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]) by smtp.lore.kernel.org (Postfix) with ESMTP id C307FC636D6 for ; Fri, 10 Feb 2023 02:51:16 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id EF4F56B00D9; Thu, 9 Feb 2023 21:51:15 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id E7E2F6B00DB; Thu, 9 Feb 2023 21:51:15 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id D1E946B00DC; Thu, 9 Feb 2023 21:51:15 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0013.hostedemail.com [216.40.44.13]) by kanga.kvack.org (Postfix) with ESMTP id BB7EA6B00D9 for ; Thu, 9 Feb 2023 21:51:15 -0500 (EST) Received: from smtpin15.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay01.hostedemail.com (Postfix) with ESMTP id 825581C6B64 for ; Fri, 10 Feb 2023 02:51:15 +0000 (UTC) X-FDA: 80449855710.15.34B4FDF Received: from out-109.mta1.migadu.com (out-109.mta1.migadu.com [95.215.58.109]) by imf19.hostedemail.com (Postfix) with ESMTP id 7BEB71A0011 for ; Fri, 10 Feb 2023 02:51:13 +0000 (UTC) Authentication-Results: imf19.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=xGCaTyzo; spf=pass (imf19.hostedemail.com: domain of yajun.deng@linux.dev designates 95.215.58.109 as permitted sender) smtp.mailfrom=yajun.deng@linux.dev; dmarc=pass (policy=none) header.from=linux.dev ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1675997473; 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=AHgREwhLRCk8vMbrhrQBJ0zTZ03LfJvnd0UiicWdo8k=; b=LSoUQyOBaSEn8D5UN6BLq4D66IxiFaN30kELgStp7tzgzBtqBi6Sp3dEmVATnxfd1ZEEFe s6bTeSnDQqk+cwlBAV6bNhDSthwDLevAKDvxlTRTnwKsvY8DBNwICWtZvBUGOaiLXJIRGc hFYIdK+D3KS+1VYXoRLmsubhL5neMis= ARC-Authentication-Results: i=1; imf19.hostedemail.com; dkim=pass header.d=linux.dev header.s=key1 header.b=xGCaTyzo; spf=pass (imf19.hostedemail.com: domain of yajun.deng@linux.dev designates 95.215.58.109 as permitted sender) smtp.mailfrom=yajun.deng@linux.dev; dmarc=pass (policy=none) header.from=linux.dev ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1675997473; a=rsa-sha256; cv=none; b=4Var2zKYXguhPPpXCf4JKsarO/nymtt/9jljVUu+S2x4bYRwB+S81iXPXHyIqKOjoya90i nmfz5W+0vUQO6KufV2IwyzTyvH9BUvkWIdaONNGJfHFdXwYzp3t7cnT+eXJy67lL+SCP1H kUK+7rJIc0opR77SX6wcj992QmXweAw= MIME-Version: 1.0 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.dev; s=key1; t=1675997471; h=from:from: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; bh=AHgREwhLRCk8vMbrhrQBJ0zTZ03LfJvnd0UiicWdo8k=; b=xGCaTyzoq+vrRO4mVJgaqDdS6ow/C0VQ47t2zQq1pEtSpJUvo/XmDodD48RAUgFCuAMtOy glIYrIdjnithUBJvBFDxW/e0fTlIdPRX0rB1ZN4CfQJzwOWYlViT31gYVx/fu32IUkOCMQ f28ocdjcP59woRKDdMntU1Yw7qR7Tv0= Date: Fri, 10 Feb 2023 02:51:06 +0000 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Report-Abuse: Please report any abuse attempt to abuse@migadu.com and include these headers. From: "Yajun Deng" Message-ID: Subject: Re: [PATCH v2] mm/page_alloc: optimize find_suitable_fallback() and fallbacks array To: "Zi Yan" Cc: