From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-alma10-1.taild15c8.ts.net [100.103.45.18]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id A57D8370ADA; Thu, 17 Sep 2026 01:35:46 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=100.103.45.18 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789608948; cv=none; b=Y4q7EtYh78XmMeknKJZhYHQ30NSswDxyk268txVwEn5rv8VWAEEwidv0L76dxgDJ4nVD38qqeFD6/1RhRYmaJY1p5IafE5QDOr3dgCEJTKzT9gnTh89GnX6CkhneER/KybdxZUpn50OSwdiczvk7xEB9tz8Jf53xMyGZ7TndU+I= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1789608948; c=relaxed/simple; bh=/GDPtICWwYIwMuKDTMe9yj5mgaGjTtxwLwr7b1m6I7k=; h=Date:From:To:Cc:Subject:Message-Id:In-Reply-To:References: Mime-Version:Content-Type; b=f9TxxkuwTIRPKKQ+gEICMxkzK1BUUtS+vuShBXOUGavXIQrjUL76jv/nfVYUQQOa+eOxrQB+vGriFJHmZ7r/hgByqICvUNXdwy0/2QAXnbkI87SmtOSnxdsR99FODGGEYyOEW8mUS4vE0sDIEeCVJ+VqngmI8b1jOAo7XnMbuJ0= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b=AaNPuBUa; arc=none smtp.client-ip=100.103.45.18 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux-foundation.org header.i=@linux-foundation.org header.b="AaNPuBUa" Received: by smtp.kernel.org (Postfix) with ESMTPSA id D65DF1F000FF; Thu, 17 Sep 2026 01:35:45 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux-foundation.org; s=korg; t=1789608946; bh=xY8MXqZQKMcl2CIWuQH5x81TYqIBertgZUarW5BI/rY=; h=Date:From:To:Cc:Subject:In-Reply-To:References; b=AaNPuBUaXfkXKF6L293sg4La152kF9SYon65H25RqbxF4jVF2jFvXi18CcDRwfWhi wv0130+KWysnx0l4YB6VKqwgbMFpsc9UA2OKhPkVYGqxsg8wD8LqHtZgIAVP1Owloc hfY0DHS4zqgTZSomdebsvxMCn5S9l0oD0ciFxm0Y= Date: Wed, 16 Sep 2026 18:35:45 -0700 From: Andrew Morton To: Muchun Song Cc: David Hildenbrand , Oscar Salvador , Madhavan Srinivasan , Michael Ellerman , Jonathan Corbet , linux-mm@kvack.org, linux-kernel@vger.kernel.org, linuxppc-dev@lists.ozlabs.org, linux-doc@vger.kernel.org, Muchun Song , Lorenzo Stoakes , Mike Rapoport , Qi Zheng , Nicholas Piggin , Christophe Leroy , Randy Dunlap Subject: Re: [PATCH v4 00/11] mm: Switch device DAX to section-based vmemmap optimization Message-Id: <20260916183545.b8244db6aa2caf783b1fa5e9@linux-foundation.org> In-Reply-To: <20260916064341.1825793-1-songmuchun@bytedance.com> References: <20260916064341.1825793-1-songmuchun@bytedance.com> X-Mailer: Sylpheed 3.8.0beta1 (GTK+ 2.24.33; x86_64-pc-linux-gnu) Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit On Wed, 16 Sep 2026 14:43:30 +0800 Muchun Song wrote: > This series is split out from the earlier, larger series "mm: Generalize > HVO for HugeTLB and device DAX" [1]. While the parent series generalizes > vmemmap optimization across HugeTLB and device DAX, this subset addresses > a single, self-contained step: switching device DAX to the section-based > sparse-vmemmap optimization infrastructure introduced for HugeTLB. > > After the HugeTLB conversion, optimized vmemmap state is described by > the memory section and the sparse-vmemmap population path can allocate or > reuse shared tail vmemmap pages based on that metadata. Device DAX still > uses the older DAX-specific population model, including a separate tail > vmemmap page reservation and architecture-specific logic to locate or > populate reusable tail pages. > > ... > > This is intended to be the third smaller step toward the broader HVO > generalization. The wider HVO consolidation between HugeTLB and device > DAX is left for follow-up series. Thanks, I updated mm-unstable to this version. > v4: > - Rename CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION to > CONFIG_VMEMMAP_OPTIMIZATION (suggested by Mike Rapoport) > - Collect Acked-by tags from Mike Rapoport > Here's how v4 altered mm.git: arch/x86/entry/vdso/vdso32/fake_32bit_build.h | 2 +- drivers/dax/Kconfig | 2 -- fs/Kconfig | 2 +- include/linux/mm.h | 2 +- include/linux/mmzone.h | 6 +++--- include/linux/page-flags.h | 2 +- include/linux/vmemmap-optimization.h | 6 +++--- mm/Kconfig | 3 ++- 8 files changed, 12 insertions(+), 13 deletions(-) --- a/arch/x86/entry/vdso/vdso32/fake_32bit_build.h~b +++ a/arch/x86/entry/vdso/vdso32/fake_32bit_build.h @@ -11,7 +11,7 @@ #undef CONFIG_PGTABLE_LEVELS #undef CONFIG_ILLEGAL_POINTER_VALUE #undef CONFIG_SPARSEMEM_VMEMMAP -#undef CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION +#undef CONFIG_VMEMMAP_OPTIMIZATION #undef CONFIG_NR_CPUS #undef CONFIG_PARAVIRT_XXL --- a/drivers/dax/Kconfig~b +++ a/drivers/dax/Kconfig @@ -8,8 +8,6 @@ if DAX config DEV_DAX tristate "Device DAX: direct access mapping device" depends on TRANSPARENT_HUGEPAGE - depends on ZONE_DEVICE - select SPARSEMEM_VMEMMAP_OPTIMIZATION if ARCH_WANT_OPTIMIZE_DAX_VMEMMAP help Support raw access to differentiated (persistence, bandwidth, latency...) memory via an mmap(2) capable character --- a/fs/Kconfig~b +++ a/fs/Kconfig @@ -278,7 +278,7 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP def_bool HUGETLB_PAGE depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP depends on SPARSEMEM_VMEMMAP - select SPARSEMEM_VMEMMAP_OPTIMIZATION + select VMEMMAP_OPTIMIZATION config HUGETLB_PMD_PAGE_TABLE_SHARING def_bool HUGETLB_PAGE --- a/include/linux/mm.h~b +++ a/include/linux/mm.h @@ -5174,7 +5174,7 @@ static inline bool __vmemmap_can_optimiz unsigned long nr_pages; unsigned long nr_vmemmap_pages; - if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION)) + if (!IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) return false; if (!pgmap || !is_power_of_2(sizeof(struct page))) --- a/include/linux/mmzone.h~b +++ a/include/linux/mmzone.h @@ -103,7 +103,7 @@ * HVO which is only active if the size of struct page is a power of 2. */ #define MAX_FOLIO_VMEMMAP_ALIGN \ - (IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION) && \ + (IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION) && \ is_power_of_2(sizeof(struct page)) ? \ MAX_FOLIO_NR_PAGES * sizeof(struct page) : 0) @@ -117,7 +117,7 @@ (MAX_FOLIO_ORDER - VMEMMAP_OPTIMIZATION_MIN_ORDER + 1) #define VMEMMAP_OPTIMIZATION_NR_ORDERS \ ((__VMEMMAP_OPTIMIZATION_NR_ORDERS > 0 && \ - IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION)) ? __VMEMMAP_OPTIMIZATION_NR_ORDERS : 0) + IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) ? __VMEMMAP_OPTIMIZATION_NR_ORDERS : 0) enum migratetype { MIGRATE_UNMOVABLE, @@ -2020,7 +2020,7 @@ struct mem_section { unsigned long section_mem_map; struct mem_section_usage *usage; -#ifdef CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION +#ifdef CONFIG_VMEMMAP_OPTIMIZATION /* * Normally, sections hold regular (order-0) pages. However, for * sections with HVO enabled, this tracks the compound page order --- a/include/linux/page-flags.h~b +++ a/include/linux/page-flags.h @@ -214,7 +214,7 @@ static __always_inline bool compound_inf * but it requires validating that struct pages are naturally aligned * for all orders up to the MAX_FOLIO_ORDER, which can be tricky. */ - if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION)) + if (!IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) return false; return is_power_of_2(sizeof(struct page)); --- a/include/linux/vmemmap-optimization.h~b +++ a/include/linux/vmemmap-optimization.h @@ -14,7 +14,7 @@ #include #include -#ifdef CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION +#ifdef CONFIG_VMEMMAP_OPTIMIZATION static inline unsigned int section_compound_order(const struct mem_section *section) { return section->compound_page_order; @@ -64,7 +64,7 @@ static inline unsigned int pfn_to_sectio { return 0; } -#endif /* CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION */ +#endif /* CONFIG_VMEMMAP_OPTIMIZATION */ static inline bool vmemmap_optimizable_pfn(unsigned long pfn) { @@ -79,7 +79,7 @@ static inline bool vmemmap_optimizable_p static inline bool vmemmap_optimizable_order(unsigned int order) { - if (!IS_ENABLED(CONFIG_SPARSEMEM_VMEMMAP_OPTIMIZATION)) + if (!IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) return false; if (!is_power_of_2(sizeof(struct page))) --- a/mm/Kconfig~b +++ a/mm/Kconfig @@ -461,7 +461,7 @@ config SPARSEMEM_VMEMMAP pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. -config SPARSEMEM_VMEMMAP_OPTIMIZATION +config VMEMMAP_OPTIMIZATION bool depends on SPARSEMEM_VMEMMAP @@ -1224,6 +1224,7 @@ config ZONE_DMA32 config ZONE_DEVICE bool "Device memory (pmem, HMM, etc...) hotplug support" depends on MEMORY_HOTREMOVE + select VMEMMAP_OPTIMIZATION if ARCH_WANT_OPTIMIZE_DAX_VMEMMAP select XARRAY_MULTI help _