linux/mm/bootmem.c

871 lines
21 KiB
C
Raw Normal View History

/*
* bootmem - A boot-time physical memory allocator and configurator
*
* Copyright (C) 1999 Ingo Molnar
* 1999 Kanoj Sarcar, SGI
* 2008 Johannes Weiner
*
* Access to this subsystem has to be serialized externally (which is true
* for the boot process anyway).
*/
#include <linux/init.h>
#include <linux/pfn.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/slab.h>
#include <linux/bootmem.h>
#include <linux/export.h>
#include <linux/kmemleak.h>
#include <linux/range.h>
x86: Use memblock to replace early_res 1. replace find_e820_area with memblock_find_in_range 2. replace reserve_early with memblock_x86_reserve_range 3. replace free_early with memblock_x86_free_range. 4. NO_BOOTMEM will switch to use memblock too. 5. use _e820, _early wrap in the patch, in following patch, will replace them all 6. because memblock_x86_free_range support partial free, we can remove some special care 7. Need to make sure that memblock_find_in_range() is called after memblock_x86_fill() so adjust some calling later in setup.c::setup_arch() -- corruption_check and mptable_update -v2: Move reserve_brk() early Before fill_memblock_area, to avoid overlap between brk and memblock_find_in_range() that could happen We have more then 128 RAM entry in E820 tables, and memblock_x86_fill() could use memblock_find_in_range() to find a new place for memblock.memory.region array. and We don't need to use extend_brk() after fill_memblock_area() So move reserve_brk() early before fill_memblock_area(). -v3: Move find_smp_config early To make sure memblock_find_in_range not find wrong place, if BIOS doesn't put mptable in right place. -v4: Treat RESERVED_KERN as RAM in memblock.memory. and they are already in memblock.reserved already.. use __NOT_KEEP_MEMBLOCK to make sure memblock related code could be freed later. -v5: Generic version __memblock_find_in_range() is going from high to low, and for 32bit active_region for 32bit does include high pages need to replace the limit with memblock.default_alloc_limit, aka get_max_mapped() -v6: Use current_limit instead -v7: check with MEMBLOCK_ERROR instead of -1ULL or -1L -v8: Set memblock_can_resize early to handle EFI with more RAM entries -v9: update after kmemleak changes in mainline Suggested-by: David S. Miller <davem@davemloft.net> Suggested-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Suggested-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Signed-off-by: H. Peter Anvin <hpa@zytor.com>
2010-08-26 04:39:17 +08:00
#include <linux/memblock.h>
#include <linux/bug.h>
#include <linux/io.h>
#include <asm/processor.h>
#include "internal.h"
#ifndef CONFIG_NEED_MULTIPLE_NODES
struct pglist_data __refdata contig_page_data = {
.bdata = &bootmem_node_data[0]
};
EXPORT_SYMBOL(contig_page_data);
#endif
unsigned long max_low_pfn;
unsigned long min_low_pfn;
unsigned long max_pfn;
unsigned long long max_possible_pfn;
bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata;
static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list);
static int bootmem_debug;
static int __init bootmem_debug_setup(char *buf)
{
bootmem_debug = 1;
return 0;
}
early_param("bootmem_debug", bootmem_debug_setup);
#define bdebug(fmt, args...) ({ \
if (unlikely(bootmem_debug)) \
printk(KERN_INFO \
"bootmem::%s " fmt, \
__func__, ## args); \
})
static unsigned long __init bootmap_bytes(unsigned long pages)
{
unsigned long bytes = DIV_ROUND_UP(pages, 8);
return ALIGN(bytes, sizeof(long));
}
/**
* bootmem_bootmap_pages - calculate bitmap size in pages
* @pages: number of pages the bitmap has to represent
*/
unsigned long __init bootmem_bootmap_pages(unsigned long pages)
{
unsigned long bytes = bootmap_bytes(pages);
return PAGE_ALIGN(bytes) >> PAGE_SHIFT;
}
/*
* link bdata in order
*/
static void __init link_bootmem(bootmem_data_t *bdata)
{
bootmem_data_t *ent;
list_for_each_entry(ent, &bdata_list, list) {
if (bdata->node_min_pfn < ent->node_min_pfn) {
list_add_tail(&bdata->list, &ent->list);
return;
}
}
list_add_tail(&bdata->list, &bdata_list);
}
/*
* Called once to set up the allocator itself.
*/
static unsigned long __init init_bootmem_core(bootmem_data_t *bdata,
unsigned long mapstart, unsigned long start, unsigned long end)
{
unsigned long mapsize;
mminit_validate_memmodel_limits(&start, &end);
bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart));
bdata->node_min_pfn = start;
bdata->node_low_pfn = end;
link_bootmem(bdata);
/*
* Initially all pages are reserved - setup_arch() has to
* register free RAM areas explicitly.
*/
mapsize = bootmap_bytes(end - start);
memset(bdata->node_bootmem_map, 0xff, mapsize);
bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n",
bdata - bootmem_node_data, start, mapstart, end, mapsize);
return mapsize;
}
/**
* init_bootmem_node - register a node as boot memory
* @pgdat: node to register
* @freepfn: pfn where the bitmap for this node is to be placed
* @startpfn: first pfn on the node
* @endpfn: first pfn after the node
*
* Returns the number of bytes needed to hold the bitmap for this node.
