[PATCH v4 01/11] mm/sparse-vmemmap: introduce CONFIG_VMEMMAP_OPTIMIZATION
From: Muchun Song <hidden>
Date: 2026-09-16 06:44:02
Also in:
linux-doc, linux-mm, lkml
Subsystem:
device direct access (dax), filesystems (vfs and infrastructure), memory management, memory management - core, memory management - mglru (multi-gen lru), the rest, x86 architecture (32-bit and 64-bit), x86 entry code, x86 vdso · Maintainers:
Dan Williams, Vishal Verma, Dave Jiang, Alison Schofield, Alexander Viro, Christian Brauner, Andrew Morton, David Hildenbrand, Linus Torvalds, Thomas Gleixner, Ingo Molnar, Borislav Petkov, Dave Hansen, Andy Lutomirski
The section-based vmemmap optimization infrastructure is still guarded by CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP, but it also can be used by device DAX. Introduce CONFIG_VMEMMAP_OPTIMIZATION as a common config for the shared infrastructure. Select the new option from HUGETLB_PAGE_OPTIMIZE_VMEMMAP and from DEV_DAX when the architecture opts in to DAX vmemmap optimization, and use it to guard the generic sparse-vmemmap state and helpers. Signed-off-by: Muchun Song <redacted> Acked-by: Qi Zheng <qi.zheng@linux.dev> Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org> --- v4: - Rename SPARSEMEM_VMEMMAP_OPTIMIZATION to VMEMMAP_OPTIMIZATION (suggested by Mike Rapoport) - Collect Acked-by from Mike Rapoport v2: - Fix SPARSEMEM_VMEMMAP_OPTIMIZATION being selected without SPARSEMEM_VMEMMAP reported by Sashiko. - Add an explicit DEV_DAX dependency on ZONE_DEVICE - Collect Acked-by from Qi Zheng --- arch/x86/entry/vdso/vdso32/fake_32bit_build.h | 2 +- drivers/dax/Kconfig | 2 ++ fs/Kconfig | 1 + include/linux/mm.h | 3 +++ include/linux/mmzone.h | 13 +++++++------ include/linux/page-flags.h | 5 ++--- mm/Kconfig | 4 ++++ mm/sparse.h | 4 ++-- 8 files changed, 22 insertions(+), 12 deletions(-)
diff --git a/arch/x86/entry/vdso/vdso32/fake_32bit_build.h b/arch/x86/entry/vdso/vdso32/fake_32bit_build.h
index bc3e549795c3..72a92cb9b53d 100644
--- a/arch/x86/entry/vdso/vdso32/fake_32bit_build.h
+++ b/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_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +#undef CONFIG_VMEMMAP_OPTIMIZATION #undef CONFIG_NR_CPUS #undef CONFIG_PARAVIRT_XXL
diff --git a/drivers/dax/Kconfig b/drivers/dax/Kconfig
index 602f9a0839a9..f50c6b32d826 100644
--- a/drivers/dax/Kconfig
+++ b/drivers/dax/Kconfig@@ -8,6 +8,8 @@ if DAX config DEV_DAX tristate "Device DAX: direct access mapping device" depends on TRANSPARENT_HUGEPAGE + depends on ZONE_DEVICE + select VMEMMAP_OPTIMIZATION if ARCH_WANT_OPTIMIZE_DAX_VMEMMAP help Support raw access to differentiated (persistence, bandwidth, latency...) memory via an mmap(2) capable character
diff --git a/fs/Kconfig b/fs/Kconfig
index d1c210c6508f..1454b7fe9641 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig@@ -278,6 +278,7 @@ config HUGETLB_PAGE_OPTIMIZE_VMEMMAP def_bool HUGETLB_PAGE depends on ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP depends on SPARSEMEM_VMEMMAP + select VMEMMAP_OPTIMIZATION config HUGETLB_PMD_PAGE_TABLE_SHARING def_bool HUGETLB_PAGE
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c49ef99b4413..070ce27e9cd3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h@@ -5175,6 +5175,9 @@ static inline bool __vmemmap_can_optimize(struct vmem_altmap *altmap, unsigned long nr_pages; unsigned long nr_vmemmap_pages; + if (!IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) + return false; + if (!pgmap || !is_power_of_2(sizeof(struct page))) return false;
