From nobody Sun Feb 8 02:42:05 2026 Received: from out2-smtp.messagingengine.com (out2-smtp.messagingengine.com [66.111.4.26]) (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 BEC4B14198F for ; Fri, 2 Feb 2024 16:16:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=66.111.4.26 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706890579; cv=none; b=TTa9twik41BK5bT6TtsJZsP7UN59yqUkOCMR0jak0vNPckXwYBaFytda6dRKo5xZ//F6tcT/pLrvvEMa1AwLiFtP2P5pq4cMPEjSQtGLglTMKYoS+ad0XhWfs1o9PkhrMo14Z8OffyM52DOURI2pI7nYgJCA+M+000VBsPvOC/U= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706890579; c=relaxed/simple; bh=CHBuBJuhamNrP6U0fj4Mt2MwBKcPu0swmlgl3BSB8TE=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=hcIG0Gr5CjCPh4r/9O/Yg2uPKRrouwyeOZJfefEWTQ9vmUEJrW9yhiMGHHo9b1ERP8qLl6/nqVKbSz+wNWFTRDBZFno0MSsQJPnF3JjClUTYrN6vGC7iSoQUVUErKk1ZrAgpej9nEFMoUR3FbbN5OvDpdUfL1Bu68wEilaEPD6Q= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=sent.com; spf=pass smtp.mailfrom=sent.com; dkim=pass (2048-bit key) header.d=sent.com header.i=@sent.com header.b=w9AwuLYZ; dkim=pass (2048-bit key) header.d=messagingengine.com header.i=@messagingengine.com header.b=jITQjR9f; arc=none smtp.client-ip=66.111.4.26 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=sent.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=sent.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=sent.com header.i=@sent.com header.b="w9AwuLYZ"; dkim=pass (2048-bit key) header.d=messagingengine.com header.i=@messagingengine.com header.b="jITQjR9f" Received: from compute5.internal (compute5.nyi.internal [10.202.2.45]) by mailout.nyi.internal (Postfix) with ESMTP id BE2FD5C0080; Fri, 2 Feb 2024 11:16:16 -0500 (EST) Received: from mailfrontend1 ([10.202.2.162]) by compute5.internal (MEProxy); Fri, 02 Feb 2024 11:16:16 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sent.com; h=cc :cc:content-transfer-encoding:content-type:content-type:date :date:from:from:in-reply-to:in-reply-to:message-id:mime-version :references:reply-to:reply-to:subject:subject:to:to; s=fm3; t= 1706890576; x=1706976976; bh=b0LGZXB2atC7cRDxeVKB29tfMJXHfhbupvu qzgL5H0w=; b=w9AwuLYZjR/BP+cqnv3LMOCFQHBsCSwi895LQemcBc+Vo5ZToOt HCHtnMIu+rwnyKxCfClEPDT0/5F+CkwVbcGInCTjWeCWmRjStV7xls7XKOArtfsI w5V3vmmkw+KiHx2VdkyMZ0QacA6O+hqiEA/i4E9XOJ9z+Q/x3xQMDQ8arvA/lk0g BqHpu1wNeN9kn2L6C96cJ1thlhPyVv97m93rRRo8gewh7pXpNJHfVbnhc94d+/OT 8eny1dAyhp8oVMCHXdhdF/yxvyNKMP/6aOC8MZKzfU4jhN/6nuOWJw7hUSqswAT0 if8thmyelZ6EE/eBsHrgVEmiLME2G476qSA== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:cc:content-transfer-encoding :content-type:content-type:date:date:feedback-id:feedback-id :from:from:in-reply-to:in-reply-to:message-id:mime-version :references:reply-to:reply-to:subject:subject:to:to:x-me-proxy :x-me-proxy:x-me-sender:x-me-sender:x-sasl-enc; s=fm3; t= 1706890576; x=1706976976; bh=b0LGZXB2atC7cRDxeVKB29tfMJXHfhbupvu qzgL5H0w=; b=jITQjR9fZ4vUH7jpIKUSGUf69CmGaNlTyKWC7zCok4dJZu5NM+M tfqbsksM2p0nTWynjXbTfU3uIPh+tzf0SEH3sdEbK6yLqYCUcsSri81slnPWg0Vl +tv7SmGQ6GXwLg/uEogMGAdWcRQ2uUpLFNRY5TeNJYaKuyqHrI9LDFZyoAHDTJrv laJlFvAREQb49Osr7ozT8+HHU7Do0nEFj3n2Ks80KnGAxDm5blkXMdpNaQpb5tkl znMVFC71CcxwrGQpSwLwE8Et4YppV1zGIp7VMnNW8+rHy1e+kLti4NGDKwzC/JLD oTrbPSupWq5z6Db9SfEWk+3EevvpLfpHAYw== X-ME-Sender: X-ME-Received: X-ME-Proxy-Cause: gggruggvucftvghtrhhoucdtuddrgedvkedrfedugedgkeehucetufdoteggodetrfdotf fvucfrrhhofhhilhgvmecuhfgrshhtofgrihhlpdfqfgfvpdfurfetoffkrfgpnffqhgen uceurghilhhouhhtmecufedttdenucesvcftvggtihhpihgvnhhtshculddquddttddmne cujfgurhephffvvefufffkofgjfhhrgggtgfesthekredtredtjeenucfhrhhomhepkghi ucgjrghnuceoiihirdihrghnsehsvghnthdrtghomheqnecuggftrfgrthhtvghrnhepje ekteekffelleekudfftdefvddtjeejuedtuedtteegjefgvedtfedujeekieevnecuvehl uhhsthgvrhfuihiivgeptdenucfrrghrrghmpehmrghilhhfrhhomhepiihirdihrghnse hsvghnthdrtghomh X-ME-Proxy: Feedback-ID: iccd040f4:Fastmail Received: by mail.messagingengine.com (Postfix) with ESMTPA; Fri, 2 Feb 2024 11:16:15 -0500 (EST) From: Zi Yan To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: Zi Yan , "Huang, Ying" , Ryan Roberts , Andrew Morton , "Matthew Wilcox (Oracle)" , David Hildenbrand , "Yin, Fengwei" , Yu Zhao , Vlastimil Babka , "Kirill A . Shutemov" , Johannes Weiner , Baolin Wang , Kemeng Shi , Mel Gorman , Rohan Puri , Mcgrof Chamberlain , Adam Manzanares , "Vishal Moola (Oracle)" Subject: [PATCH v3 1/3] mm/compaction: enable compacting >0 order folios. Date: Fri, 2 Feb 2024 11:15:52 -0500 Message-ID: <20240202161554.565023-2-zi.yan@sent.