[PATCH 6.12.y 1/2] mm: prepare to move subsection_map_init() to mm/sparse-vmemmap.c

[Sasha Levin <sashal@kernel.org>]

From: "David Hildenbrand (Arm)" <david@kernel.org>

[ Upstream commit fead6dcff83b02f8d6dc3c1ebbe4e09c05c54ee5 ]

We want to move subsection_map_init() to mm/sparse-vmemmap.c.

To prepare for getting rid of subsection_map_init() in mm/sparse.c
completely, use a static inline function for !CONFIG_SPARSEMEM_VMEMMAP.

While at it, move the declaration to internal.h and rename it to
"sparse_init_subsection_map()".

Link: https://lkml.kernel.org/r/20260320-sparsemem_cleanups-v2-11-096addc8800d@kernel.org
Signed-off-by: David Hildenbrand (Arm) <david@kernel.org>
Reviewed-by: Lorenzo Stoakes (Oracle) <ljs@kernel.org>
Reviewed-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Axel Rasmussen <axelrasmussen@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@kernel.org>
Cc: Wei Xu <weixugc@google.com>
Cc: Yuanchu Xie <yuanchu@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Stable-dep-of: 721a73e30c9e ("mm/sparse-vmemmap: fix DAX vmemmap accounting with optimization")
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/arm64/mm/mmu.c            |   5 +-
 arch/loongarch/mm/init.c       |   5 +-
 arch/powerpc/mm/mem.c          |   5 +-
 arch/riscv/mm/init.c           |   5 +-
 arch/s390/mm/init.c            |   5 +-
 arch/x86/mm/init_64.c          |   5 +-
 include/linux/memory_hotplug.h |   8 +-
 include/linux/mmzone.h         |   7 +-
 mm/internal.h                  |  47 +++++
 mm/memory_hotplug.c            |  13 +-
 mm/memremap.c                  |   4 +-
 mm/mm_init.c                   |   2 +-
 mm/sparse-vmemmap.c            | 310 +++++++++++++++++++++++++++++++++
 mm/sparse.c                    |  80 +--------
 14 files changed, 399 insertions(+), 102 deletions(-)

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 2b5e0ccc0af555..c29d16284fe819 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1384,12 +1384,13 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return ret;
 }
 
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			struct dev_pagemap *pgmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, pgmap);
 	__remove_pgd_mapping(swapper_pg_dir, __phys_to_virt(start), size);
 }
 
diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
index c595041afed4d8..a6c5fd2df2f6de 100644
--- a/arch/loongarch/mm/init.c
+++ b/arch/loongarch/mm/init.c
@@ -103,12 +103,13 @@ int arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *params)
 	return ret;
 }
 
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			struct dev_pagemap *pgmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, pgmap);
 }
 
 #ifdef CONFIG_NUMA
diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 1221c561b43a0b..7ddecbd9675198 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -157,12 +157,13 @@ int __ref arch_add_memory(int nid, u64 start, u64 size,
 	return rc;
 }
 
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			      struct dev_pagemap *pgmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, pgmap);
 	arch_remove_linear_mapping(start, size);
 }
 #endif
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 8cd8bc9b82cb29..4594f77a06ee3d 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1839,9 +1839,10 @@ int __ref arch_add_memory(int nid, u64 start, u64 size, struct mhp_params *param
 	return ret;
 }
 
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			      struct dev_pagemap *pgmap)
 {
-	__remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap);
+	__remove_pages(start >> PAGE_SHIFT, size >> PAGE_SHIFT, altmap, pgmap);
 	remove_linear_mapping(start, size);
 	flush_tlb_all();
 }
diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index 7a96623a9d2e43..58f535fd9a334d 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -290,12 +290,13 @@ int arch_add_memory(int nid, u64 start, u64 size,
 	return rc;
 }
 
-void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			struct dev_pagemap *pgmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, pgmap);
 	vmem_remove_mapping(start, size);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 63de8dbaa75ee8..8971bf1f4d8326 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1293,12 +1293,13 @@ kernel_physical_mapping_remove(unsigned long start, unsigned long end)
 	remove_pagetable(start, end, true, NULL);
 }
 
-void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap)
+void __ref arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			      struct dev_pagemap *pgmap)
 {
 	unsigned long start_pfn = start >> PAGE_SHIFT;
 	unsigned long nr_pages = size >> PAGE_SHIFT;
 
