2010-07-12 12:36:09 +08:00
|
|
|
/*
|
|
|
|
* 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>
|
2010-07-07 06:39:13 +08:00
|
|
|
#include <linux/slab.h>
|
2010-07-12 12:36:09 +08:00
|
|
|
#include <linux/init.h>
|
|
|
|
#include <linux/bitops.h>
|
2010-07-07 06:39:07 +08:00
|
|
|
#include <linux/poison.h>
|
2010-07-07 06:39:16 +08:00
|
|
|
#include <linux/pfn.h>
|
2010-07-07 06:39:19 +08:00
|
|
|
#include <linux/debugfs.h>
|
|
|
|
#include <linux/seq_file.h>
|
2010-07-12 12:36:09 +08:00
|
|
|
#include <linux/memblock.h>
|
|
|
|
|
2011-12-09 02:22:07 +08:00
|
|
|
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;
|
|
|
|
|
|
|
|
struct memblock memblock __initdata_memblock = {
|
|
|
|
.memory.regions = memblock_memory_init_regions,
|
|
|
|
.memory.cnt = 1, /* empty dummy entry */
|
|
|
|
.memory.max = INIT_MEMBLOCK_REGIONS,
|
|
|
|
|
|
|
|
.reserved.regions = memblock_reserved_init_regions,
|
|
|
|
.reserved.cnt = 1, /* empty dummy entry */
|
|
|
|
.reserved.max = INIT_MEMBLOCK_REGIONS,
|
|
|
|
|
|
|
|
.current_limit = MEMBLOCK_ALLOC_ANYWHERE,
|
|
|
|
};
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2010-07-28 13:43:02 +08:00
|
|
|
int memblock_debug __initdata_memblock;
|
|
|
|
int memblock_can_resize __initdata_memblock;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2010-07-07 06:39:13 +08:00
|
|
|
/* inline so we don't get a warning when pr_debug is compiled out */
|
|
|
|
static inline const char *memblock_type_name(struct memblock_type *type)
|
|
|
|
{
|
|
|
|
if (type == &memblock.memory)
|
|
|
|
return "memory";
|
|
|
|
else if (type == &memblock.reserved)
|
|
|
|
return "reserved";
|
|
|
|
else
|
|
|
|
return "unknown";
|
|
|
|
}
|
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
/*
|
|
|
|
* Address comparison utilities
|
|
|
|
*/
|
2010-07-28 13:43:02 +08:00
|
|
|
static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
|
2010-08-04 11:34:42 +08:00
|
|
|
phys_addr_t base2, phys_addr_t size2)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
|
|
|
return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
|
|
|
|
}
|
|
|
|
|
2011-11-01 08:09:15 +08:00
|
|
|
static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
|
|
|
|
phys_addr_t base, phys_addr_t size)
|
2010-07-12 12:36:48 +08:00
|
|
|
{
|
|
|
|
unsigned long i;
|
|
|
|
|
|
|
|
for (i = 0; i < type->cnt; i++) {
|
|
|
|
phys_addr_t rgnbase = type->regions[i].base;
|
|
|
|
phys_addr_t rgnsize = type->regions[i].size;
|
|
|
|
if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
return (i < type->cnt) ? i : -1;
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Find, allocate, deallocate or reserve unreserved regions. All allocations
|
|
|
|
* are top-down.
|
|
|
|
*/
|
|
|
|
|
2010-10-12 03:34:09 +08:00
|
|
|
static phys_addr_t __init_memblock memblock_find_region(phys_addr_t start, phys_addr_t end,
|
2010-07-12 12:36:48 +08:00
|
|
|
phys_addr_t size, phys_addr_t align)
|
|
|
|
{
|
|
|
|
phys_addr_t base, res_base;
|
|
|
|
long j;
|
|
|
|
|
2010-10-05 05:57:39 +08:00
|
|
|
/* In case, huge size is requested */
|
|
|
|
if (end < size)
|
2011-07-12 15:58:09 +08:00
|
|
|
return 0;
|
2010-10-05 05:57:39 +08:00
|
|
|
|
2011-07-12 15:58:08 +08:00
|
|
|
base = round_down(end - size, align);
|
2010-10-05 05:57:39 +08:00
|
|
|
|
2010-07-28 13:25:10 +08:00
|
|
|
/* Prevent allocations returning 0 as it's also used to
|
|
|
|
* indicate an allocation failure
|
|
|
|
*/
|
|
|
|
if (start == 0)
|
|
|
|
start = PAGE_SIZE;
|
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
while (start <= base) {
|
|
|
|
j = memblock_overlaps_region(&memblock.reserved, base, size);
|
|
|
|
if (j < 0)
|
|
|
|
return base;
|
|
|
|
res_base = memblock.reserved.regions[j].base;
|
|
|
|
if (res_base < size)
|
|
|
|
break;
|
2011-07-12 15:58:08 +08:00
|
|
|
base = round_down(res_base - size, align);
|
2010-07-12 12:36:48 +08:00
|
|
|
}
|
|
|
|
|
2011-07-12 15:58:09 +08:00
|
|
|
return 0;
|
2010-07-12 12:36:48 +08:00
|
|
|
}
|
|
|
|
|
2011-07-12 15:58:10 +08:00
|
|
|
/*
|
|
|
|
* Find a free area with specified alignment in a specific range.
