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=-6.8 required=3.0 tests=DKIM_INVALID,DKIM_SIGNED, INCLUDES_PATCH,MAILING_LIST_MULTI,SIGNED_OFF_BY,SPF_HELO_NONE,SPF_PASS 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 7CEA1C433E1 for ; Fri, 12 Jun 2020 06:55:31 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 1FDBC2081A for ; Fri, 12 Jun 2020 06:55:31 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="FJeL4Xfj" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 1FDBC2081A Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id A58668D00B0; Fri, 12 Jun 2020 02:55:30 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 9E27A8D00A0; Fri, 12 Jun 2020 02:55:30 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 8A9F38D00B0; Fri, 12 Jun 2020 02:55:30 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0071.hostedemail.com [216.40.44.71]) by kanga.kvack.org (Postfix) with ESMTP id 6C50C8D00A0 for ; Fri, 12 Jun 2020 02:55:30 -0400 (EDT) Received: from smtpin01.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay02.hostedemail.com (Postfix) with ESMTP id 3286C3578 for ; Fri, 12 Jun 2020 06:55:30 +0000 (UTC) X-FDA: 76919648820.01.bead75_4609f8d26dda Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin01.hostedemail.com (Postfix) with ESMTP id 0FDCC100079813B2 for ; Fri, 12 Jun 2020 06:55:30 +0000 (UTC) X-HE-Tag: bead75_4609f8d26dda X-Filterd-Recvd-Size: 15786 Received: from mail-pf1-f195.google.com (mail-pf1-f195.google.com [209.85.210.195]) by imf36.hostedemail.com (Postfix) with ESMTP for ; Fri, 12 Jun 2020 06:55:28 +0000 (UTC) Received: by mail-pf1-f195.google.com with SMTP id b201so3880576pfb.0 for ; Thu, 11 Jun 2020 23:55:28 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=sender:date:from:to:cc:subject:message-id:references:mime-version :content-disposition:content-transfer-encoding:in-reply-to; bh=Msr6j+i/oK2m1UNmnFHEzKgiyHbN6yqCm78HBbqt4HU=; b=FJeL4Xfjd0el49u2vPvrRmTmZ1d31iTzd4rI6VoJj7X53kcpPBDStlfB/ioXqrVf7O crnFRa/1UXM3/5l12CcvZfOPxInTRiBsIgIMmccOkf8cp4AZBQpqqAmfS6N1KrB4u+Zb 7B+K5WgQRSfjm+UYNRhDoxRFEWvo/CY89JZWdLiwzpZWmnYabcedz5ts+3m999g8a2/t fYQpMJT/9hGUmLSxtt5Hv1nrVU3dMxw6+R/ttFSLKtKdV6z2jJ9OtuLm6VYHFhiLM3ua athbrin5shiMIPrq+HwY1bDnRlDf4ouxBEapB22zaWB8rR7VTs87e/VYm2fGH8ZFalwu 7ZgA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:sender:date:from:to:cc:subject:message-id :references:mime-version:content-disposition :content-transfer-encoding:in-reply-to; bh=Msr6j+i/oK2m1UNmnFHEzKgiyHbN6yqCm78HBbqt4HU=; b=Q9iPQ3X1OC/xBeOVkqSQ+7Bzf6SLznLvV/XZLdW+nUyMA2R3gtfGHDZP4PeNN3PN4i f+ez96Xh4iKEaic/loBi/jptKKxCvZ+G3DRi2NVYyt72nzU8q1L2YtdallGJi/Oai8xh ehY0G+XhPSqmcSmq/VR/gyMC9krm3ZgkatvHXyuGswLqai1f2Mk1NHf4mUzQiWVCOuxl KXFQnP414J2PCGZWYdQiE9C5MMIzgprMrVI845WkidQOGeaUMNdEaq/MvtqFK7C724bE lYmXyz8OrnXHrY2MhOZ485nv98rTSIP+ox3oh/U2x2bwts0MAePaAsPvpvdZihwYqbcO nZGg== X-Gm-Message-State: AOAM530xLvxGenCqKrOqsiLudUke4ZRt/uaCL+rQPgSoQmrNyRDmY6Lw xgauN+zkyqQ41qT5EGCZbb4= X-Google-Smtp-Source: ABdhPJwxV/+Hq5RTNJJMPq7vG1vl0xmp6yfP6ogiuimt2sevan3BEi9c48HUpzaCO4CdLq91cG+4sg== X-Received: by 2002:aa7:9af0:: with SMTP id y16mr11028536pfp.231.1591944927693; Thu, 11 Jun 2020 23:55:27 -0700 (PDT) Received: from google.com ([2601:647:4001:3000::e690]) by smtp.gmail.com with ESMTPSA id i3sm4373739pjv.1.2020.06.11.23.55.25 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 11 Jun 2020 23:55:26 -0700 (PDT) Date: Thu, 11 Jun 2020 23:55:23 -0700 From: Minchan Kim To: Jaewon Kim Cc: mgorman@techsingularity.net, mgorman@suse.de, hannes@cmpxchg.org, akpm@linux-foundation.