linux-sg2042/mm/memblock.c

1595 lines
45 KiB
C
Raw Normal View History

/*
* Procedures for maintaining information about logical memory blocks.
*
* Peter Bergner, IBM Corp. June 2001.
* Copyright (C) 2001 Peter Bergner.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/bitops.h>
#include <linux/poison.h>
#include <linux/pfn.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/memblock.h>
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
#include <asm-generic/sections.h>
mm/memblock: add memblock memory allocation apis Introduce memblock memory allocation APIs which allow to support PAE or LPAE extension on 32 bits archs where the physical memory start address can be beyond 4GB. In such cases, existing bootmem APIs which operate on 32 bit addresses won't work and needs memblock layer which operates on 64 bit addresses. So we add equivalent APIs so that we can replace usage of bootmem with memblock interfaces. Architectures already converted to NO_BOOTMEM use these new memblock interfaces. The architectures which are still not converted to NO_BOOTMEM continue to function as is because we still maintain the fal lback option of bootmem back-end supporting these new interfaces. So no functional change as such. In long run, once all the architectures moves to NO_BOOTMEM, we can get rid of bootmem layer completely. This is one step to remove the core code dependency with bootmem and also gives path for architectures to move away from bootmem. The proposed interface will became active if both CONFIG_HAVE_MEMBLOCK and CONFIG_NO_BOOTMEM are specified by arch. In case !CONFIG_NO_BOOTMEM, the memblock() wrappers will fallback to the existing bootmem apis so that arch's not converted to NO_BOOTMEM continue to work as is. The meaning of MEMBLOCK_ALLOC_ACCESSIBLE and MEMBLOCK_ALLOC_ANYWHERE is kept same. [akpm@linux-foundation.org: s/depricated/deprecated/] Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Walmsley <paul@pwsan.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Lindgren <tony@atomide.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:50:19 +08:00
#include <linux/io.h>
#include "internal.h"
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock;
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
static struct memblock_region memblock_physmem_init_regions[INIT_PHYSMEM_REGIONS] __initdata_memblock;
#endif
struct memblock memblock __initdata_memblock = {
.memory.regions = memblock_memory_init_regions,
.memory.cnt = 1, /* empty dummy entry */
.memory.max = INIT_MEMBLOCK_REGIONS,
.reserved.regions = memblock_reserved_init_regions,
.reserved.cnt = 1, /* empty dummy entry */
.reserved.max = INIT_MEMBLOCK_REGIONS,
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
.physmem.regions = memblock_physmem_init_regions,
.physmem.cnt = 1, /* empty dummy entry */
.physmem.max = INIT_PHYSMEM_REGIONS,
#endif
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
.bottom_up = false,
.current_limit = MEMBLOCK_ALLOC_ANYWHERE,
};
int memblock_debug __initdata_memblock;
memblock, mem_hotplug: make memblock skip hotpluggable regions if needed Linux kernel cannot migrate pages used by the kernel. As a result, hotpluggable memory used by the kernel won't be able to be hot-removed. To solve this problem, the basic idea is to prevent memblock from allocating hotpluggable memory for the kernel at early time, and arrange all hotpluggable memory in ACPI SRAT(System Resource Affinity Table) as ZONE_MOVABLE when initializing zones. In the previous patches, we have marked hotpluggable memory regions with MEMBLOCK_HOTPLUG flag in memblock.memory. In this patch, we make memblock skip these hotpluggable memory regions in the default top-down allocation function if movable_node boot option is specified. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Liu Jiang <jiang.liu@huawei.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:35 +08:00
#ifdef CONFIG_MOVABLE_NODE
bool movable_node_enabled __initdata_memblock = false;
#endif
memblock: s/memblock_analyze()/memblock_allow_resize()/ and update users The only function of memblock_analyze() is now allowing resize of memblock region arrays. Rename it to memblock_allow_resize() and update its users. * The following users remain the same other than renaming. arm/mm/init.c::arm_memblock_init() microblaze/kernel/prom.c::early_init_devtree() powerpc/kernel/prom.c::early_init_devtree() openrisc/kernel/prom.c::early_init_devtree() sh/mm/init.c::paging_init() sparc/mm/init_64.c::paging_init() unicore32/mm/init.c::uc32_memblock_init() * In the following users, analyze was used to update total size which is no longer necessary. powerpc/kernel/machine_kexec.c::reserve_crashkernel() powerpc/kernel/prom.c::early_init_devtree() powerpc/mm/init_32.c::MMU_init() powerpc/mm/tlb_nohash.c::__early_init_mmu() powerpc/platforms/ps3/mm.c::ps3_mm_add_memory() powerpc/platforms/embedded6xx/wii.c::wii_memory_fixups() sh/kernel/machine_kexec.c::reserve_crashkernel() * x86/kernel/e820.c::memblock_x86_fill() was directly setting memblock_can_resize before populating memblock and calling analyze afterwards. Call memblock_allow_resize() before start populating. memblock_can_resize is now static inside memblock.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: "H. Peter Anvin" <hpa@zytor.com>
2011-12-09 02:22:08 +08:00
static int memblock_can_resize __initdata_memblock;
static int memblock_memory_in_slab __initdata_memblock = 0;
static int memblock_reserved_in_slab __initdata_memblock = 0;
/* inline so we don't get a warning when pr_debug is compiled out */
static __init_memblock const char *
memblock_type_name(struct memblock_type *type)
{
if (type == &memblock.memory)
return "memory";
else if (type == &memblock.reserved)
return "reserved";
else
return "unknown";
}
/* adjust *@size so that (@base + *@size) doesn't overflow, return new size */
static inline phys_addr_t memblock_cap_size(phys_addr_t base, phys_addr_t *size)
{
return *size = min(*size, (phys_addr_t)ULLONG_MAX - base);
}
/*
* Address comparison utilities
*/
static unsigned long __init_memblock memblock_addrs_overlap(phys_addr_t base1, phys_addr_t size1,
phys_addr_t base2, phys_addr_t size2)
{
return ((base1 < (base2 + size2)) && (base2 < (base1 + size1)));
}
static long __init_memblock memblock_overlaps_region(struct memblock_type *type,
phys_addr_t base, phys_addr_t size)
{
unsigned long i;
for (i = 0; i < type->cnt; i++) {
phys_addr_t rgnbase = type->regions[i].base;
phys_addr_t rgnsize = type->regions[i].size;
if (memblock_addrs_overlap(base, size, rgnbase, rgnsize))
break;
}
return (i < type->cnt) ? i : -1;
}
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
/*
* __memblock_find_range_bottom_up - find free area utility in bottom-up
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
*
* Utility called from memblock_find_in_range_node(), find free area bottom-up.
*
* RETURNS:
* Found address on success, 0 on failure.
*/
static phys_addr_t __init_memblock
__memblock_find_range_bottom_up(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid)
{
phys_addr_t this_start, this_end, cand;
u64 i;
for_each_free_mem_range(i, nid, &this_start, &this_end, NULL) {
this_start = clamp(this_start, start, end);
this_end = clamp(this_end, start, end);
cand = round_up(this_start, align);
if (cand < this_end && this_end - cand >= size)
return cand;
}
return 0;
}
/**
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
* __memblock_find_range_top_down - find free area utility, in top-down
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
* @size: size of free area to find
* @align: alignment of free area to find
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
* Utility called from memblock_find_in_range_node(), find free area top-down.
*
* RETURNS:
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
* Found address on success, 0 on failure.
*/
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
static phys_addr_t __init_memblock
__memblock_find_range_top_down(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid)
{
phys_addr_t this_start, this_end, cand;
u64 i;
for_each_free_mem_range_reverse(i, nid, &this_start, &this_end, NULL) {
this_start = clamp(this_start, start, end);
this_end = clamp(this_end, start, end);
if (this_end < size)
continue;
cand = round_down(this_end - size, align);
if (cand >= this_start)
return cand;
}
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
return 0;
}
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
/**
* memblock_find_in_range_node - find free area in given range and node
* @size: size of free area to find
* @align: alignment of free area to find
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
*
* Find @size free area aligned to @align in the specified range and node.
*
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
* When allocation direction is bottom-up, the @start should be greater
* than the end of the kernel image. Otherwise, it will be trimmed. The
* reason is that we want the bottom-up allocation just near the kernel
* image so it is highly likely that the allocated memory and the kernel
* will reside in the same node.
