![Andy Whitcroft](/assets/img/avatar_default.png)
Sparsemem abstracts the use of discontiguous mem_maps[]. This kind of mem_map[] is needed by discontiguous memory machines (like in the old CONFIG_DISCONTIGMEM case) as well as memory hotplug systems. Sparsemem replaces DISCONTIGMEM when enabled, and it is hoped that it can eventually become a complete replacement. A significant advantage over DISCONTIGMEM is that it's completely separated from CONFIG_NUMA. When producing this patch, it became apparent in that NUMA and DISCONTIG are often confused. Another advantage is that sparse doesn't require each NUMA node's ranges to be contiguous. It can handle overlapping ranges between nodes with no problems, where DISCONTIGMEM currently throws away that memory. Sparsemem uses an array to provide different pfn_to_page() translations for each SECTION_SIZE area of physical memory. This is what allows the mem_map[] to be chopped up. In order to do quick pfn_to_page() operations, the section number of the page is encoded in page->flags. Part of the sparsemem infrastructure enables sharing of these bits more dynamically (at compile-time) between the page_zone() and sparsemem operations. However, on 32-bit architectures, the number of bits is quite limited, and may require growing the size of the page->flags type in certain conditions. Several things might force this to occur: a decrease in the SECTION_SIZE (if you want to hotplug smaller areas of memory), an increase in the physical address space, or an increase in the number of used page->flags. One thing to note is that, once sparsemem is present, the NUMA node information no longer needs to be stored in the page->flags. It might provide speed increases on certain platforms and will be stored there if there is room. But, if out of room, an alternate (theoretically slower) mechanism is used. This patch introduces CONFIG_FLATMEM. It is used in almost all cases where there used to be an #ifndef DISCONTIG, because SPARSEMEM and DISCONTIGMEM often have to compile out the same areas of code. Signed-off-by: Andy Whitcroft <apw@shadowen.org> Signed-off-by: Dave Hansen <haveblue@us.ibm.com> Signed-off-by: Martin Bligh <mbligh@aracnet.com> Signed-off-by: Adrian Bunk <bunk@stusta.de> Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com> Signed-off-by: Bob Picco <bob.picco@hp.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
406 lines
11 KiB
C
406 lines
11 KiB
C
/*
|
|
* linux/mm/bootmem.c
|
|
*
|
|
* Copyright (C) 1999 Ingo Molnar
|
|
* Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999
|
|
*
|
|
* simple boot-time physical memory area allocator and
|
|
* free memory collector. It's used to deal with reserved
|
|
* system memory and memory holes as well.
|
|
*/
|
|
|
|
#include <linux/mm.h>
|
|
#include <linux/kernel_stat.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/interrupt.h>
|
|
#include <linux/init.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/mmzone.h>
|
|
#include <linux/module.h>
|
|
#include <asm/dma.h>
|
|
#include <asm/io.h>
|
|
#include "internal.h"
|
|
|
|
/*
|
|
* Access to this subsystem has to be serialized externally. (this is
|
|
* true for the boot process anyway)
|
|
*/
|
|
unsigned long max_low_pfn;
|
|
unsigned long min_low_pfn;
|
|
unsigned long max_pfn;
|
|
|
|
EXPORT_SYMBOL(max_pfn); /* This is exported so
|
|
* dma_get_required_mask(), which uses
|
|
* it, can be an inline function */
|
|
|
|
/* return the number of _pages_ that will be allocated for the boot bitmap */
|
|
unsigned long __init bootmem_bootmap_pages (unsigned long pages)
|
|
{
|
|
unsigned long mapsize;
|
|
|
|
mapsize = (pages+7)/8;
|
|
mapsize = (mapsize + ~PAGE_MASK) & PAGE_MASK;
|
|
mapsize >>= PAGE_SHIFT;
|
|
|
|
return mapsize;
|
|
}
|
|
|
|
/*
|
|
* Called once to set up the allocator itself.
|
|
*/
|
|
static unsigned long __init init_bootmem_core (pg_data_t *pgdat,
|
|
unsigned long mapstart, unsigned long start, unsigned long end)
|
|
{
|
|
bootmem_data_t *bdata = pgdat->bdata;
|
|
unsigned long mapsize = ((end - start)+7)/8;
|
|
|
|
pgdat->pgdat_next = pgdat_list;
|
|
pgdat_list = pgdat;
|
|
|
|
mapsize = (mapsize + (sizeof(long) - 1UL)) & ~(sizeof(long) - 1UL);
|
|
bdata->node_bootmem_map = phys_to_virt(mapstart << PAGE_SHIFT);
|
|
bdata->node_boot_start = (start << PAGE_SHIFT);
|
|
bdata->node_low_pfn = end;
|
|
|
|
/*
|
|
* Initially all pages are reserved - setup_arch() has to
|
|
* register free RAM areas explicitly.
