From 4b77739fe7893bced405891233511310554871a7 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Sat, 10 Oct 2026 15:57:50 +0800 Subject: [PATCH] mm/sparse-vmemmap: drop VMEMMAP_POPULATE_DAX Patch series "mm: Unify device DAX and HugeTLB vmemmap population paths", v4. This series is split out from the earlier, larger series "mm: Generalize HVO for HugeTLB and device DAX" [2]. While the parent series generalizes vmemmap optimization across HugeTLB and device DAX, this subset addresses a single, self-contained step: unifying their vmemmap population paths. After the preceding Device DAX conversion, both HugeTLB and Device DAX describe optimized vmemmap mappings through memory-section metadata and use per-zone shared tail vmemmap pages. The generic code, however, still carries a Device DAX-specific population flag and compound-page population path, along with arguments and helpers needed only by that path. This series first removes VMEMMAP_POPULATE_DAX and moves selection and reference handling for the shared tail page into the common vmemmap population path. It then removes the generic Device DAX-specific compound-page population path and routes section vmemmap population through vmemmap_populate(). The powerpc radix path continues to use its architecture-specific compound-page population implementation for optimizable sections. The remaining patches remove the unused ptpfn argument, open-code vmemmap_populate_address() now that no caller needs its returned PTE, and add a warning for inconsistent zone initialization of shared tail vmemmap pages. This is the fourth smaller step toward the broader HVO generalization. After this series, HugeTLB and Device DAX use the same population model instead of parallel generic paths, while powerpc keeps its architecture-specific implementation. This patch (of 6): VMEMMAP_POPULATE_DAX currently distinguishes DAX vmemmap population in two places: it keeps allocations on the normal path and takes a reference when a backing page is supplied for reuse. After Device DAX switched to the common per-zone shared tail page, both conditions can be determined locally. DAX supplies ptpfn for every shared tail mapping and requests an allocation only for compound head mappings, whose PFNs are not optimizable. Therefore, vmemmap_optimizable_pfn() alone selects the correct allocation path. When ptpfn is supplied, the caller is reusing an existing backing page. Once the slab allocator is available, take a reference for each reused mapping to balance the release performed by vmemmap_free(). Although the buddy allocator is available before slab, no vmemmap population occurs in that interval. Earlier mappings are backed by memblock/reserved memory and do not need page reference accounting. Remove VMEMMAP_POPULATE_DAX and the flags argument from the vmemmap population helpers. Link: https://lore.kernel.org/20261010075755.83339-1-songmuchun@bytedance.com Link: https://lore.kernel.org/20261010075755.83339-2-songmuchun@bytedance.com Link: https://lore.kernel.org/20260930140627.57431-1-songmuchun@bytedance.com/ [1] Link: https://lore.kernel.org/20260513130542.35604-1-songmuchun@bytedance.com/ [2] Signed-off-by: Muchun Song Signed-off-by: Andrew Morton Reviewed-by: Lance Yang Acked-by: Qi Zheng Cc: Madhavan Srinivasan Cc: Mike Rapoport Cc: David Hildenbrand Cc: Michael Ellerman Cc: Nicholas Piggin Cc: Christophe Leroy Cc: Ritesh Harjani (IBM) Cc: Shrikanth Hegde Cc: Lorenzo Stoakes Cc: Liam R. Howlett Cc: Vlastimil Babka Cc: Suren Baghdasaryan Cc: Michal Hocko --- mm/sparse-vmemmap.c | 36 +++++++++++++----------------------- 1 file changed, 13 insertions(+), 23 deletions(-) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 098975861523..b23efff80137 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -32,12 +32,6 @@ #include #include -/* - * Flags for vmemmap_populate_range and friends. - */ -/* Vmemmap population for ZONE_DEVICE compound pages */ -#define VMEMMAP_POPULATE_DAX 0x0001 - #include "internal.h" #include "mm_init.h" #include "sparse.h" @@ -241,7 +235,7 @@ struct page __ref *vmemmap_shared_tail_page(unsigned int order, struct zone *zon #endif static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node, - struct vmem_altmap *altmap, unsigned long flags) + struct vmem_altmap *altmap) { struct zone *zone; struct page *page; @@ -251,7 +245,7 @@ static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node, * Device DAX still relies on vmemmap_populate_compound_pages() for * head/first-tail allocation and tail-page reuse. */ - if (!vmemmap_optimizable_pfn(pfn) || flags & VMEMMAP_POPULATE_DAX) + if (!vmemmap_optimizable_pfn(pfn)) return vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); zone = pfn_to_zone(pfn, node); @@ -263,8 +257,7 @@ static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node, } static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, int node, - struct vmem_altmap *altmap, - unsigned long ptpfn, unsigned long flags) + struct vmem_altmap *altmap, unsigned long ptpfn) { pte_t *pte = pte_offset_kernel(pmd, addr); unsigned long pfn = page_to_pfn((struct page *)addr); @@ -273,7 +266,7 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in pte_t entry; if (ptpfn == (unsigned long)-1) { - void *p = vmemmap_alloc_pte(pfn, node, altmap, flags); + void *p = vmemmap_alloc_pte(pfn, node, altmap); if (!p) return NULL; @@ -291,7 +284,7 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in * Use try_get_page() to prevent the shared page refcount * from overflowing. */ - if ((flags & VMEMMAP_POPULATE_DAX) && + if (slab_is_available() && !try_get_page(pfn_to_page(ptpfn))) return NULL; } @@ -355,8 +348,7 @@ static pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node, struct vmem_altmap *altmap, - unsigned long ptpfn, - unsigned long flags) + unsigned long ptpfn) { pgd_t *pgd; p4d_t *p4d; @@ -376,7 +368,7 @@ static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node, pmd = vmemmap_pmd_populate(pud, addr, node); if (!pmd) return NULL; - pte = vmemmap_pte_populate(pmd, addr, node, altmap, ptpfn, flags); + pte = vmemmap_pte_populate(pmd, addr, node, altmap, ptpfn); if (!pte) return NULL; vmemmap_verify(pte, node, addr, addr + PAGE_SIZE); @@ -387,15 +379,14 @@ static pte_t * __meminit vmemmap_populate_address(unsigned long addr, int node, static int __meminit vmemmap_populate_range(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap, - unsigned long ptpfn, - unsigned long flags) + unsigned long ptpfn) { unsigned long addr = start; pte_t *pte; for (; addr < end; addr += PAGE_SIZE) { pte = vmemmap_populate_address(addr, node, altmap, - ptpfn, flags); + ptpfn); if (!pte) return -ENOMEM; } @@ -406,7 +397,7 @@ static int __meminit vmemmap_populate_range(unsigned long start, int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) { - return vmemmap_populate_range(start, end, node, altmap, -1, 0); + return vmemmap_populate_range(start, end, node, altmap, -1); } /* @@ -532,7 +523,6 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, unsigned long end, int node, struct dev_pagemap *pgmap) { - const unsigned long flags = VMEMMAP_POPULATE_DAX; const unsigned int order = pfn_to_section_compound_order(start_pfn); unsigned long size, addr; pte_t *pte; @@ -545,14 +535,14 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, if (reuse_compound_section(start_pfn, pgmap)) return vmemmap_populate_range(start, end, node, NULL, - page_to_pfn(page), flags); + page_to_pfn(page)); size = min(end - start, (1UL << order) * sizeof(struct page)); for (addr = start; addr < end; addr += size) { unsigned long next, last = addr + size; /* Populate the head page vmemmap page */ - pte = vmemmap_populate_address(addr, node, NULL, -1, flags); + pte = vmemmap_populate_address(addr, node, NULL, -1); if (!pte) return -ENOMEM; @@ -562,7 +552,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, */ next = addr + PAGE_SIZE; rc = vmemmap_populate_range(next, last, node, NULL, - page_to_pfn(page), flags); + page_to_pfn(page)); if (rc) return -ENOMEM; }