*
* If bottom-up allocation failed, will try to allocate memory top-down.
*
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
* RETURNS:
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
* Found address on success, 0 on failure.
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
*/
phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
phys_addr_t end, int nid)
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
{
phys_addr_t kernel_end, ret;
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
/* pump up @end */
if (end == MEMBLOCK_ALLOC_ACCESSIBLE)
end = memblock.current_limit;
/* avoid allocating the first page */
start = max_t(phys_addr_t, start, PAGE_SIZE);
end = max(start, end);
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
kernel_end = __pa_symbol(_end);
/*
* try bottom-up allocation only when bottom-up mode
* is set and @end is above the kernel image.
*/
if (memblock_bottom_up() && end > kernel_end) {
phys_addr_t bottom_up_start;
/* make sure we will allocate above the kernel */
bottom_up_start = max(start, kernel_end);
/* ok, try bottom-up allocation first */
ret = __memblock_find_range_bottom_up(bottom_up_start, end,
size, align, nid);
if (ret)
return ret;
/*
* we always limit bottom-up allocation above the kernel,
* but top-down allocation doesn't have the limit, so
* retrying top-down allocation may succeed when bottom-up
* allocation failed.
*
* bottom-up allocation is expected to be fail very rarely,
* so we use WARN_ONCE() here to see the stack trace if
* fail happens.
*/
WARN_ONCE(1, "memblock: bottom-up allocation failed, "
"memory hotunplug may be affected\n");
}
mm/memblock.c: factor out of top-down allocation [Problem] The current Linux cannot migrate pages used by the kernel because of the kernel direct mapping. In Linux kernel space, va = pa + PAGE_OFFSET. When the pa is changed, we cannot simply update the pagetable and keep the va unmodified. So the kernel pages are not migratable. There are also some other issues will cause the kernel pages not migratable. For example, the physical address may be cached somewhere and will be used. It is not to update all the caches. When doing memory hotplug in Linux, we first migrate all the pages in one memory device somewhere else, and then remove the device. But if pages are used by the kernel, they are not migratable. As a result, memory used by the kernel cannot be hot-removed. Modifying the kernel direct mapping mechanism is too difficult to do. And it may cause the kernel performance down and unstable. So we use the following way to do memory hotplug. [What we are doing] In Linux, memory in one numa node is divided into several zones. One of the zones is ZONE_MOVABLE, which the kernel won't use. In order to implement memory hotplug in Linux, we are going to arrange all hotpluggable memory in ZONE_MOVABLE so that the kernel won't use these memory. To do this, we need ACPI's help. In ACPI, SRAT(System Resource Affinity Table) contains NUMA info. The memory affinities in SRAT record every memory range in the system, and also, flags specifying if the memory range is hotpluggable. (Please refer to ACPI spec 5.0 5.2.16) With the help of SRAT, we have to do the following two things to achieve our goal: 1. When doing memory hot-add, allow the users arranging hotpluggable as ZONE_MOVABLE. (This has been done by the MOVABLE_NODE functionality in Linux.) 2. when the system is booting, prevent bootmem allocator from allocating hotpluggable memory for the kernel before the memory initialization finishes. The problem 2 is the key problem we are going to solve. But before solving it, we need some preparation. Please see below. [Preparation] Bootloader has to load the kernel image into memory. And this memory must be unhotpluggable. We cannot prevent this anyway. So in a memory hotplug system, we can assume any node the kernel resides in is not hotpluggable. Before SRAT is parsed, we don't know which memory ranges are hotpluggable. But memblock has already started to work. In the current kernel, memblock allocates the following memory before SRAT is parsed: setup_arch() |->memblock_x86_fill() /* memblock is ready */ |...... |->early_reserve_e820_mpc_new() /* allocate memory under 1MB */ |->reserve_real_mode() /* allocate memory under 1MB */ |->init_mem_mapping() /* allocate page tables, about 2MB to map 1GB memory */ |->dma_contiguous_reserve() /* specified by user, should be low */ |->setup_log_buf() /* specified by user, several mega bytes */ |->relocate_initrd() /* could be large, but will be freed after boot, should reorder */ |->acpi_initrd_override() /* several mega bytes */ |->reserve_crashkernel() /* could be large, should reorder */ |...... |->initmem_init() /* Parse SRAT */ According to Tejun's advice, before SRAT is parsed, we should try our best to allocate memory near the kernel image. Since the whole node the kernel resides in won't be hotpluggable, and for a modern server, a node may have at least 16GB memory, allocating several mega bytes memory around the kernel image won't cross to hotpluggable memory. [About this patchset] So this patchset is the preparation for the problem 2 that we want to solve. It does the following: 1. Make memblock be able to allocate memory bottom up. 1) Keep all the memblock APIs' prototype unmodified. 2) When the direction is bottom up, keep the start address greater than the end of kernel image. 2. Improve init_mem_mapping() to support allocate page tables in bottom up direction. 3. Introduce "movable_node" boot option to enable and disable this functionality. This patch (of 6): Create a new function __memblock_find_range_top_down to factor out of top-down allocation from memblock_find_in_range_node. This is a preparation because we will introduce a new bottom-up allocation mode in the following patch. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Tejun Heo <tj@kernel.org> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:57 +08:00
return __memblock_find_range_top_down(start, end, size, align, nid);
}
/**
* memblock_find_in_range - find free area in given range
* @start: start of candidate range
* @end: end of candidate range, can be %MEMBLOCK_ALLOC_{ANYWHERE|ACCESSIBLE}
* @size: size of free area to find
* @align: alignment of free area to find
*
* Find @size free area aligned to @align in the specified range.
*
* RETURNS:
mm/memblock.c: introduce bottom-up allocation mode The Linux kernel cannot migrate pages used by the kernel. As a result, kernel pages cannot be hot-removed. So we cannot allocate hotpluggable memory for the kernel. ACPI SRAT (System Resource Affinity Table) contains the memory hotplug info. But before SRAT is parsed, memblock has already started to allocate memory for the kernel. So we need to prevent memblock from doing this. In a memory hotplug system, any numa node the kernel resides in should be unhotpluggable. And for a modern server, each node could have at least 16GB memory. So memory around the kernel image is highly likely unhotpluggable. So the basic idea is: Allocate memory from the end of the kernel image and to the higher memory. Since memory allocation before SRAT is parsed won't be too much, it could highly likely be in the same node with kernel image. The current memblock can only allocate memory top-down. So this patch introduces a new bottom-up allocation mode to allocate memory bottom-up. And later when we use this allocation direction to allocate memory, we will limit the start address above the kernel. Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Acked-by: Toshi Kani <toshi.kani@hp.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@elte.hu> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Tejun Heo <tj@kernel.org> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Thomas Renninger <trenn@suse.de> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Rik van Riel <riel@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kamezawa Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2013-11-13 07:07:59 +08:00
* Found address on success, 0 on failure.
*/
phys_addr_t __init_memblock memblock_find_in_range(phys_addr_t start,
phys_addr_t end, phys_addr_t size,
phys_addr_t align)
{
return memblock_find_in_range_node(size, align, start, end,
NUMA_NO_NODE);
}
static void __init_memblock memblock_remove_region(struct memblock_type *type, unsigned long r)
{
type->total_size -= type->regions[r].size;
memmove(&type->regions[r], &type->regions[r + 1],
(type->cnt - (r + 1)) * sizeof(type->regions[r]));
type->cnt--;
/* Special case for empty arrays */
if (type->cnt == 0) {
WARN_ON(type->total_size != 0);
type->cnt = 1;
type->regions[0].base = 0;
type->regions[0].size = 0;
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
type->regions[0].flags = 0;
memblock_set_region_node(&type->regions[0], MAX_NUMNODES);
}
}
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
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>
2012-07-12 05:02:56 +08:00
phys_addr_t __init_memblock get_allocated_memblock_reserved_regions_info(
phys_addr_t *addr)
{
if (memblock.reserved.regions == memblock_reserved_init_regions)
return 0;
*addr = __pa(memblock.reserved.regions);
return PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.reserved.max);
}
phys_addr_t __init_memblock get_allocated_memblock_memory_regions_info(
phys_addr_t *addr)
{
if (memblock.memory.regions == memblock_memory_init_regions)
return 0;
*addr = __pa(memblock.memory.regions);
return PAGE_ALIGN(sizeof(struct memblock_region) *
memblock.memory.max);
}
#endif
/**
* memblock_double_array - double the size of the memblock regions array
* @type: memblock type of the regions array being doubled
* @new_area_start: starting address of memory range to avoid overlap with
* @new_area_size: size of memory range to avoid overlap with
*
* Double the size of the @type regions array. If memblock is being used to
* allocate memory for a new reserved regions array and there is a previously
* allocated memory range [@new_area_start,@new_area_start+@new_area_size]
* waiting to be reserved, ensure the memory used by the new array does
* not overlap.
