memblock.c

/*
 * Procedures for maintaining information about logical memory blocks.
 *
 * Peter Bergner, IBM Corp.	June 2001.
 * Copyright (C) 2001 Peter Bergner.
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/bitops.h>
#include <linux/poison.h>
#include <linux/pfn.h>
#include <linux/debugfs.h>
#include <linux/kmemleak.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
#include <linux/bootmem.h>

#include <asm/sections.h>
#include <linux/io.h>

#include "internal.h"

static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock;
#endif

struct memblock memblock __initdata_memblock = {
	.memory.regions		= memblock_memory_init_regions,
	.memory.cnt		= 1,	/* empty dummy entry */
	.memory.max		= INIT_MEMBLOCK_REGIONS,
	.memory.name		= "memory",

	.reserved.regions	= memblock_reserved_init_regions,
	.reserved.cnt		= 1,	/* empty dummy entry */
	.reserved.max		= INIT_MEMBLOCK_REGIONS,
	.reserved.name		= "reserved",

#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
	.physmem.regions	= memblock_physmem_init_regions,
	.physmem.cnt		= 1,	/* empty dummy entry */
	.physmem.max		= INIT_PHYSMEM_REGIONS,
	.physmem.name		= "physmem",
#endif

	.bottom_up		= false,
	.current_limit		= MEMBLOCK_ALLOC_ANYWHERE,
};

int memblock_debug __initdata_memblock;
static bool system_has_some_mirror __initdata_memblock = false;
static int memblock_can_resize __initdata_memblock;
static int memblock_memory_in_slab __initdata_memblock = 0;
static int memblock_reserved_in_slab __initdata_memblock = 0;

ulong __init_memblock choose_memblock_flags(void)
{
	return system_has_some_mirror ? MEMBLOCK_MIRROR : MEMBLOCK_NONE;
}

/* adjust *@size so that (@base + *@size) doesn't overflow, return new size */
static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
{
	return *size = min(*size, PHYS_ADDR_MAX - base);
}

/*
 * Address comparison utilities
 */
static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
				       phys_addr_t base2, phys_addr_t size2)
{
	return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
}

bool __init_memblock memblock_overlaps_region(struct memblock_type *type,
					phys_addr_t base, phys_addr_t size)
{
	unsigned long i;

	for (i = 0; i < type->cnt; i++)
		if (memblock_addrs_overlap(base, size, type->regions[i].base,
					   type->regions[i].size))
			break;
	return i < type->cnt;
}

/*
 * __memblock_find_range_bottom_up - find free area utility in bottom-up
 * @start: start of candidate range
 * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
 * @size: size of free area to find
 * @align: alignment of free area to find
 * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
 * @flags: pick from blocks based on memory attributes
 *
 * Utility called from memblock_find_in_range_node(), find free area bottom-up.
 *
 * RETURNS:
 * Found address on success, 0 on failure.
 */
static phys_addr_t __init_memblock
__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
				phys_addr_t size, phys_addr_t align, int nid,
				ulong flags)
{
	phys_addr_t this_start, this_end, cand;
	u64 i;

	for_each_free_mem_range(i, nid, flags, &this_start, &this_end, NULL) {
		this_start = clamp(this_start, start, end);
		this_end = clamp(this_end, start, end);

		cand = round_up(this_start, align);
		if (cand < this_end && this_end - cand >= size)
			return cand;
	}

	return 0;
}

/**
 * __memblock_find_range_top_down - find free area utility, in top-down
 * @start: start of candidate range
 * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
 * @size: size of free area to find
 * @align: alignment of free area to find
 * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
 * @flags: pick from blocks based on memory attributes
 *
 * Utility called from memblock_find_in_range_node(), find free area top-down.
 *
 * RETURNS:
 * Found address on success, 0 on failure.
 */
static phys_addr_t __init_memblock
__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
			       phys_addr_t size, phys_addr_t align, int nid,
			       ulong flags)
{
	phys_addr_t this_start, this_end, cand;
	u64 i;

	for_each_free_mem_range_reverse(i, nid, flags, &this_start, &this_end,
					NULL) {
		this_start = clamp(this_start, start, end);
		this_end = clamp(this_end, start, end);

		if (this_end < size)
			continue;

		cand = round_down(this_end - size, align);
		if (cand >= this_start)
			return cand;
	}

