From patchwork Mon Nov 30 15:18:23 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Muchun Song X-Patchwork-Id: 11940783 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=-11.6 required=3.0 tests=BAYES_00,DKIM_INVALID, DKIM_SIGNED,HEADER_FROM_DIFFERENT_DOMAINS,INCLUDES_PATCH,MAILING_LIST_MULTI, SPF_HELO_NONE,SPF_PASS,USER_AGENT_GIT 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 1BC60C64E7B for ; Mon, 30 Nov 2020 15:19:28 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 3E3C72074A for ; Mon, 30 Nov 2020 15:19:26 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=fail reason="signature verification failed" (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com header.i=@bytedance-com.20150623.gappssmtp.com header.b="T66lfaZs" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 3E3C72074A Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=bytedance.com Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id 799288D0005; Mon, 30 Nov 2020 10:19:26 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 748238D0002; Mon, 30 Nov 2020 10:19:26 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 54DF28D0005; Mon, 30 Nov 2020 10:19:26 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0078.hostedemail.com [216.40.44.78]) by kanga.kvack.org (Postfix) with ESMTP id 374238D0002 for ; Mon, 30 Nov 2020 10:19:26 -0500 (EST) Received: from smtpin10.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay05.hostedemail.com (Postfix) with ESMTP id D2FE9181AEF2A for ; Mon, 30 Nov 2020 15:19:25 +0000 (UTC) X-FDA: 77541443490.10.page22_3212d25273a2 Received: from filter.hostedemail.com (10.5.16.251.rfc1918.com [10.5.16.251]) by smtpin10.hostedemail.com (Postfix) with ESMTP id B418916A047 for ; Mon, 30 Nov 2020 15:19:25 +0000 (UTC) X-HE-Tag: page22_3212d25273a2 X-Filterd-Recvd-Size: 17535 Received: from mail-pl1-f180.google.com (mail-pl1-f180.google.com [209.85.214.180]) by imf06.hostedemail.com (Postfix) with ESMTP for ; Mon, 30 Nov 2020 15:19:24 +0000 (UTC) Received: by mail-pl1-f180.google.com with SMTP id l11so6665941plt.1 for ; Mon, 30 Nov 2020 07:19:24 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=bytedance-com.20150623.gappssmtp.com; s=20150623; h=from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=OmKhHpn9YbJJQE6n5GorMtrHeT0hAK+n9oxP3xtgBYI=; b=T66lfaZswjyVKFjI8wWCsnaig9nhqyaEWiCmYBz69PRusegypEdQ2XOm8GWyp/7j2M gV4Qlat81J0yml5xQjco9nRqxZBWeFfEghD/ZiTYDm228rdmDjTWfMB97TVVK/PrAuiW CFCro4/cx/1HAkCa42hZhNlOLivSUTZoeasoiBAhxUWr6Ow+tUTQVqpRIQSE0xRE+Pko qYY8M+g7uwb6PODDpD4SU+GQBI2oM3otpT7NkEnlP7uiqvAx3XfriSKjncShQh4+VtBf /qIKQSC6jDH+NWec0I9z4Y6puhUA9R3IIdq6vAArt8xh+WJ7tTpRCFPIOk9YXYc3wHVA N3dw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:to:cc:subject:date:message-id:mime-version :content-transfer-encoding; bh=OmKhHpn9YbJJQE6n5GorMtrHeT0hAK+n9oxP3xtgBYI=; b=VyAXt/WU6XiScsssBMJNH8wOh6VHts6XWW21wCF7XsVXW98jxL+laD/zfA641/Le2/ N2dBsnj8OD9Ev6jC1uX5RsB8LtKkfpGUhpdPnjcgeW5ucP++ZdU6AOg+PhWzjr9jNKxs n4D8VVdXsQq9G2v3wVbvZKelmT7z1vSxlfoFGyyaH9qNiAyszZNsWepJUomS6A2A/hqS yklFzt90R1k0O2+TS837BIowRSGFjb/NAyVuUeHmwpwIQPtApuUMb13X54yiBDuGTdJt T+lwERa2Z90f4u6ymJLiG35tkZcCrYxObOPpAQm0JguO1JlB9Pk92zW6dVdv8JE+mSMx jkjg== X-Gm-Message-State: AOAM531vomEJsGQoTAAth0eX4ugh0C23YtgpwimkdT7P3mVNBPXt/Za1 CsZrZTxzJg6wK1o5RpcCv/6b1A== X-Google-Smtp-Source: ABdhPJwcya/MBRTDiwN4DDyInFaunELay3DaLODzTBBGkfgBPqnJonk6YTJtGqgfeWsC3dZZ5xMfUQ== X-Received: by 2002:a17:902:eb0c:b029:da:51da:cdac with SMTP id l12-20020a170902eb0cb02900da51dacdacmr14620712plb.4.1606749561960; Mon, 30 Nov 2020 07:19:21 -0800 (PST) Received: from localhost.bytedance.net ([103.136.221.68]) by smtp.gmail.com with ESMTPSA id q12sm16201660pgv.91.2020.11.30.07.19.11 (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128); Mon, 30 Nov 2020 07:19:21 -0800 (PST) From: Muchun Song To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de, mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com, dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org, viro@zeniv.linux.org.uk, akpm@linux-foundation.org, paulmck@kernel.org, mchehab+huawei@kernel.org, pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org, oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de, almasrymina@google.com, rientjes@google.com, willy@infradead.org, osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linux-mm@kvack.org, linux-fsdevel@vger.kernel.org, Muchun Song Subject: [PATCH v7 00/15] Free some vmemmap pages of hugetlb page Date: Mon, 30 Nov 2020 23:18:23 +0800 Message-Id: <20201130151838.11208-1-songmuchun@bytedance.com> X-Mailer: git-send-email 2.21.0 (Apple Git-122) MIME-Version: 1.0 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 all, This patch series will free some vmemmap pages(struct page structures) associated with each hugetlbpage when preallocated to save memory. In order to reduce the difficulty of the first version of code review. From this version, we disable PMD/huge page mapping of vmemmap if this feature was enabled. This accutualy eliminate a bunch of the complex code doing page table manipulation. When this patch series is solid, we cam add the code of vmemmap page table manipulation in the future. The struct page structures (page structs) are used to describe a physical page frame. By default, there is a one-to-one mapping from a page frame to it's corresponding page struct. The HugeTLB pages consist of multiple base page size pages and is supported by many architectures. See hugetlbpage.rst in the Documentation directory for more details. On the x86 architecture, HugeTLB pages of size 2MB and 1GB are currently supported. Since the base page size on x86 is 4KB, a 2MB HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of 4096 base pages. For each base page, there is a corresponding page struct. Within the HugeTLB subsystem, only the first 4 page structs are used to contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER provides this upper limit. The only 'useful' information in the remaining page structs is the compound_head field, and this field is the same for all tail pages. By removing redundant page structs for HugeTLB pages, memory can returned to the buddy allocator for other uses. When the system boot up, every 2M HugeTLB has 512 struct page structs which size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE). HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | -------------> | 1 | | | +-----------+ +-----------+ | | | 2 | -------------> | 2 | | | +-----------+ +-----------+ | | | 3 | -------------> | 3 | | | +-----------+ +-----------+ | | | 4 | -------------> | 4 | | 2MB | +-----------+ +-----------+ | | | 5 | -------------> | 5 | | | +-----------+ +-----------+ | | | 6 | -------------> | 6 | | | +-----------+ +-----------+ | | | 7 | -------------> | 7 | | | +-----------+ +-----------+ | | | | | | +-----------+ The value of page->compound_head is the same for all tail pages. The first page of page structs (page 0) associated with the HugeTLB page contains the 4 page structs necessary to describe the HugeTLB. The only use of the remaining pages of page structs (page 1 to page 7) is to point to page->compound_head. Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs will be used for each HugeTLB page. This will allow us to free the remaining 6 pages to the buddy allocator. Here is how things look after remapping. HugeTLB struct pages(8 pages) page frame(8 pages) +-----------+ ---virt_to_page---> +-----------+ mapping to +-----------+ | | | 0 | -------------> | 0 | | | +-----------+ +-----------+ | | | 1 | -------------> | 1 | | | +-----------+ +-----------+ | | | 2 | ----------------^ ^ ^ ^ ^ ^ | | +-----------+ | | | | | | | | 3 | ------------------+ | | | | | | +-----------+ | | | | | | | 4 | --------------------+ | | | | 2MB | +-----------+ | | | | | | 5 | ----------------------+ | | | | +-----------+ | | | | | 6 | ------------------------+ | | | +-----------+ | | | | 7 | --------------------------+ | | +-----------+ | | | | | | +-----------+ When a HugeTLB is freed to the buddy system, we should allocate 6 pages for vmemmap pages and restore the previous mapping relationship. Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar to the 2MB HugeTLB page. We also can use this approach to free the vmemmap pages. In this case, for the 1GB HugeTLB page, we can save 4088 pages(There are 4096 pages for struct page structs, we reserve 2 pages for vmemmap and 8 pages for page tables. So we can save 4088 pages). This is a very substantial gain. On our server, run some SPDK/QEMU applications which will use 1024GB hugetlbpage. With this feature enabled, we can save ~16GB(1G hugepage)/~11GB (2MB hugepage, the worst case is 10GB while the best is 12GB) memory. Because there are vmemmap page tables reconstruction on the freeing/allocating path, it increases some overhead. Here are some overhead analysis. 1) Allocating 10240 2MB hugetlb pages. a) With this patch series applied: # time echo 10240 > /proc/sys/vm/nr_hugepages real 0m0.166s user 0m0.000s sys 0m0.166s # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [8K, 16K) 8360 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [16K, 32K) 1868 |@@@@@@@@@@@ | [32K, 64K) 10 | | [64K, 128K) 2 | | b) Without this patch series: # time echo 10240 > /proc/sys/vm/nr_hugepages real 0m0.066s user 0m0.000s sys 0m0.066s # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [4K, 8K) 10176 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [8K, 16K) 62 | | [16K, 32K) 2 | | Summarize: this feature is about ~2x slower than before. 2) Freeing 10240 2MB hugetlb pages. a) With this patch series applied: # time echo 0 > /proc/sys/vm/nr_hugepages real 0m0.004s user 0m0.000s sys 0m0.002s # bpftrace -e 'kprobe:__free_hugepage { @start[tid] = nsecs; } kretprobe:__free_hugepage /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [16K, 32K) 10240 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| b) Without this patch series: # time echo 0 > /proc/sys/vm/nr_hugepages real 0m0.077s user 0m0.001s sys 0m0.075s # bpftrace -e 'kprobe:__free_hugepage { @start[tid] = nsecs; } kretprobe:__free_hugepage /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }' Attaching 2 probes... @latency: [4K, 8K) 9950 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@| [8K, 16K) 287 |@ | [16K, 32K) 3 | | Summarize: The overhead of __free_hugepage is about ~2-4x slower than before. But according to the allocation test above, I think that here is also ~2x slower than before. But why the 'real' time of patched is smaller than before? Because In this patch series, the freeing hugetlb is asynchronous(through kwoker). Although the overhead has increased, the overhead is not significant. Like Mike said, "However, remember that the majority of use cases create hugetlb pages at or shortly after boot time and add them to the pool. So, additional overhead is at pool creation time. There is no change to 'normal run time' operations of getting a page from or returning a page to the pool (think page fault/unmap)". Todo: 1. Free all of the tail vmemmap pages Now for the 2MB HugrTLB page, we only free 6 vmemmap pages. we really can free 7 vmemmap pages. In this case, we can see 8 of the 512 struct page structures has beed set PG_head flag. If we can adjust compound_head() slightly and make compound_head() return the real head struct page when the parameter is the tail struct page but with PG_head flag set. In order to make the code evolution route clearer. This feature can can be a separate patch after this patchset is solid. 