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 CEB0EC30658 for ; Tue, 2 Jul 2024 15:29:12 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 6E8126B0083; Tue, 2 Jul 2024 11:29:12 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id 698C26B0085; Tue, 2 Jul 2024 11:29:12 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 586C06B00A1; Tue, 2 Jul 2024 11:29:12 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0011.hostedemail.com [216.40.44.11]) by kanga.kvack.org (Postfix) with ESMTP id 3B8836B0083 for ; Tue, 2 Jul 2024 11:29:12 -0400 (EDT) Received: from smtpin19.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay02.hostedemail.com (Postfix) with ESMTP id AA16F1202A9 for ; Tue, 2 Jul 2024 15:29:11 +0000 (UTC) X-FDA: 82295196102.19.7DAED1D Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by imf25.hostedemail.com (Postfix) with ESMTP id 64CFAA001F for ; Tue, 2 Jul 2024 15:29:08 +0000 (UTC) Authentication-Results: imf25.hostedemail.com; dkim=none; spf=pass (imf25.hostedemail.com: domain of ryan.roberts@arm.com designates 217.140.110.172 as permitted sender) smtp.mailfrom=ryan.roberts@arm.com; dmarc=pass (policy=none) header.from=arm.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1719934126; 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; bh=zMm1zBrkWjfMeSFipRGQ+9+XrGDOwa1wxv/X9wkBL2I=; b=CpiSScaspII+QYT003KsWH07mwPnu9fvnOqA3iDY9Tujirg5/kXf7oq/6WvqlzdBOTUFN1 RbJnq6kYl1aOo71FmbtWcI0wXbiHGc1Y3ljLeRrJVv+q0kW2a/Qhn+oUu82RNrf9N1w7c+ aIHGbTbXsUl5gxkSs4Npwr2OHrnBu7Q= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1719934126; a=rsa-sha256; cv=none; b=pz+jMfPFVwITEfr/kNbS/d6kZqW8Ar/6w17QjB4M9bmIHw7Vz0PJ6DU5H6JfLYayzJBt8C 6ojcCAKSmk9dEUplpkKXzJtOABFwBpryxyk/piH6OSpcE8n2urviTAq9OGKaLm9eak1LtG RX0uMva8PEbeiYw33L+ccHOGFQLTVzs= ARC-Authentication-Results: i=1; imf25.hostedemail.com; dkim=none; spf=pass (imf25.hostedemail.com: domain of ryan.roberts@arm.com designates 217.140.110.172 as permitted sender) smtp.mailfrom=ryan.roberts@arm.com; dmarc=pass (policy=none) header.from=arm.com Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.121.207.14]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 69935339; Tue, 2 Jul 2024 08:29:32 -0700 (PDT) Received: from [10.1.32.193] (XHFQ2J9959.cambridge.arm.com [10.1.32.193]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id E6B7A3F766; Tue, 2 Jul 2024 08:29:05 -0700 (PDT) Message-ID: Date: Tue, 2 Jul 2024 16:29:04 +0100 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH v1] mm: Fix khugepaged activation policy Content-Language: en-GB To: David Hildenbrand , Andrew Morton , Jonathan Corbet , Barry Song , Baolin Wang , Lance Yang , Yang Shi Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, stable@vger.kernel.org References: <20240702144617.2291480-1-ryan.roberts@arm.com> From: Ryan Roberts In-Reply-To: Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-Rspam-User: X-Rspamd-Server: rspam04 X-Rspamd-Queue-Id: 64CFAA001F X-Stat-Signature: cyw4gssngfw59bk88a6zupz4168xmck4 X-HE-Tag: 1719934148-529440 X-HE-Meta: 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 0w0KZ29u IaJa0IVLl3iEAB0X+dgmr39IbOfBiLqCQBnOMG9hmWKxAmu4+FxxvDJn5/BrwzDaNvuYe3rtbwhTMWjAEW3v6ve27qwu8iVuxTEPFj8uSmQaTvQuKzE+VL5z4ejL0fACPF+Cuq2+BeyNmaKjMGfx6GKJUZ24TKMk3bmzOJHWj/TRvQdD7jg+cj0/ocld6lK753IGrMOLUPIetdfcfMDnvrKi2EQSLm17lm9okR2gBykh8FZFGMGWyLH/qDsyWJGAXTZUrElakBCW6cKr70FMWdJU/eap8LlJuc7zjDhDqe8KginPi1yGH+goj6g== 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: List-Subscribe: List-Unsubscribe: On 02/07/2024 15:57, David Hildenbrand wrote: > On 02.07.24 