|
|
|
|
*/
|
|
|
|
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)
|
2010-07-12 12:36:48 +08:00
|
|
|
{
|
|
|
|
long i;
|
|
|
|
|
|
|
|
BUG_ON(0 == size);
|
|
|
|
|
|
|
|
/* Pump up max_addr */
|
2010-07-12 13:00:34 +08:00
|
|
|
if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
|
|
|
|
end = memblock.current_limit;
|
2010-07-12 12:36:48 +08:00
|
|
|
|
|
|
|
/* We do a top-down search, this tends to limit memory
|
|
|
|
* fragmentation by keeping early boot allocs near the
|
|
|
|
* top of memory
|
|
|
|
*/
|
|
|
|
for (i = memblock.memory.cnt - 1; i >= 0; i--) {
|
|
|
|
phys_addr_t memblockbase = memblock.memory.regions[i].base;
|
|
|
|
phys_addr_t memblocksize = memblock.memory.regions[i].size;
|
2010-07-12 13:00:34 +08:00
|
|
|
phys_addr_t bottom, top, found;
|
2010-07-12 12:36:48 +08:00
|
|
|
|
|
|
|
if (memblocksize < size)
|
|
|
|
continue;
|
2010-07-12 13:00:34 +08:00
|
|
|
if ((memblockbase + memblocksize) <= start)
|
|
|
|
break;
|
|
|
|
bottom = max(memblockbase, start);
|
|
|
|
top = min(memblockbase + memblocksize, end);
|
|
|
|
if (bottom >= top)
|
|
|
|
continue;
|
|
|
|
found = memblock_find_region(bottom, top, size, align);
|
2011-07-12 15:58:09 +08:00
|
|
|
if (found)
|
2010-07-12 13:00:34 +08:00
|
|
|
return found;
|
2010-07-12 12:36:48 +08:00
|
|
|
}
|
2011-07-12 15:58:09 +08:00
|
|
|
return 0;
|
2010-07-12 12:36:48 +08:00
|
|
|
}
|
|
|
|
|
2010-08-26 04:39:14 +08:00
|
|
|
/*
|
|
|
|
* Free memblock.reserved.regions
|
|
|
|
*/
|
|
|
|
int __init_memblock memblock_free_reserved_regions(void)
|
|
|
|
{
|
|
|
|
if (memblock.reserved.regions == memblock_reserved_init_regions)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
return memblock_free(__pa(memblock.reserved.regions),
|
|
|
|
sizeof(struct memblock_region) * memblock.reserved.max);
|
|
|
|
}
|
|
|
|
|
|
|
|
/*
|
|
|
|
* Reserve memblock.reserved.regions
|
|
|
|
*/
|
|
|
|
int __init_memblock memblock_reserve_reserved_regions(void)
|
|
|
|
{
|
|
|
|
if (memblock.reserved.regions == memblock_reserved_init_regions)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
return memblock_reserve(__pa(memblock.reserved.regions),
|
|
|
|
sizeof(struct memblock_region) * memblock.reserved.max);
|
|
|
|
}
|
|
|
|
|
2010-07-28 13:43:02 +08:00
|
|
|
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2011-07-14 17:43:42 +08:00
|
|
|
memmove(&type->regions[r], &type->regions[r + 1],
|
|
|
|
(type->cnt - (r + 1)) * sizeof(type->regions[r]));
|
2010-08-04 12:06:41 +08:00
|
|
|
type->cnt--;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
/* Special case for empty arrays */
|
|
|
|
if (type->cnt == 0) {
|
|
|
|
type->cnt = 1;
|
|
|
|
type->regions[0].base = 0;
|
|
|
|
type->regions[0].size = 0;
|
2011-07-14 17:43:42 +08:00
|
|
|
memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2010-07-28 13:43:02 +08:00
|
|
|
static int __init_memblock memblock_double_array(struct memblock_type *type)
|
2010-07-07 06:39:13 +08:00
|
|
|
{
|
|
|
|
struct memblock_region *new_array, *old_array;
|
|
|
|
phys_addr_t old_size, new_size, addr;
|
|
|
|
int use_slab = slab_is_available();
|
|
|
|
|
|
|
|
/* 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;
|
|
|
|
|
|
|
|
/* 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);
|
2011-07-12 15:58:09 +08:00
|
|
|
addr = new_array ? __pa(new_array) : 0;
|
2010-07-07 06:39:13 +08:00
|
|
|
} else
|
2011-07-12 15:58:10 +08:00
|
|
|
addr = memblock_find_in_range(0, MEMBLOCK_ALLOC_ACCESSIBLE, new_size, sizeof(phys_addr_t));
|
2011-07-12 15:58:09 +08:00
|
|
|
if (!addr) {
|
2010-07-07 06:39:13 +08:00
|
|
|
pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
|
|
|
|
memblock_type_name(type), type->max, type->max * 2);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
new_array = __va(addr);
|
|
|
|
|
2010-07-28 13:13:22 +08:00
|
|
|
memblock_dbg("memblock: %s array is doubled to %ld at [%#010llx-%#010llx]",
|
|
|
|
memblock_type_name(type), type->max * 2, (u64)addr, (u64)addr + new_size - 1);
|
|
|
|
|
2010-07-07 06:39:13 +08:00
|
|
|
/* 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;
|
|
|
|
|
|
|
|
/* If we use SLAB that's it, we are done */
|
|
|
|
if (use_slab)
|
|
|
|
return 0;
|
|
|
|
|
|
|
|
/* Add the new reserved region now. Should not fail ! */
|
2011-12-09 02:22:06 +08:00
|
|
|
BUG_ON(memblock_reserve(addr, new_size));
|
2010-07-07 06:39:13 +08:00
|
|
|
|
|
|
|
/* If the array wasn't our static init one, then free it. We only do
|
|
|
|
* that before SLAB is available as later on, we don't know whether
|
|
|
|
* to use kfree or free_bootmem_pages(). Shouldn't be a big deal