*
* RETURNS:
* 0 on success, -1 on failure.
*/
static int __init_memblock memblock_double_array(struct memblock_type *type,
phys_addr_t new_area_start,
phys_addr_t new_area_size)
{
struct memblock_region *new_array, *old_array;
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>
2012-07-12 05:02:56 +08:00
phys_addr_t old_alloc_size, new_alloc_size;
phys_addr_t old_size, new_size, addr;
int use_slab = slab_is_available();
int *in_slab;
/* We don't allow resizing until we know about the reserved regions
* of memory that aren't suitable for allocation
*/
if (!memblock_can_resize)
return -1;
/* Calculate new doubled size */
old_size = type->max * sizeof(struct memblock_region);
new_size = old_size << 1;
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>
2012-07-12 05:02:56 +08:00
/*
* We need to allocated new one align to PAGE_SIZE,
* so we can free them completely later.
*/
old_alloc_size = PAGE_ALIGN(old_size);
new_alloc_size = PAGE_ALIGN(new_size);
/* Retrieve the slab flag */
if (type == &memblock.memory)
in_slab = &memblock_memory_in_slab;
else
in_slab = &memblock_reserved_in_slab;
/* Try to find some space for it.
*
* WARNING: We assume that either slab_is_available() and we use it or
* we use MEMBLOCK for allocations. That means that this is unsafe to
* use when bootmem is currently active (unless bootmem itself is
* implemented on top of MEMBLOCK which isn't the case yet)
*
* This should however not be an issue for now, as we currently only
* call into MEMBLOCK while it's still active, or much later when slab
* is active for memory hotplug operations
*/
if (use_slab) {
new_array = kmalloc(new_size, GFP_KERNEL);
addr = new_array ? __pa(new_array) : 0;
} else {
/* only exclude range when trying to double reserved.regions */
if (type != &memblock.reserved)
new_area_start = new_area_size = 0;
addr = memblock_find_in_range(new_area_start + new_area_size,
memblock.current_limit,
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>
2012-07-12 05:02:56 +08:00
new_alloc_size, PAGE_SIZE);
if (!addr && new_area_size)
addr = memblock_find_in_range(0,
min(new_area_start, memblock.current_limit),
new_alloc_size, PAGE_SIZE);
new_array = addr ? __va(addr) : NULL;
}
if (!addr) {
pr_err("memblock: Failed to double %s array from %ld to %ld entries !\n",
memblock_type_name(type), type->max, type->max * 2);
return -1;
}
memblock_dbg("memblock: %s is doubled to %ld at [%#010llx-%#010llx]",
memblock_type_name(type), type->max * 2, (u64)addr,
(u64)addr + new_size - 1);
/*
* Found space, we now need to move the array over before we add the
* reserved region since it may be our reserved array itself that is
* full.
*/
memcpy(new_array, type->regions, old_size);
memset(new_array + type->max, 0, old_size);
old_array = type->regions;
type->regions = new_array;
type->max <<= 1;
/* Free old array. We needn't free it if the array is the static one */
if (*in_slab)
kfree(old_array);
else if (old_array != memblock_memory_init_regions &&
old_array != memblock_reserved_init_regions)
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>
2012-07-12 05:02:56 +08:00
memblock_free(__pa(old_array), old_alloc_size);
/*
* Reserve the new array if that comes from the memblock. Otherwise, we
* needn't do it
*/
if (!use_slab)
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>
2012-07-12 05:02:56 +08:00
BUG_ON(memblock_reserve(addr, new_alloc_size));
/* Update slab flag */
*in_slab = use_slab;
return 0;
}
/**
* memblock_merge_regions - merge neighboring compatible regions
* @type: memblock type to scan
*
* Scan @type and merge neighboring compatible regions.
*/
static void __init_memblock memblock_merge_regions(struct memblock_type *type)
{
int i = 0;
/* cnt never goes below 1 */
while (i < type->cnt - 1) {
struct memblock_region *this = &type->regions[i];
struct memblock_region *next = &type->regions[i + 1];
if (this->base + this->size != next->base ||
memblock_get_region_node(this) !=
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
memblock_get_region_node(next) ||
this->flags != next->flags) {
BUG_ON(this->base + this->size > next->base);
i++;
continue;
}
this->size += next->size;
/* move forward from next + 1, index of which is i + 2 */
memmove(next, next + 1, (type->cnt - (i + 2)) * sizeof(*next));
type->cnt--;
}
}
/**
* memblock_insert_region - insert new memblock region
* @type: memblock type to insert into
* @idx: index for the insertion point
* @base: base address of the new region
* @size: size of the new region
* @nid: node id of the new region
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
* @flags: flags of the new region
*
* Insert new memblock region [@base,@base+@size) into @type at @idx.
* @type must already have extra room to accomodate the new region.
*/
static void __init_memblock memblock_insert_region(struct memblock_type *type,
int idx, phys_addr_t base,
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
phys_addr_t size,
int nid, unsigned long flags)
{
struct memblock_region *rgn = &type->regions[idx];
BUG_ON(type->cnt >= type->max);
memmove(rgn + 1, rgn, (type->cnt - idx) * sizeof(*rgn));
rgn->base = base;
rgn->size = size;
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
rgn->flags = flags;
memblock_set_region_node(rgn, nid);
type->cnt++;
type->total_size += size;
}
/**
* memblock_add_range - add new memblock region
* @type: memblock type to add new region into
* @base: base address of the new region
* @size: size of the new region
* @nid: nid of the new region
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
* @flags: flags of the new region
*
* Add new memblock region [@base,@base+@size) into @type. The new region
* is allowed to overlap with existing ones - overlaps don't affect already
* existing regions. @type is guaranteed to be minimal (all neighbouring
* compatible regions are merged) after the addition.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_add_range(struct memblock_type *type,
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
phys_addr_t base, phys_addr_t size,
int nid, unsigned long flags)
{
bool insert = false;
phys_addr_t obase = base;
phys_addr_t end = base + memblock_cap_size(base, &size);
int i, nr_new;
if (!size)
return 0;
/* special case for empty array */
if (type->regions[0].size == 0) {
WARN_ON(type->cnt != 1 || type->total_size);
type->regions[0].base = base;
type->regions[0].size = size;
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
type->regions[0].flags = flags;
memblock_set_region_node(&type->regions[0], nid);
type->total_size = size;
return 0;
}
repeat:
/*
* The following is executed twice. Once with %false @insert and
* then with %true. The first counts the number of regions needed
* to accomodate the new area. The second actually inserts them.
*/
base = obase;
nr_new = 0;
for (i = 0; i < type->cnt; i++) {
struct memblock_region *rgn = &type->regions[i];
phys_addr_t rbase = rgn->base;
phys_addr_t rend = rbase + rgn->size;
if (rbase >= end)
break;
if (rend <= base)
continue;
/*
* @rgn overlaps. If it separates the lower part of new
* area, insert that portion.
*/
if (rbase > base) {
nr_new++;
if (insert)
memblock_insert_region(type, i++, base,
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
rbase - base, nid,
flags);
}
/* area below @rend is dealt with, forget about it */
base = min(rend, end);
}
/* insert the remaining portion */
if (base < end) {
nr_new++;
if (insert)
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
memblock_insert_region(type, i, base, end - base,
nid, flags);
}
/*
* If this was the first round, resize array and repeat for actual
* insertions; otherwise, merge and return.