	return 0;
}

/**
 * memblock_find_in_range_node - find free area in given range and node
 * @size: size of free area to find
 * @align: alignment of free area to find
 * @start: start of candidate range
 * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
 * @nid: nid of the free area to find, %NUMA_NO_NODE for any node
 * @flags: pick from blocks based on memory attributes
 *
 * Find @size free area aligned to @align in the specified range and node.
 *
 * When allocation direction is bottom-up, the @start should be greater
 * than the end of the kernel image. Otherwise, it will be trimmed. The
 * reason is that we want the bottom-up allocation just near the kernel
 * image so it is highly likely that the allocated memory and the kernel
 * will reside in the same node.
 *
 * If bottom-up allocation failed, will try to allocate memory top-down.
 *
 * RETURNS:
 * Found address on success, 0 on failure.
 */
phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
					phys_addr_t align, phys_addr_t start,
					phys_addr_t end, int nid, ulong flags)
{
	phys_addr_t kernel_end, ret;

	/* pump up @end */
	if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
		end = memblock.current_limit;

	/* avoid allocating the first page */
	start = max_t(phys_addr_t, start, PAGE_SIZE);
	end = max(start, end);
	kernel_end = __pa_symbol(_end);

	/*
	 * try bottom-up allocation only when bottom-up mode
	 * is set and @end is above the kernel image.
	 */
	if (memblock_bottom_up() && end > kernel_end) {
		phys_addr_t bottom_up_start;

		/* make sure we will allocate above the kernel */
		bottom_up_start = max(start, kernel_end);

		/* ok, try bottom-up allocation first */
		ret = __memblock_find_range_bottom_up(bottom_up_start, end,
						      size, align, nid, flags);
		if (ret)
			return ret;

		/*
		 * we always limit bottom-up allocation above the kernel,
		 * but top-down allocation doesn't have the limit, so
		 * retrying top-down allocation may succeed when bottom-up
		 * allocation failed.
		 *
		 * bottom-up allocation is expected to be fail very rarely,
		 * so we use WARN_ONCE() here to see the stack trace if
		 * fail happens.
		 */
		WARN_ONCE(1, "memblock: bottom-up allocation failed, memory hotunplug may be affected\n");
	}

	return __memblock_find_range_top_down(start, end, size, align, nid,
					      flags);
}

/**
 * memblock_find_in_range - find free area in given range
 * @start: start of candidate range
 * @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
 * @size: size of free area to find
 * @align: alignment of free area to find
 *
 * Find @size free area aligned to @align in the specified range.
 *
 * RETURNS:
 * Found address on success, 0 on failure.
 */
phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
					phys_addr_t end, phys_addr_t size,
					phys_addr_t align)
{
	phys_addr_t ret;
	ulong flags = choose_memblock_flags();

again:
	ret = memblock_find_in_range_node(size, align, start, end,
					    NUMA_NO_NODE, flags);

	if (!ret && (flags & MEMBLOCK_MIRROR)) {
		pr_warn("Could not allocate %pap bytes of mirrored memory\n",
			&size);
		flags &= ~MEMBLOCK_MIRROR;
		goto again;
	}

	return ret;
}

static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
{
	type->total_size -= type->regions[r].size;
	memmove(&type->regions[r], &type->regions[r + 1],
		(type->cnt - (r + 1)) * sizeof(type->regions[r]));
	type->cnt--;

	/* Special case for empty arrays */
	if (type->cnt == 0) {
		WARN_ON(type->total_size != 0);
		type->cnt = 1;
		type->regions[0].base = 0;
		type->regions[0].size = 0;
		type->regions[0].flags = 0;
		memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
	}
}

#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
/**
 * Discard memory and reserved arrays if they were allocated
 */
void __init memblock_discard(void)
{
	phys_addr_t addr, size;

	if (memblock.reserved.regions != memblock_reserved_init_regions) {
		addr = __pa(memblock.reserved.regions);
		size = PAGE_ALIGN(sizeof(struct memblock_region) *
				  memblock.reserved.max);
		__memblock_free_late(addr, size);
	}

	if (memblock.memory.regions != memblock_memory_init_regions) {
		addr = __pa(memblock.memory.regions);
		size = PAGE_ALIGN(sizeof(struct memblock_region) *
				  memblock.memory.max);
		__memblock_free_late(addr, size);
	}
}
#endif

