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 F063FC77B7D for ; Mon, 15 May 2023 06:36:21 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 7D941900003; Mon, 15 May 2023 02:36:21 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 788ED900002; Mon, 15 May 2023 02:36:21 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 6511C900003; Mon, 15 May 2023 02:36:21 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0014.hostedemail.com [216.40.44.14]) by kanga.kvack.org (Postfix) with ESMTP id 54AC4900002 for ; Mon, 15 May 2023 02:36:21 -0400 (EDT) Received: from smtpin14.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay08.hostedemail.com (Postfix) with ESMTP id 1904D1406BB for ; Mon, 15 May 2023 06:36:21 +0000 (UTC) X-FDA: 80791530162.14.582DE8E Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) by imf20.hostedemail.com (Postfix) with ESMTP id B44F51C0004 for ; Mon, 15 May 2023 06:36:17 +0000 (UTC) Authentication-Results: imf20.hostedemail.com; dkim=pass header.d=intel.com header.s=Intel header.b=KAkvmGp4; spf=pass (imf20.hostedemail.com: domain of ying.huang@intel.com designates 192.55.52.151 as permitted sender) smtp.mailfrom=ying.huang@intel.com; dmarc=pass (policy=none) header.from=intel.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1684132578; 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: in-reply-to:in-reply-to:references:references:dkim-signature; bh=KzSrpGzLmi1BgkGGNb4wrLKqw8rpyLohkSKRYr+5zVg=; b=P73ckqcLNJ3Vd1Pfg8Cf6rxyQzcs2ondh3IS5Wj90z2taNaEDjP4yXppYqnMZmNbI7qfeA Li8T18LdPfZRsKGWtlfduDsDLGkMrggk4f4+wSS0EQ4VvfLqZfYKCZoP4vo1m0y6ETFZKl gnNo/7gk3BNWqKi0s90jakMIF4GY89o= ARC-Authentication-Results: i=1; imf20.hostedemail.com; dkim=pass header.d=intel.com header.s=Intel header.b=KAkvmGp4; spf=pass (imf20.hostedemail.com: domain of ying.huang@intel.com designates 192.55.52.151 as permitted sender) smtp.mailfrom=ying.huang@intel.com; dmarc=pass (policy=none) header.from=intel.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1684132578; a=rsa-sha256; cv=none; b=76dtWN30KRX9PJi/HJPao3r4p1YLdz6OxCXAY3fdreRKwyrVUkIOnFCeyMkLk0xYBcpSyU C8Z0MAM9nuEsguX1lt8t90wpthxLq2DH7WSiNsS32ARLehlTSBrh9QK2MPLKw7g9KNY68q zrDm3jBTwwlx6LGryv4y5aI40tQcr2U= DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1684132577; x=1715668577; h=from:to:cc:subject:references:date:in-reply-to: message-id:mime-version; bh=KHpB5mZjdt5Oq2liYBaHyb2FnITF4gNjDV91jX4EVv4=; b=KAkvmGp4NT+hpP8C1RfP5h4LaBp9hyi/C8aihI3p8SjS/4tWYaE5Crt8 mEv7sh7w+QFuynQ3Ck0/SBRJAi9viCPZ11nztFE3OQjjLol7BnTyBfTzo aqptjwAICVY07Y4oAdc0vmiqW5AJX3X7DzU4xlo9cbmtOnhCl1FuGAxiD x5pNiJmdGSBSyngx7wNob1sfZT31w+844FUKunv34Jd1GxE5aBElopPw2 GJM0otxdK9eO2gCNJ470kPLfXAocwe+/U8TArOcxRN8YWdAh8hiBuXq/W urcGajtaH/tZKCkKJjek+LIRTSSYY2hEg2IZfzBzIlWA2S8ksciNM8LCE A==; X-IronPort-AV: E=McAfee;i="6600,9927,10710"; a="331493864" X-IronPort-AV: E=Sophos;i="5.99,275,1677571200"; d="scan'208";a="331493864" Received: from orsmga002.jf.intel.com ([10.7.209.21]) by fmsmga107.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 14 May 2023 23:36:06 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10710"; a="700851635" X-IronPort-AV: E=Sophos;i="5.99,275,1677571200"; d="scan'208";a="700851635" Received: from yhuang6-desk2.sh.intel.com (HELO yhuang6-desk2.ccr.corp.intel.com) ([10.238.208.55]) by orsmga002-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 14 May 2023 23:36:04 -0700 From: "Huang, Ying" To: Tetsuo Handa Cc: Mel Gorman , Andrew Morton , Vlastimil Babka , linux-mm Subject: Re: [PATCH v2] mm/page_alloc: don't wake kswapd from rmqueue() unless __GFP_KSWAPD_RECLAIM is specified References: <6d6fb601-6100-92b9-cea3-e7ebacc7693a@I-love.SAKURA.ne.jp> <20230513102314.md5ugj22xnv6mxob@techsingularity.net> <87edni872w.fsf@yhuang6-desk2.ccr.corp.intel.com> Date: Mon, 15 May 2023 