ZGTJsA9w34MNFegvzfj7Pfg9Mt4kRy8lp7PAQXvHV/oeU1kMa8UIhr0= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WvWWGsJ_1766468926 cluster:ay36) by smtp.aliyun-inc.com; Tue, 23 Dec 2025 13:48:47 +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, dev.jain@arm.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH v4 2/5] arm64: mm: factor out the address and ptep alignment into a new helper Date: Tue, 23 Dec 2025 13:48:36 +0800 Message-ID: <47e29030347c23ffce238ff5ed752da01a8cc7cb.1766455378.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" Factor out the contpte block's address and ptep alignment into a new helper, and will be reused in the following patch. No functional changes. Signed-off-by: Baolin Wang Reviewed-by: Ryan Roberts --- arch/arm64/mm/contpte.c | 29 +++++++++++++++++++++-------- 1 file changed, 21 insertions(+), 8 deletions(-) diff --git a/arch/arm64/mm/contpte.c b/arch/arm64/mm/contpte.c index 589bcf878938..e4ddeb46f25d 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -26,6 +26,26 @@ static inline pte_t *contpte_align_down(pte_t *ptep) return PTR_ALIGN_DOWN(ptep, sizeof(*ptep) * CONT_PTES); } =20 +static inline pte_t *contpte_align_addr_ptep(unsigned long *start, + unsigned long *end, pte_t *ptep, + unsigned int nr) +{ + /* + * Note: caller must ensure these nr PTEs are consecutive (present) + * PTEs that map consecutive pages of the same large folio within a + * single VMA and a single page table. + */ + 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); + ptep =3D contpte_align_down(ptep); + } + + return ptep; +} + static void contpte_try_unfold_partial(struct mm_struct *mm, unsigned long= addr, pte_t *ptep, unsigned int nr) { @@ -569,14 +589,7 @@ void contpte_clear_young_dirty_ptes(struct vm_area_str= uct *vma, unsigned long start =3D addr; unsigned long end =3D start + nr * PAGE_SIZE; =20 - 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); - ptep =3D contpte_align_down(ptep); - } - + ptep =3D contpte_align_addr_ptep(&start, &end, ptep, nr); __clear_young_dirty_ptes(vma, start, ptep, (end - start) / PAGE_SIZE, fla= gs); } EXPORT_SYMBOL_GPL(contpte_clear_young_dirty_ptes); --=20 2.47.3 From nobody Sat Feb 7 21:53:15 2026 Received: from out30-130.freemail.mail.aliyun.com (out30-130.freemail.mail.aliyun.com [115.124.30.130]) (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 A77E71B4224 for ; Tue, 23 Dec 2025 05:48:53 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.130 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766468936; cv=none; b=Aieo/khov/d6XCSU/k6FKUcfpEG3FTuBxj8wtpXsasLrWV0HHTMvd/e5cGXeKkvcYAbf8ruGDmeKJxe4mq+XN8YDiBO29TcwafIs4J5Win38i0d7/V7fK1rlR3jIaKnWR26F10stPjvjOxgZ46EVNvhtWdkZ3378swxfVZ4WZkA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766468936; c=relaxed/simple; bh=T4s4m7kt7+FDiwhMnoDtbxoTISmDi2O7+9xrnZ60lno=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=jnJVGgFYYsjORuPDf5hP7KVA0QnNID7E93jZtXsrP974PgiGEY2QS/LrTq3lDJC7K//hE/wMUiWDkvTEoQIcI1jDdasyyuNw3S4rCuJoxebetxhe2flfFX260ldvMEUoinIuDlL+gPxiHGKej/P+ChMZT6pJIJCSiuderb4Y6pE= 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=Pu1TNOyD; arc=none smtp.client-ip=115.124.30.130 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="Pu1TNOyD" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1766468931; h=From:To:Subject:Date:Message-ID:MIME-Version; bh=S3h6H4IPo9TPa4nxGBVzDP5j8B0g+opv6hYHBB9XsBo=; b=Pu1TNOyDD9e2Zl6krMQ92UKW2sOuZ/XA511FoZHgyvl82eQtUnR97IU/jJ+jL7vhp5HmcwvGe8wvuDw9d9cZT7/osJ6ouFq8SkX1jsRZkjJgy1LO8hEwWyWsvRd85/TubYPtwpxGnBsH+4GzgxHUAOse0wSoAZMR37T/bE90dEI= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WvWWGtH_1766468928 cluster:ay36) by smtp.aliyun-inc.com; Tue, 23 Dec 2025 13:48:49 +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, dev.jain@arm.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH v4 3/5] arm64: mm: support batch clearing of the young flag for large folios Date: Tue, 23 Dec 2025 13:48:37 +0800 Message-ID: <3b427d9010a6d52f2b91342760f12be097d21cf6.1766455378.