path: root/mm/sparse.c

// SPDX-License-Identifier: GPL-2.0
/*
 * sparse memory mappings.
 */
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/mmzone.h>
#include <linux/memblock.h>
#include <linux/compiler.h>
#include <linux/highmem.h>
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <linux/swap.h>
#include <linux/swapops.h>

#include "internal.h"
#include <asm/dma.h>

/*
 * Permanent SPARSEMEM data:
 *
 * 1) mem_section	- memory sections, mem_map's for valid memory
 */
#ifdef CONFIG_SPARSEMEM_EXTREME
struct mem_section **mem_section;
#else
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
	____cacheline_internodealigned_in_smp;
#endif
EXPORT_SYMBOL(mem_section);

#ifdef NODE_NOT_IN_PAGE_FLAGS
/*
 * If we did not store the node number in the page then we have to
 * do a lookup in the section_to_node_table in order to find which
 * node the page belongs to.
 */
#if MAX_NUMNODES <= 256
static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
#else
static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
#endif

int page_to_nid(const struct page *page)
{
	return section_to_node_table[page_to_section(page)];
}
EXPORT_SYMBOL(page_to_nid);

static void set_section_nid(unsigned long section_nr, int nid)
{
	section_to_node_table[section_nr] = nid;
}
#else /* !NODE_NOT_IN_PAGE_FLAGS */
static inline void set_section_nid(unsigned long section_nr, int nid)
{
}
#endif

#ifdef CONFIG_SPARSEMEM_EXTREME
static noinline struct mem_section __ref *sparse_index_alloc(int nid)
{
	struct mem_section *section = NULL;
	unsigned long array_size = SECTIONS_PER_ROOT *
				   sizeof(struct mem_section);

	if (slab_is_available()) {
		section = kzalloc_node(array_size, GFP_KERNEL, nid);
	} else {
		section = memblock_alloc_node(array_size, SMP_CACHE_BYTES,
					      nid);
		if (!section)
			panic("%s: Failed to allocate %lu bytes nid=%d\n",
			      __func__, array_size, nid);
	}

	return section;
}

static int __meminit sparse_index_init(unsigned long section_nr, int nid)
{
	unsigned long root = SECTION_NR_TO_ROOT(section_nr);
	struct mem_section *section;

	/*
	 * An existing section is possible in the sub-section hotplug
	 * case. First hot-add instantiates, follow-on hot-add reuses
	 * the existing section.
	 *
	 * The mem_hotplug_lock resolves the apparent race below.
	 */
	if (mem_section[root])
		return 0;

	section = sparse_index_alloc(nid);
	if (!section)
		return -ENOMEM;

	mem_section[root] = section;

	return 0;
}
#else /* !SPARSEMEM_EXTREME */
static inline int sparse_index_init(unsigned long section_nr, int nid)
{
	return 0;
}
#endif

#ifdef CONFIG_SPARSEMEM_EXTREME
unsigned long __section_nr(struct mem_section *ms)
{
	unsigned long root_nr;
	struct mem_section *root = NULL;

	for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
		root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
		if (!root)
			continue;

		if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
		     break;
	}

	VM_BUG_ON(!root);

	return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
}
#else
unsigned long __section_nr(struct mem_section *ms)
{
	return (unsigned long)(ms - mem_section[0]);
}
#endif

/*
 * During early boot, before section_mem_map is used for an actual
 * mem_map, we use section_mem_map to store the section's NUMA
 * node.  This keeps us from having to use another data structure.  The
 * node information is cleared just before we store the real mem_map.
 */
static inline unsigned long sparse_encode_early_nid(int nid)
{
	return (nid << SECTION_NID_SHIFT);
}

static inline int sparse_early_nid(struct mem_section *section)
{
	return (section->section_mem_map >> SECTION_NID_SHIFT);
}

/* Validate the physical addressing limitations of the model */
void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
						unsigned long *end_pfn)
{
	unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);

	/*
	 * Sanity checks - do not allow an architecture to pass
	 * in larger pfns than the maximum scope of sparsemem:
	 */
	if (*start_pfn > max_sparsemem_pfn) {
		mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
			"Start of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
			*start_pfn, *end_pfn, max_sparsemem_pfn);
		WARN_ON_ONCE(1);
		*start_pfn = max_sparsemem_pfn;
		*end_pfn = max_sparsemem_pfn;
	} else if (*end_pfn > max_sparsemem_pfn) {
		mminit_dprintk(MMINIT_WARNING, "pfnvalidation",
			"End of range %lu -> %lu exceeds SPARSEMEM max %lu\n",
			*start_pfn, *end_pfn, max_sparsemem_pfn);
		WARN_ON_ONCE(1);
		*end_pfn = max_sparsemem_pfn;
	}
}

/*
 * There are a number of times that we loop over NR_MEM_SECTIONS,