14:35:01 +0800 In-Reply-To: <87edni872w.fsf@yhuang6-desk2.ccr.corp.intel.com> (Ying Huang's message of "Mon, 15 May 2023 14:03:19 +0800") Message-ID: <87a5y685m2.fsf@yhuang6-desk2.ccr.corp.intel.com> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/27.1 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=ascii X-Rspam-User: X-Rspamd-Server: rspam01 X-Rspamd-Queue-Id: B44F51C0004 X-Stat-Signature: x1ffjrgtryyub7tueqjts5fdyc665753 X-HE-Tag: 1684132577-143782 X-HE-Meta: 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 gfrq1lwn O6y4GpUE+QkwhaRpdzyaik3v7ADifR6e4TqiMTyvkDquURDThOkMzaliCLHPUARelvWGmTGV7frjZj+wFdrJiJOcwk1zKh8EK8Qz+Hz8KJVogMpO+5jnJ5oGv7P6I9fteUfRiRJPuIGFVFnBoI5R0wYj8kKQQJR0VXsGHR99hs1kdB4BlLnJNpeKeuezpEK4vJIevn/D1mXB32hpBzmXsu7FktL8jMq9NM0UPchNffVkuIuIm9zdLZJncnGAyQGDobCnZN2cJhekGsGxzpGKzTbAnPX27gjN3QkUynaAz4QSkhr/3he/FWnwiVhR70IeOiJF6X9JjHi4Vw6bKuvOo7bAo4ghRcX6A/MIoaB75r9efslckibHiXNUGSacXh9kwaM1JmzB9gvnXkE3q5+4CbGJNJ140/YbWEM+6 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: Hi, Tetsuo, "Huang, Ying" writes: > Tetsuo Handa writes: > >> Commit 73444bc4d8f9 ("mm, page_alloc: do not wake kswapd with zone lock >> held") moved wakeup_kswapd() from steal_suitable_fallback() to rmqueue() >> using ZONE_BOOSTED_WATERMARK flag. >> >> Only allocation contexts that include ALLOC_KSWAPD (which corresponds to >> __GFP_KSWAPD_RECLAIM) should wake kswapd, for callers are supposed to >> remove __GFP_KSWAPD_RECLAIM if trying to hold pgdat->kswapd_wait has a >> risk of deadlock. But since zone->flags is a shared variable, a thread >> doing !__GFP_KSWAPD_RECLAIM allocation request might observe this flag >> being set immediately after another thread doing __GFP_KSWAPD_RECLAIM >> allocation request set this flag, causing possibility of deadlock. > > Sorry, I don't understand what is the deadlock here. > > I checked commit 73444bc4d8f9 ("mm, page_alloc: do not wake kswapd with > zone lock held") and the corresponding mail thread. From the below > mail, > > https://lore.kernel.org/all/20190107204627.GA25526@cmpxchg.org/ > > commit 73444bc4d8f9 fixed a circular locking ordering as follows, > > pi lock -> rq lock -> timer base lock -> zone lock -> wakeup lock > (kswapd_wait, fixed) -> pi lock > > But I don't know what is the deadlock that your patch fixed. Can you > teach me on that? Just read your email in another thread related to this patch as follow, https://lore.kernel.org/linux-mm/d642e597-cf7d-b410-16ce-22dff483fd8e@I-love.SAKURA.ne.jp/ Is that the deadlock that you tried to fix in this patch? It appears that commit 73444bc4d8f9 didn't fix the deadlock above. It just convert the circular locking ordering to, pi lock -> rq lock -> timer base lock -> wakeup lock (kswapd_wait, fixed) -> pi lock If so, I think that it's better to add corresponding information in patch description to avoid the possible confusion. Best Regards, Huang, Ying >> Signed-off-by: Tetsuo Handa >> Fixes: 73444bc4d8f9 ("mm, page_alloc: do not wake kswapd with zone lock held") >> --- >> Changes in v2: >> Check ALLOC_KSWAPD before checking ZONE_BOOSTED_WATERMARK and update >> description, suggested by Mel Gorman . >> >> mm/page_alloc.c | 3 ++- >> 1 file changed, 2 insertions(+), 1 deletion(-) >> >> diff --git a/mm/page_alloc.c b/mm/page_alloc.c >> index 47421bedc12b..ecad680cec53 100644 >> --- a/mm/page_alloc.c >> +++ b/mm/page_alloc.c >> @@ -3052,7 +3052,8 @@ struct page *rmqueue(struct zone *preferred_zone, >> >> out: >> /* Separate test+clear to avoid unnecessary atomics */ >> - if (unlikely(test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags))) { >> + if ((alloc_flags & ALLOC_KSWAPD) && >> + unlikely(test_bit(ZONE_BOOSTED_WATERMARK, &zone->flags))) { >> clear_bit(ZONE_BOOSTED_WATERMARK, &zone->flags); >> wakeup_kswapd(zone, 0, 0, zone_idx(zone)); >> }