*/
if (!insert) {
while (type->cnt + nr_new > type->max)
if (memblock_double_array(type, obase, size) < 0)
return -ENOMEM;
insert = true;
goto repeat;
} else {
memblock_merge_regions(type);
return 0;
}
}
int __init_memblock memblock_add_node(phys_addr_t base, phys_addr_t size,
int nid)
{
return memblock_add_range(&memblock.memory, base, size, nid, 0);
}
int __init_memblock memblock_add(phys_addr_t base, phys_addr_t size)
{
return memblock_add_range(&memblock.memory, base, size,
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
MAX_NUMNODES, 0);
}
/**
* memblock_isolate_range - isolate given range into disjoint memblocks
* @type: memblock type to isolate range for
* @base: base of range to isolate
* @size: size of range to isolate
* @start_rgn: out parameter for the start of isolated region
* @end_rgn: out parameter for the end of isolated region
*
* Walk @type and ensure that regions don't cross the boundaries defined by
* [@base,@base+@size). Crossing regions are split at the boundaries,
* which may create at most two more regions. The index of the first
* region inside the range is returned in *@start_rgn and end in *@end_rgn.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
static int __init_memblock memblock_isolate_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size,
int *start_rgn, int *end_rgn)
{
phys_addr_t end = base + memblock_cap_size(base, &size);
int i;
*start_rgn = *end_rgn = 0;
if (!size)
return 0;
/* we'll create at most two more regions */
while (type->cnt + 2 > type->max)
if (memblock_double_array(type, base, size) < 0)
return -ENOMEM;
for (i = 0; i < type->cnt; i++) {
struct memblock_region *rgn = &type->regions[i];
phys_addr_t rbase = rgn->base;
phys_addr_t rend = rbase + rgn->size;
if (rbase >= end)
break;
if (rend <= base)
continue;
if (rbase < base) {
/*
* @rgn intersects from below. Split and continue
* to process the next region - the new top half.
*/
rgn->base = base;
rgn->size -= base - rbase;
type->total_size -= base - rbase;
memblock_insert_region(type, i, rbase, base - rbase,
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
memblock_get_region_node(rgn),
rgn->flags);
} else if (rend > end) {
/*
* @rgn intersects from above. Split and redo the
* current region - the new bottom half.
*/
rgn->base = end;
rgn->size -= end - rbase;
type->total_size -= end - rbase;
memblock_insert_region(type, i--, rbase, end - rbase,
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
memblock_get_region_node(rgn),
rgn->flags);
} else {
/* @rgn is fully contained, record it */
if (!*end_rgn)
*start_rgn = i;
*end_rgn = i + 1;
}
}
return 0;
}
int __init_memblock memblock_remove_range(struct memblock_type *type,
phys_addr_t base, phys_addr_t size)
{
int start_rgn, end_rgn;
int i, ret;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = end_rgn - 1; i >= start_rgn; i--)
memblock_remove_region(type, i);
return 0;
}
int __init_memblock memblock_remove(phys_addr_t base, phys_addr_t size)
{
return memblock_remove_range(&memblock.memory, base, size);
}
int __init_memblock memblock_free(phys_addr_t base, phys_addr_t size)
{
memblock_dbg(" memblock_free: [%#016llx-%#016llx] %pF\n",
(unsigned long long)base,
mm/memblock: debug: correct displaying of upper memory boundary Current memblock APIs don't work on 32 PAE or LPAE extension arches where the physical memory start address beyond 4GB. The problem was discussed here [3] where Tejun, Yinghai(thanks) proposed a way forward with memblock interfaces. Based on the proposal, this series adds necessary memblock interfaces and convert the core kernel code to use them. Architectures already converted to NO_BOOTMEM use these new interfaces and other which still uses bootmem, these new interfaces just fallback to exiting bootmem APIs. So no functional change in behavior. In long run, once all the architectures moves to NO_BOOTMEM, we can get rid of bootmem layer completely. This is one step to remove the core code dependency with bootmem and also gives path for architectures to move away from bootmem. Testing is done on ARM architecture with 32 bit ARM LAPE machines with normal as well sparse(faked) memory model. This patch (of 23): When debugging is enabled (cmdline has "memblock=debug") the memblock will display upper memory boundary per each allocated/freed memory range wrongly. For example: memblock_reserve: [0x0000009e7e8000-0x0000009e7ed000] _memblock_early_alloc_try_nid_nopanic+0xfc/0x12c The 0x0000009e7ed000 is displayed instead of 0x0000009e7ecfff Hence, correct this by changing formula used to calculate upper memory boundary to (u64)base + size - 1 instead of (u64)base + size everywhere in the debug messages. Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Yinghai Lu <yinghai@kernel.org> Acked-by: Tejun Heo <tj@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Walmsley <paul@pwsan.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Tony Lindgren <tony@atomide.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:17 +08:00
(unsigned long long)base + size - 1,
(void *)_RET_IP_);
kmemleak_free_part(__va(base), size);
return memblock_remove_range(&memblock.reserved, base, size);
}
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
static int __init_memblock memblock_reserve_region(phys_addr_t base,
phys_addr_t size,
int nid,
unsigned long flags)
{
struct memblock_type *_rgn = &memblock.reserved;
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
memblock_dbg("memblock_reserve: [%#016llx-%#016llx] flags %#02lx %pF\n",
(unsigned long long)base,
mm/memblock: debug: correct displaying of upper memory boundary Current memblock APIs don't work on 32 PAE or LPAE extension arches where the physical memory start address beyond 4GB. The problem was discussed here [3] where Tejun, Yinghai(thanks) proposed a way forward with memblock interfaces. Based on the proposal, this series adds necessary memblock interfaces and convert the core kernel code to use them. Architectures already converted to NO_BOOTMEM use these new interfaces and other which still uses bootmem, these new interfaces just fallback to exiting bootmem APIs. So no functional change in behavior. In long run, once all the architectures moves to NO_BOOTMEM, we can get rid of bootmem layer completely. This is one step to remove the core code dependency with bootmem and also gives path for architectures to move away from bootmem. Testing is done on ARM architecture with 32 bit ARM LAPE machines with normal as well sparse(faked) memory model. This patch (of 23): When debugging is enabled (cmdline has "memblock=debug") the memblock will display upper memory boundary per each allocated/freed memory range wrongly. For example: memblock_reserve: [0x0000009e7e8000-0x0000009e7ed000] _memblock_early_alloc_try_nid_nopanic+0xfc/0x12c The 0x0000009e7ed000 is displayed instead of 0x0000009e7ecfff Hence, correct this by changing formula used to calculate upper memory boundary to (u64)base + size - 1 instead of (u64)base + size everywhere in the debug messages. Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Yinghai Lu <yinghai@kernel.org> Acked-by: Tejun Heo <tj@kernel.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Russell King <linux@arm.linux.org.uk> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Walmsley <paul@pwsan.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Tony Lindgren <tony@atomide.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:17 +08:00
(unsigned long long)base + size - 1,
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
flags, (void *)_RET_IP_);
return memblock_add_range(_rgn, base, size, nid, flags);
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
}
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
int __init_memblock memblock_reserve(phys_addr_t base, phys_addr_t size)
{
return memblock_reserve_region(base, size, MAX_NUMNODES, 0);
}
memblock, mem_hotplug: introduce MEMBLOCK_HOTPLUG flag to mark hotpluggable regions In find_hotpluggable_memory, once we find out a memory region which is hotpluggable, we want to mark them in memblock.memory. So that we could control memblock allocator not to allocte hotpluggable memory for the kernel later. To achieve this goal, we introduce MEMBLOCK_HOTPLUG flag to indicate the hotpluggable memory regions in memblock and a function memblock_mark_hotplug() to mark hotpluggable memory if we find one. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Liu Jiang <jiang.liu@huawei.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:23 +08:00
/**
* memblock_mark_hotplug - Mark hotpluggable memory with flag MEMBLOCK_HOTPLUG.
* @base: the base phys addr of the region
* @size: the size of the region
*
* This function isolates region [@base, @base + @size), and mark it with flag
* MEMBLOCK_HOTPLUG.
*
* Return 0 on succees, -errno on failure.
*/
int __init_memblock memblock_mark_hotplug(phys_addr_t base, phys_addr_t size)
{
struct memblock_type *type = &memblock.memory;
int i, ret, start_rgn, end_rgn;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = start_rgn; i < end_rgn; i++)
memblock_set_region_flags(&type->regions[i], MEMBLOCK_HOTPLUG);
memblock_merge_regions(type);
return 0;
}
/**
* memblock_clear_hotplug - Clear flag MEMBLOCK_HOTPLUG for a specified region.
