All of lore.kernel.org
 help / color / mirror / Atom feed
* + mm-sparse-vmemmap-support-section-based-vmemmap-optimization.patch added to mm-unstable branch
@ 2026-09-10 23:05 Andrew Morton
  0 siblings, 0 replies; only message in thread
From: Andrew Morton @ 2026-09-10 23:05 UTC (permalink / raw)
  To: mm-commits, songmuchun, akpm


The patch titled
     Subject: mm/sparse-vmemmap: support section-based vmemmap optimization
has been added to the -mm mm-unstable branch.  Its filename is
     mm-sparse-vmemmap-support-section-based-vmemmap-optimization.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-sparse-vmemmap-support-section-based-vmemmap-optimization.patch

This patch will later appear in the mm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Muchun Song <songmuchun@bytedance.com>
Subject: mm/sparse-vmemmap: support section-based vmemmap optimization
Date: Thu, 10 Sep 2026 14:32:47 +0800

Teach sparse-vmemmap population code to use the compound page order when
deciding whether a vmemmap page can be optimized.

With this information, the common sparse-vmemmap population path can
allocate or reuse shared tail vmemmap pages directly instead of relying on
HugeTLB-specific handling.

This centralizes vmemmap optimization logic in the sparse-vmemmap code,
based on section metadata, and prepares for sharing the same mechanism
across different users of vmemmap optimization, including HugeTLB and DAX.

Link: https://lore.kernel.org/20260910063256.64386-9-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Qi Zheng <qi.zheng@linux.dev>
Cc: David Hildenbrand (Arm) <david@kernel.org>
Cc: David Laight <david.laight.linux@gmail.com>
Cc: Liam R. Howlett <liam@infradead.org>
Cc: Lorenzo Stoakes <ljs@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 mm/sparse-vmemmap.c |   46 ++++++++++++++++++++++++++++++++++--------
 mm/sparse.c         |    4 +--
 mm/sparse.h         |    7 ++++++
 3 files changed, 47 insertions(+), 10 deletions(-)

--- a/mm/sparse.c~mm-sparse-vmemmap-support-section-based-vmemmap-optimization
+++ a/mm/sparse.c
@@ -305,8 +305,8 @@ static void __init sparse_init_nid(int n
 							nid, NULL, NULL);
 			if (!map)
 				panic("Failed to allocate memmap for section %lu\n", pnum);
-			memmap_boot_pages_add(DIV_ROUND_UP(PAGES_PER_SECTION * sizeof(struct page),
-							   PAGE_SIZE));
+			memmap_boot_pages_add(section_nr_vmemmap_pages(pfn, PAGES_PER_SECTION,
+								       NULL, NULL));
 			sparse_init_early_section(nid, map, pnum, 0);
 		}
 	}
--- a/mm/sparse.h~mm-sparse-vmemmap-support-section-based-vmemmap-optimization
+++ a/mm/sparse.h
@@ -111,8 +111,15 @@ static inline void sparse_init(void) {}
  */
 #ifdef CONFIG_SPARSEMEM_VMEMMAP
 void sparse_init_subsection_map(void);
+int section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
 #else
 static inline void sparse_init_subsection_map(void) {}
+static inline int section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+	return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE);
+}
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 #endif /* __MM_SPARSE_H */
--- a/mm/sparse-vmemmap.c~mm-sparse-vmemmap-support-section-based-vmemmap-optimization
+++ a/mm/sparse-vmemmap.c
@@ -148,8 +148,7 @@ void __meminit vmemmap_verify(pte_t *pte
 			start, end - 1);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
-static int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
+int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages,
 		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 {
 	const struct mem_section *ms = __pfn_to_section(pfn);
@@ -175,7 +174,6 @@ static int __meminit section_nr_vmemmap_
 
 	return 0;
 }
-#endif
 
 static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
 {
@@ -215,19 +213,44 @@ static __meminit struct page *vmemmap_ge
 
 	return tail;
 }
+#else
+static inline struct page *vmemmap_get_tail(unsigned int order, struct zone *zone)
+{
+	return NULL;
+}
 #endif
 
+static __meminit void *vmemmap_alloc_pte(unsigned long pfn, int node,
+					 struct vmem_altmap *altmap)
+{
+	struct zone *zone;
+	struct page *page;
+	const unsigned int order = pfn_to_section_compound_order(pfn);
+
+	if (!vmemmap_optimizable_pfn(pfn))
+		return vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+
+	zone = pfn_to_zone(pfn, node);
+	page = vmemmap_get_tail(order, zone);
+	if (!page)
+		return NULL;
+
+	return page_address(page);
+}
+
 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)
 {
 	pte_t *pte = pte_offset_kernel(pmd, addr);
+	unsigned long pfn = page_to_pfn((struct page *)addr);
+
 	if (pte_none(ptep_get(pte))) {
 		pte_t entry;
-		void *p;
 