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index acd94cecc0d3..56403841e887 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h@@ -102,9 +102,9 @@ * * HVO which is only active if the size of struct page is a power of 2. */ -#define MAX_FOLIO_VMEMMAP_ALIGN \ - (IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP) && \ - is_power_of_2(sizeof(struct page)) ? \ +#define MAX_FOLIO_VMEMMAP_ALIGN \ + (IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION) && \ + is_power_of_2(sizeof(struct page)) ? \ MAX_FOLIO_NR_PAGES * sizeof(struct page) : 0) /* The number of retained vmemmap pages with HVO enabled. */
@@ -116,7 +116,8 @@ #define __VMEMMAP_OPTIMIZATION_NR_ORDERS \ (MAX_FOLIO_ORDER - VMEMMAP_OPTIMIZATION_MIN_ORDER + 1) #define VMEMMAP_OPTIMIZATION_NR_ORDERS \ - (__VMEMMAP_OPTIMIZATION_NR_ORDERS > 0 ? __VMEMMAP_OPTIMIZATION_NR_ORDERS : 0) + ((__VMEMMAP_OPTIMIZATION_NR_ORDERS > 0 && \ + IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) ? __VMEMMAP_OPTIMIZATION_NR_ORDERS : 0) enum migratetype { MIGRATE_UNMOVABLE,
@@ -1155,7 +1156,7 @@ struct zone { /* Zone statistics */ atomic_long_t vm_stat[NR_VM_ZONE_STAT_ITEMS]; atomic_long_t vm_numa_event[NR_VM_NUMA_EVENT_ITEMS]; -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +#ifdef CONFIG_VMEMMAP_OPTIMIZATION struct page *vmemmap_tails[VMEMMAP_OPTIMIZATION_NR_ORDERS]; #endif } ____cacheline_internodealigned_in_smp;
@@ -2019,7 +2020,7 @@ struct mem_section { unsigned long section_mem_map; struct mem_section_usage *usage; -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +#ifdef CONFIG_VMEMMAP_OPTIMIZATION /* * Normally, sections hold regular (order-0) pages. However, for * sections with HVO enabled, this tracks the compound page order
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 86dd0470da11..7080a6a1a79e 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h@@ -208,14 +208,13 @@ enum pageflags { static __always_inline bool compound_info_has_mask(void) { /* - * Limit mask usage to HugeTLB vmemmap optimization (HVO) where it - * makes a difference. + * Limit mask usage to HVO where it makes a difference. * * The approach with mask would work in the wider set of conditions, * 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_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)) + if (!IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) return false; return is_power_of_2(sizeof(struct page));
diff --git a/mm/Kconfig b/mm/Kconfig
index bc7befafb47b..0fa2eb76e4f2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig@@ -461,6 +461,10 @@ config SPARSEMEM_VMEMMAP pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. +config VMEMMAP_OPTIMIZATION + bool + depends on SPARSEMEM_VMEMMAP + # # Select this config option from the architecture Kconfig, if it is preferred # to enable the feature of HugeTLB/dev_dax vmemmap optimization.
diff --git a/mm/sparse.h b/mm/sparse.h
index d3a71ef4fad0..d8c08a388e4e 100644
--- a/mm/sparse.h
+++ b/mm/sparse.h@@ -10,7 +10,7 @@ #include <linux/mmzone.h> -#ifdef CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP +#ifdef CONFIG_VMEMMAP_OPTIMIZATION static inline unsigned int section_compound_order(const struct mem_section *section) { return section->compound_page_order;
@@ -75,7 +75,7 @@ static inline bool vmemmap_optimizable_pfn(unsigned long pfn) static inline bool vmemmap_optimizable_order(unsigned int order) { - if (!IS_ENABLED(CONFIG_HUGETLB_PAGE_OPTIMIZE_VMEMMAP)) + if (!IS_ENABLED(CONFIG_VMEMMAP_OPTIMIZATION)) return false; if (!is_power_of_2(sizeof(struct page)))
--
2.54.0