*/
unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn,
unsigned long startpfn, unsigned long endpfn)
{
return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn);
}
/**
* init_bootmem - register boot memory
* @start: pfn where the bitmap is to be placed
* @pages: number of available physical pages
*
* Returns the number of bytes needed to hold the bitmap.
*/
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)->bdata, start, 0, pages);
}
/*
* free_bootmem_late - free bootmem pages directly to page allocator
* @addr: starting physical address of the range
* @size: size of the range in bytes
*
* This is only useful when the bootmem allocator has already been torn
* down, but we are still initializing the system. Pages are given directly
* to the page allocator, no bootmem metadata is updated because it is gone.
*/
void __init free_bootmem_late(unsigned long physaddr, unsigned long size)
{
unsigned long cursor, end;
kmemleak_free_part(__va(physaddr), size);
cursor = PFN_UP(physaddr);
end = PFN_DOWN(physaddr + size);
for (; cursor < end; cursor++) {
__free_pages_bootmem(pfn_to_page(cursor), cursor, 0);
totalram_pages++;
}
}
static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata)
{
struct page *page;
unsigned long *map, start, end, pages, cur, count = 0;
if (!bdata->node_bootmem_map)
return 0;
map = bdata->node_bootmem_map;
start = bdata->node_min_pfn;
end = bdata->node_low_pfn;
bdebug("nid=%td start=%lx end=%lx\n",
bdata - bootmem_node_data, start, end);
while (start < end) {
unsigned long idx, vec;
mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment Currently free_all_bootmem_core ignores that node_min_pfn may be not multiple of BITS_PER_LONG. Eg commit 6dccdcbe2c3e ("mm: bootmem: fix checking the bitmap when finally freeing bootmem") shifts vec by lower bits of start instead of lower bits of idx. Also if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) assumes that vec bit 0 corresponds to start pfn, which is only true when node_min_pfn is a multiple of BITS_PER_LONG. Also loop in the else clause can double-free pages (e.g. with node_min_pfn == start == 1, map[0] == ~0 on 32-bit machine page 32 will be double-freed). This bug causes the following message during xtensa kernel boot: bootmem::free_all_bootmem_core nid=0 start=1 end=8000 BUG: Bad page state in process swapper pfn:00001 page:d04bd020 count:0 mapcount:-127 mapping: (null) index:0x2 page flags: 0x0() Call Trace: bad_page+0x8c/0x9c free_pages_prepare+0x5e/0x88 free_hot_cold_page+0xc/0xa0 __free_pages+0x24/0x38 __free_pages_bootmem+0x54/0x56 free_all_bootmem_core$part$11+0xeb/0x138 free_all_bootmem+0x46/0x58 mem_init+0x25/0xa4 start_kernel+0x11e/0x25c should_never_return+0x0/0x3be7 The fix is the following: - always align vec so that its bit 0 corresponds to start - provide BITS_PER_LONG bits in vec, if those bits are available in the map - don't free pages past next start position in the else clause. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Prasad Koya <prasad.koya@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-12 06:31:52 +08:00
unsigned shift;
idx = start - bdata->node_min_pfn;
mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment Currently free_all_bootmem_core ignores that node_min_pfn may be not multiple of BITS_PER_LONG. Eg commit 6dccdcbe2c3e ("mm: bootmem: fix checking the bitmap when finally freeing bootmem") shifts vec by lower bits of start instead of lower bits of idx. Also if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) assumes that vec bit 0 corresponds to start pfn, which is only true when node_min_pfn is a multiple of BITS_PER_LONG. Also loop in the else clause can double-free pages (e.g. with node_min_pfn == start == 1, map[0] == ~0 on 32-bit machine page 32 will be double-freed). This bug causes the following message during xtensa kernel boot: bootmem::free_all_bootmem_core nid=0 start=1 end=8000 BUG: Bad page state in process swapper pfn:00001 page:d04bd020 count:0 mapcount:-127 mapping: (null) index:0x2 page flags: 0x0() Call Trace: bad_page+0x8c/0x9c free_pages_prepare+0x5e/0x88 free_hot_cold_page+0xc/0xa0 __free_pages+0x24/0x38 __free_pages_bootmem+0x54/0x56 free_all_bootmem_core$part$11+0xeb/0x138 free_all_bootmem+0x46/0x58 mem_init+0x25/0xa4 start_kernel+0x11e/0x25c should_never_return+0x0/0x3be7 The fix is the following: - always align vec so that its bit 0 corresponds to start - provide BITS_PER_LONG bits in vec, if those bits are available in the map - don't free pages past next start position in the else clause. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Prasad Koya <prasad.koya@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-12 06:31:52 +08:00
shift = idx & (BITS_PER_LONG - 1);
/*
* vec holds at most BITS_PER_LONG map bits,
* bit 0 corresponds to start.