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20240202161554.565023-1-zi.yan@sent.com> References: <20240202161554.565023-1-zi.yan@sent.com> Reply-To: Zi Yan Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable From: Zi Yan migrate_pages() supports >0 order folio migration and during compaction, even if compaction_alloc() cannot provide >0 order free pages, migrate_pages() can split the source page and try to migrate the base pages from the split. It can be a baseline and start point for adding support for compacting >0 order folios. Suggested-by: Huang Ying Signed-off-by: Zi Yan Reviewed-by: Baolin Wang Tested-by: Baolin Wang --- mm/compaction.c | 43 +++++++++++++++++++++++++++++++++++-------- 1 file changed, 35 insertions(+), 8 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index 4add68d40e8d..e43e898d2c77 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -816,6 +816,21 @@ static bool too_many_isolated(struct compact_control *= cc) return too_many; } =20 +/* + * 1. if the page order is larger than or equal to target_order (i.e., + * cc->order and when it is not -1 for global compaction), skip it since + * target_order already indicates no free page with larger than target_ord= er + * exists and later migrating it will most likely fail; + * + * 2. compacting > pageblock_order pages does not improve memory fragmenta= tion, + * skip them; + */ +static bool skip_isolation_on_order(int order, int target_order) +{ + return (target_order !=3D -1 && order >=3D target_order) || + order >=3D pageblock_order; +} + /** * isolate_migratepages_block() - isolate all migrate-able pages within * a single pageblock @@ -1010,7 +1025,7 @@ isolate_migratepages_block(struct compact_control *cc= , unsigned long low_pfn, /* * Regardless of being on LRU, compound pages such as THP and * hugetlbfs are not to be compacted unless we are attempting - * an allocation much larger than the huge page size (eg CMA). + * an allocation larger than the compound page size. * We can potentially save a lot of iterations if we skip them * at once. The check is racy, but we can consider only valid * values and the only danger is skipping too much. @@ -1018,11 +1033,18 @@ isolate_migratepages_block(struct compact_control *= cc, unsigned long low_pfn, if (PageCompound(page) && !cc->alloc_contig) { const unsigned int order =3D compound_order(page); =20 - if (likely(order <=3D MAX_PAGE_ORDER)) { - low_pfn +=3D (1UL << order) - 1; - nr_scanned +=3D (1UL << order) - 1; + /* + * Skip based on page order and compaction target order + * and skip hugetlbfs pages. + */ + if (skip_isolation_on_order(order, cc->order) || + PageHuge(page)) { + if (order <=3D MAX_PAGE_ORDER) { + low_pfn +=3D (1UL << order) - 1; + nr_scanned +=3D (1UL << order) - 1; + } + goto isolate_fail; } - goto isolate_fail; } =20 /* @@ -1165,10 +1187,11 @@ isolate_migratepages_block(struct compact_control *= cc, unsigned long low_pfn, } =20 /* - * folio become large since the non-locked check, - * and it's on LRU. + * Check LRU folio order under the lock */ - if (unlikely(folio_test_large(folio) && !cc->alloc_contig)) { + if (unlikely(skip_isolation_on_order(folio_order(folio), + cc->order) && + !cc->alloc_contig)) { low_pfn +=3D folio_nr_pages(folio) - 1; nr_scanned +=3D folio_nr_pages(folio) - 1; folio_set_lru(folio); @@ -1786,6 +1809,10 @@ static struct folio *compaction_alloc(struct folio *= src, unsigned long data) struct compact_control *cc =3D (struct compact_control *)data; struct folio *dst; =20 + /* this makes migrate_pages() split the source page and retry */ + if (folio_test_large(src) > 0) + return NULL; + if (list_empty(&cc->freepages)) { isolate_freepages(cc); =20 --=20 2.43.0 From nobody Sun Feb 8 02:42:05 2026 Received: from out2-smtp.messagingengine.com (out2-smtp.messagingengine.com [66.111.4.26]) (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 A88A7146913 for ; Fri, 2 Feb 2024 16:16:18 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=66.111.4.26 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706890580; cv=none; b=B5s3JbPJ0ZCJE0Zf9X3igsUzEmsmZJ5UVcyOe8188iNxRnhgE+o5cAP6UvRK47H52s2A0ius/qdG9yCINd9m2ohdqOKqX2KLking8ue6tbmO4AntWnqXH9o+oEQB6x9f9iRVj44t1wQGi5TA4j8ERMM+qsTarCgqYrNpq+Jtu7Y= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706890580; c=relaxed/simple; bh=Sjbq/9flKHP26VVIXKLKU/3PClA3qMbkP4jOAHyqFxI=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=hmZjSjOp96oGKTjflvfzE0fgzrFDgCXn2hLL+dptkP2lKmHtSRWGW2HgBoBMouMDZi5cdBUshRWT+fdE84aKXuyPPfGabldmr2ZuWrd6/UPEs7mQd699h2l+q6AVAbWOM2XKpYubIdVcZw0yyroa7EnQbzuEuiSZrKXXHWB0VZg= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=sent.com; spf=pass smtp.mailfrom=sent.com; dkim=pass (2048-bit key) header.d=sent.com header.i=@sent.com header.b=lhM618jh; dkim=pass (2048-bit key) header.d=messagingengine.com header.i=@messagingengine.com header.b=e2ioDS5k; arc=none smtp.client-ip=66.111.4.26 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=sent.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=sent.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=sent.com header.i=@sent.com header.b="lhM618jh"; dkim=pass (2048-bit key) header.d=messagingengine.com header.i=@messagingengine.com header.b="e2ioDS5k" Received: from compute7.internal (compute7.nyi.internal [10.202.2.48]) by mailout.nyi.internal (Postfix) with ESMTP id B700A5C0114; Fri, 2 Feb 2024 11:16:17 -0500 (EST) Received: from mailfrontend1 ([10.202.2.162]) by compute7.internal (MEProxy); Fri, 02 Feb 2024 11:16:17 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sent.com; h=cc :cc:content-transfer-encoding:content-type:content-type:date :date:from:from:in-reply-to:in-reply-to:message-id:mime-version :references:reply-to:reply-to:subject:subject:to:to; s=fm3; t= 1706890577; x=1706976977; bh=o4ZHby28qW9Br68l3xQuwrxRewdgnvINZod 3R2hEUmA=; b=lhM618jhymHQnFbLbCt+r46OvZFgJtpfYZ3fhNFVgoCcA4vTC2Q g9EO99bpRcHozcg/vMH9orlQP8aHtaZAr1awhEGRIaaGXXum3Km9pmXcBTgGsY52 1+pPA9sAlyrIqoxDey32ZXg4Te+KQL5O/uZkHLWB94pDA83hfmCYeky2i9qPj3Zp WMpql6Wsmi1imreyNZj+Mh5pFKZpQm/1ReljfsaCG836ZR4guEdvx9M5cebwzNF8 uhvWaxD52rKjpnuRlOgbLwl39Bs9TS9DRB8Cv/1iCvbG+eKi6DMAy3xJDddtwfCr qs/j38QqYk4wIOjozpn7zpU7zgMjaS5Jcmw== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:cc:content-transfer-encoding :content-type:content-type:date:date:feedback-id:feedback-id :from:from:in-reply-to:in-reply-to:message-id:mime-version :references:reply-to:reply-to:subject:subject:to:to:x-me-proxy :x-me-proxy:x-me-sender:x-me-sender:x-sasl-enc; s=fm3; t= 1706890577; x=1706976977; bh=o4ZHby28qW9Br68l3xQuwrxRewdgnvINZod 3R2hEUmA=; b=e2ioDS5kjM6BcqcbT+gOOout9yH+3tSdGcVMChoY906dfx34kLi fntipjO2M5+S3PYf6NMKP79nH3jLLlNdRr6CoO9t2SSVUTI44IXyoAwAi1H0gmQd f8PP9Mrt3TsZjBNxiE12j+RM92qYm8nAc9HQPAd6TjZbRvq91qVeBKBX+kZJRSzt o7S5ZP/yXjaKpX7x9YS3hoRJz53h3/KYIbGYWNAoFQ30QFYeDXzd7gyR3PLiIAo6 6kD5QOVLN3U05YnaR1bAlI8RLRUCbVWJQwPze6WZi8edqHXZiI1D4vih+Mfv77om MFBAAFlZK3FXyEcx9RJsr2R2ptDH/LMOYbw== X-ME-Sender: X-ME-Received: X-ME-Proxy-Cause: gggruggvucftvghtrhhoucdtuddrgedvkedrfedugedgkeehucetufdoteggodetrfdotf fvucfrrhhofhhilhgvmecuhfgrshhtofgrihhlpdfqfgfvpdfurfetoffkrfgpnffqhgen uceurghilhhouhhtmecufedttdenucesvcftvggtihhpihgvnhhtshculddquddttddmne cujfgurhephffvvefufffkofgjfhhrgggtgfesthekredtredtjeenucfhrhhomhepkghi ucgjrghnuceoiihirdihrghnsehsvghnthdrtghomheqnecuggftrfgrthhtvghrnhepje ekteekffelleekudfftdefvddtjeejuedtuedtteegjefgvedtfedujeekieevnecuvehl uhhsthgvrhfuihiivgeptdenucfrrghrrghmpehmrghilhhfrhhomhepiihirdihrghnse hsvghnthdrtghomh X-ME-Proxy: Feedback-ID: iccd040f4:Fastmail Received: by mail.messagingengine.com (Postfix) with ESMTPA; Fri, 2 Feb 2024 11:16:16 -0500 (EST) From: Zi Yan To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: Zi Yan , "Huang, Ying" , Ryan Roberts , Andrew Morton , "Matthew Wilcox (Oracle)" , David Hildenbrand , "Yin, Fengwei" , Yu Zhao , Vlastimil Babka , "Kirill A . Shutemov" , Johannes Weiner , Baolin Wang , Kemeng Shi , Mel Gorman , Rohan Puri , Mcgrof Chamberlain , Adam Manzanares , "Vishal Moola (Oracle)" Subject: [PATCH v3 2/3] mm/compaction: add support for >0 order folio memory compaction. Date: Fri, 2 Feb 2024 11:15:53 -0500 Message-ID: <20240202161554.565023-3-zi.yan@sent.