[PATCH v5 05/12] mm/sparse-vmemmap: prepare DAX vmemmap population for compound page orders
flat view
COOLING9d
REVIEWED: 3 (3M)
From: Muchun Song <hidden>
Date: 2026-09-27 02:55:37
Also in:
linux-doc, linux-mm, lkml
Subsystem:
memory management, memory management - core, the rest · Maintainers:
Andrew Morton, David Hildenbrand, Linus Torvalds
Revision v5 of 6 in this series; 1 review trailer.
Revisions (6)
Device DAX still uses vmemmap_populate_compound_pages() to populate its compound-page vmemmap mappings. That helper allocates the head and first tail vmemmap pages explicitly, then reuses the first tail page for the remaining tail page mappings. Device DAX is being moved to the section-based vmemmap optimization infrastructure, but it cannot switch to the generic section-based population path yet. Once a later patch records the DAX compound page order in section metadata, DAX head and first-tail PFNs can look optimizable to the generic helpers as well. Add a DAX-specific population flag for this transition. It keeps DAX head/first-tail allocations on the normal vmemmap allocation path, while preserving the existing page reference for reused DAX tail mappings. Signed-off-by: Muchun Song <redacted> Acked-by: Qi Zheng <qi.zheng@linux.dev> --- v3: - Update the subject and commit message to use compound page order terminology v2: - Collect Acked-by from Qi Zheng --- mm/sparse-vmemmap.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-)
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index e4dae98ba7f8..2457ea2c6dca 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c@@ -35,8 +35,8 @@ /* * Flags for vmemmap_populate_range and friends. */ -/* Get a ref on the head page struct page, for ZONE_DEVICE compound pages */ -#define VMEMMAP_POPULATE_PAGEREF 0x0001 +/* Vmemmap population for ZONE_DEVICE compound pages */ +#define VMEMMAP_POPULATE_DAX 0x0001 #include "internal.h" #include "mm_init.h"
@@ -243,13 +243,17 @@ static inline struct page *vmemmap_shared_tail_page(unsigned int order, #endif static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node, - struct vmem_altmap *altmap) + struct vmem_altmap *altmap, unsigned long flags) { struct zone *zone; struct page *page; const unsigned int order = pfn_to_section_compound_order(pfn); - if (!vmemmap_optimizable_pfn(pfn)) + /* + * 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) return vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap); zone = pfn_to_zone(pfn, node);
@@ -271,7 +275,7 @@ 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); + void *p = vmemmap_alloc_pte(pfn, node, altmap, flags); if (!p) return NULL;
@@ -286,7 +290,7 @@ static pte_t * __meminit vmemmap_pte_populate(pmd_t *pmd, unsigned long addr, in * and through vmemmap_populate_compound_pages() when * slab is available. */ - if (flags & VMEMMAP_POPULATE_PAGEREF) + if (flags & VMEMMAP_POPULATE_DAX) get_page(pfn_to_page(ptpfn)); } entry = pfn_pte(ptpfn, PAGE_KERNEL);
@@ -546,6 +550,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, unsigned long size, addr; pte_t *pte; int rc; + unsigned long flags = VMEMMAP_POPULATE_DAX; if (reuse_compound_section(start_pfn, pgmap)) { pte = compound_section_tail_page(start);
@@ -557,8 +562,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, * with just tail struct pages. */ return vmemmap_populate_range(start, end, node, NULL, - pte_pfn(ptep_get(pte)), - VMEMMAP_POPULATE_PAGEREF); + pte_pfn(ptep_get(pte)), flags); } size = min(end - start, pgmap_vmemmap_nr(pgmap) * sizeof(struct page));
@@ -566,13 +570,13 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, unsigned long next, last = addr + size; /* Populate the head page vmemmap page */ - pte = vmemmap_populate_address(addr, node, NULL, -1, 0); + pte = vmemmap_populate_address(addr, node, NULL, -1, flags); if (!pte) return -ENOMEM; /* Populate the tail pages vmemmap page */ next = addr + PAGE_SIZE; - pte = vmemmap_populate_address(next, node, NULL, -1, 0); + pte = vmemmap_populate_address(next, node, NULL, -1, flags); if (!pte) return -ENOMEM;
@@ -582,8 +586,7 @@ static int __meminit vmemmap_populate_compound_pages(unsigned long start_pfn, */ next += PAGE_SIZE; rc = vmemmap_populate_range(next, last, node, NULL, - pte_pfn(ptep_get(pte)), - VMEMMAP_POPULATE_PAGEREF); + pte_pfn(ptep_get(pte)), flags); if (rc) return -ENOMEM; }
--
2.54.0