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org, jaewon31.kim@gmail.com, ytk.lee@samsung.com, cmlaika.kim@samsung.com Subject: Re: [PATCH] page_alloc: consider highatomic reserve in wmartermark fast Message-ID: <20200612065523.GA92598@google.com> References: <20200609095128.8112-1-jaewon31.kim@samsung.com> <20200610012112.GA239587@google.com> <5EE1F134.4090001@samsung.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: <5EE1F134.4090001@samsung.com> X-Rspamd-Queue-Id: 0FDCC100079813B2 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: On Thu, Jun 11, 2020 at 05:54:12PM +0900, Jaewon Kim wrote: >=20 >=20 > On 2020=EB=85=84 06=EC=9B=94 10=EC=9D=BC 10:21, Minchan Kim wrote: > > Hi Jaewon, > > > > On Tue, Jun 09, 2020 at 06:51:28PM +0900, Jaewon Kim wrote: > >> zone_watermark_fast was introduced by commit 48ee5f3696f6 ("mm, > >> page_alloc: shortcut watermark checks for order-0 pages"). The commi= t > >> simply checks if free pages is bigger than watermark without additio= nal > >> calculation such like reducing watermark. > >> > >> It considered free cma pages but it did not consider highatomic > >> reserved. This may incur exhaustion of free pages except high order > >> atomic free pages. > >> > >> Assume that reserved_highatomic pageblock is bigger than watermark m= in, > >> and there are only few free pages except high order atomic free. Bec= ause > >> zone_watermark_fast passes the allocation without considering high o= rder > >> atomic free, normal reclaimable allocation like GFP_HIGHUSER will > >> consume all the free pages. Then finally order-0 atomic allocation m= ay > >> fail on allocation. > >> > >> This means watermark min is not protected against non-atomic allocat= ion. > >> The order-0 atomic allocation with ALLOC_HARDER unwantedly can be > >> failed. Additionally the __GFP_MEMALLOC allocation with > >> ALLOC_NO_WATERMARKS also can be failed. > >> > >> To avoid the problem, zone_watermark_fast should consider highatomic > >> reserve. If the actual size of high atomic free is counted accuratel= y > >> like cma free, we may use it. On this patch just use > >> nr_reserved_highatomic. > >> > >> This is trace log which shows GFP_HIGHUSER consumes free pages right > >> before ALLOC_NO_WATERMARKS. > >> > >> <...>-22275 [006] .... 889.213383: mm_page_alloc: page=3D0000000= 0d2be5665 pfn=3D970744 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> <...>-22275 [006] .... 889.213385: mm_page_alloc: page=3D0000000= 04b2335c2 pfn=3D970745 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> <...>-22275 [006] .... 889.213387: mm_page_alloc: page=3D0000000= 0017272e1 pfn=3D970278 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> <...>-22275 [006] .... 889.213389: mm_page_alloc: page=3D0000000= 0c4be79fb pfn=3D970279 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> <...