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20240202161554.565023-1-zi.yan@sent.com> References: <20240202161554.565023-1-zi.yan@sent.com> Reply-To: Zi Yan Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable From: Zi Yan Before last commit, memory compaction only migrates order-0 folios and skips >0 order folios. Last commit splits all >0 order folios during compaction. This commit migrates >0 order folios during compaction by keeping isolated free pages at their original size without splitting them into order-0 pages and using them directly during migration process. What is different from the prior implementation: 1. All isolated free pages are kept in a NR_PAGE_ORDERS array of page lists, where each page list stores free pages in the same order. 2. All free pages are not post_alloc_hook() processed nor buddy pages, although their orders are stored in first page's private like buddy pages. 3. During migration, in new page allocation time (i.e., in compaction_alloc()), free pages are then processed by post_alloc_hook(). When migration fails and a new page is returned (i.e., in compaction_free()), free pages are restored by reversing the post_alloc_hook() operations using newly added free_pages_prepare_fpi_none(). Step 3 is done for a latter optimization that splitting and/or merging free pages during compaction becomes easier. Note: without splitting free pages, compaction can end prematurely due to migration will return -ENOMEM even if there is free pages. This happens when no order-0 free page exist and compaction_alloc() return NULL. Signed-off-by: Zi Yan Reviewed-by: Baolin Wang Tested-by: Baolin Wang --- mm/compaction.c | 149 +++++++++++++++++++++++++++++------------------- mm/internal.h | 9 ++- mm/page_alloc.c | 6 ++ 3 files changed, 104 insertions(+), 60 deletions(-) diff --git a/mm/compaction.c b/mm/compaction.c index e43e898d2c77..58a4e3fb72ec 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -66,45 +66,67 @@ static inline void count_compact_events(enum vm_event_i= tem item, long delta) #define COMPACTION_HPAGE_ORDER (PMD_SHIFT - PAGE_SHIFT) #endif =20 -static unsigned long release_freepages(struct list_head *freelist) +static void init_page_list(struct page_list *p) { - struct page *page, *next; - unsigned long high_pfn =3D 0; - - list_for_each_entry_safe(page, next, freelist, lru) { - unsigned long pfn =3D page_to_pfn(page); - list_del(&page->lru); - __free_page(page); - if (pfn > high_pfn) - high_pfn =3D pfn; - } - - return high_pfn; + INIT_LIST_HEAD(&p->pages); + p->nr_pages =3D 0; } =20 -static void split_map_pages(struct list_head *list) +static void split_map_pages(struct page_list *freepages) { - unsigned int i, order, nr_pages; + unsigned int i, order, total_nr_pages; struct page *page, *next; LIST_HEAD(tmp_list); =20 - list_for_each_entry_safe(page, next, list, lru) { - list_del(&page->lru); + for (order =3D 0; order < NR_PAGE_ORDERS; order++) { + total_nr_pages =3D freepages[order].nr_pages * (1 << order); + freepages[order].nr_pages =3D 0; + + list_for_each_entry_safe(page, next, &freepages[order].pages, lru) { + unsigned int nr_pages; + + list_del(&page->lru); =20 - order =3D page_private(page); - nr_pages =3D 1 << order; + nr_pages =3D 1 << order; =20 - post_alloc_hook(page, order, __GFP_MOVABLE); - if (order) - split_page(page, order); + post_alloc_hook(page, order, __GFP_MOVABLE); + if (order) + split_page(page, order); =20 - for (i =3D 0; i < nr_pages; i++) { - list_add(&page->lru, &tmp_list); - page++; + for (i =3D 0; i < nr_pages; i++) { + list_add(&page->lru, &tmp_list); + page++; + } } + freepages[0].nr_pages +=3D total_nr_pages; + list_splice_init(&tmp_list, &freepages[0].pages); } +} =20 - list_splice(&tmp_list, list); +static unsigned long release_free_list(struct page_list *freepages) +{ + int order; + unsigned long high_pfn =3D 0; + + for (order =3D 0; order < NR_PAGE_ORDERS; order++) { + struct page *page, *next; + + list_for_each_entry_safe(page, next, &freepages[order].pages, lru) { + unsigned long pfn =3D page_to_pfn(page); + + list_del(&page->lru); + /* + * Convert free pages into post allocation pages, so + * that we can free them via __free_page. + */ + post_alloc_hook(page, order, __GFP_MOVABLE); + __free_pages(page, order); + if (pfn > high_pfn) + high_pfn =3D pfn; + } + freepages[order].nr_pages =3D 0; + } + return high_pfn; } =20 #ifdef CONFIG_COMPACTION @@ -583,7 +605,7 @@ static bool compact_unlock_should_abort(spinlock_t *loc= k, static unsigned long isolate_freepages_block(struct compact_control *cc, unsigned long *start_pfn, unsigned long end_pfn, - struct list_head *freelist, + struct page_list *freelist, unsigned int stride, bool strict) { @@ -657,7 +679,8 @@ static unsigned long isolate_freepages_block(struct com= pact_control *cc, nr_scanned +=3D isolated - 1; total_isolated +=3D isolated; cc->nr_freepages +=3D isolated; - list_add_tail(&page->lru, freelist); + list_add_tail(&page->lru, &freelist[order].pages); + freelist[order].nr_pages++; =20 if (!strict && cc->nr_migratepages <=3D cc->nr_freepages) { blockpfn +=3D isolated; @@ -722,7 +745,11 @@ isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn) { unsigned long isolated, pfn, block_start_pfn, block_end_pfn; - LIST_HEAD(freelist); + int order; + struct page_list tmp_freepages[NR_PAGE_ORDERS]; + + for (order =3D 0; order < NR_PAGE_ORDERS; order++) + init_page_list(&tmp_freepages[order]); =20 pfn =3D start_pfn; block_start_pfn =3D pageblock_start_pfn(pfn); @@ -753,7 +780,7 @@ isolate_freepages_range(struct compact_control *cc, break; =20 isolated =3D isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, &freelist, 0, true); + block_end_pfn, tmp_freepages, 0, true); =20 /* * In strict mode, isolate_freepages_block() returns 0 if @@ -770,15 +797,15 @@ isolate_freepages_range(struct compact_control *cc, */ } =20 - /* __isolate_free_page() does not map the pages */ - split_map_pages(&freelist); - if (pfn < end_pfn) { /* Loop terminated early, cleanup. */ - release_freepages(&freelist); + release_free_list(tmp_freepages); return 0; } =20 + /* __isolate_free_page() does not map the pages */ + split_map_pages(tmp_freepages); + /* We don't use freelists for anything. */ return pfn; } @@ -1481,7 +1508,7 @@ fast_isolate_around(struct compact_control *cc, unsig= ned long pfn) if (!page) return; =20 - isolate_freepages_block(cc, &start_pfn, end_pfn, &cc->freepages, 1, false= ); + isolate_freepages_block(cc, &start_pfn, end_pfn, cc->freepages, 1, false); =20 /* Skip this pageblock in the future as it's full or nearly full */ if (start_pfn =3D=3D end_pfn && !cc->no_set_skip_hint) @@ -1610,7 +1637,8 @@ static void fast_isolate_freepages(struct compact_con= trol *cc) nr_scanned +=3D nr_isolated - 1; total_isolated +=3D nr_isolated; cc->nr_freepages +=3D nr_isolated; - list_add_tail(&page->lru, &cc->freepages); + list_add_tail(&page->lru, &cc->freepages[order].pages); + cc->freepages[order].nr_pages++; count_compact_events(COMPACTISOLATED, nr_isolated); } else { /* If isolation fails, abort the search */ @@ -1687,13 +1715,12 @@ static void isolate_freepages(struct compact_contro= l *cc) unsigned long isolate_start_pfn; /* exact pfn we start at */ unsigned long block_end_pfn; /* end of current pageblock */ unsigned long low_pfn; /* lowest pfn scanner is able to scan */ - struct list_head *freelist =3D &cc->freepages; unsigned int stride; =20 /* Try a small search of the free lists for a candidate */ fast_isolate_freepages(cc); if (cc->nr_freepages) - goto splitmap; + return; =20 /* * Initialise the free scanner. The starting point is where we last @@ -1753,7 +1780,7 @@ static void isolate_freepages(struct compact_control = *cc) =20 /* Found