OpenCloudOS-Kernel/include/linux/memblock.h

279 lines
8.7 KiB
C
Raw Normal View History

#ifndef _LINUX_MEMBLOCK_H
#define _LINUX_MEMBLOCK_H
#ifdef __KERNEL__
#ifdef CONFIG_HAVE_MEMBLOCK
/*
* Logical memory blocks.
*
* Copyright (C) 2001 Peter Bergner, IBM Corp.
*
* 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/init.h>
#include <linux/mm.h>
#define INIT_MEMBLOCK_REGIONS 128
struct memblock_region {
phys_addr_t base;
phys_addr_t size;
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int nid;
#endif
};
struct memblock_type {
unsigned long cnt; /* number of regions */
unsigned long max; /* size of the allocated array */
phys_addr_t total_size; /* size of all regions */
struct memblock_region *regions;
};
struct memblock {
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
bool bottom_up; /* is bottom up direction? */
phys_addr_t current_limit;
struct memblock_type memory;
struct memblock_type reserved;
};
extern struct memblock memblock;
extern int memblock_debug;
#define memblock_dbg(fmt, ...) \
if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
phys_addr_t memblock_find_in_range_node(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align, int nid);
phys_addr_t memblock_find_in_range(phys_addr_t start, phys_addr_t end,
phys_addr_t size, phys_addr_t align);
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 get_allocated_memblock_reserved_regions_info(phys_addr_t *addr);
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 memblock_allow_resize(void);
int memblock_add_node(phys_addr_t base, phys_addr_t size, int nid);
int memblock_add(phys_addr_t base, phys_addr_t size);
int memblock_remove(phys_addr_t base, phys_addr_t size);
int memblock_free(phys_addr_t base, phys_addr_t size);
int memblock_reserve(phys_addr_t base, phys_addr_t size);
void memblock_trim_memory(phys_addr_t align);
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn,
unsigned long *end_pfn);
void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
unsigned long *out_end_pfn, int *out_nid);
/**
* for_each_mem_pfn_range - early memory pfn range iterator
* @i: an integer used as loop variable
* @nid: node selector, %MAX_NUMNODES for all nodes
* @p_start: ptr to ulong for start pfn of the range, can be %NULL
* @p_end: ptr to ulong for end pfn of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*
* Walks over configured memory ranges.
*/
#define for_each_mem_pfn_range(i, nid, p_start, p_end, p_nid) \
for (i = -1, __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid); \
i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
void __next_free_mem_range(u64 *idx, int nid, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
/**
* for_each_free_mem_range - iterate through free memblock areas
* @i: u64 used as loop variable
* @nid: node selector, %MAX_NUMNODES for all nodes
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*
* Walks over free (memory && !reserved) areas of memblock. Available as
* soon as memblock is initialized.
*/
#define for_each_free_mem_range(i, nid, p_start, p_end, p_nid) \
for (i = 0, \
__next_free_mem_range(&i, nid, p_start, p_end, p_nid); \
i != (u64)ULLONG_MAX; \
__next_free_mem_range(&i, nid, p_start, p_end, p_nid))
void __next_free_mem_range_rev(u64 *idx, int nid, phys_addr_t *out_start,
phys_addr_t *out_end, int *out_nid);
/**
* for_each_free_mem_range_reverse - rev-iterate through free memblock areas
* @i: u64 used as loop variable
* @nid: node selector, %MAX_NUMNODES for all nodes
* @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
* @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
* @p_nid: ptr to int for nid of the range, can be %NULL
*
* Walks over free (memory && !reserved) areas of memblock in reverse
* order. Available as soon as memblock is initialized.
