From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from bombadil.infradead.org (bombadil.infradead.org [198.137.202.133]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 9E13CD68BE7 for ; Thu, 18 Dec 2025 07:47:24 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=lists.infradead.org; s=bombadil.20210309; h=Sender:List-Subscribe:List-Help :List-Post:List-Archive:List-Unsubscribe:List-Id:Content-Transfer-Encoding: Content-Type:In-Reply-To:From:References:Cc:To:Subject:MIME-Version:Date: Message-ID:Reply-To:Content-ID:Content-Description:Resent-Date:Resent-From: Resent-Sender:Resent-To:Resent-Cc:Resent-Message-ID:List-Owner; bh=xtgxMJy+nJmKfNZGRwA0XhkF4m6Mp5Z7MBUdEpNpwCs=; b=t/ZVu2tNDOwaY5TjXdBfGCkAEP aKU0nHe0crcBei6xARcl9B4lAFAjA4ea1j9D2F7HbTc2Hy3hy03B7z87u33m7pcBZX2ZHxmtJ3V1/ fwhGEusf302oN20O8ZkrzdjC45hF8KZg2pxwK8mTLBakZH5bD9V2V52mXyZ+XXZLllC5NEQB+gOzn /x7EWVBLp3DJ25ubLOHG04habWogFEwGQzS84jUIAxrYr36nTSU83Eer3BAnyjjjlk/XqJBHDxEuB LzXmmSxtQE2s8BPYvvVeRdE8+q08OE/nw0AMRVwQ2BMwLZyek+Ut0kbtkpjrgcMaUvnnyNkkRUqTl kmZiJcIg==; Received: from localhost ([::1] helo=bombadil.infradead.org) by bombadil.infradead.org with esmtp (Exim 4.98.2 #2 (Red Hat Linux)) id 1vW8jI-00000007ytm-31oc; Thu, 18 Dec 2025 07:47:20 +0000 Received: from out30-124.freemail.mail.aliyun.com ([115.124.30.124]) by bombadil.infradead.org with esmtps (Exim 4.98.2 #2 (Red Hat Linux)) id 1vW8jD-00000007yt9-3vEC for linux-arm-kernel@lists.infradead.org; Thu, 18 Dec 2025 07:47:19 +0000 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1766044032; h=Message-ID:Date:MIME-Version:Subject:To:From:Content-Type; bh=xtgxMJy+nJmKfNZGRwA0XhkF4m6Mp5Z7MBUdEpNpwCs=; b=qweG0/veMjJAvHfJaN69RNmOJITqyL/PDfV/+woiZC2zJaetxSWgv1WCOgFGx2MuSuzUZGvu8bnK1+EW8G34hurm/0ROAi6eWBZigzoO61YuD0PMDehLHC8kaKLVgA8yZikhlpMaxK+1ACph3YrfIE8H1gd0HniS0ktwQLFKC/o= Received: from 30.74.144.118(mailfrom:baolin.wang@linux.alibaba.com fp:SMTPD_---0Wv7mHTb_1766044027 cluster:ay36) by smtp.aliyun-inc.com; Thu, 18 Dec 2025 15:47:08 +0800 Message-ID: <89cdd927-fc88-42cf-b8a1-2fbd736d5f7c@linux.alibaba.com> Date: Thu, 18 Dec 2025 15:47:07 +0800 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH v2 2/3] mm: rmap: support batched checks of the references for large folios To: Ryan Roberts , akpm@linux-foundation.org, david@kernel.org, catalin.marinas@arm.com, will@kernel.org Cc: lorenzo.stoakes@oracle.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, linux-mm@kvack.org, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org References: <545dba5e899634bc6c8ca782417d16fef3bd049f.1765439381.git.baolin.wang@linux.alibaba.com> From: Baolin Wang In-Reply-To: Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-CRM114-Version: 20100106-BlameMichelson ( TRE 0.8.0 (BSD) ) MR-646709E3 X-CRM114-CacheID: sfid-20251217_234716_591661_EF3CED7B X-CRM114-Status: GOOD ( 32.58 ) X-BeenThere: linux-arm-kernel@lists.infradead.org X-Mailman-Version: 2.1.34 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: "linux-arm-kernel" Errors-To: linux-arm-kernel-bounces+linux-arm-kernel=archiver.kernel.org@lists.infradead.org On 2025/12/18 00:39, Ryan Roberts wrote: > On 11/12/2025 08:16, 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 >> --- >> 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); > > Bug: This is broken if core-mm tries to call this for nr=1 on a pte that is part > of a contpte mapping. > > The similar fastpaths are here to prevent regressing the common small folio case. Thanks for catching this. I had considered this before, but I still missed it. > I guess here the best approach is (note no leading underscores): > > if (likely(nr == 1)) > return ptep_clear_flush_young(vma, addr, ptep); However, I prefer to use pte_cont() to check it. Later, I plan to clean up the ptep_clear_flush_young(). if (nr == 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) >> 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) \ > > Shouldn't we rename this macro to clear_flush_young_ptes_notify()? > > And potentially: > > #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ > clear_flush_young_ptes_notify(__vma, __address, __ptep, 1) > > if there are other non-batched users remaining. There are no other non-batched users now, so seems there is no need to add another redundant API. >> ({ \ >> 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 > > Let's have some function documentation here please. Sure. Will do. >> +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 (;;) { > > I know Lorenzo is pretty allergic to this style of looping :) > > He's right of course, we should probably just do this the ideomatic way and not > worry about it looking a bit different to the others. Let me use the 'while (--nr) { }' instead. > >> + 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); >> + unsigned int max_nr = (end_addr - address) >> PAGE_SHIFT; >> + pte_t pteval = ptep_get(pvmw.pte); >> + >> + nr = folio_pte_batch(folio, pvmw.pte, pteval, max_nr); >> + } >> + >> + ptes += nr; >> if (ptep_clear_flush_young_notify(vma, address, >> - pvmw.pte)) >> + pvmw.pte, nr)) >> referenced++; >> + /* Skip the batched PTEs */ >> + pvmw.pte += nr - 1; >> + pvmw.address += (nr - 1) * PAGE_SIZE; > > The -1 part is because the walker will increment by 1 I'm guessing? Right. > >> } 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); >> } >> >> - pra->mapcount--; >> + pra->mapcount -= nr; >> + if (ptes == pvmw.nr_pages) { >> + page_vma_mapped_walk_done(&pvmw); >> + break; > > What's this needed for? I'm suspicious because there wasn't an equivalent here > before. If we are sure that we batched the entire folio, we can just optimize and stop right here. Thanks for reviewing.