akpm@linux-foundation.org, mgorman@techsingularity.net, david@redhat.com, vbabka@suse.cz, rppt@linux.ibm.com, osalvador@suse.de, rppt@kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org In-Reply-To: <626a5f4c4996f57631a8e1877c7646e5@linux.dev> References: <626a5f4c4996f57631a8e1877c7646e5@linux.dev> <494D9F5D-33A4-48B4-911B-9A75CFC9BC67@nvidia.com> <4C196D76-49A9-4B06-A51F-D8A13109DF3B@nvidia.com> <20230209101144.496144-1-yajun.deng@linux.dev> X-Migadu-Flow: FLOW_OUT X-Stat-Signature: j85o5uz6iguazmigqrm3bkyiseb9dq9b X-Rspam-User: X-Rspamd-Queue-Id: 7BEB71A0011 X-Rspamd-Server: rspam06 X-HE-Tag: 1675997473-501059 X-HE-Meta: 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 y0SDke51 X9N8Y45DSnMglMG1D8VTYLuGeZIGwudfaiKDEqjsE7lkhCxA8/G4FOnOO4rrj314lvoyXSvKUnO56mSxpkaL4xlY5XAG5P0a75LkcNWgv16jK56BbNi0wjOkielvKD1k75s8g818YauOTWXRK6o7K1pAyIJ5v/liomHvpYY2278ChAtvWGizABrDnTKvKmRuA1nJKuMFprAFyAm9FD0BB/maq01UYzR4CQRmz 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: February 10, 2023 10:33 AM, "Yajun Deng" wrote:=0A= =0A> February 10, 2023 10:14 AM, "Zi Yan" wrote:=0A> =0A= >> On 9 Feb 2023, at 20:57, Yajun Deng wrote:=0A>> =0A>>> February 9, 202= 3 11:50 PM, "Zi Yan" wrote:=0A>> =0A>> On 9 Feb 2023, at= 5:11, Yajun Deng wrote:=0A>>> There is no need to execute the next loop = if it not return in the first=0A>>> loop. So add a break at the end of th= e loop.=0A>> =0A>> Can you explain why? If it is the case, MIGRATE_UNMOVA= BLE cannot fall back=0A>> to MIGRATE_MOVABLE? And MIGRATE_MOVABLE cannot = fall back to MIGRATE_UNMOVABLE?=0A>> And MIGRATE_RECLAIMABLE cannot fall = back to MIGRATE_MOVABLE?=0A>>> The return in the loop is only related to = 'order', 'migratetype' and 'only_stealable'=0A>>> variables. Even if it e= xecute the next loop, it can't change the result. So the loop=0A>>> can b= e broken if the first loop can't return.=0A>> =0A>> OK. Got it. Would the= code below look better?=0A>> =0A>> for (i =3D 0; i < MIGRATE_PCPTYPES - = 1 ; i++) {=0A>> fallback_mt =3D fallbacks[migratetype][i];=0A>> if (free_= area_empty(area, fallback_mt))=0A>> continue;=0A>> }=0A>> =0A>> if (can_s= teal_fallback(order, migratetype))=0A>> *can_steal =3D true;=0A>> =0A>> i= f (!only_stealable || *can_steal)=0A>> return fallback_mt;=0A>> =0A>> ret= urn -1;=0A> =0A> Yes, I'll submit a v3 patch.=0A> Thanks.=0A> =0A=0AI fou= nd a logical error in your code. It should be like this:=0A=0A for= (i =3D 0; i < MIGRATE_PCPTYPES - 1 ; i++) {=0A fallback_m= t =3D fallbacks[migratetype][i];=0A if (!free_area_empty(a= rea, fallback_mt))=0A break;=0A }=0A=0A = if (can_steal_fallback(order, migratetype))=0A *can_st= eal =3D true;=0A=0A if (!only_stealable || *can_steal)=0A = return fallback_mt;=0A=0A return -1;=0A=0AThis code will mo= dify the logic to the opposite.=0ASo can anyone tell me if I should use t= his code or the v2 patch?=0A=0A=0A>>> At the same time, add !migratetype_= is_mergeable() before the loop and=0A>>> reduce the first index size from= MIGRATE_TYPES to MIGRATE_PCPTYPES in=0A>>> fallbacks array.