|
|
*/
|
|
memset(bdata->node_bootmem_map, 0xff, mapsize);
|
|
|
|
return mapsize;
|
|
}
|
|
|
|
/*
|
|
* Marks a particular physical memory range as unallocatable. Usable RAM
|
|
* might be used for boot-time allocations - or it might get added
|
|
* to the free page pool later on.
|
|
*/
|
|
static void __init reserve_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
|
|
{
|
|
unsigned long i;
|
|
/*
|
|
* round up, partially reserved pages are considered
|
|
* fully reserved.
|
|
*/
|
|
unsigned long sidx = (addr - bdata->node_boot_start)/PAGE_SIZE;
|
|
unsigned long eidx = (addr + size - bdata->node_boot_start +
|
|
PAGE_SIZE-1)/PAGE_SIZE;
|
|
unsigned long end = (addr + size + PAGE_SIZE-1)/PAGE_SIZE;
|
|
|
|
BUG_ON(!size);
|
|
BUG_ON(sidx >= eidx);
|
|
BUG_ON((addr >> PAGE_SHIFT) >= bdata->node_low_pfn);
|
|
BUG_ON(end > bdata->node_low_pfn);
|
|
|
|
for (i = sidx; i < eidx; i++)
|
|
if (test_and_set_bit(i, bdata->node_bootmem_map)) {
|
|
#ifdef CONFIG_DEBUG_BOOTMEM
|
|
printk("hm, page %08lx reserved twice.\n", i*PAGE_SIZE);
|
|
#endif
|
|
}
|
|
}
|
|
|
|
static void __init free_bootmem_core(bootmem_data_t *bdata, unsigned long addr, unsigned long size)
|
|
{
|
|
unsigned long i;
|
|
unsigned long start;
|
|
/*
|
|
* round down end of usable mem, partially free pages are
|
|
* considered reserved.
|
|
*/
|
|
unsigned long sidx;
|
|
unsigned long eidx = (addr + size - bdata->node_boot_start)/PAGE_SIZE;
|
|
unsigned long end = (addr + size)/PAGE_SIZE;
|
|
|
|
BUG_ON(!size);
|
|
BUG_ON(end > bdata->node_low_pfn);
|
|
|
|
if (addr < bdata->last_success)
|
|
bdata->last_success = addr;
|
|
|
|
/*
|
|
* Round up the beginning of the address.
|
|
*/
|
|
start = (addr + PAGE_SIZE-1) / PAGE_SIZE;
|
|
sidx = start - (bdata->node_boot_start/PAGE_SIZE);
|
|
|
|
for (i = sidx; i < eidx; i++) {
|
|
if (unlikely(!test_and_clear_bit(i, bdata->node_bootmem_map)))
|
|
BUG();
|
|
}
|
|
}
|
|
|
|
/*
|
|
* We 'merge' subsequent allocations to save space. We might 'lose'
|
|
* some fraction of a page if allocations cannot be satisfied due to
|
|
* size constraints on boxes where there is physical RAM space
|
|
* fragmentation - in these cases (mostly large memory boxes) this
|
|
* is not a problem.
|
|
*
|
|
* On low memory boxes we get it right in 100% of the cases.
|
|
*
|
|
* alignment has to be a power of 2 value.
|
|
*
|
|
* NOTE: This function is _not_ reentrant.
|
|
*/
|
|
static void * __init
|
|
__alloc_bootmem_core(struct bootmem_data *bdata, unsigned long size,
|
|
unsigned long align, unsigned long goal)
|
|
{
|
|
unsigned long offset, remaining_size, areasize, preferred;
|
|
unsigned long i, start = 0, incr, eidx;
|
|
void *ret;
|
|
|
|
if(!size) {
|
|
printk("__alloc_bootmem_core(): zero-sized request\n");
|
|
BUG();
|
|
}
|
|
BUG_ON(align & (align-1));
|
|
|
|
eidx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
|
|
offset = 0;
|
|
if (align &&
|
|
(bdata->node_boot_start & (align - 1UL)) != 0)
|
|
offset = (align - (bdata->node_boot_start & (align - 1UL)));
|
|
offset >>= PAGE_SHIFT;
|
|
|
|
/*
|
|
* We try to allocate bootmem pages above 'goal'
|
|
* first, then we try to allocate lower pages.