-	__remove_pages(start_pfn, nr_pages, altmap);
+	__remove_pages(start_pfn, nr_pages, altmap, pgmap);
 	kernel_physical_mapping_remove(start, start + size);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index b27ddce5d32499..99d6ba41ed290b 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -153,9 +153,10 @@ static inline bool movable_node_is_enabled(void)
 	return movable_node_enabled;
 }
 
-extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap);
+extern void arch_remove_memory(u64 start, u64 size, struct vmem_altmap *altmap,
+			       struct dev_pagemap *pgmap);
 extern void __remove_pages(unsigned long start_pfn, unsigned long nr_pages,
-			   struct vmem_altmap *altmap);
+			   struct vmem_altmap *altmap, struct dev_pagemap *pgmap);
 
 /* reasonably generic interface to expand the physical pages */
 extern int __add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
@@ -321,7 +322,8 @@ extern int sparse_add_section(int nid, unsigned long pfn,
 		unsigned long nr_pages, struct vmem_altmap *altmap,
 		struct dev_pagemap *pgmap);
 extern void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
-				  struct vmem_altmap *altmap);
+				  struct vmem_altmap *altmap,
+				  struct dev_pagemap *pgmap);
 extern struct page *sparse_decode_mem_map(unsigned long coded_mem_map,
 					  unsigned long pnum);
 extern struct zone *zone_for_pfn_range(int online_type, int nid,
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 80bc5640bb60d2..8f932c4350fcb5 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -1815,15 +1815,13 @@ struct mem_section_usage {
 	unsigned long pageblock_flags[0];
 };
 
-void subsection_map_init(unsigned long pfn, unsigned long nr_pages);
-
 struct page;
 struct page_ext;
 struct mem_section {
 	/*
 	 * This is, logically, a pointer to an array of struct
 	 * pages.  However, it is stored with some other magic.
-	 * (see sparse.c::sparse_init_one_section())
+	 * (see sparse_init_one_section())
 	 *
 	 * Additionally during early boot we encode node id of
 	 * the location of the section here to guide allocation.
@@ -2092,8 +2090,9 @@ void sparse_init(void);
 #else
 #define sparse_init()	do {} while (0)
 #define sparse_index_init(_sec, _nid)  do {} while (0)
+#define sparse_vmemmap_init_nid_early(_nid) do {} while (0)
+#define sparse_vmemmap_init_nid_late(_nid) do {} while (0)
 #define pfn_in_present_section pfn_valid
-#define subsection_map_init(_pfn, _nr_pages) do {} while (0)
 #endif /* CONFIG_SPARSEMEM */
 
 #endif /* !__GENERATING_BOUNDS.H */
diff --git a/mm/internal.h b/mm/internal.h
index 3bfc1dc2d7eaf5..151edc2f9ab230 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -749,6 +749,53 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
 void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
 		unsigned long, enum meminit_context, struct vmem_altmap *, int);
 