/**
 * memblock_double_array - double the size of the memblock regions array
 * @type: memblock type of the regions array being doubled
 * @new_area_start: starting address of memory range to avoid overlap with
 * @new_area_size: size of memory range to avoid overlap with
 *
 * Double the size of the @type regions array. If memblock is being used to
 * allocate memory for a new reserved regions array and there is a previously
 * allocated memory range [@new_area_start,@new_area_start+@new_area_size]
 * waiting to be reserved, ensure the memory used by the new array does
 * not overlap.
 *
 * RETURNS:
 * 0 on success, -1 on failure.
 */
static int __init_memblock memblock_double_array(struct memblock_type *type,
						phys_addr_t new_area_start,
						phys_addr_t new_area_size)
{
	struct memblock_region *new_array, *old_array;
	phys_addr_t old_alloc_size, new_alloc_size;
	phys_addr_t old_size, new_size, addr;
	int use_slab = slab_is_available();
	int *in_slab;

	/* We don't allow resizing until we know about the reserved regions
	 * of memory that aren't suitable for allocation
	 */
	if (!memblock_can_resize)
		return -1;

	/* Calculate new doubled size */
	old_size = type->max * sizeof(struct memblock_region);
	new_size = old_size << 1;
	/*
	 * We need to allocated new one align to PAGE_SIZE,
	 *   so we can free them completely later.
	 */
	old_alloc_size = PAGE_ALIGN(old_size);
	new_alloc_size = PAGE_ALIGN(new_size);

	/* Retrieve the slab flag */
	if (type == &memblock.memory)
		in_slab = &memblock_memory_in_slab;
	else
		in_slab = &memblock_reserved_in_slab;

	/* Try to find some space for it.
	 *
	 * WARNING: We assume that either slab_is_available() and we use it or
	 * we use MEMBLOCK for allocations. That means that this is unsafe to
	 * use when bootmem is currently active (unless bootmem itself is
	 * implemented on top of MEMBLOCK which isn't the case yet)
	 *
	 * This should however not be an issue for now, as we currently only
	 * call into MEMBLOCK while it's still active, or much later when slab
	 * is active for memory hotplug operations
	 */
	if (use_slab) {
		new_array = kmalloc(new_size, GFP_KERNEL);
		addr = new_array ? __pa(new_array) : 0;
	} else {
		/* only exclude range when trying to double reserved.regions */
		if (type != &memblock.reserved)
			new_area_start = new_area_size = 0;

		addr = memblock_find_in_range(new_area_start + new_area_size,
						memblock.current_limit,
						new_alloc_size, PAGE_SIZE);
		if (!addr && new_area_size)
			addr = memblock_find_in_range(0,
				min(new_area_start, memblock.current_limit),
				new_alloc_size, PAGE_SIZE);

		new_array = addr ? __va(addr) : NULL;
	}
	if (!addr) {
		pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
		       type->name, type->max, type->max * 2);
		return -1;
	}

	memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]",
			type->name, type->max * 2, (u64)addr,
			(u64)addr + new_size - 1);

	/*
	 * Found space, we now need to move the array over before we add the
	 * reserved region since it may be our reserved array itself that is
	 * full.
	 */
	memcpy(new_array, type->regions, old_size);
	memset(new_array + type->max, 0, old_size);
	old_array = type->regions;
	type->regions = new_array;
	type->max <<= 1;

	/* Free old array. We needn't free it if the array is the static one */
	if (*in_slab)
		kfree(old_array);
	else if (old_array != memblock_memory_init_regions &&
		 old_array != memblock_reserved_init_regions)
		memblock_free(__pa(old_array), old_alloc_size);

	/*
	 * Reserve the new array if that comes from the memblock.  Otherwise, we
	 * needn't do it
	 */
	if (!use_slab)
		BUG_ON(memblock_reserve(addr, new_alloc_size));

	/* Update slab flag */
	*in_slab = use_slab;

	return 0;
}

/**
 * memblock_merge_regions - merge neighboring compatible regions
 * @type: memblock type to scan
 *
 * Scan @type and merge neighboring compatible regions.
 */
static void __init_memblock memblock_merge_regions(struct memblock_type *type)
{
	int i = 0;

