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 73AE5CCD185 for ; Thu, 9 Oct 2025 12:40:45 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id C7EB88E0082; Thu, 9 Oct 2025 08:40:44 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id C28278E0002; Thu, 9 Oct 2025 08:40:44 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id B18138E0082; Thu, 9 Oct 2025 08:40:44 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0010.hostedemail.com [216.40.44.10]) by kanga.kvack.org (Postfix) with ESMTP id 9F4E18E0002 for ; Thu, 9 Oct 2025 08:40:44 -0400 (EDT) Received: from smtpin23.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay07.hostedemail.com (Postfix) with ESMTP id 4DFE3160876 for ; Thu, 9 Oct 2025 12:40:44 +0000 (UTC) X-FDA: 83978534808.23.FB063D4 Received: from canpmsgout03.his.huawei.com (canpmsgout03.his.huawei.com [113.46.200.218]) by imf28.hostedemail.com (Postfix) with ESMTP id ACC43C0008 for ; Thu, 9 Oct 2025 12:40:41 +0000 (UTC) Authentication-Results: imf28.hostedemail.com; dkim=pass header.d=huawei.com header.s=dkim header.b=Sjlt8Wrj; spf=pass (imf28.hostedemail.com: domain of wangkefeng.wang@huawei.com designates 113.46.200.218 as permitted sender) smtp.mailfrom=wangkefeng.wang@huawei.com; dmarc=pass (policy=quarantine) header.from=huawei.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1760013642; 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:content-transfer-encoding: in-reply-to:in-reply-to:references:references:dkim-signature; bh=+ZMpXrP8NgcqKZQS/c5Y/oIUL2PY+0QJ4pQhIadqfW4=; b=4jBxPOFK+hQZ7BjljNKWqYnsCI85XL8ASmFmGEKJkS/vHZwAe2cr8+BcuFL92Bsyt6LP9j 2p5CR8tj7c58dGlUb6+z+rVOM5525jFEH11v2JEQegDDENdAjTQz5DwqnoICnokW9C+Uyl Pi25T9sxTpF8ZKshfEapyGlkAs6t+Wk= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1760013642; a=rsa-sha256; cv=none; b=Rh/yDxTPfyTJYdhIYidVtCMhj51Ouu23DJIs4odsqnaqTcclFNYy2ZVlI6XTBVstt8FEVB F5tJv+j14YG14VqoUqtY3ihWNnx/3/8EJPOcBsq/XTfxpv7kF9K1KE55sJEaA5S4NINJIU /t7fa9ZZt6O/tuwFKuDir96TDxX1Y5c= ARC-Authentication-Results: i=1; imf28.hostedemail.com; dkim=pass header.d=huawei.com header.s=dkim header.b=Sjlt8Wrj; spf=pass (imf28.hostedemail.com: domain of wangkefeng.wang@huawei.com designates 113.46.200.218 as permitted sender) smtp.mailfrom=wangkefeng.wang@huawei.com; dmarc=pass (policy=quarantine) header.from=huawei.com dkim-signature: v=1; a=rsa-sha256; d=huawei.com; s=dkim; c=relaxed/relaxed; q=dns/txt; h=From; bh=+ZMpXrP8NgcqKZQS/c5Y/oIUL2PY+0QJ4pQhIadqfW4=; b=Sjlt8WrjchWcc2q5q5mIvbbH1J5u9UPxUloy9kregfovZWzMXp+IiYfqnysf5JnW2ssfHsLrZ rEOhAAN5+XhfTwPBo/2TqqBvWqtkKpLbBi7swjNMn6clQRisrUJWqACQQV+IH/6jJqNDuOuXgix JfQenKmq32+shUriuB1zzyE= Received: from mail.maildlp.com (unknown [172.19.162.254]) by canpmsgout03.his.huawei.com (SkyGuard) with ESMTPS id 4cj8bD0yVYzpSvj; Thu, 9 Oct 2025 20:39:52 +0800 (CST) Received: from dggpemf100008.china.huawei.com (unknown [7.185.36.138]) by mail.maildlp.com (Postfix) with ESMTPS id A620B180485; Thu, 9 Oct 2025 20:40:36 +0800 (CST) Received: from [10.174.177.243] (10.174.177.243) by dggpemf100008.china.huawei.com (7.185.36.138) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1544.11; Thu, 9 Oct 2025 20:40:35 +0800 Message-ID: <941380bf-7939-4bde-bbaa-8cc19c6a9122@huawei.com> Date: Thu, 9 Oct 2025 20:40:31 +0800 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird From: Kefeng Wang Subject: Re: [PATCH v2 1/8] mm: page_alloc: optimize pfn_range_valid_contig() To: David Hildenbrand , Andrew Morton , Oscar Salvador , Muchun Song , Zi Yan , Matthew Wilcox CC: , , Vlastimil Babka , Brendan Jackman , Johannes Weiner , References: <20250918132000.1951232-1-wangkefeng.wang@huawei.com> <20250918132000.1951232-2-wangkefeng.wang@huawei.com> <17bd2977-6a04-402f-ae84-306167cd16d6@redhat.com> Content-Language: en-US In-Reply-To: <17bd2977-6a04-402f-ae84-306167cd16d6@redhat.com> Content-Type: text/plain; charset="UTF-8"; format=flowed Content-Transfer-Encoding: 8bit X-Originating-IP: [10.174.177.243] X-ClientProxiedBy: kwepems500001.china.huawei.com (7.221.188.70) To dggpemf100008.china.huawei.com (7.185.36.138) X-Rspamd-Server: rspam05 X-Stat-Signature: p91redwo5q9f43oobhqqgywr8k7j4x38 X-Rspam-User: X-Rspamd-Queue-Id: ACC43C0008 X-HE-Tag: 1760013641-167839 X-HE-Meta: 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 AzWwiCut zSa++NEtIawXtYPfVe2HInmDB71S4Nog6dD2ExBibIGxf3Lt716uV8r0A3ANLDxy8HnBhEHb7Y/v6ydEul3MQj05TfcSr4ThtCeUlM+Awy/0LgZz+pWSvSt2yH5nUVaxKU75CfMT2Z2RCl4+WU79rfA9yVB5d83Cx9eAxDWfT5a1gdx2pYfMt7Cg5pl70Jvl48zwrpu2ch6JdFauTmeNIgdUqE5sHVCDqIeOxXixRAgcNwVW/a6o/gOlLHzc7CgiRr8MSAjrP8K73cbXpevYq4X+t7NgIigCMJdPqpmMZqB4efQAB4TBCtbL3wKvwIdS2zIcqXg6Jddc73K5Rv6ewizEYELQpDSQfucgq9s8oUBhoGoX8WpKJRgj//GF1aWKWCmQg0VnL9h7HACOCcVlcJMmPochvJxP5dRIoxY4mhRrDGD/TcyExO/oN/A== X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: On 2025/9/30 17:56, David Hildenbrand wrote: > On 18.09.25 15:19, Kefeng Wang wrote: >> The alloc_contig_pages() spends a lot of time in >> pfn_range_valid_contig(), >> we could check whether the page in this pfn range could be allocated >> before alloc_contig_range(), if the page can't be migrated, no further >> action is required, and also skip some unnecessary iterations for >> compound pages such as THP and non-compound high order buddy, which >> save times a lot too. The check is racy, but the only danger is skipping >> too much. >> >> A simple test on machine with 116G free memory, allocate 120 * 1G >> HugeTLB folios(107 successfully returned), >> >>    time echo 120 > /sys/kernel/mm/hugepages/hugepages-1048576kB/ >> nr_hugepages >> >> Before: 0m2.124s >> After:  0m0.602s >> >> Signed-off-by: Kefeng Wang >> --- >>   mm/page_alloc.c | 20 ++++++++++++++++++-- >>   1 file changed, 18 insertions(+), 2 deletions(-) >> >> diff --git a/mm/page_alloc.c b/mm/page_alloc.c >> index 478beaf95f84..5b7d705e9710 100644 >> --- a/mm/page_alloc.c >> +++ b/mm/page_alloc.c >> @@ -7012,6 +7012,7 @@ static bool pfn_range_valid_contig(struct zone >> *z, unsigned long start_pfn, >>   { >>       unsigned long i, end_pfn = start_pfn + nr_pages; >>       struct page *page; >> +    struct folio *folio; >>       for (i = start_pfn; i < end_pfn; i++) { >>           page = pfn_to_online_page(i); >> @@ -7021,11 +7022,26 @@ static bool pfn_range_valid_contig(struct zone >> *z, unsigned long start_pfn, >>           if (page_zone(page) != z) >>               return false; >> -        if (PageReserved(page)) >> +        folio = page_folio(page); >> +        if (folio_test_reserved(folio)) >>               return false; >> -        if (PageHuge(page)) >> +        if (folio_test_hugetlb(folio)) >>               return false; >> + >> +        /* The following type of folios aren't migrated */ >> +        if (folio_test_pgtable(folio) | folio_test_stack(folio)) >> +            return false; >> + > > I don't enjoy us open coding this here. has_unmovable_pages() has a much > better heuristics. > > I suggest you drop this patch for now from this series, as it seems to > be independent from the rest, and instead see if you could reuse some of > the has_unmovable_pages() logic instead. > OK，I will try to check if has_unmovable_pages() could be used. The new patches are added when I test alloc_contig_pages/ alloc_contig_frozen_pages with different GFP flags. Let me remove them and resend them separately. [1] https://lore.kernel.org/linux-mm/39ea6d31-ec9c-4053-a875-8e86a8676a62@huawei.com/