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 that map cons= ecutive pages of the same large folio in a single VMA and a single page table. 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 | 33 ++++++++++++++++++-------------- 2 files changed, 25 insertions(+), 20 deletions(-) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgta= ble.h index 445e18e92221..d5fbe72e820a 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1648,10 +1648,10 @@ 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); +int contpte_test_and_clear_young_ptes(struct vm_area_struct *vma, + unsigned long addr, pte_t *ptep, unsigned int nr); +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, @@ -1823,7 +1823,7 @@ 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 @@ -1835,7 +1835,7 @@ 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 e4ddeb46f25d..b929a455103f 100644 --- a/arch/arm64/mm/contpte.c +++ b/arch/arm64/mm/contpte.c @@ -508,8 +508,9 @@ 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 @@ -518,41 +519,45 @@ int contpte_ptep_test_and_clear_young(struct vm_area_= struct *vma, * contig range when the range is covered by a single folio, we can get * away with clearing young for the whole contig range here, so we avoid * having to unfold. + * + * The 'nr' means consecutive (present) PTEs that map consecutive pages + * of the same large folio in a single VMA and a single page table. */ =20 + unsigned long end =3D addr + nr * PAGE_SIZE; int young =3D 0; - int i; =20 - ptep =3D contpte_align_down(ptep); - addr =3D ALIGN_DOWN(addr, CONT_PTE_SIZE); - - for (i =3D 0; i < CONT_PTES; i++, ptep++, addr +=3D PAGE_SIZE) + ptep =3D contpte_align_addr_ptep(&addr, &end, ptep, nr); + for (; addr !=3D end; ptep++, addr +=3D PAGE_SIZE) young |=3D __ptep_test_and_clear_young(vma, addr, 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 end =3D addr + nr * PAGE_SIZE; + + contpte_align_addr_ptep(&addr, &end, ptep, nr); /* * 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, addr, 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 From nobody Sat Feb 7 21:53:15 2026 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 EC40B2F6925 for ; Tue, 23 Dec 2025 05:48:59 +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=1766468942; cv=none; b=odvr24WdA/ixH+zcDL9n6jnW1bG2l3ZIbpHP11hkOdIU+VyUUoE/6lKvfhsGWYpmF1XXR+YPmrvXspkW4DeEsY0egnpBGL8myi3tKYmQ4uaEHyuYOtl4GXkuNyNW02Pm2y/BXmJibkS2FO4lb/AB8UGDZk9bYDYYrJr3r0rrjY8= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766468942; c=relaxed/simple; bh=AbpNJ53XiNQB+ihBMnJB1YHaPI4D8/93a/l9IvJQhA4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=DYHGPRwR0TkZNNUB9uXusS+gGqfKz82wO00m0dtD3WdbvV0AukrINk1dpdoh01XWdhZ+U9gSLT9GMuDJ6658YpC3LZoi0PEqVl70U0g6D87P9MWlzM0ExuYYapX2aJoeNZT8v9F+LnmcasCHm0YCrJpiB2DLsdDjz+5+YUKeUPo= 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=fs9aGpkC; 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="fs9aGpkC" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1766468932; h=From:To:Subject:Date:Message-ID:MIME-Version; bh=PtUq0ncq36I/75r0SFbFKqq7ZzUUx0G3Kvd2RjStNxc=; b=fs9aGpkCNiPUE/ARJ2RUEyvJpl4LC+hgxSZ7OMFxVLYU9mgcQN3DSImnaRwK+18jqNRofMcxyybIpNekJSpK8P55Bc3pN8DvWV0fyyfFheb/aIxZSZ5heIqnY2/dwnXchFiLUWV0pLs6WWT4paDzxdFjEeEAC9YRXIoqbZ9KAW4= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WvWaJjs_1766468930 cluster:ay36) by smtp.aliyun-inc.com; Tue, 23 Dec 2025 13:48:50 +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, dev.jain@arm.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH v4 4/5] arm64: mm: implement the architecture-specific clear_flush_young_ptes() Date: Tue, 23 Dec 2025 13:48:38 +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" Implement the Arm64 architecture-specific clear_flush_young_ptes() to enable batched checking of young flags and TLB flushing, improving performance dur= ing 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 Reviewed-by: Ryan Roberts --- arch/arm64/include/asm/pgtable.h | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgta= ble.h index d5fbe72e820a..84a6bdabb1f9 100644 --- a/arch/arm64/include/asm/pgtable.h +++ b/arch/arm64/include/asm/pgtable.h @@ -1838,6 +1838,17 @@ 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 && !pte_cont(__ptep_get(ptep)))) + 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) --=20 2.47.3 From nobody Sat Feb 7 21:53:15 2026 Received: from out30-112.freemail.mail.aliyun.com (out30-112.freemail.mail.aliyun.com [115.124.30.112]) (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 945132BE05B for ; Tue, 23 Dec 2025 05:49:02 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.112 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766468944; cv=none; b=iSDVOm78PIMz1UQqAw7lGDo86kQVrELsLl0p7g0z9zqx/WE6aoCD5nSZddmeJje9VEkwAoXDpnUfNgdG8B4SvKzyIvNsR5gr56+pr8fMmm+JTXMPZhUNF08eLJ0UnADUnczs9ryyE31A/h5n8gibf7Ew1LSHh+CSt3vDCcbRB2Q= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1766468944; c=relaxed/simple; bh=VXh/o28OXwT6EP2TyzG92ME41my07jcdRQ29RZ/in6Q=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=JM3iXSnkEul7u5ALepYIKF3g7voZP7tAJATj0S5Lj2ZBwpDf0twKsW1vN9/9Y6k0idfFHZvEf4pOrfepvNHFKAh3Ng4M7prjVX05NxFclARPyYS2rDocbzJRDvKKqD+297dAkVE44Kdi4u4dqT2UWzokDHons2JKWMiSslt+bgY= 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=F6QcNR32; arc=none smtp.client-ip=115.124.30.112 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="F6QcNR32" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1766468934; h=From:To:Subject:Date:Message-ID:MIME-Version; bh=L8grYI0Jwq9L4Vxa84m+Wpr8ZQOY0j4j8t2HLaHt6zk=; b=F6QcNR32scZ94ZZB2nGdeXuxBO+ySRbl13YTyXMsYXXolVcT+fcT1Mh0Jk1YFCroP4eBvWK/OXJH/nceM62vL/mbGXRZD0PznJFpcnrTQJ+hBDNmlzxirIu62lFd+3mjaWyQjnpIVjs4tcwOtEFVoKk+vAuG7JGOdhwFHvBe6pI= Received: from localhost(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0WvWSzHD_1766468931 cluster:ay36) by smtp.aliyun-inc.com; Tue, 23 Dec 2025 13:48:52 +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, dev.jain@arm.com, baolin.wang@linux.alibaba.com, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org Subject: [PATCH v4 5/5] mm: rmap: support batched unmapping for file large folios Date: Tue, 23 Dec 2025 13:48:39 +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" Similar to folio_referenced_one(), we can apply batched unmapping for file large folios to optimize the performance of file folios reclamation. Barry previously implemented batched unmapping for lazyfree anonymous large folios[1] and did not further optimize anonymous large folios or file-backed large folios at that stage. As for file-backed large folios, the batched unmapping support is relatively straightforward, as we only need to clear the consecutive (present) PTE entries for file-backed large folios. 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 75% performance improvement on my Arm64 32-core server (and 50%+ improvement on my X86 machine) with this patch. W/o patch: real 0m1.018s user 0m0.000s sys 0m1.018s W/ patch: real 0m0.249s user 0m0.000s sys 0m0.249s [1] https://lore.kernel.org/all/20250214093015.51024-4-21cnbao@gmail.com/T/= #u Acked-by: Barry Song Signed-off-by: Baolin Wang Reviewed-by: Ryan Roberts --- mm/rmap.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/mm/rmap.c b/mm/rmap.c index a0fc05f5966f..7482121d4e92 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1862,9 +1862,10 @@ static inline unsigned int folio_unmap_pte_batch(str= uct folio *folio, end_addr =3D pmd_addr_end(addr, vma->vm_end); max_nr =3D (end_addr - addr) >> PAGE_SHIFT; =20 - /* We only support lazyfree batching for now ... */ - if (!folio_test_anon(folio) || folio_test_swapbacked(folio)) + /* We only support lazyfree or file folios batching for now ... */ + if (folio_test_anon(folio) && folio_test_swapbacked(folio)) return 1; + if (pte_unused(pte)) return 1; =20 @@ -2230,7 +2231,7 @@ static bool try_to_unmap_one(struct folio *folio, str= uct vm_area_struct *vma, * * See Documentation/mm/mmu_notifier.rst */ - dec_mm_counter(mm, mm_counter_file(folio)); + add_mm_counter(mm, mm_counter_file(folio), -nr_pages); } discard: if (unlikely(folio_test_hugetlb(folio))) { --=20 2.47.3