>-22275 [006] .... 889.213391: mm_page_alloc: page=3D0000000= 0f8a51d4f pfn=3D970260 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> <...>-22275 [006] .... 889.213393: mm_page_alloc: page=3D0000000= 06ba8f5ac pfn=3D970261 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> <...>-22275 [006] .... 889.213395: mm_page_alloc: page=3D0000000= 0819f1cd3 pfn=3D970196 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> <...>-22275 [006] .... 889.213396: mm_page_alloc: page=3D0000000= 0f6b72a64 pfn=3D970197 order=3D0 migratetype=3D0 nr_free=3D3650 gfp_flags= =3DGFP_HIGHUSER|__GFP_ZERO > >> kswapd0-1207 [005] ...1 889.213398: mm_page_alloc: page=3D (null)= pfn=3D0 order=3D0 migratetype=3D1 nr_free=3D3650 gfp_flags=3DGFP_NOWAIT|= __GFP_HIGHMEM|__GFP_NOWARN|__GFP_MOVABLE > >> > >> This is an example of ALLOC_HARDER allocation failure. > >> > >> <4>[ 6207.637280] [3: Binder:9343_3:22875] Binder:9343_3: page all= ocation failure: order:0, mode:0x480020(GFP_ATOMIC), nodemask=3D(null) > >> <4>[ 6207.637311] [3: Binder:9343_3:22875] Call trace: > >> <4>[ 6207.637346] [3: Binder:9343_3:22875] [] du= mp_stack+0xb8/0xf0 > >> <4>[ 6207.637356] [3: Binder:9343_3:22875] [] wa= rn_alloc+0xd8/0x12c > >> <4>[ 6207.637365] [3: Binder:9343_3:22875] [] __= alloc_pages_nodemask+0x120c/0x1250 > >> <4>[ 6207.637374] [3: Binder:9343_3:22875] [] ne= w_slab+0x128/0x604 > >> <4>[ 6207.637381] [3: Binder:9343_3:22875] [] __= _slab_alloc+0x508/0x670 > >> <4>[ 6207.637387] [3: Binder:9343_3:22875] [] __= kmalloc+0x2f8/0x310 > >> <4>[ 6207.637396] [3: Binder:9343_3:22875] [] co= ntext_struct_to_string+0x104/0x1cc > >> <4>[ 6207.637404] [3: Binder:9343_3:22875] [] se= curity_sid_to_context_core+0x74/0x144 > >> <4>[ 6207.637412] [3: Binder:9343_3:22875] [] se= curity_sid_to_context+0x10/0x18 > >> <4>[ 6207.637421] [3: Binder:9343_3:22875] [] se= linux_secid_to_secctx+0x20/0x28 > >> <4>[ 6207.637430] [3: Binder:9343_3:22875] [] se= curity_secid_to_secctx+0x3c/0x70 > >> <4>[ 6207.637442] [3: Binder:9343_3:22875] [] bi= nder_transaction+0xe68/0x454c > >> <4>[ 6207.637569] [3: Binder:9343_3:22875] Mem-Info: > >> <4>[ 6207.637595] [3: Binder:9343_3:22875] active_anon:102061 inac= tive_anon:81551 isolated_anon:0 > >> <4>[ 6207.637595] [3: Binder:9343_3:22875] active_file:59102 inac= tive_file:68924 isolated_file:64 > >> <4>[ 6207.637595] [3: Binder:9343_3:22875] unevictable:611 dirty:= 63 writeback:0 unstable:0 > >> <4>[ 6207.637595] [3: Binder:9343_3:22875] slab_reclaimable:13324= slab_unreclaimable:44354 > >> <4>[ 6207.637595] [3: Binder:9343_3:22875] mapped:83015 shmem:485= 8 pagetables:26316 bounce:0 > >> <4>[ 6207.637595] [3: Binder:9343_3:22875] free:2727 free_pcp:103= 5 free_cma:178 > >> <4>[ 6207.637616] [3: Binder:9343_3:22875] Node 0 active_anon:4082= 44kB inactive_anon:326204kB active_file:236408kB inactive_file:275696kB u= nevictable:2444kB isolated(anon):0kB isolated(file):256kB mapped:332060kB= dirty:252kB writeback:0kB shmem:19432kB writeback_tmp:0kB unstable:0kB a= ll_unreclaimable? no > >> <4>[ 6207.637627] [3: Binder:9343_3:22875] Normal free:10908kB min= :6192kB