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 kanga.kvack.org (kanga.kvack.org [205.233.56.17]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id B2E01FC591C for ; Thu, 26 Feb 2026 09:58:07 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id D23EB6B0089; Thu, 26 Feb 2026 04:58:06 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id CD21A6B008A; Thu, 26 Feb 2026 04:58:06 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id BB3136B008C; Thu, 26 Feb 2026 04:58:06 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0016.hostedemail.com [216.40.44.16]) by kanga.kvack.org (Postfix) with ESMTP id A5D9B6B0089 for ; Thu, 26 Feb 2026 04:58:06 -0500 (EST) Received: from smtpin24.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay03.hostedemail.com (Postfix) with ESMTP id 51E16BC9D6 for ; Thu, 26 Feb 2026 09:58:06 +0000 (UTC) X-FDA: 84486156972.24.B345B96 Received: from mail-pl1-f171.google.com (mail-pl1-f171.google.com [209.85.214.171]) by imf20.hostedemail.com (Postfix) with ESMTP id 77DB31C000A for ; Thu, 26 Feb 2026 09:58:04 +0000 (UTC) Authentication-Results: imf20.hostedemail.com; dkim=pass header.d=gmail.com header.s=20230601 header.b=emnKTryW; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (imf20.hostedemail.com: domain of vernon2gm@gmail.com designates 209.85.214.171 as permitted sender) smtp.mailfrom=vernon2gm@gmail.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1772099884; a=rsa-sha256; cv=none; b=Bu/ePA2jHQ8IwATi7aGzUYPQlWTNyiTPvIM2d5vlSYGDBuzgsWZX0lRYr4ZzH2qLIsHmZj icWibopQQSP8VGZyf8rR97OExFvW6FTC0hbhoDSrIaL1Hk7UfNMpYvEYsyVlPjFwOUmmN8 9qKRwyWWRggPwttfp33yEVqCTE281hk= ARC-Authentication-Results: i=1; imf20.hostedemail.com; dkim=pass header.d=gmail.com header.s=20230601 header.b=emnKTryW; dmarc=pass (policy=none) header.from=gmail.com; spf=pass (imf20.hostedemail.com: domain of vernon2gm@gmail.com designates 209.85.214.171 as permitted sender) smtp.mailfrom=vernon2gm@gmail.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1772099884; h=from:from:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=23/t8wTYRID9qPCAnpeEZAiV1ILTIxUka8dj1HYCRwo=; b=4ijJtWqO8Iji6N8U/JmXRT75CUBV+PB0idGqyyG2Zp9wLOHUUMJvTrZU3IsEYSw0cL0VdK FLIlythPnG+I3T2DMTP5eQPUxLiZA28iehBdElfGFU03iGO3SIMBa7wl7A0f4TxJQynMca bVUSNTPAzabnX0DyLM/6vYHpPe740yc= Received: by mail-pl1-f171.google.com with SMTP id d9443c01a7336-2ade574f05eso4288975ad.3 for ; Thu, 26 Feb 2026 01:58:04 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1772099883; x=1772704683; darn=kvack.org; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:from:to:cc:subject:date:message-id:reply-to; bh=23/t8wTYRID9qPCAnpeEZAiV1ILTIxUka8dj1HYCRwo=; b=emnKTryW4HzqomZ0nIV1cpuSaptYM7w/BiICBTn1hJFabs4goK63SLmOEmlpJln2Ze TJLJdFHXYUn1g3ZIUtMgMQ+idZg3RSWmmYrxm34/iftwUcEdx9qYJPkVKP7+htmpnF6D ISeSyVHOQiS/dxYXVaqqVl9qyYj/zV6NYebnpB+QaP116UIP1hBgNfL8eo2uh4WsJJJH 1OBx6D3BddRQu0i61Fp2I9egIlAvocQaUA3Cf7frmChutGT8ACCW6IkPLKrXXXut5KWt wdttbHx5CULccBRT8HBGougFAFO7HBr28W3AzwvK9HpszBlYTiIxwYTZQIvzjdQZeK1l