	/* cnt never goes below 1 */
	while (i < type->cnt - 1) {
		struct memblock_region *this = &type->regions[i];
		struct memblock_region *next = &type->regions[i + 1];

		if (this->base + this->size != next->base ||
		    memblock_get_region_node(this) !=
		    memblock_get_region_node(next) ||
		    this->flags != next->flags) {
			BUG_ON(this->base + this->size > next->base);
			i++;
			continue;
		}

		this->size += next->size;
		/* move forward from next + 1, index of which is i + 2 */
		memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
		type->cnt--;
	}
}

/**
 * memblock_insert_region - insert new memblock region
 * @type:	memblock type to insert into
 * @idx:	index for the insertion point
 * @base:	base address of the new region
 * @size:	size of the new region
 * @nid:	node id of the new region
 * @flags:	flags of the new region
 *
 * Insert new memblock region [@base,@base+@size) into @type at @idx.
 * @type must already have extra room to accommodate the new region.
 */
static void __init_memblock memblock_insert_region(struct memblock_type *type,
						   int idx, phys_addr_t base,
						   phys_addr_t size,
						   int nid, unsigned long flags)
{
	struct memblock_region *rgn = &type->regions[idx];

	BUG_ON(type->cnt >= type->max);
	memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn));
	rgn->base = base;
	rgn->size = size;
	rgn->flags = flags;
	memblock_set_region_node(rgn, nid);
	type->cnt++;
	type->total_size += size;
}

/**
 * memblock_add_range - add new memblock region
 * @type: memblock type to add new region into
 * @base: base address of the new region
 * @size: size of the new region
 * @nid: nid of the new region
 * @flags: flags of the new region
 *
 * Add new memblock region [@base,@base+@size) into @type.  The new region
 * is allowed to overlap with existing ones - overlaps don't affect already
 * existing regions.  @type is guaranteed to be minimal (all neighbouring
 * compatible regions are merged) after the addition.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
int __init_memblock memblock_add_range(struct memblock_type *type,
				phys_addr_t base, phys_addr_t size,
				int nid, unsigned long flags)
{
	bool insert = false;
	phys_addr_t obase = base;
	phys_addr_t end = base + memblock_cap_size(base, &size);
	int idx, nr_new;
	struct memblock_region *rgn;

	if (!size)
		return 0;

	/* special case for empty array */
	if (type->regions[0].size == 0) {
		WARN_ON(type->cnt != 1 || type->total_size);
		type->regions[0].base = base;
		type->regions[0].size = size;
		type->regions[0].flags = flags;
		memblock_set_region_node(&type->regions[0], nid);
		type->total_size = size;
		return 0;
	}
repeat:
	/*
	 * The following is executed twice.  Once with %false @insert and
	 * then with %true.  The first counts the number of regions needed
	 * to accommodate the new area.  The second actually inserts them.
	 */
	base = obase;
	nr_new = 0;

	for_each_memblock_type(idx, type, rgn) {
		phys_addr_t rbase = rgn->base;
		phys_addr_t rend = rbase + rgn->size;

		if (rbase >= end)
			break;
		if (rend <= base)
			continue;
		/*
		 * @rgn overlaps.  If it separates the lower part of new
		 * area, insert that portion.
		 */
		if (rbase > base) {
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
			WARN_ON(nid != memblock_get_region_node(rgn));
#endif
			WARN_ON(flags != rgn->flags);
			nr_new++;
			if (insert)
				memblock_insert_region(type, idx++, base,
						       rbase - base, nid,
						       flags);
		}
		/* area below @rend is dealt with, forget about it */
		base = min(rend, end);
	}

	/* insert the remaining portion */
	if (base < end) {
		nr_new++;
		if (insert)
			memblock_insert_region(type, idx, base, end - base,
					       nid, flags);
	}

	if (!nr_new)
		return 0;

	/*
	 * If this was the first round, resize array and repeat for actual
	 * insertions; otherwise, merge and return.
	 */
	if (!insert) {
		while (type->cnt + nr_new > type->max)
			if (memblock_double_array(type, obase, size) < 0)
				return -ENOMEM;
		insert = true;
		goto repeat;
	} else {
		memblock_merge_regions(type);
		return 0;
	}
}

int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
				       int nid)
{
	return memblock_add_range(&memblock.memory, base, size, nid, 0);
}

int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
	phys_addr_t end = base + size - 1;

	memblock_dbg("memblock_add: [%pa-%pa] %pF\n",
		     &base, &end, (void *)_RET_IP_);