=0A>> =0A>> Y= ou sent a patch: https://lore.kernel.org/all/20230203100132.1627787-1-yaj= un.deng@linux.dev/T/#u,=0A>> why not squash this one into that? Why do=0A= >> we need two separate small patches working on the same code?=0A>>> Yes= , this is better, but I overlooked this one when I sent the first patch. = It is already merged.=0A>>> =0A>>> As Vlastimil Babka said, reduce the fi= rst index from MIGRATE_TYPES to MIGRATE_PCPTYPES may be=0A>>> cause out o= f bounds access of the shrinked fallbacks array If we don't judge the ran= ge of=0A>>> migratetype. But this doesn't happen with the second index.= =0A>> =0A>> Thanks.=0A>>> Signed-off-by: Yajun Deng =0A>>> Acked-by: Vlastimil Babka =0A>>> ---=0A>>> includ= e/linux/mmzone.h | 2 +-=0A>>> mm/page_alloc.c | 11 +++++------=0A>>> 2 fi= les changed, 6 insertions(+), 7 deletions(-)=0A>>> =0A>>> diff --git a/in= clude/linux/mmzone.h b/include/linux/mmzone.h=0A>>> index ab94985ee7d9..0= a817b8c7fb2 100644=0A>>> --- a/include/linux/mmzone.h=0A>>> +++ b/include= /linux/mmzone.h=0A>>> @@ -85,7 +85,7 @@ static inline bool is_migrate_mov= able(int mt)=0A>>> * Check whether a migratetype can be merged with anoth= er migratetype.=0A>>> *=0A>>> * It is only mergeable when it can fall bac= k to other migratetypes for=0A>>> - * allocation. See fallbacks[MIGRATE_T= YPES][3] in page_alloc.c.=0A>>> + * allocation. See fallbacks[][] array i= n page_alloc.c.=0A>>> */=0A>>> static inline bool migratetype_is_mergeabl= e(int mt)=0A>>> {=0A>>> diff --git a/mm/page_alloc.c b/mm/page_alloc.c=0A= >>> index 1113483fa6c5..536e8d838fb5 100644=0A>>> --- a/mm/page_alloc.c= =0A>>> +++ b/mm/page_alloc.c=0A>>> @@ -2603,7 +2603,7 @@ struct page *__r= mqueue_smallest(struct zone *zone, unsigned int order,=0A>>> *=0A>>> * Th= e other migratetypes do not have fallbacks.=0A>>> */=0A>>> -static int fa= llbacks[MIGRATE_TYPES][MIGRATE_PCPTYPES - 1] =3D {=0A>>> +static int fall= backs[MIGRATE_PCPTYPES][MIGRATE_PCPTYPES - 1] =3D {=0A>>> [MIGRATE_UNMOVA= BLE] =3D { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE },=0A>>> [MIGRATE_MOVABLE= ] =3D { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE },=0A>>> [MIGRATE_RECLAIMA= BLE] =3D { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE },=0A>>> @@ -2861,7 +2861,7= @@ int find_suitable_fallback(struct free_area *area, unsigned int order= ,=0A>>> int i;=0A>>> int fallback_mt;=0A>>> =0A>>> - if (area->nr_free = =3D=3D 0)=0A>>> + if (area->nr_free =3D=3D 0 || !migratetype_is_mergeable= (migratetype))=0A>>> return -1;=0A>>> =0A>>> *can_steal =3D false;=0A>>> = @@ -2873,11 +2873,10 @@ int find_suitable_fallback(struct free_area *area= , unsigned int order,=0A>>> if (can_steal_fallback(order, migratetype))= =0A>>> *can_steal =3D true;=0A>>> =0A>>> - if (!only_stealable)=0A>>> - r= eturn fallback_mt;=0A>>> -=0A>>> - if (*can_steal)=0A>>> + if (!only_stea= lable || *can_steal)=0A>>> return fallback_mt;=0A>>> + else=0A>>> + break= ;=0A>>> }=0A>>> =0A>>> return -1;=0A>>> --=0A>>> 2.25.1=0A>> =0A>> --=0A>= > Best Regards,=0A>> Yan, Zi=0A>> =0A>> --=0A>> Best Regards,=0A>> Yan, Z= i