|
|
|
|
* anyways
|
|
|
|
*/
|
|
|
|
if (old_array != memblock_memory_init_regions &&
|
|
|
|
old_array != memblock_reserved_init_regions)
|
|
|
|
memblock_free(__pa(old_array), old_size);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-07-12 17:15:55 +08:00
|
|
|
/**
|
|
|
|
* 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)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2011-07-12 17:15:55 +08:00
|
|
|
int i = 0;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 17:15:55 +08:00
|
|
|
/* 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];
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-14 17:43:42 +08:00
|
|
|
if (this->base + this->size != next->base ||
|
|
|
|
memblock_get_region_node(this) !=
|
|
|
|
memblock_get_region_node(next)) {
|
2011-07-12 17:15:55 +08:00
|
|
|
BUG_ON(this->base + this->size > next->base);
|
|
|
|
i++;
|
|
|
|
continue;
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
}
|
|
|
|
|
2011-07-12 17:15:55 +08:00
|
|
|
this->size += next->size;
|
|
|
|
memmove(next, next + 1, (type->cnt - (i + 1)) * sizeof(*next));
|
|
|
|
type->cnt--;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
2011-07-12 17:15:55 +08:00
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 17:15:55 +08:00
|
|
|
/**
|
|
|
|
* 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
|
|
|
|
*
|
|
|
|
* Insert new memblock region [@base,@base+@size) into @type at @idx.
|
|
|
|
* @type must already have extra room to accomodate the new region.
|
|
|
|
*/
|
|
|
|
static void __init_memblock memblock_insert_region(struct memblock_type *type,
|
|
|
|
int idx, phys_addr_t base,
|
2011-07-14 17:43:42 +08:00
|
|
|
phys_addr_t size, int nid)
|
2011-07-12 17:15:55 +08:00
|
|
|
{
|
|
|
|
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;
|
2011-07-14 17:43:42 +08:00
|
|
|
memblock_set_region_node(rgn, nid);
|
2011-07-12 17:15:55 +08:00
|
|
|
type->cnt++;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* memblock_add_region - 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
|
|
|
|
*
|
|
|
|
* 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.
|
|
|
|
*/
|
2011-12-09 02:22:06 +08:00
|
|
|
static int __init_memblock memblock_add_region(struct memblock_type *type,
|
|
|
|
phys_addr_t base, phys_addr_t size)
|
2011-07-12 17:15:55 +08:00
|
|
|
{
|
|
|
|
bool insert = false;
|
|
|
|
phys_addr_t obase = base, end = base + size;
|
|
|
|
int i, nr_new;
|
|
|
|
|
|
|
|
/* special case for empty array */
|
|
|
|
if (type->regions[0].size == 0) {
|
|
|
|
WARN_ON(type->cnt != 1);
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
type->regions[0].base = base;
|
|
|
|
type->regions[0].size = size;
|
2011-07-14 17:43:42 +08:00
|
|
|
memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
return 0;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
2011-07-12 17:15:55 +08:00
|
|
|
repeat:
|
|
|
|
/*
|
|
|
|
* The following is executed twice. Once with %false @insert and
|
|
|
|
* then with %true. The first counts the number of regions needed
|
|
|
|
* to accomodate the new area. The second actually inserts them.
|
2010-07-07 06:39:13 +08:00
|
|
|
*/
|
2011-07-12 17:15:55 +08:00
|
|
|
base = obase;
|
|
|
|
nr_new = 0;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 17:15:55 +08:00
|
|
|
for (i = 0; i < type->cnt; i++) {
|
|
|
|
struct memblock_region *rgn = &type->regions[i];
|
|
|
|
phys_addr_t rbase = rgn->base;
|
|
|
|
phys_addr_t rend = rbase + rgn->size;
|
|
|
|
|
|
|
|
if (rbase >= end)
|
2010-07-12 12:36:09 +08:00
|
|
|
break;
|
2011-07-12 17:15:55 +08:00
|
|
|
if (rend <= base)
|
|
|
|
continue;
|
|
|
|
/*
|
|
|
|
* @rgn overlaps. If it separates the lower part of new
|
|
|
|
* area, insert that portion.
|
|
|
|
*/
|
|
|
|
if (rbase > base) {
|
|
|
|
nr_new++;
|
|
|
|
if (insert)
|
|
|
|
memblock_insert_region(type, i++, base,
|
2011-07-14 17:43:42 +08:00
|
|
|
rbase - base, MAX_NUMNODES);
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
2011-07-12 17:15:55 +08:00
|
|
|
/* area below @rend is dealt with, forget about it */
|
|
|
|
base = min(rend, end);
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
2011-07-12 17:15:55 +08:00
|
|
|
|
|
|
|
/* insert the remaining portion */
|
|
|
|
if (base < end) {
|
|
|
|
nr_new++;
|
|
|
|
if (insert)
|
2011-07-14 17:43:42 +08:00
|
|
|
memblock_insert_region(type, i, base, end - base,
|
|
|
|
MAX_NUMNODES);
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2011-07-12 17:15:55 +08:00
|
|
|
/*
|
|
|
|
* If this was the first round, resize array and repeat for actual
|
|
|
|
* insertions; otherwise, merge and return.
