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 9CF2FC48BF6 for ; Thu, 7 Mar 2024 11:13:12 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 2D0066B015A; Thu, 7 Mar 2024 06:13:12 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 280FC6B015B; Thu, 7 Mar 2024 06:13:12 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 148606B015C; Thu, 7 Mar 2024 06:13:12 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0015.hostedemail.com [216.40.44.15]) by kanga.kvack.org (Postfix) with ESMTP id 003FB6B015A for ; Thu, 7 Mar 2024 06:13:11 -0500 (EST) Received: from smtpin09.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay10.hostedemail.com (Postfix) with ESMTP id 928F6C0853 for ; Thu, 7 Mar 2024 11:13:11 +0000 (UTC) X-FDA: 81869981382.09.FB58E7B Received: from foss.arm.com (foss.arm.com [217.140.110.172]) by imf30.hostedemail.com (Postfix) with ESMTP id 9D5D580018 for ; Thu, 7 Mar 2024 11:13:09 +0000 (UTC) Authentication-Results: imf30.hostedemail.com; dkim=none; dmarc=pass (policy=none) header.from=arm.com; spf=pass (imf30.hostedemail.com: domain of ryan.roberts@arm.com designates 217.140.110.172 as permitted sender) smtp.mailfrom=ryan.roberts@arm.com ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1709809990; a=rsa-sha256; cv=none; b=cBFvj+WHjId8Ej8uEMopbG81CqcMMLYTaTnoBhtYtmDypPr3vbjU8ls5yWSOVry7XPLec+ /hVBWRofuq+PfGkDt+T5O+bAxlp0C+PdL+x8OSuCYMi1sm2jbvXFaCX2SfWroPA9tpshdU fpK7ip2wgAQERlyOEf1Wt1YfUs6tUe4= ARC-Authentication-Results: i=1; imf30.hostedemail.com; dkim=none; dmarc=pass (policy=none) header.from=arm.com; spf=pass (imf30.hostedemail.com: domain of ryan.roberts@arm.com designates 217.140.110.172 as permitted sender) smtp.mailfrom=ryan.roberts@arm.com ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1709809990; 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=iMlEppWpT1QdRLmDGk1EXtqI2PdyL2JIv2HCasSrxPg=; b=i4qPKD9fgOyF8ISOOcERz2mY5zjug1yX3vZyafxOM2B+I8u6auMOGuDTha6alpcbpuagr0 QIgpyCJy7HU8BA8ZVkKG8GEbb8LZvwHpgyoX0VePxBfazM9FAhprQBhqzgofjFJsjzjTfm J4ZAszSATHi2wIMO7QPL17VjpFSdVdk= 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 89E631FB; Thu, 7 Mar 2024 03:13:45 -0800 (PST) Received: from [10.1.25.184] (XHFQ2J9959.cambridge.arm.com [10.1.25.184]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 44DCD3F762; Thu, 7 Mar 2024 03:13:06 -0800 (PST) Message-ID: Date: Thu, 7 Mar 2024 11:13:04 +0000 MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Subject: Re: [PATCH v2 1/1] mm/madvise: enhance lazyfreeing with mTHP in madvise_free Content-Language: en-GB To: David Hildenbrand , Barry Song <21cnbao@gmail.com> Cc: Lance Yang , Vishal Moola , akpm@linux-foundation.org, zokeefe@google.com, shy828301@gmail.com, mhocko@suse.com, fengwei.yin@intel.com, xiehuan09@gmail.com, wangkefeng.wang@huawei.com, songmuchun@bytedance.com, peterx@redhat.com, minchan@kernel.org, linux-mm@kvack.org, linux-kernel@vger.kernel.org References: <20240307061425.21013-1-ioworker0@gmail.com> <03458c20-5544-411b-9b8d-b4600a9b802f@arm.com> <501c9f77-1459-467a-8619-78e86b46d300@arm.com> <8f84c7d6-982a-4933-a7a7-3f640df64991@redhat.com> From: Ryan Roberts In-Reply-To: Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-Rspamd-Server: rspam08 X-Rspamd-Queue-Id: 9D5D580018 X-Stat-Signature: ee8fq7unt6oqn3o58dyu9w6xdptoowr7 X-Rspam-User: X-HE-Tag: 1709809989-87908 X-HE-Meta: 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 7eg== 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 07/03/2024 10:54, David Hildenbrand wrote: > On 07.03.24 11:54, David Hildenbrand wrote: >> On 07.03.24 11:50, Ryan Roberts wrote: >>> On 07/03/2024 09:33, Barry Song wrote: >>>> On Thu, Mar 7, 2024 at 10:07 PM Ryan Roberts wrote: >>>>> >>>>> On 07/03/2024 08:10, Barry Song wrote: >>>>>> On Thu, Mar 7, 2024 at 9:00 PM Lance Yang wrote: >>>>>>> >>>>>>> Hey Barry, >>>>>>> >>>>>>> Thanks for taking time to review! >>>>>>> >>>>>>> On Thu, Mar 7, 2024 at 3:00 PM Barry Song <21cnbao@gmail.com> wrote: >>>>>>>> >>>>>>>> On Thu, Mar 7, 2024 at 7:15 PM Lance Yang wrote: >>>>>>>>> >>>>>>> [...] >>>>>>>>> +static inline bool can_mark_large_folio_lazyfree(unsigned long addr, >>>>>>>>> +                                                struct folio *folio, >>>>>>>>> pte_t *start_pte) >>>>>>>>> +{ >>>>>>>>> +       int nr_pages = folio_nr_pages(folio); >>>>>>>>> +       fpb_t flags = FPB_IGNORE_DIRTY | FPB_IGNORE_SOFT_DIRTY; >>>>>>>>> + >>>>>>>>> +       for (int i = 0; i < nr_pages; i++) >>>>>>>>> +               if (page_mapcount(folio_page(folio, i)) != 1) >>>>>>>>> +                       return false; >>>>>>>> >>>>>>>> we have moved to folio_estimated_sharers though it is not precise, so >>>>>>>> we don't do >>>>>>>> this check with lots of loops and depending on the subpage's mapcount. >>>>>>> >>>>>>> If we don't check the subpage’s mapcount, and there is a cow folio >>>>>>> associated >>>>>>> with this folio and the cow folio has smaller size than this folio, >>>>>>> should we still >>>>>>> mark this folio as lazyfree? >>>>>> >>>>>> I agree, this is true. However, we've somehow accepted the fact that >>>>>> folio_likely_mapped_shared >>>>>> can result in false negatives or false positives to balance the >>>>>> overhead.  So I really don't know :-) >>>>>> >>>>>> Maybe David and Vishal can give some comments here. >>>>>> >>>>>>> >>>>>>>> BTW, do we need to rebase our work against David's changes[1]? >>>>>>>> [1] >>>>>>>> https://lore.kernel.org/linux-mm/20240227201548.857831-1-david@redhat.com/ >>>>>>> >>>>>>> Yes, we should rebase our work against David’s changes. >>>>>>> >>>>>>>> >>>>>>>>> + >>>>>>>>> +       return nr_pages == folio_pte_batch(folio, addr, start_pte, >>>>>>>>> +                                        ptep_get(start_pte), nr_pages, >>>>>>>>> flags, NULL); >>>>>>>>> +} >>>>>>>>> + >>>>>>>>>    static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr, >>>>>>>>>                                   unsigned long end, struct mm_walk *walk) >>>>>>>>> >>>>>>>>> @@ -676,11 +690,45 @@ static int madvise_free_pte_range(pmd_t *pmd, >>>>>>>>> unsigned long addr, >>>>>>>>>                    */ >>>>>>>>>                   if (folio_test_large(folio)) { >>>>>>>>>                           int err; >>>>>>>>> +                       unsigned long next_addr, align; >>>>>>>>> >>>>>>>>> -                       if (folio_estimated_sharers(folio) != 1) >>>>>>>>> -                               break; >>>>>>>>> -                       if (!folio_trylock(folio)) >>>>>>>>> -                               break; >>>>>>>>> +                       if (folio_estimated_sharers(folio) != 1 || >>>>>>>>> +                           !folio_trylock(folio)) >>>>>>>>> +                               goto skip_large_folio; >>>>>>>> >>>>>>>> >>>>>>>> I don't think we can skip all the PTEs for nr_pages, as some of them >>>>>>>> might be >>>>>>>> pointing to other folios. >>>>>>>> >>>>>>>> for example, for a large folio with 16PTEs, you do MADV_DONTNEED(15-16), >>>>>>>> and write the memory of PTE15 and PTE16, you get page faults, thus PTE15 >>>>>>>> and PTE16 will point to two different small folios. We can only skip >>>>>>>> when we >>>>>>>> are sure nr_pages == folio_pte_batch() is sure. >>>>>>> >>>>>>> Agreed. Thanks for pointing that