mm/sparse-vmemmap.c

// SPDX-License-Identifier: GPL-2.0
/*
 * Virtual Memory Map support
 *
 * (C) 2007 sgi. Christoph Lameter.
 *
 * Virtual memory maps allow VM primitives pfn_to_page, page_to_pfn,
 * virt_to_page, page_address() to be implemented as a base offset
 * calculation without memory access.
 *
 * However, virtual mappings need a page table and TLBs. Many Linux
 * architectures already map their physical space using 1-1 mappings
 * via TLBs. For those arches the virtual memory map is essentially
 * for free if we use the same page size as the 1-1 mappings. In that
 * case the overhead consists of a few additional pages that are
 * allocated to create a view of memory for vmemmap.
 *
 * The architecture is expected to provide a vmemmap_populate() function
 * to instantiate the mapping.
 */
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/memblock.h>
#include <linux/memremap.h>
#include <linux/highmem.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/sched.h>
#include <linux/pgalloc.h>

#include <asm/dma.h>
#include <asm/tlbflush.h>

#include "internal.h"
#include "mm_init.h"
#include "sparse.h"

void __ref *vmemmap_alloc_block(unsigned long size, int node)
{
	/* If the main allocator is up use that, fallback to bootmem. */
	if (slab_is_available()) {
		gfp_t gfp_mask = GFP_KERNEL|__GFP_RETRY_MAYFAIL|__GFP_NOWARN;
		int order = get_order(size);
		static bool warned;
		struct page *page;

		page = alloc_pages_node(node, gfp_mask, order);
		if (page)
			return page_address(page);

		if (!warned) {
			warn_alloc(gfp_mask & ~__GFP_NOWARN, NULL,
				   "vmemmap alloc failure: order:%u", order);
			warned = true;
		}
		return NULL;
	} else
		return memmap_alloc(size, size, __pa(MAX_DMA_ADDRESS), node);
}

static void * __meminit altmap_alloc_block_buf(unsigned long size,
					       struct vmem_altmap *altmap);

/* need to make sure size is all the same during early stage */
void * __meminit vmemmap_alloc_block_buf(unsigned long size, int node,
					 struct vmem_altmap *altmap)
{
	if (altmap)
		return altmap_alloc_block_buf(size, altmap);

	return vmemmap_alloc_block(size, node);
}

static unsigned long __meminit vmem_altmap_next_pfn(struct vmem_altmap *altmap)
{
	return altmap->base_pfn + altmap->reserve + altmap->alloc
		+ altmap->align;
}

static unsigned long __meminit vmem_altmap_nr_free(struct vmem_altmap *altmap)
{
	unsigned long allocated = altmap->alloc + altmap->align;

	if (altmap->free > allocated)
		return altmap->free - allocated;
	return 0;
}

static void * __meminit altmap_alloc_block_buf(unsigned long size,
					       struct vmem_altmap *altmap)
{
	unsigned long pfn, nr_pfns, nr_align;

	if (size & ~PAGE_MASK) {
		pr_warn_once("%s: allocations must be multiple of PAGE_SIZE (%ld)\n",
				__func__, size);
		return NULL;
	}

	pfn = vmem_altmap_next_pfn(altmap);
	nr_pfns = size >> PAGE_SHIFT;
	nr_align = 1UL << find_first_bit(&nr_pfns, BITS_PER_LONG);
	nr_align = ALIGN(pfn, nr_align) - pfn;
	if (nr_pfns + nr_align > vmem_altmap_nr_free(altmap))
		return NULL;

	altmap->alloc += nr_pfns;
	altmap->align += nr_align;
	pfn += nr_align;

	pr_debug("%s: pfn: %#lx alloc: %ld align: %ld nr: %#lx\n",
			__func__, pfn, altmap->alloc, altmap->align, nr_pfns);
	return __va(__pfn_to_phys(pfn));
}

void __meminit vmemmap_verify(pte_t *pte, int node,
				unsigned long start, unsigned long end)
{
	unsigned long pfn = pte_pfn(ptep_get(pte));
	int actual_node = early_pfn_to_nid(pfn);

	if (node_distance(actual_node, node) > LOCAL_DISTANCE)
		pr_warn_once("[%lx-%lx] potential offnode page_structs\n",
			start, end - 1);
}

int __meminit section_nr_vmemmap_pages(unsigned long pfn, unsigned long nr_pages)
{
	const struct mem_section *ms = __pfn_to_section(pfn);
	const int order = section_compound_order(ms);
	const unsigned long pages_per_compound = 1UL << order;

	VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SUBSECTION));
	VM_WARN_ON_ONCE(nr_pages > PAGES_PER_SECTION);

	if (!section_vmemmap_optimizable(ms))
		return DIV_ROUND_UP(nr_pages * sizeof(struct page), PAGE_SIZE);

	if (order < PFN_SECTION_SHIFT) {
		VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, pages_per_compound));
		return VMEMMAP_OPTIMIZATION_PAGES * nr_pages / pages_per_compound;
	}

	VM_WARN_ON_ONCE(!IS_ALIGNED(pfn | nr_pages, PAGES_PER_SECTION));

	if (IS_ALIGNED(pfn, pages_per_compound))
		return VMEMMAP_OPTIMIZATION_PAGES;

	return 0;
}

static void * __meminit vmemmap_alloc_block_zero(unsigned long size, int node)
{
	void *p = vmemmap_alloc_block(size, node);

	if (!p)
		return NULL;
	memset(p, 0, size);

	return p;
}

#ifdef CONFIG_VMEMMAP_OPTIMIZATION
#define VMEMMAP_OPTIMIZATION_NR_ORDERS	(MAX_FOLIO_ORDER - VMEMMAP_OPTIMIZATION_MIN_ORDER + 1)

static __ref struct page **vmemmap_tails(struct zone *zone)
{
	const size_t size = array_size(VMEMMAP_OPTIMIZATION_NR_ORDERS,
				       sizeof(*zone->vmemmap_tails));
	struct page **pages = READ_ONCE(zone->vmemmap_tails);

	if (pages)
		return pages;

	pages = slab_is_available() ? kzalloc_objs(*pages, VMEMMAP_OPTIMIZATION_NR_ORDERS) :
		memblock_alloc(size, __alignof__(*pages));
	if (!pages)
		return NULL;

	if (cmpxchg(&zone->vmemmap_tails, NULL, pages) != NULL) {
		if (slab_is_available())
			kfree(pages);
		else
			memblock_free(pages, size);
		pages = READ_ONCE(zone->vmemmap_tails);
	}

	return pages;
}

struct page __ref *vmemmap_shared_tail_page(unsigned int order, struct zone *zone)
{
	const unsigned int idx = order - VMEMMAP_OPTIMIZATION_MIN_ORDER;
	struct page *page, **pages;
	void *addr;

	if (WARN_ON_ONCE(idx >= VMEMMAP_OPTIMIZATION_NR_ORDERS))
		return NULL;

	pages = vmemmap_tails(zone);
	if (!pages)
		return NULL;

	page = READ_ONCE(pages[idx]);
	if (page)
		return page;

	addr = vmemmap_alloc_block(PAGE_SIZE, zone_to_nid(zone));
	if (!addr)
		return NULL;

	for (int i = 0; i < PAGE_SIZE / sizeof(struct page); i++) {
		page = (struct page *)addr + i;
		mm_zero_struct_page(page);
		atomic_set(&page->_mapcount, -1);
		set_page_node(page, zone_to_nid(zone));
		set_page_zone(page, zone_idx(zone));
		if (zone_is_zone_device(zone))
			__SetPageReserved(page);
		prep_compound_tail(page, NULL, order);
	}

	page = virt_to_page(addr);
	if (cmpxchg(&pages[idx], NULL, page) != NULL) {
		if (slab_is_available())
			__free_page(page);
		else
			memblock_free(addr, PAGE_SIZE);
		page = READ_ONCE(pages[idx]);
	}

	return page;
}
#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);