+#ifdef CONFIG_SPARSEMEM
+int sparse_index_init(unsigned long section_nr, int nid);
+
+static inline void sparse_init_one_section(struct mem_section *ms,
+		unsigned long pnum, struct page *mem_map,
+		struct mem_section_usage *usage, unsigned long flags)
+{
+	unsigned long coded_mem_map;
+
+	BUILD_BUG_ON(SECTION_MAP_LAST_BIT > PFN_SECTION_SHIFT);
+
+	/*
+	 * We encode the start PFN of the section into the mem_map such that
+	 * page_to_pfn() on !CONFIG_SPARSEMEM_VMEMMAP can simply subtract it
+	 * from the page pointer to obtain the PFN.
+	 */
+	coded_mem_map = (unsigned long)(mem_map - section_nr_to_pfn(pnum));
+	VM_WARN_ON_ONCE(coded_mem_map & ~SECTION_MAP_MASK);
+
+	ms->section_mem_map &= ~SECTION_MAP_MASK;
+	ms->section_mem_map |= coded_mem_map;
+	ms->section_mem_map |= flags | SECTION_HAS_MEM_MAP;
+	ms->usage = usage;
+}
+
+static inline void __section_mark_present(struct mem_section *ms,
+		unsigned long section_nr)
+{
+	if (section_nr > __highest_present_section_nr)
+		__highest_present_section_nr = section_nr;
+
+	ms->section_mem_map |= SECTION_MARKED_PRESENT;
+}
+#endif /* CONFIG_SPARSEMEM */
+
+/*
+ * mm/sparse-vmemmap.c
+ */
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+void sparse_init_subsection_map(unsigned long pfn, unsigned long nr_pages);
+#else
+static inline void sparse_init_subsection_map(unsigned long pfn,
+		unsigned long nr_pages)
+{
+}
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
+
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
 /*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3e2140891a9d36..9479cb19cecf25 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -564,6 +564,7 @@ void remove_pfn_range_from_zone(struct zone *zone,
  * @pfn: starting pageframe (must be aligned to start of a section)
  * @nr_pages: number of pages to remove (must be multiple of section size)
  * @altmap: alternative device page map or %NULL if default memmap is used
+ * @pgmap: device page map or %NULL if not ZONE_DEVICE
  *
  * Generic helper function to remove section mappings and sysfs entries
  * for the section of the memory we are removing. Caller needs to make
@@ -571,7 +572,7 @@ void remove_pfn_range_from_zone(struct zone *zone,
  * calling offline_pages().
  */
 void __remove_pages(unsigned long pfn, unsigned long nr_pages,
-		    struct vmem_altmap *altmap)
+		    struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
 {
 	const unsigned long end_pfn = pfn + nr_pages;
 	unsigned long cur_nr_pages;
@@ -586,7 +587,7 @@ void __remove_pages(unsigned long pfn, unsigned long nr_pages,
 		/* Select all remaining pages up to the next section boundary */
 		cur_nr_pages = min(end_pfn - pfn,
 				   SECTION_ALIGN_UP(pfn + 1) - pfn);
-		sparse_remove_section(pfn, cur_nr_pages, altmap);
+		sparse_remove_section(pfn, cur_nr_pages, altmap, pgmap);
 	}
 }
 
@@ -1411,7 +1412,7 @@ static void remove_memory_blocks_and_altmaps(u64 start, u64 size)
 
 		remove_memory_block_devices(cur_start, memblock_size);
 
-		arch_remove_memory(cur_start, memblock_size, altmap);
+		arch_remove_memory(cur_start, memblock_size, altmap, NULL);
 
 		/* Verify that all vmemmap pages have actually been freed. */
 		WARN(altmap->alloc, "Altmap not fully unmapped");
@@ -1456,7 +1457,7 @@ static int create_altmaps_and_memory_blocks(int nid, struct memory_group *group,
 		ret = create_memory_block_devices(cur_start, memblock_size,
 						  params.altmap, group);
 		if (ret) {
-			arch_remove_memory(cur_start, memblock_size, params.altmap);
+			arch_remove_memory(cur_start, memblock_size, params.altmap, NULL);
 			kfree(params.altmap);
 			goto out;
 		}
@@ -1534,7 +1535,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		/* create memory block devices after memory was added */
 		ret = create_memory_block_devices(start, size, NULL, group);
 		if (ret) {
-			arch_remove_memory(start, size, params.altmap);
+			arch_remove_memory(start, size, params.altmap, NULL);
 			goto error;
 		}
 	}
@@ -2273,7 +2274,7 @@ static int try_remove_memory(u64 start, u64 size)
 		 * No altmaps present, do the removal directly
 		 */
 		remove_memory_block_devices(start, size);
-		arch_remove_memory(start, size, NULL);
+		arch_remove_memory(start, size, NULL, NULL);
 	} else {
 		/* all memblocks in the range have altmaps */
 		remove_memory_blocks_and_altmaps(start, size);
diff --git a/mm/memremap.c b/mm/memremap.c
index 40d4547ce5144e..66544defad3eda 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -122,10 +122,10 @@ static void pageunmap_range(struct dev_pagemap *pgmap, int range_id)
 				   PHYS_PFN(range_len(range)));
 	if (pgmap->type == MEMORY_DEVICE_PRIVATE) {
 		__remove_pages(PHYS_PFN(range->start),
-			       PHYS_PFN(range_len(range)), NULL);
+			       PHYS_PFN(range_len(range)), NULL, pgmap);
 	} else {
 		arch_remove_memory(range->start, range_len(range),
-				pgmap_altmap(pgmap));
+				pgmap_altmap(pgmap), pgmap);
 		kasan_remove_zero_shadow(__va(range->start), range_len(range));
 	}
 	mem_hotplug_done();
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 1450b2bb98ee32..b522a642fec8ff 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1831,7 +1831,7 @@ void __init free_area_init(unsigned long *max_zone_pfn)
 		pr_info("  node %3d: [mem %#018Lx-%#018Lx]\n", nid,
 			(u64)start_pfn << PAGE_SHIFT,
 			((u64)end_pfn << PAGE_SHIFT) - 1);
-		subsection_map_init(start_pfn, end_pfn - start_pfn);
+		sparse_init_subsection_map(start_pfn, end_pfn - start_pfn);
 	}
 