a block suitable for isolating free pages from. */ nr_isolated =3D isolate_freepages_block(cc, &isolate_start_pfn, - block_end_pfn, freelist, stride, false); + block_end_pfn, cc->freepages, stride, false); =20 /* Update the skip hint if the full pageblock was scanned */ if (isolate_start_pfn =3D=3D block_end_pfn) @@ -1794,10 +1821,6 @@ static void isolate_freepages(struct compact_control= *cc) * and the loop terminated due to isolate_start_pfn < low_pfn */ cc->free_pfn =3D isolate_start_pfn; - -splitmap: - /* __isolate_free_page() does not map the pages */ - split_map_pages(freelist); } =20 /* @@ -1808,23 +1831,22 @@ static struct folio *compaction_alloc(struct folio = *src, unsigned long data) { struct compact_control *cc =3D (struct compact_control *)data; struct folio *dst; + int order =3D folio_order(src); =20 - /* this makes migrate_pages() split the source page and retry */ - if (folio_test_large(src) > 0) - return NULL; - - if (list_empty(&cc->freepages)) { + if (!cc->freepages[order].nr_pages) { isolate_freepages(cc); - - if (list_empty(&cc->freepages)) + if (!cc->freepages[order].nr_pages) return NULL; } =20 - dst =3D list_entry(cc->freepages.next, struct folio, lru); + dst =3D list_first_entry(&cc->freepages[order].pages, struct folio, lru); + cc->freepages[order].nr_pages--; list_del(&dst->lru); - cc->nr_freepages--; - - return dst; + post_alloc_hook(&dst->page, order, __GFP_MOVABLE); + if (order) + prep_compound_page(&dst->page, order); + cc->nr_freepages -=3D 1 << order; + return page_rmappable_folio(&dst->page); } =20 /* @@ -1835,9 +1857,17 @@ static struct folio *compaction_alloc(struct folio *= src, unsigned long data) static void compaction_free(struct folio *dst, unsigned long data) { struct compact_control *cc =3D (struct compact_control *)data; + int order =3D folio_order(dst); + struct page *page =3D &dst->page; + + folio_set_count(dst, 0); + free_pages_prepare_fpi_none(page, order); =20 - list_add(&dst->lru, &cc->freepages); - cc->nr_freepages++; + INIT_LIST_HEAD(&dst->lru); + + list_add(&dst->lru, &cc->freepages[order].pages); + cc->freepages[order].nr_pages++; + cc->nr_freepages +=3D 1 << order; } =20 /* possible outcome of isolate_migratepages */ @@ -2461,6 +2491,7 @@ compact_zone(struct compact_control *cc, struct captu= re_control *capc) const bool sync =3D cc->mode !=3D MIGRATE_ASYNC; bool update_cached; unsigned int nr_succeeded =3D 0; + int order; =20 /* * These counters track activities during zone compaction. Initialize @@ -2470,7 +2501,8 @@ compact_zone(struct compact_control *cc, struct captu= re_control *capc) cc->total_free_scanned =3D 0; cc->nr_migratepages =3D 0; cc->nr_freepages =3D 0; - INIT_LIST_HEAD(&cc->freepages); + for (order =3D 0; order < NR_PAGE_ORDERS; order++) + init_page_list(&cc->freepages[order]); INIT_LIST_HEAD(&cc->migratepages); =20 cc->migratetype =3D gfp_migratetype(cc->gfp_mask); @@ -2656,7 +2688,7 @@ compact_zone(struct compact_control *cc, struct captu= re_control *capc) * so we don't leave any returned pages behind in the next attempt. */ if (cc->nr_freepages > 0) { - unsigned long free_pfn =3D release_freepages(&cc->freepages); + unsigned long free_pfn =3D release_free_list(cc->freepages); =20 cc->nr_freepages =3D 0; VM_BUG_ON(free_pfn =3D=3D 0); @@ -2675,7 +2707,6 @@ compact_zone(struct compact_control *cc, struct captu= re_control *capc) =20 trace_mm_compaction_end(cc, start_pfn, end_pfn, sync, ret); =20 - VM_BUG_ON(!list_empty(&cc->freepages)); VM_BUG_ON(!list_empty(&cc->migratepages)); =20 return ret; diff --git a/mm/internal.h b/mm/internal.h index 1e29c5821a1d..c6ea449c5353 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -447,6 +447,8 @@ extern void prep_compound_page(struct page *page, unsig= ned int order); =20 extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); +extern bool free_pages_prepare_fpi_none(struct page *page, unsigned int or= der); + extern int user_min_free_kbytes; =20 extern void free_unref_page(struct page *page, unsigned int order); @@ -473,6 +475,11 @@ int split_free_page(struct page *free_page, /* * in