low:44388kB high:47060kB active_anon:409160kB inactive_anon:32592= 4kB active_file:235820kB inactive_file:276628kB unevictable:2444kB writep= ending:252kB present:3076096kB managed:2673676kB mlocked:2444kB kernel_st= ack:62512kB pagetables:105264kB bounce:0kB free_pcp:4140kB local_pcp:40kB= free_cma:712kB > >> <4>[ 6207.637632] [3: Binder:9343_3:22875] lowmem_reserve[]: 0 0 > >> <4>[ 6207.637637] [3: Binder:9343_3:22875] Normal: 505*4kB (H) 357= *8kB (H) 201*16kB (H) 65*32kB (H) 1*64kB (H) 0*128kB 0*256kB 0*512kB 0*10= 24kB 0*2048kB 0*4096kB =3D 10236kB > >> <4>[ 6207.637655] [3: Binder:9343_3:22875] 138826 total pagecache = pages > >> <4>[ 6207.637663] [3: Binder:9343_3:22875] 5460 pages in swap cach= e > >> <4>[ 6207.637668] [3: Binder:9343_3:22875] Swap cache stats: add 8= 273090, delete 8267506, find 1004381/4060142 > >> > >> This is an example of ALLOC_NO_WATERMARKS allocation failure. > >> > >> <6>[ 156.701551] [4: kswapd0: 1209] kswapd0 cpuset=3D/ mems= _allowed=3D0 > >> <4>[ 156.701563] [4: kswapd0: 1209] CPU: 4 PID: 1209 Comm: = kswapd0 Tainted: G W 4.14.113-18113966 #1 > >> <4>[ 156.701572] [4: kswapd0: 1209] Call trace: > >> <4>[ 156.701605] [4: kswapd0: 1209] [<0000000000000000>] du= mp_stack+0x68/0x90 > >> <4>[ 156.701612] [4: kswapd0: 1209] [<0000000000000000>] wa= rn_alloc+0x104/0x198 > >> <4>[ 156.701617] [4: kswapd0: 1209] [<0000000000000000>] __= alloc_pages_nodemask+0xdc0/0xdf0 > >> <4>[ 156.701623] [4: kswapd0: 1209] [<0000000000000000>] zs= _malloc+0x148/0x3d0 > >> <4>[ 156.701630] [4: kswapd0: 1209] [<0000000000000000>] zr= am_bvec_rw+0x250/0x568 > >> <4>[ 156.701634] [4: kswapd0: 1209] [<0000000000000000>] zr= am_rw_page+0x8c/0xe0 > >> <4>[ 156.701640] [4: kswapd0: 1209] [<0000000000000000>] bd= ev_write_page+0x70/0xbc > >> <4>[ 156.701645] [4: kswapd0: 1209] [<0000000000000000>] __= swap_writepage+0x58/0x37c > >> <4>[ 156.701649] [4: kswapd0: 1209] [<0000000000000000>] sw= ap_writepage+0x40/0x4c > >> <4>[ 156.701654] [4: kswapd0: 1209] [<0000000000000000>] sh= rink_page_list+0xc3c/0xf54 > >> <4>[ 156.701659] [4: kswapd0: 1209] [<0000000000000000>] sh= rink_inactive_list+0x2b0/0x61c > >> <4>[ 156.701664] [4: kswapd0: 1209] [<0000000000000000>] sh= rink_node_memcg+0x23c/0x618 > >> <4>[ 156.701668] [4: kswapd0: 1209] [<0000000000000000>] sh= rink_node+0x1c8/0x304 > >> <4>[ 156.701673] [4: kswapd0: 1209] [<0000000000000000>] ks= wapd+0x680/0x7c4 > >> <4>[ 156.701679] [4: kswapd0: 1209] [<0000000000000000>] kt= hread+0x110/0x120 > >> <4>[ 156.701684] [4: kswapd0: 1209] [<0000000000000000>] re= t_from_fork+0x10/0x18 > >> <4>[ 156.701689] [4: kswapd0: 1209] Mem-Info: > >> <4>[ 156.701712] [4: kswapd0: 1209] active_anon:88690 inact= ive_anon:88630 isolated_anon:0 > >> <4>[ 156.701712] [4: kswapd0: 1209] active_file:99173 inac= tive_file:169305 isolated_file:32 > >> <4>[ 156.701712] [4: kswapd0: 1209] unevictable:48292 dirt= y:538 writeback:38 unstable:0 > >> <4>[ 156.701712] [4: kswapd0: 1209] slab_reclaimable:15131= slab_unreclaimable:47762 > >> <4>[ 156.701712] [4: kswapd0: 1209] mapped:274654 shmem:28= 24 pagetables:25088 bounce:0 > >> <4>[ 156.701712] [4: kswapd0: 1209] free:2489 