	/*
	 * Before slab is available, vmemmap optimization is used for early
	 * system RAM, whose zone can be determined from the PFN.
	 *
	 * Once slab is available, only ZONE_DEVICE memory reaches this
	 * optimized population path. Its zone span has not been initialized
	 * while its vmemmap is being populated, so pfn_to_zone() cannot be
	 * used. Obtain ZONE_DEVICE directly from the node instead.
	 */
	zone = slab_is_available() ? device_zone(node) : pfn_to_zone(pfn, node);
	page = vmemmap_shared_tail_page(order, zone);
	if (!page)
		return NULL;

	/*
	 * During early vmemmap population, the shared tail vmemmap backing
	 * page is allocated from memblock before its struct page can safely
	 * participate in page refcounting. Therefore, no reference can be
	 * held for each shared PTE mapping, and the mappings must be unshared
	 * before the vmemmap is depopulated.
	 *
	 * Once slab is available, the shared backing page is allocated from
	 * the buddy allocator and can be refcounted. Hold one reference for
	 * each shared PTE mapping. The architecture vmemmap teardown drops
	 * the reference through __free_pages() when removing the mapping,
	 * preventing the backing page from being freed while it is shared.
	 *
	 * The backing page may be shared by enough PTE mappings to exhaust
	 * the positive range of its reference count. Stop populating the
	 * vmemmap if another reference cannot be acquired.
	 */
	if (slab_is_available() && !try_get_page(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)
{
	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 = vmemmap_alloc_pte(pfn, node, altmap);

		if (!p)
			return NULL;

		entry = pfn_pte(PHYS_PFN(__pa(p)), PAGE_KERNEL);
		set_pte_at(&init_mm, addr, pte, entry);
	} else if (WARN_ON_ONCE(vmemmap_optimizable_pfn(pfn)))
		return NULL;
	return pte;
}

static pmd_t * __meminit vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node)
{
	pmd_t *pmd = pmd_offset(pud, addr);
	if (pmd_none(*pmd)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		kernel_pte_init(p);
		pmd_populate_kernel(&init_mm, pmd, p);
	}
	return pmd;
}

static pud_t * __meminit vmemmap_pud_populate(p4d_t *p4d, unsigned long addr, int node)
{
	pud_t *pud = pud_offset(p4d, addr);
	if (pud_none(*pud)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		pmd_init(p);
		pud_populate(&init_mm, pud, p);
	}
	return pud;
}

static p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node)
{
	p4d_t *p4d = p4d_offset(pgd, addr);
	if (p4d_none(*p4d)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		pud_init(p);
		p4d_populate_kernel(addr, p4d, p);
	}
	return p4d;
}

static pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node)
{
	pgd_t *pgd = pgd_offset_k(addr);
	if (pgd_none(*pgd)) {
		void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node);
		if (!p)
			return NULL;
		pgd_populate_kernel(addr, pgd, p);
	}
	return pgd;
}

int __meminit vmemmap_populate_basepages(unsigned long start, unsigned long end,
					 int node, struct vmem_altmap *altmap)
{
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	pmd_t *pmd;
	pte_t *pte;

	for (unsigned long addr = start; addr < end; addr += PAGE_SIZE) {
		pgd = vmemmap_pgd_populate(addr, node);
		if (!pgd)
			return -ENOMEM;
		p4d = vmemmap_p4d_populate(pgd, addr, node);
		if (!p4d)
			return -ENOMEM;
		pud = vmemmap_pud_populate(p4d, addr, node);
		if (!pud)
			return -ENOMEM;
		pmd = vmemmap_pmd_populate(pud, addr, node);
		if (!pmd)
			return -ENOMEM;
		pte = vmemmap_pte_populate(pmd, addr, node, altmap);
		if (!pte)
			return -ENOMEM;
		vmemmap_verify(pte, node, addr, addr + PAGE_SIZE);
	}

	return 0;
}

/*
 * Write protect the mirrored tail page structs for HVO. This will be
 * called from the hugetlb code when gathering and initializing the
 * memblock allocated gigantic pages. The write protect can't be
 * done earlier, since it can't be guaranteed that the reserved
 * page structures will not be written to during initialization,
 * even if CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled.
 *
 * The PTEs are known to exist, and nothing else should be touching
 * these pages. The caller is responsible for any TLB flushing.
 */
void vmemmap_wrprotect_hvo(unsigned long addr, unsigned long end,
				    int node, unsigned long headsize)
{
	unsigned long maddr;
	pte_t *pte;