*/
vec = ~map[idx / BITS_PER_LONG];
mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment Currently free_all_bootmem_core ignores that node_min_pfn may be not multiple of BITS_PER_LONG. Eg commit 6dccdcbe2c3e ("mm: bootmem: fix checking the bitmap when finally freeing bootmem") shifts vec by lower bits of start instead of lower bits of idx. Also if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) assumes that vec bit 0 corresponds to start pfn, which is only true when node_min_pfn is a multiple of BITS_PER_LONG. Also loop in the else clause can double-free pages (e.g. with node_min_pfn == start == 1, map[0] == ~0 on 32-bit machine page 32 will be double-freed). This bug causes the following message during xtensa kernel boot: bootmem::free_all_bootmem_core nid=0 start=1 end=8000 BUG: Bad page state in process swapper pfn:00001 page:d04bd020 count:0 mapcount:-127 mapping: (null) index:0x2 page flags: 0x0() Call Trace: bad_page+0x8c/0x9c free_pages_prepare+0x5e/0x88 free_hot_cold_page+0xc/0xa0 __free_pages+0x24/0x38 __free_pages_bootmem+0x54/0x56 free_all_bootmem_core$part$11+0xeb/0x138 free_all_bootmem+0x46/0x58 mem_init+0x25/0xa4 start_kernel+0x11e/0x25c should_never_return+0x0/0x3be7 The fix is the following: - always align vec so that its bit 0 corresponds to start - provide BITS_PER_LONG bits in vec, if those bits are available in the map - don't free pages past next start position in the else clause. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Prasad Koya <prasad.koya@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-12 06:31:52 +08:00
if (shift) {
vec >>= shift;
if (end - start >= BITS_PER_LONG)
vec |= ~map[idx / BITS_PER_LONG + 1] <<
(BITS_PER_LONG - shift);
}
/*
* If we have a properly aligned and fully unreserved
* BITS_PER_LONG block of pages in front of us, free
* it in one go.
*/
if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) {
int order = ilog2(BITS_PER_LONG);
__free_pages_bootmem(pfn_to_page(start), start, order);
count += BITS_PER_LONG;
start += BITS_PER_LONG;
} else {
cur = start;
mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment Currently free_all_bootmem_core ignores that node_min_pfn may be not multiple of BITS_PER_LONG. Eg commit 6dccdcbe2c3e ("mm: bootmem: fix checking the bitmap when finally freeing bootmem") shifts vec by lower bits of start instead of lower bits of idx. Also if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) assumes that vec bit 0 corresponds to start pfn, which is only true when node_min_pfn is a multiple of BITS_PER_LONG. Also loop in the else clause can double-free pages (e.g. with node_min_pfn == start == 1, map[0] == ~0 on 32-bit machine page 32 will be double-freed). This bug causes the following message during xtensa kernel boot: bootmem::free_all_bootmem_core nid=0 start=1 end=8000 BUG: Bad page state in process swapper pfn:00001 page:d04bd020 count:0 mapcount:-127 mapping: (null) index:0x2 page flags: 0x0() Call Trace: bad_page+0x8c/0x9c free_pages_prepare+0x5e/0x88 free_hot_cold_page+0xc/0xa0 __free_pages+0x24/0x38 __free_pages_bootmem+0x54/0x56 free_all_bootmem_core$part$11+0xeb/0x138 free_all_bootmem+0x46/0x58 mem_init+0x25/0xa4 start_kernel+0x11e/0x25c should_never_return+0x0/0x3be7 The fix is the following: - always align vec so that its bit 0 corresponds to start - provide BITS_PER_LONG bits in vec, if those bits are available in the map - don't free pages past next start position in the else clause. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Prasad Koya <prasad.koya@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-12 06:31:52 +08:00
start = ALIGN(start + 1, BITS_PER_LONG);
while (vec && cur != start) {
if (vec & 1) {
mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment Currently free_all_bootmem_core ignores that node_min_pfn may be not multiple of BITS_PER_LONG. Eg commit 6dccdcbe2c3e ("mm: bootmem: fix checking the bitmap when finally freeing bootmem") shifts vec by lower bits of start instead of lower bits of idx. Also if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) assumes that vec bit 0 corresponds to start pfn, which is only true when node_min_pfn is a multiple of BITS_PER_LONG. Also loop in the else clause can double-free pages (e.g. with node_min_pfn == start == 1, map[0] == ~0 on 32-bit machine page 32 will be double-freed). This bug causes the following message during xtensa kernel boot: bootmem::free_all_bootmem_core nid=0 start=1 end=8000 BUG: Bad page state in process swapper pfn:00001 page:d04bd020 count:0 mapcount:-127 mapping: (null) index:0x2 page flags: 0x0() Call Trace: bad_page+0x8c/0x9c free_pages_prepare+0x5e/0x88 free_hot_cold_page+0xc/0xa0 __free_pages+0x24/0x38 __free_pages_bootmem+0x54/0x56 free_all_bootmem_core$part$11+0xeb/0x138 free_all_bootmem+0x46/0x58 mem_init+0x25/0xa4 start_kernel+0x11e/0x25c should_never_return+0x0/0x3be7 The fix is the following: - always align vec so that its bit 0 corresponds to start - provide BITS_PER_LONG bits in vec, if those bits are available in the map - don't free pages past next start position in the else clause. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Prasad Koya <prasad.koya@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-12 06:31:52 +08:00
page = pfn_to_page(cur);
__free_pages_bootmem(page, cur, 0);
count++;
}
vec >>= 1;