|
|
*/
|
|
if (goal && (goal >= bdata->node_boot_start) &&
|
|
((goal >> PAGE_SHIFT) < bdata->node_low_pfn)) {
|
|
preferred = goal - bdata->node_boot_start;
|
|
|
|
if (bdata->last_success >= preferred)
|
|
preferred = bdata->last_success;
|
|
} else
|
|
preferred = 0;
|
|
|
|
preferred = ((preferred + align - 1) & ~(align - 1)) >> PAGE_SHIFT;
|
|
preferred += offset;
|
|
areasize = (size+PAGE_SIZE-1)/PAGE_SIZE;
|
|
incr = align >> PAGE_SHIFT ? : 1;
|
|
|
|
restart_scan:
|
|
for (i = preferred; i < eidx; i += incr) {
|
|
unsigned long j;
|
|
i = find_next_zero_bit(bdata->node_bootmem_map, eidx, i);
|
|
i = ALIGN(i, incr);
|
|
if (test_bit(i, bdata->node_bootmem_map))
|
|
continue;
|
|
for (j = i + 1; j < i + areasize; ++j) {
|
|
if (j >= eidx)
|
|
goto fail_block;
|
|
if (test_bit (j, bdata->node_bootmem_map))
|
|
goto fail_block;
|
|
}
|
|
start = i;
|
|
goto found;
|
|
fail_block:
|
|
i = ALIGN(j, incr);
|
|
}
|
|
|
|
if (preferred > offset) {
|
|
preferred = offset;
|
|
goto restart_scan;
|
|
}
|
|
return NULL;
|
|
|
|
found:
|
|
bdata->last_success = start << PAGE_SHIFT;
|
|
BUG_ON(start >= eidx);
|
|
|
|
/*
|
|
* Is the next page of the previous allocation-end the start
|
|
* of this allocation's buffer? If yes then we can 'merge'
|
|
* the previous partial page with this allocation.
|
|
*/
|
|
if (align < PAGE_SIZE &&
|
|
bdata->last_offset && bdata->last_pos+1 == start) {
|
|
offset = (bdata->last_offset+align-1) & ~(align-1);
|
|
BUG_ON(offset > PAGE_SIZE);
|
|
remaining_size = PAGE_SIZE-offset;
|
|
if (size < remaining_size) {
|
|
areasize = 0;
|
|
/* last_pos unchanged */
|
|
bdata->last_offset = offset+size;
|
|
ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
|
|
bdata->node_boot_start);
|
|
} else {
|
|
remaining_size = size - remaining_size;
|
|
areasize = (remaining_size+PAGE_SIZE-1)/PAGE_SIZE;
|
|
ret = phys_to_virt(bdata->last_pos*PAGE_SIZE + offset +
|
|
bdata->node_boot_start);
|
|
bdata->last_pos = start+areasize-1;
|
|
bdata->last_offset = remaining_size;
|
|
}
|
|
bdata->last_offset &= ~PAGE_MASK;
|
|
} else {
|
|
bdata->last_pos = start + areasize - 1;
|
|
bdata->last_offset = size & ~PAGE_MASK;
|
|
ret = phys_to_virt(start * PAGE_SIZE + bdata->node_boot_start);
|
|
}
|
|
|
|
/*
|
|
* Reserve the area now:
|
|
*/
|
|
for (i = start; i < start+areasize; i++)
|
|
if (unlikely(test_and_set_bit(i, bdata->node_bootmem_map)))
|
|
BUG();
|
|
memset(ret, 0, size);
|
|
return ret;
|
|
}
|
|
|
|
static unsigned long __init free_all_bootmem_core(pg_data_t *pgdat)
|
|
{
|
|
struct page *page;
|
|
unsigned long pfn;
|
|
bootmem_data_t *bdata = pgdat->bdata;
|
|
unsigned long i, count, total = 0;
|
|
unsigned long idx;
|
|
unsigned long *map;
|
|
int gofast = 0;
|
|
|
|
BUG_ON(!bdata->node_bootmem_map);
|
|
|
|
count = 0;
|
|
/* first extant page of the node */
|
|
pfn = bdata->node_boot_start >> PAGE_SHIFT;
|
|
idx = bdata->node_low_pfn - (bdata->node_boot_start >> PAGE_SHIFT);
|
|
map = bdata->node_bootmem_map;
|
|
/* Check physaddr is O(LOG2(BITS_PER_LONG)) page aligned */
|
|
if (bdata->node_boot_start == 0 ||
|
|
ffs(bdata->node_boot_start) - PAGE_SHIFT > ffs(BITS_PER_LONG))
|
|
gofast = 1;
|
|
for (i = 0; i < idx; ) {
|
|
unsigned long v = ~map[i / BITS_PER_LONG];
|
|
|
|
if (gofast && v == ~0UL) {
|
|
int j, order;
|
|
|
|