free_pcp:444= free_cma:3 > >> <4>[ 156.701728] [4: kswapd0: 1209] Node 0 active_anon:3547= 60kB inactive_anon:354520kB active_file:396692kB inactive_file:677220kB u= nevictable:193168kB isolated(anon):0kB isolated(file):128kB mapped:109861= 6kB dirty:2152kB writeback:152kB shmem:11296kB writeback_tmp:0kB unstable= :0kB all_unreclaimable? no > >> <4>[ 156.701738] [4: kswapd0: 1209] Normal free:9956kB min:= 7428kB low:93440kB high:97032kB active_anon:355176kB inactive_anon:354580= kB active_file:396196kB inactive_file:677284kB unevictable:193168kB write= pending:2304kB present:4081664kB managed:3593324kB mlocked:193168kB kerne= l_stack:55008kB pagetables:100352kB bounce:0kB free_pcp:1776kB local_pcp:= 656kB free_cma:12kB > >> <4>[ 156.701741] [4: kswapd0: 1209] lowmem_reserve[]: 0 0 > >> <4>[ 156.701747] [4: kswapd0: 1209] Normal: 196*4kB (H) 141= *8kB (H) 109*16kB (H) 63*32kB (H) 20*64kB (H) 8*128kB (H) 2*256kB (H) 1*5= 12kB (H) 0*1024kB 0*2048kB 0*4096kB =3D 9000kB > >> > >> Signed-off-by: Jaewon Kim > >> Reported-by: Yong-Taek Lee > >> --- > >> mm/page_alloc.c | 13 +++++++++++-- > >> 1 file changed, 11 insertions(+), 2 deletions(-) > >> > >> diff --git a/mm/page_alloc.c b/mm/page_alloc.c > >> index 13cc653122b7..00869378d387 100644 > >> --- a/mm/page_alloc.c > >> +++ b/mm/page_alloc.c > >> @@ -3553,6 +3553,11 @@ static inline bool zone_watermark_fast(struct= zone *z, unsigned int order, > >> { > >> long free_pages =3D zone_page_state(z, NR_FREE_PAGES); > >> long cma_pages =3D 0; > >> + long highatomic =3D 0; > >> + const bool alloc_harder =3D (alloc_flags & (ALLOC_HARDER|ALLOC_OOM= )); > >> + > >> + if (likely(!alloc_harder)) > >> + highatomic =3D z->nr_reserved_highatomic; > >> =20 > >> #ifdef CONFIG_CMA > >> /* If allocation can't use CMA areas don't use free CMA pages */ > >> @@ -3567,8 +3572,12 @@ static inline bool zone_watermark_fast(struct= zone *z, unsigned int order, > >> * the caller is !atomic then it'll uselessly search the free > >> * list. That corner case is then slower but it is harmless. > >> */ > >> - if (!order && (free_pages - cma_pages) > mark + z->lowmem_reserve[= classzone_idx]) > >> - return true; > >> + if (!order) { > >> + long fast_free =3D free_pages - cma_pages - highatomic; > > > > With your change, it seems we share most code for getting free_pages=20 > > between zone_watermark_fast and __zone_watermark_ok. Only difference > > between them is min calculation. If so, can we share most code betwee= n > > them via introducing like __zone_watermark_free static inline functio= n? > > So, we didn't miss one place in future if we change something. > > > Hello thank you for your comment. >=20 > I tried to share some code. > Because __zone_watermark_ok gets free pages as argument, > I just could make a function calculating unusable free. >=20 > static inline long __zone_watermark_unusable_free(struct zone *z, > unsigned int alloc_= flags) >=20 > on zone_watermark_fast > free_pages -=3D __zone_watermark_unusable_free(z, alloc_flags); >=20 > on __zone_watermark_ok > free_pages -=3D __zone_watermark_unusable_free(z, alloc_flags); Don't you need order argument? Anyway, it looks good to me. Thanks!