mm: bootmem: fix free_all_bootmem_core() with odd bitmap alignment Currently free_all_bootmem_core ignores that node_min_pfn may be not multiple of BITS_PER_LONG. Eg commit 6dccdcbe2c3e ("mm: bootmem: fix checking the bitmap when finally freeing bootmem") shifts vec by lower bits of start instead of lower bits of idx. Also if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) assumes that vec bit 0 corresponds to start pfn, which is only true when node_min_pfn is a multiple of BITS_PER_LONG. Also loop in the else clause can double-free pages (e.g. with node_min_pfn == start == 1, map[0] == ~0 on 32-bit machine page 32 will be double-freed). This bug causes the following message during xtensa kernel boot: bootmem::free_all_bootmem_core nid=0 start=1 end=8000 BUG: Bad page state in process swapper pfn:00001 page:d04bd020 count:0 mapcount:-127 mapping: (null) index:0x2 page flags: 0x0() Call Trace: bad_page+0x8c/0x9c free_pages_prepare+0x5e/0x88 free_hot_cold_page+0xc/0xa0 __free_pages+0x24/0x38 __free_pages_bootmem+0x54/0x56 free_all_bootmem_core$part$11+0xeb/0x138 free_all_bootmem+0x46/0x58 mem_init+0x25/0xa4 start_kernel+0x11e/0x25c should_never_return+0x0/0x3be7 The fix is the following: - always align vec so that its bit 0 corresponds to start - provide BITS_PER_LONG bits in vec, if those bits are available in the map - don't free pages past next start position in the else clause. Signed-off-by: Max Filippov <jcmvbkbc@gmail.com> Cc: Gavin Shan <shangw@linux.vnet.ibm.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Tejun Heo <tj@kernel.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Prasad Koya <prasad.koya@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-01-12 06:31:52 +08:00
++cur;
}
}
}
cur = bdata->node_min_pfn;
page = virt_to_page(bdata->node_bootmem_map);
pages = bdata->node_low_pfn - bdata->node_min_pfn;
pages = bootmem_bootmap_pages(pages);
count += pages;
while (pages--)
__free_pages_bootmem(page++, cur++, 0);
bdata->node_bootmem_map = NULL;
bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count);
return count;
}
mm: accurately calculate zone->managed_pages for highmem zones Commit "mm: introduce new field 'managed_pages' to struct zone" assumes that all highmem pages will be freed into the buddy system by function mem_init(). But that's not always true, some architectures may reserve some highmem pages during boot. For example PPC may allocate highmem pages for giagant HugeTLB pages, and several architectures have code to check PageReserved flag to exclude highmem pages allocated during boot when freeing highmem pages into the buddy system. So treat highmem pages in the same way as normal pages, that is to: 1) reset zone->managed_pages to zero in mem_init(). 2) recalculate managed_pages when freeing pages into the buddy system. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:11 +08:00
static int reset_managed_pages_done __initdata;
void reset_node_managed_pages(pg_data_t *pgdat)
mm: introduce new field "managed_pages" to struct zone Currently a zone's present_pages is calcuated as below, which is inaccurate and may cause trouble to memory hotplug. spanned_pages - absent_pages - memmap_pages - dma_reserve. During fixing bugs caused by inaccurate zone->present_pages, we found zone->present_pages has been abused. The field zone->present_pages may have different meanings in different contexts: 1) pages existing in a zone. 2) pages managed by the buddy system. For more discussions about the issue, please refer to: http://lkml.org/lkml/2012/11/5/866 https://patchwork.kernel.org/patch/1346751/ This patchset tries to introduce a new field named "managed_pages" to struct zone, which counts "pages managed by the buddy system". And revert zone->present_pages to count "physical pages existing in a zone", which also keep in consistence with pgdat->node_present_pages. We will set an initial value for zone->managed_pages in function free_area_init_core() and will adjust it later if the initial value is inaccurate. For DMA/normal zones, the initial value is set to: (spanned_pages - absent_pages - memmap_pages - dma_reserve) Later zone->managed_pages will be adjusted to the accurate value when the bootmem allocator frees all free pages to the buddy system in function free_all_bootmem_node() and free_all_bootmem(). The bootmem allocator doesn't touch highmem pages, so highmem zones' managed_pages is set to the accurate value "spanned_pages - absent_pages" in function free_area_init_core() and won't be updated anymore. This patch also adds a new field "managed_pages" to /proc/zoneinfo and sysrq showmem. [akpm@linux-foundation.org: small comment tweaks] Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Maciej Rutecki <maciej.rutecki@gmail.com> Tested-by: Chris Clayton <chris2553@googlemail.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-13 05:52:12 +08:00
{
struct zone *z;
for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
mm: accurately calculate zone->managed_pages for highmem zones Commit "mm: introduce new field 'managed_pages' to struct zone" assumes that all highmem pages will be freed into the buddy system by function mem_init(). But that's not always true, some architectures may reserve some highmem pages during boot. For example PPC may allocate highmem pages for giagant HugeTLB pages, and several architectures have code to check PageReserved flag to exclude highmem pages allocated during boot when freeing highmem pages into the buddy system. So treat highmem pages in the same way as normal pages, that is to: 1) reset zone->managed_pages to zero in mem_init(). 2) recalculate managed_pages when freeing pages into the buddy system. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:11 +08:00
z->managed_pages = 0;
}
void __init reset_all_zones_managed_pages(void)
{
struct pglist_data *pgdat;
if (reset_managed_pages_done)
return;