* @base: the base phys addr of the region
* @size: the size of the region
*
* This function isolates region [@base, @base + @size), and clear flag
* MEMBLOCK_HOTPLUG for the isolated regions.
*
* Return 0 on succees, -errno on failure.
*/
int __init_memblock memblock_clear_hotplug(phys_addr_t base, phys_addr_t size)
{
struct memblock_type *type = &memblock.memory;
int i, ret, start_rgn, end_rgn;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = start_rgn; i < end_rgn; i++)
memblock_clear_region_flags(&type->regions[i],
MEMBLOCK_HOTPLUG);
memblock_merge_regions(type);
return 0;
}
/**
* __next__mem_range - next function for for_each_free_mem_range() etc.
* @idx: pointer to u64 loop variable
* @nid: node selector, %NUMA_NO_NODE for all nodes
* @type_a: pointer to memblock_type from where the range is taken
* @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
* Find the first area from *@idx which matches @nid, fill the out
* parameters, and update *@idx for the next iteration. The lower 32bit of
* *@idx contains index into type_a and the upper 32bit indexes the
* areas before each region in type_b. For example, if type_b regions
* look like the following,
*
* 0:[0-16), 1:[32-48), 2:[128-130)
*
* The upper 32bit indexes the following regions.
*
* 0:[0-0), 1:[16-32), 2:[48-128), 3:[130-MAX)
*
* As both region arrays are sorted, the function advances the two indices
* in lockstep and returns each intersection.
*/
void __init_memblock __next_mem_range(u64 *idx, int nid,
struct memblock_type *type_a,
struct memblock_type *type_b,
phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid)
{
int idx_a = *idx & 0xffffffff;
int idx_b = *idx >> 32;
if (WARN_ONCE(nid == MAX_NUMNODES,
"Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
for (; idx_a < type_a->cnt; idx_a++) {
struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
int m_nid = memblock_get_region_node(m);
/* only memory regions are associated with nodes, check it */
if (nid != NUMA_NO_NODE && nid != m_nid)
continue;
/* skip hotpluggable memory regions if needed */
if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
continue;
if (!type_b) {
if (out_start)
*out_start = m_start;
if (out_end)
*out_end = m_end;
if (out_nid)
*out_nid = m_nid;
idx_a++;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
/* scan areas before each reservation */
for (; idx_b < type_b->cnt + 1; idx_b++) {
struct memblock_region *r;
phys_addr_t r_start;
phys_addr_t r_end;
r = &type_b->regions[idx_b];
r_start = idx_b ? r[-1].base + r[-1].size : 0;
r_end = idx_b < type_b->cnt ?
r->base : ULLONG_MAX;
/*
* if idx_b advanced past idx_a,
* break out to advance idx_a
*/
if (r_start >= m_end)
break;
/* if the two regions intersect, we're done */
if (m_start < r_end) {
if (out_start)
*out_start =
max(m_start, r_start);
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
*out_nid = m_nid;
/*
* The region which ends first is
* advanced for the next iteration.
*/
if (m_end <= r_end)
idx_a++;
else
idx_b++;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
}
/* signal end of iteration */
*idx = ULLONG_MAX;
}
/**
* __next_mem_range_rev - generic next function for for_each_*_range_rev()
*
* Finds the next range from type_a which is not marked as unsuitable
* in type_b.
*
* @idx: pointer to u64 loop variable
* @nid: nid: node selector, %NUMA_NO_NODE for all nodes
* @type_a: pointer to memblock_type from where the range is taken
* @type_b: pointer to memblock_type which excludes memory from being taken
* @out_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @out_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @out_nid: ptr to int for nid of the range, can be %NULL
*
* Reverse of __next_mem_range().
*/
void __init_memblock __next_mem_range_rev(u64 *idx, int nid,
struct memblock_type *type_a,
struct memblock_type *type_b,
phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid)
{
int idx_a = *idx & 0xffffffff;
int idx_b = *idx >> 32;
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
if (*idx == (u64)ULLONG_MAX) {
idx_a = type_a->cnt - 1;
idx_b = type_b->cnt;
}
for (; idx_a >= 0; idx_a--) {
struct memblock_region *m = &type_a->regions[idx_a];
phys_addr_t m_start = m->base;
phys_addr_t m_end = m->base + m->size;
int m_nid = memblock_get_region_node(m);
/* only memory regions are associated with nodes, check it */
if (nid != NUMA_NO_NODE && nid != m_nid)
continue;
memblock, mem_hotplug: make memblock skip hotpluggable regions if needed Linux kernel cannot migrate pages used by the kernel. As a result, hotpluggable memory used by the kernel won't be able to be hot-removed. To solve this problem, the basic idea is to prevent memblock from allocating hotpluggable memory for the kernel at early time, and arrange all hotpluggable memory in ACPI SRAT(System Resource Affinity Table) as ZONE_MOVABLE when initializing zones. In the previous patches, we have marked hotpluggable memory regions with MEMBLOCK_HOTPLUG flag in memblock.memory. In this patch, we make memblock skip these hotpluggable memory regions in the default top-down allocation function if movable_node boot option is specified. [akpm@linux-foundation.org: coding-style fixes] Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Signed-off-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Liu Jiang <jiang.liu@huawei.com> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Wen Congyang <wency@cn.fujitsu.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:35 +08:00
/* skip hotpluggable memory regions if needed */
if (movable_node_is_enabled() && memblock_is_hotpluggable(m))
continue;
if (!type_b) {
if (out_start)
*out_start = m_start;
if (out_end)
*out_end = m_end;
if (out_nid)
*out_nid = m_nid;
idx_a++;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
/* scan areas before each reservation */
for (; idx_b >= 0; idx_b--) {
struct memblock_region *r;
phys_addr_t r_start;
phys_addr_t r_end;
r = &type_b->regions[idx_b];
r_start = idx_b ? r[-1].base + r[-1].size : 0;
r_end = idx_b < type_b->cnt ?
r->base : ULLONG_MAX;
/*
* if idx_b advanced past idx_a,
* break out to advance idx_a
*/
if (r_end <= m_start)
break;
/* if the two regions intersect, we're done */
if (m_end > r_start) {
if (out_start)
*out_start = max(m_start, r_start);
if (out_end)
*out_end = min(m_end, r_end);
if (out_nid)
*out_nid = m_nid;
if (m_start >= r_start)
idx_a--;
else
idx_b--;
*idx = (u32)idx_a | (u64)idx_b << 32;
return;
}
}
}
/* signal end of iteration */
*idx = ULLONG_MAX;
}
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
/*
* Common iterator interface used to define for_each_mem_range().
*/
void __init_memblock __next_mem_pfn_range(int *idx, int nid,
unsigned long *out_start_pfn,
unsigned long *out_end_pfn, int *out_nid)
{
struct memblock_type *type = &memblock.memory;
struct memblock_region *r;
while (++*idx < type->cnt) {
r = &type->regions[*idx];
if (PFN_UP(r->base) >= PFN_DOWN(r->base + r->size))
continue;
if (nid == MAX_NUMNODES || nid == r->nid)
break;
}
if (*idx >= type->cnt) {
*idx = -1;
return;
}
if (out_start_pfn)
*out_start_pfn = PFN_UP(r->base);
if (out_end_pfn)
*out_end_pfn = PFN_DOWN(r->base + r->size);
if (out_nid)
*out_nid = r->nid;
}
/**
* memblock_set_node - set node ID on memblock regions
* @base: base of area to set node ID for
* @size: size of area to set node ID for
* @type: memblock type to set node ID for
* @nid: node ID to set
*
* Set the nid of memblock @type regions in [@base,@base+@size) to @nid.
* Regions which cross the area boundaries are split as necessary.
*
* RETURNS:
* 0 on success, -errno on failure.
*/
int __init_memblock memblock_set_node(phys_addr_t base, phys_addr_t size,
struct memblock_type *type, int nid)
{
int start_rgn, end_rgn;
int i, ret;
ret = memblock_isolate_range(type, base, size, &start_rgn, &end_rgn);
if (ret)
return ret;
for (i = start_rgn; i < end_rgn; i++)
memblock_set_region_node(&type->regions[i], nid);
memblock_merge_regions(type);
return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
phys_addr_t end, int nid)
{
phys_addr_t found;
if (!align)
align = SMP_CACHE_BYTES;
found = memblock_find_in_range_node(size, align, start, end, nid);
if (found && !memblock_reserve(found, size)) {
/*
* The min_count is set to 0 so that memblock allocations are
* never reported as leaks.