2. Support for other architectures (e.g. aarch64). 3. Enable PMD/huge page mapping of vmemmap even if this feature was enabled. Changelog in v7: 1. Rebase to linux-next 20201130 2. Do not use basepage mapping for vmemmap when this feature is disabled. Thanks to Oscar and Barry. 3. Rework some patchs. [PATCH v6 08/16] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page [PATCH v6 10/16] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page Changelog in v6: 1. Disable PMD/huge page mapping of vmemmap if this feature was enabled. 2. Simplify the first version code. Changelog in v5: 1. Rework somme comments and code in the [PATCH v4 04/21] and [PATCH v4 05/21]. Thanks to Mike and Oscar's suggestions. Changelog in v4: 1. Move all the vmemmap functions to hugetlb_vmemmap.c. 2. Make the CONFIG_HUGETLB_PAGE_FREE_VMEMMAP default to y, if we want to disable this feature, we should disable it by a boot/kernel command line. 3. Remove vmemmap_pgtable_{init, deposit, withdraw}() helper functions. 4. Initialize page table lock for vmemmap through core_initcall mechanism. Thanks for Mike and Oscar's suggestions. Changelog in v3: 1. Rename some helps function name. Thanks Mike. 2. Rework some code. Thanks Mike and Oscar. 3. Remap the tail vmemmap page with PAGE_KERNEL_RO instead of PAGE_KERNEL. Thanks Matthew. 4. Add some overhead analysis in the cover letter. 5. Use vmemap pmd table lock instead of a hugetlb specific global lock. Changelog in v2: 1. Fix do not call dissolve_compound_page in alloc_huge_page_vmemmap(). 2. Fix some typo and code style problems. 3. Remove unused handle_vmemmap_fault(). 4. Merge some commits to one commit suggested by Mike. Muchun Song (15): mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c mm/memory_hotplug: Move {get,put}_page_bootmem() to bootmem_info.c mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() mm/hugetlb: Disable freeing vmemmap if struct page size is not power of two x86/mm/64: Disable PMD page mapping of vmemmap mm/hugetlb: Free the vmemmap pages associated with each hugetlb page mm/hugetlb: Defer freeing of HugeTLB pages mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page mm/hugetlb: Set the PageHWPoison to the raw error page mm/hugetlb: Flush work when dissolving hugetlb page mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap mm/hugetlb: Gather discrete indexes of tail page mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Documentation/admin-guide/kernel-parameters.txt | 9 + Documentation/admin-guide/mm/hugetlbpage.rst | 3 + arch/x86/mm/init_64.c | 13 +- fs/Kconfig | 14 + include/linux/bootmem_info.h | 64 +++++ include/linux/hugetlb.h | 35 +++ include/linux/hugetlb_cgroup.h | 15 +- include/linux/memory_hotplug.h | 27 -- mm/Makefile | 2 + mm/bootmem_info.c | 124 ++++++++ mm/hugetlb.c | 144 ++++++++-- mm/hugetlb_vmemmap.c | 367 ++++++++++++++++++++++++ mm/hugetlb_vmemmap.h | 79 +++++ mm/memory_hotplug.c | 116 -------- mm/sparse.c | 1 + 15 files changed, 834 insertions(+), 179 deletions(-) create mode 100644 include/linux/bootmem_info.h create mode 100644 mm/bootmem_info.c create mode 100644 mm/hugetlb_vmemmap.c create mode 100644 mm/hugetlb_vmemmap.h