 		if (ptpfn == (unsigned long)-1) {
-			p = vmemmap_alloc_block_buf(PAGE_SIZE, node, altmap);
+			void *p = vmemmap_alloc_pte(pfn, node, altmap);
+
 			if (!p)
 				return NULL;
 			ptpfn = PHYS_PFN(__pa(p));
@@ -246,7 +269,8 @@ static pte_t * __meminit vmemmap_pte_pop
 		}
 		entry = pfn_pte(ptpfn, PAGE_KERNEL);
 		set_pte_at(&init_mm, addr, pte, entry);
-	}
+	} else if (WARN_ON_ONCE(vmemmap_optimizable_pfn(pfn)))
+		return NULL;
 	return pte;
 }
 
@@ -435,6 +459,9 @@ int __meminit vmemmap_populate_hugepages
 	pmd_t *pmd;
 
 	for (addr = start; addr < end; addr = next) {
+		unsigned long pfn = page_to_pfn((struct page *)addr);
+		const struct mem_section *ms = __pfn_to_section(pfn);
+
 		next = pmd_addr_end(addr, end);
 
 		pgd = vmemmap_pgd_populate(addr, node);
@@ -450,7 +477,7 @@ int __meminit vmemmap_populate_hugepages
 			return -ENOMEM;
 
 		pmd = pmd_offset(pud, addr);
-		if (pmd_none(pmdp_get(pmd))) {
+		if (pmd_none(pmdp_get(pmd)) && !section_vmemmap_optimizable(ms)) {
 			void *p;
 
 			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
@@ -468,8 +495,11 @@ int __meminit vmemmap_populate_hugepages
 				 */
 				return -ENOMEM;
 			}
-		} else if (vmemmap_check_pmd(pmd, node, addr, next))
+		} else if (vmemmap_check_pmd(pmd, node, addr, next)) {
+			if (WARN_ON_ONCE(section_vmemmap_optimizable(ms)))
+				return -EOPNOTSUPP;
 			continue;
+		}
 		if (vmemmap_populate_basepages(addr, next, node, altmap))
 			return -ENOMEM;
 	}
_

Patches currently in -mm which might be from songmuchun@bytedance.com are

mm-sparse-relax-struct-mem_section-size-constraints.patch
mm-sparse-vmemmap-rename-hvo-order-macros.patch
mm-mm_init-skip-initializing-shared-vmemmap-tail-pages.patch
mm-sparse-vmemmap-initialize-shared-tail-vmemmap-pages-on-allocation.patch
mm-sparse-vmemmap-support-section-based-vmemmap-accounting.patch
mm-mm_init-factor-out-pfn_to_zone.patch
mm-sparse-vmemmap-move-helpers-ahead-of-future-callers.patch
mm-sparse-vmemmap-support-section-based-vmemmap-optimization.patch
mm-sparse-initialize-memory-sections-earlier.patch
mm-hugetlb-switch-hugetlb-to-section-based-vmemmap-optimization.patch
mm-sparse-vmemmap-remove-sparsemem_vmemmap_preinit-support.patch
mm-sparse-inline-usemap-allocation-into-sparse_init_nid.patch
mm-sparse-remove-section_map_size.patch
mm-hugetlb-remove-huge_bootmem_hvo.patch
mm-hugetlb-remove-huge_bootmem_cma.patch
mm-hugetlb-localize-struct-huge_bootmem_page.patch
mm-hugetlb-localize-huge_bootmem_zones_valid.patch
mm-sparse-vmemmap-introduce-config_sparsemem_vmemmap_optimization.patch
mm-sparse-vmemmap-factor-out-shared-vmemmap-tail-page-allocation.patch
mm-sparse-vmemmap-open-code-init_compound_tail.patch
mm-sparse-vmemmap-prepare-dax-vmemmap-population-for-section-orders.patch
mm-sparse-vmemmap-set-section-order-for-device-dax.patch
mm-sparse-vmemmap-switch-device-dax-to-shared-tail-vmemmap-pages.patch
mm-sparse-vmemmap-move-hvo-helpers-to-a-public-header.patch
powerpc-mm-switch-device-dax-to-shared-tail-vmemmap-pages.patch
mm-sparse-vmemmap-drop-the-extra-tail-page-from-device-dax-reservation.patch
mm-sparse-vmemmap-drop-unused-section_nr_vmemmap_pages-arguments.patch
documentation-mm-update-dax-vmemmap-deduplication-docs.patch


^ permalink raw reply	[flat|nested] only message in thread

only message in thread, other threads:[~2026-09-10 23:05 UTC | newest]

Thread overview: (only message) (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-09-10 23:05 + mm-sparse-vmemmap-support-section-based-vmemmap-optimization.patch added to mm-unstable branch Andrew Morton

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.