rBmg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1772099883; x=1772704683; h=in-reply-to:content-disposition:mime-version:references:message-id :subject:cc:to:from:date:x-gm-gg:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=23/t8wTYRID9qPCAnpeEZAiV1ILTIxUka8dj1HYCRwo=; b=dl4rAMBP8jnd++emV5DUNEfHBVxA45G6D8p4eDtaOPMLrrEHjRRu+f08QJxmZgDQtW tDzPccpDYC8SN4Ol9oK7DaXjK3D9sWUV/3qKknGBp7d0ZuQTka6H1A3DAgCXgGB/o6Ty u5/a+3bZaTZWePQvptEy4o65/b37KqLdfmnJP/NBzDGAAAvfT0Dz5NAJMxSn5/Y+C70g KIzLyKwXAFZ3jX5olKcWwJp0uoVHKHw3JPzcoG6tK+uwkgDUlyg28SdUGBw04aUJKI0N Rz2wDKLi03OSv5HPFDLhn66L9GU8UBdyXsoRLMS1al7N8D4A5jCsCMmhxzCPFVyfUxFh B5EA== X-Forwarded-Encrypted: i=1; AJvYcCUq/in25kr0BrUIS9vVhm+AMLu67BsrtZkZnRUzoKYKu8eLvsm5bi9SHqYdLe8ym88wSms3NLvx+w==@kvack.org X-Gm-Message-State: AOJu0YwQMu9dnlNUxsxHQuEoyvNUnJbgoV/d5FLTjoQvfhEHerFVIvwc XuOJzqsCqt6FVEgCI2lQAP+wdIBOq6B+dIt2xhqJZ5oJd7erDQTDmnjN X-Gm-Gg: ATEYQzwM9FHJImB6eafafEKPm1tkWvqo+A1B7S7Er+YsLCdFQFpbMdwmekWwiT12aVC B6msoEkR0EYYthuFpyFy7uBEDQ4yvNnS4zd17122fWHmsx9p5TRas5zqv7SpE1LFk/HxV97YtQo gief4T61Wyn2CYKt8JcAqfYVbUt4rgZoZHUgqndSmo/MfCGSQm6QXj9zu3SMSme7GVE1OQMffZQ gXZwZdqmctBomU8ye5RaVGxb5GQ858QjKy6xZ/eG6gJU+x+Uk4YLlStysPoAJnvB5AP9ABP+U9H nRq2z/xnAhHRvAWkXvAHxNvrUlTxGTtkjc8ki1uVtlHssKiFLvqzN+vIXO9FxMUj1j+6BY4RUB4 sjGxJQ4K+QM/XslCmnkN5gQ7ME+SVOsstmyEiLf+fIQ0xHfcRPfiSKmfDDSc4E0SpS9xYitQriR +lk2mvmnRLi2e2gXb9A7XcZRh4JfzO2VqHJzStsqHu6eeEXCyMAVWngTIu7+vAIIzvpg7OcL7nk 3KGWg== X-Received: by 2002:a17:903:2f46:b0:2a9:451b:422 with SMTP id d9443c01a7336-2ae02e4a546mr16549075ad.14.1772099883212; Thu, 26 Feb 2026 01:58:03 -0800 (PST) Received: from localhost.localdomain (n058152022206.netvigator.com. [58.152.22.206]) by smtp.gmail.com with ESMTPSA id d9443c01a7336-2adfb5dbac7sm29218235ad.37.2026.02.26.01.57.59 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 26 Feb 2026 01:58:02 -0800 (PST) Date: Thu, 26 Feb 2026 17:57:56 +0800 From: Vernon Yang To: "David Hildenbrand (Arm)" Cc: akpm@linux-foundation.org, lorenzo.stoakes@oracle.com, ziy@nvidia.com, dev.jain@arm.com, baohua@kernel.org, lance.yang@linux.dev, richard.weiyang@gmail.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org, Vernon Yang Subject: Re: [PATCH] mm: khugepaged: simplify scanning progress in pmd Message-ID: References: <20260226081313.53518-1-vernon2gm@gmail.com> <06ff4738-e81a-49ab-9204-74a6829d8d8b@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <06ff4738-e81a-49ab-9204-74a6829d8d8b@kernel.org> X-Rspam-User: X-Rspamd-Server: rspam06 X-Rspamd-Queue-Id: 77DB31C000A X-Stat-Signature: z5rt17tkxmhw4pnhqrcmq57jrx9hjbis X-HE-Tag: 1772099884-684617 X-HE-Meta: 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 qaSvpCuC 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 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: On Thu, Feb 26, 2026 at 09:42:41AM +0100, David Hildenbrand (Arm) wrote: > On 2/26/26 09:13, Vernon Yang wrote: > > From: Vernon Yang > > > > Placing "cur_progress" inside "struct collapse_control" makes the > > overall code simpler, there