 	/* Initialise every node */
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 3e88708886e371..c9da0ea63f234a 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -31,6 +31,8 @@
 
 #include <asm/dma.h>
 
+#include "internal.h"
+
 /*
  * Allocate a block of memory to be used to back the virtual memory map
  * or to back the page tables that are used to create the mapping.
@@ -476,3 +478,311 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
 
 	return pfn_to_page(pfn);
 }
+
+static void subsection_mask_set(unsigned long *map, unsigned long pfn,
+		unsigned long nr_pages)
+{
+	int idx = subsection_map_index(pfn);
+	int end = subsection_map_index(pfn + nr_pages - 1);
+
+	bitmap_set(map, idx, end - idx + 1);
+}
+
+void __init sparse_init_subsection_map(unsigned long pfn, unsigned long nr_pages)
+{
+	int end_sec_nr = pfn_to_section_nr(pfn + nr_pages - 1);
+	unsigned long nr, start_sec_nr = pfn_to_section_nr(pfn);
+
+	for (nr = start_sec_nr; nr <= end_sec_nr; nr++) {
+		struct mem_section *ms;
+		unsigned long pfns;
+
+		pfns = min(nr_pages, PAGES_PER_SECTION
+				- (pfn & ~PAGE_SECTION_MASK));
+		ms = __nr_to_section(nr);
+		subsection_mask_set(ms->usage->subsection_map, pfn, pfns);
+
+		pr_debug("%s: sec: %lu pfns: %lu set(%d, %d)\n", __func__, nr,
+				pfns, subsection_map_index(pfn),
+				subsection_map_index(pfn + pfns - 1));
+
+		pfn += pfns;
+		nr_pages -= pfns;
+	}
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+
+/* Mark all memory sections within the pfn range as online */
+void online_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(pfn);
+		struct mem_section *ms = __nr_to_section(section_nr);
+
+		ms->section_mem_map |= SECTION_IS_ONLINE;
+	}
+}
+
+/* Mark all memory sections within the pfn range as offline */
+void offline_mem_sections(unsigned long start_pfn, unsigned long end_pfn)
+{
+	unsigned long pfn;
+
+	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		unsigned long section_nr = pfn_to_section_nr(pfn);
+		struct mem_section *ms = __nr_to_section(section_nr);
+
+		ms->section_mem_map &= ~SECTION_IS_ONLINE;
+	}
+}
+
+static struct page * __meminit populate_section_memmap(unsigned long pfn,
+		unsigned long nr_pages, int nid, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
+{
+	struct page *page = __populate_section_memmap(pfn, nr_pages, nid, altmap,
+						      pgmap);
+
+	memmap_pages_add(DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE));
+
+	return page;
+}
+
+static void depopulate_section_memmap(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+	unsigned long start = (unsigned long) pfn_to_page(pfn);
+	unsigned long end = start + nr_pages * sizeof(struct page);
+
+	memmap_pages_add(-1L * (DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE)));
+	vmemmap_free(start, end, altmap);
+}
+
+static void free_map_bootmem(struct page *memmap)
+{
+	unsigned long start = (unsigned long)memmap;
+	unsigned long end = (unsigned long)(memmap + PAGES_PER_SECTION);
+
+	memmap_boot_pages_add(-1L * (DIV_ROUND_UP(PAGES_PER_SECTION * sizeof(struct page),
+						  PAGE_SIZE)));
+	vmemmap_free(start, end, NULL);
+}
+
+static int clear_subsection_map(unsigned long pfn, unsigned long nr_pages)
+{