mm: accurately calculate zone->managed_pages for highmem zones Commit "mm: introduce new field 'managed_pages' to struct zone" assumes that all highmem pages will be freed into the buddy system by function mem_init(). But that's not always true, some architectures may reserve some highmem pages during boot. For example PPC may allocate highmem pages for giagant HugeTLB pages, and several architectures have code to check PageReserved flag to exclude highmem pages allocated during boot when freeing highmem pages into the buddy system. So treat highmem pages in the same way as normal pages, that is to: 1) reset zone->managed_pages to zero in mem_init(). 2) recalculate managed_pages when freeing pages into the buddy system. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:11 +08:00
for_each_online_pgdat(pgdat)
reset_node_managed_pages(pgdat);
mm: accurately calculate zone->managed_pages for highmem zones Commit "mm: introduce new field 'managed_pages' to struct zone" assumes that all highmem pages will be freed into the buddy system by function mem_init(). But that's not always true, some architectures may reserve some highmem pages during boot. For example PPC may allocate highmem pages for giagant HugeTLB pages, and several architectures have code to check PageReserved flag to exclude highmem pages allocated during boot when freeing highmem pages into the buddy system. So treat highmem pages in the same way as normal pages, that is to: 1) reset zone->managed_pages to zero in mem_init(). 2) recalculate managed_pages when freeing pages into the buddy system. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:11 +08:00
reset_managed_pages_done = 1;
mm: introduce new field "managed_pages" to struct zone Currently a zone's present_pages is calcuated as below, which is inaccurate and may cause trouble to memory hotplug. spanned_pages - absent_pages - memmap_pages - dma_reserve. During fixing bugs caused by inaccurate zone->present_pages, we found zone->present_pages has been abused. The field zone->present_pages may have different meanings in different contexts: 1) pages existing in a zone. 2) pages managed by the buddy system. For more discussions about the issue, please refer to: http://lkml.org/lkml/2012/11/5/866 https://patchwork.kernel.org/patch/1346751/ This patchset tries to introduce a new field named "managed_pages" to struct zone, which counts "pages managed by the buddy system". And revert zone->present_pages to count "physical pages existing in a zone", which also keep in consistence with pgdat->node_present_pages. We will set an initial value for zone->managed_pages in function free_area_init_core() and will adjust it later if the initial value is inaccurate. For DMA/normal zones, the initial value is set to: (spanned_pages - absent_pages - memmap_pages - dma_reserve) Later zone->managed_pages will be adjusted to the accurate value when the bootmem allocator frees all free pages to the buddy system in function free_all_bootmem_node() and free_all_bootmem(). The bootmem allocator doesn't touch highmem pages, so highmem zones' managed_pages is set to the accurate value "spanned_pages - absent_pages" in function free_area_init_core() and won't be updated anymore. This patch also adds a new field "managed_pages" to /proc/zoneinfo and sysrq showmem. [akpm@linux-foundation.org: small comment tweaks] Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Maciej Rutecki <maciej.rutecki@gmail.com> Tested-by: Chris Clayton <chris2553@googlemail.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-13 05:52:12 +08:00
}
/**
* free_all_bootmem - release free pages to the buddy allocator
*
* Returns the number of pages actually released.
*/
unsigned long __init free_all_bootmem(void)
{
unsigned long total_pages = 0;
bootmem_data_t *bdata;
mm: introduce new field "managed_pages" to struct zone Currently a zone's present_pages is calcuated as below, which is inaccurate and may cause trouble to memory hotplug. spanned_pages - absent_pages - memmap_pages - dma_reserve. During fixing bugs caused by inaccurate zone->present_pages, we found zone->present_pages has been abused. The field zone->present_pages may have different meanings in different contexts: 1) pages existing in a zone. 2) pages managed by the buddy system. For more discussions about the issue, please refer to: http://lkml.org/lkml/2012/11/5/866 https://patchwork.kernel.org/patch/1346751/ This patchset tries to introduce a new field named "managed_pages" to struct zone, which counts "pages managed by the buddy system". And revert zone->present_pages to count "physical pages existing in a zone", which also keep in consistence with pgdat->node_present_pages. We will set an initial value for zone->managed_pages in function free_area_init_core() and will adjust it later if the initial value is inaccurate. For DMA/normal zones, the initial value is set to: (spanned_pages - absent_pages - memmap_pages - dma_reserve) Later zone->managed_pages will be adjusted to the accurate value when the bootmem allocator frees all free pages to the buddy system in function free_all_bootmem_node() and free_all_bootmem(). The bootmem allocator doesn't touch highmem pages, so highmem zones' managed_pages is set to the accurate value "spanned_pages - absent_pages" in function free_area_init_core() and won't be updated anymore. This patch also adds a new field "managed_pages" to /proc/zoneinfo and sysrq showmem. [akpm@linux-foundation.org: small comment tweaks] Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: David Rientjes <rientjes@google.com> Cc: Maciej Rutecki <maciej.rutecki@gmail.com> Tested-by: Chris Clayton <chris2553@googlemail.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-12-13 05:52:12 +08:00
