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]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id CF2C4FD8FFD for ; Fri, 27 Feb 2026 19:43:15 +0000 (UTC) Received: by kanga.kvack.org (Postfix) id 3BB1F6B00BB; Fri, 27 Feb 2026 14:43:15 -0500 (EST) Received: by kanga.kvack.org (Postfix, from userid 40) id 365A96B00BC; Fri, 27 Feb 2026 14:43:15 -0500 (EST) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id 265536B00BE; Fri, 27 Feb 2026 14:43:15 -0500 (EST) X-Delivered-To: linux-mm@kvack.org Received: from relay.hostedemail.com (smtprelay0012.hostedemail.com [216.40.44.12]) by kanga.kvack.org (Postfix) with ESMTP id 11F286B00BB for ; Fri, 27 Feb 2026 14:43:15 -0500 (EST) Received: from smtpin02.hostedemail.com (a10.router.float.18 [10.200.18.1]) by unirelay05.hostedemail.com (Postfix) with ESMTP id B6B6A59BD5 for ; Fri, 27 Feb 2026 19:43:14 +0000 (UTC) X-FDA: 84491260308.02.7AEB377 Received: from sea.source.kernel.org (sea.source.kernel.org [172.234.252.31]) by imf04.hostedemail.com (Postfix) with ESMTP id B6F1940006 for ; Fri, 27 Feb 2026 19:43:12 +0000 (UTC) Authentication-Results: imf04.hostedemail.com; dkim=pass header.d=kernel.org header.s=k20201202 header.b=nR5TWSeg; spf=pass (imf04.hostedemail.com: domain of kas@kernel.org designates 172.234.252.31 as permitted sender) smtp.mailfrom=kas@kernel.org; dmarc=pass (policy=quarantine) header.from=kernel.org ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=hostedemail.com; s=arc-20220608; t=1772221392; 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-transfer-encoding:content-transfer-encoding: in-reply-to:references:dkim-signature; bh=sE1G1HL9oYx5uFfLbALmuzlxOBXXMmht3rkQfyJsuFM=; b=jQDQGbbaLWwsFUODvgizlwLfnACY63UTNBY4mA4ikacImRviP2u8nCHj6keJwzh9iCfyyX JiiC/Z5dQt1VimKUv0S3ot/+mRgoFGq8y+VKFwmazjjAO2ngPS3fpKo9yJFDytlLIWft+2 lElPhAqaLMg9f2HagrSQeJ3jbHnVhE4= ARC-Seal: i=1; s=arc-20220608; d=hostedemail.com; t=1772221392; a=rsa-sha256; cv=none; b=17+CGbMwljHI2Tq5mk/k6w46HV2usF/ao/WmIvHL5keBTZakBIbm7Uq3Lo/a0+2DtH8rQQ f8dF2a2/CqM7zdnrnrLP5Uf+8uYhW+O2eHeGHr2S4FqB1KKUgUt+530ujOg9UFtvAwPKej AMcUYaJGBvDshxIz17B5tE5RUi+r7Gs= ARC-Authentication-Results: i=1; imf04.hostedemail.com; dkim=pass header.d=kernel.org header.s=k20201202 header.b=nR5TWSeg; spf=pass (imf04.hostedemail.com: domain of kas@kernel.org designates 172.234.252.31 as permitted sender) smtp.mailfrom=kas@kernel.org; dmarc=pass (policy=quarantine) header.from=kernel.org Received: from smtp.kernel.org (transwarp.subspace.kernel.org [100.75.92.58]) by sea.source.kernel.org (Postfix) with ESMTP id ADE1C409DD; Fri, 27 Feb 2026 19:43:11 +0000 (UTC) Received: by smtp.kernel.org (Postfix) with ESMTPSA id 90F64C19421; Fri, 27 Feb 2026 19:43:10 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1772221391; bh=Eqd+kkKOLROO+nOoXS7ZuwJRjspyFKG6DtwT0T4pgSU=; h=From:To:Cc:Subject:Date:From; b=nR5TWSegwVG/clKHCY8uB3wbisVSqNHj/WKQx7dWenFLHuYoE20ZOkBwXbbzngg00 wGf4b2eDa4C9MrJU+Gf5jz+b5gkBl+BgXNPcoFCofcvFe+XyCKxLTuUMumTwkT9sfO fkxFKpVDgEEnaOoDc5VxF3o7BhuI2CUF1vDcybfyDkLwxp0rXSVbF/yw5SLtwv0P77 Fn2ShcHLtt29YwGD4yBU3W+VNvNYG9DmSm5m1yvbywLZx60sY4w4lioY08TlbtYnG6 IXGGaNHhiiNlvkwsIkip0/8l34BFa/WAzdoeqki/ejt8nipAZZ5Lma8M6gW7DBkCZ8 EofLgek+n7mfA== Received: from phl-compute-01.internal (phl-compute-01.internal [10.202.2.41]) by mailfauth.phl.internal (Postfix) with ESMTP id AA341F40068; Fri, 27 Feb 2026 14:43:09 -0500 (EST) Received: from phl-frontend-03 ([10.202.2.162]) by phl-compute-01.internal (MEProxy); Fri, 27 Feb 2026 