+	DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+	DECLARE_BITMAP(tmp, SUBSECTIONS_PER_SECTION) = { 0 };
+	struct mem_section *ms = __pfn_to_section(pfn);
+	unsigned long *subsection_map = ms->usage
+		? &ms->usage->subsection_map[0] : NULL;
+
+	subsection_mask_set(map, pfn, nr_pages);
+	if (subsection_map)
+		bitmap_and(tmp, map, subsection_map, SUBSECTIONS_PER_SECTION);
+
+	if (WARN(!subsection_map || !bitmap_equal(tmp, map, SUBSECTIONS_PER_SECTION),
+				"section already deactivated (%#lx + %ld)\n",
+				pfn, nr_pages))
+		return -EINVAL;
+
+	bitmap_xor(subsection_map, map, subsection_map, SUBSECTIONS_PER_SECTION);
+	return 0;
+}
+
+static bool is_subsection_map_empty(struct mem_section *ms)
+{
+	return bitmap_empty(&ms->usage->subsection_map[0],
+			    SUBSECTIONS_PER_SECTION);
+}
+
+static int fill_subsection_map(unsigned long pfn, unsigned long nr_pages)
+{
+	struct mem_section *ms = __pfn_to_section(pfn);
+	DECLARE_BITMAP(map, SUBSECTIONS_PER_SECTION) = { 0 };
+	unsigned long *subsection_map;
+	int rc = 0;
+
+	subsection_mask_set(map, pfn, nr_pages);
+
+	subsection_map = &ms->usage->subsection_map[0];
+
+	if (bitmap_empty(map, SUBSECTIONS_PER_SECTION))
+		rc = -EINVAL;
+	else if (bitmap_intersects(map, subsection_map, SUBSECTIONS_PER_SECTION))
+		rc = -EEXIST;
+	else
+		bitmap_or(subsection_map, map, subsection_map,
+				SUBSECTIONS_PER_SECTION);
+
+	return rc;
+}
+
+/*
+ * To deactivate a memory region, there are 3 cases to handle:
+ *
+ * 1. deactivation of a partial hot-added section:
+ *      a) section was present at memory init.
+ *      b) section was hot-added post memory init.
+ * 2. deactivation of a complete hot-added section.
+ * 3. deactivation of a complete section from memory init.
+ *
+ * For 1, when subsection_map does not empty we will not be freeing the
+ * usage map, but still need to free the vmemmap range.
+ */
+static void section_deactivate(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+	struct mem_section *ms = __pfn_to_section(pfn);
+	bool section_is_early = early_section(ms);
+	struct page *memmap = NULL;
+	bool empty;
+
+	if (clear_subsection_map(pfn, nr_pages))
+		return;
+
+	empty = is_subsection_map_empty(ms);
+	if (empty) {
+		/*
+		 * Mark the section invalid so that valid_section()
+		 * return false. This prevents code from dereferencing
+		 * ms->usage array.
+		 */
+		ms->section_mem_map &= ~SECTION_HAS_MEM_MAP;
+
+		/*
+		 * When removing an early section, the usage map is kept (as the
+		 * usage maps of other sections fall into the same page). It
+		 * will be re-used when re-adding the section - which is then no
+		 * longer an early section. If the usage map is PageReserved, it
+		 * was allocated during boot.
+		 */
+		if (!PageReserved(virt_to_page(ms->usage))) {
+			kfree_rcu(ms->usage, rcu);
+			WRITE_ONCE(ms->usage, NULL);
+		}
+		memmap = pfn_to_page(SECTION_ALIGN_DOWN(pfn));
+	}
+
+	/*
+	 * The memmap of early sections is always fully populated. See
+	 * section_activate() and pfn_valid() .
+	 */
+	if (!section_is_early)
+		depopulate_section_memmap(pfn, nr_pages, altmap, pgmap);
+	else if (memmap)
+		free_map_bootmem(memmap);
+
+	if (empty)
+		ms->section_mem_map = (unsigned long)NULL;
+}
+
+static struct page * __meminit section_activate(int nid, unsigned long pfn,