	return memblock_add_range(&memblock.memory, base, size, MAX_NUMNODES, 0);
}

/**
 * memblock_isolate_range - isolate given range into disjoint memblocks
 * @type: memblock type to isolate range for
 * @base: base of range to isolate
 * @size: size of range to isolate
 * @start_rgn: out parameter for the start of isolated region
 * @end_rgn: out parameter for the end of isolated region
 *
 * Walk @type and ensure that regions don't cross the boundaries defined by
 * [@base,@base+@size).  Crossing regions are split at the boundaries,
 * which may create at most two more regions.  The index of the first
 * region inside the range is returned in *@start_rgn and end in *@end_rgn.
 *
 * RETURNS:
 * 0 on success, -errno on failure.
 */
static int __init_memblock memblock_isolate_range(struct memblock_type *type,
					phys_addr_t base, phys_addr_t size,
					int *start_rgn, int *end_rgn)
{
	phys_addr_t end = base + memblock_cap_size(base, &size);
	int idx;
	struct memblock_region *rgn;

	*start_rgn = *end_rgn = 0;

	if (!size)
		return 0;

	/* we'll create at most two more regions */
	while (type->cnt + 2 > type->max)
		if (memblock_double_array(type, base, size) < 0)
			return -ENOMEM;

	for_each_memblock_type(idx, type, rgn) {
		phys_addr_t rbase = rgn->base;
		phys_addr_t rend = rbase + rgn->size;

		if (rbase >= end)
			break;
		if (rend <= base)
			continue;

		if (rbase < base) {
			/*
			 * @rgn intersects from below.  Split and continue
			 * to process the next region - the new top half.
			 */
			rgn->base = base;
			rgn->size -= base - rbase;
			type->total_size -= base - rbase;
			memblock_insert_region(type, idx, rbase, base - rbase,
					       memblock_get_region_node(rgn),
					       rgn->flags);
		} else if (rend > end) {
			/*
			 * @rgn intersects from above.  Split and redo the
			 * current region - the new bottom half.
			 */
			rgn->base = end;
			rgn->size -= end - rbase;
			type->total_size -= end - rbase;
			memblock_insert_region(type, idx--, rbase, end - rbase,
					       memblock_get_region_node(rgn),
					       rgn->flags);
		} else {
			/* @rgn is fully contained, record it */
			if (!*end_rgn)
				*start_rgn = idx;
			*end_rgn = idx + 1;
		}
	}

	return 0;
}

static int __init_memblock memblock_remove_range(struct memblock_type *type,
					  phys_addr_t base, phys_addr_t size)
{
	int start_rgn, end_rgn;
	int i, ret;

	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;

	for (i = end_rgn - 1; i >= start_rgn; i--)
		memblock_remove_region(type, i);
	return 0;
}

int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
{
	phys_addr_t end = base + size - 1;

	memblock_dbg("memblock_remove: [%pa-%pa] %pS\n",
		     &base, &end, (void *)_RET_IP_);

	return memblock_remove_range(&memblock.memory, base, size);
}


int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
{
	phys_addr_t end = base + size - 1;

	memblock_dbg("   memblock_free: [%pa-%pa] %pF\n",
		     &base, &end, (void *)_RET_IP_);

	kmemleak_free_part_phys(base, size);
	return memblock_remove_range(&memblock.reserved, base, size);
}

int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
{
	phys_addr_t end = base + size - 1;

	memblock_dbg("memblock_reserve: [%pa-%pa] %pF\n",
		     &base, &end, (void *)_RET_IP_);

	return memblock_add_range(&memblock.reserved, base, size, MAX_NUMNODES, 0);
}

/**
 *
 * This function isolates region [@base, @base + @size), and sets/clears flag
 *
 * Return 0 on success, -errno on failure.
 */
static int __init_memblock memblock_setclr_flag(phys_addr_t base,
				phys_addr_t size, int set, int flag)
{
	struct memblock_type *type = &memblock.memory;
	int i, ret, start_rgn, end_rgn;

	ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
	if (ret)
		return ret;

	for (i = start_rgn; i < end_rgn; i++)
		if (set)
			memblock_set_region_flags(&type->regions[i], flag);
		else
			memblock_clear_region_flags(&type->regions[i], flag);

	memblock_merge_regions(type);
	return 0;
}

/**
 * memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG.
 * @base: the base phys addr of the region
 * @size: the size of the region
 *
 * Return 0 on success, -errno on failure.
 */
int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
{
	return memblock_setclr_flag(base, size, 1, MEMBLOCK_HOTPLUG);
}