also coincidentally has a 4-bytes hole, > > as shown below: > > > > struct collapse_control { > > bool is_khugepaged; /* 0 1 */ > > /* XXX 3 bytes hole, try to pack */ > > u32 node_load[64]; /* 4 256 */ > > /* XXX 4 bytes hole, try to pack */ > > /* --- cacheline 4 boundary (256 bytes) was 8 bytes ago --- */ > > nodemask_t alloc_nmask; /* 264 8 */ > > > > /* size: 272, cachelines: 5, members: 3 */ > > /* sum members: 265, holes: 2, sum holes: 7 */ > > /* last cacheline: 16 bytes */ > > }; > > > > Also rename "cur_progress" to "progress_in_pmd", make it clearer. > > > > No function changes. > > > > Signed-off-by: Vernon Yang > > --- > > We should really squash that into the original patch and revisit it. Yes, squashing this patch into the original patch makes the git commit log clearer. > Because I think we might be able to do even better. > > Could we just switch to "cc->progress" like so (modified original patch): > > > diff --git a/mm/khugepaged.c b/mm/khugepaged.c > index 4d7baf220ad9..5d67e5e60ece 100644 > --- a/mm/khugepaged.c > +++ b/mm/khugepaged.c > @@ -68,7 +68,10 @@ enum scan_result { > static struct task_struct *khugepaged_thread __read_mostly; > static DEFINE_MUTEX(khugepaged_mutex); > > -/* default scan 8*HPAGE_PMD_NR ptes (or vmas) every 10 second */ > +/* > + * default scan 8*HPAGE_PMD_NR ptes, pte_mapped_hugepage, pmd_mapped, > + * no_pte_table or vmas every 10 second. > + */ > static unsigned int khugepaged_pages_to_scan __read_mostly; > static unsigned int khugepaged_pages_collapsed; > static unsigned int khugepaged_full_scans; > @@ -100,6 +103,9 @@ struct collapse_control { > /* Num pages scanned per node */ > u32 node_load[MAX_NUMNODES]; > > + /* Num pages scanned (see khugepaged_pages_to_scan). */ > + unsigned int progress; > + > /* nodemask for allocation fallback */ > nodemask_t alloc_nmask; > }; > @@ -1247,19 +1253,24 @@ static enum scan_result hpage_collapse_scan_pmd(struct mm_struct *mm, > VM_BUG_ON(start_addr & ~HPAGE_PMD_MASK); > > result = find_pmd_or_thp_or_none(mm, start_addr, &pmd); > - if (result != SCAN_SUCCEED) > + if (result != SCAN_SUCCEED) { > + cc->progress++; > goto out; > + } > > memset(cc->node_load, 0, sizeof(cc->node_load)); > nodes_clear(cc->alloc_nmask); > pte = pte_offset_map_lock(mm, pmd, start_addr, &ptl); > if (!pte) { > + cc->progress++; > result = SCAN_NO_PTE_TABLE; > goto out; > } > > for (addr = start_addr, _pte = pte; _pte < pte + HPAGE_PMD_NR; > _pte++, addr += PAGE_SIZE) { > + cc->progress++; > + > pte_t pteval = ptep_get(_pte); > if (pte_none_or_zero(pteval)) { > ++none_or_zero; > @@ -2370,6 +2381,10 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned > } > } > rcu_read_unlock(); > + if (result == SCAN_PTE_MAPPED_HUGEPAGE) > + cc->progress++; > + else > + cc->progress += HPAGE_PMD_NR; > > if (result == SCAN_SUCCEED) { > if (cc->is_khugepaged && > @@ -2385,8 +2400,8 @@ static enum scan_result hpage_collapse_scan_file(struct mm_struct *mm, unsigned > return