linux/mm/nobootmem.c

426 lines
11 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 <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);
}
memblock: free allocated memblock_reserved_regions later memblock_free_reserved_regions() calls memblock_free(), but memblock_free() would double reserved.regions too, so we could free the old range for reserved.regions. Also tj said there is another bug which could be related to this. | I don't think we're saving any noticeable | amount by doing this "free - give it to page allocator - reserve | again" dancing. We should just allocate regions aligned to page | boundaries and free them later when memblock is no longer in use. in that case, when DEBUG_PAGEALLOC, will get panic: memblock_free: [0x0000102febc080-0x0000102febf080] memblock_free_reserved_regions+0x37/0x39 BUG: unable to handle kernel paging request at ffff88102febd948 IP: [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155 PGD 4826063 PUD cf67a067 PMD cf7fa067 PTE 800000102febd160 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC CPU 0 Pid: 0, comm: swapper Not tainted 3.5.0-rc2-next-20120614-sasha #447 RIP: 0010:[<ffffffff836a5774>] [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155 See the discussion at https://lkml.org/lkml/2012/6/13/469 So try to allocate with PAGE_SIZE alignment and free it later. Reported-by: Sasha Levin <levinsasha928@gmail.com> Acked-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-11 21:02:56 +00:00
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);
return end_pfn - start_pfn;
}
unsigned long __init free_low_memory_core_early(int nodeid)
{
unsigned long count = 0;
memblock: free allocated memblock_reserved_regions later memblock_free_reserved_regions() calls memblock_free(), but memblock_free() would double reserved.regions too, so we could free the old range for reserved.regions. Also tj said there is another bug which could be related to this. | I don't think we're saving any noticeable | amount by doing this "free - give it to page allocator - reserve | again" dancing. We should just allocate regions aligned to page | boundaries and free them later when memblock is no longer in use. in that case, when DEBUG_PAGEALLOC, will get panic: memblock_free: [0x0000102febc080-0x0000102febf080] memblock_free_reserved_regions+0x37/0x39 BUG: unable to handle kernel paging request at ffff88102febd948 IP: [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155 PGD 4826063 PUD cf67a067 PMD cf7fa067 PTE 800000102febd160 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC CPU 0 Pid: 0, comm: swapper Not tainted 3.5.0-rc2-next-20120614-sasha #447 RIP: 0010:[<ffffffff836a5774>] [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155 See the discussion at https://lkml.org/lkml/2012/6/13/469 So try to allocate with PAGE_SIZE alignment and free it later. Reported-by: Sasha Levin <levinsasha928@gmail.com> Acked-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-11 21:02:56 +00:00
phys_addr_t start, end, size;
u64 i;
memblock: free allocated memblock_reserved_regions later memblock_free_reserved_regions() calls memblock_free(), but memblock_free() would double reserved.regions too, so we could free the old range for reserved.regions. Also tj said there is another bug which could be related to this. | I don't think we're saving any noticeable | amount by doing this "free - give it to page allocator - reserve | again" dancing. We should just allocate regions aligned to page | boundaries and free them later when memblock is no longer in use. in that case, when DEBUG_PAGEALLOC, will get panic: memblock_free: [0x0000102febc080-0x0000102febf080] memblock_free_reserved_regions+0x37/0x39 BUG: unable to handle kernel paging request at ffff88102febd948 IP: [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155 PGD 4826063 PUD cf67a067 PMD cf7fa067 PTE 800000102febd160 Oops: 0000 [#1] PREEMPT SMP DEBUG_PAGEALLOC CPU 0 Pid: 0, comm: swapper Not tainted 3.5.0-rc2-next-20120614-sasha #447 RIP: 0010:[<ffffffff836a5774>] [<ffffffff836a5774>] __next_free_mem_range+0x9b/0x155 See the discussion at https://lkml.org/lkml/2012/6/13/469 So try to allocate with PAGE_SIZE alignment and free it later. Reported-by: Sasha Levin <levinsasha928@gmail.com> Acked-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Yinghai Lu <yinghai@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-07-11 21:02:56 +00:00
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;
}
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>
2012-12-12 21:52:12 +00:00
static void reset_node_lowmem_managed_pages(pg_data_t *pgdat)
{
struct zone *z;
/*
* In free_area_init_core(), highmem zone's managed_pages is set to
* present_pages, and bootmem allocator doesn't allocate from highmem
* zones. So there's no need to recalculate managed_pages because all
* highmem pages will be managed by the buddy system. Here highmem
* zone also includes highmem movable zone.
*/
for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++)
if (!is_highmem(z))
z->managed_pages = 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)
{
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>
2012-12-12 21:52:12 +00:00
struct pglist_data *pgdat;
for_each_online_pgdat(pgdat)
reset_node_lowmem_managed_pages(pgdat);
/*
* 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);
}
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);
}