/**
 * memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region.
 * @base: the base phys addr of the region
 * @size: the size of the region
 *
 * Return 0 on success, -errno on failure.
 */
int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
{
	return memblock_setclr_flag(base, size, 0, MEMBLOCK_HOTPLUG);
}

/**
 * memblock_mark_mirror - Mark mirrored memory with flag MEMBLOCK_MIRROR.
 * @base: the base phys addr of the region
 * @size: the size of the region
 *
 * Return 0 on success, -errno on failure.
 */
int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size)
{
	system_has_some_mirror = true;

	return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR);
}

/**
 * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP.
 * @base: the base phys addr of the region
 * @size: the size of the region
 *
 * Return 0 on success, -errno on failure.
 */
int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size)
{
	return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP);
}

/**
 * memblock_clear_nomap - Clear flag MEMBLOCK_NOMAP for a specified region.
 * @base: the base phys addr of the region
 * @size: the size of the region
 *
 * Return 0 on success, -errno on failure.
 */
int __init_memblock memblock_clear_nomap(phys_addr_t base, phys_addr_t size)
{
	return memblock_setclr_flag(base, size, 0, MEMBLOCK_NOMAP);
}

/**
 * __next_reserved_mem_region - next function for for_each_reserved_region()
 * @idx: pointer to u64 loop variable
 * @out_start: ptr to phys_addr_t for start address of the region, can be %NULL
 * @out_end: ptr to phys_addr_t for end address of the region, can be %NULL
 *
 * Iterate over all reserved memory regions.
 */
void __init_memblock __next_reserved_mem_region(u64 *idx,
					   phys_addr_t *out_start,
					   phys_addr_t *out_end)
{
	struct memblock_type *type = &memblock.reserved;

	if (*idx < type->cnt) {
		struct memblock_region *r = &type->regions[*idx];
		phys_addr_t base = r->base;
		phys_addr_t size = r->size;

		if (out_start)
			*out_start = base;
		if (out_end)
			*out_end = base + size - 1;

		*idx += 1;
		return;
	}

	/* signal end of iteration */
	*idx = ULLONG_MAX;
}

/**
 * __next__mem_range - next function for for_each_free_mem_range() etc.
 * @idx: pointer to u64 loop variable
 * @nid: node selector, %NUMA_NO_NODE for all nodes
 * @flags: pick from blocks based on memory attributes
 * @type_a: pointer to memblock_type from where the range is taken
 * @type_b: pointer to memblock_type which excludes memory from being taken
 * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
 * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
 * @out_nid: ptr to int for nid of the range, can be %NULL
 *
 * Find the first area from *@idx which matches @nid, fill the out
 * parameters, and update *@idx for the next iteration.  The lower 32bit of
 * *@idx contains index into type_a and the upper 32bit indexes the
 * areas before each region in type_b.	For example, if type_b regions
 * look like the following,
 *
 *	0:[0-16), 1:[32-48), 2:[128-130)
 *
 * The upper 32bit indexes the following regions.
 *
 *	0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX)
 *
 * As both region arrays are sorted, the function advances the two indices
 * in lockstep and returns each intersection.
 */
void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags,
				      struct memblock_type *type_a,
				      struct memblock_type *type_b,
				      phys_addr_t *out_start,
				      phys_addr_t *out_end, int *out_nid)
{
	int idx_a = *idx & 0xffffffff;
	int idx_b = *idx >> 32;

	if (WARN_ONCE(nid == MAX_NUMNODES,
	"Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
		nid = NUMA_NO_NODE;

	for (; idx_a < type_a->cnt; idx_a++) {
		struct memblock_region *m = &type_a->regions[idx_a];

		phys_addr_t m_start = m->base;
		phys_addr_t m_end = m->base + m->size;
		int	    m_nid = memblock_get_region_node(m);

		/* only memory regions are associated with nodes, check it */
		if (nid != NUMA_NO_NODE && nid != m_nid)
			continue;

		/* skip hotpluggable memory regions if needed */
		if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
			continue;

		/* if we want mirror memory skip non-mirror memory regions */
		if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
			continue;