|
2010-07-07 06:39:13 +08:00
|
|
|
*/
|
2011-07-12 17:15:55 +08:00
|
|
|
if (!insert) {
|
|
|
|
while (type->cnt + nr_new > type->max)
|
|
|
|
if (memblock_double_array(type) < 0)
|
|
|
|
return -ENOMEM;
|
|
|
|
insert = true;
|
|
|
|
goto repeat;
|
|
|
|
} else {
|
|
|
|
memblock_merge_regions(type);
|
|
|
|
return 0;
|
2010-07-07 06:39:13 +08:00
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2011-12-09 02:22:06 +08:00
|
|
|
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-08-04 12:06:41 +08:00
|
|
|
return memblock_add_region(&memblock.memory, base, size);
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2011-12-09 02:22:06 +08:00
|
|
|
static int __init_memblock __memblock_remove(struct memblock_type *type,
|
|
|
|
phys_addr_t base, phys_addr_t size)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-08-04 11:34:42 +08:00
|
|
|
phys_addr_t end = base + size;
|
2010-07-12 12:36:09 +08:00
|
|
|
int i;
|
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
/* Walk through the array for collisions */
|
|
|
|
for (i = 0; i < type->cnt; i++) {
|
|
|
|
struct memblock_region *rgn = &type->regions[i];
|
|
|
|
phys_addr_t rend = rgn->base + rgn->size;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
/* Nothing more to do, exit */
|
|
|
|
if (rgn->base > end || rgn->size == 0)
|
2010-07-12 12:36:09 +08:00
|
|
|
break;
|
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
/* If we fully enclose the block, drop it */
|
|
|
|
if (base <= rgn->base && end >= rend) {
|
|
|
|
memblock_remove_region(type, i--);
|
|
|
|
continue;
|
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
/* If we are fully enclosed within a block
|
|
|
|
* then we need to split it and we are done
|
|
|
|
*/
|
|
|
|
if (base > rgn->base && end < rend) {
|
|
|
|
rgn->size = base - rgn->base;
|
|
|
|
if (!memblock_add_region(type, end, rend - end))
|
|
|
|
return 0;
|
|
|
|
/* Failure to split is bad, we at least
|
|
|
|
* restore the block before erroring
|
|
|
|
*/
|
|
|
|
rgn->size = rend - rgn->base;
|
|
|
|
WARN_ON(1);
|
|
|
|
return -1;
|
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
/* Check if we need to trim the bottom of a block */
|
|
|
|
if (rgn->base < end && rend > end) {
|
|
|
|
rgn->size -= end - rgn->base;
|
|
|
|
rgn->base = end;
|
|
|
|
break;
|
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
/* And check if we need to trim the top of a block */
|
|
|
|
if (base < rend)
|
|
|
|
rgn->size -= rend - base;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
mm/memblock: properly handle overlaps and fix error path
Currently memblock_reserve() or memblock_free() don't handle overlaps of
any kind. There is some special casing for coalescing exactly adjacent
regions but that's about it.
This is annoying because typically memblock_reserve() is used to mark
regions passed by the firmware as reserved and we all know how much we can
trust our firmwares...
Also, with the current code, if we do something it doesn't handle right
such as trying to memblock_reserve() a large range spanning multiple
existing smaller reserved regions for example, or doing overlapping
reservations, it can silently corrupt the internal region array, causing
odd errors much later on, such as allocations returning reserved regions
etc...
This patch rewrites the underlying functions that add or remove a region
to the arrays. The new code is a lot more robust as it fully handles
overlapping regions. It's also, imho, simpler than the previous
implementation.
In addition, while doing so, I found a bug where if we fail to double the
array while adding a region, we would remove the last region of the array
rather than the region we just allocated. This fixes it too.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: Yinghai Lu <yinghai@kernel.org>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-03-23 07:33:43 +08:00
|
|
|
}
|
|
|
|
return 0;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2011-12-09 02:22:06 +08:00
|
|
|
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
|
|
|
return __memblock_remove(&memblock.memory, base, size);
|
|
|
|
}
|
|
|
|
|
2011-12-09 02:22:06 +08:00
|
|
|
int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2011-07-12 17:16:06 +08:00
|
|
|
memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n",
|
2011-07-15 02:57:10 +08:00
|
|
|
(unsigned long long)base,
|
|
|
|
(unsigned long long)base + size,
|
|
|
|
(void *)_RET_IP_);
|
2011-07-12 17:16:06 +08:00
|
|
|
|
2010-07-12 12:36:09 +08:00
|
|
|
return __memblock_remove(&memblock.reserved, base, size);
|
|
|
|
}
|
|
|
|
|
2011-12-09 02:22:06 +08:00
|
|
|
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-08-04 12:06:41 +08:00
|
|
|
struct memblock_type *_rgn = &memblock.reserved;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 17:16:06 +08:00
