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 X-Spam-Level: X-Spam-Status: No, score=-12.2 required=3.0 tests=BAYES_00, HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI,NICE_REPLY_A, SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS,UNPARSEABLE_RELAY,URIBL_BLOCKED, USER_AGENT_SANE_1 autolearn=ham autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 427B9C433DF for ; Sun, 16 Aug 2020 13:54:53 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 701EE207FB for ; Sun, 16 Aug 2020 13:54:52 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 701EE207FB Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id CFFC56B0002; Sun, 16 Aug 2020 09:54:51 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id C61A06B0005; Sun, 16 Aug 2020 09:54:51 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id B01616B0006; Sun, 16 Aug 2020 09:54:51 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0232.hostedemail.com [216.40.44.232]) by kanga.kvack.org (Postfix) with ESMTP id 954926B0002 for ; Sun, 16 Aug 2020 09:54:51 -0400 (EDT) Received: from smtpin17.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay04.hostedemail.com (Postfix) with ESMTP id 54DAB1DFA for ; Sun, 16 Aug 2020 13:54:51 +0000 (UTC) X-FDA: 77156577582.17.army55_0f0013f2700e Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin17.hostedemail.com (Postfix) with ESMTP id 29202180D0181 for ; Sun, 16 Aug 2020 13:54:51 +0000 (UTC) X-HE-Tag: army55_0f0013f2700e X-Filterd-Recvd-Size: 7855 Received: from out30-132.freemail.mail.aliyun.com (out30-132.freemail.mail.aliyun.com [115.124.30.132]) by imf47.hostedemail.com (Postfix) with ESMTP for ; Sun, 16 Aug 2020 13:54:49 +0000 (UTC) X-Alimail-AntiSpam:AC=PASS;BC=-1|-1;BR=01201311R811e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e07488;MF=alex.shi@linux.alibaba.com;NM=1;PH=DS;RN=6;SR=0;TI=SMTPD_---0U5uIxVf_1597586074; Received: from IT-FVFX43SYHV2H.lan(mailfrom:alex.shi@linux.alibaba.com fp:SMTPD_---0U5uIxVf_1597586074) by smtp.aliyun-inc.com(127.0.0.1); Sun, 16 Aug 2020 21:54:35 +0800 Subject: Re: [PATCH 1/2] mm/pageblock: mitigation cmpxchg false sharing in pageblock flags To: Matthew Wilcox Cc: Andrew Morton , Hugh Dickins , Alexander Duyck , linux-mm@kvack.org, linux-kernel@vger.kernel.org References: <1597549677-7480-1-git-send-email-alex.shi@linux.alibaba.com> <20200816040905.GF17456@casper.infradead.org> From: Alex Shi Message-ID: <112dcd31-70cf-9151-912c-da84fd6be7e9@linux.alibaba.com> Date: Sun, 16 Aug 2020 21:53:37 +0800 User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.15; rv:68.0) Gecko/20100101 Thunderbird/68.7.0 MIME-Version: 1.0 In-Reply-To: <20200816040905.GF17456@casper.infradead.org> Content-Type: text/plain; charset=gbk X-Rspamd-Queue-Id: 29202180D0181 X-Spamd-Result: default: False [0.00 / 100.00] X-Rspamd-Server: rspam04 Content-Transfer-Encoding: quoted-printable 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: =D4=DA 2020/8/16 =CF=C2=CE=E712:09, Matthew Wilcox =D0=B4=B5=C0: > On Sun, Aug 16, 2020 at 11:47:56AM +0800, Alex Shi wrote: >> +++ b/mm/page_alloc.c >> @@ -467,6 +467,8 @@ static inline int pfn_to_bitidx(struct page *page,= unsigned long pfn) >> return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS; >> } >> =20 >> +#define BITS_PER_CHAR 8 >=20 > include/linux/bits.h:#define BITS_PER_BYTE 8 Thank for reminder! >=20 >> bitmap =3D get_pageblock_bitmap(page, pfn); >> bitidx =3D pfn_to_bitidx(page, pfn); >> - word_bitidx =3D bitidx / BITS_PER_LONG; >> - bitidx &=3D (BITS_PER_LONG-1); >> + word_bitidx =3D bitidx / BITS_PER_CHAR; >> + bitidx &=3D (BITS_PER_CHAR-1); >=20 > It's not a word any more. it's a byte. >=20 Yes, will change this. Thanks! >From 963425639f56c1ba1c997653a4ff6885c81dc0ab Mon Sep 17 00:00:00 2001 From: Alex Shi Date: Sat, 15 Aug 2020 22:54:17 +0800 Subject: [PATCH 1/2] mm/pageblock: mitigation cmpxchg false sharing in pageblock flags pageblock_flags is used as long, since every pageblock_flags is just 4 bits, 'long' size will include 8(32bit machine) or 16 pageblocks' flags, that flag setting has to sync in cmpxchg with 7 or 15 other pageblock flags. It would cause long waiting for sync. If we could change the pageblock_flags variable as char, we could use char size cmpxchg, which just sync up with 2 pageblock flags. it could relief much false sharing in cmpxchg. Signed-off-by: Alex Shi Cc: Andrew Morton Cc: Hugh Dickins Cc: Alexander Duyck Cc: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org --- include/linux/mmzone.h | 6 +++--- include/linux/pageblock-flags.h | 2 +- mm/page_alloc.c | 38 +++++++++++++++++++----------------= --- 3 files changed, 23 insertions(+), 23 deletions(-) diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 0ed520954843..c92d6d24527d 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -438,7 +438,7 @@ struct zone { * Flags for a pageblock_nr_pages block. See pageblock-flags.h. * In SPARSEMEM, this map is stored in struct mem_section */ - unsigned long *pageblock_flags; + unsigned char *pageblock_flags; #endif /* CONFIG_SPARSEMEM */ =20 /* zone_start_pfn =3D=3D zone_start_paddr >> PAGE_SHIFT */ @@ -1159,7 +1159,7 @@ struct mem_section_usage { DECLARE_BITMAP(subsection_map, SUBSECTIONS_PER_SECTION); #endif /* See declaration of similar field in struct zone */ - unsigned long pageblock_flags[0]; + unsigned char pageblock_flags[0]; }; =20 void subsection_map_init(unsigned long pfn, unsigned long nr_pages); @@ -1212,7 +1212,7 @@ struct mem_section { extern struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROO= T]; #endif =20 -static inline unsigned long *section_to_usemap(struct mem_section *ms) +static inline unsigned char *section_to_usemap(struct mem_section *ms) { return ms->usage->pageblock_flags; } diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-fl= ags.h index fff52ad370c1..d189441568eb 100644 --- a/include/linux/pageblock-flags.h +++ b/include/linux/pageblock-flags.h @@ -54,7 +54,7 @@ enum pageblock_bits { /* Forward declaration */ struct page; =20 -unsigned long get_pfnblock_flags_mask(struct page *page, +unsigned char get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long mask); =20 diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 66d45e9cc358..eb5cca7e8683 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -447,7 +447,7 @@ static inline bool defer_init(int nid, unsigned long = pfn, unsigned long end_pfn) #endif =20 /* Return a pointer to the bitmap storing bits affecting a block of page= s */ -static inline unsigned long *get_pageblock_bitmap(struct page *page, +static inline unsigned char *get_pageblock_bitmap(struct page *page, unsigned long pfn) { #ifdef CONFIG_SPARSEMEM @@ -476,24 +476,24 @@ static inline int pfn_to_bitidx(struct page *page, = unsigned long pfn) * Return: pageblock_bits flags */ static __always_inline -unsigned long __get_pfnblock_flags_mask(struct page *page, +unsigned char __get_pfnblock_flags_mask(struct page *page, unsigned long pfn, unsigned long mask) { - unsigned long *bitmap; - unsigned long bitidx, word_bitidx; - unsigned long word; + unsigned char *bitmap; + unsigned long bitidx, byte_bitidx; + unsigned char byte; =20 bitmap =3D get_pageblock_bitmap(page, pfn); bitidx =3D pfn_to_bitidx(page, pfn); - word_bitidx =3D bitidx / BITS_PER_LONG; - bitidx &=3D (BITS_PER_LONG-1); + byte_bitidx =3D bitidx / BITS_PER_BYTE; + bitidx &=3D (BITS_PER_BYTE-1); =20 - word =3D bitmap[word_bitidx]; - return (word >> bitidx) & mask; + byte =3D bitmap[byte_bitidx]; + return (byte >> bitidx) & mask; } =20 -unsigned long get_pfnblock_flags_mask(struct page *page, unsigned long p= fn, +unsigned char get_pfnblock_flags_mask(struct page *page, unsigned long p= fn, unsigned long mask) { return __get_pfnblock_flags_mask(page, pfn, mask); @@ -515,29 +515,29 @@ void set_pfnblock_flags_mask(struct page *page, uns= igned long flags, unsigned long pfn, unsigned long mask) { - unsigned long *bitmap; - unsigned long bitidx, word_bitidx; - unsigned long old_word, word; + unsigned char *bitmap; + unsigned long bitidx, byte_bitidx; + unsigned char old_byte, byte; =20 BUILD_BUG_ON(NR_PAGEBLOCK_BITS !=3D 4); BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits)); =20 bitmap =3D get_pageblock_bitmap(page, pfn); bitidx =3D pfn_to_bitidx(page, pfn); - word_bitidx =3D bitidx / BITS_PER_LONG; - bitidx &=3D (BITS_PER_LONG-1); + byte_bitidx =3D bitidx / BITS_PER_BYTE; + bitidx &=3D (BITS_PER_BYTE-1); =20 VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page); =20 mask <<=3D bitidx; flags <<=3D bitidx; =20 - word =3D READ_ONCE(bitmap[word_bitidx]); + byte =3D READ_ONCE(bitmap[byte_bitidx]); for (;;) { - old_word =3D cmpxchg(&bitmap[word_bitidx], word, (word & ~mask) | flag= s); - if (word =3D=3D old_word) + old_byte =3D cmpxchg(&bitmap[byte_bitidx], byte, (byte & ~mask) | flag= s); + if (byte =3D=3D old_byte) break; - word =3D old_word; + byte =3D old_byte; } } =20 --=20 1.8.3.1