		/* skip nomap memory unless we were asked for it explicitly */
		if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
			continue;

		if (!type_b) {
			if (out_start)
				*out_start = m_start;
			if (out_end)
				*out_end = m_end;
			if (out_nid)
				*out_nid = m_nid;
			idx_a++;
			*idx = (u32)idx_a | (u64)idx_b << 32;
			return;
		}

		/* scan areas before each reservation */
		for (; idx_b < type_b->cnt + 1; idx_b++) {
			struct memblock_region *r;
			phys_addr_t r_start;
			phys_addr_t r_end;

			r = &type_b->regions[idx_b];
			r_start = idx_b ? r[-1].base + r[-1].size : 0;
			r_end = idx_b < type_b->cnt ?
				r->base : PHYS_ADDR_MAX;

			/*
			 * if idx_b advanced past idx_a,
			 * break out to advance idx_a
			 */
			if (r_start >= m_end)
				break;
			/* if the two regions intersect, we're done */
			if (m_start < r_end) {
				if (out_start)
					*out_start =
						max(m_start, r_start);
				if (out_end)
					*out_end = min(m_end, r_end);
				if (out_nid)
					*out_nid = m_nid;
				/*
				 * The region which ends first is
				 * advanced for the next iteration.
				 */
				if (m_end <= r_end)
					idx_a++;
				else
					idx_b++;
				*idx = (u32)idx_a | (u64)idx_b << 32;
				return;
			}
		}
	}

	/* signal end of iteration */
	*idx = ULLONG_MAX;
}

/**
 * __next_mem_range_rev - generic next function for for_each_*_range_rev()
 *
 * Finds the next range from type_a which is not marked as unsuitable
 * in type_b.
 *
 * @idx: pointer to u64 loop variable
 * @nid: node selector, %NUMA_NO_NODE for all nodes
 * @flags: pick from blocks based on memory attributes
 * @type_a: pointer to memblock_type from where the range is taken
 * @type_b: pointer to memblock_type which excludes memory from being taken
 * @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
 * @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
 * @out_nid: ptr to int for nid of the range, can be %NULL
 *
 * Reverse of __next_mem_range().
 */
void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags,
					  struct memblock_type *type_a,
					  struct memblock_type *type_b,
					  phys_addr_t *out_start,
					  phys_addr_t *out_end, int *out_nid)
{
	int idx_a = *idx & 0xffffffff;
	int idx_b = *idx >> 32;

	if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
		nid = NUMA_NO_NODE;

	if (*idx == (u64)ULLONG_MAX) {
		idx_a = type_a->cnt - 1;
		if (type_b != NULL)
			idx_b = type_b->cnt;
		else
			idx_b = 0;
	}

	for (; idx_a >= 0; idx_a--) {
		struct memblock_region *m = &type_a->regions[idx_a];

		phys_addr_t m_start = m->base;
		phys_addr_t m_end = m->base + m->size;
		int m_nid = memblock_get_region_node(m);

		/* only memory regions are associated with nodes, check it */
		if (nid != NUMA_NO_NODE && nid != m_nid)
			continue;

		/* skip hotpluggable memory regions if needed */
		if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
			continue;

		/* if we want mirror memory skip non-mirror memory regions */
		if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m))
			continue;

		/* skip nomap memory unless we were asked for it explicitly */
		if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m))
			continue;

		if (!type_b) {
			if (out_start)
				*out_start = m_start;
			if (out_end)
				*out_end = m_end;
			if (out_nid)
				*out_nid = m_nid;
			idx_a--;
			*idx = (u32)idx_a | (u64)idx_b << 32;
			return;
		}

		/* scan areas before each reservation */
		for (; idx_b >= 0; idx_b--) {
			struct memblock_region *r;
			phys_addr_t r_start;
			phys_addr_t r_end;

			r = &type_b->regions[idx_b];
			r_start = idx_b ? r[-1].base + r[-1].size : 0;
			r_end = idx_b < type_b->cnt ?
				r->base : PHYS_ADDR_MAX;
			/*
			 * if idx_b advanced past idx_a,
			 * break out to advance idx_a
			 */

			if (r_end <= m_start)
				break;
			/* if the two regions intersect, we're done */
			if (m_end > r_start) {
				if (out_start)
					*out_start = max(m_start, r_start);
				if (out_end)
					*out_end = min(m_end, r_end);
				if (out_nid)
					*out_nid = m_nid;
				if (m_start >= r_start)
					idx_a--;
				else