|
|
|
memblock_dbg("memblock_reserve: [%#016llx-%#016llx] %pF\n",
|
2011-07-15 02:57:10 +08:00
|
|
|
(unsigned long long)base,
|
|
|
|
(unsigned long long)base + size,
|
|
|
|
(void *)_RET_IP_);
|
2010-07-12 12:36:09 +08:00
|
|
|
BUG_ON(0 == size);
|
|
|
|
|
|
|
|
return memblock_add_region(_rgn, base, size);
|
|
|
|
}
|
|
|
|
|
2011-07-12 17:15:59 +08:00
|
|
|
/**
|
|
|
|
* __next_free_mem_range - next function for for_each_free_mem_range()
|
|
|
|
* @idx: pointer to u64 loop variable
|
|
|
|
* @nid: nid: node selector, %MAX_NUMNODES for all nodes
|
|
|
|
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
|
|
|
|
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
|
|
|
|
* @p_nid: ptr to int for nid of the range, can be %NULL
|
|
|
|
*
|
|
|
|
* Find the first free 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 memory region and the upper 32bit indexes the
|
|
|
|
* areas before each reserved region. For example, if reserved 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_free_mem_range(u64 *idx, int nid,
|
|
|
|
phys_addr_t *out_start,
|
|
|
|
phys_addr_t *out_end, int *out_nid)
|
|
|
|
{
|
|
|
|
struct memblock_type *mem = &memblock.memory;
|
|
|
|
struct memblock_type *rsv = &memblock.reserved;
|
|
|
|
int mi = *idx & 0xffffffff;
|
|
|
|
int ri = *idx >> 32;
|
|
|
|
|
|
|
|
for ( ; mi < mem->cnt; mi++) {
|
|
|
|
struct memblock_region *m = &mem->regions[mi];
|
|
|
|
phys_addr_t m_start = m->base;
|
|
|
|
phys_addr_t m_end = m->base + m->size;
|
|
|
|
|
|
|
|
/* only memory regions are associated with nodes, check it */
|
|
|
|
if (nid != MAX_NUMNODES && nid != memblock_get_region_node(m))
|
|
|
|
continue;
|
|
|
|
|
|
|
|
/* scan areas before each reservation for intersection */
|
|
|
|
for ( ; ri < rsv->cnt + 1; ri++) {
|
|
|
|
struct memblock_region *r = &rsv->regions[ri];
|
|
|
|
phys_addr_t r_start = ri ? r[-1].base + r[-1].size : 0;
|
|
|
|
phys_addr_t r_end = ri < rsv->cnt ? r->base : ULLONG_MAX;
|
|
|
|
|
|
|
|
/* if ri advanced past mi, break out to advance mi */
|
|
|
|
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 = memblock_get_region_node(m);
|
|
|
|
/*
|
|
|
|
* The region which ends first is advanced
|
|
|
|
* for the next iteration.
|
|
|
|
*/
|
|
|
|
if (m_end <= r_end)
|
|
|
|
mi++;
|
|
|
|
else
|
|
|
|
ri++;
|
|
|
|
*idx = (u32)mi | (u64)ri << 32;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
/* signal end of iteration */
|
|
|
|
*idx = ULLONG_MAX;
|
|
|
|
}
|
|
|
|
|
2011-07-14 17:43:42 +08:00
|
|
|
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
|
|
|
|
/*
|
|
|
|
* Common iterator interface used to define for_each_mem_range().
|
|
|
|
*/
|
|
|
|
void __init_memblock __next_mem_pfn_range(int *idx, int nid,
|
|
|
|
unsigned long *out_start_pfn,
|
|
|
|
unsigned long *out_end_pfn, int *out_nid)
|
|
|
|
{
|
|
|
|
struct memblock_type *type = &memblock.memory;
|
|
|
|
struct memblock_region *r;
|
|
|
|
|
|
|
|
while (++*idx < type->cnt) {
|
|
|
|
r = &type->regions[*idx];
|
|
|
|
|
|
|
|
if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size))
|
|
|
|
continue;
|
|
|
|
if (nid == MAX_NUMNODES || nid == r->nid)
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
if (*idx >= type->cnt) {
|
|
|
|
*idx = -1;
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (out_start_pfn)
|
|
|
|
*out_start_pfn = PFN_UP(r->base);
|
|
|
|
if (out_end_pfn)
|
|
|
|
*out_end_pfn = PFN_DOWN(r->base + r->size);
|
|
|
|
if (out_nid)
|
|
|
|
*out_nid = r->nid;
|
|
|
|
}
|
|
|
|
|
|
|
|
/**
|
|
|
|
* memblock_set_node - set node ID on memblock regions
|
|
|
|
* @base: base of area to set node ID for
|
|
|
|
* @size: size of area to set node ID for
|
|
|
|
* @nid: node ID to set
|
|
|
|
*
|
|
|
|
* Set the nid of memblock memory regions in [@base,@base+@size) to @nid.
|
|
|
|
* Regions which cross the area boundaries are split as necessary.
|
|
|
|
*
|
|
|
|
* RETURNS:
|
|
|
|
* 0 on success, -errno on failure.
|
|
|
|
*/
|
|
|
|
int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
|
|
|
|
int nid)
|
|
|
|
{
|
|
|
|
struct memblock_type *type = &memblock.memory;
|
|
|
|
phys_addr_t end = base + size;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
/* we'll create at most two more regions */
|
|
|
|
while (type->cnt + 2 > type->max)
|
|
|
|
if (memblock_double_array(type) < 0)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
for (i = 0; i < type->cnt; i++) {
|
|
|
|
struct memblock_region *rgn = &type->regions[i];
|
|
|
|
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 = rend - rgn->base;
|
|
|
|
memblock_insert_region(type, i, rbase, base - rbase,
|
|
|
|
rgn->nid);
|
|
|
|
} else if (rend > end) {
|
|
|
|
/*
|
|
|
|
* @rgn intersects from above. Split and redo the
|
|
|
|
* current region - the new bottom half.