*/
#define for_each_free_mem_range_reverse(i, nid, p_start, p_end, p_nid) \
for (i = (u64)ULLONG_MAX, \
__next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid); \
i != (u64)ULLONG_MAX; \
__next_free_mem_range_rev(&i, nid, p_start, p_end, p_nid))
#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP
int memblock_set_node(phys_addr_t base, phys_addr_t size, int nid);
static inline void memblock_set_region_node(struct memblock_region *r, int nid)
{
r->nid = nid;
}
static inline int memblock_get_region_node(const struct memblock_region *r)
{
return r->nid;
}
#else
static inline void memblock_set_region_node(struct memblock_region *r, int nid)
{
}
static inline int memblock_get_region_node(const struct memblock_region *r)
{
return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid);
phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid);
phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
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
#ifdef CONFIG_MOVABLE_NODE
/*
* Set the allocation direction to bottom-up or top-down.
*/
static inline void memblock_set_bottom_up(bool enable)
{
memblock.bottom_up = enable;
}
/*
* Check if the allocation direction is bottom-up or not.
* if this is true, that said, memblock will allocate memory
* in bottom-up direction.
*/
static inline bool memblock_bottom_up(void)
{
return memblock.bottom_up;
}
#else
static inline void memblock_set_bottom_up(bool enable) {}
static inline bool memblock_bottom_up(void) { return false; }
#endif
/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0)
#define MEMBLOCK_ALLOC_ACCESSIBLE 0
phys_addr_t memblock_alloc_base(phys_addr_t size, phys_addr_t align,
phys_addr_t max_addr);
phys_addr_t __memblock_alloc_base(phys_addr_t size, phys_addr_t align,
phys_addr_t max_addr);
phys_addr_t memblock_phys_mem_size(void);
phys_addr_t memblock_mem_size(unsigned long limit_pfn);
phys_addr_t memblock_start_of_DRAM(void);
phys_addr_t memblock_end_of_DRAM(void);
void memblock_enforce_memory_limit(phys_addr_t memory_limit);
int memblock_is_memory(phys_addr_t addr);
int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
int memblock_is_reserved(phys_addr_t addr);
int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
extern void __memblock_dump_all(void);
static inline void memblock_dump_all(void)
{
if (memblock_debug)
__memblock_dump_all();
}
/**
* memblock_set_current_limit - Set the current allocation limit to allow
* limiting allocations to what is currently
* accessible during boot
* @limit: New limit value (physical address)
*/
void memblock_set_current_limit(phys_addr_t limit);
/*
* pfn conversion functions
*
* While the memory MEMBLOCKs should always be page aligned, the reserved
* MEMBLOCKs may not be. This accessor attempt to provide a very clear
* idea of what they return for such non aligned MEMBLOCKs.
*/
/**
* memblock_region_memory_base_pfn - Return the lowest pfn intersecting with the memory region
* @reg: memblock_region structure
*/
static inline unsigned long memblock_region_memory_base_pfn(const struct memblock_region *reg)
{
return PFN_UP(reg->base);
}
/**
* memblock_region_memory_end_pfn - Return the end_pfn this region
* @reg: memblock_region structure
*/
static inline unsigned long memblock_region_memory_end_pfn(const struct memblock_region *reg)
{
return PFN_DOWN(reg->base + reg->size);
}
/**
* memblock_region_reserved_base_pfn - Return the lowest pfn intersecting with the reserved region
* @reg: memblock_region structure
*/
static inline unsigned long memblock_region_reserved_base_pfn(const struct memblock_region *reg)
{
return PFN_DOWN(reg->base);
}
/**
* memblock_region_reserved_end_pfn - Return the end_pfn this region
* @reg: memblock_region structure
*/
static inline unsigned long memblock_region_reserved_end_pfn(const struct memblock_region *reg)
{
return PFN_UP(reg->base + reg->size);
}
#define for_each_memblock(memblock_type, region) \
for (region = memblock.memblock_type.regions; \
region < (memblock.memblock_type.regions + memblock.memblock_type.cnt); \
region++)
#ifdef CONFIG_ARCH_DISCARD_MEMBLOCK
#define __init_memblock __meminit
#define __initdata_memblock __meminitdata
#else
#define __init_memblock
#define __initdata_memblock
#endif
#else
static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align)
{
return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK */
#endif /* __KERNEL__ */
#endif /* _LINUX_MEMBLOCK_H */