mm: accurately calculate zone->managed_pages for highmem zones Commit "mm: introduce new field 'managed_pages' to struct zone" assumes that all highmem pages will be freed into the buddy system by function mem_init(). But that's not always true, some architectures may reserve some highmem pages during boot. For example PPC may allocate highmem pages for giagant HugeTLB pages, and several architectures have code to check PageReserved flag to exclude highmem pages allocated during boot when freeing highmem pages into the buddy system. So treat highmem pages in the same way as normal pages, that is to: 1) reset zone->managed_pages to zero in mem_init(). 2) recalculate managed_pages when freeing pages into the buddy system. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Minchan Kim <minchan@kernel.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: David Howells <dhowells@redhat.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michel Lespinasse <walken@google.com> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:11 +08:00
reset_all_zones_managed_pages();
list_for_each_entry(bdata, &bdata_list, list)
total_pages += free_all_bootmem_core(bdata);
mm: concentrate modification of totalram_pages into the mm core Concentrate code to modify totalram_pages into the mm core, so the arch memory initialized code doesn't need to take care of it. With these changes applied, only following functions from mm core modify global variable totalram_pages: free_bootmem_late(), free_all_bootmem(), free_all_bootmem_node(), adjust_managed_page_count(). With this patch applied, it will be much more easier for us to keep totalram_pages and zone->managed_pages in consistence. Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Acked-by: David Howells <dhowells@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Michael S. Tsirkin" <mst@redhat.com> Cc: <sworddragon2@aol.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Metcalf <cmetcalf@tilera.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jeremy Fitzhardinge <jeremy@goop.org> Cc: Jianguo Wu <wujianguo@huawei.com> Cc: Joonsoo Kim <js1304@gmail.com> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Michel Lespinasse <walken@google.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Rusty Russell <rusty@rustcorp.com.au> Cc: Tang Chen <tangchen@cn.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Will Deacon <will.deacon@arm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <rmk@arm.linux.org.uk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-07-04 06:03:24 +08:00
totalram_pages += total_pages;
return total_pages;
}
static void __init __free(bootmem_data_t *bdata,
unsigned long sidx, unsigned long eidx)
{
unsigned long idx;
bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data,
sidx + bdata->node_min_pfn,
eidx + bdata->node_min_pfn);
if (WARN_ON(bdata->node_bootmem_map == NULL))
return;
if (bdata->hint_idx > sidx)
bdata->hint_idx = sidx;
for (idx = sidx; idx < eidx; idx++)
if (!test_and_clear_bit(idx, bdata->node_bootmem_map))
BUG();
}
static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx,
unsigned long eidx, int flags)
{
unsigned long idx;
int exclusive = flags & BOOTMEM_EXCLUSIVE;
bdebug("nid=%td start=%lx end=%lx flags=%x\n",
bdata - bootmem_node_data,
sidx + bdata->node_min_pfn,
eidx + bdata->node_min_pfn,
flags);
if (WARN_ON(bdata->node_bootmem_map == NULL))
return 0;
for (idx = sidx; idx < eidx; idx++)
if (test_and_set_bit(idx, bdata->node_bootmem_map)) {
if (exclusive) {
__free(bdata, sidx, idx);
return -EBUSY;
}
bdebug("silent double reserve of PFN %lx\n",
idx + bdata->node_min_pfn);
}
return 0;
}
static int __init mark_bootmem_node(bootmem_data_t *bdata,
unsigned long start, unsigned long end,
int reserve, int flags)
{
unsigned long sidx, eidx;
bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n",
bdata - bootmem_node_data, start, end, reserve, flags);
BUG_ON(start < bdata->node_min_pfn);
BUG_ON(end > bdata->node_low_pfn);
sidx = start - bdata->node_min_pfn;
eidx = end - bdata->node_min_pfn;
if (reserve)
return __reserve(bdata, sidx, eidx, flags);
else
__free(bdata, sidx, eidx);
return 0;
}
static int __init mark_bootmem(unsigned long start, unsigned long end,
int reserve, int flags)
{
unsigned long pos;
bootmem_data_t *bdata;
pos = start;
list_for_each_entry(bdata, &bdata_list, list) {
int err;
unsigned long max;
if (pos < bdata->node_min_pfn ||
pos >= bdata->node_low_pfn) {
BUG_ON(pos != start);
continue;
}
max = min(bdata->node_low_pfn, end);
err = mark_bootmem_node(bdata, pos, max, reserve, flags);
if (reserve && err) {
mark_bootmem(start, pos, 0, 0);
return err;
}
if (max == end)
return 0;
pos = bdata->node_low_pfn;
}
BUG();
}
/**
* free_bootmem_node - mark a page range as usable
* @pgdat: node the range resides on
* @physaddr: starting address of the range
* @size: size of the range in bytes
*
* Partial pages will be considered reserved and left as they are.
*
* The range must reside completely on the specified node.
*/
void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
unsigned long size)
{
unsigned long start, end;
kmemleak_free_part(__va(physaddr), size);
start = PFN_UP(physaddr);
end = PFN_DOWN(physaddr + size);
mark_bootmem_node(pgdat->bdata, start, end, 0, 0);
}
/**
* free_bootmem - mark a page range as usable
* @addr: starting physical address of the range
* @size: size of the range in bytes
*
* Partial pages will be considered reserved and left as they are.
*
* The range must be contiguous but may span node boundaries.