mm/compaction.c */ + +struct page_list { + struct list_head pages; + unsigned long nr_pages; +}; /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts @@ -481,7 +488,7 @@ int split_free_page(struct page *free_page, * completes when free_pfn <=3D migrate_pfn */ struct compact_control { - struct list_head freepages; /* List of free pages to migrate to */ + struct page_list freepages[NR_PAGE_ORDERS]; /* List of free pages to migr= ate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5be4cd8f6b5a..c7c135e6d5ee 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1179,6 +1179,12 @@ static __always_inline bool free_pages_prepare(struc= t page *page, return true; } =20 +__always_inline bool free_pages_prepare_fpi_none(struct page *page, + unsigned int order) +{ + return free_pages_prepare(page, order, FPI_NONE); +} + /* * Frees a number of pages from the PCP lists * Assumes all pages on list are in same zone. --=20 2.43.0 From nobody Sun Feb 8 02:42:05 2026 Received: from out2-smtp.messagingengine.com (out2-smtp.messagingengine.com [66.111.4.26]) (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 17A9F1474B2 for ; Fri, 2 Feb 2024 16:16:19 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=66.111.4.26 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706890581; cv=none; b=ADFiwMIzklFKesO8G1WdnIGqcYK0fC3BCcguf9R56l7yo3AOegsUNfkDPp50gyiSHa3h6U6/b8yuuyOAHhTFNmUiDjz31BN9LBdhjELEHfUPRckkKM+0rYWph+WRk1AWqXNbL18mM5fv2DYS/y/yM0YfShFMNmQ16mrkHVnBCLs= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1706890581; c=relaxed/simple; bh=JQ3XAd6+1pk8HTCEGu8mix5SOQ7LMO81KCcmw2HK8Iw=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=rDfCbmNNWS0hrEybw09hTXwexXHsQtg13kA8cvJ933cG/LvYZQBu5vTUUG0ZKf6K0/U8WNwXvQxD2E3B7KUA9V+jIYSTLZen9Um3qwPs1KKLwQQ06aDXdZCsEiyxnPWXfwkyX4AAH5pxmh8JGLUTCXBgS8npWdUcDLkIJjRAYvI= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=sent.com; spf=pass smtp.mailfrom=sent.com; dkim=pass (2048-bit key) header.d=sent.com header.i=@sent.com header.b=Q6BNiPci; dkim=pass (2048-bit key) header.d=messagingengine.com header.i=@messagingengine.com header.b=w3EzSPMY; arc=none smtp.client-ip=66.111.4.26 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=sent.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=sent.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=sent.com header.i=@sent.com header.b="Q6BNiPci"; dkim=pass (2048-bit key) header.d=messagingengine.com header.i=@messagingengine.com header.b="w3EzSPMY" Received: from compute3.internal (compute3.nyi.internal [10.202.2.43]) by mailout.nyi.internal (Postfix) with ESMTP id 450FD5C0108; Fri, 2 Feb 2024 11:16:19 -0500 (EST) Received: from mailfrontend1 ([10.202.2.162]) by compute3.internal (MEProxy); Fri, 02 Feb 2024 11:16:19 -0500 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=sent.com; h=cc :cc:content-transfer-encoding:content-type:content-type:date :date:from:from:in-reply-to:in-reply-to:message-id:mime-version :references:reply-to:reply-to:subject:subject:to:to; s=fm3; t= 1706890579; x=1706976979; bh=Srz2TBF5bSmmDzT+fRItHrkdBt/FNKVEiEo yh1M6V+0=; b=Q6BNiPcizadAd+EZgLpzobSWkpvEDzg+ntUAZW2HFba3/Lbpme2 O8sD/KsTLcClEooEDS+rgni1VKTOJVvjKG2BECTjNiNda9PMom5VpxTwxk+kmX9g 5SJAxrVHTNtZxoS5jAUi56r/D8XWcS0OJh2+HEwhuwHmt1t9F6ixsOpYuh0Z62lf jsolvlGzfHgQFVTRoeCZd2VaMnTaM1ocYqJaIOR1z9/NUXsfDnUeuUp37YoN3RGo h9R7gudHRW7KTw4tSyeCZ1fkU5pRSQ2k5vAl5Zfe3Gl+tFLgCwcmgP1//oQ2W0+0 ZAsBefLjP95IPfEJx9zsNtGrcaHxRnXII7w== DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d= messagingengine.com; h=cc:cc:content-transfer-encoding :content-type:content-type:date:date:feedback-id:feedback-id :from:from:in-reply-to:in-reply-to:message-id:mime-version :references:reply-to:reply-to:subject:subject:to:to:x-me-proxy :x-me-proxy:x-me-sender:x-me-sender:x-sasl-enc; s=fm3; t= 1706890579; x=1706976979; bh=Srz2TBF5bSmmDzT+fRItHrkdBt/FNKVEiEo yh1M6V+0=; b=w3EzSPMYiSxw7VrU6CcZVS7tnyWg0o5f4EO+FRuCOUgJup6WH3A gUN6QtlNYcx+Xn13uj0UTgRkf7/WGHrUMYbh0SZWawyQ1VsQMjqfWMGZIYZFIdqB TgfodME8fk/7pVIskKCsZPmLBTaZTRcAhff4gV09XWLcq2pcbc6xc//W7iVxO8y1 