|
|
|
|
*/
|
|
|
|
rgn->base = end;
|
|
|
|
rgn->size = rend - rgn->base;
|
|
|
|
memblock_insert_region(type, i--, rbase, end - rbase,
|
|
|
|
rgn->nid);
|
|
|
|
} else {
|
|
|
|
/* @rgn is fully contained, set ->nid */
|
|
|
|
rgn->nid = nid;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
memblock_merge_regions(type);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
|
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-07-12 12:36:48 +08:00
|
|
|
phys_addr_t found;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
/* We align the size to limit fragmentation. Without this, a lot of
|
|
|
|
* small allocs quickly eat up the whole reserve array on sparc
|
|
|
|
*/
|
2011-07-12 15:58:08 +08:00
|
|
|
size = round_up(size, align);
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 15:58:10 +08:00
|
|
|
found = memblock_find_in_range(0, max_addr, size, align);
|
2011-12-09 02:22:06 +08:00
|
|
|
if (found && !memblock_reserve(found, size))
|
2010-07-12 12:36:48 +08:00
|
|
|
return found;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
return 0;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-07-12 12:36:48 +08:00
|
|
|
phys_addr_t alloc;
|
|
|
|
|
|
|
|
alloc = __memblock_alloc_base(size, align, max_addr);
|
|
|
|
|
|
|
|
if (alloc == 0)
|
|
|
|
panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
|
|
|
|
(unsigned long long) size, (unsigned long long) max_addr);
|
|
|
|
|
|
|
|
return alloc;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-07-12 12:36:48 +08:00
|
|
|
return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
|
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
|
|
|
|
|
2010-07-12 12:36:48 +08:00
|
|
|
/*
|
2011-07-12 16:46:33 +08:00
|
|
|
* Additional node-local top-down allocators.
|
2010-07-07 06:39:16 +08:00
|
|
|
*
|
|
|
|
* WARNING: Only available after early_node_map[] has been populated,
|
|
|
|
* on some architectures, that is after all the calls to add_active_range()
|
|
|
|
* have been done to populate it.
|
2010-07-12 12:36:48 +08:00
|
|
|
*/
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 16:46:33 +08:00
|
|
|
static phys_addr_t __init memblock_nid_range_rev(phys_addr_t start,
|
|
|
|
phys_addr_t end, int *nid)
|
2010-07-07 06:38:59 +08:00
|
|
|
{
|
2010-07-07 06:39:16 +08:00
|
|
|
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
|
|
|
|
unsigned long start_pfn, end_pfn;
|
|
|
|
int i;
|
|
|
|
|
2011-07-12 16:46:31 +08:00
|
|
|
for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, nid)
|
2011-07-12 16:46:33 +08:00
|
|
|
if (end > PFN_PHYS(start_pfn) && end <= PFN_PHYS(end_pfn))
|
|
|
|
return max(start, PFN_PHYS(start_pfn));
|
2010-07-07 06:39:16 +08:00
|
|
|
#endif
|
2010-07-07 06:38:59 +08:00
|
|
|
*nid = 0;
|
2011-07-12 16:46:33 +08:00
|
|
|
return start;
|
2010-07-07 06:38:59 +08:00
|
|
|
}
|
|
|
|
|
2011-07-12 16:46:34 +08:00
|
|
|
phys_addr_t __init memblock_find_in_range_node(phys_addr_t start,
|
|
|
|
phys_addr_t end,
|
2010-08-04 11:34:42 +08:00
|
|
|
phys_addr_t size,
|
|
|
|
phys_addr_t align, int nid)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2011-07-12 16:46:34 +08:00
|
|
|
struct memblock_type *mem = &memblock.memory;
|
|
|
|
int i;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 16:46:34 +08:00
|
|
|
BUG_ON(0 == size);
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 16:46:34 +08:00
|
|
|
/* Pump up max_addr */
|
|
|
|
if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
|
|
|
|
end = memblock.current_limit;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 16:46:34 +08:00
|
|
|
for (i = mem->cnt - 1; i >= 0; i--) {
|
|
|
|
struct memblock_region *r = &mem->regions[i];
|
|
|
|
phys_addr_t base = max(start, r->base);
|
|
|
|
phys_addr_t top = min(end, r->base + r->size);
|
|
|
|
|
|
|
|
while (base < top) {
|
|
|
|
phys_addr_t tbase, ret;
|
|
|
|
int tnid;
|
|
|
|
|
|
|
|
tbase = memblock_nid_range_rev(base, top, &tnid);
|
|
|
|
if (nid == MAX_NUMNODES || tnid == nid) {
|
|
|
|
ret = memblock_find_region(tbase, top, size, align);
|
|
|
|
if (ret)
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
top = tbase;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
}
|
2011-07-12 16:46:34 +08:00
|
|
|
|
2011-07-12 15:58:09 +08:00
|
|
|
return 0;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2010-08-04 11:34:42 +08:00
|
|
|
phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2011-07-12 16:46:34 +08:00
|
|
|
phys_addr_t found;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2011-07-12 16:46:34 +08:00