out. >>>>>>> >>>>>>>> >>>>>>>>> + >>>>>>>>> +                       align = folio_nr_pages(folio) * PAGE_SIZE; >>>>>>>>> +                       next_addr = ALIGN_DOWN(addr + align, align); >>>>>>>>> + >>>>>>>>> +                       /* >>>>>>>>> +                        * If we mark only the subpages as lazyfree, or >>>>>>>>> +                        * cannot mark the entire large folio as lazyfree, >>>>>>>>> +                        * then just split it. >>>>>>>>> +                        */ >>>>>>>>> +                       if (next_addr > end || next_addr - addr != >>>>>>>>> align || >>>>>>>>> +                           !can_mark_large_folio_lazyfree(addr, folio, >>>>>>>>> pte)) >>>>>>>>> +                               goto split_large_folio; >>>>>>>>> + >>>>>>>>> +                       /* >>>>>>>>> +                        * Avoid unnecessary folio splitting if the large >>>>>>>>> +                        * folio is entirely within the given range. >>>>>>>>> +                        */ >>>>>>>>> +                       folio_clear_dirty(folio); >>>>>>>>> +                       folio_unlock(folio); >>>>>>>>> +                       for (; addr != next_addr; pte++, addr += >>>>>>>>> PAGE_SIZE) { >>>>>>>>> +                               ptent = ptep_get(pte); >>>>>>>>> +                               if (pte_young(ptent) || >>>>>>>>> pte_dirty(ptent)) { >>>>>>>>> +                                       ptent = ptep_get_and_clear_full( >>>>>>>>> +                                               mm, addr, pte, >>>>>>>>> tlb->fullmm); >>>>>>>>> +                                       ptent = pte_mkold(ptent); >>>>>>>>> +                                       ptent = pte_mkclean(ptent); >>>>>>>>> +                                       set_pte_at(mm, addr, pte, ptent); >>>>>>>>> +                                       tlb_remove_tlb_entry(tlb, pte, >>>>>>>>> addr); >>>>>>>>> +                               } >>>>>>>> >>>>>>>> Can we do this in batches? for a CONT-PTE mapped large folio, you are >>>>>>>> unfolding >>>>>>>> and folding again. It seems quite expensive. >>>>> >>>>> I'm not convinced we should be doing this in batches. We want the initial >>>>> folio_pte_batch() to be as loose as possible regarding permissions so that we >>>>> reduce our chances of splitting folios to the min. (e.g. ignore SW bits like >>>>> soft dirty, etc). I think it might be possible that some PTEs are RO and other >>>>> RW too (e.g. due to cow - although with the current cow impl, probably not. >>>>> But >>>>> its fragile to assume that). Anyway, if we do an initial batch that ignores >>>>> all >>>> >>>> You are correct. I believe this scenario could indeed occur. For instance, >>>> if process A forks process B and then unmaps itself, leaving B as the >>>> sole process owning the large folio.  The current wp_page_reuse() function >>>> will reuse PTE one by one while the specific subpage is written. >>> >>> Hmm - I thought it would only reuse if the total mapcount for the folio was 1. >>> And since it is a large folio with each page mapped once in proc B, I thought >>> every subpage write would cause a copy except the last one? I haven't looked at >>> the code for a while. But I had it in my head that this is an area we need to >>> improve for mTHP. >> >> wp_page_reuse() will currently reuse a PTE part of a large folio only if >> a single PTE remains mapped (refcount == 0). > > ^ == 1 Ahh yes. That's what I meant. I got the behacviour vagulely right though. Anyway, regardless, I'm not sure we want to batch here. Or if we do, we want to batch function that will only clear access and dirty.