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
+{
+	struct mem_section *ms = __pfn_to_section(pfn);
+	struct mem_section_usage *usage = NULL;
+	struct page *memmap;
+	int rc;
+
+	if (!ms->usage) {
+		usage = kzalloc(mem_section_usage_size(), GFP_KERNEL);
+		if (!usage)
+			return ERR_PTR(-ENOMEM);
+		ms->usage = usage;
+	}
+
+	rc = fill_subsection_map(pfn, nr_pages);
+	if (rc) {
+		if (usage)
+			ms->usage = NULL;
+		kfree(usage);
+		return ERR_PTR(rc);
+	}
+
+	/*
+	 * The early init code does not consider partially populated
+	 * initial sections, it simply assumes that memory will never be
+	 * referenced.  If we hot-add memory into such a section then we
+	 * do not need to populate the memmap and can simply reuse what
+	 * is already there.
+	 */
+	if (nr_pages < PAGES_PER_SECTION && early_section(ms))
+		return pfn_to_page(pfn);
+
+	memmap = populate_section_memmap(pfn, nr_pages, nid, altmap, pgmap);
+	if (!memmap) {
+		section_deactivate(pfn, nr_pages, altmap, pgmap);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return memmap;
+}
+
+/**
+ * sparse_add_section - add a memory section, or populate an existing one
+ * @nid: The node to add section on
+ * @start_pfn: start pfn of the memory range
+ * @nr_pages: number of pfns to add in the section
+ * @altmap: alternate pfns to allocate the memmap backing store
+ * @pgmap: alternate compound page geometry for devmap mappings
+ *
+ * This is only intended for hotplug.
+ *
+ * Note that only VMEMMAP supports sub-section aligned hotplug,
+ * the proper alignment and size are gated by check_pfn_span().
+ *
+ *
+ * Return:
+ * * 0		- On success.
+ * * -EEXIST	- Section has been present.
+ * * -ENOMEM	- Out of memory.
+ */
+int __meminit sparse_add_section(int nid, unsigned long start_pfn,
+		unsigned long nr_pages, struct vmem_altmap *altmap,
+		struct dev_pagemap *pgmap)
+{
+	unsigned long section_nr = pfn_to_section_nr(start_pfn);
+	struct mem_section *ms;
+	struct page *memmap;
+	int ret;
+
+	ret = sparse_index_init(section_nr, nid);
+	if (ret < 0)
+		return ret;
+
+	memmap = section_activate(nid, start_pfn, nr_pages, altmap, pgmap);
+	if (IS_ERR(memmap))
+		return PTR_ERR(memmap);
+
+	/*
+	 * Poison uninitialized struct pages in order to catch invalid flags
+	 * combinations.
+	 */
+	page_init_poison(memmap, sizeof(struct page) * nr_pages);
+
+	ms = __nr_to_section(section_nr);
+	__section_mark_present(ms, section_nr);
+
+	/* Align memmap to section boundary in the subsection case */
+	if (section_nr_to_pfn(section_nr) != start_pfn)
+		memmap = pfn_to_page(section_nr_to_pfn(section_nr));
+	sparse_init_one_section(ms, section_nr, memmap, ms->usage, 0);
+
+	return 0;
+}
+
+void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
+		struct vmem_altmap *altmap, struct dev_pagemap *pgmap)
+{
+	struct mem_section *ms = __pfn_to_section(pfn);
+
+	if (WARN_ON_ONCE(!valid_section(ms)))
+		return;
+
+	section_deactivate(pfn, nr_pages, altmap, pgmap);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
diff --git a/mm/sparse.c b/mm/sparse.c
index eb6c5cb27ed1ec..5b0c47e3aa85d7 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -79,7 +79,7 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid)
 	return section;
 }
 