16:46, Ryan Roberts wrote: >> Since the introduction of mTHP, the docuementation has stated that >> khugepaged would be enabled when any mTHP size is enabled, and disabled >> when all mTHP sizes are disabled. There are 2 problems with this; 1. >> this is not what was implemented by the code and 2. this is not the >> desirable behavior. >> >> Desirable behavior is for khugepaged to be enabled when any PMD-sized >> THP is enabled, anon or file. (Note that file THP is still controlled by >> the top-level control so we must always consider that, as well as the >> PMD-size mTHP control for anon). khugepaged only supports collapsing to >> PMD-sized THP so there is no value in enabling it when PMD-sized THP is >> disabled. So let's change the code and documentation to reflect this >> policy. >> >> Further, per-size enabled control modification events were not >> previously forwarded to khugepaged to give it an opportunity to start or >> stop. Consequently the following was resulting in khugepaged eroneously >> not being activated: >> >>    echo never > /sys/kernel/mm/transparent_hugepage/enabled >>    echo always > /sys/kernel/mm/transparent_hugepage/hugepages-2048kB/enabled >> >> Signed-off-by: Ryan Roberts >> Fixes: 3485b88390b0 ("mm: thp: introduce multi-size THP sysfs interface") >> Closes: >> https://lore.kernel.org/linux-mm/7a0bbe69-1e3d-4263-b206-da007791a5c4@redhat.com/ >> Cc: stable@vger.kernel.org >> --- >> >> Hi All, >> >> Applies on top of today's mm-unstable (9bb8753acdd8). No regressions observed in >> mm selftests. >> >> When fixing this I also noticed that khugepaged doesn't get (and never has been) >> activated/deactivated by `shmem_enabled=`. I'm not sure if khugepaged knows how >> to collapse shmem - perhaps it should be activated in this case? >> > > Call me confused. > > khugepaged_scan_mm_slot() and madvise_collapse() only all > hpage_collapse_scan_file() with ... IS_ENABLED(CONFIG_SHMEM) ? Looks like khugepaged_scan_mm_slot() was converted from: if (shmem_file(vma->vm_file)) { to: if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { By 99cb0dbd47a15d395bf3faa78dc122bc5efe3fc0 which adds THP collapse support for non-shmem files. Clearly that looks wrong, but I guess never spotted in practice because noone disables shemem? I guess madvise_collapse() was a copy/paste? > > collapse_file() is only called by hpage_collapse_scan_file() ... and there we > check "shmem_file(file)". > > So why is the IS_ENABLED(CONFIG_SHMEM) check in there if collapse_file() seems > to "collapse filemap/tmpfs/shmem pages into huge one". > > Anyhow, we certainly can collapse shmem (that's how it all started IIUC). Yes, thanks for pointing me at it. Should have just searched "shmem" in khugepaged.c :-/ > > Besides that, khugepaged only seems to collapse !shmem with >   VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); That makes sense. I guess I could use IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) to tighen the (non-shmem) file THP check in hugepage_pmd_enabled() (currently I'm unconditionally using the top-level enabled setting as a "is THP enabled for files" check). But back to my original question, I think hugepage_pmd_enabled() should also be explicitly checking the appropriate shmem_enabled controls and ORing in the result? Otherwise in a situation where only shmem is THP enabled (and file/anon THP is disabled) khugepaged won't run. > > The thp_vma_allowable_order() check tests if we are allowed to collapse a > PMD_ORDER in that VMA. I don't follow the relevance of this statement.