mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-24 19:20:50 +07:00
7f1290f2f2
I think zone->present_pages indicates pages that buddy system can management, it should be: zone->present_pages = spanned pages - absent pages - bootmem pages, but is now: zone->present_pages = spanned pages - absent pages - memmap pages. spanned pages: total size, including holes. absent pages: holes. bootmem pages: pages used in system boot, managed by bootmem allocator. memmap pages: pages used by page structs. This may cause zone->present_pages less than it should be. For example, numa node 1 has ZONE_NORMAL and ZONE_MOVABLE, it's memmap and other bootmem will be allocated from ZONE_MOVABLE, so ZONE_NORMAL's present_pages should be spanned pages - absent pages, but now it also minus memmap pages(free_area_init_core), which are actually allocated from ZONE_MOVABLE. When offlining all memory of a zone, this will cause zone->present_pages less than 0, because present_pages is unsigned long type, it is actually a very large integer, it indirectly caused zone->watermark[WMARK_MIN] becomes a large integer(setup_per_zone_wmarks()), than cause totalreserve_pages become a large integer(calculate_totalreserve_pages()), and finally cause memory allocating failure when fork process(__vm_enough_memory()). [root@localhost ~]# dmesg -bash: fork: Cannot allocate memory I think the bug described in http://marc.info/?l=linux-mm&m=134502182714186&w=2 is also caused by wrong zone present pages. This patch intends to fix-up zone->present_pages when memory are freed to buddy system on x86_64 and IA64 platforms. Signed-off-by: Jianguo Wu <wujianguo@huawei.com> Signed-off-by: Jiang Liu <jiang.liu@huawei.com> Reported-by: Petr Tesarik <ptesarik@suse.cz> Tested-by: Petr Tesarik <ptesarik@suse.cz> Cc: "Luck, Tony" <tony.luck@intel.com> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Minchan Kim <minchan.kim@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: David Rientjes <rientjes@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
414 lines
11 KiB
C
414 lines
11 KiB
C
/*
|
|
* 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 <linux/slab.h>
|
|
#include <linux/bootmem.h>
|
|
#include <linux/export.h>
|
|
#include <linux/kmemleak.h>
|
|
#include <linux/range.h>
|
|
#include <linux/memblock.h>
|
|
|
|
#include <asm/bug.h>
|
|
#include <asm/io.h>
|
|
#include <asm/processor.h>
|
|
|
|
#include "internal.h"
|
|
|
|
#ifndef CONFIG_NEED_MULTIPLE_NODES
|
|
struct pglist_data __refdata contig_page_data;
|
|
EXPORT_SYMBOL(contig_page_data);
|
|
#endif
|
|
|
|
unsigned long max_low_pfn;
|
|
unsigned long min_low_pfn;
|
|
unsigned long max_pfn;
|
|
|
|
static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align,
|
|
u64 goal, u64 limit)
|
|
{
|
|
void *ptr;
|
|
u64 addr;
|
|
|
|
if (limit > memblock.current_limit)
|
|
limit = memblock.current_limit;
|
|
|
|
addr = memblock_find_in_range_node(goal, limit, size, align, nid);
|
|
if (!addr)
|
|
return NULL;
|
|
|
|
ptr = phys_to_virt(addr);
|
|
memset(ptr, 0, size);
|
|
memblock_reserve(addr, size);
|
|
/*
|
|
* The min_count is set to 0 so that bootmem allocated blocks
|
|
* are never reported as leaks.