-static int __meminit sparse_index_init(unsigned long section_nr, int nid)
+int __meminit sparse_index_init(unsigned long section_nr, int nid)
 {
 	unsigned long root = SECTION_NR_TO_ROOT(section_nr);
 	struct mem_section *section;
@@ -103,7 +103,7 @@ static int __meminit sparse_index_init(unsigned long section_nr, int nid)
 	return 0;
 }
 #else /* !SPARSEMEM_EXTREME */
-static inline int sparse_index_init(unsigned long section_nr, int nid)
+int sparse_index_init(unsigned long section_nr, int nid)
 {
 	return 0;
 }
@@ -161,14 +161,6 @@ static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
  * those loops early.
  */
 unsigned long __highest_present_section_nr;
-static void __section_mark_present(struct mem_section *ms,
-		unsigned long section_nr)
-{
-	if (section_nr > __highest_present_section_nr)
-		__highest_present_section_nr = section_nr;
-
-	ms->section_mem_map |= SECTION_MARKED_PRESENT;
-}
 
 #define for_each_present_section_nr(start, section_nr)		\
 	for (section_nr = next_present_section_nr(start-1);	\
@@ -180,44 +172,6 @@ static inline unsigned long first_present_section_nr(void)
 	return next_present_section_nr(-1);
 }
 
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
-static void subsection_mask_set(unsigned long *map, unsigned long pfn,
-		unsigned long nr_pages)
-{
-	int idx = subsection_map_index(pfn);
-	int end = subsection_map_index(pfn + nr_pages - 1);
-
-	bitmap_set(map, idx, end - idx + 1);
-}
-
-void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
-{
-	int end_sec_nr = pfn_to_section_nr(pfn + nr_pages - 1);
-	unsigned long nr, start_sec_nr = pfn_to_section_nr(pfn);
-
-	for (nr = start_sec_nr; nr <= end_sec_nr; nr++) {
-		struct mem_section *ms;
-		unsigned long pfns;
-
-		pfns = min(nr_pages, PAGES_PER_SECTION
-				- (pfn & ~PAGE_SECTION_MASK));
-		ms = __nr_to_section(nr);
-		subsection_mask_set(ms->usage->subsection_map, pfn, pfns);
-
-		pr_debug("%s: sec: %lu pfns: %lu set(%d, %d)\n", __func__, nr,
-				pfns, subsection_map_index(pfn),
-				subsection_map_index(pfn + pfns - 1));
-
-		pfn += pfns;
-		nr_pages -= pfns;
-	}
-}
-#else
-void __init subsection_map_init(unsigned long pfn, unsigned long nr_pages)
-{
-}
-#endif
-
 /* Record a memory area against a node. */
 static void __init memory_present(int nid, unsigned long start, unsigned long end)
 {
@@ -268,20 +222,6 @@ static void __init memblocks_present(void)
 		memory_present(nid, start, end);
 }
 
-/*
- * Subtle, we encode the real pfn into the mem_map such that
- * the identity pfn - section_mem_map will return the actual
- * physical page frame number.
- */
-static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
-{
-	unsigned long coded_mem_map =
-		(unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
-	BUILD_BUG_ON(SECTION_MAP_LAST_BIT > PFN_SECTION_SHIFT);
-	BUG_ON(coded_mem_map & ~SECTION_MAP_MASK);
-	return coded_mem_map;
-}
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * Decode mem_map from the coded memmap
@@ -294,16 +234,6 @@ struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pn
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-static void __meminit sparse_init_one_section(struct mem_section *ms,
-		unsigned long pnum, struct page *mem_map,
-		struct mem_section_usage *usage, unsigned long flags)
-{
-	ms->section_mem_map &= ~SECTION_MAP_MASK;
-	ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum)
-		| SECTION_HAS_MEM_MAP | flags;
-	ms->usage = usage;
-}
-
 static unsigned long usemap_size(void)
 {
 	return BITS_TO_LONGS(SECTION_BLOCKFLAGS_BITS) * sizeof(unsigned long);
@@ -587,6 +517,7 @@ void __init sparse_init(void)
 	vmemmap_populate_print_last();
 }
 
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
 #ifdef CONFIG_MEMORY_HOTPLUG
 
 /* Mark all memory sections within the pfn range as online */
@@ -918,7 +849,6 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 		page_init_poison(memmap, sizeof(struct page) * nr_pages);
 
 	ms = __nr_to_section(section_nr);
-	set_section_nid(section_nr, nid);
 	__section_mark_present(ms, section_nr);
 
 	/* Align memmap to section boundary in the subsection case */
@@ -930,7 +860,8 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 }
 
 void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
-			   struct vmem_altmap *altmap)
+			   struct vmem_altmap *altmap,
+			   struct dev_pagemap *pgmap)
 {
 	struct mem_section *ms = __pfn_to_section(pfn);
 
@@ -940,3 +871,4 @@ void sparse_remove_section(unsigned long pfn, unsigned long nr_pages,
 	section_deactivate(pfn, nr_pages, altmap);
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
-- 
2.53.0