*/
kmemleak_alloc(__va(found), size, 0, 0);
return found;
}
return 0;
}
phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align,
phys_addr_t start, phys_addr_t end)
{
return memblock_alloc_range_nid(size, align, start, end, NUMA_NO_NODE);
}
static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t max_addr,
int nid)
{
return memblock_alloc_range_nid(size, align, 0, max_addr, nid);
}
phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid)
{
return memblock_alloc_base_nid(size, align, MEMBLOCK_ALLOC_ACCESSIBLE, nid);
}
phys_addr_t __init __memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
{
return memblock_alloc_base_nid(size, align, max_addr, NUMA_NO_NODE);
}
phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys_addr_t max_addr)
{
phys_addr_t alloc;
alloc = __memblock_alloc_base(size, align, max_addr);
if (alloc == 0)
panic("ERROR: Failed to allocate 0x%llx bytes below 0x%llx.\n",
(unsigned long long) size, (unsigned long long) max_addr);
return alloc;
}
phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align)
{
return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid)
{
phys_addr_t res = memblock_alloc_nid(size, align, nid);
if (res)
return res;
return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE);
}
mm/memblock: add memblock memory allocation apis Introduce memblock memory allocation APIs which allow to support PAE or LPAE extension on 32 bits archs where the physical memory start address can be beyond 4GB. In such cases, existing bootmem APIs which operate on 32 bit addresses won't work and needs memblock layer which operates on 64 bit addresses. So we add equivalent APIs so that we can replace usage of bootmem with memblock interfaces. Architectures already converted to NO_BOOTMEM use these new memblock interfaces. The architectures which are still not converted to NO_BOOTMEM continue to function as is because we still maintain the fal lback option of bootmem back-end supporting these new interfaces. So no functional change as such. In long run, once all the architectures moves to NO_BOOTMEM, we can get rid of bootmem layer completely. This is one step to remove the core code dependency with bootmem and also gives path for architectures to move away from bootmem. The proposed interface will became active if both CONFIG_HAVE_MEMBLOCK and CONFIG_NO_BOOTMEM are specified by arch. In case !CONFIG_NO_BOOTMEM, the memblock() wrappers will fallback to the existing bootmem apis so that arch's not converted to NO_BOOTMEM continue to work as is. The meaning of MEMBLOCK_ALLOC_ACCESSIBLE and MEMBLOCK_ALLOC_ANYWHERE is kept same. [akpm@linux-foundation.org: s/depricated/deprecated/] Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Walmsley <paul@pwsan.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Lindgren <tony@atomide.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:50:19 +08:00
/**
* memblock_virt_alloc_internal - allocate boot memory block
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region to allocate (phys address)
* @max_addr: the upper bound of the memory region to allocate (phys address)
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* The @min_addr limit is dropped if it can not be satisfied and the allocation
* will fall back to memory below @min_addr. Also, allocation may fall back
* to any node in the system if the specified node can not
* hold the requested memory.
*
* The allocation is performed from memory region limited by
* memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE.
*
* The memory block is aligned on SMP_CACHE_BYTES if @align == 0.
*
* The phys address of allocated boot memory block is converted to virtual and
* allocated memory is reset to 0.
*
* In addition, function sets the min_count to 0 using kmemleak_alloc for
* allocated boot memory block, so that it is never reported as leaks.
*
* RETURNS:
* Virtual address of allocated memory block on success, NULL on failure.
*/
static void * __init memblock_virt_alloc_internal(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
phys_addr_t alloc;
void *ptr;
if (WARN_ONCE(nid == MAX_NUMNODES, "Usage of MAX_NUMNODES is deprecated. Use NUMA_NO_NODE instead\n"))
nid = NUMA_NO_NODE;
mm/memblock: add memblock memory allocation apis Introduce memblock memory allocation APIs which allow to support PAE or LPAE extension on 32 bits archs where the physical memory start address can be beyond 4GB. In such cases, existing bootmem APIs which operate on 32 bit addresses won't work and needs memblock layer which operates on 64 bit addresses. So we add equivalent APIs so that we can replace usage of bootmem with memblock interfaces. Architectures already converted to NO_BOOTMEM use these new memblock interfaces. The architectures which are still not converted to NO_BOOTMEM continue to function as is because we still maintain the fal lback option of bootmem back-end supporting these new interfaces. So no functional change as such. In long run, once all the architectures moves to NO_BOOTMEM, we can get rid of bootmem layer completely. This is one step to remove the core code dependency with bootmem and also gives path for architectures to move away from bootmem. The proposed interface will became active if both CONFIG_HAVE_MEMBLOCK and CONFIG_NO_BOOTMEM are specified by arch. In case !CONFIG_NO_BOOTMEM, the memblock() wrappers will fallback to the existing bootmem apis so that arch's not converted to NO_BOOTMEM continue to work as is. The meaning of MEMBLOCK_ALLOC_ACCESSIBLE and MEMBLOCK_ALLOC_ANYWHERE is kept same. [akpm@linux-foundation.org: s/depricated/deprecated/] Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Walmsley <paul@pwsan.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Lindgren <tony@atomide.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:50:19 +08:00
/*
* Detect any accidental use of these APIs after slab is ready, as at
* this moment memblock may be deinitialized already and its
* internal data may be destroyed (after execution of free_all_bootmem)
*/
if (WARN_ON_ONCE(slab_is_available()))
return kzalloc_node(size, GFP_NOWAIT, nid);
if (!align)
align = SMP_CACHE_BYTES;
if (max_addr > memblock.current_limit)
max_addr = memblock.current_limit;
mm/memblock: add memblock memory allocation apis Introduce memblock memory allocation APIs which allow to support PAE or LPAE extension on 32 bits archs where the physical memory start address can be beyond 4GB. In such cases, existing bootmem APIs which operate on 32 bit addresses won't work and needs memblock layer which operates on 64 bit addresses. So we add equivalent APIs so that we can replace usage of bootmem with memblock interfaces. Architectures already converted to NO_BOOTMEM use these new memblock interfaces. The architectures which are still not converted to NO_BOOTMEM continue to function as is because we still maintain the fal lback option of bootmem back-end supporting these new interfaces. So no functional change as such. In long run, once all the architectures moves to NO_BOOTMEM, we can get rid of bootmem layer completely. This is one step to remove the core code dependency with bootmem and also gives path for architectures to move away from bootmem. The proposed interface will became active if both CONFIG_HAVE_MEMBLOCK and CONFIG_NO_BOOTMEM are specified by arch. In case !CONFIG_NO_BOOTMEM, the memblock() wrappers will fallback to the existing bootmem apis so that arch's not converted to NO_BOOTMEM continue to work as is. The meaning of MEMBLOCK_ALLOC_ACCESSIBLE and MEMBLOCK_ALLOC_ANYWHERE is kept same. [akpm@linux-foundation.org: s/depricated/deprecated/] Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Walmsley <paul@pwsan.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Lindgren <tony@atomide.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:50:19 +08:00
again:
alloc = memblock_find_in_range_node(size, align, min_addr, max_addr,
nid);
if (alloc)
goto done;
if (nid != NUMA_NO_NODE) {
alloc = memblock_find_in_range_node(size, align, min_addr,
max_addr, NUMA_NO_NODE);
if (alloc)
goto done;
}
if (min_addr) {
min_addr = 0;
goto again;
} else {
goto error;
}
done:
memblock_reserve(alloc, size);
ptr = phys_to_virt(alloc);
memset(ptr, 0, size);
/*
* The min_count is set to 0 so that bootmem allocated blocks
* are never reported as leaks. This is because many of these blocks
* are only referred via the physical address which is not
* looked up by kmemleak.
*/
kmemleak_alloc(ptr, size, 0, 0);
return ptr;
error:
return NULL;
}
/**
* memblock_virt_alloc_try_nid_nopanic - allocate boot memory block
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public version of _memblock_virt_alloc_try_nid_nopanic() which provides
* additional debug information (including caller info), if enabled.