page = pfn_to_page(pfn);
|
|
count += BITS_PER_LONG;
|
|
__ClearPageReserved(page);
|
|
order = ffs(BITS_PER_LONG) - 1;
|
|
set_page_refs(page, order);
|
|
for (j = 1; j < BITS_PER_LONG; j++) {
|
|
if (j + 16 < BITS_PER_LONG)
|
|
prefetchw(page + j + 16);
|
|
__ClearPageReserved(page + j);
|
|
}
|
|
__free_pages(page, order);
|
|
i += BITS_PER_LONG;
|
|
page += BITS_PER_LONG;
|
|
} else if (v) {
|
|
unsigned long m;
|
|
|
|
page = pfn_to_page(pfn);
|
|
for (m = 1; m && i < idx; m<<=1, page++, i++) {
|
|
if (v & m) {
|
|
count++;
|
|
__ClearPageReserved(page);
|
|
set_page_refs(page, 0);
|
|
__free_page(page);
|
|
}
|
|
}
|
|
} else {
|
|
i+=BITS_PER_LONG;
|
|
}
|
|
pfn += BITS_PER_LONG;
|
|
}
|
|
total += count;
|
|
|
|
/*
|
|
* Now free the allocator bitmap itself, it's not
|
|
* needed anymore:
|
|
*/
|
|
page = virt_to_page(bdata->node_bootmem_map);
|
|
count = 0;
|
|
for (i = 0; i < ((bdata->node_low_pfn-(bdata->node_boot_start >> PAGE_SHIFT))/8 + PAGE_SIZE-1)/PAGE_SIZE; i++,page++) {
|
|
count++;
|
|
__ClearPageReserved(page);
|
|
set_page_count(page, 1);
|
|
__free_page(page);
|
|
}
|
|
total += count;
|
|
bdata->node_bootmem_map = NULL;
|
|
|
|
return total;
|
|
}
|
|
|
|
unsigned long __init init_bootmem_node (pg_data_t *pgdat, unsigned long freepfn, unsigned long startpfn, unsigned long endpfn)
|
|
{
|
|
return(init_bootmem_core(pgdat, freepfn, startpfn, endpfn));
|
|
}
|
|
|
|
void __init reserve_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
|
|
{
|
|
reserve_bootmem_core(pgdat->bdata, physaddr, size);
|
|
}
|
|
|
|
void __init free_bootmem_node (pg_data_t *pgdat, unsigned long physaddr, unsigned long size)
|
|
{
|
|
free_bootmem_core(pgdat->bdata, physaddr, size);
|
|
}
|
|
|
|
unsigned long __init free_all_bootmem_node (pg_data_t *pgdat)
|
|
{
|
|
return(free_all_bootmem_core(pgdat));
|
|
}
|
|
|
|
unsigned long __init init_bootmem (unsigned long start, unsigned long pages)
|
|
{
|
|
max_low_pfn = pages;
|
|
min_low_pfn = start;
|
|
return(init_bootmem_core(NODE_DATA(0), start, 0, pages));
|
|
}
|
|
|
|
#ifndef CONFIG_HAVE_ARCH_BOOTMEM_NODE
|
|
void __init reserve_bootmem (unsigned long addr, unsigned long size)
|
|
{
|
|
reserve_bootmem_core(NODE_DATA(0)->bdata, addr, size);
|
|
}
|
|
#endif /* !CONFIG_HAVE_ARCH_BOOTMEM_NODE */
|
|
|
|
void __init free_bootmem (unsigned long addr, unsigned long size)
|
|
{
|
|
free_bootmem_core(NODE_DATA(0)->bdata, addr, size);
|
|
}
|
|
|
|
unsigned long __init free_all_bootmem (void)
|
|
{
|
|
return(free_all_bootmem_core(NODE_DATA(0)));
|
|
}
|
|
|
|
void * __init __alloc_bootmem (unsigned long size, unsigned long align, unsigned long goal)
|
|
{
|
|
pg_data_t *pgdat = pgdat_list;
|
|
void *ptr;
|
|
|
|
for_each_pgdat(pgdat)
|
|
if ((ptr = __alloc_bootmem_core(pgdat->bdata, size,
|
|
align, goal)))
|
|
return(ptr);
|
|
|
|
/*
|
|
* Whoops, we cannot satisfy the allocation request.
|
|
*/
|
|
printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
|
|
panic("Out of memory");
|
|
return NULL;
|
|
}
|
|
|
|
void * __init __alloc_bootmem_node (pg_data_t *pgdat, unsigned long size, unsigned long align, unsigned long goal)
|
|
{
|
|
void *ptr;
|
|
|
|
ptr = __alloc_bootmem_core(pgdat->bdata, size, align, goal);
|
|
if (ptr)
|
|
return (ptr);
|
|
|
|
return __alloc_bootmem(size, align, goal);
|
|
}
|
|
|