linux/mm/nobootmem.c

452 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;
ulong flags = choose_memblock_flags();
if (limit > memblock.current_limit)
limit = memblock.current_limit;
again:
mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute Some high end Intel Xeon systems report uncorrectable memory errors as a recoverable machine check. Linux has included code for some time to process these and just signal the affected processes (or even recover completely if the error was in a read only page that can be replaced by reading from disk). But we have no recovery path for errors encountered during kernel code execution. Except for some very specific cases were are unlikely to ever be able to recover. Enter memory mirroring. Actually 3rd generation of memory mirroing. Gen1: All memory is mirrored Pro: No s/w enabling - h/w just gets good data from other side of the mirror Con: Halves effective memory capacity available to OS/applications Gen2: Partial memory mirror - just mirror memory begind some memory controllers Pro: Keep more of the capacity Con: Nightmare to enable. Have to choose between allocating from mirrored memory for safety vs. NUMA local memory for performance Gen3: Address range partial memory mirror - some mirror on each memory controller Pro: Can tune the amount of mirror and keep NUMA performance Con: I have to write memory management code to implement The current plan is just to use mirrored memory for kernel allocations. This has been broken into two phases: 1) This patch series - find the mirrored memory, use it for boot time allocations 2) Wade into mm/page_alloc.c and define a ZONE_MIRROR to pick up the unused mirrored memory from mm/memblock.c and only give it out to select kernel allocations (this is still being scoped because page_alloc.c is scary). This patch (of 3): Add extra "flags" to memblock to allow selection of memory based on attribute. No functional changes Signed-off-by: Tony Luck <tony.luck@intel.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Xiexiuqi <xiexiuqi@huawei.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Naoya Horiguchi <nao.horiguchi@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 23:58:09 +00:00
addr = memblock_find_in_range_node(size, align, goal, limit, nid,
flags);
if (!addr && (flags & MEMBLOCK_MIRROR)) {
flags &= ~MEMBLOCK_MIRROR;
pr_warn("Could not allocate %pap bytes of mirrored memory\n",
&size);
goto again;
}
if (!addr)
return NULL;
if (memblock_reserve(addr, size))
return NULL;
ptr = phys_to_virt(addr);
memset(ptr, 0, 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), cursor, 0);
totalram_pages++;
}
}
static void __init __free_pages_memory(unsigned long start, unsigned long end)
{
int order;
while (start < end) {
order = min(MAX_ORDER - 1UL, __ffs(start));
while (start + (1UL << order) > end)
order--;
__free_pages_bootmem(pfn_to_page(start), start, order);
start += (1UL << order);
}
}
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;
}
static unsigned long __init free_low_memory_core_early(void)
{
unsigned long count = 0;
phys_addr_t start, end;
u64 i;
memblock_clear_hotplug(0, -1);
for_each_reserved_mem_region(i, &start, &end)
reserve_bootmem_region(start, end);
mm/memblock: add extra "flags" to memblock to allow selection of memory based on attribute Some high end Intel Xeon systems report uncorrectable memory errors as a recoverable machine check. Linux has included code for some time to process these and just signal the affected processes (or even recover completely if the error was in a read only page that can be replaced by reading from disk). But we have no recovery path for errors encountered during kernel code execution. Except for some very specific cases were are unlikely to ever be able to recover. Enter memory mirroring. Actually 3rd generation of memory mirroing. Gen1: All memory is mirrored Pro: No s/w enabling - h/w just gets good data from other side of the mirror Con: Halves effective memory capacity available to OS/applications Gen2: Partial memory mirror - just mirror memory begind some memory controllers Pro: Keep more of the capacity Con: Nightmare to enable. Have to choose between allocating from mirrored memory for safety vs. NUMA local memory for performance Gen3: Address range partial memory mirror - some mirror on each memory controller Pro: Can tune the amount of mirror and keep NUMA performance Con: I have to write memory management code to implement The current plan is just to use mirrored memory for kernel allocations. This has been broken into two phases: 1) This patch series - find the mirrored memory, use it for boot time allocations 2) Wade into mm/page_alloc.c and define a ZONE_MIRROR to pick up the unused mirrored memory from mm/memblock.c and only give it out to select kernel allocations (this is still being scoped because page_alloc.c is scary). This patch (of 3): Add extra "flags" to memblock to allow selection of memory based on attribute. No functional changes Signed-off-by: Tony Luck <tony.luck@intel.com> Cc: Xishi Qiu <qiuxishi@huawei.com> Cc: Hanjun Guo <guohanjun@huawei.com> Cc: Xiexiuqi <xiexiuqi@huawei.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Naoya Horiguchi <nao.horiguchi@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-06-24 23:58:09 +00:00
for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end,
NULL)
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
count += __free_memory_core(start, end);
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
{
phys_addr_t size;
/* Free memblock.reserved array if it was allocated */
size = get_allocated_memblock_reserved_regions_info(&start);
if (size)
count += __free_memory_core(start, start + size);
/* Free memblock.memory array if it was allocated */
size = get_allocated_memblock_memory_regions_info(&start);
if (size)
count += __free_memory_core(start, start + size);
}
#endif
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>
2013-07-03 22:03:11 +00:00
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>
2012-12-12 21:52:12 +00:00
{
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>
2013-07-03 22:03:11 +00:00
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>
2013-07-03 22:03:11 +00:00
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>
2013-07-03 22:03:11 +00:00
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>
2012-12-12 21:52:12 +00:00
}
/**
* free_all_bootmem - release free pages to the buddy allocator
*
* Returns the number of pages actually released.
*/
unsigned long __init free_all_bootmem(void)
{
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>
2013-07-03 22:03:24 +00:00
unsigned long pages;
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>
2013-07-03 22:03:11 +00:00
reset_all_zones_managed_pages();
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
/*
* We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id
* because in some case like Node0 doesn't have RAM installed
* low ram will be on Node1
*/
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>
2013-07-03 22:03:24 +00:00
pages = free_low_memory_core_early();
totalram_pages += pages;
return pages;
}
/**
* 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)
{
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)
{
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(NUMA_NO_NODE, 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(NUMA_NO_NODE, 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);
}
static 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);
}