14:43:09 -0500 X-ME-Sender: X-ME-Received: X-ME-Proxy-Cause: gggruggvucftvghtrhhoucdtuddrgeefgedrtddtgddvgeelkeejucetufdoteggodetrf dotffvucfrrhhofhhilhgvmecuhfgrshhtofgrihhlpdfurfetoffkrfgpnffqhgenuceu rghilhhouhhtmecufedttdenucesvcftvggtihhpihgvnhhtshculddquddttddmnecujf gurhephffvvefufffkofgggfestdekredtredttdenucfhrhhomhepfdfmihhrhihlucfu hhhuthhsvghmrghuucdlofgvthgrmddfuceokhgrsheskhgvrhhnvghlrdhorhhgqeenuc ggtffrrghtthgvrhhnpeetieekffduudfgheektddvgeetieefteefudefheekffeiteff ffelieeiueevhfenucevlhhushhtvghrufhiiigvpedtnecurfgrrhgrmhepmhgrihhlfh hrohhmpehkihhrihhllhdomhgvshhmthhprghuthhhphgvrhhsohhnrghlihhthidqudei udduiedvieehhedqvdekgeeggeejvdekqdhkrghspeepkhgvrhhnvghlrdhorhhgsehshh huthgvmhhovhdrnhgrmhgvpdhnsggprhgtphhtthhopedvkedpmhhouggvpehsmhhtphho uhhtpdhrtghpthhtoheprghkphhmsehlihhnuhigqdhfohhunhgurghtihhonhdrohhrgh dprhgtphhtthhopehmuhgthhhunhdrshhonhhgsehlihhnuhigrdguvghvpdhrtghpthht ohepuggrvhhiugeskhgvrhhnvghlrdhorhhgpdhrtghpthhtohepfihilhhlhiesihhnfh hrrgguvggrugdrohhrghdprhgtphhtthhopehushgrmhgrrghrihhfieegvdesghhmrghi lhdrtghomhdprhgtphhtthhopehfvhgulhesghhoohhglhgvrdgtohhmpdhrtghpthhtoh epohhsrghlvhgrughorhesshhushgvrdguvgdprhgtphhtthhopehrphhptheskhgvrhhn vghlrdhorhhgpdhrtghpthhtohepvhgsrggskhgrsehsuhhsvgdrtgii X-ME-Proxy: Feedback-ID: i10464835:Fastmail Received: by mail.messagingengine.com (Postfix) with ESMTPA; Fri, 27 Feb 2026 14:43:09 -0500 (EST) From: "Kiryl Shutsemau (Meta)" To: Andrew Morton , Muchun Song , David Hildenbrand , Matthew Wilcox , Usama Arif , Frank van der Linden Cc: Oscar Salvador , Mike Rapoport , Vlastimil Babka , Lorenzo Stoakes , Zi Yan , Baoquan He , Michal Hocko , Johannes Weiner , Jonathan Corbet , Huacai Chen , WANG Xuerui , Palmer Dabbelt , Paul Walmsley , Albert Ou , Alexandre Ghiti , kernel-team@meta.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-doc@vger.kernel.org, loongarch@lists.linux.dev, linux-riscv@lists.infradead.org, "Kiryl Shutsemau (Meta)" Subject: [PATCHv7 RESEND 00/17] mm: Eliminate fake head pages from vmemmap optimization Date: Fri, 27 Feb 2026 19:42:38 +0000 Message-ID: <20260227194302.274384-1-kas@kernel.org> X-Mailer: git-send-email 2.51.2 MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Rspam-User: X-Stat-Signature: z1pw35gs5z1yi8fw89xqrg17ws6mjbdt X-Rspamd-Queue-Id: B6F1940006 X-Rspamd-Server: rspam03 X-HE-Tag: 1772221392-807943 X-HE-Meta: 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 K7oqzsiG RRJumTHY1Do0NReUeIgHT+YYTNri/ctKaE69cLMXqQlgMaPsVD38xzsspmlTPqsl7mcgMUxoa8p10QF2+3pTZQexg5YYV/gHpEWPDn5L7P4KbYBC/m+mADYNQYDtAQePdWm0NI8Ox63038ngHFHmANGjC2/h+UGLdwsqRxMUKCxrPB1P7c965mu8TEtI9fMF0327i90XZAady/fKE4U+K15gr7d4f6ifMQV7CdQGlRIMlhsQ= Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: List-Subscribe: List-Unsubscribe: This series removes "fake head pages" from the HugeTLB vmemmap optimization (HVO) by changing how tail pages encode their relationship to the head page. It simplifies compound_head() and page_ref_add_unless(). Both are in the hot path. Background ========== HVO reduces memory overhead by freeing vmemmap pages for HugeTLB pages and remapping the freed virtual addresses to a single physical page. Previously, all tail page vmemmap entries were remapped to the first vmemmap page (containing the head struct page), creating "fake heads" - tail pages that appear to have PG_head set when accessed through the deduplicated vmemmap. This required special handling in compound_head() to detect and work around fake heads, adding