|
|
|
/*
|
|
|
|
* We align the size to limit fragmentation. Without this, a lot of
|
2010-07-12 12:24:57 +08:00
|
|
|
* small allocs quickly eat up the whole reserve array on sparc
|
|
|
|
*/
|
2011-07-12 15:58:08 +08:00
|
|
|
size = round_up(size, align);
|
2010-07-12 12:24:57 +08:00
|
|
|
|
2011-07-12 16:46:34 +08:00
|
|
|
found = memblock_find_in_range_node(0, MEMBLOCK_ALLOC_ACCESSIBLE,
|
|
|
|
size, align, nid);
|
2011-12-09 02:22:06 +08:00
|
|
|
if (found && !memblock_reserve(found, size))
|
2011-07-12 16:46:34 +08:00
|
|
|
return found;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2010-07-07 06:39:17 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
|
|
|
|
{
|
|
|
|
phys_addr_t res = memblock_alloc_nid(size, align, nid);
|
|
|
|
|
|
|
|
if (res)
|
|
|
|
return res;
|
2011-07-12 15:58:07 +08:00
|
|
|
return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2010-07-07 06:39:17 +08:00
|
|
|
|
|
|
|
/*
|
|
|
|
* Remaining API functions
|
|
|
|
*/
|
|
|
|
|
2010-07-12 12:36:09 +08:00
|
|
|
/* You must call memblock_analyze() before this. */
|
2010-08-04 11:34:42 +08:00
|
|
|
phys_addr_t __init memblock_phys_mem_size(void)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-07-28 12:31:29 +08:00
|
|
|
return memblock.memory_size;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2011-11-01 08:08:16 +08:00
|
|
|
/* lowest address */
|
|
|
|
phys_addr_t __init_memblock memblock_start_of_DRAM(void)
|
|
|
|
{
|
|
|
|
return memblock.memory.regions[0].base;
|
|
|
|
}
|
|
|
|
|
2010-07-28 13:43:02 +08:00
|
|
|
phys_addr_t __init_memblock memblock_end_of_DRAM(void)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
|
|
|
int idx = memblock.memory.cnt - 1;
|
|
|
|
|
2010-08-04 12:06:41 +08:00
|
|
|
return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/* You must call memblock_analyze() after this. */
|
2010-08-04 11:34:42 +08:00
|
|
|
void __init memblock_enforce_memory_limit(phys_addr_t memory_limit)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
|
|
|
unsigned long i;
|
2010-08-04 11:34:42 +08:00
|
|
|
phys_addr_t limit;
|
2010-08-04 12:06:41 +08:00
|
|
|
struct memblock_region *p;
|
2010-07-12 12:36:09 +08:00
|
|
|
|
|
|
|
if (!memory_limit)
|
|
|
|
return;
|
|
|
|
|
|
|
|
/* Truncate the memblock regions to satisfy the memory limit. */
|
|
|
|
limit = memory_limit;
|
|
|
|
for (i = 0; i < memblock.memory.cnt; i++) {
|
2010-08-04 12:06:41 +08:00
|
|
|
if (limit > memblock.memory.regions[i].size) {
|
|
|
|
limit -= memblock.memory.regions[i].size;
|
2010-07-12 12:36:09 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2010-08-04 12:06:41 +08:00
|
|
|
memblock.memory.regions[i].size = limit;
|
2010-07-12 12:36:09 +08:00
|
|
|
memblock.memory.cnt = i + 1;
|
|
|
|
break;
|
|
|
|
}
|
|
|
|
|
|
|
|
memory_limit = memblock_end_of_DRAM();
|
|
|
|
|
|
|
|
/* And truncate any reserves above the limit also. */
|
|
|
|
for (i = 0; i < memblock.reserved.cnt; i++) {
|
2010-08-04 12:06:41 +08:00
|
|
|
p = &memblock.reserved.regions[i];
|
2010-07-12 12:36:09 +08:00
|
|
|
|
|
|
|
if (p->base > memory_limit)
|
|
|
|
p->size = 0;
|
|
|
|
else if ((p->base + p->size) > memory_limit)
|
|
|
|
p->size = memory_limit - p->base;
|
|
|
|
|
|
|
|
if (p->size == 0) {
|
|
|
|
memblock_remove_region(&memblock.reserved, i);
|
|
|
|
i--;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2010-10-12 03:34:09 +08:00
|
|
|
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
|
2010-08-04 12:38:47 +08:00
|
|
|
{
|
|
|
|
unsigned int left = 0, right = type->cnt;
|
|
|
|
|
|
|
|
do {
|
|
|
|
unsigned int mid = (right + left) / 2;
|
|
|
|
|
|
|
|
if (addr < type->regions[mid].base)
|
|
|
|
right = mid;
|
|
|
|
else if (addr >= (type->regions[mid].base +
|
|
|
|
type->regions[mid].size))
|
|
|
|
left = mid + 1;
|
|
|
|
else
|
|
|
|
return mid;
|
|
|
|
} while (left < right);
|
|
|
|
return -1;
|
|
|
|
}
|
|
|
|
|
2010-08-04 11:34:42 +08:00
|
|
|
int __init memblock_is_reserved(phys_addr_t addr)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-08-04 12:38:47 +08:00
|
|
|
return memblock_search(&memblock.reserved, addr) != -1;
|
|
|
|
}
|
2010-07-12 12:36:09 +08:00
|
|
|
|
2010-09-16 04:05:29 +08:00
|
|
|
int __init_memblock memblock_is_memory(phys_addr_t addr)
|
2010-08-04 12:38:47 +08:00
|
|
|
{
|
|
|
|
return memblock_search(&memblock.memory, addr) != -1;
|
|
|
|
}
|
|
|
|
|
2010-09-16 04:05:29 +08:00
|
|
|
int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
|
2010-08-04 12:38:47 +08:00