*
* RETURNS:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid_nopanic(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n",
__func__, (u64)size, (u64)align, nid, (u64)min_addr,
(u64)max_addr, (void *)_RET_IP_);
return memblock_virt_alloc_internal(size, align, min_addr,
max_addr, nid);
}
/**
* memblock_virt_alloc_try_nid - allocate boot memory block with panicking
* @size: size of memory block to be allocated in bytes
* @align: alignment of the region and block's size
* @min_addr: the lower bound of the memory region from where the allocation
* is preferred (phys address)
* @max_addr: the upper bound of the memory region from where the allocation
* is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to
* allocate only from memory limited by memblock.current_limit value
* @nid: nid of the free area to find, %NUMA_NO_NODE for any node
*
* Public panicking version of _memblock_virt_alloc_try_nid_nopanic()
* which provides debug information (including caller info), if enabled,
* and panics if the request can not be satisfied.
*
* RETURNS:
* Virtual address of allocated memory block on success, NULL on failure.
*/
void * __init memblock_virt_alloc_try_nid(
phys_addr_t size, phys_addr_t align,
phys_addr_t min_addr, phys_addr_t max_addr,
int nid)
{
void *ptr;
memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx %pF\n",
__func__, (u64)size, (u64)align, nid, (u64)min_addr,
(u64)max_addr, (void *)_RET_IP_);
ptr = memblock_virt_alloc_internal(size, align,
min_addr, max_addr, nid);
if (ptr)
return ptr;
panic("%s: Failed to allocate %llu bytes align=0x%llx nid=%d from=0x%llx max_addr=0x%llx\n",
__func__, (u64)size, (u64)align, nid, (u64)min_addr,
(u64)max_addr);
return NULL;
}
/**
* __memblock_free_early - free boot memory block
* @base: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
* Free boot memory block previously allocated by memblock_virt_alloc_xx() API.
* The freeing memory will not be released to the buddy allocator.
*/
void __init __memblock_free_early(phys_addr_t base, phys_addr_t size)
{
memblock_dbg("%s: [%#016llx-%#016llx] %pF\n",
__func__, (u64)base, (u64)base + size - 1,
(void *)_RET_IP_);
kmemleak_free_part(__va(base), size);
memblock_remove_range(&memblock.reserved, base, size);
mm/memblock: add memblock memory allocation apis Introduce memblock memory allocation APIs which allow to support PAE or LPAE extension on 32 bits archs where the physical memory start address can be beyond 4GB. In such cases, existing bootmem APIs which operate on 32 bit addresses won't work and needs memblock layer which operates on 64 bit addresses. So we add equivalent APIs so that we can replace usage of bootmem with memblock interfaces. Architectures already converted to NO_BOOTMEM use these new memblock interfaces. The architectures which are still not converted to NO_BOOTMEM continue to function as is because we still maintain the fal lback option of bootmem back-end supporting these new interfaces. So no functional change as such. In long run, once all the architectures moves to NO_BOOTMEM, we can get rid of bootmem layer completely. This is one step to remove the core code dependency with bootmem and also gives path for architectures to move away from bootmem. The proposed interface will became active if both CONFIG_HAVE_MEMBLOCK and CONFIG_NO_BOOTMEM are specified by arch. In case !CONFIG_NO_BOOTMEM, the memblock() wrappers will fallback to the existing bootmem apis so that arch's not converted to NO_BOOTMEM continue to work as is. The meaning of MEMBLOCK_ALLOC_ACCESSIBLE and MEMBLOCK_ALLOC_ANYWHERE is kept same. [akpm@linux-foundation.org: s/depricated/deprecated/] Signed-off-by: Grygorii Strashko <grygorii.strashko@ti.com> Signed-off-by: Santosh Shilimkar <santosh.shilimkar@ti.com> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Tejun Heo <tj@kernel.org> Cc: "Rafael J. Wysocki" <rjw@sisk.pl> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Christoph Lameter <cl@linux-foundation.org> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Cc: Michal Hocko <mhocko@suse.cz> Cc: Paul Walmsley <paul@pwsan.com> Cc: Pavel Machek <pavel@ucw.cz> Cc: Russell King <linux@arm.linux.org.uk> Cc: Tony Lindgren <tony@atomide.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:50:19 +08:00
}
/*
* __memblock_free_late - free bootmem block pages directly to buddy allocator
* @addr: phys starting address of the boot memory block
* @size: size of the boot memory block in bytes
*
* This is only useful when the bootmem allocator has already been torn
* down, but we are still initializing the system. Pages are released directly
* to the buddy allocator, no bootmem metadata is updated because it is gone.
*/
void __init __memblock_free_late(phys_addr_t base, phys_addr_t size)
{
u64 cursor, end;
memblock_dbg("%s: [%#016llx-%#016llx] %pF\n",
__func__, (u64)base, (u64)base + size - 1,
(void *)_RET_IP_);
kmemleak_free_part(__va(base), size);
cursor = PFN_UP(base);
end = PFN_DOWN(base + size);
for (; cursor < end; cursor++) {
__free_pages_bootmem(pfn_to_page(cursor), 0);
totalram_pages++;
}
}
/*
* Remaining API functions
*/
phys_addr_t __init memblock_phys_mem_size(void)
{
return memblock.memory.total_size;
}
phys_addr_t __init memblock_mem_size(unsigned long limit_pfn)
{
unsigned long pages = 0;
struct memblock_region *r;
unsigned long start_pfn, end_pfn;
for_each_memblock(memory, r) {
start_pfn = memblock_region_memory_base_pfn(r);
end_pfn = memblock_region_memory_end_pfn(r);
start_pfn = min_t(unsigned long, start_pfn, limit_pfn);
end_pfn = min_t(unsigned long, end_pfn, limit_pfn);
pages += end_pfn - start_pfn;
}
return PFN_PHYS(pages);
}
/* lowest address */
phys_addr_t __init_memblock memblock_start_of_DRAM(void)
{
return memblock.memory.regions[0].base;
}
phys_addr_t __init_memblock memblock_end_of_DRAM(void)
{
int idx = memblock.memory.cnt - 1;
return (memblock.memory.regions[idx].base + memblock.memory.regions[idx].size);
}
void __init memblock_enforce_memory_limit(phys_addr_t limit)
{
phys_addr_t max_addr = (phys_addr_t)ULLONG_MAX;
struct memblock_region *r;
if (!limit)
return;
/* find out max address */
for_each_memblock(memory, r) {
if (limit <= r->size) {
max_addr = r->base + limit;
break;
}
limit -= r->size;
}
/* truncate both memory and reserved regions */
memblock_remove_range(&memblock.memory, max_addr,
(phys_addr_t)ULLONG_MAX);
memblock_remove_range(&memblock.reserved, max_addr,
(phys_addr_t)ULLONG_MAX);
}
static int __init_memblock memblock_search(struct memblock_type *type, phys_addr_t addr)
{
unsigned int left = 0, right = type->cnt;
do {
unsigned int mid = (right + left) / 2;
if (addr < type->regions[mid].base)
right = mid;
else if (addr >= (type->regions[mid].base +
type->regions[mid].size))
left = mid + 1;
else
return mid;
} while (left < right);
return -1;
}
int __init memblock_is_reserved(phys_addr_t addr)
{
return memblock_search(&memblock.reserved, addr) != -1;
}
int __init_memblock memblock_is_memory(phys_addr_t addr)
{
return memblock_search(&memblock.memory, addr) != -1;
}
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int __init_memblock memblock_search_pfn_nid(unsigned long pfn,
unsigned long *start_pfn, unsigned long *end_pfn)
{
struct memblock_type *type = &memblock.memory;
int mid = memblock_search(type, PFN_PHYS(pfn));
if (mid == -1)
return -1;
*start_pfn = PFN_DOWN(type->regions[mid].base);
*end_pfn = PFN_DOWN(type->regions[mid].base + type->regions[mid].size);
return type->regions[mid].nid;
}
#endif
/**
* memblock_is_region_memory - check if a region is a subset of memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base+@size) is a subset of a memory block.
*
* RETURNS:
* 0 if false, non-zero if true
*/
int __init_memblock memblock_is_region_memory(phys_addr_t base, phys_addr_t size)
{
int idx = memblock_search(&memblock.memory, base);
phys_addr_t end = base + memblock_cap_size(base, &size);
if (idx == -1)
return 0;
return memblock.memory.regions[idx].base <= base &&
(memblock.memory.regions[idx].base +
memblock.memory.regions[idx].size) >= end;
}
/**
* memblock_is_region_reserved - check if a region intersects reserved memory
* @base: base of region to check
* @size: size of region to check
*
* Check if the region [@base, @base+@size) intersects a reserved memory block.