complexity and overhead to a very hot path. New Approach ============ For architectures/configs where sizeof(struct page) is a power of 2 (the common case), this series changes how position of the head page is encoded in the tail pages. Instead of storing a pointer to the head page, the ->compound_info (renamed from ->compound_head) now stores a mask. The mask can be applied to any tail page's virtual address to compute the head page address. Critically, all tail pages of the same order now have identical compound_info values, regardless of which compound page they belong to. The key insight is that all tail pages of the same order now have identical compound_info values, regardless of which compound page they belong to. In v7, these shared tail pages are allocated per-zone. This ensures that zone information (stored in page->flags) is correct even for shared tail pages, removing the need for the special-casing in page_zonenum() proposed in earlier versions. To support per-zone shared pages for boot-allocated gigantic pages, the vmemmap population is deferred until zones are initialized. This simplifies the logic significantly and allows the removal of vmemmap_undo_hvo(). Benefits ======== 1. Simplified compound_head(): No fake head detection needed, can be implemented in a branchless manner. 2. Simplified page_ref_add_unless(): RCU protection removed since there's no race with fake head remapping. 3. Cleaner architecture: The shared tail pages are truly read-only and contain valid tail page metadata. If sizeof(struct page) is not power-of-2, there are no functional changes. HVO is not supported in this configuration. I had hoped to see performance improvement, but my testing thus far has shown either no change or only a slight improvement within the noise. Series Organization =================== Patch 1: Move MAX_FOLIO_ORDER definition to mmzone.h. Patches 2-4: Refactoring of field names and interfaces. Patches 5-6: Architecture alignment for LoongArch and RISC-V. Patch 7: Mask-based compound_head() implementation. Patch 8: Add memmap alignment checks. Patch 9: Branchless compound_head() optimization. Patch 10: Defer vmemmap population for bootmem hugepages. Patch 11: Refactor vmemmap_walk. Patch 12: x86 vDSO build fix. Patch 13: Eliminate fake heads with per-zone shared tail pages. Patches 14-16: Cleanup of fake head infrastructure. Patch 17: Documentation update. Patch 18: Use compound_head() in page_slab(). Changes in v7: ============== - Move vmemmap_tails from per-node to per-zone. This ensures tail pages have correct zone information. - Defer vmemmap population for boot-allocated huge pages to hugetlb_vmemmap_init_late(). This makes zone information available during population and allows removing vmemmap_undo_hvo(). - Undefine CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP for x86 vdso32 to fix build issues. - Remove the patch that modified page_zonenum(), as per-zone shared pages make it unnecessary. Changes in v6: ============== - Simplify memmap alignment check in mm/sparse.c: use VM_BUG_ON() (Muchun) - Store struct page pointers in vmemmap_tails[] instead of PFNs. (Muchun) - Fix build error on powerpc due to negative NR_VMEMMAP_TAILS. Changes in v5: ============== - Rebased to mm-everything-2026-01-27-04-35 - Add arch-specific patches to align vmemmap to maximal folio size for riscv and LoongArch architectures. - Strengthen the memmap alignment check in mm/sparse.c: use BUG() for CONFIG_DEBUG_VM, WARN() otherwise. (Muchun) - Use