result; > } > > -static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result *result, > - struct collapse_control *cc) > +static void khugepaged_scan_mm_slot(unsigned int progress_max, > + enum scan_result *result, struct collapse_control *cc) > __releases(&khugepaged_mm_lock) > __acquires(&khugepaged_mm_lock) > { > @@ -2394,9 +2409,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result > struct mm_slot *slot; > struct mm_struct *mm; > struct vm_area_struct *vma; > - int progress = 0; > > - VM_BUG_ON(!pages); > lockdep_assert_held(&khugepaged_mm_lock); > *result = SCAN_FAIL; > > @@ -2419,7 +2432,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result > if (unlikely(!mmap_read_trylock(mm))) > goto breakouterloop_mmap_lock; > > - progress++; > + cc->progress++; > if (unlikely(hpage_collapse_test_exit_or_disable(mm))) > goto breakouterloop; > > @@ -2429,17 +2442,17 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result > > cond_resched(); > if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { > - progress++; > + cc->progress++; > break; > } > if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_KHUGEPAGED, PMD_ORDER)) { > - progress++; > + cc->progress++; > continue; > } > hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); > hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); > if (khugepaged_scan.address > hend) { > - progress++; > + cc->progress++; > continue; > } > if (khugepaged_scan.address < hstart) > @@ -2486,7 +2499,6 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result > > /* move to next address */ > khugepaged_scan.address += HPAGE_PMD_SIZE; > - progress += HPAGE_PMD_NR; > if (!mmap_locked) > /* > * We released mmap_lock so break loop. Note > @@ -2496,7 +2508,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result > * correct result back to caller. > */ > goto breakouterloop_mmap_lock; > - if (progress >= pages) > + if (cc->progress >= progress_max) > goto breakouterloop; > } > } > @@ -2527,9 +2539,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, enum scan_result > collect_mm_slot(slot); > } > > - trace_mm_khugepaged_scan(mm, progress, khugepaged_scan.mm_slot == NULL); > - > - return progress; > + trace_mm_khugepaged_scan(mm, cc->progress, khugepaged_scan.mm_slot == NULL); > } > > static int khugepaged_has_work(void) > @@ -2545,13 +2555,14 @@ static int khugepaged_wait_event(void) > > static void khugepaged_do_scan(struct collapse_control *cc) > { > - unsigned int progress = 0, pass_through_head = 0; > - unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); > + const unsigned int progress_max = READ_ONCE(khugepaged_pages_to_scan); > + unsigned int pass_through_head = 0; > bool wait = true; > enum scan_result result = SCAN_SUCCEED; > > lru_add_drain_all(); > > + cc->progress = 0; madvise(MADV_COLLAPSE) is missing the initialization of "cc->progress" because "cc = kmalloc_obj(*cc)". We need to manually initialize it in madvise_collapse(). LGTM, I will submit v2 with this patch and squashed into the original patch. -- Cheers, Vernon