*/
void __init free_bootmem(unsigned long physaddr, unsigned long size)
{
unsigned long start, end;
kmemleak_free_part(__va(physaddr), size);
start = PFN_UP(physaddr);
end = PFN_DOWN(physaddr + size);
mark_bootmem(start, end, 0, 0);
}
/**
* reserve_bootmem_node - mark a page range as reserved
* @pgdat: node the range resides on
* @physaddr: starting address of the range
* @size: size of the range in bytes
* @flags: reservation flags (see linux/bootmem.h)
*
* Partial pages will be reserved.
*
* The range must reside completely on the specified node.
*/
int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
unsigned long size, int flags)
{
unsigned long start, end;
start = PFN_DOWN(physaddr);
end = PFN_UP(physaddr + size);
return mark_bootmem_node(pgdat->bdata, start, end, 1, flags);
}
/**
* reserve_bootmem - mark a page range as reserved
* @addr: starting address of the range
* @size: size of the range in bytes
* @flags: reservation flags (see linux/bootmem.h)
*
* Partial pages will be reserved.
*
* The range must be contiguous but may span node boundaries.
*/
int __init reserve_bootmem(unsigned long addr, unsigned long size,
int flags)
{
unsigned long start, end;
start = PFN_DOWN(addr);
end = PFN_UP(addr + size);
return mark_bootmem(start, end, 1, flags);
}
static unsigned long __init align_idx(struct bootmem_data *bdata,
unsigned long idx, unsigned long step)
{
unsigned long base = bdata->node_min_pfn;
/*
* Align the index with respect to the node start so that the
* combination of both satisfies the requested alignment.
*/
return ALIGN(base + idx, step) - base;
}
static unsigned long __init align_off(struct bootmem_data *bdata,
unsigned long off, unsigned long align)
{
unsigned long base = PFN_PHYS(bdata->node_min_pfn);
/* Same as align_idx for byte offsets */
return ALIGN(base + off, align) - base;
}
static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata,
unsigned long size, unsigned long align,
unsigned long goal, unsigned long limit)
{
unsigned long fallback = 0;
unsigned long min, max, start, sidx, midx, step;
bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n",
bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT,
align, goal, limit);
BUG_ON(!size);
BUG_ON(align & (align - 1));
BUG_ON(limit && goal + size > limit);
if (!bdata->node_bootmem_map)
return NULL;
min = bdata->node_min_pfn;
max = bdata->node_low_pfn;
goal >>= PAGE_SHIFT;
limit >>= PAGE_SHIFT;
if (limit && max > limit)
max = limit;
if (max <= min)
return NULL;
step = max(align >> PAGE_SHIFT, 1UL);
if (goal && min < goal && goal < max)
start = ALIGN(goal, step);
else
start = ALIGN(min, step);
sidx = start - bdata->node_min_pfn;
midx = max - bdata->node_min_pfn;
if (bdata->hint_idx > sidx) {
/*
* Handle the valid case of sidx being zero and still
* catch the fallback below.
*/
fallback = sidx + 1;
sidx = align_idx(bdata, bdata->hint_idx, step);
}
while (1) {
int merge;
void *region;
unsigned long eidx, i, start_off, end_off;
find_block:
sidx = find_next_zero_bit(bdata->node_bootmem_map, midx, sidx);
sidx = align_idx(bdata, sidx, step);
eidx = sidx + PFN_UP(size);
if (sidx >= midx || eidx > midx)
break;
for (i = sidx; i < eidx; i++)
if (test_bit(i, bdata->node_bootmem_map)) {
sidx = align_idx(bdata, i, step);
if (sidx == i)
sidx += step;
goto find_block;
}
bootmem allocator: alloc_bootmem_core(): page-align the end offset This is the minimal sequence that jams the allocator: void *p, *q, *r; p = alloc_bootmem(PAGE_SIZE); q = alloc_bootmem(64); free_bootmem(p, PAGE_SIZE); p = alloc_bootmem(PAGE_SIZE); r = alloc_bootmem(64); after this sequence (assuming that the allocator was empty or page-aligned before), pointer "q" will be equal to pointer "r". What's hapenning inside the allocator: p = alloc_bootmem(PAGE_SIZE); in allocator: last_end_off == PAGE_SIZE, bitmap contains bits 10000... q = alloc_bootmem(64); in allocator: last_end_off == PAGE_SIZE + 64, bitmap contains 11000... free_bootmem(p, PAGE_SIZE); in allocator: last_end_off == PAGE_SIZE + 64, bitmap contains 01000... p = alloc_bootmem(PAGE_SIZE); in allocator: last_end_off == PAGE_SIZE, bitmap contains 11000... r = alloc_bootmem(64); and now: it finds bit "2", as a place where to allocate (sidx) it hits the condition if (bdata->last_end_off && PFN_DOWN(bdata->last_end_off) + 1 == sidx)) start_off = ALIGN(bdata->last_end_off, align); -you can see that the condition is true, so it assigns start_off = ALIGN(bdata->last_end_off, align); (that is PAGE_SIZE) and allocates over already allocated block. With the patch it tries to continue at the end of previous allocation only if the previous allocation ended in the middle of the page. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Acked-by: Johannes Weiner <hannes@saeurebad.de> Cc: David Miller <davem@davemloft.net> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-08-15 15:40:17 +08:00
if (bdata->last_end_off & (PAGE_SIZE - 1) &&
PFN_DOWN(bdata->last_end_off) + 1 == sidx)
start_off = align_off(bdata, bdata->last_end_off, align);
else
start_off = PFN_PHYS(sidx);
merge = PFN_DOWN(start_off) < sidx;
end_off = start_off + size;
bdata->last_end_off = end_off;
bdata->hint_idx = PFN_UP(end_off);
/*
* Reserve the area now:
*/
if (__reserve(bdata, PFN_DOWN(start_off) + merge,
PFN_UP(end_off), BOOTMEM_EXCLUSIVE))
BUG();
region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) +
start_off);
memset(region, 0, size);
/*
* The min_count is set to 0 so that bootmem allocated blocks
* are never reported as leaks.