	for (maddr = addr + headsize; maddr < end; maddr += PAGE_SIZE) {
		pte = virt_to_kpte(maddr);
		ptep_set_wrprotect(&init_mm, maddr, pte);
	}
}

void __weak __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
				      unsigned long addr, unsigned long next)
{
	WARN_ON_ONCE(!pmd_set_huge(pmd, virt_to_phys(p), PAGE_KERNEL));
}

int __weak __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
				       unsigned long addr, unsigned long next)
{
	if (!pmd_leaf(pmdp_get(pmd)))
		return 0;
	vmemmap_verify((pte_t *)pmd, node, addr, next);

	return 1;
}

int __meminit vmemmap_populate_hugepages(unsigned long start, unsigned long end,
					 int node, struct vmem_altmap *altmap)
{
	unsigned long addr;
	unsigned long next;
	pgd_t *pgd;
	p4d_t *p4d;
	pud_t *pud;
	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);
		if (!pgd)
			return -ENOMEM;

		p4d = vmemmap_p4d_populate(pgd, addr, node);
		if (!p4d)
			return -ENOMEM;

		pud = vmemmap_pud_populate(p4d, addr, node);
		if (!pud)
			return -ENOMEM;

		pmd = pmd_offset(pud, addr);
		if (pmd_none(pmdp_get(pmd)) && !section_vmemmap_optimizable(ms)) {
			void *p;

			p = vmemmap_alloc_block_buf(PMD_SIZE, node, altmap);
			if (p) {
				vmemmap_set_pmd(pmd, p, node, addr, next);
				continue;
			} else if (altmap) {
				/*
				 * No fallback: In any case we care about, the
				 * altmap should be reasonably sized and aligned
				 * such that vmemmap_alloc_block_buf() will always
				 * succeed. For consistency with the PTE case,
				 * return an error here as failure could indicate
				 * a configuration issue with the size of the altmap.
				 */
				return -ENOMEM;
			}
		} 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;
	}
	return 0;
}

struct page * __meminit __populate_section_memmap(unsigned long pfn,
		unsigned long nr_pages, int nid, 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);
	int r;

	if (WARN_ON_ONCE(!IS_ALIGNED(pfn, PAGES_PER_SUBSECTION) ||
		!IS_ALIGNED(nr_pages, PAGES_PER_SUBSECTION)))
		return NULL;

	r = vmemmap_populate(start, end, nid, altmap);
	if (r < 0)
		return NULL;

	flush_cache_vmap(start, end);

	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);
}

static void __init sparse_init_subsection_map_range(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;
	}
}

void __init sparse_init_subsection_map(void)
{
	int i, nid;
	unsigned long start, end;

	for_each_mem_pfn_range(i, MAX_NUMNODES, &start, &end, &nid)
		sparse_init_subsection_map_range(start, end - start);
}

#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(section_nr_vmemmap_pages(pfn, nr_pages));

	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(-section_nr_vmemmap_pages(pfn, nr_pages));
	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);
	unsigned long pfn = page_to_pfn(memmap);

	memmap_boot_pages_add(-section_nr_vmemmap_pages(pfn, PAGES_PER_SECTION));
	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;
		section_set_compound_order(ms, 0);
	}
}

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;
	unsigned int order;
	int rc;

	order = vmemmap_can_optimize(altmap, pgmap) ? pgmap->vmemmap_shift : 0;
	if (nr_pages < PAGES_PER_SECTION && section_compound_order(ms))
		return ERR_PTR(-EOPNOTSUPP);

	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);

	section_set_compound_order_range(pfn, nr_pages, order);
	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);

	ms = __nr_to_section(section_nr);
	/*
	 * Poison uninitialized struct pages to catch invalid flag combinations.
	 *
	 * Tail struct pages in a vmemmap-optimized section are initialized and
	 * shared during vmemmap population, so they must not be overwritten here.
	 */
	if (!section_vmemmap_optimizable(ms))
		page_init_poison(memmap, sizeof(struct page) * nr_pages);

	__highest_used_section_nr = max(section_nr, __highest_used_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);

	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 */