|
|
*/
|
|
kmemleak_alloc(ptr, size, 0, 0);
|
|
return ptr;
|
|
}
|
|
|
|
/*
|
|
* free_bootmem_late - free bootmem pages directly to page allocator
|
|
* @addr: starting 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 addr, unsigned long size)
|
|
{
|
|
unsigned long cursor, end;
|
|
|
|
kmemleak_free_part(__va(addr), size);
|
|
|
|
cursor = PFN_UP(addr);
|
|
end = PFN_DOWN(addr + size);
|
|
|
|
for (; cursor < end; cursor++) {
|
|
__free_pages_bootmem(pfn_to_page(cursor), 0);
|
|
totalram_pages++;
|
|
}
|
|
}
|
|
|
|
static void __init __free_pages_memory(unsigned long start, unsigned long end)
|
|
{
|
|
unsigned long i, start_aligned, end_aligned;
|
|
int order = ilog2(BITS_PER_LONG);
|
|
|
|
start_aligned = (start + (BITS_PER_LONG - 1)) & ~(BITS_PER_LONG - 1);
|
|
end_aligned = end & ~(BITS_PER_LONG - 1);
|
|
|
|
if (end_aligned <= start_aligned) {
|
|
for (i = start; i < end; i++)
|
|
__free_pages_bootmem(pfn_to_page(i), 0);
|
|
|
|
return;
|
|
}
|
|
|
|
for (i = start; i < start_aligned; i++)
|
|
__free_pages_bootmem(pfn_to_page(i), 0);
|
|
|
|
for (i = start_aligned; i < end_aligned; i += BITS_PER_LONG)
|
|
__free_pages_bootmem(pfn_to_page(i), order);
|
|
|
|
for (i = end_aligned; i < end; i++)
|
|
__free_pages_bootmem(pfn_to_page(i), 0);
|
|
}
|
|
|
|
static unsigned long __init __free_memory_core(phys_addr_t start,
|
|
phys_addr_t end)
|
|
{
|
|
unsigned long start_pfn = PFN_UP(start);
|
|
unsigned long end_pfn = min_t(unsigned long,
|
|
PFN_DOWN(end), max_low_pfn);
|
|
|
|
if (start_pfn > end_pfn)
|
|
return 0;
|
|
|
|
__free_pages_memory(start_pfn, end_pfn);
|
|
fixup_zone_present_pages(pfn_to_nid(start >> PAGE_SHIFT),
|
|
start_pfn, end_pfn);
|
|
|
|
return end_pfn - start_pfn;
|
|
}
|
|
|
|
unsigned long __init free_low_memory_core_early(int nodeid)
|
|
{
|
|
unsigned long count = 0;
|
|
phys_addr_t start, end, size;
|
|
u64 i;
|
|
|
|
reset_zone_present_pages();
|
|
for_each_free_mem_range(i, MAX_NUMNODES, &start, &end, NULL)
|
|
count += __free_memory_core(start, end);
|
|
|
|
/* free range that is used for reserved array if we allocate it */
|
|
size = get_allocated_memblock_reserved_regions_info(&start);
|
|
if (size)
|
|
count += __free_memory_core(start, start + size);
|
|
|
|
return count;
|
|
}
|
|
|
|
/**
|
|
* free_all_bootmem_node - release a node's free pages to the buddy allocator
|
|
* @pgdat: node to be released
|
|
*
|
|
* Returns the number of pages actually released.
|
|
*/
|
|
unsigned long __init free_all_bootmem_node(pg_data_t *pgdat)
|
|
{
|
|
register_page_bootmem_info_node(pgdat);
|
|
|
|
/* free_low_memory_core_early(MAX_NUMNODES) will be called later */
|
|
return 0;
|
|
}
|
|
|
|
/**
|
|
* free_all_bootmem - release free pages to the buddy allocator
|
|
*
|
|
* Returns the number of pages actually released.
|
|
*/
|
|
unsigned long __init free_all_bootmem(void)
|
|
{
|
|
/*
|
|
* We need to use MAX_NUMNODES instead of NODE_DATA(0)->node_id
|
|
* because in some case like Node0 doesn't have RAM installed
|
|
* low ram will be on Node1
|
|
*/
|
|
return free_low_memory_core_early(MAX_NUMNODES);
|
|
}
|
|
|
|
/**
|
|
* 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)
|
|
{
|
|
kmemleak_free_part(__va(physaddr), size);
|
|
memblock_free(physaddr, size);
|
|
}
|
|
|
|
/**
|
|
* free_bootmem - mark a page range as usable
|
|
* @addr: 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 be contiguous but may span node boundaries.
|
|
*/
|
|
void __init free_bootmem(unsigned long addr, unsigned long size)
|
|
{
|
|
kmemleak_free_part(__va(addr), size);
|
|
memblock_free(addr, size);
|
|
}
|
|
|
|
static void * __init ___alloc_bootmem_nopanic(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);
|
|
|
|
restart:
|
|
|
|
ptr = __alloc_memory_core_early(MAX_NUMNODES, size, align, goal, limit);
|
|
|
|
if (ptr)
|
|
return ptr;
|
|
|
|
if (goal != 0) {
|
|
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 = -1UL;
|
|
|
|
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 = -1UL;
|
|
|
|
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;
|
|
|
|
again:
|
|
ptr = __alloc_memory_core_early(pgdat->node_id, size, align,
|
|
goal, limit);
|
|
if (ptr)
|
|
return ptr;
|
|
|
|
ptr = __alloc_memory_core_early(MAX_NUMNODES, 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, limit);
|
|
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)
|
|
{
|
|
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);
|
|
}
|
|
|
|
/**
|
|
* __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);
|
|
}
|