|
|
|
{
|
2011-01-21 06:44:20 +08:00
|
|
|
int idx = memblock_search(&memblock.memory, base);
|
2010-08-04 12:38:47 +08:00
|
|
|
|
|
|
|
if (idx == -1)
|
|
|
|
return 0;
|
2011-01-21 06:44:20 +08:00
|
|
|
return memblock.memory.regions[idx].base <= base &&
|
|
|
|
(memblock.memory.regions[idx].base +
|
|
|
|
memblock.memory.regions[idx].size) >= (base + size);
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2010-07-28 13:43:02 +08:00
|
|
|
int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
|
2010-07-12 12:36:09 +08:00
|
|
|
{
|
2010-08-04 12:17:17 +08:00
|
|
|
return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
|
2010-07-12 12:36:09 +08:00
|
|
|
}
|
|
|
|
|
2010-07-07 06:39:01 +08:00
|
|
|
|
2010-09-16 04:05:29 +08:00
|
|
|
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
|
2010-07-07 06:39:01 +08:00
|
|
|
{
|
|
|
|
memblock.current_limit = limit;
|
|
|
|
}
|
|
|
|
|
2011-07-14 17:43:42 +08:00
|
|
|
static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
|
2010-07-12 12:36:48 +08:00
|
|
|
{
|
|
|
|
unsigned long long base, size;
|
|
|
|
int i;
|
|
|
|
|
2011-07-14 17:43:42 +08:00
|
|
|
pr_info(" %s.cnt = 0x%lx\n", name, type->cnt);
|
2010-07-12 12:36:48 +08:00
|
|
|
|
2011-07-14 17:43:42 +08:00
|
|
|
for (i = 0; i < type->cnt; i++) {
|
|
|
|
struct memblock_region *rgn = &type->regions[i];
|
|
|
|
char nid_buf[32] = "";
|
|
|
|
|
|
|
|
base = rgn->base;
|
|
|
|
size = rgn->size;
|
|
|
|
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
|
|
|
|
if (memblock_get_region_node(rgn) != MAX_NUMNODES)
|
|
|
|
snprintf(nid_buf, sizeof(nid_buf), " on node %d",
|
|
|
|
memblock_get_region_node(rgn));
|
|
|
|
#endif
|
|
|
|
pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s\n",
|
|
|
|
name, i, base, base + size - 1, size, nid_buf);
|
2010-07-12 12:36:48 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2011-12-09 02:22:06 +08:00
|
|
|
void __init_memblock __memblock_dump_all(void)
|
2010-07-12 12:36:48 +08:00
|
|
|
{
|
|
|
|
pr_info("MEMBLOCK configuration:\n");
|
|
|
|
pr_info(" memory size = 0x%llx\n", (unsigned long long)memblock.memory_size);
|
|
|
|
|
|
|
|
memblock_dump(&memblock.memory, "memory");
|
|
|
|
memblock_dump(&memblock.reserved, "reserved");
|
|
|
|
}
|
|
|
|
|
|
|
|
void __init memblock_analyze(void)
|
|
|
|
{
|
|
|
|
int i;
|
|
|
|
|
|
|
|
memblock.memory_size = 0;
|
|
|
|
|
|
|
|
for (i = 0; i < memblock.memory.cnt; i++)
|
|
|
|
memblock.memory_size += memblock.memory.regions[i].size;
|
2010-07-07 06:39:13 +08:00
|
|
|
|
|
|
|
/* We allow resizing from there */
|
|
|
|
memblock_can_resize = 1;
|
2010-07-12 12:36:48 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static int __init early_memblock(char *p)
|
|
|
|
{
|
|
|
|
if (p && strstr(p, "debug"))
|
|
|
|
memblock_debug = 1;
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
early_param("memblock", early_memblock);
|
|
|
|
|
2011-07-14 17:46:03 +08:00
|
|
|
#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK)
|
2010-07-07 06:39:19 +08:00
|
|
|
|
|
|
|
static int memblock_debug_show(struct seq_file *m, void *private)
|
|
|
|
{
|
|
|
|
struct memblock_type *type = m->private;
|
|
|
|
struct memblock_region *reg;
|
|
|
|
int i;
|
|
|
|
|
|
|
|
for (i = 0; i < type->cnt; i++) {
|
|
|
|
reg = &type->regions[i];
|
|
|
|
seq_printf(m, "%4d: ", i);
|
|
|
|
if (sizeof(phys_addr_t) == 4)
|
|
|
|
seq_printf(m, "0x%08lx..0x%08lx\n",
|
|
|
|
(unsigned long)reg->base,
|
|
|
|
(unsigned long)(reg->base + reg->size - 1));
|
|
|
|
else
|
|
|
|
seq_printf(m, "0x%016llx..0x%016llx\n",
|
|
|
|
(unsigned long long)reg->base,
|
|
|
|
(unsigned long long)(reg->base + reg->size - 1));
|
|
|
|
|
|
|
|
}
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int memblock_debug_open(struct inode *inode, struct file *file)
|
|
|
|
{
|
|
|
|
return single_open(file, memblock_debug_show, inode->i_private);
|
|
|
|
}
|
|
|
|
|
|
|
|
static const struct file_operations memblock_debug_fops = {
|
|
|
|
.open = memblock_debug_open,
|
|
|
|
.read = seq_read,
|
|
|
|
.llseek = seq_lseek,
|
|
|
|
.release = single_release,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int __init memblock_init_debugfs(void)
|
|
|
|
{
|
|
|
|
struct dentry *root = debugfs_create_dir("memblock", NULL);
|
|
|
|
if (!root)
|
|
|
|
return -ENXIO;
|
|
|
|
debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
|
|
|
|
debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
__initcall(memblock_init_debugfs);
|
|
|
|
|
|
|
|
#endif /* CONFIG_DEBUG_FS */
|