*/
kmemleak_alloc(region, size, 0, 0);
return region;
}
if (fallback) {
sidx = align_idx(bdata, fallback - 1, step);
fallback = 0;
goto find_block;
}
return NULL;
}
static void * __init alloc_bootmem_core(unsigned long size,
unsigned long align,
unsigned long goal,
unsigned long limit)
{
bootmem_data_t *bdata;
void *region;
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc(size, GFP_NOWAIT);
list_for_each_entry(bdata, &bdata_list, list) {
if (goal && bdata->node_low_pfn <= PFN_DOWN(goal))
continue;
if (limit && bdata->node_min_pfn >= PFN_DOWN(limit))
break;
region = alloc_bootmem_bdata(bdata, size, align, goal, limit);
if (region)
return region;
}
return NULL;
}
static void * __init ___alloc_bootmem_nopanic(unsigned long size,
unsigned long align,
unsigned long goal,
unsigned long limit)
{
void *ptr;
restart:
ptr = alloc_bootmem_core(size, align, goal, limit);
if (ptr)
return ptr;
if (goal) {
goal = 0;
goto restart;
}
return NULL;
}
/**
* __alloc_bootmem_nopanic - allocate boot memory without panicking
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may happen on any node in the system.
*
* Returns NULL on failure.
*/
void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align,
unsigned long goal)
{
unsigned long limit = 0;
return ___alloc_bootmem_nopanic(size, align, goal, limit);
}
static void * __init ___alloc_bootmem(unsigned long size, unsigned long align,
unsigned long goal, unsigned long limit)
{
void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit);
if (mem)
return mem;
/*
* Whoops, we cannot satisfy the allocation request.
*/
printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
panic("Out of memory");
return NULL;
}
/**
* __alloc_bootmem - allocate boot memory
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may happen on any node in the system.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem(unsigned long size, unsigned long align,
unsigned long goal)
{
unsigned long limit = 0;
return ___alloc_bootmem(size, align, goal, limit);
}
void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat,
unsigned long size, unsigned long align,
unsigned long goal, unsigned long limit)
{
void *ptr;
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc(size, GFP_NOWAIT);
again:
/* do not panic in alloc_bootmem_bdata() */
if (limit && goal + size > limit)
limit = 0;
ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit);
if (ptr)
return ptr;
ptr = alloc_bootmem_core(size, align, goal, limit);
if (ptr)
return ptr;
if (goal) {
goal = 0;
goto again;
}
return NULL;
}
void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
}
void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal,
unsigned long limit)
{
void *ptr;
ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0);
if (ptr)
return ptr;
printk(KERN_ALERT "bootmem alloc of %lu bytes failed!\n", size);
panic("Out of memory");
return NULL;
}
/**
* __alloc_bootmem_node - allocate boot memory from a specific node
* @pgdat: node to allocate from
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may fall back to any node in the system if the specified node
* can not hold the requested memory.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
return ___alloc_bootmem_node(pgdat, size, align, goal, 0);
}
void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
#ifdef MAX_DMA32_PFN
unsigned long end_pfn;
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
/* update goal according ...MAX_DMA32_PFN */
end_pfn = pgdat_end_pfn(pgdat);
if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) &&
(goal >> PAGE_SHIFT) < MAX_DMA32_PFN) {
void *ptr;
unsigned long new_goal;
new_goal = MAX_DMA32_PFN << PAGE_SHIFT;
ptr = alloc_bootmem_bdata(pgdat->bdata, size, align,
new_goal, 0);
if (ptr)
return ptr;
}
#endif
return __alloc_bootmem_node(pgdat, size, align, goal);
}
#ifndef ARCH_LOW_ADDRESS_LIMIT
#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL
#endif
/**
* __alloc_bootmem_low - allocate low boot memory
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may happen on any node in the system.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem_low(unsigned long size, unsigned long align,
unsigned long goal)
{
return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT);
}
void * __init __alloc_bootmem_low_nopanic(unsigned long size,
unsigned long align,
unsigned long goal)
{
return ___alloc_bootmem_nopanic(size, align, goal,
ARCH_LOW_ADDRESS_LIMIT);
}
/**
* __alloc_bootmem_low_node - allocate low boot memory from a specific node
* @pgdat: node to allocate from
* @size: size of the request in bytes
* @align: alignment of the region
* @goal: preferred starting address of the region
*
* The goal is dropped if it can not be satisfied and the allocation will
* fall back to memory below @goal.
*
* Allocation may fall back to any node in the system if the specified node
* can not hold the requested memory.
*
* The function panics if the request can not be satisfied.
*/
void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size,
unsigned long align, unsigned long goal)
{
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id);
return ___alloc_bootmem_node(pgdat, size, align,
goal, ARCH_LOW_ADDRESS_LIMIT);
}