cmpxchg() instead of hugetlb_lock to update vmemmap_tails array. (Muchun) - Update page_slab(). Changes in v4: ============== - Fix build issues due to linux/mmzone.h <-> linux/pgtable.h dependency loop by avoiding including linux/pgtable.h into linux/mmzone.h - Rework vmemmap_remap_alloc() interface. (Muchun) - Use &folio->page instead of folio address for optimization target. (Muchun) Changes in v3: ============== - Fixed error recovery path in vmemmap_remap_free() to pass correct start address for TLB flush. (Muchun) - Wrapped the mask-based compound_info encoding within CONFIG_SPARSEMEM_VMEMMAP check via compound_info_has_mask(). For other memory models, alignment guarantees are harder to verify. (Muchun) - Updated vmemmap_dedup.rst documentation wording: changed "vmemmap_tail shared for the struct hstate" to "A single, per-node page frame shared among all hugepages of the same size". (Muchun) - Fixed build error with MAX_FOLIO_ORDER expanding to undefined PUD_ORDER in certain configurations. (kernel test robot) Changes in v2: ============== - Handle boot-allocated huge pages correctly. (Frank) - Changed from per-hstate vmemmap_tail to per-node vmemmap_tails[] array in pglist_data. (Muchun) - Added spin_lock(&hugetlb_lock) protection in vmemmap_get_tail() to fix a race condition where two threads could both allocate tail pages. The losing thread now properly frees its allocated page. (Usama) - Add warning if memmap is not aligned to MAX_FOLIO_SIZE, which is required for the mask approach. (Muchun) - Make page_zonenum() use head page - correctness fix since shared tail pages cannot have valid zone information. (Muchun) - Added 'const' qualifier to head parameter in set_compound_head() and prep_compound_tail(). (Usama) - Updated commit messages. Kiryl Shutsemau (16): mm: Move MAX_FOLIO_ORDER definition to mmzone.h mm: Change the interface of prep_compound_tail() mm: Rename the 'compound_head' field in the 'struct page' to 'compound_info' mm: Move set/clear_compound_head() next to compound_head() riscv/mm: Align vmemmap to maximal folio size LoongArch/mm: Align vmemmap to maximal folio size mm: Rework compound_head() for power-of-2 sizeof(struct page) mm/sparse: Check memmap alignment for compound_info_has_mask() mm/hugetlb: Refactor code around vmemmap_walk mm/hugetlb: Remove fake head pages mm: Drop fake head checks hugetlb: Remove VMEMMAP_SYNCHRONIZE_RCU mm/hugetlb: Remove hugetlb_optimize_vmemmap_key static key mm: Remove the branch from compound_head() hugetlb: Update vmemmap_dedup.rst mm/slab: Use compound_head() in page_slab() Kiryl Shutsemau (Meta) (2): mm/hugetlb: Defer vmemmap population for bootmem hugepages x86/vdso: Undefine CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP for vdso32 .../admin-guide/kdump/vmcoreinfo.rst | 2 +- Documentation/mm/vmemmap_dedup.rst | 62 ++- arch/loongarch/include/asm/pgtable.h | 3 +- arch/riscv/mm/init.c | 3 +- arch/x86/entry/vdso/vdso32/fake_32bit_build.h | 1 + include/linux/mm.h | 36 +- include/linux/mm_types.h | 20 +- include/linux/mmzone.h | 57 +++ include/linux/page-flags.h | 166 ++++---- include/linux/page_ref.h | 8 +- include/linux/types.h | 2 +- kernel/vmcore_info.c | 2 +- mm/hugetlb.c | 8 +- mm/hugetlb_vmemmap.c | 362 +++++++++--------- mm/internal.h | 18 +- mm/mm_init.c | 2 +- mm/page_alloc.c | 4 +- mm/slab.h | 8 +- mm/sparse-vmemmap.c | 110 +++--- mm/sparse.c | 5 + mm/util.c | 16 +- 21 files changed, 448 insertions(+), 447 deletions(-) -- 2.51.2