*
* RETURNS:
* 0 if false, non-zero if true
*/
int __init_memblock memblock_is_region_reserved(phys_addr_t base, phys_addr_t size)
{
memblock_cap_size(base, &size);
return memblock_overlaps_region(&memblock.reserved, base, size) >= 0;
}
void __init_memblock memblock_trim_memory(phys_addr_t align)
{
phys_addr_t start, end, orig_start, orig_end;
struct memblock_region *r;
for_each_memblock(memory, r) {
orig_start = r->base;
orig_end = r->base + r->size;
start = round_up(orig_start, align);
end = round_down(orig_end, align);
if (start == orig_start && end == orig_end)
continue;
if (start < end) {
r->base = start;
r->size = end - start;
} else {
memblock_remove_region(&memblock.memory,
r - memblock.memory.regions);
r--;
}
}
}
void __init_memblock memblock_set_current_limit(phys_addr_t limit)
{
memblock.current_limit = limit;
}
phys_addr_t __init_memblock memblock_get_current_limit(void)
{
return memblock.current_limit;
}
static void __init_memblock memblock_dump(struct memblock_type *type, char *name)
{
unsigned long long base, size;
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
unsigned long flags;
int i;
pr_info(" %s.cnt = 0x%lx\n", name, type->cnt);
for (i = 0; i < type->cnt; i++) {
struct memblock_region *rgn = &type->regions[i];
char nid_buf[32] = "";
base = rgn->base;
size = rgn->size;
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
flags = rgn->flags;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
if (memblock_get_region_node(rgn) != MAX_NUMNODES)
snprintf(nid_buf, sizeof(nid_buf), " on node %d",
memblock_get_region_node(rgn));
#endif
memblock, numa: introduce flags field into memblock There is no flag in memblock to describe what type the memory is. Sometimes, we may use memblock to reserve some memory for special usage. And we want to know what kind of memory it is. So we need a way to In hotplug environment, we want to reserve hotpluggable memory so the kernel won't be able to use it. And when the system is up, we have to free these hotpluggable memory to buddy. So we need to mark these memory first. In order to do so, we need to mark out these special memory in memblock. In this patch, we introduce a new "flags" member into memblock_region: struct memblock_region { phys_addr_t base; phys_addr_t size; unsigned long flags; /* This is new. */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int nid; #endif }; This patch does the following things: 1) Add "flags" member to memblock_region. 2) Modify the following APIs' prototype: memblock_add_region() memblock_insert_region() 3) Add memblock_reserve_region() to support reserve memory with flags, and keep memblock_reserve()'s prototype unmodified. 4) Modify other APIs to support flags, but keep their prototype unmodified. The idea is from Wen Congyang <wency@cn.fujitsu.com> and Liu Jiang <jiang.liu@huawei.com>. Suggested-by: Wen Congyang <wency@cn.fujitsu.com> Suggested-by: Liu Jiang <jiang.liu@huawei.com> Signed-off-by: Tang Chen <tangchen@cn.fujitsu.com> Reviewed-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: "Rafael J . Wysocki" <rjw@sisk.pl> Cc: Chen Tang <imtangchen@gmail.com> Cc: Gong Chen <gong.chen@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiang Liu <jiang.liu@huawei.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Larry Woodman <lwoodman@redhat.com> Cc: Len Brown <lenb@kernel.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Michal Nazarewicz <mina86@mina86.com> Cc: Minchan Kim <minchan@kernel.org> Cc: Prarit Bhargava <prarit@redhat.com> Cc: Rik van Riel <riel@redhat.com> Cc: Taku Izumi <izumi.taku@jp.fujitsu.com> Cc: Tejun Heo <tj@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Thomas Renninger <trenn@suse.de> Cc: Toshi Kani <toshi.kani@hp.com> Cc: Vasilis Liaskovitis <vasilis.liaskovitis@profitbricks.com> Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com> Cc: Yasuaki Ishimatsu <isimatu.yasuaki@jp.fujitsu.com> Cc: Yinghai Lu <yinghai@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-22 07:49:20 +08:00
pr_info(" %s[%#x]\t[%#016llx-%#016llx], %#llx bytes%s flags: %#lx\n",
name, i, base, base + size - 1, size, nid_buf, flags);
}
}
void __init_memblock __memblock_dump_all(void)
{
pr_info("MEMBLOCK configuration:\n");
pr_info(" memory size = %#llx reserved size = %#llx\n",
(unsigned long long)memblock.memory.total_size,
(unsigned long long)memblock.reserved.total_size);
memblock_dump(&memblock.memory, "memory");
memblock_dump(&memblock.reserved, "reserved");
}
memblock: s/memblock_analyze()/memblock_allow_resize()/ and update users The only function of memblock_analyze() is now allowing resize of memblock region arrays. Rename it to memblock_allow_resize() and update its users. * The following users remain the same other than renaming. arm/mm/init.c::arm_memblock_init() microblaze/kernel/prom.c::early_init_devtree() powerpc/kernel/prom.c::early_init_devtree() openrisc/kernel/prom.c::early_init_devtree() sh/mm/init.c::paging_init() sparc/mm/init_64.c::paging_init() unicore32/mm/init.c::uc32_memblock_init() * In the following users, analyze was used to update total size which is no longer necessary. powerpc/kernel/machine_kexec.c::reserve_crashkernel() powerpc/kernel/prom.c::early_init_devtree() powerpc/mm/init_32.c::MMU_init() powerpc/mm/tlb_nohash.c::__early_init_mmu() powerpc/platforms/ps3/mm.c::ps3_mm_add_memory() powerpc/platforms/embedded6xx/wii.c::wii_memory_fixups() sh/kernel/machine_kexec.c::reserve_crashkernel() * x86/kernel/e820.c::memblock_x86_fill() was directly setting memblock_can_resize before populating memblock and calling analyze afterwards. Call memblock_allow_resize() before start populating. memblock_can_resize is now static inside memblock.c. Signed-off-by: Tejun Heo <tj@kernel.org> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Yinghai Lu <yinghai@kernel.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Mundt <lethal@linux-sh.org> Cc: "David S. Miller" <davem@davemloft.net> Cc: Guan Xuetao <gxt@mprc.pku.edu.cn> Cc: "H. Peter Anvin" <hpa@zytor.com>
2011-12-09 02:22:08 +08:00
void __init memblock_allow_resize(void)
{
memblock_can_resize = 1;
}
static int __init early_memblock(char *p)
{
if (p && strstr(p, "debug"))
memblock_debug = 1;
return 0;
}
early_param("memblock", early_memblock);
#if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK)
static int memblock_debug_show(struct seq_file *m, void *private)
{
struct memblock_type *type = m->private;
struct memblock_region *reg;
int i;
for (i = 0; i < type->cnt; i++) {
reg = &type->regions[i];
seq_printf(m, "%4d: ", i);
if (sizeof(phys_addr_t) == 4)
seq_printf(m, "0x%08lx..0x%08lx\n",
(unsigned long)reg->base,
(unsigned long)(reg->base + reg->size - 1));
else
seq_printf(m, "0x%016llx..0x%016llx\n",
(unsigned long long)reg->base,
(unsigned long long)(reg->base + reg->size - 1));
}
return 0;
}
static int memblock_debug_open(struct inode *inode, struct file *file)
{
return single_open(file, memblock_debug_show, inode->i_private);
}
static const struct file_operations memblock_debug_fops = {
.open = memblock_debug_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
static int __init memblock_init_debugfs(void)
{
struct dentry *root = debugfs_create_dir("memblock", NULL);
if (!root)
return -ENXIO;
debugfs_create_file("memory", S_IRUGO, root, &memblock.memory, &memblock_debug_fops);
debugfs_create_file("reserved", S_IRUGO, root, &memblock.reserved, &memblock_debug_fops);
#ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP
debugfs_create_file("physmem", S_IRUGO, root, &memblock.physmem, &memblock_debug_fops);
#endif
return 0;
}
__initcall(memblock_init_debugfs);
#endif /* CONFIG_DEBUG_FS */