k6Mv24maaJmmjZhsBbAUxbjFqyQp+8mkxO3FQkx6tvJUlZgqg+MLuMvmItlouDmy QqdBcxCFwfun+0ZBRcIHVEJ2iA/lBy8U/xlgdDOcFYEGbzGP8Vtg7NECbWUCEn7U NABFdFaLw/It9y8LVlvkv8GiKqoNy+b8vYQ== X-ME-Sender: X-ME-Received: X-ME-Proxy-Cause: gggruggvucftvghtrhhoucdtuddrgedvkedrfedugedgkeehucetufdoteggodetrfdotf fvucfrrhhofhhilhgvmecuhfgrshhtofgrihhlpdfqfgfvpdfurfetoffkrfgpnffqhgen uceurghilhhouhhtmecufedttdenucesvcftvggtihhpihgvnhhtshculddquddttddmne cujfgurhephffvvefufffkofgjfhhrgggtgfesthekredtredtjeenucfhrhhomhepkghi ucgjrghnuceoiihirdihrghnsehsvghnthdrtghomheqnecuggftrfgrthhtvghrnhepje ekteekffelleekudfftdefvddtjeejuedtuedtteegjefgvedtfedujeekieevnecuvehl uhhsthgvrhfuihiivgeptdenucfrrghrrghmpehmrghilhhfrhhomhepiihirdihrghnse hsvghnthdrtghomh X-ME-Proxy: Feedback-ID: iccd040f4:Fastmail Received: by mail.messagingengine.com (Postfix) with ESMTPA; Fri, 2 Feb 2024 11:16:17 -0500 (EST) From: Zi Yan To: linux-mm@kvack.org, linux-kernel@vger.kernel.org Cc: Zi Yan , "Huang, Ying" , Ryan Roberts , Andrew Morton , "Matthew Wilcox (Oracle)" , David Hildenbrand , "Yin, Fengwei" , Yu Zhao , Vlastimil Babka , "Kirill A . Shutemov" , Johannes Weiner , Baolin Wang , Kemeng Shi , Mel Gorman , Rohan Puri , Mcgrof Chamberlain , Adam Manzanares , "Vishal Moola (Oracle)" Subject: [PATCH v3 3/3] mm/compaction: optimize >0 order folio compaction with free page split. Date: Fri, 2 Feb 2024 11:15:54 -0500 Message-ID: <20240202161554.565023-4-zi.yan@sent.com> X-Mailer: git-send-email 2.43.0 In-Reply-To: <20240202161554.565023-1-zi.yan@sent.com> References: <20240202161554.565023-1-zi.yan@sent.com> Reply-To: Zi Yan Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable From: Zi Yan During migration in a memory compaction, free pages are placed in an array of page lists based on their order. But the desired free page order (i.e., the order of a source page) might not be always present, thus leading to migration failures and premature compaction termination. Split a high order free pages when source migration page has a lower order to increase migration successful rate. Note: merging free pages when a migration fails and a lower order free page is returned via compaction_free() is possible, but there is too much work. Since the free pages are not buddy pages, it is hard to identify these free pages using existing PFN-based page merging algorithm. Signed-off-by: Zi Yan Reviewed-by: Baolin Wang Tested-by: Baolin Wang --- mm/compaction.c | 37 ++++++++++++++++++++++++++++++++++++- 1 file changed, 36 insertions(+), 1 deletion(-) diff --git a/mm/compaction.c b/mm/compaction.c index 58a4e3fb72ec..fa9993c8a389 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -1832,9 +1832,43 @@ static struct folio *compaction_alloc(struct folio *= src, unsigned long data) struct compact_control *cc =3D (struct compact_control *)data; struct folio *dst; int order =3D folio_order(src); + bool has_isolated_pages =3D false; =20 +again: if (!cc->freepages[order].nr_pages) { - isolate_freepages(cc); + int i; + + for (i =3D order + 1; i < NR_PAGE_ORDERS; i++) { + if (cc->freepages[i].nr_pages) { + struct page *freepage =3D + list_first_entry(&cc->freepages[i].pages, + struct page, lru); + + int start_order =3D i; + unsigned long size =3D 1 << start_order; + + list_del(&freepage->lru); + cc->freepages[i].nr_pages--; + + while (start_order > order) { + start_order--; + size >>=3D 1; + + list_add(&freepage[size].lru, + &cc->freepages[start_order].pages); + cc->freepages[start_order].nr_pages++; + set_page_private(&freepage[size], start_order); + } + dst =3D (struct folio *)freepage; + goto done; + } + } + if (!has_isolated_pages) { + isolate_freepages(cc); + has_isolated_pages =3D true; + goto again; + } + if (!cc->freepages[order].nr_pages) return NULL; } @@ -1842,6 +1876,7 @@ static struct folio *compaction_alloc(struct folio *s= rc, unsigned long data) dst =3D list_first_entry(&cc->freepages[order].pages, struct folio, lru); cc->freepages[order].nr_pages--; list_del(&dst->lru); +done: post_alloc_hook(&dst->page, order, __GFP_MOVABLE); if (order) prep_compound_page(&dst->page, order); --=20 2.43.0